Command that produces this log: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 ---------------------------------------------------------------------------------------------------- > trainable params: >>> pad_vector: torch.Size([1, 1, 1024]) >>> xlmr.embeddings.word_embeddings.weight: torch.Size([250002, 1024]) >>> xlmr.embeddings.position_embeddings.weight: torch.Size([514, 1024]) >>> xlmr.embeddings.token_type_embeddings.weight: torch.Size([1, 1024]) >>> xlmr.embeddings.LayerNorm.weight: torch.Size([1024]) >>> xlmr.embeddings.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.0.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.0.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.0.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.0.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.0.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.0.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.0.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.0.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.0.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.0.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.0.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.0.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.0.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.0.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.0.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.0.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.1.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.1.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.1.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.1.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.1.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.1.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.1.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.1.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.1.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.1.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.1.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.1.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.1.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.1.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.1.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.1.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.2.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.2.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.2.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.2.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.2.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.2.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.2.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.2.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.2.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.2.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.2.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.2.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.2.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.2.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.2.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.2.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.3.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.3.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.3.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.3.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.3.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.3.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.3.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.3.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.3.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.3.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.3.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.3.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.3.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.3.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.3.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.3.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.4.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.4.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.4.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.4.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.4.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.4.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.4.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.4.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.4.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.4.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.4.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.4.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.4.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.4.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.4.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.4.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.5.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.5.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.5.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.5.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.5.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.5.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.5.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.5.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.5.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.5.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.5.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.5.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.5.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.5.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.5.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.5.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.6.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.6.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.6.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.6.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.6.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.6.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.6.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.6.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.6.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.6.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.6.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.6.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.6.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.6.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.6.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.6.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.7.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.7.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.7.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.7.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.7.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.7.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.7.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.7.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.7.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.7.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.7.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.7.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.7.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.7.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.7.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.7.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.8.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.8.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.8.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.8.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.8.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.8.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.8.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.8.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.8.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.8.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.8.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.8.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.8.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.8.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.8.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.8.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.9.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.9.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.9.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.9.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.9.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.9.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.9.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.9.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.9.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.9.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.9.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.9.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.9.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.9.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.9.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.9.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.10.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.10.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.10.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.10.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.10.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.10.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.10.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.10.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.10.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.10.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.10.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.10.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.10.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.10.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.10.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.10.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.11.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.11.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.11.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.11.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.11.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.11.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.11.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.11.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.11.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.11.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.11.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.11.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.11.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.11.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.11.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.11.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.12.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.12.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.12.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.12.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.12.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.12.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.12.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.12.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.12.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.12.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.12.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.12.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.12.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.12.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.12.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.12.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.13.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.13.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.13.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.13.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.13.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.13.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.13.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.13.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.13.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.13.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.13.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.13.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.13.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.13.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.13.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.13.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.14.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.14.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.14.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.14.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.14.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.14.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.14.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.14.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.14.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.14.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.14.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.14.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.14.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.14.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.14.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.14.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.15.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.15.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.15.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.15.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.15.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.15.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.15.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.15.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.15.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.15.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.15.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.15.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.15.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.15.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.15.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.15.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.16.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.16.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.16.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.16.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.16.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.16.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.16.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.16.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.16.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.16.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.16.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.16.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.16.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.16.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.16.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.16.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.17.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.17.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.17.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.17.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.17.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.17.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.17.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.17.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.17.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.17.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.17.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.17.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.17.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.17.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.17.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.17.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.18.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.18.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.18.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.18.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.18.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.18.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.18.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.18.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.18.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.18.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.18.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.18.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.18.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.18.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.18.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.18.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.19.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.19.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.19.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.19.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.19.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.19.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.19.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.19.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.19.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.19.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.19.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.19.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.19.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.19.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.19.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.19.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.20.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.20.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.20.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.20.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.20.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.20.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.20.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.20.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.20.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.20.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.20.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.20.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.20.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.20.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.20.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.20.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.21.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.21.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.21.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.21.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.21.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.21.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.21.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.21.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.21.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.21.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.21.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.21.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.21.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.21.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.21.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.21.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.22.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.22.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.22.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.22.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.22.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.22.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.22.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.22.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.22.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.22.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.22.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.22.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.22.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.22.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.22.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.22.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.23.attention.self.query.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.23.attention.self.query.bias: torch.Size([1024]) >>> xlmr.encoder.layer.23.attention.self.key.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.23.attention.self.key.bias: torch.Size([1024]) >>> xlmr.encoder.layer.23.attention.self.value.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.23.attention.self.value.bias: torch.Size([1024]) >>> xlmr.encoder.layer.23.attention.output.dense.weight: torch.Size([1024, 1024]) >>> xlmr.encoder.layer.23.attention.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.23.attention.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.23.attention.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.encoder.layer.23.intermediate.dense.weight: torch.Size([4096, 1024]) >>> xlmr.encoder.layer.23.intermediate.dense.bias: torch.Size([4096]) >>> xlmr.encoder.layer.23.output.dense.weight: torch.Size([1024, 4096]) >>> xlmr.encoder.layer.23.output.dense.bias: torch.Size([1024]) >>> xlmr.encoder.layer.23.output.LayerNorm.weight: torch.Size([1024]) >>> xlmr.encoder.layer.23.output.LayerNorm.bias: torch.Size([1024]) >>> xlmr.pooler.dense.weight: torch.Size([1024, 1024]) >>> xlmr.pooler.dense.bias: torch.Size([1024]) >>> upos_embedding.weight: torch.Size([19, 50]) >>> dist_embedding.weight: torch.Size([104, 50]) >>> deprel_embedding.weight: torch.Size([38, 50]) >>> gcn_layer.W.0.weight: torch.Size([450, 50]) >>> gcn_layer.W.0.bias: torch.Size([450]) >>> gcn_layer.W.1.weight: torch.Size([450, 450]) >>> gcn_layer.W.1.bias: torch.Size([450]) >>> trans_rep.weight: torch.Size([1024, 2924]) >>> trans_rep.bias: torch.Size([1024]) >>> mention_label_ffn.layers.0.weight: torch.Size([350, 1024]) >>> mention_label_ffn.layers.0.bias: torch.Size([350]) >>> mention_label_ffn.layers.1.weight: torch.Size([11, 350]) >>> mention_label_ffn.layers.1.bias: torch.Size([11]) >>> trigger_label_ffn.layers.0.weight: torch.Size([450, 1024]) >>> trigger_label_ffn.layers.0.bias: torch.Size([450]) >>> trigger_label_ffn.layers.1.weight: torch.Size([231, 450]) >>> trigger_label_ffn.layers.1.bias: torch.Size([231]) >>> event_type_ffn.layers.0.weight: torch.Size([450, 1024]) >>> event_type_ffn.layers.0.bias: torch.Size([450]) >>> event_type_ffn.layers.1.weight: torch.Size([116, 450]) >>> event_type_ffn.layers.1.bias: torch.Size([116]) >>> role_type_ffn.layers.0.weight: torch.Size([350, 1024]) >>> role_type_ffn.layers.0.bias: torch.Size([350]) >>> role_type_ffn.layers.1.weight: torch.Size([6, 350]) >>> role_type_ffn.layers.1.bias: torch.Size([6]) >>> trigger_crf.transition: torch.Size([233, 233]) >>> mention_crf.transition: torch.Size([13, 13]) n_trainable_params: 564977528, n_nontrainable_params: 0 ---------------------------------------------------------------------------------------------------- ****************************** Epoch: 0 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 05:01:21.703994: step: 2/1545, loss: 8.078238487243652 2023-01-23 05:01:22.629561: step: 4/1545, loss: 6.407975673675537 2023-01-23 05:01:23.467754: step: 6/1545, loss: 5.232830047607422 2023-01-23 05:01:24.307506: step: 8/1545, loss: 13.010278701782227 2023-01-23 05:01:25.222263: step: 10/1545, loss: 8.113531112670898 2023-01-23 05:01:26.140251: step: 12/1545, loss: 8.447321891784668 2023-01-23 05:01:26.989692: step: 14/1545, loss: 5.953680992126465 2023-01-23 05:01:27.855321: step: 16/1545, loss: 8.604791641235352 2023-01-23 05:01:28.727403: step: 18/1545, loss: 7.519055366516113 2023-01-23 05:01:29.576378: step: 20/1545, loss: 7.005523204803467 2023-01-23 05:01:30.454337: step: 22/1545, loss: 8.471688270568848 2023-01-23 05:01:31.404881: step: 24/1545, loss: 4.964112281799316 2023-01-23 05:01:32.261051: step: 26/1545, loss: 7.216348648071289 2023-01-23 05:01:33.144070: step: 28/1545, loss: 6.717325687408447 2023-01-23 05:01:33.990769: step: 30/1545, loss: 5.670198917388916 2023-01-23 05:01:34.863183: step: 32/1545, loss: 7.482447147369385 2023-01-23 05:01:35.729741: step: 34/1545, loss: 5.425549030303955 2023-01-23 05:01:36.589679: step: 36/1545, loss: 8.33028507232666 2023-01-23 05:01:37.477063: step: 38/1545, loss: 10.776671409606934 2023-01-23 05:01:38.319912: step: 40/1545, loss: 9.639650344848633 2023-01-23 05:01:39.174119: step: 42/1545, loss: 5.98823881149292 2023-01-23 05:01:40.076723: step: 44/1545, loss: 6.758458137512207 2023-01-23 05:01:40.972407: step: 46/1545, loss: 5.2989373207092285 2023-01-23 05:01:41.850678: step: 48/1545, loss: 6.045010089874268 2023-01-23 05:01:42.699834: step: 50/1545, loss: 8.836732864379883 2023-01-23 05:01:43.567112: step: 52/1545, loss: 7.051332950592041 2023-01-23 05:01:44.491415: step: 54/1545, loss: 5.612408638000488 2023-01-23 05:01:45.372589: step: 56/1545, loss: 6.838583946228027 2023-01-23 05:01:46.255529: step: 58/1545, loss: 6.007237911224365 2023-01-23 05:01:47.086225: step: 60/1545, loss: 10.898975372314453 2023-01-23 05:01:47.966652: step: 62/1545, loss: 8.41567611694336 2023-01-23 05:01:48.823592: step: 64/1545, loss: 6.733139514923096 2023-01-23 05:01:49.691825: step: 66/1545, loss: 13.49292278289795 2023-01-23 05:01:50.704423: step: 68/1545, loss: 9.765254020690918 2023-01-23 05:01:51.556917: step: 70/1545, loss: 8.605293273925781 2023-01-23 05:01:52.418522: step: 72/1545, loss: 5.486252784729004 2023-01-23 05:01:53.311562: step: 74/1545, loss: 7.36837911605835 2023-01-23 05:01:54.209634: step: 76/1545, loss: 7.750473499298096 2023-01-23 05:01:55.119864: step: 78/1545, loss: 4.7817511558532715 2023-01-23 05:01:55.966580: step: 80/1545, loss: 5.458348751068115 2023-01-23 05:01:56.896470: step: 82/1545, loss: 6.534160614013672 2023-01-23 05:01:57.820980: step: 84/1545, loss: 7.824183940887451 2023-01-23 05:01:58.673970: step: 86/1545, loss: 5.73176383972168 2023-01-23 05:01:59.556744: step: 88/1545, loss: 5.785432815551758 2023-01-23 05:02:00.443699: step: 90/1545, loss: 7.580147743225098 2023-01-23 05:02:01.279479: step: 92/1545, loss: 8.416411399841309 2023-01-23 05:02:02.140337: step: 94/1545, loss: 7.966456890106201 2023-01-23 05:02:03.015865: step: 96/1545, loss: 9.042646408081055 2023-01-23 05:02:03.882146: step: 98/1545, loss: 8.109177589416504 2023-01-23 05:02:04.734750: step: 100/1545, loss: 9.654241561889648 2023-01-23 05:02:05.576958: step: 102/1545, loss: 4.660295009613037 2023-01-23 05:02:06.412040: step: 104/1545, loss: 6.259700775146484 2023-01-23 05:02:07.270927: step: 106/1545, loss: 9.639998435974121 2023-01-23 05:02:08.103018: step: 108/1545, loss: 6.717731952667236 2023-01-23 05:02:09.012028: step: 110/1545, loss: 7.045222282409668 2023-01-23 05:02:09.939711: step: 112/1545, loss: 5.739577293395996 2023-01-23 05:02:10.800923: step: 114/1545, loss: 5.765110015869141 2023-01-23 05:02:11.658413: step: 116/1545, loss: 7.301506996154785 2023-01-23 05:02:12.616747: step: 118/1545, loss: 7.946010589599609 2023-01-23 05:02:13.579220: step: 120/1545, loss: 6.722315311431885 2023-01-23 05:02:14.462042: step: 122/1545, loss: 12.178071022033691 2023-01-23 05:02:15.336443: step: 124/1545, loss: 5.698235034942627 2023-01-23 05:02:16.254180: step: 126/1545, loss: 7.115219593048096 2023-01-23 05:02:17.213940: step: 128/1545, loss: 6.66035795211792 2023-01-23 05:02:18.096386: step: 130/1545, loss: 5.071753025054932 2023-01-23 05:02:18.966363: step: 132/1545, loss: 4.477313995361328 2023-01-23 05:02:19.819728: step: 134/1545, loss: 5.635747909545898 2023-01-23 05:02:20.662536: step: 136/1545, loss: 9.311676979064941 2023-01-23 05:02:21.546712: step: 138/1545, loss: 8.23282241821289 2023-01-23 05:02:22.402143: step: 140/1545, loss: 4.786867141723633 2023-01-23 05:02:23.237367: step: 142/1545, loss: 7.737656116485596 2023-01-23 05:02:24.067614: step: 144/1545, loss: 4.201442718505859 2023-01-23 05:02:24.947408: step: 146/1545, loss: 9.283477783203125 2023-01-23 05:02:25.821611: step: 148/1545, loss: 4.52247953414917 2023-01-23 05:02:26.710299: step: 150/1545, loss: 8.10423755645752 2023-01-23 05:02:27.547430: step: 152/1545, loss: 5.21783447265625 2023-01-23 05:02:28.415838: step: 154/1545, loss: 4.989076137542725 2023-01-23 05:02:29.279472: step: 156/1545, loss: 5.129931449890137 2023-01-23 05:02:30.154703: step: 158/1545, loss: 14.694831848144531 2023-01-23 05:02:31.008205: step: 160/1545, loss: 4.505146026611328 2023-01-23 05:02:31.911854: step: 162/1545, loss: 5.421171188354492 2023-01-23 05:02:32.818651: step: 164/1545, loss: 7.6301984786987305 2023-01-23 05:02:33.675171: step: 166/1545, loss: 7.986936569213867 2023-01-23 05:02:34.539407: step: 168/1545, loss: 5.077517509460449 2023-01-23 05:02:35.432253: step: 170/1545, loss: 9.07819938659668 2023-01-23 05:02:36.297317: step: 172/1545, loss: 5.37606143951416 2023-01-23 05:02:37.199331: step: 174/1545, loss: 3.8658881187438965 2023-01-23 05:02:38.199022: step: 176/1545, loss: 5.44419002532959 2023-01-23 05:02:39.046424: step: 178/1545, loss: 11.745176315307617 2023-01-23 05:02:39.908216: step: 180/1545, loss: 3.4559872150421143 2023-01-23 05:02:40.785046: step: 182/1545, loss: 3.873915195465088 2023-01-23 05:02:41.667099: step: 184/1545, loss: 4.348193645477295 2023-01-23 05:02:42.584141: step: 186/1545, loss: 6.252188205718994 2023-01-23 05:02:43.436758: step: 188/1545, loss: 5.093369483947754 2023-01-23 05:02:44.331072: step: 190/1545, loss: 3.9054179191589355 2023-01-23 05:02:45.204089: step: 192/1545, loss: 7.673865795135498 2023-01-23 05:02:46.147528: step: 194/1545, loss: 6.078701019287109 2023-01-23 05:02:46.989245: step: 196/1545, loss: 5.265119552612305 2023-01-23 05:02:47.885302: step: 198/1545, loss: 6.230378150939941 2023-01-23 05:02:48.772918: step: 200/1545, loss: 7.2223734855651855 2023-01-23 05:02:49.737894: step: 202/1545, loss: 5.934558391571045 2023-01-23 05:02:50.621576: step: 204/1545, loss: 7.239955902099609 2023-01-23 05:02:51.498209: step: 206/1545, loss: 6.681726455688477 2023-01-23 05:02:52.440955: step: 208/1545, loss: 7.078614711761475 2023-01-23 05:02:53.291229: step: 210/1545, loss: 5.724277496337891 2023-01-23 05:02:54.169217: step: 212/1545, loss: 5.256679058074951 2023-01-23 05:02:55.009982: step: 214/1545, loss: 5.719870090484619 2023-01-23 05:02:55.881925: step: 216/1545, loss: 6.605286598205566 2023-01-23 05:02:56.715470: step: 218/1545, loss: 9.931156158447266 2023-01-23 05:02:57.587451: step: 220/1545, loss: 7.917030334472656 2023-01-23 05:02:58.466406: step: 222/1545, loss: 11.584047317504883 2023-01-23 05:02:59.348948: step: 224/1545, loss: 8.118707656860352 2023-01-23 05:03:00.252895: step: 226/1545, loss: 5.34097146987915 2023-01-23 05:03:01.135025: step: 228/1545, loss: 11.008840560913086 2023-01-23 05:03:02.026265: step: 230/1545, loss: 10.615436553955078 2023-01-23 05:03:02.948349: step: 232/1545, loss: 4.078309535980225 2023-01-23 05:03:03.807745: step: 234/1545, loss: 4.571131706237793 2023-01-23 05:03:04.664221: step: 236/1545, loss: 7.259772300720215 2023-01-23 05:03:05.494326: step: 238/1545, loss: 3.566148042678833 2023-01-23 05:03:06.344111: step: 240/1545, loss: 4.416587829589844 2023-01-23 05:03:07.212075: step: 242/1545, loss: 4.1966729164123535 2023-01-23 05:03:08.063981: step: 244/1545, loss: 5.49576997756958 2023-01-23 05:03:08.904443: step: 246/1545, loss: 4.184207916259766 2023-01-23 05:03:09.821283: step: 248/1545, loss: 10.643694877624512 2023-01-23 05:03:10.704041: step: 250/1545, loss: 3.5929946899414062 2023-01-23 05:03:11.556281: step: 252/1545, loss: 3.7984509468078613 2023-01-23 05:03:12.417884: step: 254/1545, loss: 7.485105514526367 2023-01-23 05:03:13.417398: step: 256/1545, loss: 6.524544715881348 2023-01-23 05:03:14.282298: step: 258/1545, loss: 5.488447666168213 2023-01-23 05:03:15.193110: step: 260/1545, loss: 7.232985019683838 2023-01-23 05:03:16.042154: step: 262/1545, loss: 4.0569281578063965 2023-01-23 05:03:16.887326: step: 264/1545, loss: 4.719406604766846 2023-01-23 05:03:17.794891: step: 266/1545, loss: 6.4471516609191895 2023-01-23 05:03:18.706409: step: 268/1545, loss: 4.208990573883057 2023-01-23 05:03:19.569162: step: 270/1545, loss: 7.273632526397705 2023-01-23 05:03:20.425097: step: 272/1545, loss: 4.79964542388916 2023-01-23 05:03:21.323121: step: 274/1545, loss: 5.303208827972412 2023-01-23 05:03:22.198175: step: 276/1545, loss: 5.672492504119873 2023-01-23 05:03:23.073466: step: 278/1545, loss: 6.695729732513428 2023-01-23 05:03:23.938526: step: 280/1545, loss: 7.239502429962158 2023-01-23 05:03:24.807532: step: 282/1545, loss: 3.330021858215332 2023-01-23 05:03:25.659467: step: 284/1545, loss: 2.93204402923584 2023-01-23 05:03:26.534584: step: 286/1545, loss: 6.693894863128662 2023-01-23 05:03:27.431762: step: 288/1545, loss: 4.434856414794922 2023-01-23 05:03:28.309957: step: 290/1545, loss: 3.603672742843628 2023-01-23 05:03:29.192449: step: 292/1545, loss: 5.68459939956665 2023-01-23 05:03:30.095009: step: 294/1545, loss: 4.9858503341674805 2023-01-23 05:03:30.968037: step: 296/1545, loss: 4.390952110290527 2023-01-23 05:03:31.828923: step: 298/1545, loss: 4.293670177459717 2023-01-23 05:03:32.687988: step: 300/1545, loss: 3.351612091064453 2023-01-23 05:03:33.563544: step: 302/1545, loss: 6.33828592300415 2023-01-23 05:03:34.538611: step: 304/1545, loss: 9.558019638061523 2023-01-23 05:03:35.431176: step: 306/1545, loss: 11.349566459655762 2023-01-23 05:03:36.265959: step: 308/1545, loss: 7.158538341522217 2023-01-23 05:03:37.148864: step: 310/1545, loss: 2.805094003677368 2023-01-23 05:03:38.005194: step: 312/1545, loss: 6.565910816192627 2023-01-23 05:03:38.929265: step: 314/1545, loss: 5.776557445526123 2023-01-23 05:03:39.761140: step: 316/1545, loss: 3.776581048965454 2023-01-23 05:03:40.612074: step: 318/1545, loss: 4.96656608581543 2023-01-23 05:03:41.412891: step: 320/1545, loss: 3.9395368099212646 2023-01-23 05:03:42.297253: step: 322/1545, loss: 3.3510377407073975 2023-01-23 05:03:43.143625: step: 324/1545, loss: 6.0416364669799805 2023-01-23 05:03:44.014148: step: 326/1545, loss: 3.335925579071045 2023-01-23 05:03:44.871503: step: 328/1545, loss: 13.529763221740723 2023-01-23 05:03:45.729394: step: 330/1545, loss: 7.390220642089844 2023-01-23 05:03:46.631067: step: 332/1545, loss: 5.83591890335083 2023-01-23 05:03:47.508655: step: 334/1545, loss: 5.500558853149414 2023-01-23 05:03:48.393052: step: 336/1545, loss: 5.705944538116455 2023-01-23 05:03:49.341451: step: 338/1545, loss: 5.68239688873291 2023-01-23 05:03:50.207845: step: 340/1545, loss: 2.995154619216919 2023-01-23 05:03:51.089947: step: 342/1545, loss: 7.4647650718688965 2023-01-23 05:03:51.984708: step: 344/1545, loss: 4.0771989822387695 2023-01-23 05:03:52.848146: step: 346/1545, loss: 3.530529022216797 2023-01-23 05:03:53.860646: step: 348/1545, loss: 3.2923741340637207 2023-01-23 05:03:54.748112: step: 350/1545, loss: 3.974323034286499 2023-01-23 05:03:55.599451: step: 352/1545, loss: 4.520718574523926 2023-01-23 05:03:56.470290: step: 354/1545, loss: 11.046045303344727 2023-01-23 05:03:57.329286: step: 356/1545, loss: 5.237056732177734 2023-01-23 05:03:58.201432: step: 358/1545, loss: 6.2807207107543945 2023-01-23 05:03:59.052390: step: 360/1545, loss: 4.053141117095947 2023-01-23 05:03:59.952828: step: 362/1545, loss: 5.148562908172607 2023-01-23 05:04:00.836828: step: 364/1545, loss: 7.013742446899414 2023-01-23 05:04:01.706974: step: 366/1545, loss: 4.890805244445801 2023-01-23 05:04:02.549267: step: 368/1545, loss: 4.0160722732543945 2023-01-23 05:04:03.418970: step: 370/1545, loss: 7.387300968170166 2023-01-23 05:04:04.279316: step: 372/1545, loss: 6.186699390411377 2023-01-23 05:04:05.102042: step: 374/1545, loss: 3.521078586578369 2023-01-23 05:04:05.975959: step: 376/1545, loss: 6.1183905601501465 2023-01-23 05:04:06.905067: step: 378/1545, loss: 6.8236775398254395 2023-01-23 05:04:07.765136: step: 380/1545, loss: 3.5665881633758545 2023-01-23 05:04:08.615221: step: 382/1545, loss: 4.617011070251465 2023-01-23 05:04:09.477915: step: 384/1545, loss: 5.681252956390381 2023-01-23 05:04:10.363419: step: 386/1545, loss: 3.7036936283111572 2023-01-23 05:04:11.225972: step: 388/1545, loss: 3.527740001678467 2023-01-23 05:04:12.146668: step: 390/1545, loss: 3.8793785572052 2023-01-23 05:04:13.012595: step: 392/1545, loss: 3.560988426208496 2023-01-23 05:04:13.918831: step: 394/1545, loss: 5.642096519470215 2023-01-23 05:04:14.792374: step: 396/1545, loss: 4.791525840759277 2023-01-23 05:04:15.688943: step: 398/1545, loss: 2.906942129135132 2023-01-23 05:04:16.589826: step: 400/1545, loss: 7.284374713897705 2023-01-23 05:04:17.497980: step: 402/1545, loss: 6.429243564605713 2023-01-23 05:04:18.350607: step: 404/1545, loss: 5.469204425811768 2023-01-23 05:04:19.342301: step: 406/1545, loss: 5.319288730621338 2023-01-23 05:04:20.208931: step: 408/1545, loss: 3.458641290664673 2023-01-23 05:04:21.106089: step: 410/1545, loss: 5.143209457397461 2023-01-23 05:04:22.087527: step: 412/1545, loss: 2.543855667114258 2023-01-23 05:04:22.978836: step: 414/1545, loss: 5.1487345695495605 2023-01-23 05:04:23.854033: step: 416/1545, loss: 5.8067545890808105 2023-01-23 05:04:24.730635: step: 418/1545, loss: 5.987931251525879 2023-01-23 05:04:25.676555: step: 420/1545, loss: 5.157989978790283 2023-01-23 05:04:26.562370: step: 422/1545, loss: 14.008072853088379 2023-01-23 05:04:27.550708: step: 424/1545, loss: 4.662139415740967 2023-01-23 05:04:28.457015: step: 426/1545, loss: 7.164475917816162 2023-01-23 05:04:29.352339: step: 428/1545, loss: 7.694714546203613 2023-01-23 05:04:30.206492: step: 430/1545, loss: 4.7635297775268555 2023-01-23 05:04:31.059150: step: 432/1545, loss: 3.565347671508789 2023-01-23 05:04:31.962959: step: 434/1545, loss: 5.980462551116943 2023-01-23 05:04:32.846120: step: 436/1545, loss: 4.663553237915039 2023-01-23 05:04:33.739230: step: 438/1545, loss: 4.18388032913208 2023-01-23 05:04:34.683248: step: 440/1545, loss: 4.8447980880737305 2023-01-23 05:04:35.550644: step: 442/1545, loss: 7.535865306854248 2023-01-23 05:04:36.435684: step: 444/1545, loss: 4.8219122886657715 2023-01-23 05:04:37.329214: step: 446/1545, loss: 5.906406402587891 2023-01-23 05:04:38.209332: step: 448/1545, loss: 5.533777713775635 2023-01-23 05:04:39.087292: step: 450/1545, loss: 2.631350517272949 2023-01-23 05:04:39.994638: step: 452/1545, loss: 5.8406982421875 2023-01-23 05:04:40.869975: step: 454/1545, loss: 3.1396069526672363 2023-01-23 05:04:41.779395: step: 456/1545, loss: 7.182733058929443 2023-01-23 05:04:42.724805: step: 458/1545, loss: 3.8370158672332764 2023-01-23 05:04:43.602205: step: 460/1545, loss: 5.1854095458984375 2023-01-23 05:04:44.473527: step: 462/1545, loss: 2.8089871406555176 2023-01-23 05:04:45.333235: step: 464/1545, loss: 3.623229742050171 2023-01-23 05:04:46.232892: step: 466/1545, loss: 3.7239720821380615 2023-01-23 05:04:47.079433: step: 468/1545, loss: 3.966308832168579 2023-01-23 05:04:47.981332: step: 470/1545, loss: 4.703065872192383 2023-01-23 05:04:48.873296: step: 472/1545, loss: 3.3469252586364746 2023-01-23 05:04:49.805794: step: 474/1545, loss: 5.432595252990723 2023-01-23 05:04:50.680935: step: 476/1545, loss: 5.515427112579346 2023-01-23 05:04:51.561777: step: 478/1545, loss: 4.068740367889404 2023-01-23 05:04:52.406480: step: 480/1545, loss: 11.057109832763672 2023-01-23 05:04:53.288762: step: 482/1545, loss: 4.854352951049805 2023-01-23 05:04:54.130363: step: 484/1545, loss: 4.6560845375061035 2023-01-23 05:04:55.014459: step: 486/1545, loss: 3.4716687202453613 2023-01-23 05:04:55.909352: step: 488/1545, loss: 5.499330520629883 2023-01-23 05:04:56.827147: step: 490/1545, loss: 7.374691963195801 2023-01-23 05:04:57.679378: step: 492/1545, loss: 4.568471908569336 2023-01-23 05:04:58.570975: step: 494/1545, loss: 3.0877902507781982 2023-01-23 05:04:59.435522: step: 496/1545, loss: 3.874614715576172 2023-01-23 05:05:00.313381: step: 498/1545, loss: 7.761325836181641 2023-01-23 05:05:01.177205: step: 500/1545, loss: 7.649982452392578 2023-01-23 05:05:02.059692: step: 502/1545, loss: 3.8625869750976562 2023-01-23 05:05:02.966046: step: 504/1545, loss: 3.328517436981201 2023-01-23 05:05:03.833426: step: 506/1545, loss: 2.539393663406372 2023-01-23 05:05:04.703208: step: 508/1545, loss: 4.646358013153076 2023-01-23 05:05:05.548728: step: 510/1545, loss: 3.78393816947937 2023-01-23 05:05:06.375570: step: 512/1545, loss: 4.307103157043457 2023-01-23 05:05:07.230341: step: 514/1545, loss: 5.086462497711182 2023-01-23 05:05:08.220420: step: 516/1545, loss: 3.663881301879883 2023-01-23 05:05:09.067642: step: 518/1545, loss: 2.009982109069824 2023-01-23 05:05:09.965936: step: 520/1545, loss: 5.109470844268799 2023-01-23 05:05:10.830892: step: 522/1545, loss: 7.733456134796143 2023-01-23 05:05:11.715323: step: 524/1545, loss: 10.186944007873535 2023-01-23 05:05:12.563090: step: 526/1545, loss: 5.827422142028809 2023-01-23 05:05:13.463072: step: 528/1545, loss: 4.577707290649414 2023-01-23 05:05:14.366497: step: 530/1545, loss: 4.34785795211792 2023-01-23 05:05:15.291832: step: 532/1545, loss: 3.1790881156921387 2023-01-23 05:05:16.145809: step: 534/1545, loss: 5.4468464851379395 2023-01-23 05:05:17.002949: step: 536/1545, loss: 5.133413791656494 2023-01-23 05:05:17.940656: step: 538/1545, loss: 6.496743202209473 2023-01-23 05:05:18.811519: step: 540/1545, loss: 12.40195369720459 2023-01-23 05:05:19.722956: step: 542/1545, loss: 4.632413864135742 2023-01-23 05:05:20.623555: step: 544/1545, loss: 6.768752098083496 2023-01-23 05:05:21.473220: step: 546/1545, loss: 4.712409019470215 2023-01-23 05:05:22.346081: step: 548/1545, loss: 2.582777738571167 2023-01-23 05:05:23.234104: step: 550/1545, loss: 3.7974228858947754 2023-01-23 05:05:24.113495: step: 552/1545, loss: 2.9265480041503906 2023-01-23 05:05:25.055601: step: 554/1545, loss: 3.740534543991089 2023-01-23 05:05:25.912392: step: 556/1545, loss: 7.397613048553467 2023-01-23 05:05:26.792591: step: 558/1545, loss: 3.7617740631103516 2023-01-23 05:05:27.655959: step: 560/1545, loss: 2.8259782791137695 2023-01-23 05:05:28.507291: step: 562/1545, loss: 10.785689353942871 2023-01-23 05:05:29.352353: step: 564/1545, loss: 4.243443965911865 2023-01-23 05:05:30.209945: step: 566/1545, loss: 1.8018250465393066 2023-01-23 05:05:31.048946: step: 568/1545, loss: 5.727973461151123 2023-01-23 05:05:31.909116: step: 570/1545, loss: 6.360323429107666 2023-01-23 05:05:32.788389: step: 572/1545, loss: 2.7756807804107666 2023-01-23 05:05:33.749260: step: 574/1545, loss: 3.509481906890869 2023-01-23 05:05:34.646784: step: 576/1545, loss: 7.530373573303223 2023-01-23 05:05:35.544028: step: 578/1545, loss: 2.9100072383880615 2023-01-23 05:05:36.401295: step: 580/1545, loss: 7.2576398849487305 2023-01-23 05:05:37.255310: step: 582/1545, loss: 4.188411712646484 2023-01-23 05:05:38.171935: step: 584/1545, loss: 5.536933422088623 2023-01-23 05:05:39.044811: step: 586/1545, loss: 3.1392948627471924 2023-01-23 05:05:39.924890: step: 588/1545, loss: 4.318648338317871 2023-01-23 05:05:40.816587: step: 590/1545, loss: 2.885826587677002 2023-01-23 05:05:41.685915: step: 592/1545, loss: 5.132269859313965 2023-01-23 05:05:42.556236: step: 594/1545, loss: 2.209625720977783 2023-01-23 05:05:43.417456: step: 596/1545, loss: 5.836862564086914 2023-01-23 05:05:44.331558: step: 598/1545, loss: 4.611673355102539 2023-01-23 05:05:45.224569: step: 600/1545, loss: 3.8291208744049072 2023-01-23 05:05:46.072419: step: 602/1545, loss: 3.907522678375244 2023-01-23 05:05:46.962958: step: 604/1545, loss: 4.433989524841309 2023-01-23 05:05:47.883975: step: 606/1545, loss: 4.966212272644043 2023-01-23 05:05:48.772450: step: 608/1545, loss: 6.644162178039551 2023-01-23 05:05:49.717521: step: 610/1545, loss: 7.578949928283691 2023-01-23 05:05:50.587814: step: 612/1545, loss: 5.216118812561035 2023-01-23 05:05:51.453735: step: 614/1545, loss: 3.4011783599853516 2023-01-23 05:05:52.386465: step: 616/1545, loss: 3.690493583679199 2023-01-23 05:05:53.308863: step: 618/1545, loss: 17.419584274291992 2023-01-23 05:05:54.220169: step: 620/1545, loss: 4.14307975769043 2023-01-23 05:05:55.074475: step: 622/1545, loss: 3.707852363586426 2023-01-23 05:05:55.972968: step: 624/1545, loss: 4.551555633544922 2023-01-23 05:05:56.904236: step: 626/1545, loss: 4.655937194824219 2023-01-23 05:05:57.777983: step: 628/1545, loss: 3.501995086669922 2023-01-23 05:05:58.704795: step: 630/1545, loss: 2.609506368637085 2023-01-23 05:05:59.659168: step: 632/1545, loss: 3.784557342529297 2023-01-23 05:06:00.590459: step: 634/1545, loss: 2.6700236797332764 2023-01-23 05:06:01.494886: step: 636/1545, loss: 4.248157978057861 2023-01-23 05:06:02.402267: step: 638/1545, loss: 3.4020168781280518 2023-01-23 05:06:03.292870: step: 640/1545, loss: 5.329861640930176 2023-01-23 05:06:04.127187: step: 642/1545, loss: 5.096200942993164 2023-01-23 05:06:05.036742: step: 644/1545, loss: 3.892302989959717 2023-01-23 05:06:05.900690: step: 646/1545, loss: 4.953890800476074 2023-01-23 05:06:06.792286: step: 648/1545, loss: 3.329859733581543 2023-01-23 05:06:07.716147: step: 650/1545, loss: 3.0698060989379883 2023-01-23 05:06:08.621502: step: 652/1545, loss: 4.896823406219482 2023-01-23 05:06:09.538136: step: 654/1545, loss: 6.171009540557861 2023-01-23 05:06:10.402880: step: 656/1545, loss: 3.827925682067871 2023-01-23 05:06:11.298484: step: 658/1545, loss: 5.634634494781494 2023-01-23 05:06:12.215350: step: 660/1545, loss: 6.436311721801758 2023-01-23 05:06:13.125151: step: 662/1545, loss: 3.5229618549346924 2023-01-23 05:06:13.993566: step: 664/1545, loss: 3.5564489364624023 2023-01-23 05:06:14.914612: step: 666/1545, loss: 3.816361904144287 2023-01-23 05:06:15.784466: step: 668/1545, loss: 7.1784749031066895 2023-01-23 05:06:16.657498: step: 670/1545, loss: 3.650569438934326 2023-01-23 05:06:17.553973: step: 672/1545, loss: 8.245752334594727 2023-01-23 05:06:18.428458: step: 674/1545, loss: 2.7159788608551025 2023-01-23 05:06:19.307622: step: 676/1545, loss: 4.305588722229004 2023-01-23 05:06:20.317197: step: 678/1545, loss: 5.4866838455200195 2023-01-23 05:06:21.184817: step: 680/1545, loss: 3.394024133682251 2023-01-23 05:06:22.104453: step: 682/1545, loss: 4.519356727600098 2023-01-23 05:06:22.920457: step: 684/1545, loss: 7.066222190856934 2023-01-23 05:06:23.782086: step: 686/1545, loss: 3.1152760982513428 2023-01-23 05:06:24.646985: step: 688/1545, loss: 5.5992631912231445 2023-01-23 05:06:25.494125: step: 690/1545, loss: 5.803457736968994 2023-01-23 05:06:26.343517: step: 692/1545, loss: 4.760037422180176 2023-01-23 05:06:27.246153: step: 694/1545, loss: 3.847874402999878 2023-01-23 05:06:28.083740: step: 696/1545, loss: 3.9333558082580566 2023-01-23 05:06:28.998722: step: 698/1545, loss: 12.863389015197754 2023-01-23 05:06:29.857809: step: 700/1545, loss: 4.849617958068848 2023-01-23 05:06:30.739700: step: 702/1545, loss: 2.6521120071411133 2023-01-23 05:06:31.598957: step: 704/1545, loss: 2.8712642192840576 2023-01-23 05:06:32.480652: step: 706/1545, loss: 4.793381214141846 2023-01-23 05:06:33.371077: step: 708/1545, loss: 2.2470905780792236 2023-01-23 05:06:34.277101: step: 710/1545, loss: 3.0242831707000732 2023-01-23 05:06:35.201510: step: 712/1545, loss: 5.107677459716797 2023-01-23 05:06:36.071589: step: 714/1545, loss: 2.4410338401794434 2023-01-23 05:06:36.940659: step: 716/1545, loss: 4.284115314483643 2023-01-23 05:06:37.812172: step: 718/1545, loss: 4.657960891723633 2023-01-23 05:06:38.708428: step: 720/1545, loss: 5.5503458976745605 2023-01-23 05:06:39.558321: step: 722/1545, loss: 3.032393217086792 2023-01-23 05:06:40.472411: step: 724/1545, loss: 5.9930524826049805 2023-01-23 05:06:41.366021: step: 726/1545, loss: 3.980097532272339 2023-01-23 05:06:42.283229: step: 728/1545, loss: 3.70194411277771 2023-01-23 05:06:43.143880: step: 730/1545, loss: 5.592124938964844 2023-01-23 05:06:44.025530: step: 732/1545, loss: 3.868898391723633 2023-01-23 05:06:44.963280: step: 734/1545, loss: 5.731993675231934 2023-01-23 05:06:45.825817: step: 736/1545, loss: 3.2974424362182617 2023-01-23 05:06:46.750615: step: 738/1545, loss: 3.5648610591888428 2023-01-23 05:06:47.676070: step: 740/1545, loss: 4.760150909423828 2023-01-23 05:06:48.562419: step: 742/1545, loss: 3.849153757095337 2023-01-23 05:06:49.447272: step: 744/1545, loss: 3.414581298828125 2023-01-23 05:06:50.300243: step: 746/1545, loss: 3.5416178703308105 2023-01-23 05:06:51.193882: step: 748/1545, loss: 5.299128532409668 2023-01-23 05:06:52.080482: step: 750/1545, loss: 2.6251914501190186 2023-01-23 05:06:52.985700: step: 752/1545, loss: 3.9597949981689453 2023-01-23 05:06:53.848433: step: 754/1545, loss: 2.623854875564575 2023-01-23 05:06:54.734495: step: 756/1545, loss: 4.075788497924805 2023-01-23 05:06:55.624099: step: 758/1545, loss: 5.242593765258789 2023-01-23 05:06:56.472490: step: 760/1545, loss: 2.4300503730773926 2023-01-23 05:06:57.331314: step: 762/1545, loss: 7.973336219787598 2023-01-23 05:06:58.274768: step: 764/1545, loss: 6.0596442222595215 2023-01-23 05:06:59.197035: step: 766/1545, loss: 2.3351376056671143 2023-01-23 05:07:00.181927: step: 768/1545, loss: 5.44029426574707 2023-01-23 05:07:01.050097: step: 770/1545, loss: 3.964010715484619 2023-01-23 05:07:01.950240: step: 772/1545, loss: 5.599957466125488 2023-01-23 05:07:02.826710: step: 774/1545, loss: 3.2484397888183594 2023-01-23 05:07:03.694778: step: 776/1545, loss: 3.3632736206054688 2023-01-23 05:07:04.614782: step: 778/1545, loss: 3.7967822551727295 2023-01-23 05:07:05.490151: step: 780/1545, loss: 5.0811567306518555 2023-01-23 05:07:06.376299: step: 782/1545, loss: 3.9317588806152344 2023-01-23 05:07:07.294533: step: 784/1545, loss: 4.521950721740723 2023-01-23 05:07:08.155267: step: 786/1545, loss: 3.8797357082366943 2023-01-23 05:07:09.056035: step: 788/1545, loss: 4.389268398284912 2023-01-23 05:07:09.954783: step: 790/1545, loss: 2.1467905044555664 2023-01-23 05:07:10.831300: step: 792/1545, loss: 4.421832084655762 2023-01-23 05:07:11.697425: step: 794/1545, loss: 1.852537989616394 2023-01-23 05:07:12.612005: step: 796/1545, loss: 11.738564491271973 2023-01-23 05:07:13.535889: step: 798/1545, loss: 3.124138593673706 2023-01-23 05:07:14.406749: step: 800/1545, loss: 2.8071043491363525 2023-01-23 05:07:15.259908: step: 802/1545, loss: 3.33056640625 2023-01-23 05:07:16.131366: step: 804/1545, loss: 2.752485513687134 2023-01-23 05:07:17.022015: step: 806/1545, loss: 2.9254560470581055 2023-01-23 05:07:17.891091: step: 808/1545, loss: 12.019871711730957 2023-01-23 05:07:18.787139: step: 810/1545, loss: 2.022952079772949 2023-01-23 05:07:19.712733: step: 812/1545, loss: 2.5631155967712402 2023-01-23 05:07:20.607150: step: 814/1545, loss: 2.29512619972229 2023-01-23 05:07:21.476411: step: 816/1545, loss: 6.522487640380859 2023-01-23 05:07:22.360043: step: 818/1545, loss: 2.9985427856445312 2023-01-23 05:07:23.270387: step: 820/1545, loss: 4.3347015380859375 2023-01-23 05:07:24.183036: step: 822/1545, loss: 4.735441207885742 2023-01-23 05:07:25.102571: step: 824/1545, loss: 3.1545543670654297 2023-01-23 05:07:25.973368: step: 826/1545, loss: 2.078664779663086 2023-01-23 05:07:26.875513: step: 828/1545, loss: 2.4625279903411865 2023-01-23 05:07:27.753402: step: 830/1545, loss: 3.138990879058838 2023-01-23 05:07:28.646615: step: 832/1545, loss: 3.4779837131500244 2023-01-23 05:07:29.492286: step: 834/1545, loss: 6.236569404602051 2023-01-23 05:07:30.398455: step: 836/1545, loss: 2.877244710922241 2023-01-23 05:07:31.257143: step: 838/1545, loss: 6.613051414489746 2023-01-23 05:07:32.130997: step: 840/1545, loss: 12.666677474975586 2023-01-23 05:07:32.983792: step: 842/1545, loss: 5.216363906860352 2023-01-23 05:07:33.833256: step: 844/1545, loss: 5.5245680809021 2023-01-23 05:07:34.719983: step: 846/1545, loss: 3.930640697479248 2023-01-23 05:07:35.610916: step: 848/1545, loss: 3.776700973510742 2023-01-23 05:07:36.479520: step: 850/1545, loss: 5.967137813568115 2023-01-23 05:07:37.467133: step: 852/1545, loss: 3.0733001232147217 2023-01-23 05:07:38.341324: step: 854/1545, loss: 5.5204758644104 2023-01-23 05:07:39.238025: step: 856/1545, loss: 2.4807820320129395 2023-01-23 05:07:40.123665: step: 858/1545, loss: 6.1239166259765625 2023-01-23 05:07:40.969908: step: 860/1545, loss: 4.039193630218506 2023-01-23 05:07:41.843786: step: 862/1545, loss: 3.909637689590454 2023-01-23 05:07:42.717731: step: 864/1545, loss: 5.86976957321167 2023-01-23 05:07:43.600049: step: 866/1545, loss: 10.550395011901855 2023-01-23 05:07:44.494646: step: 868/1545, loss: 3.4940404891967773 2023-01-23 05:07:45.398848: step: 870/1545, loss: 3.7105624675750732 2023-01-23 05:07:46.306366: step: 872/1545, loss: 2.062563180923462 2023-01-23 05:07:47.211063: step: 874/1545, loss: 2.9529778957366943 2023-01-23 05:07:48.054393: step: 876/1545, loss: 3.405573844909668 2023-01-23 05:07:48.898456: step: 878/1545, loss: 2.2048261165618896 2023-01-23 05:07:49.768966: step: 880/1545, loss: 2.017582416534424 2023-01-23 05:07:50.658605: step: 882/1545, loss: 3.262845277786255 2023-01-23 05:07:51.600351: step: 884/1545, loss: 2.201634645462036 2023-01-23 05:07:52.488499: step: 886/1545, loss: 2.5340523719787598 2023-01-23 05:07:53.382527: step: 888/1545, loss: 6.51765251159668 2023-01-23 05:07:54.284872: step: 890/1545, loss: 3.565216302871704 2023-01-23 05:07:55.158822: step: 892/1545, loss: 3.797306776046753 2023-01-23 05:07:56.021059: step: 894/1545, loss: 2.649207353591919 2023-01-23 05:07:56.921909: step: 896/1545, loss: 2.491175889968872 2023-01-23 05:07:57.797704: step: 898/1545, loss: 2.4262969493865967 2023-01-23 05:07:58.643883: step: 900/1545, loss: 4.312516212463379 2023-01-23 05:07:59.505924: step: 902/1545, loss: 8.861574172973633 2023-01-23 05:08:00.402171: step: 904/1545, loss: 2.9927897453308105 2023-01-23 05:08:01.273531: step: 906/1545, loss: 2.009052038192749 2023-01-23 05:08:02.189032: step: 908/1545, loss: 2.3727409839630127 2023-01-23 05:08:03.027758: step: 910/1545, loss: 3.0685324668884277 2023-01-23 05:08:03.901518: step: 912/1545, loss: 2.7316131591796875 2023-01-23 05:08:04.804232: step: 914/1545, loss: 3.956498146057129 2023-01-23 05:08:05.687431: step: 916/1545, loss: 1.898313045501709 2023-01-23 05:08:06.587907: step: 918/1545, loss: 4.356161117553711 2023-01-23 05:08:07.547011: step: 920/1545, loss: 4.19920539855957 2023-01-23 05:08:08.386262: step: 922/1545, loss: 3.116014242172241 2023-01-23 05:08:09.276700: step: 924/1545, loss: 2.7464327812194824 2023-01-23 05:08:10.139643: step: 926/1545, loss: 5.674986362457275 2023-01-23 05:08:11.060892: step: 928/1545, loss: 4.054687023162842 2023-01-23 05:08:11.927899: step: 930/1545, loss: 5.019675254821777 2023-01-23 05:08:12.791503: step: 932/1545, loss: 2.664700508117676 2023-01-23 05:08:13.681863: step: 934/1545, loss: 2.8837215900421143 2023-01-23 05:08:14.572056: step: 936/1545, loss: 2.7275514602661133 2023-01-23 05:08:15.465318: step: 938/1545, loss: 7.541682243347168 2023-01-23 05:08:16.351867: step: 940/1545, loss: 3.795931577682495 2023-01-23 05:08:17.247864: step: 942/1545, loss: 2.7677090167999268 2023-01-23 05:08:18.128191: step: 944/1545, loss: 3.8494837284088135 2023-01-23 05:08:19.032231: step: 946/1545, loss: 3.2237560749053955 2023-01-23 05:08:19.941516: step: 948/1545, loss: 3.02377986907959 2023-01-23 05:08:20.866650: step: 950/1545, loss: 3.8076820373535156 2023-01-23 05:08:21.841454: step: 952/1545, loss: 3.0232348442077637 2023-01-23 05:08:22.694346: step: 954/1545, loss: 3.363629102706909 2023-01-23 05:08:23.551135: step: 956/1545, loss: 2.400892734527588 2023-01-23 05:08:24.413992: step: 958/1545, loss: 3.0287272930145264 2023-01-23 05:08:25.276201: step: 960/1545, loss: 3.04996919631958 2023-01-23 05:08:26.140383: step: 962/1545, loss: 2.337515354156494 2023-01-23 05:08:27.022943: step: 964/1545, loss: 2.859468698501587 2023-01-23 05:08:27.928453: step: 966/1545, loss: 1.7861343622207642 2023-01-23 05:08:28.792055: step: 968/1545, loss: 3.4521658420562744 2023-01-23 05:08:29.678157: step: 970/1545, loss: 4.080350399017334 2023-01-23 05:08:30.617071: step: 972/1545, loss: 2.7405474185943604 2023-01-23 05:08:31.602376: step: 974/1545, loss: 4.331506729125977 2023-01-23 05:08:32.472556: step: 976/1545, loss: 2.3054556846618652 2023-01-23 05:08:33.332807: step: 978/1545, loss: 1.954980731010437 2023-01-23 05:08:34.203874: step: 980/1545, loss: 3.5387377738952637 2023-01-23 05:08:35.102121: step: 982/1545, loss: 3.7230401039123535 2023-01-23 05:08:35.977285: step: 984/1545, loss: 2.588057041168213 2023-01-23 05:08:36.872097: step: 986/1545, loss: 2.2532238960266113 2023-01-23 05:08:37.720140: step: 988/1545, loss: 2.057206392288208 2023-01-23 05:08:38.568397: step: 990/1545, loss: 6.341231346130371 2023-01-23 05:08:39.479324: step: 992/1545, loss: 3.253664016723633 2023-01-23 05:08:40.374895: step: 994/1545, loss: 2.8036439418792725 2023-01-23 05:08:41.235041: step: 996/1545, loss: 2.543393611907959 2023-01-23 05:08:42.097303: step: 998/1545, loss: 1.2473468780517578 2023-01-23 05:08:43.005330: step: 1000/1545, loss: 3.484001398086548 2023-01-23 05:08:43.882465: step: 1002/1545, loss: 3.443617820739746 2023-01-23 05:08:44.789050: step: 1004/1545, loss: 2.346567153930664 2023-01-23 05:08:45.646107: step: 1006/1545, loss: 6.187777996063232 2023-01-23 05:08:46.520626: step: 1008/1545, loss: 7.659043312072754 2023-01-23 05:08:47.394301: step: 1010/1545, loss: 3.0492138862609863 2023-01-23 05:08:48.266556: step: 1012/1545, loss: 3.3440558910369873 2023-01-23 05:08:49.178345: step: 1014/1545, loss: 4.905281066894531 2023-01-23 05:08:50.084105: step: 1016/1545, loss: 2.6316146850585938 2023-01-23 05:08:50.947201: step: 1018/1545, loss: 2.5139310359954834 2023-01-23 05:08:51.823597: step: 1020/1545, loss: 2.7048115730285645 2023-01-23 05:08:52.721069: step: 1022/1545, loss: 3.5517759323120117 2023-01-23 05:08:53.587483: step: 1024/1545, loss: 3.031414747238159 2023-01-23 05:08:54.475966: step: 1026/1545, loss: 2.5508010387420654 2023-01-23 05:08:55.346453: step: 1028/1545, loss: 3.4740850925445557 2023-01-23 05:08:56.211105: step: 1030/1545, loss: 3.819815158843994 2023-01-23 05:08:57.039971: step: 1032/1545, loss: 2.769824266433716 2023-01-23 05:08:57.948258: step: 1034/1545, loss: 3.2350311279296875 2023-01-23 05:08:58.869537: step: 1036/1545, loss: 6.28524923324585 2023-01-23 05:08:59.746059: step: 1038/1545, loss: 4.744021892547607 2023-01-23 05:09:00.656791: step: 1040/1545, loss: 4.772756576538086 2023-01-23 05:09:01.518909: step: 1042/1545, loss: 3.4905574321746826 2023-01-23 05:09:02.365558: step: 1044/1545, loss: 3.1643402576446533 2023-01-23 05:09:03.242278: step: 1046/1545, loss: 1.2150143384933472 2023-01-23 05:09:04.137331: step: 1048/1545, loss: 3.810340166091919 2023-01-23 05:09:04.997143: step: 1050/1545, loss: 2.766655683517456 2023-01-23 05:09:05.888196: step: 1052/1545, loss: 3.2598581314086914 2023-01-23 05:09:06.784771: step: 1054/1545, loss: 2.8099000453948975 2023-01-23 05:09:07.666015: step: 1056/1545, loss: 9.432713508605957 2023-01-23 05:09:08.531735: step: 1058/1545, loss: 2.550886392593384 2023-01-23 05:09:09.491219: step: 1060/1545, loss: 3.5101869106292725 2023-01-23 05:09:10.364457: step: 1062/1545, loss: 3.096097230911255 2023-01-23 05:09:11.219199: step: 1064/1545, loss: 2.3455944061279297 2023-01-23 05:09:12.126484: step: 1066/1545, loss: 3.7766616344451904 2023-01-23 05:09:13.007991: step: 1068/1545, loss: 4.224192142486572 2023-01-23 05:09:13.860160: step: 1070/1545, loss: 2.8408472537994385 2023-01-23 05:09:14.755189: step: 1072/1545, loss: 3.066740036010742 2023-01-23 05:09:15.635844: step: 1074/1545, loss: 3.2055981159210205 2023-01-23 05:09:16.508452: step: 1076/1545, loss: 6.815956115722656 2023-01-23 05:09:17.335992: step: 1078/1545, loss: 2.5765695571899414 2023-01-23 05:09:18.319260: step: 1080/1545, loss: 2.0995237827301025 2023-01-23 05:09:19.240013: step: 1082/1545, loss: 2.8493614196777344 2023-01-23 05:09:20.098903: step: 1084/1545, loss: 3.2829949855804443 2023-01-23 05:09:20.987732: step: 1086/1545, loss: 2.1811435222625732 2023-01-23 05:09:21.848785: step: 1088/1545, loss: 3.8520493507385254 2023-01-23 05:09:22.738124: step: 1090/1545, loss: 2.6260735988616943 2023-01-23 05:09:23.616496: step: 1092/1545, loss: 1.136293649673462 2023-01-23 05:09:24.483083: step: 1094/1545, loss: 2.1966254711151123 2023-01-23 05:09:25.355580: step: 1096/1545, loss: 1.632912516593933 2023-01-23 05:09:26.238173: step: 1098/1545, loss: 2.271207571029663 2023-01-23 05:09:27.110387: step: 1100/1545, loss: 7.267696380615234 2023-01-23 05:09:27.969011: step: 1102/1545, loss: 0.9157484173774719 2023-01-23 05:09:28.833511: step: 1104/1545, loss: 2.6578171253204346 2023-01-23 05:09:29.679635: step: 1106/1545, loss: 0.9975342750549316 2023-01-23 05:09:30.591126: step: 1108/1545, loss: 4.976865768432617 2023-01-23 05:09:31.464232: step: 1110/1545, loss: 3.177949905395508 2023-01-23 05:09:32.308094: step: 1112/1545, loss: 2.966130256652832 2023-01-23 05:09:33.206250: step: 1114/1545, loss: 3.113067865371704 2023-01-23 05:09:34.088899: step: 1116/1545, loss: 4.259593963623047 2023-01-23 05:09:34.959078: step: 1118/1545, loss: 3.3270721435546875 2023-01-23 05:09:35.857244: step: 1120/1545, loss: 3.7586729526519775 2023-01-23 05:09:36.736485: step: 1122/1545, loss: 3.9958243370056152 2023-01-23 05:09:37.578955: step: 1124/1545, loss: 3.053541421890259 2023-01-23 05:09:38.472658: step: 1126/1545, loss: 2.55826473236084 2023-01-23 05:09:39.401965: step: 1128/1545, loss: 3.7326741218566895 2023-01-23 05:09:40.246987: step: 1130/1545, loss: 3.9116005897521973 2023-01-23 05:09:41.123899: step: 1132/1545, loss: 2.2790892124176025 2023-01-23 05:09:42.092444: step: 1134/1545, loss: 3.8440146446228027 2023-01-23 05:09:42.952477: step: 1136/1545, loss: 3.8927571773529053 2023-01-23 05:09:43.781363: step: 1138/1545, loss: 2.3092000484466553 2023-01-23 05:09:44.645421: step: 1140/1545, loss: 2.644916534423828 2023-01-23 05:09:45.531933: step: 1142/1545, loss: 3.830113410949707 2023-01-23 05:09:46.389977: step: 1144/1545, loss: 3.0802628993988037 2023-01-23 05:09:47.222378: step: 1146/1545, loss: 2.647757053375244 2023-01-23 05:09:48.115535: step: 1148/1545, loss: 3.722057580947876 2023-01-23 05:09:49.018287: step: 1150/1545, loss: 5.4382853507995605 2023-01-23 05:09:49.858640: step: 1152/1545, loss: 2.1474437713623047 2023-01-23 05:09:50.766209: step: 1154/1545, loss: 3.888843059539795 2023-01-23 05:09:51.627862: step: 1156/1545, loss: 1.5369926691055298 2023-01-23 05:09:52.503918: step: 1158/1545, loss: 1.4685176610946655 2023-01-23 05:09:53.393686: step: 1160/1545, loss: 3.0163516998291016 2023-01-23 05:09:54.265299: step: 1162/1545, loss: 4.0419416427612305 2023-01-23 05:09:55.127583: step: 1164/1545, loss: 2.7520666122436523 2023-01-23 05:09:56.006202: step: 1166/1545, loss: 2.5428214073181152 2023-01-23 05:09:56.892243: step: 1168/1545, loss: 2.327474594116211 2023-01-23 05:09:57.795085: step: 1170/1545, loss: 5.087017059326172 2023-01-23 05:09:58.678237: step: 1172/1545, loss: 5.112860202789307 2023-01-23 05:09:59.530899: step: 1174/1545, loss: 3.12223744392395 2023-01-23 05:10:00.475103: step: 1176/1545, loss: 4.230081081390381 2023-01-23 05:10:01.364546: step: 1178/1545, loss: 3.535609245300293 2023-01-23 05:10:02.200461: step: 1180/1545, loss: 3.323516368865967 2023-01-23 05:10:03.102341: step: 1182/1545, loss: 1.9667503833770752 2023-01-23 05:10:03.974476: step: 1184/1545, loss: 4.914681434631348 2023-01-23 05:10:04.846642: step: 1186/1545, loss: 2.2765438556671143 2023-01-23 05:10:05.765956: step: 1188/1545, loss: 4.683783531188965 2023-01-23 05:10:06.609169: step: 1190/1545, loss: 2.587454319000244 2023-01-23 05:10:07.480618: step: 1192/1545, loss: 2.5319793224334717 2023-01-23 05:10:08.356367: step: 1194/1545, loss: 3.0659894943237305 2023-01-23 05:10:09.254457: step: 1196/1545, loss: 2.866987943649292 2023-01-23 05:10:10.147327: step: 1198/1545, loss: 2.049600124359131 2023-01-23 05:10:11.029456: step: 1200/1545, loss: 3.1092026233673096 2023-01-23 05:10:11.908502: step: 1202/1545, loss: 6.7587080001831055 2023-01-23 05:10:12.762443: step: 1204/1545, loss: 3.858042001724243 2023-01-23 05:10:13.641245: step: 1206/1545, loss: 5.037951946258545 2023-01-23 05:10:14.491605: step: 1208/1545, loss: 1.924971580505371 2023-01-23 05:10:15.361731: step: 1210/1545, loss: 2.6935763359069824 2023-01-23 05:10:16.231456: step: 1212/1545, loss: 2.6527798175811768 2023-01-23 05:10:17.141220: step: 1214/1545, loss: 2.575039863586426 2023-01-23 05:10:17.997599: step: 1216/1545, loss: 6.5190839767456055 2023-01-23 05:10:18.896208: step: 1218/1545, loss: 2.2695138454437256 2023-01-23 05:10:19.759576: step: 1220/1545, loss: 1.3951032161712646 2023-01-23 05:10:20.688566: step: 1222/1545, loss: 2.374575614929199 2023-01-23 05:10:21.591962: step: 1224/1545, loss: 2.3477418422698975 2023-01-23 05:10:22.475336: step: 1226/1545, loss: 2.5567808151245117 2023-01-23 05:10:23.347491: step: 1228/1545, loss: 2.3528714179992676 2023-01-23 05:10:24.238306: step: 1230/1545, loss: 3.11909556388855 2023-01-23 05:10:25.105971: step: 1232/1545, loss: 2.280095100402832 2023-01-23 05:10:25.973238: step: 1234/1545, loss: 9.641624450683594 2023-01-23 05:10:26.845472: step: 1236/1545, loss: 1.6523810625076294 2023-01-23 05:10:27.721074: step: 1238/1545, loss: 2.545200824737549 2023-01-23 05:10:28.608889: step: 1240/1545, loss: 3.4129209518432617 2023-01-23 05:10:29.506815: step: 1242/1545, loss: 2.529862880706787 2023-01-23 05:10:30.391773: step: 1244/1545, loss: 3.652649402618408 2023-01-23 05:10:31.255077: step: 1246/1545, loss: 2.856757402420044 2023-01-23 05:10:32.139486: step: 1248/1545, loss: 1.886415719985962 2023-01-23 05:10:33.007072: step: 1250/1545, loss: 2.866947650909424 2023-01-23 05:10:33.889902: step: 1252/1545, loss: 1.7114150524139404 2023-01-23 05:10:34.796473: step: 1254/1545, loss: 2.0792958736419678 2023-01-23 05:10:35.660398: step: 1256/1545, loss: 2.430840015411377 2023-01-23 05:10:36.523513: step: 1258/1545, loss: 2.885977029800415 2023-01-23 05:10:37.414627: step: 1260/1545, loss: 3.294112205505371 2023-01-23 05:10:38.277598: step: 1262/1545, loss: 2.260676145553589 2023-01-23 05:10:39.141726: step: 1264/1545, loss: 1.3439302444458008 2023-01-23 05:10:40.011530: step: 1266/1545, loss: 3.284059762954712 2023-01-23 05:10:40.881167: step: 1268/1545, loss: 2.9040582180023193 2023-01-23 05:10:41.721986: step: 1270/1545, loss: 9.047331809997559 2023-01-23 05:10:42.607418: step: 1272/1545, loss: 2.732178211212158 2023-01-23 05:10:43.435648: step: 1274/1545, loss: 1.6234326362609863 2023-01-23 05:10:44.294463: step: 1276/1545, loss: 2.7263243198394775 2023-01-23 05:10:45.157366: step: 1278/1545, loss: 2.914306640625 2023-01-23 05:10:46.008634: step: 1280/1545, loss: 1.923107624053955 2023-01-23 05:10:46.881691: step: 1282/1545, loss: 1.3477632999420166 2023-01-23 05:10:47.779343: step: 1284/1545, loss: 3.1087255477905273 2023-01-23 05:10:48.639381: step: 1286/1545, loss: 2.0884971618652344 2023-01-23 05:10:49.546595: step: 1288/1545, loss: 3.1074917316436768 2023-01-23 05:10:50.458791: step: 1290/1545, loss: 3.4713568687438965 2023-01-23 05:10:51.357434: step: 1292/1545, loss: 1.9233590364456177 2023-01-23 05:10:52.269635: step: 1294/1545, loss: 2.725221633911133 2023-01-23 05:10:53.120627: step: 1296/1545, loss: 2.261284589767456 2023-01-23 05:10:53.974087: step: 1298/1545, loss: 1.7837773561477661 2023-01-23 05:10:54.822344: step: 1300/1545, loss: 3.441027879714966 2023-01-23 05:10:55.687511: step: 1302/1545, loss: 1.4369900226593018 2023-01-23 05:10:56.547564: step: 1304/1545, loss: 7.618218421936035 2023-01-23 05:10:57.422653: step: 1306/1545, loss: 1.9862881898880005 2023-01-23 05:10:58.305049: step: 1308/1545, loss: 10.256463050842285 2023-01-23 05:10:59.201498: step: 1310/1545, loss: 2.576969861984253 2023-01-23 05:11:00.116842: step: 1312/1545, loss: 2.874433994293213 2023-01-23 05:11:00.965527: step: 1314/1545, loss: 2.9281578063964844 2023-01-23 05:11:01.832096: step: 1316/1545, loss: 6.314938545227051 2023-01-23 05:11:02.710777: step: 1318/1545, loss: 2.2550928592681885 2023-01-23 05:11:03.598608: step: 1320/1545, loss: 4.339580535888672 2023-01-23 05:11:04.496143: step: 1322/1545, loss: 1.9170279502868652 2023-01-23 05:11:05.358622: step: 1324/1545, loss: 1.8455395698547363 2023-01-23 05:11:06.227272: step: 1326/1545, loss: 7.130923748016357 2023-01-23 05:11:07.114095: step: 1328/1545, loss: 3.2275049686431885 2023-01-23 05:11:07.970448: step: 1330/1545, loss: 4.159206867218018 2023-01-23 05:11:08.877274: step: 1332/1545, loss: 2.3554999828338623 2023-01-23 05:11:09.748235: step: 1334/1545, loss: 4.872841835021973 2023-01-23 05:11:10.593657: step: 1336/1545, loss: 3.5277624130249023 2023-01-23 05:11:11.490934: step: 1338/1545, loss: 3.179905652999878 2023-01-23 05:11:12.361638: step: 1340/1545, loss: 7.08409309387207 2023-01-23 05:11:13.241126: step: 1342/1545, loss: 3.6470303535461426 2023-01-23 05:11:14.116892: step: 1344/1545, loss: 2.8683629035949707 2023-01-23 05:11:14.986627: step: 1346/1545, loss: 2.088379144668579 2023-01-23 05:11:15.839112: step: 1348/1545, loss: 6.231141567230225 2023-01-23 05:11:16.745328: step: 1350/1545, loss: 4.31614351272583 2023-01-23 05:11:17.616056: step: 1352/1545, loss: 1.8482136726379395 2023-01-23 05:11:18.520817: step: 1354/1545, loss: 1.7195703983306885 2023-01-23 05:11:19.379334: step: 1356/1545, loss: 2.6640713214874268 2023-01-23 05:11:20.237144: step: 1358/1545, loss: 7.8377909660339355 2023-01-23 05:11:21.106659: step: 1360/1545, loss: 1.5745007991790771 2023-01-23 05:11:21.956540: step: 1362/1545, loss: 2.2214503288269043 2023-01-23 05:11:22.819682: step: 1364/1545, loss: 4.587332248687744 2023-01-23 05:11:23.692487: step: 1366/1545, loss: 2.843843936920166 2023-01-23 05:11:24.595234: step: 1368/1545, loss: 2.452530860900879 2023-01-23 05:11:25.467504: step: 1370/1545, loss: 1.9716047048568726 2023-01-23 05:11:26.344915: step: 1372/1545, loss: 1.8382806777954102 2023-01-23 05:11:27.244900: step: 1374/1545, loss: 6.5106682777404785 2023-01-23 05:11:28.114296: step: 1376/1545, loss: 2.4581432342529297 2023-01-23 05:11:28.991771: step: 1378/1545, loss: 3.9985926151275635 2023-01-23 05:11:29.867722: step: 1380/1545, loss: 3.7473065853118896 2023-01-23 05:11:30.758126: step: 1382/1545, loss: 3.1645092964172363 2023-01-23 05:11:31.645204: step: 1384/1545, loss: 2.2426655292510986 2023-01-23 05:11:32.507307: step: 1386/1545, loss: 3.2522122859954834 2023-01-23 05:11:33.400748: step: 1388/1545, loss: 2.765604257583618 2023-01-23 05:11:34.392716: step: 1390/1545, loss: 2.6251630783081055 2023-01-23 05:11:35.259589: step: 1392/1545, loss: 2.021496295928955 2023-01-23 05:11:36.127075: step: 1394/1545, loss: 3.3648879528045654 2023-01-23 05:11:37.022957: step: 1396/1545, loss: 2.8495707511901855 2023-01-23 05:11:37.870114: step: 1398/1545, loss: 3.270089864730835 2023-01-23 05:11:38.762933: step: 1400/1545, loss: 4.179500102996826 2023-01-23 05:11:39.633604: step: 1402/1545, loss: 3.4015390872955322 2023-01-23 05:11:40.492234: step: 1404/1545, loss: 1.7440210580825806 2023-01-23 05:11:41.399903: step: 1406/1545, loss: 2.872415781021118 2023-01-23 05:11:42.281656: step: 1408/1545, loss: 1.7466707229614258 2023-01-23 05:11:43.125668: step: 1410/1545, loss: 2.649402379989624 2023-01-23 05:11:44.001568: step: 1412/1545, loss: 4.945300102233887 2023-01-23 05:11:44.859064: step: 1414/1545, loss: 2.4729549884796143 2023-01-23 05:11:45.726508: step: 1416/1545, loss: 1.448643445968628 2023-01-23 05:11:46.635198: step: 1418/1545, loss: 2.261218786239624 2023-01-23 05:11:47.520297: step: 1420/1545, loss: 7.105202674865723 2023-01-23 05:11:48.360450: step: 1422/1545, loss: 1.8806098699569702 2023-01-23 05:11:49.294362: step: 1424/1545, loss: 4.120715141296387 2023-01-23 05:11:50.132539: step: 1426/1545, loss: 1.2120057344436646 2023-01-23 05:11:50.979634: step: 1428/1545, loss: 1.7051336765289307 2023-01-23 05:11:51.864605: step: 1430/1545, loss: 4.900132179260254 2023-01-23 05:11:52.749698: step: 1432/1545, loss: 1.6365224123001099 2023-01-23 05:11:53.616414: step: 1434/1545, loss: 2.193455934524536 2023-01-23 05:11:54.460423: step: 1436/1545, loss: 1.70008385181427 2023-01-23 05:11:55.296427: step: 1438/1545, loss: 2.4383015632629395 2023-01-23 05:11:56.157836: step: 1440/1545, loss: 2.6495022773742676 2023-01-23 05:11:57.004812: step: 1442/1545, loss: 2.636500835418701 2023-01-23 05:11:57.854484: step: 1444/1545, loss: 1.2590831518173218 2023-01-23 05:11:58.732026: step: 1446/1545, loss: 1.9188687801361084 2023-01-23 05:11:59.570339: step: 1448/1545, loss: 4.289154529571533 2023-01-23 05:12:00.421269: step: 1450/1545, loss: 3.2454640865325928 2023-01-23 05:12:01.329442: step: 1452/1545, loss: 2.9359235763549805 2023-01-23 05:12:02.187105: step: 1454/1545, loss: 3.77286696434021 2023-01-23 05:12:03.071430: step: 1456/1545, loss: 4.5785231590271 2023-01-23 05:12:03.913272: step: 1458/1545, loss: 2.755521535873413 2023-01-23 05:12:04.786051: step: 1460/1545, loss: 2.6882033348083496 2023-01-23 05:12:05.688426: step: 1462/1545, loss: 1.723899245262146 2023-01-23 05:12:06.540310: step: 1464/1545, loss: 3.3572750091552734 2023-01-23 05:12:07.404400: step: 1466/1545, loss: 2.90515398979187 2023-01-23 05:12:08.269594: step: 1468/1545, loss: 2.719172477722168 2023-01-23 05:12:09.140794: step: 1470/1545, loss: 1.68186616897583 2023-01-23 05:12:09.999025: step: 1472/1545, loss: 3.031567096710205 2023-01-23 05:12:10.908959: step: 1474/1545, loss: 2.9132511615753174 2023-01-23 05:12:11.777246: step: 1476/1545, loss: 4.0764617919921875 2023-01-23 05:12:12.656295: step: 1478/1545, loss: 3.8954803943634033 2023-01-23 05:12:13.513752: step: 1480/1545, loss: 3.164895534515381 2023-01-23 05:12:14.374980: step: 1482/1545, loss: 3.7684781551361084 2023-01-23 05:12:15.242762: step: 1484/1545, loss: 3.281604528427124 2023-01-23 05:12:16.106163: step: 1486/1545, loss: 3.1247851848602295 2023-01-23 05:12:16.988123: step: 1488/1545, loss: 8.514967918395996 2023-01-23 05:12:17.853570: step: 1490/1545, loss: 2.128113031387329 2023-01-23 05:12:18.682440: step: 1492/1545, loss: 1.689803123474121 2023-01-23 05:12:19.564281: step: 1494/1545, loss: 3.269277334213257 2023-01-23 05:12:20.516679: step: 1496/1545, loss: 2.3645334243774414 2023-01-23 05:12:21.372994: step: 1498/1545, loss: 2.2601096630096436 2023-01-23 05:12:22.303324: step: 1500/1545, loss: 1.8668644428253174 2023-01-23 05:12:23.167412: step: 1502/1545, loss: 3.294492483139038 2023-01-23 05:12:24.049169: step: 1504/1545, loss: 2.844475269317627 2023-01-23 05:12:24.915658: step: 1506/1545, loss: 2.3069941997528076 2023-01-23 05:12:25.810422: step: 1508/1545, loss: 4.481807708740234 2023-01-23 05:12:26.683631: step: 1510/1545, loss: 5.647739887237549 2023-01-23 05:12:27.544087: step: 1512/1545, loss: 2.801279306411743 2023-01-23 05:12:28.399487: step: 1514/1545, loss: 1.8131794929504395 2023-01-23 05:12:29.241544: step: 1516/1545, loss: 1.7189995050430298 2023-01-23 05:12:30.121587: step: 1518/1545, loss: 1.7483819723129272 2023-01-23 05:12:31.052236: step: 1520/1545, loss: 1.802081823348999 2023-01-23 05:12:31.922599: step: 1522/1545, loss: 1.78665292263031 2023-01-23 05:12:32.803679: step: 1524/1545, loss: 3.304713010787964 2023-01-23 05:12:33.707805: step: 1526/1545, loss: 3.6125059127807617 2023-01-23 05:12:34.538795: step: 1528/1545, loss: 2.3885486125946045 2023-01-23 05:12:35.361965: step: 1530/1545, loss: 1.7045634984970093 2023-01-23 05:12:36.240955: step: 1532/1545, loss: 3.3775103092193604 2023-01-23 05:12:37.132413: step: 1534/1545, loss: 10.86194896697998 2023-01-23 05:12:38.051931: step: 1536/1545, loss: 2.8400497436523438 2023-01-23 05:12:38.895670: step: 1538/1545, loss: 1.7434929609298706 2023-01-23 05:12:39.785953: step: 1540/1545, loss: 2.0175492763519287 2023-01-23 05:12:40.663605: step: 1542/1545, loss: 4.660427570343018 2023-01-23 05:12:41.529003: step: 1544/1545, loss: 4.24084997177124 2023-01-23 05:12:42.425465: step: 1546/1545, loss: 2.296536922454834 2023-01-23 05:12:43.278319: step: 1548/1545, loss: 1.2951436042785645 2023-01-23 05:12:44.128855: step: 1550/1545, loss: 1.4443557262420654 2023-01-23 05:12:44.987534: step: 1552/1545, loss: 1.682992935180664 2023-01-23 05:12:45.888615: step: 1554/1545, loss: 1.1387302875518799 2023-01-23 05:12:46.744211: step: 1556/1545, loss: 2.5528979301452637 2023-01-23 05:12:47.616203: step: 1558/1545, loss: 2.899286985397339 2023-01-23 05:12:48.496115: step: 1560/1545, loss: 2.402252674102783 2023-01-23 05:12:49.464787: step: 1562/1545, loss: 1.8667834997177124 2023-01-23 05:12:50.292112: step: 1564/1545, loss: 1.6943299770355225 2023-01-23 05:12:51.211716: step: 1566/1545, loss: 3.2156450748443604 2023-01-23 05:12:52.070813: step: 1568/1545, loss: 0.8997929692268372 2023-01-23 05:12:52.984169: step: 1570/1545, loss: 2.1567537784576416 2023-01-23 05:12:53.856077: step: 1572/1545, loss: 1.9705758094787598 2023-01-23 05:12:54.743168: step: 1574/1545, loss: 2.7040984630584717 2023-01-23 05:12:55.609125: step: 1576/1545, loss: 2.633984327316284 2023-01-23 05:12:56.485949: step: 1578/1545, loss: 1.8764536380767822 2023-01-23 05:12:57.360642: step: 1580/1545, loss: 2.604687452316284 2023-01-23 05:12:58.244964: step: 1582/1545, loss: 1.5281929969787598 2023-01-23 05:12:59.151261: step: 1584/1545, loss: 3.067983388900757 2023-01-23 05:13:00.024496: step: 1586/1545, loss: 2.0433731079101562 2023-01-23 05:13:00.888178: step: 1588/1545, loss: 2.3067171573638916 2023-01-23 05:13:01.780845: step: 1590/1545, loss: 1.3941479921340942 2023-01-23 05:13:02.628582: step: 1592/1545, loss: 3.6905856132507324 2023-01-23 05:13:03.486556: step: 1594/1545, loss: 2.671466827392578 2023-01-23 05:13:04.372355: step: 1596/1545, loss: 1.6903516054153442 2023-01-23 05:13:05.331007: step: 1598/1545, loss: 1.9143472909927368 2023-01-23 05:13:06.207902: step: 1600/1545, loss: 1.9953057765960693 2023-01-23 05:13:07.069138: step: 1602/1545, loss: 1.7530632019042969 2023-01-23 05:13:07.934449: step: 1604/1545, loss: 2.1248369216918945 2023-01-23 05:13:08.796335: step: 1606/1545, loss: 4.591507911682129 2023-01-23 05:13:09.656983: step: 1608/1545, loss: 1.5221740007400513 2023-01-23 05:13:10.547046: step: 1610/1545, loss: 2.3465003967285156 2023-01-23 05:13:11.413116: step: 1612/1545, loss: 2.1221301555633545 2023-01-23 05:13:12.253829: step: 1614/1545, loss: 2.466174364089966 2023-01-23 05:13:13.146762: step: 1616/1545, loss: 3.3117315769195557 2023-01-23 05:13:14.015475: step: 1618/1545, loss: 7.813490867614746 2023-01-23 05:13:14.888603: step: 1620/1545, loss: 1.8321443796157837 2023-01-23 05:13:15.723943: step: 1622/1545, loss: 1.400964617729187 2023-01-23 05:13:16.573047: step: 1624/1545, loss: 4.667362213134766 2023-01-23 05:13:17.424115: step: 1626/1545, loss: 1.2342982292175293 2023-01-23 05:13:18.310244: step: 1628/1545, loss: 6.527574062347412 2023-01-23 05:13:19.160223: step: 1630/1545, loss: 2.6416618824005127 2023-01-23 05:13:20.025199: step: 1632/1545, loss: 2.5044612884521484 2023-01-23 05:13:20.899602: step: 1634/1545, loss: 8.656023979187012 2023-01-23 05:13:21.778124: step: 1636/1545, loss: 5.053381443023682 2023-01-23 05:13:22.632573: step: 1638/1545, loss: 2.5015218257904053 2023-01-23 05:13:23.502126: step: 1640/1545, loss: 1.4347535371780396 2023-01-23 05:13:24.418915: step: 1642/1545, loss: 2.8648228645324707 2023-01-23 05:13:25.289688: step: 1644/1545, loss: 2.169494390487671 2023-01-23 05:13:26.207382: step: 1646/1545, loss: 4.00032377243042 2023-01-23 05:13:27.102419: step: 1648/1545, loss: 1.9431999921798706 2023-01-23 05:13:27.966449: step: 1650/1545, loss: 2.14132022857666 2023-01-23 05:13:28.854624: step: 1652/1545, loss: 4.386419296264648 2023-01-23 05:13:29.729811: step: 1654/1545, loss: 2.1867494583129883 2023-01-23 05:13:30.583050: step: 1656/1545, loss: 1.6451796293258667 2023-01-23 05:13:31.471178: step: 1658/1545, loss: 4.677586555480957 2023-01-23 05:13:32.372724: step: 1660/1545, loss: 3.205828905105591 2023-01-23 05:13:33.239966: step: 1662/1545, loss: 1.3151671886444092 2023-01-23 05:13:34.097543: step: 1664/1545, loss: 10.932612419128418 2023-01-23 05:13:35.011836: step: 1666/1545, loss: 1.7725876569747925 2023-01-23 05:13:35.880196: step: 1668/1545, loss: 2.040663242340088 2023-01-23 05:13:36.741313: step: 1670/1545, loss: 3.257197141647339 2023-01-23 05:13:37.699915: step: 1672/1545, loss: 3.018678665161133 2023-01-23 05:13:38.552269: step: 1674/1545, loss: 3.663323402404785 2023-01-23 05:13:39.426327: step: 1676/1545, loss: 1.3685297966003418 2023-01-23 05:13:40.261475: step: 1678/1545, loss: 1.889908790588379 2023-01-23 05:13:41.125268: step: 1680/1545, loss: 2.0379080772399902 2023-01-23 05:13:41.995835: step: 1682/1545, loss: 1.700289011001587 2023-01-23 05:13:42.868364: step: 1684/1545, loss: 2.521479845046997 2023-01-23 05:13:43.751746: step: 1686/1545, loss: 2.1085104942321777 2023-01-23 05:13:44.638007: step: 1688/1545, loss: 1.166634440422058 2023-01-23 05:13:45.520933: step: 1690/1545, loss: 1.4399685859680176 2023-01-23 05:13:46.412886: step: 1692/1545, loss: 8.030037879943848 2023-01-23 05:13:47.296905: step: 1694/1545, loss: 5.853471755981445 2023-01-23 05:13:48.172193: step: 1696/1545, loss: 2.9344098567962646 2023-01-23 05:13:49.049487: step: 1698/1545, loss: 2.9497768878936768 2023-01-23 05:13:49.908754: step: 1700/1545, loss: 2.1812050342559814 2023-01-23 05:13:50.779644: step: 1702/1545, loss: 2.6095080375671387 2023-01-23 05:13:51.673805: step: 1704/1545, loss: 3.5398097038269043 2023-01-23 05:13:52.555875: step: 1706/1545, loss: 10.288355827331543 2023-01-23 05:13:53.422729: step: 1708/1545, loss: 1.703343391418457 2023-01-23 05:13:54.320531: step: 1710/1545, loss: 2.6056766510009766 2023-01-23 05:13:55.222051: step: 1712/1545, loss: 3.6316587924957275 2023-01-23 05:13:56.145638: step: 1714/1545, loss: 1.5264838933944702 2023-01-23 05:13:57.029841: step: 1716/1545, loss: 4.556839942932129 2023-01-23 05:13:57.906545: step: 1718/1545, loss: 2.7333061695098877 2023-01-23 05:13:58.805746: step: 1720/1545, loss: 1.76029634475708 2023-01-23 05:13:59.693607: step: 1722/1545, loss: 1.956417202949524 2023-01-23 05:14:00.564536: step: 1724/1545, loss: 2.6150362491607666 2023-01-23 05:14:01.437067: step: 1726/1545, loss: 3.681044101715088 2023-01-23 05:14:02.316623: step: 1728/1545, loss: 2.794797658920288 2023-01-23 05:14:03.211706: step: 1730/1545, loss: 2.988982677459717 2023-01-23 05:14:04.064982: step: 1732/1545, loss: 2.3321046829223633 2023-01-23 05:14:04.957437: step: 1734/1545, loss: 1.1772187948226929 2023-01-23 05:14:05.831569: step: 1736/1545, loss: 1.5968823432922363 2023-01-23 05:14:06.678007: step: 1738/1545, loss: 2.14370059967041 2023-01-23 05:14:07.547027: step: 1740/1545, loss: 5.35334587097168 2023-01-23 05:14:08.376023: step: 1742/1545, loss: 3.750476598739624 2023-01-23 05:14:09.204467: step: 1744/1545, loss: 2.103437662124634 2023-01-23 05:14:10.071389: step: 1746/1545, loss: 2.145785093307495 2023-01-23 05:14:10.983119: step: 1748/1545, loss: 1.1636618375778198 2023-01-23 05:14:11.865763: step: 1750/1545, loss: 1.117841362953186 2023-01-23 05:14:12.703798: step: 1752/1545, loss: 4.1894097328186035 2023-01-23 05:14:13.569493: step: 1754/1545, loss: 1.522029161453247 2023-01-23 05:14:14.456581: step: 1756/1545, loss: 2.062908172607422 2023-01-23 05:14:15.355314: step: 1758/1545, loss: 2.0821444988250732 2023-01-23 05:14:16.211184: step: 1760/1545, loss: 2.1757030487060547 2023-01-23 05:14:17.054447: step: 1762/1545, loss: 1.6892818212509155 2023-01-23 05:14:17.907407: step: 1764/1545, loss: 4.912388801574707 2023-01-23 05:14:18.783205: step: 1766/1545, loss: 2.5329487323760986 2023-01-23 05:14:19.670875: step: 1768/1545, loss: 8.292662620544434 2023-01-23 05:14:20.524847: step: 1770/1545, loss: 2.78715181350708 2023-01-23 05:14:21.367299: step: 1772/1545, loss: 3.522742748260498 2023-01-23 05:14:22.224694: step: 1774/1545, loss: 1.2741087675094604 2023-01-23 05:14:23.110716: step: 1776/1545, loss: 2.6950442790985107 2023-01-23 05:14:23.960882: step: 1778/1545, loss: 6.847694396972656 2023-01-23 05:14:24.815469: step: 1780/1545, loss: 1.9608815908432007 2023-01-23 05:14:25.671239: step: 1782/1545, loss: 2.1476802825927734 2023-01-23 05:14:26.575749: step: 1784/1545, loss: 0.906697154045105 2023-01-23 05:14:27.414559: step: 1786/1545, loss: 4.544790267944336 2023-01-23 05:14:28.280133: step: 1788/1545, loss: 1.9451558589935303 2023-01-23 05:14:29.157150: step: 1790/1545, loss: 2.0711135864257812 2023-01-23 05:14:30.022778: step: 1792/1545, loss: 2.107156991958618 2023-01-23 05:14:30.947778: step: 1794/1545, loss: 1.881421446800232 2023-01-23 05:14:31.802892: step: 1796/1545, loss: 4.366698741912842 2023-01-23 05:14:32.666430: step: 1798/1545, loss: 9.694891929626465 2023-01-23 05:14:33.543855: step: 1800/1545, loss: 2.629509210586548 2023-01-23 05:14:34.385578: step: 1802/1545, loss: 1.6214408874511719 2023-01-23 05:14:35.224677: step: 1804/1545, loss: 1.6227911710739136 2023-01-23 05:14:36.094283: step: 1806/1545, loss: 4.065802574157715 2023-01-23 05:14:36.962275: step: 1808/1545, loss: 1.8815594911575317 2023-01-23 05:14:37.906545: step: 1810/1545, loss: 1.9343957901000977 2023-01-23 05:14:38.750285: step: 1812/1545, loss: 1.6224271059036255 2023-01-23 05:14:39.635910: step: 1814/1545, loss: 2.224940299987793 2023-01-23 05:14:40.509549: step: 1816/1545, loss: 2.3314614295959473 2023-01-23 05:14:41.408081: step: 1818/1545, loss: 1.5241341590881348 2023-01-23 05:14:42.284693: step: 1820/1545, loss: 2.8465726375579834 2023-01-23 05:14:43.178162: step: 1822/1545, loss: 1.3643393516540527 2023-01-23 05:14:44.097993: step: 1824/1545, loss: 5.243529796600342 2023-01-23 05:14:44.969466: step: 1826/1545, loss: 1.3538007736206055 2023-01-23 05:14:45.857250: step: 1828/1545, loss: 2.6151061058044434 2023-01-23 05:14:46.746407: step: 1830/1545, loss: 3.967653274536133 2023-01-23 05:14:47.623995: step: 1832/1545, loss: 2.831577777862549 2023-01-23 05:14:48.479357: step: 1834/1545, loss: 4.5303874015808105 2023-01-23 05:14:49.358901: step: 1836/1545, loss: 2.484100103378296 2023-01-23 05:14:50.228926: step: 1838/1545, loss: 4.047296524047852 2023-01-23 05:14:51.125466: step: 1840/1545, loss: 1.5895694494247437 2023-01-23 05:14:52.010305: step: 1842/1545, loss: 2.5777947902679443 2023-01-23 05:14:52.912333: step: 1844/1545, loss: 1.4239211082458496 2023-01-23 05:14:53.782304: step: 1846/1545, loss: 3.7714760303497314 2023-01-23 05:14:54.638988: step: 1848/1545, loss: 4.332126617431641 2023-01-23 05:14:55.532885: step: 1850/1545, loss: 2.7461392879486084 2023-01-23 05:14:56.379038: step: 1852/1545, loss: 1.1356086730957031 2023-01-23 05:14:57.260198: step: 1854/1545, loss: 5.15290641784668 2023-01-23 05:14:58.131518: step: 1856/1545, loss: 2.170457363128662 2023-01-23 05:14:58.974723: step: 1858/1545, loss: 1.1632729768753052 2023-01-23 05:14:59.827700: step: 1860/1545, loss: 1.571079134941101 2023-01-23 05:15:00.778959: step: 1862/1545, loss: 4.917539119720459 2023-01-23 05:15:01.637836: step: 1864/1545, loss: 5.002762317657471 2023-01-23 05:15:02.532434: step: 1866/1545, loss: 2.9719483852386475 2023-01-23 05:15:03.385401: step: 1868/1545, loss: 1.1180528402328491 2023-01-23 05:15:04.262481: step: 1870/1545, loss: 5.58929967880249 2023-01-23 05:15:05.249579: step: 1872/1545, loss: 2.281243085861206 2023-01-23 05:15:06.093401: step: 1874/1545, loss: 1.7095283269882202 2023-01-23 05:15:06.974390: step: 1876/1545, loss: 2.0649936199188232 2023-01-23 05:15:07.837754: step: 1878/1545, loss: 2.3295679092407227 2023-01-23 05:15:08.711953: step: 1880/1545, loss: 4.883394241333008 2023-01-23 05:15:09.633904: step: 1882/1545, loss: 2.811936855316162 2023-01-23 05:15:10.469736: step: 1884/1545, loss: 2.5650253295898438 2023-01-23 05:15:11.308010: step: 1886/1545, loss: 2.0100159645080566 2023-01-23 05:15:12.206812: step: 1888/1545, loss: 1.8767002820968628 2023-01-23 05:15:13.112754: step: 1890/1545, loss: 6.873069763183594 2023-01-23 05:15:13.989173: step: 1892/1545, loss: 2.665626049041748 2023-01-23 05:15:14.859390: step: 1894/1545, loss: 2.579364776611328 2023-01-23 05:15:15.725865: step: 1896/1545, loss: 1.9226939678192139 2023-01-23 05:15:16.592722: step: 1898/1545, loss: 4.19879150390625 2023-01-23 05:15:17.449393: step: 1900/1545, loss: 2.817575216293335 2023-01-23 05:15:18.337376: step: 1902/1545, loss: 1.2076627016067505 2023-01-23 05:15:19.313251: step: 1904/1545, loss: 1.7631956338882446 2023-01-23 05:15:20.153422: step: 1906/1545, loss: 3.8833260536193848 2023-01-23 05:15:21.001085: step: 1908/1545, loss: 2.2219300270080566 2023-01-23 05:15:21.886445: step: 1910/1545, loss: 1.8503987789154053 2023-01-23 05:15:22.762872: step: 1912/1545, loss: 2.0758566856384277 2023-01-23 05:15:23.605989: step: 1914/1545, loss: 1.6132954359054565 2023-01-23 05:15:24.511699: step: 1916/1545, loss: 3.0550265312194824 2023-01-23 05:15:25.389522: step: 1918/1545, loss: 1.8153157234191895 2023-01-23 05:15:26.247568: step: 1920/1545, loss: 1.58811354637146 2023-01-23 05:15:27.096081: step: 1922/1545, loss: 2.1872427463531494 2023-01-23 05:15:27.989092: step: 1924/1545, loss: 2.5231685638427734 2023-01-23 05:15:28.887532: step: 1926/1545, loss: 1.2601670026779175 2023-01-23 05:15:29.768210: step: 1928/1545, loss: 1.5029020309448242 2023-01-23 05:15:30.634742: step: 1930/1545, loss: 2.68129563331604 2023-01-23 05:15:31.520372: step: 1932/1545, loss: 2.4047975540161133 2023-01-23 05:15:32.338125: step: 1934/1545, loss: 2.008868455886841 2023-01-23 05:15:33.277736: step: 1936/1545, loss: 2.5395348072052 2023-01-23 05:15:34.127577: step: 1938/1545, loss: 1.1046286821365356 2023-01-23 05:15:34.987256: step: 1940/1545, loss: 2.607207775115967 2023-01-23 05:15:35.904331: step: 1942/1545, loss: 1.6123707294464111 2023-01-23 05:15:36.797774: step: 1944/1545, loss: 4.47161340713501 2023-01-23 05:15:37.642676: step: 1946/1545, loss: 4.552103042602539 2023-01-23 05:15:38.512229: step: 1948/1545, loss: 3.0862929821014404 2023-01-23 05:15:39.391325: step: 1950/1545, loss: 1.724111795425415 2023-01-23 05:15:40.280101: step: 1952/1545, loss: 1.7811884880065918 2023-01-23 05:15:41.167346: step: 1954/1545, loss: 1.5204123258590698 2023-01-23 05:15:42.028140: step: 1956/1545, loss: 1.0909876823425293 2023-01-23 05:15:42.928624: step: 1958/1545, loss: 3.3754818439483643 2023-01-23 05:15:43.782923: step: 1960/1545, loss: 3.3957414627075195 2023-01-23 05:15:44.687762: step: 1962/1545, loss: 1.586545467376709 2023-01-23 05:15:45.552656: step: 1964/1545, loss: 5.093800067901611 2023-01-23 05:15:46.476015: step: 1966/1545, loss: 2.8787992000579834 2023-01-23 05:15:47.318877: step: 1968/1545, loss: 1.9639601707458496 2023-01-23 05:15:48.168834: step: 1970/1545, loss: 1.4228270053863525 2023-01-23 05:15:49.036770: step: 1972/1545, loss: 1.390031337738037 2023-01-23 05:15:49.951742: step: 1974/1545, loss: 2.535949945449829 2023-01-23 05:15:50.787640: step: 1976/1545, loss: 1.8228187561035156 2023-01-23 05:15:51.716503: step: 1978/1545, loss: 1.970035433769226 2023-01-23 05:15:52.596493: step: 1980/1545, loss: 2.705944061279297 2023-01-23 05:15:53.440010: step: 1982/1545, loss: 1.5751093626022339 2023-01-23 05:15:54.395778: step: 1984/1545, loss: 4.48061990737915 2023-01-23 05:15:55.299116: step: 1986/1545, loss: 4.947110652923584 2023-01-23 05:15:56.184417: step: 1988/1545, loss: 1.4809125661849976 2023-01-23 05:15:57.058483: step: 1990/1545, loss: 2.029266834259033 2023-01-23 05:15:57.905486: step: 1992/1545, loss: 1.532315731048584 2023-01-23 05:15:58.810658: step: 1994/1545, loss: 1.1092228889465332 2023-01-23 05:15:59.664891: step: 1996/1545, loss: 2.2347147464752197 2023-01-23 05:16:00.519347: step: 1998/1545, loss: 1.482987642288208 2023-01-23 05:16:01.422815: step: 2000/1545, loss: 3.4330477714538574 2023-01-23 05:16:02.298155: step: 2002/1545, loss: 1.2787805795669556 2023-01-23 05:16:03.212958: step: 2004/1545, loss: 0.7049325108528137 2023-01-23 05:16:04.052939: step: 2006/1545, loss: 1.222865343093872 2023-01-23 05:16:04.930174: step: 2008/1545, loss: 1.5706260204315186 2023-01-23 05:16:05.780357: step: 2010/1545, loss: 8.423796653747559 2023-01-23 05:16:06.628712: step: 2012/1545, loss: 1.672947645187378 2023-01-23 05:16:07.491029: step: 2014/1545, loss: 3.0830624103546143 2023-01-23 05:16:08.326840: step: 2016/1545, loss: 2.8170785903930664 2023-01-23 05:16:09.166315: step: 2018/1545, loss: 2.4211699962615967 2023-01-23 05:16:09.979487: step: 2020/1545, loss: 1.0219380855560303 2023-01-23 05:16:10.827948: step: 2022/1545, loss: 1.778041958808899 2023-01-23 05:16:11.699358: step: 2024/1545, loss: 1.7532702684402466 2023-01-23 05:16:12.526658: step: 2026/1545, loss: 3.9199869632720947 2023-01-23 05:16:13.418194: step: 2028/1545, loss: 1.2901755571365356 2023-01-23 05:16:14.309190: step: 2030/1545, loss: 1.5665820837020874 2023-01-23 05:16:15.170300: step: 2032/1545, loss: 2.1045899391174316 2023-01-23 05:16:16.039877: step: 2034/1545, loss: 1.7709096670150757 2023-01-23 05:16:16.878948: step: 2036/1545, loss: 1.4745128154754639 2023-01-23 05:16:17.769918: step: 2038/1545, loss: 2.6352641582489014 2023-01-23 05:16:18.631290: step: 2040/1545, loss: 6.889646530151367 2023-01-23 05:16:19.513593: step: 2042/1545, loss: 1.230458378791809 2023-01-23 05:16:20.358151: step: 2044/1545, loss: 0.9485775232315063 2023-01-23 05:16:21.224859: step: 2046/1545, loss: 2.241142749786377 2023-01-23 05:16:22.122187: step: 2048/1545, loss: 2.215588092803955 2023-01-23 05:16:23.030967: step: 2050/1545, loss: 1.6956279277801514 2023-01-23 05:16:23.859978: step: 2052/1545, loss: 2.9207448959350586 2023-01-23 05:16:24.721346: step: 2054/1545, loss: 1.2159781455993652 2023-01-23 05:16:25.600497: step: 2056/1545, loss: 0.9147109985351562 2023-01-23 05:16:26.478951: step: 2058/1545, loss: 4.115941047668457 2023-01-23 05:16:27.337232: step: 2060/1545, loss: 2.3693783283233643 2023-01-23 05:16:28.234331: step: 2062/1545, loss: 1.54592764377594 2023-01-23 05:16:29.109501: step: 2064/1545, loss: 1.9485042095184326 2023-01-23 05:16:29.967952: step: 2066/1545, loss: 1.26503586769104 2023-01-23 05:16:30.878403: step: 2068/1545, loss: 1.6021369695663452 2023-01-23 05:16:31.705748: step: 2070/1545, loss: 2.096264600753784 2023-01-23 05:16:32.570841: step: 2072/1545, loss: 1.2395436763763428 2023-01-23 05:16:33.405410: step: 2074/1545, loss: 4.461483955383301 2023-01-23 05:16:34.298227: step: 2076/1545, loss: 1.6315553188323975 2023-01-23 05:16:35.192847: step: 2078/1545, loss: 1.6621742248535156 2023-01-23 05:16:36.050680: step: 2080/1545, loss: 1.7242681980133057 2023-01-23 05:16:36.901764: step: 2082/1545, loss: 0.856045126914978 2023-01-23 05:16:37.812545: step: 2084/1545, loss: 1.351896047592163 2023-01-23 05:16:38.732416: step: 2086/1545, loss: 2.1104049682617188 2023-01-23 05:16:39.612250: step: 2088/1545, loss: 1.6460199356079102 2023-01-23 05:16:40.530913: step: 2090/1545, loss: 1.6908217668533325 2023-01-23 05:16:41.406024: step: 2092/1545, loss: 1.8991843461990356 2023-01-23 05:16:42.254943: step: 2094/1545, loss: 1.6378761529922485 2023-01-23 05:16:43.108344: step: 2096/1545, loss: 1.4349491596221924 2023-01-23 05:16:43.979310: step: 2098/1545, loss: 2.6313536167144775 2023-01-23 05:16:44.835924: step: 2100/1545, loss: 1.9093108177185059 2023-01-23 05:16:45.757490: step: 2102/1545, loss: 1.2173449993133545 2023-01-23 05:16:46.613545: step: 2104/1545, loss: 1.4679198265075684 2023-01-23 05:16:47.492115: step: 2106/1545, loss: 2.598033905029297 2023-01-23 05:16:48.385363: step: 2108/1545, loss: 2.5601327419281006 2023-01-23 05:16:49.301253: step: 2110/1545, loss: 1.1720796823501587 2023-01-23 05:16:50.153208: step: 2112/1545, loss: 1.3908332586288452 2023-01-23 05:16:51.011903: step: 2114/1545, loss: 2.410752296447754 2023-01-23 05:16:51.851925: step: 2116/1545, loss: 7.460543632507324 2023-01-23 05:16:52.691707: step: 2118/1545, loss: 3.602522134780884 2023-01-23 05:16:53.557488: step: 2120/1545, loss: 1.4534006118774414 2023-01-23 05:16:54.437441: step: 2122/1545, loss: 1.107771873474121 2023-01-23 05:16:55.308953: step: 2124/1545, loss: 1.6336407661437988 2023-01-23 05:16:56.194252: step: 2126/1545, loss: 1.8660304546356201 2023-01-23 05:16:57.103765: step: 2128/1545, loss: 3.919032335281372 2023-01-23 05:16:58.005862: step: 2130/1545, loss: 1.8768692016601562 2023-01-23 05:16:58.953830: step: 2132/1545, loss: 1.9340993165969849 2023-01-23 05:16:59.852973: step: 2134/1545, loss: 3.699920415878296 2023-01-23 05:17:00.727809: step: 2136/1545, loss: 1.504217267036438 2023-01-23 05:17:01.688396: step: 2138/1545, loss: 1.2012104988098145 2023-01-23 05:17:02.571356: step: 2140/1545, loss: 2.2112157344818115 2023-01-23 05:17:03.472654: step: 2142/1545, loss: 1.8595908880233765 2023-01-23 05:17:04.383517: step: 2144/1545, loss: 1.5824006795883179 2023-01-23 05:17:05.255176: step: 2146/1545, loss: 1.0213805437088013 2023-01-23 05:17:06.096873: step: 2148/1545, loss: 1.0733224153518677 2023-01-23 05:17:06.966951: step: 2150/1545, loss: 1.2867707014083862 2023-01-23 05:17:07.807090: step: 2152/1545, loss: 1.482514500617981 2023-01-23 05:17:08.704539: step: 2154/1545, loss: 0.9429205656051636 2023-01-23 05:17:09.553634: step: 2156/1545, loss: 1.363826870918274 2023-01-23 05:17:10.397396: step: 2158/1545, loss: 5.9399027824401855 2023-01-23 05:17:11.244695: step: 2160/1545, loss: 4.3472442626953125 2023-01-23 05:17:12.148846: step: 2162/1545, loss: 4.5698323249816895 2023-01-23 05:17:13.068383: step: 2164/1545, loss: 1.8746914863586426 2023-01-23 05:17:13.912590: step: 2166/1545, loss: 1.3776342868804932 2023-01-23 05:17:14.822041: step: 2168/1545, loss: 4.784692764282227 2023-01-23 05:17:15.682201: step: 2170/1545, loss: 3.88122820854187 2023-01-23 05:17:16.558101: step: 2172/1545, loss: 1.2286789417266846 2023-01-23 05:17:17.454254: step: 2174/1545, loss: 1.2191154956817627 2023-01-23 05:17:18.340558: step: 2176/1545, loss: 4.042562961578369 2023-01-23 05:17:19.208605: step: 2178/1545, loss: 1.5732895135879517 2023-01-23 05:17:20.100739: step: 2180/1545, loss: 1.6974838972091675 2023-01-23 05:17:20.960354: step: 2182/1545, loss: 1.043886661529541 2023-01-23 05:17:21.837077: step: 2184/1545, loss: 3.8540873527526855 2023-01-23 05:17:22.670745: step: 2186/1545, loss: 0.7580413222312927 2023-01-23 05:17:23.514804: step: 2188/1545, loss: 1.3131020069122314 2023-01-23 05:17:24.434698: step: 2190/1545, loss: 3.020681381225586 2023-01-23 05:17:25.301627: step: 2192/1545, loss: 1.9378981590270996 2023-01-23 05:17:26.183265: step: 2194/1545, loss: 3.9681384563446045 2023-01-23 05:17:27.040252: step: 2196/1545, loss: 1.783353567123413 2023-01-23 05:17:27.897018: step: 2198/1545, loss: 2.2360997200012207 2023-01-23 05:17:28.751425: step: 2200/1545, loss: 1.798818826675415 2023-01-23 05:17:29.634922: step: 2202/1545, loss: 3.526310920715332 2023-01-23 05:17:30.491741: step: 2204/1545, loss: 1.4311994314193726 2023-01-23 05:17:31.424779: step: 2206/1545, loss: 3.514061450958252 2023-01-23 05:17:32.276873: step: 2208/1545, loss: 1.1801745891571045 2023-01-23 05:17:33.129291: step: 2210/1545, loss: 0.9011772274971008 2023-01-23 05:17:33.994160: step: 2212/1545, loss: 1.64669930934906 2023-01-23 05:17:34.864634: step: 2214/1545, loss: 1.4178789854049683 2023-01-23 05:17:35.741989: step: 2216/1545, loss: 2.3165745735168457 2023-01-23 05:17:36.610976: step: 2218/1545, loss: 1.6980687379837036 2023-01-23 05:17:37.477706: step: 2220/1545, loss: 1.9010149240493774 2023-01-23 05:17:38.340712: step: 2222/1545, loss: 1.839338779449463 2023-01-23 05:17:39.362087: step: 2224/1545, loss: 4.779167652130127 2023-01-23 05:17:40.186265: step: 2226/1545, loss: 10.280488014221191 2023-01-23 05:17:41.044615: step: 2228/1545, loss: 2.130188465118408 2023-01-23 05:17:41.922077: step: 2230/1545, loss: 1.5944581031799316 2023-01-23 05:17:42.866124: step: 2232/1545, loss: 2.343461036682129 2023-01-23 05:17:43.831709: step: 2234/1545, loss: 2.3451755046844482 2023-01-23 05:17:44.702550: step: 2236/1545, loss: 1.8497776985168457 2023-01-23 05:17:45.562457: step: 2238/1545, loss: 1.793517827987671 2023-01-23 05:17:46.446149: step: 2240/1545, loss: 4.497383117675781 2023-01-23 05:17:47.302587: step: 2242/1545, loss: 1.1195366382598877 2023-01-23 05:17:48.145058: step: 2244/1545, loss: 1.028300166130066 2023-01-23 05:17:49.031262: step: 2246/1545, loss: 1.5103018283843994 2023-01-23 05:17:49.912898: step: 2248/1545, loss: 2.7286763191223145 2023-01-23 05:17:50.793148: step: 2250/1545, loss: 1.489654779434204 2023-01-23 05:17:51.656705: step: 2252/1545, loss: 1.2531569004058838 2023-01-23 05:17:52.522514: step: 2254/1545, loss: 5.167257785797119 2023-01-23 05:17:53.394933: step: 2256/1545, loss: 6.217461109161377 2023-01-23 05:17:54.241332: step: 2258/1545, loss: 1.7643070220947266 2023-01-23 05:17:55.141569: step: 2260/1545, loss: 2.902440071105957 2023-01-23 05:17:56.007048: step: 2262/1545, loss: 1.6858899593353271 2023-01-23 05:17:56.856307: step: 2264/1545, loss: 2.171264410018921 2023-01-23 05:17:57.690117: step: 2266/1545, loss: 2.662555694580078 2023-01-23 05:17:58.607359: step: 2268/1545, loss: 1.2332504987716675 2023-01-23 05:17:59.472787: step: 2270/1545, loss: 0.9939723014831543 2023-01-23 05:18:00.317661: step: 2272/1545, loss: 2.1647889614105225 2023-01-23 05:18:01.210911: step: 2274/1545, loss: 2.7007946968078613 2023-01-23 05:18:02.069475: step: 2276/1545, loss: 1.5260342359542847 2023-01-23 05:18:02.947933: step: 2278/1545, loss: 5.189181327819824 2023-01-23 05:18:03.852413: step: 2280/1545, loss: 1.3251804113388062 2023-01-23 05:18:04.697749: step: 2282/1545, loss: 2.8402838706970215 2023-01-23 05:18:05.589120: step: 2284/1545, loss: 2.971855878829956 2023-01-23 05:18:06.452077: step: 2286/1545, loss: 4.102859020233154 2023-01-23 05:18:07.328282: step: 2288/1545, loss: 1.2287734746932983 2023-01-23 05:18:08.179345: step: 2290/1545, loss: 1.6966521739959717 2023-01-23 05:18:09.033700: step: 2292/1545, loss: 1.0225250720977783 2023-01-23 05:18:09.927728: step: 2294/1545, loss: 2.549985408782959 2023-01-23 05:18:10.802781: step: 2296/1545, loss: 2.373913526535034 2023-01-23 05:18:11.671842: step: 2298/1545, loss: 2.034034490585327 2023-01-23 05:18:12.536580: step: 2300/1545, loss: 0.9246492385864258 2023-01-23 05:18:13.370519: step: 2302/1545, loss: 7.56800651550293 2023-01-23 05:18:14.238561: step: 2304/1545, loss: 1.816282033920288 2023-01-23 05:18:15.142614: step: 2306/1545, loss: 2.954707622528076 2023-01-23 05:18:15.980898: step: 2308/1545, loss: 1.722923994064331 2023-01-23 05:18:16.826275: step: 2310/1545, loss: 1.7723227739334106 2023-01-23 05:18:17.717011: step: 2312/1545, loss: 1.839402675628662 2023-01-23 05:18:18.623320: step: 2314/1545, loss: 1.4351270198822021 2023-01-23 05:18:19.485554: step: 2316/1545, loss: 1.9119490385055542 2023-01-23 05:18:20.485952: step: 2318/1545, loss: 4.661867618560791 2023-01-23 05:18:21.462379: step: 2320/1545, loss: 1.705259084701538 2023-01-23 05:18:22.344360: step: 2322/1545, loss: 1.5890498161315918 2023-01-23 05:18:23.190419: step: 2324/1545, loss: 1.7680232524871826 2023-01-23 05:18:24.039949: step: 2326/1545, loss: 4.912835121154785 2023-01-23 05:18:24.912603: step: 2328/1545, loss: 8.463071823120117 2023-01-23 05:18:25.817276: step: 2330/1545, loss: 1.6927289962768555 2023-01-23 05:18:26.700187: step: 2332/1545, loss: 3.973888635635376 2023-01-23 05:18:27.555130: step: 2334/1545, loss: 1.0888234376907349 2023-01-23 05:18:28.421618: step: 2336/1545, loss: 1.7956784963607788 2023-01-23 05:18:29.282684: step: 2338/1545, loss: 1.9180353879928589 2023-01-23 05:18:30.146191: step: 2340/1545, loss: 1.6864440441131592 2023-01-23 05:18:31.045130: step: 2342/1545, loss: 4.806419372558594 2023-01-23 05:18:31.872047: step: 2344/1545, loss: 1.5283277034759521 2023-01-23 05:18:32.711805: step: 2346/1545, loss: 1.8940517902374268 2023-01-23 05:18:33.627826: step: 2348/1545, loss: 2.049121856689453 2023-01-23 05:18:34.499944: step: 2350/1545, loss: 1.8177571296691895 2023-01-23 05:18:35.398681: step: 2352/1545, loss: 2.251753330230713 2023-01-23 05:18:36.256546: step: 2354/1545, loss: 1.5927613973617554 2023-01-23 05:18:37.149609: step: 2356/1545, loss: 1.1744060516357422 2023-01-23 05:18:38.121356: step: 2358/1545, loss: 1.9891761541366577 2023-01-23 05:18:38.979683: step: 2360/1545, loss: 1.1846293210983276 2023-01-23 05:18:39.891943: step: 2362/1545, loss: 1.297255277633667 2023-01-23 05:18:40.782840: step: 2364/1545, loss: 1.099353313446045 2023-01-23 05:18:41.669941: step: 2366/1545, loss: 4.165179252624512 2023-01-23 05:18:42.520241: step: 2368/1545, loss: 1.8103830814361572 2023-01-23 05:18:43.394368: step: 2370/1545, loss: 4.442145347595215 2023-01-23 05:18:44.285410: step: 2372/1545, loss: 4.470189571380615 2023-01-23 05:18:45.189644: step: 2374/1545, loss: 2.4537291526794434 2023-01-23 05:18:46.072151: step: 2376/1545, loss: 2.111961603164673 2023-01-23 05:18:46.988260: step: 2378/1545, loss: 0.816279947757721 2023-01-23 05:18:47.836366: step: 2380/1545, loss: 1.2887506484985352 2023-01-23 05:18:48.721200: step: 2382/1545, loss: 6.334158897399902 2023-01-23 05:18:49.647489: step: 2384/1545, loss: 0.9231662154197693 2023-01-23 05:18:50.538324: step: 2386/1545, loss: 3.0284459590911865 2023-01-23 05:18:51.396203: step: 2388/1545, loss: 4.3408050537109375 2023-01-23 05:18:52.269972: step: 2390/1545, loss: 1.1157560348510742 2023-01-23 05:18:53.124721: step: 2392/1545, loss: 1.2656961679458618 2023-01-23 05:18:53.970673: step: 2394/1545, loss: 2.451329469680786 2023-01-23 05:18:54.838519: step: 2396/1545, loss: 1.7094857692718506 2023-01-23 05:18:55.692060: step: 2398/1545, loss: 2.421318531036377 2023-01-23 05:18:56.571735: step: 2400/1545, loss: 1.6694279909133911 2023-01-23 05:18:57.437964: step: 2402/1545, loss: 1.4088484048843384 2023-01-23 05:18:58.278632: step: 2404/1545, loss: 2.6793620586395264 2023-01-23 05:18:59.168549: step: 2406/1545, loss: 0.9922075271606445 2023-01-23 05:19:00.123484: step: 2408/1545, loss: 2.420133352279663 2023-01-23 05:19:00.976989: step: 2410/1545, loss: 1.191339373588562 2023-01-23 05:19:01.887424: step: 2412/1545, loss: 1.9696646928787231 2023-01-23 05:19:02.772007: step: 2414/1545, loss: 0.8788246512413025 2023-01-23 05:19:03.661248: step: 2416/1545, loss: 0.6581028699874878 2023-01-23 05:19:04.575077: step: 2418/1545, loss: 3.4258816242218018 2023-01-23 05:19:05.479791: step: 2420/1545, loss: 1.8984160423278809 2023-01-23 05:19:06.362894: step: 2422/1545, loss: 2.421701669692993 2023-01-23 05:19:07.227694: step: 2424/1545, loss: 1.7075551748275757 2023-01-23 05:19:08.089952: step: 2426/1545, loss: 1.5086441040039062 2023-01-23 05:19:08.933506: step: 2428/1545, loss: 1.1047719717025757 2023-01-23 05:19:09.780349: step: 2430/1545, loss: 0.9894453287124634 2023-01-23 05:19:10.755625: step: 2432/1545, loss: 1.8730816841125488 2023-01-23 05:19:11.589505: step: 2434/1545, loss: 7.725741386413574 2023-01-23 05:19:12.477194: step: 2436/1545, loss: 1.463282585144043 2023-01-23 05:19:13.338091: step: 2438/1545, loss: 2.186110258102417 2023-01-23 05:19:14.241460: step: 2440/1545, loss: 1.3136494159698486 2023-01-23 05:19:15.158402: step: 2442/1545, loss: 7.516469478607178 2023-01-23 05:19:16.036536: step: 2444/1545, loss: 1.097916603088379 2023-01-23 05:19:16.991477: step: 2446/1545, loss: 2.484973430633545 2023-01-23 05:19:17.899490: step: 2448/1545, loss: 2.1670727729797363 2023-01-23 05:19:18.805559: step: 2450/1545, loss: 1.489668846130371 2023-01-23 05:19:19.653276: step: 2452/1545, loss: 1.6911418437957764 2023-01-23 05:19:20.542177: step: 2454/1545, loss: 1.4545787572860718 2023-01-23 05:19:21.388299: step: 2456/1545, loss: 4.15122652053833 2023-01-23 05:19:22.271003: step: 2458/1545, loss: 1.6783363819122314 2023-01-23 05:19:23.137167: step: 2460/1545, loss: 1.670593500137329 2023-01-23 05:19:24.022627: step: 2462/1545, loss: 2.1145505905151367 2023-01-23 05:19:24.881100: step: 2464/1545, loss: 0.862197995185852 2023-01-23 05:19:25.736678: step: 2466/1545, loss: 1.5632294416427612 2023-01-23 05:19:26.564035: step: 2468/1545, loss: 1.089728832244873 2023-01-23 05:19:27.412355: step: 2470/1545, loss: 1.9467787742614746 2023-01-23 05:19:28.270860: step: 2472/1545, loss: 7.084536075592041 2023-01-23 05:19:29.184739: step: 2474/1545, loss: 1.6434332132339478 2023-01-23 05:19:30.049758: step: 2476/1545, loss: 1.517723798751831 2023-01-23 05:19:30.918532: step: 2478/1545, loss: 0.9476736187934875 2023-01-23 05:19:31.828876: step: 2480/1545, loss: 1.2602044343948364 2023-01-23 05:19:32.686247: step: 2482/1545, loss: 1.1119095087051392 2023-01-23 05:19:33.556369: step: 2484/1545, loss: 1.8255077600479126 2023-01-23 05:19:34.437896: step: 2486/1545, loss: 1.9505256414413452 2023-01-23 05:19:35.361581: step: 2488/1545, loss: 5.614938735961914 2023-01-23 05:19:36.226882: step: 2490/1545, loss: 1.4026011228561401 2023-01-23 05:19:37.066703: step: 2492/1545, loss: 0.9476630091667175 2023-01-23 05:19:37.905147: step: 2494/1545, loss: 1.4799566268920898 2023-01-23 05:19:38.780764: step: 2496/1545, loss: 3.196387767791748 2023-01-23 05:19:39.660538: step: 2498/1545, loss: 4.88433313369751 2023-01-23 05:19:40.512505: step: 2500/1545, loss: 1.9769740104675293 2023-01-23 05:19:41.352804: step: 2502/1545, loss: 1.7141042947769165 2023-01-23 05:19:42.197973: step: 2504/1545, loss: 1.2597382068634033 2023-01-23 05:19:43.064016: step: 2506/1545, loss: 0.7328996062278748 2023-01-23 05:19:44.008018: step: 2508/1545, loss: 1.9077163934707642 2023-01-23 05:19:44.867524: step: 2510/1545, loss: 3.6281487941741943 2023-01-23 05:19:45.699886: step: 2512/1545, loss: 1.9675098657608032 2023-01-23 05:19:46.575177: step: 2514/1545, loss: 2.1201419830322266 2023-01-23 05:19:47.429090: step: 2516/1545, loss: 1.2052583694458008 2023-01-23 05:19:48.268608: step: 2518/1545, loss: 7.846577167510986 2023-01-23 05:19:49.226710: step: 2520/1545, loss: 3.996574878692627 2023-01-23 05:19:50.188886: step: 2522/1545, loss: 1.0190508365631104 2023-01-23 05:19:51.073851: step: 2524/1545, loss: 1.5820658206939697 2023-01-23 05:19:51.948209: step: 2526/1545, loss: 1.0567787885665894 2023-01-23 05:19:52.798184: step: 2528/1545, loss: 3.7086331844329834 2023-01-23 05:19:53.686781: step: 2530/1545, loss: 1.4339029788970947 2023-01-23 05:19:54.651444: step: 2532/1545, loss: 1.4392271041870117 2023-01-23 05:19:55.543039: step: 2534/1545, loss: 1.9274346828460693 2023-01-23 05:19:56.399268: step: 2536/1545, loss: 0.7614643573760986 2023-01-23 05:19:57.341538: step: 2538/1545, loss: 1.2965139150619507 2023-01-23 05:19:58.200473: step: 2540/1545, loss: 4.173358917236328 2023-01-23 05:19:59.094923: step: 2542/1545, loss: 3.0352513790130615 2023-01-23 05:19:59.941967: step: 2544/1545, loss: 1.010894775390625 2023-01-23 05:20:00.874634: step: 2546/1545, loss: 1.279410481452942 2023-01-23 05:20:01.762026: step: 2548/1545, loss: 1.0320559740066528 2023-01-23 05:20:02.685652: step: 2550/1545, loss: 1.8890053033828735 2023-01-23 05:20:03.545566: step: 2552/1545, loss: 1.2343813180923462 2023-01-23 05:20:04.382031: step: 2554/1545, loss: 1.7631666660308838 2023-01-23 05:20:05.227132: step: 2556/1545, loss: 0.9120847582817078 2023-01-23 05:20:06.098501: step: 2558/1545, loss: 1.3611832857131958 2023-01-23 05:20:06.972711: step: 2560/1545, loss: 2.2730937004089355 2023-01-23 05:20:07.858978: step: 2562/1545, loss: 2.5813636779785156 2023-01-23 05:20:08.730910: step: 2564/1545, loss: 3.9136242866516113 2023-01-23 05:20:09.619864: step: 2566/1545, loss: 1.1835250854492188 2023-01-23 05:20:10.489850: step: 2568/1545, loss: 4.011836051940918 2023-01-23 05:20:11.389341: step: 2570/1545, loss: 5.456521511077881 2023-01-23 05:20:12.241165: step: 2572/1545, loss: 1.4538335800170898 2023-01-23 05:20:13.154391: step: 2574/1545, loss: 2.166358709335327 2023-01-23 05:20:14.029986: step: 2576/1545, loss: 1.3956454992294312 2023-01-23 05:20:14.873059: step: 2578/1545, loss: 0.7215080261230469 2023-01-23 05:20:15.716257: step: 2580/1545, loss: 2.2398297786712646 2023-01-23 05:20:16.584417: step: 2582/1545, loss: 0.9616599082946777 2023-01-23 05:20:17.414118: step: 2584/1545, loss: 3.362844228744507 2023-01-23 05:20:18.249578: step: 2586/1545, loss: 1.6273002624511719 2023-01-23 05:20:19.117351: step: 2588/1545, loss: 3.468496561050415 2023-01-23 05:20:20.026923: step: 2590/1545, loss: 1.0527898073196411 2023-01-23 05:20:20.856781: step: 2592/1545, loss: 1.3330715894699097 2023-01-23 05:20:21.712073: step: 2594/1545, loss: 1.0803817510604858 2023-01-23 05:20:22.550246: step: 2596/1545, loss: 1.0772103071212769 2023-01-23 05:20:23.405362: step: 2598/1545, loss: 1.4868544340133667 2023-01-23 05:20:24.277974: step: 2600/1545, loss: 1.739072322845459 2023-01-23 05:20:25.161487: step: 2602/1545, loss: 1.193223476409912 2023-01-23 05:20:26.011543: step: 2604/1545, loss: 0.8762859106063843 2023-01-23 05:20:26.871973: step: 2606/1545, loss: 1.092985987663269 2023-01-23 05:20:27.721891: step: 2608/1545, loss: 1.22055184841156 2023-01-23 05:20:28.657019: step: 2610/1545, loss: 2.472175359725952 2023-01-23 05:20:29.540493: step: 2612/1545, loss: 2.5064971446990967 2023-01-23 05:20:30.474216: step: 2614/1545, loss: 2.6740493774414062 2023-01-23 05:20:31.358945: step: 2616/1545, loss: 1.1543190479278564 2023-01-23 05:20:32.220319: step: 2618/1545, loss: 1.1942894458770752 2023-01-23 05:20:33.061446: step: 2620/1545, loss: 1.3442572355270386 2023-01-23 05:20:33.914502: step: 2622/1545, loss: 1.8586320877075195 2023-01-23 05:20:34.822806: step: 2624/1545, loss: 1.8199496269226074 2023-01-23 05:20:35.741007: step: 2626/1545, loss: 1.8039506673812866 2023-01-23 05:20:36.689801: step: 2628/1545, loss: 1.1494570970535278 2023-01-23 05:20:37.607831: step: 2630/1545, loss: 1.1091281175613403 2023-01-23 05:20:38.574856: step: 2632/1545, loss: 2.7304790019989014 2023-01-23 05:20:39.591990: step: 2634/1545, loss: 3.395490884780884 2023-01-23 05:20:40.464467: step: 2636/1545, loss: 1.2205398082733154 2023-01-23 05:20:41.374178: step: 2638/1545, loss: 1.3457889556884766 2023-01-23 05:20:42.208715: step: 2640/1545, loss: 1.2195886373519897 2023-01-23 05:20:43.107400: step: 2642/1545, loss: 0.914300799369812 2023-01-23 05:20:43.971605: step: 2644/1545, loss: 2.79484486579895 2023-01-23 05:20:44.843391: step: 2646/1545, loss: 3.4610681533813477 2023-01-23 05:20:45.714382: step: 2648/1545, loss: 1.826912760734558 2023-01-23 05:20:46.575149: step: 2650/1545, loss: 1.222765564918518 2023-01-23 05:20:47.459432: step: 2652/1545, loss: 1.2826348543167114 2023-01-23 05:20:48.316677: step: 2654/1545, loss: 1.271023154258728 2023-01-23 05:20:49.156267: step: 2656/1545, loss: 8.260614395141602 2023-01-23 05:20:50.036800: step: 2658/1545, loss: 2.0140433311462402 2023-01-23 05:20:50.928932: step: 2660/1545, loss: 1.7491449117660522 2023-01-23 05:20:51.855777: step: 2662/1545, loss: 1.719430923461914 2023-01-23 05:20:52.804648: step: 2664/1545, loss: 2.3867690563201904 2023-01-23 05:20:53.669399: step: 2666/1545, loss: 1.1679004430770874 2023-01-23 05:20:54.578521: step: 2668/1545, loss: 7.702174186706543 2023-01-23 05:20:55.424279: step: 2670/1545, loss: 1.3836058378219604 2023-01-23 05:20:56.291654: step: 2672/1545, loss: 1.2073830366134644 2023-01-23 05:20:57.150598: step: 2674/1545, loss: 0.8913516998291016 2023-01-23 05:20:58.040410: step: 2676/1545, loss: 1.193953514099121 2023-01-23 05:20:58.916565: step: 2678/1545, loss: 2.5836246013641357 2023-01-23 05:20:59.787356: step: 2680/1545, loss: 0.819246768951416 2023-01-23 05:21:00.713385: step: 2682/1545, loss: 1.431616187095642 2023-01-23 05:21:01.577324: step: 2684/1545, loss: 1.4640178680419922 2023-01-23 05:21:02.398211: step: 2686/1545, loss: 1.7198041677474976 2023-01-23 05:21:03.231770: step: 2688/1545, loss: 1.6548899412155151 2023-01-23 05:21:04.199770: step: 2690/1545, loss: 0.5225217342376709 2023-01-23 05:21:05.025872: step: 2692/1545, loss: 1.0517640113830566 2023-01-23 05:21:05.899255: step: 2694/1545, loss: 1.2209131717681885 2023-01-23 05:21:06.750143: step: 2696/1545, loss: 1.2814704179763794 2023-01-23 05:21:07.625897: step: 2698/1545, loss: 3.4031903743743896 2023-01-23 05:21:08.535385: step: 2700/1545, loss: 2.3939754962921143 2023-01-23 05:21:09.403014: step: 2702/1545, loss: 0.9928281307220459 2023-01-23 05:21:10.251773: step: 2704/1545, loss: 1.7286756038665771 2023-01-23 05:21:11.118787: step: 2706/1545, loss: 1.6823146343231201 2023-01-23 05:21:12.052681: step: 2708/1545, loss: 2.577000141143799 2023-01-23 05:21:12.935581: step: 2710/1545, loss: 1.5025615692138672 2023-01-23 05:21:13.818872: step: 2712/1545, loss: 2.6551432609558105 2023-01-23 05:21:14.673808: step: 2714/1545, loss: 1.3570477962493896 2023-01-23 05:21:15.526801: step: 2716/1545, loss: 0.9901993274688721 2023-01-23 05:21:16.373301: step: 2718/1545, loss: 1.0220930576324463 2023-01-23 05:21:17.241189: step: 2720/1545, loss: 10.597166061401367 2023-01-23 05:21:18.188378: step: 2722/1545, loss: 2.159482955932617 2023-01-23 05:21:19.055369: step: 2724/1545, loss: 1.3152494430541992 2023-01-23 05:21:20.041979: step: 2726/1545, loss: 0.9503380656242371 2023-01-23 05:21:20.962876: step: 2728/1545, loss: 3.152024507522583 2023-01-23 05:21:21.863595: step: 2730/1545, loss: 1.191519021987915 2023-01-23 05:21:22.726341: step: 2732/1545, loss: 1.190651774406433 2023-01-23 05:21:23.613072: step: 2734/1545, loss: 0.82206130027771 2023-01-23 05:21:24.469281: step: 2736/1545, loss: 7.478773593902588 2023-01-23 05:21:25.322921: step: 2738/1545, loss: 1.4464324712753296 2023-01-23 05:21:26.202630: step: 2740/1545, loss: 3.4285919666290283 2023-01-23 05:21:27.077398: step: 2742/1545, loss: 0.71102374792099 2023-01-23 05:21:27.964347: step: 2744/1545, loss: 1.2081763744354248 2023-01-23 05:21:28.840818: step: 2746/1545, loss: 1.1601189374923706 2023-01-23 05:21:29.693792: step: 2748/1545, loss: 0.9583237767219543 2023-01-23 05:21:30.573365: step: 2750/1545, loss: 1.1563303470611572 2023-01-23 05:21:31.486930: step: 2752/1545, loss: 1.7395957708358765 2023-01-23 05:21:32.352760: step: 2754/1545, loss: 1.3428981304168701 2023-01-23 05:21:33.259563: step: 2756/1545, loss: 0.747988760471344 2023-01-23 05:21:34.149228: step: 2758/1545, loss: 2.207848072052002 2023-01-23 05:21:35.050449: step: 2760/1545, loss: 1.0199624300003052 2023-01-23 05:21:35.904155: step: 2762/1545, loss: 0.9105365872383118 2023-01-23 05:21:36.752866: step: 2764/1545, loss: 1.8820013999938965 2023-01-23 05:21:37.649250: step: 2766/1545, loss: 1.1034071445465088 2023-01-23 05:21:38.515057: step: 2768/1545, loss: 3.474959135055542 2023-01-23 05:21:39.380008: step: 2770/1545, loss: 1.4917272329330444 2023-01-23 05:21:40.271245: step: 2772/1545, loss: 1.8148597478866577 2023-01-23 05:21:41.162784: step: 2774/1545, loss: 0.8439175486564636 2023-01-23 05:21:42.022903: step: 2776/1545, loss: 1.086692214012146 2023-01-23 05:21:42.896604: step: 2778/1545, loss: 2.9358649253845215 2023-01-23 05:21:43.785047: step: 2780/1545, loss: 0.9264121651649475 2023-01-23 05:21:44.766464: step: 2782/1545, loss: 2.783630609512329 2023-01-23 05:21:45.686400: step: 2784/1545, loss: 1.3086086511611938 2023-01-23 05:21:46.577164: step: 2786/1545, loss: 1.505124568939209 2023-01-23 05:21:47.403536: step: 2788/1545, loss: 1.8214255571365356 2023-01-23 05:21:48.268487: step: 2790/1545, loss: 1.232495665550232 2023-01-23 05:21:49.112711: step: 2792/1545, loss: 1.5222806930541992 2023-01-23 05:21:49.965855: step: 2794/1545, loss: 3.616741180419922 2023-01-23 05:21:50.795067: step: 2796/1545, loss: 1.0754101276397705 2023-01-23 05:21:51.665621: step: 2798/1545, loss: 7.398376941680908 2023-01-23 05:21:52.556656: step: 2800/1545, loss: 1.3450648784637451 2023-01-23 05:21:53.480405: step: 2802/1545, loss: 1.8275490999221802 2023-01-23 05:21:54.316758: step: 2804/1545, loss: 0.6638216972351074 2023-01-23 05:21:55.184319: step: 2806/1545, loss: 0.5587237477302551 2023-01-23 05:21:56.098495: step: 2808/1545, loss: 4.342129707336426 2023-01-23 05:21:56.957189: step: 2810/1545, loss: 1.8132494688034058 2023-01-23 05:21:57.827458: step: 2812/1545, loss: 1.3102636337280273 2023-01-23 05:21:58.685529: step: 2814/1545, loss: 1.5246909856796265 2023-01-23 05:21:59.591652: step: 2816/1545, loss: 1.8754112720489502 2023-01-23 05:22:00.483065: step: 2818/1545, loss: 1.5976600646972656 2023-01-23 05:22:01.366699: step: 2820/1545, loss: 1.1031379699707031 2023-01-23 05:22:02.242643: step: 2822/1545, loss: 1.1922705173492432 2023-01-23 05:22:03.090227: step: 2824/1545, loss: 2.5580506324768066 2023-01-23 05:22:03.945216: step: 2826/1545, loss: 1.2609156370162964 2023-01-23 05:22:04.790211: step: 2828/1545, loss: 1.2926205396652222 2023-01-23 05:22:05.648055: step: 2830/1545, loss: 1.6271849870681763 2023-01-23 05:22:06.474939: step: 2832/1545, loss: 2.834946393966675 2023-01-23 05:22:07.316205: step: 2834/1545, loss: 3.5413153171539307 2023-01-23 05:22:08.249089: step: 2836/1545, loss: 5.216129779815674 2023-01-23 05:22:09.125778: step: 2838/1545, loss: 0.8447067737579346 2023-01-23 05:22:09.987019: step: 2840/1545, loss: 2.568739414215088 2023-01-23 05:22:10.833354: step: 2842/1545, loss: 1.7463748455047607 2023-01-23 05:22:11.711433: step: 2844/1545, loss: 1.7506885528564453 2023-01-23 05:22:12.645481: step: 2846/1545, loss: 1.2356586456298828 2023-01-23 05:22:13.510486: step: 2848/1545, loss: 1.2300059795379639 2023-01-23 05:22:14.415200: step: 2850/1545, loss: 1.29292893409729 2023-01-23 05:22:15.267111: step: 2852/1545, loss: 1.4889025688171387 2023-01-23 05:22:16.125423: step: 2854/1545, loss: 1.121024489402771 2023-01-23 05:22:16.990785: step: 2856/1545, loss: 0.6223651766777039 2023-01-23 05:22:17.884172: step: 2858/1545, loss: 3.927253484725952 2023-01-23 05:22:18.733851: step: 2860/1545, loss: 2.260533094406128 2023-01-23 05:22:19.641820: step: 2862/1545, loss: 1.9116898775100708 2023-01-23 05:22:20.503652: step: 2864/1545, loss: 1.4242138862609863 2023-01-23 05:22:21.406681: step: 2866/1545, loss: 1.1196317672729492 2023-01-23 05:22:22.370291: step: 2868/1545, loss: 2.727001905441284 2023-01-23 05:22:23.238493: step: 2870/1545, loss: 7.667150020599365 2023-01-23 05:22:24.103838: step: 2872/1545, loss: 1.1956809759140015 2023-01-23 05:22:24.963193: step: 2874/1545, loss: 0.7681881189346313 2023-01-23 05:22:25.889461: step: 2876/1545, loss: 2.615532636642456 2023-01-23 05:22:26.758662: step: 2878/1545, loss: 0.8371472954750061 2023-01-23 05:22:27.661769: step: 2880/1545, loss: 1.1168218851089478 2023-01-23 05:22:28.562781: step: 2882/1545, loss: 7.522594451904297 2023-01-23 05:22:29.431396: step: 2884/1545, loss: 1.306318759918213 2023-01-23 05:22:30.276290: step: 2886/1545, loss: 2.6996772289276123 2023-01-23 05:22:31.191978: step: 2888/1545, loss: 1.6192930936813354 2023-01-23 05:22:32.040677: step: 2890/1545, loss: 1.4236875772476196 2023-01-23 05:22:32.932271: step: 2892/1545, loss: 1.1636251211166382 2023-01-23 05:22:33.785111: step: 2894/1545, loss: 4.116802215576172 2023-01-23 05:22:34.627063: step: 2896/1545, loss: 1.4084910154342651 2023-01-23 05:22:35.481270: step: 2898/1545, loss: 1.9635658264160156 2023-01-23 05:22:36.350562: step: 2900/1545, loss: 2.0665881633758545 2023-01-23 05:22:37.225461: step: 2902/1545, loss: 1.8286789655685425 2023-01-23 05:22:38.083298: step: 2904/1545, loss: 1.4712110757827759 2023-01-23 05:22:38.939439: step: 2906/1545, loss: 1.8484511375427246 2023-01-23 05:22:39.809245: step: 2908/1545, loss: 1.508066177368164 2023-01-23 05:22:40.691411: step: 2910/1545, loss: 1.1586557626724243 2023-01-23 05:22:41.596256: step: 2912/1545, loss: 3.3669626712799072 2023-01-23 05:22:42.588751: step: 2914/1545, loss: 4.361322402954102 2023-01-23 05:22:43.438405: step: 2916/1545, loss: 2.161329746246338 2023-01-23 05:22:44.343462: step: 2918/1545, loss: 3.0484166145324707 2023-01-23 05:22:45.251270: step: 2920/1545, loss: 4.280872821807861 2023-01-23 05:22:46.089680: step: 2922/1545, loss: 1.0318965911865234 2023-01-23 05:22:46.954087: step: 2924/1545, loss: 0.9563688635826111 2023-01-23 05:22:47.871511: step: 2926/1545, loss: 0.7571932673454285 2023-01-23 05:22:48.705311: step: 2928/1545, loss: 1.5976483821868896 2023-01-23 05:22:49.603719: step: 2930/1545, loss: 3.146852731704712 2023-01-23 05:22:50.465953: step: 2932/1545, loss: 1.320544958114624 2023-01-23 05:22:51.324250: step: 2934/1545, loss: 1.5703444480895996 2023-01-23 05:22:52.212864: step: 2936/1545, loss: 1.3700532913208008 2023-01-23 05:22:53.060326: step: 2938/1545, loss: 3.7048542499542236 2023-01-23 05:22:53.943111: step: 2940/1545, loss: 0.972433865070343 2023-01-23 05:22:54.802214: step: 2942/1545, loss: 1.4157766103744507 2023-01-23 05:22:55.706305: step: 2944/1545, loss: 3.5249829292297363 2023-01-23 05:22:56.545439: step: 2946/1545, loss: 0.7291365265846252 2023-01-23 05:22:57.377024: step: 2948/1545, loss: 1.8563876152038574 2023-01-23 05:22:58.272537: step: 2950/1545, loss: 4.8249831199646 2023-01-23 05:22:59.135316: step: 2952/1545, loss: 1.4026515483856201 2023-01-23 05:23:00.032441: step: 2954/1545, loss: 2.0395257472991943 2023-01-23 05:23:00.893831: step: 2956/1545, loss: 1.5908901691436768 2023-01-23 05:23:01.747979: step: 2958/1545, loss: 7.121215343475342 2023-01-23 05:23:02.620141: step: 2960/1545, loss: 0.9850191473960876 2023-01-23 05:23:03.497433: step: 2962/1545, loss: 1.3731414079666138 2023-01-23 05:23:04.364094: step: 2964/1545, loss: 0.8791061043739319 2023-01-23 05:23:05.251288: step: 2966/1545, loss: 0.9495904445648193 2023-01-23 05:23:06.090770: step: 2968/1545, loss: 1.5556734800338745 2023-01-23 05:23:06.965124: step: 2970/1545, loss: 1.3228837251663208 2023-01-23 05:23:07.866711: step: 2972/1545, loss: 2.06101131439209 2023-01-23 05:23:08.728739: step: 2974/1545, loss: 2.3934407234191895 2023-01-23 05:23:09.626410: step: 2976/1545, loss: 1.5663211345672607 2023-01-23 05:23:10.495392: step: 2978/1545, loss: 1.1779651641845703 2023-01-23 05:23:11.399577: step: 2980/1545, loss: 1.5773345232009888 2023-01-23 05:23:12.288141: step: 2982/1545, loss: 2.7450928688049316 2023-01-23 05:23:13.136833: step: 2984/1545, loss: 2.29542875289917 2023-01-23 05:23:13.991510: step: 2986/1545, loss: 1.8650050163269043 2023-01-23 05:23:14.862296: step: 2988/1545, loss: 1.8337079286575317 2023-01-23 05:23:15.714548: step: 2990/1545, loss: 2.1105844974517822 2023-01-23 05:23:16.636122: step: 2992/1545, loss: 2.415182113647461 2023-01-23 05:23:17.510847: step: 2994/1545, loss: 0.9943368434906006 2023-01-23 05:23:18.369859: step: 2996/1545, loss: 1.831270456314087 2023-01-23 05:23:19.289929: step: 2998/1545, loss: 2.820903778076172 2023-01-23 05:23:20.222168: step: 3000/1545, loss: 1.674666404724121 2023-01-23 05:23:21.142987: step: 3002/1545, loss: 3.7482171058654785 2023-01-23 05:23:22.010593: step: 3004/1545, loss: 3.0172736644744873 2023-01-23 05:23:22.926768: step: 3006/1545, loss: 1.3050488233566284 2023-01-23 05:23:23.829925: step: 3008/1545, loss: 2.342358112335205 2023-01-23 05:23:24.664563: step: 3010/1545, loss: 1.0257315635681152 2023-01-23 05:23:25.537979: step: 3012/1545, loss: 1.6215518712997437 2023-01-23 05:23:26.414602: step: 3014/1545, loss: 10.214521408081055 2023-01-23 05:23:27.296109: step: 3016/1545, loss: 1.5703461170196533 2023-01-23 05:23:28.185312: step: 3018/1545, loss: 1.0941040515899658 2023-01-23 05:23:29.063452: step: 3020/1545, loss: 2.114464044570923 2023-01-23 05:23:29.923326: step: 3022/1545, loss: 1.628883719444275 2023-01-23 05:23:30.822446: step: 3024/1545, loss: 2.068950891494751 2023-01-23 05:23:31.734211: step: 3026/1545, loss: 0.9152653217315674 2023-01-23 05:23:32.631390: step: 3028/1545, loss: 1.0489153861999512 2023-01-23 05:23:33.497915: step: 3030/1545, loss: 1.350223183631897 2023-01-23 05:23:34.361310: step: 3032/1545, loss: 1.8058953285217285 2023-01-23 05:23:35.254931: step: 3034/1545, loss: 2.1991732120513916 2023-01-23 05:23:36.143121: step: 3036/1545, loss: 0.7616283297538757 2023-01-23 05:23:37.006688: step: 3038/1545, loss: 2.262812376022339 2023-01-23 05:23:37.856881: step: 3040/1545, loss: 3.1072497367858887 2023-01-23 05:23:38.730529: step: 3042/1545, loss: 3.7739622592926025 2023-01-23 05:23:39.624685: step: 3044/1545, loss: 5.001954078674316 2023-01-23 05:23:40.465899: step: 3046/1545, loss: 1.5993824005126953 2023-01-23 05:23:41.415868: step: 3048/1545, loss: 1.6292915344238281 2023-01-23 05:23:42.283843: step: 3050/1545, loss: 1.6342434883117676 2023-01-23 05:23:43.180940: step: 3052/1545, loss: 1.2391469478607178 2023-01-23 05:23:44.069299: step: 3054/1545, loss: 3.3136091232299805 2023-01-23 05:23:44.936482: step: 3056/1545, loss: 1.3176499605178833 2023-01-23 05:23:45.775431: step: 3058/1545, loss: 4.1605224609375 2023-01-23 05:23:46.658480: step: 3060/1545, loss: 1.898827314376831 2023-01-23 05:23:47.509501: step: 3062/1545, loss: 1.134132981300354 2023-01-23 05:23:48.398537: step: 3064/1545, loss: 3.9663596153259277 2023-01-23 05:23:49.330206: step: 3066/1545, loss: 1.2929874658584595 2023-01-23 05:23:50.212480: step: 3068/1545, loss: 1.2219265699386597 2023-01-23 05:23:51.069123: step: 3070/1545, loss: 1.182862639427185 2023-01-23 05:23:51.933112: step: 3072/1545, loss: 0.9621493220329285 2023-01-23 05:23:52.810972: step: 3074/1545, loss: 0.6681761145591736 2023-01-23 05:23:53.751207: step: 3076/1545, loss: 2.281313419342041 2023-01-23 05:23:54.575195: step: 3078/1545, loss: 1.0682315826416016 2023-01-23 05:23:55.425108: step: 3080/1545, loss: 1.1999261379241943 2023-01-23 05:23:56.304064: step: 3082/1545, loss: 11.065885543823242 2023-01-23 05:23:57.158174: step: 3084/1545, loss: 3.242558717727661 2023-01-23 05:23:58.040363: step: 3086/1545, loss: 1.4680583477020264 2023-01-23 05:23:58.936030: step: 3088/1545, loss: 3.7859914302825928 2023-01-23 05:23:59.844651: step: 3090/1545, loss: 3.6111247539520264 ================================================== Loss: 3.441 -------------------- Dev Chinese: {'event': {'p': 0.5910577971646674, 'r': 0.7217043941411452, 'f1': 0.6498800959232615}, 'argument': {'p': 0.5394602050331777, 'r': 0.5487473193413837, 'f1': 0.5440641325714943}, 'combined': 0.35357645066396876, 'epoch': 0} Test Chinese: {'event': {'p': 0.628068303094984, 'r': 0.7525575447570333, 'f1': 0.6847004072134962}, 'argument': {'p': 0.5481112704378934, 'r': 0.5596042631462748, 'f1': 0.5537981445888243}, 'combined': 0.37918581511404664, 'epoch': 0} Dev Korean: {'event': {'p': 0.5929978118161926, 'r': 0.7217043941411452, 'f1': 0.6510510510510511}, 'argument': {'p': 0.5387353965925397, 'r': 0.5399496762242283, 'f1': 0.5393418529489291}, 'combined': 0.35113908023822177, 'epoch': 0} Test Korean: {'event': {'p': 0.6137566137566137, 'r': 0.7416879795396419, 'f1': 0.6716850028951941}, 'argument': {'p': 0.5403725277710205, 'r': 0.5546145844617005, 'f1': 0.5474009357665343}, 'combined': 0.3676809991251765, 'epoch': 0} Dev Russian: {'event': {'p': 0.5590551181102362, 'r': 0.7563249001331558, 'f1': 0.6428975664968875}, 'argument': {'p': 0.5366216502105567, 'r': 0.551602497997394, 'f1': 0.5440089584908998}, 'combined': 0.34974203556630573, 'epoch': 0} Test Russian: {'event': {'p': 0.6103637269556552, 'r': 0.7832480818414322, 'f1': 0.6860823298795855}, 'argument': {'p': 0.5456215226774778, 'r': 0.5625827909854293, 'f1': 0.5539723591853573}, 'combined': 0.3800706468787805, 'epoch': 0} Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.5105152208584702, 'r': 0.4852004165183808, 'f1': 0.4975360203281702}, 'combined': 0.3392291047692069, 'epoch': 0} Korean: {'event': {'p': 0.6666666666666666, 'r': 0.5396825396825397, 'f1': 0.5964912280701754}, 'argument': {'p': 0.4049995892895167, 'r': 0.20797276206758963, 'f1': 0.27482114987502915}, 'combined': 0.16392840518861387, 'epoch': 0} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.3675100588780262, 'r': 0.4200114958606013, 'f1': 0.39201072946989457}, 'combined': 0.21833508983133368, 'epoch': 0} New best chinese model... New best korean model... New best russian model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5910577971646674, 'r': 0.7217043941411452, 'f1': 0.6498800959232615}, 'argument': {'p': 0.5394602050331777, 'r': 0.5487473193413837, 'f1': 0.5440641325714943}, 'combined': 0.35357645066396876, 'epoch': 0} Test for Chinese: {'event': {'p': 0.628068303094984, 'r': 0.7525575447570333, 'f1': 0.6847004072134962}, 'argument': {'p': 0.5481112704378934, 'r': 0.5596042631462748, 'f1': 0.5537981445888243}, 'combined': 0.37918581511404664, 'epoch': 0} Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.5105152208584702, 'r': 0.4852004165183808, 'f1': 0.4975360203281702}, 'combined': 0.3392291047692069, 'epoch': 0} -------------------- Dev for Korean: {'event': {'p': 0.5929978118161926, 'r': 0.7217043941411452, 'f1': 0.6510510510510511}, 'argument': {'p': 0.5387353965925397, 'r': 0.5399496762242283, 'f1': 0.5393418529489291}, 'combined': 0.35113908023822177, 'epoch': 0} Test for Korean: {'event': {'p': 0.6137566137566137, 'r': 0.7416879795396419, 'f1': 0.6716850028951941}, 'argument': {'p': 0.5403725277710205, 'r': 0.5546145844617005, 'f1': 0.5474009357665343}, 'combined': 0.3676809991251765, 'epoch': 0} Korean: {'event': {'p': 0.6666666666666666, 'r': 0.5396825396825397, 'f1': 0.5964912280701754}, 'argument': {'p': 0.4049995892895167, 'r': 0.20797276206758963, 'f1': 0.27482114987502915}, 'combined': 0.16392840518861387, 'epoch': 0} -------------------- Dev for Russian: {'event': {'p': 0.5590551181102362, 'r': 0.7563249001331558, 'f1': 0.6428975664968875}, 'argument': {'p': 0.5366216502105567, 'r': 0.551602497997394, 'f1': 0.5440089584908998}, 'combined': 0.34974203556630573, 'epoch': 0} Test for Russian: {'event': {'p': 0.6103637269556552, 'r': 0.7832480818414322, 'f1': 0.6860823298795855}, 'argument': {'p': 0.5456215226774778, 'r': 0.5625827909854293, 'f1': 0.5539723591853573}, 'combined': 0.3800706468787805, 'epoch': 0} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.3675100588780262, 'r': 0.4200114958606013, 'f1': 0.39201072946989457}, 'combined': 0.21833508983133368, 'epoch': 0} ****************************** Epoch: 1 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 05:29:26.126777: step: 2/1545, loss: 3.1149637699127197 2023-01-23 05:29:27.064078: step: 4/1545, loss: 1.7320308685302734 2023-01-23 05:29:27.957405: step: 6/1545, loss: 0.8943949937820435 2023-01-23 05:29:28.873819: step: 8/1545, loss: 1.117972731590271 2023-01-23 05:29:29.734042: step: 10/1545, loss: 1.2720890045166016 2023-01-23 05:29:30.602140: step: 12/1545, loss: 1.3797763586044312 2023-01-23 05:29:31.485887: step: 14/1545, loss: 1.7006750106811523 2023-01-23 05:29:32.343703: step: 16/1545, loss: 1.5175455808639526 2023-01-23 05:29:33.245372: step: 18/1545, loss: 1.7327064275741577 2023-01-23 05:29:34.144840: step: 20/1545, loss: 4.7188639640808105 2023-01-23 05:29:34.994901: step: 22/1545, loss: 1.7453161478042603 2023-01-23 05:29:35.971980: step: 24/1545, loss: 6.965583324432373 2023-01-23 05:29:36.843858: step: 26/1545, loss: 2.0404233932495117 2023-01-23 05:29:37.674061: step: 28/1545, loss: 1.2748608589172363 2023-01-23 05:29:38.590917: step: 30/1545, loss: 4.044244766235352 2023-01-23 05:29:39.524767: step: 32/1545, loss: 5.289247989654541 2023-01-23 05:29:40.398673: step: 34/1545, loss: 0.8385306596755981 2023-01-23 05:29:41.308297: step: 36/1545, loss: 1.0760815143585205 2023-01-23 05:29:42.194286: step: 38/1545, loss: 3.97084641456604 2023-01-23 05:29:43.071876: step: 40/1545, loss: 1.273655652999878 2023-01-23 05:29:43.952249: step: 42/1545, loss: 2.1221776008605957 2023-01-23 05:29:44.817785: step: 44/1545, loss: 8.07535171508789 2023-01-23 05:29:45.707605: step: 46/1545, loss: 0.5910334587097168 2023-01-23 05:29:46.599603: step: 48/1545, loss: 2.2542617321014404 2023-01-23 05:29:47.499287: step: 50/1545, loss: 3.715953826904297 2023-01-23 05:29:48.395438: step: 52/1545, loss: 1.0395385026931763 2023-01-23 05:29:49.315230: step: 54/1545, loss: 0.7429625988006592 2023-01-23 05:29:50.240418: step: 56/1545, loss: 1.4140375852584839 2023-01-23 05:29:51.128770: step: 58/1545, loss: 3.8226583003997803 2023-01-23 05:29:51.959728: step: 60/1545, loss: 1.0467160940170288 2023-01-23 05:29:52.845468: step: 62/1545, loss: 1.352614402770996 2023-01-23 05:29:53.828129: step: 64/1545, loss: 1.0607935190200806 2023-01-23 05:29:54.692799: step: 66/1545, loss: 4.766565322875977 2023-01-23 05:29:55.543642: step: 68/1545, loss: 0.5647056102752686 2023-01-23 05:29:56.394530: step: 70/1545, loss: 1.2532206773757935 2023-01-23 05:29:57.299490: step: 72/1545, loss: 1.4183681011199951 2023-01-23 05:29:58.167539: step: 74/1545, loss: 0.8500452041625977 2023-01-23 05:29:59.052513: step: 76/1545, loss: 1.6066588163375854 2023-01-23 05:29:59.928949: step: 78/1545, loss: 1.1315561532974243 2023-01-23 05:30:00.851076: step: 80/1545, loss: 1.4948344230651855 2023-01-23 05:30:01.754370: step: 82/1545, loss: 1.2156715393066406 2023-01-23 05:30:02.637272: step: 84/1545, loss: 1.076902985572815 2023-01-23 05:30:03.533444: step: 86/1545, loss: 2.5330729484558105 2023-01-23 05:30:04.372925: step: 88/1545, loss: 0.7427834868431091 2023-01-23 05:30:05.247059: step: 90/1545, loss: 3.7109315395355225 2023-01-23 05:30:06.139852: step: 92/1545, loss: 2.2990784645080566 2023-01-23 05:30:07.016024: step: 94/1545, loss: 3.796483278274536 2023-01-23 05:30:07.830433: step: 96/1545, loss: 0.6436119079589844 2023-01-23 05:30:08.672749: step: 98/1545, loss: 1.2933443784713745 2023-01-23 05:30:09.590494: step: 100/1545, loss: 1.2998043298721313 2023-01-23 05:30:10.490250: step: 102/1545, loss: 1.2641373872756958 2023-01-23 05:30:11.385535: step: 104/1545, loss: 1.983137845993042 2023-01-23 05:30:12.252106: step: 106/1545, loss: 2.8068044185638428 2023-01-23 05:30:13.103072: step: 108/1545, loss: 3.3284599781036377 2023-01-23 05:30:14.037319: step: 110/1545, loss: 1.914648413658142 2023-01-23 05:30:14.963448: step: 112/1545, loss: 4.421858310699463 2023-01-23 05:30:15.846310: step: 114/1545, loss: 0.9269938468933105 2023-01-23 05:30:16.718694: step: 116/1545, loss: 0.6384387612342834 2023-01-23 05:30:17.673958: step: 118/1545, loss: 2.5349950790405273 2023-01-23 05:30:18.557942: step: 120/1545, loss: 1.7715201377868652 2023-01-23 05:30:19.462394: step: 122/1545, loss: 0.663686990737915 2023-01-23 05:30:20.369229: step: 124/1545, loss: 7.775847434997559 2023-01-23 05:30:21.271820: step: 126/1545, loss: 0.7395831346511841 2023-01-23 05:30:22.151236: step: 128/1545, loss: 8.516589164733887 2023-01-23 05:30:23.082088: step: 130/1545, loss: 1.810770034790039 2023-01-23 05:30:23.926880: step: 132/1545, loss: 3.5984041690826416 2023-01-23 05:30:24.820221: step: 134/1545, loss: 3.8822219371795654 2023-01-23 05:30:25.704945: step: 136/1545, loss: 1.233494758605957 2023-01-23 05:30:26.589428: step: 138/1545, loss: 5.04141902923584 2023-01-23 05:30:27.457535: step: 140/1545, loss: 1.4330365657806396 2023-01-23 05:30:28.311577: step: 142/1545, loss: 1.3825997114181519 2023-01-23 05:30:29.207739: step: 144/1545, loss: 2.089618682861328 2023-01-23 05:30:30.106231: step: 146/1545, loss: 1.4223817586898804 2023-01-23 05:30:30.986507: step: 148/1545, loss: 1.1394424438476562 2023-01-23 05:30:31.859960: step: 150/1545, loss: 0.9088478088378906 2023-01-23 05:30:32.682336: step: 152/1545, loss: 1.0602210760116577 2023-01-23 05:30:33.571558: step: 154/1545, loss: 1.2473163604736328 2023-01-23 05:30:34.508451: step: 156/1545, loss: 2.322974920272827 2023-01-23 05:30:35.353037: step: 158/1545, loss: 1.1346346139907837 2023-01-23 05:30:36.188535: step: 160/1545, loss: 4.736021995544434 2023-01-23 05:30:37.089285: step: 162/1545, loss: 1.3806772232055664 2023-01-23 05:30:38.012361: step: 164/1545, loss: 1.9775851964950562 2023-01-23 05:30:38.941510: step: 166/1545, loss: 0.8546457290649414 2023-01-23 05:30:39.818736: step: 168/1545, loss: 1.4450106620788574 2023-01-23 05:30:40.689436: step: 170/1545, loss: 0.6032669544219971 2023-01-23 05:30:41.578474: step: 172/1545, loss: 3.410093307495117 2023-01-23 05:30:42.472732: step: 174/1545, loss: 0.6118611097335815 2023-01-23 05:30:43.410598: step: 176/1545, loss: 1.8600441217422485 2023-01-23 05:30:44.345705: step: 178/1545, loss: 3.1007089614868164 2023-01-23 05:30:45.219282: step: 180/1545, loss: 1.5056114196777344 2023-01-23 05:30:46.098237: step: 182/1545, loss: 0.9278672933578491 2023-01-23 05:30:46.994737: step: 184/1545, loss: 1.563810110092163 2023-01-23 05:30:47.866460: step: 186/1545, loss: 7.168918609619141 2023-01-23 05:30:48.759993: step: 188/1545, loss: 1.5905081033706665 2023-01-23 05:30:49.653793: step: 190/1545, loss: 0.6169613003730774 2023-01-23 05:30:50.594619: step: 192/1545, loss: 1.4358128309249878 2023-01-23 05:30:51.471670: step: 194/1545, loss: 0.8298859000205994 2023-01-23 05:30:52.351866: step: 196/1545, loss: 1.1616034507751465 2023-01-23 05:30:53.192658: step: 198/1545, loss: 0.4312817454338074 2023-01-23 05:30:54.064926: step: 200/1545, loss: 2.290128469467163 2023-01-23 05:30:54.949883: step: 202/1545, loss: 1.3750919103622437 2023-01-23 05:30:55.825110: step: 204/1545, loss: 1.0226540565490723 2023-01-23 05:30:56.751199: step: 206/1545, loss: 0.9181981682777405 2023-01-23 05:30:57.634542: step: 208/1545, loss: 0.9593851566314697 2023-01-23 05:30:58.528438: step: 210/1545, loss: 1.5049530267715454 2023-01-23 05:30:59.407277: step: 212/1545, loss: 1.6348892450332642 2023-01-23 05:31:00.291430: step: 214/1545, loss: 3.6528868675231934 2023-01-23 05:31:01.152465: step: 216/1545, loss: 1.0767147541046143 2023-01-23 05:31:02.017590: step: 218/1545, loss: 7.770503997802734 2023-01-23 05:31:02.972909: step: 220/1545, loss: 1.9912670850753784 2023-01-23 05:31:03.919182: step: 222/1545, loss: 1.493067979812622 2023-01-23 05:31:04.864455: step: 224/1545, loss: 2.5152595043182373 2023-01-23 05:31:05.747620: step: 226/1545, loss: 0.860901951789856 2023-01-23 05:31:06.731482: step: 228/1545, loss: 1.5856627225875854 2023-01-23 05:31:07.615435: step: 230/1545, loss: 1.4050939083099365 2023-01-23 05:31:08.492125: step: 232/1545, loss: 0.8275127410888672 2023-01-23 05:31:09.384902: step: 234/1545, loss: 1.2081239223480225 2023-01-23 05:31:10.284056: step: 236/1545, loss: 1.1065117120742798 2023-01-23 05:31:11.169481: step: 238/1545, loss: 1.1934701204299927 2023-01-23 05:31:12.078302: step: 240/1545, loss: 3.982819080352783 2023-01-23 05:31:12.930861: step: 242/1545, loss: 1.4964430332183838 2023-01-23 05:31:13.811000: step: 244/1545, loss: 3.5231332778930664 2023-01-23 05:31:14.728806: step: 246/1545, loss: 0.7524357438087463 2023-01-23 05:31:15.682484: step: 248/1545, loss: 1.066490888595581 2023-01-23 05:31:16.590052: step: 250/1545, loss: 8.313496589660645 2023-01-23 05:31:17.461370: step: 252/1545, loss: 1.320859670639038 2023-01-23 05:31:18.355731: step: 254/1545, loss: 1.7040971517562866 2023-01-23 05:31:19.237524: step: 256/1545, loss: 1.7115968465805054 2023-01-23 05:31:20.132476: step: 258/1545, loss: 0.5520563721656799 2023-01-23 05:31:21.032769: step: 260/1545, loss: 1.4389346837997437 2023-01-23 05:31:21.920660: step: 262/1545, loss: 2.35910964012146 2023-01-23 05:31:22.809681: step: 264/1545, loss: 1.5101748704910278 2023-01-23 05:31:23.701723: step: 266/1545, loss: 3.3582112789154053 2023-01-23 05:31:24.617398: step: 268/1545, loss: 2.0751380920410156 2023-01-23 05:31:25.444762: step: 270/1545, loss: 0.8759374022483826 2023-01-23 05:31:26.324254: step: 272/1545, loss: 0.6482056379318237 2023-01-23 05:31:27.168561: step: 274/1545, loss: 3.2697913646698 2023-01-23 05:31:28.033343: step: 276/1545, loss: 4.262721538543701 2023-01-23 05:31:28.900770: step: 278/1545, loss: 0.6899072527885437 2023-01-23 05:31:29.796797: step: 280/1545, loss: 1.0466138124465942 2023-01-23 05:31:30.681092: step: 282/1545, loss: 0.5982242226600647 2023-01-23 05:31:31.559962: step: 284/1545, loss: 5.077452659606934 2023-01-23 05:31:32.530959: step: 286/1545, loss: 3.860179901123047 2023-01-23 05:31:33.374135: step: 288/1545, loss: 8.53872013092041 2023-01-23 05:31:34.211883: step: 290/1545, loss: 1.792335867881775 2023-01-23 05:31:35.070231: step: 292/1545, loss: 0.8502791523933411 2023-01-23 05:31:35.929965: step: 294/1545, loss: 1.1237050294876099 2023-01-23 05:31:36.786863: step: 296/1545, loss: 1.0926902294158936 2023-01-23 05:31:37.631555: step: 298/1545, loss: 1.3847259283065796 2023-01-23 05:31:38.507622: step: 300/1545, loss: 4.353172779083252 2023-01-23 05:31:39.397459: step: 302/1545, loss: 0.920001745223999 2023-01-23 05:31:40.342193: step: 304/1545, loss: 4.011536121368408 2023-01-23 05:31:41.253564: step: 306/1545, loss: 1.6530218124389648 2023-01-23 05:31:42.135563: step: 308/1545, loss: 1.6209728717803955 2023-01-23 05:31:43.013254: step: 310/1545, loss: 3.5501601696014404 2023-01-23 05:31:43.891340: step: 312/1545, loss: 0.8819898366928101 2023-01-23 05:31:44.747909: step: 314/1545, loss: 3.9047224521636963 2023-01-23 05:31:45.623835: step: 316/1545, loss: 1.3178718090057373 2023-01-23 05:31:46.489735: step: 318/1545, loss: 1.3045613765716553 2023-01-23 05:31:47.370386: step: 320/1545, loss: 1.748517632484436 2023-01-23 05:31:48.231575: step: 322/1545, loss: 2.0753986835479736 2023-01-23 05:31:49.070643: step: 324/1545, loss: 1.2652249336242676 2023-01-23 05:31:49.930834: step: 326/1545, loss: 1.793316125869751 2023-01-23 05:31:50.828374: step: 328/1545, loss: 1.1155472993850708 2023-01-23 05:31:51.704368: step: 330/1545, loss: 1.346253752708435 2023-01-23 05:31:52.728401: step: 332/1545, loss: 1.1706645488739014 2023-01-23 05:31:53.643733: step: 334/1545, loss: 2.4915733337402344 2023-01-23 05:31:54.522103: step: 336/1545, loss: 0.9793811440467834 2023-01-23 05:31:55.373058: step: 338/1545, loss: 1.1044228076934814 2023-01-23 05:31:56.253887: step: 340/1545, loss: 3.8294260501861572 2023-01-23 05:31:57.149978: step: 342/1545, loss: 1.641862392425537 2023-01-23 05:31:58.029211: step: 344/1545, loss: 0.9190602898597717 2023-01-23 05:31:58.948512: step: 346/1545, loss: 0.5715243220329285 2023-01-23 05:31:59.794756: step: 348/1545, loss: 0.4954596757888794 2023-01-23 05:32:00.658461: step: 350/1545, loss: 1.1733665466308594 2023-01-23 05:32:01.608467: step: 352/1545, loss: 1.104498028755188 2023-01-23 05:32:02.477183: step: 354/1545, loss: 1.1995518207550049 2023-01-23 05:32:03.365650: step: 356/1545, loss: 1.0136491060256958 2023-01-23 05:32:04.272241: step: 358/1545, loss: 2.5000860691070557 2023-01-23 05:32:05.187671: step: 360/1545, loss: 2.6085731983184814 2023-01-23 05:32:06.097071: step: 362/1545, loss: 2.358351945877075 2023-01-23 05:32:07.011484: step: 364/1545, loss: 1.1147536039352417 2023-01-23 05:32:07.870548: step: 366/1545, loss: 1.0883617401123047 2023-01-23 05:32:08.804095: step: 368/1545, loss: 1.1526466608047485 2023-01-23 05:32:09.687843: step: 370/1545, loss: 3.942718744277954 2023-01-23 05:32:10.574741: step: 372/1545, loss: 1.3247538805007935 2023-01-23 05:32:11.481356: step: 374/1545, loss: 1.655619740486145 2023-01-23 05:32:12.348260: step: 376/1545, loss: 1.8399306535720825 2023-01-23 05:32:13.240521: step: 378/1545, loss: 1.4500304460525513 2023-01-23 05:32:14.159718: step: 380/1545, loss: 0.9812621474266052 2023-01-23 05:32:15.059598: step: 382/1545, loss: 1.8364465236663818 2023-01-23 05:32:15.989691: step: 384/1545, loss: 1.5177265405654907 2023-01-23 05:32:16.835866: step: 386/1545, loss: 3.3897106647491455 2023-01-23 05:32:17.812169: step: 388/1545, loss: 1.399997353553772 2023-01-23 05:32:18.737172: step: 390/1545, loss: 1.949103832244873 2023-01-23 05:32:19.633799: step: 392/1545, loss: 1.3855546712875366 2023-01-23 05:32:20.613052: step: 394/1545, loss: 1.7462393045425415 2023-01-23 05:32:21.543718: step: 396/1545, loss: 3.2914347648620605 2023-01-23 05:32:22.402372: step: 398/1545, loss: 1.5005215406417847 2023-01-23 05:32:23.308620: step: 400/1545, loss: 4.246308326721191 2023-01-23 05:32:24.196853: step: 402/1545, loss: 2.888611078262329 2023-01-23 05:32:25.059871: step: 404/1545, loss: 0.9678376317024231 2023-01-23 05:32:25.960891: step: 406/1545, loss: 1.202475666999817 2023-01-23 05:32:26.864243: step: 408/1545, loss: 0.893769383430481 2023-01-23 05:32:27.731907: step: 410/1545, loss: 4.361119747161865 2023-01-23 05:32:28.633187: step: 412/1545, loss: 0.9625327587127686 2023-01-23 05:32:29.489362: step: 414/1545, loss: 3.3063364028930664 2023-01-23 05:32:30.398633: step: 416/1545, loss: 1.4372526407241821 2023-01-23 05:32:31.259488: step: 418/1545, loss: 3.957134962081909 2023-01-23 05:32:32.179295: step: 420/1545, loss: 2.020512580871582 2023-01-23 05:32:33.061011: step: 422/1545, loss: 0.741587221622467 2023-01-23 05:32:33.984091: step: 424/1545, loss: 1.9861177206039429 2023-01-23 05:32:34.859685: step: 426/1545, loss: 8.113430976867676 2023-01-23 05:32:35.771272: step: 428/1545, loss: 1.5751196146011353 2023-01-23 05:32:36.679374: step: 430/1545, loss: 2.6524226665496826 2023-01-23 05:32:37.557094: step: 432/1545, loss: 1.375846266746521 2023-01-23 05:32:38.451085: step: 434/1545, loss: 1.4805865287780762 2023-01-23 05:32:39.348604: step: 436/1545, loss: 1.6022517681121826 2023-01-23 05:32:40.259885: step: 438/1545, loss: 1.762531042098999 2023-01-23 05:32:41.113477: step: 440/1545, loss: 1.4452934265136719 2023-01-23 05:32:42.019606: step: 442/1545, loss: 1.1455976963043213 2023-01-23 05:32:42.872264: step: 444/1545, loss: 1.1952786445617676 2023-01-23 05:32:43.830782: step: 446/1545, loss: 1.6515913009643555 2023-01-23 05:32:44.705201: step: 448/1545, loss: 0.8480638265609741 2023-01-23 05:32:45.585527: step: 450/1545, loss: 1.5569798946380615 2023-01-23 05:32:46.465537: step: 452/1545, loss: 0.7151567935943604 2023-01-23 05:32:47.357276: step: 454/1545, loss: 1.1732957363128662 2023-01-23 05:32:48.245851: step: 456/1545, loss: 0.785082995891571 2023-01-23 05:32:49.119049: step: 458/1545, loss: 1.3268318176269531 2023-01-23 05:32:50.014883: step: 460/1545, loss: 1.7248258590698242 2023-01-23 05:32:50.983641: step: 462/1545, loss: 0.9383922219276428 2023-01-23 05:32:51.864679: step: 464/1545, loss: 0.5797030925750732 2023-01-23 05:32:52.766669: step: 466/1545, loss: 1.7024192810058594 2023-01-23 05:32:53.695842: step: 468/1545, loss: 1.4694454669952393 2023-01-23 05:32:54.584729: step: 470/1545, loss: 6.617453575134277 2023-01-23 05:32:55.454182: step: 472/1545, loss: 1.086921215057373 2023-01-23 05:32:56.340174: step: 474/1545, loss: 0.6896027326583862 2023-01-23 05:32:57.224856: step: 476/1545, loss: 1.628387689590454 2023-01-23 05:32:58.073961: step: 478/1545, loss: 1.616514801979065 2023-01-23 05:32:58.967403: step: 480/1545, loss: 1.004554033279419 2023-01-23 05:32:59.847582: step: 482/1545, loss: 0.6622971892356873 2023-01-23 05:33:00.729454: step: 484/1545, loss: 1.0462268590927124 2023-01-23 05:33:01.594976: step: 486/1545, loss: 1.278900146484375 2023-01-23 05:33:02.510454: step: 488/1545, loss: 0.6964499950408936 2023-01-23 05:33:03.399896: step: 490/1545, loss: 1.077918291091919 2023-01-23 05:33:04.282817: step: 492/1545, loss: 0.9670190215110779 2023-01-23 05:33:05.266803: step: 494/1545, loss: 4.477618217468262 2023-01-23 05:33:06.116237: step: 496/1545, loss: 2.1073360443115234 2023-01-23 05:33:06.996406: step: 498/1545, loss: 1.219565749168396 2023-01-23 05:33:07.879439: step: 500/1545, loss: 0.9039798378944397 2023-01-23 05:33:08.756539: step: 502/1545, loss: 1.6337512731552124 2023-01-23 05:33:09.614824: step: 504/1545, loss: 2.449183940887451 2023-01-23 05:33:10.470096: step: 506/1545, loss: 0.6957292556762695 2023-01-23 05:33:11.412589: step: 508/1545, loss: 1.1898488998413086 2023-01-23 05:33:12.292394: step: 510/1545, loss: 2.02347993850708 2023-01-23 05:33:13.160617: step: 512/1545, loss: 6.986033916473389 2023-01-23 05:33:14.016995: step: 514/1545, loss: 1.2766001224517822 2023-01-23 05:33:14.862949: step: 516/1545, loss: 1.377442717552185 2023-01-23 05:33:15.742314: step: 518/1545, loss: 5.759607791900635 2023-01-23 05:33:16.596670: step: 520/1545, loss: 0.5361687541007996 2023-01-23 05:33:17.478319: step: 522/1545, loss: 0.9094308018684387 2023-01-23 05:33:18.325317: step: 524/1545, loss: 1.8261922597885132 2023-01-23 05:33:19.313645: step: 526/1545, loss: 0.8946618437767029 2023-01-23 05:33:20.181590: step: 528/1545, loss: 1.1033774614334106 2023-01-23 05:33:21.047424: step: 530/1545, loss: 3.3563613891601562 2023-01-23 05:33:21.945361: step: 532/1545, loss: 3.5782196521759033 2023-01-23 05:33:22.878068: step: 534/1545, loss: 1.340826153755188 2023-01-23 05:33:23.796141: step: 536/1545, loss: 1.4732747077941895 2023-01-23 05:33:24.713743: step: 538/1545, loss: 3.6224889755249023 2023-01-23 05:33:25.595494: step: 540/1545, loss: 0.770258903503418 2023-01-23 05:33:26.503832: step: 542/1545, loss: 3.80115008354187 2023-01-23 05:33:27.350385: step: 544/1545, loss: 1.232886791229248 2023-01-23 05:33:28.237639: step: 546/1545, loss: 0.8468860983848572 2023-01-23 05:33:29.083505: step: 548/1545, loss: 1.230950951576233 2023-01-23 05:33:30.051060: step: 550/1545, loss: 3.7873542308807373 2023-01-23 05:33:30.979960: step: 552/1545, loss: 3.83333158493042 2023-01-23 05:33:31.937343: step: 554/1545, loss: 1.2095646858215332 2023-01-23 05:33:32.812648: step: 556/1545, loss: 1.8694026470184326 2023-01-23 05:33:33.704491: step: 558/1545, loss: 0.7707173824310303 2023-01-23 05:33:34.605320: step: 560/1545, loss: 4.863715648651123 2023-01-23 05:33:35.479304: step: 562/1545, loss: 1.480851650238037 2023-01-23 05:33:36.298239: step: 564/1545, loss: 3.474525213241577 2023-01-23 05:33:37.235268: step: 566/1545, loss: 0.969619870185852 2023-01-23 05:33:38.143616: step: 568/1545, loss: 1.0252808332443237 2023-01-23 05:33:39.007904: step: 570/1545, loss: 1.4857057332992554 2023-01-23 05:33:39.869837: step: 572/1545, loss: 1.0652018785476685 2023-01-23 05:33:40.756537: step: 574/1545, loss: 0.7669819593429565 2023-01-23 05:33:41.658484: step: 576/1545, loss: 1.2522464990615845 2023-01-23 05:33:42.571199: step: 578/1545, loss: 1.7009519338607788 2023-01-23 05:33:43.417185: step: 580/1545, loss: 3.4894096851348877 2023-01-23 05:33:44.379595: step: 582/1545, loss: 0.2992636263370514 2023-01-23 05:33:45.309034: step: 584/1545, loss: 1.1203480958938599 2023-01-23 05:33:46.154508: step: 586/1545, loss: 0.8382143378257751 2023-01-23 05:33:47.007543: step: 588/1545, loss: 1.0715926885604858 2023-01-23 05:33:47.867758: step: 590/1545, loss: 1.5230427980422974 2023-01-23 05:33:48.757835: step: 592/1545, loss: 0.6399126052856445 2023-01-23 05:33:49.653720: step: 594/1545, loss: 1.0403348207473755 2023-01-23 05:33:50.554633: step: 596/1545, loss: 1.4812880754470825 2023-01-23 05:33:51.438073: step: 598/1545, loss: 0.7425628900527954 2023-01-23 05:33:52.299142: step: 600/1545, loss: 0.7208539247512817 2023-01-23 05:33:53.192304: step: 602/1545, loss: 1.2124645709991455 2023-01-23 05:33:54.090125: step: 604/1545, loss: 1.817689299583435 2023-01-23 05:33:54.975740: step: 606/1545, loss: 1.3680880069732666 2023-01-23 05:33:55.838580: step: 608/1545, loss: 1.3907992839813232 2023-01-23 05:33:56.730200: step: 610/1545, loss: 1.178178310394287 2023-01-23 05:33:57.635856: step: 612/1545, loss: 1.5005604028701782 2023-01-23 05:33:58.488223: step: 614/1545, loss: 0.7278531193733215 2023-01-23 05:33:59.344499: step: 616/1545, loss: 3.982694149017334 2023-01-23 05:34:00.236893: step: 618/1545, loss: 6.6513166427612305 2023-01-23 05:34:01.104290: step: 620/1545, loss: 1.0045313835144043 2023-01-23 05:34:02.000988: step: 622/1545, loss: 0.7749031782150269 2023-01-23 05:34:02.945304: step: 624/1545, loss: 1.391281008720398 2023-01-23 05:34:03.865576: step: 626/1545, loss: 1.4946420192718506 2023-01-23 05:34:04.784779: step: 628/1545, loss: 1.956882357597351 2023-01-23 05:34:05.705155: step: 630/1545, loss: 1.372261881828308 2023-01-23 05:34:06.608511: step: 632/1545, loss: 0.9925772547721863 2023-01-23 05:34:07.501628: step: 634/1545, loss: 2.4114818572998047 2023-01-23 05:34:08.385075: step: 636/1545, loss: 0.8360869288444519 2023-01-23 05:34:09.265338: step: 638/1545, loss: 0.6766372323036194 2023-01-23 05:34:10.105662: step: 640/1545, loss: 2.072549343109131 2023-01-23 05:34:10.980964: step: 642/1545, loss: 0.7976041436195374 2023-01-23 05:34:11.825837: step: 644/1545, loss: 0.9810271263122559 2023-01-23 05:34:12.686718: step: 646/1545, loss: 1.3042575120925903 2023-01-23 05:34:13.636903: step: 648/1545, loss: 2.8262343406677246 2023-01-23 05:34:14.540716: step: 650/1545, loss: 0.7829896807670593 2023-01-23 05:34:15.420207: step: 652/1545, loss: 3.261347532272339 2023-01-23 05:34:16.369594: step: 654/1545, loss: 0.7095248699188232 2023-01-23 05:34:17.248744: step: 656/1545, loss: 1.9255181550979614 2023-01-23 05:34:18.099924: step: 658/1545, loss: 3.0829546451568604 2023-01-23 05:34:18.977752: step: 660/1545, loss: 1.0717767477035522 2023-01-23 05:34:19.949011: step: 662/1545, loss: 1.0684776306152344 2023-01-23 05:34:20.835066: step: 664/1545, loss: 1.4710347652435303 2023-01-23 05:34:21.695039: step: 666/1545, loss: 1.528163194656372 2023-01-23 05:34:22.573400: step: 668/1545, loss: 3.331310749053955 2023-01-23 05:34:23.425624: step: 670/1545, loss: 4.143773078918457 2023-01-23 05:34:24.320797: step: 672/1545, loss: 1.202936053276062 2023-01-23 05:34:25.171127: step: 674/1545, loss: 0.850481390953064 2023-01-23 05:34:26.024243: step: 676/1545, loss: 1.6157399415969849 2023-01-23 05:34:26.881978: step: 678/1545, loss: 1.1426986455917358 2023-01-23 05:34:27.743738: step: 680/1545, loss: 0.6109277009963989 2023-01-23 05:34:28.637969: step: 682/1545, loss: 1.278777837753296 2023-01-23 05:34:29.509674: step: 684/1545, loss: 0.6271103024482727 2023-01-23 05:34:30.385139: step: 686/1545, loss: 1.6364405155181885 2023-01-23 05:34:31.241056: step: 688/1545, loss: 0.7653480768203735 2023-01-23 05:34:32.078406: step: 690/1545, loss: 3.1589770317077637 2023-01-23 05:34:32.969174: step: 692/1545, loss: 1.2934809923171997 2023-01-23 05:34:33.856893: step: 694/1545, loss: 1.0232040882110596 2023-01-23 05:34:34.725622: step: 696/1545, loss: 0.8193864822387695 2023-01-23 05:34:35.615080: step: 698/1545, loss: 0.7503810524940491 2023-01-23 05:34:36.470400: step: 700/1545, loss: 0.9124669432640076 2023-01-23 05:34:37.306247: step: 702/1545, loss: 1.7471086978912354 2023-01-23 05:34:38.181513: step: 704/1545, loss: 2.6428639888763428 2023-01-23 05:34:39.003866: step: 706/1545, loss: 6.982085227966309 2023-01-23 05:34:39.873048: step: 708/1545, loss: 1.4640263319015503 2023-01-23 05:34:40.793329: step: 710/1545, loss: 7.2796783447265625 2023-01-23 05:34:41.670032: step: 712/1545, loss: 1.4157423973083496 2023-01-23 05:34:42.496884: step: 714/1545, loss: 3.1072182655334473 2023-01-23 05:34:43.348246: step: 716/1545, loss: 0.8164094686508179 2023-01-23 05:34:44.179874: step: 718/1545, loss: 2.754389524459839 2023-01-23 05:34:45.003160: step: 720/1545, loss: 0.7124640345573425 2023-01-23 05:34:45.952537: step: 722/1545, loss: 1.3785977363586426 2023-01-23 05:34:46.829361: step: 724/1545, loss: 1.6720199584960938 2023-01-23 05:34:47.702858: step: 726/1545, loss: 2.165370225906372 2023-01-23 05:34:48.559231: step: 728/1545, loss: 0.6147910952568054 2023-01-23 05:34:49.419253: step: 730/1545, loss: 0.7622197270393372 2023-01-23 05:34:50.280769: step: 732/1545, loss: 9.431013107299805 2023-01-23 05:34:51.146045: step: 734/1545, loss: 0.7573798894882202 2023-01-23 05:34:52.016240: step: 736/1545, loss: 1.033991813659668 2023-01-23 05:34:52.916240: step: 738/1545, loss: 2.026813507080078 2023-01-23 05:34:53.789835: step: 740/1545, loss: 5.910475730895996 2023-01-23 05:34:54.643725: step: 742/1545, loss: 3.644850492477417 2023-01-23 05:34:55.511768: step: 744/1545, loss: 1.5904591083526611 2023-01-23 05:34:56.376573: step: 746/1545, loss: 0.980070948600769 2023-01-23 05:34:57.302719: step: 748/1545, loss: 1.3928828239440918 2023-01-23 05:34:58.180778: step: 750/1545, loss: 1.1660594940185547 2023-01-23 05:34:59.065037: step: 752/1545, loss: 4.307346820831299 2023-01-23 05:34:59.976287: step: 754/1545, loss: 0.5240815281867981 2023-01-23 05:35:00.866278: step: 756/1545, loss: 1.9850072860717773 2023-01-23 05:35:01.768673: step: 758/1545, loss: 0.7242934703826904 2023-01-23 05:35:02.643869: step: 760/1545, loss: 1.1964709758758545 2023-01-23 05:35:03.504555: step: 762/1545, loss: 1.0352967977523804 2023-01-23 05:35:04.386824: step: 764/1545, loss: 3.638815402984619 2023-01-23 05:35:05.274077: step: 766/1545, loss: 1.5057507753372192 2023-01-23 05:35:06.148917: step: 768/1545, loss: 1.4088711738586426 2023-01-23 05:35:07.015167: step: 770/1545, loss: 0.7216222882270813 2023-01-23 05:35:07.876931: step: 772/1545, loss: 1.1613751649856567 2023-01-23 05:35:08.788237: step: 774/1545, loss: 1.8108946084976196 2023-01-23 05:35:09.651254: step: 776/1545, loss: 1.7471765279769897 2023-01-23 05:35:10.513756: step: 778/1545, loss: 0.5433627963066101 2023-01-23 05:35:11.422280: step: 780/1545, loss: 3.266636610031128 2023-01-23 05:35:12.293313: step: 782/1545, loss: 1.083158254623413 2023-01-23 05:35:13.159518: step: 784/1545, loss: 0.8562330603599548 2023-01-23 05:35:14.062818: step: 786/1545, loss: 1.3219093084335327 2023-01-23 05:35:14.943908: step: 788/1545, loss: 3.798337459564209 2023-01-23 05:35:15.801922: step: 790/1545, loss: 0.49667632579803467 2023-01-23 05:35:16.696541: step: 792/1545, loss: 1.8034651279449463 2023-01-23 05:35:17.591435: step: 794/1545, loss: 8.306628227233887 2023-01-23 05:35:18.457008: step: 796/1545, loss: 2.5766830444335938 2023-01-23 05:35:19.363523: step: 798/1545, loss: 1.3983347415924072 2023-01-23 05:35:20.347702: step: 800/1545, loss: 1.2574572563171387 2023-01-23 05:35:21.220545: step: 802/1545, loss: 3.180687427520752 2023-01-23 05:35:22.120201: step: 804/1545, loss: 1.4173468351364136 2023-01-23 05:35:23.012495: step: 806/1545, loss: 1.635726809501648 2023-01-23 05:35:23.926300: step: 808/1545, loss: 3.4149279594421387 2023-01-23 05:35:24.803416: step: 810/1545, loss: 0.9884877800941467 2023-01-23 05:35:25.676417: step: 812/1545, loss: 1.5593111515045166 2023-01-23 05:35:26.542043: step: 814/1545, loss: 0.8538004159927368 2023-01-23 05:35:27.417545: step: 816/1545, loss: 0.8184060454368591 2023-01-23 05:35:28.339025: step: 818/1545, loss: 1.358904242515564 2023-01-23 05:35:29.200732: step: 820/1545, loss: 0.8503298163414001 2023-01-23 05:35:30.079193: step: 822/1545, loss: 1.9869784116744995 2023-01-23 05:35:30.933565: step: 824/1545, loss: 0.7031875848770142 2023-01-23 05:35:31.865672: step: 826/1545, loss: 3.0103092193603516 2023-01-23 05:35:32.715782: step: 828/1545, loss: 1.026231288909912 2023-01-23 05:35:33.573592: step: 830/1545, loss: 1.2719480991363525 2023-01-23 05:35:34.486281: step: 832/1545, loss: 1.0052250623703003 2023-01-23 05:35:35.370816: step: 834/1545, loss: 1.5178555250167847 2023-01-23 05:35:36.263973: step: 836/1545, loss: 1.2871990203857422 2023-01-23 05:35:37.103136: step: 838/1545, loss: 3.58811092376709 2023-01-23 05:35:37.966936: step: 840/1545, loss: 0.7259933948516846 2023-01-23 05:35:38.831158: step: 842/1545, loss: 3.109919309616089 2023-01-23 05:35:39.737217: step: 844/1545, loss: 1.1481788158416748 2023-01-23 05:35:40.640810: step: 846/1545, loss: 2.204615592956543 2023-01-23 05:35:41.506693: step: 848/1545, loss: 2.9678585529327393 2023-01-23 05:35:42.449194: step: 850/1545, loss: 0.9455195069313049 2023-01-23 05:35:43.303737: step: 852/1545, loss: 3.7151107788085938 2023-01-23 05:35:44.178385: step: 854/1545, loss: 4.202964782714844 2023-01-23 05:35:45.107093: step: 856/1545, loss: 1.9385486841201782 2023-01-23 05:35:45.981162: step: 858/1545, loss: 1.6572805643081665 2023-01-23 05:35:46.860208: step: 860/1545, loss: 1.3890407085418701 2023-01-23 05:35:47.765751: step: 862/1545, loss: 3.6068115234375 2023-01-23 05:35:48.616232: step: 864/1545, loss: 1.4281920194625854 2023-01-23 05:35:49.491384: step: 866/1545, loss: 1.097206711769104 2023-01-23 05:35:50.371651: step: 868/1545, loss: 0.5883658528327942 2023-01-23 05:35:51.254922: step: 870/1545, loss: 1.0186034440994263 2023-01-23 05:35:52.136597: step: 872/1545, loss: 1.5317673683166504 2023-01-23 05:35:53.014845: step: 874/1545, loss: 0.7102224230766296 2023-01-23 05:35:53.928682: step: 876/1545, loss: 1.0101511478424072 2023-01-23 05:35:54.780425: step: 878/1545, loss: 2.691016435623169 2023-01-23 05:35:55.656913: step: 880/1545, loss: 3.383038282394409 2023-01-23 05:35:56.539856: step: 882/1545, loss: 0.6369414925575256 2023-01-23 05:35:57.396882: step: 884/1545, loss: 0.5810001492500305 2023-01-23 05:35:58.285628: step: 886/1545, loss: 3.7644166946411133 2023-01-23 05:35:59.183527: step: 888/1545, loss: 2.0815577507019043 2023-01-23 05:36:00.074120: step: 890/1545, loss: 1.005037784576416 2023-01-23 05:36:00.945813: step: 892/1545, loss: 1.741721749305725 2023-01-23 05:36:01.860105: step: 894/1545, loss: 0.9804162383079529 2023-01-23 05:36:02.719277: step: 896/1545, loss: 1.4968507289886475 2023-01-23 05:36:03.577982: step: 898/1545, loss: 2.956366777420044 2023-01-23 05:36:04.478830: step: 900/1545, loss: 1.8533687591552734 2023-01-23 05:36:05.326955: step: 902/1545, loss: 1.5015404224395752 2023-01-23 05:36:06.308869: step: 904/1545, loss: 1.4467320442199707 2023-01-23 05:36:07.200994: step: 906/1545, loss: 0.7424469590187073 2023-01-23 05:36:08.097661: step: 908/1545, loss: 1.7326500415802002 2023-01-23 05:36:08.975249: step: 910/1545, loss: 1.333466649055481 2023-01-23 05:36:09.908646: step: 912/1545, loss: 1.2021812200546265 2023-01-23 05:36:10.776964: step: 914/1545, loss: 1.1606861352920532 2023-01-23 05:36:11.696630: step: 916/1545, loss: 0.9075968861579895 2023-01-23 05:36:12.552497: step: 918/1545, loss: 1.013990879058838 2023-01-23 05:36:13.413402: step: 920/1545, loss: 0.8735312819480896 2023-01-23 05:36:14.275236: step: 922/1545, loss: 2.8121705055236816 2023-01-23 05:36:15.118951: step: 924/1545, loss: 1.2086094617843628 2023-01-23 05:36:16.073353: step: 926/1545, loss: 1.2973973751068115 2023-01-23 05:36:16.981210: step: 928/1545, loss: 3.691910982131958 2023-01-23 05:36:17.875659: step: 930/1545, loss: 3.6209945678710938 2023-01-23 05:36:18.720519: step: 932/1545, loss: 1.7574084997177124 2023-01-23 05:36:19.627573: step: 934/1545, loss: 0.45943930745124817 2023-01-23 05:36:20.527118: step: 936/1545, loss: 9.910658836364746 2023-01-23 05:36:21.442486: step: 938/1545, loss: 1.1879154443740845 2023-01-23 05:36:22.369155: step: 940/1545, loss: 0.750794529914856 2023-01-23 05:36:23.196458: step: 942/1545, loss: 1.0908969640731812 2023-01-23 05:36:24.069989: step: 944/1545, loss: 1.7498127222061157 2023-01-23 05:36:24.985913: step: 946/1545, loss: 1.5632946491241455 2023-01-23 05:36:25.872407: step: 948/1545, loss: 1.9589897394180298 2023-01-23 05:36:26.747695: step: 950/1545, loss: 1.9298969507217407 2023-01-23 05:36:27.635509: step: 952/1545, loss: 0.9361266493797302 2023-01-23 05:36:28.554939: step: 954/1545, loss: 1.0186399221420288 2023-01-23 05:36:29.437853: step: 956/1545, loss: 0.768650233745575 2023-01-23 05:36:30.335150: step: 958/1545, loss: 0.3837401568889618 2023-01-23 05:36:31.230876: step: 960/1545, loss: 0.8340388536453247 2023-01-23 05:36:32.113236: step: 962/1545, loss: 1.0081559419631958 2023-01-23 05:36:32.983192: step: 964/1545, loss: 3.8550572395324707 2023-01-23 05:36:33.881483: step: 966/1545, loss: 0.7695547342300415 2023-01-23 05:36:34.761536: step: 968/1545, loss: 1.2793341875076294 2023-01-23 05:36:35.624192: step: 970/1545, loss: 2.7714931964874268 2023-01-23 05:36:36.460279: step: 972/1545, loss: 1.0507723093032837 2023-01-23 05:36:37.292833: step: 974/1545, loss: 0.6560794711112976 2023-01-23 05:36:38.174349: step: 976/1545, loss: 1.071568489074707 2023-01-23 05:36:39.063559: step: 978/1545, loss: 0.503253698348999 2023-01-23 05:36:39.983049: step: 980/1545, loss: 3.843177080154419 2023-01-23 05:36:40.903725: step: 982/1545, loss: 0.8991328477859497 2023-01-23 05:36:41.751756: step: 984/1545, loss: 3.0021536350250244 2023-01-23 05:36:42.652611: step: 986/1545, loss: 3.3269195556640625 2023-01-23 05:36:43.533146: step: 988/1545, loss: 2.470134735107422 2023-01-23 05:36:44.422422: step: 990/1545, loss: 1.548207402229309 2023-01-23 05:36:45.386157: step: 992/1545, loss: 1.2178394794464111 2023-01-23 05:36:46.255730: step: 994/1545, loss: 0.8880836367607117 2023-01-23 05:36:47.132213: step: 996/1545, loss: 1.4340357780456543 2023-01-23 05:36:48.018754: step: 998/1545, loss: 0.7494058609008789 2023-01-23 05:36:48.962393: step: 1000/1545, loss: 1.7306925058364868 2023-01-23 05:36:49.871696: step: 1002/1545, loss: 1.2902263402938843 2023-01-23 05:36:50.843015: step: 1004/1545, loss: 1.2925958633422852 2023-01-23 05:36:51.697904: step: 1006/1545, loss: 0.3146628737449646 2023-01-23 05:36:52.577719: step: 1008/1545, loss: 0.9332473874092102 2023-01-23 05:36:53.410275: step: 1010/1545, loss: 7.120151996612549 2023-01-23 05:36:54.232073: step: 1012/1545, loss: 0.8483479619026184 2023-01-23 05:36:55.071197: step: 1014/1545, loss: 1.1508328914642334 2023-01-23 05:36:55.936272: step: 1016/1545, loss: 0.7569577097892761 2023-01-23 05:36:56.858280: step: 1018/1545, loss: 0.5986477136611938 2023-01-23 05:36:57.705595: step: 1020/1545, loss: 2.9610064029693604 2023-01-23 05:36:58.589326: step: 1022/1545, loss: 1.0864042043685913 2023-01-23 05:36:59.452242: step: 1024/1545, loss: 0.8846886157989502 2023-01-23 05:37:00.313288: step: 1026/1545, loss: 1.3466236591339111 2023-01-23 05:37:01.225937: step: 1028/1545, loss: 0.9563863277435303 2023-01-23 05:37:02.137242: step: 1030/1545, loss: 0.8226268291473389 2023-01-23 05:37:03.040037: step: 1032/1545, loss: 1.230491280555725 2023-01-23 05:37:03.903667: step: 1034/1545, loss: 0.8373197913169861 2023-01-23 05:37:04.786228: step: 1036/1545, loss: 1.098616361618042 2023-01-23 05:37:05.632455: step: 1038/1545, loss: 1.1676874160766602 2023-01-23 05:37:06.489271: step: 1040/1545, loss: 2.4899230003356934 2023-01-23 05:37:07.376783: step: 1042/1545, loss: 0.949245810508728 2023-01-23 05:37:08.262349: step: 1044/1545, loss: 1.455654263496399 2023-01-23 05:37:09.143040: step: 1046/1545, loss: 2.1348729133605957 2023-01-23 05:37:10.000530: step: 1048/1545, loss: 0.6151314377784729 2023-01-23 05:37:10.878607: step: 1050/1545, loss: 0.8523764610290527 2023-01-23 05:37:11.802258: step: 1052/1545, loss: 0.5552821159362793 2023-01-23 05:37:12.666547: step: 1054/1545, loss: 2.097508430480957 2023-01-23 05:37:13.610772: step: 1056/1545, loss: 0.7880107760429382 2023-01-23 05:37:14.498014: step: 1058/1545, loss: 0.5608936548233032 2023-01-23 05:37:15.364360: step: 1060/1545, loss: 0.8188149333000183 2023-01-23 05:37:16.304496: step: 1062/1545, loss: 1.817088007926941 2023-01-23 05:37:17.174053: step: 1064/1545, loss: 0.9682031273841858 2023-01-23 05:37:18.023116: step: 1066/1545, loss: 2.413987159729004 2023-01-23 05:37:18.967445: step: 1068/1545, loss: 0.7459801435470581 2023-01-23 05:37:19.921322: step: 1070/1545, loss: 1.8808485269546509 2023-01-23 05:37:20.770167: step: 1072/1545, loss: 0.7791970372200012 2023-01-23 05:37:21.677250: step: 1074/1545, loss: 3.0458714962005615 2023-01-23 05:37:22.541645: step: 1076/1545, loss: 3.972907066345215 2023-01-23 05:37:23.414712: step: 1078/1545, loss: 1.380556344985962 2023-01-23 05:37:24.284288: step: 1080/1545, loss: 3.3509724140167236 2023-01-23 05:37:25.120956: step: 1082/1545, loss: 1.1238079071044922 2023-01-23 05:37:26.003853: step: 1084/1545, loss: 2.222622871398926 2023-01-23 05:37:26.840868: step: 1086/1545, loss: 2.6837236881256104 2023-01-23 05:37:27.743561: step: 1088/1545, loss: 1.280910849571228 2023-01-23 05:37:28.698376: step: 1090/1545, loss: 1.1599032878875732 2023-01-23 05:37:29.656477: step: 1092/1545, loss: 2.7312393188476562 2023-01-23 05:37:30.550894: step: 1094/1545, loss: 2.689195156097412 2023-01-23 05:37:31.441907: step: 1096/1545, loss: 1.863477110862732 2023-01-23 05:37:32.359241: step: 1098/1545, loss: 1.0507612228393555 2023-01-23 05:37:33.277952: step: 1100/1545, loss: 0.9257872104644775 2023-01-23 05:37:34.169101: step: 1102/1545, loss: 1.0243830680847168 2023-01-23 05:37:35.032997: step: 1104/1545, loss: 0.8530887961387634 2023-01-23 05:37:35.893894: step: 1106/1545, loss: 3.386803388595581 2023-01-23 05:37:36.797252: step: 1108/1545, loss: 1.9588115215301514 2023-01-23 05:37:37.637635: step: 1110/1545, loss: 1.3577837944030762 2023-01-23 05:37:38.476830: step: 1112/1545, loss: 0.8112106323242188 2023-01-23 05:37:39.362254: step: 1114/1545, loss: 0.7659320831298828 2023-01-23 05:37:40.217712: step: 1116/1545, loss: 0.9056885242462158 2023-01-23 05:37:41.085781: step: 1118/1545, loss: 0.6231094598770142 2023-01-23 05:37:41.924515: step: 1120/1545, loss: 0.8855637907981873 2023-01-23 05:37:42.810263: step: 1122/1545, loss: 1.0140244960784912 2023-01-23 05:37:43.721033: step: 1124/1545, loss: 1.4283472299575806 2023-01-23 05:37:44.573950: step: 1126/1545, loss: 1.1973915100097656 2023-01-23 05:37:45.457418: step: 1128/1545, loss: 1.573052167892456 2023-01-23 05:37:46.354349: step: 1130/1545, loss: 3.525057315826416 2023-01-23 05:37:47.229632: step: 1132/1545, loss: 0.7666445970535278 2023-01-23 05:37:48.109359: step: 1134/1545, loss: 0.746798574924469 2023-01-23 05:37:49.004605: step: 1136/1545, loss: 1.2081239223480225 2023-01-23 05:37:49.874038: step: 1138/1545, loss: 0.6749717593193054 2023-01-23 05:37:50.751383: step: 1140/1545, loss: 1.7606574296951294 2023-01-23 05:37:51.597507: step: 1142/1545, loss: 1.4360655546188354 2023-01-23 05:37:52.467544: step: 1144/1545, loss: 1.7879891395568848 2023-01-23 05:37:53.335083: step: 1146/1545, loss: 0.765755295753479 2023-01-23 05:37:54.198417: step: 1148/1545, loss: 0.6701222658157349 2023-01-23 05:37:55.061281: step: 1150/1545, loss: 1.1523092985153198 2023-01-23 05:37:55.953341: step: 1152/1545, loss: 1.1768289804458618 2023-01-23 05:37:56.830797: step: 1154/1545, loss: 1.2347862720489502 2023-01-23 05:37:57.688858: step: 1156/1545, loss: 0.9690998196601868 2023-01-23 05:37:58.633010: step: 1158/1545, loss: 1.3469960689544678 2023-01-23 05:37:59.482561: step: 1160/1545, loss: 2.6837451457977295 2023-01-23 05:38:00.364599: step: 1162/1545, loss: 0.7937602996826172 2023-01-23 05:38:01.235270: step: 1164/1545, loss: 1.1121444702148438 2023-01-23 05:38:02.112577: step: 1166/1545, loss: 1.9055010080337524 2023-01-23 05:38:02.992688: step: 1168/1545, loss: 1.4222416877746582 2023-01-23 05:38:03.832557: step: 1170/1545, loss: 0.4413107931613922 2023-01-23 05:38:04.697971: step: 1172/1545, loss: 2.990800380706787 2023-01-23 05:38:05.563747: step: 1174/1545, loss: 6.616722583770752 2023-01-23 05:38:06.427617: step: 1176/1545, loss: 3.075772762298584 2023-01-23 05:38:07.294740: step: 1178/1545, loss: 7.398430347442627 2023-01-23 05:38:08.174029: step: 1180/1545, loss: 3.79689359664917 2023-01-23 05:38:09.040958: step: 1182/1545, loss: 0.5808138847351074 2023-01-23 05:38:09.903402: step: 1184/1545, loss: 1.096144199371338 2023-01-23 05:38:10.785803: step: 1186/1545, loss: 0.8943195343017578 2023-01-23 05:38:11.759947: step: 1188/1545, loss: 1.2458385229110718 2023-01-23 05:38:12.658085: step: 1190/1545, loss: 0.6493878960609436 2023-01-23 05:38:13.539464: step: 1192/1545, loss: 1.1074244976043701 2023-01-23 05:38:14.395780: step: 1194/1545, loss: 0.7633231282234192 2023-01-23 05:38:15.297167: step: 1196/1545, loss: 1.9187136888504028 2023-01-23 05:38:16.159162: step: 1198/1545, loss: 0.9664453864097595 2023-01-23 05:38:17.026246: step: 1200/1545, loss: 1.1789610385894775 2023-01-23 05:38:17.867729: step: 1202/1545, loss: 1.6674119234085083 2023-01-23 05:38:18.759242: step: 1204/1545, loss: 0.8828078508377075 2023-01-23 05:38:19.643900: step: 1206/1545, loss: 1.0838381052017212 2023-01-23 05:38:20.530622: step: 1208/1545, loss: 3.353961706161499 2023-01-23 05:38:21.451817: step: 1210/1545, loss: 1.8276023864746094 2023-01-23 05:38:22.291497: step: 1212/1545, loss: 0.8606019020080566 2023-01-23 05:38:23.170568: step: 1214/1545, loss: 7.258559703826904 2023-01-23 05:38:24.010738: step: 1216/1545, loss: 4.191100120544434 2023-01-23 05:38:24.923500: step: 1218/1545, loss: 1.0899981260299683 2023-01-23 05:38:25.766946: step: 1220/1545, loss: 1.1577118635177612 2023-01-23 05:38:26.621086: step: 1222/1545, loss: 3.0229203701019287 2023-01-23 05:38:27.468640: step: 1224/1545, loss: 0.8965882658958435 2023-01-23 05:38:28.383635: step: 1226/1545, loss: 0.7958230376243591 2023-01-23 05:38:29.272733: step: 1228/1545, loss: 0.8604629039764404 2023-01-23 05:38:30.166592: step: 1230/1545, loss: 0.9013358950614929 2023-01-23 05:38:31.022298: step: 1232/1545, loss: 0.8276753425598145 2023-01-23 05:38:31.926715: step: 1234/1545, loss: 1.896380066871643 2023-01-23 05:38:32.801700: step: 1236/1545, loss: 0.753909707069397 2023-01-23 05:38:33.716621: step: 1238/1545, loss: 3.3929593563079834 2023-01-23 05:38:34.591015: step: 1240/1545, loss: 0.6256499886512756 2023-01-23 05:38:35.473062: step: 1242/1545, loss: 1.9504655599594116 2023-01-23 05:38:36.316693: step: 1244/1545, loss: 0.8569677472114563 2023-01-23 05:38:37.153451: step: 1246/1545, loss: 3.4724457263946533 2023-01-23 05:38:38.058385: step: 1248/1545, loss: 0.8358120322227478 2023-01-23 05:38:38.925087: step: 1250/1545, loss: 1.1686047315597534 2023-01-23 05:38:39.763417: step: 1252/1545, loss: 3.620021104812622 2023-01-23 05:38:40.657410: step: 1254/1545, loss: 2.9588067531585693 2023-01-23 05:38:41.537201: step: 1256/1545, loss: 0.8494884967803955 2023-01-23 05:38:42.392486: step: 1258/1545, loss: 2.1949970722198486 2023-01-23 05:38:43.250649: step: 1260/1545, loss: 0.675258994102478 2023-01-23 05:38:44.138567: step: 1262/1545, loss: 0.6273306012153625 2023-01-23 05:38:45.054080: step: 1264/1545, loss: 1.5808085203170776 2023-01-23 05:38:45.901385: step: 1266/1545, loss: 1.1569249629974365 2023-01-23 05:38:46.796454: step: 1268/1545, loss: 2.821479558944702 2023-01-23 05:38:47.688596: step: 1270/1545, loss: 7.271817684173584 2023-01-23 05:38:48.570226: step: 1272/1545, loss: 0.6942298412322998 2023-01-23 05:38:49.445297: step: 1274/1545, loss: 1.0973604917526245 2023-01-23 05:38:50.346374: step: 1276/1545, loss: 1.0661934614181519 2023-01-23 05:38:51.251340: step: 1278/1545, loss: 1.1562162637710571 2023-01-23 05:38:52.147300: step: 1280/1545, loss: 1.7141172885894775 2023-01-23 05:38:53.017227: step: 1282/1545, loss: 2.499239206314087 2023-01-23 05:38:53.896245: step: 1284/1545, loss: 0.647437334060669 2023-01-23 05:38:54.796597: step: 1286/1545, loss: 1.7471671104431152 2023-01-23 05:38:55.697149: step: 1288/1545, loss: 2.10333251953125 2023-01-23 05:38:56.550940: step: 1290/1545, loss: 0.6685611009597778 2023-01-23 05:38:57.433240: step: 1292/1545, loss: 2.021540641784668 2023-01-23 05:38:58.399316: step: 1294/1545, loss: 1.1060421466827393 2023-01-23 05:38:59.266796: step: 1296/1545, loss: 1.1599395275115967 2023-01-23 05:39:00.134490: step: 1298/1545, loss: 0.9170559048652649 2023-01-23 05:39:01.046309: step: 1300/1545, loss: 3.8903145790100098 2023-01-23 05:39:01.969417: step: 1302/1545, loss: 1.9383987188339233 2023-01-23 05:39:02.892169: step: 1304/1545, loss: 0.5016692280769348 2023-01-23 05:39:03.765586: step: 1306/1545, loss: 1.0227108001708984 2023-01-23 05:39:04.693516: step: 1308/1545, loss: 1.4878679513931274 2023-01-23 05:39:05.563676: step: 1310/1545, loss: 1.0370315313339233 2023-01-23 05:39:06.494536: step: 1312/1545, loss: 0.8640087246894836 2023-01-23 05:39:07.376104: step: 1314/1545, loss: 1.2195765972137451 2023-01-23 05:39:08.279974: step: 1316/1545, loss: 1.6640589237213135 2023-01-23 05:39:09.159011: step: 1318/1545, loss: 1.1120496988296509 2023-01-23 05:39:10.084984: step: 1320/1545, loss: 2.1370677947998047 2023-01-23 05:39:10.938796: step: 1322/1545, loss: 0.7531442046165466 2023-01-23 05:39:11.807726: step: 1324/1545, loss: 0.7747008204460144 2023-01-23 05:39:12.698493: step: 1326/1545, loss: 1.7889184951782227 2023-01-23 05:39:13.574861: step: 1328/1545, loss: 2.7341341972351074 2023-01-23 05:39:14.475377: step: 1330/1545, loss: 1.5700116157531738 2023-01-23 05:39:15.341292: step: 1332/1545, loss: 1.5711560249328613 2023-01-23 05:39:16.208467: step: 1334/1545, loss: 0.9232937097549438 2023-01-23 05:39:17.081413: step: 1336/1545, loss: 2.1845743656158447 2023-01-23 05:39:17.968157: step: 1338/1545, loss: 3.451554298400879 2023-01-23 05:39:18.979587: step: 1340/1545, loss: 0.7958398461341858 2023-01-23 05:39:19.905044: step: 1342/1545, loss: 0.4816122353076935 2023-01-23 05:39:20.792194: step: 1344/1545, loss: 1.1312971115112305 2023-01-23 05:39:21.673373: step: 1346/1545, loss: 1.3127983808517456 2023-01-23 05:39:22.520303: step: 1348/1545, loss: 1.135742425918579 2023-01-23 05:39:23.402354: step: 1350/1545, loss: 1.2481894493103027 2023-01-23 05:39:24.260763: step: 1352/1545, loss: 0.6225075125694275 2023-01-23 05:39:25.170194: step: 1354/1545, loss: 3.1551313400268555 2023-01-23 05:39:26.028352: step: 1356/1545, loss: 1.1107836961746216 2023-01-23 05:39:26.889658: step: 1358/1545, loss: 0.4943709373474121 2023-01-23 05:39:27.755328: step: 1360/1545, loss: 1.288980484008789 2023-01-23 05:39:28.626736: step: 1362/1545, loss: 6.070662975311279 2023-01-23 05:39:29.515093: step: 1364/1545, loss: 0.558456301689148 2023-01-23 05:39:30.405958: step: 1366/1545, loss: 1.9383509159088135 2023-01-23 05:39:31.260295: step: 1368/1545, loss: 0.852009117603302 2023-01-23 05:39:32.133914: step: 1370/1545, loss: 8.302397727966309 2023-01-23 05:39:33.048559: step: 1372/1545, loss: 0.9121009707450867 2023-01-23 05:39:33.904847: step: 1374/1545, loss: 1.432145118713379 2023-01-23 05:39:34.794910: step: 1376/1545, loss: 2.1914100646972656 2023-01-23 05:39:35.677319: step: 1378/1545, loss: 2.3614771366119385 2023-01-23 05:39:36.525743: step: 1380/1545, loss: 0.8020082116127014 2023-01-23 05:39:37.413360: step: 1382/1545, loss: 0.9080972671508789 2023-01-23 05:39:38.234332: step: 1384/1545, loss: 3.4160196781158447 2023-01-23 05:39:39.102899: step: 1386/1545, loss: 1.0411931276321411 2023-01-23 05:39:40.025860: step: 1388/1545, loss: 1.3659478425979614 2023-01-23 05:39:40.948009: step: 1390/1545, loss: 3.5504045486450195 2023-01-23 05:39:41.839467: step: 1392/1545, loss: 1.1814900636672974 2023-01-23 05:39:42.711256: step: 1394/1545, loss: 0.7466868758201599 2023-01-23 05:39:43.592799: step: 1396/1545, loss: 7.994483470916748 2023-01-23 05:39:44.484918: step: 1398/1545, loss: 1.3062760829925537 2023-01-23 05:39:45.332493: step: 1400/1545, loss: 1.6650147438049316 2023-01-23 05:39:46.308588: step: 1402/1545, loss: 4.78262186050415 2023-01-23 05:39:47.145402: step: 1404/1545, loss: 0.5320816040039062 2023-01-23 05:39:48.017554: step: 1406/1545, loss: 7.387606620788574 2023-01-23 05:39:48.873194: step: 1408/1545, loss: 1.0045909881591797 2023-01-23 05:39:49.727875: step: 1410/1545, loss: 1.4940041303634644 2023-01-23 05:39:50.590564: step: 1412/1545, loss: 0.6516192555427551 2023-01-23 05:39:51.478002: step: 1414/1545, loss: 1.729557752609253 2023-01-23 05:39:52.397174: step: 1416/1545, loss: 1.4277836084365845 2023-01-23 05:39:53.296120: step: 1418/1545, loss: 7.453025817871094 2023-01-23 05:39:54.167473: step: 1420/1545, loss: 1.5765886306762695 2023-01-23 05:39:55.036768: step: 1422/1545, loss: 2.9511404037475586 2023-01-23 05:39:55.884630: step: 1424/1545, loss: 3.1031453609466553 2023-01-23 05:39:56.725509: step: 1426/1545, loss: 1.0706589221954346 2023-01-23 05:39:57.548214: step: 1428/1545, loss: 1.0237693786621094 2023-01-23 05:39:58.471011: step: 1430/1545, loss: 1.2219442129135132 2023-01-23 05:39:59.350206: step: 1432/1545, loss: 1.2468829154968262 2023-01-23 05:40:00.206769: step: 1434/1545, loss: 1.5788612365722656 2023-01-23 05:40:01.120210: step: 1436/1545, loss: 0.9647355079650879 2023-01-23 05:40:02.008477: step: 1438/1545, loss: 0.9045026302337646 2023-01-23 05:40:02.910149: step: 1440/1545, loss: 1.4708449840545654 2023-01-23 05:40:03.852745: step: 1442/1545, loss: 0.8342490196228027 2023-01-23 05:40:04.688164: step: 1444/1545, loss: 4.108487129211426 2023-01-23 05:40:05.586145: step: 1446/1545, loss: 1.1995272636413574 2023-01-23 05:40:06.448024: step: 1448/1545, loss: 0.5945190191268921 2023-01-23 05:40:07.369530: step: 1450/1545, loss: 0.5429835319519043 2023-01-23 05:40:08.237361: step: 1452/1545, loss: 3.781090497970581 2023-01-23 05:40:09.142578: step: 1454/1545, loss: 0.7594828009605408 2023-01-23 05:40:10.003202: step: 1456/1545, loss: 0.6443821787834167 2023-01-23 05:40:10.879622: step: 1458/1545, loss: 0.8486462831497192 2023-01-23 05:40:11.724624: step: 1460/1545, loss: 1.2092037200927734 2023-01-23 05:40:12.608506: step: 1462/1545, loss: 9.01501750946045 2023-01-23 05:40:13.505402: step: 1464/1545, loss: 1.861729621887207 2023-01-23 05:40:14.363654: step: 1466/1545, loss: 1.2726686000823975 2023-01-23 05:40:15.226104: step: 1468/1545, loss: 1.444840669631958 2023-01-23 05:40:16.125658: step: 1470/1545, loss: 1.5847675800323486 2023-01-23 05:40:17.026679: step: 1472/1545, loss: 0.7020716071128845 2023-01-23 05:40:17.889750: step: 1474/1545, loss: 1.083938717842102 2023-01-23 05:40:18.741189: step: 1476/1545, loss: 0.8745202422142029 2023-01-23 05:40:19.620305: step: 1478/1545, loss: 1.9483704566955566 2023-01-23 05:40:20.490243: step: 1480/1545, loss: 0.410510390996933 2023-01-23 05:40:21.407584: step: 1482/1545, loss: 5.50372314453125 2023-01-23 05:40:22.329867: step: 1484/1545, loss: 1.9187341928482056 2023-01-23 05:40:23.190396: step: 1486/1545, loss: 1.3357281684875488 2023-01-23 05:40:24.056181: step: 1488/1545, loss: 0.9865601062774658 2023-01-23 05:40:24.967720: step: 1490/1545, loss: 1.6387964487075806 2023-01-23 05:40:25.834703: step: 1492/1545, loss: 1.3790793418884277 2023-01-23 05:40:26.713423: step: 1494/1545, loss: 0.9623010158538818 2023-01-23 05:40:27.603429: step: 1496/1545, loss: 0.9719133973121643 2023-01-23 05:40:28.504948: step: 1498/1545, loss: 0.47324633598327637 2023-01-23 05:40:29.397012: step: 1500/1545, loss: 1.1544667482376099 2023-01-23 05:40:30.267081: step: 1502/1545, loss: 1.8567698001861572 2023-01-23 05:40:31.130649: step: 1504/1545, loss: 0.8944264054298401 2023-01-23 05:40:32.012148: step: 1506/1545, loss: 2.134817123413086 2023-01-23 05:40:32.871819: step: 1508/1545, loss: 0.4856812655925751 2023-01-23 05:40:33.714581: step: 1510/1545, loss: 1.3588874340057373 2023-01-23 05:40:34.603442: step: 1512/1545, loss: 6.545570373535156 2023-01-23 05:40:35.504850: step: 1514/1545, loss: 0.5592557191848755 2023-01-23 05:40:36.384306: step: 1516/1545, loss: 1.027336835861206 2023-01-23 05:40:37.291119: step: 1518/1545, loss: 3.4385688304901123 2023-01-23 05:40:38.131177: step: 1520/1545, loss: 1.712199091911316 2023-01-23 05:40:39.058070: step: 1522/1545, loss: 2.2512245178222656 2023-01-23 05:40:39.957819: step: 1524/1545, loss: 0.8166149854660034 2023-01-23 05:40:40.788404: step: 1526/1545, loss: 1.0708098411560059 2023-01-23 05:40:41.656249: step: 1528/1545, loss: 0.6049855947494507 2023-01-23 05:40:42.547034: step: 1530/1545, loss: 0.6673245429992676 2023-01-23 05:40:43.404034: step: 1532/1545, loss: 1.9624789953231812 2023-01-23 05:40:44.283768: step: 1534/1545, loss: 0.9885633587837219 2023-01-23 05:40:45.152534: step: 1536/1545, loss: 4.401087284088135 2023-01-23 05:40:46.016205: step: 1538/1545, loss: 1.0139801502227783 2023-01-23 05:40:46.911630: step: 1540/1545, loss: 3.4208810329437256 2023-01-23 05:40:47.839697: step: 1542/1545, loss: 1.3494253158569336 2023-01-23 05:40:48.728121: step: 1544/1545, loss: 1.0503591299057007 2023-01-23 05:40:49.621785: step: 1546/1545, loss: 3.469560384750366 2023-01-23 05:40:50.485984: step: 1548/1545, loss: 0.6150567531585693 2023-01-23 05:40:51.393490: step: 1550/1545, loss: 3.1067848205566406 2023-01-23 05:40:52.288139: step: 1552/1545, loss: 1.7351832389831543 2023-01-23 05:40:53.160590: step: 1554/1545, loss: 1.7534162998199463 2023-01-23 05:40:53.990288: step: 1556/1545, loss: 1.23439621925354 2023-01-23 05:40:54.871017: step: 1558/1545, loss: 0.8639032244682312 2023-01-23 05:40:55.695894: step: 1560/1545, loss: 3.868082046508789 2023-01-23 05:40:56.581648: step: 1562/1545, loss: 1.2695327997207642 2023-01-23 05:40:57.417399: step: 1564/1545, loss: 3.8117525577545166 2023-01-23 05:40:58.266572: step: 1566/1545, loss: 0.7316080927848816 2023-01-23 05:40:59.170303: step: 1568/1545, loss: 1.1216710805892944 2023-01-23 05:41:00.032005: step: 1570/1545, loss: 0.5610706806182861 2023-01-23 05:41:00.906468: step: 1572/1545, loss: 1.011433482170105 2023-01-23 05:41:01.780171: step: 1574/1545, loss: 1.1262333393096924 2023-01-23 05:41:02.654565: step: 1576/1545, loss: 0.38149136304855347 2023-01-23 05:41:03.500755: step: 1578/1545, loss: 0.6997714638710022 2023-01-23 05:41:04.368716: step: 1580/1545, loss: 6.87227725982666 2023-01-23 05:41:05.258014: step: 1582/1545, loss: 1.006395697593689 2023-01-23 05:41:06.196141: step: 1584/1545, loss: 1.3836983442306519 2023-01-23 05:41:07.072655: step: 1586/1545, loss: 0.5825586318969727 2023-01-23 05:41:07.920782: step: 1588/1545, loss: 0.7038135528564453 2023-01-23 05:41:08.806883: step: 1590/1545, loss: 1.0983715057373047 2023-01-23 05:41:09.757562: step: 1592/1545, loss: 1.353542447090149 2023-01-23 05:41:10.619636: step: 1594/1545, loss: 1.1067414283752441 2023-01-23 05:41:11.488341: step: 1596/1545, loss: 0.45179736614227295 2023-01-23 05:41:12.349504: step: 1598/1545, loss: 1.773681640625 2023-01-23 05:41:13.335753: step: 1600/1545, loss: 2.106945514678955 2023-01-23 05:41:14.193700: step: 1602/1545, loss: 1.1447725296020508 2023-01-23 05:41:15.125412: step: 1604/1545, loss: 0.7824391722679138 2023-01-23 05:41:15.984642: step: 1606/1545, loss: 2.4317257404327393 2023-01-23 05:41:16.823547: step: 1608/1545, loss: 1.5086861848831177 2023-01-23 05:41:17.681273: step: 1610/1545, loss: 0.8521987795829773 2023-01-23 05:41:18.614355: step: 1612/1545, loss: 0.7871000170707703 2023-01-23 05:41:19.525947: step: 1614/1545, loss: 1.0136960744857788 2023-01-23 05:41:20.403326: step: 1616/1545, loss: 1.1605221033096313 2023-01-23 05:41:21.310113: step: 1618/1545, loss: 2.6424076557159424 2023-01-23 05:41:22.195003: step: 1620/1545, loss: 0.8590205311775208 2023-01-23 05:41:23.115522: step: 1622/1545, loss: 0.7900682091712952 2023-01-23 05:41:24.012115: step: 1624/1545, loss: 1.5860565900802612 2023-01-23 05:41:24.886214: step: 1626/1545, loss: 1.0969674587249756 2023-01-23 05:41:25.762035: step: 1628/1545, loss: 1.900850534439087 2023-01-23 05:41:26.645966: step: 1630/1545, loss: 0.5972522497177124 2023-01-23 05:41:27.532482: step: 1632/1545, loss: 1.2863125801086426 2023-01-23 05:41:28.456455: step: 1634/1545, loss: 1.370107889175415 2023-01-23 05:41:29.309500: step: 1636/1545, loss: 0.6705527901649475 2023-01-23 05:41:30.173177: step: 1638/1545, loss: 1.235553503036499 2023-01-23 05:41:31.000657: step: 1640/1545, loss: 1.1298233270645142 2023-01-23 05:41:31.886365: step: 1642/1545, loss: 1.136554479598999 2023-01-23 05:41:32.894570: step: 1644/1545, loss: 1.1594873666763306 2023-01-23 05:41:33.839525: step: 1646/1545, loss: 6.572237014770508 2023-01-23 05:41:34.733882: step: 1648/1545, loss: 1.5475428104400635 2023-01-23 05:41:35.617641: step: 1650/1545, loss: 1.3929075002670288 2023-01-23 05:41:36.564451: step: 1652/1545, loss: 1.3691326379776 2023-01-23 05:41:37.461650: step: 1654/1545, loss: 0.8569575548171997 2023-01-23 05:41:38.329848: step: 1656/1545, loss: 0.3836544156074524 2023-01-23 05:41:39.256445: step: 1658/1545, loss: 1.2864890098571777 2023-01-23 05:41:40.259458: step: 1660/1545, loss: 0.7256394028663635 2023-01-23 05:41:41.139181: step: 1662/1545, loss: 0.6970654129981995 2023-01-23 05:41:42.052833: step: 1664/1545, loss: 1.5323714017868042 2023-01-23 05:41:42.934184: step: 1666/1545, loss: 0.4832899272441864 2023-01-23 05:41:43.812497: step: 1668/1545, loss: 0.7508485317230225 2023-01-23 05:41:44.712103: step: 1670/1545, loss: 3.8197717666625977 2023-01-23 05:41:45.613745: step: 1672/1545, loss: 1.2587647438049316 2023-01-23 05:41:46.515082: step: 1674/1545, loss: 0.7289960980415344 2023-01-23 05:41:47.359449: step: 1676/1545, loss: 0.4796937108039856 2023-01-23 05:41:48.204162: step: 1678/1545, loss: 1.2683924436569214 2023-01-23 05:41:49.095912: step: 1680/1545, loss: 0.4908730983734131 2023-01-23 05:41:49.942770: step: 1682/1545, loss: 1.4596400260925293 2023-01-23 05:41:50.827339: step: 1684/1545, loss: 3.045466899871826 2023-01-23 05:41:51.709106: step: 1686/1545, loss: 0.9235209822654724 2023-01-23 05:41:52.600480: step: 1688/1545, loss: 0.608159601688385 2023-01-23 05:41:53.499099: step: 1690/1545, loss: 1.223384141921997 2023-01-23 05:41:54.401302: step: 1692/1545, loss: 1.2087762355804443 2023-01-23 05:41:55.260083: step: 1694/1545, loss: 1.7107772827148438 2023-01-23 05:41:56.132108: step: 1696/1545, loss: 1.1320462226867676 2023-01-23 05:41:56.999539: step: 1698/1545, loss: 2.189927816390991 2023-01-23 05:41:57.871979: step: 1700/1545, loss: 1.1120449304580688 2023-01-23 05:41:58.741773: step: 1702/1545, loss: 0.7625613808631897 2023-01-23 05:41:59.658557: step: 1704/1545, loss: 0.8612613677978516 2023-01-23 05:42:00.519152: step: 1706/1545, loss: 1.427522897720337 2023-01-23 05:42:01.374642: step: 1708/1545, loss: 1.2141526937484741 2023-01-23 05:42:02.250501: step: 1710/1545, loss: 1.4754016399383545 2023-01-23 05:42:03.195699: step: 1712/1545, loss: 1.867507815361023 2023-01-23 05:42:04.041722: step: 1714/1545, loss: 1.1987714767456055 2023-01-23 05:42:04.923175: step: 1716/1545, loss: 1.0196423530578613 2023-01-23 05:42:05.891266: step: 1718/1545, loss: 2.3684959411621094 2023-01-23 05:42:06.837086: step: 1720/1545, loss: 0.9887377619743347 2023-01-23 05:42:07.820002: step: 1722/1545, loss: 0.8055461645126343 2023-01-23 05:42:08.720325: step: 1724/1545, loss: 1.0776299238204956 2023-01-23 05:42:09.582223: step: 1726/1545, loss: 0.8968037366867065 2023-01-23 05:42:10.414276: step: 1728/1545, loss: 3.0384910106658936 2023-01-23 05:42:11.302886: step: 1730/1545, loss: 2.0291216373443604 2023-01-23 05:42:12.216793: step: 1732/1545, loss: 3.4364914894104004 2023-01-23 05:42:13.098045: step: 1734/1545, loss: 2.489347219467163 2023-01-23 05:42:13.975355: step: 1736/1545, loss: 1.2528985738754272 2023-01-23 05:42:14.869828: step: 1738/1545, loss: 1.793649435043335 2023-01-23 05:42:15.726804: step: 1740/1545, loss: 0.507133960723877 2023-01-23 05:42:16.679516: step: 1742/1545, loss: 1.7147789001464844 2023-01-23 05:42:17.543535: step: 1744/1545, loss: 1.3765273094177246 2023-01-23 05:42:18.398657: step: 1746/1545, loss: 0.8586242198944092 2023-01-23 05:42:19.305894: step: 1748/1545, loss: 2.8082101345062256 2023-01-23 05:42:20.162372: step: 1750/1545, loss: 1.5043362379074097 2023-01-23 05:42:21.072194: step: 1752/1545, loss: 1.239211916923523 2023-01-23 05:42:21.907127: step: 1754/1545, loss: 1.7220535278320312 2023-01-23 05:42:22.797043: step: 1756/1545, loss: 3.5104293823242188 2023-01-23 05:42:23.688531: step: 1758/1545, loss: 1.3536372184753418 2023-01-23 05:42:24.590194: step: 1760/1545, loss: 1.6020570993423462 2023-01-23 05:42:25.453271: step: 1762/1545, loss: 1.4931719303131104 2023-01-23 05:42:26.354519: step: 1764/1545, loss: 0.548424482345581 2023-01-23 05:42:27.240414: step: 1766/1545, loss: 0.8625931143760681 2023-01-23 05:42:28.110391: step: 1768/1545, loss: 1.7878873348236084 2023-01-23 05:42:29.012644: step: 1770/1545, loss: 1.7361929416656494 2023-01-23 05:42:29.872744: step: 1772/1545, loss: 5.432867050170898 2023-01-23 05:42:30.726898: step: 1774/1545, loss: 3.738208770751953 2023-01-23 05:42:31.636518: step: 1776/1545, loss: 7.252011299133301 2023-01-23 05:42:32.515409: step: 1778/1545, loss: 1.2429431676864624 2023-01-23 05:42:33.445638: step: 1780/1545, loss: 0.7358487248420715 2023-01-23 05:42:34.353965: step: 1782/1545, loss: 0.6263068914413452 2023-01-23 05:42:35.201267: step: 1784/1545, loss: 1.4861040115356445 2023-01-23 05:42:36.044000: step: 1786/1545, loss: 0.8025970458984375 2023-01-23 05:42:36.905639: step: 1788/1545, loss: 3.4130263328552246 2023-01-23 05:42:37.784451: step: 1790/1545, loss: 1.774192214012146 2023-01-23 05:42:38.685910: step: 1792/1545, loss: 0.6307086944580078 2023-01-23 05:42:39.554423: step: 1794/1545, loss: 0.7640730738639832 2023-01-23 05:42:40.401125: step: 1796/1545, loss: 7.251170635223389 2023-01-23 05:42:41.257868: step: 1798/1545, loss: 0.8114332556724548 2023-01-23 05:42:42.120994: step: 1800/1545, loss: 1.2028324604034424 2023-01-23 05:42:43.002281: step: 1802/1545, loss: 1.1257939338684082 2023-01-23 05:42:43.881478: step: 1804/1545, loss: 3.7044050693511963 2023-01-23 05:42:44.778626: step: 1806/1545, loss: 10.076282501220703 2023-01-23 05:42:45.618072: step: 1808/1545, loss: 1.360600233078003 2023-01-23 05:42:46.462187: step: 1810/1545, loss: 3.4588959217071533 2023-01-23 05:42:47.346716: step: 1812/1545, loss: 9.103175163269043 2023-01-23 05:42:48.232156: step: 1814/1545, loss: 1.1475716829299927 2023-01-23 05:42:49.112673: step: 1816/1545, loss: 0.9774792194366455 2023-01-23 05:42:49.991443: step: 1818/1545, loss: 3.403695583343506 2023-01-23 05:42:50.837742: step: 1820/1545, loss: 3.1045148372650146 2023-01-23 05:42:51.723988: step: 1822/1545, loss: 1.1125911474227905 2023-01-23 05:42:52.644557: step: 1824/1545, loss: 1.5135788917541504 2023-01-23 05:42:53.473363: step: 1826/1545, loss: 6.498156547546387 2023-01-23 05:42:54.384278: step: 1828/1545, loss: 1.3178184032440186 2023-01-23 05:42:55.268744: step: 1830/1545, loss: 1.028542399406433 2023-01-23 05:42:56.151858: step: 1832/1545, loss: 0.48541784286499023 2023-01-23 05:42:57.044569: step: 1834/1545, loss: 3.3176701068878174 2023-01-23 05:42:57.908859: step: 1836/1545, loss: 1.1041593551635742 2023-01-23 05:42:58.757680: step: 1838/1545, loss: 3.6009035110473633 2023-01-23 05:42:59.620629: step: 1840/1545, loss: 0.734443724155426 2023-01-23 05:43:00.508356: step: 1842/1545, loss: 0.8956899642944336 2023-01-23 05:43:01.343520: step: 1844/1545, loss: 0.33606836199760437 2023-01-23 05:43:02.221659: step: 1846/1545, loss: 0.8594300150871277 2023-01-23 05:43:03.108453: step: 1848/1545, loss: 1.8303520679473877 2023-01-23 05:43:03.995974: step: 1850/1545, loss: 1.4009305238723755 2023-01-23 05:43:04.895093: step: 1852/1545, loss: 1.8376905918121338 2023-01-23 05:43:05.765722: step: 1854/1545, loss: 1.647790551185608 2023-01-23 05:43:06.660066: step: 1856/1545, loss: 0.38812196254730225 2023-01-23 05:43:07.570513: step: 1858/1545, loss: 0.807858943939209 2023-01-23 05:43:08.439344: step: 1860/1545, loss: 1.8741148710250854 2023-01-23 05:43:09.339430: step: 1862/1545, loss: 1.946125864982605 2023-01-23 05:43:10.240753: step: 1864/1545, loss: 0.42251813411712646 2023-01-23 05:43:11.090627: step: 1866/1545, loss: 1.0119283199310303 2023-01-23 05:43:11.982718: step: 1868/1545, loss: 0.6895779967308044 2023-01-23 05:43:12.877426: step: 1870/1545, loss: 3.2298192977905273 2023-01-23 05:43:13.751915: step: 1872/1545, loss: 0.8481868505477905 2023-01-23 05:43:14.630061: step: 1874/1545, loss: 1.235008955001831 2023-01-23 05:43:15.545807: step: 1876/1545, loss: 3.8957886695861816 2023-01-23 05:43:16.404156: step: 1878/1545, loss: 1.369076132774353 2023-01-23 05:43:17.307319: step: 1880/1545, loss: 1.288919448852539 2023-01-23 05:43:18.136519: step: 1882/1545, loss: 7.129945755004883 2023-01-23 05:43:19.023877: step: 1884/1545, loss: 7.3016276359558105 2023-01-23 05:43:19.938933: step: 1886/1545, loss: 1.1440346240997314 2023-01-23 05:43:20.784303: step: 1888/1545, loss: 0.8110491633415222 2023-01-23 05:43:21.681815: step: 1890/1545, loss: 1.0141816139221191 2023-01-23 05:43:22.577533: step: 1892/1545, loss: 1.4224133491516113 2023-01-23 05:43:23.452260: step: 1894/1545, loss: 1.2534511089324951 2023-01-23 05:43:24.330585: step: 1896/1545, loss: 1.0522128343582153 2023-01-23 05:43:25.175505: step: 1898/1545, loss: 1.340168833732605 2023-01-23 05:43:26.118861: step: 1900/1545, loss: 3.5250794887542725 2023-01-23 05:43:27.036345: step: 1902/1545, loss: 1.6887266635894775 2023-01-23 05:43:28.005427: step: 1904/1545, loss: 0.7232352495193481 2023-01-23 05:43:28.852047: step: 1906/1545, loss: 3.4020938873291016 2023-01-23 05:43:29.726682: step: 1908/1545, loss: 1.056302547454834 2023-01-23 05:43:30.597526: step: 1910/1545, loss: 1.882390022277832 2023-01-23 05:43:31.469029: step: 1912/1545, loss: 0.9529452323913574 2023-01-23 05:43:32.350481: step: 1914/1545, loss: 1.6528040170669556 2023-01-23 05:43:33.219744: step: 1916/1545, loss: 3.33561372756958 2023-01-23 05:43:34.111998: step: 1918/1545, loss: 1.431038737297058 2023-01-23 05:43:34.977445: step: 1920/1545, loss: 2.1626129150390625 2023-01-23 05:43:35.949804: step: 1922/1545, loss: 1.1621832847595215 2023-01-23 05:43:36.792271: step: 1924/1545, loss: 1.2473050355911255 2023-01-23 05:43:37.661783: step: 1926/1545, loss: 1.3088268041610718 2023-01-23 05:43:38.533484: step: 1928/1545, loss: 1.210758924484253 2023-01-23 05:43:39.389555: step: 1930/1545, loss: 1.0379806756973267 2023-01-23 05:43:40.270549: step: 1932/1545, loss: 0.8537649512290955 2023-01-23 05:43:41.136645: step: 1934/1545, loss: 1.0816433429718018 2023-01-23 05:43:42.003633: step: 1936/1545, loss: 0.44329363107681274 2023-01-23 05:43:42.878360: step: 1938/1545, loss: 9.521543502807617 2023-01-23 05:43:43.765066: step: 1940/1545, loss: 0.8351912498474121 2023-01-23 05:43:44.684177: step: 1942/1545, loss: 0.9066963791847229 2023-01-23 05:43:45.516949: step: 1944/1545, loss: 0.6322430372238159 2023-01-23 05:43:46.374561: step: 1946/1545, loss: 2.0202834606170654 2023-01-23 05:43:47.246493: step: 1948/1545, loss: 1.2696044445037842 2023-01-23 05:43:48.151963: step: 1950/1545, loss: 0.6503176093101501 2023-01-23 05:43:49.040678: step: 1952/1545, loss: 0.8358094096183777 2023-01-23 05:43:49.876823: step: 1954/1545, loss: 0.588756799697876 2023-01-23 05:43:50.719181: step: 1956/1545, loss: 5.676264762878418 2023-01-23 05:43:51.600032: step: 1958/1545, loss: 0.7852839827537537 2023-01-23 05:43:52.441739: step: 1960/1545, loss: 1.133434534072876 2023-01-23 05:43:53.304249: step: 1962/1545, loss: 1.1145516633987427 2023-01-23 05:43:54.180987: step: 1964/1545, loss: 0.783116340637207 2023-01-23 05:43:55.061670: step: 1966/1545, loss: 0.6504597067832947 2023-01-23 05:43:55.901067: step: 1968/1545, loss: 0.6929334998130798 2023-01-23 05:43:56.806523: step: 1970/1545, loss: 1.3569278717041016 2023-01-23 05:43:57.663789: step: 1972/1545, loss: 0.48626208305358887 2023-01-23 05:43:58.531836: step: 1974/1545, loss: 1.3777403831481934 2023-01-23 05:43:59.470063: step: 1976/1545, loss: 1.0881537199020386 2023-01-23 05:44:00.401789: step: 1978/1545, loss: 1.655769944190979 2023-01-23 05:44:01.250210: step: 1980/1545, loss: 0.4167000949382782 2023-01-23 05:44:02.155476: step: 1982/1545, loss: 1.138322114944458 2023-01-23 05:44:03.009545: step: 1984/1545, loss: 1.209859848022461 2023-01-23 05:44:03.876884: step: 1986/1545, loss: 0.5641697645187378 2023-01-23 05:44:04.714760: step: 1988/1545, loss: 1.2089306116104126 2023-01-23 05:44:05.574998: step: 1990/1545, loss: 0.7858896851539612 2023-01-23 05:44:06.446426: step: 1992/1545, loss: 1.3135782480239868 2023-01-23 05:44:07.347475: step: 1994/1545, loss: 1.180802345275879 2023-01-23 05:44:08.230146: step: 1996/1545, loss: 1.9955549240112305 2023-01-23 05:44:09.053636: step: 1998/1545, loss: 2.1810457706451416 2023-01-23 05:44:09.911524: step: 2000/1545, loss: 0.8488776087760925 2023-01-23 05:44:10.773980: step: 2002/1545, loss: 3.026721239089966 2023-01-23 05:44:11.648496: step: 2004/1545, loss: 0.8523863554000854 2023-01-23 05:44:12.527821: step: 2006/1545, loss: 1.9269307851791382 2023-01-23 05:44:13.401127: step: 2008/1545, loss: 0.6481420993804932 2023-01-23 05:44:14.265560: step: 2010/1545, loss: 1.3795868158340454 2023-01-23 05:44:15.150741: step: 2012/1545, loss: 1.13383150100708 2023-01-23 05:44:16.010834: step: 2014/1545, loss: 0.7268655896186829 2023-01-23 05:44:16.893675: step: 2016/1545, loss: 0.4302346110343933 2023-01-23 05:44:17.818413: step: 2018/1545, loss: 0.8212596774101257 2023-01-23 05:44:18.731272: step: 2020/1545, loss: 0.6855722069740295 2023-01-23 05:44:19.700122: step: 2022/1545, loss: 0.745327889919281 2023-01-23 05:44:20.611002: step: 2024/1545, loss: 1.3882321119308472 2023-01-23 05:44:21.464731: step: 2026/1545, loss: 3.2299704551696777 2023-01-23 05:44:22.373871: step: 2028/1545, loss: 1.1962597370147705 2023-01-23 05:44:23.293939: step: 2030/1545, loss: 1.375101923942566 2023-01-23 05:44:24.167236: step: 2032/1545, loss: 0.6947159767150879 2023-01-23 05:44:25.029443: step: 2034/1545, loss: 0.45611047744750977 2023-01-23 05:44:25.910734: step: 2036/1545, loss: 1.622072458267212 2023-01-23 05:44:26.798218: step: 2038/1545, loss: 2.635662078857422 2023-01-23 05:44:27.656075: step: 2040/1545, loss: 1.0033955574035645 2023-01-23 05:44:28.549423: step: 2042/1545, loss: 1.8001090288162231 2023-01-23 05:44:29.405075: step: 2044/1545, loss: 0.9648497104644775 2023-01-23 05:44:30.283578: step: 2046/1545, loss: 0.8255117535591125 2023-01-23 05:44:31.174856: step: 2048/1545, loss: 1.0480095148086548 2023-01-23 05:44:32.049593: step: 2050/1545, loss: 0.7005330920219421 2023-01-23 05:44:32.914397: step: 2052/1545, loss: 0.4844265878200531 2023-01-23 05:44:33.803347: step: 2054/1545, loss: 1.3449475765228271 2023-01-23 05:44:34.660124: step: 2056/1545, loss: 0.772276759147644 2023-01-23 05:44:35.511484: step: 2058/1545, loss: 0.9717065095901489 2023-01-23 05:44:36.375159: step: 2060/1545, loss: 1.6634488105773926 2023-01-23 05:44:37.280395: step: 2062/1545, loss: 0.7589244246482849 2023-01-23 05:44:38.138851: step: 2064/1545, loss: 0.9567700028419495 2023-01-23 05:44:39.007631: step: 2066/1545, loss: 1.2954494953155518 2023-01-23 05:44:39.879611: step: 2068/1545, loss: 1.616769552230835 2023-01-23 05:44:40.851046: step: 2070/1545, loss: 1.1294937133789062 2023-01-23 05:44:41.688876: step: 2072/1545, loss: 0.5431910157203674 2023-01-23 05:44:42.574105: step: 2074/1545, loss: 1.0173054933547974 2023-01-23 05:44:43.448340: step: 2076/1545, loss: 0.7410720586776733 2023-01-23 05:44:44.320324: step: 2078/1545, loss: 4.155523777008057 2023-01-23 05:44:45.178223: step: 2080/1545, loss: 1.0457744598388672 2023-01-23 05:44:46.011166: step: 2082/1545, loss: 0.9544810056686401 2023-01-23 05:44:46.880998: step: 2084/1545, loss: 1.180546760559082 2023-01-23 05:44:47.783179: step: 2086/1545, loss: 0.3162703812122345 2023-01-23 05:44:48.702656: step: 2088/1545, loss: 3.3825812339782715 2023-01-23 05:44:49.621584: step: 2090/1545, loss: 0.7869051098823547 2023-01-23 05:44:50.548673: step: 2092/1545, loss: 3.838435411453247 2023-01-23 05:44:51.453027: step: 2094/1545, loss: 0.7904515266418457 2023-01-23 05:44:52.353709: step: 2096/1545, loss: 6.159639835357666 2023-01-23 05:44:53.252511: step: 2098/1545, loss: 0.9711830019950867 2023-01-23 05:44:54.163565: step: 2100/1545, loss: 1.9299335479736328 2023-01-23 05:44:54.995682: step: 2102/1545, loss: 0.5981963872909546 2023-01-23 05:44:55.883130: step: 2104/1545, loss: 3.7500224113464355 2023-01-23 05:44:56.791291: step: 2106/1545, loss: 1.5852445363998413 2023-01-23 05:44:57.685897: step: 2108/1545, loss: 0.7587074637413025 2023-01-23 05:44:58.557290: step: 2110/1545, loss: 0.9946025609970093 2023-01-23 05:44:59.403264: step: 2112/1545, loss: 8.26130485534668 2023-01-23 05:45:00.279771: step: 2114/1545, loss: 3.591895341873169 2023-01-23 05:45:01.161891: step: 2116/1545, loss: 1.4322103261947632 2023-01-23 05:45:02.077583: step: 2118/1545, loss: 0.9477992653846741 2023-01-23 05:45:02.943052: step: 2120/1545, loss: 5.4593071937561035 2023-01-23 05:45:03.801821: step: 2122/1545, loss: 1.1170920133590698 2023-01-23 05:45:04.675420: step: 2124/1545, loss: 0.8787168860435486 2023-01-23 05:45:05.521360: step: 2126/1545, loss: 0.8606507182121277 2023-01-23 05:45:06.392944: step: 2128/1545, loss: 6.846020698547363 2023-01-23 05:45:07.287391: step: 2130/1545, loss: 1.9582544565200806 2023-01-23 05:45:08.132129: step: 2132/1545, loss: 0.9306904077529907 2023-01-23 05:45:09.076075: step: 2134/1545, loss: 1.3733328580856323 2023-01-23 05:45:09.953239: step: 2136/1545, loss: 1.0684961080551147 2023-01-23 05:45:10.836065: step: 2138/1545, loss: 0.5646055936813354 2023-01-23 05:45:11.745374: step: 2140/1545, loss: 8.444927215576172 2023-01-23 05:45:12.628573: step: 2142/1545, loss: 0.9012018442153931 2023-01-23 05:45:13.479866: step: 2144/1545, loss: 0.36671823263168335 2023-01-23 05:45:14.403620: step: 2146/1545, loss: 1.9333672523498535 2023-01-23 05:45:15.273338: step: 2148/1545, loss: 0.6959819197654724 2023-01-23 05:45:16.105490: step: 2150/1545, loss: 2.954662322998047 2023-01-23 05:45:16.973266: step: 2152/1545, loss: 0.7348374724388123 2023-01-23 05:45:17.808548: step: 2154/1545, loss: 3.229362726211548 2023-01-23 05:45:18.660488: step: 2156/1545, loss: 0.9003589153289795 2023-01-23 05:45:19.505848: step: 2158/1545, loss: 3.0962257385253906 2023-01-23 05:45:20.392454: step: 2160/1545, loss: 4.105323314666748 2023-01-23 05:45:21.280829: step: 2162/1545, loss: 1.0993305444717407 2023-01-23 05:45:22.198445: step: 2164/1545, loss: 1.2449718713760376 2023-01-23 05:45:23.047811: step: 2166/1545, loss: 1.3201063871383667 2023-01-23 05:45:23.945910: step: 2168/1545, loss: 0.9350348711013794 2023-01-23 05:45:24.859187: step: 2170/1545, loss: 3.4689769744873047 2023-01-23 05:45:25.719800: step: 2172/1545, loss: 3.825512409210205 2023-01-23 05:45:26.623761: step: 2174/1545, loss: 0.7439584732055664 2023-01-23 05:45:27.500838: step: 2176/1545, loss: 1.3054975271224976 2023-01-23 05:45:28.406946: step: 2178/1545, loss: 0.8433261513710022 2023-01-23 05:45:29.271965: step: 2180/1545, loss: 0.5013432502746582 2023-01-23 05:45:30.148795: step: 2182/1545, loss: 1.456002116203308 2023-01-23 05:45:31.028677: step: 2184/1545, loss: 0.5633605122566223 2023-01-23 05:45:31.931879: step: 2186/1545, loss: 0.7236223220825195 2023-01-23 05:45:32.831027: step: 2188/1545, loss: 1.0950980186462402 2023-01-23 05:45:33.722924: step: 2190/1545, loss: 1.8244024515151978 2023-01-23 05:45:34.614969: step: 2192/1545, loss: 3.3875019550323486 2023-01-23 05:45:35.476269: step: 2194/1545, loss: 1.2582224607467651 2023-01-23 05:45:36.354195: step: 2196/1545, loss: 1.182460069656372 2023-01-23 05:45:37.190431: step: 2198/1545, loss: 0.705586314201355 2023-01-23 05:45:38.074809: step: 2200/1545, loss: 3.386110305786133 2023-01-23 05:45:38.966119: step: 2202/1545, loss: 3.246696710586548 2023-01-23 05:45:39.883175: step: 2204/1545, loss: 0.9395704865455627 2023-01-23 05:45:40.769086: step: 2206/1545, loss: 1.3442257642745972 2023-01-23 05:45:41.725781: step: 2208/1545, loss: 0.9684025049209595 2023-01-23 05:45:42.578418: step: 2210/1545, loss: 0.6592898964881897 2023-01-23 05:45:43.422194: step: 2212/1545, loss: 0.6668332815170288 2023-01-23 05:45:44.274356: step: 2214/1545, loss: 1.0731092691421509 2023-01-23 05:45:45.131669: step: 2216/1545, loss: 1.119574785232544 2023-01-23 05:45:46.007603: step: 2218/1545, loss: 3.4835548400878906 2023-01-23 05:45:46.874461: step: 2220/1545, loss: 0.7719776034355164 2023-01-23 05:45:47.722065: step: 2222/1545, loss: 2.111443281173706 2023-01-23 05:45:48.608133: step: 2224/1545, loss: 0.6974895596504211 2023-01-23 05:45:49.549556: step: 2226/1545, loss: 1.0350507497787476 2023-01-23 05:45:50.456357: step: 2228/1545, loss: 1.1715644598007202 2023-01-23 05:45:51.373077: step: 2230/1545, loss: 0.8003025054931641 2023-01-23 05:45:52.252104: step: 2232/1545, loss: 1.1872663497924805 2023-01-23 05:45:53.117519: step: 2234/1545, loss: 2.972062349319458 2023-01-23 05:45:53.978264: step: 2236/1545, loss: 0.5511969327926636 2023-01-23 05:45:54.908063: step: 2238/1545, loss: 1.4502336978912354 2023-01-23 05:45:55.801138: step: 2240/1545, loss: 0.8459370136260986 2023-01-23 05:45:56.681845: step: 2242/1545, loss: 0.944206178188324 2023-01-23 05:45:57.575181: step: 2244/1545, loss: 1.0388977527618408 2023-01-23 05:45:58.455930: step: 2246/1545, loss: 0.6982152462005615 2023-01-23 05:45:59.348885: step: 2248/1545, loss: 0.9224929213523865 2023-01-23 05:46:00.199978: step: 2250/1545, loss: 1.246734619140625 2023-01-23 05:46:01.062032: step: 2252/1545, loss: 6.118118762969971 2023-01-23 05:46:01.891229: step: 2254/1545, loss: 4.608163833618164 2023-01-23 05:46:02.850493: step: 2256/1545, loss: 3.243101119995117 2023-01-23 05:46:03.812116: step: 2258/1545, loss: 1.0031250715255737 2023-01-23 05:46:04.751021: step: 2260/1545, loss: 1.1440924406051636 2023-01-23 05:46:05.621459: step: 2262/1545, loss: 0.7630054950714111 2023-01-23 05:46:06.466130: step: 2264/1545, loss: 1.2028374671936035 2023-01-23 05:46:07.329268: step: 2266/1545, loss: 0.347920298576355 2023-01-23 05:46:08.187188: step: 2268/1545, loss: 1.1895099878311157 2023-01-23 05:46:09.068803: step: 2270/1545, loss: 1.5253807306289673 2023-01-23 05:46:09.927667: step: 2272/1545, loss: 0.7185483574867249 2023-01-23 05:46:10.832068: step: 2274/1545, loss: 1.2463819980621338 2023-01-23 05:46:11.719123: step: 2276/1545, loss: 3.3689470291137695 2023-01-23 05:46:12.630515: step: 2278/1545, loss: 1.2230297327041626 2023-01-23 05:46:13.492419: step: 2280/1545, loss: 1.7234350442886353 2023-01-23 05:46:14.350572: step: 2282/1545, loss: 9.610610008239746 2023-01-23 05:46:15.222458: step: 2284/1545, loss: 3.33892560005188 2023-01-23 05:46:16.100956: step: 2286/1545, loss: 0.5258116722106934 2023-01-23 05:46:16.992989: step: 2288/1545, loss: 0.9353924989700317 2023-01-23 05:46:17.860234: step: 2290/1545, loss: 0.46991050243377686 2023-01-23 05:46:18.756284: step: 2292/1545, loss: 1.412253737449646 2023-01-23 05:46:19.639262: step: 2294/1545, loss: 0.9424563050270081 2023-01-23 05:46:20.516967: step: 2296/1545, loss: 1.3144536018371582 2023-01-23 05:46:21.374871: step: 2298/1545, loss: 0.9918779730796814 2023-01-23 05:46:22.232930: step: 2300/1545, loss: 0.8131289482116699 2023-01-23 05:46:23.161115: step: 2302/1545, loss: 0.9184980988502502 2023-01-23 05:46:24.064113: step: 2304/1545, loss: 0.9629288911819458 2023-01-23 05:46:24.929375: step: 2306/1545, loss: 3.4255549907684326 2023-01-23 05:46:25.798735: step: 2308/1545, loss: 1.0374189615249634 2023-01-23 05:46:26.672031: step: 2310/1545, loss: 2.947540760040283 2023-01-23 05:46:27.534793: step: 2312/1545, loss: 2.135265827178955 2023-01-23 05:46:28.428886: step: 2314/1545, loss: 0.733357310295105 2023-01-23 05:46:29.290487: step: 2316/1545, loss: 3.656172752380371 2023-01-23 05:46:30.169886: step: 2318/1545, loss: 0.40161457657814026 2023-01-23 05:46:31.036742: step: 2320/1545, loss: 2.4114370346069336 2023-01-23 05:46:31.950806: step: 2322/1545, loss: 4.356436252593994 2023-01-23 05:46:32.797534: step: 2324/1545, loss: 0.9130485653877258 2023-01-23 05:46:33.658988: step: 2326/1545, loss: 0.6707656383514404 2023-01-23 05:46:34.507781: step: 2328/1545, loss: 0.9387125372886658 2023-01-23 05:46:35.376212: step: 2330/1545, loss: 1.2188314199447632 2023-01-23 05:46:36.226470: step: 2332/1545, loss: 0.8219494819641113 2023-01-23 05:46:37.130690: step: 2334/1545, loss: 0.8609316349029541 2023-01-23 05:46:37.984338: step: 2336/1545, loss: 0.6112568378448486 2023-01-23 05:46:38.859460: step: 2338/1545, loss: 1.5568368434906006 2023-01-23 05:46:39.727369: step: 2340/1545, loss: 1.0907971858978271 2023-01-23 05:46:40.589219: step: 2342/1545, loss: 0.7655278444290161 2023-01-23 05:46:41.523637: step: 2344/1545, loss: 3.8006110191345215 2023-01-23 05:46:42.385460: step: 2346/1545, loss: 0.8657279014587402 2023-01-23 05:46:43.225642: step: 2348/1545, loss: 1.1482902765274048 2023-01-23 05:46:44.084634: step: 2350/1545, loss: 0.9585080742835999 2023-01-23 05:46:44.999112: step: 2352/1545, loss: 0.8592802286148071 2023-01-23 05:46:45.892907: step: 2354/1545, loss: 1.0617235898971558 2023-01-23 05:46:46.720824: step: 2356/1545, loss: 2.9999032020568848 2023-01-23 05:46:47.590937: step: 2358/1545, loss: 2.140216827392578 2023-01-23 05:46:48.500395: step: 2360/1545, loss: 1.1724661588668823 2023-01-23 05:46:49.433928: step: 2362/1545, loss: 1.2098174095153809 2023-01-23 05:46:50.312758: step: 2364/1545, loss: 0.5535933971405029 2023-01-23 05:46:51.168211: step: 2366/1545, loss: 0.6609868407249451 2023-01-23 05:46:52.068928: step: 2368/1545, loss: 0.8451291918754578 2023-01-23 05:46:52.908575: step: 2370/1545, loss: 1.8273580074310303 2023-01-23 05:46:53.783766: step: 2372/1545, loss: 1.2612985372543335 2023-01-23 05:46:54.664363: step: 2374/1545, loss: 1.2990477085113525 2023-01-23 05:46:55.586619: step: 2376/1545, loss: 0.8014304637908936 2023-01-23 05:46:56.456023: step: 2378/1545, loss: 0.497341126203537 2023-01-23 05:46:57.328140: step: 2380/1545, loss: 1.6813719272613525 2023-01-23 05:46:58.179205: step: 2382/1545, loss: 1.1517750024795532 2023-01-23 05:46:59.021852: step: 2384/1545, loss: 1.0595959424972534 2023-01-23 05:46:59.881328: step: 2386/1545, loss: 6.262671947479248 2023-01-23 05:47:00.749651: step: 2388/1545, loss: 7.047909736633301 2023-01-23 05:47:01.643960: step: 2390/1545, loss: 0.9013703465461731 2023-01-23 05:47:02.564685: step: 2392/1545, loss: 6.953060150146484 2023-01-23 05:47:03.453783: step: 2394/1545, loss: 0.7972542643547058 2023-01-23 05:47:04.346674: step: 2396/1545, loss: 0.8118257522583008 2023-01-23 05:47:05.242388: step: 2398/1545, loss: 1.518896460533142 2023-01-23 05:47:06.128581: step: 2400/1545, loss: 0.8917863965034485 2023-01-23 05:47:06.992645: step: 2402/1545, loss: 3.6911795139312744 2023-01-23 05:47:07.923151: step: 2404/1545, loss: 7.724160194396973 2023-01-23 05:47:08.778707: step: 2406/1545, loss: 1.0836365222930908 2023-01-23 05:47:09.643554: step: 2408/1545, loss: 0.5559634566307068 2023-01-23 05:47:10.534285: step: 2410/1545, loss: 1.738154411315918 2023-01-23 05:47:11.383577: step: 2412/1545, loss: 0.7593392133712769 2023-01-23 05:47:12.312403: step: 2414/1545, loss: 0.5566662549972534 2023-01-23 05:47:13.199068: step: 2416/1545, loss: 0.9797518253326416 2023-01-23 05:47:14.052495: step: 2418/1545, loss: 0.9341845512390137 2023-01-23 05:47:14.982916: step: 2420/1545, loss: 1.140604019165039 2023-01-23 05:47:15.858803: step: 2422/1545, loss: 0.7483692169189453 2023-01-23 05:47:16.802385: step: 2424/1545, loss: 0.9151092767715454 2023-01-23 05:47:17.690920: step: 2426/1545, loss: 0.6391274929046631 2023-01-23 05:47:18.579575: step: 2428/1545, loss: 1.6153464317321777 2023-01-23 05:47:19.509980: step: 2430/1545, loss: 1.6740437746047974 2023-01-23 05:47:20.393595: step: 2432/1545, loss: 1.1312254667282104 2023-01-23 05:47:21.407405: step: 2434/1545, loss: 0.7872166633605957 2023-01-23 05:47:22.274233: step: 2436/1545, loss: 1.52683424949646 2023-01-23 05:47:23.187297: step: 2438/1545, loss: 1.2904082536697388 2023-01-23 05:47:24.047038: step: 2440/1545, loss: 0.5579237341880798 2023-01-23 05:47:24.908702: step: 2442/1545, loss: 0.8790760636329651 2023-01-23 05:47:25.797790: step: 2444/1545, loss: 2.96444034576416 2023-01-23 05:47:26.647001: step: 2446/1545, loss: 2.458545684814453 2023-01-23 05:47:27.511513: step: 2448/1545, loss: 1.5628960132598877 2023-01-23 05:47:28.366093: step: 2450/1545, loss: 0.5249378085136414 2023-01-23 05:47:29.291189: step: 2452/1545, loss: 1.1208183765411377 2023-01-23 05:47:30.161157: step: 2454/1545, loss: 1.265861988067627 2023-01-23 05:47:31.046616: step: 2456/1545, loss: 0.7490820288658142 2023-01-23 05:47:31.889238: step: 2458/1545, loss: 0.9155324697494507 2023-01-23 05:47:32.844501: step: 2460/1545, loss: 0.8469260931015015 2023-01-23 05:47:33.696349: step: 2462/1545, loss: 0.7727434039115906 2023-01-23 05:47:34.620463: step: 2464/1545, loss: 0.9914982318878174 2023-01-23 05:47:35.530499: step: 2466/1545, loss: 0.5798844695091248 2023-01-23 05:47:36.393518: step: 2468/1545, loss: 0.716646671295166 2023-01-23 05:47:37.268412: step: 2470/1545, loss: 3.3213918209075928 2023-01-23 05:47:38.167958: step: 2472/1545, loss: 4.05242919921875 2023-01-23 05:47:39.084155: step: 2474/1545, loss: 1.4874346256256104 2023-01-23 05:47:39.973594: step: 2476/1545, loss: 1.4046145677566528 2023-01-23 05:47:40.811714: step: 2478/1545, loss: 7.159915924072266 2023-01-23 05:47:41.702258: step: 2480/1545, loss: 0.6852790713310242 2023-01-23 05:47:42.590936: step: 2482/1545, loss: 1.2759380340576172 2023-01-23 05:47:43.486417: step: 2484/1545, loss: 1.1986833810806274 2023-01-23 05:47:44.388377: step: 2486/1545, loss: 3.4397692680358887 2023-01-23 05:47:45.259604: step: 2488/1545, loss: 0.7729688286781311 2023-01-23 05:47:46.162722: step: 2490/1545, loss: 1.125017762184143 2023-01-23 05:47:47.192152: step: 2492/1545, loss: 1.4844404458999634 2023-01-23 05:47:48.121990: step: 2494/1545, loss: 1.510564923286438 2023-01-23 05:47:48.978677: step: 2496/1545, loss: 1.3308796882629395 2023-01-23 05:47:49.834083: step: 2498/1545, loss: 0.6407856941223145 2023-01-23 05:47:50.735289: step: 2500/1545, loss: 1.4684998989105225 2023-01-23 05:47:51.617093: step: 2502/1545, loss: 0.6418526768684387 2023-01-23 05:47:52.478056: step: 2504/1545, loss: 1.073090672492981 2023-01-23 05:47:53.365695: step: 2506/1545, loss: 1.0712120532989502 2023-01-23 05:47:54.232873: step: 2508/1545, loss: 1.5163453817367554 2023-01-23 05:47:55.163322: step: 2510/1545, loss: 4.24892520904541 2023-01-23 05:47:56.052520: step: 2512/1545, loss: 0.6973613500595093 2023-01-23 05:47:56.934019: step: 2514/1545, loss: 0.7613804340362549 2023-01-23 05:47:57.799246: step: 2516/1545, loss: 0.7605746984481812 2023-01-23 05:47:58.669846: step: 2518/1545, loss: 0.8313897252082825 2023-01-23 05:47:59.560549: step: 2520/1545, loss: 0.8480675220489502 2023-01-23 05:48:00.457561: step: 2522/1545, loss: 3.0830376148223877 2023-01-23 05:48:01.315212: step: 2524/1545, loss: 0.4898408055305481 2023-01-23 05:48:02.221226: step: 2526/1545, loss: 0.860659658908844 2023-01-23 05:48:03.138403: step: 2528/1545, loss: 1.389190912246704 2023-01-23 05:48:03.982139: step: 2530/1545, loss: 1.6946954727172852 2023-01-23 05:48:04.948165: step: 2532/1545, loss: 1.2591114044189453 2023-01-23 05:48:05.821709: step: 2534/1545, loss: 0.6826120615005493 2023-01-23 05:48:06.680549: step: 2536/1545, loss: 1.3996442556381226 2023-01-23 05:48:07.559796: step: 2538/1545, loss: 0.6621110439300537 2023-01-23 05:48:08.481622: step: 2540/1545, loss: 1.381072759628296 2023-01-23 05:48:09.376530: step: 2542/1545, loss: 1.0613696575164795 2023-01-23 05:48:10.286916: step: 2544/1545, loss: 2.5095372200012207 2023-01-23 05:48:11.165625: step: 2546/1545, loss: 1.1854908466339111 2023-01-23 05:48:12.063224: step: 2548/1545, loss: 0.8197810649871826 2023-01-23 05:48:12.948292: step: 2550/1545, loss: 1.277604103088379 2023-01-23 05:48:13.825094: step: 2552/1545, loss: 1.14376962184906 2023-01-23 05:48:14.747137: step: 2554/1545, loss: 1.2428804636001587 2023-01-23 05:48:15.633324: step: 2556/1545, loss: 3.1887331008911133 2023-01-23 05:48:16.488853: step: 2558/1545, loss: 0.47522515058517456 2023-01-23 05:48:17.356079: step: 2560/1545, loss: 0.5776157975196838 2023-01-23 05:48:18.253212: step: 2562/1545, loss: 0.6008688807487488 2023-01-23 05:48:19.073213: step: 2564/1545, loss: 0.8075317740440369 2023-01-23 05:48:19.969269: step: 2566/1545, loss: 1.0445674657821655 2023-01-23 05:48:20.840537: step: 2568/1545, loss: 9.705816268920898 2023-01-23 05:48:21.688830: step: 2570/1545, loss: 0.5329177975654602 2023-01-23 05:48:22.555264: step: 2572/1545, loss: 0.9318610429763794 2023-01-23 05:48:23.425401: step: 2574/1545, loss: 3.22766375541687 2023-01-23 05:48:24.326968: step: 2576/1545, loss: 2.0982813835144043 2023-01-23 05:48:25.186896: step: 2578/1545, loss: 0.865628719329834 2023-01-23 05:48:26.053337: step: 2580/1545, loss: 0.8091229796409607 2023-01-23 05:48:26.906855: step: 2582/1545, loss: 1.0705236196517944 2023-01-23 05:48:27.853843: step: 2584/1545, loss: 0.5769184231758118 2023-01-23 05:48:28.787040: step: 2586/1545, loss: 0.8916604518890381 2023-01-23 05:48:29.659342: step: 2588/1545, loss: 0.5065488219261169 2023-01-23 05:48:30.547156: step: 2590/1545, loss: 4.371595859527588 2023-01-23 05:48:31.428505: step: 2592/1545, loss: 0.8557414412498474 2023-01-23 05:48:32.311795: step: 2594/1545, loss: 0.9373472929000854 2023-01-23 05:48:33.188909: step: 2596/1545, loss: 1.2218159437179565 2023-01-23 05:48:34.040296: step: 2598/1545, loss: 0.7561673521995544 2023-01-23 05:48:34.906979: step: 2600/1545, loss: 0.9598917365074158 2023-01-23 05:48:35.809851: step: 2602/1545, loss: 0.9875278472900391 2023-01-23 05:48:36.678125: step: 2604/1545, loss: 1.0482423305511475 2023-01-23 05:48:37.520735: step: 2606/1545, loss: 1.7626726627349854 2023-01-23 05:48:38.391415: step: 2608/1545, loss: 0.7883321642875671 2023-01-23 05:48:39.233516: step: 2610/1545, loss: 1.5479038953781128 2023-01-23 05:48:40.059577: step: 2612/1545, loss: 1.5601351261138916 2023-01-23 05:48:40.935758: step: 2614/1545, loss: 0.5218055248260498 2023-01-23 05:48:41.799568: step: 2616/1545, loss: 0.5409718155860901 2023-01-23 05:48:42.671574: step: 2618/1545, loss: 2.899146795272827 2023-01-23 05:48:43.562883: step: 2620/1545, loss: 0.6500975489616394 2023-01-23 05:48:44.413543: step: 2622/1545, loss: 0.3464343249797821 2023-01-23 05:48:45.296685: step: 2624/1545, loss: 0.716151237487793 2023-01-23 05:48:46.179712: step: 2626/1545, loss: 0.6689616441726685 2023-01-23 05:48:47.067971: step: 2628/1545, loss: 0.5697665810585022 2023-01-23 05:48:47.936256: step: 2630/1545, loss: 1.1173464059829712 2023-01-23 05:48:48.782277: step: 2632/1545, loss: 0.8300507068634033 2023-01-23 05:48:49.648239: step: 2634/1545, loss: 1.4254772663116455 2023-01-23 05:48:50.548160: step: 2636/1545, loss: 2.1442906856536865 2023-01-23 05:48:51.465949: step: 2638/1545, loss: 0.5834376811981201 2023-01-23 05:48:52.382020: step: 2640/1545, loss: 1.4222644567489624 2023-01-23 05:48:53.254725: step: 2642/1545, loss: 0.92196124792099 2023-01-23 05:48:54.143281: step: 2644/1545, loss: 1.2279181480407715 2023-01-23 05:48:55.015840: step: 2646/1545, loss: 1.0725762844085693 2023-01-23 05:48:55.896882: step: 2648/1545, loss: 3.234189510345459 2023-01-23 05:48:56.788612: step: 2650/1545, loss: 6.109043121337891 2023-01-23 05:48:57.689406: step: 2652/1545, loss: 0.7638752460479736 2023-01-23 05:48:58.593856: step: 2654/1545, loss: 1.1751607656478882 2023-01-23 05:48:59.499920: step: 2656/1545, loss: 0.9711552858352661 2023-01-23 05:49:00.385819: step: 2658/1545, loss: 1.2357360124588013 2023-01-23 05:49:01.273445: step: 2660/1545, loss: 3.1617271900177 2023-01-23 05:49:02.148255: step: 2662/1545, loss: 9.303524017333984 2023-01-23 05:49:03.036027: step: 2664/1545, loss: 0.8699169158935547 2023-01-23 05:49:03.906973: step: 2666/1545, loss: 1.3721219301223755 2023-01-23 05:49:04.751462: step: 2668/1545, loss: 1.0361523628234863 2023-01-23 05:49:05.597804: step: 2670/1545, loss: 0.5905728936195374 2023-01-23 05:49:06.477595: step: 2672/1545, loss: 0.9544439315795898 2023-01-23 05:49:07.361831: step: 2674/1545, loss: 7.804486274719238 2023-01-23 05:49:08.285116: step: 2676/1545, loss: 0.9426326751708984 2023-01-23 05:49:09.127130: step: 2678/1545, loss: 0.6093837022781372 2023-01-23 05:49:10.015718: step: 2680/1545, loss: 0.8524318933486938 2023-01-23 05:49:10.902217: step: 2682/1545, loss: 1.6113409996032715 2023-01-23 05:49:11.764085: step: 2684/1545, loss: 0.826755702495575 2023-01-23 05:49:12.640349: step: 2686/1545, loss: 2.5483851432800293 2023-01-23 05:49:13.541815: step: 2688/1545, loss: 3.6867828369140625 2023-01-23 05:49:14.406336: step: 2690/1545, loss: 2.9846608638763428 2023-01-23 05:49:15.290534: step: 2692/1545, loss: 1.381831169128418 2023-01-23 05:49:16.220671: step: 2694/1545, loss: 0.9937873482704163 2023-01-23 05:49:17.093225: step: 2696/1545, loss: 0.526128888130188 2023-01-23 05:49:17.961419: step: 2698/1545, loss: 1.4251312017440796 2023-01-23 05:49:18.796318: step: 2700/1545, loss: 0.9678131341934204 2023-01-23 05:49:19.704674: step: 2702/1545, loss: 0.5908358693122864 2023-01-23 05:49:20.596069: step: 2704/1545, loss: 1.3719863891601562 2023-01-23 05:49:21.472302: step: 2706/1545, loss: 1.5636630058288574 2023-01-23 05:49:22.296618: step: 2708/1545, loss: 5.387164115905762 2023-01-23 05:49:23.158162: step: 2710/1545, loss: 0.672640323638916 2023-01-23 05:49:23.995464: step: 2712/1545, loss: 7.741538047790527 2023-01-23 05:49:24.942396: step: 2714/1545, loss: 1.3881361484527588 2023-01-23 05:49:25.794045: step: 2716/1545, loss: 0.6189260482788086 2023-01-23 05:49:26.656231: step: 2718/1545, loss: 1.6297494173049927 2023-01-23 05:49:27.497744: step: 2720/1545, loss: 1.1225601434707642 2023-01-23 05:49:28.330734: step: 2722/1545, loss: 1.083922028541565 2023-01-23 05:49:29.223195: step: 2724/1545, loss: 1.515005111694336 2023-01-23 05:49:30.091151: step: 2726/1545, loss: 0.26313480734825134 2023-01-23 05:49:30.964273: step: 2728/1545, loss: 1.3790603876113892 2023-01-23 05:49:31.891799: step: 2730/1545, loss: 0.5484755635261536 2023-01-23 05:49:32.772366: step: 2732/1545, loss: 0.7131212949752808 2023-01-23 05:49:33.688639: step: 2734/1545, loss: 1.0821529626846313 2023-01-23 05:49:34.521912: step: 2736/1545, loss: 1.2112822532653809 2023-01-23 05:49:35.430700: step: 2738/1545, loss: 0.6742055416107178 2023-01-23 05:49:36.337192: step: 2740/1545, loss: 1.2643667459487915 2023-01-23 05:49:37.231577: step: 2742/1545, loss: 0.9303247332572937 2023-01-23 05:49:38.088713: step: 2744/1545, loss: 1.9010670185089111 2023-01-23 05:49:38.981090: step: 2746/1545, loss: 4.1768798828125 2023-01-23 05:49:39.888891: step: 2748/1545, loss: 1.5925674438476562 2023-01-23 05:49:40.790311: step: 2750/1545, loss: 0.630104660987854 2023-01-23 05:49:41.636052: step: 2752/1545, loss: 9.007349014282227 2023-01-23 05:49:42.507481: step: 2754/1545, loss: 0.9785153269767761 2023-01-23 05:49:43.373060: step: 2756/1545, loss: 1.2876880168914795 2023-01-23 05:49:44.219499: step: 2758/1545, loss: 1.2299258708953857 2023-01-23 05:49:45.071737: step: 2760/1545, loss: 3.554821729660034 2023-01-23 05:49:46.001192: step: 2762/1545, loss: 1.6132904291152954 2023-01-23 05:49:46.878282: step: 2764/1545, loss: 3.059115409851074 2023-01-23 05:49:47.759790: step: 2766/1545, loss: 1.6590007543563843 2023-01-23 05:49:48.647543: step: 2768/1545, loss: 1.247865915298462 2023-01-23 05:49:49.513327: step: 2770/1545, loss: 0.44456684589385986 2023-01-23 05:49:50.454992: step: 2772/1545, loss: 1.7126206159591675 2023-01-23 05:49:51.308363: step: 2774/1545, loss: 0.6815442442893982 2023-01-23 05:49:52.157961: step: 2776/1545, loss: 1.7974499464035034 2023-01-23 05:49:53.042057: step: 2778/1545, loss: 0.8273130655288696 2023-01-23 05:49:53.960653: step: 2780/1545, loss: 1.0598965883255005 2023-01-23 05:49:54.860097: step: 2782/1545, loss: 0.5566844344139099 2023-01-23 05:49:55.714355: step: 2784/1545, loss: 1.0121053457260132 2023-01-23 05:49:56.625930: step: 2786/1545, loss: 1.0689107179641724 2023-01-23 05:49:57.532102: step: 2788/1545, loss: 1.2023245096206665 2023-01-23 05:49:58.493731: step: 2790/1545, loss: 0.7778468728065491 2023-01-23 05:49:59.360771: step: 2792/1545, loss: 0.9954265356063843 2023-01-23 05:50:00.220202: step: 2794/1545, loss: 0.6553298830986023 2023-01-23 05:50:01.130388: step: 2796/1545, loss: 6.9314398765563965 2023-01-23 05:50:02.034562: step: 2798/1545, loss: 0.6124110817909241 2023-01-23 05:50:02.923817: step: 2800/1545, loss: 0.8214631080627441 2023-01-23 05:50:03.810832: step: 2802/1545, loss: 1.6390761137008667 2023-01-23 05:50:04.687450: step: 2804/1545, loss: 1.1052165031433105 2023-01-23 05:50:05.552821: step: 2806/1545, loss: 3.2954249382019043 2023-01-23 05:50:06.430193: step: 2808/1545, loss: 1.4152607917785645 2023-01-23 05:50:07.297405: step: 2810/1545, loss: 0.7306228280067444 2023-01-23 05:50:08.156374: step: 2812/1545, loss: 0.6035749912261963 2023-01-23 05:50:09.001312: step: 2814/1545, loss: 1.0048127174377441 2023-01-23 05:50:09.853499: step: 2816/1545, loss: 0.5940400958061218 2023-01-23 05:50:10.730832: step: 2818/1545, loss: 3.396796464920044 2023-01-23 05:50:11.597520: step: 2820/1545, loss: 3.5266854763031006 2023-01-23 05:50:12.521046: step: 2822/1545, loss: 0.8176065683364868 2023-01-23 05:50:13.378409: step: 2824/1545, loss: 0.979278564453125 2023-01-23 05:50:14.208483: step: 2826/1545, loss: 0.8729529976844788 2023-01-23 05:50:15.063182: step: 2828/1545, loss: 0.6792396903038025 2023-01-23 05:50:15.964437: step: 2830/1545, loss: 1.3655579090118408 2023-01-23 05:50:16.845212: step: 2832/1545, loss: 4.22922945022583 2023-01-23 05:50:17.768599: step: 2834/1545, loss: 1.6376663446426392 2023-01-23 05:50:18.666216: step: 2836/1545, loss: 1.546345591545105 2023-01-23 05:50:19.535322: step: 2838/1545, loss: 1.4586375951766968 2023-01-23 05:50:20.405148: step: 2840/1545, loss: 1.266482949256897 2023-01-23 05:50:21.289128: step: 2842/1545, loss: 3.236555337905884 2023-01-23 05:50:22.188673: step: 2844/1545, loss: 0.7525172829627991 2023-01-23 05:50:23.171225: step: 2846/1545, loss: 1.3234117031097412 2023-01-23 05:50:24.127756: step: 2848/1545, loss: 0.892853319644928 2023-01-23 05:50:25.071386: step: 2850/1545, loss: 1.1306477785110474 2023-01-23 05:50:25.951772: step: 2852/1545, loss: 0.8434217572212219 2023-01-23 05:50:26.838549: step: 2854/1545, loss: 1.1801708936691284 2023-01-23 05:50:27.700545: step: 2856/1545, loss: 6.17758846282959 2023-01-23 05:50:28.586050: step: 2858/1545, loss: 0.9665339589118958 2023-01-23 05:50:29.478474: step: 2860/1545, loss: 0.985522985458374 2023-01-23 05:50:30.320125: step: 2862/1545, loss: 1.2567145824432373 2023-01-23 05:50:31.122030: step: 2864/1545, loss: 1.028913974761963 2023-01-23 05:50:31.976875: step: 2866/1545, loss: 0.47656261920928955 2023-01-23 05:50:32.837364: step: 2868/1545, loss: 1.6206650733947754 2023-01-23 05:50:33.738193: step: 2870/1545, loss: 1.1910098791122437 2023-01-23 05:50:34.603293: step: 2872/1545, loss: 2.9784252643585205 2023-01-23 05:50:35.459444: step: 2874/1545, loss: 0.705570638179779 2023-01-23 05:50:36.357783: step: 2876/1545, loss: 1.6785688400268555 2023-01-23 05:50:37.266341: step: 2878/1545, loss: 1.524505853652954 2023-01-23 05:50:38.158834: step: 2880/1545, loss: 0.7620023488998413 2023-01-23 05:50:39.053872: step: 2882/1545, loss: 6.84545373916626 2023-01-23 05:50:39.929812: step: 2884/1545, loss: 1.1281296014785767 2023-01-23 05:50:40.806757: step: 2886/1545, loss: 1.064469337463379 2023-01-23 05:50:41.656147: step: 2888/1545, loss: 3.3697667121887207 2023-01-23 05:50:42.534841: step: 2890/1545, loss: 0.9384564161300659 2023-01-23 05:50:43.388349: step: 2892/1545, loss: 1.021353840827942 2023-01-23 05:50:44.227274: step: 2894/1545, loss: 3.192699432373047 2023-01-23 05:50:45.086391: step: 2896/1545, loss: 0.788902223110199 2023-01-23 05:50:45.965792: step: 2898/1545, loss: 1.668044924736023 2023-01-23 05:50:46.814161: step: 2900/1545, loss: 0.8700380325317383 2023-01-23 05:50:47.715193: step: 2902/1545, loss: 1.5859659910202026 2023-01-23 05:50:48.565804: step: 2904/1545, loss: 2.093827486038208 2023-01-23 05:50:49.476687: step: 2906/1545, loss: 1.2531499862670898 2023-01-23 05:50:50.372742: step: 2908/1545, loss: 1.0675357580184937 2023-01-23 05:50:51.300816: step: 2910/1545, loss: 0.47274094820022583 2023-01-23 05:50:52.173802: step: 2912/1545, loss: 1.1659396886825562 2023-01-23 05:50:53.072459: step: 2914/1545, loss: 3.2407500743865967 2023-01-23 05:50:53.994181: step: 2916/1545, loss: 2.2509098052978516 2023-01-23 05:50:54.849427: step: 2918/1545, loss: 2.1141912937164307 2023-01-23 05:50:55.707262: step: 2920/1545, loss: 8.61052417755127 2023-01-23 05:50:56.564718: step: 2922/1545, loss: 3.3841536045074463 2023-01-23 05:50:57.419629: step: 2924/1545, loss: 1.2448554039001465 2023-01-23 05:50:58.351419: step: 2926/1545, loss: 1.028791904449463 2023-01-23 05:50:59.248766: step: 2928/1545, loss: 1.4185271263122559 2023-01-23 05:51:00.146444: step: 2930/1545, loss: 0.7557521462440491 2023-01-23 05:51:01.030910: step: 2932/1545, loss: 0.8962587714195251 2023-01-23 05:51:01.901694: step: 2934/1545, loss: 1.3044036626815796 2023-01-23 05:51:02.803241: step: 2936/1545, loss: 0.949617862701416 2023-01-23 05:51:03.644998: step: 2938/1545, loss: 0.2632312476634979 2023-01-23 05:51:04.490442: step: 2940/1545, loss: 3.075233221054077 2023-01-23 05:51:05.392384: step: 2942/1545, loss: 0.8628420829772949 2023-01-23 05:51:06.251939: step: 2944/1545, loss: 0.8262337446212769 2023-01-23 05:51:07.136803: step: 2946/1545, loss: 1.4704053401947021 2023-01-23 05:51:08.067644: step: 2948/1545, loss: 0.9812518358230591 2023-01-23 05:51:08.927188: step: 2950/1545, loss: 0.6464030742645264 2023-01-23 05:51:09.818294: step: 2952/1545, loss: 1.7934952974319458 2023-01-23 05:51:10.709961: step: 2954/1545, loss: 1.1207610368728638 2023-01-23 05:51:11.585675: step: 2956/1545, loss: 6.560628890991211 2023-01-23 05:51:12.483153: step: 2958/1545, loss: 1.0002049207687378 2023-01-23 05:51:13.345987: step: 2960/1545, loss: 1.1666383743286133 2023-01-23 05:51:14.250335: step: 2962/1545, loss: 1.3969331979751587 2023-01-23 05:51:15.159216: step: 2964/1545, loss: 0.48465004563331604 2023-01-23 05:51:16.033398: step: 2966/1545, loss: 0.8910053968429565 2023-01-23 05:51:16.873456: step: 2968/1545, loss: 0.7840720415115356 2023-01-23 05:51:17.726018: step: 2970/1545, loss: 1.0385403633117676 2023-01-23 05:51:18.589685: step: 2972/1545, loss: 2.240638256072998 2023-01-23 05:51:19.518362: step: 2974/1545, loss: 3.3027536869049072 2023-01-23 05:51:20.468357: step: 2976/1545, loss: 0.9627964496612549 2023-01-23 05:51:21.347688: step: 2978/1545, loss: 1.184945821762085 2023-01-23 05:51:22.227174: step: 2980/1545, loss: 1.6415269374847412 2023-01-23 05:51:23.178333: step: 2982/1545, loss: 0.751107394695282 2023-01-23 05:51:24.117401: step: 2984/1545, loss: 0.6673790812492371 2023-01-23 05:51:24.962425: step: 2986/1545, loss: 1.1034014225006104 2023-01-23 05:51:25.853773: step: 2988/1545, loss: 0.7099111676216125 2023-01-23 05:51:26.763755: step: 2990/1545, loss: 0.9154269695281982 2023-01-23 05:51:27.667886: step: 2992/1545, loss: 0.8466952443122864 2023-01-23 05:51:28.570699: step: 2994/1545, loss: 0.6452532410621643 2023-01-23 05:51:29.471727: step: 2996/1545, loss: 0.6158635020256042 2023-01-23 05:51:30.350655: step: 2998/1545, loss: 1.0876985788345337 2023-01-23 05:51:31.241900: step: 3000/1545, loss: 4.539388179779053 2023-01-23 05:51:32.151605: step: 3002/1545, loss: 1.2532349824905396 2023-01-23 05:51:33.057704: step: 3004/1545, loss: 2.947148323059082 2023-01-23 05:51:33.932544: step: 3006/1545, loss: 1.785713791847229 2023-01-23 05:51:34.797109: step: 3008/1545, loss: 1.07610285282135 2023-01-23 05:51:35.664743: step: 3010/1545, loss: 1.3666521310806274 2023-01-23 05:51:36.558138: step: 3012/1545, loss: 1.0837178230285645 2023-01-23 05:51:37.556232: step: 3014/1545, loss: 4.290818691253662 2023-01-23 05:51:38.444696: step: 3016/1545, loss: 1.4725172519683838 2023-01-23 05:51:39.339322: step: 3018/1545, loss: 1.9792606830596924 2023-01-23 05:51:40.249304: step: 3020/1545, loss: 0.5490928292274475 2023-01-23 05:51:41.091188: step: 3022/1545, loss: 1.189521312713623 2023-01-23 05:51:41.967627: step: 3024/1545, loss: 2.1527888774871826 2023-01-23 05:51:42.839963: step: 3026/1545, loss: 1.1696434020996094 2023-01-23 05:51:43.701470: step: 3028/1545, loss: 3.1509079933166504 2023-01-23 05:51:44.609156: step: 3030/1545, loss: 1.2678582668304443 2023-01-23 05:51:45.462870: step: 3032/1545, loss: 0.5888697504997253 2023-01-23 05:51:46.310615: step: 3034/1545, loss: 0.6165697574615479 2023-01-23 05:51:47.246548: step: 3036/1545, loss: 0.840735137462616 2023-01-23 05:51:48.127692: step: 3038/1545, loss: 1.0328313112258911 2023-01-23 05:51:49.024502: step: 3040/1545, loss: 0.6558700203895569 2023-01-23 05:51:49.876503: step: 3042/1545, loss: 1.433127760887146 2023-01-23 05:51:50.744523: step: 3044/1545, loss: 0.7707238793373108 2023-01-23 05:51:51.654133: step: 3046/1545, loss: 0.7832382321357727 2023-01-23 05:51:52.513082: step: 3048/1545, loss: 1.5784434080123901 2023-01-23 05:51:53.342972: step: 3050/1545, loss: 6.256181240081787 2023-01-23 05:51:54.224871: step: 3052/1545, loss: 1.2249526977539062 2023-01-23 05:51:55.087304: step: 3054/1545, loss: 2.649127960205078 2023-01-23 05:51:55.984993: step: 3056/1545, loss: 1.8813188076019287 2023-01-23 05:51:56.854583: step: 3058/1545, loss: 0.8273302316665649 2023-01-23 05:51:57.715874: step: 3060/1545, loss: 0.9737459421157837 2023-01-23 05:51:58.581433: step: 3062/1545, loss: 0.9247097373008728 2023-01-23 05:51:59.508549: step: 3064/1545, loss: 7.242690086364746 2023-01-23 05:52:00.349312: step: 3066/1545, loss: 0.5441460609436035 2023-01-23 05:52:01.234120: step: 3068/1545, loss: 1.2642107009887695 2023-01-23 05:52:02.070622: step: 3070/1545, loss: 0.4225403368473053 2023-01-23 05:52:02.961913: step: 3072/1545, loss: 1.042083978652954 2023-01-23 05:52:03.952314: step: 3074/1545, loss: 0.9412772059440613 2023-01-23 05:52:04.816382: step: 3076/1545, loss: 0.34324347972869873 2023-01-23 05:52:05.662103: step: 3078/1545, loss: 0.3956749439239502 2023-01-23 05:52:06.519509: step: 3080/1545, loss: 1.0605164766311646 2023-01-23 05:52:07.384637: step: 3082/1545, loss: 3.211163282394409 2023-01-23 05:52:08.251626: step: 3084/1545, loss: 6.4946370124816895 2023-01-23 05:52:09.122646: step: 3086/1545, loss: 0.6808621287345886 2023-01-23 05:52:09.969879: step: 3088/1545, loss: 7.267405033111572 2023-01-23 05:52:10.838282: step: 3090/1545, loss: 3.1110260486602783 ================================================== Loss: 1.769 -------------------- Dev Chinese: {'event': {'p': 0.5976008724100327, 'r': 0.729693741677763, 'f1': 0.657074340527578}, 'argument': {'p': 0.6028173133182873, 'r': 0.6596273219032567, 'f1': 0.6299440924176101}, 'combined': 0.41392009909454475, 'epoch': 1} Test Chinese: {'event': {'p': 0.6350053361792957, 'r': 0.7608695652173914, 'f1': 0.692262943571844}, 'argument': {'p': 0.6367310808893076, 'r': 0.7166870066956367, 'f1': 0.6743472643356324}, 'combined': 0.4668256221986053, 'epoch': 1} Dev Korean: {'event': {'p': 0.6061269146608315, 'r': 0.7376830892143809, 'f1': 0.6654654654654655}, 'argument': {'p': 0.6008600156798031, 'r': 0.6690267041603817, 'f1': 0.6331137882953913}, 'combined': 0.42131536182059676, 'epoch': 1} Test Korean: {'event': {'p': 0.6232804232804233, 'r': 0.7531969309462916, 'f1': 0.6821077012159815}, 'argument': {'p': 0.6315981785010799, 'r': 0.7147159189006099, 'f1': 0.6705913180208881}, 'combined': 0.4574155023906232, 'epoch': 1} Dev Russian: {'event': {'p': 0.5698818897637795, 'r': 0.7709720372836218, 'f1': 0.6553480475382004}, 'argument': {'p': 0.5917286542565424, 'r': 0.6709364268735599, 'f1': 0.6288481639331521}, 'combined': 0.4121144164315734, 'epoch': 1} Test Russian: {'event': {'p': 0.6178375685102142, 'r': 0.7928388746803069, 'f1': 0.69448333800056}, 'argument': {'p': 0.6356813558492974, 'r': 0.7266631010476607, 'f1': 0.6781342016420302}, 'combined': 0.47095290396870193, 'epoch': 1} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.5602212602212602, 'r': 0.6805993822522747, 'f1': 0.614571083974069}, 'combined': 0.42833742216374515, 'epoch': 1} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.5115322670045308, 'r': 0.26287074832177276, 'f1': 0.34727878677371815}, 'combined': 0.21324136029965152, 'epoch': 1} Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.499025657742763, 'r': 0.5703150374203005, 'f1': 0.5322940349256139}, 'combined': 0.2829917654034909, 'epoch': 1} New best chinese model... New best korean model... New best russian model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5976008724100327, 'r': 0.729693741677763, 'f1': 0.657074340527578}, 'argument': {'p': 0.6028173133182873, 'r': 0.6596273219032567, 'f1': 0.6299440924176101}, 'combined': 0.41392009909454475, 'epoch': 1} Test for Chinese: {'event': {'p': 0.6350053361792957, 'r': 0.7608695652173914, 'f1': 0.692262943571844}, 'argument': {'p': 0.6367310808893076, 'r': 0.7166870066956367, 'f1': 0.6743472643356324}, 'combined': 0.4668256221986053, 'epoch': 1} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.5602212602212602, 'r': 0.6805993822522747, 'f1': 0.614571083974069}, 'combined': 0.42833742216374515, 'epoch': 1} -------------------- Dev for Korean: {'event': {'p': 0.6061269146608315, 'r': 0.7376830892143809, 'f1': 0.6654654654654655}, 'argument': {'p': 0.6008600156798031, 'r': 0.6690267041603817, 'f1': 0.6331137882953913}, 'combined': 0.42131536182059676, 'epoch': 1} Test for Korean: {'event': {'p': 0.6232804232804233, 'r': 0.7531969309462916, 'f1': 0.6821077012159815}, 'argument': {'p': 0.6315981785010799, 'r': 0.7147159189006099, 'f1': 0.6705913180208881}, 'combined': 0.4574155023906232, 'epoch': 1} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.5115322670045308, 'r': 0.26287074832177276, 'f1': 0.34727878677371815}, 'combined': 0.21324136029965152, 'epoch': 1} -------------------- Dev for Russian: {'event': {'p': 0.5698818897637795, 'r': 0.7709720372836218, 'f1': 0.6553480475382004}, 'argument': {'p': 0.5917286542565424, 'r': 0.6709364268735599, 'f1': 0.6288481639331521}, 'combined': 0.4121144164315734, 'epoch': 1} Test for Russian: {'event': {'p': 0.6178375685102142, 'r': 0.7928388746803069, 'f1': 0.69448333800056}, 'argument': {'p': 0.6356813558492974, 'r': 0.7266631010476607, 'f1': 0.6781342016420302}, 'combined': 0.47095290396870193, 'epoch': 1} Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.499025657742763, 'r': 0.5703150374203005, 'f1': 0.5322940349256139}, 'combined': 0.2829917654034909, 'epoch': 1} ****************************** Epoch: 2 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 05:57:42.979849: step: 2/1545, loss: 1.3297486305236816 2023-01-23 05:57:43.852556: step: 4/1545, loss: 1.2991448640823364 2023-01-23 05:57:44.766253: step: 6/1545, loss: 0.7078776359558105 2023-01-23 05:57:45.728706: step: 8/1545, loss: 0.9362592101097107 2023-01-23 05:57:46.682371: step: 10/1545, loss: 0.9317670464515686 2023-01-23 05:57:47.558447: step: 12/1545, loss: 1.0500307083129883 2023-01-23 05:57:48.428011: step: 14/1545, loss: 0.6382607817649841 2023-01-23 05:57:49.295927: step: 16/1545, loss: 2.9002573490142822 2023-01-23 05:57:50.143777: step: 18/1545, loss: 0.7839460372924805 2023-01-23 05:57:51.043820: step: 20/1545, loss: 2.8905909061431885 2023-01-23 05:57:51.965500: step: 22/1545, loss: 1.3969954252243042 2023-01-23 05:57:52.828711: step: 24/1545, loss: 0.7285501956939697 2023-01-23 05:57:53.706810: step: 26/1545, loss: 0.6016092300415039 2023-01-23 05:57:54.528347: step: 28/1545, loss: 1.1332526206970215 2023-01-23 05:57:55.397095: step: 30/1545, loss: 0.6630937457084656 2023-01-23 05:57:56.315601: step: 32/1545, loss: 0.6870733499526978 2023-01-23 05:57:57.203008: step: 34/1545, loss: 0.5402155518531799 2023-01-23 05:57:58.117251: step: 36/1545, loss: 1.013369083404541 2023-01-23 05:57:59.046946: step: 38/1545, loss: 0.8058503270149231 2023-01-23 05:57:59.945964: step: 40/1545, loss: 0.8360027074813843 2023-01-23 05:58:00.821222: step: 42/1545, loss: 1.487958312034607 2023-01-23 05:58:01.720520: step: 44/1545, loss: 0.8805326223373413 2023-01-23 05:58:02.641764: step: 46/1545, loss: 0.7395769357681274 2023-01-23 05:58:03.538027: step: 48/1545, loss: 0.5846818089485168 2023-01-23 05:58:04.504722: step: 50/1545, loss: 0.9604097604751587 2023-01-23 05:58:05.371447: step: 52/1545, loss: 1.3656624555587769 2023-01-23 05:58:06.300427: step: 54/1545, loss: 1.3495957851409912 2023-01-23 05:58:07.190457: step: 56/1545, loss: 0.9901919960975647 2023-01-23 05:58:08.054504: step: 58/1545, loss: 1.0449578762054443 2023-01-23 05:58:08.914908: step: 60/1545, loss: 0.33168137073516846 2023-01-23 05:58:09.817097: step: 62/1545, loss: 1.0037258863449097 2023-01-23 05:58:10.668640: step: 64/1545, loss: 1.5738574266433716 2023-01-23 05:58:11.536170: step: 66/1545, loss: 3.5076239109039307 2023-01-23 05:58:12.388468: step: 68/1545, loss: 0.5468751192092896 2023-01-23 05:58:13.322566: step: 70/1545, loss: 0.8422093391418457 2023-01-23 05:58:14.235871: step: 72/1545, loss: 1.2967591285705566 2023-01-23 05:58:15.111308: step: 74/1545, loss: 0.8592974543571472 2023-01-23 05:58:16.021325: step: 76/1545, loss: 0.8360338807106018 2023-01-23 05:58:16.898633: step: 78/1545, loss: 1.4757957458496094 2023-01-23 05:58:17.749891: step: 80/1545, loss: 0.6676158905029297 2023-01-23 05:58:18.604312: step: 82/1545, loss: 0.5956865549087524 2023-01-23 05:58:19.538024: step: 84/1545, loss: 1.1994781494140625 2023-01-23 05:58:20.379197: step: 86/1545, loss: 1.1499569416046143 2023-01-23 05:58:21.330915: step: 88/1545, loss: 1.3215454816818237 2023-01-23 05:58:22.227465: step: 90/1545, loss: 1.339681625366211 2023-01-23 05:58:23.119765: step: 92/1545, loss: 0.546328067779541 2023-01-23 05:58:24.037786: step: 94/1545, loss: 1.4051707983016968 2023-01-23 05:58:24.977767: step: 96/1545, loss: 1.1681663990020752 2023-01-23 05:58:25.922897: step: 98/1545, loss: 0.6824421286582947 2023-01-23 05:58:26.820301: step: 100/1545, loss: 0.6934859752655029 2023-01-23 05:58:27.721466: step: 102/1545, loss: 1.65715754032135 2023-01-23 05:58:28.621649: step: 104/1545, loss: 0.7274887561798096 2023-01-23 05:58:29.529929: step: 106/1545, loss: 0.5660488605499268 2023-01-23 05:58:30.453939: step: 108/1545, loss: 1.6350131034851074 2023-01-23 05:58:31.464733: step: 110/1545, loss: 1.1577874422073364 2023-01-23 05:58:32.340848: step: 112/1545, loss: 0.6091365218162537 2023-01-23 05:58:33.216273: step: 114/1545, loss: 3.2330188751220703 2023-01-23 05:58:34.130331: step: 116/1545, loss: 3.0297811031341553 2023-01-23 05:58:35.048356: step: 118/1545, loss: 0.7509654760360718 2023-01-23 05:58:35.981282: step: 120/1545, loss: 0.4815255105495453 2023-01-23 05:58:36.850477: step: 122/1545, loss: 1.1120591163635254 2023-01-23 05:58:37.716296: step: 124/1545, loss: 2.1090378761291504 2023-01-23 05:58:38.570316: step: 126/1545, loss: 0.4937931001186371 2023-01-23 05:58:39.446058: step: 128/1545, loss: 1.1807615756988525 2023-01-23 05:58:40.342752: step: 130/1545, loss: 2.939906597137451 2023-01-23 05:58:41.252736: step: 132/1545, loss: 0.8853132128715515 2023-01-23 05:58:42.139194: step: 134/1545, loss: 3.4716928005218506 2023-01-23 05:58:43.032558: step: 136/1545, loss: 0.6640578508377075 2023-01-23 05:58:43.902197: step: 138/1545, loss: 4.951048374176025 2023-01-23 05:58:44.746405: step: 140/1545, loss: 0.7519556879997253 2023-01-23 05:58:45.759805: step: 142/1545, loss: 1.468375325202942 2023-01-23 05:58:46.648811: step: 144/1545, loss: 1.3087631464004517 2023-01-23 05:58:47.537805: step: 146/1545, loss: 0.9874944686889648 2023-01-23 05:58:48.408230: step: 148/1545, loss: 1.2230067253112793 2023-01-23 05:58:49.296337: step: 150/1545, loss: 2.9726743698120117 2023-01-23 05:58:50.185811: step: 152/1545, loss: 1.041949987411499 2023-01-23 05:58:51.092586: step: 154/1545, loss: 0.7344487309455872 2023-01-23 05:58:52.067349: step: 156/1545, loss: 1.0020880699157715 2023-01-23 05:58:52.939692: step: 158/1545, loss: 0.47395408153533936 2023-01-23 05:58:53.922799: step: 160/1545, loss: 0.5408796668052673 2023-01-23 05:58:54.816039: step: 162/1545, loss: 0.9837980270385742 2023-01-23 05:58:55.717371: step: 164/1545, loss: 0.6626771688461304 2023-01-23 05:58:56.631821: step: 166/1545, loss: 0.8179726600646973 2023-01-23 05:58:57.544616: step: 168/1545, loss: 3.590522050857544 2023-01-23 05:58:58.437696: step: 170/1545, loss: 0.4803752601146698 2023-01-23 05:58:59.326157: step: 172/1545, loss: 1.1063883304595947 2023-01-23 05:59:00.174949: step: 174/1545, loss: 0.7797290682792664 2023-01-23 05:59:01.145186: step: 176/1545, loss: 0.6613909006118774 2023-01-23 05:59:02.040855: step: 178/1545, loss: 0.8448843359947205 2023-01-23 05:59:02.941664: step: 180/1545, loss: 1.1911053657531738 2023-01-23 05:59:03.806670: step: 182/1545, loss: 0.8732295632362366 2023-01-23 05:59:04.710102: step: 184/1545, loss: 0.8473087549209595 2023-01-23 05:59:05.571747: step: 186/1545, loss: 0.8375707268714905 2023-01-23 05:59:06.448391: step: 188/1545, loss: 0.773801863193512 2023-01-23 05:59:07.335066: step: 190/1545, loss: 0.8899549245834351 2023-01-23 05:59:08.232536: step: 192/1545, loss: 0.6041489839553833 2023-01-23 05:59:09.112720: step: 194/1545, loss: 0.5784350037574768 2023-01-23 05:59:10.033639: step: 196/1545, loss: 2.9715261459350586 2023-01-23 05:59:10.961963: step: 198/1545, loss: 1.5810339450836182 2023-01-23 05:59:11.838276: step: 200/1545, loss: 0.9747074246406555 2023-01-23 05:59:12.723287: step: 202/1545, loss: 0.8321868181228638 2023-01-23 05:59:13.617435: step: 204/1545, loss: 0.7052026391029358 2023-01-23 05:59:14.486681: step: 206/1545, loss: 0.9511076807975769 2023-01-23 05:59:15.352713: step: 208/1545, loss: 1.8689087629318237 2023-01-23 05:59:16.252150: step: 210/1545, loss: 0.7005360722541809 2023-01-23 05:59:17.125160: step: 212/1545, loss: 1.0130736827850342 2023-01-23 05:59:17.968972: step: 214/1545, loss: 0.7336393594741821 2023-01-23 05:59:18.843530: step: 216/1545, loss: 1.0890120267868042 2023-01-23 05:59:19.733510: step: 218/1545, loss: 0.9981014728546143 2023-01-23 05:59:20.579191: step: 220/1545, loss: 2.751951217651367 2023-01-23 05:59:21.470732: step: 222/1545, loss: 0.9060100317001343 2023-01-23 05:59:22.350508: step: 224/1545, loss: 3.0683445930480957 2023-01-23 05:59:23.198686: step: 226/1545, loss: 1.1957879066467285 2023-01-23 05:59:24.079165: step: 228/1545, loss: 3.0201621055603027 2023-01-23 05:59:24.974947: step: 230/1545, loss: 3.076974630355835 2023-01-23 05:59:25.837656: step: 232/1545, loss: 0.7084323167800903 2023-01-23 05:59:26.722146: step: 234/1545, loss: 1.3477141857147217 2023-01-23 05:59:27.597977: step: 236/1545, loss: 6.916990756988525 2023-01-23 05:59:28.449329: step: 238/1545, loss: 0.49980756640434265 2023-01-23 05:59:29.351094: step: 240/1545, loss: 1.3648511171340942 2023-01-23 05:59:30.288833: step: 242/1545, loss: 0.9514776468276978 2023-01-23 05:59:31.154434: step: 244/1545, loss: 0.6872262358665466 2023-01-23 05:59:32.046783: step: 246/1545, loss: 2.352350950241089 2023-01-23 05:59:32.920198: step: 248/1545, loss: 1.5713046789169312 2023-01-23 05:59:33.778766: step: 250/1545, loss: 1.023024082183838 2023-01-23 05:59:34.654319: step: 252/1545, loss: 0.5695706009864807 2023-01-23 05:59:35.633521: step: 254/1545, loss: 1.5100147724151611 2023-01-23 05:59:36.518385: step: 256/1545, loss: 3.485071897506714 2023-01-23 05:59:37.388312: step: 258/1545, loss: 0.9501185417175293 2023-01-23 05:59:38.253014: step: 260/1545, loss: 0.7182027697563171 2023-01-23 05:59:39.220991: step: 262/1545, loss: 0.8567444682121277 2023-01-23 05:59:40.085207: step: 264/1545, loss: 0.8226269483566284 2023-01-23 05:59:41.047365: step: 266/1545, loss: 1.2251163721084595 2023-01-23 05:59:41.925263: step: 268/1545, loss: 0.9329964518547058 2023-01-23 05:59:42.833543: step: 270/1545, loss: 0.28249990940093994 2023-01-23 05:59:43.740754: step: 272/1545, loss: 3.00343656539917 2023-01-23 05:59:44.571656: step: 274/1545, loss: 0.573904275894165 2023-01-23 05:59:45.492782: step: 276/1545, loss: 1.880926251411438 2023-01-23 05:59:46.410230: step: 278/1545, loss: 2.8210055828094482 2023-01-23 05:59:47.318847: step: 280/1545, loss: 1.3716109991073608 2023-01-23 05:59:48.182279: step: 282/1545, loss: 7.092351913452148 2023-01-23 05:59:49.120352: step: 284/1545, loss: 6.572216987609863 2023-01-23 05:59:49.984924: step: 286/1545, loss: 0.7301847338676453 2023-01-23 05:59:50.877559: step: 288/1545, loss: 0.6165364980697632 2023-01-23 05:59:51.767855: step: 290/1545, loss: 1.0137808322906494 2023-01-23 05:59:52.616716: step: 292/1545, loss: 0.3957183361053467 2023-01-23 05:59:53.471627: step: 294/1545, loss: 3.1263551712036133 2023-01-23 05:59:54.339617: step: 296/1545, loss: 0.8274261355400085 2023-01-23 05:59:55.247191: step: 298/1545, loss: 3.1413002014160156 2023-01-23 05:59:56.140738: step: 300/1545, loss: 3.337341785430908 2023-01-23 05:59:57.060491: step: 302/1545, loss: 0.7867300510406494 2023-01-23 05:59:57.957031: step: 304/1545, loss: 0.7376832962036133 2023-01-23 05:59:58.858752: step: 306/1545, loss: 1.0720313787460327 2023-01-23 05:59:59.767036: step: 308/1545, loss: 0.9092682600021362 2023-01-23 06:00:00.630898: step: 310/1545, loss: 0.7759250998497009 2023-01-23 06:00:01.552654: step: 312/1545, loss: 0.5610350370407104 2023-01-23 06:00:02.443160: step: 314/1545, loss: 1.4714454412460327 2023-01-23 06:00:03.386490: step: 316/1545, loss: 0.9580036997795105 2023-01-23 06:00:04.273845: step: 318/1545, loss: 0.5117520689964294 2023-01-23 06:00:05.178697: step: 320/1545, loss: 3.331580638885498 2023-01-23 06:00:06.038766: step: 322/1545, loss: 0.48887917399406433 2023-01-23 06:00:07.046187: step: 324/1545, loss: 0.4287315309047699 2023-01-23 06:00:07.904407: step: 326/1545, loss: 0.9968904852867126 2023-01-23 06:00:08.818890: step: 328/1545, loss: 3.654350757598877 2023-01-23 06:00:09.714091: step: 330/1545, loss: 1.1533384323120117 2023-01-23 06:00:10.556159: step: 332/1545, loss: 2.9271445274353027 2023-01-23 06:00:11.427721: step: 334/1545, loss: 0.6731301546096802 2023-01-23 06:00:12.271082: step: 336/1545, loss: 1.2038161754608154 2023-01-23 06:00:13.167177: step: 338/1545, loss: 1.0961967706680298 2023-01-23 06:00:14.023661: step: 340/1545, loss: 0.330649733543396 2023-01-23 06:00:14.920054: step: 342/1545, loss: 0.8331710696220398 2023-01-23 06:00:15.770426: step: 344/1545, loss: 0.7749860882759094 2023-01-23 06:00:16.681647: step: 346/1545, loss: 0.9594419002532959 2023-01-23 06:00:17.654257: step: 348/1545, loss: 0.8284891247749329 2023-01-23 06:00:18.549059: step: 350/1545, loss: 1.0254329442977905 2023-01-23 06:00:19.450409: step: 352/1545, loss: 7.75828218460083 2023-01-23 06:00:20.421531: step: 354/1545, loss: 0.8641607761383057 2023-01-23 06:00:21.312106: step: 356/1545, loss: 0.8619933128356934 2023-01-23 06:00:22.176637: step: 358/1545, loss: 0.5869525671005249 2023-01-23 06:00:23.072332: step: 360/1545, loss: 0.6829507946968079 2023-01-23 06:00:23.955741: step: 362/1545, loss: 0.942060112953186 2023-01-23 06:00:24.792970: step: 364/1545, loss: 0.6705254912376404 2023-01-23 06:00:25.628840: step: 366/1545, loss: 0.21015393733978271 2023-01-23 06:00:26.538361: step: 368/1545, loss: 1.3894805908203125 2023-01-23 06:00:27.417734: step: 370/1545, loss: 0.6498987078666687 2023-01-23 06:00:28.290141: step: 372/1545, loss: 0.5149598121643066 2023-01-23 06:00:29.150705: step: 374/1545, loss: 1.0513006448745728 2023-01-23 06:00:30.043889: step: 376/1545, loss: 0.3303945064544678 2023-01-23 06:00:30.897163: step: 378/1545, loss: 0.8811735510826111 2023-01-23 06:00:31.752473: step: 380/1545, loss: 3.0250818729400635 2023-01-23 06:00:32.632885: step: 382/1545, loss: 3.0252280235290527 2023-01-23 06:00:33.473131: step: 384/1545, loss: 0.5393100380897522 2023-01-23 06:00:34.421572: step: 386/1545, loss: 1.6348105669021606 2023-01-23 06:00:35.320377: step: 388/1545, loss: 1.6176085472106934 2023-01-23 06:00:36.281497: step: 390/1545, loss: 2.7717342376708984 2023-01-23 06:00:37.152173: step: 392/1545, loss: 0.7369230389595032 2023-01-23 06:00:38.036319: step: 394/1545, loss: 2.39394474029541 2023-01-23 06:00:38.952294: step: 396/1545, loss: 1.4771710634231567 2023-01-23 06:00:39.838044: step: 398/1545, loss: 2.7871904373168945 2023-01-23 06:00:40.679153: step: 400/1545, loss: 7.120505332946777 2023-01-23 06:00:41.558970: step: 402/1545, loss: 3.5989527702331543 2023-01-23 06:00:42.448469: step: 404/1545, loss: 0.9560001492500305 2023-01-23 06:00:43.325331: step: 406/1545, loss: 0.9396143555641174 2023-01-23 06:00:44.197296: step: 408/1545, loss: 4.077795505523682 2023-01-23 06:00:45.040175: step: 410/1545, loss: 1.0705193281173706 2023-01-23 06:00:45.913630: step: 412/1545, loss: 0.6118122935295105 2023-01-23 06:00:46.759864: step: 414/1545, loss: 6.949729919433594 2023-01-23 06:00:47.608069: step: 416/1545, loss: 1.3385283946990967 2023-01-23 06:00:48.446600: step: 418/1545, loss: 0.39881640672683716 2023-01-23 06:00:49.342113: step: 420/1545, loss: 1.2323659658432007 2023-01-23 06:00:50.195458: step: 422/1545, loss: 1.0220744609832764 2023-01-23 06:00:51.178190: step: 424/1545, loss: 1.566380500793457 2023-01-23 06:00:52.020611: step: 426/1545, loss: 0.490800678730011 2023-01-23 06:00:52.893474: step: 428/1545, loss: 0.7173141837120056 2023-01-23 06:00:53.798450: step: 430/1545, loss: 1.8782308101654053 2023-01-23 06:00:54.679262: step: 432/1545, loss: 1.2249959707260132 2023-01-23 06:00:55.645624: step: 434/1545, loss: 0.7596553564071655 2023-01-23 06:00:56.539481: step: 436/1545, loss: 0.7684752941131592 2023-01-23 06:00:57.432184: step: 438/1545, loss: 0.2637139558792114 2023-01-23 06:00:58.287196: step: 440/1545, loss: 0.7976958751678467 2023-01-23 06:00:59.116404: step: 442/1545, loss: 3.064615249633789 2023-01-23 06:00:59.987516: step: 444/1545, loss: 3.849778890609741 2023-01-23 06:01:00.929576: step: 446/1545, loss: 0.2890819013118744 2023-01-23 06:01:01.794106: step: 448/1545, loss: 1.2364903688430786 2023-01-23 06:01:02.723268: step: 450/1545, loss: 0.760448157787323 2023-01-23 06:01:03.627221: step: 452/1545, loss: 1.2180182933807373 2023-01-23 06:01:04.494219: step: 454/1545, loss: 0.7053441405296326 2023-01-23 06:01:05.356623: step: 456/1545, loss: 1.0859888792037964 2023-01-23 06:01:06.212367: step: 458/1545, loss: 1.1636593341827393 2023-01-23 06:01:07.139365: step: 460/1545, loss: 1.0831031799316406 2023-01-23 06:01:08.003703: step: 462/1545, loss: 0.6745121479034424 2023-01-23 06:01:08.933750: step: 464/1545, loss: 0.36973538994789124 2023-01-23 06:01:09.845947: step: 466/1545, loss: 0.7066555619239807 2023-01-23 06:01:10.760219: step: 468/1545, loss: 1.0526858568191528 2023-01-23 06:01:11.661203: step: 470/1545, loss: 3.5132009983062744 2023-01-23 06:01:12.553699: step: 472/1545, loss: 1.035637378692627 2023-01-23 06:01:13.431632: step: 474/1545, loss: 3.3699328899383545 2023-01-23 06:01:14.273655: step: 476/1545, loss: 0.6639299988746643 2023-01-23 06:01:15.126819: step: 478/1545, loss: 1.436868667602539 2023-01-23 06:01:16.076296: step: 480/1545, loss: 3.230950117111206 2023-01-23 06:01:16.959303: step: 482/1545, loss: 0.5407443642616272 2023-01-23 06:01:17.953988: step: 484/1545, loss: 0.926655113697052 2023-01-23 06:01:18.835428: step: 486/1545, loss: 0.6065933108329773 2023-01-23 06:01:19.706763: step: 488/1545, loss: 1.0915048122406006 2023-01-23 06:01:20.620220: step: 490/1545, loss: 1.3984767198562622 2023-01-23 06:01:21.552680: step: 492/1545, loss: 0.8612754344940186 2023-01-23 06:01:22.420318: step: 494/1545, loss: 1.1699649095535278 2023-01-23 06:01:23.344558: step: 496/1545, loss: 2.7308061122894287 2023-01-23 06:01:24.283534: step: 498/1545, loss: 1.1004027128219604 2023-01-23 06:01:25.200568: step: 500/1545, loss: 5.646115303039551 2023-01-23 06:01:26.087555: step: 502/1545, loss: 2.3705670833587646 2023-01-23 06:01:26.972707: step: 504/1545, loss: 0.48456984758377075 2023-01-23 06:01:27.864858: step: 506/1545, loss: 1.0580227375030518 2023-01-23 06:01:28.828406: step: 508/1545, loss: 1.5645908117294312 2023-01-23 06:01:29.679529: step: 510/1545, loss: 3.0591068267822266 2023-01-23 06:01:30.551240: step: 512/1545, loss: 2.7776758670806885 2023-01-23 06:01:31.473325: step: 514/1545, loss: 3.6701736450195312 2023-01-23 06:01:32.390203: step: 516/1545, loss: 1.4413487911224365 2023-01-23 06:01:33.286543: step: 518/1545, loss: 2.3911709785461426 2023-01-23 06:01:34.151574: step: 520/1545, loss: 0.8551402688026428 2023-01-23 06:01:35.023714: step: 522/1545, loss: 3.1506690979003906 2023-01-23 06:01:35.914889: step: 524/1545, loss: 0.3418073058128357 2023-01-23 06:01:36.800095: step: 526/1545, loss: 1.0675203800201416 2023-01-23 06:01:37.656731: step: 528/1545, loss: 2.973576545715332 2023-01-23 06:01:38.589712: step: 530/1545, loss: 0.6023473739624023 2023-01-23 06:01:39.438273: step: 532/1545, loss: 7.333294868469238 2023-01-23 06:01:40.295819: step: 534/1545, loss: 0.5444911122322083 2023-01-23 06:01:41.136759: step: 536/1545, loss: 0.8098152875900269 2023-01-23 06:01:41.983779: step: 538/1545, loss: 0.4449928402900696 2023-01-23 06:01:42.878143: step: 540/1545, loss: 3.118655204772949 2023-01-23 06:01:43.752238: step: 542/1545, loss: 1.5710091590881348 2023-01-23 06:01:44.649350: step: 544/1545, loss: 0.5926788449287415 2023-01-23 06:01:45.528425: step: 546/1545, loss: 3.1736390590667725 2023-01-23 06:01:46.384546: step: 548/1545, loss: 0.6285527944564819 2023-01-23 06:01:47.258310: step: 550/1545, loss: 0.5821153521537781 2023-01-23 06:01:48.124789: step: 552/1545, loss: 6.063039302825928 2023-01-23 06:01:48.985537: step: 554/1545, loss: 1.2004039287567139 2023-01-23 06:01:49.876097: step: 556/1545, loss: 0.8229226469993591 2023-01-23 06:01:50.755976: step: 558/1545, loss: 1.698250412940979 2023-01-23 06:01:51.689645: step: 560/1545, loss: 0.5316849946975708 2023-01-23 06:01:52.572641: step: 562/1545, loss: 0.9366372227668762 2023-01-23 06:01:53.460994: step: 564/1545, loss: 0.8036006689071655 2023-01-23 06:01:54.323665: step: 566/1545, loss: 0.5706720352172852 2023-01-23 06:01:55.209909: step: 568/1545, loss: 9.269672393798828 2023-01-23 06:01:56.047658: step: 570/1545, loss: 0.34134599566459656 2023-01-23 06:01:57.044459: step: 572/1545, loss: 1.7958191633224487 2023-01-23 06:01:57.973564: step: 574/1545, loss: 0.7901819348335266 2023-01-23 06:01:58.833954: step: 576/1545, loss: 0.39791545271873474 2023-01-23 06:01:59.729309: step: 578/1545, loss: 1.063887596130371 2023-01-23 06:02:00.644846: step: 580/1545, loss: 1.956342101097107 2023-01-23 06:02:01.518145: step: 582/1545, loss: 0.6874403953552246 2023-01-23 06:02:02.540721: step: 584/1545, loss: 0.8377348184585571 2023-01-23 06:02:03.465577: step: 586/1545, loss: 1.3187546730041504 2023-01-23 06:02:04.345572: step: 588/1545, loss: 1.1018282175064087 2023-01-23 06:02:05.262756: step: 590/1545, loss: 1.1990718841552734 2023-01-23 06:02:06.161779: step: 592/1545, loss: 1.0256092548370361 2023-01-23 06:02:07.005892: step: 594/1545, loss: 1.2234907150268555 2023-01-23 06:02:07.880457: step: 596/1545, loss: 0.36000514030456543 2023-01-23 06:02:08.735051: step: 598/1545, loss: 0.6909502148628235 2023-01-23 06:02:09.592894: step: 600/1545, loss: 1.4992882013320923 2023-01-23 06:02:10.494291: step: 602/1545, loss: 1.1113409996032715 2023-01-23 06:02:11.344159: step: 604/1545, loss: 3.5219502449035645 2023-01-23 06:02:12.280689: step: 606/1545, loss: 0.4477962851524353 2023-01-23 06:02:13.174543: step: 608/1545, loss: 1.2187278270721436 2023-01-23 06:02:14.045129: step: 610/1545, loss: 0.5379084944725037 2023-01-23 06:02:14.928409: step: 612/1545, loss: 1.1046075820922852 2023-01-23 06:02:15.788537: step: 614/1545, loss: 1.179795503616333 2023-01-23 06:02:16.668456: step: 616/1545, loss: 3.0679633617401123 2023-01-23 06:02:17.557007: step: 618/1545, loss: 0.7204756736755371 2023-01-23 06:02:18.444078: step: 620/1545, loss: 0.810936450958252 2023-01-23 06:02:19.291797: step: 622/1545, loss: 0.700025200843811 2023-01-23 06:02:20.185686: step: 624/1545, loss: 1.0585300922393799 2023-01-23 06:02:21.062650: step: 626/1545, loss: 3.573103666305542 2023-01-23 06:02:21.963047: step: 628/1545, loss: 0.5141561627388 2023-01-23 06:02:22.833205: step: 630/1545, loss: 0.5387965440750122 2023-01-23 06:02:23.694289: step: 632/1545, loss: 0.8327959179878235 2023-01-23 06:02:24.577968: step: 634/1545, loss: 0.3520951271057129 2023-01-23 06:02:25.454196: step: 636/1545, loss: 1.0285184383392334 2023-01-23 06:02:26.333549: step: 638/1545, loss: 0.8597216010093689 2023-01-23 06:02:27.155004: step: 640/1545, loss: 0.7615970969200134 2023-01-23 06:02:28.037634: step: 642/1545, loss: 0.7163519263267517 2023-01-23 06:02:28.907565: step: 644/1545, loss: 0.869876503944397 2023-01-23 06:02:29.799376: step: 646/1545, loss: 1.3745384216308594 2023-01-23 06:02:30.693645: step: 648/1545, loss: 0.9657951593399048 2023-01-23 06:02:31.574524: step: 650/1545, loss: 0.5153569579124451 2023-01-23 06:02:32.473605: step: 652/1545, loss: 0.6594284772872925 2023-01-23 06:02:33.328990: step: 654/1545, loss: 0.33222663402557373 2023-01-23 06:02:34.262334: step: 656/1545, loss: 0.5382282733917236 2023-01-23 06:02:35.113164: step: 658/1545, loss: 7.0188069343566895 2023-01-23 06:02:35.925592: step: 660/1545, loss: 0.5188484191894531 2023-01-23 06:02:36.816797: step: 662/1545, loss: 1.1398906707763672 2023-01-23 06:02:37.692680: step: 664/1545, loss: 0.42564070224761963 2023-01-23 06:02:38.568192: step: 666/1545, loss: 1.1324394941329956 2023-01-23 06:02:39.414357: step: 668/1545, loss: 1.3359956741333008 2023-01-23 06:02:40.272895: step: 670/1545, loss: 0.9931121468544006 2023-01-23 06:02:41.184046: step: 672/1545, loss: 1.6423083543777466 2023-01-23 06:02:42.039973: step: 674/1545, loss: 6.592198848724365 2023-01-23 06:02:42.916120: step: 676/1545, loss: 2.931762456893921 2023-01-23 06:02:43.793492: step: 678/1545, loss: 3.8062045574188232 2023-01-23 06:02:44.650550: step: 680/1545, loss: 0.5111461877822876 2023-01-23 06:02:45.506027: step: 682/1545, loss: 3.275815963745117 2023-01-23 06:02:46.384656: step: 684/1545, loss: 0.7201319932937622 2023-01-23 06:02:47.299362: step: 686/1545, loss: 1.0422240495681763 2023-01-23 06:02:48.194360: step: 688/1545, loss: 0.557243824005127 2023-01-23 06:02:49.051471: step: 690/1545, loss: 5.26857328414917 2023-01-23 06:02:49.949321: step: 692/1545, loss: 3.8813085556030273 2023-01-23 06:02:50.836834: step: 694/1545, loss: 1.388856291770935 2023-01-23 06:02:51.766982: step: 696/1545, loss: 1.0133761167526245 2023-01-23 06:02:52.620920: step: 698/1545, loss: 1.1518449783325195 2023-01-23 06:02:53.575850: step: 700/1545, loss: 0.8188406825065613 2023-01-23 06:02:54.498359: step: 702/1545, loss: 0.8838814496994019 2023-01-23 06:02:55.373913: step: 704/1545, loss: 1.3064897060394287 2023-01-23 06:02:56.232641: step: 706/1545, loss: 0.7496433854103088 2023-01-23 06:02:57.053956: step: 708/1545, loss: 1.074776291847229 2023-01-23 06:02:57.912338: step: 710/1545, loss: 0.9307544231414795 2023-01-23 06:02:58.786145: step: 712/1545, loss: 0.502495288848877 2023-01-23 06:02:59.639094: step: 714/1545, loss: 0.843657374382019 2023-01-23 06:03:00.488221: step: 716/1545, loss: 0.5125856399536133 2023-01-23 06:03:01.343792: step: 718/1545, loss: 0.46697184443473816 2023-01-23 06:03:02.301225: step: 720/1545, loss: 1.09080171585083 2023-01-23 06:03:03.173382: step: 722/1545, loss: 1.371267318725586 2023-01-23 06:03:04.036658: step: 724/1545, loss: 1.1126866340637207 2023-01-23 06:03:04.920280: step: 726/1545, loss: 5.51374626159668 2023-01-23 06:03:05.850394: step: 728/1545, loss: 7.036138534545898 2023-01-23 06:03:06.730304: step: 730/1545, loss: 0.5720931887626648 2023-01-23 06:03:07.586101: step: 732/1545, loss: 10.52627182006836 2023-01-23 06:03:08.426789: step: 734/1545, loss: 0.45412981510162354 2023-01-23 06:03:09.279180: step: 736/1545, loss: 0.5870221853256226 2023-01-23 06:03:10.119613: step: 738/1545, loss: 0.3298480808734894 2023-01-23 06:03:11.053984: step: 740/1545, loss: 0.9771155118942261 2023-01-23 06:03:11.966336: step: 742/1545, loss: 0.3992237150669098 2023-01-23 06:03:12.829451: step: 744/1545, loss: 0.525119423866272 2023-01-23 06:03:13.741090: step: 746/1545, loss: 0.8206445574760437 2023-01-23 06:03:14.589710: step: 748/1545, loss: 2.7072880268096924 2023-01-23 06:03:15.437151: step: 750/1545, loss: 3.0223565101623535 2023-01-23 06:03:16.344405: step: 752/1545, loss: 0.9195078015327454 2023-01-23 06:03:17.245418: step: 754/1545, loss: 0.46239545941352844 2023-01-23 06:03:18.101248: step: 756/1545, loss: 0.367306113243103 2023-01-23 06:03:19.036539: step: 758/1545, loss: 1.3986445665359497 2023-01-23 06:03:19.888745: step: 760/1545, loss: 3.006510019302368 2023-01-23 06:03:20.745049: step: 762/1545, loss: 0.9586946964263916 2023-01-23 06:03:21.689887: step: 764/1545, loss: 0.5874378085136414 2023-01-23 06:03:22.569248: step: 766/1545, loss: 1.4412263631820679 2023-01-23 06:03:23.405058: step: 768/1545, loss: 2.8666560649871826 2023-01-23 06:03:24.264588: step: 770/1545, loss: 0.8623455762863159 2023-01-23 06:03:25.116384: step: 772/1545, loss: 0.8871852159500122 2023-01-23 06:03:26.001780: step: 774/1545, loss: 0.6486992835998535 2023-01-23 06:03:26.898531: step: 776/1545, loss: 0.8042804002761841 2023-01-23 06:03:27.801964: step: 778/1545, loss: 0.485493928194046 2023-01-23 06:03:28.687466: step: 780/1545, loss: 0.8689150810241699 2023-01-23 06:03:29.573805: step: 782/1545, loss: 0.9792509078979492 2023-01-23 06:03:30.440760: step: 784/1545, loss: 0.7222737669944763 2023-01-23 06:03:31.332595: step: 786/1545, loss: 1.4581024646759033 2023-01-23 06:03:32.284130: step: 788/1545, loss: 1.0704845190048218 2023-01-23 06:03:33.148766: step: 790/1545, loss: 0.4023002088069916 2023-01-23 06:03:33.991145: step: 792/1545, loss: 0.4641471803188324 2023-01-23 06:03:34.882229: step: 794/1545, loss: 0.9053494930267334 2023-01-23 06:03:35.789044: step: 796/1545, loss: 1.731448769569397 2023-01-23 06:03:36.611295: step: 798/1545, loss: 0.4569045901298523 2023-01-23 06:03:37.493436: step: 800/1545, loss: 0.9672364592552185 2023-01-23 06:03:38.344039: step: 802/1545, loss: 1.6609418392181396 2023-01-23 06:03:39.231208: step: 804/1545, loss: 0.9371834993362427 2023-01-23 06:03:40.087443: step: 806/1545, loss: 0.5712290406227112 2023-01-23 06:03:40.954261: step: 808/1545, loss: 0.5197474956512451 2023-01-23 06:03:41.801770: step: 810/1545, loss: 0.5409666299819946 2023-01-23 06:03:42.669744: step: 812/1545, loss: 0.7275758385658264 2023-01-23 06:03:43.557653: step: 814/1545, loss: 0.6348446011543274 2023-01-23 06:03:44.417334: step: 816/1545, loss: 1.3059656620025635 2023-01-23 06:03:45.306852: step: 818/1545, loss: 1.4635237455368042 2023-01-23 06:03:46.148872: step: 820/1545, loss: 1.287503719329834 2023-01-23 06:03:47.014669: step: 822/1545, loss: 3.5029456615448 2023-01-23 06:03:47.876507: step: 824/1545, loss: 2.7994637489318848 2023-01-23 06:03:48.767886: step: 826/1545, loss: 0.8340473175048828 2023-01-23 06:03:49.666783: step: 828/1545, loss: 2.0489580631256104 2023-01-23 06:03:50.534061: step: 830/1545, loss: 1.418641209602356 2023-01-23 06:03:51.423403: step: 832/1545, loss: 0.5097987651824951 2023-01-23 06:03:52.334908: step: 834/1545, loss: 0.4582628607749939 2023-01-23 06:03:53.238313: step: 836/1545, loss: 0.5279343128204346 2023-01-23 06:03:54.093543: step: 838/1545, loss: 0.44041457772254944 2023-01-23 06:03:55.011352: step: 840/1545, loss: 2.322638988494873 2023-01-23 06:03:55.905145: step: 842/1545, loss: 0.9762657284736633 2023-01-23 06:03:56.756381: step: 844/1545, loss: 0.5154922008514404 2023-01-23 06:03:57.609001: step: 846/1545, loss: 0.9703733325004578 2023-01-23 06:03:58.470648: step: 848/1545, loss: 3.6455774307250977 2023-01-23 06:03:59.363108: step: 850/1545, loss: 1.7242470979690552 2023-01-23 06:04:00.216978: step: 852/1545, loss: 0.1838737428188324 2023-01-23 06:04:01.175420: step: 854/1545, loss: 0.5467466115951538 2023-01-23 06:04:02.089066: step: 856/1545, loss: 1.5611441135406494 2023-01-23 06:04:02.943056: step: 858/1545, loss: 3.8363053798675537 2023-01-23 06:04:03.779388: step: 860/1545, loss: 0.6427506804466248 2023-01-23 06:04:04.679493: step: 862/1545, loss: 1.1483770608901978 2023-01-23 06:04:05.560339: step: 864/1545, loss: 1.3809561729431152 2023-01-23 06:04:06.459636: step: 866/1545, loss: 3.083691358566284 2023-01-23 06:04:07.332944: step: 868/1545, loss: 0.2956004738807678 2023-01-23 06:04:08.205126: step: 870/1545, loss: 0.838477611541748 2023-01-23 06:04:09.077845: step: 872/1545, loss: 0.5131229758262634 2023-01-23 06:04:09.956010: step: 874/1545, loss: 0.2755756378173828 2023-01-23 06:04:10.822476: step: 876/1545, loss: 0.5842872858047485 2023-01-23 06:04:11.686881: step: 878/1545, loss: 1.9310203790664673 2023-01-23 06:04:12.570362: step: 880/1545, loss: 1.3186242580413818 2023-01-23 06:04:13.428642: step: 882/1545, loss: 1.2285383939743042 2023-01-23 06:04:14.324533: step: 884/1545, loss: 0.8499998450279236 2023-01-23 06:04:15.233164: step: 886/1545, loss: 2.306037425994873 2023-01-23 06:04:16.077477: step: 888/1545, loss: 0.3474969267845154 2023-01-23 06:04:16.959260: step: 890/1545, loss: 0.7917951345443726 2023-01-23 06:04:17.834091: step: 892/1545, loss: 0.6086254715919495 2023-01-23 06:04:18.689606: step: 894/1545, loss: 2.83998703956604 2023-01-23 06:04:19.581000: step: 896/1545, loss: 0.9343719482421875 2023-01-23 06:04:20.481288: step: 898/1545, loss: 0.3378014862537384 2023-01-23 06:04:21.337810: step: 900/1545, loss: 0.7811684608459473 2023-01-23 06:04:22.225677: step: 902/1545, loss: 1.0838958024978638 2023-01-23 06:04:23.094637: step: 904/1545, loss: 3.2461416721343994 2023-01-23 06:04:23.946542: step: 906/1545, loss: 1.5834273099899292 2023-01-23 06:04:24.863488: step: 908/1545, loss: 1.5064235925674438 2023-01-23 06:04:25.729504: step: 910/1545, loss: 1.3961290121078491 2023-01-23 06:04:26.592599: step: 912/1545, loss: 1.0028432607650757 2023-01-23 06:04:27.462832: step: 914/1545, loss: 0.9378625154495239 2023-01-23 06:04:28.313493: step: 916/1545, loss: 2.844864845275879 2023-01-23 06:04:29.160373: step: 918/1545, loss: 1.2733162641525269 2023-01-23 06:04:30.022742: step: 920/1545, loss: 3.6127829551696777 2023-01-23 06:04:30.897968: step: 922/1545, loss: 0.7028093338012695 2023-01-23 06:04:31.744156: step: 924/1545, loss: 0.6876599192619324 2023-01-23 06:04:32.596787: step: 926/1545, loss: 0.4121714234352112 2023-01-23 06:04:33.471716: step: 928/1545, loss: 2.882019281387329 2023-01-23 06:04:34.349182: step: 930/1545, loss: 1.0319091081619263 2023-01-23 06:04:35.226773: step: 932/1545, loss: 0.33707109093666077 2023-01-23 06:04:36.097088: step: 934/1545, loss: 0.41694825887680054 2023-01-23 06:04:36.967698: step: 936/1545, loss: 3.1115026473999023 2023-01-23 06:04:37.845841: step: 938/1545, loss: 0.7407422661781311 2023-01-23 06:04:38.755633: step: 940/1545, loss: 0.8434483408927917 2023-01-23 06:04:39.640462: step: 942/1545, loss: 3.485264301300049 2023-01-23 06:04:40.511619: step: 944/1545, loss: 7.054275035858154 2023-01-23 06:04:41.389698: step: 946/1545, loss: 0.9983529448509216 2023-01-23 06:04:42.246292: step: 948/1545, loss: 2.6219873428344727 2023-01-23 06:04:43.154890: step: 950/1545, loss: 0.6947326064109802 2023-01-23 06:04:44.045313: step: 952/1545, loss: 2.804666757583618 2023-01-23 06:04:44.914873: step: 954/1545, loss: 0.923701822757721 2023-01-23 06:04:45.757780: step: 956/1545, loss: 3.198268413543701 2023-01-23 06:04:46.633976: step: 958/1545, loss: 0.43209344148635864 2023-01-23 06:04:47.509506: step: 960/1545, loss: 0.7460455894470215 2023-01-23 06:04:48.419385: step: 962/1545, loss: 1.2378727197647095 2023-01-23 06:04:49.376757: step: 964/1545, loss: 1.1742756366729736 2023-01-23 06:04:50.236940: step: 966/1545, loss: 0.5204724073410034 2023-01-23 06:04:51.120080: step: 968/1545, loss: 0.3506412208080292 2023-01-23 06:04:52.012625: step: 970/1545, loss: 0.8695308566093445 2023-01-23 06:04:52.905202: step: 972/1545, loss: 0.6941975951194763 2023-01-23 06:04:53.807261: step: 974/1545, loss: 2.8677988052368164 2023-01-23 06:04:54.693128: step: 976/1545, loss: 0.8061336278915405 2023-01-23 06:04:55.585305: step: 978/1545, loss: 0.628669798374176 2023-01-23 06:04:56.468359: step: 980/1545, loss: 0.8948194980621338 2023-01-23 06:04:57.324866: step: 982/1545, loss: 3.24120831489563 2023-01-23 06:04:58.179430: step: 984/1545, loss: 0.5067419409751892 2023-01-23 06:04:59.068366: step: 986/1545, loss: 1.0033305883407593 2023-01-23 06:04:59.962642: step: 988/1545, loss: 0.8512389063835144 2023-01-23 06:05:00.919153: step: 990/1545, loss: 0.9597765207290649 2023-01-23 06:05:01.793767: step: 992/1545, loss: 1.3141908645629883 2023-01-23 06:05:02.624063: step: 994/1545, loss: 1.4361059665679932 2023-01-23 06:05:03.575183: step: 996/1545, loss: 0.35154882073402405 2023-01-23 06:05:04.451806: step: 998/1545, loss: 0.42045119404792786 2023-01-23 06:05:05.343953: step: 1000/1545, loss: 0.830848753452301 2023-01-23 06:05:06.212442: step: 1002/1545, loss: 0.628602921962738 2023-01-23 06:05:07.088524: step: 1004/1545, loss: 0.8657359480857849 2023-01-23 06:05:07.921420: step: 1006/1545, loss: 0.47050437331199646 2023-01-23 06:05:08.787178: step: 1008/1545, loss: 3.1239118576049805 2023-01-23 06:05:09.668463: step: 1010/1545, loss: 1.0438685417175293 2023-01-23 06:05:10.567166: step: 1012/1545, loss: 1.1542034149169922 2023-01-23 06:05:11.453543: step: 1014/1545, loss: 1.7413758039474487 2023-01-23 06:05:12.273098: step: 1016/1545, loss: 0.6407222151756287 2023-01-23 06:05:13.266607: step: 1018/1545, loss: 0.5215455889701843 2023-01-23 06:05:14.162425: step: 1020/1545, loss: 0.9942494630813599 2023-01-23 06:05:15.039937: step: 1022/1545, loss: 1.1911543607711792 2023-01-23 06:05:15.921834: step: 1024/1545, loss: 0.721310555934906 2023-01-23 06:05:16.764863: step: 1026/1545, loss: 0.9746103882789612 2023-01-23 06:05:17.633739: step: 1028/1545, loss: 3.472224473953247 2023-01-23 06:05:18.511847: step: 1030/1545, loss: 0.8681427240371704 2023-01-23 06:05:19.412799: step: 1032/1545, loss: 1.2118711471557617 2023-01-23 06:05:20.301045: step: 1034/1545, loss: 1.1468110084533691 2023-01-23 06:05:21.182846: step: 1036/1545, loss: 1.1769732236862183 2023-01-23 06:05:22.038643: step: 1038/1545, loss: 0.7900716066360474 2023-01-23 06:05:22.939247: step: 1040/1545, loss: 0.9690685272216797 2023-01-23 06:05:23.845488: step: 1042/1545, loss: 2.027095317840576 2023-01-23 06:05:24.711419: step: 1044/1545, loss: 0.8667497038841248 2023-01-23 06:05:25.598532: step: 1046/1545, loss: 1.0788086652755737 2023-01-23 06:05:26.506389: step: 1048/1545, loss: 0.5367423892021179 2023-01-23 06:05:27.355990: step: 1050/1545, loss: 6.690375804901123 2023-01-23 06:05:28.244465: step: 1052/1545, loss: 0.4514434337615967 2023-01-23 06:05:29.113065: step: 1054/1545, loss: 0.8513346314430237 2023-01-23 06:05:29.956751: step: 1056/1545, loss: 0.42589491605758667 2023-01-23 06:05:30.830921: step: 1058/1545, loss: 0.5563670992851257 2023-01-23 06:05:31.694492: step: 1060/1545, loss: 0.9157394170761108 2023-01-23 06:05:32.549330: step: 1062/1545, loss: 0.5037863254547119 2023-01-23 06:05:33.449000: step: 1064/1545, loss: 0.8257279396057129 2023-01-23 06:05:34.300587: step: 1066/1545, loss: 0.5147174000740051 2023-01-23 06:05:35.156770: step: 1068/1545, loss: 0.8114479780197144 2023-01-23 06:05:36.028845: step: 1070/1545, loss: 0.935230553150177 2023-01-23 06:05:36.871774: step: 1072/1545, loss: 1.4080411195755005 2023-01-23 06:05:37.778094: step: 1074/1545, loss: 0.5940614342689514 2023-01-23 06:05:38.654876: step: 1076/1545, loss: 0.3959164321422577 2023-01-23 06:05:39.558318: step: 1078/1545, loss: 1.0889610052108765 2023-01-23 06:05:40.429639: step: 1080/1545, loss: 0.8566166162490845 2023-01-23 06:05:41.310883: step: 1082/1545, loss: 0.5970672965049744 2023-01-23 06:05:42.233603: step: 1084/1545, loss: 0.8670282959938049 2023-01-23 06:05:43.087695: step: 1086/1545, loss: 1.0246360301971436 2023-01-23 06:05:44.013155: step: 1088/1545, loss: 0.7624412775039673 2023-01-23 06:05:44.871565: step: 1090/1545, loss: 0.6452200412750244 2023-01-23 06:05:45.763241: step: 1092/1545, loss: 2.8901331424713135 2023-01-23 06:05:46.655510: step: 1094/1545, loss: 1.0269277095794678 2023-01-23 06:05:47.516608: step: 1096/1545, loss: 0.38882288336753845 2023-01-23 06:05:48.366863: step: 1098/1545, loss: 1.6788005828857422 2023-01-23 06:05:49.263533: step: 1100/1545, loss: 1.8577853441238403 2023-01-23 06:05:50.151817: step: 1102/1545, loss: 0.8538137674331665 2023-01-23 06:05:51.054350: step: 1104/1545, loss: 1.0109540224075317 2023-01-23 06:05:51.934688: step: 1106/1545, loss: 1.2216854095458984 2023-01-23 06:05:52.777985: step: 1108/1545, loss: 0.3322075605392456 2023-01-23 06:05:53.634534: step: 1110/1545, loss: 0.5103092789649963 2023-01-23 06:05:54.493129: step: 1112/1545, loss: 0.8986063599586487 2023-01-23 06:05:55.343370: step: 1114/1545, loss: 2.83548641204834 2023-01-23 06:05:56.263545: step: 1116/1545, loss: 0.417210191488266 2023-01-23 06:05:57.188021: step: 1118/1545, loss: 0.6981808543205261 2023-01-23 06:05:58.056775: step: 1120/1545, loss: 7.186389446258545 2023-01-23 06:05:58.934634: step: 1122/1545, loss: 2.9283761978149414 2023-01-23 06:05:59.785954: step: 1124/1545, loss: 0.9181124567985535 2023-01-23 06:06:00.637898: step: 1126/1545, loss: 0.4917280375957489 2023-01-23 06:06:01.555893: step: 1128/1545, loss: 5.703842639923096 2023-01-23 06:06:02.426144: step: 1130/1545, loss: 1.4482901096343994 2023-01-23 06:06:03.300039: step: 1132/1545, loss: 0.8833592534065247 2023-01-23 06:06:04.169677: step: 1134/1545, loss: 1.8495405912399292 2023-01-23 06:06:05.047653: step: 1136/1545, loss: 0.9360967874526978 2023-01-23 06:06:05.928242: step: 1138/1545, loss: 0.34487229585647583 2023-01-23 06:06:06.834834: step: 1140/1545, loss: 3.2316012382507324 2023-01-23 06:06:07.642943: step: 1142/1545, loss: 2.8555009365081787 2023-01-23 06:06:08.461979: step: 1144/1545, loss: 0.5742371678352356 2023-01-23 06:06:09.289560: step: 1146/1545, loss: 5.736136436462402 2023-01-23 06:06:10.148645: step: 1148/1545, loss: 3.383594036102295 2023-01-23 06:06:11.004237: step: 1150/1545, loss: 0.2459334284067154 2023-01-23 06:06:11.862051: step: 1152/1545, loss: 1.1734241247177124 2023-01-23 06:06:12.747497: step: 1154/1545, loss: 1.067533254623413 2023-01-23 06:06:13.628321: step: 1156/1545, loss: 2.4511051177978516 2023-01-23 06:06:14.488624: step: 1158/1545, loss: 1.6632336378097534 2023-01-23 06:06:15.365885: step: 1160/1545, loss: 1.4955939054489136 2023-01-23 06:06:16.251806: step: 1162/1545, loss: 0.9512483477592468 2023-01-23 06:06:17.132477: step: 1164/1545, loss: 1.125178337097168 2023-01-23 06:06:17.985959: step: 1166/1545, loss: 0.6881971955299377 2023-01-23 06:06:18.880715: step: 1168/1545, loss: 0.5726808309555054 2023-01-23 06:06:19.762640: step: 1170/1545, loss: 0.5002964735031128 2023-01-23 06:06:20.632356: step: 1172/1545, loss: 4.365999698638916 2023-01-23 06:06:21.538929: step: 1174/1545, loss: 0.7077828049659729 2023-01-23 06:06:22.396827: step: 1176/1545, loss: 6.67168664932251 2023-01-23 06:06:23.218235: step: 1178/1545, loss: 0.37899529933929443 2023-01-23 06:06:24.141478: step: 1180/1545, loss: 3.430053234100342 2023-01-23 06:06:25.125520: step: 1182/1545, loss: 1.4257309436798096 2023-01-23 06:06:25.972963: step: 1184/1545, loss: 1.0832887887954712 2023-01-23 06:06:26.812100: step: 1186/1545, loss: 0.9374309182167053 2023-01-23 06:06:27.667532: step: 1188/1545, loss: 0.5146670341491699 2023-01-23 06:06:28.555945: step: 1190/1545, loss: 6.367352485656738 2023-01-23 06:06:29.419238: step: 1192/1545, loss: 0.46635282039642334 2023-01-23 06:06:30.290372: step: 1194/1545, loss: 0.7505818605422974 2023-01-23 06:06:31.196703: step: 1196/1545, loss: 0.8921345472335815 2023-01-23 06:06:32.061451: step: 1198/1545, loss: 0.8666847944259644 2023-01-23 06:06:32.954838: step: 1200/1545, loss: 1.268011212348938 2023-01-23 06:06:33.840390: step: 1202/1545, loss: 1.2596155405044556 2023-01-23 06:06:34.698052: step: 1204/1545, loss: 0.5368059873580933 2023-01-23 06:06:35.556382: step: 1206/1545, loss: 0.31396937370300293 2023-01-23 06:06:36.463739: step: 1208/1545, loss: 1.1014472246170044 2023-01-23 06:06:37.318151: step: 1210/1545, loss: 2.12919545173645 2023-01-23 06:06:38.188852: step: 1212/1545, loss: 0.8876931071281433 2023-01-23 06:06:39.112576: step: 1214/1545, loss: 1.3394460678100586 2023-01-23 06:06:39.969929: step: 1216/1545, loss: 1.0773886442184448 2023-01-23 06:06:40.896996: step: 1218/1545, loss: 1.3990671634674072 2023-01-23 06:06:41.774510: step: 1220/1545, loss: 1.415470838546753 2023-01-23 06:06:42.588354: step: 1222/1545, loss: 0.6063874959945679 2023-01-23 06:06:43.517643: step: 1224/1545, loss: 0.44947585463523865 2023-01-23 06:06:44.372894: step: 1226/1545, loss: 1.1164144277572632 2023-01-23 06:06:45.265059: step: 1228/1545, loss: 1.1997389793395996 2023-01-23 06:06:46.170441: step: 1230/1545, loss: 1.0160940885543823 2023-01-23 06:06:47.031283: step: 1232/1545, loss: 0.9385704398155212 2023-01-23 06:06:47.957301: step: 1234/1545, loss: 3.3371284008026123 2023-01-23 06:06:48.799349: step: 1236/1545, loss: 9.65737533569336 2023-01-23 06:06:49.703535: step: 1238/1545, loss: 0.35852697491645813 2023-01-23 06:06:50.563374: step: 1240/1545, loss: 2.9621431827545166 2023-01-23 06:06:51.432103: step: 1242/1545, loss: 0.8405062556266785 2023-01-23 06:06:52.365735: step: 1244/1545, loss: 1.1116864681243896 2023-01-23 06:06:53.248607: step: 1246/1545, loss: 0.43850815296173096 2023-01-23 06:06:54.120840: step: 1248/1545, loss: 0.35739612579345703 2023-01-23 06:06:55.004703: step: 1250/1545, loss: 0.8519480228424072 2023-01-23 06:06:55.878328: step: 1252/1545, loss: 0.9413802623748779 2023-01-23 06:06:56.761650: step: 1254/1545, loss: 0.6015636920928955 2023-01-23 06:06:57.636727: step: 1256/1545, loss: 0.4933101534843445 2023-01-23 06:06:58.522117: step: 1258/1545, loss: 1.479311466217041 2023-01-23 06:06:59.440392: step: 1260/1545, loss: 1.3031153678894043 2023-01-23 06:07:00.316042: step: 1262/1545, loss: 0.6672260761260986 2023-01-23 06:07:01.209982: step: 1264/1545, loss: 0.6633504629135132 2023-01-23 06:07:02.116300: step: 1266/1545, loss: 0.6993687152862549 2023-01-23 06:07:03.060695: step: 1268/1545, loss: 1.433301329612732 2023-01-23 06:07:04.008425: step: 1270/1545, loss: 0.6267402768135071 2023-01-23 06:07:04.890101: step: 1272/1545, loss: 0.584388017654419 2023-01-23 06:07:05.771910: step: 1274/1545, loss: 1.2607855796813965 2023-01-23 06:07:06.662305: step: 1276/1545, loss: 1.7685290575027466 2023-01-23 06:07:07.572006: step: 1278/1545, loss: 0.48711925745010376 2023-01-23 06:07:08.419378: step: 1280/1545, loss: 0.8535054922103882 2023-01-23 06:07:09.370850: step: 1282/1545, loss: 1.2876746654510498 2023-01-23 06:07:10.249515: step: 1284/1545, loss: 1.0473823547363281 2023-01-23 06:07:11.119067: step: 1286/1545, loss: 0.6918832063674927 2023-01-23 06:07:11.984699: step: 1288/1545, loss: 0.4085366129875183 2023-01-23 06:07:12.900619: step: 1290/1545, loss: 1.0506888628005981 2023-01-23 06:07:13.798143: step: 1292/1545, loss: 1.2213318347930908 2023-01-23 06:07:14.634293: step: 1294/1545, loss: 1.098223328590393 2023-01-23 06:07:15.545771: step: 1296/1545, loss: 0.9199473857879639 2023-01-23 06:07:16.468006: step: 1298/1545, loss: 1.4695316553115845 2023-01-23 06:07:17.350086: step: 1300/1545, loss: 0.6830780506134033 2023-01-23 06:07:18.240377: step: 1302/1545, loss: 3.3073067665100098 2023-01-23 06:07:19.181036: step: 1304/1545, loss: 0.7267423272132874 2023-01-23 06:07:20.086765: step: 1306/1545, loss: 0.7926324605941772 2023-01-23 06:07:20.989833: step: 1308/1545, loss: 1.4953914880752563 2023-01-23 06:07:21.877270: step: 1310/1545, loss: 1.2563319206237793 2023-01-23 06:07:22.739341: step: 1312/1545, loss: 0.9806743264198303 2023-01-23 06:07:23.630754: step: 1314/1545, loss: 0.6957041621208191 2023-01-23 06:07:24.566039: step: 1316/1545, loss: 0.6658676266670227 2023-01-23 06:07:25.454026: step: 1318/1545, loss: 1.8501560688018799 2023-01-23 06:07:26.354354: step: 1320/1545, loss: 0.7321560978889465 2023-01-23 06:07:27.211096: step: 1322/1545, loss: 0.6002597212791443 2023-01-23 06:07:28.100024: step: 1324/1545, loss: 1.3717132806777954 2023-01-23 06:07:29.024570: step: 1326/1545, loss: 1.6885877847671509 2023-01-23 06:07:29.897304: step: 1328/1545, loss: 1.1983412504196167 2023-01-23 06:07:30.726713: step: 1330/1545, loss: 4.15266227722168 2023-01-23 06:07:31.591778: step: 1332/1545, loss: 0.7454445362091064 2023-01-23 06:07:32.495773: step: 1334/1545, loss: 3.290177822113037 2023-01-23 06:07:33.428936: step: 1336/1545, loss: 0.6545748710632324 2023-01-23 06:07:34.317957: step: 1338/1545, loss: 3.1938774585723877 2023-01-23 06:07:35.216323: step: 1340/1545, loss: 1.1415705680847168 2023-01-23 06:07:36.144572: step: 1342/1545, loss: 6.666759490966797 2023-01-23 06:07:37.026365: step: 1344/1545, loss: 0.3688201308250427 2023-01-23 06:07:37.953315: step: 1346/1545, loss: 1.0770845413208008 2023-01-23 06:07:38.810702: step: 1348/1545, loss: 0.5641283392906189 2023-01-23 06:07:39.714040: step: 1350/1545, loss: 0.9717930555343628 2023-01-23 06:07:40.581716: step: 1352/1545, loss: 1.156427264213562 2023-01-23 06:07:41.457517: step: 1354/1545, loss: 1.133493423461914 2023-01-23 06:07:42.446325: step: 1356/1545, loss: 0.3594035804271698 2023-01-23 06:07:43.308813: step: 1358/1545, loss: 0.760402500629425 2023-01-23 06:07:44.236870: step: 1360/1545, loss: 0.8608778715133667 2023-01-23 06:07:45.146724: step: 1362/1545, loss: 0.9461063742637634 2023-01-23 06:07:46.026132: step: 1364/1545, loss: 1.9328553676605225 2023-01-23 06:07:46.954407: step: 1366/1545, loss: 1.244157075881958 2023-01-23 06:07:47.906971: step: 1368/1545, loss: 1.512623906135559 2023-01-23 06:07:48.798204: step: 1370/1545, loss: 1.0631413459777832 2023-01-23 06:07:49.682855: step: 1372/1545, loss: 0.5625447630882263 2023-01-23 06:07:50.541751: step: 1374/1545, loss: 0.42080849409103394 2023-01-23 06:07:51.405721: step: 1376/1545, loss: 0.9581096768379211 2023-01-23 06:07:52.268753: step: 1378/1545, loss: 6.380359649658203 2023-01-23 06:07:53.150005: step: 1380/1545, loss: 6.779704570770264 2023-01-23 06:07:53.993646: step: 1382/1545, loss: 0.8415676355361938 2023-01-23 06:07:54.863527: step: 1384/1545, loss: 0.9031073451042175 2023-01-23 06:07:55.795374: step: 1386/1545, loss: 1.3564637899398804 2023-01-23 06:07:56.665604: step: 1388/1545, loss: 1.2297496795654297 2023-01-23 06:07:57.575437: step: 1390/1545, loss: 0.9407849907875061 2023-01-23 06:07:58.420396: step: 1392/1545, loss: 0.7870444059371948 2023-01-23 06:07:59.274021: step: 1394/1545, loss: 0.7948070168495178 2023-01-23 06:08:00.137759: step: 1396/1545, loss: 0.9871343374252319 2023-01-23 06:08:01.031578: step: 1398/1545, loss: 1.060320496559143 2023-01-23 06:08:01.926083: step: 1400/1545, loss: 0.9624011516571045 2023-01-23 06:08:02.822065: step: 1402/1545, loss: 0.48860955238342285 2023-01-23 06:08:03.731585: step: 1404/1545, loss: 0.8352779150009155 2023-01-23 06:08:04.652687: step: 1406/1545, loss: 0.795120120048523 2023-01-23 06:08:05.485984: step: 1408/1545, loss: 1.081301212310791 2023-01-23 06:08:06.343731: step: 1410/1545, loss: 0.784473717212677 2023-01-23 06:08:07.282780: step: 1412/1545, loss: 0.5346126556396484 2023-01-23 06:08:08.134127: step: 1414/1545, loss: 0.5630212426185608 2023-01-23 06:08:09.028943: step: 1416/1545, loss: 0.8777555823326111 2023-01-23 06:08:09.945482: step: 1418/1545, loss: 1.3831709623336792 2023-01-23 06:08:10.831267: step: 1420/1545, loss: 0.7647010087966919 2023-01-23 06:08:11.729577: step: 1422/1545, loss: 1.3385826349258423 2023-01-23 06:08:12.576168: step: 1424/1545, loss: 1.2859605550765991 2023-01-23 06:08:13.485711: step: 1426/1545, loss: 1.208093523979187 2023-01-23 06:08:14.351699: step: 1428/1545, loss: 0.6669759750366211 2023-01-23 06:08:15.272875: step: 1430/1545, loss: 1.2240581512451172 2023-01-23 06:08:16.135783: step: 1432/1545, loss: 0.7556395530700684 2023-01-23 06:08:17.038016: step: 1434/1545, loss: 0.5894186496734619 2023-01-23 06:08:17.897271: step: 1436/1545, loss: 1.2279454469680786 2023-01-23 06:08:18.774167: step: 1438/1545, loss: 0.4228024482727051 2023-01-23 06:08:19.714378: step: 1440/1545, loss: 3.1517882347106934 2023-01-23 06:08:20.694629: step: 1442/1545, loss: 0.7646558284759521 2023-01-23 06:08:21.557905: step: 1444/1545, loss: 0.7749971747398376 2023-01-23 06:08:22.426614: step: 1446/1545, loss: 0.7171952128410339 2023-01-23 06:08:23.292709: step: 1448/1545, loss: 0.6601264476776123 2023-01-23 06:08:24.144946: step: 1450/1545, loss: 0.41725438833236694 2023-01-23 06:08:25.007957: step: 1452/1545, loss: 0.8507360219955444 2023-01-23 06:08:25.946492: step: 1454/1545, loss: 0.6903996467590332 2023-01-23 06:08:26.802887: step: 1456/1545, loss: 1.164942979812622 2023-01-23 06:08:27.743775: step: 1458/1545, loss: 1.4015735387802124 2023-01-23 06:08:28.624380: step: 1460/1545, loss: 0.8573119044303894 2023-01-23 06:08:29.483748: step: 1462/1545, loss: 9.005577087402344 2023-01-23 06:08:30.357263: step: 1464/1545, loss: 2.8088324069976807 2023-01-23 06:08:31.228198: step: 1466/1545, loss: 0.8857323527336121 2023-01-23 06:08:32.089367: step: 1468/1545, loss: 6.9032087326049805 2023-01-23 06:08:32.946967: step: 1470/1545, loss: 3.2039248943328857 2023-01-23 06:08:33.849290: step: 1472/1545, loss: 1.284471035003662 2023-01-23 06:08:34.704173: step: 1474/1545, loss: 7.5548295974731445 2023-01-23 06:08:35.576133: step: 1476/1545, loss: 1.159490704536438 2023-01-23 06:08:36.466285: step: 1478/1545, loss: 1.0319491624832153 2023-01-23 06:08:37.399105: step: 1480/1545, loss: 1.383690595626831 2023-01-23 06:08:38.267768: step: 1482/1545, loss: 1.0329718589782715 2023-01-23 06:08:39.130961: step: 1484/1545, loss: 5.212948799133301 2023-01-23 06:08:40.006543: step: 1486/1545, loss: 0.7827998399734497 2023-01-23 06:08:40.903648: step: 1488/1545, loss: 1.1123175621032715 2023-01-23 06:08:41.773113: step: 1490/1545, loss: 3.2902779579162598 2023-01-23 06:08:42.682365: step: 1492/1545, loss: 3.36599063873291 2023-01-23 06:08:43.581005: step: 1494/1545, loss: 0.9332168698310852 2023-01-23 06:08:44.481685: step: 1496/1545, loss: 3.3112854957580566 2023-01-23 06:08:45.361177: step: 1498/1545, loss: 6.247706413269043 2023-01-23 06:08:46.206567: step: 1500/1545, loss: 1.0046803951263428 2023-01-23 06:08:47.073293: step: 1502/1545, loss: 0.4395734965801239 2023-01-23 06:08:47.941380: step: 1504/1545, loss: 0.7073631286621094 2023-01-23 06:08:48.806616: step: 1506/1545, loss: 0.6955268979072571 2023-01-23 06:08:49.737017: step: 1508/1545, loss: 1.0995709896087646 2023-01-23 06:08:50.652799: step: 1510/1545, loss: 1.4076294898986816 2023-01-23 06:08:51.526046: step: 1512/1545, loss: 0.5605723857879639 2023-01-23 06:08:52.428829: step: 1514/1545, loss: 1.0921896696090698 2023-01-23 06:08:53.399843: step: 1516/1545, loss: 0.5066638588905334 2023-01-23 06:08:54.255327: step: 1518/1545, loss: 0.626232922077179 2023-01-23 06:08:55.115175: step: 1520/1545, loss: 1.766924500465393 2023-01-23 06:08:56.029203: step: 1522/1545, loss: 0.3843228816986084 2023-01-23 06:08:56.957140: step: 1524/1545, loss: 1.2172645330429077 2023-01-23 06:08:57.850029: step: 1526/1545, loss: 2.240694522857666 2023-01-23 06:08:58.744874: step: 1528/1545, loss: 0.522983968257904 2023-01-23 06:08:59.643055: step: 1530/1545, loss: 7.341116428375244 2023-01-23 06:09:00.532506: step: 1532/1545, loss: 3.046581745147705 2023-01-23 06:09:01.400521: step: 1534/1545, loss: 0.6890467405319214 2023-01-23 06:09:02.291455: step: 1536/1545, loss: 0.8208014965057373 2023-01-23 06:09:03.198154: step: 1538/1545, loss: 0.41004887223243713 2023-01-23 06:09:04.109265: step: 1540/1545, loss: 0.9570422768592834 2023-01-23 06:09:05.088366: step: 1542/1545, loss: 1.2703099250793457 2023-01-23 06:09:05.971204: step: 1544/1545, loss: 1.1084768772125244 2023-01-23 06:09:06.860118: step: 1546/1545, loss: 0.6128636002540588 2023-01-23 06:09:07.711216: step: 1548/1545, loss: 3.634892225265503 2023-01-23 06:09:08.596789: step: 1550/1545, loss: 3.126126289367676 2023-01-23 06:09:09.514178: step: 1552/1545, loss: 1.4385349750518799 2023-01-23 06:09:10.402379: step: 1554/1545, loss: 0.9011270403862 2023-01-23 06:09:11.262447: step: 1556/1545, loss: 2.9077398777008057 2023-01-23 06:09:12.113400: step: 1558/1545, loss: 1.2189537286758423 2023-01-23 06:09:12.982875: step: 1560/1545, loss: 0.9368565082550049 2023-01-23 06:09:13.858247: step: 1562/1545, loss: 0.769242525100708 2023-01-23 06:09:14.797420: step: 1564/1545, loss: 0.4373544752597809 2023-01-23 06:09:15.669246: step: 1566/1545, loss: 1.0325291156768799 2023-01-23 06:09:16.568963: step: 1568/1545, loss: 1.0299757719039917 2023-01-23 06:09:17.486793: step: 1570/1545, loss: 1.416538119316101 2023-01-23 06:09:18.363538: step: 1572/1545, loss: 1.3178715705871582 2023-01-23 06:09:19.353039: step: 1574/1545, loss: 0.27487051486968994 2023-01-23 06:09:20.211346: step: 1576/1545, loss: 0.9870073199272156 2023-01-23 06:09:21.100481: step: 1578/1545, loss: 0.8107362985610962 2023-01-23 06:09:21.968486: step: 1580/1545, loss: 0.2351817488670349 2023-01-23 06:09:22.816692: step: 1582/1545, loss: 1.1770235300064087 2023-01-23 06:09:23.774497: step: 1584/1545, loss: 0.9229533076286316 2023-01-23 06:09:24.636211: step: 1586/1545, loss: 1.3774408102035522 2023-01-23 06:09:25.545207: step: 1588/1545, loss: 6.433629989624023 2023-01-23 06:09:26.425545: step: 1590/1545, loss: 0.7036618590354919 2023-01-23 06:09:27.315069: step: 1592/1545, loss: 3.6658132076263428 2023-01-23 06:09:28.212604: step: 1594/1545, loss: 0.5262780785560608 2023-01-23 06:09:29.130216: step: 1596/1545, loss: 1.7958018779754639 2023-01-23 06:09:30.017078: step: 1598/1545, loss: 0.867190957069397 2023-01-23 06:09:30.877951: step: 1600/1545, loss: 0.48375174403190613 2023-01-23 06:09:31.769782: step: 1602/1545, loss: 0.5897930264472961 2023-01-23 06:09:32.647312: step: 1604/1545, loss: 0.5990215539932251 2023-01-23 06:09:33.548072: step: 1606/1545, loss: 1.6780421733856201 2023-01-23 06:09:34.465310: step: 1608/1545, loss: 6.521529197692871 2023-01-23 06:09:35.326972: step: 1610/1545, loss: 1.0532954931259155 2023-01-23 06:09:36.199417: step: 1612/1545, loss: 0.772139847278595 2023-01-23 06:09:37.050217: step: 1614/1545, loss: 2.819592237472534 2023-01-23 06:09:37.890941: step: 1616/1545, loss: 0.7098190188407898 2023-01-23 06:09:38.770245: step: 1618/1545, loss: 0.7061166167259216 2023-01-23 06:09:39.687222: step: 1620/1545, loss: 0.443955659866333 2023-01-23 06:09:40.557739: step: 1622/1545, loss: 3.732121706008911 2023-01-23 06:09:41.471781: step: 1624/1545, loss: 0.5915817022323608 2023-01-23 06:09:42.318013: step: 1626/1545, loss: 5.256930351257324 2023-01-23 06:09:43.236959: step: 1628/1545, loss: 0.8273001313209534 2023-01-23 06:09:44.111330: step: 1630/1545, loss: 0.9781028032302856 2023-01-23 06:09:45.089041: step: 1632/1545, loss: 0.5942613482475281 2023-01-23 06:09:45.974867: step: 1634/1545, loss: 0.9563982486724854 2023-01-23 06:09:46.832911: step: 1636/1545, loss: 0.7430781722068787 2023-01-23 06:09:47.728344: step: 1638/1545, loss: 0.8268759250640869 2023-01-23 06:09:48.674414: step: 1640/1545, loss: 0.5208162069320679 2023-01-23 06:09:49.567271: step: 1642/1545, loss: 0.6207646727561951 2023-01-23 06:09:50.440228: step: 1644/1545, loss: 0.6365024447441101 2023-01-23 06:09:51.309335: step: 1646/1545, loss: 2.612644672393799 2023-01-23 06:09:52.220537: step: 1648/1545, loss: 0.6833253502845764 2023-01-23 06:09:53.154142: step: 1650/1545, loss: 2.9818203449249268 2023-01-23 06:09:54.151700: step: 1652/1545, loss: 0.8121057152748108 2023-01-23 06:09:55.013653: step: 1654/1545, loss: 0.31283897161483765 2023-01-23 06:09:55.905680: step: 1656/1545, loss: 3.8617475032806396 2023-01-23 06:09:56.794795: step: 1658/1545, loss: 3.0266857147216797 2023-01-23 06:09:57.710952: step: 1660/1545, loss: 0.7537947297096252 2023-01-23 06:09:58.595131: step: 1662/1545, loss: 0.5915930867195129 2023-01-23 06:09:59.482959: step: 1664/1545, loss: 0.8506314158439636 2023-01-23 06:10:00.388886: step: 1666/1545, loss: 0.6147925853729248 2023-01-23 06:10:01.309690: step: 1668/1545, loss: 1.0670524835586548 2023-01-23 06:10:02.223532: step: 1670/1545, loss: 0.7923159599304199 2023-01-23 06:10:03.095387: step: 1672/1545, loss: 0.7617655396461487 2023-01-23 06:10:04.010834: step: 1674/1545, loss: 1.2134214639663696 2023-01-23 06:10:04.848558: step: 1676/1545, loss: 1.208810567855835 2023-01-23 06:10:05.724575: step: 1678/1545, loss: 0.836770236492157 2023-01-23 06:10:06.560072: step: 1680/1545, loss: 1.2136051654815674 2023-01-23 06:10:07.398288: step: 1682/1545, loss: 1.1988211870193481 2023-01-23 06:10:08.260143: step: 1684/1545, loss: 0.22717007994651794 2023-01-23 06:10:09.128718: step: 1686/1545, loss: 3.5575289726257324 2023-01-23 06:10:09.974830: step: 1688/1545, loss: 0.5430354475975037 2023-01-23 06:10:10.824190: step: 1690/1545, loss: 0.8073663115501404 2023-01-23 06:10:11.653145: step: 1692/1545, loss: 1.3455562591552734 2023-01-23 06:10:12.511319: step: 1694/1545, loss: 1.0263705253601074 2023-01-23 06:10:13.446320: step: 1696/1545, loss: 0.6529726982116699 2023-01-23 06:10:14.281606: step: 1698/1545, loss: 1.2477200031280518 2023-01-23 06:10:15.152257: step: 1700/1545, loss: 0.8236998319625854 2023-01-23 06:10:16.037605: step: 1702/1545, loss: 0.852374255657196 2023-01-23 06:10:16.920886: step: 1704/1545, loss: 0.7526907920837402 2023-01-23 06:10:17.869990: step: 1706/1545, loss: 0.702103853225708 2023-01-23 06:10:18.746904: step: 1708/1545, loss: 0.7062089443206787 2023-01-23 06:10:19.628673: step: 1710/1545, loss: 0.4778439700603485 2023-01-23 06:10:20.494837: step: 1712/1545, loss: 0.8999240398406982 2023-01-23 06:10:21.347682: step: 1714/1545, loss: 0.39110684394836426 2023-01-23 06:10:22.223363: step: 1716/1545, loss: 1.867894172668457 2023-01-23 06:10:23.094592: step: 1718/1545, loss: 1.1170786619186401 2023-01-23 06:10:23.949425: step: 1720/1545, loss: 0.3863041400909424 2023-01-23 06:10:24.840326: step: 1722/1545, loss: 3.240300178527832 2023-01-23 06:10:25.774270: step: 1724/1545, loss: 0.8003141283988953 2023-01-23 06:10:26.632591: step: 1726/1545, loss: 3.233736753463745 2023-01-23 06:10:27.518404: step: 1728/1545, loss: 0.8196156620979309 2023-01-23 06:10:28.404633: step: 1730/1545, loss: 0.8569440841674805 2023-01-23 06:10:29.280487: step: 1732/1545, loss: 0.9235038757324219 2023-01-23 06:10:30.169760: step: 1734/1545, loss: 0.7663767337799072 2023-01-23 06:10:31.032040: step: 1736/1545, loss: 0.2832220792770386 2023-01-23 06:10:31.946713: step: 1738/1545, loss: 1.155113697052002 2023-01-23 06:10:32.786456: step: 1740/1545, loss: 0.6553808450698853 2023-01-23 06:10:33.671872: step: 1742/1545, loss: 0.3979378342628479 2023-01-23 06:10:34.551236: step: 1744/1545, loss: 0.7634334564208984 2023-01-23 06:10:35.427432: step: 1746/1545, loss: 0.5432004332542419 2023-01-23 06:10:36.301960: step: 1748/1545, loss: 1.4422887563705444 2023-01-23 06:10:37.219902: step: 1750/1545, loss: 0.7768768668174744 2023-01-23 06:10:38.108336: step: 1752/1545, loss: 1.1012847423553467 2023-01-23 06:10:39.007282: step: 1754/1545, loss: 0.6189234256744385 2023-01-23 06:10:39.892571: step: 1756/1545, loss: 1.0039830207824707 2023-01-23 06:10:40.763914: step: 1758/1545, loss: 0.2640991806983948 2023-01-23 06:10:41.646603: step: 1760/1545, loss: 3.020078659057617 2023-01-23 06:10:42.510000: step: 1762/1545, loss: 3.1513304710388184 2023-01-23 06:10:43.393672: step: 1764/1545, loss: 3.172191858291626 2023-01-23 06:10:44.246223: step: 1766/1545, loss: 1.350772500038147 2023-01-23 06:10:45.174726: step: 1768/1545, loss: 1.8333510160446167 2023-01-23 06:10:46.051525: step: 1770/1545, loss: 3.3210554122924805 2023-01-23 06:10:47.010190: step: 1772/1545, loss: 1.5804698467254639 2023-01-23 06:10:47.940832: step: 1774/1545, loss: 0.8028968572616577 2023-01-23 06:10:48.842495: step: 1776/1545, loss: 0.5849732756614685 2023-01-23 06:10:49.725248: step: 1778/1545, loss: 1.3230313062667847 2023-01-23 06:10:50.570259: step: 1780/1545, loss: 3.484828472137451 2023-01-23 06:10:51.475235: step: 1782/1545, loss: 0.548994779586792 2023-01-23 06:10:52.326762: step: 1784/1545, loss: 0.63251131772995 2023-01-23 06:10:53.208290: step: 1786/1545, loss: 0.874087929725647 2023-01-23 06:10:54.129164: step: 1788/1545, loss: 1.4196590185165405 2023-01-23 06:10:55.002647: step: 1790/1545, loss: 0.5346685647964478 2023-01-23 06:10:55.880264: step: 1792/1545, loss: 0.7371695637702942 2023-01-23 06:10:56.849110: step: 1794/1545, loss: 0.27728402614593506 2023-01-23 06:10:57.704228: step: 1796/1545, loss: 1.6068278551101685 2023-01-23 06:10:58.618685: step: 1798/1545, loss: 1.2619144916534424 2023-01-23 06:10:59.472193: step: 1800/1545, loss: 0.7137714624404907 2023-01-23 06:11:00.407286: step: 1802/1545, loss: 1.1744461059570312 2023-01-23 06:11:01.319494: step: 1804/1545, loss: 0.5230898261070251 2023-01-23 06:11:02.170476: step: 1806/1545, loss: 0.8347081542015076 2023-01-23 06:11:03.013583: step: 1808/1545, loss: 0.3481460213661194 2023-01-23 06:11:03.880180: step: 1810/1545, loss: 0.9562810063362122 2023-01-23 06:11:04.751570: step: 1812/1545, loss: 0.8785134553909302 2023-01-23 06:11:05.645994: step: 1814/1545, loss: 1.049479365348816 2023-01-23 06:11:06.497852: step: 1816/1545, loss: 0.8642470240592957 2023-01-23 06:11:07.364846: step: 1818/1545, loss: 1.163943886756897 2023-01-23 06:11:08.301290: step: 1820/1545, loss: 1.120402216911316 2023-01-23 06:11:09.222524: step: 1822/1545, loss: 0.6128277778625488 2023-01-23 06:11:10.076172: step: 1824/1545, loss: 3.960726022720337 2023-01-23 06:11:10.971868: step: 1826/1545, loss: 0.47035789489746094 2023-01-23 06:11:11.871872: step: 1828/1545, loss: 3.5929172039031982 2023-01-23 06:11:12.748300: step: 1830/1545, loss: 3.6034884452819824 2023-01-23 06:11:13.682826: step: 1832/1545, loss: 1.1088829040527344 2023-01-23 06:11:14.551663: step: 1834/1545, loss: 1.2795610427856445 2023-01-23 06:11:15.375857: step: 1836/1545, loss: 1.0037826299667358 2023-01-23 06:11:16.249366: step: 1838/1545, loss: 1.727279543876648 2023-01-23 06:11:17.128394: step: 1840/1545, loss: 0.5240848660469055 2023-01-23 06:11:18.007177: step: 1842/1545, loss: 0.9618561863899231 2023-01-23 06:11:18.883947: step: 1844/1545, loss: 2.1485774517059326 2023-01-23 06:11:19.741143: step: 1846/1545, loss: 1.506737232208252 2023-01-23 06:11:20.613514: step: 1848/1545, loss: 0.6144452691078186 2023-01-23 06:11:21.524152: step: 1850/1545, loss: 0.5227932929992676 2023-01-23 06:11:22.393266: step: 1852/1545, loss: 1.331467866897583 2023-01-23 06:11:23.287707: step: 1854/1545, loss: 1.7367100715637207 2023-01-23 06:11:24.232096: step: 1856/1545, loss: 0.8985303044319153 2023-01-23 06:11:25.103611: step: 1858/1545, loss: 1.322638750076294 2023-01-23 06:11:25.960050: step: 1860/1545, loss: 1.4061349630355835 2023-01-23 06:11:26.843038: step: 1862/1545, loss: 0.6549632549285889 2023-01-23 06:11:27.710940: step: 1864/1545, loss: 0.8963990807533264 2023-01-23 06:11:28.597711: step: 1866/1545, loss: 0.4756295382976532 2023-01-23 06:11:29.454167: step: 1868/1545, loss: 0.6720805168151855 2023-01-23 06:11:30.360930: step: 1870/1545, loss: 0.686960756778717 2023-01-23 06:11:31.334432: step: 1872/1545, loss: 0.9769124388694763 2023-01-23 06:11:32.188613: step: 1874/1545, loss: 2.1643106937408447 2023-01-23 06:11:33.181927: step: 1876/1545, loss: 1.3663824796676636 2023-01-23 06:11:34.082588: step: 1878/1545, loss: 0.47830966114997864 2023-01-23 06:11:34.963704: step: 1880/1545, loss: 0.42647382616996765 2023-01-23 06:11:35.866502: step: 1882/1545, loss: 0.8451916575431824 2023-01-23 06:11:36.755138: step: 1884/1545, loss: 0.784562885761261 2023-01-23 06:11:37.652058: step: 1886/1545, loss: 3.2023532390594482 2023-01-23 06:11:38.527065: step: 1888/1545, loss: 2.9932150840759277 2023-01-23 06:11:39.389565: step: 1890/1545, loss: 6.134037494659424 2023-01-23 06:11:40.276267: step: 1892/1545, loss: 11.143755912780762 2023-01-23 06:11:41.159202: step: 1894/1545, loss: 0.5819617509841919 2023-01-23 06:11:42.009071: step: 1896/1545, loss: 1.4185816049575806 2023-01-23 06:11:42.883379: step: 1898/1545, loss: 0.6144124269485474 2023-01-23 06:11:43.782706: step: 1900/1545, loss: 0.955568790435791 2023-01-23 06:11:44.636610: step: 1902/1545, loss: 1.0936017036437988 2023-01-23 06:11:45.571785: step: 1904/1545, loss: 0.2927267849445343 2023-01-23 06:11:46.448361: step: 1906/1545, loss: 0.8743471503257751 2023-01-23 06:11:47.306169: step: 1908/1545, loss: 0.7342495918273926 2023-01-23 06:11:48.208300: step: 1910/1545, loss: 1.2716022729873657 2023-01-23 06:11:49.059663: step: 1912/1545, loss: 2.834843397140503 2023-01-23 06:11:49.936480: step: 1914/1545, loss: 0.48580965399742126 2023-01-23 06:11:50.800027: step: 1916/1545, loss: 0.8083015084266663 2023-01-23 06:11:51.735815: step: 1918/1545, loss: 1.2683260440826416 2023-01-23 06:11:52.574520: step: 1920/1545, loss: 1.0610626935958862 2023-01-23 06:11:53.431917: step: 1922/1545, loss: 0.45227164030075073 2023-01-23 06:11:54.291527: step: 1924/1545, loss: 1.8824665546417236 2023-01-23 06:11:55.192214: step: 1926/1545, loss: 0.7356679439544678 2023-01-23 06:11:56.053472: step: 1928/1545, loss: 1.304715633392334 2023-01-23 06:11:57.014211: step: 1930/1545, loss: 6.38797664642334 2023-01-23 06:11:57.897656: step: 1932/1545, loss: 1.1106783151626587 2023-01-23 06:11:58.749205: step: 1934/1545, loss: 0.4559077024459839 2023-01-23 06:11:59.642866: step: 1936/1545, loss: 1.1795384883880615 2023-01-23 06:12:00.557614: step: 1938/1545, loss: 0.8003882765769958 2023-01-23 06:12:01.428569: step: 1940/1545, loss: 6.833339691162109 2023-01-23 06:12:02.315627: step: 1942/1545, loss: 1.4773164987564087 2023-01-23 06:12:03.168060: step: 1944/1545, loss: 0.7644426226615906 2023-01-23 06:12:04.119499: step: 1946/1545, loss: 0.9684181213378906 2023-01-23 06:12:04.999134: step: 1948/1545, loss: 3.2360117435455322 2023-01-23 06:12:05.874243: step: 1950/1545, loss: 0.7753073573112488 2023-01-23 06:12:06.774739: step: 1952/1545, loss: 1.0157798528671265 2023-01-23 06:12:07.660737: step: 1954/1545, loss: 7.012663841247559 2023-01-23 06:12:08.515752: step: 1956/1545, loss: 1.3976941108703613 2023-01-23 06:12:09.375810: step: 1958/1545, loss: 0.9134364128112793 2023-01-23 06:12:10.264158: step: 1960/1545, loss: 0.9548817873001099 2023-01-23 06:12:11.148082: step: 1962/1545, loss: 0.8332924842834473 2023-01-23 06:12:11.989870: step: 1964/1545, loss: 0.4612998366355896 2023-01-23 06:12:12.893597: step: 1966/1545, loss: 1.1966520547866821 2023-01-23 06:12:13.776166: step: 1968/1545, loss: 7.775073528289795 2023-01-23 06:12:14.637768: step: 1970/1545, loss: 2.790938377380371 2023-01-23 06:12:15.525718: step: 1972/1545, loss: 1.068734049797058 2023-01-23 06:12:16.407892: step: 1974/1545, loss: 3.1436100006103516 2023-01-23 06:12:17.276338: step: 1976/1545, loss: 0.7404652833938599 2023-01-23 06:12:18.214403: step: 1978/1545, loss: 1.1288173198699951 2023-01-23 06:12:19.136127: step: 1980/1545, loss: 1.1934428215026855 2023-01-23 06:12:19.996366: step: 1982/1545, loss: 0.5098572373390198 2023-01-23 06:12:20.882471: step: 1984/1545, loss: 3.5126473903656006 2023-01-23 06:12:21.799445: step: 1986/1545, loss: 1.048400640487671 2023-01-23 06:12:22.731136: step: 1988/1545, loss: 0.7944270372390747 2023-01-23 06:12:23.588539: step: 1990/1545, loss: 1.5575361251831055 2023-01-23 06:12:24.491763: step: 1992/1545, loss: 0.9076969027519226 2023-01-23 06:12:25.370835: step: 1994/1545, loss: 0.5859847664833069 2023-01-23 06:12:26.301472: step: 1996/1545, loss: 0.4420800805091858 2023-01-23 06:12:27.175737: step: 1998/1545, loss: 0.8831037878990173 2023-01-23 06:12:28.042499: step: 2000/1545, loss: 3.1910643577575684 2023-01-23 06:12:28.913147: step: 2002/1545, loss: 0.6543571352958679 2023-01-23 06:12:29.795162: step: 2004/1545, loss: 2.5730888843536377 2023-01-23 06:12:30.685571: step: 2006/1545, loss: 1.0286791324615479 2023-01-23 06:12:31.554059: step: 2008/1545, loss: 0.6725202202796936 2023-01-23 06:12:32.459273: step: 2010/1545, loss: 0.5410431623458862 2023-01-23 06:12:33.341370: step: 2012/1545, loss: 1.422852873802185 2023-01-23 06:12:34.247970: step: 2014/1545, loss: 0.4865967631340027 2023-01-23 06:12:35.121671: step: 2016/1545, loss: 0.7068657279014587 2023-01-23 06:12:35.956812: step: 2018/1545, loss: 0.5078771114349365 2023-01-23 06:12:36.860158: step: 2020/1545, loss: 0.7739605903625488 2023-01-23 06:12:37.703891: step: 2022/1545, loss: 1.003852367401123 2023-01-23 06:12:38.605713: step: 2024/1545, loss: 0.7818652987480164 2023-01-23 06:12:39.470804: step: 2026/1545, loss: 3.0341134071350098 2023-01-23 06:12:40.325698: step: 2028/1545, loss: 0.5078012943267822 2023-01-23 06:12:41.228040: step: 2030/1545, loss: 1.130571961402893 2023-01-23 06:12:42.136762: step: 2032/1545, loss: 3.748253345489502 2023-01-23 06:12:42.988270: step: 2034/1545, loss: 2.9848790168762207 2023-01-23 06:12:43.826619: step: 2036/1545, loss: 0.4707631766796112 2023-01-23 06:12:44.715023: step: 2038/1545, loss: 1.482438087463379 2023-01-23 06:12:45.600828: step: 2040/1545, loss: 2.785770893096924 2023-01-23 06:12:46.489651: step: 2042/1545, loss: 6.576028823852539 2023-01-23 06:12:47.389913: step: 2044/1545, loss: 0.7649105787277222 2023-01-23 06:12:48.265149: step: 2046/1545, loss: 1.0268864631652832 2023-01-23 06:12:49.156673: step: 2048/1545, loss: 0.7102678418159485 2023-01-23 06:12:50.024293: step: 2050/1545, loss: 0.8756704926490784 2023-01-23 06:12:50.929112: step: 2052/1545, loss: 0.5236844420433044 2023-01-23 06:12:51.792374: step: 2054/1545, loss: 0.7678630352020264 2023-01-23 06:12:52.644774: step: 2056/1545, loss: 3.297753095626831 2023-01-23 06:12:53.537334: step: 2058/1545, loss: 1.0461264848709106 2023-01-23 06:12:54.391332: step: 2060/1545, loss: 0.8886682987213135 2023-01-23 06:12:55.285511: step: 2062/1545, loss: 1.237091302871704 2023-01-23 06:12:56.170180: step: 2064/1545, loss: 1.0200437307357788 2023-01-23 06:12:57.052616: step: 2066/1545, loss: 0.9920545816421509 2023-01-23 06:12:57.907323: step: 2068/1545, loss: 0.9072170853614807 2023-01-23 06:12:58.856136: step: 2070/1545, loss: 1.2341617345809937 2023-01-23 06:12:59.749680: step: 2072/1545, loss: 1.3885382413864136 2023-01-23 06:13:00.604140: step: 2074/1545, loss: 0.5381878018379211 2023-01-23 06:13:01.538288: step: 2076/1545, loss: 1.2634217739105225 2023-01-23 06:13:02.399864: step: 2078/1545, loss: 0.8663774728775024 2023-01-23 06:13:03.314387: step: 2080/1545, loss: 0.5694935321807861 2023-01-23 06:13:04.188226: step: 2082/1545, loss: 0.7956369519233704 2023-01-23 06:13:05.139743: step: 2084/1545, loss: 0.8390076756477356 2023-01-23 06:13:06.029447: step: 2086/1545, loss: 1.7120704650878906 2023-01-23 06:13:06.885931: step: 2088/1545, loss: 1.0380748510360718 2023-01-23 06:13:07.773689: step: 2090/1545, loss: 0.48229995369911194 2023-01-23 06:13:08.599120: step: 2092/1545, loss: 2.8930654525756836 2023-01-23 06:13:09.469801: step: 2094/1545, loss: 0.6861674189567566 2023-01-23 06:13:10.315356: step: 2096/1545, loss: 0.8419686555862427 2023-01-23 06:13:11.227471: step: 2098/1545, loss: 1.0703684091567993 2023-01-23 06:13:12.078598: step: 2100/1545, loss: 0.5605739951133728 2023-01-23 06:13:12.968623: step: 2102/1545, loss: 0.8509119749069214 2023-01-23 06:13:13.810098: step: 2104/1545, loss: 0.7433502078056335 2023-01-23 06:13:14.728531: step: 2106/1545, loss: 2.8749449253082275 2023-01-23 06:13:15.599775: step: 2108/1545, loss: 1.06813383102417 2023-01-23 06:13:16.469964: step: 2110/1545, loss: 1.0725867748260498 2023-01-23 06:13:17.324897: step: 2112/1545, loss: 1.2783827781677246 2023-01-23 06:13:18.190422: step: 2114/1545, loss: 0.6730623245239258 2023-01-23 06:13:19.084879: step: 2116/1545, loss: 0.918838620185852 2023-01-23 06:13:19.954589: step: 2118/1545, loss: 0.9208887815475464 2023-01-23 06:13:20.842570: step: 2120/1545, loss: 0.6743975281715393 2023-01-23 06:13:21.700618: step: 2122/1545, loss: 0.5899969339370728 2023-01-23 06:13:22.566182: step: 2124/1545, loss: 0.6113951802253723 2023-01-23 06:13:23.414440: step: 2126/1545, loss: 0.406671404838562 2023-01-23 06:13:24.244433: step: 2128/1545, loss: 0.4388429522514343 2023-01-23 06:13:25.264188: step: 2130/1545, loss: 0.9625780582427979 2023-01-23 06:13:26.151488: step: 2132/1545, loss: 0.7486484050750732 2023-01-23 06:13:27.021672: step: 2134/1545, loss: 1.1746939420700073 2023-01-23 06:13:27.948016: step: 2136/1545, loss: 0.4032546579837799 2023-01-23 06:13:28.924804: step: 2138/1545, loss: 0.5881575345993042 2023-01-23 06:13:29.817409: step: 2140/1545, loss: 0.8674177527427673 2023-01-23 06:13:30.703852: step: 2142/1545, loss: 0.7641012668609619 2023-01-23 06:13:31.610756: step: 2144/1545, loss: 0.25281378626823425 2023-01-23 06:13:32.452990: step: 2146/1545, loss: 0.7660033106803894 2023-01-23 06:13:33.372903: step: 2148/1545, loss: 0.8925408720970154 2023-01-23 06:13:34.225005: step: 2150/1545, loss: 1.3579825162887573 2023-01-23 06:13:35.099063: step: 2152/1545, loss: 0.9766587615013123 2023-01-23 06:13:35.954699: step: 2154/1545, loss: 0.8460885882377625 2023-01-23 06:13:36.824559: step: 2156/1545, loss: 0.8896337747573853 2023-01-23 06:13:37.714857: step: 2158/1545, loss: 1.3482555150985718 2023-01-23 06:13:38.646171: step: 2160/1545, loss: 0.5994163155555725 2023-01-23 06:13:39.550252: step: 2162/1545, loss: 7.034087657928467 2023-01-23 06:13:40.480409: step: 2164/1545, loss: 0.9459083080291748 2023-01-23 06:13:41.365460: step: 2166/1545, loss: 0.8859612941741943 2023-01-23 06:13:42.247637: step: 2168/1545, loss: 0.765541136264801 2023-01-23 06:13:43.142308: step: 2170/1545, loss: 0.8420155644416809 2023-01-23 06:13:43.991359: step: 2172/1545, loss: 0.5899473428726196 2023-01-23 06:13:44.851729: step: 2174/1545, loss: 0.8350297808647156 2023-01-23 06:13:45.728289: step: 2176/1545, loss: 0.9344297647476196 2023-01-23 06:13:46.615713: step: 2178/1545, loss: 2.9004855155944824 2023-01-23 06:13:47.478118: step: 2180/1545, loss: 3.40547513961792 2023-01-23 06:13:48.338602: step: 2182/1545, loss: 0.8523802161216736 2023-01-23 06:13:49.286996: step: 2184/1545, loss: 1.1821681261062622 2023-01-23 06:13:50.147404: step: 2186/1545, loss: 0.861617386341095 2023-01-23 06:13:51.032221: step: 2188/1545, loss: 1.1762175559997559 2023-01-23 06:13:51.908100: step: 2190/1545, loss: 0.7502158284187317 2023-01-23 06:13:52.839136: step: 2192/1545, loss: 7.324232578277588 2023-01-23 06:13:53.778837: step: 2194/1545, loss: 0.8908608555793762 2023-01-23 06:13:54.685615: step: 2196/1545, loss: 0.6339485049247742 2023-01-23 06:13:55.570563: step: 2198/1545, loss: 0.47583532333374023 2023-01-23 06:13:56.490832: step: 2200/1545, loss: 0.6126729846000671 2023-01-23 06:13:57.360898: step: 2202/1545, loss: 0.34502583742141724 2023-01-23 06:13:58.204948: step: 2204/1545, loss: 0.2951253354549408 2023-01-23 06:13:59.084959: step: 2206/1545, loss: 0.26715973019599915 2023-01-23 06:13:59.950814: step: 2208/1545, loss: 1.425219178199768 2023-01-23 06:14:00.902672: step: 2210/1545, loss: 3.373021364212036 2023-01-23 06:14:01.752598: step: 2212/1545, loss: 0.47612082958221436 2023-01-23 06:14:02.682632: step: 2214/1545, loss: 1.5162843465805054 2023-01-23 06:14:03.564789: step: 2216/1545, loss: 0.8329571485519409 2023-01-23 06:14:04.400054: step: 2218/1545, loss: 0.5252253413200378 2023-01-23 06:14:05.299665: step: 2220/1545, loss: 0.9450862407684326 2023-01-23 06:14:06.224734: step: 2222/1545, loss: 1.1812901496887207 2023-01-23 06:14:07.120414: step: 2224/1545, loss: 1.0937098264694214 2023-01-23 06:14:08.003588: step: 2226/1545, loss: 0.30194035172462463 2023-01-23 06:14:08.838200: step: 2228/1545, loss: 4.000166893005371 2023-01-23 06:14:09.707082: step: 2230/1545, loss: 1.5041335821151733 2023-01-23 06:14:10.594381: step: 2232/1545, loss: 0.4197429418563843 2023-01-23 06:14:11.470053: step: 2234/1545, loss: 0.4716333746910095 2023-01-23 06:14:12.329298: step: 2236/1545, loss: 0.8496631979942322 2023-01-23 06:14:13.197361: step: 2238/1545, loss: 0.9376907348632812 2023-01-23 06:14:14.135970: step: 2240/1545, loss: 0.6511625647544861 2023-01-23 06:14:15.088424: step: 2242/1545, loss: 0.6655474305152893 2023-01-23 06:14:16.003080: step: 2244/1545, loss: 0.40165308117866516 2023-01-23 06:14:16.894836: step: 2246/1545, loss: 0.23933768272399902 2023-01-23 06:14:17.765975: step: 2248/1545, loss: 0.3396545648574829 2023-01-23 06:14:18.605857: step: 2250/1545, loss: 0.4571147859096527 2023-01-23 06:14:19.495497: step: 2252/1545, loss: 1.331794023513794 2023-01-23 06:14:20.385465: step: 2254/1545, loss: 9.108797073364258 2023-01-23 06:14:21.305753: step: 2256/1545, loss: 2.8784749507904053 2023-01-23 06:14:22.157271: step: 2258/1545, loss: 0.4577253758907318 2023-01-23 06:14:23.012616: step: 2260/1545, loss: 1.1959489583969116 2023-01-23 06:14:24.041308: step: 2262/1545, loss: 3.5267117023468018 2023-01-23 06:14:24.974810: step: 2264/1545, loss: 1.2898896932601929 2023-01-23 06:14:25.818199: step: 2266/1545, loss: 0.28952649235725403 2023-01-23 06:14:26.698993: step: 2268/1545, loss: 0.7482442855834961 2023-01-23 06:14:27.551442: step: 2270/1545, loss: 0.4671156704425812 2023-01-23 06:14:28.372358: step: 2272/1545, loss: 3.3889193534851074 2023-01-23 06:14:29.176568: step: 2274/1545, loss: 0.4084171950817108 2023-01-23 06:14:30.037917: step: 2276/1545, loss: 1.235846757888794 2023-01-23 06:14:30.938318: step: 2278/1545, loss: 0.6431294083595276 2023-01-23 06:14:31.848782: step: 2280/1545, loss: 0.506472110748291 2023-01-23 06:14:32.680030: step: 2282/1545, loss: 0.7063987851142883 2023-01-23 06:14:33.561900: step: 2284/1545, loss: 1.352724313735962 2023-01-23 06:14:34.444677: step: 2286/1545, loss: 1.2502942085266113 2023-01-23 06:14:35.346070: step: 2288/1545, loss: 1.1451939344406128 2023-01-23 06:14:36.254480: step: 2290/1545, loss: 0.7688295841217041 2023-01-23 06:14:37.146397: step: 2292/1545, loss: 0.9116706252098083 2023-01-23 06:14:38.037482: step: 2294/1545, loss: 0.9386852383613586 2023-01-23 06:14:38.917631: step: 2296/1545, loss: 0.6774575114250183 2023-01-23 06:14:39.840133: step: 2298/1545, loss: 1.174914002418518 2023-01-23 06:14:40.711117: step: 2300/1545, loss: 0.5864061117172241 2023-01-23 06:14:41.619624: step: 2302/1545, loss: 1.024807095527649 2023-01-23 06:14:42.516006: step: 2304/1545, loss: 0.6600725054740906 2023-01-23 06:14:43.370248: step: 2306/1545, loss: 0.6983304619789124 2023-01-23 06:14:44.277221: step: 2308/1545, loss: 1.2034108638763428 2023-01-23 06:14:45.157532: step: 2310/1545, loss: 4.171336650848389 2023-01-23 06:14:46.007132: step: 2312/1545, loss: 0.7126199007034302 2023-01-23 06:14:46.872604: step: 2314/1545, loss: 0.8119590282440186 2023-01-23 06:14:47.722351: step: 2316/1545, loss: 0.5909827947616577 2023-01-23 06:14:48.629356: step: 2318/1545, loss: 1.00569748878479 2023-01-23 06:14:49.509620: step: 2320/1545, loss: 4.103519916534424 2023-01-23 06:14:50.392869: step: 2322/1545, loss: 1.1033107042312622 2023-01-23 06:14:51.337786: step: 2324/1545, loss: 0.6424861550331116 2023-01-23 06:14:52.252053: step: 2326/1545, loss: 0.5326475501060486 2023-01-23 06:14:53.159863: step: 2328/1545, loss: 2.1164979934692383 2023-01-23 06:14:54.017576: step: 2330/1545, loss: 0.8957887887954712 2023-01-23 06:14:54.885447: step: 2332/1545, loss: 2.8274049758911133 2023-01-23 06:14:55.760616: step: 2334/1545, loss: 1.4017082452774048 2023-01-23 06:14:56.628743: step: 2336/1545, loss: 0.9298343062400818 2023-01-23 06:14:57.482512: step: 2338/1545, loss: 0.9260937571525574 2023-01-23 06:14:58.373154: step: 2340/1545, loss: 1.1840933561325073 2023-01-23 06:14:59.208900: step: 2342/1545, loss: 0.8805722594261169 2023-01-23 06:15:00.089924: step: 2344/1545, loss: 0.7127124071121216 2023-01-23 06:15:01.015087: step: 2346/1545, loss: 1.4274368286132812 2023-01-23 06:15:01.948532: step: 2348/1545, loss: 2.696537494659424 2023-01-23 06:15:02.825205: step: 2350/1545, loss: 0.7379690408706665 2023-01-23 06:15:03.672661: step: 2352/1545, loss: 3.4017019271850586 2023-01-23 06:15:04.566739: step: 2354/1545, loss: 1.081566572189331 2023-01-23 06:15:05.445361: step: 2356/1545, loss: 0.8974564075469971 2023-01-23 06:15:06.295543: step: 2358/1545, loss: 0.7291873097419739 2023-01-23 06:15:07.153462: step: 2360/1545, loss: 0.362276554107666 2023-01-23 06:15:08.030711: step: 2362/1545, loss: 1.518754482269287 2023-01-23 06:15:08.975622: step: 2364/1545, loss: 0.7427237033843994 2023-01-23 06:15:09.855199: step: 2366/1545, loss: 1.128271222114563 2023-01-23 06:15:10.759234: step: 2368/1545, loss: 1.7957369089126587 2023-01-23 06:15:11.659359: step: 2370/1545, loss: 0.9533534049987793 2023-01-23 06:15:12.508165: step: 2372/1545, loss: 1.6297050714492798 2023-01-23 06:15:13.429578: step: 2374/1545, loss: 0.9052348136901855 2023-01-23 06:15:14.302496: step: 2376/1545, loss: 0.9826951026916504 2023-01-23 06:15:15.167920: step: 2378/1545, loss: 1.252221703529358 2023-01-23 06:15:16.045216: step: 2380/1545, loss: 0.7891566753387451 2023-01-23 06:15:16.938116: step: 2382/1545, loss: 0.759320080280304 2023-01-23 06:15:17.801171: step: 2384/1545, loss: 0.39346644282341003 2023-01-23 06:15:18.658130: step: 2386/1545, loss: 0.5344929695129395 2023-01-23 06:15:19.637198: step: 2388/1545, loss: 0.5542062520980835 2023-01-23 06:15:20.523927: step: 2390/1545, loss: 1.848830223083496 2023-01-23 06:15:21.393243: step: 2392/1545, loss: 0.43965208530426025 2023-01-23 06:15:22.267750: step: 2394/1545, loss: 1.2868901491165161 2023-01-23 06:15:23.175128: step: 2396/1545, loss: 3.189185857772827 2023-01-23 06:15:24.060912: step: 2398/1545, loss: 3.06792950630188 2023-01-23 06:15:24.908459: step: 2400/1545, loss: 2.7111425399780273 2023-01-23 06:15:25.790307: step: 2402/1545, loss: 0.6229475736618042 2023-01-23 06:15:26.693871: step: 2404/1545, loss: 0.9126234650611877 2023-01-23 06:15:27.561892: step: 2406/1545, loss: 0.9039761424064636 2023-01-23 06:15:28.444548: step: 2408/1545, loss: 2.583142042160034 2023-01-23 06:15:29.322402: step: 2410/1545, loss: 0.7682861685752869 2023-01-23 06:15:30.298029: step: 2412/1545, loss: 13.635993003845215 2023-01-23 06:15:31.213075: step: 2414/1545, loss: 1.2753987312316895 2023-01-23 06:15:32.098293: step: 2416/1545, loss: 0.8784481287002563 2023-01-23 06:15:32.983201: step: 2418/1545, loss: 0.7632952928543091 2023-01-23 06:15:33.858942: step: 2420/1545, loss: 1.2085016965866089 2023-01-23 06:15:34.770999: step: 2422/1545, loss: 1.1949830055236816 2023-01-23 06:15:35.677494: step: 2424/1545, loss: 6.449619293212891 2023-01-23 06:15:36.523333: step: 2426/1545, loss: 0.9337713122367859 2023-01-23 06:15:37.391110: step: 2428/1545, loss: 1.1792776584625244 2023-01-23 06:15:38.260458: step: 2430/1545, loss: 0.6704910397529602 2023-01-23 06:15:39.159201: step: 2432/1545, loss: 0.27641764283180237 2023-01-23 06:15:40.021849: step: 2434/1545, loss: 0.7028283476829529 2023-01-23 06:15:40.866991: step: 2436/1545, loss: 0.5431740283966064 2023-01-23 06:15:41.759313: step: 2438/1545, loss: 1.2830370664596558 2023-01-23 06:15:42.643979: step: 2440/1545, loss: 0.2254249006509781 2023-01-23 06:15:43.515588: step: 2442/1545, loss: 3.2012319564819336 2023-01-23 06:15:44.409660: step: 2444/1545, loss: 0.9103410840034485 2023-01-23 06:15:45.278165: step: 2446/1545, loss: 0.8460462689399719 2023-01-23 06:15:46.153030: step: 2448/1545, loss: 0.7369756698608398 2023-01-23 06:15:47.004159: step: 2450/1545, loss: 0.6119635105133057 2023-01-23 06:15:47.908818: step: 2452/1545, loss: 0.7956328988075256 2023-01-23 06:15:48.797630: step: 2454/1545, loss: 1.4388078451156616 2023-01-23 06:15:49.763608: step: 2456/1545, loss: 0.627934455871582 2023-01-23 06:15:50.606737: step: 2458/1545, loss: 0.36527732014656067 2023-01-23 06:15:51.460418: step: 2460/1545, loss: 1.7380086183547974 2023-01-23 06:15:52.323021: step: 2462/1545, loss: 1.2238781452178955 2023-01-23 06:15:53.194812: step: 2464/1545, loss: 1.043737530708313 2023-01-23 06:15:54.076175: step: 2466/1545, loss: 0.4629502296447754 2023-01-23 06:15:55.032284: step: 2468/1545, loss: 1.522569179534912 2023-01-23 06:15:55.923524: step: 2470/1545, loss: 0.42111703753471375 2023-01-23 06:15:56.758625: step: 2472/1545, loss: 0.9529165029525757 2023-01-23 06:15:57.625977: step: 2474/1545, loss: 0.687218964099884 2023-01-23 06:15:58.513131: step: 2476/1545, loss: 2.9416160583496094 2023-01-23 06:15:59.380786: step: 2478/1545, loss: 1.3244954347610474 2023-01-23 06:16:00.305888: step: 2480/1545, loss: 0.5812538266181946 2023-01-23 06:16:01.183935: step: 2482/1545, loss: 0.41222599148750305 2023-01-23 06:16:02.021170: step: 2484/1545, loss: 0.9516597986221313 2023-01-23 06:16:02.876876: step: 2486/1545, loss: 1.3375468254089355 2023-01-23 06:16:03.751855: step: 2488/1545, loss: 0.8891750574111938 2023-01-23 06:16:04.607712: step: 2490/1545, loss: 1.733229398727417 2023-01-23 06:16:05.475924: step: 2492/1545, loss: 1.3095303773880005 2023-01-23 06:16:06.398323: step: 2494/1545, loss: 1.2742023468017578 2023-01-23 06:16:07.244003: step: 2496/1545, loss: 0.736778199672699 2023-01-23 06:16:08.187434: step: 2498/1545, loss: 0.768250584602356 2023-01-23 06:16:09.064457: step: 2500/1545, loss: 1.1940741539001465 2023-01-23 06:16:09.938255: step: 2502/1545, loss: 0.4188658595085144 2023-01-23 06:16:10.798827: step: 2504/1545, loss: 0.9685382843017578 2023-01-23 06:16:11.688929: step: 2506/1545, loss: 1.3564502000808716 2023-01-23 06:16:12.568208: step: 2508/1545, loss: 0.8942918181419373 2023-01-23 06:16:13.419331: step: 2510/1545, loss: 1.0103191137313843 2023-01-23 06:16:14.262862: step: 2512/1545, loss: 3.131258726119995 2023-01-23 06:16:15.186054: step: 2514/1545, loss: 0.810117781162262 2023-01-23 06:16:16.123960: step: 2516/1545, loss: 2.6226086616516113 2023-01-23 06:16:17.003374: step: 2518/1545, loss: 0.788322925567627 2023-01-23 06:16:17.870008: step: 2520/1545, loss: 1.0955013036727905 2023-01-23 06:16:18.759372: step: 2522/1545, loss: 0.582757294178009 2023-01-23 06:16:19.718819: step: 2524/1545, loss: 1.0100823640823364 2023-01-23 06:16:20.599652: step: 2526/1545, loss: 0.5327647924423218 2023-01-23 06:16:21.488548: step: 2528/1545, loss: 1.2027790546417236 2023-01-23 06:16:22.370564: step: 2530/1545, loss: 0.458234965801239 2023-01-23 06:16:23.263802: step: 2532/1545, loss: 0.7432717680931091 2023-01-23 06:16:24.195618: step: 2534/1545, loss: 0.5872328281402588 2023-01-23 06:16:25.050110: step: 2536/1545, loss: 0.34458020329475403 2023-01-23 06:16:25.928680: step: 2538/1545, loss: 0.6790757179260254 2023-01-23 06:16:26.843464: step: 2540/1545, loss: 1.3667635917663574 2023-01-23 06:16:27.758139: step: 2542/1545, loss: 3.288576126098633 2023-01-23 06:16:28.652535: step: 2544/1545, loss: 2.811264991760254 2023-01-23 06:16:29.526270: step: 2546/1545, loss: 0.36913809180259705 2023-01-23 06:16:30.420176: step: 2548/1545, loss: 1.098427176475525 2023-01-23 06:16:31.255654: step: 2550/1545, loss: 3.057694911956787 2023-01-23 06:16:32.101436: step: 2552/1545, loss: 0.6933318972587585 2023-01-23 06:16:32.984331: step: 2554/1545, loss: 1.1904520988464355 2023-01-23 06:16:33.863285: step: 2556/1545, loss: 1.0079857110977173 2023-01-23 06:16:34.770924: step: 2558/1545, loss: 0.7193378806114197 2023-01-23 06:16:35.648159: step: 2560/1545, loss: 1.0250022411346436 2023-01-23 06:16:36.528025: step: 2562/1545, loss: 1.1161088943481445 2023-01-23 06:16:37.359157: step: 2564/1545, loss: 1.240907907485962 2023-01-23 06:16:38.236365: step: 2566/1545, loss: 0.6458344459533691 2023-01-23 06:16:39.143429: step: 2568/1545, loss: 6.2096357345581055 2023-01-23 06:16:40.008883: step: 2570/1545, loss: 1.1484359502792358 2023-01-23 06:16:40.866018: step: 2572/1545, loss: 1.0932546854019165 2023-01-23 06:16:41.732202: step: 2574/1545, loss: 3.009823799133301 2023-01-23 06:16:42.592889: step: 2576/1545, loss: 0.609820544719696 2023-01-23 06:16:43.468279: step: 2578/1545, loss: 6.7871551513671875 2023-01-23 06:16:44.351066: step: 2580/1545, loss: 1.0670905113220215 2023-01-23 06:16:45.229097: step: 2582/1545, loss: 0.8534599542617798 2023-01-23 06:16:46.127089: step: 2584/1545, loss: 0.391345351934433 2023-01-23 06:16:47.011275: step: 2586/1545, loss: 0.5818516612052917 2023-01-23 06:16:47.880813: step: 2588/1545, loss: 1.335153579711914 2023-01-23 06:16:48.748341: step: 2590/1545, loss: 0.5249457359313965 2023-01-23 06:16:49.629859: step: 2592/1545, loss: 0.4538325071334839 2023-01-23 06:16:50.525771: step: 2594/1545, loss: 1.3095289468765259 2023-01-23 06:16:51.395095: step: 2596/1545, loss: 0.8521267771720886 2023-01-23 06:16:52.287759: step: 2598/1545, loss: 0.7307634949684143 2023-01-23 06:16:53.182486: step: 2600/1545, loss: 0.630987823009491 2023-01-23 06:16:54.035528: step: 2602/1545, loss: 0.5869147181510925 2023-01-23 06:16:54.917832: step: 2604/1545, loss: 2.033398389816284 2023-01-23 06:16:55.759454: step: 2606/1545, loss: 1.0232324600219727 2023-01-23 06:16:56.650507: step: 2608/1545, loss: 0.470900297164917 2023-01-23 06:16:57.512953: step: 2610/1545, loss: 0.7521023750305176 2023-01-23 06:16:58.397698: step: 2612/1545, loss: 1.3035670518875122 2023-01-23 06:16:59.293034: step: 2614/1545, loss: 3.301325559616089 2023-01-23 06:17:00.159361: step: 2616/1545, loss: 1.0498626232147217 2023-01-23 06:17:01.030028: step: 2618/1545, loss: 5.225356578826904 2023-01-23 06:17:01.981424: step: 2620/1545, loss: 0.44368457794189453 2023-01-23 06:17:02.884378: step: 2622/1545, loss: 0.6507720351219177 2023-01-23 06:17:03.742344: step: 2624/1545, loss: 1.4470422267913818 2023-01-23 06:17:04.584116: step: 2626/1545, loss: 1.0209627151489258 2023-01-23 06:17:05.470676: step: 2628/1545, loss: 0.7909441590309143 2023-01-23 06:17:06.331888: step: 2630/1545, loss: 3.3590965270996094 2023-01-23 06:17:07.194392: step: 2632/1545, loss: 2.8603482246398926 2023-01-23 06:17:08.054763: step: 2634/1545, loss: 2.941471815109253 2023-01-23 06:17:08.984069: step: 2636/1545, loss: 0.14105071127414703 2023-01-23 06:17:09.853101: step: 2638/1545, loss: 0.3500332832336426 2023-01-23 06:17:10.721514: step: 2640/1545, loss: 0.744299590587616 2023-01-23 06:17:11.631084: step: 2642/1545, loss: 1.341931700706482 2023-01-23 06:17:12.463951: step: 2644/1545, loss: 0.979753851890564 2023-01-23 06:17:13.353740: step: 2646/1545, loss: 2.0536415576934814 2023-01-23 06:17:14.264889: step: 2648/1545, loss: 6.746807098388672 2023-01-23 06:17:15.133989: step: 2650/1545, loss: 1.114149570465088 2023-01-23 06:17:16.113733: step: 2652/1545, loss: 0.2615000307559967 2023-01-23 06:17:17.004835: step: 2654/1545, loss: 1.007692813873291 2023-01-23 06:17:17.912791: step: 2656/1545, loss: 0.8749117255210876 2023-01-23 06:17:18.850098: step: 2658/1545, loss: 0.3402954936027527 2023-01-23 06:17:19.757426: step: 2660/1545, loss: 0.7523267865180969 2023-01-23 06:17:20.641345: step: 2662/1545, loss: 0.4500807225704193 2023-01-23 06:17:21.525239: step: 2664/1545, loss: 0.5033014416694641 2023-01-23 06:17:22.356910: step: 2666/1545, loss: 7.794245719909668 2023-01-23 06:17:23.204698: step: 2668/1545, loss: 0.7124781608581543 2023-01-23 06:17:24.079547: step: 2670/1545, loss: 1.0424301624298096 2023-01-23 06:17:24.967994: step: 2672/1545, loss: 0.9462292194366455 2023-01-23 06:17:25.810130: step: 2674/1545, loss: 3.1436173915863037 2023-01-23 06:17:26.695593: step: 2676/1545, loss: 0.819339394569397 2023-01-23 06:17:27.594928: step: 2678/1545, loss: 2.8531038761138916 2023-01-23 06:17:28.478229: step: 2680/1545, loss: 1.2509901523590088 2023-01-23 06:17:29.353803: step: 2682/1545, loss: 0.9484467506408691 2023-01-23 06:17:30.197985: step: 2684/1545, loss: 0.9320753812789917 2023-01-23 06:17:31.060881: step: 2686/1545, loss: 1.8619272708892822 2023-01-23 06:17:32.013400: step: 2688/1545, loss: 0.7007502913475037 2023-01-23 06:17:32.861170: step: 2690/1545, loss: 1.4322587251663208 2023-01-23 06:17:33.759145: step: 2692/1545, loss: 2.865156412124634 2023-01-23 06:17:34.619860: step: 2694/1545, loss: 0.43986427783966064 2023-01-23 06:17:35.488913: step: 2696/1545, loss: 0.6623266935348511 2023-01-23 06:17:36.365333: step: 2698/1545, loss: 0.7017749547958374 2023-01-23 06:17:37.221767: step: 2700/1545, loss: 1.658281922340393 2023-01-23 06:17:38.110876: step: 2702/1545, loss: 0.6944625973701477 2023-01-23 06:17:38.942463: step: 2704/1545, loss: 0.5005613565444946 2023-01-23 06:17:39.802942: step: 2706/1545, loss: 2.7326221466064453 2023-01-23 06:17:40.657448: step: 2708/1545, loss: 0.6959399580955505 2023-01-23 06:17:41.573181: step: 2710/1545, loss: 0.7217367887496948 2023-01-23 06:17:42.444170: step: 2712/1545, loss: 0.521811842918396 2023-01-23 06:17:43.303327: step: 2714/1545, loss: 0.6326722502708435 2023-01-23 06:17:44.216166: step: 2716/1545, loss: 0.9943639039993286 2023-01-23 06:17:45.078029: step: 2718/1545, loss: 0.8102888464927673 2023-01-23 06:17:46.037370: step: 2720/1545, loss: 1.4108535051345825 2023-01-23 06:17:46.929138: step: 2722/1545, loss: 0.4570881128311157 2023-01-23 06:17:47.843460: step: 2724/1545, loss: 0.7493947148323059 2023-01-23 06:17:48.678736: step: 2726/1545, loss: 0.3265403211116791 2023-01-23 06:17:49.537307: step: 2728/1545, loss: 0.7439025044441223 2023-01-23 06:17:50.434912: step: 2730/1545, loss: 2.7952826023101807 2023-01-23 06:17:51.316504: step: 2732/1545, loss: 0.5710558891296387 2023-01-23 06:17:52.193801: step: 2734/1545, loss: 0.9114544987678528 2023-01-23 06:17:53.083306: step: 2736/1545, loss: 1.0023560523986816 2023-01-23 06:17:53.941092: step: 2738/1545, loss: 1.0708101987838745 2023-01-23 06:17:54.836059: step: 2740/1545, loss: 1.234997034072876 2023-01-23 06:17:55.715497: step: 2742/1545, loss: 0.2527763545513153 2023-01-23 06:17:56.618822: step: 2744/1545, loss: 2.118096351623535 2023-01-23 06:17:57.503320: step: 2746/1545, loss: 0.7769732475280762 2023-01-23 06:17:58.395387: step: 2748/1545, loss: 0.918812096118927 2023-01-23 06:17:59.304730: step: 2750/1545, loss: 0.722940981388092 2023-01-23 06:18:00.202093: step: 2752/1545, loss: 0.5391671061515808 2023-01-23 06:18:01.074847: step: 2754/1545, loss: 0.609589695930481 2023-01-23 06:18:01.915801: step: 2756/1545, loss: 0.45100659132003784 2023-01-23 06:18:02.836129: step: 2758/1545, loss: 0.8341823816299438 2023-01-23 06:18:03.721708: step: 2760/1545, loss: 6.369227409362793 2023-01-23 06:18:04.679781: step: 2762/1545, loss: 0.9088860750198364 2023-01-23 06:18:05.547490: step: 2764/1545, loss: 0.23177054524421692 2023-01-23 06:18:06.408450: step: 2766/1545, loss: 0.3898395001888275 2023-01-23 06:18:07.343970: step: 2768/1545, loss: 0.432620108127594 2023-01-23 06:18:08.237158: step: 2770/1545, loss: 1.9505105018615723 2023-01-23 06:18:09.110632: step: 2772/1545, loss: 1.9724777936935425 2023-01-23 06:18:10.035061: step: 2774/1545, loss: 0.4214915633201599 2023-01-23 06:18:10.879604: step: 2776/1545, loss: 1.0224310159683228 2023-01-23 06:18:11.737337: step: 2778/1545, loss: 0.4311838150024414 2023-01-23 06:18:12.647962: step: 2780/1545, loss: 0.599998414516449 2023-01-23 06:18:13.490671: step: 2782/1545, loss: 0.739910364151001 2023-01-23 06:18:14.368866: step: 2784/1545, loss: 0.6532590985298157 2023-01-23 06:18:15.251873: step: 2786/1545, loss: 1.1784062385559082 2023-01-23 06:18:16.107779: step: 2788/1545, loss: 0.6767762303352356 2023-01-23 06:18:16.985365: step: 2790/1545, loss: 0.7060685157775879 2023-01-23 06:18:17.833599: step: 2792/1545, loss: 0.8163670301437378 2023-01-23 06:18:18.670509: step: 2794/1545, loss: 7.3910651206970215 2023-01-23 06:18:19.554127: step: 2796/1545, loss: 0.5244950652122498 2023-01-23 06:18:20.399957: step: 2798/1545, loss: 0.7030046582221985 2023-01-23 06:18:21.282294: step: 2800/1545, loss: 1.3266886472702026 2023-01-23 06:18:22.159966: step: 2802/1545, loss: 2.587188959121704 2023-01-23 06:18:23.069230: step: 2804/1545, loss: 0.958868145942688 2023-01-23 06:18:23.917968: step: 2806/1545, loss: 1.084189534187317 2023-01-23 06:18:24.751962: step: 2808/1545, loss: 0.33898526430130005 2023-01-23 06:18:25.666902: step: 2810/1545, loss: 0.6735947132110596 2023-01-23 06:18:26.534345: step: 2812/1545, loss: 3.328742265701294 2023-01-23 06:18:27.393447: step: 2814/1545, loss: 0.43674328923225403 2023-01-23 06:18:28.240278: step: 2816/1545, loss: 0.4149225950241089 2023-01-23 06:18:29.092740: step: 2818/1545, loss: 0.5650965571403503 2023-01-23 06:18:29.961063: step: 2820/1545, loss: 1.1205350160598755 2023-01-23 06:18:30.834879: step: 2822/1545, loss: 1.1529139280319214 2023-01-23 06:18:31.672647: step: 2824/1545, loss: 0.8852217793464661 2023-01-23 06:18:32.549876: step: 2826/1545, loss: 0.43690186738967896 2023-01-23 06:18:33.436462: step: 2828/1545, loss: 0.47742801904678345 2023-01-23 06:18:34.325330: step: 2830/1545, loss: 1.3219658136367798 2023-01-23 06:18:35.193065: step: 2832/1545, loss: 0.9534135460853577 2023-01-23 06:18:36.092087: step: 2834/1545, loss: 0.7479755878448486 2023-01-23 06:18:36.993107: step: 2836/1545, loss: 6.901674747467041 2023-01-23 06:18:37.852537: step: 2838/1545, loss: 1.0500304698944092 2023-01-23 06:18:38.724917: step: 2840/1545, loss: 1.4410486221313477 2023-01-23 06:18:39.628783: step: 2842/1545, loss: 0.7424737215042114 2023-01-23 06:18:40.483999: step: 2844/1545, loss: 1.2989503145217896 2023-01-23 06:18:41.387707: step: 2846/1545, loss: 1.1041747331619263 2023-01-23 06:18:42.243364: step: 2848/1545, loss: 0.3363998830318451 2023-01-23 06:18:43.122670: step: 2850/1545, loss: 2.822664976119995 2023-01-23 06:18:44.010981: step: 2852/1545, loss: 3.1384377479553223 2023-01-23 06:18:44.930742: step: 2854/1545, loss: 1.2812318801879883 2023-01-23 06:18:45.809463: step: 2856/1545, loss: 0.6733417510986328 2023-01-23 06:18:46.701450: step: 2858/1545, loss: 1.4806855916976929 2023-01-23 06:18:47.562560: step: 2860/1545, loss: 0.8128320574760437 2023-01-23 06:18:48.446997: step: 2862/1545, loss: 0.5391222834587097 2023-01-23 06:18:49.311565: step: 2864/1545, loss: 0.27411967515945435 2023-01-23 06:18:50.235930: step: 2866/1545, loss: 1.4315154552459717 2023-01-23 06:18:51.127242: step: 2868/1545, loss: 1.112316370010376 2023-01-23 06:18:52.023486: step: 2870/1545, loss: 0.717961847782135 2023-01-23 06:18:52.893931: step: 2872/1545, loss: 0.4857925474643707 2023-01-23 06:18:53.768215: step: 2874/1545, loss: 0.44834238290786743 2023-01-23 06:18:54.655202: step: 2876/1545, loss: 0.3705950677394867 2023-01-23 06:18:55.518482: step: 2878/1545, loss: 6.748498439788818 2023-01-23 06:18:56.374052: step: 2880/1545, loss: 0.5224647521972656 2023-01-23 06:18:57.364712: step: 2882/1545, loss: 2.965226173400879 2023-01-23 06:18:58.265538: step: 2884/1545, loss: 0.7002339959144592 2023-01-23 06:18:59.148418: step: 2886/1545, loss: 0.7274543642997742 2023-01-23 06:19:00.024399: step: 2888/1545, loss: 0.21969850361347198 2023-01-23 06:19:00.905463: step: 2890/1545, loss: 0.6725419163703918 2023-01-23 06:19:01.787693: step: 2892/1545, loss: 1.02388596534729 2023-01-23 06:19:02.673157: step: 2894/1545, loss: 1.6878029108047485 2023-01-23 06:19:03.542327: step: 2896/1545, loss: 0.2863501310348511 2023-01-23 06:19:04.455498: step: 2898/1545, loss: 0.49437206983566284 2023-01-23 06:19:05.357690: step: 2900/1545, loss: 0.11025906354188919 2023-01-23 06:19:06.273135: step: 2902/1545, loss: 0.851268470287323 2023-01-23 06:19:07.222351: step: 2904/1545, loss: 2.782184362411499 2023-01-23 06:19:08.140388: step: 2906/1545, loss: 6.098674774169922 2023-01-23 06:19:09.045589: step: 2908/1545, loss: 2.929331064224243 2023-01-23 06:19:09.927285: step: 2910/1545, loss: 0.6345117688179016 2023-01-23 06:19:10.793408: step: 2912/1545, loss: 0.46799567341804504 2023-01-23 06:19:11.674137: step: 2914/1545, loss: 3.28415584564209 2023-01-23 06:19:12.509585: step: 2916/1545, loss: 0.5908794403076172 2023-01-23 06:19:13.416768: step: 2918/1545, loss: 6.37601900100708 2023-01-23 06:19:14.361637: step: 2920/1545, loss: 1.5476429462432861 2023-01-23 06:19:15.283957: step: 2922/1545, loss: 1.0048375129699707 2023-01-23 06:19:16.159917: step: 2924/1545, loss: 3.0805037021636963 2023-01-23 06:19:17.048396: step: 2926/1545, loss: 2.4976484775543213 2023-01-23 06:19:17.908561: step: 2928/1545, loss: 0.30182111263275146 2023-01-23 06:19:18.805197: step: 2930/1545, loss: 1.1534634828567505 2023-01-23 06:19:19.683861: step: 2932/1545, loss: 1.5050373077392578 2023-01-23 06:19:20.618670: step: 2934/1545, loss: 0.9204381108283997 2023-01-23 06:19:21.495025: step: 2936/1545, loss: 2.573819398880005 2023-01-23 06:19:22.353849: step: 2938/1545, loss: 1.178635835647583 2023-01-23 06:19:23.292212: step: 2940/1545, loss: 1.0161038637161255 2023-01-23 06:19:24.144541: step: 2942/1545, loss: 0.6354043483734131 2023-01-23 06:19:25.007274: step: 2944/1545, loss: 0.5230968594551086 2023-01-23 06:19:25.894318: step: 2946/1545, loss: 0.5095927119255066 2023-01-23 06:19:26.776547: step: 2948/1545, loss: 0.7282428741455078 2023-01-23 06:19:27.679444: step: 2950/1545, loss: 0.3731711506843567 2023-01-23 06:19:28.549653: step: 2952/1545, loss: 0.4374561607837677 2023-01-23 06:19:29.422439: step: 2954/1545, loss: 1.1528747081756592 2023-01-23 06:19:30.323825: step: 2956/1545, loss: 0.7130159139633179 2023-01-23 06:19:31.238726: step: 2958/1545, loss: 1.276012897491455 2023-01-23 06:19:32.098290: step: 2960/1545, loss: 0.48531797528266907 2023-01-23 06:19:32.947150: step: 2962/1545, loss: 0.8365974426269531 2023-01-23 06:19:33.791062: step: 2964/1545, loss: 0.6874678730964661 2023-01-23 06:19:34.703752: step: 2966/1545, loss: 0.832048773765564 2023-01-23 06:19:35.601239: step: 2968/1545, loss: 0.65666264295578 2023-01-23 06:19:36.463146: step: 2970/1545, loss: 3.4760384559631348 2023-01-23 06:19:37.348912: step: 2972/1545, loss: 1.359755277633667 2023-01-23 06:19:38.191189: step: 2974/1545, loss: 0.5920718312263489 2023-01-23 06:19:39.019250: step: 2976/1545, loss: 0.46302366256713867 2023-01-23 06:19:39.869257: step: 2978/1545, loss: 0.5834753513336182 2023-01-23 06:19:40.781545: step: 2980/1545, loss: 2.9556996822357178 2023-01-23 06:19:41.618810: step: 2982/1545, loss: 4.304744720458984 2023-01-23 06:19:42.524063: step: 2984/1545, loss: 0.7492455244064331 2023-01-23 06:19:43.391827: step: 2986/1545, loss: 0.6241407990455627 2023-01-23 06:19:44.286460: step: 2988/1545, loss: 0.549045741558075 2023-01-23 06:19:45.186279: step: 2990/1545, loss: 0.9973545074462891 2023-01-23 06:19:46.109299: step: 2992/1545, loss: 2.9636731147766113 2023-01-23 06:19:46.981549: step: 2994/1545, loss: 0.5867740511894226 2023-01-23 06:19:47.893832: step: 2996/1545, loss: 3.2370095252990723 2023-01-23 06:19:48.763568: step: 2998/1545, loss: 1.7234773635864258 2023-01-23 06:19:49.658034: step: 3000/1545, loss: 0.7461053729057312 2023-01-23 06:19:50.573955: step: 3002/1545, loss: 4.257495403289795 2023-01-23 06:19:51.462347: step: 3004/1545, loss: 1.0761032104492188 2023-01-23 06:19:52.358738: step: 3006/1545, loss: 0.9266116619110107 2023-01-23 06:19:53.278143: step: 3008/1545, loss: 0.7678651809692383 2023-01-23 06:19:54.122203: step: 3010/1545, loss: 0.7266334891319275 2023-01-23 06:19:55.068130: step: 3012/1545, loss: 1.033161997795105 2023-01-23 06:19:55.981995: step: 3014/1545, loss: 1.0317106246948242 2023-01-23 06:19:56.870286: step: 3016/1545, loss: 3.060065507888794 2023-01-23 06:19:57.770180: step: 3018/1545, loss: 0.835731565952301 2023-01-23 06:19:58.637034: step: 3020/1545, loss: 1.1359339952468872 2023-01-23 06:19:59.526248: step: 3022/1545, loss: 0.5931851267814636 2023-01-23 06:20:00.385582: step: 3024/1545, loss: 0.9028806686401367 2023-01-23 06:20:01.335140: step: 3026/1545, loss: 0.5021992921829224 2023-01-23 06:20:02.243549: step: 3028/1545, loss: 0.5460386276245117 2023-01-23 06:20:03.099961: step: 3030/1545, loss: 0.34350258111953735 2023-01-23 06:20:03.971192: step: 3032/1545, loss: 1.3437535762786865 2023-01-23 06:20:04.855302: step: 3034/1545, loss: 0.5109038352966309 2023-01-23 06:20:05.757492: step: 3036/1545, loss: 0.8149771690368652 2023-01-23 06:20:06.657360: step: 3038/1545, loss: 0.6929861903190613 2023-01-23 06:20:07.508547: step: 3040/1545, loss: 3.2286219596862793 2023-01-23 06:20:08.359413: step: 3042/1545, loss: 1.0449987649917603 2023-01-23 06:20:09.198496: step: 3044/1545, loss: 0.6893014311790466 2023-01-23 06:20:10.126893: step: 3046/1545, loss: 2.9068801403045654 2023-01-23 06:20:10.975125: step: 3048/1545, loss: 0.6738775968551636 2023-01-23 06:20:11.899730: step: 3050/1545, loss: 0.7305009961128235 2023-01-23 06:20:12.787020: step: 3052/1545, loss: 1.652166724205017 2023-01-23 06:20:13.669758: step: 3054/1545, loss: 0.4411058723926544 2023-01-23 06:20:14.515345: step: 3056/1545, loss: 3.016690254211426 2023-01-23 06:20:15.382601: step: 3058/1545, loss: 1.227459192276001 2023-01-23 06:20:16.235997: step: 3060/1545, loss: 0.6036270260810852 2023-01-23 06:20:17.149612: step: 3062/1545, loss: 0.8372176885604858 2023-01-23 06:20:18.024908: step: 3064/1545, loss: 0.8034610152244568 2023-01-23 06:20:18.891098: step: 3066/1545, loss: 4.247446537017822 2023-01-23 06:20:19.806198: step: 3068/1545, loss: 0.605990469455719 2023-01-23 06:20:20.627884: step: 3070/1545, loss: 1.1114264726638794 2023-01-23 06:20:21.514350: step: 3072/1545, loss: 0.8199895024299622 2023-01-23 06:20:22.342379: step: 3074/1545, loss: 0.558996856212616 2023-01-23 06:20:23.204182: step: 3076/1545, loss: 0.3669028878211975 2023-01-23 06:20:24.074350: step: 3078/1545, loss: 3.857410192489624 2023-01-23 06:20:24.939050: step: 3080/1545, loss: 0.7418080568313599 2023-01-23 06:20:25.794706: step: 3082/1545, loss: 0.7666930556297302 2023-01-23 06:20:26.673488: step: 3084/1545, loss: 0.2957890033721924 2023-01-23 06:20:27.609247: step: 3086/1545, loss: 2.70629620552063 2023-01-23 06:20:28.459785: step: 3088/1545, loss: 0.4997479319572449 2023-01-23 06:20:29.312208: step: 3090/1545, loss: 3.235130786895752 ================================================== Loss: 1.410 -------------------- Dev Chinese: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.587981304984902, 'r': 0.6864912618410113, 'f1': 0.6334291353218994}, 'combined': 0.4215265828580986, 'epoch': 2} Test Chinese: {'event': {'p': 0.6360725720384205, 'r': 0.7621483375959079, 'f1': 0.6934264107038975}, 'argument': {'p': 0.628516619423252, 'r': 0.7394313169685317, 'f1': 0.6794774264035156}, 'combined': 0.4711675929453115, 'epoch': 2} Dev Korean: {'event': {'p': 0.611597374179431, 'r': 0.7443408788282291, 'f1': 0.6714714714714715}, 'argument': {'p': 0.592062414933287, 'r': 0.6894791458652102, 'f1': 0.6370682007265497}, 'combined': 0.42777312216953906, 'epoch': 2} Test Korean: {'event': {'p': 0.6264550264550265, 'r': 0.7570332480818415, 'f1': 0.6855819339895773}, 'argument': {'p': 0.6242069589433683, 'r': 0.7378293346439585, 'f1': 0.6762789029421492}, 'combined': 0.4636445981954283, 'epoch': 2} Dev Russian: {'event': {'p': 0.5708661417322834, 'r': 0.7723035952063915, 'f1': 0.656479909451047}, 'argument': {'p': 0.581316540030282, 'r': 0.6982456364859079, 'f1': 0.6344384742574395}, 'combined': 0.41649611213278426, 'epoch': 2} Test Russian: {'event': {'p': 0.6223218734429496, 'r': 0.7985933503836317, 'f1': 0.6995239428731448}, 'argument': {'p': 0.6284616341238207, 'r': 0.7497726317151879, 'f1': 0.6837782879562884}, 'combined': 0.4783192840422314, 'epoch': 2} Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.5654826409793297, 'r': 0.7056849486601552, 'f1': 0.6278520499108733}, 'combined': 0.42808094312104994, 'epoch': 2} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.5058144469909176, 'r': 0.3582852332852333, 'f1': 0.41945588287051705}, 'combined': 0.2575606298327736, 'epoch': 2} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5047448393420144, 'r': 0.621917748474982, 'f1': 0.557238302633584}, 'combined': 0.310360573618705, 'epoch': 2} New best chinese model... New best korean model... New best russian model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.587981304984902, 'r': 0.6864912618410113, 'f1': 0.6334291353218994}, 'combined': 0.4215265828580986, 'epoch': 2} Test for Chinese: {'event': {'p': 0.6360725720384205, 'r': 0.7621483375959079, 'f1': 0.6934264107038975}, 'argument': {'p': 0.628516619423252, 'r': 0.7394313169685317, 'f1': 0.6794774264035156}, 'combined': 0.4711675929453115, 'epoch': 2} Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.5654826409793297, 'r': 0.7056849486601552, 'f1': 0.6278520499108733}, 'combined': 0.42808094312104994, 'epoch': 2} -------------------- Dev for Korean: {'event': {'p': 0.611597374179431, 'r': 0.7443408788282291, 'f1': 0.6714714714714715}, 'argument': {'p': 0.592062414933287, 'r': 0.6894791458652102, 'f1': 0.6370682007265497}, 'combined': 0.42777312216953906, 'epoch': 2} Test for Korean: {'event': {'p': 0.6264550264550265, 'r': 0.7570332480818415, 'f1': 0.6855819339895773}, 'argument': {'p': 0.6242069589433683, 'r': 0.7378293346439585, 'f1': 0.6762789029421492}, 'combined': 0.4636445981954283, 'epoch': 2} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.5058144469909176, 'r': 0.3582852332852333, 'f1': 0.41945588287051705}, 'combined': 0.2575606298327736, 'epoch': 2} -------------------- Dev for Russian: {'event': {'p': 0.5708661417322834, 'r': 0.7723035952063915, 'f1': 0.656479909451047}, 'argument': {'p': 0.581316540030282, 'r': 0.6982456364859079, 'f1': 0.6344384742574395}, 'combined': 0.41649611213278426, 'epoch': 2} Test for Russian: {'event': {'p': 0.6223218734429496, 'r': 0.7985933503836317, 'f1': 0.6995239428731448}, 'argument': {'p': 0.6284616341238207, 'r': 0.7497726317151879, 'f1': 0.6837782879562884}, 'combined': 0.4783192840422314, 'epoch': 2} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5047448393420144, 'r': 0.621917748474982, 'f1': 0.557238302633584}, 'combined': 0.310360573618705, 'epoch': 2} ****************************** Epoch: 3 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 06:26:18.375305: step: 2/1545, loss: 0.7754907608032227 2023-01-23 06:26:19.290455: step: 4/1545, loss: 3.829986810684204 2023-01-23 06:26:20.198837: step: 6/1545, loss: 0.2663247883319855 2023-01-23 06:26:21.100412: step: 8/1545, loss: 0.48395588994026184 2023-01-23 06:26:22.067785: step: 10/1545, loss: 0.6997342705726624 2023-01-23 06:26:22.972211: step: 12/1545, loss: 1.1014710664749146 2023-01-23 06:26:23.841688: step: 14/1545, loss: 2.8528974056243896 2023-01-23 06:26:24.706675: step: 16/1545, loss: 0.9709441661834717 2023-01-23 06:26:25.579142: step: 18/1545, loss: 0.4416245222091675 2023-01-23 06:26:26.489746: step: 20/1545, loss: 0.9860389232635498 2023-01-23 06:26:27.386393: step: 22/1545, loss: 0.6625866889953613 2023-01-23 06:26:28.281518: step: 24/1545, loss: 0.5876668691635132 2023-01-23 06:26:29.201848: step: 26/1545, loss: 1.0714796781539917 2023-01-23 06:26:30.049456: step: 28/1545, loss: 0.41322290897369385 2023-01-23 06:26:30.894826: step: 30/1545, loss: 0.5627943277359009 2023-01-23 06:26:31.779487: step: 32/1545, loss: 1.2821439504623413 2023-01-23 06:26:32.620762: step: 34/1545, loss: 5.5171732902526855 2023-01-23 06:26:33.503688: step: 36/1545, loss: 0.5709048509597778 2023-01-23 06:26:34.354624: step: 38/1545, loss: 0.35548409819602966 2023-01-23 06:26:35.237564: step: 40/1545, loss: 1.5798208713531494 2023-01-23 06:26:36.093019: step: 42/1545, loss: 0.4875607490539551 2023-01-23 06:26:36.981886: step: 44/1545, loss: 3.357170581817627 2023-01-23 06:26:37.859242: step: 46/1545, loss: 1.107782006263733 2023-01-23 06:26:38.701363: step: 48/1545, loss: 0.9028570652008057 2023-01-23 06:26:39.597184: step: 50/1545, loss: 0.8765893578529358 2023-01-23 06:26:40.476060: step: 52/1545, loss: 6.5091352462768555 2023-01-23 06:26:41.344229: step: 54/1545, loss: 0.9663152694702148 2023-01-23 06:26:42.209329: step: 56/1545, loss: 1.3836339712142944 2023-01-23 06:26:43.108433: step: 58/1545, loss: 0.8140333294868469 2023-01-23 06:26:43.979717: step: 60/1545, loss: 0.5959665179252625 2023-01-23 06:26:44.912828: step: 62/1545, loss: 0.3523382544517517 2023-01-23 06:26:45.792841: step: 64/1545, loss: 0.5209255218505859 2023-01-23 06:26:46.657000: step: 66/1545, loss: 0.21703840792179108 2023-01-23 06:26:47.533968: step: 68/1545, loss: 0.5033050179481506 2023-01-23 06:26:48.480097: step: 70/1545, loss: 0.6920579075813293 2023-01-23 06:26:49.358105: step: 72/1545, loss: 0.6245449185371399 2023-01-23 06:26:50.232640: step: 74/1545, loss: 1.1979074478149414 2023-01-23 06:26:51.083626: step: 76/1545, loss: 0.4939412474632263 2023-01-23 06:26:51.946808: step: 78/1545, loss: 0.6992339491844177 2023-01-23 06:26:52.835334: step: 80/1545, loss: 0.7647864818572998 2023-01-23 06:26:53.690948: step: 82/1545, loss: 0.5915340781211853 2023-01-23 06:26:54.563654: step: 84/1545, loss: 0.1917285919189453 2023-01-23 06:26:55.426807: step: 86/1545, loss: 0.34078943729400635 2023-01-23 06:26:56.312120: step: 88/1545, loss: 1.1740070581436157 2023-01-23 06:26:57.195707: step: 90/1545, loss: 0.6731175780296326 2023-01-23 06:26:58.101758: step: 92/1545, loss: 0.3438848555088043 2023-01-23 06:26:59.068264: step: 94/1545, loss: 5.7946038246154785 2023-01-23 06:26:59.966430: step: 96/1545, loss: 1.8268632888793945 2023-01-23 06:27:00.845238: step: 98/1545, loss: 0.24430017173290253 2023-01-23 06:27:01.704034: step: 100/1545, loss: 0.40414097905158997 2023-01-23 06:27:02.631616: step: 102/1545, loss: 3.56935453414917 2023-01-23 06:27:03.518302: step: 104/1545, loss: 1.0757942199707031 2023-01-23 06:27:04.384153: step: 106/1545, loss: 0.38021114468574524 2023-01-23 06:27:05.230294: step: 108/1545, loss: 0.7466749548912048 2023-01-23 06:27:06.148140: step: 110/1545, loss: 1.0193817615509033 2023-01-23 06:27:06.971379: step: 112/1545, loss: 0.21752071380615234 2023-01-23 06:27:07.874665: step: 114/1545, loss: 0.729808509349823 2023-01-23 06:27:08.699521: step: 116/1545, loss: 6.087677001953125 2023-01-23 06:27:09.637306: step: 118/1545, loss: 0.9793216586112976 2023-01-23 06:27:10.516572: step: 120/1545, loss: 7.242247581481934 2023-01-23 06:27:11.394319: step: 122/1545, loss: 0.9996810555458069 2023-01-23 06:27:12.233012: step: 124/1545, loss: 0.6377561688423157 2023-01-23 06:27:13.093611: step: 126/1545, loss: 0.2533184885978699 2023-01-23 06:27:13.930270: step: 128/1545, loss: 0.9139395356178284 2023-01-23 06:27:14.824228: step: 130/1545, loss: 0.7720551490783691 2023-01-23 06:27:15.681919: step: 132/1545, loss: 1.065148949623108 2023-01-23 06:27:16.572776: step: 134/1545, loss: 0.4046597182750702 2023-01-23 06:27:17.477343: step: 136/1545, loss: 0.5268514752388 2023-01-23 06:27:18.345820: step: 138/1545, loss: 0.8618074655532837 2023-01-23 06:27:19.239567: step: 140/1545, loss: 0.354688823223114 2023-01-23 06:27:20.128450: step: 142/1545, loss: 0.5152649283409119 2023-01-23 06:27:21.004573: step: 144/1545, loss: 0.6078568696975708 2023-01-23 06:27:21.898503: step: 146/1545, loss: 0.7453160285949707 2023-01-23 06:27:22.801671: step: 148/1545, loss: 0.620050311088562 2023-01-23 06:27:23.703495: step: 150/1545, loss: 1.357035517692566 2023-01-23 06:27:24.646888: step: 152/1545, loss: 2.9154212474823 2023-01-23 06:27:25.577685: step: 154/1545, loss: 0.7833928465843201 2023-01-23 06:27:26.469196: step: 156/1545, loss: 0.7632428407669067 2023-01-23 06:27:27.353482: step: 158/1545, loss: 0.8409305810928345 2023-01-23 06:27:28.199603: step: 160/1545, loss: 0.39843297004699707 2023-01-23 06:27:29.111266: step: 162/1545, loss: 0.795374870300293 2023-01-23 06:27:29.964528: step: 164/1545, loss: 0.3864750862121582 2023-01-23 06:27:30.820785: step: 166/1545, loss: 2.840826988220215 2023-01-23 06:27:31.711109: step: 168/1545, loss: 0.287241131067276 2023-01-23 06:27:32.589538: step: 170/1545, loss: 0.19776593148708344 2023-01-23 06:27:33.501156: step: 172/1545, loss: 0.4912635087966919 2023-01-23 06:27:34.382372: step: 174/1545, loss: 0.6619413495063782 2023-01-23 06:27:35.238195: step: 176/1545, loss: 0.2325843870639801 2023-01-23 06:27:36.109204: step: 178/1545, loss: 1.51106858253479 2023-01-23 06:27:36.939332: step: 180/1545, loss: 5.873887538909912 2023-01-23 06:27:37.820641: step: 182/1545, loss: 0.8597232103347778 2023-01-23 06:27:38.647388: step: 184/1545, loss: 0.8220877647399902 2023-01-23 06:27:39.555059: step: 186/1545, loss: 1.0663392543792725 2023-01-23 06:27:40.413621: step: 188/1545, loss: 3.1243178844451904 2023-01-23 06:27:41.288683: step: 190/1545, loss: 0.3006238341331482 2023-01-23 06:27:42.221497: step: 192/1545, loss: 0.6257586479187012 2023-01-23 06:27:43.153493: step: 194/1545, loss: 1.1536235809326172 2023-01-23 06:27:44.020504: step: 196/1545, loss: 0.4136682450771332 2023-01-23 06:27:44.952630: step: 198/1545, loss: 0.8214704990386963 2023-01-23 06:27:45.867390: step: 200/1545, loss: 0.9983774423599243 2023-01-23 06:27:46.748442: step: 202/1545, loss: 2.9001150131225586 2023-01-23 06:27:47.645905: step: 204/1545, loss: 0.9134802222251892 2023-01-23 06:27:48.507472: step: 206/1545, loss: 0.8862398862838745 2023-01-23 06:27:49.411245: step: 208/1545, loss: 0.5966681241989136 2023-01-23 06:27:50.299949: step: 210/1545, loss: 1.615329384803772 2023-01-23 06:27:51.289056: step: 212/1545, loss: 0.6719927787780762 2023-01-23 06:27:52.186718: step: 214/1545, loss: 0.5144401788711548 2023-01-23 06:27:53.064749: step: 216/1545, loss: 0.5389183759689331 2023-01-23 06:27:53.924450: step: 218/1545, loss: 6.670395374298096 2023-01-23 06:27:54.792250: step: 220/1545, loss: 1.1979966163635254 2023-01-23 06:27:55.648344: step: 222/1545, loss: 2.4819469451904297 2023-01-23 06:27:56.532001: step: 224/1545, loss: 1.1688989400863647 2023-01-23 06:27:57.424645: step: 226/1545, loss: 0.8684476017951965 2023-01-23 06:27:58.353232: step: 228/1545, loss: 0.40119513869285583 2023-01-23 06:27:59.216557: step: 230/1545, loss: 0.45990821719169617 2023-01-23 06:28:00.066771: step: 232/1545, loss: 0.94594806432724 2023-01-23 06:28:00.959030: step: 234/1545, loss: 0.7900841236114502 2023-01-23 06:28:01.897955: step: 236/1545, loss: 0.33589306473731995 2023-01-23 06:28:02.758359: step: 238/1545, loss: 0.32983317971229553 2023-01-23 06:28:03.662061: step: 240/1545, loss: 0.7938433885574341 2023-01-23 06:28:04.534836: step: 242/1545, loss: 2.907505989074707 2023-01-23 06:28:05.431316: step: 244/1545, loss: 0.5909743905067444 2023-01-23 06:28:06.309147: step: 246/1545, loss: 0.836975634098053 2023-01-23 06:28:07.314700: step: 248/1545, loss: 0.6903351545333862 2023-01-23 06:28:08.273358: step: 250/1545, loss: 0.792818546295166 2023-01-23 06:28:09.143862: step: 252/1545, loss: 1.1832529306411743 2023-01-23 06:28:10.042339: step: 254/1545, loss: 0.5324094295501709 2023-01-23 06:28:10.896220: step: 256/1545, loss: 0.5155327916145325 2023-01-23 06:28:11.798454: step: 258/1545, loss: 3.051243543624878 2023-01-23 06:28:12.670820: step: 260/1545, loss: 0.24195069074630737 2023-01-23 06:28:13.524856: step: 262/1545, loss: 0.9135804176330566 2023-01-23 06:28:14.394567: step: 264/1545, loss: 6.3445305824279785 2023-01-23 06:28:15.260610: step: 266/1545, loss: 1.3476487398147583 2023-01-23 06:28:16.258653: step: 268/1545, loss: 1.3815985918045044 2023-01-23 06:28:17.194788: step: 270/1545, loss: 0.7301703095436096 2023-01-23 06:28:18.040752: step: 272/1545, loss: 0.2176157683134079 2023-01-23 06:28:18.948246: step: 274/1545, loss: 0.8462095260620117 2023-01-23 06:28:19.851463: step: 276/1545, loss: 0.6884959936141968 2023-01-23 06:28:20.725949: step: 278/1545, loss: 0.6807866096496582 2023-01-23 06:28:21.603166: step: 280/1545, loss: 0.6525231599807739 2023-01-23 06:28:22.464352: step: 282/1545, loss: 0.7951508164405823 2023-01-23 06:28:23.404792: step: 284/1545, loss: 1.084784746170044 2023-01-23 06:28:24.292510: step: 286/1545, loss: 0.7421521544456482 2023-01-23 06:28:25.156015: step: 288/1545, loss: 0.32981979846954346 2023-01-23 06:28:26.037960: step: 290/1545, loss: 0.7984214425086975 2023-01-23 06:28:26.922042: step: 292/1545, loss: 2.8993752002716064 2023-01-23 06:28:27.850549: step: 294/1545, loss: 0.6804813146591187 2023-01-23 06:28:28.794156: step: 296/1545, loss: 3.5282468795776367 2023-01-23 06:28:29.758010: step: 298/1545, loss: 0.8301466703414917 2023-01-23 06:28:30.673644: step: 300/1545, loss: 0.5483973622322083 2023-01-23 06:28:31.624454: step: 302/1545, loss: 0.6992273926734924 2023-01-23 06:28:32.515612: step: 304/1545, loss: 0.3481065034866333 2023-01-23 06:28:33.383047: step: 306/1545, loss: 0.6108725666999817 2023-01-23 06:28:34.285669: step: 308/1545, loss: 1.0089716911315918 2023-01-23 06:28:35.147000: step: 310/1545, loss: 0.5875160098075867 2023-01-23 06:28:36.018129: step: 312/1545, loss: 0.5618184208869934 2023-01-23 06:28:36.909512: step: 314/1545, loss: 3.3256397247314453 2023-01-23 06:28:37.777425: step: 316/1545, loss: 0.5273430347442627 2023-01-23 06:28:38.664256: step: 318/1545, loss: 0.30515214800834656 2023-01-23 06:28:39.555895: step: 320/1545, loss: 0.4712083339691162 2023-01-23 06:28:40.473505: step: 322/1545, loss: 0.5046191215515137 2023-01-23 06:28:41.418063: step: 324/1545, loss: 0.6063463687896729 2023-01-23 06:28:42.298547: step: 326/1545, loss: 0.4681728482246399 2023-01-23 06:28:43.199428: step: 328/1545, loss: 1.3115754127502441 2023-01-23 06:28:44.078936: step: 330/1545, loss: 2.973728656768799 2023-01-23 06:28:45.028212: step: 332/1545, loss: 0.6317371726036072 2023-01-23 06:28:45.855825: step: 334/1545, loss: 8.35256290435791 2023-01-23 06:28:46.715303: step: 336/1545, loss: 1.404201865196228 2023-01-23 06:28:47.580889: step: 338/1545, loss: 0.4761478900909424 2023-01-23 06:28:48.436700: step: 340/1545, loss: 0.5437574982643127 2023-01-23 06:28:49.380667: step: 342/1545, loss: 0.9178043007850647 2023-01-23 06:28:50.264277: step: 344/1545, loss: 1.185259461402893 2023-01-23 06:28:51.163670: step: 346/1545, loss: 0.8363149762153625 2023-01-23 06:28:52.062132: step: 348/1545, loss: 0.49840956926345825 2023-01-23 06:28:52.943754: step: 350/1545, loss: 0.28393134474754333 2023-01-23 06:28:53.825109: step: 352/1545, loss: 0.89049232006073 2023-01-23 06:28:54.709971: step: 354/1545, loss: 1.1030008792877197 2023-01-23 06:28:55.582457: step: 356/1545, loss: 0.41427627205848694 2023-01-23 06:28:56.455576: step: 358/1545, loss: 0.6652129292488098 2023-01-23 06:28:57.375245: step: 360/1545, loss: 0.7415369749069214 2023-01-23 06:28:58.238451: step: 362/1545, loss: 0.40264004468917847 2023-01-23 06:28:59.142662: step: 364/1545, loss: 0.2884249985218048 2023-01-23 06:29:00.049311: step: 366/1545, loss: 0.4798493981361389 2023-01-23 06:29:00.966188: step: 368/1545, loss: 0.9345938563346863 2023-01-23 06:29:01.857199: step: 370/1545, loss: 0.3929157555103302 2023-01-23 06:29:02.709278: step: 372/1545, loss: 0.1480945348739624 2023-01-23 06:29:03.561886: step: 374/1545, loss: 0.3596889078617096 2023-01-23 06:29:04.562025: step: 376/1545, loss: 0.7124133110046387 2023-01-23 06:29:05.397720: step: 378/1545, loss: 0.36402857303619385 2023-01-23 06:29:06.272576: step: 380/1545, loss: 0.4959232211112976 2023-01-23 06:29:07.157393: step: 382/1545, loss: 0.7349965572357178 2023-01-23 06:29:08.051949: step: 384/1545, loss: 0.6054844856262207 2023-01-23 06:29:08.907891: step: 386/1545, loss: 3.447054862976074 2023-01-23 06:29:09.765478: step: 388/1545, loss: 0.9781855940818787 2023-01-23 06:29:10.604498: step: 390/1545, loss: 0.9619913101196289 2023-01-23 06:29:11.505654: step: 392/1545, loss: 3.4945271015167236 2023-01-23 06:29:12.375597: step: 394/1545, loss: 6.174680233001709 2023-01-23 06:29:13.262986: step: 396/1545, loss: 2.588824987411499 2023-01-23 06:29:14.099870: step: 398/1545, loss: 0.198579341173172 2023-01-23 06:29:14.984448: step: 400/1545, loss: 0.6850980520248413 2023-01-23 06:29:16.016275: step: 402/1545, loss: 0.6749040484428406 2023-01-23 06:29:16.963338: step: 404/1545, loss: 0.6838339567184448 2023-01-23 06:29:17.847826: step: 406/1545, loss: 0.5765314102172852 2023-01-23 06:29:18.768798: step: 408/1545, loss: 2.286393404006958 2023-01-23 06:29:19.679668: step: 410/1545, loss: 0.5967913866043091 2023-01-23 06:29:20.555096: step: 412/1545, loss: 0.41807490587234497 2023-01-23 06:29:21.418152: step: 414/1545, loss: 0.6199749708175659 2023-01-23 06:29:22.350425: step: 416/1545, loss: 0.5373380184173584 2023-01-23 06:29:23.208352: step: 418/1545, loss: 0.900288999080658 2023-01-23 06:29:24.092913: step: 420/1545, loss: 0.6183394193649292 2023-01-23 06:29:24.932480: step: 422/1545, loss: 3.0015978813171387 2023-01-23 06:29:25.862505: step: 424/1545, loss: 0.9955317974090576 2023-01-23 06:29:26.773247: step: 426/1545, loss: 0.7979664206504822 2023-01-23 06:29:27.703681: step: 428/1545, loss: 3.215106725692749 2023-01-23 06:29:28.643590: step: 430/1545, loss: 0.4982835650444031 2023-01-23 06:29:29.499150: step: 432/1545, loss: 0.19043898582458496 2023-01-23 06:29:30.346816: step: 434/1545, loss: 0.28296416997909546 2023-01-23 06:29:31.181390: step: 436/1545, loss: 3.30818772315979 2023-01-23 06:29:32.055632: step: 438/1545, loss: 3.1321067810058594 2023-01-23 06:29:32.901750: step: 440/1545, loss: 0.7909923195838928 2023-01-23 06:29:33.896427: step: 442/1545, loss: 3.4173078536987305 2023-01-23 06:29:34.760357: step: 444/1545, loss: 0.6640270948410034 2023-01-23 06:29:35.602471: step: 446/1545, loss: 3.456874132156372 2023-01-23 06:29:36.412204: step: 448/1545, loss: 2.3548102378845215 2023-01-23 06:29:37.272060: step: 450/1545, loss: 2.9548418521881104 2023-01-23 06:29:38.130103: step: 452/1545, loss: 1.8503292798995972 2023-01-23 06:29:39.031687: step: 454/1545, loss: 0.907633364200592 2023-01-23 06:29:39.895051: step: 456/1545, loss: 1.0644060373306274 2023-01-23 06:29:40.748221: step: 458/1545, loss: 0.7845977544784546 2023-01-23 06:29:41.671060: step: 460/1545, loss: 0.7128153443336487 2023-01-23 06:29:42.561879: step: 462/1545, loss: 0.4316290616989136 2023-01-23 06:29:43.450027: step: 464/1545, loss: 0.7988235950469971 2023-01-23 06:29:44.396586: step: 466/1545, loss: 1.1633415222167969 2023-01-23 06:29:45.246157: step: 468/1545, loss: 0.5662360787391663 2023-01-23 06:29:46.109514: step: 470/1545, loss: 0.7945058345794678 2023-01-23 06:29:46.959130: step: 472/1545, loss: 0.6851043701171875 2023-01-23 06:29:47.838610: step: 474/1545, loss: 0.6282572746276855 2023-01-23 06:29:48.742823: step: 476/1545, loss: 0.5473529696464539 2023-01-23 06:29:49.633835: step: 478/1545, loss: 2.8087499141693115 2023-01-23 06:29:50.483150: step: 480/1545, loss: 0.30789029598236084 2023-01-23 06:29:51.379192: step: 482/1545, loss: 0.3530843257904053 2023-01-23 06:29:52.239949: step: 484/1545, loss: 0.9362466931343079 2023-01-23 06:29:53.131441: step: 486/1545, loss: 0.5156282186508179 2023-01-23 06:29:54.018229: step: 488/1545, loss: 0.6075120568275452 2023-01-23 06:29:54.943131: step: 490/1545, loss: 0.7295407652854919 2023-01-23 06:29:55.868224: step: 492/1545, loss: 0.9915094971656799 2023-01-23 06:29:56.762714: step: 494/1545, loss: 3.5876989364624023 2023-01-23 06:29:57.625373: step: 496/1545, loss: 0.7575486302375793 2023-01-23 06:29:58.502519: step: 498/1545, loss: 0.45881378650665283 2023-01-23 06:29:59.327840: step: 500/1545, loss: 5.626538276672363 2023-01-23 06:30:00.203991: step: 502/1545, loss: 0.34435969591140747 2023-01-23 06:30:01.079766: step: 504/1545, loss: 2.4403202533721924 2023-01-23 06:30:01.969386: step: 506/1545, loss: 2.9084999561309814 2023-01-23 06:30:02.872379: step: 508/1545, loss: 0.908841609954834 2023-01-23 06:30:03.705667: step: 510/1545, loss: 1.6492358446121216 2023-01-23 06:30:04.572584: step: 512/1545, loss: 0.410193532705307 2023-01-23 06:30:05.430351: step: 514/1545, loss: 0.3758355677127838 2023-01-23 06:30:06.279536: step: 516/1545, loss: 0.20593778789043427 2023-01-23 06:30:07.159476: step: 518/1545, loss: 6.406315326690674 2023-01-23 06:30:07.994681: step: 520/1545, loss: 0.9437866806983948 2023-01-23 06:30:08.964259: step: 522/1545, loss: 0.38045111298561096 2023-01-23 06:30:09.831816: step: 524/1545, loss: 0.690701961517334 2023-01-23 06:30:10.727151: step: 526/1545, loss: 0.7529895305633545 2023-01-23 06:30:11.590904: step: 528/1545, loss: 0.29159435629844666 2023-01-23 06:30:12.459660: step: 530/1545, loss: 0.4450659155845642 2023-01-23 06:30:13.324667: step: 532/1545, loss: 0.4272512197494507 2023-01-23 06:30:14.235935: step: 534/1545, loss: 0.33414000272750854 2023-01-23 06:30:15.203354: step: 536/1545, loss: 0.8244391083717346 2023-01-23 06:30:16.097115: step: 538/1545, loss: 0.3448244631290436 2023-01-23 06:30:16.956750: step: 540/1545, loss: 1.8853317499160767 2023-01-23 06:30:17.861741: step: 542/1545, loss: 0.31440281867980957 2023-01-23 06:30:18.752561: step: 544/1545, loss: 0.6519888639450073 2023-01-23 06:30:19.647424: step: 546/1545, loss: 0.3795575201511383 2023-01-23 06:30:20.545964: step: 548/1545, loss: 0.2891670763492584 2023-01-23 06:30:21.391097: step: 550/1545, loss: 3.2629799842834473 2023-01-23 06:30:22.262548: step: 552/1545, loss: 0.4381817877292633 2023-01-23 06:30:23.145997: step: 554/1545, loss: 4.117376804351807 2023-01-23 06:30:24.060202: step: 556/1545, loss: 0.3528043329715729 2023-01-23 06:30:24.935466: step: 558/1545, loss: 0.35349154472351074 2023-01-23 06:30:25.824115: step: 560/1545, loss: 0.5474166870117188 2023-01-23 06:30:26.687307: step: 562/1545, loss: 5.605886936187744 2023-01-23 06:30:27.568333: step: 564/1545, loss: 0.394095778465271 2023-01-23 06:30:28.407877: step: 566/1545, loss: 0.7099308967590332 2023-01-23 06:30:29.265265: step: 568/1545, loss: 0.4402250051498413 2023-01-23 06:30:30.153015: step: 570/1545, loss: 0.7844901084899902 2023-01-23 06:30:31.015747: step: 572/1545, loss: 0.7602032423019409 2023-01-23 06:30:31.849421: step: 574/1545, loss: 0.46486741304397583 2023-01-23 06:30:32.696118: step: 576/1545, loss: 1.0024060010910034 2023-01-23 06:30:33.674368: step: 578/1545, loss: 0.46527355909347534 2023-01-23 06:30:34.558805: step: 580/1545, loss: 0.34830543398857117 2023-01-23 06:30:35.393597: step: 582/1545, loss: 0.9807842969894409 2023-01-23 06:30:36.279075: step: 584/1545, loss: 0.46310263872146606 2023-01-23 06:30:37.161162: step: 586/1545, loss: 0.408270001411438 2023-01-23 06:30:38.036353: step: 588/1545, loss: 0.7132278084754944 2023-01-23 06:30:38.916758: step: 590/1545, loss: 0.6018863916397095 2023-01-23 06:30:39.842291: step: 592/1545, loss: 3.222224473953247 2023-01-23 06:30:40.752678: step: 594/1545, loss: 0.9352612495422363 2023-01-23 06:30:41.619721: step: 596/1545, loss: 0.7181644439697266 2023-01-23 06:30:42.471992: step: 598/1545, loss: 0.550404965877533 2023-01-23 06:30:43.380787: step: 600/1545, loss: 0.6547116637229919 2023-01-23 06:30:44.239687: step: 602/1545, loss: 1.7715167999267578 2023-01-23 06:30:45.123746: step: 604/1545, loss: 3.5407443046569824 2023-01-23 06:30:45.991363: step: 606/1545, loss: 0.7868282794952393 2023-01-23 06:30:46.904623: step: 608/1545, loss: 0.3402748107910156 2023-01-23 06:30:47.809852: step: 610/1545, loss: 0.7017775774002075 2023-01-23 06:30:48.691266: step: 612/1545, loss: 0.7704329490661621 2023-01-23 06:30:49.522082: step: 614/1545, loss: 0.7484405636787415 2023-01-23 06:30:50.410495: step: 616/1545, loss: 0.7157866358757019 2023-01-23 06:30:51.294590: step: 618/1545, loss: 0.5309341549873352 2023-01-23 06:30:52.346410: step: 620/1545, loss: 0.9697134494781494 2023-01-23 06:30:53.216996: step: 622/1545, loss: 0.48106375336647034 2023-01-23 06:30:54.134271: step: 624/1545, loss: 1.2856229543685913 2023-01-23 06:30:55.126900: step: 626/1545, loss: 1.221028208732605 2023-01-23 06:30:55.975601: step: 628/1545, loss: 0.5806260108947754 2023-01-23 06:30:56.855367: step: 630/1545, loss: 0.6337090730667114 2023-01-23 06:30:57.752990: step: 632/1545, loss: 0.7382482290267944 2023-01-23 06:30:58.644725: step: 634/1545, loss: 0.8842423558235168 2023-01-23 06:30:59.543012: step: 636/1545, loss: 0.5733793377876282 2023-01-23 06:31:00.390156: step: 638/1545, loss: 0.9132137298583984 2023-01-23 06:31:01.271262: step: 640/1545, loss: 0.5801121592521667 2023-01-23 06:31:02.136695: step: 642/1545, loss: 0.5945698022842407 2023-01-23 06:31:02.999563: step: 644/1545, loss: 4.888370513916016 2023-01-23 06:31:03.924547: step: 646/1545, loss: 0.40137821435928345 2023-01-23 06:31:04.804927: step: 648/1545, loss: 0.7343988418579102 2023-01-23 06:31:05.680178: step: 650/1545, loss: 2.5856518745422363 2023-01-23 06:31:06.540393: step: 652/1545, loss: 0.24888652563095093 2023-01-23 06:31:07.415346: step: 654/1545, loss: 0.6831642389297485 2023-01-23 06:31:08.314127: step: 656/1545, loss: 2.4989709854125977 2023-01-23 06:31:09.252846: step: 658/1545, loss: 0.5073463320732117 2023-01-23 06:31:10.121832: step: 660/1545, loss: 2.972529649734497 2023-01-23 06:31:10.994118: step: 662/1545, loss: 0.4484286606311798 2023-01-23 06:31:11.969127: step: 664/1545, loss: 0.1972292810678482 2023-01-23 06:31:12.889977: step: 666/1545, loss: 1.022054672241211 2023-01-23 06:31:13.757141: step: 668/1545, loss: 1.3923828601837158 2023-01-23 06:31:14.650994: step: 670/1545, loss: 0.23524092137813568 2023-01-23 06:31:15.530207: step: 672/1545, loss: 0.1771930307149887 2023-01-23 06:31:16.439587: step: 674/1545, loss: 0.36880919337272644 2023-01-23 06:31:17.331727: step: 676/1545, loss: 0.5101821422576904 2023-01-23 06:31:18.191384: step: 678/1545, loss: 2.6964375972747803 2023-01-23 06:31:19.031070: step: 680/1545, loss: 2.7889087200164795 2023-01-23 06:31:19.921014: step: 682/1545, loss: 0.414382666349411 2023-01-23 06:31:20.877294: step: 684/1545, loss: 1.4350738525390625 2023-01-23 06:31:21.741842: step: 686/1545, loss: 0.7882567644119263 2023-01-23 06:31:22.609681: step: 688/1545, loss: 0.9635141491889954 2023-01-23 06:31:23.469629: step: 690/1545, loss: 0.7309684753417969 2023-01-23 06:31:24.345647: step: 692/1545, loss: 0.763477623462677 2023-01-23 06:31:25.231098: step: 694/1545, loss: 0.9696363210678101 2023-01-23 06:31:26.084531: step: 696/1545, loss: 0.8067173957824707 2023-01-23 06:31:26.947971: step: 698/1545, loss: 0.9611991047859192 2023-01-23 06:31:27.830088: step: 700/1545, loss: 3.5082497596740723 2023-01-23 06:31:28.722889: step: 702/1545, loss: 2.401987314224243 2023-01-23 06:31:29.605424: step: 704/1545, loss: 0.27895528078079224 2023-01-23 06:31:30.433394: step: 706/1545, loss: 0.35528847575187683 2023-01-23 06:31:31.331218: step: 708/1545, loss: 0.672760546207428 2023-01-23 06:31:32.196407: step: 710/1545, loss: 0.4341910779476166 2023-01-23 06:31:33.070409: step: 712/1545, loss: 6.360921382904053 2023-01-23 06:31:33.945080: step: 714/1545, loss: 0.6212481260299683 2023-01-23 06:31:34.796879: step: 716/1545, loss: 1.1146782636642456 2023-01-23 06:31:35.637858: step: 718/1545, loss: 0.4685077965259552 2023-01-23 06:31:36.478836: step: 720/1545, loss: 0.3646269738674164 2023-01-23 06:31:37.350083: step: 722/1545, loss: 1.1843576431274414 2023-01-23 06:31:38.213909: step: 724/1545, loss: 0.2925862669944763 2023-01-23 06:31:39.125601: step: 726/1545, loss: 0.9569036960601807 2023-01-23 06:31:39.954829: step: 728/1545, loss: 0.4814584255218506 2023-01-23 06:31:40.873230: step: 730/1545, loss: 1.0375752449035645 2023-01-23 06:31:41.824168: step: 732/1545, loss: 0.33078131079673767 2023-01-23 06:31:42.708869: step: 734/1545, loss: 0.4799172282218933 2023-01-23 06:31:43.571228: step: 736/1545, loss: 0.8983328342437744 2023-01-23 06:31:44.441950: step: 738/1545, loss: 0.5997323989868164 2023-01-23 06:31:45.276616: step: 740/1545, loss: 0.33477482199668884 2023-01-23 06:31:46.156911: step: 742/1545, loss: 0.18495802581310272 2023-01-23 06:31:47.067111: step: 744/1545, loss: 0.4688572883605957 2023-01-23 06:31:47.950667: step: 746/1545, loss: 0.8837396502494812 2023-01-23 06:31:48.797465: step: 748/1545, loss: 0.2863341271877289 2023-01-23 06:31:49.695230: step: 750/1545, loss: 0.18641917407512665 2023-01-23 06:31:50.532731: step: 752/1545, loss: 1.3818351030349731 2023-01-23 06:31:51.401085: step: 754/1545, loss: 1.0712956190109253 2023-01-23 06:31:52.292600: step: 756/1545, loss: 0.817832350730896 2023-01-23 06:31:53.151236: step: 758/1545, loss: 3.504265785217285 2023-01-23 06:31:54.036908: step: 760/1545, loss: 5.92225456237793 2023-01-23 06:31:54.925470: step: 762/1545, loss: 0.6067999601364136 2023-01-23 06:31:55.764535: step: 764/1545, loss: 1.2849173545837402 2023-01-23 06:31:56.647108: step: 766/1545, loss: 1.0899198055267334 2023-01-23 06:31:57.513536: step: 768/1545, loss: 0.3335901200771332 2023-01-23 06:31:58.378598: step: 770/1545, loss: 0.5611814856529236 2023-01-23 06:31:59.238378: step: 772/1545, loss: 0.8167347311973572 2023-01-23 06:32:00.156928: step: 774/1545, loss: 0.4968363642692566 2023-01-23 06:32:01.005803: step: 776/1545, loss: 3.5330958366394043 2023-01-23 06:32:01.902224: step: 778/1545, loss: 0.7271833419799805 2023-01-23 06:32:02.824263: step: 780/1545, loss: 0.46375754475593567 2023-01-23 06:32:03.698590: step: 782/1545, loss: 0.7536205649375916 2023-01-23 06:32:04.552319: step: 784/1545, loss: 0.43994733691215515 2023-01-23 06:32:05.434458: step: 786/1545, loss: 0.3470936119556427 2023-01-23 06:32:06.304649: step: 788/1545, loss: 0.6646099090576172 2023-01-23 06:32:07.173135: step: 790/1545, loss: 0.6109217405319214 2023-01-23 06:32:08.090861: step: 792/1545, loss: 2.6085715293884277 2023-01-23 06:32:09.000179: step: 794/1545, loss: 0.7020270824432373 2023-01-23 06:32:09.917337: step: 796/1545, loss: 1.0274826288223267 2023-01-23 06:32:10.763701: step: 798/1545, loss: 0.883023202419281 2023-01-23 06:32:11.625342: step: 800/1545, loss: 0.49144986271858215 2023-01-23 06:32:12.513484: step: 802/1545, loss: 0.9392192959785461 2023-01-23 06:32:13.407914: step: 804/1545, loss: 1.069204330444336 2023-01-23 06:32:14.271168: step: 806/1545, loss: 0.909464955329895 2023-01-23 06:32:15.116439: step: 808/1545, loss: 0.6912413239479065 2023-01-23 06:32:15.963468: step: 810/1545, loss: 0.9526829719543457 2023-01-23 06:32:16.852823: step: 812/1545, loss: 0.698200523853302 2023-01-23 06:32:17.722526: step: 814/1545, loss: 3.5409250259399414 2023-01-23 06:32:18.607260: step: 816/1545, loss: 2.7270803451538086 2023-01-23 06:32:19.497414: step: 818/1545, loss: 0.7293714284896851 2023-01-23 06:32:20.379945: step: 820/1545, loss: 0.5146104097366333 2023-01-23 06:32:21.286222: step: 822/1545, loss: 0.883606493473053 2023-01-23 06:32:22.149414: step: 824/1545, loss: 0.7425508499145508 2023-01-23 06:32:23.078610: step: 826/1545, loss: 0.9813473224639893 2023-01-23 06:32:23.989295: step: 828/1545, loss: 0.9722498655319214 2023-01-23 06:32:24.917463: step: 830/1545, loss: 1.0045195817947388 2023-01-23 06:32:25.838726: step: 832/1545, loss: 0.9240204095840454 2023-01-23 06:32:26.714732: step: 834/1545, loss: 0.45471587777137756 2023-01-23 06:32:27.593172: step: 836/1545, loss: 0.9466776847839355 2023-01-23 06:32:28.466187: step: 838/1545, loss: 0.821980357170105 2023-01-23 06:32:29.329102: step: 840/1545, loss: 0.2832198143005371 2023-01-23 06:32:30.177961: step: 842/1545, loss: 2.706648349761963 2023-01-23 06:32:31.048057: step: 844/1545, loss: 2.7666332721710205 2023-01-23 06:32:31.939777: step: 846/1545, loss: 0.696101725101471 2023-01-23 06:32:32.807013: step: 848/1545, loss: 5.7705397605896 2023-01-23 06:32:33.689984: step: 850/1545, loss: 0.5264796018600464 2023-01-23 06:32:34.600630: step: 852/1545, loss: 1.2005338668823242 2023-01-23 06:32:35.454701: step: 854/1545, loss: 0.2963904142379761 2023-01-23 06:32:36.327133: step: 856/1545, loss: 0.9049073457717896 2023-01-23 06:32:37.216182: step: 858/1545, loss: 0.3894522786140442 2023-01-23 06:32:38.114180: step: 860/1545, loss: 0.7421970367431641 2023-01-23 06:32:38.967267: step: 862/1545, loss: 0.38382086157798767 2023-01-23 06:32:39.840045: step: 864/1545, loss: 0.5347716808319092 2023-01-23 06:32:40.710763: step: 866/1545, loss: 1.5541447401046753 2023-01-23 06:32:41.630217: step: 868/1545, loss: 0.5717743635177612 2023-01-23 06:32:42.505426: step: 870/1545, loss: 0.8369989991188049 2023-01-23 06:32:43.396964: step: 872/1545, loss: 0.574687123298645 2023-01-23 06:32:44.256669: step: 874/1545, loss: 1.0288007259368896 2023-01-23 06:32:45.148431: step: 876/1545, loss: 1.1487427949905396 2023-01-23 06:32:46.048695: step: 878/1545, loss: 1.3966370820999146 2023-01-23 06:32:46.882005: step: 880/1545, loss: 0.977814793586731 2023-01-23 06:32:47.803357: step: 882/1545, loss: 0.535284161567688 2023-01-23 06:32:48.720288: step: 884/1545, loss: 4.154404163360596 2023-01-23 06:32:49.690997: step: 886/1545, loss: 0.7306129336357117 2023-01-23 06:32:50.551834: step: 888/1545, loss: 0.5872649550437927 2023-01-23 06:32:51.441425: step: 890/1545, loss: 2.953270673751831 2023-01-23 06:32:52.313363: step: 892/1545, loss: 1.0054248571395874 2023-01-23 06:32:53.199420: step: 894/1545, loss: 0.6510311961174011 2023-01-23 06:32:54.071973: step: 896/1545, loss: 0.6232800483703613 2023-01-23 06:32:54.960772: step: 898/1545, loss: 0.3958294689655304 2023-01-23 06:32:55.815858: step: 900/1545, loss: 0.8000847697257996 2023-01-23 06:32:56.673174: step: 902/1545, loss: 0.8175826668739319 2023-01-23 06:32:57.557579: step: 904/1545, loss: 1.4845006465911865 2023-01-23 06:32:58.441371: step: 906/1545, loss: 0.9354042410850525 2023-01-23 06:32:59.327565: step: 908/1545, loss: 0.8440616130828857 2023-01-23 06:33:00.223147: step: 910/1545, loss: 0.33719760179519653 2023-01-23 06:33:01.111823: step: 912/1545, loss: 0.4304664134979248 2023-01-23 06:33:02.012920: step: 914/1545, loss: 0.7933158874511719 2023-01-23 06:33:02.895275: step: 916/1545, loss: 0.35736432671546936 2023-01-23 06:33:03.793635: step: 918/1545, loss: 1.3513884544372559 2023-01-23 06:33:04.696224: step: 920/1545, loss: 0.556831419467926 2023-01-23 06:33:05.584913: step: 922/1545, loss: 0.6243575811386108 2023-01-23 06:33:06.427023: step: 924/1545, loss: 0.7017307877540588 2023-01-23 06:33:07.345121: step: 926/1545, loss: 0.403828501701355 2023-01-23 06:33:08.247600: step: 928/1545, loss: 0.3880878686904907 2023-01-23 06:33:09.123390: step: 930/1545, loss: 2.6977217197418213 2023-01-23 06:33:10.034512: step: 932/1545, loss: 2.4646148681640625 2023-01-23 06:33:10.926545: step: 934/1545, loss: 0.45413583517074585 2023-01-23 06:33:11.841636: step: 936/1545, loss: 0.750912606716156 2023-01-23 06:33:12.706758: step: 938/1545, loss: 1.0342602729797363 2023-01-23 06:33:13.561468: step: 940/1545, loss: 0.3069947361946106 2023-01-23 06:33:14.537752: step: 942/1545, loss: 0.6812856197357178 2023-01-23 06:33:15.410604: step: 944/1545, loss: 0.504744291305542 2023-01-23 06:33:16.310433: step: 946/1545, loss: 0.857690691947937 2023-01-23 06:33:17.203981: step: 948/1545, loss: 4.194729804992676 2023-01-23 06:33:18.092266: step: 950/1545, loss: 0.9762575626373291 2023-01-23 06:33:19.003625: step: 952/1545, loss: 0.5482752919197083 2023-01-23 06:33:19.864757: step: 954/1545, loss: 5.626163959503174 2023-01-23 06:33:20.728240: step: 956/1545, loss: 2.4040935039520264 2023-01-23 06:33:21.664683: step: 958/1545, loss: 0.7848169207572937 2023-01-23 06:33:22.581884: step: 960/1545, loss: 0.7181039452552795 2023-01-23 06:33:23.440093: step: 962/1545, loss: 2.903521776199341 2023-01-23 06:33:24.336136: step: 964/1545, loss: 1.2486730813980103 2023-01-23 06:33:25.270451: step: 966/1545, loss: 0.5661880373954773 2023-01-23 06:33:26.122963: step: 968/1545, loss: 0.5228816866874695 2023-01-23 06:33:27.028220: step: 970/1545, loss: 0.3901720643043518 2023-01-23 06:33:27.899434: step: 972/1545, loss: 0.2820630967617035 2023-01-23 06:33:28.822626: step: 974/1545, loss: 3.1567602157592773 2023-01-23 06:33:29.825720: step: 976/1545, loss: 0.5257549285888672 2023-01-23 06:33:30.724235: step: 978/1545, loss: 1.1302247047424316 2023-01-23 06:33:31.606555: step: 980/1545, loss: 2.063058376312256 2023-01-23 06:33:32.460971: step: 982/1545, loss: 0.824059784412384 2023-01-23 06:33:33.311655: step: 984/1545, loss: 2.1311588287353516 2023-01-23 06:33:34.151452: step: 986/1545, loss: 0.2916993796825409 2023-01-23 06:33:35.115525: step: 988/1545, loss: 0.5084181427955627 2023-01-23 06:33:36.016485: step: 990/1545, loss: 1.7854937314987183 2023-01-23 06:33:36.873927: step: 992/1545, loss: 2.568866729736328 2023-01-23 06:33:37.757523: step: 994/1545, loss: 0.5680502653121948 2023-01-23 06:33:38.666861: step: 996/1545, loss: 2.780507802963257 2023-01-23 06:33:39.548099: step: 998/1545, loss: 0.7417853474617004 2023-01-23 06:33:40.471752: step: 1000/1545, loss: 0.6385790109634399 2023-01-23 06:33:41.353587: step: 1002/1545, loss: 0.45254096388816833 2023-01-23 06:33:42.259458: step: 1004/1545, loss: 2.9322144985198975 2023-01-23 06:33:43.128605: step: 1006/1545, loss: 0.8301493525505066 2023-01-23 06:33:43.999139: step: 1008/1545, loss: 0.7073600888252258 2023-01-23 06:33:44.965222: step: 1010/1545, loss: 0.9967445731163025 2023-01-23 06:33:45.832319: step: 1012/1545, loss: 0.8088362216949463 2023-01-23 06:33:46.770605: step: 1014/1545, loss: 1.251255750656128 2023-01-23 06:33:47.635656: step: 1016/1545, loss: 0.6089984774589539 2023-01-23 06:33:48.505501: step: 1018/1545, loss: 0.4546748697757721 2023-01-23 06:33:49.402076: step: 1020/1545, loss: 0.7102826833724976 2023-01-23 06:33:50.267093: step: 1022/1545, loss: 0.49169084429740906 2023-01-23 06:33:51.154025: step: 1024/1545, loss: 0.635947048664093 2023-01-23 06:33:52.035988: step: 1026/1545, loss: 0.8728625178337097 2023-01-23 06:33:52.889978: step: 1028/1545, loss: 1.0594871044158936 2023-01-23 06:33:53.758816: step: 1030/1545, loss: 0.416934609413147 2023-01-23 06:33:54.648646: step: 1032/1545, loss: 0.5777702331542969 2023-01-23 06:33:55.508370: step: 1034/1545, loss: 0.7116779685020447 2023-01-23 06:33:56.361404: step: 1036/1545, loss: 0.4810258746147156 2023-01-23 06:33:57.248800: step: 1038/1545, loss: 0.7736976742744446 2023-01-23 06:33:58.136857: step: 1040/1545, loss: 0.5981934666633606 2023-01-23 06:33:59.061259: step: 1042/1545, loss: 0.45425528287887573 2023-01-23 06:33:59.960367: step: 1044/1545, loss: 0.3406766951084137 2023-01-23 06:34:00.908931: step: 1046/1545, loss: 0.7698712944984436 2023-01-23 06:34:01.775720: step: 1048/1545, loss: 0.9556031823158264 2023-01-23 06:34:02.634204: step: 1050/1545, loss: 2.8518083095550537 2023-01-23 06:34:03.485531: step: 1052/1545, loss: 0.6587660908699036 2023-01-23 06:34:04.348311: step: 1054/1545, loss: 0.6352123022079468 2023-01-23 06:34:05.200486: step: 1056/1545, loss: 0.2819254398345947 2023-01-23 06:34:06.061607: step: 1058/1545, loss: 0.7314082384109497 2023-01-23 06:34:06.957673: step: 1060/1545, loss: 1.1448661088943481 2023-01-23 06:34:07.813325: step: 1062/1545, loss: 0.6911136507987976 2023-01-23 06:34:08.654440: step: 1064/1545, loss: 0.6001548767089844 2023-01-23 06:34:09.533990: step: 1066/1545, loss: 0.2948186993598938 2023-01-23 06:34:10.408000: step: 1068/1545, loss: 0.5600830316543579 2023-01-23 06:34:11.339747: step: 1070/1545, loss: 0.3684391677379608 2023-01-23 06:34:12.287909: step: 1072/1545, loss: 1.3993643522262573 2023-01-23 06:34:13.156015: step: 1074/1545, loss: 1.9604181051254272 2023-01-23 06:34:14.024939: step: 1076/1545, loss: 0.7553662657737732 2023-01-23 06:34:14.881045: step: 1078/1545, loss: 0.7170141935348511 2023-01-23 06:34:15.737718: step: 1080/1545, loss: 1.5496187210083008 2023-01-23 06:34:16.625472: step: 1082/1545, loss: 2.1996541023254395 2023-01-23 06:34:17.503694: step: 1084/1545, loss: 0.7052716612815857 2023-01-23 06:34:18.404628: step: 1086/1545, loss: 0.6963484287261963 2023-01-23 06:34:19.313767: step: 1088/1545, loss: 0.9095985889434814 2023-01-23 06:34:20.188998: step: 1090/1545, loss: 0.4105549454689026 2023-01-23 06:34:21.082908: step: 1092/1545, loss: 0.7098442912101746 2023-01-23 06:34:21.973341: step: 1094/1545, loss: 1.965936541557312 2023-01-23 06:34:22.840799: step: 1096/1545, loss: 0.7928605675697327 2023-01-23 06:34:23.709073: step: 1098/1545, loss: 1.8839703798294067 2023-01-23 06:34:24.655941: step: 1100/1545, loss: 0.6389756202697754 2023-01-23 06:34:25.507470: step: 1102/1545, loss: 0.48319923877716064 2023-01-23 06:34:26.344139: step: 1104/1545, loss: 0.4246375858783722 2023-01-23 06:34:27.209275: step: 1106/1545, loss: 3.461207866668701 2023-01-23 06:34:28.080844: step: 1108/1545, loss: 0.5860686302185059 2023-01-23 06:34:28.971634: step: 1110/1545, loss: 3.1564576625823975 2023-01-23 06:34:29.922811: step: 1112/1545, loss: 0.4784051179885864 2023-01-23 06:34:30.820055: step: 1114/1545, loss: 0.7744613885879517 2023-01-23 06:34:31.698772: step: 1116/1545, loss: 1.1380935907363892 2023-01-23 06:34:32.579631: step: 1118/1545, loss: 0.9835503697395325 2023-01-23 06:34:33.498406: step: 1120/1545, loss: 0.8043296337127686 2023-01-23 06:34:34.389753: step: 1122/1545, loss: 1.0300062894821167 2023-01-23 06:34:35.259452: step: 1124/1545, loss: 5.204714298248291 2023-01-23 06:34:36.163634: step: 1126/1545, loss: 1.3948338031768799 2023-01-23 06:34:37.041729: step: 1128/1545, loss: 1.122228741645813 2023-01-23 06:34:37.882646: step: 1130/1545, loss: 0.9844070672988892 2023-01-23 06:34:38.753166: step: 1132/1545, loss: 0.9945937395095825 2023-01-23 06:34:39.601844: step: 1134/1545, loss: 0.48416343331336975 2023-01-23 06:34:40.469709: step: 1136/1545, loss: 2.8021249771118164 2023-01-23 06:34:41.375253: step: 1138/1545, loss: 2.358992338180542 2023-01-23 06:34:42.253402: step: 1140/1545, loss: 0.6059249043464661 2023-01-23 06:34:43.113191: step: 1142/1545, loss: 2.0335278511047363 2023-01-23 06:34:43.959191: step: 1144/1545, loss: 0.597068190574646 2023-01-23 06:34:44.816475: step: 1146/1545, loss: 0.6783427000045776 2023-01-23 06:34:45.747223: step: 1148/1545, loss: 0.5159839987754822 2023-01-23 06:34:46.597528: step: 1150/1545, loss: 0.3690456449985504 2023-01-23 06:34:47.551949: step: 1152/1545, loss: 0.6783503890037537 2023-01-23 06:34:48.416661: step: 1154/1545, loss: 0.8655570149421692 2023-01-23 06:34:49.289777: step: 1156/1545, loss: 1.2313569784164429 2023-01-23 06:34:50.155830: step: 1158/1545, loss: 0.4479771852493286 2023-01-23 06:34:51.014882: step: 1160/1545, loss: 1.6678059101104736 2023-01-23 06:34:51.861293: step: 1162/1545, loss: 0.7537886500358582 2023-01-23 06:34:52.722536: step: 1164/1545, loss: 0.6838782429695129 2023-01-23 06:34:53.557518: step: 1166/1545, loss: 0.6326023936271667 2023-01-23 06:34:54.398602: step: 1168/1545, loss: 0.5741488337516785 2023-01-23 06:34:55.298101: step: 1170/1545, loss: 1.3547865152359009 2023-01-23 06:34:56.170695: step: 1172/1545, loss: 0.3488531708717346 2023-01-23 06:34:57.026862: step: 1174/1545, loss: 0.29541710019111633 2023-01-23 06:34:57.979038: step: 1176/1545, loss: 1.1827036142349243 2023-01-23 06:34:58.855324: step: 1178/1545, loss: 1.136570692062378 2023-01-23 06:34:59.745600: step: 1180/1545, loss: 0.801984429359436 2023-01-23 06:35:00.608987: step: 1182/1545, loss: 1.5658953189849854 2023-01-23 06:35:01.469404: step: 1184/1545, loss: 0.7259972095489502 2023-01-23 06:35:02.348260: step: 1186/1545, loss: 0.5257279872894287 2023-01-23 06:35:03.288766: step: 1188/1545, loss: 0.929570198059082 2023-01-23 06:35:04.212336: step: 1190/1545, loss: 1.0608887672424316 2023-01-23 06:35:05.081174: step: 1192/1545, loss: 0.41386857628822327 2023-01-23 06:35:05.958341: step: 1194/1545, loss: 0.31861260533332825 2023-01-23 06:35:06.919816: step: 1196/1545, loss: 0.2979377508163452 2023-01-23 06:35:07.811393: step: 1198/1545, loss: 0.48161780834198 2023-01-23 06:35:08.700155: step: 1200/1545, loss: 0.6860335469245911 2023-01-23 06:35:09.544704: step: 1202/1545, loss: 0.9247743487358093 2023-01-23 06:35:10.399636: step: 1204/1545, loss: 0.5868303179740906 2023-01-23 06:35:11.351224: step: 1206/1545, loss: 0.63630211353302 2023-01-23 06:35:12.207030: step: 1208/1545, loss: 0.49148207902908325 2023-01-23 06:35:13.113744: step: 1210/1545, loss: 0.5068795680999756 2023-01-23 06:35:14.094103: step: 1212/1545, loss: 0.5543949604034424 2023-01-23 06:35:15.020759: step: 1214/1545, loss: 1.1976022720336914 2023-01-23 06:35:15.952241: step: 1216/1545, loss: 0.86160808801651 2023-01-23 06:35:16.825827: step: 1218/1545, loss: 0.533493161201477 2023-01-23 06:35:17.659999: step: 1220/1545, loss: 0.2516409754753113 2023-01-23 06:35:18.611910: step: 1222/1545, loss: 0.6646698117256165 2023-01-23 06:35:19.512832: step: 1224/1545, loss: 0.35994961857795715 2023-01-23 06:35:20.369595: step: 1226/1545, loss: 0.41133907437324524 2023-01-23 06:35:21.302155: step: 1228/1545, loss: 0.8905478715896606 2023-01-23 06:35:22.165251: step: 1230/1545, loss: 0.8040834665298462 2023-01-23 06:35:23.045002: step: 1232/1545, loss: 0.8449832201004028 2023-01-23 06:35:23.925924: step: 1234/1545, loss: 0.5289225578308105 2023-01-23 06:35:24.827606: step: 1236/1545, loss: 2.623322010040283 2023-01-23 06:35:25.726544: step: 1238/1545, loss: 1.3341102600097656 2023-01-23 06:35:26.584187: step: 1240/1545, loss: 0.6510881185531616 2023-01-23 06:35:27.446544: step: 1242/1545, loss: 0.2929508090019226 2023-01-23 06:35:28.322910: step: 1244/1545, loss: 0.2939821183681488 2023-01-23 06:35:29.223348: step: 1246/1545, loss: 0.628098726272583 2023-01-23 06:35:30.094979: step: 1248/1545, loss: 0.691914975643158 2023-01-23 06:35:30.964351: step: 1250/1545, loss: 0.24194324016571045 2023-01-23 06:35:31.826841: step: 1252/1545, loss: 0.7184439897537231 2023-01-23 06:35:32.701114: step: 1254/1545, loss: 0.8904834389686584 2023-01-23 06:35:33.589944: step: 1256/1545, loss: 2.7970590591430664 2023-01-23 06:35:34.432640: step: 1258/1545, loss: 0.36668968200683594 2023-01-23 06:35:35.374886: step: 1260/1545, loss: 0.4564873278141022 2023-01-23 06:35:36.239643: step: 1262/1545, loss: 0.732948362827301 2023-01-23 06:35:37.099954: step: 1264/1545, loss: 0.4964057505130768 2023-01-23 06:35:37.981421: step: 1266/1545, loss: 1.8686721324920654 2023-01-23 06:35:38.904513: step: 1268/1545, loss: 1.3361892700195312 2023-01-23 06:35:39.822391: step: 1270/1545, loss: 0.534213125705719 2023-01-23 06:35:40.712655: step: 1272/1545, loss: 3.5829365253448486 2023-01-23 06:35:41.557083: step: 1274/1545, loss: 0.760720431804657 2023-01-23 06:35:42.398629: step: 1276/1545, loss: 0.4870484173297882 2023-01-23 06:35:43.256893: step: 1278/1545, loss: 0.5043160915374756 2023-01-23 06:35:44.108930: step: 1280/1545, loss: 0.5577282905578613 2023-01-23 06:35:44.985146: step: 1282/1545, loss: 0.7280421853065491 2023-01-23 06:35:45.831516: step: 1284/1545, loss: 2.273601770401001 2023-01-23 06:35:46.753765: step: 1286/1545, loss: 0.9323094487190247 2023-01-23 06:35:47.608422: step: 1288/1545, loss: 0.4334772825241089 2023-01-23 06:35:48.437415: step: 1290/1545, loss: 0.509178638458252 2023-01-23 06:35:49.305144: step: 1292/1545, loss: 3.7124040126800537 2023-01-23 06:35:50.164345: step: 1294/1545, loss: 1.1226201057434082 2023-01-23 06:35:51.025260: step: 1296/1545, loss: 0.8710903525352478 2023-01-23 06:35:51.853701: step: 1298/1545, loss: 0.7501679062843323 2023-01-23 06:35:52.732564: step: 1300/1545, loss: 1.4859881401062012 2023-01-23 06:35:53.650673: step: 1302/1545, loss: 0.4953252077102661 2023-01-23 06:35:54.509378: step: 1304/1545, loss: 0.547685980796814 2023-01-23 06:35:55.427526: step: 1306/1545, loss: 0.36327818036079407 2023-01-23 06:35:56.272030: step: 1308/1545, loss: 0.6150341033935547 2023-01-23 06:35:57.168075: step: 1310/1545, loss: 0.3854549825191498 2023-01-23 06:35:58.020100: step: 1312/1545, loss: 0.9252903461456299 2023-01-23 06:35:58.894966: step: 1314/1545, loss: 1.042511224746704 2023-01-23 06:35:59.801132: step: 1316/1545, loss: 0.95781010389328 2023-01-23 06:36:00.672165: step: 1318/1545, loss: 0.49076047539711 2023-01-23 06:36:01.611300: step: 1320/1545, loss: 0.5460929274559021 2023-01-23 06:36:02.524373: step: 1322/1545, loss: 1.0452096462249756 2023-01-23 06:36:03.367489: step: 1324/1545, loss: 0.35856369137763977 2023-01-23 06:36:04.290761: step: 1326/1545, loss: 1.037171721458435 2023-01-23 06:36:05.154131: step: 1328/1545, loss: 0.9858412742614746 2023-01-23 06:36:06.021526: step: 1330/1545, loss: 0.7271382808685303 2023-01-23 06:36:06.886322: step: 1332/1545, loss: 0.366937518119812 2023-01-23 06:36:07.770420: step: 1334/1545, loss: 0.5721368193626404 2023-01-23 06:36:08.631784: step: 1336/1545, loss: 1.2353699207305908 2023-01-23 06:36:09.470379: step: 1338/1545, loss: 0.20885013043880463 2023-01-23 06:36:10.340215: step: 1340/1545, loss: 0.8387637734413147 2023-01-23 06:36:11.237122: step: 1342/1545, loss: 0.996653139591217 2023-01-23 06:36:12.099540: step: 1344/1545, loss: 0.7582343220710754 2023-01-23 06:36:12.925754: step: 1346/1545, loss: 0.8699442744255066 2023-01-23 06:36:13.779339: step: 1348/1545, loss: 0.40425384044647217 2023-01-23 06:36:14.666139: step: 1350/1545, loss: 0.6927008628845215 2023-01-23 06:36:15.546916: step: 1352/1545, loss: 0.796119749546051 2023-01-23 06:36:16.438156: step: 1354/1545, loss: 1.2916406393051147 2023-01-23 06:36:17.315465: step: 1356/1545, loss: 0.5228915214538574 2023-01-23 06:36:18.141271: step: 1358/1545, loss: 0.20627009868621826 2023-01-23 06:36:18.980144: step: 1360/1545, loss: 0.4762641489505768 2023-01-23 06:36:19.835024: step: 1362/1545, loss: 0.2590300738811493 2023-01-23 06:36:20.728624: step: 1364/1545, loss: 0.8900386095046997 2023-01-23 06:36:21.651297: step: 1366/1545, loss: 2.7049922943115234 2023-01-23 06:36:22.531537: step: 1368/1545, loss: 0.8639727234840393 2023-01-23 06:36:23.415903: step: 1370/1545, loss: 0.5007631778717041 2023-01-23 06:36:24.291379: step: 1372/1545, loss: 0.9937966465950012 2023-01-23 06:36:25.179072: step: 1374/1545, loss: 1.382645606994629 2023-01-23 06:36:26.046967: step: 1376/1545, loss: 0.4800873100757599 2023-01-23 06:36:26.920829: step: 1378/1545, loss: 1.4388352632522583 2023-01-23 06:36:27.789921: step: 1380/1545, loss: 0.8396663665771484 2023-01-23 06:36:28.657219: step: 1382/1545, loss: 1.2209633588790894 2023-01-23 06:36:29.509028: step: 1384/1545, loss: 0.24311107397079468 2023-01-23 06:36:30.426159: step: 1386/1545, loss: 0.4438336491584778 2023-01-23 06:36:31.402259: step: 1388/1545, loss: 1.1696767807006836 2023-01-23 06:36:32.264710: step: 1390/1545, loss: 1.0562715530395508 2023-01-23 06:36:33.146173: step: 1392/1545, loss: 1.3802465200424194 2023-01-23 06:36:34.083959: step: 1394/1545, loss: 0.7080627083778381 2023-01-23 06:36:34.978968: step: 1396/1545, loss: 1.0068641901016235 2023-01-23 06:36:35.826104: step: 1398/1545, loss: 0.5084733366966248 2023-01-23 06:36:36.695677: step: 1400/1545, loss: 1.2710845470428467 2023-01-23 06:36:37.620828: step: 1402/1545, loss: 0.48115864396095276 2023-01-23 06:36:38.484037: step: 1404/1545, loss: 0.4155831038951874 2023-01-23 06:36:39.368273: step: 1406/1545, loss: 0.43257105350494385 2023-01-23 06:36:40.241953: step: 1408/1545, loss: 1.2712934017181396 2023-01-23 06:36:41.149336: step: 1410/1545, loss: 0.928991973400116 2023-01-23 06:36:42.059367: step: 1412/1545, loss: 0.9411171078681946 2023-01-23 06:36:42.955526: step: 1414/1545, loss: 0.6801178455352783 2023-01-23 06:36:43.811641: step: 1416/1545, loss: 0.4670538604259491 2023-01-23 06:36:44.721009: step: 1418/1545, loss: 0.6589787602424622 2023-01-23 06:36:45.596712: step: 1420/1545, loss: 0.6384276151657104 2023-01-23 06:36:46.436560: step: 1422/1545, loss: 0.3328218162059784 2023-01-23 06:36:47.263139: step: 1424/1545, loss: 1.6528558731079102 2023-01-23 06:36:48.117619: step: 1426/1545, loss: 0.4094640910625458 2023-01-23 06:36:48.990227: step: 1428/1545, loss: 1.9057774543762207 2023-01-23 06:36:49.867697: step: 1430/1545, loss: 3.9181947708129883 2023-01-23 06:36:50.747562: step: 1432/1545, loss: 0.9664626717567444 2023-01-23 06:36:51.673559: step: 1434/1545, loss: 0.4565715491771698 2023-01-23 06:36:52.571788: step: 1436/1545, loss: 0.6069220900535583 2023-01-23 06:36:53.476679: step: 1438/1545, loss: 0.7816827893257141 2023-01-23 06:36:54.329906: step: 1440/1545, loss: 0.30837976932525635 2023-01-23 06:36:55.187327: step: 1442/1545, loss: 1.0365606546401978 2023-01-23 06:36:56.074833: step: 1444/1545, loss: 0.252056747674942 2023-01-23 06:36:56.954794: step: 1446/1545, loss: 1.3783011436462402 2023-01-23 06:36:57.811152: step: 1448/1545, loss: 0.7684051990509033 2023-01-23 06:36:58.679085: step: 1450/1545, loss: 0.7938041090965271 2023-01-23 06:36:59.512909: step: 1452/1545, loss: 1.1656467914581299 2023-01-23 06:37:00.426700: step: 1454/1545, loss: 0.4573667645454407 2023-01-23 06:37:01.311789: step: 1456/1545, loss: 0.5409027338027954 2023-01-23 06:37:02.237991: step: 1458/1545, loss: 1.5015848875045776 2023-01-23 06:37:03.112225: step: 1460/1545, loss: 1.130378246307373 2023-01-23 06:37:03.969547: step: 1462/1545, loss: 0.6625455617904663 2023-01-23 06:37:04.817656: step: 1464/1545, loss: 0.9745924472808838 2023-01-23 06:37:05.688859: step: 1466/1545, loss: 0.3418116569519043 2023-01-23 06:37:06.569055: step: 1468/1545, loss: 0.4494553804397583 2023-01-23 06:37:07.463253: step: 1470/1545, loss: 0.6912697553634644 2023-01-23 06:37:08.327171: step: 1472/1545, loss: 0.8630918264389038 2023-01-23 06:37:09.205607: step: 1474/1545, loss: 0.43362465500831604 2023-01-23 06:37:10.090925: step: 1476/1545, loss: 0.49811333417892456 2023-01-23 06:37:10.958405: step: 1478/1545, loss: 0.564080536365509 2023-01-23 06:37:11.846516: step: 1480/1545, loss: 0.4201054871082306 2023-01-23 06:37:12.709246: step: 1482/1545, loss: 0.41711923480033875 2023-01-23 06:37:13.560947: step: 1484/1545, loss: 0.5985534191131592 2023-01-23 06:37:14.405689: step: 1486/1545, loss: 0.5880816578865051 2023-01-23 06:37:15.266470: step: 1488/1545, loss: 1.1611711978912354 2023-01-23 06:37:16.149670: step: 1490/1545, loss: 0.7350593209266663 2023-01-23 06:37:17.100940: step: 1492/1545, loss: 0.5490592122077942 2023-01-23 06:37:18.055662: step: 1494/1545, loss: 0.9544775485992432 2023-01-23 06:37:18.968416: step: 1496/1545, loss: 1.6369702816009521 2023-01-23 06:37:19.783959: step: 1498/1545, loss: 0.5758504867553711 2023-01-23 06:37:20.615775: step: 1500/1545, loss: 0.7368077039718628 2023-01-23 06:37:21.482447: step: 1502/1545, loss: 1.3893439769744873 2023-01-23 06:37:22.349186: step: 1504/1545, loss: 0.32681843638420105 2023-01-23 06:37:23.229736: step: 1506/1545, loss: 1.6122931241989136 2023-01-23 06:37:24.096660: step: 1508/1545, loss: 0.4978468716144562 2023-01-23 06:37:25.008348: step: 1510/1545, loss: 0.6578901410102844 2023-01-23 06:37:25.869461: step: 1512/1545, loss: 0.5331190228462219 2023-01-23 06:37:26.712887: step: 1514/1545, loss: 0.5114383697509766 2023-01-23 06:37:27.550819: step: 1516/1545, loss: 0.7291643619537354 2023-01-23 06:37:28.455522: step: 1518/1545, loss: 1.2905937433242798 2023-01-23 06:37:29.341223: step: 1520/1545, loss: 0.8822138905525208 2023-01-23 06:37:30.195491: step: 1522/1545, loss: 0.3440537452697754 2023-01-23 06:37:31.059926: step: 1524/1545, loss: 0.4567714333534241 2023-01-23 06:37:31.911237: step: 1526/1545, loss: 1.3380976915359497 2023-01-23 06:37:32.835388: step: 1528/1545, loss: 0.6434738039970398 2023-01-23 06:37:33.675547: step: 1530/1545, loss: 0.9908981323242188 2023-01-23 06:37:34.517365: step: 1532/1545, loss: 1.5804728269577026 2023-01-23 06:37:35.416012: step: 1534/1545, loss: 0.6659321784973145 2023-01-23 06:37:36.292786: step: 1536/1545, loss: 0.8209267258644104 2023-01-23 06:37:37.217414: step: 1538/1545, loss: 0.2058832347393036 2023-01-23 06:37:38.101656: step: 1540/1545, loss: 1.0623682737350464 2023-01-23 06:37:39.023034: step: 1542/1545, loss: 1.5092988014221191 2023-01-23 06:37:39.927509: step: 1544/1545, loss: 0.56621253490448 2023-01-23 06:37:40.865652: step: 1546/1545, loss: 1.5733498334884644 2023-01-23 06:37:41.782496: step: 1548/1545, loss: 0.7827165722846985 2023-01-23 06:37:42.654705: step: 1550/1545, loss: 0.35367918014526367 2023-01-23 06:37:43.590384: step: 1552/1545, loss: 1.103240728378296 2023-01-23 06:37:44.487380: step: 1554/1545, loss: 1.0009968280792236 2023-01-23 06:37:45.453078: step: 1556/1545, loss: 1.0879926681518555 2023-01-23 06:37:46.310351: step: 1558/1545, loss: 0.44289180636405945 2023-01-23 06:37:47.220334: step: 1560/1545, loss: 0.33301296830177307 2023-01-23 06:37:48.053822: step: 1562/1545, loss: 0.17897534370422363 2023-01-23 06:37:48.964207: step: 1564/1545, loss: 3.259387493133545 2023-01-23 06:37:49.861427: step: 1566/1545, loss: 0.39467674493789673 2023-01-23 06:37:50.750393: step: 1568/1545, loss: 0.5956233143806458 2023-01-23 06:37:51.602524: step: 1570/1545, loss: 0.9961344003677368 2023-01-23 06:37:52.502815: step: 1572/1545, loss: 1.0507500171661377 2023-01-23 06:37:53.412718: step: 1574/1545, loss: 1.6196835041046143 2023-01-23 06:37:54.326486: step: 1576/1545, loss: 0.7598511576652527 2023-01-23 06:37:55.203203: step: 1578/1545, loss: 2.4525561332702637 2023-01-23 06:37:56.097916: step: 1580/1545, loss: 7.596437454223633 2023-01-23 06:37:57.016708: step: 1582/1545, loss: 0.6404609084129333 2023-01-23 06:37:57.854169: step: 1584/1545, loss: 0.7837436199188232 2023-01-23 06:37:58.739827: step: 1586/1545, loss: 0.6895748376846313 2023-01-23 06:37:59.685453: step: 1588/1545, loss: 0.8417477607727051 2023-01-23 06:38:00.563190: step: 1590/1545, loss: 0.34078851342201233 2023-01-23 06:38:01.447805: step: 1592/1545, loss: 1.9990679025650024 2023-01-23 06:38:02.332637: step: 1594/1545, loss: 0.6027674078941345 2023-01-23 06:38:03.208045: step: 1596/1545, loss: 0.4765099585056305 2023-01-23 06:38:04.122902: step: 1598/1545, loss: 0.8730245232582092 2023-01-23 06:38:05.035906: step: 1600/1545, loss: 0.6330609917640686 2023-01-23 06:38:05.938248: step: 1602/1545, loss: 1.6403098106384277 2023-01-23 06:38:06.850260: step: 1604/1545, loss: 0.5067822933197021 2023-01-23 06:38:07.720988: step: 1606/1545, loss: 0.498211145401001 2023-01-23 06:38:08.589417: step: 1608/1545, loss: 3.063979387283325 2023-01-23 06:38:09.481229: step: 1610/1545, loss: 0.3655860424041748 2023-01-23 06:38:10.360084: step: 1612/1545, loss: 0.5672870874404907 2023-01-23 06:38:11.255917: step: 1614/1545, loss: 0.48137420415878296 2023-01-23 06:38:12.153586: step: 1616/1545, loss: 0.6274750232696533 2023-01-23 06:38:13.016962: step: 1618/1545, loss: 0.41037508845329285 2023-01-23 06:38:13.872478: step: 1620/1545, loss: 1.05845308303833 2023-01-23 06:38:14.730362: step: 1622/1545, loss: 0.838006854057312 2023-01-23 06:38:15.605797: step: 1624/1545, loss: 0.6853530406951904 2023-01-23 06:38:16.448611: step: 1626/1545, loss: 0.2930094599723816 2023-01-23 06:38:17.322737: step: 1628/1545, loss: 1.1270962953567505 2023-01-23 06:38:18.236782: step: 1630/1545, loss: 0.33601200580596924 2023-01-23 06:38:19.107064: step: 1632/1545, loss: 0.22609774768352509 2023-01-23 06:38:20.016135: step: 1634/1545, loss: 0.8048348426818848 2023-01-23 06:38:20.915855: step: 1636/1545, loss: 0.7787859439849854 2023-01-23 06:38:21.837212: step: 1638/1545, loss: 0.747477114200592 2023-01-23 06:38:22.772627: step: 1640/1545, loss: 1.5504162311553955 2023-01-23 06:38:23.658074: step: 1642/1545, loss: 0.6814461946487427 2023-01-23 06:38:24.530355: step: 1644/1545, loss: 0.45938003063201904 2023-01-23 06:38:25.411362: step: 1646/1545, loss: 0.31261539459228516 2023-01-23 06:38:26.300810: step: 1648/1545, loss: 0.9922192692756653 2023-01-23 06:38:27.162558: step: 1650/1545, loss: 0.7047970294952393 2023-01-23 06:38:28.089591: step: 1652/1545, loss: 1.3595550060272217 2023-01-23 06:38:29.023890: step: 1654/1545, loss: 2.018404960632324 2023-01-23 06:38:29.915280: step: 1656/1545, loss: 0.44466885924339294 2023-01-23 06:38:30.824990: step: 1658/1545, loss: 0.40832000970840454 2023-01-23 06:38:31.700098: step: 1660/1545, loss: 0.49379074573516846 2023-01-23 06:38:32.528003: step: 1662/1545, loss: 0.41548100113868713 2023-01-23 06:38:33.378376: step: 1664/1545, loss: 0.5161266326904297 2023-01-23 06:38:34.259235: step: 1666/1545, loss: 0.7948151230812073 2023-01-23 06:38:35.170018: step: 1668/1545, loss: 0.6228778958320618 2023-01-23 06:38:36.040460: step: 1670/1545, loss: 0.23619450628757477 2023-01-23 06:38:36.901267: step: 1672/1545, loss: 1.2732524871826172 2023-01-23 06:38:37.783169: step: 1674/1545, loss: 0.4616542458534241 2023-01-23 06:38:38.705334: step: 1676/1545, loss: 0.8475364446640015 2023-01-23 06:38:39.541437: step: 1678/1545, loss: 0.6262155175209045 2023-01-23 06:38:40.470037: step: 1680/1545, loss: 0.40322789549827576 2023-01-23 06:38:41.332700: step: 1682/1545, loss: 0.8147352337837219 2023-01-23 06:38:42.217996: step: 1684/1545, loss: 0.1194724515080452 2023-01-23 06:38:43.046453: step: 1686/1545, loss: 1.5150891542434692 2023-01-23 06:38:43.869005: step: 1688/1545, loss: 0.925473153591156 2023-01-23 06:38:44.761311: step: 1690/1545, loss: 0.4045504629611969 2023-01-23 06:38:45.628453: step: 1692/1545, loss: 0.23605619370937347 2023-01-23 06:38:46.505766: step: 1694/1545, loss: 1.9700489044189453 2023-01-23 06:38:47.372020: step: 1696/1545, loss: 0.4547181725502014 2023-01-23 06:38:48.241166: step: 1698/1545, loss: 0.49278002977371216 2023-01-23 06:38:49.132807: step: 1700/1545, loss: 0.7814158201217651 2023-01-23 06:38:50.002451: step: 1702/1545, loss: 0.7188379168510437 2023-01-23 06:38:50.904568: step: 1704/1545, loss: 0.25387507677078247 2023-01-23 06:38:51.790280: step: 1706/1545, loss: 1.471229076385498 2023-01-23 06:38:52.697389: step: 1708/1545, loss: 0.6907533407211304 2023-01-23 06:38:53.602128: step: 1710/1545, loss: 0.4020799398422241 2023-01-23 06:38:54.539800: step: 1712/1545, loss: 0.6967505812644958 2023-01-23 06:38:55.428888: step: 1714/1545, loss: 0.5953666567802429 2023-01-23 06:38:56.288852: step: 1716/1545, loss: 1.0392327308654785 2023-01-23 06:38:57.193990: step: 1718/1545, loss: 1.0031547546386719 2023-01-23 06:38:58.067852: step: 1720/1545, loss: 0.7445579171180725 2023-01-23 06:38:58.979145: step: 1722/1545, loss: 0.8738583922386169 2023-01-23 06:38:59.879654: step: 1724/1545, loss: 0.6895627975463867 2023-01-23 06:39:00.797027: step: 1726/1545, loss: 0.7366570830345154 2023-01-23 06:39:01.668706: step: 1728/1545, loss: 0.6488150954246521 2023-01-23 06:39:02.553307: step: 1730/1545, loss: 0.6455932855606079 2023-01-23 06:39:03.463112: step: 1732/1545, loss: 0.9449650049209595 2023-01-23 06:39:04.397529: step: 1734/1545, loss: 0.6878739595413208 2023-01-23 06:39:05.287797: step: 1736/1545, loss: 0.49266573786735535 2023-01-23 06:39:06.256506: step: 1738/1545, loss: 0.6016219258308411 2023-01-23 06:39:07.128547: step: 1740/1545, loss: 0.7180655002593994 2023-01-23 06:39:08.023029: step: 1742/1545, loss: 0.5938626527786255 2023-01-23 06:39:08.969786: step: 1744/1545, loss: 0.7107702493667603 2023-01-23 06:39:09.869195: step: 1746/1545, loss: 0.4686730206012726 2023-01-23 06:39:10.890669: step: 1748/1545, loss: 0.9830465316772461 2023-01-23 06:39:11.761561: step: 1750/1545, loss: 0.5696598887443542 2023-01-23 06:39:12.609996: step: 1752/1545, loss: 1.3603507280349731 2023-01-23 06:39:13.498137: step: 1754/1545, loss: 0.6687204837799072 2023-01-23 06:39:14.382666: step: 1756/1545, loss: 0.6035076975822449 2023-01-23 06:39:15.279875: step: 1758/1545, loss: 0.3502070903778076 2023-01-23 06:39:16.194177: step: 1760/1545, loss: 0.7769081592559814 2023-01-23 06:39:17.117599: step: 1762/1545, loss: 1.2659728527069092 2023-01-23 06:39:17.962229: step: 1764/1545, loss: 0.38676705956459045 2023-01-23 06:39:18.875361: step: 1766/1545, loss: 0.6725775003433228 2023-01-23 06:39:19.828873: step: 1768/1545, loss: 3.0968430042266846 2023-01-23 06:39:20.724888: step: 1770/1545, loss: 1.8170963525772095 2023-01-23 06:39:21.612195: step: 1772/1545, loss: 0.7425113916397095 2023-01-23 06:39:22.541843: step: 1774/1545, loss: 0.6664076447486877 2023-01-23 06:39:23.401568: step: 1776/1545, loss: 0.42983973026275635 2023-01-23 06:39:24.319535: step: 1778/1545, loss: 0.3868533968925476 2023-01-23 06:39:25.190011: step: 1780/1545, loss: 4.028554439544678 2023-01-23 06:39:26.034366: step: 1782/1545, loss: 0.16620208323001862 2023-01-23 06:39:26.943258: step: 1784/1545, loss: 1.1033718585968018 2023-01-23 06:39:27.877115: step: 1786/1545, loss: 0.6276470422744751 2023-01-23 06:39:28.737511: step: 1788/1545, loss: 0.9188356399536133 2023-01-23 06:39:29.628355: step: 1790/1545, loss: 0.6218307018280029 2023-01-23 06:39:30.515568: step: 1792/1545, loss: 0.6326479911804199 2023-01-23 06:39:31.397233: step: 1794/1545, loss: 0.5505648255348206 2023-01-23 06:39:32.242777: step: 1796/1545, loss: 0.8341614603996277 2023-01-23 06:39:33.091034: step: 1798/1545, loss: 0.4035501778125763 2023-01-23 06:39:33.964478: step: 1800/1545, loss: 0.6049641370773315 2023-01-23 06:39:34.864042: step: 1802/1545, loss: 0.6383153796195984 2023-01-23 06:39:35.742503: step: 1804/1545, loss: 0.4053420126438141 2023-01-23 06:39:36.607894: step: 1806/1545, loss: 0.5042244791984558 2023-01-23 06:39:37.504954: step: 1808/1545, loss: 1.817773461341858 2023-01-23 06:39:38.387673: step: 1810/1545, loss: 0.32716888189315796 2023-01-23 06:39:39.263657: step: 1812/1545, loss: 0.9055688977241516 2023-01-23 06:39:40.169862: step: 1814/1545, loss: 0.33775386214256287 2023-01-23 06:39:41.096569: step: 1816/1545, loss: 7.581445693969727 2023-01-23 06:39:41.961169: step: 1818/1545, loss: 0.9056195616722107 2023-01-23 06:39:42.837431: step: 1820/1545, loss: 0.7800469994544983 2023-01-23 06:39:43.728924: step: 1822/1545, loss: 3.5154240131378174 2023-01-23 06:39:44.615262: step: 1824/1545, loss: 0.7041589021682739 2023-01-23 06:39:45.483554: step: 1826/1545, loss: 0.7501626014709473 2023-01-23 06:39:46.342312: step: 1828/1545, loss: 0.704445481300354 2023-01-23 06:39:47.216007: step: 1830/1545, loss: 0.5983424782752991 2023-01-23 06:39:48.061232: step: 1832/1545, loss: 1.377928376197815 2023-01-23 06:39:48.905724: step: 1834/1545, loss: 0.9994732141494751 2023-01-23 06:39:49.752299: step: 1836/1545, loss: 0.34000295400619507 2023-01-23 06:39:50.634843: step: 1838/1545, loss: 0.41600045561790466 2023-01-23 06:39:51.472736: step: 1840/1545, loss: 0.5520830154418945 2023-01-23 06:39:52.416087: step: 1842/1545, loss: 0.6646279096603394 2023-01-23 06:39:53.309586: step: 1844/1545, loss: 0.4629107713699341 2023-01-23 06:39:54.161569: step: 1846/1545, loss: 0.6206154823303223 2023-01-23 06:39:55.039035: step: 1848/1545, loss: 0.27534666657447815 2023-01-23 06:39:55.947205: step: 1850/1545, loss: 0.5777553915977478 2023-01-23 06:39:56.866193: step: 1852/1545, loss: 1.3073034286499023 2023-01-23 06:39:57.748814: step: 1854/1545, loss: 1.2785568237304688 2023-01-23 06:39:58.617382: step: 1856/1545, loss: 1.8887896537780762 2023-01-23 06:39:59.503872: step: 1858/1545, loss: 0.42706331610679626 2023-01-23 06:40:00.389497: step: 1860/1545, loss: 0.8150723576545715 2023-01-23 06:40:01.260861: step: 1862/1545, loss: 0.35354936122894287 2023-01-23 06:40:02.156079: step: 1864/1545, loss: 0.7217667102813721 2023-01-23 06:40:03.040642: step: 1866/1545, loss: 0.29927772283554077 2023-01-23 06:40:03.910648: step: 1868/1545, loss: 0.6707549095153809 2023-01-23 06:40:04.824351: step: 1870/1545, loss: 0.8829177021980286 2023-01-23 06:40:05.680932: step: 1872/1545, loss: 1.5073456764221191 2023-01-23 06:40:06.589932: step: 1874/1545, loss: 0.9351788759231567 2023-01-23 06:40:07.493853: step: 1876/1545, loss: 0.8524561524391174 2023-01-23 06:40:08.304233: step: 1878/1545, loss: 0.47706499695777893 2023-01-23 06:40:09.177007: step: 1880/1545, loss: 0.7854053974151611 2023-01-23 06:40:10.024723: step: 1882/1545, loss: 0.8171612024307251 2023-01-23 06:40:10.925255: step: 1884/1545, loss: 0.691372275352478 2023-01-23 06:40:11.819003: step: 1886/1545, loss: 3.003561496734619 2023-01-23 06:40:12.676085: step: 1888/1545, loss: 0.9691040515899658 2023-01-23 06:40:13.541229: step: 1890/1545, loss: 0.7498630285263062 2023-01-23 06:40:14.441979: step: 1892/1545, loss: 2.1708343029022217 2023-01-23 06:40:15.313322: step: 1894/1545, loss: 0.6840937733650208 2023-01-23 06:40:16.141446: step: 1896/1545, loss: 0.7404078841209412 2023-01-23 06:40:16.994352: step: 1898/1545, loss: 0.3472096920013428 2023-01-23 06:40:17.846095: step: 1900/1545, loss: 1.0708606243133545 2023-01-23 06:40:18.730949: step: 1902/1545, loss: 0.7891952991485596 2023-01-23 06:40:19.598777: step: 1904/1545, loss: 0.7310138940811157 2023-01-23 06:40:20.451015: step: 1906/1545, loss: 0.7924895882606506 2023-01-23 06:40:21.358665: step: 1908/1545, loss: 0.9090575575828552 2023-01-23 06:40:22.228064: step: 1910/1545, loss: 0.5822734832763672 2023-01-23 06:40:23.156163: step: 1912/1545, loss: 0.7590585947036743 2023-01-23 06:40:24.065151: step: 1914/1545, loss: 0.7892448306083679 2023-01-23 06:40:24.988642: step: 1916/1545, loss: 3.35502028465271 2023-01-23 06:40:25.838214: step: 1918/1545, loss: 0.9151750802993774 2023-01-23 06:40:26.724203: step: 1920/1545, loss: 2.083620071411133 2023-01-23 06:40:27.627268: step: 1922/1545, loss: 0.5755285024642944 2023-01-23 06:40:28.512702: step: 1924/1545, loss: 0.8101328611373901 2023-01-23 06:40:29.366259: step: 1926/1545, loss: 0.8663620948791504 2023-01-23 06:40:30.240174: step: 1928/1545, loss: 0.3430624008178711 2023-01-23 06:40:31.119303: step: 1930/1545, loss: 0.6669445037841797 2023-01-23 06:40:32.025801: step: 1932/1545, loss: 1.467298150062561 2023-01-23 06:40:32.862188: step: 1934/1545, loss: 0.7403351664543152 2023-01-23 06:40:33.732228: step: 1936/1545, loss: 0.8723815679550171 2023-01-23 06:40:34.629304: step: 1938/1545, loss: 1.3592066764831543 2023-01-23 06:40:35.512533: step: 1940/1545, loss: 1.2040661573410034 2023-01-23 06:40:36.361650: step: 1942/1545, loss: 0.5832449197769165 2023-01-23 06:40:37.194791: step: 1944/1545, loss: 0.8226637244224548 2023-01-23 06:40:38.028218: step: 1946/1545, loss: 0.4056723415851593 2023-01-23 06:40:38.952611: step: 1948/1545, loss: 1.0871762037277222 2023-01-23 06:40:39.878181: step: 1950/1545, loss: 0.6490030884742737 2023-01-23 06:40:40.733503: step: 1952/1545, loss: 0.43270426988601685 2023-01-23 06:40:41.602386: step: 1954/1545, loss: 0.9541547894477844 2023-01-23 06:40:42.452232: step: 1956/1545, loss: 0.5445816516876221 2023-01-23 06:40:43.294721: step: 1958/1545, loss: 0.38528138399124146 2023-01-23 06:40:44.123705: step: 1960/1545, loss: 0.8157950043678284 2023-01-23 06:40:45.034720: step: 1962/1545, loss: 0.4071025550365448 2023-01-23 06:40:45.918226: step: 1964/1545, loss: 2.0935349464416504 2023-01-23 06:40:46.785795: step: 1966/1545, loss: 0.6834383606910706 2023-01-23 06:40:47.638735: step: 1968/1545, loss: 0.42657366394996643 2023-01-23 06:40:48.462236: step: 1970/1545, loss: 0.43421775102615356 2023-01-23 06:40:49.345957: step: 1972/1545, loss: 1.168701171875 2023-01-23 06:40:50.208045: step: 1974/1545, loss: 1.0757648944854736 2023-01-23 06:40:51.063607: step: 1976/1545, loss: 0.4814697504043579 2023-01-23 06:40:51.901717: step: 1978/1545, loss: 0.74751877784729 2023-01-23 06:40:52.714427: step: 1980/1545, loss: 1.1064125299453735 2023-01-23 06:40:53.602364: step: 1982/1545, loss: 0.5893270373344421 2023-01-23 06:40:54.477285: step: 1984/1545, loss: 0.5397899746894836 2023-01-23 06:40:55.344617: step: 1986/1545, loss: 3.403158664703369 2023-01-23 06:40:56.205817: step: 1988/1545, loss: 0.4570658504962921 2023-01-23 06:40:57.056037: step: 1990/1545, loss: 0.6406636238098145 2023-01-23 06:40:57.911493: step: 1992/1545, loss: 0.8931028246879578 2023-01-23 06:40:58.792669: step: 1994/1545, loss: 0.6058233380317688 2023-01-23 06:40:59.704442: step: 1996/1545, loss: 0.2918055057525635 2023-01-23 06:41:00.588162: step: 1998/1545, loss: 1.0453393459320068 2023-01-23 06:41:01.429231: step: 2000/1545, loss: 0.5826637148857117 2023-01-23 06:41:02.291358: step: 2002/1545, loss: 0.25875699520111084 2023-01-23 06:41:03.181011: step: 2004/1545, loss: 0.4419656991958618 2023-01-23 06:41:04.055491: step: 2006/1545, loss: 0.38605260848999023 2023-01-23 06:41:04.955802: step: 2008/1545, loss: 0.985861599445343 2023-01-23 06:41:05.820518: step: 2010/1545, loss: 0.9671735763549805 2023-01-23 06:41:06.694628: step: 2012/1545, loss: 1.4412002563476562 2023-01-23 06:41:07.575295: step: 2014/1545, loss: 1.467706561088562 2023-01-23 06:41:08.539673: step: 2016/1545, loss: 2.495988130569458 2023-01-23 06:41:09.437838: step: 2018/1545, loss: 2.1610984802246094 2023-01-23 06:41:10.317523: step: 2020/1545, loss: 0.44587093591690063 2023-01-23 06:41:11.200611: step: 2022/1545, loss: 0.8601323366165161 2023-01-23 06:41:12.066828: step: 2024/1545, loss: 2.9200847148895264 2023-01-23 06:41:12.950954: step: 2026/1545, loss: 0.9752967357635498 2023-01-23 06:41:13.823349: step: 2028/1545, loss: 1.0524927377700806 2023-01-23 06:41:14.706577: step: 2030/1545, loss: 0.56965172290802 2023-01-23 06:41:15.609547: step: 2032/1545, loss: 0.666322648525238 2023-01-23 06:41:16.451535: step: 2034/1545, loss: 0.3242398500442505 2023-01-23 06:41:17.322061: step: 2036/1545, loss: 0.9806121587753296 2023-01-23 06:41:18.167723: step: 2038/1545, loss: 0.24932920932769775 2023-01-23 06:41:19.059525: step: 2040/1545, loss: 0.987173318862915 2023-01-23 06:41:19.933819: step: 2042/1545, loss: 0.5054224133491516 2023-01-23 06:41:20.864496: step: 2044/1545, loss: 0.9503864049911499 2023-01-23 06:41:21.699499: step: 2046/1545, loss: 0.7315289378166199 2023-01-23 06:41:22.583258: step: 2048/1545, loss: 0.9231951832771301 2023-01-23 06:41:23.451771: step: 2050/1545, loss: 0.46814656257629395 2023-01-23 06:41:24.324262: step: 2052/1545, loss: 1.5328925848007202 2023-01-23 06:41:25.228568: step: 2054/1545, loss: 0.37624916434288025 2023-01-23 06:41:26.121325: step: 2056/1545, loss: 0.946917712688446 2023-01-23 06:41:27.002392: step: 2058/1545, loss: 0.5183879733085632 2023-01-23 06:41:27.842717: step: 2060/1545, loss: 0.47152218222618103 2023-01-23 06:41:28.708009: step: 2062/1545, loss: 0.3723420798778534 2023-01-23 06:41:29.576380: step: 2064/1545, loss: 0.35117095708847046 2023-01-23 06:41:30.438763: step: 2066/1545, loss: 0.8869153261184692 2023-01-23 06:41:31.334687: step: 2068/1545, loss: 3.0523934364318848 2023-01-23 06:41:32.233279: step: 2070/1545, loss: 0.2885616421699524 2023-01-23 06:41:33.089073: step: 2072/1545, loss: 7.291131019592285 2023-01-23 06:41:34.005384: step: 2074/1545, loss: 0.818493127822876 2023-01-23 06:41:34.832456: step: 2076/1545, loss: 1.1533057689666748 2023-01-23 06:41:35.693627: step: 2078/1545, loss: 0.37715500593185425 2023-01-23 06:41:36.559202: step: 2080/1545, loss: 2.3474345207214355 2023-01-23 06:41:37.439924: step: 2082/1545, loss: 0.5097461938858032 2023-01-23 06:41:38.393106: step: 2084/1545, loss: 0.8601007461547852 2023-01-23 06:41:39.249828: step: 2086/1545, loss: 0.5043876767158508 2023-01-23 06:41:40.141579: step: 2088/1545, loss: 0.6868459582328796 2023-01-23 06:41:41.012943: step: 2090/1545, loss: 0.7195110321044922 2023-01-23 06:41:41.895961: step: 2092/1545, loss: 0.3625566363334656 2023-01-23 06:41:42.770354: step: 2094/1545, loss: 0.6784547567367554 2023-01-23 06:41:43.654588: step: 2096/1545, loss: 0.5212097764015198 2023-01-23 06:41:44.499629: step: 2098/1545, loss: 2.645078659057617 2023-01-23 06:41:45.401761: step: 2100/1545, loss: 0.556215763092041 2023-01-23 06:41:46.254987: step: 2102/1545, loss: 0.6836684942245483 2023-01-23 06:41:47.142237: step: 2104/1545, loss: 0.9945170283317566 2023-01-23 06:41:48.021876: step: 2106/1545, loss: 0.3282667100429535 2023-01-23 06:41:48.883444: step: 2108/1545, loss: 6.614832878112793 2023-01-23 06:41:49.725010: step: 2110/1545, loss: 1.3438090085983276 2023-01-23 06:41:50.681714: step: 2112/1545, loss: 1.743804931640625 2023-01-23 06:41:51.619877: step: 2114/1545, loss: 1.0835151672363281 2023-01-23 06:41:52.483953: step: 2116/1545, loss: 0.9968510866165161 2023-01-23 06:41:53.352734: step: 2118/1545, loss: 0.813235878944397 2023-01-23 06:41:54.276922: step: 2120/1545, loss: 2.0446927547454834 2023-01-23 06:41:55.168938: step: 2122/1545, loss: 0.4392942190170288 2023-01-23 06:41:56.053266: step: 2124/1545, loss: 1.0039944648742676 2023-01-23 06:41:56.904985: step: 2126/1545, loss: 0.5574544072151184 2023-01-23 06:41:57.790008: step: 2128/1545, loss: 1.7554742097854614 2023-01-23 06:41:58.660675: step: 2130/1545, loss: 0.9297273755073547 2023-01-23 06:41:59.532423: step: 2132/1545, loss: 0.5128101706504822 2023-01-23 06:42:00.446909: step: 2134/1545, loss: 0.6111211180686951 2023-01-23 06:42:01.305141: step: 2136/1545, loss: 0.9508414268493652 2023-01-23 06:42:02.172814: step: 2138/1545, loss: 0.40520644187927246 2023-01-23 06:42:03.053926: step: 2140/1545, loss: 1.0617377758026123 2023-01-23 06:42:03.935337: step: 2142/1545, loss: 0.7658462524414062 2023-01-23 06:42:04.786037: step: 2144/1545, loss: 0.7636556625366211 2023-01-23 06:42:05.610661: step: 2146/1545, loss: 0.36061742901802063 2023-01-23 06:42:06.525920: step: 2148/1545, loss: 0.8910658359527588 2023-01-23 06:42:07.377082: step: 2150/1545, loss: 1.8062652349472046 2023-01-23 06:42:08.246443: step: 2152/1545, loss: 0.6767816543579102 2023-01-23 06:42:09.224489: step: 2154/1545, loss: 1.1276739835739136 2023-01-23 06:42:10.106623: step: 2156/1545, loss: 0.9996477365493774 2023-01-23 06:42:10.966166: step: 2158/1545, loss: 0.8150196075439453 2023-01-23 06:42:11.840174: step: 2160/1545, loss: 0.9777321815490723 2023-01-23 06:42:12.695751: step: 2162/1545, loss: 0.5772659778594971 2023-01-23 06:42:13.534566: step: 2164/1545, loss: 1.0754822492599487 2023-01-23 06:42:14.388144: step: 2166/1545, loss: 0.9387607574462891 2023-01-23 06:42:15.258137: step: 2168/1545, loss: 0.5119339227676392 2023-01-23 06:42:16.170314: step: 2170/1545, loss: 0.6469589471817017 2023-01-23 06:42:17.079507: step: 2172/1545, loss: 0.5020946860313416 2023-01-23 06:42:17.959207: step: 2174/1545, loss: 0.9025045037269592 2023-01-23 06:42:18.865295: step: 2176/1545, loss: 0.3230557441711426 2023-01-23 06:42:19.787910: step: 2178/1545, loss: 0.4893551766872406 2023-01-23 06:42:20.739884: step: 2180/1545, loss: 2.155906915664673 2023-01-23 06:42:21.635996: step: 2182/1545, loss: 0.610925018787384 2023-01-23 06:42:22.611913: step: 2184/1545, loss: 3.246824264526367 2023-01-23 06:42:23.497334: step: 2186/1545, loss: 1.5730371475219727 2023-01-23 06:42:24.359033: step: 2188/1545, loss: 1.0371339321136475 2023-01-23 06:42:25.254359: step: 2190/1545, loss: 2.95932936668396 2023-01-23 06:42:26.150650: step: 2192/1545, loss: 4.114962100982666 2023-01-23 06:42:27.071036: step: 2194/1545, loss: 0.6160654425621033 2023-01-23 06:42:27.976837: step: 2196/1545, loss: 0.935553252696991 2023-01-23 06:42:28.845736: step: 2198/1545, loss: 1.3440614938735962 2023-01-23 06:42:29.711015: step: 2200/1545, loss: 0.644202709197998 2023-01-23 06:42:30.599914: step: 2202/1545, loss: 0.5015627145767212 2023-01-23 06:42:31.479600: step: 2204/1545, loss: 1.2731608152389526 2023-01-23 06:42:32.356164: step: 2206/1545, loss: 1.231396198272705 2023-01-23 06:42:33.239808: step: 2208/1545, loss: 0.7324413061141968 2023-01-23 06:42:34.090253: step: 2210/1545, loss: 1.0112379789352417 2023-01-23 06:42:35.011798: step: 2212/1545, loss: 1.3219811916351318 2023-01-23 06:42:35.861695: step: 2214/1545, loss: 0.3249415457248688 2023-01-23 06:42:36.700822: step: 2216/1545, loss: 0.6994938254356384 2023-01-23 06:42:37.670098: step: 2218/1545, loss: 1.180130124092102 2023-01-23 06:42:38.528094: step: 2220/1545, loss: 0.9678968191146851 2023-01-23 06:42:39.362698: step: 2222/1545, loss: 0.2909242510795593 2023-01-23 06:42:40.243016: step: 2224/1545, loss: 0.7572341561317444 2023-01-23 06:42:41.086396: step: 2226/1545, loss: 0.5018633008003235 2023-01-23 06:42:41.997540: step: 2228/1545, loss: 1.092093825340271 2023-01-23 06:42:42.819475: step: 2230/1545, loss: 1.0221917629241943 2023-01-23 06:42:43.705243: step: 2232/1545, loss: 3.238783836364746 2023-01-23 06:42:44.597776: step: 2234/1545, loss: 0.699036717414856 2023-01-23 06:42:45.486349: step: 2236/1545, loss: 0.5285317897796631 2023-01-23 06:42:46.348159: step: 2238/1545, loss: 1.0539209842681885 2023-01-23 06:42:47.244820: step: 2240/1545, loss: 1.1996785402297974 2023-01-23 06:42:48.152786: step: 2242/1545, loss: 0.6141759753227234 2023-01-23 06:42:49.077419: step: 2244/1545, loss: 0.7633554339408875 2023-01-23 06:42:49.949915: step: 2246/1545, loss: 1.5834252834320068 2023-01-23 06:42:50.848468: step: 2248/1545, loss: 1.6408390998840332 2023-01-23 06:42:51.740196: step: 2250/1545, loss: 0.8778888583183289 2023-01-23 06:42:52.617594: step: 2252/1545, loss: 0.7819978594779968 2023-01-23 06:42:53.525426: step: 2254/1545, loss: 0.35252517461776733 2023-01-23 06:42:54.425739: step: 2256/1545, loss: 0.6935374736785889 2023-01-23 06:42:55.324019: step: 2258/1545, loss: 0.3578052222728729 2023-01-23 06:42:56.222202: step: 2260/1545, loss: 0.5222357511520386 2023-01-23 06:42:57.070510: step: 2262/1545, loss: 2.242016077041626 2023-01-23 06:42:57.946246: step: 2264/1545, loss: 0.3829460144042969 2023-01-23 06:42:58.767686: step: 2266/1545, loss: 0.6245324611663818 2023-01-23 06:42:59.683376: step: 2268/1545, loss: 0.47614172101020813 2023-01-23 06:43:00.569618: step: 2270/1545, loss: 0.5564340949058533 2023-01-23 06:43:01.418158: step: 2272/1545, loss: 1.0193122625350952 2023-01-23 06:43:02.262047: step: 2274/1545, loss: 0.968385636806488 2023-01-23 06:43:03.127769: step: 2276/1545, loss: 0.7960737943649292 2023-01-23 06:43:03.993550: step: 2278/1545, loss: 0.900382936000824 2023-01-23 06:43:04.908616: step: 2280/1545, loss: 0.9682382941246033 2023-01-23 06:43:05.793747: step: 2282/1545, loss: 1.0644490718841553 2023-01-23 06:43:06.827716: step: 2284/1545, loss: 0.31327638030052185 2023-01-23 06:43:07.725615: step: 2286/1545, loss: 0.658570408821106 2023-01-23 06:43:08.613271: step: 2288/1545, loss: 0.5690374374389648 2023-01-23 06:43:09.437178: step: 2290/1545, loss: 1.1822155714035034 2023-01-23 06:43:10.320823: step: 2292/1545, loss: 0.6384420394897461 2023-01-23 06:43:11.155831: step: 2294/1545, loss: 0.5007272958755493 2023-01-23 06:43:12.038329: step: 2296/1545, loss: 0.4468061327934265 2023-01-23 06:43:12.950439: step: 2298/1545, loss: 0.9585045576095581 2023-01-23 06:43:13.822045: step: 2300/1545, loss: 1.0242433547973633 2023-01-23 06:43:14.703247: step: 2302/1545, loss: 0.7552143931388855 2023-01-23 06:43:15.564864: step: 2304/1545, loss: 0.3968214988708496 2023-01-23 06:43:16.460089: step: 2306/1545, loss: 1.0875495672225952 2023-01-23 06:43:17.338161: step: 2308/1545, loss: 1.1228896379470825 2023-01-23 06:43:18.271124: step: 2310/1545, loss: 1.0494334697723389 2023-01-23 06:43:19.144072: step: 2312/1545, loss: 0.8063926696777344 2023-01-23 06:43:20.037653: step: 2314/1545, loss: 0.3358873724937439 2023-01-23 06:43:20.906067: step: 2316/1545, loss: 0.692255973815918 2023-01-23 06:43:21.747218: step: 2318/1545, loss: 0.5131352543830872 2023-01-23 06:43:22.618871: step: 2320/1545, loss: 0.6790043115615845 2023-01-23 06:43:23.515048: step: 2322/1545, loss: 0.6064445376396179 2023-01-23 06:43:24.434275: step: 2324/1545, loss: 0.8359370231628418 2023-01-23 06:43:25.280833: step: 2326/1545, loss: 0.8675090074539185 2023-01-23 06:43:26.164946: step: 2328/1545, loss: 1.2832109928131104 2023-01-23 06:43:27.034631: step: 2330/1545, loss: 0.7269479632377625 2023-01-23 06:43:27.948062: step: 2332/1545, loss: 0.4816049039363861 2023-01-23 06:43:28.848254: step: 2334/1545, loss: 0.7466965913772583 2023-01-23 06:43:29.722756: step: 2336/1545, loss: 0.7963277697563171 2023-01-23 06:43:30.676128: step: 2338/1545, loss: 0.6372954249382019 2023-01-23 06:43:31.550686: step: 2340/1545, loss: 1.088066816329956 2023-01-23 06:43:32.426730: step: 2342/1545, loss: 1.1616374254226685 2023-01-23 06:43:33.343564: step: 2344/1545, loss: 6.961299896240234 2023-01-23 06:43:34.224710: step: 2346/1545, loss: 0.4607347249984741 2023-01-23 06:43:35.093438: step: 2348/1545, loss: 0.9059371948242188 2023-01-23 06:43:35.954798: step: 2350/1545, loss: 0.4344549775123596 2023-01-23 06:43:36.806016: step: 2352/1545, loss: 1.033694863319397 2023-01-23 06:43:37.710592: step: 2354/1545, loss: 0.48412710428237915 2023-01-23 06:43:38.623907: step: 2356/1545, loss: 0.6968271136283875 2023-01-23 06:43:39.496817: step: 2358/1545, loss: 3.097055196762085 2023-01-23 06:43:40.365072: step: 2360/1545, loss: 0.9733448028564453 2023-01-23 06:43:41.209645: step: 2362/1545, loss: 2.7848665714263916 2023-01-23 06:43:42.098412: step: 2364/1545, loss: 1.1704233884811401 2023-01-23 06:43:42.986879: step: 2366/1545, loss: 1.0657399892807007 2023-01-23 06:43:43.875078: step: 2368/1545, loss: 0.5054136514663696 2023-01-23 06:43:44.728542: step: 2370/1545, loss: 1.0840595960617065 2023-01-23 06:43:45.613089: step: 2372/1545, loss: 0.45628973841667175 2023-01-23 06:43:46.495209: step: 2374/1545, loss: 0.5542339086532593 2023-01-23 06:43:47.352701: step: 2376/1545, loss: 0.5098366737365723 2023-01-23 06:43:48.215657: step: 2378/1545, loss: 0.9502481818199158 2023-01-23 06:43:49.113539: step: 2380/1545, loss: 0.7101659774780273 2023-01-23 06:43:50.009669: step: 2382/1545, loss: 0.21186020970344543 2023-01-23 06:43:50.855937: step: 2384/1545, loss: 0.551653265953064 2023-01-23 06:43:51.706001: step: 2386/1545, loss: 0.8017196655273438 2023-01-23 06:43:52.610571: step: 2388/1545, loss: 2.2707936763763428 2023-01-23 06:43:53.504138: step: 2390/1545, loss: 0.6659739017486572 2023-01-23 06:43:54.392749: step: 2392/1545, loss: 3.2799832820892334 2023-01-23 06:43:55.293957: step: 2394/1545, loss: 0.4977070987224579 2023-01-23 06:43:56.218113: step: 2396/1545, loss: 0.895016610622406 2023-01-23 06:43:57.069513: step: 2398/1545, loss: 0.6617626547813416 2023-01-23 06:43:57.933660: step: 2400/1545, loss: 0.5168131589889526 2023-01-23 06:43:58.839584: step: 2402/1545, loss: 0.6046427488327026 2023-01-23 06:43:59.691398: step: 2404/1545, loss: 0.5063260197639465 2023-01-23 06:44:00.578275: step: 2406/1545, loss: 0.695894718170166 2023-01-23 06:44:01.449528: step: 2408/1545, loss: 0.6823177933692932 2023-01-23 06:44:02.378731: step: 2410/1545, loss: 0.5918008685112 2023-01-23 06:44:03.275304: step: 2412/1545, loss: 0.450386106967926 2023-01-23 06:44:04.181126: step: 2414/1545, loss: 0.23879335820674896 2023-01-23 06:44:05.048429: step: 2416/1545, loss: 1.225411057472229 2023-01-23 06:44:05.954345: step: 2418/1545, loss: 1.442557454109192 2023-01-23 06:44:06.851000: step: 2420/1545, loss: 0.4767126739025116 2023-01-23 06:44:07.726620: step: 2422/1545, loss: 0.44148677587509155 2023-01-23 06:44:08.605940: step: 2424/1545, loss: 0.27587640285491943 2023-01-23 06:44:09.473472: step: 2426/1545, loss: 6.002376079559326 2023-01-23 06:44:10.337888: step: 2428/1545, loss: 1.1695802211761475 2023-01-23 06:44:11.194918: step: 2430/1545, loss: 1.1252174377441406 2023-01-23 06:44:12.098568: step: 2432/1545, loss: 3.6157426834106445 2023-01-23 06:44:12.993614: step: 2434/1545, loss: 0.9487878680229187 2023-01-23 06:44:13.881088: step: 2436/1545, loss: 1.0545786619186401 2023-01-23 06:44:14.762000: step: 2438/1545, loss: 0.5466817617416382 2023-01-23 06:44:15.603106: step: 2440/1545, loss: 2.3656129837036133 2023-01-23 06:44:16.491318: step: 2442/1545, loss: 1.484961986541748 2023-01-23 06:44:17.383246: step: 2444/1545, loss: 0.7989349961280823 2023-01-23 06:44:18.274457: step: 2446/1545, loss: 1.8967539072036743 2023-01-23 06:44:19.157360: step: 2448/1545, loss: 0.40178394317626953 2023-01-23 06:44:20.037918: step: 2450/1545, loss: 1.7138184309005737 2023-01-23 06:44:20.913153: step: 2452/1545, loss: 2.5834670066833496 2023-01-23 06:44:21.855352: step: 2454/1545, loss: 1.2809653282165527 2023-01-23 06:44:22.717405: step: 2456/1545, loss: 0.8423370718955994 2023-01-23 06:44:23.592919: step: 2458/1545, loss: 3.2310984134674072 2023-01-23 06:44:24.504914: step: 2460/1545, loss: 0.5873060822486877 2023-01-23 06:44:25.398144: step: 2462/1545, loss: 0.9158127903938293 2023-01-23 06:44:26.267076: step: 2464/1545, loss: 0.6905798316001892 2023-01-23 06:44:27.122253: step: 2466/1545, loss: 0.6063595414161682 2023-01-23 06:44:27.986400: step: 2468/1545, loss: 0.8330078125 2023-01-23 06:44:28.841353: step: 2470/1545, loss: 0.7895230054855347 2023-01-23 06:44:29.671749: step: 2472/1545, loss: 1.1279348134994507 2023-01-23 06:44:30.532265: step: 2474/1545, loss: 0.5362089276313782 2023-01-23 06:44:31.397128: step: 2476/1545, loss: 0.7588481903076172 2023-01-23 06:44:32.333344: step: 2478/1545, loss: 1.176496982574463 2023-01-23 06:44:33.268884: step: 2480/1545, loss: 0.9848339557647705 2023-01-23 06:44:34.130326: step: 2482/1545, loss: 0.851006031036377 2023-01-23 06:44:34.998582: step: 2484/1545, loss: 1.5898712873458862 2023-01-23 06:44:35.889059: step: 2486/1545, loss: 0.44548743963241577 2023-01-23 06:44:36.760326: step: 2488/1545, loss: 1.3350365161895752 2023-01-23 06:44:37.674660: step: 2490/1545, loss: 1.1655125617980957 2023-01-23 06:44:38.567790: step: 2492/1545, loss: 0.5983826518058777 2023-01-23 06:44:39.433388: step: 2494/1545, loss: 1.4575588703155518 2023-01-23 06:44:40.319106: step: 2496/1545, loss: 1.0826971530914307 2023-01-23 06:44:41.171746: step: 2498/1545, loss: 1.2339755296707153 2023-01-23 06:44:42.013873: step: 2500/1545, loss: 0.38173148036003113 2023-01-23 06:44:42.939638: step: 2502/1545, loss: 0.809851348400116 2023-01-23 06:44:43.827076: step: 2504/1545, loss: 0.9575706720352173 2023-01-23 06:44:44.705691: step: 2506/1545, loss: 0.34804272651672363 2023-01-23 06:44:45.617559: step: 2508/1545, loss: 0.5956403017044067 2023-01-23 06:44:46.535520: step: 2510/1545, loss: 0.5920643210411072 2023-01-23 06:44:47.424243: step: 2512/1545, loss: 0.6385155320167542 2023-01-23 06:44:48.288674: step: 2514/1545, loss: 1.0181814432144165 2023-01-23 06:44:49.152322: step: 2516/1545, loss: 2.5298993587493896 2023-01-23 06:44:50.044481: step: 2518/1545, loss: 0.2749670147895813 2023-01-23 06:44:50.908239: step: 2520/1545, loss: 0.4223915636539459 2023-01-23 06:44:51.791989: step: 2522/1545, loss: 0.45050206780433655 2023-01-23 06:44:52.644297: step: 2524/1545, loss: 0.5870482325553894 2023-01-23 06:44:53.558903: step: 2526/1545, loss: 1.0017207860946655 2023-01-23 06:44:54.425657: step: 2528/1545, loss: 1.5411003828048706 2023-01-23 06:44:55.281977: step: 2530/1545, loss: 1.015142560005188 2023-01-23 06:44:56.173978: step: 2532/1545, loss: 0.36967870593070984 2023-01-23 06:44:57.143382: step: 2534/1545, loss: 0.7437177300453186 2023-01-23 06:44:58.018909: step: 2536/1545, loss: 0.386662095785141 2023-01-23 06:44:58.869288: step: 2538/1545, loss: 0.5933478474617004 2023-01-23 06:44:59.769930: step: 2540/1545, loss: 1.983137845993042 2023-01-23 06:45:00.662398: step: 2542/1545, loss: 4.032649993896484 2023-01-23 06:45:01.539464: step: 2544/1545, loss: 1.5480663776397705 2023-01-23 06:45:02.365433: step: 2546/1545, loss: 1.875828504562378 2023-01-23 06:45:03.304388: step: 2548/1545, loss: 2.3728413581848145 2023-01-23 06:45:04.159181: step: 2550/1545, loss: 0.32542362809181213 2023-01-23 06:45:05.034575: step: 2552/1545, loss: 0.7044771909713745 2023-01-23 06:45:05.894790: step: 2554/1545, loss: 1.295711636543274 2023-01-23 06:45:06.780920: step: 2556/1545, loss: 0.4038443863391876 2023-01-23 06:45:07.633603: step: 2558/1545, loss: 0.2280384600162506 2023-01-23 06:45:08.516100: step: 2560/1545, loss: 1.5978565216064453 2023-01-23 06:45:09.380772: step: 2562/1545, loss: 0.9681299924850464 2023-01-23 06:45:10.217452: step: 2564/1545, loss: 0.8708966970443726 2023-01-23 06:45:11.088374: step: 2566/1545, loss: 0.9714062213897705 2023-01-23 06:45:11.939538: step: 2568/1545, loss: 0.46423378586769104 2023-01-23 06:45:12.812318: step: 2570/1545, loss: 0.6414473652839661 2023-01-23 06:45:13.639458: step: 2572/1545, loss: 0.8295812606811523 2023-01-23 06:45:14.515944: step: 2574/1545, loss: 0.33856186270713806 2023-01-23 06:45:15.449838: step: 2576/1545, loss: 1.369385004043579 2023-01-23 06:45:16.353075: step: 2578/1545, loss: 0.6931553483009338 2023-01-23 06:45:17.202516: step: 2580/1545, loss: 0.5348036885261536 2023-01-23 06:45:18.094762: step: 2582/1545, loss: 0.6752693057060242 2023-01-23 06:45:19.061314: step: 2584/1545, loss: 2.7618908882141113 2023-01-23 06:45:19.971224: step: 2586/1545, loss: 0.8040867447853088 2023-01-23 06:45:20.835823: step: 2588/1545, loss: 0.8782546520233154 2023-01-23 06:45:21.748586: step: 2590/1545, loss: 1.8902170658111572 2023-01-23 06:45:22.651883: step: 2592/1545, loss: 1.318054437637329 2023-01-23 06:45:23.503839: step: 2594/1545, loss: 1.1041996479034424 2023-01-23 06:45:24.385245: step: 2596/1545, loss: 1.1936427354812622 2023-01-23 06:45:25.244307: step: 2598/1545, loss: 1.1044175624847412 2023-01-23 06:45:26.112927: step: 2600/1545, loss: 0.9727383255958557 2023-01-23 06:45:26.975286: step: 2602/1545, loss: 0.6869530081748962 2023-01-23 06:45:27.886487: step: 2604/1545, loss: 0.727815568447113 2023-01-23 06:45:28.821082: step: 2606/1545, loss: 0.9508592486381531 2023-01-23 06:45:29.723887: step: 2608/1545, loss: 0.5604376196861267 2023-01-23 06:45:30.571383: step: 2610/1545, loss: 1.268626093864441 2023-01-23 06:45:31.453151: step: 2612/1545, loss: 1.2138910293579102 2023-01-23 06:45:32.349621: step: 2614/1545, loss: 0.42409420013427734 2023-01-23 06:45:33.207474: step: 2616/1545, loss: 0.3579034209251404 2023-01-23 06:45:34.135049: step: 2618/1545, loss: 0.3833290934562683 2023-01-23 06:45:35.021398: step: 2620/1545, loss: 0.5825059413909912 2023-01-23 06:45:35.901414: step: 2622/1545, loss: 6.855599403381348 2023-01-23 06:45:36.860142: step: 2624/1545, loss: 1.818720817565918 2023-01-23 06:45:37.717002: step: 2626/1545, loss: 0.8465240001678467 2023-01-23 06:45:38.595354: step: 2628/1545, loss: 0.9067847728729248 2023-01-23 06:45:39.456964: step: 2630/1545, loss: 0.7721933722496033 2023-01-23 06:45:40.343529: step: 2632/1545, loss: 0.881989598274231 2023-01-23 06:45:41.243477: step: 2634/1545, loss: 0.8648640513420105 2023-01-23 06:45:42.169892: step: 2636/1545, loss: 0.5654072761535645 2023-01-23 06:45:43.034595: step: 2638/1545, loss: 0.5010374784469604 2023-01-23 06:45:43.901350: step: 2640/1545, loss: 0.7602236866950989 2023-01-23 06:45:44.803469: step: 2642/1545, loss: 0.8747208714485168 2023-01-23 06:45:45.685274: step: 2644/1545, loss: 0.3830230236053467 2023-01-23 06:45:46.608347: step: 2646/1545, loss: 1.9737058877944946 2023-01-23 06:45:47.473174: step: 2648/1545, loss: 0.8541534543037415 2023-01-23 06:45:48.329149: step: 2650/1545, loss: 0.2941327393054962 2023-01-23 06:45:49.252411: step: 2652/1545, loss: 0.5871683359146118 2023-01-23 06:45:50.103488: step: 2654/1545, loss: 0.7310200333595276 2023-01-23 06:45:50.983623: step: 2656/1545, loss: 0.4980136752128601 2023-01-23 06:45:51.806347: step: 2658/1545, loss: 0.5183873772621155 2023-01-23 06:45:52.652584: step: 2660/1545, loss: 0.3519322872161865 2023-01-23 06:45:53.533756: step: 2662/1545, loss: 0.9960128664970398 2023-01-23 06:45:54.432264: step: 2664/1545, loss: 1.7630934715270996 2023-01-23 06:45:55.327637: step: 2666/1545, loss: 0.5089808106422424 2023-01-23 06:45:56.271729: step: 2668/1545, loss: 1.0931832790374756 2023-01-23 06:45:57.136254: step: 2670/1545, loss: 0.8289106488227844 2023-01-23 06:45:57.977370: step: 2672/1545, loss: 0.9383198022842407 2023-01-23 06:45:58.802612: step: 2674/1545, loss: 0.6683852076530457 2023-01-23 06:45:59.695045: step: 2676/1545, loss: 0.7785965204238892 2023-01-23 06:46:00.677526: step: 2678/1545, loss: 0.5188937187194824 2023-01-23 06:46:01.551562: step: 2680/1545, loss: 0.7745670080184937 2023-01-23 06:46:02.455792: step: 2682/1545, loss: 0.3886992335319519 2023-01-23 06:46:03.372077: step: 2684/1545, loss: 1.1455029249191284 2023-01-23 06:46:04.306379: step: 2686/1545, loss: 1.1385518312454224 2023-01-23 06:46:05.172613: step: 2688/1545, loss: 0.38354364037513733 2023-01-23 06:46:06.082180: step: 2690/1545, loss: 2.2929742336273193 2023-01-23 06:46:06.942389: step: 2692/1545, loss: 0.40240874886512756 2023-01-23 06:46:07.820868: step: 2694/1545, loss: 0.29530036449432373 2023-01-23 06:46:08.692478: step: 2696/1545, loss: 0.3672957718372345 2023-01-23 06:46:09.564927: step: 2698/1545, loss: 0.5635839700698853 2023-01-23 06:46:10.462122: step: 2700/1545, loss: 1.0125747919082642 2023-01-23 06:46:11.333436: step: 2702/1545, loss: 1.024226427078247 2023-01-23 06:46:12.251975: step: 2704/1545, loss: 0.35884034633636475 2023-01-23 06:46:13.111585: step: 2706/1545, loss: 1.5287106037139893 2023-01-23 06:46:14.025189: step: 2708/1545, loss: 0.6626287698745728 2023-01-23 06:46:14.954231: step: 2710/1545, loss: 0.767130434513092 2023-01-23 06:46:15.844319: step: 2712/1545, loss: 0.8142864108085632 2023-01-23 06:46:16.738669: step: 2714/1545, loss: 3.7430667877197266 2023-01-23 06:46:17.617675: step: 2716/1545, loss: 0.8735135197639465 2023-01-23 06:46:18.541419: step: 2718/1545, loss: 1.894659161567688 2023-01-23 06:46:19.463869: step: 2720/1545, loss: 0.7039130926132202 2023-01-23 06:46:20.353380: step: 2722/1545, loss: 0.6306461691856384 2023-01-23 06:46:21.287138: step: 2724/1545, loss: 0.7233990430831909 2023-01-23 06:46:22.167169: step: 2726/1545, loss: 0.5600360631942749 2023-01-23 06:46:23.053036: step: 2728/1545, loss: 0.5783894062042236 2023-01-23 06:46:23.934286: step: 2730/1545, loss: 0.6231798529624939 2023-01-23 06:46:24.813407: step: 2732/1545, loss: 0.9848540425300598 2023-01-23 06:46:25.731377: step: 2734/1545, loss: 2.0324978828430176 2023-01-23 06:46:26.581990: step: 2736/1545, loss: 0.36028286814689636 2023-01-23 06:46:27.474269: step: 2738/1545, loss: 1.2573145627975464 2023-01-23 06:46:28.385045: step: 2740/1545, loss: 0.6722250580787659 2023-01-23 06:46:29.247043: step: 2742/1545, loss: 0.583499550819397 2023-01-23 06:46:30.149841: step: 2744/1545, loss: 0.7949234247207642 2023-01-23 06:46:31.030618: step: 2746/1545, loss: 6.044120788574219 2023-01-23 06:46:31.930413: step: 2748/1545, loss: 0.35838109254837036 2023-01-23 06:46:32.785024: step: 2750/1545, loss: 0.4609668254852295 2023-01-23 06:46:33.650694: step: 2752/1545, loss: 1.9181509017944336 2023-01-23 06:46:34.562225: step: 2754/1545, loss: 4.579744338989258 2023-01-23 06:46:35.426506: step: 2756/1545, loss: 0.520826518535614 2023-01-23 06:46:36.310719: step: 2758/1545, loss: 0.8726540803909302 2023-01-23 06:46:37.221740: step: 2760/1545, loss: 6.386144161224365 2023-01-23 06:46:38.096605: step: 2762/1545, loss: 2.0024311542510986 2023-01-23 06:46:38.985603: step: 2764/1545, loss: 0.4980751574039459 2023-01-23 06:46:39.891608: step: 2766/1545, loss: 0.7043128609657288 2023-01-23 06:46:40.793901: step: 2768/1545, loss: 0.5288091897964478 2023-01-23 06:46:41.756226: step: 2770/1545, loss: 0.8021379709243774 2023-01-23 06:46:42.628197: step: 2772/1545, loss: 1.104690670967102 2023-01-23 06:46:43.489375: step: 2774/1545, loss: 0.7102335095405579 2023-01-23 06:46:44.348925: step: 2776/1545, loss: 0.5752816796302795 2023-01-23 06:46:45.222172: step: 2778/1545, loss: 0.6838282346725464 2023-01-23 06:46:46.099358: step: 2780/1545, loss: 0.46183544397354126 2023-01-23 06:46:47.024397: step: 2782/1545, loss: 0.36786842346191406 2023-01-23 06:46:47.903509: step: 2784/1545, loss: 0.861537516117096 2023-01-23 06:46:48.822446: step: 2786/1545, loss: 0.48243993520736694 2023-01-23 06:46:49.860311: step: 2788/1545, loss: 1.1755446195602417 2023-01-23 06:46:50.758561: step: 2790/1545, loss: 0.31925028562545776 2023-01-23 06:46:51.653592: step: 2792/1545, loss: 1.1608185768127441 2023-01-23 06:46:52.557146: step: 2794/1545, loss: 0.5687741637229919 2023-01-23 06:46:53.438694: step: 2796/1545, loss: 1.1450157165527344 2023-01-23 06:46:54.335518: step: 2798/1545, loss: 0.7426730394363403 2023-01-23 06:46:55.214298: step: 2800/1545, loss: 0.4111537039279938 2023-01-23 06:46:56.108375: step: 2802/1545, loss: 1.0491763353347778 2023-01-23 06:46:56.986846: step: 2804/1545, loss: 0.717638373374939 2023-01-23 06:46:57.927766: step: 2806/1545, loss: 0.8308647871017456 2023-01-23 06:46:58.820690: step: 2808/1545, loss: 1.382859468460083 2023-01-23 06:46:59.714228: step: 2810/1545, loss: 0.6454938650131226 2023-01-23 06:47:00.599179: step: 2812/1545, loss: 0.7502270340919495 2023-01-23 06:47:01.504396: step: 2814/1545, loss: 0.8899505138397217 2023-01-23 06:47:02.354903: step: 2816/1545, loss: 0.3485814929008484 2023-01-23 06:47:03.275444: step: 2818/1545, loss: 0.30883467197418213 2023-01-23 06:47:04.170839: step: 2820/1545, loss: 1.0799509286880493 2023-01-23 06:47:05.042531: step: 2822/1545, loss: 1.218664288520813 2023-01-23 06:47:05.908922: step: 2824/1545, loss: 0.8069949150085449 2023-01-23 06:47:06.788839: step: 2826/1545, loss: 3.0572965145111084 2023-01-23 06:47:07.667566: step: 2828/1545, loss: 1.0315996408462524 2023-01-23 06:47:08.568094: step: 2830/1545, loss: 2.158029317855835 2023-01-23 06:47:09.464570: step: 2832/1545, loss: 0.34961026906967163 2023-01-23 06:47:10.356434: step: 2834/1545, loss: 0.898147702217102 2023-01-23 06:47:11.249456: step: 2836/1545, loss: 0.7486512660980225 2023-01-23 06:47:12.145764: step: 2838/1545, loss: 1.3623428344726562 2023-01-23 06:47:13.046030: step: 2840/1545, loss: 0.8642460107803345 2023-01-23 06:47:13.891086: step: 2842/1545, loss: 3.1156792640686035 2023-01-23 06:47:14.780830: step: 2844/1545, loss: 3.1627440452575684 2023-01-23 06:47:15.670337: step: 2846/1545, loss: 2.546276569366455 2023-01-23 06:47:16.577918: step: 2848/1545, loss: 0.4786328971385956 2023-01-23 06:47:17.481434: step: 2850/1545, loss: 6.871494293212891 2023-01-23 06:47:18.358964: step: 2852/1545, loss: 0.7101919651031494 2023-01-23 06:47:19.248729: step: 2854/1545, loss: 0.49580687284469604 2023-01-23 06:47:20.142766: step: 2856/1545, loss: 0.764151930809021 2023-01-23 06:47:21.002865: step: 2858/1545, loss: 0.3614681661128998 2023-01-23 06:47:21.868175: step: 2860/1545, loss: 1.0594521760940552 2023-01-23 06:47:22.744260: step: 2862/1545, loss: 0.724796712398529 2023-01-23 06:47:23.652859: step: 2864/1545, loss: 0.2792966365814209 2023-01-23 06:47:24.535402: step: 2866/1545, loss: 0.37987667322158813 2023-01-23 06:47:25.419788: step: 2868/1545, loss: 0.5585179924964905 2023-01-23 06:47:26.313848: step: 2870/1545, loss: 1.298500418663025 2023-01-23 06:47:27.229905: step: 2872/1545, loss: 0.6086698174476624 2023-01-23 06:47:28.136773: step: 2874/1545, loss: 0.47135239839553833 2023-01-23 06:47:28.983823: step: 2876/1545, loss: 0.6166694164276123 2023-01-23 06:47:29.845645: step: 2878/1545, loss: 0.8420296311378479 2023-01-23 06:47:30.736835: step: 2880/1545, loss: 0.6138226389884949 2023-01-23 06:47:31.586329: step: 2882/1545, loss: 1.1518536806106567 2023-01-23 06:47:32.462451: step: 2884/1545, loss: 0.8058708906173706 2023-01-23 06:47:33.305900: step: 2886/1545, loss: 0.31866487860679626 2023-01-23 06:47:34.205288: step: 2888/1545, loss: 1.333570122718811 2023-01-23 06:47:35.106331: step: 2890/1545, loss: 0.4821382462978363 2023-01-23 06:47:35.962058: step: 2892/1545, loss: 0.5437027812004089 2023-01-23 06:47:36.916440: step: 2894/1545, loss: 0.9036655426025391 2023-01-23 06:47:37.873931: step: 2896/1545, loss: 1.1322174072265625 2023-01-23 06:47:38.778134: step: 2898/1545, loss: 0.9285292029380798 2023-01-23 06:47:39.698484: step: 2900/1545, loss: 2.096142530441284 2023-01-23 06:47:40.535255: step: 2902/1545, loss: 0.36743277311325073 2023-01-23 06:47:41.427203: step: 2904/1545, loss: 0.4453984200954437 2023-01-23 06:47:42.280468: step: 2906/1545, loss: 1.4107980728149414 2023-01-23 06:47:43.181988: step: 2908/1545, loss: 0.43976110219955444 2023-01-23 06:47:44.051341: step: 2910/1545, loss: 0.34138253331184387 2023-01-23 06:47:44.933626: step: 2912/1545, loss: 0.9359905123710632 2023-01-23 06:47:45.794796: step: 2914/1545, loss: 0.6326450109481812 2023-01-23 06:47:46.675370: step: 2916/1545, loss: 0.4865342676639557 2023-01-23 06:47:47.534104: step: 2918/1545, loss: 0.6229748129844666 2023-01-23 06:47:48.410152: step: 2920/1545, loss: 1.4428606033325195 2023-01-23 06:47:49.333196: step: 2922/1545, loss: 0.9876816868782043 2023-01-23 06:47:50.240761: step: 2924/1545, loss: 1.574539065361023 2023-01-23 06:47:51.130277: step: 2926/1545, loss: 0.2991692125797272 2023-01-23 06:47:52.014310: step: 2928/1545, loss: 1.0161879062652588 2023-01-23 06:47:52.903249: step: 2930/1545, loss: 0.8119407296180725 2023-01-23 06:47:53.791849: step: 2932/1545, loss: 0.7757352590560913 2023-01-23 06:47:54.705040: step: 2934/1545, loss: 0.44400277733802795 2023-01-23 06:47:55.571058: step: 2936/1545, loss: 0.47284144163131714 2023-01-23 06:47:56.518098: step: 2938/1545, loss: 8.313455581665039 2023-01-23 06:47:57.408090: step: 2940/1545, loss: 0.49725764989852905 2023-01-23 06:47:58.303351: step: 2942/1545, loss: 1.0250121355056763 2023-01-23 06:47:59.168727: step: 2944/1545, loss: 1.0996111631393433 2023-01-23 06:48:00.028086: step: 2946/1545, loss: 1.0813952684402466 2023-01-23 06:48:00.886240: step: 2948/1545, loss: 0.2951088845729828 2023-01-23 06:48:01.746397: step: 2950/1545, loss: 0.483755886554718 2023-01-23 06:48:02.796483: step: 2952/1545, loss: 0.8848114609718323 2023-01-23 06:48:03.686263: step: 2954/1545, loss: 0.6826122403144836 2023-01-23 06:48:04.583059: step: 2956/1545, loss: 0.29666203260421753 2023-01-23 06:48:05.532642: step: 2958/1545, loss: 0.6079160571098328 2023-01-23 06:48:06.391103: step: 2960/1545, loss: 0.7869312167167664 2023-01-23 06:48:07.293654: step: 2962/1545, loss: 1.2807772159576416 2023-01-23 06:48:08.219989: step: 2964/1545, loss: 1.1309764385223389 2023-01-23 06:48:09.102094: step: 2966/1545, loss: 0.49010419845581055 2023-01-23 06:48:09.986869: step: 2968/1545, loss: 0.9912394285202026 2023-01-23 06:48:10.863416: step: 2970/1545, loss: 0.7195227742195129 2023-01-23 06:48:11.736482: step: 2972/1545, loss: 1.0241172313690186 2023-01-23 06:48:12.621572: step: 2974/1545, loss: 0.8534413576126099 2023-01-23 06:48:13.500991: step: 2976/1545, loss: 0.5502020716667175 2023-01-23 06:48:14.376788: step: 2978/1545, loss: 0.8512901067733765 2023-01-23 06:48:15.275304: step: 2980/1545, loss: 0.8429717421531677 2023-01-23 06:48:16.180815: step: 2982/1545, loss: 0.8841388821601868 2023-01-23 06:48:17.039450: step: 2984/1545, loss: 0.6116099953651428 2023-01-23 06:48:17.919957: step: 2986/1545, loss: 0.5815504789352417 2023-01-23 06:48:18.821296: step: 2988/1545, loss: 0.7037491202354431 2023-01-23 06:48:19.823412: step: 2990/1545, loss: 2.7644009590148926 2023-01-23 06:48:20.688489: step: 2992/1545, loss: 1.456650733947754 2023-01-23 06:48:21.560873: step: 2994/1545, loss: 0.5447834134101868 2023-01-23 06:48:22.438943: step: 2996/1545, loss: 2.0911526679992676 2023-01-23 06:48:23.301974: step: 2998/1545, loss: 0.808972954750061 2023-01-23 06:48:24.207820: step: 3000/1545, loss: 0.7605047225952148 2023-01-23 06:48:25.115258: step: 3002/1545, loss: 0.6325650215148926 2023-01-23 06:48:26.021637: step: 3004/1545, loss: 0.711383581161499 2023-01-23 06:48:26.969556: step: 3006/1545, loss: 0.6161215901374817 2023-01-23 06:48:27.885809: step: 3008/1545, loss: 0.6687226295471191 2023-01-23 06:48:28.785858: step: 3010/1545, loss: 0.9028365612030029 2023-01-23 06:48:29.705985: step: 3012/1545, loss: 2.1847143173217773 2023-01-23 06:48:30.581661: step: 3014/1545, loss: 0.4931810796260834 2023-01-23 06:48:31.470482: step: 3016/1545, loss: 1.1123358011245728 2023-01-23 06:48:32.391231: step: 3018/1545, loss: 0.8080180883407593 2023-01-23 06:48:33.278162: step: 3020/1545, loss: 0.355218768119812 2023-01-23 06:48:34.126961: step: 3022/1545, loss: 0.8272327184677124 2023-01-23 06:48:35.007925: step: 3024/1545, loss: 0.5958314538002014 2023-01-23 06:48:35.890839: step: 3026/1545, loss: 0.8602036237716675 2023-01-23 06:48:36.822080: step: 3028/1545, loss: 2.2722551822662354 2023-01-23 06:48:37.706433: step: 3030/1545, loss: 0.25240689516067505 2023-01-23 06:48:38.584540: step: 3032/1545, loss: 0.32321661710739136 2023-01-23 06:48:39.453718: step: 3034/1545, loss: 0.3581610918045044 2023-01-23 06:48:40.318019: step: 3036/1545, loss: 3.108750343322754 2023-01-23 06:48:41.213634: step: 3038/1545, loss: 1.5707162618637085 2023-01-23 06:48:42.112400: step: 3040/1545, loss: 3.4579341411590576 2023-01-23 06:48:43.036509: step: 3042/1545, loss: 0.30254870653152466 2023-01-23 06:48:43.917306: step: 3044/1545, loss: 1.0232220888137817 2023-01-23 06:48:44.849925: step: 3046/1545, loss: 0.6339308023452759 2023-01-23 06:48:45.738134: step: 3048/1545, loss: 0.9873512387275696 2023-01-23 06:48:46.623320: step: 3050/1545, loss: 0.6937241554260254 2023-01-23 06:48:47.495800: step: 3052/1545, loss: 0.7635018229484558 2023-01-23 06:48:48.382962: step: 3054/1545, loss: 0.7329870462417603 2023-01-23 06:48:49.324447: step: 3056/1545, loss: 0.5566713213920593 2023-01-23 06:48:50.281595: step: 3058/1545, loss: 1.2565758228302002 2023-01-23 06:48:51.168286: step: 3060/1545, loss: 1.060754656791687 2023-01-23 06:48:52.049524: step: 3062/1545, loss: 0.6585805416107178 2023-01-23 06:48:52.937404: step: 3064/1545, loss: 0.503890335559845 2023-01-23 06:48:53.804271: step: 3066/1545, loss: 0.5272998213768005 2023-01-23 06:48:54.687382: step: 3068/1545, loss: 0.257194846868515 2023-01-23 06:48:55.606433: step: 3070/1545, loss: 1.1411409378051758 2023-01-23 06:48:56.477420: step: 3072/1545, loss: 0.7232611775398254 2023-01-23 06:48:57.321895: step: 3074/1545, loss: 0.7479471564292908 2023-01-23 06:48:58.201150: step: 3076/1545, loss: 0.22070740163326263 2023-01-23 06:48:59.086612: step: 3078/1545, loss: 0.49659717082977295 2023-01-23 06:49:00.013352: step: 3080/1545, loss: 0.6931501030921936 2023-01-23 06:49:00.868840: step: 3082/1545, loss: 0.6298823952674866 2023-01-23 06:49:01.791054: step: 3084/1545, loss: 1.4777681827545166 2023-01-23 06:49:02.666064: step: 3086/1545, loss: 1.1922955513000488 2023-01-23 06:49:03.520664: step: 3088/1545, loss: 0.37821701169013977 2023-01-23 06:49:04.401121: step: 3090/1545, loss: 6.213527679443359 ================================================== Loss: 1.047 -------------------- Dev Chinese: {'event': {'p': 0.604143947655398, 'r': 0.7376830892143809, 'f1': 0.6642685851318945}, 'argument': {'p': 0.6551612787541361, 'r': 0.6306417698187268, 'f1': 0.6426677379693508}, 'combined': 0.4269039890108158, 'epoch': 3} Test Chinese: {'event': {'p': 0.6435432230522946, 'r': 0.7710997442455243, 'f1': 0.7015706806282722}, 'argument': {'p': 0.7100295259176541, 'r': 0.7032621838864146, 'f1': 0.7066296526849514}, 'combined': 0.49575064638630095, 'epoch': 3} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6621925205794895, 'r': 0.6288590127817241, 'f1': 0.6450954497205971}, 'combined': 0.43161341200525233, 'epoch': 3} Test Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7041948357813179, 'r': 0.7012269648259177, 'f1': 0.7027077666329988}, 'combined': 0.48827407061933914, 'epoch': 3} Dev Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6951841648811345, 'r': 0.5687870439936555, 'f1': 0.625665748393021}, 'combined': 0.4360700670618026, 'epoch': 3} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6058186000046465, 'r': 0.3568520520575315, 'f1': 0.44914137586551384}, 'combined': 0.28366823738874564, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} New best chinese model... New best korean model... New best russian model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.604143947655398, 'r': 0.7376830892143809, 'f1': 0.6642685851318945}, 'argument': {'p': 0.6551612787541361, 'r': 0.6306417698187268, 'f1': 0.6426677379693508}, 'combined': 0.4269039890108158, 'epoch': 3} Test for Chinese: {'event': {'p': 0.6435432230522946, 'r': 0.7710997442455243, 'f1': 0.7015706806282722}, 'argument': {'p': 0.7100295259176541, 'r': 0.7032621838864146, 'f1': 0.7066296526849514}, 'combined': 0.49575064638630095, 'epoch': 3} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6951841648811345, 'r': 0.5687870439936555, 'f1': 0.625665748393021}, 'combined': 0.4360700670618026, 'epoch': 3} -------------------- Dev for Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6621925205794895, 'r': 0.6288590127817241, 'f1': 0.6450954497205971}, 'combined': 0.43161341200525233, 'epoch': 3} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7041948357813179, 'r': 0.7012269648259177, 'f1': 0.7027077666329988}, 'combined': 0.48827407061933914, 'epoch': 3} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6058186000046465, 'r': 0.3568520520575315, 'f1': 0.44914137586551384}, 'combined': 0.28366823738874564, 'epoch': 3} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 4 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 06:54:32.200741: step: 2/1545, loss: 0.2932772934436798 2023-01-23 06:54:33.044837: step: 4/1545, loss: 0.9855912923812866 2023-01-23 06:54:33.933051: step: 6/1545, loss: 1.3033429384231567 2023-01-23 06:54:34.815749: step: 8/1545, loss: 0.6016029119491577 2023-01-23 06:54:35.677331: step: 10/1545, loss: 0.3337879180908203 2023-01-23 06:54:36.553980: step: 12/1545, loss: 0.6573000550270081 2023-01-23 06:54:37.454206: step: 14/1545, loss: 6.14711856842041 2023-01-23 06:54:38.342745: step: 16/1545, loss: 0.7830049991607666 2023-01-23 06:54:39.252301: step: 18/1545, loss: 0.5409223437309265 2023-01-23 06:54:40.130724: step: 20/1545, loss: 0.5708777904510498 2023-01-23 06:54:40.987515: step: 22/1545, loss: 0.5166948437690735 2023-01-23 06:54:41.851863: step: 24/1545, loss: 0.6103779077529907 2023-01-23 06:54:42.691660: step: 26/1545, loss: 0.4572678208351135 2023-01-23 06:54:43.575388: step: 28/1545, loss: 0.4895382523536682 2023-01-23 06:54:44.450859: step: 30/1545, loss: 1.004988431930542 2023-01-23 06:54:45.303335: step: 32/1545, loss: 0.3930642306804657 2023-01-23 06:54:46.222274: step: 34/1545, loss: 0.2103937864303589 2023-01-23 06:54:47.119354: step: 36/1545, loss: 0.8106293678283691 2023-01-23 06:54:48.003349: step: 38/1545, loss: 0.5069474577903748 2023-01-23 06:54:48.845785: step: 40/1545, loss: 6.551005840301514 2023-01-23 06:54:49.751348: step: 42/1545, loss: 0.3671974241733551 2023-01-23 06:54:50.630231: step: 44/1545, loss: 0.48229652643203735 2023-01-23 06:54:51.519917: step: 46/1545, loss: 0.7100682258605957 2023-01-23 06:54:52.389935: step: 48/1545, loss: 0.5903062224388123 2023-01-23 06:54:53.284854: step: 50/1545, loss: 1.3944295644760132 2023-01-23 06:54:54.164159: step: 52/1545, loss: 0.5870274901390076 2023-01-23 06:54:55.068608: step: 54/1545, loss: 0.6184887886047363 2023-01-23 06:54:55.936296: step: 56/1545, loss: 1.3395980596542358 2023-01-23 06:54:56.806156: step: 58/1545, loss: 0.6352716684341431 2023-01-23 06:54:57.669736: step: 60/1545, loss: 0.5707845091819763 2023-01-23 06:54:58.568161: step: 62/1545, loss: 0.5376710295677185 2023-01-23 06:54:59.480165: step: 64/1545, loss: 0.4252484142780304 2023-01-23 06:55:00.390124: step: 66/1545, loss: 0.42870810627937317 2023-01-23 06:55:01.296774: step: 68/1545, loss: 0.7400371432304382 2023-01-23 06:55:02.198838: step: 70/1545, loss: 0.8037129640579224 2023-01-23 06:55:03.129438: step: 72/1545, loss: 2.790295124053955 2023-01-23 06:55:03.985128: step: 74/1545, loss: 0.5082063674926758 2023-01-23 06:55:04.849528: step: 76/1545, loss: 0.22980818152427673 2023-01-23 06:55:05.702688: step: 78/1545, loss: 0.9033201336860657 2023-01-23 06:55:06.580617: step: 80/1545, loss: 0.7441097497940063 2023-01-23 06:55:07.477161: step: 82/1545, loss: 0.4145011901855469 2023-01-23 06:55:08.368597: step: 84/1545, loss: 0.5237090587615967 2023-01-23 06:55:09.251451: step: 86/1545, loss: 0.7127460837364197 2023-01-23 06:55:10.149444: step: 88/1545, loss: 0.8054667711257935 2023-01-23 06:55:11.032267: step: 90/1545, loss: 0.33636438846588135 2023-01-23 06:55:11.906297: step: 92/1545, loss: 0.7993491291999817 2023-01-23 06:55:12.791818: step: 94/1545, loss: 0.4826851487159729 2023-01-23 06:55:13.709540: step: 96/1545, loss: 1.1625542640686035 2023-01-23 06:55:14.541165: step: 98/1545, loss: 0.7182455062866211 2023-01-23 06:55:15.410420: step: 100/1545, loss: 0.9749849438667297 2023-01-23 06:55:16.267723: step: 102/1545, loss: 0.7122009992599487 2023-01-23 06:55:17.159636: step: 104/1545, loss: 0.3450353443622589 2023-01-23 06:55:18.027244: step: 106/1545, loss: 0.6301352381706238 2023-01-23 06:55:18.868060: step: 108/1545, loss: 0.40428781509399414 2023-01-23 06:55:19.719628: step: 110/1545, loss: 0.7574556469917297 2023-01-23 06:55:20.589459: step: 112/1545, loss: 0.6108757257461548 2023-01-23 06:55:21.482967: step: 114/1545, loss: 0.6175575852394104 2023-01-23 06:55:22.340827: step: 116/1545, loss: 0.7835478186607361 2023-01-23 06:55:23.289244: step: 118/1545, loss: 0.6905444264411926 2023-01-23 06:55:24.172062: step: 120/1545, loss: 0.9193381071090698 2023-01-23 06:55:25.041480: step: 122/1545, loss: 0.6584562659263611 2023-01-23 06:55:25.922309: step: 124/1545, loss: 0.3987574577331543 2023-01-23 06:55:26.769500: step: 126/1545, loss: 2.782370090484619 2023-01-23 06:55:27.670106: step: 128/1545, loss: 0.35748806595802307 2023-01-23 06:55:28.555976: step: 130/1545, loss: 0.5669959783554077 2023-01-23 06:55:29.455117: step: 132/1545, loss: 0.45935583114624023 2023-01-23 06:55:30.326622: step: 134/1545, loss: 0.5065933465957642 2023-01-23 06:55:31.201687: step: 136/1545, loss: 0.8454428315162659 2023-01-23 06:55:32.053302: step: 138/1545, loss: 0.4855470657348633 2023-01-23 06:55:32.918725: step: 140/1545, loss: 2.8816323280334473 2023-01-23 06:55:33.916756: step: 142/1545, loss: 0.30379754304885864 2023-01-23 06:55:34.801919: step: 144/1545, loss: 0.4755384922027588 2023-01-23 06:55:35.645681: step: 146/1545, loss: 0.49500948190689087 2023-01-23 06:55:36.496126: step: 148/1545, loss: 0.7575356960296631 2023-01-23 06:55:37.380847: step: 150/1545, loss: 0.8510699272155762 2023-01-23 06:55:38.244495: step: 152/1545, loss: 8.531131744384766 2023-01-23 06:55:39.079482: step: 154/1545, loss: 0.9432578086853027 2023-01-23 06:55:39.947363: step: 156/1545, loss: 0.31003665924072266 2023-01-23 06:55:40.794904: step: 158/1545, loss: 0.31354326009750366 2023-01-23 06:55:41.649026: step: 160/1545, loss: 0.5629007816314697 2023-01-23 06:55:42.516577: step: 162/1545, loss: 0.46874526143074036 2023-01-23 06:55:43.409970: step: 164/1545, loss: 1.5200666189193726 2023-01-23 06:55:44.289815: step: 166/1545, loss: 0.5141246914863586 2023-01-23 06:55:45.165890: step: 168/1545, loss: 0.5369479656219482 2023-01-23 06:55:46.077404: step: 170/1545, loss: 0.2705128788948059 2023-01-23 06:55:46.969964: step: 172/1545, loss: 0.7405262589454651 2023-01-23 06:55:47.957076: step: 174/1545, loss: 0.4982093870639801 2023-01-23 06:55:48.833228: step: 176/1545, loss: 0.3754882216453552 2023-01-23 06:55:49.755365: step: 178/1545, loss: 0.30670851469039917 2023-01-23 06:55:50.655884: step: 180/1545, loss: 0.3317197859287262 2023-01-23 06:55:51.533469: step: 182/1545, loss: 0.47267505526542664 2023-01-23 06:55:52.387030: step: 184/1545, loss: 0.41685348749160767 2023-01-23 06:55:53.244620: step: 186/1545, loss: 0.25756582617759705 2023-01-23 06:55:54.127220: step: 188/1545, loss: 0.357103556394577 2023-01-23 06:55:55.039429: step: 190/1545, loss: 0.4128018319606781 2023-01-23 06:55:55.929262: step: 192/1545, loss: 1.4927581548690796 2023-01-23 06:55:56.793254: step: 194/1545, loss: 0.28007274866104126 2023-01-23 06:55:57.676917: step: 196/1545, loss: 0.9819271564483643 2023-01-23 06:55:58.551794: step: 198/1545, loss: 0.5920519828796387 2023-01-23 06:55:59.420239: step: 200/1545, loss: 0.5177531838417053 2023-01-23 06:56:00.354468: step: 202/1545, loss: 0.259873628616333 2023-01-23 06:56:01.224919: step: 204/1545, loss: 0.6055641174316406 2023-01-23 06:56:02.082318: step: 206/1545, loss: 0.8092571496963501 2023-01-23 06:56:02.951861: step: 208/1545, loss: 0.18791420757770538 2023-01-23 06:56:03.804739: step: 210/1545, loss: 0.854875922203064 2023-01-23 06:56:04.661811: step: 212/1545, loss: 0.7231153249740601 2023-01-23 06:56:05.711647: step: 214/1545, loss: 0.8572783470153809 2023-01-23 06:56:06.597472: step: 216/1545, loss: 1.0376176834106445 2023-01-23 06:56:07.471655: step: 218/1545, loss: 0.4278765022754669 2023-01-23 06:56:08.343442: step: 220/1545, loss: 0.5106942057609558 2023-01-23 06:56:09.214401: step: 222/1545, loss: 0.8480420112609863 2023-01-23 06:56:10.121528: step: 224/1545, loss: 0.7553911805152893 2023-01-23 06:56:11.020591: step: 226/1545, loss: 0.4293045997619629 2023-01-23 06:56:11.887665: step: 228/1545, loss: 0.5915791988372803 2023-01-23 06:56:12.742092: step: 230/1545, loss: 0.249301940202713 2023-01-23 06:56:13.601540: step: 232/1545, loss: 0.6224079132080078 2023-01-23 06:56:14.527975: step: 234/1545, loss: 1.0613007545471191 2023-01-23 06:56:15.475028: step: 236/1545, loss: 0.8540357351303101 2023-01-23 06:56:16.325989: step: 238/1545, loss: 0.43106311559677124 2023-01-23 06:56:17.232470: step: 240/1545, loss: 1.1982094049453735 2023-01-23 06:56:18.145698: step: 242/1545, loss: 7.436939716339111 2023-01-23 06:56:19.032340: step: 244/1545, loss: 0.2813226580619812 2023-01-23 06:56:19.912694: step: 246/1545, loss: 1.1131651401519775 2023-01-23 06:56:20.798992: step: 248/1545, loss: 0.49585989117622375 2023-01-23 06:56:21.715846: step: 250/1545, loss: 1.3624403476715088 2023-01-23 06:56:22.605307: step: 252/1545, loss: 0.7592456936836243 2023-01-23 06:56:23.515944: step: 254/1545, loss: 0.3806765675544739 2023-01-23 06:56:24.543694: step: 256/1545, loss: 0.2865067720413208 2023-01-23 06:56:25.436487: step: 258/1545, loss: 0.26537996530532837 2023-01-23 06:56:26.299556: step: 260/1545, loss: 0.9998347759246826 2023-01-23 06:56:27.177861: step: 262/1545, loss: 0.7651529908180237 2023-01-23 06:56:28.023363: step: 264/1545, loss: 7.031776428222656 2023-01-23 06:56:28.872537: step: 266/1545, loss: 1.4142115116119385 2023-01-23 06:56:29.712725: step: 268/1545, loss: 1.1767138242721558 2023-01-23 06:56:30.542117: step: 270/1545, loss: 0.5122210383415222 2023-01-23 06:56:31.431207: step: 272/1545, loss: 0.18263250589370728 2023-01-23 06:56:32.329711: step: 274/1545, loss: 0.5006676912307739 2023-01-23 06:56:33.215097: step: 276/1545, loss: 0.8816105723381042 2023-01-23 06:56:34.111152: step: 278/1545, loss: 2.4744873046875 2023-01-23 06:56:34.990765: step: 280/1545, loss: 0.2768149673938751 2023-01-23 06:56:35.892620: step: 282/1545, loss: 0.520426869392395 2023-01-23 06:56:36.738905: step: 284/1545, loss: 0.5822815299034119 2023-01-23 06:56:37.658987: step: 286/1545, loss: 0.3249123990535736 2023-01-23 06:56:38.547846: step: 288/1545, loss: 0.5254348516464233 2023-01-23 06:56:39.406378: step: 290/1545, loss: 0.8558444380760193 2023-01-23 06:56:40.249841: step: 292/1545, loss: 3.6563520431518555 2023-01-23 06:56:41.104758: step: 294/1545, loss: 0.5303341150283813 2023-01-23 06:56:41.962920: step: 296/1545, loss: 0.4479852318763733 2023-01-23 06:56:42.856212: step: 298/1545, loss: 0.2017207145690918 2023-01-23 06:56:43.745945: step: 300/1545, loss: 0.2607888877391815 2023-01-23 06:56:44.624136: step: 302/1545, loss: 0.49456968903541565 2023-01-23 06:56:45.477732: step: 304/1545, loss: 0.8844661116600037 2023-01-23 06:56:46.378248: step: 306/1545, loss: 0.5664223432540894 2023-01-23 06:56:47.249363: step: 308/1545, loss: 0.30395498871803284 2023-01-23 06:56:48.210937: step: 310/1545, loss: 0.7550394535064697 2023-01-23 06:56:49.099480: step: 312/1545, loss: 0.3102724254131317 2023-01-23 06:56:49.981839: step: 314/1545, loss: 0.4871395528316498 2023-01-23 06:56:50.895946: step: 316/1545, loss: 0.53740394115448 2023-01-23 06:56:51.753950: step: 318/1545, loss: 0.12902426719665527 2023-01-23 06:56:52.618006: step: 320/1545, loss: 0.6868087649345398 2023-01-23 06:56:53.489269: step: 322/1545, loss: 0.4730883240699768 2023-01-23 06:56:54.432507: step: 324/1545, loss: 0.3360619843006134 2023-01-23 06:56:55.293538: step: 326/1545, loss: 0.40501895546913147 2023-01-23 06:56:56.135277: step: 328/1545, loss: 0.43290260434150696 2023-01-23 06:56:56.984219: step: 330/1545, loss: 0.5579159259796143 2023-01-23 06:56:57.853410: step: 332/1545, loss: 0.4885479509830475 2023-01-23 06:56:58.772897: step: 334/1545, loss: 1.1686419248580933 2023-01-23 06:56:59.626975: step: 336/1545, loss: 0.3176593482494354 2023-01-23 06:57:00.504776: step: 338/1545, loss: 0.39153555035591125 2023-01-23 06:57:01.457824: step: 340/1545, loss: 1.550930380821228 2023-01-23 06:57:02.344647: step: 342/1545, loss: 0.6473723649978638 2023-01-23 06:57:03.220130: step: 344/1545, loss: 0.4621823728084564 2023-01-23 06:57:04.139506: step: 346/1545, loss: 0.39203622937202454 2023-01-23 06:57:05.007285: step: 348/1545, loss: 0.3914787173271179 2023-01-23 06:57:05.902981: step: 350/1545, loss: 0.528509259223938 2023-01-23 06:57:06.755832: step: 352/1545, loss: 0.43570154905319214 2023-01-23 06:57:07.722510: step: 354/1545, loss: 0.899368405342102 2023-01-23 06:57:08.600957: step: 356/1545, loss: 0.6273516416549683 2023-01-23 06:57:09.498668: step: 358/1545, loss: 0.8681079745292664 2023-01-23 06:57:10.393288: step: 360/1545, loss: 0.21723559498786926 2023-01-23 06:57:11.262035: step: 362/1545, loss: 0.9281333088874817 2023-01-23 06:57:12.137770: step: 364/1545, loss: 0.5201545357704163 2023-01-23 06:57:13.054993: step: 366/1545, loss: 0.442608118057251 2023-01-23 06:57:13.906120: step: 368/1545, loss: 0.4697791039943695 2023-01-23 06:57:14.768663: step: 370/1545, loss: 0.5005799531936646 2023-01-23 06:57:15.624709: step: 372/1545, loss: 0.51694256067276 2023-01-23 06:57:16.561639: step: 374/1545, loss: 0.49486759305000305 2023-01-23 06:57:17.406298: step: 376/1545, loss: 0.7354305982589722 2023-01-23 06:57:18.253160: step: 378/1545, loss: 0.5430145263671875 2023-01-23 06:57:19.136305: step: 380/1545, loss: 0.5467586517333984 2023-01-23 06:57:20.047817: step: 382/1545, loss: 1.0513092279434204 2023-01-23 06:57:20.953731: step: 384/1545, loss: 0.8972488045692444 2023-01-23 06:57:21.850376: step: 386/1545, loss: 0.558684766292572 2023-01-23 06:57:22.795652: step: 388/1545, loss: 1.3722037076950073 2023-01-23 06:57:23.673593: step: 390/1545, loss: 0.1525323987007141 2023-01-23 06:57:24.531183: step: 392/1545, loss: 1.249860167503357 2023-01-23 06:57:25.387514: step: 394/1545, loss: 0.5500820279121399 2023-01-23 06:57:26.292031: step: 396/1545, loss: 0.5180668830871582 2023-01-23 06:57:27.183778: step: 398/1545, loss: 2.827662229537964 2023-01-23 06:57:28.026617: step: 400/1545, loss: 0.5117440819740295 2023-01-23 06:57:28.932262: step: 402/1545, loss: 0.2907971739768982 2023-01-23 06:57:29.787914: step: 404/1545, loss: 0.353517085313797 2023-01-23 06:57:30.683380: step: 406/1545, loss: 0.7468734979629517 2023-01-23 06:57:31.608831: step: 408/1545, loss: 0.6518236398696899 2023-01-23 06:57:32.484332: step: 410/1545, loss: 0.4428409934043884 2023-01-23 06:57:33.378847: step: 412/1545, loss: 0.3463338315486908 2023-01-23 06:57:34.287201: step: 414/1545, loss: 7.565736293792725 2023-01-23 06:57:35.150329: step: 416/1545, loss: 0.6683131456375122 2023-01-23 06:57:36.003628: step: 418/1545, loss: 0.5504780411720276 2023-01-23 06:57:36.965026: step: 420/1545, loss: 0.6794542670249939 2023-01-23 06:57:37.843522: step: 422/1545, loss: 1.4114832878112793 2023-01-23 06:57:38.775915: step: 424/1545, loss: 0.30350908637046814 2023-01-23 06:57:39.719403: step: 426/1545, loss: 3.2882773876190186 2023-01-23 06:57:40.623937: step: 428/1545, loss: 0.46745312213897705 2023-01-23 06:57:41.526120: step: 430/1545, loss: 1.0049382448196411 2023-01-23 06:57:42.413824: step: 432/1545, loss: 1.0731068849563599 2023-01-23 06:57:43.383153: step: 434/1545, loss: 0.718569815158844 2023-01-23 06:57:44.284953: step: 436/1545, loss: 0.4413207471370697 2023-01-23 06:57:45.203205: step: 438/1545, loss: 1.3665504455566406 2023-01-23 06:57:46.155459: step: 440/1545, loss: 0.21776644885540009 2023-01-23 06:57:47.036032: step: 442/1545, loss: 1.0108500719070435 2023-01-23 06:57:47.944816: step: 444/1545, loss: 0.5046966671943665 2023-01-23 06:57:48.793262: step: 446/1545, loss: 0.728771984577179 2023-01-23 06:57:49.678076: step: 448/1545, loss: 0.8687385320663452 2023-01-23 06:57:50.554570: step: 450/1545, loss: 0.2358543872833252 2023-01-23 06:57:51.430266: step: 452/1545, loss: 0.3042042851448059 2023-01-23 06:57:52.328873: step: 454/1545, loss: 0.4290681481361389 2023-01-23 06:57:53.192164: step: 456/1545, loss: 0.32232680916786194 2023-01-23 06:57:54.076266: step: 458/1545, loss: 1.0774787664413452 2023-01-23 06:57:54.961031: step: 460/1545, loss: 0.3187812864780426 2023-01-23 06:57:55.842815: step: 462/1545, loss: 0.4462986886501312 2023-01-23 06:57:56.708073: step: 464/1545, loss: 0.3847392499446869 2023-01-23 06:57:57.576018: step: 466/1545, loss: 0.6916882395744324 2023-01-23 06:57:58.457989: step: 468/1545, loss: 0.3465867340564728 2023-01-23 06:57:59.340918: step: 470/1545, loss: 0.6124218106269836 2023-01-23 06:58:00.243172: step: 472/1545, loss: 0.8148135542869568 2023-01-23 06:58:01.101801: step: 474/1545, loss: 0.7203616499900818 2023-01-23 06:58:01.954377: step: 476/1545, loss: 1.4358881711959839 2023-01-23 06:58:02.862787: step: 478/1545, loss: 0.830734372138977 2023-01-23 06:58:03.729647: step: 480/1545, loss: 0.42901813983917236 2023-01-23 06:58:04.603166: step: 482/1545, loss: 0.40516477823257446 2023-01-23 06:58:05.466378: step: 484/1545, loss: 0.38275855779647827 2023-01-23 06:58:06.349248: step: 486/1545, loss: 0.7094866633415222 2023-01-23 06:58:07.197604: step: 488/1545, loss: 0.4437600076198578 2023-01-23 06:58:08.072785: step: 490/1545, loss: 0.9346483945846558 2023-01-23 06:58:08.989563: step: 492/1545, loss: 2.863058090209961 2023-01-23 06:58:09.831324: step: 494/1545, loss: 2.683267593383789 2023-01-23 06:58:10.706048: step: 496/1545, loss: 0.5228344202041626 2023-01-23 06:58:11.601106: step: 498/1545, loss: 0.23836931586265564 2023-01-23 06:58:12.453377: step: 500/1545, loss: 0.6271231174468994 2023-01-23 06:58:13.301385: step: 502/1545, loss: 0.3424484431743622 2023-01-23 06:58:14.149820: step: 504/1545, loss: 0.8484320640563965 2023-01-23 06:58:15.042455: step: 506/1545, loss: 0.936549186706543 2023-01-23 06:58:15.922806: step: 508/1545, loss: 0.609932541847229 2023-01-23 06:58:16.799783: step: 510/1545, loss: 0.498893678188324 2023-01-23 06:58:17.672813: step: 512/1545, loss: 3.837773084640503 2023-01-23 06:58:18.578895: step: 514/1545, loss: 1.9111194610595703 2023-01-23 06:58:19.424828: step: 516/1545, loss: 0.22503900527954102 2023-01-23 06:58:20.337338: step: 518/1545, loss: 0.5031247735023499 2023-01-23 06:58:21.210601: step: 520/1545, loss: 0.8811452388763428 2023-01-23 06:58:22.062382: step: 522/1545, loss: 0.45338577032089233 2023-01-23 06:58:22.986164: step: 524/1545, loss: 0.369476318359375 2023-01-23 06:58:23.899526: step: 526/1545, loss: 0.6158081293106079 2023-01-23 06:58:24.779331: step: 528/1545, loss: 0.3411683440208435 2023-01-23 06:58:25.719167: step: 530/1545, loss: 0.7183812856674194 2023-01-23 06:58:26.601258: step: 532/1545, loss: 0.9460495114326477 2023-01-23 06:58:27.455871: step: 534/1545, loss: 0.4577365517616272 2023-01-23 06:58:28.316890: step: 536/1545, loss: 0.7842181921005249 2023-01-23 06:58:29.215694: step: 538/1545, loss: 0.9313349723815918 2023-01-23 06:58:30.090892: step: 540/1545, loss: 0.5000910758972168 2023-01-23 06:58:30.930283: step: 542/1545, loss: 0.4382396936416626 2023-01-23 06:58:31.828421: step: 544/1545, loss: 0.5665705800056458 2023-01-23 06:58:32.693531: step: 546/1545, loss: 1.1633384227752686 2023-01-23 06:58:33.551273: step: 548/1545, loss: 0.7285594940185547 2023-01-23 06:58:34.443698: step: 550/1545, loss: 0.5665557980537415 2023-01-23 06:58:35.323723: step: 552/1545, loss: 0.5784997344017029 2023-01-23 06:58:36.218677: step: 554/1545, loss: 0.8453528881072998 2023-01-23 06:58:37.201188: step: 556/1545, loss: 0.3309337794780731 2023-01-23 06:58:38.076024: step: 558/1545, loss: 0.7132992744445801 2023-01-23 06:58:38.946599: step: 560/1545, loss: 0.6705386638641357 2023-01-23 06:58:39.830625: step: 562/1545, loss: 0.42642444372177124 2023-01-23 06:58:40.680388: step: 564/1545, loss: 0.6751492619514465 2023-01-23 06:58:41.594173: step: 566/1545, loss: 0.8685186505317688 2023-01-23 06:58:42.449907: step: 568/1545, loss: 0.4536246657371521 2023-01-23 06:58:43.350607: step: 570/1545, loss: 0.39174386858940125 2023-01-23 06:58:44.219527: step: 572/1545, loss: 0.52219158411026 2023-01-23 06:58:45.141812: step: 574/1545, loss: 0.5026745796203613 2023-01-23 06:58:46.038740: step: 576/1545, loss: 0.9404630661010742 2023-01-23 06:58:46.936975: step: 578/1545, loss: 0.9222724437713623 2023-01-23 06:58:47.763986: step: 580/1545, loss: 1.4733983278274536 2023-01-23 06:58:48.664716: step: 582/1545, loss: 0.6588184237480164 2023-01-23 06:58:49.537942: step: 584/1545, loss: 0.5622268319129944 2023-01-23 06:58:50.400319: step: 586/1545, loss: 0.3475593030452728 2023-01-23 06:58:51.251366: step: 588/1545, loss: 0.4983069896697998 2023-01-23 06:58:52.125989: step: 590/1545, loss: 0.6406307816505432 2023-01-23 06:58:53.020411: step: 592/1545, loss: 0.8952642679214478 2023-01-23 06:58:53.925437: step: 594/1545, loss: 0.5967479348182678 2023-01-23 06:58:54.810470: step: 596/1545, loss: 0.5063178539276123 2023-01-23 06:58:55.674755: step: 598/1545, loss: 0.2737317383289337 2023-01-23 06:58:56.517392: step: 600/1545, loss: 0.44088292121887207 2023-01-23 06:58:57.373603: step: 602/1545, loss: 1.5954962968826294 2023-01-23 06:58:58.223466: step: 604/1545, loss: 0.3484382629394531 2023-01-23 06:58:59.104096: step: 606/1545, loss: 1.2773288488388062 2023-01-23 06:58:59.990769: step: 608/1545, loss: 0.4310756027698517 2023-01-23 06:59:00.868366: step: 610/1545, loss: 0.2411893755197525 2023-01-23 06:59:01.767086: step: 612/1545, loss: 0.639578104019165 2023-01-23 06:59:02.645570: step: 614/1545, loss: 0.49406248331069946 2023-01-23 06:59:03.578572: step: 616/1545, loss: 0.7395191788673401 2023-01-23 06:59:04.445397: step: 618/1545, loss: 1.306909203529358 2023-01-23 06:59:05.304492: step: 620/1545, loss: 0.5381298065185547 2023-01-23 06:59:06.164197: step: 622/1545, loss: 0.4458060562610626 2023-01-23 06:59:07.080325: step: 624/1545, loss: 1.2730597257614136 2023-01-23 06:59:07.955138: step: 626/1545, loss: 0.3599282503128052 2023-01-23 06:59:08.808567: step: 628/1545, loss: 0.13488617539405823 2023-01-23 06:59:09.683990: step: 630/1545, loss: 0.4916088581085205 2023-01-23 06:59:10.542406: step: 632/1545, loss: 0.534687340259552 2023-01-23 06:59:11.457031: step: 634/1545, loss: 0.7365366816520691 2023-01-23 06:59:12.355065: step: 636/1545, loss: 0.423196017742157 2023-01-23 06:59:13.198086: step: 638/1545, loss: 0.476564884185791 2023-01-23 06:59:14.083011: step: 640/1545, loss: 0.531166136264801 2023-01-23 06:59:14.936907: step: 642/1545, loss: 0.6505522727966309 2023-01-23 06:59:15.807807: step: 644/1545, loss: 0.798644483089447 2023-01-23 06:59:16.724626: step: 646/1545, loss: 0.7642494440078735 2023-01-23 06:59:17.591529: step: 648/1545, loss: 0.8089947700500488 2023-01-23 06:59:18.458749: step: 650/1545, loss: 0.39636263251304626 2023-01-23 06:59:19.379370: step: 652/1545, loss: 0.9033337831497192 2023-01-23 06:59:20.277576: step: 654/1545, loss: 0.93709796667099 2023-01-23 06:59:21.143609: step: 656/1545, loss: 0.6985796093940735 2023-01-23 06:59:22.051197: step: 658/1545, loss: 0.639281690120697 2023-01-23 06:59:22.912144: step: 660/1545, loss: 0.6989939212799072 2023-01-23 06:59:23.805685: step: 662/1545, loss: 0.4318713843822479 2023-01-23 06:59:24.705200: step: 664/1545, loss: 0.6032357811927795 2023-01-23 06:59:25.636829: step: 666/1545, loss: 3.1832504272460938 2023-01-23 06:59:26.576754: step: 668/1545, loss: 0.853341817855835 2023-01-23 06:59:27.513958: step: 670/1545, loss: 0.8736479878425598 2023-01-23 06:59:28.363420: step: 672/1545, loss: 0.4932667911052704 2023-01-23 06:59:29.254388: step: 674/1545, loss: 0.42263510823249817 2023-01-23 06:59:30.109056: step: 676/1545, loss: 0.745974063873291 2023-01-23 06:59:31.001467: step: 678/1545, loss: 0.3778117597103119 2023-01-23 06:59:31.868093: step: 680/1545, loss: 0.5698838829994202 2023-01-23 06:59:32.789596: step: 682/1545, loss: 0.4098707437515259 2023-01-23 06:59:33.639895: step: 684/1545, loss: 0.20289254188537598 2023-01-23 06:59:34.556883: step: 686/1545, loss: 0.8518143892288208 2023-01-23 06:59:35.421107: step: 688/1545, loss: 1.2192764282226562 2023-01-23 06:59:36.304830: step: 690/1545, loss: 0.440767377614975 2023-01-23 06:59:37.225035: step: 692/1545, loss: 0.47512030601501465 2023-01-23 06:59:38.087908: step: 694/1545, loss: 0.47557637095451355 2023-01-23 06:59:38.953276: step: 696/1545, loss: 1.4468269348144531 2023-01-23 06:59:39.846416: step: 698/1545, loss: 1.1423901319503784 2023-01-23 06:59:40.745467: step: 700/1545, loss: 0.40790611505508423 2023-01-23 06:59:41.646017: step: 702/1545, loss: 0.655979335308075 2023-01-23 06:59:42.538757: step: 704/1545, loss: 0.8578943014144897 2023-01-23 06:59:43.399558: step: 706/1545, loss: 0.36600103974342346 2023-01-23 06:59:44.232511: step: 708/1545, loss: 0.3452058434486389 2023-01-23 06:59:45.104219: step: 710/1545, loss: 0.3776530921459198 2023-01-23 06:59:45.978092: step: 712/1545, loss: 0.42816251516342163 2023-01-23 06:59:46.889970: step: 714/1545, loss: 0.287932813167572 2023-01-23 06:59:47.789430: step: 716/1545, loss: 0.7718954682350159 2023-01-23 06:59:48.649724: step: 718/1545, loss: 1.2136660814285278 2023-01-23 06:59:49.544474: step: 720/1545, loss: 0.8725754022598267 2023-01-23 06:59:50.423538: step: 722/1545, loss: 0.4130621552467346 2023-01-23 06:59:51.265687: step: 724/1545, loss: 0.24303719401359558 2023-01-23 06:59:52.138072: step: 726/1545, loss: 1.3568135499954224 2023-01-23 06:59:53.051691: step: 728/1545, loss: 0.3029206097126007 2023-01-23 06:59:53.968345: step: 730/1545, loss: 0.3061510920524597 2023-01-23 06:59:54.819855: step: 732/1545, loss: 0.6369943618774414 2023-01-23 06:59:55.698564: step: 734/1545, loss: 0.23185700178146362 2023-01-23 06:59:56.554622: step: 736/1545, loss: 0.5347594618797302 2023-01-23 06:59:57.426499: step: 738/1545, loss: 0.6434715986251831 2023-01-23 06:59:58.284318: step: 740/1545, loss: 0.8044193983078003 2023-01-23 06:59:59.153634: step: 742/1545, loss: 0.8418523073196411 2023-01-23 07:00:00.011745: step: 744/1545, loss: 0.6820354461669922 2023-01-23 07:00:00.874120: step: 746/1545, loss: 0.2807243764400482 2023-01-23 07:00:01.739851: step: 748/1545, loss: 0.6973724365234375 2023-01-23 07:00:02.587622: step: 750/1545, loss: 0.6575984954833984 2023-01-23 07:00:03.440754: step: 752/1545, loss: 0.2637934982776642 2023-01-23 07:00:04.265160: step: 754/1545, loss: 0.48233115673065186 2023-01-23 07:00:05.140182: step: 756/1545, loss: 0.6338199377059937 2023-01-23 07:00:05.988753: step: 758/1545, loss: 0.8054561614990234 2023-01-23 07:00:06.878875: step: 760/1545, loss: 0.6246817708015442 2023-01-23 07:00:07.887376: step: 762/1545, loss: 0.6982158422470093 2023-01-23 07:00:08.780373: step: 764/1545, loss: 0.8526408076286316 2023-01-23 07:00:09.675947: step: 766/1545, loss: 0.937842845916748 2023-01-23 07:00:10.536932: step: 768/1545, loss: 0.5328707098960876 2023-01-23 07:00:11.403786: step: 770/1545, loss: 0.5565445423126221 2023-01-23 07:00:12.268576: step: 772/1545, loss: 0.23399323225021362 2023-01-23 07:00:13.103280: step: 774/1545, loss: 0.1262228935956955 2023-01-23 07:00:13.963944: step: 776/1545, loss: 0.39150598645210266 2023-01-23 07:00:14.793254: step: 778/1545, loss: 0.8033809065818787 2023-01-23 07:00:15.649097: step: 780/1545, loss: 0.560346245765686 2023-01-23 07:00:16.521587: step: 782/1545, loss: 1.0008984804153442 2023-01-23 07:00:17.397008: step: 784/1545, loss: 0.829260528087616 2023-01-23 07:00:18.234973: step: 786/1545, loss: 0.980197012424469 2023-01-23 07:00:19.089615: step: 788/1545, loss: 0.8022227883338928 2023-01-23 07:00:19.996396: step: 790/1545, loss: 1.1309045553207397 2023-01-23 07:00:20.838827: step: 792/1545, loss: 0.3491538465023041 2023-01-23 07:00:21.787243: step: 794/1545, loss: 0.9936571717262268 2023-01-23 07:00:22.680373: step: 796/1545, loss: 0.39888304471969604 2023-01-23 07:00:23.551351: step: 798/1545, loss: 0.6918337345123291 2023-01-23 07:00:24.405032: step: 800/1545, loss: 0.3503648042678833 2023-01-23 07:00:25.250738: step: 802/1545, loss: 0.3639630973339081 2023-01-23 07:00:26.087485: step: 804/1545, loss: 0.3176223635673523 2023-01-23 07:00:26.963752: step: 806/1545, loss: 0.6090238094329834 2023-01-23 07:00:27.821500: step: 808/1545, loss: 3.136789321899414 2023-01-23 07:00:28.719192: step: 810/1545, loss: 0.5952932238578796 2023-01-23 07:00:29.577873: step: 812/1545, loss: 0.48008060455322266 2023-01-23 07:00:30.498093: step: 814/1545, loss: 0.7362787127494812 2023-01-23 07:00:31.378460: step: 816/1545, loss: 0.39908963441848755 2023-01-23 07:00:32.321920: step: 818/1545, loss: 0.4840414524078369 2023-01-23 07:00:33.178977: step: 820/1545, loss: 0.2921487092971802 2023-01-23 07:00:34.038111: step: 822/1545, loss: 1.2653125524520874 2023-01-23 07:00:34.947996: step: 824/1545, loss: 0.7879428267478943 2023-01-23 07:00:35.833917: step: 826/1545, loss: 0.1897767335176468 2023-01-23 07:00:36.677656: step: 828/1545, loss: 0.5921138525009155 2023-01-23 07:00:37.571396: step: 830/1545, loss: 0.4701050817966461 2023-01-23 07:00:38.452268: step: 832/1545, loss: 0.6217015385627747 2023-01-23 07:00:39.322495: step: 834/1545, loss: 0.36727672815322876 2023-01-23 07:00:40.191029: step: 836/1545, loss: 3.0670993328094482 2023-01-23 07:00:41.136724: step: 838/1545, loss: 0.3741965591907501 2023-01-23 07:00:41.994344: step: 840/1545, loss: 0.5082721710205078 2023-01-23 07:00:42.844841: step: 842/1545, loss: 0.8721711039543152 2023-01-23 07:00:43.739506: step: 844/1545, loss: 0.46532952785491943 2023-01-23 07:00:44.579095: step: 846/1545, loss: 0.2589671313762665 2023-01-23 07:00:45.430565: step: 848/1545, loss: 0.3658961057662964 2023-01-23 07:00:46.323461: step: 850/1545, loss: 0.5528525710105896 2023-01-23 07:00:47.170096: step: 852/1545, loss: 0.9031064510345459 2023-01-23 07:00:48.066921: step: 854/1545, loss: 0.41246312856674194 2023-01-23 07:00:48.975615: step: 856/1545, loss: 0.3896995782852173 2023-01-23 07:00:49.838503: step: 858/1545, loss: 0.9887354969978333 2023-01-23 07:00:50.742162: step: 860/1545, loss: 1.2912670373916626 2023-01-23 07:00:51.595249: step: 862/1545, loss: 0.6635960936546326 2023-01-23 07:00:52.497343: step: 864/1545, loss: 0.8569130301475525 2023-01-23 07:00:53.377968: step: 866/1545, loss: 0.6100997924804688 2023-01-23 07:00:54.270391: step: 868/1545, loss: 0.4051249027252197 2023-01-23 07:00:55.224371: step: 870/1545, loss: 0.6552062630653381 2023-01-23 07:00:56.135709: step: 872/1545, loss: 1.5270030498504639 2023-01-23 07:00:57.035179: step: 874/1545, loss: 0.5525621771812439 2023-01-23 07:00:58.016392: step: 876/1545, loss: 0.6913830041885376 2023-01-23 07:00:58.888746: step: 878/1545, loss: 0.39208853244781494 2023-01-23 07:00:59.791830: step: 880/1545, loss: 1.3855968713760376 2023-01-23 07:01:00.620571: step: 882/1545, loss: 0.4195866286754608 2023-01-23 07:01:01.475150: step: 884/1545, loss: 2.837806224822998 2023-01-23 07:01:02.390602: step: 886/1545, loss: 0.6585245728492737 2023-01-23 07:01:03.267009: step: 888/1545, loss: 0.37456175684928894 2023-01-23 07:01:04.176441: step: 890/1545, loss: 0.4640342891216278 2023-01-23 07:01:05.066512: step: 892/1545, loss: 0.19171229004859924 2023-01-23 07:01:05.913445: step: 894/1545, loss: 0.7227683067321777 2023-01-23 07:01:06.800547: step: 896/1545, loss: 0.7188205718994141 2023-01-23 07:01:07.662902: step: 898/1545, loss: 2.923593759536743 2023-01-23 07:01:08.543330: step: 900/1545, loss: 0.329172819852829 2023-01-23 07:01:09.447588: step: 902/1545, loss: 0.7049820423126221 2023-01-23 07:01:10.352408: step: 904/1545, loss: 0.7500600814819336 2023-01-23 07:01:11.240155: step: 906/1545, loss: 0.2345781922340393 2023-01-23 07:01:12.078449: step: 908/1545, loss: 0.24551498889923096 2023-01-23 07:01:12.974345: step: 910/1545, loss: 0.4074411690235138 2023-01-23 07:01:13.893183: step: 912/1545, loss: 1.1039665937423706 2023-01-23 07:01:14.749341: step: 914/1545, loss: 1.6587098836898804 2023-01-23 07:01:15.673865: step: 916/1545, loss: 0.4049578309059143 2023-01-23 07:01:16.558034: step: 918/1545, loss: 1.3781027793884277 2023-01-23 07:01:17.418609: step: 920/1545, loss: 0.44867077469825745 2023-01-23 07:01:18.279032: step: 922/1545, loss: 0.5957541465759277 2023-01-23 07:01:19.203261: step: 924/1545, loss: 1.4395427703857422 2023-01-23 07:01:20.060545: step: 926/1545, loss: 0.6226880550384521 2023-01-23 07:01:20.937229: step: 928/1545, loss: 1.5294171571731567 2023-01-23 07:01:21.816356: step: 930/1545, loss: 0.5358924269676208 2023-01-23 07:01:22.702148: step: 932/1545, loss: 0.7031636238098145 2023-01-23 07:01:23.556654: step: 934/1545, loss: 0.3951265513896942 2023-01-23 07:01:24.461461: step: 936/1545, loss: 0.7942575812339783 2023-01-23 07:01:25.309171: step: 938/1545, loss: 0.48260244727134705 2023-01-23 07:01:26.168831: step: 940/1545, loss: 0.5388815402984619 2023-01-23 07:01:27.030179: step: 942/1545, loss: 0.797375500202179 2023-01-23 07:01:27.919379: step: 944/1545, loss: 0.2740352749824524 2023-01-23 07:01:28.817677: step: 946/1545, loss: 0.13303221762180328 2023-01-23 07:01:29.653984: step: 948/1545, loss: 0.7169011831283569 2023-01-23 07:01:30.541120: step: 950/1545, loss: 0.5855246782302856 2023-01-23 07:01:31.411580: step: 952/1545, loss: 0.42233559489250183 2023-01-23 07:01:32.262277: step: 954/1545, loss: 0.5293166041374207 2023-01-23 07:01:33.108210: step: 956/1545, loss: 0.9162197113037109 2023-01-23 07:01:33.980973: step: 958/1545, loss: 0.6026222109794617 2023-01-23 07:01:34.848275: step: 960/1545, loss: 0.7434423565864563 2023-01-23 07:01:35.819825: step: 962/1545, loss: 0.573522686958313 2023-01-23 07:01:36.685367: step: 964/1545, loss: 0.24474404752254486 2023-01-23 07:01:37.542084: step: 966/1545, loss: 1.8561428785324097 2023-01-23 07:01:38.467762: step: 968/1545, loss: 0.3559473156929016 2023-01-23 07:01:39.370352: step: 970/1545, loss: 0.5491920709609985 2023-01-23 07:01:40.337954: step: 972/1545, loss: 0.6494349837303162 2023-01-23 07:01:41.196997: step: 974/1545, loss: 0.8709071278572083 2023-01-23 07:01:42.072977: step: 976/1545, loss: 0.36779823899269104 2023-01-23 07:01:42.924925: step: 978/1545, loss: 0.674408495426178 2023-01-23 07:01:43.802477: step: 980/1545, loss: 0.6443720459938049 2023-01-23 07:01:44.678820: step: 982/1545, loss: 0.5428880453109741 2023-01-23 07:01:45.602261: step: 984/1545, loss: 0.5089409351348877 2023-01-23 07:01:46.510463: step: 986/1545, loss: 0.6207321882247925 2023-01-23 07:01:47.433693: step: 988/1545, loss: 0.546328067779541 2023-01-23 07:01:48.400180: step: 990/1545, loss: 0.4213552474975586 2023-01-23 07:01:49.319936: step: 992/1545, loss: 0.511951744556427 2023-01-23 07:01:50.230013: step: 994/1545, loss: 0.416732519865036 2023-01-23 07:01:51.150513: step: 996/1545, loss: 0.8738593459129333 2023-01-23 07:01:52.019924: step: 998/1545, loss: 0.7881285548210144 2023-01-23 07:01:52.990323: step: 1000/1545, loss: 0.5176211595535278 2023-01-23 07:01:53.863888: step: 1002/1545, loss: 0.9229618906974792 2023-01-23 07:01:54.764079: step: 1004/1545, loss: 0.20530185103416443 2023-01-23 07:01:55.634781: step: 1006/1545, loss: 0.20971684157848358 2023-01-23 07:01:56.493957: step: 1008/1545, loss: 0.7392311096191406 2023-01-23 07:01:57.356065: step: 1010/1545, loss: 0.3024865984916687 2023-01-23 07:01:58.221534: step: 1012/1545, loss: 0.8599970936775208 2023-01-23 07:01:59.081356: step: 1014/1545, loss: 0.360019326210022 2023-01-23 07:01:59.981013: step: 1016/1545, loss: 0.2469097375869751 2023-01-23 07:02:00.881697: step: 1018/1545, loss: 3.2765257358551025 2023-01-23 07:02:01.734251: step: 1020/1545, loss: 0.8059390187263489 2023-01-23 07:02:02.563665: step: 1022/1545, loss: 0.7846093773841858 2023-01-23 07:02:03.394203: step: 1024/1545, loss: 0.4383646547794342 2023-01-23 07:02:04.238591: step: 1026/1545, loss: 0.8855360746383667 2023-01-23 07:02:05.143970: step: 1028/1545, loss: 0.6308877468109131 2023-01-23 07:02:06.061007: step: 1030/1545, loss: 0.8368576169013977 2023-01-23 07:02:06.963775: step: 1032/1545, loss: 1.4534844160079956 2023-01-23 07:02:07.849791: step: 1034/1545, loss: 0.9690589308738708 2023-01-23 07:02:08.746502: step: 1036/1545, loss: 0.4602174758911133 2023-01-23 07:02:09.619725: step: 1038/1545, loss: 0.8696770071983337 2023-01-23 07:02:10.519709: step: 1040/1545, loss: 0.4833393096923828 2023-01-23 07:02:11.436197: step: 1042/1545, loss: 0.4050602316856384 2023-01-23 07:02:12.296442: step: 1044/1545, loss: 0.7733181118965149 2023-01-23 07:02:13.182399: step: 1046/1545, loss: 2.5339150428771973 2023-01-23 07:02:14.058667: step: 1048/1545, loss: 0.36668312549591064 2023-01-23 07:02:14.918397: step: 1050/1545, loss: 0.9582293033599854 2023-01-23 07:02:15.811689: step: 1052/1545, loss: 0.36387085914611816 2023-01-23 07:02:16.682237: step: 1054/1545, loss: 0.41209083795547485 2023-01-23 07:02:17.526515: step: 1056/1545, loss: 0.5862048864364624 2023-01-23 07:02:18.405005: step: 1058/1545, loss: 0.27356624603271484 2023-01-23 07:02:19.319799: step: 1060/1545, loss: 0.43136343359947205 2023-01-23 07:02:20.164322: step: 1062/1545, loss: 0.6219906806945801 2023-01-23 07:02:20.994708: step: 1064/1545, loss: 1.2157105207443237 2023-01-23 07:02:21.870507: step: 1066/1545, loss: 0.47590136528015137 2023-01-23 07:02:22.756677: step: 1068/1545, loss: 6.371492385864258 2023-01-23 07:02:23.651138: step: 1070/1545, loss: 0.8285357356071472 2023-01-23 07:02:24.552548: step: 1072/1545, loss: 0.4223557710647583 2023-01-23 07:02:25.417943: step: 1074/1545, loss: 0.580122709274292 2023-01-23 07:02:26.255746: step: 1076/1545, loss: 0.44524386525154114 2023-01-23 07:02:27.124784: step: 1078/1545, loss: 0.2763242721557617 2023-01-23 07:02:28.028374: step: 1080/1545, loss: 0.7269994616508484 2023-01-23 07:02:28.905892: step: 1082/1545, loss: 0.29797810316085815 2023-01-23 07:02:29.784025: step: 1084/1545, loss: 0.5508825778961182 2023-01-23 07:02:30.680173: step: 1086/1545, loss: 2.964817762374878 2023-01-23 07:02:31.540992: step: 1088/1545, loss: 0.7185841798782349 2023-01-23 07:02:32.400502: step: 1090/1545, loss: 0.5163610577583313 2023-01-23 07:02:33.270721: step: 1092/1545, loss: 1.7525686025619507 2023-01-23 07:02:34.164264: step: 1094/1545, loss: 0.8778411746025085 2023-01-23 07:02:35.012597: step: 1096/1545, loss: 0.49821528792381287 2023-01-23 07:02:35.858371: step: 1098/1545, loss: 1.048919439315796 2023-01-23 07:02:36.682179: step: 1100/1545, loss: 0.6531074643135071 2023-01-23 07:02:37.511344: step: 1102/1545, loss: 0.5131419897079468 2023-01-23 07:02:38.360097: step: 1104/1545, loss: 0.3461447060108185 2023-01-23 07:02:39.226244: step: 1106/1545, loss: 0.850592851638794 2023-01-23 07:02:40.147101: step: 1108/1545, loss: 1.140924096107483 2023-01-23 07:02:41.007788: step: 1110/1545, loss: 0.6150572896003723 2023-01-23 07:02:41.910009: step: 1112/1545, loss: 1.1864001750946045 2023-01-23 07:02:42.766544: step: 1114/1545, loss: 1.2211296558380127 2023-01-23 07:02:43.629485: step: 1116/1545, loss: 0.7061011791229248 2023-01-23 07:02:44.512484: step: 1118/1545, loss: 0.42122307419776917 2023-01-23 07:02:45.384540: step: 1120/1545, loss: 0.38791927695274353 2023-01-23 07:02:46.337944: step: 1122/1545, loss: 0.2903163731098175 2023-01-23 07:02:47.234170: step: 1124/1545, loss: 0.6953955292701721 2023-01-23 07:02:48.113720: step: 1126/1545, loss: 0.47120240330696106 2023-01-23 07:02:49.062813: step: 1128/1545, loss: 0.564741313457489 2023-01-23 07:02:49.944131: step: 1130/1545, loss: 0.18912717700004578 2023-01-23 07:02:50.826206: step: 1132/1545, loss: 1.1601366996765137 2023-01-23 07:02:51.697162: step: 1134/1545, loss: 0.10792884230613708 2023-01-23 07:02:52.594973: step: 1136/1545, loss: 0.8071603775024414 2023-01-23 07:02:53.497393: step: 1138/1545, loss: 0.6244475245475769 2023-01-23 07:02:54.391685: step: 1140/1545, loss: 1.5926778316497803 2023-01-23 07:02:55.276837: step: 1142/1545, loss: 0.6559938192367554 2023-01-23 07:02:56.176295: step: 1144/1545, loss: 0.6046194434165955 2023-01-23 07:02:57.033518: step: 1146/1545, loss: 2.6796607971191406 2023-01-23 07:02:57.919549: step: 1148/1545, loss: 0.22517701983451843 2023-01-23 07:02:58.803148: step: 1150/1545, loss: 0.6656724810600281 2023-01-23 07:02:59.639243: step: 1152/1545, loss: 0.633878231048584 2023-01-23 07:03:00.495019: step: 1154/1545, loss: 1.2488677501678467 2023-01-23 07:03:01.361388: step: 1156/1545, loss: 0.5298436284065247 2023-01-23 07:03:02.283515: step: 1158/1545, loss: 0.9816290736198425 2023-01-23 07:03:03.169621: step: 1160/1545, loss: 0.5517785549163818 2023-01-23 07:03:04.007466: step: 1162/1545, loss: 0.8202470541000366 2023-01-23 07:03:04.903509: step: 1164/1545, loss: 0.5433082580566406 2023-01-23 07:03:05.767204: step: 1166/1545, loss: 0.499853253364563 2023-01-23 07:03:06.673652: step: 1168/1545, loss: 0.5531941652297974 2023-01-23 07:03:07.533889: step: 1170/1545, loss: 0.8657525181770325 2023-01-23 07:03:08.377174: step: 1172/1545, loss: 0.19497135281562805 2023-01-23 07:03:09.270293: step: 1174/1545, loss: 0.5720064640045166 2023-01-23 07:03:10.159182: step: 1176/1545, loss: 0.5108135342597961 2023-01-23 07:03:11.173058: step: 1178/1545, loss: 0.35095441341400146 2023-01-23 07:03:12.072784: step: 1180/1545, loss: 0.6713809967041016 2023-01-23 07:03:12.935625: step: 1182/1545, loss: 0.6693251132965088 2023-01-23 07:03:13.835172: step: 1184/1545, loss: 0.7051352858543396 2023-01-23 07:03:14.681894: step: 1186/1545, loss: 0.2850642502307892 2023-01-23 07:03:15.621608: step: 1188/1545, loss: 0.7115606665611267 2023-01-23 07:03:16.550092: step: 1190/1545, loss: 0.34110787510871887 2023-01-23 07:03:17.444427: step: 1192/1545, loss: 0.43653804063796997 2023-01-23 07:03:18.306911: step: 1194/1545, loss: 0.5485275387763977 2023-01-23 07:03:19.164774: step: 1196/1545, loss: 0.4846709668636322 2023-01-23 07:03:20.017388: step: 1198/1545, loss: 0.31002965569496155 2023-01-23 07:03:20.887601: step: 1200/1545, loss: 0.4894427955150604 2023-01-23 07:03:21.761602: step: 1202/1545, loss: 0.33842653036117554 2023-01-23 07:03:22.620956: step: 1204/1545, loss: 0.775698721408844 2023-01-23 07:03:23.463355: step: 1206/1545, loss: 0.24970543384552002 2023-01-23 07:03:24.304531: step: 1208/1545, loss: 0.7822529077529907 2023-01-23 07:03:25.238262: step: 1210/1545, loss: 0.48919495940208435 2023-01-23 07:03:26.104765: step: 1212/1545, loss: 1.2564752101898193 2023-01-23 07:03:26.972837: step: 1214/1545, loss: 0.3836629390716553 2023-01-23 07:03:27.841725: step: 1216/1545, loss: 0.12442566454410553 2023-01-23 07:03:28.693958: step: 1218/1545, loss: 2.9104442596435547 2023-01-23 07:03:29.576392: step: 1220/1545, loss: 0.3456083834171295 2023-01-23 07:03:30.449333: step: 1222/1545, loss: 0.6324564814567566 2023-01-23 07:03:31.306046: step: 1224/1545, loss: 0.4806416928768158 2023-01-23 07:03:32.206241: step: 1226/1545, loss: 0.4766479432582855 2023-01-23 07:03:33.087479: step: 1228/1545, loss: 0.959876537322998 2023-01-23 07:03:33.960276: step: 1230/1545, loss: 0.43356120586395264 2023-01-23 07:03:34.836086: step: 1232/1545, loss: 0.4320236146450043 2023-01-23 07:03:35.687660: step: 1234/1545, loss: 0.7017846703529358 2023-01-23 07:03:36.549884: step: 1236/1545, loss: 1.0527451038360596 2023-01-23 07:03:37.412856: step: 1238/1545, loss: 0.6992232799530029 2023-01-23 07:03:38.282109: step: 1240/1545, loss: 0.7613738775253296 2023-01-23 07:03:39.179713: step: 1242/1545, loss: 6.718959331512451 2023-01-23 07:03:40.130812: step: 1244/1545, loss: 0.5439280271530151 2023-01-23 07:03:40.960590: step: 1246/1545, loss: 0.7674617767333984 2023-01-23 07:03:41.818909: step: 1248/1545, loss: 1.799306035041809 2023-01-23 07:03:42.756800: step: 1250/1545, loss: 0.8594212532043457 2023-01-23 07:03:43.666963: step: 1252/1545, loss: 0.5479043126106262 2023-01-23 07:03:44.541043: step: 1254/1545, loss: 0.4832364022731781 2023-01-23 07:03:45.426599: step: 1256/1545, loss: 0.4976797103881836 2023-01-23 07:03:46.317120: step: 1258/1545, loss: 0.3628728687763214 2023-01-23 07:03:47.214463: step: 1260/1545, loss: 0.7900595664978027 2023-01-23 07:03:48.111216: step: 1262/1545, loss: 0.3974354565143585 2023-01-23 07:03:48.977314: step: 1264/1545, loss: 0.42127394676208496 2023-01-23 07:03:49.818857: step: 1266/1545, loss: 0.8788760900497437 2023-01-23 07:03:50.698698: step: 1268/1545, loss: 0.7325339913368225 2023-01-23 07:03:51.601383: step: 1270/1545, loss: 0.42308706045150757 2023-01-23 07:03:52.459120: step: 1272/1545, loss: 0.19897426664829254 2023-01-23 07:03:53.373523: step: 1274/1545, loss: 0.42145901918411255 2023-01-23 07:03:54.237743: step: 1276/1545, loss: 0.5689331293106079 2023-01-23 07:03:55.117253: step: 1278/1545, loss: 0.9176508188247681 2023-01-23 07:03:55.972314: step: 1280/1545, loss: 0.3665611743927002 2023-01-23 07:03:56.933600: step: 1282/1545, loss: 0.7059505581855774 2023-01-23 07:03:57.861392: step: 1284/1545, loss: 0.43327829241752625 2023-01-23 07:03:58.698424: step: 1286/1545, loss: 0.35166454315185547 2023-01-23 07:03:59.563121: step: 1288/1545, loss: 1.0672757625579834 2023-01-23 07:04:00.491452: step: 1290/1545, loss: 0.3601195812225342 2023-01-23 07:04:01.362084: step: 1292/1545, loss: 0.4374508857727051 2023-01-23 07:04:02.242721: step: 1294/1545, loss: 0.4598119258880615 2023-01-23 07:04:03.100702: step: 1296/1545, loss: 0.33533820509910583 2023-01-23 07:04:03.984925: step: 1298/1545, loss: 0.37140145897865295 2023-01-23 07:04:04.864113: step: 1300/1545, loss: 0.4341382384300232 2023-01-23 07:04:05.718755: step: 1302/1545, loss: 0.7329733967781067 2023-01-23 07:04:06.560691: step: 1304/1545, loss: 0.3228808045387268 2023-01-23 07:04:07.409396: step: 1306/1545, loss: 0.45769253373146057 2023-01-23 07:04:08.299109: step: 1308/1545, loss: 0.7427687644958496 2023-01-23 07:04:09.165387: step: 1310/1545, loss: 0.4718082547187805 2023-01-23 07:04:10.052918: step: 1312/1545, loss: 0.20809322595596313 2023-01-23 07:04:10.934684: step: 1314/1545, loss: 0.9632852077484131 2023-01-23 07:04:11.791447: step: 1316/1545, loss: 0.8918419480323792 2023-01-23 07:04:12.676962: step: 1318/1545, loss: 3.001143455505371 2023-01-23 07:04:13.532659: step: 1320/1545, loss: 0.21734455227851868 2023-01-23 07:04:14.373091: step: 1322/1545, loss: 0.44675886631011963 2023-01-23 07:04:15.260378: step: 1324/1545, loss: 0.5617456436157227 2023-01-23 07:04:16.155328: step: 1326/1545, loss: 0.27764514088630676 2023-01-23 07:04:17.004978: step: 1328/1545, loss: 0.6448047757148743 2023-01-23 07:04:17.896915: step: 1330/1545, loss: 0.23182085156440735 2023-01-23 07:04:18.821054: step: 1332/1545, loss: 1.3978157043457031 2023-01-23 07:04:19.826214: step: 1334/1545, loss: 0.42419832944869995 2023-01-23 07:04:20.661307: step: 1336/1545, loss: 0.3957540690898895 2023-01-23 07:04:21.519215: step: 1338/1545, loss: 0.4611654281616211 2023-01-23 07:04:22.405450: step: 1340/1545, loss: 1.5748515129089355 2023-01-23 07:04:23.298575: step: 1342/1545, loss: 0.8056463003158569 2023-01-23 07:04:24.199749: step: 1344/1545, loss: 0.6673383116722107 2023-01-23 07:04:25.135496: step: 1346/1545, loss: 0.31895145773887634 2023-01-23 07:04:25.989147: step: 1348/1545, loss: 0.6049467921257019 2023-01-23 07:04:26.830803: step: 1350/1545, loss: 3.426224946975708 2023-01-23 07:04:27.686248: step: 1352/1545, loss: 0.6947992444038391 2023-01-23 07:04:28.528868: step: 1354/1545, loss: 0.4777361750602722 2023-01-23 07:04:29.407219: step: 1356/1545, loss: 1.742002248764038 2023-01-23 07:04:30.254801: step: 1358/1545, loss: 0.224758118391037 2023-01-23 07:04:31.161036: step: 1360/1545, loss: 0.3469463586807251 2023-01-23 07:04:32.030702: step: 1362/1545, loss: 1.9175653457641602 2023-01-23 07:04:32.902493: step: 1364/1545, loss: 1.7625503540039062 2023-01-23 07:04:33.805478: step: 1366/1545, loss: 0.5729175209999084 2023-01-23 07:04:34.648635: step: 1368/1545, loss: 0.7650392651557922 2023-01-23 07:04:35.519631: step: 1370/1545, loss: 0.5837336778640747 2023-01-23 07:04:36.397385: step: 1372/1545, loss: 1.1514291763305664 2023-01-23 07:04:37.238439: step: 1374/1545, loss: 0.2996912896633148 2023-01-23 07:04:38.186378: step: 1376/1545, loss: 0.42471545934677124 2023-01-23 07:04:39.043027: step: 1378/1545, loss: 0.5174898505210876 2023-01-23 07:04:39.919614: step: 1380/1545, loss: 0.9307125210762024 2023-01-23 07:04:40.790837: step: 1382/1545, loss: 1.8176897764205933 2023-01-23 07:04:41.690538: step: 1384/1545, loss: 1.0810950994491577 2023-01-23 07:04:42.556788: step: 1386/1545, loss: 0.529879629611969 2023-01-23 07:04:43.419889: step: 1388/1545, loss: 0.5014030933380127 2023-01-23 07:04:44.308292: step: 1390/1545, loss: 0.5728806257247925 2023-01-23 07:04:45.194875: step: 1392/1545, loss: 0.43123722076416016 2023-01-23 07:04:46.102761: step: 1394/1545, loss: 0.8627728223800659 2023-01-23 07:04:46.973834: step: 1396/1545, loss: 3.268012285232544 2023-01-23 07:04:47.838208: step: 1398/1545, loss: 0.8095030784606934 2023-01-23 07:04:48.695137: step: 1400/1545, loss: 0.3445925712585449 2023-01-23 07:04:49.608823: step: 1402/1545, loss: 0.5973898768424988 2023-01-23 07:04:50.487124: step: 1404/1545, loss: 0.7075603604316711 2023-01-23 07:04:51.382883: step: 1406/1545, loss: 0.9803794026374817 2023-01-23 07:04:52.325852: step: 1408/1545, loss: 0.8817542791366577 2023-01-23 07:04:53.213095: step: 1410/1545, loss: 0.5020835995674133 2023-01-23 07:04:54.128477: step: 1412/1545, loss: 0.410902738571167 2023-01-23 07:04:55.109102: step: 1414/1545, loss: 0.884758710861206 2023-01-23 07:04:56.044185: step: 1416/1545, loss: 3.5251951217651367 2023-01-23 07:04:56.951565: step: 1418/1545, loss: 0.5553598403930664 2023-01-23 07:04:57.809089: step: 1420/1545, loss: 0.24004459381103516 2023-01-23 07:04:58.660613: step: 1422/1545, loss: 0.9069527387619019 2023-01-23 07:04:59.508254: step: 1424/1545, loss: 0.9829181432723999 2023-01-23 07:05:00.370618: step: 1426/1545, loss: 0.4528229832649231 2023-01-23 07:05:01.304627: step: 1428/1545, loss: 0.8795957565307617 2023-01-23 07:05:02.215240: step: 1430/1545, loss: 0.8235829472541809 2023-01-23 07:05:03.109949: step: 1432/1545, loss: 0.5431016683578491 2023-01-23 07:05:04.004476: step: 1434/1545, loss: 0.37106090784072876 2023-01-23 07:05:04.899878: step: 1436/1545, loss: 0.37874650955200195 2023-01-23 07:05:05.749540: step: 1438/1545, loss: 3.345534086227417 2023-01-23 07:05:06.678987: step: 1440/1545, loss: 0.9224960207939148 2023-01-23 07:05:07.559684: step: 1442/1545, loss: 1.55290949344635 2023-01-23 07:05:08.459377: step: 1444/1545, loss: 0.7843928337097168 2023-01-23 07:05:09.377836: step: 1446/1545, loss: 0.37682801485061646 2023-01-23 07:05:10.247464: step: 1448/1545, loss: 0.3725268244743347 2023-01-23 07:05:11.277587: step: 1450/1545, loss: 3.8426692485809326 2023-01-23 07:05:12.157501: step: 1452/1545, loss: 2.1005122661590576 2023-01-23 07:05:12.994574: step: 1454/1545, loss: 1.298583984375 2023-01-23 07:05:13.867457: step: 1456/1545, loss: 0.4544888138771057 2023-01-23 07:05:14.720847: step: 1458/1545, loss: 0.48727720975875854 2023-01-23 07:05:15.563507: step: 1460/1545, loss: 0.5627217888832092 2023-01-23 07:05:16.433737: step: 1462/1545, loss: 0.14250609278678894 2023-01-23 07:05:17.304475: step: 1464/1545, loss: 1.07443106174469 2023-01-23 07:05:18.191820: step: 1466/1545, loss: 0.7080105543136597 2023-01-23 07:05:19.064999: step: 1468/1545, loss: 1.6176310777664185 2023-01-23 07:05:19.939526: step: 1470/1545, loss: 3.793043613433838 2023-01-23 07:05:20.802346: step: 1472/1545, loss: 0.7633883953094482 2023-01-23 07:05:21.690034: step: 1474/1545, loss: 0.662463366985321 2023-01-23 07:05:22.587870: step: 1476/1545, loss: 1.3730452060699463 2023-01-23 07:05:23.535185: step: 1478/1545, loss: 0.8356965780258179 2023-01-23 07:05:24.429343: step: 1480/1545, loss: 0.41740405559539795 2023-01-23 07:05:25.307561: step: 1482/1545, loss: 0.4912091791629791 2023-01-23 07:05:26.191814: step: 1484/1545, loss: 0.6637025475502014 2023-01-23 07:05:27.061782: step: 1486/1545, loss: 1.181637167930603 2023-01-23 07:05:27.912505: step: 1488/1545, loss: 0.14443711936473846 2023-01-23 07:05:28.810308: step: 1490/1545, loss: 0.22467684745788574 2023-01-23 07:05:29.675889: step: 1492/1545, loss: 0.7982181310653687 2023-01-23 07:05:30.544646: step: 1494/1545, loss: 0.43553677201271057 2023-01-23 07:05:31.360096: step: 1496/1545, loss: 1.5880169868469238 2023-01-23 07:05:32.235707: step: 1498/1545, loss: 0.8693270087242126 2023-01-23 07:05:33.119368: step: 1500/1545, loss: 0.3354431688785553 2023-01-23 07:05:34.027196: step: 1502/1545, loss: 0.18143333494663239 2023-01-23 07:05:34.994234: step: 1504/1545, loss: 0.3608987033367157 2023-01-23 07:05:35.861171: step: 1506/1545, loss: 2.759978771209717 2023-01-23 07:05:36.711133: step: 1508/1545, loss: 0.8619982600212097 2023-01-23 07:05:37.629436: step: 1510/1545, loss: 0.9591243863105774 2023-01-23 07:05:38.554345: step: 1512/1545, loss: 0.41857677698135376 2023-01-23 07:05:39.419398: step: 1514/1545, loss: 0.31207436323165894 2023-01-23 07:05:40.274486: step: 1516/1545, loss: 0.870003342628479 2023-01-23 07:05:41.161593: step: 1518/1545, loss: 0.40422922372817993 2023-01-23 07:05:42.062745: step: 1520/1545, loss: 0.3637855052947998 2023-01-23 07:05:42.945680: step: 1522/1545, loss: 0.16519813239574432 2023-01-23 07:05:43.940649: step: 1524/1545, loss: 0.8699760437011719 2023-01-23 07:05:44.837499: step: 1526/1545, loss: 0.9578626155853271 2023-01-23 07:05:45.673525: step: 1528/1545, loss: 0.24421274662017822 2023-01-23 07:05:46.535708: step: 1530/1545, loss: 1.4284470081329346 2023-01-23 07:05:47.504731: step: 1532/1545, loss: 0.6062007546424866 2023-01-23 07:05:48.352932: step: 1534/1545, loss: 4.115848064422607 2023-01-23 07:05:49.240679: step: 1536/1545, loss: 2.991236925125122 2023-01-23 07:05:50.123704: step: 1538/1545, loss: 0.4376474618911743 2023-01-23 07:05:50.959320: step: 1540/1545, loss: 0.46135205030441284 2023-01-23 07:05:51.815433: step: 1542/1545, loss: 0.816552996635437 2023-01-23 07:05:52.743538: step: 1544/1545, loss: 1.079414963722229 2023-01-23 07:05:53.602212: step: 1546/1545, loss: 0.4514644742012024 2023-01-23 07:05:54.480384: step: 1548/1545, loss: 0.6358073353767395 2023-01-23 07:05:55.379587: step: 1550/1545, loss: 2.950098991394043 2023-01-23 07:05:56.267437: step: 1552/1545, loss: 0.6858778595924377 2023-01-23 07:05:57.160828: step: 1554/1545, loss: 1.394667625427246 2023-01-23 07:05:58.018657: step: 1556/1545, loss: 0.3093675374984741 2023-01-23 07:05:58.946535: step: 1558/1545, loss: 0.38894832134246826 2023-01-23 07:05:59.811046: step: 1560/1545, loss: 0.7949759364128113 2023-01-23 07:06:00.727514: step: 1562/1545, loss: 0.46820148825645447 2023-01-23 07:06:01.612976: step: 1564/1545, loss: 0.38167616724967957 2023-01-23 07:06:02.449205: step: 1566/1545, loss: 0.33969441056251526 2023-01-23 07:06:03.315134: step: 1568/1545, loss: 0.6495680809020996 2023-01-23 07:06:04.294249: step: 1570/1545, loss: 0.7150909304618835 2023-01-23 07:06:05.145696: step: 1572/1545, loss: 0.6531983613967896 2023-01-23 07:06:06.019594: step: 1574/1545, loss: 0.22280848026275635 2023-01-23 07:06:06.932169: step: 1576/1545, loss: 0.3698117733001709 2023-01-23 07:06:07.819330: step: 1578/1545, loss: 0.47595691680908203 2023-01-23 07:06:08.710886: step: 1580/1545, loss: 1.3501174449920654 2023-01-23 07:06:09.602458: step: 1582/1545, loss: 0.6739301681518555 2023-01-23 07:06:10.472562: step: 1584/1545, loss: 1.0017715692520142 2023-01-23 07:06:11.332975: step: 1586/1545, loss: 0.5180791020393372 2023-01-23 07:06:12.221243: step: 1588/1545, loss: 0.9644940495491028 2023-01-23 07:06:13.097860: step: 1590/1545, loss: 1.031062126159668 2023-01-23 07:06:13.932245: step: 1592/1545, loss: 0.4486284852027893 2023-01-23 07:06:14.870169: step: 1594/1545, loss: 0.5477848052978516 2023-01-23 07:06:15.770127: step: 1596/1545, loss: 0.78229820728302 2023-01-23 07:06:16.693345: step: 1598/1545, loss: 0.5687263607978821 2023-01-23 07:06:17.570907: step: 1600/1545, loss: 0.48968207836151123 2023-01-23 07:06:18.454253: step: 1602/1545, loss: 0.5343583822250366 2023-01-23 07:06:19.318905: step: 1604/1545, loss: 0.6186745166778564 2023-01-23 07:06:20.206375: step: 1606/1545, loss: 0.745535671710968 2023-01-23 07:06:21.100307: step: 1608/1545, loss: 0.5483789443969727 2023-01-23 07:06:22.027813: step: 1610/1545, loss: 0.47838547825813293 2023-01-23 07:06:22.898451: step: 1612/1545, loss: 0.33851906657218933 2023-01-23 07:06:23.750291: step: 1614/1545, loss: 0.5417491793632507 2023-01-23 07:06:24.709570: step: 1616/1545, loss: 0.5501264333724976 2023-01-23 07:06:25.571977: step: 1618/1545, loss: 0.42190301418304443 2023-01-23 07:06:26.436490: step: 1620/1545, loss: 0.5882989764213562 2023-01-23 07:06:27.292845: step: 1622/1545, loss: 0.44063425064086914 2023-01-23 07:06:28.150528: step: 1624/1545, loss: 0.488899290561676 2023-01-23 07:06:29.042996: step: 1626/1545, loss: 0.7594214677810669 2023-01-23 07:06:29.923680: step: 1628/1545, loss: 1.5885580778121948 2023-01-23 07:06:30.827758: step: 1630/1545, loss: 0.11065458506345749 2023-01-23 07:06:31.733436: step: 1632/1545, loss: 1.026435375213623 2023-01-23 07:06:32.661110: step: 1634/1545, loss: 0.8509678244590759 2023-01-23 07:06:33.545298: step: 1636/1545, loss: 0.6233675479888916 2023-01-23 07:06:34.440856: step: 1638/1545, loss: 0.19609840214252472 2023-01-23 07:06:35.305434: step: 1640/1545, loss: 0.753307044506073 2023-01-23 07:06:36.191034: step: 1642/1545, loss: 1.2787584066390991 2023-01-23 07:06:37.058888: step: 1644/1545, loss: 3.206465005874634 2023-01-23 07:06:37.927603: step: 1646/1545, loss: 1.1251246929168701 2023-01-23 07:06:38.788031: step: 1648/1545, loss: 0.4091956317424774 2023-01-23 07:06:39.681322: step: 1650/1545, loss: 1.0985733270645142 2023-01-23 07:06:40.544880: step: 1652/1545, loss: 0.6314365863800049 2023-01-23 07:06:41.401793: step: 1654/1545, loss: 0.5064471960067749 2023-01-23 07:06:42.275489: step: 1656/1545, loss: 0.6827453374862671 2023-01-23 07:06:43.131667: step: 1658/1545, loss: 0.7296227216720581 2023-01-23 07:06:44.040564: step: 1660/1545, loss: 0.8284912109375 2023-01-23 07:06:44.967772: step: 1662/1545, loss: 0.830720841884613 2023-01-23 07:06:45.833315: step: 1664/1545, loss: 0.6280282139778137 2023-01-23 07:06:46.684298: step: 1666/1545, loss: 0.6856997013092041 2023-01-23 07:06:47.607007: step: 1668/1545, loss: 0.8551082611083984 2023-01-23 07:06:48.526442: step: 1670/1545, loss: 2.268899917602539 2023-01-23 07:06:49.423158: step: 1672/1545, loss: 0.47113749384880066 2023-01-23 07:06:50.280215: step: 1674/1545, loss: 0.5310896039009094 2023-01-23 07:06:51.156059: step: 1676/1545, loss: 0.2501368820667267 2023-01-23 07:06:52.013926: step: 1678/1545, loss: 0.8922429084777832 2023-01-23 07:06:52.870741: step: 1680/1545, loss: 0.897113561630249 2023-01-23 07:06:53.749266: step: 1682/1545, loss: 0.4005351662635803 2023-01-23 07:06:54.626800: step: 1684/1545, loss: 0.6100523471832275 2023-01-23 07:06:55.500519: step: 1686/1545, loss: 0.3701263964176178 2023-01-23 07:06:56.444584: step: 1688/1545, loss: 0.35860249400138855 2023-01-23 07:06:57.359198: step: 1690/1545, loss: 0.24697081744670868 2023-01-23 07:06:58.249908: step: 1692/1545, loss: 0.25656798481941223 2023-01-23 07:06:59.151862: step: 1694/1545, loss: 0.3031778335571289 2023-01-23 07:07:00.027278: step: 1696/1545, loss: 0.4025399088859558 2023-01-23 07:07:01.006422: step: 1698/1545, loss: 0.871156632900238 2023-01-23 07:07:01.896256: step: 1700/1545, loss: 1.15049409866333 2023-01-23 07:07:02.753317: step: 1702/1545, loss: 2.720351219177246 2023-01-23 07:07:03.594296: step: 1704/1545, loss: 0.41698041558265686 2023-01-23 07:07:04.498616: step: 1706/1545, loss: 0.35964691638946533 2023-01-23 07:07:05.409510: step: 1708/1545, loss: 1.2253338098526 2023-01-23 07:07:06.342285: step: 1710/1545, loss: 6.8491902351379395 2023-01-23 07:07:07.179127: step: 1712/1545, loss: 0.4329913258552551 2023-01-23 07:07:08.105977: step: 1714/1545, loss: 1.701462984085083 2023-01-23 07:07:08.963942: step: 1716/1545, loss: 0.4141095280647278 2023-01-23 07:07:09.866988: step: 1718/1545, loss: 0.4702719748020172 2023-01-23 07:07:10.771584: step: 1720/1545, loss: 0.6626760959625244 2023-01-23 07:07:11.600170: step: 1722/1545, loss: 0.4675162136554718 2023-01-23 07:07:12.456185: step: 1724/1545, loss: 0.29403433203697205 2023-01-23 07:07:13.370735: step: 1726/1545, loss: 0.5598494410514832 2023-01-23 07:07:14.270185: step: 1728/1545, loss: 0.45644477009773254 2023-01-23 07:07:15.186045: step: 1730/1545, loss: 1.5554847717285156 2023-01-23 07:07:16.071257: step: 1732/1545, loss: 0.445308119058609 2023-01-23 07:07:16.952916: step: 1734/1545, loss: 0.36399608850479126 2023-01-23 07:07:17.791195: step: 1736/1545, loss: 0.12748755514621735 2023-01-23 07:07:18.690115: step: 1738/1545, loss: 1.1713975667953491 2023-01-23 07:07:19.553628: step: 1740/1545, loss: 0.4862375557422638 2023-01-23 07:07:20.417887: step: 1742/1545, loss: 0.4062744081020355 2023-01-23 07:07:21.330096: step: 1744/1545, loss: 1.1890772581100464 2023-01-23 07:07:22.228820: step: 1746/1545, loss: 3.3782730102539062 2023-01-23 07:07:23.114123: step: 1748/1545, loss: 1.2865076065063477 2023-01-23 07:07:23.975040: step: 1750/1545, loss: 0.7693016529083252 2023-01-23 07:07:24.864262: step: 1752/1545, loss: 0.6851909160614014 2023-01-23 07:07:25.746476: step: 1754/1545, loss: 3.5748746395111084 2023-01-23 07:07:26.600405: step: 1756/1545, loss: 0.7800940871238708 2023-01-23 07:07:27.494959: step: 1758/1545, loss: 1.119994878768921 2023-01-23 07:07:28.508014: step: 1760/1545, loss: 0.5812965035438538 2023-01-23 07:07:29.405716: step: 1762/1545, loss: 0.4014569818973541 2023-01-23 07:07:30.260173: step: 1764/1545, loss: 0.5167969465255737 2023-01-23 07:07:31.133870: step: 1766/1545, loss: 0.768390953540802 2023-01-23 07:07:32.034277: step: 1768/1545, loss: 0.9123548865318298 2023-01-23 07:07:32.949462: step: 1770/1545, loss: 0.8136498928070068 2023-01-23 07:07:33.840554: step: 1772/1545, loss: 0.25847935676574707 2023-01-23 07:07:34.714309: step: 1774/1545, loss: 0.5149414539337158 2023-01-23 07:07:35.592610: step: 1776/1545, loss: 0.909182608127594 2023-01-23 07:07:36.487150: step: 1778/1545, loss: 1.7181442975997925 2023-01-23 07:07:37.425912: step: 1780/1545, loss: 0.3743470311164856 2023-01-23 07:07:38.381995: step: 1782/1545, loss: 1.1139415502548218 2023-01-23 07:07:39.271948: step: 1784/1545, loss: 0.7162856459617615 2023-01-23 07:07:40.115839: step: 1786/1545, loss: 2.84142804145813 2023-01-23 07:07:40.951847: step: 1788/1545, loss: 1.4143849611282349 2023-01-23 07:07:41.825049: step: 1790/1545, loss: 0.4541093707084656 2023-01-23 07:07:42.711123: step: 1792/1545, loss: 0.646750271320343 2023-01-23 07:07:43.599788: step: 1794/1545, loss: 0.5390247106552124 2023-01-23 07:07:44.529312: step: 1796/1545, loss: 0.5883165001869202 2023-01-23 07:07:45.416997: step: 1798/1545, loss: 0.42643603682518005 2023-01-23 07:07:46.291144: step: 1800/1545, loss: 0.3783618211746216 2023-01-23 07:07:47.195671: step: 1802/1545, loss: 1.4330880641937256 2023-01-23 07:07:48.068049: step: 1804/1545, loss: 1.8101550340652466 2023-01-23 07:07:48.951270: step: 1806/1545, loss: 0.26723381876945496 2023-01-23 07:07:49.825361: step: 1808/1545, loss: 0.7419074773788452 2023-01-23 07:07:50.724905: step: 1810/1545, loss: 0.587172269821167 2023-01-23 07:07:51.636092: step: 1812/1545, loss: 0.20937252044677734 2023-01-23 07:07:52.524502: step: 1814/1545, loss: 0.8361580967903137 2023-01-23 07:07:53.386349: step: 1816/1545, loss: 0.6054602265357971 2023-01-23 07:07:54.346422: step: 1818/1545, loss: 0.7678704857826233 2023-01-23 07:07:55.237127: step: 1820/1545, loss: 0.42482826113700867 2023-01-23 07:07:56.121637: step: 1822/1545, loss: 1.1796438694000244 2023-01-23 07:07:57.047401: step: 1824/1545, loss: 0.41309624910354614 2023-01-23 07:07:57.943433: step: 1826/1545, loss: 0.5075334906578064 2023-01-23 07:07:58.779411: step: 1828/1545, loss: 0.47353172302246094 2023-01-23 07:07:59.718129: step: 1830/1545, loss: 0.49209287762641907 2023-01-23 07:08:00.598771: step: 1832/1545, loss: 0.5892300009727478 2023-01-23 07:08:01.456649: step: 1834/1545, loss: 1.1960983276367188 2023-01-23 07:08:02.309576: step: 1836/1545, loss: 0.4830595552921295 2023-01-23 07:08:03.164840: step: 1838/1545, loss: 0.31666314601898193 2023-01-23 07:08:04.052428: step: 1840/1545, loss: 0.3286648690700531 2023-01-23 07:08:04.972921: step: 1842/1545, loss: 0.7854427099227905 2023-01-23 07:08:05.797002: step: 1844/1545, loss: 0.8469856977462769 2023-01-23 07:08:06.682623: step: 1846/1545, loss: 0.5379553437232971 2023-01-23 07:08:07.616750: step: 1848/1545, loss: 0.8228965401649475 2023-01-23 07:08:08.475087: step: 1850/1545, loss: 0.2689565122127533 2023-01-23 07:08:09.369996: step: 1852/1545, loss: 2.401218891143799 2023-01-23 07:08:10.246271: step: 1854/1545, loss: 0.20916923880577087 2023-01-23 07:08:11.153302: step: 1856/1545, loss: 0.7801869511604309 2023-01-23 07:08:12.076753: step: 1858/1545, loss: 0.7741929888725281 2023-01-23 07:08:12.923581: step: 1860/1545, loss: 0.3336527943611145 2023-01-23 07:08:13.823842: step: 1862/1545, loss: 0.5230178833007812 2023-01-23 07:08:14.708804: step: 1864/1545, loss: 2.520202159881592 2023-01-23 07:08:15.629795: step: 1866/1545, loss: 0.6914812922477722 2023-01-23 07:08:16.499419: step: 1868/1545, loss: 0.36985328793525696 2023-01-23 07:08:17.399474: step: 1870/1545, loss: 1.66837477684021 2023-01-23 07:08:18.306141: step: 1872/1545, loss: 0.2590561807155609 2023-01-23 07:08:19.225895: step: 1874/1545, loss: 0.7428992390632629 2023-01-23 07:08:20.046087: step: 1876/1545, loss: 0.7565005421638489 2023-01-23 07:08:20.931616: step: 1878/1545, loss: 0.9320431351661682 2023-01-23 07:08:21.808823: step: 1880/1545, loss: 1.184208631515503 2023-01-23 07:08:22.709265: step: 1882/1545, loss: 0.25944221019744873 2023-01-23 07:08:23.691106: step: 1884/1545, loss: 0.512604296207428 2023-01-23 07:08:24.573804: step: 1886/1545, loss: 1.0825791358947754 2023-01-23 07:08:25.446016: step: 1888/1545, loss: 0.8550824522972107 2023-01-23 07:08:26.322252: step: 1890/1545, loss: 0.22284582257270813 2023-01-23 07:08:27.239244: step: 1892/1545, loss: 0.5132009983062744 2023-01-23 07:08:28.097896: step: 1894/1545, loss: 1.2897462844848633 2023-01-23 07:08:28.946461: step: 1896/1545, loss: 0.8239790201187134 2023-01-23 07:08:29.792097: step: 1898/1545, loss: 1.2178367376327515 2023-01-23 07:08:30.646252: step: 1900/1545, loss: 2.8198764324188232 2023-01-23 07:08:31.508359: step: 1902/1545, loss: 0.8640639185905457 2023-01-23 07:08:32.379070: step: 1904/1545, loss: 0.9084045886993408 2023-01-23 07:08:33.294529: step: 1906/1545, loss: 0.6621357202529907 2023-01-23 07:08:34.166189: step: 1908/1545, loss: 0.6683575510978699 2023-01-23 07:08:35.093604: step: 1910/1545, loss: 0.6975103616714478 2023-01-23 07:08:35.970041: step: 1912/1545, loss: 0.6081189513206482 2023-01-23 07:08:36.828139: step: 1914/1545, loss: 5.303460597991943 2023-01-23 07:08:37.693421: step: 1916/1545, loss: 0.9308074712753296 2023-01-23 07:08:38.583118: step: 1918/1545, loss: 0.3737744688987732 2023-01-23 07:08:39.453898: step: 1920/1545, loss: 0.5647538900375366 2023-01-23 07:08:40.348177: step: 1922/1545, loss: 1.1266485452651978 2023-01-23 07:08:41.196999: step: 1924/1545, loss: 0.1932772994041443 2023-01-23 07:08:42.055943: step: 1926/1545, loss: 0.6097514033317566 2023-01-23 07:08:42.938817: step: 1928/1545, loss: 0.44930872321128845 2023-01-23 07:08:43.803193: step: 1930/1545, loss: 0.40449249744415283 2023-01-23 07:08:44.691694: step: 1932/1545, loss: 0.7294046878814697 2023-01-23 07:08:45.556507: step: 1934/1545, loss: 0.8196622133255005 2023-01-23 07:08:46.531346: step: 1936/1545, loss: 0.5349857807159424 2023-01-23 07:08:47.398985: step: 1938/1545, loss: 0.6963149905204773 2023-01-23 07:08:48.263903: step: 1940/1545, loss: 0.5634703636169434 2023-01-23 07:08:49.163816: step: 1942/1545, loss: 0.5431591868400574 2023-01-23 07:08:50.056743: step: 1944/1545, loss: 0.354282408952713 2023-01-23 07:08:50.899921: step: 1946/1545, loss: 0.587565541267395 2023-01-23 07:08:51.751948: step: 1948/1545, loss: 0.6407392621040344 2023-01-23 07:08:52.594887: step: 1950/1545, loss: 0.20443302392959595 2023-01-23 07:08:53.463228: step: 1952/1545, loss: 0.7622167468070984 2023-01-23 07:08:54.308038: step: 1954/1545, loss: 0.3714374005794525 2023-01-23 07:08:55.220579: step: 1956/1545, loss: 0.5377883911132812 2023-01-23 07:08:56.107839: step: 1958/1545, loss: 0.4775814414024353 2023-01-23 07:08:56.956638: step: 1960/1545, loss: 0.303182989358902 2023-01-23 07:08:57.835613: step: 1962/1545, loss: 0.27247223258018494 2023-01-23 07:08:58.723416: step: 1964/1545, loss: 0.7616614103317261 2023-01-23 07:08:59.656044: step: 1966/1545, loss: 1.9630589485168457 2023-01-23 07:09:00.515879: step: 1968/1545, loss: 0.8943546414375305 2023-01-23 07:09:01.389239: step: 1970/1545, loss: 0.7921478748321533 2023-01-23 07:09:02.307481: step: 1972/1545, loss: 1.3261785507202148 2023-01-23 07:09:03.166209: step: 1974/1545, loss: 0.3235645890235901 2023-01-23 07:09:04.076527: step: 1976/1545, loss: 0.8305429220199585 2023-01-23 07:09:04.926526: step: 1978/1545, loss: 0.20832620561122894 2023-01-23 07:09:05.809311: step: 1980/1545, loss: 0.45921918749809265 2023-01-23 07:09:06.693589: step: 1982/1545, loss: 1.067854404449463 2023-01-23 07:09:07.557912: step: 1984/1545, loss: 1.325471043586731 2023-01-23 07:09:08.519071: step: 1986/1545, loss: 0.297122597694397 2023-01-23 07:09:09.379444: step: 1988/1545, loss: 0.41035181283950806 2023-01-23 07:09:10.265224: step: 1990/1545, loss: 0.3735405206680298 2023-01-23 07:09:11.192669: step: 1992/1545, loss: 0.40115320682525635 2023-01-23 07:09:12.060774: step: 1994/1545, loss: 0.3695565462112427 2023-01-23 07:09:12.919825: step: 1996/1545, loss: 0.6582939028739929 2023-01-23 07:09:13.779874: step: 1998/1545, loss: 0.5883685946464539 2023-01-23 07:09:14.685444: step: 2000/1545, loss: 0.7582486867904663 2023-01-23 07:09:15.537468: step: 2002/1545, loss: 1.3722922801971436 2023-01-23 07:09:16.401696: step: 2004/1545, loss: 0.34449833631515503 2023-01-23 07:09:17.242434: step: 2006/1545, loss: 1.021224021911621 2023-01-23 07:09:18.091194: step: 2008/1545, loss: 0.26506561040878296 2023-01-23 07:09:18.960226: step: 2010/1545, loss: 0.9752325415611267 2023-01-23 07:09:19.889284: step: 2012/1545, loss: 0.7433720827102661 2023-01-23 07:09:20.737747: step: 2014/1545, loss: 0.7108146548271179 2023-01-23 07:09:21.614009: step: 2016/1545, loss: 0.49137958884239197 2023-01-23 07:09:22.483288: step: 2018/1545, loss: 0.4485519528388977 2023-01-23 07:09:23.329848: step: 2020/1545, loss: 0.6751546263694763 2023-01-23 07:09:24.198714: step: 2022/1545, loss: 0.18145886063575745 2023-01-23 07:09:25.094748: step: 2024/1545, loss: 0.6187326312065125 2023-01-23 07:09:25.960883: step: 2026/1545, loss: 0.7719003558158875 2023-01-23 07:09:26.822533: step: 2028/1545, loss: 0.7926626801490784 2023-01-23 07:09:27.741833: step: 2030/1545, loss: 0.80987149477005 2023-01-23 07:09:28.658678: step: 2032/1545, loss: 0.32340651750564575 2023-01-23 07:09:29.544131: step: 2034/1545, loss: 0.32402342557907104 2023-01-23 07:09:30.389671: step: 2036/1545, loss: 1.3976353406906128 2023-01-23 07:09:31.283533: step: 2038/1545, loss: 0.5858558416366577 2023-01-23 07:09:32.148523: step: 2040/1545, loss: 2.8905534744262695 2023-01-23 07:09:33.058761: step: 2042/1545, loss: 0.8496806025505066 2023-01-23 07:09:34.091950: step: 2044/1545, loss: 0.7175456881523132 2023-01-23 07:09:34.980644: step: 2046/1545, loss: 0.60645592212677 2023-01-23 07:09:35.852385: step: 2048/1545, loss: 0.7803036570549011 2023-01-23 07:09:36.791524: step: 2050/1545, loss: 0.709891676902771 2023-01-23 07:09:37.652120: step: 2052/1545, loss: 0.6406861543655396 2023-01-23 07:09:38.508829: step: 2054/1545, loss: 0.3537514805793762 2023-01-23 07:09:39.380518: step: 2056/1545, loss: 0.288837730884552 2023-01-23 07:09:40.284781: step: 2058/1545, loss: 0.45113956928253174 2023-01-23 07:09:41.194451: step: 2060/1545, loss: 1.0123366117477417 2023-01-23 07:09:42.083230: step: 2062/1545, loss: 0.3146979510784149 2023-01-23 07:09:42.962159: step: 2064/1545, loss: 1.0180493593215942 2023-01-23 07:09:43.860242: step: 2066/1545, loss: 0.8369433879852295 2023-01-23 07:09:44.760095: step: 2068/1545, loss: 0.735474169254303 2023-01-23 07:09:45.639161: step: 2070/1545, loss: 0.6744190454483032 2023-01-23 07:09:46.525439: step: 2072/1545, loss: 6.2720417976379395 2023-01-23 07:09:47.378548: step: 2074/1545, loss: 0.8992842435836792 2023-01-23 07:09:48.278311: step: 2076/1545, loss: 0.6964024305343628 2023-01-23 07:09:49.278987: step: 2078/1545, loss: 0.6635973453521729 2023-01-23 07:09:50.128007: step: 2080/1545, loss: 0.7148681879043579 2023-01-23 07:09:50.997249: step: 2082/1545, loss: 0.4019063115119934 2023-01-23 07:09:51.882163: step: 2084/1545, loss: 0.7703628540039062 2023-01-23 07:09:52.765570: step: 2086/1545, loss: 3.356257915496826 2023-01-23 07:09:53.619896: step: 2088/1545, loss: 0.233237162232399 2023-01-23 07:09:54.493824: step: 2090/1545, loss: 0.7420739531517029 2023-01-23 07:09:55.349861: step: 2092/1545, loss: 0.38946637511253357 2023-01-23 07:09:56.197248: step: 2094/1545, loss: 0.7138599753379822 2023-01-23 07:09:57.062726: step: 2096/1545, loss: 0.4380597174167633 2023-01-23 07:09:57.974066: step: 2098/1545, loss: 1.2267986536026 2023-01-23 07:09:58.874501: step: 2100/1545, loss: 1.0993986129760742 2023-01-23 07:09:59.764179: step: 2102/1545, loss: 0.5408153533935547 2023-01-23 07:10:00.651800: step: 2104/1545, loss: 0.9850885272026062 2023-01-23 07:10:01.493442: step: 2106/1545, loss: 0.5634206533432007 2023-01-23 07:10:02.406659: step: 2108/1545, loss: 0.7850678563117981 2023-01-23 07:10:03.299704: step: 2110/1545, loss: 1.2966781854629517 2023-01-23 07:10:04.200860: step: 2112/1545, loss: 1.053598165512085 2023-01-23 07:10:05.041608: step: 2114/1545, loss: 0.4346238970756531 2023-01-23 07:10:05.899785: step: 2116/1545, loss: 1.069196105003357 2023-01-23 07:10:06.772953: step: 2118/1545, loss: 0.3236140310764313 2023-01-23 07:10:07.614858: step: 2120/1545, loss: 0.5901090502738953 2023-01-23 07:10:08.532591: step: 2122/1545, loss: 0.49493667483329773 2023-01-23 07:10:09.409802: step: 2124/1545, loss: 1.277878999710083 2023-01-23 07:10:10.269270: step: 2126/1545, loss: 0.32876870036125183 2023-01-23 07:10:11.165367: step: 2128/1545, loss: 0.9711942076683044 2023-01-23 07:10:12.073068: step: 2130/1545, loss: 0.40672287344932556 2023-01-23 07:10:12.960362: step: 2132/1545, loss: 2.0395007133483887 2023-01-23 07:10:13.846917: step: 2134/1545, loss: 0.5408305525779724 2023-01-23 07:10:14.726367: step: 2136/1545, loss: 0.8881927728652954 2023-01-23 07:10:15.593354: step: 2138/1545, loss: 0.9611845016479492 2023-01-23 07:10:16.470319: step: 2140/1545, loss: 3.1826934814453125 2023-01-23 07:10:17.327484: step: 2142/1545, loss: 0.6302477121353149 2023-01-23 07:10:18.167590: step: 2144/1545, loss: 0.4694052040576935 2023-01-23 07:10:19.116706: step: 2146/1545, loss: 0.60160893201828 2023-01-23 07:10:20.022401: step: 2148/1545, loss: 0.4349803626537323 2023-01-23 07:10:20.894678: step: 2150/1545, loss: 0.5013397932052612 2023-01-23 07:10:21.774932: step: 2152/1545, loss: 0.8504445552825928 2023-01-23 07:10:22.646544: step: 2154/1545, loss: 0.3626965284347534 2023-01-23 07:10:23.515774: step: 2156/1545, loss: 0.9202859401702881 2023-01-23 07:10:24.487867: step: 2158/1545, loss: 0.5040654540061951 2023-01-23 07:10:25.334900: step: 2160/1545, loss: 0.4727645218372345 2023-01-23 07:10:26.315906: step: 2162/1545, loss: 5.253635883331299 2023-01-23 07:10:27.224447: step: 2164/1545, loss: 3.1143381595611572 2023-01-23 07:10:28.151776: step: 2166/1545, loss: 0.4115419387817383 2023-01-23 07:10:29.009368: step: 2168/1545, loss: 3.3942501544952393 2023-01-23 07:10:29.888114: step: 2170/1545, loss: 0.6615109443664551 2023-01-23 07:10:30.747511: step: 2172/1545, loss: 0.5100424885749817 2023-01-23 07:10:31.633942: step: 2174/1545, loss: 1.309809684753418 2023-01-23 07:10:32.510744: step: 2176/1545, loss: 0.5472327470779419 2023-01-23 07:10:33.437705: step: 2178/1545, loss: 7.32505989074707 2023-01-23 07:10:34.325664: step: 2180/1545, loss: 0.4955712556838989 2023-01-23 07:10:35.206646: step: 2182/1545, loss: 1.2491801977157593 2023-01-23 07:10:36.056536: step: 2184/1545, loss: 0.6350496411323547 2023-01-23 07:10:36.906828: step: 2186/1545, loss: 0.3574397563934326 2023-01-23 07:10:37.814396: step: 2188/1545, loss: 0.8030209541320801 2023-01-23 07:10:38.647284: step: 2190/1545, loss: 0.5282435417175293 2023-01-23 07:10:39.519293: step: 2192/1545, loss: 0.3395693898200989 2023-01-23 07:10:40.386576: step: 2194/1545, loss: 0.6634287238121033 2023-01-23 07:10:41.256849: step: 2196/1545, loss: 0.5120567679405212 2023-01-23 07:10:42.150585: step: 2198/1545, loss: 0.47239500284194946 2023-01-23 07:10:43.005849: step: 2200/1545, loss: 0.7407844066619873 2023-01-23 07:10:43.943894: step: 2202/1545, loss: 0.5750683546066284 2023-01-23 07:10:44.844461: step: 2204/1545, loss: 0.7756746411323547 2023-01-23 07:10:45.693273: step: 2206/1545, loss: 0.5129026770591736 2023-01-23 07:10:46.622482: step: 2208/1545, loss: 0.5345216989517212 2023-01-23 07:10:47.506274: step: 2210/1545, loss: 0.948448896408081 2023-01-23 07:10:48.374150: step: 2212/1545, loss: 0.4452264904975891 2023-01-23 07:10:49.254088: step: 2214/1545, loss: 0.5561801791191101 2023-01-23 07:10:50.122035: step: 2216/1545, loss: 0.6485195159912109 2023-01-23 07:10:50.962237: step: 2218/1545, loss: 0.3696850538253784 2023-01-23 07:10:51.831019: step: 2220/1545, loss: 0.18146798014640808 2023-01-23 07:10:52.682921: step: 2222/1545, loss: 0.40587493777275085 2023-01-23 07:10:53.698316: step: 2224/1545, loss: 0.14408044517040253 2023-01-23 07:10:54.585695: step: 2226/1545, loss: 0.35796642303466797 2023-01-23 07:10:55.518197: step: 2228/1545, loss: 0.6304763555526733 2023-01-23 07:10:56.371083: step: 2230/1545, loss: 0.6152441501617432 2023-01-23 07:10:57.256539: step: 2232/1545, loss: 0.7355676889419556 2023-01-23 07:10:58.104562: step: 2234/1545, loss: 1.0417108535766602 2023-01-23 07:10:58.989716: step: 2236/1545, loss: 0.8329203128814697 2023-01-23 07:10:59.843090: step: 2238/1545, loss: 0.35014113783836365 2023-01-23 07:11:00.735884: step: 2240/1545, loss: 0.44222280383110046 2023-01-23 07:11:01.610679: step: 2242/1545, loss: 0.7137089371681213 2023-01-23 07:11:02.474781: step: 2244/1545, loss: 0.45413637161254883 2023-01-23 07:11:03.339247: step: 2246/1545, loss: 1.017886757850647 2023-01-23 07:11:04.192873: step: 2248/1545, loss: 1.4399492740631104 2023-01-23 07:11:05.089945: step: 2250/1545, loss: 0.8772203922271729 2023-01-23 07:11:05.982948: step: 2252/1545, loss: 0.29772087931632996 2023-01-23 07:11:06.888203: step: 2254/1545, loss: 0.5994104743003845 2023-01-23 07:11:07.767400: step: 2256/1545, loss: 0.9523487687110901 2023-01-23 07:11:08.619574: step: 2258/1545, loss: 0.26314541697502136 2023-01-23 07:11:09.476710: step: 2260/1545, loss: 0.77487713098526 2023-01-23 07:11:10.360724: step: 2262/1545, loss: 1.4141104221343994 2023-01-23 07:11:11.246910: step: 2264/1545, loss: 0.23284339904785156 2023-01-23 07:11:12.180774: step: 2266/1545, loss: 1.2435102462768555 2023-01-23 07:11:13.065739: step: 2268/1545, loss: 0.3951057195663452 2023-01-23 07:11:13.962003: step: 2270/1545, loss: 0.4697912335395813 2023-01-23 07:11:14.971702: step: 2272/1545, loss: 0.5913233757019043 2023-01-23 07:11:15.868638: step: 2274/1545, loss: 0.27854761481285095 2023-01-23 07:11:16.765870: step: 2276/1545, loss: 0.41350626945495605 2023-01-23 07:11:17.669208: step: 2278/1545, loss: 0.2874518036842346 2023-01-23 07:11:18.604814: step: 2280/1545, loss: 0.6188335418701172 2023-01-23 07:11:19.478948: step: 2282/1545, loss: 0.7721560001373291 2023-01-23 07:11:20.366391: step: 2284/1545, loss: 0.38569191098213196 2023-01-23 07:11:21.226444: step: 2286/1545, loss: 2.603937864303589 2023-01-23 07:11:22.109206: step: 2288/1545, loss: 0.841926634311676 2023-01-23 07:11:22.970834: step: 2290/1545, loss: 0.35500943660736084 2023-01-23 07:11:23.887447: step: 2292/1545, loss: 0.4254674017429352 2023-01-23 07:11:24.772029: step: 2294/1545, loss: 0.8550783395767212 2023-01-23 07:11:25.673357: step: 2296/1545, loss: 0.24945427477359772 2023-01-23 07:11:26.543100: step: 2298/1545, loss: 1.7710539102554321 2023-01-23 07:11:27.447109: step: 2300/1545, loss: 1.1459641456604004 2023-01-23 07:11:28.366950: step: 2302/1545, loss: 0.5839455723762512 2023-01-23 07:11:29.249959: step: 2304/1545, loss: 0.7062535285949707 2023-01-23 07:11:30.117781: step: 2306/1545, loss: 0.5272574424743652 2023-01-23 07:11:31.002502: step: 2308/1545, loss: 0.815822422504425 2023-01-23 07:11:31.851196: step: 2310/1545, loss: 0.25487393140792847 2023-01-23 07:11:32.737257: step: 2312/1545, loss: 0.7158369421958923 2023-01-23 07:11:33.570091: step: 2314/1545, loss: 0.5917204022407532 2023-01-23 07:11:34.460760: step: 2316/1545, loss: 0.3226301670074463 2023-01-23 07:11:35.339746: step: 2318/1545, loss: 0.70396888256073 2023-01-23 07:11:36.178260: step: 2320/1545, loss: 0.40422093868255615 2023-01-23 07:11:37.030373: step: 2322/1545, loss: 0.17904460430145264 2023-01-23 07:11:37.878419: step: 2324/1545, loss: 0.4737340211868286 2023-01-23 07:11:38.750718: step: 2326/1545, loss: 6.666106224060059 2023-01-23 07:11:39.607303: step: 2328/1545, loss: 0.40432873368263245 2023-01-23 07:11:40.492354: step: 2330/1545, loss: 0.36293572187423706 2023-01-23 07:11:41.445547: step: 2332/1545, loss: 0.5664627552032471 2023-01-23 07:11:42.292894: step: 2334/1545, loss: 0.8089752197265625 2023-01-23 07:11:43.188683: step: 2336/1545, loss: 0.8560605049133301 2023-01-23 07:11:44.066962: step: 2338/1545, loss: 0.7034879922866821 2023-01-23 07:11:44.906349: step: 2340/1545, loss: 0.4999226927757263 2023-01-23 07:11:45.741720: step: 2342/1545, loss: 1.463930606842041 2023-01-23 07:11:46.597663: step: 2344/1545, loss: 0.9342858791351318 2023-01-23 07:11:47.460366: step: 2346/1545, loss: 0.8946669697761536 2023-01-23 07:11:48.295911: step: 2348/1545, loss: 0.6820348501205444 2023-01-23 07:11:49.143607: step: 2350/1545, loss: 0.6715524196624756 2023-01-23 07:11:50.000030: step: 2352/1545, loss: 0.29505953192710876 2023-01-23 07:11:50.844178: step: 2354/1545, loss: 3.086467742919922 2023-01-23 07:11:51.745400: step: 2356/1545, loss: 0.6016338467597961 2023-01-23 07:11:52.595316: step: 2358/1545, loss: 1.1711852550506592 2023-01-23 07:11:53.488066: step: 2360/1545, loss: 2.640031099319458 2023-01-23 07:11:54.338268: step: 2362/1545, loss: 0.374644935131073 2023-01-23 07:11:55.170537: step: 2364/1545, loss: 0.5563400983810425 2023-01-23 07:11:56.102941: step: 2366/1545, loss: 0.3292029798030853 2023-01-23 07:11:57.020934: step: 2368/1545, loss: 6.006721019744873 2023-01-23 07:11:57.930386: step: 2370/1545, loss: 0.5976297855377197 2023-01-23 07:11:58.791251: step: 2372/1545, loss: 0.7143774628639221 2023-01-23 07:11:59.674332: step: 2374/1545, loss: 1.0688749551773071 2023-01-23 07:12:00.580163: step: 2376/1545, loss: 0.35912975668907166 2023-01-23 07:12:01.467601: step: 2378/1545, loss: 0.9131386876106262 2023-01-23 07:12:02.342000: step: 2380/1545, loss: 1.0821212530136108 2023-01-23 07:12:03.208155: step: 2382/1545, loss: 0.9634374976158142 2023-01-23 07:12:04.101831: step: 2384/1545, loss: 0.6072725057601929 2023-01-23 07:12:04.997271: step: 2386/1545, loss: 0.6680231690406799 2023-01-23 07:12:05.876613: step: 2388/1545, loss: 1.0850768089294434 2023-01-23 07:12:06.762121: step: 2390/1545, loss: 1.069837212562561 2023-01-23 07:12:07.606444: step: 2392/1545, loss: 1.6740450859069824 2023-01-23 07:12:08.489548: step: 2394/1545, loss: 0.6231518387794495 2023-01-23 07:12:09.377562: step: 2396/1545, loss: 0.5547047853469849 2023-01-23 07:12:10.252742: step: 2398/1545, loss: 0.4499553442001343 2023-01-23 07:12:11.124756: step: 2400/1545, loss: 0.4018017649650574 2023-01-23 07:12:12.048262: step: 2402/1545, loss: 0.4628877639770508 2023-01-23 07:12:12.917738: step: 2404/1545, loss: 0.3398647606372833 2023-01-23 07:12:13.810443: step: 2406/1545, loss: 0.8448259234428406 2023-01-23 07:12:14.664464: step: 2408/1545, loss: 0.27846574783325195 2023-01-23 07:12:15.547724: step: 2410/1545, loss: 0.24522165954113007 2023-01-23 07:12:16.416630: step: 2412/1545, loss: 1.1643370389938354 2023-01-23 07:12:17.302418: step: 2414/1545, loss: 1.2361137866973877 2023-01-23 07:12:18.159707: step: 2416/1545, loss: 2.0345571041107178 2023-01-23 07:12:19.041637: step: 2418/1545, loss: 0.7459917664527893 2023-01-23 07:12:19.950096: step: 2420/1545, loss: 1.312364101409912 2023-01-23 07:12:20.839361: step: 2422/1545, loss: 0.5377834439277649 2023-01-23 07:12:21.723931: step: 2424/1545, loss: 0.582134485244751 2023-01-23 07:12:22.589069: step: 2426/1545, loss: 0.4537101089954376 2023-01-23 07:12:23.467327: step: 2428/1545, loss: 0.4800664484500885 2023-01-23 07:12:24.353384: step: 2430/1545, loss: 0.46679869294166565 2023-01-23 07:12:25.349783: step: 2432/1545, loss: 3.035134792327881 2023-01-23 07:12:26.245011: step: 2434/1545, loss: 0.45931848883628845 2023-01-23 07:12:27.105642: step: 2436/1545, loss: 0.3045114278793335 2023-01-23 07:12:28.018205: step: 2438/1545, loss: 0.4169117212295532 2023-01-23 07:12:28.901839: step: 2440/1545, loss: 1.189041018486023 2023-01-23 07:12:29.748747: step: 2442/1545, loss: 0.36045002937316895 2023-01-23 07:12:30.622661: step: 2444/1545, loss: 0.40710097551345825 2023-01-23 07:12:31.487959: step: 2446/1545, loss: 0.5637850761413574 2023-01-23 07:12:32.363978: step: 2448/1545, loss: 0.3347185254096985 2023-01-23 07:12:33.279994: step: 2450/1545, loss: 0.8643357753753662 2023-01-23 07:12:34.153965: step: 2452/1545, loss: 0.34080082178115845 2023-01-23 07:12:35.062226: step: 2454/1545, loss: 0.44572213292121887 2023-01-23 07:12:35.963747: step: 2456/1545, loss: 0.3678855299949646 2023-01-23 07:12:36.847010: step: 2458/1545, loss: 0.9357534050941467 2023-01-23 07:12:37.719291: step: 2460/1545, loss: 1.0562999248504639 2023-01-23 07:12:38.575417: step: 2462/1545, loss: 3.158867120742798 2023-01-23 07:12:39.419129: step: 2464/1545, loss: 0.7709726691246033 2023-01-23 07:12:40.298110: step: 2466/1545, loss: 0.26585134863853455 2023-01-23 07:12:41.153941: step: 2468/1545, loss: 0.6244451403617859 2023-01-23 07:12:41.986192: step: 2470/1545, loss: 1.1143410205841064 2023-01-23 07:12:42.881493: step: 2472/1545, loss: 0.7414608001708984 2023-01-23 07:12:43.722784: step: 2474/1545, loss: 0.914901614189148 2023-01-23 07:12:44.561607: step: 2476/1545, loss: 0.7816883325576782 2023-01-23 07:12:45.457200: step: 2478/1545, loss: 0.509016215801239 2023-01-23 07:12:46.345014: step: 2480/1545, loss: 1.3139458894729614 2023-01-23 07:12:47.213778: step: 2482/1545, loss: 1.0690560340881348 2023-01-23 07:12:48.067181: step: 2484/1545, loss: 0.53706294298172 2023-01-23 07:12:48.977560: step: 2486/1545, loss: 0.8048719763755798 2023-01-23 07:12:49.840328: step: 2488/1545, loss: 0.8626259565353394 2023-01-23 07:12:50.731168: step: 2490/1545, loss: 0.31385260820388794 2023-01-23 07:12:51.607582: step: 2492/1545, loss: 0.3339175283908844 2023-01-23 07:12:52.472150: step: 2494/1545, loss: 0.34423375129699707 2023-01-23 07:12:53.406404: step: 2496/1545, loss: 0.8473989367485046 2023-01-23 07:12:54.259941: step: 2498/1545, loss: 1.388164758682251 2023-01-23 07:12:55.162728: step: 2500/1545, loss: 0.3987504243850708 2023-01-23 07:12:56.139508: step: 2502/1545, loss: 3.308908224105835 2023-01-23 07:12:56.967014: step: 2504/1545, loss: 0.4740947484970093 2023-01-23 07:12:57.835351: step: 2506/1545, loss: 0.6571619510650635 2023-01-23 07:12:58.775485: step: 2508/1545, loss: 0.7713498473167419 2023-01-23 07:12:59.620704: step: 2510/1545, loss: 0.495835542678833 2023-01-23 07:13:00.576177: step: 2512/1545, loss: 0.34113049507141113 2023-01-23 07:13:01.478169: step: 2514/1545, loss: 0.6357412338256836 2023-01-23 07:13:02.368844: step: 2516/1545, loss: 0.2891641855239868 2023-01-23 07:13:03.261836: step: 2518/1545, loss: 0.3959623873233795 2023-01-23 07:13:04.139089: step: 2520/1545, loss: 0.5367554426193237 2023-01-23 07:13:05.045729: step: 2522/1545, loss: 1.0809149742126465 2023-01-23 07:13:05.958360: step: 2524/1545, loss: 0.24668608605861664 2023-01-23 07:13:06.811599: step: 2526/1545, loss: 0.4667195975780487 2023-01-23 07:13:07.691611: step: 2528/1545, loss: 0.3509114384651184 2023-01-23 07:13:08.558250: step: 2530/1545, loss: 0.5563684701919556 2023-01-23 07:13:09.413326: step: 2532/1545, loss: 0.2817223072052002 2023-01-23 07:13:10.307336: step: 2534/1545, loss: 0.20032842457294464 2023-01-23 07:13:11.213529: step: 2536/1545, loss: 0.519745945930481 2023-01-23 07:13:12.095390: step: 2538/1545, loss: 0.7192205190658569 2023-01-23 07:13:12.954150: step: 2540/1545, loss: 0.2579615116119385 2023-01-23 07:13:13.892724: step: 2542/1545, loss: 0.32710450887680054 2023-01-23 07:13:14.733477: step: 2544/1545, loss: 2.6850078105926514 2023-01-23 07:13:15.624365: step: 2546/1545, loss: 1.3537373542785645 2023-01-23 07:13:16.474432: step: 2548/1545, loss: 0.7728175520896912 2023-01-23 07:13:17.330800: step: 2550/1545, loss: 0.2276400476694107 2023-01-23 07:13:18.193630: step: 2552/1545, loss: 0.909138560295105 2023-01-23 07:13:19.063986: step: 2554/1545, loss: 0.6386112570762634 2023-01-23 07:13:19.946966: step: 2556/1545, loss: 0.38396868109703064 2023-01-23 07:13:20.840501: step: 2558/1545, loss: 0.4178643822669983 2023-01-23 07:13:21.702928: step: 2560/1545, loss: 0.2904616892337799 2023-01-23 07:13:22.564148: step: 2562/1545, loss: 0.24206219613552094 2023-01-23 07:13:23.421923: step: 2564/1545, loss: 0.7666686177253723 2023-01-23 07:13:24.324425: step: 2566/1545, loss: 0.5468252897262573 2023-01-23 07:13:25.219234: step: 2568/1545, loss: 1.1007980108261108 2023-01-23 07:13:26.078542: step: 2570/1545, loss: 0.8089632391929626 2023-01-23 07:13:26.970962: step: 2572/1545, loss: 0.9118446707725525 2023-01-23 07:13:27.814097: step: 2574/1545, loss: 1.0998164415359497 2023-01-23 07:13:28.717061: step: 2576/1545, loss: 0.9282693862915039 2023-01-23 07:13:29.601735: step: 2578/1545, loss: 0.27874481678009033 2023-01-23 07:13:30.506771: step: 2580/1545, loss: 0.6014619469642639 2023-01-23 07:13:31.405147: step: 2582/1545, loss: 0.39828166365623474 2023-01-23 07:13:32.315751: step: 2584/1545, loss: 0.3193552792072296 2023-01-23 07:13:33.200175: step: 2586/1545, loss: 0.748534619808197 2023-01-23 07:13:34.085763: step: 2588/1545, loss: 0.7185123562812805 2023-01-23 07:13:34.943312: step: 2590/1545, loss: 0.31764087080955505 2023-01-23 07:13:35.849239: step: 2592/1545, loss: 0.8082343935966492 2023-01-23 07:13:36.758492: step: 2594/1545, loss: 0.7309175133705139 2023-01-23 07:13:37.617843: step: 2596/1545, loss: 1.022542119026184 2023-01-23 07:13:38.533760: step: 2598/1545, loss: 0.6405450105667114 2023-01-23 07:13:39.399357: step: 2600/1545, loss: 6.442676067352295 2023-01-23 07:13:40.258765: step: 2602/1545, loss: 0.7782634496688843 2023-01-23 07:13:41.121735: step: 2604/1545, loss: 0.7506415843963623 2023-01-23 07:13:42.016855: step: 2606/1545, loss: 0.7733330130577087 2023-01-23 07:13:42.874017: step: 2608/1545, loss: 0.34637171030044556 2023-01-23 07:13:43.783076: step: 2610/1545, loss: 0.9137457013130188 2023-01-23 07:13:44.677613: step: 2612/1545, loss: 0.37345367670059204 2023-01-23 07:13:45.576102: step: 2614/1545, loss: 0.7066261768341064 2023-01-23 07:13:46.444407: step: 2616/1545, loss: 0.8076724410057068 2023-01-23 07:13:47.324876: step: 2618/1545, loss: 1.125542402267456 2023-01-23 07:13:48.244446: step: 2620/1545, loss: 1.3866944313049316 2023-01-23 07:13:49.152891: step: 2622/1545, loss: 0.6096787452697754 2023-01-23 07:13:50.023689: step: 2624/1545, loss: 0.3690956234931946 2023-01-23 07:13:50.894002: step: 2626/1545, loss: 1.0127702951431274 2023-01-23 07:13:51.760501: step: 2628/1545, loss: 0.551329493522644 2023-01-23 07:13:52.624246: step: 2630/1545, loss: 0.5534269213676453 2023-01-23 07:13:53.506338: step: 2632/1545, loss: 0.6066418886184692 2023-01-23 07:13:54.411481: step: 2634/1545, loss: 0.8854458332061768 2023-01-23 07:13:55.300595: step: 2636/1545, loss: 0.7036030292510986 2023-01-23 07:13:56.149112: step: 2638/1545, loss: 0.33756598830223083 2023-01-23 07:13:57.045769: step: 2640/1545, loss: 0.9529829621315002 2023-01-23 07:13:57.950412: step: 2642/1545, loss: 0.4027285575866699 2023-01-23 07:13:58.827272: step: 2644/1545, loss: 0.09860904514789581 2023-01-23 07:13:59.766085: step: 2646/1545, loss: 0.5362284183502197 2023-01-23 07:14:00.715292: step: 2648/1545, loss: 0.14244519174098969 2023-01-23 07:14:01.591744: step: 2650/1545, loss: 0.11581730097532272 2023-01-23 07:14:02.481153: step: 2652/1545, loss: 1.0465924739837646 2023-01-23 07:14:03.362733: step: 2654/1545, loss: 1.284583330154419 2023-01-23 07:14:04.327978: step: 2656/1545, loss: 0.5493966937065125 2023-01-23 07:14:05.200497: step: 2658/1545, loss: 0.7085657119750977 2023-01-23 07:14:06.027858: step: 2660/1545, loss: 0.26377561688423157 2023-01-23 07:14:06.856828: step: 2662/1545, loss: 2.2728142738342285 2023-01-23 07:14:07.765235: step: 2664/1545, loss: 0.3517928421497345 2023-01-23 07:14:08.621617: step: 2666/1545, loss: 0.4618570804595947 2023-01-23 07:14:09.484881: step: 2668/1545, loss: 0.3319101333618164 2023-01-23 07:14:10.388581: step: 2670/1545, loss: 0.24971653521060944 2023-01-23 07:14:11.262798: step: 2672/1545, loss: 0.6233475208282471 2023-01-23 07:14:12.155048: step: 2674/1545, loss: 0.46293869614601135 2023-01-23 07:14:13.028840: step: 2676/1545, loss: 1.2977304458618164 2023-01-23 07:14:13.944769: step: 2678/1545, loss: 0.9337108135223389 2023-01-23 07:14:14.817861: step: 2680/1545, loss: 0.2028563767671585 2023-01-23 07:14:15.719435: step: 2682/1545, loss: 0.8642461895942688 2023-01-23 07:14:16.633963: step: 2684/1545, loss: 0.7265794277191162 2023-01-23 07:14:17.522885: step: 2686/1545, loss: 0.9429227113723755 2023-01-23 07:14:18.416786: step: 2688/1545, loss: 0.5804077386856079 2023-01-23 07:14:19.362272: step: 2690/1545, loss: 0.2591712176799774 2023-01-23 07:14:20.229499: step: 2692/1545, loss: 0.538563072681427 2023-01-23 07:14:21.102150: step: 2694/1545, loss: 0.37052053213119507 2023-01-23 07:14:21.948328: step: 2696/1545, loss: 0.1864696592092514 2023-01-23 07:14:22.818062: step: 2698/1545, loss: 0.5572517514228821 2023-01-23 07:14:23.662047: step: 2700/1545, loss: 0.37212932109832764 2023-01-23 07:14:24.518482: step: 2702/1545, loss: 0.8986777663230896 2023-01-23 07:14:25.370417: step: 2704/1545, loss: 1.3179851770401 2023-01-23 07:14:26.204687: step: 2706/1545, loss: 0.4186723530292511 2023-01-23 07:14:27.097063: step: 2708/1545, loss: 2.6499862670898438 2023-01-23 07:14:27.956015: step: 2710/1545, loss: 0.9965740442276001 2023-01-23 07:14:28.836166: step: 2712/1545, loss: 0.45810985565185547 2023-01-23 07:14:29.717911: step: 2714/1545, loss: 3.303518533706665 2023-01-23 07:14:30.580414: step: 2716/1545, loss: 0.4869508445262909 2023-01-23 07:14:31.465565: step: 2718/1545, loss: 1.080330491065979 2023-01-23 07:14:32.352192: step: 2720/1545, loss: 0.4869067370891571 2023-01-23 07:14:33.268683: step: 2722/1545, loss: 0.750068187713623 2023-01-23 07:14:34.197160: step: 2724/1545, loss: 0.24956490099430084 2023-01-23 07:14:35.066099: step: 2726/1545, loss: 0.5017454624176025 2023-01-23 07:14:35.981752: step: 2728/1545, loss: 0.503385066986084 2023-01-23 07:14:36.839969: step: 2730/1545, loss: 1.8159196376800537 2023-01-23 07:14:37.702138: step: 2732/1545, loss: 0.30581560730934143 2023-01-23 07:14:38.566656: step: 2734/1545, loss: 0.518924355506897 2023-01-23 07:14:39.424602: step: 2736/1545, loss: 0.8006158471107483 2023-01-23 07:14:40.311661: step: 2738/1545, loss: 0.3297022879123688 2023-01-23 07:14:41.222951: step: 2740/1545, loss: 0.8306999802589417 2023-01-23 07:14:42.085187: step: 2742/1545, loss: 1.5024172067642212 2023-01-23 07:14:42.967790: step: 2744/1545, loss: 0.6038708686828613 2023-01-23 07:14:43.806302: step: 2746/1545, loss: 1.8248803615570068 2023-01-23 07:14:44.760326: step: 2748/1545, loss: 0.2908894121646881 2023-01-23 07:14:45.631773: step: 2750/1545, loss: 0.5396203398704529 2023-01-23 07:14:46.599099: step: 2752/1545, loss: 0.6537067890167236 2023-01-23 07:14:47.463240: step: 2754/1545, loss: 0.6891039609909058 2023-01-23 07:14:48.349150: step: 2756/1545, loss: 0.19333192706108093 2023-01-23 07:14:49.323952: step: 2758/1545, loss: 0.7277188897132874 2023-01-23 07:14:50.202928: step: 2760/1545, loss: 0.737822949886322 2023-01-23 07:14:51.084174: step: 2762/1545, loss: 0.5226430892944336 2023-01-23 07:14:51.964419: step: 2764/1545, loss: 0.4050449728965759 2023-01-23 07:14:52.836774: step: 2766/1545, loss: 3.2076618671417236 2023-01-23 07:14:53.721662: step: 2768/1545, loss: 1.1709736585617065 2023-01-23 07:14:54.626837: step: 2770/1545, loss: 0.5274191498756409 2023-01-23 07:14:55.524528: step: 2772/1545, loss: 0.6891539096832275 2023-01-23 07:14:56.411004: step: 2774/1545, loss: 0.8514978289604187 2023-01-23 07:14:57.282525: step: 2776/1545, loss: 0.3180861175060272 2023-01-23 07:14:58.159021: step: 2778/1545, loss: 2.987302780151367 2023-01-23 07:14:59.054082: step: 2780/1545, loss: 3.177872896194458 2023-01-23 07:14:59.920185: step: 2782/1545, loss: 0.6358349323272705 2023-01-23 07:15:00.807259: step: 2784/1545, loss: 0.6260530948638916 2023-01-23 07:15:01.667101: step: 2786/1545, loss: 0.5045256018638611 2023-01-23 07:15:02.574918: step: 2788/1545, loss: 0.5243799090385437 2023-01-23 07:15:03.509522: step: 2790/1545, loss: 0.29339537024497986 2023-01-23 07:15:04.403623: step: 2792/1545, loss: 0.3265027403831482 2023-01-23 07:15:05.248532: step: 2794/1545, loss: 0.3973765969276428 2023-01-23 07:15:06.136609: step: 2796/1545, loss: 0.4362894296646118 2023-01-23 07:15:06.978142: step: 2798/1545, loss: 0.5406041145324707 2023-01-23 07:15:07.861796: step: 2800/1545, loss: 0.6288004517555237 2023-01-23 07:15:08.759737: step: 2802/1545, loss: 0.719645619392395 2023-01-23 07:15:09.659284: step: 2804/1545, loss: 0.8183953762054443 2023-01-23 07:15:10.528521: step: 2806/1545, loss: 0.7888867259025574 2023-01-23 07:15:11.385431: step: 2808/1545, loss: 0.5650973916053772 2023-01-23 07:15:12.229064: step: 2810/1545, loss: 0.36973410844802856 2023-01-23 07:15:13.091458: step: 2812/1545, loss: 0.4609168767929077 2023-01-23 07:15:14.043281: step: 2814/1545, loss: 0.7636885046958923 2023-01-23 07:15:14.916882: step: 2816/1545, loss: 3.0872952938079834 2023-01-23 07:15:15.779625: step: 2818/1545, loss: 0.28746968507766724 2023-01-23 07:15:16.653575: step: 2820/1545, loss: 0.6876355409622192 2023-01-23 07:15:17.568723: step: 2822/1545, loss: 0.1998617798089981 2023-01-23 07:15:18.428609: step: 2824/1545, loss: 0.8830557465553284 2023-01-23 07:15:19.348992: step: 2826/1545, loss: 0.8076013326644897 2023-01-23 07:15:20.212517: step: 2828/1545, loss: 0.6754577159881592 2023-01-23 07:15:21.078473: step: 2830/1545, loss: 1.3436322212219238 2023-01-23 07:15:21.934356: step: 2832/1545, loss: 0.37460488080978394 2023-01-23 07:15:22.770561: step: 2834/1545, loss: 0.2727838456630707 2023-01-23 07:15:23.727378: step: 2836/1545, loss: 0.3860854506492615 2023-01-23 07:15:24.596012: step: 2838/1545, loss: 0.5218878984451294 2023-01-23 07:15:25.460269: step: 2840/1545, loss: 0.8296137452125549 2023-01-23 07:15:26.367997: step: 2842/1545, loss: 1.088044285774231 2023-01-23 07:15:27.328370: step: 2844/1545, loss: 0.4235442578792572 2023-01-23 07:15:28.191849: step: 2846/1545, loss: 1.0828450918197632 2023-01-23 07:15:29.047984: step: 2848/1545, loss: 0.2457093745470047 2023-01-23 07:15:29.939366: step: 2850/1545, loss: 0.745669960975647 2023-01-23 07:15:30.824270: step: 2852/1545, loss: 2.363025426864624 2023-01-23 07:15:31.669177: step: 2854/1545, loss: 0.43440383672714233 2023-01-23 07:15:32.532320: step: 2856/1545, loss: 1.0327785015106201 2023-01-23 07:15:33.452943: step: 2858/1545, loss: 1.013757586479187 2023-01-23 07:15:34.308406: step: 2860/1545, loss: 0.4868794083595276 2023-01-23 07:15:35.189883: step: 2862/1545, loss: 0.7545222640037537 2023-01-23 07:15:36.045415: step: 2864/1545, loss: 0.16865338385105133 2023-01-23 07:15:36.982232: step: 2866/1545, loss: 0.8692122101783752 2023-01-23 07:15:37.856050: step: 2868/1545, loss: 2.416388511657715 2023-01-23 07:15:38.789455: step: 2870/1545, loss: 0.5509288907051086 2023-01-23 07:15:39.711535: step: 2872/1545, loss: 0.33163902163505554 2023-01-23 07:15:40.572576: step: 2874/1545, loss: 0.47809144854545593 2023-01-23 07:15:41.437929: step: 2876/1545, loss: 0.5264312028884888 2023-01-23 07:15:42.310014: step: 2878/1545, loss: 5.752710819244385 2023-01-23 07:15:43.193856: step: 2880/1545, loss: 0.3645298480987549 2023-01-23 07:15:44.071908: step: 2882/1545, loss: 0.7722182869911194 2023-01-23 07:15:44.925333: step: 2884/1545, loss: 0.8129874467849731 2023-01-23 07:15:45.835785: step: 2886/1545, loss: 0.7141930460929871 2023-01-23 07:15:46.713903: step: 2888/1545, loss: 0.5945845246315002 2023-01-23 07:15:47.548903: step: 2890/1545, loss: 0.8096344470977783 2023-01-23 07:15:48.486348: step: 2892/1545, loss: 0.5986541509628296 2023-01-23 07:15:49.354503: step: 2894/1545, loss: 1.1273701190948486 2023-01-23 07:15:50.199320: step: 2896/1545, loss: 0.21354711055755615 2023-01-23 07:15:51.071758: step: 2898/1545, loss: 2.7372207641601562 2023-01-23 07:15:51.964089: step: 2900/1545, loss: 0.884568989276886 2023-01-23 07:15:52.836433: step: 2902/1545, loss: 0.2605483829975128 2023-01-23 07:15:53.736401: step: 2904/1545, loss: 0.1365518718957901 2023-01-23 07:15:54.550113: step: 2906/1545, loss: 0.28402161598205566 2023-01-23 07:15:55.470348: step: 2908/1545, loss: 0.9054224491119385 2023-01-23 07:15:56.341968: step: 2910/1545, loss: 0.46717098355293274 2023-01-23 07:15:57.200383: step: 2912/1545, loss: 0.6495782732963562 2023-01-23 07:15:58.024257: step: 2914/1545, loss: 0.6557191610336304 2023-01-23 07:15:58.899107: step: 2916/1545, loss: 0.25975272059440613 2023-01-23 07:15:59.772735: step: 2918/1545, loss: 0.6488455533981323 2023-01-23 07:16:00.632549: step: 2920/1545, loss: 0.4106121063232422 2023-01-23 07:16:01.502396: step: 2922/1545, loss: 0.7252354621887207 2023-01-23 07:16:02.389468: step: 2924/1545, loss: 1.3546290397644043 2023-01-23 07:16:03.265083: step: 2926/1545, loss: 0.881003737449646 2023-01-23 07:16:04.121838: step: 2928/1545, loss: 0.5602912902832031 2023-01-23 07:16:04.981498: step: 2930/1545, loss: 0.556410551071167 2023-01-23 07:16:05.840892: step: 2932/1545, loss: 0.5398417711257935 2023-01-23 07:16:06.787884: step: 2934/1545, loss: 0.31577128171920776 2023-01-23 07:16:07.681473: step: 2936/1545, loss: 0.6432288289070129 2023-01-23 07:16:08.571823: step: 2938/1545, loss: 0.4189210832118988 2023-01-23 07:16:09.419634: step: 2940/1545, loss: 0.49104025959968567 2023-01-23 07:16:10.284166: step: 2942/1545, loss: 0.25261712074279785 2023-01-23 07:16:11.171834: step: 2944/1545, loss: 0.6851822733879089 2023-01-23 07:16:12.063294: step: 2946/1545, loss: 0.28679361939430237 2023-01-23 07:16:12.949246: step: 2948/1545, loss: 0.778994619846344 2023-01-23 07:16:13.860841: step: 2950/1545, loss: 0.271234929561615 2023-01-23 07:16:14.727285: step: 2952/1545, loss: 0.39781880378723145 2023-01-23 07:16:15.595613: step: 2954/1545, loss: 0.8252264261245728 2023-01-23 07:16:16.465221: step: 2956/1545, loss: 0.6650265455245972 2023-01-23 07:16:17.348774: step: 2958/1545, loss: 0.5310274958610535 2023-01-23 07:16:18.238368: step: 2960/1545, loss: 1.035476803779602 2023-01-23 07:16:19.149926: step: 2962/1545, loss: 0.6020408272743225 2023-01-23 07:16:20.008643: step: 2964/1545, loss: 0.725313127040863 2023-01-23 07:16:20.876474: step: 2966/1545, loss: 0.46781057119369507 2023-01-23 07:16:21.718190: step: 2968/1545, loss: 0.9997844696044922 2023-01-23 07:16:22.712979: step: 2970/1545, loss: 0.6614837646484375 2023-01-23 07:16:23.649495: step: 2972/1545, loss: 0.6463035345077515 2023-01-23 07:16:24.502673: step: 2974/1545, loss: 0.9968361854553223 2023-01-23 07:16:25.397795: step: 2976/1545, loss: 1.2952543497085571 2023-01-23 07:16:26.287218: step: 2978/1545, loss: 1.3227981328964233 2023-01-23 07:16:27.306806: step: 2980/1545, loss: 0.5301834940910339 2023-01-23 07:16:28.219700: step: 2982/1545, loss: 0.5487790703773499 2023-01-23 07:16:29.103221: step: 2984/1545, loss: 0.4307583272457123 2023-01-23 07:16:29.948729: step: 2986/1545, loss: 0.3615306615829468 2023-01-23 07:16:30.839946: step: 2988/1545, loss: 0.28095847368240356 2023-01-23 07:16:31.763163: step: 2990/1545, loss: 0.7054452300071716 2023-01-23 07:16:32.642914: step: 2992/1545, loss: 0.4363240599632263 2023-01-23 07:16:33.529777: step: 2994/1545, loss: 1.0932918787002563 2023-01-23 07:16:34.451787: step: 2996/1545, loss: 0.45858046412467957 2023-01-23 07:16:35.344159: step: 2998/1545, loss: 0.7367437481880188 2023-01-23 07:16:36.222729: step: 3000/1545, loss: 0.6037881374359131 2023-01-23 07:16:37.158567: step: 3002/1545, loss: 8.991649627685547 2023-01-23 07:16:38.046157: step: 3004/1545, loss: 0.3695792853832245 2023-01-23 07:16:38.915701: step: 3006/1545, loss: 0.34642013907432556 2023-01-23 07:16:39.784321: step: 3008/1545, loss: 0.44687750935554504 2023-01-23 07:16:40.704705: step: 3010/1545, loss: 0.3924264907836914 2023-01-23 07:16:41.628035: step: 3012/1545, loss: 0.471829354763031 2023-01-23 07:16:42.524819: step: 3014/1545, loss: 0.3228556513786316 2023-01-23 07:16:43.424760: step: 3016/1545, loss: 0.5847991704940796 2023-01-23 07:16:44.319869: step: 3018/1545, loss: 0.5120004415512085 2023-01-23 07:16:45.163814: step: 3020/1545, loss: 3.179321527481079 2023-01-23 07:16:46.021153: step: 3022/1545, loss: 1.1021301746368408 2023-01-23 07:16:46.880310: step: 3024/1545, loss: 1.1838006973266602 2023-01-23 07:16:47.821094: step: 3026/1545, loss: 0.6904273629188538 2023-01-23 07:16:48.680252: step: 3028/1545, loss: 1.5515210628509521 2023-01-23 07:16:49.548765: step: 3030/1545, loss: 0.46477100253105164 2023-01-23 07:16:50.390294: step: 3032/1545, loss: 1.6376596689224243 2023-01-23 07:16:51.334442: step: 3034/1545, loss: 1.0977580547332764 2023-01-23 07:16:52.262833: step: 3036/1545, loss: 0.8023313283920288 2023-01-23 07:16:53.149090: step: 3038/1545, loss: 1.358319640159607 2023-01-23 07:16:54.050821: step: 3040/1545, loss: 0.5015067458152771 2023-01-23 07:16:54.951400: step: 3042/1545, loss: 0.8902459144592285 2023-01-23 07:16:55.848922: step: 3044/1545, loss: 0.9210633635520935 2023-01-23 07:16:56.782048: step: 3046/1545, loss: 0.8514809608459473 2023-01-23 07:16:57.624002: step: 3048/1545, loss: 1.092631459236145 2023-01-23 07:16:58.486046: step: 3050/1545, loss: 1.570461392402649 2023-01-23 07:16:59.444734: step: 3052/1545, loss: 0.6635987758636475 2023-01-23 07:17:00.339511: step: 3054/1545, loss: 0.38972407579421997 2023-01-23 07:17:01.250489: step: 3056/1545, loss: 0.6797530651092529 2023-01-23 07:17:02.141063: step: 3058/1545, loss: 2.0926942825317383 2023-01-23 07:17:03.104133: step: 3060/1545, loss: 1.0612879991531372 2023-01-23 07:17:03.976122: step: 3062/1545, loss: 2.906886577606201 2023-01-23 07:17:04.869155: step: 3064/1545, loss: 0.6604012846946716 2023-01-23 07:17:05.739576: step: 3066/1545, loss: 2.347612142562866 2023-01-23 07:17:06.640562: step: 3068/1545, loss: 1.3229175806045532 2023-01-23 07:17:07.526890: step: 3070/1545, loss: 0.691052258014679 2023-01-23 07:17:08.414466: step: 3072/1545, loss: 1.3544905185699463 2023-01-23 07:17:09.316234: step: 3074/1545, loss: 0.4183766543865204 2023-01-23 07:17:10.227243: step: 3076/1545, loss: 0.3792620599269867 2023-01-23 07:17:11.089711: step: 3078/1545, loss: 0.7681507468223572 2023-01-23 07:17:11.976864: step: 3080/1545, loss: 0.5999738574028015 2023-01-23 07:17:12.857492: step: 3082/1545, loss: 0.630769670009613 2023-01-23 07:17:13.726231: step: 3084/1545, loss: 6.27526330947876 2023-01-23 07:17:14.650634: step: 3086/1545, loss: 2.1788430213928223 2023-01-23 07:17:15.566826: step: 3088/1545, loss: 0.8934766054153442 2023-01-23 07:17:16.487352: step: 3090/1545, loss: 0.38108181953430176 ================================================== Loss: 0.826 -------------------- Dev Chinese: {'event': {'p': 0.6030534351145038, 'r': 0.7363515312916112, 'f1': 0.6630695443645084}, 'argument': {'p': 0.639051346299566, 'r': 0.6801878850583704, 'f1': 0.6589782555750419}, 'combined': 0.43694841167026155, 'epoch': 4} Test Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6895525757392267, 'r': 0.7216860418355543, 'f1': 0.7052534742536323}, 'combined': 0.4906824637622712, 'epoch': 4} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6433246520356244, 'r': 0.6844393854363974, 'f1': 0.6632454518254343}, 'combined': 0.4437570170171374, 'epoch': 4} Test Korean: {'event': {'p': 0.6264550264550265, 'r': 0.7570332480818415, 'f1': 0.6855819339895773}, 'argument': {'p': 0.6873315855909078, 'r': 0.7186217381101572, 'f1': 0.7026284733196001}, 'combined': 0.4817093876145956, 'epoch': 4} Dev Russian: {'event': {'p': 0.5698818897637795, 'r': 0.7709720372836218, 'f1': 0.6553480475382004}, 'argument': {'p': 0.6428217111128143, 'r': 0.6888691116223282, 'f1': 0.6650492944846267}, 'combined': 0.43583875665715777, 'epoch': 4} Test Russian: {'event': {'p': 0.6193323368211261, 'r': 0.7947570332480819, 'f1': 0.6961635396247551}, 'argument': {'p': 0.6924442431098461, 'r': 0.7305533047860525, 'f1': 0.7109884777130794}, 'combined': 0.49496425527715365, 'epoch': 4} Chinese: {'event': {'p': 0.5641025641025641, 'r': 0.8148148148148148, 'f1': 0.6666666666666667}, 'argument': {'p': 0.6782739677476518, 'r': 0.6390349778779529, 'f1': 0.6580700623253815}, 'combined': 0.4387133748835877, 'epoch': 4} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.5904022242695012, 'r': 0.3073326646882335, 'f1': 0.40423936076109995}, 'combined': 0.24821715134453506, 'epoch': 4} Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.5603976466214615, 'r': 0.5904189491190398, 'f1': 0.5750167156637606}, 'combined': 0.3057050893402271, 'epoch': 4} New best chinese model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6030534351145038, 'r': 0.7363515312916112, 'f1': 0.6630695443645084}, 'argument': {'p': 0.639051346299566, 'r': 0.6801878850583704, 'f1': 0.6589782555750419}, 'combined': 0.43694841167026155, 'epoch': 4} Test for Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6895525757392267, 'r': 0.7216860418355543, 'f1': 0.7052534742536323}, 'combined': 0.4906824637622712, 'epoch': 4} Chinese: {'event': {'p': 0.5641025641025641, 'r': 0.8148148148148148, 'f1': 0.6666666666666667}, 'argument': {'p': 0.6782739677476518, 'r': 0.6390349778779529, 'f1': 0.6580700623253815}, 'combined': 0.4387133748835877, 'epoch': 4} -------------------- Dev for Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6621925205794895, 'r': 0.6288590127817241, 'f1': 0.6450954497205971}, 'combined': 0.43161341200525233, 'epoch': 3} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7041948357813179, 'r': 0.7012269648259177, 'f1': 0.7027077666329988}, 'combined': 0.48827407061933914, 'epoch': 3} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6058186000046465, 'r': 0.3568520520575315, 'f1': 0.44914137586551384}, 'combined': 0.28366823738874564, 'epoch': 3} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 5 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 07:22:41.354922: step: 2/1545, loss: 0.5339401364326477 2023-01-23 07:22:42.215766: step: 4/1545, loss: 0.7780286073684692 2023-01-23 07:22:43.086450: step: 6/1545, loss: 0.3954189419746399 2023-01-23 07:22:43.974248: step: 8/1545, loss: 0.2791214883327484 2023-01-23 07:22:44.844706: step: 10/1545, loss: 0.21736107766628265 2023-01-23 07:22:45.749321: step: 12/1545, loss: 0.5670729279518127 2023-01-23 07:22:46.639013: step: 14/1545, loss: 0.207185760140419 2023-01-23 07:22:47.540818: step: 16/1545, loss: 0.6299096941947937 2023-01-23 07:22:48.465030: step: 18/1545, loss: 0.6317072510719299 2023-01-23 07:22:49.360944: step: 20/1545, loss: 0.5952789783477783 2023-01-23 07:22:50.212565: step: 22/1545, loss: 0.18306785821914673 2023-01-23 07:22:51.079509: step: 24/1545, loss: 0.29143375158309937 2023-01-23 07:22:52.028203: step: 26/1545, loss: 0.5820053815841675 2023-01-23 07:22:52.910938: step: 28/1545, loss: 1.3444275856018066 2023-01-23 07:22:53.848676: step: 30/1545, loss: 0.7728564143180847 2023-01-23 07:22:54.758576: step: 32/1545, loss: 0.9483658075332642 2023-01-23 07:22:55.671926: step: 34/1545, loss: 0.3985631763935089 2023-01-23 07:22:56.535231: step: 36/1545, loss: 1.2344632148742676 2023-01-23 07:22:57.445354: step: 38/1545, loss: 0.1507657766342163 2023-01-23 07:22:58.319685: step: 40/1545, loss: 1.5206152200698853 2023-01-23 07:22:59.222292: step: 42/1545, loss: 0.6986105442047119 2023-01-23 07:23:00.108479: step: 44/1545, loss: 0.44743022322654724 2023-01-23 07:23:00.985823: step: 46/1545, loss: 0.2619965970516205 2023-01-23 07:23:01.864097: step: 48/1545, loss: 0.41124698519706726 2023-01-23 07:23:02.716403: step: 50/1545, loss: 0.31409576535224915 2023-01-23 07:23:03.559488: step: 52/1545, loss: 0.4720090627670288 2023-01-23 07:23:04.440161: step: 54/1545, loss: 1.1808476448059082 2023-01-23 07:23:05.287032: step: 56/1545, loss: 0.13561050593852997 2023-01-23 07:23:06.158027: step: 58/1545, loss: 0.9214658141136169 2023-01-23 07:23:07.048103: step: 60/1545, loss: 0.6296623349189758 2023-01-23 07:23:07.906358: step: 62/1545, loss: 0.19458797574043274 2023-01-23 07:23:08.783255: step: 64/1545, loss: 0.30029481649398804 2023-01-23 07:23:09.665384: step: 66/1545, loss: 0.47908106446266174 2023-01-23 07:23:10.672103: step: 68/1545, loss: 0.6158205270767212 2023-01-23 07:23:11.543437: step: 70/1545, loss: 0.5848821997642517 2023-01-23 07:23:12.475811: step: 72/1545, loss: 0.42061829566955566 2023-01-23 07:23:13.362460: step: 74/1545, loss: 0.48614203929901123 2023-01-23 07:23:14.271070: step: 76/1545, loss: 0.2798021733760834 2023-01-23 07:23:15.169013: step: 78/1545, loss: 0.3018839955329895 2023-01-23 07:23:16.050326: step: 80/1545, loss: 0.28314557671546936 2023-01-23 07:23:16.900903: step: 82/1545, loss: 0.6449396014213562 2023-01-23 07:23:17.790392: step: 84/1545, loss: 0.42641592025756836 2023-01-23 07:23:18.704278: step: 86/1545, loss: 0.24569794535636902 2023-01-23 07:23:19.583668: step: 88/1545, loss: 0.35108304023742676 2023-01-23 07:23:20.496605: step: 90/1545, loss: 0.9138343334197998 2023-01-23 07:23:21.375145: step: 92/1545, loss: 0.4990598261356354 2023-01-23 07:23:22.230404: step: 94/1545, loss: 0.4736619293689728 2023-01-23 07:23:23.157717: step: 96/1545, loss: 0.9496140480041504 2023-01-23 07:23:24.045091: step: 98/1545, loss: 1.207778811454773 2023-01-23 07:23:25.021180: step: 100/1545, loss: 0.188052237033844 2023-01-23 07:23:25.941346: step: 102/1545, loss: 0.5512608289718628 2023-01-23 07:23:26.863916: step: 104/1545, loss: 0.5079878568649292 2023-01-23 07:23:27.722229: step: 106/1545, loss: 0.6881954073905945 2023-01-23 07:23:28.580402: step: 108/1545, loss: 0.8935093879699707 2023-01-23 07:23:29.453490: step: 110/1545, loss: 1.2928247451782227 2023-01-23 07:23:30.324450: step: 112/1545, loss: 0.21308359503746033 2023-01-23 07:23:31.168534: step: 114/1545, loss: 0.614954948425293 2023-01-23 07:23:32.044878: step: 116/1545, loss: 0.5820819735527039 2023-01-23 07:23:32.933929: step: 118/1545, loss: 0.47264280915260315 2023-01-23 07:23:33.844594: step: 120/1545, loss: 0.5095226764678955 2023-01-23 07:23:34.739563: step: 122/1545, loss: 0.7600464224815369 2023-01-23 07:23:35.629150: step: 124/1545, loss: 0.3175007402896881 2023-01-23 07:23:36.519626: step: 126/1545, loss: 0.28943848609924316 2023-01-23 07:23:37.417058: step: 128/1545, loss: 0.6563620567321777 2023-01-23 07:23:38.316283: step: 130/1545, loss: 2.9800920486450195 2023-01-23 07:23:39.191945: step: 132/1545, loss: 0.712171196937561 2023-01-23 07:23:40.029450: step: 134/1545, loss: 0.1673000454902649 2023-01-23 07:23:40.917696: step: 136/1545, loss: 0.7005615830421448 2023-01-23 07:23:41.823431: step: 138/1545, loss: 5.97499942779541 2023-01-23 07:23:42.723868: step: 140/1545, loss: 0.6822385191917419 2023-01-23 07:23:43.647055: step: 142/1545, loss: 0.25488483905792236 2023-01-23 07:23:44.486591: step: 144/1545, loss: 0.8800963759422302 2023-01-23 07:23:45.329002: step: 146/1545, loss: 0.12325932830572128 2023-01-23 07:23:46.208042: step: 148/1545, loss: 0.20096899569034576 2023-01-23 07:23:47.108782: step: 150/1545, loss: 0.2993202805519104 2023-01-23 07:23:48.026091: step: 152/1545, loss: 1.2250926494598389 2023-01-23 07:23:48.866150: step: 154/1545, loss: 0.4410163462162018 2023-01-23 07:23:49.688701: step: 156/1545, loss: 0.8963986039161682 2023-01-23 07:23:50.627607: step: 158/1545, loss: 1.1726408004760742 2023-01-23 07:23:51.514575: step: 160/1545, loss: 0.30231520533561707 2023-01-23 07:23:52.441960: step: 162/1545, loss: 0.16489458084106445 2023-01-23 07:23:53.310743: step: 164/1545, loss: 0.7857978343963623 2023-01-23 07:23:54.237135: step: 166/1545, loss: 0.22670142352581024 2023-01-23 07:23:55.210393: step: 168/1545, loss: 0.3992401659488678 2023-01-23 07:23:56.092924: step: 170/1545, loss: 0.4263038635253906 2023-01-23 07:23:56.955258: step: 172/1545, loss: 0.2837265729904175 2023-01-23 07:23:57.894240: step: 174/1545, loss: 0.23793214559555054 2023-01-23 07:23:58.771771: step: 176/1545, loss: 2.446367025375366 2023-01-23 07:23:59.669033: step: 178/1545, loss: 0.44604119658470154 2023-01-23 07:24:00.584805: step: 180/1545, loss: 0.3285290002822876 2023-01-23 07:24:01.475932: step: 182/1545, loss: 0.15906347334384918 2023-01-23 07:24:02.303481: step: 184/1545, loss: 0.34221211075782776 2023-01-23 07:24:03.182581: step: 186/1545, loss: 0.1514100730419159 2023-01-23 07:24:04.025563: step: 188/1545, loss: 0.46944659948349 2023-01-23 07:24:04.927484: step: 190/1545, loss: 0.744683027267456 2023-01-23 07:24:05.826869: step: 192/1545, loss: 0.4712647497653961 2023-01-23 07:24:06.773582: step: 194/1545, loss: 3.1230719089508057 2023-01-23 07:24:07.635555: step: 196/1545, loss: 0.22043555974960327 2023-01-23 07:24:08.541841: step: 198/1545, loss: 0.7858866453170776 2023-01-23 07:24:09.403208: step: 200/1545, loss: 0.816512942314148 2023-01-23 07:24:10.244511: step: 202/1545, loss: 0.25606071949005127 2023-01-23 07:24:11.133238: step: 204/1545, loss: 0.6091718077659607 2023-01-23 07:24:12.075052: step: 206/1545, loss: 0.4115815758705139 2023-01-23 07:24:12.999211: step: 208/1545, loss: 1.5177305936813354 2023-01-23 07:24:13.875127: step: 210/1545, loss: 0.3706420361995697 2023-01-23 07:24:14.780803: step: 212/1545, loss: 0.630408525466919 2023-01-23 07:24:15.655428: step: 214/1545, loss: 0.3469828963279724 2023-01-23 07:24:16.500832: step: 216/1545, loss: 0.17804360389709473 2023-01-23 07:24:17.373869: step: 218/1545, loss: 0.5801075100898743 2023-01-23 07:24:18.222631: step: 220/1545, loss: 0.8129631280899048 2023-01-23 07:24:19.052562: step: 222/1545, loss: 0.34006044268608093 2023-01-23 07:24:19.989694: step: 224/1545, loss: 0.6699924468994141 2023-01-23 07:24:20.865762: step: 226/1545, loss: 0.5555011630058289 2023-01-23 07:24:21.760159: step: 228/1545, loss: 0.3206527531147003 2023-01-23 07:24:22.668250: step: 230/1545, loss: 0.39025506377220154 2023-01-23 07:24:23.521352: step: 232/1545, loss: 0.5529720783233643 2023-01-23 07:24:24.405460: step: 234/1545, loss: 0.6329159736633301 2023-01-23 07:24:25.318233: step: 236/1545, loss: 0.4140985906124115 2023-01-23 07:24:26.181600: step: 238/1545, loss: 0.5824954509735107 2023-01-23 07:24:27.021333: step: 240/1545, loss: 1.0790129899978638 2023-01-23 07:24:27.895163: step: 242/1545, loss: 0.6673212051391602 2023-01-23 07:24:28.740631: step: 244/1545, loss: 0.28231510519981384 2023-01-23 07:24:29.606749: step: 246/1545, loss: 0.8872848153114319 2023-01-23 07:24:30.441364: step: 248/1545, loss: 0.9015000462532043 2023-01-23 07:24:31.314228: step: 250/1545, loss: 0.5415128469467163 2023-01-23 07:24:32.179453: step: 252/1545, loss: 0.556389570236206 2023-01-23 07:24:33.077288: step: 254/1545, loss: 0.6028233170509338 2023-01-23 07:24:33.965233: step: 256/1545, loss: 0.33147528767585754 2023-01-23 07:24:34.882491: step: 258/1545, loss: 1.224715232849121 2023-01-23 07:24:35.801914: step: 260/1545, loss: 0.5155166387557983 2023-01-23 07:24:36.695323: step: 262/1545, loss: 0.30565932393074036 2023-01-23 07:24:37.596243: step: 264/1545, loss: 0.23070962727069855 2023-01-23 07:24:38.436237: step: 266/1545, loss: 0.24360699951648712 2023-01-23 07:24:39.278884: step: 268/1545, loss: 0.37338194251060486 2023-01-23 07:24:40.176449: step: 270/1545, loss: 0.3064696788787842 2023-01-23 07:24:41.120079: step: 272/1545, loss: 0.6432580351829529 2023-01-23 07:24:42.006012: step: 274/1545, loss: 1.6465191841125488 2023-01-23 07:24:42.881233: step: 276/1545, loss: 0.3737487494945526 2023-01-23 07:24:43.729822: step: 278/1545, loss: 0.6563710570335388 2023-01-23 07:24:44.599171: step: 280/1545, loss: 0.5881117582321167 2023-01-23 07:24:45.483341: step: 282/1545, loss: 1.167374849319458 2023-01-23 07:24:46.388577: step: 284/1545, loss: 0.5009508728981018 2023-01-23 07:24:47.291835: step: 286/1545, loss: 0.9973888397216797 2023-01-23 07:24:48.125338: step: 288/1545, loss: 0.6347449421882629 2023-01-23 07:24:49.031778: step: 290/1545, loss: 0.13398092985153198 2023-01-23 07:24:49.920918: step: 292/1545, loss: 0.2132987231016159 2023-01-23 07:24:50.798279: step: 294/1545, loss: 0.6043987274169922 2023-01-23 07:24:51.693042: step: 296/1545, loss: 0.7447916865348816 2023-01-23 07:24:52.599165: step: 298/1545, loss: 2.723252058029175 2023-01-23 07:24:53.463202: step: 300/1545, loss: 0.3015804886817932 2023-01-23 07:24:54.319059: step: 302/1545, loss: 0.5424986481666565 2023-01-23 07:24:55.211190: step: 304/1545, loss: 0.2678692042827606 2023-01-23 07:24:56.076188: step: 306/1545, loss: 0.663326621055603 2023-01-23 07:24:56.946657: step: 308/1545, loss: 0.5790338516235352 2023-01-23 07:24:57.820029: step: 310/1545, loss: 0.2657102942466736 2023-01-23 07:24:58.705534: step: 312/1545, loss: 0.1880662590265274 2023-01-23 07:24:59.607604: step: 314/1545, loss: 0.8634220361709595 2023-01-23 07:25:00.490762: step: 316/1545, loss: 2.9598770141601562 2023-01-23 07:25:01.354863: step: 318/1545, loss: 0.8694064021110535 2023-01-23 07:25:02.229177: step: 320/1545, loss: 0.3848987817764282 2023-01-23 07:25:03.143015: step: 322/1545, loss: 0.5393024682998657 2023-01-23 07:25:04.069894: step: 324/1545, loss: 0.7558292150497437 2023-01-23 07:25:05.024143: step: 326/1545, loss: 0.5157275795936584 2023-01-23 07:25:05.855783: step: 328/1545, loss: 0.5990792512893677 2023-01-23 07:25:06.754492: step: 330/1545, loss: 0.6629083752632141 2023-01-23 07:25:07.665339: step: 332/1545, loss: 0.35031405091285706 2023-01-23 07:25:08.578349: step: 334/1545, loss: 0.3219822347164154 2023-01-23 07:25:09.463432: step: 336/1545, loss: 0.14937077462673187 2023-01-23 07:25:10.303376: step: 338/1545, loss: 0.5892860293388367 2023-01-23 07:25:11.227884: step: 340/1545, loss: 0.15126319229602814 2023-01-23 07:25:12.084964: step: 342/1545, loss: 0.3706247806549072 2023-01-23 07:25:12.933451: step: 344/1545, loss: 0.22423918545246124 2023-01-23 07:25:13.833353: step: 346/1545, loss: 0.4052659571170807 2023-01-23 07:25:14.708674: step: 348/1545, loss: 0.3120614290237427 2023-01-23 07:25:15.611822: step: 350/1545, loss: 0.7227029800415039 2023-01-23 07:25:16.588513: step: 352/1545, loss: 0.29580458998680115 2023-01-23 07:25:17.491143: step: 354/1545, loss: 0.5699419975280762 2023-01-23 07:25:18.361901: step: 356/1545, loss: 0.552455484867096 2023-01-23 07:25:19.294081: step: 358/1545, loss: 0.23973090946674347 2023-01-23 07:25:20.151770: step: 360/1545, loss: 0.4063147306442261 2023-01-23 07:25:21.030089: step: 362/1545, loss: 0.3300448954105377 2023-01-23 07:25:21.894730: step: 364/1545, loss: 0.47823280096054077 2023-01-23 07:25:22.793194: step: 366/1545, loss: 0.9077639579772949 2023-01-23 07:25:23.684676: step: 368/1545, loss: 0.7712293863296509 2023-01-23 07:25:24.576387: step: 370/1545, loss: 0.4629696011543274 2023-01-23 07:25:25.422376: step: 372/1545, loss: 0.8235386610031128 2023-01-23 07:25:26.265611: step: 374/1545, loss: 0.4484897553920746 2023-01-23 07:25:27.194941: step: 376/1545, loss: 0.4724138379096985 2023-01-23 07:25:28.125488: step: 378/1545, loss: 0.733954906463623 2023-01-23 07:25:28.976403: step: 380/1545, loss: 0.646205723285675 2023-01-23 07:25:29.830313: step: 382/1545, loss: 0.5681236386299133 2023-01-23 07:25:30.698693: step: 384/1545, loss: 0.4669715166091919 2023-01-23 07:25:31.582027: step: 386/1545, loss: 0.3882695734500885 2023-01-23 07:25:32.420263: step: 388/1545, loss: 1.032439947128296 2023-01-23 07:25:33.321621: step: 390/1545, loss: 0.8571329712867737 2023-01-23 07:25:34.185557: step: 392/1545, loss: 0.1612180918455124 2023-01-23 07:25:35.020938: step: 394/1545, loss: 0.43464046716690063 2023-01-23 07:25:35.888990: step: 396/1545, loss: 0.41265180706977844 2023-01-23 07:25:36.729584: step: 398/1545, loss: 0.7306790947914124 2023-01-23 07:25:37.643315: step: 400/1545, loss: 0.31968560814857483 2023-01-23 07:25:38.622252: step: 402/1545, loss: 0.5202000737190247 2023-01-23 07:25:39.558781: step: 404/1545, loss: 0.5606844425201416 2023-01-23 07:25:40.406741: step: 406/1545, loss: 0.5166323781013489 2023-01-23 07:25:41.275432: step: 408/1545, loss: 0.4361051619052887 2023-01-23 07:25:42.156214: step: 410/1545, loss: 0.4655502438545227 2023-01-23 07:25:43.040930: step: 412/1545, loss: 0.6449314951896667 2023-01-23 07:25:43.883723: step: 414/1545, loss: 0.4162159860134125 2023-01-23 07:25:44.776727: step: 416/1545, loss: 0.6848524808883667 2023-01-23 07:25:45.637759: step: 418/1545, loss: 1.0213156938552856 2023-01-23 07:25:46.593202: step: 420/1545, loss: 0.3919239044189453 2023-01-23 07:25:47.427992: step: 422/1545, loss: 0.12289253622293472 2023-01-23 07:25:48.282880: step: 424/1545, loss: 0.9181515574455261 2023-01-23 07:25:49.173842: step: 426/1545, loss: 0.6581493616104126 2023-01-23 07:25:50.089009: step: 428/1545, loss: 0.3178764283657074 2023-01-23 07:25:50.955243: step: 430/1545, loss: 0.5705885887145996 2023-01-23 07:25:51.853582: step: 432/1545, loss: 1.5560981035232544 2023-01-23 07:25:52.709984: step: 434/1545, loss: 0.6664606928825378 2023-01-23 07:25:53.569849: step: 436/1545, loss: 0.5687675476074219 2023-01-23 07:25:54.419538: step: 438/1545, loss: 0.5273395776748657 2023-01-23 07:25:55.261990: step: 440/1545, loss: 0.6085668802261353 2023-01-23 07:25:56.169534: step: 442/1545, loss: 0.9351891279220581 2023-01-23 07:25:57.028102: step: 444/1545, loss: 0.3695051670074463 2023-01-23 07:25:57.871001: step: 446/1545, loss: 0.6758711934089661 2023-01-23 07:25:58.739244: step: 448/1545, loss: 0.33140984177589417 2023-01-23 07:25:59.636813: step: 450/1545, loss: 0.4738213121891022 2023-01-23 07:26:00.550984: step: 452/1545, loss: 3.216519355773926 2023-01-23 07:26:01.408819: step: 454/1545, loss: 0.3736589848995209 2023-01-23 07:26:02.299935: step: 456/1545, loss: 0.6447851657867432 2023-01-23 07:26:03.219330: step: 458/1545, loss: 3.0106687545776367 2023-01-23 07:26:04.124997: step: 460/1545, loss: 0.18454763293266296 2023-01-23 07:26:04.984256: step: 462/1545, loss: 6.419022083282471 2023-01-23 07:26:05.904013: step: 464/1545, loss: 0.3588733971118927 2023-01-23 07:26:06.799241: step: 466/1545, loss: 0.09886228293180466 2023-01-23 07:26:07.685043: step: 468/1545, loss: 0.36554858088493347 2023-01-23 07:26:08.593655: step: 470/1545, loss: 0.4072869122028351 2023-01-23 07:26:09.447831: step: 472/1545, loss: 0.4188387989997864 2023-01-23 07:26:10.449695: step: 474/1545, loss: 0.5707752108573914 2023-01-23 07:26:11.377944: step: 476/1545, loss: 0.5230769515037537 2023-01-23 07:26:12.226557: step: 478/1545, loss: 0.5775150656700134 2023-01-23 07:26:13.119103: step: 480/1545, loss: 0.4176042377948761 2023-01-23 07:26:13.959757: step: 482/1545, loss: 0.3311624526977539 2023-01-23 07:26:14.854381: step: 484/1545, loss: 0.2142481654882431 2023-01-23 07:26:15.763487: step: 486/1545, loss: 0.4993978440761566 2023-01-23 07:26:16.631894: step: 488/1545, loss: 0.5288512706756592 2023-01-23 07:26:17.520565: step: 490/1545, loss: 0.5246862769126892 2023-01-23 07:26:18.384326: step: 492/1545, loss: 0.9409307241439819 2023-01-23 07:26:19.277103: step: 494/1545, loss: 0.7223541140556335 2023-01-23 07:26:20.219255: step: 496/1545, loss: 0.40554115176200867 2023-01-23 07:26:21.128355: step: 498/1545, loss: 2.8459434509277344 2023-01-23 07:26:22.012577: step: 500/1545, loss: 0.4883370101451874 2023-01-23 07:26:22.876949: step: 502/1545, loss: 0.510930597782135 2023-01-23 07:26:23.752531: step: 504/1545, loss: 3.1261215209960938 2023-01-23 07:26:24.585902: step: 506/1545, loss: 0.26033732295036316 2023-01-23 07:26:25.467713: step: 508/1545, loss: 0.652935802936554 2023-01-23 07:26:26.313943: step: 510/1545, loss: 0.3785286247730255 2023-01-23 07:26:27.152533: step: 512/1545, loss: 0.21490807831287384 2023-01-23 07:26:28.117616: step: 514/1545, loss: 0.6259742975234985 2023-01-23 07:26:29.041931: step: 516/1545, loss: 0.4967701733112335 2023-01-23 07:26:29.939629: step: 518/1545, loss: 2.8857176303863525 2023-01-23 07:26:30.841906: step: 520/1545, loss: 0.2354499250650406 2023-01-23 07:26:31.707702: step: 522/1545, loss: 0.6101125478744507 2023-01-23 07:26:32.651582: step: 524/1545, loss: 0.3338281810283661 2023-01-23 07:26:33.524297: step: 526/1545, loss: 0.7261174917221069 2023-01-23 07:26:34.398718: step: 528/1545, loss: 0.6600897312164307 2023-01-23 07:26:35.318840: step: 530/1545, loss: 0.26997432112693787 2023-01-23 07:26:36.152627: step: 532/1545, loss: 0.4053143858909607 2023-01-23 07:26:37.066584: step: 534/1545, loss: 0.3563312292098999 2023-01-23 07:26:37.979235: step: 536/1545, loss: 0.5080151557922363 2023-01-23 07:26:38.868322: step: 538/1545, loss: 0.6306663155555725 2023-01-23 07:26:39.797428: step: 540/1545, loss: 1.8853906393051147 2023-01-23 07:26:40.654932: step: 542/1545, loss: 0.6035308837890625 2023-01-23 07:26:41.507509: step: 544/1545, loss: 0.29103660583496094 2023-01-23 07:26:42.360302: step: 546/1545, loss: 0.48559364676475525 2023-01-23 07:26:43.230171: step: 548/1545, loss: 0.9878638982772827 2023-01-23 07:26:44.110311: step: 550/1545, loss: 0.2724266052246094 2023-01-23 07:26:44.950236: step: 552/1545, loss: 0.23206979036331177 2023-01-23 07:26:45.811987: step: 554/1545, loss: 0.7673052549362183 2023-01-23 07:26:46.685422: step: 556/1545, loss: 0.3211750388145447 2023-01-23 07:26:47.620037: step: 558/1545, loss: 0.2973823547363281 2023-01-23 07:26:48.482463: step: 560/1545, loss: 0.39064866304397583 2023-01-23 07:26:49.355896: step: 562/1545, loss: 0.24081511795520782 2023-01-23 07:26:50.215439: step: 564/1545, loss: 0.29105550050735474 2023-01-23 07:26:51.091631: step: 566/1545, loss: 0.5177100896835327 2023-01-23 07:26:51.944652: step: 568/1545, loss: 0.6103808283805847 2023-01-23 07:26:52.826324: step: 570/1545, loss: 0.3304624557495117 2023-01-23 07:26:53.667258: step: 572/1545, loss: 0.2823246717453003 2023-01-23 07:26:54.562400: step: 574/1545, loss: 1.9069682359695435 2023-01-23 07:26:55.458191: step: 576/1545, loss: 0.45488661527633667 2023-01-23 07:26:56.296060: step: 578/1545, loss: 0.3077685236930847 2023-01-23 07:26:57.210655: step: 580/1545, loss: 0.22211095690727234 2023-01-23 07:26:58.091775: step: 582/1545, loss: 0.055441856384277344 2023-01-23 07:26:58.988294: step: 584/1545, loss: 0.5509242415428162 2023-01-23 07:26:59.817899: step: 586/1545, loss: 0.8812701106071472 2023-01-23 07:27:00.745723: step: 588/1545, loss: 1.0456902980804443 2023-01-23 07:27:01.631804: step: 590/1545, loss: 1.4290900230407715 2023-01-23 07:27:02.532406: step: 592/1545, loss: 1.0333797931671143 2023-01-23 07:27:03.398582: step: 594/1545, loss: 0.596723735332489 2023-01-23 07:27:04.284357: step: 596/1545, loss: 0.04440087825059891 2023-01-23 07:27:05.173676: step: 598/1545, loss: 0.4137074053287506 2023-01-23 07:27:06.006668: step: 600/1545, loss: 1.0598440170288086 2023-01-23 07:27:06.913370: step: 602/1545, loss: 0.3853835165500641 2023-01-23 07:27:07.838746: step: 604/1545, loss: 0.8318643569946289 2023-01-23 07:27:08.711908: step: 606/1545, loss: 0.6389350891113281 2023-01-23 07:27:09.572851: step: 608/1545, loss: 0.5121399760246277 2023-01-23 07:27:10.459070: step: 610/1545, loss: 0.15342919528484344 2023-01-23 07:27:11.343073: step: 612/1545, loss: 0.5720568299293518 2023-01-23 07:27:12.278513: step: 614/1545, loss: 6.280740261077881 2023-01-23 07:27:13.109312: step: 616/1545, loss: 0.3749784529209137 2023-01-23 07:27:14.009512: step: 618/1545, loss: 0.859624981880188 2023-01-23 07:27:14.908640: step: 620/1545, loss: 0.3935673236846924 2023-01-23 07:27:15.818243: step: 622/1545, loss: 0.324286550283432 2023-01-23 07:27:16.707900: step: 624/1545, loss: 0.7980687618255615 2023-01-23 07:27:17.672532: step: 626/1545, loss: 0.8163121342658997 2023-01-23 07:27:18.556652: step: 628/1545, loss: 0.43959057331085205 2023-01-23 07:27:19.452043: step: 630/1545, loss: 0.32973790168762207 2023-01-23 07:27:20.370745: step: 632/1545, loss: 1.6769931316375732 2023-01-23 07:27:21.225204: step: 634/1545, loss: 0.3304235339164734 2023-01-23 07:27:22.063533: step: 636/1545, loss: 0.4985816776752472 2023-01-23 07:27:22.935883: step: 638/1545, loss: 0.757274866104126 2023-01-23 07:27:23.831973: step: 640/1545, loss: 0.08423132449388504 2023-01-23 07:27:24.671790: step: 642/1545, loss: 0.400544673204422 2023-01-23 07:27:25.546635: step: 644/1545, loss: 0.7068777680397034 2023-01-23 07:27:26.440596: step: 646/1545, loss: 0.6874064207077026 2023-01-23 07:27:27.404144: step: 648/1545, loss: 0.512690544128418 2023-01-23 07:27:28.297280: step: 650/1545, loss: 0.4007074534893036 2023-01-23 07:27:29.161713: step: 652/1545, loss: 0.6584481000900269 2023-01-23 07:27:30.082526: step: 654/1545, loss: 0.26370200514793396 2023-01-23 07:27:30.959051: step: 656/1545, loss: 0.4717034697532654 2023-01-23 07:27:31.826806: step: 658/1545, loss: 0.3041177988052368 2023-01-23 07:27:32.734004: step: 660/1545, loss: 0.2906787395477295 2023-01-23 07:27:33.578672: step: 662/1545, loss: 0.4811016023159027 2023-01-23 07:27:34.482300: step: 664/1545, loss: 3.5037741661071777 2023-01-23 07:27:35.332945: step: 666/1545, loss: 2.8787264823913574 2023-01-23 07:27:36.192300: step: 668/1545, loss: 0.9669634699821472 2023-01-23 07:27:37.044902: step: 670/1545, loss: 0.23660840094089508 2023-01-23 07:27:37.908888: step: 672/1545, loss: 0.29271838068962097 2023-01-23 07:27:38.759072: step: 674/1545, loss: 0.832770049571991 2023-01-23 07:27:39.706971: step: 676/1545, loss: 0.39896249771118164 2023-01-23 07:27:40.547145: step: 678/1545, loss: 0.8459029197692871 2023-01-23 07:27:41.460107: step: 680/1545, loss: 0.553142249584198 2023-01-23 07:27:42.381133: step: 682/1545, loss: 0.42009100317955017 2023-01-23 07:27:43.326125: step: 684/1545, loss: 0.4230736792087555 2023-01-23 07:27:44.259298: step: 686/1545, loss: 0.38308700919151306 2023-01-23 07:27:45.130726: step: 688/1545, loss: 0.4042928218841553 2023-01-23 07:27:46.013655: step: 690/1545, loss: 0.3469899296760559 2023-01-23 07:27:46.862993: step: 692/1545, loss: 0.1326245367527008 2023-01-23 07:27:47.734724: step: 694/1545, loss: 0.36446812748908997 2023-01-23 07:27:48.605953: step: 696/1545, loss: 0.2942831218242645 2023-01-23 07:27:49.472332: step: 698/1545, loss: 0.674609363079071 2023-01-23 07:27:50.348501: step: 700/1545, loss: 0.5275267958641052 2023-01-23 07:27:51.212436: step: 702/1545, loss: 0.24869468808174133 2023-01-23 07:27:52.084358: step: 704/1545, loss: 0.4479903280735016 2023-01-23 07:27:52.954488: step: 706/1545, loss: 0.9854447841644287 2023-01-23 07:27:53.876378: step: 708/1545, loss: 0.19046132266521454 2023-01-23 07:27:54.769072: step: 710/1545, loss: 0.2274949848651886 2023-01-23 07:27:55.657259: step: 712/1545, loss: 1.333678960800171 2023-01-23 07:27:56.546493: step: 714/1545, loss: 0.5681682229042053 2023-01-23 07:27:57.403006: step: 716/1545, loss: 0.5374947190284729 2023-01-23 07:27:58.301291: step: 718/1545, loss: 0.4254085123538971 2023-01-23 07:27:59.272663: step: 720/1545, loss: 0.9865374565124512 2023-01-23 07:28:00.134397: step: 722/1545, loss: 0.204319030046463 2023-01-23 07:28:01.029690: step: 724/1545, loss: 0.5801162719726562 2023-01-23 07:28:01.894693: step: 726/1545, loss: 0.6985263228416443 2023-01-23 07:28:02.755995: step: 728/1545, loss: 0.5873334407806396 2023-01-23 07:28:03.613770: step: 730/1545, loss: 0.7160648107528687 2023-01-23 07:28:04.489435: step: 732/1545, loss: 0.29396748542785645 2023-01-23 07:28:05.351473: step: 734/1545, loss: 0.44530820846557617 2023-01-23 07:28:06.262619: step: 736/1545, loss: 4.000535011291504 2023-01-23 07:28:07.104634: step: 738/1545, loss: 0.7162187695503235 2023-01-23 07:28:07.961494: step: 740/1545, loss: 0.3381999731063843 2023-01-23 07:28:08.827487: step: 742/1545, loss: 0.7007330060005188 2023-01-23 07:28:09.695096: step: 744/1545, loss: 0.6862451434135437 2023-01-23 07:28:10.597062: step: 746/1545, loss: 0.3882414698600769 2023-01-23 07:28:11.484768: step: 748/1545, loss: 0.6912431120872498 2023-01-23 07:28:12.363220: step: 750/1545, loss: 0.3715898394584656 2023-01-23 07:28:13.243202: step: 752/1545, loss: 0.3348052203655243 2023-01-23 07:28:14.110098: step: 754/1545, loss: 0.7035717368125916 2023-01-23 07:28:15.018206: step: 756/1545, loss: 0.7877832651138306 2023-01-23 07:28:15.887723: step: 758/1545, loss: 0.4226045608520508 2023-01-23 07:28:16.790845: step: 760/1545, loss: 0.8784363269805908 2023-01-23 07:28:17.654229: step: 762/1545, loss: 0.5192849040031433 2023-01-23 07:28:18.561367: step: 764/1545, loss: 0.3293739855289459 2023-01-23 07:28:19.412509: step: 766/1545, loss: 0.12259720265865326 2023-01-23 07:28:20.239902: step: 768/1545, loss: 0.4646879732608795 2023-01-23 07:28:21.140471: step: 770/1545, loss: 0.1289694756269455 2023-01-23 07:28:22.058997: step: 772/1545, loss: 0.6719198822975159 2023-01-23 07:28:22.884448: step: 774/1545, loss: 0.555114209651947 2023-01-23 07:28:23.736915: step: 776/1545, loss: 0.6130912899971008 2023-01-23 07:28:24.582611: step: 778/1545, loss: 0.3311135470867157 2023-01-23 07:28:25.481861: step: 780/1545, loss: 0.6104981899261475 2023-01-23 07:28:26.354330: step: 782/1545, loss: 3.2041678428649902 2023-01-23 07:28:27.233143: step: 784/1545, loss: 0.9928704500198364 2023-01-23 07:28:28.106342: step: 786/1545, loss: 0.27548983693122864 2023-01-23 07:28:28.997706: step: 788/1545, loss: 0.6389018297195435 2023-01-23 07:28:29.873729: step: 790/1545, loss: 0.33292093873023987 2023-01-23 07:28:30.801901: step: 792/1545, loss: 0.5144174098968506 2023-01-23 07:28:31.679797: step: 794/1545, loss: 0.12709960341453552 2023-01-23 07:28:32.569652: step: 796/1545, loss: 0.8237005472183228 2023-01-23 07:28:33.461626: step: 798/1545, loss: 0.20243962109088898 2023-01-23 07:28:34.316617: step: 800/1545, loss: 0.5559059381484985 2023-01-23 07:28:35.198224: step: 802/1545, loss: 0.16454598307609558 2023-01-23 07:28:36.088178: step: 804/1545, loss: 0.3106417953968048 2023-01-23 07:28:36.981330: step: 806/1545, loss: 0.14099439978599548 2023-01-23 07:28:37.847439: step: 808/1545, loss: 0.5301478505134583 2023-01-23 07:28:38.766362: step: 810/1545, loss: 0.4685046076774597 2023-01-23 07:28:39.627476: step: 812/1545, loss: 1.0054067373275757 2023-01-23 07:28:40.493946: step: 814/1545, loss: 0.49851325154304504 2023-01-23 07:28:41.431135: step: 816/1545, loss: 0.2941604554653168 2023-01-23 07:28:42.300653: step: 818/1545, loss: 0.4415302872657776 2023-01-23 07:28:43.148350: step: 820/1545, loss: 0.531559407711029 2023-01-23 07:28:44.045709: step: 822/1545, loss: 1.1194921731948853 2023-01-23 07:28:44.931875: step: 824/1545, loss: 0.6400059461593628 2023-01-23 07:28:45.833231: step: 826/1545, loss: 1.020902395248413 2023-01-23 07:28:46.681901: step: 828/1545, loss: 0.4131966531276703 2023-01-23 07:28:47.539339: step: 830/1545, loss: 0.2775649130344391 2023-01-23 07:28:48.510268: step: 832/1545, loss: 0.2973967492580414 2023-01-23 07:28:49.408038: step: 834/1545, loss: 0.5909639596939087 2023-01-23 07:28:50.341541: step: 836/1545, loss: 0.8124196529388428 2023-01-23 07:28:51.273129: step: 838/1545, loss: 0.5649405717849731 2023-01-23 07:28:52.159296: step: 840/1545, loss: 0.19378328323364258 2023-01-23 07:28:53.007283: step: 842/1545, loss: 0.42743825912475586 2023-01-23 07:28:53.871247: step: 844/1545, loss: 0.5647724270820618 2023-01-23 07:28:54.770949: step: 846/1545, loss: 0.19649837911128998 2023-01-23 07:28:55.685839: step: 848/1545, loss: 0.4152781367301941 2023-01-23 07:28:56.591179: step: 850/1545, loss: 1.3815644979476929 2023-01-23 07:28:57.451134: step: 852/1545, loss: 0.6132031679153442 2023-01-23 07:28:58.335160: step: 854/1545, loss: 0.7647165060043335 2023-01-23 07:28:59.207809: step: 856/1545, loss: 0.46999865770339966 2023-01-23 07:29:00.131814: step: 858/1545, loss: 0.209867462515831 2023-01-23 07:29:01.016556: step: 860/1545, loss: 0.6735981702804565 2023-01-23 07:29:01.935716: step: 862/1545, loss: 0.2311106026172638 2023-01-23 07:29:02.837331: step: 864/1545, loss: 0.514765202999115 2023-01-23 07:29:03.753530: step: 866/1545, loss: 0.1823328137397766 2023-01-23 07:29:04.643787: step: 868/1545, loss: 0.3566599190235138 2023-01-23 07:29:05.496717: step: 870/1545, loss: 1.1029677391052246 2023-01-23 07:29:06.430153: step: 872/1545, loss: 0.22125685214996338 2023-01-23 07:29:07.315883: step: 874/1545, loss: 0.5954781174659729 2023-01-23 07:29:08.160474: step: 876/1545, loss: 0.6736935973167419 2023-01-23 07:29:09.036197: step: 878/1545, loss: 0.9595202207565308 2023-01-23 07:29:09.938910: step: 880/1545, loss: 1.1949241161346436 2023-01-23 07:29:10.861814: step: 882/1545, loss: 0.7984528541564941 2023-01-23 07:29:11.737624: step: 884/1545, loss: 0.30444762110710144 2023-01-23 07:29:12.634342: step: 886/1545, loss: 0.6068898439407349 2023-01-23 07:29:13.534058: step: 888/1545, loss: 0.5034614205360413 2023-01-23 07:29:14.446215: step: 890/1545, loss: 0.3410494923591614 2023-01-23 07:29:15.311039: step: 892/1545, loss: 0.8689569234848022 2023-01-23 07:29:16.154837: step: 894/1545, loss: 1.1942510604858398 2023-01-23 07:29:17.045856: step: 896/1545, loss: 3.759809970855713 2023-01-23 07:29:17.891261: step: 898/1545, loss: 0.6802175641059875 2023-01-23 07:29:18.763775: step: 900/1545, loss: 0.337870329618454 2023-01-23 07:29:19.653051: step: 902/1545, loss: 2.8653039932250977 2023-01-23 07:29:20.542683: step: 904/1545, loss: 0.46704572439193726 2023-01-23 07:29:21.432718: step: 906/1545, loss: 0.5567729473114014 2023-01-23 07:29:22.275138: step: 908/1545, loss: 2.8847007751464844 2023-01-23 07:29:23.164138: step: 910/1545, loss: 7.030391216278076 2023-01-23 07:29:24.060484: step: 912/1545, loss: 0.7344987392425537 2023-01-23 07:29:24.931729: step: 914/1545, loss: 0.503021776676178 2023-01-23 07:29:25.818873: step: 916/1545, loss: 0.8453863859176636 2023-01-23 07:29:26.730935: step: 918/1545, loss: 0.43683549761772156 2023-01-23 07:29:27.594221: step: 920/1545, loss: 0.5135310888290405 2023-01-23 07:29:28.506213: step: 922/1545, loss: 0.2905680537223816 2023-01-23 07:29:29.345294: step: 924/1545, loss: 0.24860729277133942 2023-01-23 07:29:30.285445: step: 926/1545, loss: 0.6028825640678406 2023-01-23 07:29:31.167579: step: 928/1545, loss: 2.1997570991516113 2023-01-23 07:29:32.048579: step: 930/1545, loss: 0.3104032278060913 2023-01-23 07:29:32.909910: step: 932/1545, loss: 0.6168110370635986 2023-01-23 07:29:33.794921: step: 934/1545, loss: 0.902073860168457 2023-01-23 07:29:34.665714: step: 936/1545, loss: 2.7689731121063232 2023-01-23 07:29:35.533521: step: 938/1545, loss: 0.7697121500968933 2023-01-23 07:29:36.399360: step: 940/1545, loss: 0.3605830669403076 2023-01-23 07:29:37.286814: step: 942/1545, loss: 0.7980629801750183 2023-01-23 07:29:38.230025: step: 944/1545, loss: 0.18854151666164398 2023-01-23 07:29:39.107253: step: 946/1545, loss: 0.9569988250732422 2023-01-23 07:29:40.025527: step: 948/1545, loss: 0.5501629114151001 2023-01-23 07:29:40.871386: step: 950/1545, loss: 2.783761739730835 2023-01-23 07:29:41.734712: step: 952/1545, loss: 0.6978602409362793 2023-01-23 07:29:42.645639: step: 954/1545, loss: 0.435041606426239 2023-01-23 07:29:43.517111: step: 956/1545, loss: 1.0470805168151855 2023-01-23 07:29:44.393256: step: 958/1545, loss: 0.6516966819763184 2023-01-23 07:29:45.310076: step: 960/1545, loss: 0.7857576608657837 2023-01-23 07:29:46.169754: step: 962/1545, loss: 0.5044625401496887 2023-01-23 07:29:47.041780: step: 964/1545, loss: 2.572124481201172 2023-01-23 07:29:47.893337: step: 966/1545, loss: 0.6839255094528198 2023-01-23 07:29:48.820846: step: 968/1545, loss: 0.5034652352333069 2023-01-23 07:29:49.709382: step: 970/1545, loss: 0.5346359014511108 2023-01-23 07:29:50.573661: step: 972/1545, loss: 0.3575751781463623 2023-01-23 07:29:51.498480: step: 974/1545, loss: 0.5311371088027954 2023-01-23 07:29:52.364976: step: 976/1545, loss: 0.8675087690353394 2023-01-23 07:29:53.219440: step: 978/1545, loss: 0.3751344382762909 2023-01-23 07:29:54.069108: step: 980/1545, loss: 0.6816698312759399 2023-01-23 07:29:54.963719: step: 982/1545, loss: 0.4050791561603546 2023-01-23 07:29:55.854577: step: 984/1545, loss: 0.39722204208374023 2023-01-23 07:29:56.729193: step: 986/1545, loss: 0.18657135963439941 2023-01-23 07:29:57.591505: step: 988/1545, loss: 0.26560500264167786 2023-01-23 07:29:58.522854: step: 990/1545, loss: 0.6712402701377869 2023-01-23 07:29:59.420841: step: 992/1545, loss: 0.24646392464637756 2023-01-23 07:30:00.320253: step: 994/1545, loss: 2.8552167415618896 2023-01-23 07:30:01.173368: step: 996/1545, loss: 0.21852223575115204 2023-01-23 07:30:02.049968: step: 998/1545, loss: 0.5996408462524414 2023-01-23 07:30:02.903905: step: 1000/1545, loss: 0.5352027416229248 2023-01-23 07:30:03.838351: step: 1002/1545, loss: 1.9637733697891235 2023-01-23 07:30:04.709092: step: 1004/1545, loss: 0.3468226492404938 2023-01-23 07:30:05.544876: step: 1006/1545, loss: 0.43342143297195435 2023-01-23 07:30:06.421869: step: 1008/1545, loss: 0.28076010942459106 2023-01-23 07:30:07.298917: step: 1010/1545, loss: 1.750807762145996 2023-01-23 07:30:08.174343: step: 1012/1545, loss: 0.3751125931739807 2023-01-23 07:30:09.082668: step: 1014/1545, loss: 0.5538268685340881 2023-01-23 07:30:09.987987: step: 1016/1545, loss: 0.575873851776123 2023-01-23 07:30:10.874669: step: 1018/1545, loss: 0.25777560472488403 2023-01-23 07:30:11.751354: step: 1020/1545, loss: 0.41550615429878235 2023-01-23 07:30:12.614457: step: 1022/1545, loss: 0.9157196283340454 2023-01-23 07:30:13.476523: step: 1024/1545, loss: 0.40631771087646484 2023-01-23 07:30:14.424808: step: 1026/1545, loss: 0.7013624906539917 2023-01-23 07:30:15.296106: step: 1028/1545, loss: 0.5996281504631042 2023-01-23 07:30:16.182828: step: 1030/1545, loss: 0.7905334234237671 2023-01-23 07:30:17.093255: step: 1032/1545, loss: 0.590205192565918 2023-01-23 07:30:17.975991: step: 1034/1545, loss: 0.5628809332847595 2023-01-23 07:30:18.877350: step: 1036/1545, loss: 0.26771092414855957 2023-01-23 07:30:19.741505: step: 1038/1545, loss: 0.3771686851978302 2023-01-23 07:30:20.695606: step: 1040/1545, loss: 1.5593440532684326 2023-01-23 07:30:21.571879: step: 1042/1545, loss: 0.4341242015361786 2023-01-23 07:30:22.534881: step: 1044/1545, loss: 0.6965537071228027 2023-01-23 07:30:23.380385: step: 1046/1545, loss: 0.4674553871154785 2023-01-23 07:30:24.280989: step: 1048/1545, loss: 0.7627580761909485 2023-01-23 07:30:25.168223: step: 1050/1545, loss: 0.6278766989707947 2023-01-23 07:30:26.032029: step: 1052/1545, loss: 0.22057855129241943 2023-01-23 07:30:26.879256: step: 1054/1545, loss: 0.29772359132766724 2023-01-23 07:30:27.767612: step: 1056/1545, loss: 0.4883517026901245 2023-01-23 07:30:28.629144: step: 1058/1545, loss: 0.26220765709877014 2023-01-23 07:30:29.554943: step: 1060/1545, loss: 0.6113341450691223 2023-01-23 07:30:30.485563: step: 1062/1545, loss: 0.36150822043418884 2023-01-23 07:30:31.379539: step: 1064/1545, loss: 0.4547630548477173 2023-01-23 07:30:32.239329: step: 1066/1545, loss: 1.0293974876403809 2023-01-23 07:30:33.126629: step: 1068/1545, loss: 0.15378586947917938 2023-01-23 07:30:33.976539: step: 1070/1545, loss: 0.27045977115631104 2023-01-23 07:30:34.853515: step: 1072/1545, loss: 0.41969478130340576 2023-01-23 07:30:35.749712: step: 1074/1545, loss: 0.6122809648513794 2023-01-23 07:30:36.589412: step: 1076/1545, loss: 6.061173439025879 2023-01-23 07:30:37.518017: step: 1078/1545, loss: 0.36729133129119873 2023-01-23 07:30:38.349162: step: 1080/1545, loss: 0.7302696108818054 2023-01-23 07:30:39.213086: step: 1082/1545, loss: 0.9915440678596497 2023-01-23 07:30:40.169377: step: 1084/1545, loss: 0.24249497056007385 2023-01-23 07:30:41.056054: step: 1086/1545, loss: 0.3358074128627777 2023-01-23 07:30:41.961297: step: 1088/1545, loss: 0.4703402519226074 2023-01-23 07:30:42.872689: step: 1090/1545, loss: 0.6378198862075806 2023-01-23 07:30:43.760326: step: 1092/1545, loss: 0.5765533447265625 2023-01-23 07:30:44.620239: step: 1094/1545, loss: 0.3440801799297333 2023-01-23 07:30:45.569700: step: 1096/1545, loss: 0.39580801129341125 2023-01-23 07:30:46.404516: step: 1098/1545, loss: 0.4951246678829193 2023-01-23 07:30:47.262345: step: 1100/1545, loss: 0.7155473232269287 2023-01-23 07:30:48.120649: step: 1102/1545, loss: 0.5221801996231079 2023-01-23 07:30:49.022679: step: 1104/1545, loss: 0.3624618947505951 2023-01-23 07:30:49.895652: step: 1106/1545, loss: 2.800593614578247 2023-01-23 07:30:50.769048: step: 1108/1545, loss: 6.7137322425842285 2023-01-23 07:30:51.609505: step: 1110/1545, loss: 0.3805124759674072 2023-01-23 07:30:52.491544: step: 1112/1545, loss: 0.6829116940498352 2023-01-23 07:30:53.355980: step: 1114/1545, loss: 0.43117254972457886 2023-01-23 07:30:54.371407: step: 1116/1545, loss: 0.9971698522567749 2023-01-23 07:30:55.280059: step: 1118/1545, loss: 0.26803717017173767 2023-01-23 07:30:56.215153: step: 1120/1545, loss: 0.28110170364379883 2023-01-23 07:30:57.074224: step: 1122/1545, loss: 0.44542568922042847 2023-01-23 07:30:57.916326: step: 1124/1545, loss: 0.6763566136360168 2023-01-23 07:30:58.802897: step: 1126/1545, loss: 0.20437823235988617 2023-01-23 07:30:59.644979: step: 1128/1545, loss: 0.2939123809337616 2023-01-23 07:31:00.530754: step: 1130/1545, loss: 1.6267763376235962 2023-01-23 07:31:01.421807: step: 1132/1545, loss: 0.9071288108825684 2023-01-23 07:31:02.292720: step: 1134/1545, loss: 0.827156126499176 2023-01-23 07:31:03.188834: step: 1136/1545, loss: 0.37784844636917114 2023-01-23 07:31:04.049673: step: 1138/1545, loss: 0.5874662399291992 2023-01-23 07:31:04.904334: step: 1140/1545, loss: 0.8954342007637024 2023-01-23 07:31:05.806588: step: 1142/1545, loss: 0.738322913646698 2023-01-23 07:31:06.700037: step: 1144/1545, loss: 1.595410704612732 2023-01-23 07:31:07.574206: step: 1146/1545, loss: 1.77998685836792 2023-01-23 07:31:08.426244: step: 1148/1545, loss: 0.15201203525066376 2023-01-23 07:31:09.261796: step: 1150/1545, loss: 0.18909399211406708 2023-01-23 07:31:10.129111: step: 1152/1545, loss: 0.25020936131477356 2023-01-23 07:31:11.054221: step: 1154/1545, loss: 0.7225345969200134 2023-01-23 07:31:11.945789: step: 1156/1545, loss: 1.2511730194091797 2023-01-23 07:31:12.819873: step: 1158/1545, loss: 0.3931916356086731 2023-01-23 07:31:13.668739: step: 1160/1545, loss: 0.43709731101989746 2023-01-23 07:31:14.551776: step: 1162/1545, loss: 0.6517738699913025 2023-01-23 07:31:15.459427: step: 1164/1545, loss: 0.3871457576751709 2023-01-23 07:31:16.343113: step: 1166/1545, loss: 0.10775747895240784 2023-01-23 07:31:17.226823: step: 1168/1545, loss: 1.337328314781189 2023-01-23 07:31:18.120415: step: 1170/1545, loss: 2.370588779449463 2023-01-23 07:31:18.987302: step: 1172/1545, loss: 0.7423384189605713 2023-01-23 07:31:19.881909: step: 1174/1545, loss: 0.3173198699951172 2023-01-23 07:31:20.770578: step: 1176/1545, loss: 0.5100396275520325 2023-01-23 07:31:21.672020: step: 1178/1545, loss: 0.383431077003479 2023-01-23 07:31:22.539074: step: 1180/1545, loss: 0.2817322313785553 2023-01-23 07:31:23.439091: step: 1182/1545, loss: 0.31075528264045715 2023-01-23 07:31:24.281900: step: 1184/1545, loss: 0.6313117742538452 2023-01-23 07:31:25.140765: step: 1186/1545, loss: 0.9403086304664612 2023-01-23 07:31:26.007163: step: 1188/1545, loss: 0.26050224900245667 2023-01-23 07:31:26.849614: step: 1190/1545, loss: 0.9843766689300537 2023-01-23 07:31:27.754313: step: 1192/1545, loss: 1.602031946182251 2023-01-23 07:31:28.673052: step: 1194/1545, loss: 0.7318593859672546 2023-01-23 07:31:29.567088: step: 1196/1545, loss: 2.940634250640869 2023-01-23 07:31:30.592394: step: 1198/1545, loss: 0.6982203722000122 2023-01-23 07:31:31.438010: step: 1200/1545, loss: 0.42539602518081665 2023-01-23 07:31:32.317309: step: 1202/1545, loss: 0.3320583999156952 2023-01-23 07:31:33.139967: step: 1204/1545, loss: 0.4279624819755554 2023-01-23 07:31:33.991532: step: 1206/1545, loss: 0.9533736109733582 2023-01-23 07:31:34.848793: step: 1208/1545, loss: 1.1268173456192017 2023-01-23 07:31:35.715988: step: 1210/1545, loss: 0.6011914014816284 2023-01-23 07:31:36.630941: step: 1212/1545, loss: 0.5801642537117004 2023-01-23 07:31:37.517476: step: 1214/1545, loss: 0.6762493252754211 2023-01-23 07:31:38.394017: step: 1216/1545, loss: 0.30228492617607117 2023-01-23 07:31:39.243054: step: 1218/1545, loss: 0.3824913799762726 2023-01-23 07:31:40.105825: step: 1220/1545, loss: 0.5959181785583496 2023-01-23 07:31:40.953448: step: 1222/1545, loss: 0.9201918840408325 2023-01-23 07:31:41.839955: step: 1224/1545, loss: 0.2788045406341553 2023-01-23 07:31:42.712933: step: 1226/1545, loss: 0.4550771117210388 2023-01-23 07:31:43.685832: step: 1228/1545, loss: 0.6069190502166748 2023-01-23 07:31:44.543713: step: 1230/1545, loss: 0.2455403208732605 2023-01-23 07:31:45.433886: step: 1232/1545, loss: 0.4404696524143219 2023-01-23 07:31:46.253757: step: 1234/1545, loss: 0.3517642915248871 2023-01-23 07:31:47.106633: step: 1236/1545, loss: 0.2975755035877228 2023-01-23 07:31:47.980435: step: 1238/1545, loss: 0.7163832187652588 2023-01-23 07:31:48.870683: step: 1240/1545, loss: 0.1592397689819336 2023-01-23 07:31:49.741873: step: 1242/1545, loss: 0.49618738889694214 2023-01-23 07:31:50.680358: step: 1244/1545, loss: 1.026024341583252 2023-01-23 07:31:51.515135: step: 1246/1545, loss: 0.3788059949874878 2023-01-23 07:31:52.371726: step: 1248/1545, loss: 0.707081139087677 2023-01-23 07:31:53.258745: step: 1250/1545, loss: 0.35260963439941406 2023-01-23 07:31:54.166784: step: 1252/1545, loss: 0.7310576438903809 2023-01-23 07:31:55.081998: step: 1254/1545, loss: 0.2873956859111786 2023-01-23 07:31:55.969150: step: 1256/1545, loss: 0.5960148572921753 2023-01-23 07:31:56.798287: step: 1258/1545, loss: 0.3272304832935333 2023-01-23 07:31:57.697184: step: 1260/1545, loss: 0.9025127291679382 2023-01-23 07:31:58.579797: step: 1262/1545, loss: 0.6381398439407349 2023-01-23 07:31:59.425849: step: 1264/1545, loss: 0.35019025206565857 2023-01-23 07:32:00.302967: step: 1266/1545, loss: 0.5943032503128052 2023-01-23 07:32:01.212425: step: 1268/1545, loss: 0.2797730267047882 2023-01-23 07:32:02.095913: step: 1270/1545, loss: 0.578211784362793 2023-01-23 07:32:03.000061: step: 1272/1545, loss: 2.743814706802368 2023-01-23 07:32:03.905488: step: 1274/1545, loss: 0.8339812755584717 2023-01-23 07:32:04.785394: step: 1276/1545, loss: 0.19260022044181824 2023-01-23 07:32:05.676806: step: 1278/1545, loss: 0.28079017996788025 2023-01-23 07:32:06.553530: step: 1280/1545, loss: 5.3271589279174805 2023-01-23 07:32:07.419176: step: 1282/1545, loss: 0.3806162178516388 2023-01-23 07:32:08.283136: step: 1284/1545, loss: 0.2211112678050995 2023-01-23 07:32:09.191929: step: 1286/1545, loss: 0.2027304321527481 2023-01-23 07:32:10.124531: step: 1288/1545, loss: 0.3904030919075012 2023-01-23 07:32:10.985838: step: 1290/1545, loss: 0.530445396900177 2023-01-23 07:32:11.826154: step: 1292/1545, loss: 0.6051645278930664 2023-01-23 07:32:12.766845: step: 1294/1545, loss: 0.5418934226036072 2023-01-23 07:32:13.633940: step: 1296/1545, loss: 0.46887168288230896 2023-01-23 07:32:14.465353: step: 1298/1545, loss: 1.1077724695205688 2023-01-23 07:32:15.312986: step: 1300/1545, loss: 0.4366365373134613 2023-01-23 07:32:16.194018: step: 1302/1545, loss: 0.27979785203933716 2023-01-23 07:32:17.048581: step: 1304/1545, loss: 0.4808986186981201 2023-01-23 07:32:17.946908: step: 1306/1545, loss: 0.4840971827507019 2023-01-23 07:32:18.797851: step: 1308/1545, loss: 0.5255663394927979 2023-01-23 07:32:19.676670: step: 1310/1545, loss: 0.8746792078018188 2023-01-23 07:32:20.547538: step: 1312/1545, loss: 0.7848596572875977 2023-01-23 07:32:21.425386: step: 1314/1545, loss: 1.1914719343185425 2023-01-23 07:32:22.284236: step: 1316/1545, loss: 0.5725301504135132 2023-01-23 07:32:23.202423: step: 1318/1545, loss: 0.11804075539112091 2023-01-23 07:32:24.076450: step: 1320/1545, loss: 0.4221995770931244 2023-01-23 07:32:24.988658: step: 1322/1545, loss: 1.7370115518569946 2023-01-23 07:32:25.955923: step: 1324/1545, loss: 1.3726179599761963 2023-01-23 07:32:26.857532: step: 1326/1545, loss: 2.0377025604248047 2023-01-23 07:32:27.742739: step: 1328/1545, loss: 0.5021401643753052 2023-01-23 07:32:28.660058: step: 1330/1545, loss: 0.4235436022281647 2023-01-23 07:32:29.516478: step: 1332/1545, loss: 0.40118151903152466 2023-01-23 07:32:30.402208: step: 1334/1545, loss: 0.47110122442245483 2023-01-23 07:32:31.260622: step: 1336/1545, loss: 0.2142452746629715 2023-01-23 07:32:32.155442: step: 1338/1545, loss: 0.9959790110588074 2023-01-23 07:32:33.039444: step: 1340/1545, loss: 0.7399562001228333 2023-01-23 07:32:33.889844: step: 1342/1545, loss: 0.5051155686378479 2023-01-23 07:32:34.757756: step: 1344/1545, loss: 0.4831992983818054 2023-01-23 07:32:35.585151: step: 1346/1545, loss: 0.19223253428936005 2023-01-23 07:32:36.496733: step: 1348/1545, loss: 0.3460606038570404 2023-01-23 07:32:37.332390: step: 1350/1545, loss: 0.10609959065914154 2023-01-23 07:32:38.200789: step: 1352/1545, loss: 0.16098925471305847 2023-01-23 07:32:39.048209: step: 1354/1545, loss: 0.22882571816444397 2023-01-23 07:32:39.894704: step: 1356/1545, loss: 0.3723149597644806 2023-01-23 07:32:40.788631: step: 1358/1545, loss: 0.0700378566980362 2023-01-23 07:32:41.707376: step: 1360/1545, loss: 0.6289253234863281 2023-01-23 07:32:42.666395: step: 1362/1545, loss: 0.25883764028549194 2023-01-23 07:32:43.589876: step: 1364/1545, loss: 0.9979850053787231 2023-01-23 07:32:44.436337: step: 1366/1545, loss: 0.2775644063949585 2023-01-23 07:32:45.251169: step: 1368/1545, loss: 0.12664444744586945 2023-01-23 07:32:46.156913: step: 1370/1545, loss: 0.8198251724243164 2023-01-23 07:32:47.034874: step: 1372/1545, loss: 0.5338143706321716 2023-01-23 07:32:47.884299: step: 1374/1545, loss: 3.024979829788208 2023-01-23 07:32:48.799109: step: 1376/1545, loss: 1.254595398902893 2023-01-23 07:32:49.688131: step: 1378/1545, loss: 0.5074794292449951 2023-01-23 07:32:50.539598: step: 1380/1545, loss: 0.17224952578544617 2023-01-23 07:32:51.424336: step: 1382/1545, loss: 1.6199430227279663 2023-01-23 07:32:52.290560: step: 1384/1545, loss: 0.49254918098449707 2023-01-23 07:32:53.148150: step: 1386/1545, loss: 0.2685869634151459 2023-01-23 07:32:54.033143: step: 1388/1545, loss: 0.308036744594574 2023-01-23 07:32:54.911754: step: 1390/1545, loss: 0.8889702558517456 2023-01-23 07:32:55.810743: step: 1392/1545, loss: 0.4519979953765869 2023-01-23 07:32:56.678186: step: 1394/1545, loss: 0.325596421957016 2023-01-23 07:32:57.565036: step: 1396/1545, loss: 1.9318205118179321 2023-01-23 07:32:58.458983: step: 1398/1545, loss: 0.417165070772171 2023-01-23 07:32:59.291247: step: 1400/1545, loss: 0.2995816171169281 2023-01-23 07:33:00.142646: step: 1402/1545, loss: 1.0667635202407837 2023-01-23 07:33:01.074981: step: 1404/1545, loss: 0.63909912109375 2023-01-23 07:33:01.980024: step: 1406/1545, loss: 0.41774114966392517 2023-01-23 07:33:02.842232: step: 1408/1545, loss: 0.36729753017425537 2023-01-23 07:33:03.716235: step: 1410/1545, loss: 0.4767416715621948 2023-01-23 07:33:04.586845: step: 1412/1545, loss: 0.6277151703834534 2023-01-23 07:33:05.443008: step: 1414/1545, loss: 0.27952840924263 2023-01-23 07:33:06.322383: step: 1416/1545, loss: 0.8781722784042358 2023-01-23 07:33:07.199450: step: 1418/1545, loss: 0.17927873134613037 2023-01-23 07:33:08.038892: step: 1420/1545, loss: 0.37170079350471497 2023-01-23 07:33:08.888558: step: 1422/1545, loss: 0.699293851852417 2023-01-23 07:33:09.815764: step: 1424/1545, loss: 1.2056535482406616 2023-01-23 07:33:10.707854: step: 1426/1545, loss: 1.6840548515319824 2023-01-23 07:33:11.562745: step: 1428/1545, loss: 0.6297683119773865 2023-01-23 07:33:12.596791: step: 1430/1545, loss: 0.2065836638212204 2023-01-23 07:33:13.451896: step: 1432/1545, loss: 0.12122040241956711 2023-01-23 07:33:14.321535: step: 1434/1545, loss: 0.40325072407722473 2023-01-23 07:33:15.260810: step: 1436/1545, loss: 0.2375839203596115 2023-01-23 07:33:16.161698: step: 1438/1545, loss: 0.40952226519584656 2023-01-23 07:33:17.014831: step: 1440/1545, loss: 0.43307816982269287 2023-01-23 07:33:17.885862: step: 1442/1545, loss: 0.7018965482711792 2023-01-23 07:33:18.724989: step: 1444/1545, loss: 0.4008820354938507 2023-01-23 07:33:19.622323: step: 1446/1545, loss: 0.7540109157562256 2023-01-23 07:33:20.481421: step: 1448/1545, loss: 0.15086311101913452 2023-01-23 07:33:21.393917: step: 1450/1545, loss: 0.08490835130214691 2023-01-23 07:33:22.285387: step: 1452/1545, loss: 0.280728816986084 2023-01-23 07:33:23.145327: step: 1454/1545, loss: 0.8184300065040588 2023-01-23 07:33:24.026724: step: 1456/1545, loss: 0.45521676540374756 2023-01-23 07:33:24.914811: step: 1458/1545, loss: 0.7015402317047119 2023-01-23 07:33:25.758343: step: 1460/1545, loss: 0.3089509606361389 2023-01-23 07:33:26.623584: step: 1462/1545, loss: 0.19601644575595856 2023-01-23 07:33:27.538880: step: 1464/1545, loss: 0.2520970106124878 2023-01-23 07:33:28.388858: step: 1466/1545, loss: 0.5187829732894897 2023-01-23 07:33:29.240604: step: 1468/1545, loss: 0.1847701370716095 2023-01-23 07:33:30.084062: step: 1470/1545, loss: 0.9717105031013489 2023-01-23 07:33:31.014361: step: 1472/1545, loss: 0.14187464118003845 2023-01-23 07:33:31.864342: step: 1474/1545, loss: 0.3344445824623108 2023-01-23 07:33:32.721781: step: 1476/1545, loss: 0.5039590001106262 2023-01-23 07:33:33.583852: step: 1478/1545, loss: 0.42997536063194275 2023-01-23 07:33:34.481351: step: 1480/1545, loss: 0.4493499994277954 2023-01-23 07:33:35.383903: step: 1482/1545, loss: 0.7973239421844482 2023-01-23 07:33:36.251563: step: 1484/1545, loss: 0.2593356668949127 2023-01-23 07:33:37.122281: step: 1486/1545, loss: 2.119175434112549 2023-01-23 07:33:37.984869: step: 1488/1545, loss: 0.4694696366786957 2023-01-23 07:33:38.883310: step: 1490/1545, loss: 1.2552274465560913 2023-01-23 07:33:39.830549: step: 1492/1545, loss: 0.3756677210330963 2023-01-23 07:33:40.699370: step: 1494/1545, loss: 0.30297473073005676 2023-01-23 07:33:41.540597: step: 1496/1545, loss: 0.53011155128479 2023-01-23 07:33:42.414220: step: 1498/1545, loss: 2.7189974784851074 2023-01-23 07:33:43.285958: step: 1500/1545, loss: 0.819780707359314 2023-01-23 07:33:44.094828: step: 1502/1545, loss: 0.3775336742401123 2023-01-23 07:33:44.960756: step: 1504/1545, loss: 0.3747589588165283 2023-01-23 07:33:45.819943: step: 1506/1545, loss: 0.8475229740142822 2023-01-23 07:33:46.753973: step: 1508/1545, loss: 0.3815055191516876 2023-01-23 07:33:47.615966: step: 1510/1545, loss: 0.3557485044002533 2023-01-23 07:33:48.540704: step: 1512/1545, loss: 0.5517610907554626 2023-01-23 07:33:49.459035: step: 1514/1545, loss: 0.16237807273864746 2023-01-23 07:33:50.351721: step: 1516/1545, loss: 3.316161632537842 2023-01-23 07:33:51.224958: step: 1518/1545, loss: 0.6562069654464722 2023-01-23 07:33:52.095162: step: 1520/1545, loss: 0.2651701271533966 2023-01-23 07:33:52.992753: step: 1522/1545, loss: 1.5353668928146362 2023-01-23 07:33:53.819833: step: 1524/1545, loss: 1.7042213678359985 2023-01-23 07:33:54.730081: step: 1526/1545, loss: 0.6195593476295471 2023-01-23 07:33:55.585192: step: 1528/1545, loss: 0.3320419490337372 2023-01-23 07:33:56.488603: step: 1530/1545, loss: 0.3481166362762451 2023-01-23 07:33:57.359954: step: 1532/1545, loss: 0.711707353591919 2023-01-23 07:33:58.239705: step: 1534/1545, loss: 0.8267597556114197 2023-01-23 07:33:59.150224: step: 1536/1545, loss: 0.14001448452472687 2023-01-23 07:34:00.034863: step: 1538/1545, loss: 0.47292840480804443 2023-01-23 07:34:00.884239: step: 1540/1545, loss: 0.40614306926727295 2023-01-23 07:34:01.870184: step: 1542/1545, loss: 0.30296891927719116 2023-01-23 07:34:02.794304: step: 1544/1545, loss: 0.32768234610557556 2023-01-23 07:34:03.668257: step: 1546/1545, loss: 0.3605706989765167 2023-01-23 07:34:04.579180: step: 1548/1545, loss: 0.8213576674461365 2023-01-23 07:34:05.519890: step: 1550/1545, loss: 0.6921624541282654 2023-01-23 07:34:06.389467: step: 1552/1545, loss: 0.3134850859642029 2023-01-23 07:34:07.210908: step: 1554/1545, loss: 0.8460861444473267 2023-01-23 07:34:08.124401: step: 1556/1545, loss: 0.3245958983898163 2023-01-23 07:34:08.985641: step: 1558/1545, loss: 0.6041489839553833 2023-01-23 07:34:09.975759: step: 1560/1545, loss: 0.2896674573421478 2023-01-23 07:34:10.850444: step: 1562/1545, loss: 0.8191152215003967 2023-01-23 07:34:11.700039: step: 1564/1545, loss: 0.772260844707489 2023-01-23 07:34:12.560103: step: 1566/1545, loss: 1.0485539436340332 2023-01-23 07:34:13.438656: step: 1568/1545, loss: 0.7669302225112915 2023-01-23 07:34:14.299010: step: 1570/1545, loss: 0.3772231936454773 2023-01-23 07:34:15.223711: step: 1572/1545, loss: 0.8345100283622742 2023-01-23 07:34:16.081866: step: 1574/1545, loss: 0.35231977701187134 2023-01-23 07:34:16.936818: step: 1576/1545, loss: 0.2295685112476349 2023-01-23 07:34:17.776362: step: 1578/1545, loss: 0.22398200631141663 2023-01-23 07:34:18.682266: step: 1580/1545, loss: 0.4587920308113098 2023-01-23 07:34:19.663992: step: 1582/1545, loss: 0.4084432125091553 2023-01-23 07:34:20.576483: step: 1584/1545, loss: 0.40320104360580444 2023-01-23 07:34:21.468175: step: 1586/1545, loss: 1.015903115272522 2023-01-23 07:34:22.334066: step: 1588/1545, loss: 0.7208713293075562 2023-01-23 07:34:23.175582: step: 1590/1545, loss: 0.4806908369064331 2023-01-23 07:34:24.030930: step: 1592/1545, loss: 0.353092759847641 2023-01-23 07:34:24.900756: step: 1594/1545, loss: 0.19596943259239197 2023-01-23 07:34:25.765268: step: 1596/1545, loss: 0.5539882779121399 2023-01-23 07:34:26.733985: step: 1598/1545, loss: 0.35696646571159363 2023-01-23 07:34:27.605940: step: 1600/1545, loss: 1.2200467586517334 2023-01-23 07:34:28.520892: step: 1602/1545, loss: 0.253228098154068 2023-01-23 07:34:29.419065: step: 1604/1545, loss: 1.1883586645126343 2023-01-23 07:34:30.383452: step: 1606/1545, loss: 0.5127720832824707 2023-01-23 07:34:31.324535: step: 1608/1545, loss: 2.5854380130767822 2023-01-23 07:34:32.134301: step: 1610/1545, loss: 0.37901923060417175 2023-01-23 07:34:32.972040: step: 1612/1545, loss: 0.15590061247348785 2023-01-23 07:34:33.865996: step: 1614/1545, loss: 0.5824854373931885 2023-01-23 07:34:34.725738: step: 1616/1545, loss: 0.392404705286026 2023-01-23 07:34:35.657435: step: 1618/1545, loss: 0.4915558993816376 2023-01-23 07:34:36.556767: step: 1620/1545, loss: 0.7164822816848755 2023-01-23 07:34:37.411253: step: 1622/1545, loss: 0.28426969051361084 2023-01-23 07:34:38.294738: step: 1624/1545, loss: 7.222412586212158 2023-01-23 07:34:39.170021: step: 1626/1545, loss: 1.705232858657837 2023-01-23 07:34:40.043332: step: 1628/1545, loss: 0.6385241746902466 2023-01-23 07:34:40.932514: step: 1630/1545, loss: 2.2537689208984375 2023-01-23 07:34:41.761663: step: 1632/1545, loss: 0.6933020949363708 2023-01-23 07:34:42.621231: step: 1634/1545, loss: 0.289793461561203 2023-01-23 07:34:43.519958: step: 1636/1545, loss: 3.2216315269470215 2023-01-23 07:34:44.494588: step: 1638/1545, loss: 0.640414834022522 2023-01-23 07:34:45.378755: step: 1640/1545, loss: 0.36279428005218506 2023-01-23 07:34:46.247991: step: 1642/1545, loss: 0.6299559473991394 2023-01-23 07:34:47.088971: step: 1644/1545, loss: 0.5813661813735962 2023-01-23 07:34:47.994135: step: 1646/1545, loss: 0.3977559506893158 2023-01-23 07:34:48.862294: step: 1648/1545, loss: 0.4197240471839905 2023-01-23 07:34:49.758752: step: 1650/1545, loss: 6.601246356964111 2023-01-23 07:34:50.695150: step: 1652/1545, loss: 0.2593086361885071 2023-01-23 07:34:51.594284: step: 1654/1545, loss: 0.25360968708992004 2023-01-23 07:34:52.483560: step: 1656/1545, loss: 0.215562105178833 2023-01-23 07:34:53.335467: step: 1658/1545, loss: 1.032940149307251 2023-01-23 07:34:54.224817: step: 1660/1545, loss: 0.4773313105106354 2023-01-23 07:34:55.165243: step: 1662/1545, loss: 5.800097465515137 2023-01-23 07:34:56.030293: step: 1664/1545, loss: 0.6040709614753723 2023-01-23 07:34:56.896530: step: 1666/1545, loss: 1.6386343240737915 2023-01-23 07:34:57.756116: step: 1668/1545, loss: 2.569321393966675 2023-01-23 07:34:58.604918: step: 1670/1545, loss: 0.6246617436408997 2023-01-23 07:34:59.490305: step: 1672/1545, loss: 0.9769133925437927 2023-01-23 07:35:00.371169: step: 1674/1545, loss: 1.1097595691680908 2023-01-23 07:35:01.252872: step: 1676/1545, loss: 0.9768537878990173 2023-01-23 07:35:02.186036: step: 1678/1545, loss: 1.3295224905014038 2023-01-23 07:35:03.107910: step: 1680/1545, loss: 0.6167385578155518 2023-01-23 07:35:03.988447: step: 1682/1545, loss: 0.9838741421699524 2023-01-23 07:35:04.910173: step: 1684/1545, loss: 0.5809248089790344 2023-01-23 07:35:05.805307: step: 1686/1545, loss: 0.6796049475669861 2023-01-23 07:35:06.740751: step: 1688/1545, loss: 0.5062656402587891 2023-01-23 07:35:07.641754: step: 1690/1545, loss: 1.5897620916366577 2023-01-23 07:35:08.517307: step: 1692/1545, loss: 0.41140374541282654 2023-01-23 07:35:09.395635: step: 1694/1545, loss: 1.4197720289230347 2023-01-23 07:35:10.282383: step: 1696/1545, loss: 0.5485459566116333 2023-01-23 07:35:11.177672: step: 1698/1545, loss: 0.4504745602607727 2023-01-23 07:35:12.054230: step: 1700/1545, loss: 0.29651257395744324 2023-01-23 07:35:12.962448: step: 1702/1545, loss: 0.3554045557975769 2023-01-23 07:35:13.810833: step: 1704/1545, loss: 0.4786364436149597 2023-01-23 07:35:14.711324: step: 1706/1545, loss: 1.165558099746704 2023-01-23 07:35:15.606771: step: 1708/1545, loss: 0.40462759137153625 2023-01-23 07:35:16.506617: step: 1710/1545, loss: 3.6138617992401123 2023-01-23 07:35:17.428215: step: 1712/1545, loss: 0.743809700012207 2023-01-23 07:35:18.319487: step: 1714/1545, loss: 0.36387643218040466 2023-01-23 07:35:19.228989: step: 1716/1545, loss: 0.7087926268577576 2023-01-23 07:35:20.100989: step: 1718/1545, loss: 0.6799668669700623 2023-01-23 07:35:20.984047: step: 1720/1545, loss: 0.8832476735115051 2023-01-23 07:35:21.868054: step: 1722/1545, loss: 0.44895634055137634 2023-01-23 07:35:22.731328: step: 1724/1545, loss: 0.36027398705482483 2023-01-23 07:35:23.583127: step: 1726/1545, loss: 1.0513169765472412 2023-01-23 07:35:24.452204: step: 1728/1545, loss: 0.2686297297477722 2023-01-23 07:35:25.320956: step: 1730/1545, loss: 0.35279980301856995 2023-01-23 07:35:26.204579: step: 1732/1545, loss: 0.21724365651607513 2023-01-23 07:35:27.048154: step: 1734/1545, loss: 0.17900961637496948 2023-01-23 07:35:27.914382: step: 1736/1545, loss: 0.11739957332611084 2023-01-23 07:35:28.771274: step: 1738/1545, loss: 0.29028740525245667 2023-01-23 07:35:29.663362: step: 1740/1545, loss: 2.552614688873291 2023-01-23 07:35:30.676813: step: 1742/1545, loss: 0.6622680425643921 2023-01-23 07:35:31.565288: step: 1744/1545, loss: 0.35771822929382324 2023-01-23 07:35:32.490922: step: 1746/1545, loss: 0.7125332951545715 2023-01-23 07:35:33.389629: step: 1748/1545, loss: 0.8907274007797241 2023-01-23 07:35:34.264748: step: 1750/1545, loss: 0.34370970726013184 2023-01-23 07:35:35.162638: step: 1752/1545, loss: 0.267996221780777 2023-01-23 07:35:36.026143: step: 1754/1545, loss: 0.4669540226459503 2023-01-23 07:35:36.876514: step: 1756/1545, loss: 0.8679146766662598 2023-01-23 07:35:37.735356: step: 1758/1545, loss: 0.41911834478378296 2023-01-23 07:35:38.609665: step: 1760/1545, loss: 0.23792453110218048 2023-01-23 07:35:39.480224: step: 1762/1545, loss: 0.6183888912200928 2023-01-23 07:35:40.387223: step: 1764/1545, loss: 0.3085484504699707 2023-01-23 07:35:41.281141: step: 1766/1545, loss: 1.6218839883804321 2023-01-23 07:35:42.149375: step: 1768/1545, loss: 1.2495428323745728 2023-01-23 07:35:43.013704: step: 1770/1545, loss: 0.35714995861053467 2023-01-23 07:35:43.977699: step: 1772/1545, loss: 0.5028138756752014 2023-01-23 07:35:44.865087: step: 1774/1545, loss: 0.7378065586090088 2023-01-23 07:35:45.747773: step: 1776/1545, loss: 0.30649083852767944 2023-01-23 07:35:46.624667: step: 1778/1545, loss: 3.5023610591888428 2023-01-23 07:35:47.509116: step: 1780/1545, loss: 0.4725298285484314 2023-01-23 07:35:48.376222: step: 1782/1545, loss: 0.6298626065254211 2023-01-23 07:35:49.271655: step: 1784/1545, loss: 1.5537694692611694 2023-01-23 07:35:50.174076: step: 1786/1545, loss: 0.41021016240119934 2023-01-23 07:35:51.066243: step: 1788/1545, loss: 0.6251460909843445 2023-01-23 07:35:51.972867: step: 1790/1545, loss: 0.4493609070777893 2023-01-23 07:35:52.848599: step: 1792/1545, loss: 0.5539501309394836 2023-01-23 07:35:53.699890: step: 1794/1545, loss: 0.34832656383514404 2023-01-23 07:35:54.578415: step: 1796/1545, loss: 0.6600630283355713 2023-01-23 07:35:55.502245: step: 1798/1545, loss: 0.4971758723258972 2023-01-23 07:35:56.394330: step: 1800/1545, loss: 0.3613394796848297 2023-01-23 07:35:57.262929: step: 1802/1545, loss: 0.7451246976852417 2023-01-23 07:35:58.139470: step: 1804/1545, loss: 0.4110865592956543 2023-01-23 07:35:59.025725: step: 1806/1545, loss: 0.5638744831085205 2023-01-23 07:35:59.909352: step: 1808/1545, loss: 0.8936035633087158 2023-01-23 07:36:00.768349: step: 1810/1545, loss: 0.8355745077133179 2023-01-23 07:36:01.618642: step: 1812/1545, loss: 0.6585228443145752 2023-01-23 07:36:02.485637: step: 1814/1545, loss: 0.6492664813995361 2023-01-23 07:36:03.362526: step: 1816/1545, loss: 5.59675407409668 2023-01-23 07:36:04.229669: step: 1818/1545, loss: 2.2834997177124023 2023-01-23 07:36:05.160957: step: 1820/1545, loss: 0.9388369917869568 2023-01-23 07:36:06.055963: step: 1822/1545, loss: 1.461849331855774 2023-01-23 07:36:06.997805: step: 1824/1545, loss: 0.5807781219482422 2023-01-23 07:36:07.926503: step: 1826/1545, loss: 0.6801634430885315 2023-01-23 07:36:08.756238: step: 1828/1545, loss: 0.7230404615402222 2023-01-23 07:36:09.667695: step: 1830/1545, loss: 0.4946284592151642 2023-01-23 07:36:10.506277: step: 1832/1545, loss: 1.0809928178787231 2023-01-23 07:36:11.365319: step: 1834/1545, loss: 0.47170430421829224 2023-01-23 07:36:12.292454: step: 1836/1545, loss: 2.7085344791412354 2023-01-23 07:36:13.173239: step: 1838/1545, loss: 0.4151713252067566 2023-01-23 07:36:14.097786: step: 1840/1545, loss: 1.1582682132720947 2023-01-23 07:36:14.964308: step: 1842/1545, loss: 1.211820125579834 2023-01-23 07:36:15.892689: step: 1844/1545, loss: 0.30880609154701233 2023-01-23 07:36:16.746681: step: 1846/1545, loss: 0.5369495749473572 2023-01-23 07:36:17.598126: step: 1848/1545, loss: 0.7976698279380798 2023-01-23 07:36:18.453634: step: 1850/1545, loss: 0.5986706018447876 2023-01-23 07:36:19.312666: step: 1852/1545, loss: 0.2418416142463684 2023-01-23 07:36:20.164780: step: 1854/1545, loss: 0.4915926456451416 2023-01-23 07:36:21.065800: step: 1856/1545, loss: 0.2675488591194153 2023-01-23 07:36:21.905197: step: 1858/1545, loss: 0.7581246495246887 2023-01-23 07:36:22.801027: step: 1860/1545, loss: 0.8585411310195923 2023-01-23 07:36:23.671651: step: 1862/1545, loss: 0.5121473073959351 2023-01-23 07:36:24.590802: step: 1864/1545, loss: 2.151583194732666 2023-01-23 07:36:25.432482: step: 1866/1545, loss: 0.3706871569156647 2023-01-23 07:36:26.298085: step: 1868/1545, loss: 0.17173321545124054 2023-01-23 07:36:27.140498: step: 1870/1545, loss: 0.7385793924331665 2023-01-23 07:36:27.998345: step: 1872/1545, loss: 0.310346394777298 2023-01-23 07:36:28.891307: step: 1874/1545, loss: 0.41346243023872375 2023-01-23 07:36:29.734993: step: 1876/1545, loss: 0.16432948410511017 2023-01-23 07:36:30.583724: step: 1878/1545, loss: 0.5935401916503906 2023-01-23 07:36:31.481905: step: 1880/1545, loss: 7.727423667907715 2023-01-23 07:36:32.378351: step: 1882/1545, loss: 0.4780309796333313 2023-01-23 07:36:33.256103: step: 1884/1545, loss: 0.38398125767707825 2023-01-23 07:36:34.132298: step: 1886/1545, loss: 0.3072183132171631 2023-01-23 07:36:34.973089: step: 1888/1545, loss: 0.6011112332344055 2023-01-23 07:36:35.819478: step: 1890/1545, loss: 0.3672184646129608 2023-01-23 07:36:36.647462: step: 1892/1545, loss: 0.4874172806739807 2023-01-23 07:36:37.521449: step: 1894/1545, loss: 0.2583790719509125 2023-01-23 07:36:38.433431: step: 1896/1545, loss: 0.8366602063179016 2023-01-23 07:36:39.294153: step: 1898/1545, loss: 0.3069402873516083 2023-01-23 07:36:40.156932: step: 1900/1545, loss: 0.29507869482040405 2023-01-23 07:36:41.071989: step: 1902/1545, loss: 0.6735225319862366 2023-01-23 07:36:41.963455: step: 1904/1545, loss: 0.23084989190101624 2023-01-23 07:36:42.825675: step: 1906/1545, loss: 0.33000126481056213 2023-01-23 07:36:43.793060: step: 1908/1545, loss: 0.5406249761581421 2023-01-23 07:36:44.663038: step: 1910/1545, loss: 0.479132741689682 2023-01-23 07:36:45.520327: step: 1912/1545, loss: 0.6147604584693909 2023-01-23 07:36:46.403626: step: 1914/1545, loss: 0.22057144343852997 2023-01-23 07:36:47.299527: step: 1916/1545, loss: 0.6394293308258057 2023-01-23 07:36:48.146704: step: 1918/1545, loss: 0.35872983932495117 2023-01-23 07:36:49.031283: step: 1920/1545, loss: 0.49693870544433594 2023-01-23 07:36:49.931408: step: 1922/1545, loss: 0.5136330723762512 2023-01-23 07:36:50.785831: step: 1924/1545, loss: 0.6540898084640503 2023-01-23 07:36:51.627868: step: 1926/1545, loss: 0.7208805680274963 2023-01-23 07:36:52.493276: step: 1928/1545, loss: 0.866233766078949 2023-01-23 07:36:53.350243: step: 1930/1545, loss: 0.5958753824234009 2023-01-23 07:36:54.208648: step: 1932/1545, loss: 0.9041691422462463 2023-01-23 07:36:55.145114: step: 1934/1545, loss: 0.2599678337574005 2023-01-23 07:36:56.005161: step: 1936/1545, loss: 0.579077959060669 2023-01-23 07:36:56.934603: step: 1938/1545, loss: 0.25370270013809204 2023-01-23 07:36:57.810474: step: 1940/1545, loss: 0.35241153836250305 2023-01-23 07:36:58.684253: step: 1942/1545, loss: 0.2923751175403595 2023-01-23 07:36:59.555577: step: 1944/1545, loss: 1.4284659624099731 2023-01-23 07:37:00.436438: step: 1946/1545, loss: 0.8266757726669312 2023-01-23 07:37:01.316044: step: 1948/1545, loss: 0.358257532119751 2023-01-23 07:37:02.224693: step: 1950/1545, loss: 0.7287195920944214 2023-01-23 07:37:03.147395: step: 1952/1545, loss: 0.12660770118236542 2023-01-23 07:37:04.056817: step: 1954/1545, loss: 0.4426373839378357 2023-01-23 07:37:04.970148: step: 1956/1545, loss: 0.5663570761680603 2023-01-23 07:37:05.839242: step: 1958/1545, loss: 0.45092126727104187 2023-01-23 07:37:06.795168: step: 1960/1545, loss: 0.6744584441184998 2023-01-23 07:37:07.698017: step: 1962/1545, loss: 0.23249301314353943 2023-01-23 07:37:08.598706: step: 1964/1545, loss: 4.742470741271973 2023-01-23 07:37:09.439466: step: 1966/1545, loss: 0.635643720626831 2023-01-23 07:37:10.318501: step: 1968/1545, loss: 0.9200101494789124 2023-01-23 07:37:11.209954: step: 1970/1545, loss: 0.810088038444519 2023-01-23 07:37:12.079190: step: 1972/1545, loss: 0.3353208899497986 2023-01-23 07:37:12.985870: step: 1974/1545, loss: 0.3085276484489441 2023-01-23 07:37:13.873414: step: 1976/1545, loss: 0.4242677092552185 2023-01-23 07:37:14.749598: step: 1978/1545, loss: 0.4688350558280945 2023-01-23 07:37:15.630658: step: 1980/1545, loss: 0.25495144724845886 2023-01-23 07:37:16.552480: step: 1982/1545, loss: 0.9058592915534973 2023-01-23 07:37:17.436050: step: 1984/1545, loss: 0.4588048756122589 2023-01-23 07:37:18.327477: step: 1986/1545, loss: 0.6359163522720337 2023-01-23 07:37:19.245823: step: 1988/1545, loss: 0.43114370107650757 2023-01-23 07:37:20.121146: step: 1990/1545, loss: 0.4079873561859131 2023-01-23 07:37:21.030952: step: 1992/1545, loss: 0.48241353034973145 2023-01-23 07:37:21.930502: step: 1994/1545, loss: 0.55881267786026 2023-01-23 07:37:22.783467: step: 1996/1545, loss: 0.2941367030143738 2023-01-23 07:37:23.654988: step: 1998/1545, loss: 0.27768176794052124 2023-01-23 07:37:24.524585: step: 2000/1545, loss: 0.7876664996147156 2023-01-23 07:37:25.400934: step: 2002/1545, loss: 0.5688458681106567 2023-01-23 07:37:26.268845: step: 2004/1545, loss: 0.6295020580291748 2023-01-23 07:37:27.161609: step: 2006/1545, loss: 0.19027455151081085 2023-01-23 07:37:28.031063: step: 2008/1545, loss: 1.48065185546875 2023-01-23 07:37:28.898598: step: 2010/1545, loss: 0.6180834174156189 2023-01-23 07:37:29.782661: step: 2012/1545, loss: 0.3796517252922058 2023-01-23 07:37:30.660095: step: 2014/1545, loss: 0.2787681519985199 2023-01-23 07:37:31.628995: step: 2016/1545, loss: 0.46491697430610657 2023-01-23 07:37:32.537184: step: 2018/1545, loss: 1.3281736373901367 2023-01-23 07:37:33.405447: step: 2020/1545, loss: 0.5347513556480408 2023-01-23 07:37:34.259163: step: 2022/1545, loss: 0.5735498666763306 2023-01-23 07:37:35.093785: step: 2024/1545, loss: 0.5073699951171875 2023-01-23 07:37:35.946892: step: 2026/1545, loss: 0.11821761727333069 2023-01-23 07:37:36.806736: step: 2028/1545, loss: 0.33115577697753906 2023-01-23 07:37:37.668072: step: 2030/1545, loss: 0.6457048058509827 2023-01-23 07:37:38.567631: step: 2032/1545, loss: 1.8847815990447998 2023-01-23 07:37:39.438400: step: 2034/1545, loss: 0.529695451259613 2023-01-23 07:37:40.382593: step: 2036/1545, loss: 0.3913149833679199 2023-01-23 07:37:41.326152: step: 2038/1545, loss: 0.5250703692436218 2023-01-23 07:37:42.210079: step: 2040/1545, loss: 0.48452627658843994 2023-01-23 07:37:43.088793: step: 2042/1545, loss: 0.4917075037956238 2023-01-23 07:37:43.937973: step: 2044/1545, loss: 0.812488853931427 2023-01-23 07:37:44.811963: step: 2046/1545, loss: 0.43527865409851074 2023-01-23 07:37:45.682231: step: 2048/1545, loss: 0.5064465403556824 2023-01-23 07:37:46.569753: step: 2050/1545, loss: 0.394431471824646 2023-01-23 07:37:47.432923: step: 2052/1545, loss: 0.24927228689193726 2023-01-23 07:37:48.322061: step: 2054/1545, loss: 1.1120693683624268 2023-01-23 07:37:49.168871: step: 2056/1545, loss: 0.8107728958129883 2023-01-23 07:37:50.035171: step: 2058/1545, loss: 0.7602616548538208 2023-01-23 07:37:50.911868: step: 2060/1545, loss: 0.36259597539901733 2023-01-23 07:37:51.858144: step: 2062/1545, loss: 0.9658337831497192 2023-01-23 07:37:52.834100: step: 2064/1545, loss: 1.1581753492355347 2023-01-23 07:37:53.730500: step: 2066/1545, loss: 0.7841518521308899 2023-01-23 07:37:54.575130: step: 2068/1545, loss: 0.5471829175949097 2023-01-23 07:37:55.411540: step: 2070/1545, loss: 0.4913099408149719 2023-01-23 07:37:56.255501: step: 2072/1545, loss: 0.421690970659256 2023-01-23 07:37:57.121982: step: 2074/1545, loss: 0.8089261054992676 2023-01-23 07:37:58.010977: step: 2076/1545, loss: 1.4340449571609497 2023-01-23 07:37:58.917182: step: 2078/1545, loss: 0.5569272637367249 2023-01-23 07:37:59.753517: step: 2080/1545, loss: 0.38099405169487 2023-01-23 07:38:00.636492: step: 2082/1545, loss: 0.3892800211906433 2023-01-23 07:38:01.555926: step: 2084/1545, loss: 0.8895976543426514 2023-01-23 07:38:02.433685: step: 2086/1545, loss: 0.7075809240341187 2023-01-23 07:38:03.299060: step: 2088/1545, loss: 0.31851616501808167 2023-01-23 07:38:04.195532: step: 2090/1545, loss: 0.44275718927383423 2023-01-23 07:38:05.086397: step: 2092/1545, loss: 1.7468137741088867 2023-01-23 07:38:05.934370: step: 2094/1545, loss: 0.7450019717216492 2023-01-23 07:38:06.854081: step: 2096/1545, loss: 0.35604190826416016 2023-01-23 07:38:07.728793: step: 2098/1545, loss: 0.49510931968688965 2023-01-23 07:38:08.637526: step: 2100/1545, loss: 0.705402135848999 2023-01-23 07:38:09.499638: step: 2102/1545, loss: 0.7448916435241699 2023-01-23 07:38:10.391043: step: 2104/1545, loss: 0.7028387784957886 2023-01-23 07:38:11.291995: step: 2106/1545, loss: 0.5209231972694397 2023-01-23 07:38:12.188598: step: 2108/1545, loss: 0.8116728067398071 2023-01-23 07:38:13.063306: step: 2110/1545, loss: 0.7450947761535645 2023-01-23 07:38:13.917605: step: 2112/1545, loss: 0.47051310539245605 2023-01-23 07:38:14.773059: step: 2114/1545, loss: 0.31007710099220276 2023-01-23 07:38:15.645569: step: 2116/1545, loss: 0.26644474267959595 2023-01-23 07:38:16.562068: step: 2118/1545, loss: 0.783234179019928 2023-01-23 07:38:17.431158: step: 2120/1545, loss: 0.25929611921310425 2023-01-23 07:38:18.320227: step: 2122/1545, loss: 0.5167330503463745 2023-01-23 07:38:19.168204: step: 2124/1545, loss: 0.2844926118850708 2023-01-23 07:38:20.130582: step: 2126/1545, loss: 0.7168096303939819 2023-01-23 07:38:21.042592: step: 2128/1545, loss: 0.3199750781059265 2023-01-23 07:38:21.913839: step: 2130/1545, loss: 1.0647906064987183 2023-01-23 07:38:22.776112: step: 2132/1545, loss: 0.18190453946590424 2023-01-23 07:38:23.643399: step: 2134/1545, loss: 0.1626969277858734 2023-01-23 07:38:24.564032: step: 2136/1545, loss: 0.33875611424446106 2023-01-23 07:38:25.440736: step: 2138/1545, loss: 0.7141597270965576 2023-01-23 07:38:26.280890: step: 2140/1545, loss: 0.12602075934410095 2023-01-23 07:38:27.194018: step: 2142/1545, loss: 3.0675601959228516 2023-01-23 07:38:28.071487: step: 2144/1545, loss: 0.2576792538166046 2023-01-23 07:38:28.978134: step: 2146/1545, loss: 0.4096306264400482 2023-01-23 07:38:29.853679: step: 2148/1545, loss: 0.5087984204292297 2023-01-23 07:38:30.736699: step: 2150/1545, loss: 0.9384908080101013 2023-01-23 07:38:31.590013: step: 2152/1545, loss: 0.3014499843120575 2023-01-23 07:38:32.468380: step: 2154/1545, loss: 0.4613129198551178 2023-01-23 07:38:33.340631: step: 2156/1545, loss: 0.4497763216495514 2023-01-23 07:38:34.337928: step: 2158/1545, loss: 0.7916123270988464 2023-01-23 07:38:35.175627: step: 2160/1545, loss: 0.1732373982667923 2023-01-23 07:38:36.022161: step: 2162/1545, loss: 0.24310477077960968 2023-01-23 07:38:36.917187: step: 2164/1545, loss: 0.1925722062587738 2023-01-23 07:38:37.797093: step: 2166/1545, loss: 0.5673576593399048 2023-01-23 07:38:38.673049: step: 2168/1545, loss: 0.40240442752838135 2023-01-23 07:38:39.535357: step: 2170/1545, loss: 0.6928342580795288 2023-01-23 07:38:40.511169: step: 2172/1545, loss: 0.5118777751922607 2023-01-23 07:38:41.424138: step: 2174/1545, loss: 0.595469057559967 2023-01-23 07:38:42.279374: step: 2176/1545, loss: 0.12856613099575043 2023-01-23 07:38:43.190020: step: 2178/1545, loss: 0.5010190606117249 2023-01-23 07:38:44.082993: step: 2180/1545, loss: 3.5714058876037598 2023-01-23 07:38:44.913022: step: 2182/1545, loss: 0.40748557448387146 2023-01-23 07:38:45.826174: step: 2184/1545, loss: 0.6992641687393188 2023-01-23 07:38:46.705758: step: 2186/1545, loss: 1.1867649555206299 2023-01-23 07:38:47.569071: step: 2188/1545, loss: 0.7823182344436646 2023-01-23 07:38:48.424615: step: 2190/1545, loss: 0.2947860658168793 2023-01-23 07:38:49.356256: step: 2192/1545, loss: 0.9495705366134644 2023-01-23 07:38:50.228792: step: 2194/1545, loss: 1.1334890127182007 2023-01-23 07:38:51.070118: step: 2196/1545, loss: 0.5698174834251404 2023-01-23 07:38:51.952693: step: 2198/1545, loss: 0.46415749192237854 2023-01-23 07:38:52.840419: step: 2200/1545, loss: 1.1453858613967896 2023-01-23 07:38:53.698373: step: 2202/1545, loss: 0.9557284712791443 2023-01-23 07:38:54.581723: step: 2204/1545, loss: 0.41646045446395874 2023-01-23 07:38:55.458062: step: 2206/1545, loss: 0.5012049674987793 2023-01-23 07:38:56.357133: step: 2208/1545, loss: 0.5053617358207703 2023-01-23 07:38:57.233694: step: 2210/1545, loss: 0.35335421562194824 2023-01-23 07:38:58.113291: step: 2212/1545, loss: 0.4452192783355713 2023-01-23 07:38:58.974031: step: 2214/1545, loss: 0.3194883167743683 2023-01-23 07:38:59.894124: step: 2216/1545, loss: 0.8615350127220154 2023-01-23 07:39:00.771499: step: 2218/1545, loss: 0.6176438927650452 2023-01-23 07:39:01.645499: step: 2220/1545, loss: 0.35952720046043396 2023-01-23 07:39:02.511359: step: 2222/1545, loss: 0.19318047165870667 2023-01-23 07:39:03.372618: step: 2224/1545, loss: 0.7709653377532959 2023-01-23 07:39:04.209107: step: 2226/1545, loss: 0.293148934841156 2023-01-23 07:39:05.073733: step: 2228/1545, loss: 0.4467710554599762 2023-01-23 07:39:05.954454: step: 2230/1545, loss: 0.14870397746562958 2023-01-23 07:39:06.839420: step: 2232/1545, loss: 1.1768977642059326 2023-01-23 07:39:07.696227: step: 2234/1545, loss: 0.9803098440170288 2023-01-23 07:39:08.549982: step: 2236/1545, loss: 0.6988773941993713 2023-01-23 07:39:09.405266: step: 2238/1545, loss: 0.43524521589279175 2023-01-23 07:39:10.252116: step: 2240/1545, loss: 0.19058121740818024 2023-01-23 07:39:11.166484: step: 2242/1545, loss: 2.990375518798828 2023-01-23 07:39:12.046056: step: 2244/1545, loss: 0.2981732189655304 2023-01-23 07:39:12.942621: step: 2246/1545, loss: 0.44637730717658997 2023-01-23 07:39:13.856658: step: 2248/1545, loss: 0.3337201774120331 2023-01-23 07:39:14.717713: step: 2250/1545, loss: 0.17084169387817383 2023-01-23 07:39:15.591431: step: 2252/1545, loss: 0.6508634686470032 2023-01-23 07:39:16.439162: step: 2254/1545, loss: 0.4902605414390564 2023-01-23 07:39:17.286934: step: 2256/1545, loss: 0.3910190761089325 2023-01-23 07:39:18.159616: step: 2258/1545, loss: 0.19817592203617096 2023-01-23 07:39:19.030592: step: 2260/1545, loss: 0.5947831869125366 2023-01-23 07:39:19.922062: step: 2262/1545, loss: 0.8529403805732727 2023-01-23 07:39:20.781136: step: 2264/1545, loss: 0.7085956335067749 2023-01-23 07:39:21.640876: step: 2266/1545, loss: 1.6619521379470825 2023-01-23 07:39:22.519685: step: 2268/1545, loss: 0.7557869553565979 2023-01-23 07:39:23.391476: step: 2270/1545, loss: 0.7499747276306152 2023-01-23 07:39:24.220206: step: 2272/1545, loss: 0.5672037601470947 2023-01-23 07:39:25.061591: step: 2274/1545, loss: 0.5325821042060852 2023-01-23 07:39:25.937618: step: 2276/1545, loss: 0.32038623094558716 2023-01-23 07:39:26.832713: step: 2278/1545, loss: 0.6833617091178894 2023-01-23 07:39:27.725457: step: 2280/1545, loss: 0.7452988624572754 2023-01-23 07:39:28.597466: step: 2282/1545, loss: 0.36132657527923584 2023-01-23 07:39:29.489645: step: 2284/1545, loss: 0.2039213478565216 2023-01-23 07:39:30.335815: step: 2286/1545, loss: 0.2009456306695938 2023-01-23 07:39:31.220289: step: 2288/1545, loss: 0.9486904144287109 2023-01-23 07:39:32.099398: step: 2290/1545, loss: 0.36451783776283264 2023-01-23 07:39:33.019676: step: 2292/1545, loss: 0.7466373443603516 2023-01-23 07:39:33.930971: step: 2294/1545, loss: 0.5386289954185486 2023-01-23 07:39:34.887826: step: 2296/1545, loss: 0.640052080154419 2023-01-23 07:39:35.771958: step: 2298/1545, loss: 0.17384932935237885 2023-01-23 07:39:36.644477: step: 2300/1545, loss: 0.23785680532455444 2023-01-23 07:39:37.643339: step: 2302/1545, loss: 0.28962501883506775 2023-01-23 07:39:38.551382: step: 2304/1545, loss: 0.506283700466156 2023-01-23 07:39:39.423438: step: 2306/1545, loss: 0.2411055862903595 2023-01-23 07:39:40.335181: step: 2308/1545, loss: 0.7406638860702515 2023-01-23 07:39:41.216421: step: 2310/1545, loss: 0.9675042033195496 2023-01-23 07:39:42.121554: step: 2312/1545, loss: 1.327872395515442 2023-01-23 07:39:43.023597: step: 2314/1545, loss: 0.44275057315826416 2023-01-23 07:39:44.048852: step: 2316/1545, loss: 0.8322468996047974 2023-01-23 07:39:44.957672: step: 2318/1545, loss: 0.6603029370307922 2023-01-23 07:39:45.836016: step: 2320/1545, loss: 0.45970627665519714 2023-01-23 07:39:46.738987: step: 2322/1545, loss: 1.357954740524292 2023-01-23 07:39:47.664570: step: 2324/1545, loss: 0.5877213478088379 2023-01-23 07:39:48.542214: step: 2326/1545, loss: 0.9175800681114197 2023-01-23 07:39:49.413809: step: 2328/1545, loss: 0.4004208743572235 2023-01-23 07:39:50.290635: step: 2330/1545, loss: 0.6058845520019531 2023-01-23 07:39:51.193721: step: 2332/1545, loss: 0.30940699577331543 2023-01-23 07:39:52.108486: step: 2334/1545, loss: 0.9645555019378662 2023-01-23 07:39:52.985927: step: 2336/1545, loss: 0.4960689842700958 2023-01-23 07:39:53.884851: step: 2338/1545, loss: 0.3964989185333252 2023-01-23 07:39:54.804528: step: 2340/1545, loss: 0.10021829605102539 2023-01-23 07:39:55.687119: step: 2342/1545, loss: 0.5930830836296082 2023-01-23 07:39:56.580815: step: 2344/1545, loss: 1.0593249797821045 2023-01-23 07:39:57.489862: step: 2346/1545, loss: 0.34358054399490356 2023-01-23 07:39:58.379403: step: 2348/1545, loss: 0.259447306394577 2023-01-23 07:39:59.220613: step: 2350/1545, loss: 0.8445950746536255 2023-01-23 07:40:00.099084: step: 2352/1545, loss: 0.2794569134712219 2023-01-23 07:40:01.003759: step: 2354/1545, loss: 0.24446427822113037 2023-01-23 07:40:01.887052: step: 2356/1545, loss: 0.9380451440811157 2023-01-23 07:40:02.805326: step: 2358/1545, loss: 0.38350796699523926 2023-01-23 07:40:03.684112: step: 2360/1545, loss: 0.38053494691848755 2023-01-23 07:40:04.552334: step: 2362/1545, loss: 0.2563379406929016 2023-01-23 07:40:05.443504: step: 2364/1545, loss: 0.642327606678009 2023-01-23 07:40:06.299145: step: 2366/1545, loss: 0.9094073176383972 2023-01-23 07:40:07.160400: step: 2368/1545, loss: 0.4503467082977295 2023-01-23 07:40:08.035959: step: 2370/1545, loss: 0.6866271495819092 2023-01-23 07:40:08.964624: step: 2372/1545, loss: 0.9102525115013123 2023-01-23 07:40:09.810888: step: 2374/1545, loss: 1.4990774393081665 2023-01-23 07:40:10.706317: step: 2376/1545, loss: 0.20716246962547302 2023-01-23 07:40:11.570887: step: 2378/1545, loss: 0.39907270669937134 2023-01-23 07:40:12.432212: step: 2380/1545, loss: 0.4284711480140686 2023-01-23 07:40:13.322834: step: 2382/1545, loss: 0.45071637630462646 2023-01-23 07:40:14.202586: step: 2384/1545, loss: 0.5858060717582703 2023-01-23 07:40:15.067500: step: 2386/1545, loss: 0.9053834676742554 2023-01-23 07:40:15.980599: step: 2388/1545, loss: 0.4028615653514862 2023-01-23 07:40:16.852701: step: 2390/1545, loss: 0.5931637287139893 2023-01-23 07:40:17.811325: step: 2392/1545, loss: 0.730903685092926 2023-01-23 07:40:18.740195: step: 2394/1545, loss: 0.36234796047210693 2023-01-23 07:40:19.683499: step: 2396/1545, loss: 0.6244697570800781 2023-01-23 07:40:20.602312: step: 2398/1545, loss: 1.0261701345443726 2023-01-23 07:40:21.523470: step: 2400/1545, loss: 1.5926814079284668 2023-01-23 07:40:22.405362: step: 2402/1545, loss: 0.42020612955093384 2023-01-23 07:40:23.266902: step: 2404/1545, loss: 2.2248849868774414 2023-01-23 07:40:24.158727: step: 2406/1545, loss: 0.4928428530693054 2023-01-23 07:40:25.052285: step: 2408/1545, loss: 0.5747723579406738 2023-01-23 07:40:25.941377: step: 2410/1545, loss: 0.3945370316505432 2023-01-23 07:40:26.833731: step: 2412/1545, loss: 0.8284485936164856 2023-01-23 07:40:27.683488: step: 2414/1545, loss: 2.5955166816711426 2023-01-23 07:40:28.575689: step: 2416/1545, loss: 0.7593674659729004 2023-01-23 07:40:29.418900: step: 2418/1545, loss: 0.5087367296218872 2023-01-23 07:40:30.297543: step: 2420/1545, loss: 0.24219873547554016 2023-01-23 07:40:31.181177: step: 2422/1545, loss: 0.5698055624961853 2023-01-23 07:40:32.100835: step: 2424/1545, loss: 0.865071713924408 2023-01-23 07:40:32.961167: step: 2426/1545, loss: 0.2977500855922699 2023-01-23 07:40:33.855130: step: 2428/1545, loss: 0.40027034282684326 2023-01-23 07:40:34.760430: step: 2430/1545, loss: 0.1285242736339569 2023-01-23 07:40:35.652770: step: 2432/1545, loss: 0.45182982087135315 2023-01-23 07:40:36.511250: step: 2434/1545, loss: 0.7431174516677856 2023-01-23 07:40:37.372458: step: 2436/1545, loss: 0.2176540195941925 2023-01-23 07:40:38.281102: step: 2438/1545, loss: 0.9974832534790039 2023-01-23 07:40:39.193245: step: 2440/1545, loss: 1.0065960884094238 2023-01-23 07:40:40.037210: step: 2442/1545, loss: 0.3539775609970093 2023-01-23 07:40:40.921624: step: 2444/1545, loss: 0.4914550185203552 2023-01-23 07:40:41.899790: step: 2446/1545, loss: 0.6646360754966736 2023-01-23 07:40:42.812369: step: 2448/1545, loss: 0.20083361864089966 2023-01-23 07:40:43.686085: step: 2450/1545, loss: 0.921460747718811 2023-01-23 07:40:44.540843: step: 2452/1545, loss: 0.5715033411979675 2023-01-23 07:40:45.463129: step: 2454/1545, loss: 0.5377703905105591 2023-01-23 07:40:46.312326: step: 2456/1545, loss: 0.6439918279647827 2023-01-23 07:40:47.155402: step: 2458/1545, loss: 1.1200721263885498 2023-01-23 07:40:48.064647: step: 2460/1545, loss: 0.9148993492126465 2023-01-23 07:40:48.947726: step: 2462/1545, loss: 0.6146767735481262 2023-01-23 07:40:49.845727: step: 2464/1545, loss: 0.47971034049987793 2023-01-23 07:40:50.701088: step: 2466/1545, loss: 0.2534962594509125 2023-01-23 07:40:51.574996: step: 2468/1545, loss: 0.17878583073616028 2023-01-23 07:40:52.410265: step: 2470/1545, loss: 0.8565443754196167 2023-01-23 07:40:53.289602: step: 2472/1545, loss: 0.5010622143745422 2023-01-23 07:40:54.176542: step: 2474/1545, loss: 0.48584452271461487 2023-01-23 07:40:55.062585: step: 2476/1545, loss: 0.7828781604766846 2023-01-23 07:40:55.945431: step: 2478/1545, loss: 0.6867905855178833 2023-01-23 07:40:56.812450: step: 2480/1545, loss: 0.8862643837928772 2023-01-23 07:40:57.696841: step: 2482/1545, loss: 0.809906542301178 2023-01-23 07:40:58.572267: step: 2484/1545, loss: 0.4107757806777954 2023-01-23 07:40:59.467071: step: 2486/1545, loss: 0.8347183465957642 2023-01-23 07:41:00.329170: step: 2488/1545, loss: 0.7118911743164062 2023-01-23 07:41:01.190341: step: 2490/1545, loss: 0.322306364774704 2023-01-23 07:41:02.109792: step: 2492/1545, loss: 0.3071942925453186 2023-01-23 07:41:03.019230: step: 2494/1545, loss: 0.3845570981502533 2023-01-23 07:41:03.944989: step: 2496/1545, loss: 0.46044784784317017 2023-01-23 07:41:04.797289: step: 2498/1545, loss: 0.3551901578903198 2023-01-23 07:41:05.651331: step: 2500/1545, loss: 0.8455206751823425 2023-01-23 07:41:06.545717: step: 2502/1545, loss: 0.4807603359222412 2023-01-23 07:41:07.393078: step: 2504/1545, loss: 0.5033286213874817 2023-01-23 07:41:08.207450: step: 2506/1545, loss: 0.3682060241699219 2023-01-23 07:41:09.181378: step: 2508/1545, loss: 0.3713730275630951 2023-01-23 07:41:10.035617: step: 2510/1545, loss: 3.2135908603668213 2023-01-23 07:41:10.941815: step: 2512/1545, loss: 0.8467177152633667 2023-01-23 07:41:11.856660: step: 2514/1545, loss: 0.5695114135742188 2023-01-23 07:41:12.755786: step: 2516/1545, loss: 0.6725680828094482 2023-01-23 07:41:13.639727: step: 2518/1545, loss: 0.42948123812675476 2023-01-23 07:41:14.553470: step: 2520/1545, loss: 0.5239713191986084 2023-01-23 07:41:15.459723: step: 2522/1545, loss: 0.6193720698356628 2023-01-23 07:41:16.324750: step: 2524/1545, loss: 0.4411102533340454 2023-01-23 07:41:17.185773: step: 2526/1545, loss: 0.47948381304740906 2023-01-23 07:41:18.053901: step: 2528/1545, loss: 0.41455504298210144 2023-01-23 07:41:19.005634: step: 2530/1545, loss: 0.30571356415748596 2023-01-23 07:41:19.910766: step: 2532/1545, loss: 1.577420949935913 2023-01-23 07:41:20.792010: step: 2534/1545, loss: 0.2083926498889923 2023-01-23 07:41:21.715789: step: 2536/1545, loss: 0.3007129728794098 2023-01-23 07:41:22.598900: step: 2538/1545, loss: 0.28313082456588745 2023-01-23 07:41:23.464717: step: 2540/1545, loss: 0.21277524530887604 2023-01-23 07:41:24.381357: step: 2542/1545, loss: 0.6093752384185791 2023-01-23 07:41:25.259478: step: 2544/1545, loss: 0.5070400238037109 2023-01-23 07:41:26.150388: step: 2546/1545, loss: 1.525367021560669 2023-01-23 07:41:27.046829: step: 2548/1545, loss: 0.41775742173194885 2023-01-23 07:41:27.905910: step: 2550/1545, loss: 0.5132458806037903 2023-01-23 07:41:28.800889: step: 2552/1545, loss: 0.5642614364624023 2023-01-23 07:41:29.665104: step: 2554/1545, loss: 0.410626083612442 2023-01-23 07:41:30.530616: step: 2556/1545, loss: 0.24851754307746887 2023-01-23 07:41:31.397982: step: 2558/1545, loss: 0.36876678466796875 2023-01-23 07:41:32.288646: step: 2560/1545, loss: 0.9890487790107727 2023-01-23 07:41:33.153347: step: 2562/1545, loss: 0.323860764503479 2023-01-23 07:41:34.051400: step: 2564/1545, loss: 2.4163453578948975 2023-01-23 07:41:34.961511: step: 2566/1545, loss: 1.176523208618164 2023-01-23 07:41:35.853831: step: 2568/1545, loss: 0.20119528472423553 2023-01-23 07:41:36.724923: step: 2570/1545, loss: 0.5768796801567078 2023-01-23 07:41:37.589026: step: 2572/1545, loss: 1.446934461593628 2023-01-23 07:41:38.434094: step: 2574/1545, loss: 0.2731781601905823 2023-01-23 07:41:39.337546: step: 2576/1545, loss: 0.9028826951980591 2023-01-23 07:41:40.190102: step: 2578/1545, loss: 0.8357374668121338 2023-01-23 07:41:41.064895: step: 2580/1545, loss: 1.2429769039154053 2023-01-23 07:41:41.991123: step: 2582/1545, loss: 1.0741891860961914 2023-01-23 07:41:42.857588: step: 2584/1545, loss: 0.4705413281917572 2023-01-23 07:41:43.744478: step: 2586/1545, loss: 0.7209222316741943 2023-01-23 07:41:44.672024: step: 2588/1545, loss: 0.39986154437065125 2023-01-23 07:41:45.589790: step: 2590/1545, loss: 0.7046756148338318 2023-01-23 07:41:46.457146: step: 2592/1545, loss: 0.6043294072151184 2023-01-23 07:41:47.328142: step: 2594/1545, loss: 1.1585818529129028 2023-01-23 07:41:48.182684: step: 2596/1545, loss: 0.6454061269760132 2023-01-23 07:41:49.093452: step: 2598/1545, loss: 2.2471137046813965 2023-01-23 07:41:49.982829: step: 2600/1545, loss: 0.24034510552883148 2023-01-23 07:41:50.875269: step: 2602/1545, loss: 0.3350473940372467 2023-01-23 07:41:51.747453: step: 2604/1545, loss: 0.7272305488586426 2023-01-23 07:41:52.588461: step: 2606/1545, loss: 0.4685494899749756 2023-01-23 07:41:53.534690: step: 2608/1545, loss: 0.5803953409194946 2023-01-23 07:41:54.415024: step: 2610/1545, loss: 0.5323747992515564 2023-01-23 07:41:55.281822: step: 2612/1545, loss: 0.15747076272964478 2023-01-23 07:41:56.175016: step: 2614/1545, loss: 0.16764739155769348 2023-01-23 07:41:57.080985: step: 2616/1545, loss: 0.698137104511261 2023-01-23 07:41:57.993135: step: 2618/1545, loss: 0.6202337145805359 2023-01-23 07:41:58.894203: step: 2620/1545, loss: 0.8341272473335266 2023-01-23 07:41:59.756422: step: 2622/1545, loss: 0.272777795791626 2023-01-23 07:42:00.650974: step: 2624/1545, loss: 0.4108559191226959 2023-01-23 07:42:01.489607: step: 2626/1545, loss: 0.4748997390270233 2023-01-23 07:42:02.339580: step: 2628/1545, loss: 0.12708653509616852 2023-01-23 07:42:03.229570: step: 2630/1545, loss: 0.2371087372303009 2023-01-23 07:42:04.110583: step: 2632/1545, loss: 0.6462839245796204 2023-01-23 07:42:04.984139: step: 2634/1545, loss: 0.3507818877696991 2023-01-23 07:42:05.902902: step: 2636/1545, loss: 2.0940771102905273 2023-01-23 07:42:06.835160: step: 2638/1545, loss: 0.773552417755127 2023-01-23 07:42:07.710070: step: 2640/1545, loss: 0.7012552618980408 2023-01-23 07:42:08.578865: step: 2642/1545, loss: 0.5820091366767883 2023-01-23 07:42:09.490301: step: 2644/1545, loss: 0.9219287037849426 2023-01-23 07:42:10.331218: step: 2646/1545, loss: 0.6122065782546997 2023-01-23 07:42:11.193990: step: 2648/1545, loss: 0.5301016569137573 2023-01-23 07:42:12.110192: step: 2650/1545, loss: 0.26468774676322937 2023-01-23 07:42:13.078076: step: 2652/1545, loss: 2.8972907066345215 2023-01-23 07:42:13.969943: step: 2654/1545, loss: 0.9712168574333191 2023-01-23 07:42:14.867354: step: 2656/1545, loss: 0.37827587127685547 2023-01-23 07:42:15.792167: step: 2658/1545, loss: 0.5242220163345337 2023-01-23 07:42:16.634172: step: 2660/1545, loss: 0.3400411903858185 2023-01-23 07:42:17.497700: step: 2662/1545, loss: 0.44623038172721863 2023-01-23 07:42:18.429115: step: 2664/1545, loss: 0.43015578389167786 2023-01-23 07:42:19.336781: step: 2666/1545, loss: 0.6073823571205139 2023-01-23 07:42:20.202402: step: 2668/1545, loss: 0.5528082847595215 2023-01-23 07:42:21.063948: step: 2670/1545, loss: 0.4229380786418915 2023-01-23 07:42:21.925495: step: 2672/1545, loss: 2.2661025524139404 2023-01-23 07:42:22.800349: step: 2674/1545, loss: 1.100022315979004 2023-01-23 07:42:23.711254: step: 2676/1545, loss: 0.27335795760154724 2023-01-23 07:42:24.613016: step: 2678/1545, loss: 0.5197696089744568 2023-01-23 07:42:25.503308: step: 2680/1545, loss: 2.9797728061676025 2023-01-23 07:42:26.374219: step: 2682/1545, loss: 0.37746068835258484 2023-01-23 07:42:27.293912: step: 2684/1545, loss: 1.0706621408462524 2023-01-23 07:42:28.150172: step: 2686/1545, loss: 0.3742217421531677 2023-01-23 07:42:29.001088: step: 2688/1545, loss: 0.20044761896133423 2023-01-23 07:42:29.854360: step: 2690/1545, loss: 0.3486967384815216 2023-01-23 07:42:30.747108: step: 2692/1545, loss: 0.47897064685821533 2023-01-23 07:42:31.647310: step: 2694/1545, loss: 0.22390365600585938 2023-01-23 07:42:32.570058: step: 2696/1545, loss: 0.44853049516677856 2023-01-23 07:42:33.432108: step: 2698/1545, loss: 0.6373702883720398 2023-01-23 07:42:34.344820: step: 2700/1545, loss: 0.6973922848701477 2023-01-23 07:42:35.241458: step: 2702/1545, loss: 0.5074951648712158 2023-01-23 07:42:36.134238: step: 2704/1545, loss: 0.5114434957504272 2023-01-23 07:42:37.107491: step: 2706/1545, loss: 0.6928076148033142 2023-01-23 07:42:38.065431: step: 2708/1545, loss: 0.4833209216594696 2023-01-23 07:42:38.953278: step: 2710/1545, loss: 0.5955733060836792 2023-01-23 07:42:39.829367: step: 2712/1545, loss: 0.5750623345375061 2023-01-23 07:42:40.708215: step: 2714/1545, loss: 0.5418244004249573 2023-01-23 07:42:41.617542: step: 2716/1545, loss: 0.4006415009498596 2023-01-23 07:42:42.485903: step: 2718/1545, loss: 0.40362533926963806 2023-01-23 07:42:43.366042: step: 2720/1545, loss: 0.48785752058029175 2023-01-23 07:42:44.214428: step: 2722/1545, loss: 0.2011132538318634 2023-01-23 07:42:45.092658: step: 2724/1545, loss: 0.2701306641101837 2023-01-23 07:42:45.989820: step: 2726/1545, loss: 0.9871010780334473 2023-01-23 07:42:46.871611: step: 2728/1545, loss: 0.6273821592330933 2023-01-23 07:42:47.733773: step: 2730/1545, loss: 0.5646161437034607 2023-01-23 07:42:48.676539: step: 2732/1545, loss: 0.28912353515625 2023-01-23 07:42:49.540939: step: 2734/1545, loss: 0.44987374544143677 2023-01-23 07:42:50.403030: step: 2736/1545, loss: 0.8768922090530396 2023-01-23 07:42:51.294247: step: 2738/1545, loss: 0.4202587902545929 2023-01-23 07:42:52.136606: step: 2740/1545, loss: 0.1749061942100525 2023-01-23 07:42:53.034859: step: 2742/1545, loss: 0.4998385012149811 2023-01-23 07:42:54.015678: step: 2744/1545, loss: 0.6375656723976135 2023-01-23 07:42:54.936705: step: 2746/1545, loss: 0.8272649049758911 2023-01-23 07:42:55.864688: step: 2748/1545, loss: 0.952298104763031 2023-01-23 07:42:56.772582: step: 2750/1545, loss: 0.7011255025863647 2023-01-23 07:42:57.633505: step: 2752/1545, loss: 0.9494163990020752 2023-01-23 07:42:58.471429: step: 2754/1545, loss: 0.29283520579338074 2023-01-23 07:42:59.349959: step: 2756/1545, loss: 0.33223962783813477 2023-01-23 07:43:00.246596: step: 2758/1545, loss: 0.7752867341041565 2023-01-23 07:43:01.158623: step: 2760/1545, loss: 0.13441182672977448 2023-01-23 07:43:02.007842: step: 2762/1545, loss: 0.7590081691741943 2023-01-23 07:43:02.915313: step: 2764/1545, loss: 1.8520885705947876 2023-01-23 07:43:03.799504: step: 2766/1545, loss: 0.20331498980522156 2023-01-23 07:43:04.674966: step: 2768/1545, loss: 0.435956746339798 2023-01-23 07:43:05.557090: step: 2770/1545, loss: 0.5658666491508484 2023-01-23 07:43:06.479030: step: 2772/1545, loss: 1.1522536277770996 2023-01-23 07:43:07.329925: step: 2774/1545, loss: 0.5413987636566162 2023-01-23 07:43:08.194849: step: 2776/1545, loss: 0.4760115146636963 2023-01-23 07:43:09.059954: step: 2778/1545, loss: 0.4225914180278778 2023-01-23 07:43:09.919577: step: 2780/1545, loss: 0.9209985733032227 2023-01-23 07:43:10.816596: step: 2782/1545, loss: 0.7356386184692383 2023-01-23 07:43:11.687511: step: 2784/1545, loss: 0.30481669306755066 2023-01-23 07:43:12.586557: step: 2786/1545, loss: 0.17238084971904755 2023-01-23 07:43:13.559530: step: 2788/1545, loss: 0.3583184778690338 2023-01-23 07:43:14.461402: step: 2790/1545, loss: 0.19357995688915253 2023-01-23 07:43:15.314649: step: 2792/1545, loss: 0.6631024479866028 2023-01-23 07:43:16.231116: step: 2794/1545, loss: 0.2353978306055069 2023-01-23 07:43:17.137448: step: 2796/1545, loss: 0.4252280592918396 2023-01-23 07:43:18.105777: step: 2798/1545, loss: 2.6002533435821533 2023-01-23 07:43:19.035567: step: 2800/1545, loss: 0.3422248065471649 2023-01-23 07:43:19.935398: step: 2802/1545, loss: 0.8351191282272339 2023-01-23 07:43:20.876830: step: 2804/1545, loss: 0.34240859746932983 2023-01-23 07:43:21.782268: step: 2806/1545, loss: 0.21781088411808014 2023-01-23 07:43:22.798536: step: 2808/1545, loss: 0.2608690559864044 2023-01-23 07:43:23.663464: step: 2810/1545, loss: 2.226848602294922 2023-01-23 07:43:24.544830: step: 2812/1545, loss: 1.1642736196517944 2023-01-23 07:43:25.401576: step: 2814/1545, loss: 1.079169511795044 2023-01-23 07:43:26.274239: step: 2816/1545, loss: 0.4365918040275574 2023-01-23 07:43:27.162777: step: 2818/1545, loss: 0.4578666388988495 2023-01-23 07:43:28.092298: step: 2820/1545, loss: 0.7078759670257568 2023-01-23 07:43:29.019236: step: 2822/1545, loss: 0.5200361609458923 2023-01-23 07:43:29.896835: step: 2824/1545, loss: 0.6140855550765991 2023-01-23 07:43:30.802933: step: 2826/1545, loss: 0.5073709487915039 2023-01-23 07:43:31.675102: step: 2828/1545, loss: 0.4267066419124603 2023-01-23 07:43:32.584680: step: 2830/1545, loss: 0.7208720445632935 2023-01-23 07:43:33.488145: step: 2832/1545, loss: 0.19120562076568604 2023-01-23 07:43:34.403078: step: 2834/1545, loss: 0.7166843414306641 2023-01-23 07:43:35.300289: step: 2836/1545, loss: 0.5608412623405457 2023-01-23 07:43:36.211627: step: 2838/1545, loss: 0.34508591890335083 2023-01-23 07:43:37.097201: step: 2840/1545, loss: 0.5687950849533081 2023-01-23 07:43:37.959498: step: 2842/1545, loss: 0.8978386521339417 2023-01-23 07:43:38.858151: step: 2844/1545, loss: 0.3833874464035034 2023-01-23 07:43:39.745021: step: 2846/1545, loss: 0.6940616369247437 2023-01-23 07:43:40.626904: step: 2848/1545, loss: 0.5042193531990051 2023-01-23 07:43:41.526882: step: 2850/1545, loss: 0.4319455623626709 2023-01-23 07:43:42.434261: step: 2852/1545, loss: 0.2547816336154938 2023-01-23 07:43:43.365497: step: 2854/1545, loss: 2.0775821208953857 2023-01-23 07:43:44.237212: step: 2856/1545, loss: 0.6166068911552429 2023-01-23 07:43:45.149447: step: 2858/1545, loss: 3.013789415359497 2023-01-23 07:43:46.004698: step: 2860/1545, loss: 0.7848672866821289 2023-01-23 07:43:46.942529: step: 2862/1545, loss: 0.17432916164398193 2023-01-23 07:43:47.827814: step: 2864/1545, loss: 0.9856634140014648 2023-01-23 07:43:48.703162: step: 2866/1545, loss: 0.5764420628547668 2023-01-23 07:43:49.632317: step: 2868/1545, loss: 0.7132235765457153 2023-01-23 07:43:50.489464: step: 2870/1545, loss: 0.6401544213294983 2023-01-23 07:43:51.390532: step: 2872/1545, loss: 0.6274430155754089 2023-01-23 07:43:52.340211: step: 2874/1545, loss: 0.5285770893096924 2023-01-23 07:43:53.197304: step: 2876/1545, loss: 1.6834697723388672 2023-01-23 07:43:54.091023: step: 2878/1545, loss: 0.3775327801704407 2023-01-23 07:43:55.031761: step: 2880/1545, loss: 0.7185589671134949 2023-01-23 07:43:55.930620: step: 2882/1545, loss: 0.40533411502838135 2023-01-23 07:43:56.831443: step: 2884/1545, loss: 1.4607222080230713 2023-01-23 07:43:57.699296: step: 2886/1545, loss: 0.47882145643234253 2023-01-23 07:43:58.596336: step: 2888/1545, loss: 0.3910500705242157 2023-01-23 07:43:59.548176: step: 2890/1545, loss: 0.47730332612991333 2023-01-23 07:44:00.424567: step: 2892/1545, loss: 2.522498369216919 2023-01-23 07:44:01.299409: step: 2894/1545, loss: 0.47959673404693604 2023-01-23 07:44:02.179364: step: 2896/1545, loss: 0.3730939030647278 2023-01-23 07:44:03.078517: step: 2898/1545, loss: 0.5477051138877869 2023-01-23 07:44:03.994441: step: 2900/1545, loss: 0.33283042907714844 2023-01-23 07:44:04.847115: step: 2902/1545, loss: 0.523898720741272 2023-01-23 07:44:05.739652: step: 2904/1545, loss: 2.1437511444091797 2023-01-23 07:44:06.656833: step: 2906/1545, loss: 0.47126132249832153 2023-01-23 07:44:07.529445: step: 2908/1545, loss: 0.5547157526016235 2023-01-23 07:44:08.447680: step: 2910/1545, loss: 0.23721785843372345 2023-01-23 07:44:09.337867: step: 2912/1545, loss: 0.6741501092910767 2023-01-23 07:44:10.230592: step: 2914/1545, loss: 1.5273319482803345 2023-01-23 07:44:11.070274: step: 2916/1545, loss: 0.366122305393219 2023-01-23 07:44:11.985120: step: 2918/1545, loss: 0.2297305464744568 2023-01-23 07:44:12.868332: step: 2920/1545, loss: 0.21246746182441711 2023-01-23 07:44:13.739545: step: 2922/1545, loss: 0.5335383415222168 2023-01-23 07:44:14.638807: step: 2924/1545, loss: 0.5647444725036621 2023-01-23 07:44:15.559658: step: 2926/1545, loss: 0.48099449276924133 2023-01-23 07:44:16.401455: step: 2928/1545, loss: 0.38608333468437195 2023-01-23 07:44:17.237746: step: 2930/1545, loss: 3.2703566551208496 2023-01-23 07:44:18.099228: step: 2932/1545, loss: 2.9096946716308594 2023-01-23 07:44:19.033103: step: 2934/1545, loss: 1.270353078842163 2023-01-23 07:44:20.011565: step: 2936/1545, loss: 0.7491454482078552 2023-01-23 07:44:20.909911: step: 2938/1545, loss: 0.4011918902397156 2023-01-23 07:44:21.875753: step: 2940/1545, loss: 0.4788656532764435 2023-01-23 07:44:22.761573: step: 2942/1545, loss: 0.6133207082748413 2023-01-23 07:44:23.664386: step: 2944/1545, loss: 0.44290265440940857 2023-01-23 07:44:24.611451: step: 2946/1545, loss: 0.32694512605667114 2023-01-23 07:44:25.497816: step: 2948/1545, loss: 0.684008777141571 2023-01-23 07:44:26.366604: step: 2950/1545, loss: 0.43980956077575684 2023-01-23 07:44:27.256719: step: 2952/1545, loss: 0.5835226774215698 2023-01-23 07:44:28.141831: step: 2954/1545, loss: 0.33338165283203125 2023-01-23 07:44:29.135606: step: 2956/1545, loss: 1.0298086404800415 2023-01-23 07:44:30.041304: step: 2958/1545, loss: 3.520881414413452 2023-01-23 07:44:30.891077: step: 2960/1545, loss: 0.3409305214881897 2023-01-23 07:44:31.780699: step: 2962/1545, loss: 0.7989415526390076 2023-01-23 07:44:32.689142: step: 2964/1545, loss: 0.3365379273891449 2023-01-23 07:44:33.533572: step: 2966/1545, loss: 0.27995631098747253 2023-01-23 07:44:34.435806: step: 2968/1545, loss: 0.911385715007782 2023-01-23 07:44:35.290902: step: 2970/1545, loss: 0.5109126567840576 2023-01-23 07:44:36.127106: step: 2972/1545, loss: 0.1910167932510376 2023-01-23 07:44:37.125093: step: 2974/1545, loss: 1.069859504699707 2023-01-23 07:44:38.046347: step: 2976/1545, loss: 0.6277813911437988 2023-01-23 07:44:38.923107: step: 2978/1545, loss: 0.8538720011711121 2023-01-23 07:44:39.795316: step: 2980/1545, loss: 0.4601183831691742 2023-01-23 07:44:40.664842: step: 2982/1545, loss: 1.115135669708252 2023-01-23 07:44:41.554832: step: 2984/1545, loss: 0.17614582180976868 2023-01-23 07:44:42.475074: step: 2986/1545, loss: 0.5467448830604553 2023-01-23 07:44:43.391727: step: 2988/1545, loss: 0.4421853721141815 2023-01-23 07:44:44.287526: step: 2990/1545, loss: 2.1505701541900635 2023-01-23 07:44:45.191867: step: 2992/1545, loss: 0.34375837445259094 2023-01-23 07:44:46.110709: step: 2994/1545, loss: 2.1384809017181396 2023-01-23 07:44:46.960503: step: 2996/1545, loss: 0.6783618927001953 2023-01-23 07:44:47.812012: step: 2998/1545, loss: 0.710269570350647 2023-01-23 07:44:48.717036: step: 3000/1545, loss: 0.3558613359928131 2023-01-23 07:44:49.679606: step: 3002/1545, loss: 3.1661250591278076 2023-01-23 07:44:50.627708: step: 3004/1545, loss: 0.6093809604644775 2023-01-23 07:44:51.543192: step: 3006/1545, loss: 0.38330087065696716 2023-01-23 07:44:52.546322: step: 3008/1545, loss: 1.0209215879440308 2023-01-23 07:44:53.510417: step: 3010/1545, loss: 1.2203038930892944 2023-01-23 07:44:54.349887: step: 3012/1545, loss: 5.2964911460876465 2023-01-23 07:44:55.268054: step: 3014/1545, loss: 0.8291586637496948 2023-01-23 07:44:56.243378: step: 3016/1545, loss: 0.6339734196662903 2023-01-23 07:44:57.109646: step: 3018/1545, loss: 0.5532954931259155 2023-01-23 07:44:57.987560: step: 3020/1545, loss: 0.872288703918457 2023-01-23 07:44:58.854192: step: 3022/1545, loss: 0.3762250244617462 2023-01-23 07:44:59.738001: step: 3024/1545, loss: 4.584064960479736 2023-01-23 07:45:00.654034: step: 3026/1545, loss: 0.1452779918909073 2023-01-23 07:45:01.533543: step: 3028/1545, loss: 0.44144412875175476 2023-01-23 07:45:02.413875: step: 3030/1545, loss: 0.5743011832237244 2023-01-23 07:45:03.337518: step: 3032/1545, loss: 1.2038859128952026 2023-01-23 07:45:04.246084: step: 3034/1545, loss: 0.6193630695343018 2023-01-23 07:45:05.148758: step: 3036/1545, loss: 0.556462287902832 2023-01-23 07:45:06.031731: step: 3038/1545, loss: 0.2905272841453552 2023-01-23 07:45:06.904232: step: 3040/1545, loss: 0.5380570292472839 2023-01-23 07:45:07.780361: step: 3042/1545, loss: 0.400649756193161 2023-01-23 07:45:08.685259: step: 3044/1545, loss: 0.614631712436676 2023-01-23 07:45:09.605010: step: 3046/1545, loss: 0.3864578902721405 2023-01-23 07:45:10.493749: step: 3048/1545, loss: 0.8180779218673706 2023-01-23 07:45:11.382705: step: 3050/1545, loss: 0.6618485450744629 2023-01-23 07:45:12.277864: step: 3052/1545, loss: 1.410089135169983 2023-01-23 07:45:13.163962: step: 3054/1545, loss: 0.30688515305519104 2023-01-23 07:45:14.057923: step: 3056/1545, loss: 1.018798828125 2023-01-23 07:45:14.922086: step: 3058/1545, loss: 0.3483065664768219 2023-01-23 07:45:15.825241: step: 3060/1545, loss: 0.8263020515441895 2023-01-23 07:45:16.692431: step: 3062/1545, loss: 0.4585091471672058 2023-01-23 07:45:17.635652: step: 3064/1545, loss: 0.9957217574119568 2023-01-23 07:45:18.524884: step: 3066/1545, loss: 0.5536385774612427 2023-01-23 07:45:19.462428: step: 3068/1545, loss: 0.5182892680168152 2023-01-23 07:45:20.332973: step: 3070/1545, loss: 0.5009862184524536 2023-01-23 07:45:21.173048: step: 3072/1545, loss: 0.35029277205467224 2023-01-23 07:45:22.066349: step: 3074/1545, loss: 0.8685345649719238 2023-01-23 07:45:22.975280: step: 3076/1545, loss: 0.40568509697914124 2023-01-23 07:45:23.834301: step: 3078/1545, loss: 0.51116544008255 2023-01-23 07:45:24.741919: step: 3080/1545, loss: 0.561583936214447 2023-01-23 07:45:25.651042: step: 3082/1545, loss: 2.270995855331421 2023-01-23 07:45:26.576363: step: 3084/1545, loss: 0.23392121493816376 2023-01-23 07:45:27.491578: step: 3086/1545, loss: 0.27087223529815674 2023-01-23 07:45:28.346529: step: 3088/1545, loss: 4.839550971984863 2023-01-23 07:45:29.232255: step: 3090/1545, loss: 1.6920313835144043 ================================================== Loss: 0.716 -------------------- Dev Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6964114198955085, 'r': 0.6234341752956798, 'f1': 0.657905259237779}, 'combined': 0.43308151957019264, 'epoch': 5} Test Chinese: {'event': {'p': 0.6350053361792957, 'r': 0.7608695652173914, 'f1': 0.692262943571844}, 'argument': {'p': 0.7272924330941487, 'r': 0.6900381570870325, 'f1': 0.708175684166213}, 'combined': 0.4902437836869072, 'epoch': 5} Dev Korean: {'event': {'p': 0.6105032822757112, 'r': 0.7430093209054593, 'f1': 0.6702702702702702}, 'argument': {'p': 0.6914323890031635, 'r': 0.6157583794121126, 'f1': 0.651404978696081}, 'combined': 0.4366173911260218, 'epoch': 5} Test Korean: {'event': {'p': 0.6253968253968254, 'r': 0.7557544757033248, 'f1': 0.6844238563983787}, 'argument': {'p': 0.7217273465797566, 'r': 0.6830584493271099, 'f1': 0.7018606874131883}, 'combined': 0.48037019833375133, 'epoch': 5} Dev Russian: {'event': {'p': 0.5669291338582677, 'r': 0.7669773635153129, 'f1': 0.6519524617996605}, 'argument': {'p': 0.693675105554045, 'r': 0.6305685594183976, 'f1': 0.6606181680661036}, 'combined': 0.4306916409802781, 'epoch': 5} Test Russian: {'event': {'p': 0.6233183856502242, 'r': 0.7998721227621484, 'f1': 0.7006440772892747}, 'argument': {'p': 0.7281978207557468, 'r': 0.6927557703258528, 'f1': 0.7100347899233893}, 'combined': 0.4974816702291571, 'epoch': 5} Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.6753413767302655, 'r': 0.6027840387344519, 'f1': 0.6370032199726521}, 'combined': 0.4632750690710198, 'epoch': 5} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6556681954409226, 'r': 0.3951972684849397, 'f1': 0.49315214699830073}, 'combined': 0.31146451389366364, 'epoch': 5} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.6320465795835254, 'r': 0.5530407571355848, 'f1': 0.5899101409446238}, 'combined': 0.3285575468552335, 'epoch': 5} New best chinese model... New best korean model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6964114198955085, 'r': 0.6234341752956798, 'f1': 0.657905259237779}, 'combined': 0.43308151957019264, 'epoch': 5} Test for Chinese: {'event': {'p': 0.6350053361792957, 'r': 0.7608695652173914, 'f1': 0.692262943571844}, 'argument': {'p': 0.7272924330941487, 'r': 0.6900381570870325, 'f1': 0.708175684166213}, 'combined': 0.4902437836869072, 'epoch': 5} Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.6753413767302655, 'r': 0.6027840387344519, 'f1': 0.6370032199726521}, 'combined': 0.4632750690710198, 'epoch': 5} -------------------- Dev for Korean: {'event': {'p': 0.6105032822757112, 'r': 0.7430093209054593, 'f1': 0.6702702702702702}, 'argument': {'p': 0.6914323890031635, 'r': 0.6157583794121126, 'f1': 0.651404978696081}, 'combined': 0.4366173911260218, 'epoch': 5} Test for Korean: {'event': {'p': 0.6253968253968254, 'r': 0.7557544757033248, 'f1': 0.6844238563983787}, 'argument': {'p': 0.7217273465797566, 'r': 0.6830584493271099, 'f1': 0.7018606874131883}, 'combined': 0.48037019833375133, 'epoch': 5} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6556681954409226, 'r': 0.3951972684849397, 'f1': 0.49315214699830073}, 'combined': 0.31146451389366364, 'epoch': 5} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 6 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 07:50:57.834277: step: 2/1545, loss: 0.42893439531326294 2023-01-23 07:50:58.681282: step: 4/1545, loss: 0.4024112820625305 2023-01-23 07:50:59.515772: step: 6/1545, loss: 0.7472184896469116 2023-01-23 07:51:00.420541: step: 8/1545, loss: 0.43145740032196045 2023-01-23 07:51:01.275594: step: 10/1545, loss: 0.4431711435317993 2023-01-23 07:51:02.139159: step: 12/1545, loss: 0.59794682264328 2023-01-23 07:51:03.065413: step: 14/1545, loss: 0.3567464351654053 2023-01-23 07:51:03.924427: step: 16/1545, loss: 0.3200010657310486 2023-01-23 07:51:04.861888: step: 18/1545, loss: 5.323441982269287 2023-01-23 07:51:05.793947: step: 20/1545, loss: 0.16699333488941193 2023-01-23 07:51:06.761035: step: 22/1545, loss: 0.8784658908843994 2023-01-23 07:51:07.698426: step: 24/1545, loss: 0.1299605667591095 2023-01-23 07:51:08.574116: step: 26/1545, loss: 0.25295957922935486 2023-01-23 07:51:09.453889: step: 28/1545, loss: 0.5563297867774963 2023-01-23 07:51:10.307926: step: 30/1545, loss: 0.182212233543396 2023-01-23 07:51:11.146685: step: 32/1545, loss: 0.11569239944219589 2023-01-23 07:51:11.964015: step: 34/1545, loss: 0.13852359354496002 2023-01-23 07:51:12.853543: step: 36/1545, loss: 0.3779805898666382 2023-01-23 07:51:13.748953: step: 38/1545, loss: 0.6967212557792664 2023-01-23 07:51:14.630588: step: 40/1545, loss: 0.33913305401802063 2023-01-23 07:51:15.509996: step: 42/1545, loss: 0.21211345493793488 2023-01-23 07:51:16.381525: step: 44/1545, loss: 0.4107503890991211 2023-01-23 07:51:17.220853: step: 46/1545, loss: 0.5241456627845764 2023-01-23 07:51:18.087224: step: 48/1545, loss: 0.22338005900382996 2023-01-23 07:51:18.966361: step: 50/1545, loss: 0.29227519035339355 2023-01-23 07:51:19.849890: step: 52/1545, loss: 0.33583155274391174 2023-01-23 07:51:20.697476: step: 54/1545, loss: 0.13994021713733673 2023-01-23 07:51:21.602747: step: 56/1545, loss: 0.9622036218643188 2023-01-23 07:51:22.445846: step: 58/1545, loss: 0.43312695622444153 2023-01-23 07:51:23.306776: step: 60/1545, loss: 0.4171743094921112 2023-01-23 07:51:24.142022: step: 62/1545, loss: 0.21626430749893188 2023-01-23 07:51:25.029442: step: 64/1545, loss: 0.6173324584960938 2023-01-23 07:51:25.965174: step: 66/1545, loss: 0.46835944056510925 2023-01-23 07:51:26.865868: step: 68/1545, loss: 0.29383695125579834 2023-01-23 07:51:27.779541: step: 70/1545, loss: 0.4621519446372986 2023-01-23 07:51:28.763532: step: 72/1545, loss: 0.3374672532081604 2023-01-23 07:51:29.601322: step: 74/1545, loss: 0.2692663073539734 2023-01-23 07:51:30.518349: step: 76/1545, loss: 0.6048665046691895 2023-01-23 07:51:31.400452: step: 78/1545, loss: 1.7906817197799683 2023-01-23 07:51:32.258369: step: 80/1545, loss: 0.3390214443206787 2023-01-23 07:51:33.175617: step: 82/1545, loss: 0.29822131991386414 2023-01-23 07:51:34.035483: step: 84/1545, loss: 0.34952259063720703 2023-01-23 07:51:34.908361: step: 86/1545, loss: 0.1709543913602829 2023-01-23 07:51:35.803605: step: 88/1545, loss: 0.2981722354888916 2023-01-23 07:51:36.660455: step: 90/1545, loss: 0.1745058000087738 2023-01-23 07:51:37.499329: step: 92/1545, loss: 0.24230484664440155 2023-01-23 07:51:38.381566: step: 94/1545, loss: 0.6002039909362793 2023-01-23 07:51:39.239867: step: 96/1545, loss: 0.2954406142234802 2023-01-23 07:51:40.103828: step: 98/1545, loss: 0.3543975055217743 2023-01-23 07:51:40.996992: step: 100/1545, loss: 0.07032885402441025 2023-01-23 07:51:41.883861: step: 102/1545, loss: 0.29158246517181396 2023-01-23 07:51:42.747979: step: 104/1545, loss: 0.15339043736457825 2023-01-23 07:51:43.598389: step: 106/1545, loss: 0.8932031393051147 2023-01-23 07:51:44.474692: step: 108/1545, loss: 0.10835447907447815 2023-01-23 07:51:45.353933: step: 110/1545, loss: 0.20206446945667267 2023-01-23 07:51:46.228577: step: 112/1545, loss: 0.9545279741287231 2023-01-23 07:51:47.057889: step: 114/1545, loss: 0.35320326685905457 2023-01-23 07:51:47.927194: step: 116/1545, loss: 0.4444003403186798 2023-01-23 07:51:48.794320: step: 118/1545, loss: 0.0658297911286354 2023-01-23 07:51:49.671879: step: 120/1545, loss: 0.7709249258041382 2023-01-23 07:51:50.556502: step: 122/1545, loss: 0.2479335367679596 2023-01-23 07:51:51.465829: step: 124/1545, loss: 0.18629451096057892 2023-01-23 07:51:52.349672: step: 126/1545, loss: 0.25284379720687866 2023-01-23 07:51:53.233835: step: 128/1545, loss: 0.359720915555954 2023-01-23 07:51:54.098124: step: 130/1545, loss: 0.2347411811351776 2023-01-23 07:51:54.987101: step: 132/1545, loss: 0.5131204724311829 2023-01-23 07:51:55.911845: step: 134/1545, loss: 0.7345717549324036 2023-01-23 07:51:56.772802: step: 136/1545, loss: 0.6435197591781616 2023-01-23 07:51:57.596091: step: 138/1545, loss: 0.3501676917076111 2023-01-23 07:51:58.539674: step: 140/1545, loss: 0.40014368295669556 2023-01-23 07:51:59.430134: step: 142/1545, loss: 0.22971969842910767 2023-01-23 07:52:00.303580: step: 144/1545, loss: 0.3058934211730957 2023-01-23 07:52:01.154340: step: 146/1545, loss: 0.3930911421775818 2023-01-23 07:52:02.003905: step: 148/1545, loss: 0.7020494341850281 2023-01-23 07:52:02.843251: step: 150/1545, loss: 0.28214016556739807 2023-01-23 07:52:03.730686: step: 152/1545, loss: 0.6300147771835327 2023-01-23 07:52:04.617166: step: 154/1545, loss: 0.5225220322608948 2023-01-23 07:52:05.497250: step: 156/1545, loss: 0.3170319199562073 2023-01-23 07:52:06.353548: step: 158/1545, loss: 0.1596611738204956 2023-01-23 07:52:07.284470: step: 160/1545, loss: 0.3276526629924774 2023-01-23 07:52:08.176372: step: 162/1545, loss: 0.276102751493454 2023-01-23 07:52:09.056236: step: 164/1545, loss: 0.4696749746799469 2023-01-23 07:52:09.969989: step: 166/1545, loss: 0.2244108021259308 2023-01-23 07:52:10.804475: step: 168/1545, loss: 0.33451876044273376 2023-01-23 07:52:11.728924: step: 170/1545, loss: 0.2824341356754303 2023-01-23 07:52:12.573860: step: 172/1545, loss: 0.41891783475875854 2023-01-23 07:52:13.458002: step: 174/1545, loss: 0.31015709042549133 2023-01-23 07:52:14.307337: step: 176/1545, loss: 0.15404880046844482 2023-01-23 07:52:15.176981: step: 178/1545, loss: 0.6774522662162781 2023-01-23 07:52:16.111411: step: 180/1545, loss: 0.3094152808189392 2023-01-23 07:52:17.015707: step: 182/1545, loss: 0.06532733887434006 2023-01-23 07:52:17.868120: step: 184/1545, loss: 0.35344475507736206 2023-01-23 07:52:18.727136: step: 186/1545, loss: 0.3682878911495209 2023-01-23 07:52:19.661918: step: 188/1545, loss: 0.947996199131012 2023-01-23 07:52:20.523866: step: 190/1545, loss: 0.9685216546058655 2023-01-23 07:52:21.424352: step: 192/1545, loss: 0.41482383012771606 2023-01-23 07:52:22.304263: step: 194/1545, loss: 0.722403883934021 2023-01-23 07:52:23.196103: step: 196/1545, loss: 0.42141392827033997 2023-01-23 07:52:24.073609: step: 198/1545, loss: 0.27003568410873413 2023-01-23 07:52:24.936503: step: 200/1545, loss: 0.21262997388839722 2023-01-23 07:52:25.815370: step: 202/1545, loss: 0.6935011744499207 2023-01-23 07:52:26.715291: step: 204/1545, loss: 0.2978323698043823 2023-01-23 07:52:27.576444: step: 206/1545, loss: 6.671670913696289 2023-01-23 07:52:28.451257: step: 208/1545, loss: 0.34129929542541504 2023-01-23 07:52:29.321065: step: 210/1545, loss: 0.13473592698574066 2023-01-23 07:52:30.180888: step: 212/1545, loss: 0.3284607231616974 2023-01-23 07:52:31.063454: step: 214/1545, loss: 0.4243706464767456 2023-01-23 07:52:31.949846: step: 216/1545, loss: 0.11219049245119095 2023-01-23 07:52:32.855542: step: 218/1545, loss: 0.8613790273666382 2023-01-23 07:52:33.710786: step: 220/1545, loss: 1.089550256729126 2023-01-23 07:52:34.590792: step: 222/1545, loss: 0.1277715116739273 2023-01-23 07:52:35.450335: step: 224/1545, loss: 0.2756979465484619 2023-01-23 07:52:36.343629: step: 226/1545, loss: 0.14060303568840027 2023-01-23 07:52:37.212626: step: 228/1545, loss: 0.606952428817749 2023-01-23 07:52:38.117150: step: 230/1545, loss: 0.59992915391922 2023-01-23 07:52:38.985420: step: 232/1545, loss: 0.6384779810905457 2023-01-23 07:52:39.902832: step: 234/1545, loss: 0.4466930329799652 2023-01-23 07:52:40.810711: step: 236/1545, loss: 0.17516613006591797 2023-01-23 07:52:41.684449: step: 238/1545, loss: 0.46097061038017273 2023-01-23 07:52:42.548733: step: 240/1545, loss: 0.4459277093410492 2023-01-23 07:52:43.467223: step: 242/1545, loss: 0.6147555708885193 2023-01-23 07:52:44.333049: step: 244/1545, loss: 0.20526842772960663 2023-01-23 07:52:45.190722: step: 246/1545, loss: 0.15513712167739868 2023-01-23 07:52:46.106102: step: 248/1545, loss: 0.847663938999176 2023-01-23 07:52:47.024426: step: 250/1545, loss: 0.32120421528816223 2023-01-23 07:52:47.893399: step: 252/1545, loss: 0.47763776779174805 2023-01-23 07:52:48.762637: step: 254/1545, loss: 0.34409987926483154 2023-01-23 07:52:49.664465: step: 256/1545, loss: 0.2804535925388336 2023-01-23 07:52:50.529136: step: 258/1545, loss: 0.3321290612220764 2023-01-23 07:52:51.391464: step: 260/1545, loss: 0.4554556608200073 2023-01-23 07:52:52.247802: step: 262/1545, loss: 0.2443663626909256 2023-01-23 07:52:53.142616: step: 264/1545, loss: 0.2592301070690155 2023-01-23 07:52:54.078868: step: 266/1545, loss: 0.2561083734035492 2023-01-23 07:52:54.990848: step: 268/1545, loss: 1.0795314311981201 2023-01-23 07:52:55.866594: step: 270/1545, loss: 0.5485743284225464 2023-01-23 07:52:56.736434: step: 272/1545, loss: 2.6735124588012695 2023-01-23 07:52:57.582912: step: 274/1545, loss: 0.33847275376319885 2023-01-23 07:52:58.469809: step: 276/1545, loss: 0.5485754609107971 2023-01-23 07:52:59.313246: step: 278/1545, loss: 0.08280033618211746 2023-01-23 07:53:00.187308: step: 280/1545, loss: 0.4385044574737549 2023-01-23 07:53:01.129278: step: 282/1545, loss: 0.7904424071311951 2023-01-23 07:53:02.020824: step: 284/1545, loss: 0.34608957171440125 2023-01-23 07:53:02.905544: step: 286/1545, loss: 0.3074616491794586 2023-01-23 07:53:03.752860: step: 288/1545, loss: 0.46651530265808105 2023-01-23 07:53:04.613133: step: 290/1545, loss: 0.1712968349456787 2023-01-23 07:53:05.493673: step: 292/1545, loss: 0.49625954031944275 2023-01-23 07:53:06.424407: step: 294/1545, loss: 0.500815749168396 2023-01-23 07:53:07.364237: step: 296/1545, loss: 0.820769190788269 2023-01-23 07:53:08.257919: step: 298/1545, loss: 0.4064594507217407 2023-01-23 07:53:09.232699: step: 300/1545, loss: 0.5540177226066589 2023-01-23 07:53:10.082710: step: 302/1545, loss: 0.2305263876914978 2023-01-23 07:53:10.936977: step: 304/1545, loss: 0.3387526571750641 2023-01-23 07:53:11.787340: step: 306/1545, loss: 0.8730970621109009 2023-01-23 07:53:12.678273: step: 308/1545, loss: 4.336792469024658 2023-01-23 07:53:13.588116: step: 310/1545, loss: 0.5405839681625366 2023-01-23 07:53:14.481810: step: 312/1545, loss: 0.3074510097503662 2023-01-23 07:53:15.341921: step: 314/1545, loss: 1.2631874084472656 2023-01-23 07:53:16.202697: step: 316/1545, loss: 0.2997710406780243 2023-01-23 07:53:17.057820: step: 318/1545, loss: 0.19588442146778107 2023-01-23 07:53:17.921337: step: 320/1545, loss: 0.679569661617279 2023-01-23 07:53:18.837584: step: 322/1545, loss: 2.971982955932617 2023-01-23 07:53:19.701489: step: 324/1545, loss: 3.6456761360168457 2023-01-23 07:53:20.574713: step: 326/1545, loss: 0.20913542807102203 2023-01-23 07:53:21.446938: step: 328/1545, loss: 0.9041591286659241 2023-01-23 07:53:22.299576: step: 330/1545, loss: 0.07516732811927795 2023-01-23 07:53:23.171312: step: 332/1545, loss: 6.971844673156738 2023-01-23 07:53:24.010994: step: 334/1545, loss: 0.3775506913661957 2023-01-23 07:53:24.877593: step: 336/1545, loss: 0.21731683611869812 2023-01-23 07:53:25.765031: step: 338/1545, loss: 0.5485098361968994 2023-01-23 07:53:26.632782: step: 340/1545, loss: 0.28426751494407654 2023-01-23 07:53:27.515542: step: 342/1545, loss: 0.4103425145149231 2023-01-23 07:53:28.501243: step: 344/1545, loss: 0.28295356035232544 2023-01-23 07:53:29.387560: step: 346/1545, loss: 0.22482134401798248 2023-01-23 07:53:30.259181: step: 348/1545, loss: 0.32556504011154175 2023-01-23 07:53:31.124692: step: 350/1545, loss: 0.5727220773696899 2023-01-23 07:53:31.993760: step: 352/1545, loss: 0.23186728358268738 2023-01-23 07:53:32.854060: step: 354/1545, loss: 0.3076353073120117 2023-01-23 07:53:33.693365: step: 356/1545, loss: 0.9486901164054871 2023-01-23 07:53:34.544505: step: 358/1545, loss: 0.6883069276809692 2023-01-23 07:53:35.399713: step: 360/1545, loss: 0.23678600788116455 2023-01-23 07:53:36.284936: step: 362/1545, loss: 0.30178728699684143 2023-01-23 07:53:37.162976: step: 364/1545, loss: 0.1671275496482849 2023-01-23 07:53:38.075014: step: 366/1545, loss: 0.2910677194595337 2023-01-23 07:53:38.979946: step: 368/1545, loss: 0.3998064398765564 2023-01-23 07:53:39.876582: step: 370/1545, loss: 0.4093371033668518 2023-01-23 07:53:40.763539: step: 372/1545, loss: 2.669900894165039 2023-01-23 07:53:41.693075: step: 374/1545, loss: 0.5001115798950195 2023-01-23 07:53:42.536270: step: 376/1545, loss: 0.2616727352142334 2023-01-23 07:53:43.530509: step: 378/1545, loss: 0.4357346296310425 2023-01-23 07:53:44.388118: step: 380/1545, loss: 0.3210959732532501 2023-01-23 07:53:45.243381: step: 382/1545, loss: 0.6585939526557922 2023-01-23 07:53:46.113340: step: 384/1545, loss: 0.3307269215583801 2023-01-23 07:53:47.024974: step: 386/1545, loss: 0.4933951795101166 2023-01-23 07:53:47.873830: step: 388/1545, loss: 0.3361026346683502 2023-01-23 07:53:48.740523: step: 390/1545, loss: 0.15889263153076172 2023-01-23 07:53:49.677002: step: 392/1545, loss: 0.3381328284740448 2023-01-23 07:53:50.603810: step: 394/1545, loss: 0.09444626420736313 2023-01-23 07:53:51.536883: step: 396/1545, loss: 0.36623287200927734 2023-01-23 07:53:52.414290: step: 398/1545, loss: 0.5875319242477417 2023-01-23 07:53:53.316577: step: 400/1545, loss: 2.173001289367676 2023-01-23 07:53:54.194787: step: 402/1545, loss: 0.5286204218864441 2023-01-23 07:53:55.114336: step: 404/1545, loss: 0.2935541570186615 2023-01-23 07:53:55.965797: step: 406/1545, loss: 0.38267794251441956 2023-01-23 07:53:56.856508: step: 408/1545, loss: 1.1915932893753052 2023-01-23 07:53:57.743141: step: 410/1545, loss: 0.08772706985473633 2023-01-23 07:53:58.629138: step: 412/1545, loss: 0.6699076294898987 2023-01-23 07:53:59.512711: step: 414/1545, loss: 0.35382288694381714 2023-01-23 07:54:00.375575: step: 416/1545, loss: 0.21266673505306244 2023-01-23 07:54:01.244095: step: 418/1545, loss: 0.2716420888900757 2023-01-23 07:54:02.107576: step: 420/1545, loss: 0.5820888876914978 2023-01-23 07:54:02.957549: step: 422/1545, loss: 0.22280971705913544 2023-01-23 07:54:03.843427: step: 424/1545, loss: 0.4711531400680542 2023-01-23 07:54:04.725873: step: 426/1545, loss: 0.41499441862106323 2023-01-23 07:54:05.587820: step: 428/1545, loss: 0.13504071533679962 2023-01-23 07:54:06.559692: step: 430/1545, loss: 1.0754307508468628 2023-01-23 07:54:07.438382: step: 432/1545, loss: 0.523791491985321 2023-01-23 07:54:08.317825: step: 434/1545, loss: 0.36906301975250244 2023-01-23 07:54:09.181087: step: 436/1545, loss: 0.14108076691627502 2023-01-23 07:54:10.041755: step: 438/1545, loss: 0.6472454071044922 2023-01-23 07:54:10.914299: step: 440/1545, loss: 0.27367570996284485 2023-01-23 07:54:11.787617: step: 442/1545, loss: 1.84122896194458 2023-01-23 07:54:12.657563: step: 444/1545, loss: 0.08654658496379852 2023-01-23 07:54:13.506045: step: 446/1545, loss: 0.3559401333332062 2023-01-23 07:54:14.411402: step: 448/1545, loss: 0.5939930081367493 2023-01-23 07:54:15.295068: step: 450/1545, loss: 0.3384209871292114 2023-01-23 07:54:16.161232: step: 452/1545, loss: 0.28619158267974854 2023-01-23 07:54:17.117997: step: 454/1545, loss: 0.12021695077419281 2023-01-23 07:54:18.020299: step: 456/1545, loss: 0.1837509721517563 2023-01-23 07:54:18.868545: step: 458/1545, loss: 0.508794903755188 2023-01-23 07:54:19.773144: step: 460/1545, loss: 0.27033311128616333 2023-01-23 07:54:20.690312: step: 462/1545, loss: 0.15107731521129608 2023-01-23 07:54:21.514461: step: 464/1545, loss: 0.091227225959301 2023-01-23 07:54:22.389028: step: 466/1545, loss: 0.4400041103363037 2023-01-23 07:54:23.242447: step: 468/1545, loss: 0.2310771346092224 2023-01-23 07:54:24.081496: step: 470/1545, loss: 0.28301098942756653 2023-01-23 07:54:25.015953: step: 472/1545, loss: 0.1899489015340805 2023-01-23 07:54:25.949743: step: 474/1545, loss: 0.5510974526405334 2023-01-23 07:54:26.848418: step: 476/1545, loss: 1.1807150840759277 2023-01-23 07:54:27.741599: step: 478/1545, loss: 0.1243029534816742 2023-01-23 07:54:28.683808: step: 480/1545, loss: 0.32026487588882446 2023-01-23 07:54:29.555092: step: 482/1545, loss: 0.5857892036437988 2023-01-23 07:54:30.486142: step: 484/1545, loss: 0.35018840432167053 2023-01-23 07:54:31.341126: step: 486/1545, loss: 0.6485934257507324 2023-01-23 07:54:32.233684: step: 488/1545, loss: 0.40419113636016846 2023-01-23 07:54:33.161893: step: 490/1545, loss: 0.7382578253746033 2023-01-23 07:54:34.039458: step: 492/1545, loss: 0.4243549406528473 2023-01-23 07:54:34.974899: step: 494/1545, loss: 0.3034237325191498 2023-01-23 07:54:35.850947: step: 496/1545, loss: 0.9188178181648254 2023-01-23 07:54:36.705834: step: 498/1545, loss: 0.4097345769405365 2023-01-23 07:54:37.595199: step: 500/1545, loss: 0.3132888376712799 2023-01-23 07:54:38.430734: step: 502/1545, loss: 0.3883357048034668 2023-01-23 07:54:39.336559: step: 504/1545, loss: 0.7614994049072266 2023-01-23 07:54:40.223316: step: 506/1545, loss: 0.2733573615550995 2023-01-23 07:54:41.117455: step: 508/1545, loss: 0.22189411520957947 2023-01-23 07:54:41.985589: step: 510/1545, loss: 1.0843141078948975 2023-01-23 07:54:42.926517: step: 512/1545, loss: 0.3412573039531708 2023-01-23 07:54:43.776692: step: 514/1545, loss: 0.7302554249763489 2023-01-23 07:54:44.632973: step: 516/1545, loss: 0.2104392647743225 2023-01-23 07:54:45.544942: step: 518/1545, loss: 1.3950121402740479 2023-01-23 07:54:46.488337: step: 520/1545, loss: 0.572421669960022 2023-01-23 07:54:47.397377: step: 522/1545, loss: 0.3045460879802704 2023-01-23 07:54:48.263854: step: 524/1545, loss: 0.43099549412727356 2023-01-23 07:54:49.113243: step: 526/1545, loss: 0.20903922617435455 2023-01-23 07:54:50.029082: step: 528/1545, loss: 2.678703784942627 2023-01-23 07:54:50.897355: step: 530/1545, loss: 0.748775064945221 2023-01-23 07:54:51.829698: step: 532/1545, loss: 0.3680720627307892 2023-01-23 07:54:52.745793: step: 534/1545, loss: 0.2723883390426636 2023-01-23 07:54:53.619499: step: 536/1545, loss: 0.2765986919403076 2023-01-23 07:54:54.512027: step: 538/1545, loss: 0.6484888195991516 2023-01-23 07:54:55.359314: step: 540/1545, loss: 0.3285869061946869 2023-01-23 07:54:56.250072: step: 542/1545, loss: 0.4414421617984772 2023-01-23 07:54:57.141451: step: 544/1545, loss: 0.4096936583518982 2023-01-23 07:54:58.026717: step: 546/1545, loss: 0.4740683138370514 2023-01-23 07:54:58.955981: step: 548/1545, loss: 0.9372580051422119 2023-01-23 07:54:59.854061: step: 550/1545, loss: 1.7474071979522705 2023-01-23 07:55:00.743701: step: 552/1545, loss: 3.980431079864502 2023-01-23 07:55:01.672461: step: 554/1545, loss: 0.3510505259037018 2023-01-23 07:55:02.575919: step: 556/1545, loss: 0.4825068414211273 2023-01-23 07:55:03.429116: step: 558/1545, loss: 0.15762735903263092 2023-01-23 07:55:04.300774: step: 560/1545, loss: 0.8806937336921692 2023-01-23 07:55:05.203450: step: 562/1545, loss: 0.7529121041297913 2023-01-23 07:55:06.152712: step: 564/1545, loss: 0.3753141760826111 2023-01-23 07:55:06.995537: step: 566/1545, loss: 0.19636982679367065 2023-01-23 07:55:07.856092: step: 568/1545, loss: 0.06459936499595642 2023-01-23 07:55:08.739801: step: 570/1545, loss: 0.6716350317001343 2023-01-23 07:55:09.596454: step: 572/1545, loss: 0.4336954355239868 2023-01-23 07:55:10.490298: step: 574/1545, loss: 0.1984148919582367 2023-01-23 07:55:11.388413: step: 576/1545, loss: 0.6274268627166748 2023-01-23 07:55:12.281037: step: 578/1545, loss: 0.19766771793365479 2023-01-23 07:55:13.172588: step: 580/1545, loss: 0.31220972537994385 2023-01-23 07:55:14.049155: step: 582/1545, loss: 0.2896970808506012 2023-01-23 07:55:14.953821: step: 584/1545, loss: 0.4433284401893616 2023-01-23 07:55:15.863989: step: 586/1545, loss: 0.5510727167129517 2023-01-23 07:55:16.756097: step: 588/1545, loss: 0.2030864953994751 2023-01-23 07:55:17.636985: step: 590/1545, loss: 0.557979166507721 2023-01-23 07:55:18.552344: step: 592/1545, loss: 0.2729750871658325 2023-01-23 07:55:19.425381: step: 594/1545, loss: 0.1136188730597496 2023-01-23 07:55:20.276122: step: 596/1545, loss: 0.7836673855781555 2023-01-23 07:55:21.141130: step: 598/1545, loss: 0.24496477842330933 2023-01-23 07:55:22.011077: step: 600/1545, loss: 0.8221741914749146 2023-01-23 07:55:22.892954: step: 602/1545, loss: 0.41324013471603394 2023-01-23 07:55:23.792885: step: 604/1545, loss: 1.2040494680404663 2023-01-23 07:55:24.650150: step: 606/1545, loss: 0.8885039687156677 2023-01-23 07:55:25.556867: step: 608/1545, loss: 0.2883416414260864 2023-01-23 07:55:26.495907: step: 610/1545, loss: 0.3093799948692322 2023-01-23 07:55:27.409215: step: 612/1545, loss: 0.25488224625587463 2023-01-23 07:55:28.277002: step: 614/1545, loss: 0.5325049757957458 2023-01-23 07:55:29.148449: step: 616/1545, loss: 0.15669414401054382 2023-01-23 07:55:30.052715: step: 618/1545, loss: 0.0975506454706192 2023-01-23 07:55:30.900642: step: 620/1545, loss: 0.3714921474456787 2023-01-23 07:55:31.765198: step: 622/1545, loss: 0.21233946084976196 2023-01-23 07:55:32.650662: step: 624/1545, loss: 0.41784459352493286 2023-01-23 07:55:33.531495: step: 626/1545, loss: 0.9717372059822083 2023-01-23 07:55:34.438341: step: 628/1545, loss: 0.25818514823913574 2023-01-23 07:55:35.337939: step: 630/1545, loss: 0.11180116981267929 2023-01-23 07:55:36.215601: step: 632/1545, loss: 0.6504707336425781 2023-01-23 07:55:37.092196: step: 634/1545, loss: 0.8141500353813171 2023-01-23 07:55:37.982981: step: 636/1545, loss: 0.19950978457927704 2023-01-23 07:55:38.893465: step: 638/1545, loss: 0.2966908812522888 2023-01-23 07:55:39.756618: step: 640/1545, loss: 3.6476454734802246 2023-01-23 07:55:40.665738: step: 642/1545, loss: 0.2832760214805603 2023-01-23 07:55:41.531574: step: 644/1545, loss: 0.5057684183120728 2023-01-23 07:55:42.441803: step: 646/1545, loss: 0.5733891129493713 2023-01-23 07:55:43.296060: step: 648/1545, loss: 0.2949889600276947 2023-01-23 07:55:44.149721: step: 650/1545, loss: 0.11715294420719147 2023-01-23 07:55:45.017318: step: 652/1545, loss: 0.4805879592895508 2023-01-23 07:55:45.907586: step: 654/1545, loss: 0.453544020652771 2023-01-23 07:55:46.782440: step: 656/1545, loss: 0.6830840110778809 2023-01-23 07:55:47.651133: step: 658/1545, loss: 1.1176824569702148 2023-01-23 07:55:48.587065: step: 660/1545, loss: 0.6469705700874329 2023-01-23 07:55:49.448708: step: 662/1545, loss: 0.23882120847702026 2023-01-23 07:55:50.352293: step: 664/1545, loss: 0.35840436816215515 2023-01-23 07:55:51.201244: step: 666/1545, loss: 0.35850876569747925 2023-01-23 07:55:52.104298: step: 668/1545, loss: 0.532866895198822 2023-01-23 07:55:52.967841: step: 670/1545, loss: 0.48143428564071655 2023-01-23 07:55:53.843623: step: 672/1545, loss: 0.5848015546798706 2023-01-23 07:55:54.769296: step: 674/1545, loss: 0.2674514651298523 2023-01-23 07:55:55.617563: step: 676/1545, loss: 0.4752017855644226 2023-01-23 07:55:56.457210: step: 678/1545, loss: 0.23400141298770905 2023-01-23 07:55:57.406510: step: 680/1545, loss: 0.35542166233062744 2023-01-23 07:55:58.291348: step: 682/1545, loss: 0.2771241068840027 2023-01-23 07:55:59.214040: step: 684/1545, loss: 0.4176081120967865 2023-01-23 07:56:00.137911: step: 686/1545, loss: 1.7724217176437378 2023-01-23 07:56:01.058546: step: 688/1545, loss: 0.3978549540042877 2023-01-23 07:56:01.958081: step: 690/1545, loss: 0.47089797258377075 2023-01-23 07:56:02.834510: step: 692/1545, loss: 0.4000034034252167 2023-01-23 07:56:03.736000: step: 694/1545, loss: 0.548412024974823 2023-01-23 07:56:04.618207: step: 696/1545, loss: 1.1071460247039795 2023-01-23 07:56:05.513786: step: 698/1545, loss: 0.20810526609420776 2023-01-23 07:56:06.379515: step: 700/1545, loss: 0.406882107257843 2023-01-23 07:56:07.256673: step: 702/1545, loss: 0.7013258337974548 2023-01-23 07:56:08.093631: step: 704/1545, loss: 0.1762402355670929 2023-01-23 07:56:08.954103: step: 706/1545, loss: 0.3983248472213745 2023-01-23 07:56:09.810214: step: 708/1545, loss: 0.9300262331962585 2023-01-23 07:56:10.690429: step: 710/1545, loss: 0.8106288909912109 2023-01-23 07:56:11.600800: step: 712/1545, loss: 0.7639957070350647 2023-01-23 07:56:12.514105: step: 714/1545, loss: 0.3409759998321533 2023-01-23 07:56:13.387744: step: 716/1545, loss: 0.3849368095397949 2023-01-23 07:56:14.236717: step: 718/1545, loss: 0.8203272819519043 2023-01-23 07:56:15.155977: step: 720/1545, loss: 0.22413328289985657 2023-01-23 07:56:16.033303: step: 722/1545, loss: 0.6455672383308411 2023-01-23 07:56:16.928084: step: 724/1545, loss: 0.5051586627960205 2023-01-23 07:56:17.799011: step: 726/1545, loss: 0.4579460024833679 2023-01-23 07:56:18.705699: step: 728/1545, loss: 0.42526552081108093 2023-01-23 07:56:19.656397: step: 730/1545, loss: 0.20704540610313416 2023-01-23 07:56:20.497001: step: 732/1545, loss: 0.04318283870816231 2023-01-23 07:56:21.386816: step: 734/1545, loss: 0.39570385217666626 2023-01-23 07:56:22.281065: step: 736/1545, loss: 2.8999931812286377 2023-01-23 07:56:23.241533: step: 738/1545, loss: 1.9121829271316528 2023-01-23 07:56:24.116647: step: 740/1545, loss: 0.27760979533195496 2023-01-23 07:56:24.983883: step: 742/1545, loss: 0.3156566023826599 2023-01-23 07:56:25.878720: step: 744/1545, loss: 0.5511283278465271 2023-01-23 07:56:26.747699: step: 746/1545, loss: 3.4975180625915527 2023-01-23 07:56:27.616040: step: 748/1545, loss: 0.9199991822242737 2023-01-23 07:56:28.498022: step: 750/1545, loss: 0.10265325754880905 2023-01-23 07:56:29.397975: step: 752/1545, loss: 0.5703623294830322 2023-01-23 07:56:30.255212: step: 754/1545, loss: 0.2472861111164093 2023-01-23 07:56:31.140106: step: 756/1545, loss: 0.1405564248561859 2023-01-23 07:56:31.991907: step: 758/1545, loss: 0.3889578580856323 2023-01-23 07:56:32.849995: step: 760/1545, loss: 0.15420381724834442 2023-01-23 07:56:33.785781: step: 762/1545, loss: 2.1361916065216064 2023-01-23 07:56:34.701866: step: 764/1545, loss: 0.940758466720581 2023-01-23 07:56:35.584253: step: 766/1545, loss: 0.25175926089286804 2023-01-23 07:56:36.452200: step: 768/1545, loss: 0.22611401975154877 2023-01-23 07:56:37.359312: step: 770/1545, loss: 0.6021183729171753 2023-01-23 07:56:38.236977: step: 772/1545, loss: 0.37923896312713623 2023-01-23 07:56:39.137900: step: 774/1545, loss: 0.398865669965744 2023-01-23 07:56:40.018788: step: 776/1545, loss: 0.5157921314239502 2023-01-23 07:56:40.948724: step: 778/1545, loss: 0.5764532685279846 2023-01-23 07:56:41.841174: step: 780/1545, loss: 1.1236166954040527 2023-01-23 07:56:42.690393: step: 782/1545, loss: 0.4381276071071625 2023-01-23 07:56:43.548637: step: 784/1545, loss: 0.4284103810787201 2023-01-23 07:56:44.421675: step: 786/1545, loss: 0.5774341225624084 2023-01-23 07:56:45.283668: step: 788/1545, loss: 0.3860696256160736 2023-01-23 07:56:46.188109: step: 790/1545, loss: 0.2331557422876358 2023-01-23 07:56:47.126505: step: 792/1545, loss: 2.254094123840332 2023-01-23 07:56:47.986245: step: 794/1545, loss: 0.4651734232902527 2023-01-23 07:56:48.880678: step: 796/1545, loss: 0.3793373107910156 2023-01-23 07:56:49.732188: step: 798/1545, loss: 0.43567749857902527 2023-01-23 07:56:50.609387: step: 800/1545, loss: 0.521862268447876 2023-01-23 07:56:51.464634: step: 802/1545, loss: 0.2441255748271942 2023-01-23 07:56:52.352272: step: 804/1545, loss: 0.6120854020118713 2023-01-23 07:56:53.204345: step: 806/1545, loss: 0.2655388414859772 2023-01-23 07:56:54.100801: step: 808/1545, loss: 0.25241318345069885 2023-01-23 07:56:54.960988: step: 810/1545, loss: 1.7239741086959839 2023-01-23 07:56:55.833117: step: 812/1545, loss: 0.22734202444553375 2023-01-23 07:56:56.768853: step: 814/1545, loss: 0.5452067255973816 2023-01-23 07:56:57.718602: step: 816/1545, loss: 2.4538867473602295 2023-01-23 07:56:58.605682: step: 818/1545, loss: 0.17614562809467316 2023-01-23 07:56:59.521098: step: 820/1545, loss: 0.5011057257652283 2023-01-23 07:57:00.454040: step: 822/1545, loss: 0.9222742319107056 2023-01-23 07:57:01.429866: step: 824/1545, loss: 0.4101877808570862 2023-01-23 07:57:02.296203: step: 826/1545, loss: 0.35684406757354736 2023-01-23 07:57:03.204727: step: 828/1545, loss: 0.2242758572101593 2023-01-23 07:57:04.085742: step: 830/1545, loss: 0.3136598467826843 2023-01-23 07:57:04.969418: step: 832/1545, loss: 0.6967641711235046 2023-01-23 07:57:05.862405: step: 834/1545, loss: 0.0938425064086914 2023-01-23 07:57:06.705885: step: 836/1545, loss: 0.32899999618530273 2023-01-23 07:57:07.587419: step: 838/1545, loss: 0.13704685866832733 2023-01-23 07:57:08.456928: step: 840/1545, loss: 0.7379525303840637 2023-01-23 07:57:09.300835: step: 842/1545, loss: 0.16166526079177856 2023-01-23 07:57:10.138631: step: 844/1545, loss: 0.2580627501010895 2023-01-23 07:57:10.977535: step: 846/1545, loss: 0.6698176860809326 2023-01-23 07:57:11.819719: step: 848/1545, loss: 0.12559625506401062 2023-01-23 07:57:12.703458: step: 850/1545, loss: 0.37792232632637024 2023-01-23 07:57:13.570006: step: 852/1545, loss: 0.4190056622028351 2023-01-23 07:57:14.485014: step: 854/1545, loss: 0.2790347635746002 2023-01-23 07:57:15.361061: step: 856/1545, loss: 0.5605399012565613 2023-01-23 07:57:16.259526: step: 858/1545, loss: 0.13085193932056427 2023-01-23 07:57:17.096756: step: 860/1545, loss: 3.1586718559265137 2023-01-23 07:57:17.944909: step: 862/1545, loss: 0.7085497975349426 2023-01-23 07:57:18.803464: step: 864/1545, loss: 0.10961753875017166 2023-01-23 07:57:19.727135: step: 866/1545, loss: 0.19579751789569855 2023-01-23 07:57:20.544181: step: 868/1545, loss: 0.16574084758758545 2023-01-23 07:57:21.441202: step: 870/1545, loss: 0.22078673541545868 2023-01-23 07:57:22.343356: step: 872/1545, loss: 0.5124961137771606 2023-01-23 07:57:23.275251: step: 874/1545, loss: 0.7926976680755615 2023-01-23 07:57:24.173033: step: 876/1545, loss: 2.5331804752349854 2023-01-23 07:57:25.115772: step: 878/1545, loss: 1.4008687734603882 2023-01-23 07:57:26.041275: step: 880/1545, loss: 0.3041895031929016 2023-01-23 07:57:26.939143: step: 882/1545, loss: 0.11875957995653152 2023-01-23 07:57:27.788095: step: 884/1545, loss: 0.278094083070755 2023-01-23 07:57:28.716563: step: 886/1545, loss: 0.1904895305633545 2023-01-23 07:57:29.595118: step: 888/1545, loss: 0.5229521989822388 2023-01-23 07:57:30.488058: step: 890/1545, loss: 0.6247726082801819 2023-01-23 07:57:31.328088: step: 892/1545, loss: 0.22706836462020874 2023-01-23 07:57:32.152011: step: 894/1545, loss: 0.10631159693002701 2023-01-23 07:57:33.026372: step: 896/1545, loss: 0.16900579631328583 2023-01-23 07:57:33.920053: step: 898/1545, loss: 0.18698765337467194 2023-01-23 07:57:34.798208: step: 900/1545, loss: 0.2788923978805542 2023-01-23 07:57:35.710735: step: 902/1545, loss: 0.2716233730316162 2023-01-23 07:57:36.625996: step: 904/1545, loss: 0.6494823694229126 2023-01-23 07:57:37.528223: step: 906/1545, loss: 0.2993340492248535 2023-01-23 07:57:38.417080: step: 908/1545, loss: 0.595591127872467 2023-01-23 07:57:39.282284: step: 910/1545, loss: 6.371088981628418 2023-01-23 07:57:40.226208: step: 912/1545, loss: 0.43098509311676025 2023-01-23 07:57:41.103822: step: 914/1545, loss: 1.1876622438430786 2023-01-23 07:57:41.991581: step: 916/1545, loss: 0.7282477021217346 2023-01-23 07:57:42.868336: step: 918/1545, loss: 1.1218680143356323 2023-01-23 07:57:43.768837: step: 920/1545, loss: 0.3010600805282593 2023-01-23 07:57:44.638368: step: 922/1545, loss: 0.7047837376594543 2023-01-23 07:57:45.478705: step: 924/1545, loss: 0.3199109137058258 2023-01-23 07:57:46.333992: step: 926/1545, loss: 0.14192192256450653 2023-01-23 07:57:47.227505: step: 928/1545, loss: 0.14012975990772247 2023-01-23 07:57:48.112726: step: 930/1545, loss: 0.28379228711128235 2023-01-23 07:57:49.132647: step: 932/1545, loss: 0.5840400457382202 2023-01-23 07:57:49.998404: step: 934/1545, loss: 0.5107634663581848 2023-01-23 07:57:50.871537: step: 936/1545, loss: 0.30224642157554626 2023-01-23 07:57:51.726916: step: 938/1545, loss: 0.21965451538562775 2023-01-23 07:57:52.550014: step: 940/1545, loss: 0.6369367837905884 2023-01-23 07:57:53.456612: step: 942/1545, loss: 0.5673019886016846 2023-01-23 07:57:54.331738: step: 944/1545, loss: 0.2507059574127197 2023-01-23 07:57:55.192124: step: 946/1545, loss: 0.2635664641857147 2023-01-23 07:57:56.073091: step: 948/1545, loss: 0.5309767723083496 2023-01-23 07:57:56.951929: step: 950/1545, loss: 2.5184693336486816 2023-01-23 07:57:57.821333: step: 952/1545, loss: 0.3667992055416107 2023-01-23 07:57:58.662585: step: 954/1545, loss: 0.5413157343864441 2023-01-23 07:57:59.572361: step: 956/1545, loss: 0.5162838697433472 2023-01-23 07:58:00.431410: step: 958/1545, loss: 1.0516051054000854 2023-01-23 07:58:01.284327: step: 960/1545, loss: 0.9848342537879944 2023-01-23 07:58:02.147075: step: 962/1545, loss: 0.6618834733963013 2023-01-23 07:58:03.014604: step: 964/1545, loss: 0.325895220041275 2023-01-23 07:58:03.901333: step: 966/1545, loss: 0.228847935795784 2023-01-23 07:58:04.722659: step: 968/1545, loss: 0.3473527133464813 2023-01-23 07:58:05.613872: step: 970/1545, loss: 0.8082705140113831 2023-01-23 07:58:06.542560: step: 972/1545, loss: 0.33878934383392334 2023-01-23 07:58:07.432938: step: 974/1545, loss: 0.38916707038879395 2023-01-23 07:58:08.291985: step: 976/1545, loss: 0.3469613790512085 2023-01-23 07:58:09.220539: step: 978/1545, loss: 0.7187334895133972 2023-01-23 07:58:10.183374: step: 980/1545, loss: 0.7747113108634949 2023-01-23 07:58:11.059938: step: 982/1545, loss: 0.31627345085144043 2023-01-23 07:58:11.899958: step: 984/1545, loss: 2.040440797805786 2023-01-23 07:58:12.756406: step: 986/1545, loss: 0.9208753705024719 2023-01-23 07:58:13.611875: step: 988/1545, loss: 0.13064172863960266 2023-01-23 07:58:14.476989: step: 990/1545, loss: 0.29317811131477356 2023-01-23 07:58:15.384913: step: 992/1545, loss: 0.37049561738967896 2023-01-23 07:58:16.255110: step: 994/1545, loss: 0.432155966758728 2023-01-23 07:58:17.108123: step: 996/1545, loss: 0.14619328081607819 2023-01-23 07:58:18.025002: step: 998/1545, loss: 0.14702743291854858 2023-01-23 07:58:18.882674: step: 1000/1545, loss: 0.6113474369049072 2023-01-23 07:58:19.764524: step: 1002/1545, loss: 0.4759220480918884 2023-01-23 07:58:20.623747: step: 1004/1545, loss: 0.33437561988830566 2023-01-23 07:58:21.472920: step: 1006/1545, loss: 0.4284687638282776 2023-01-23 07:58:22.340760: step: 1008/1545, loss: 0.6950617432594299 2023-01-23 07:58:23.243070: step: 1010/1545, loss: 0.35572993755340576 2023-01-23 07:58:24.129101: step: 1012/1545, loss: 0.31863564252853394 2023-01-23 07:58:24.988992: step: 1014/1545, loss: 0.41326022148132324 2023-01-23 07:58:25.831943: step: 1016/1545, loss: 0.32807692885398865 2023-01-23 07:58:26.731884: step: 1018/1545, loss: 1.1554802656173706 2023-01-23 07:58:27.626719: step: 1020/1545, loss: 0.49965158104896545 2023-01-23 07:58:28.507675: step: 1022/1545, loss: 0.23858262598514557 2023-01-23 07:58:29.370149: step: 1024/1545, loss: 0.16512371599674225 2023-01-23 07:58:30.262781: step: 1026/1545, loss: 0.16472072899341583 2023-01-23 07:58:31.185719: step: 1028/1545, loss: 0.13321562111377716 2023-01-23 07:58:32.047839: step: 1030/1545, loss: 0.6215464472770691 2023-01-23 07:58:32.990916: step: 1032/1545, loss: 1.1957119703292847 2023-01-23 07:58:33.881164: step: 1034/1545, loss: 0.7502291798591614 2023-01-23 07:58:34.769593: step: 1036/1545, loss: 0.31429940462112427 2023-01-23 07:58:35.687884: step: 1038/1545, loss: 0.7447029948234558 2023-01-23 07:58:36.554466: step: 1040/1545, loss: 0.11754468083381653 2023-01-23 07:58:37.460630: step: 1042/1545, loss: 1.7590678930282593 2023-01-23 07:58:38.352820: step: 1044/1545, loss: 0.42967674136161804 2023-01-23 07:58:39.270913: step: 1046/1545, loss: 1.1149327754974365 2023-01-23 07:58:40.109029: step: 1048/1545, loss: 0.601389467716217 2023-01-23 07:58:41.075808: step: 1050/1545, loss: 0.43111252784729004 2023-01-23 07:58:41.984750: step: 1052/1545, loss: 0.4243663549423218 2023-01-23 07:58:42.888580: step: 1054/1545, loss: 0.3635028600692749 2023-01-23 07:58:43.753431: step: 1056/1545, loss: 0.20784024894237518 2023-01-23 07:58:44.707701: step: 1058/1545, loss: 0.49592605233192444 2023-01-23 07:58:45.650345: step: 1060/1545, loss: 0.40921223163604736 2023-01-23 07:58:46.495729: step: 1062/1545, loss: 0.6718056797981262 2023-01-23 07:58:47.373034: step: 1064/1545, loss: 0.4598206877708435 2023-01-23 07:58:48.260786: step: 1066/1545, loss: 0.26371508836746216 2023-01-23 07:58:49.118316: step: 1068/1545, loss: 0.38054710626602173 2023-01-23 07:58:50.049476: step: 1070/1545, loss: 0.515232264995575 2023-01-23 07:58:50.964678: step: 1072/1545, loss: 0.2881371080875397 2023-01-23 07:58:51.867622: step: 1074/1545, loss: 0.36751124262809753 2023-01-23 07:58:52.740671: step: 1076/1545, loss: 0.5912438035011292 2023-01-23 07:58:53.626615: step: 1078/1545, loss: 0.6800157427787781 2023-01-23 07:58:54.492266: step: 1080/1545, loss: 0.5831153392791748 2023-01-23 07:58:55.390851: step: 1082/1545, loss: 0.25257647037506104 2023-01-23 07:58:56.255045: step: 1084/1545, loss: 0.5930193662643433 2023-01-23 07:58:57.181282: step: 1086/1545, loss: 0.5995363593101501 2023-01-23 07:58:58.054004: step: 1088/1545, loss: 0.22244316339492798 2023-01-23 07:58:58.950579: step: 1090/1545, loss: 0.29292282462120056 2023-01-23 07:58:59.804956: step: 1092/1545, loss: 0.3710966110229492 2023-01-23 07:59:00.678878: step: 1094/1545, loss: 1.007489562034607 2023-01-23 07:59:01.561102: step: 1096/1545, loss: 0.3972358703613281 2023-01-23 07:59:02.431371: step: 1098/1545, loss: 0.25511133670806885 2023-01-23 07:59:03.310679: step: 1100/1545, loss: 0.3535189926624298 2023-01-23 07:59:04.179192: step: 1102/1545, loss: 0.25002723932266235 2023-01-23 07:59:05.020286: step: 1104/1545, loss: 0.2610933184623718 2023-01-23 07:59:05.859736: step: 1106/1545, loss: 0.6185325980186462 2023-01-23 07:59:06.718219: step: 1108/1545, loss: 0.8048930168151855 2023-01-23 07:59:07.585412: step: 1110/1545, loss: 0.604500949382782 2023-01-23 07:59:08.456013: step: 1112/1545, loss: 0.21386553347110748 2023-01-23 07:59:09.348485: step: 1114/1545, loss: 0.40117576718330383 2023-01-23 07:59:10.244490: step: 1116/1545, loss: 0.3033287823200226 2023-01-23 07:59:11.113916: step: 1118/1545, loss: 0.760330319404602 2023-01-23 07:59:12.025447: step: 1120/1545, loss: 0.42558687925338745 2023-01-23 07:59:12.924704: step: 1122/1545, loss: 0.3483389616012573 2023-01-23 07:59:13.764439: step: 1124/1545, loss: 0.15213772654533386 2023-01-23 07:59:14.611278: step: 1126/1545, loss: 0.14483428001403809 2023-01-23 07:59:15.484904: step: 1128/1545, loss: 2.5111947059631348 2023-01-23 07:59:16.339864: step: 1130/1545, loss: 0.24116213619709015 2023-01-23 07:59:17.218267: step: 1132/1545, loss: 0.43356168270111084 2023-01-23 07:59:18.071747: step: 1134/1545, loss: 0.22758613526821136 2023-01-23 07:59:18.912818: step: 1136/1545, loss: 0.17038710415363312 2023-01-23 07:59:19.761066: step: 1138/1545, loss: 0.20069396495819092 2023-01-23 07:59:20.649283: step: 1140/1545, loss: 0.47250211238861084 2023-01-23 07:59:21.500989: step: 1142/1545, loss: 0.339137464761734 2023-01-23 07:59:22.534148: step: 1144/1545, loss: 0.32612061500549316 2023-01-23 07:59:23.393257: step: 1146/1545, loss: 0.975673496723175 2023-01-23 07:59:24.265085: step: 1148/1545, loss: 0.3420546054840088 2023-01-23 07:59:25.164703: step: 1150/1545, loss: 0.2898653745651245 2023-01-23 07:59:26.030611: step: 1152/1545, loss: 0.5179094672203064 2023-01-23 07:59:26.872922: step: 1154/1545, loss: 0.3303718864917755 2023-01-23 07:59:27.779388: step: 1156/1545, loss: 0.3766821026802063 2023-01-23 07:59:28.697231: step: 1158/1545, loss: 0.46806302666664124 2023-01-23 07:59:29.583233: step: 1160/1545, loss: 0.46793174743652344 2023-01-23 07:59:30.491275: step: 1162/1545, loss: 0.3473378121852875 2023-01-23 07:59:31.375628: step: 1164/1545, loss: 0.3842755854129791 2023-01-23 07:59:32.230598: step: 1166/1545, loss: 1.0747607946395874 2023-01-23 07:59:33.086525: step: 1168/1545, loss: 0.2816271483898163 2023-01-23 07:59:33.974040: step: 1170/1545, loss: 0.29053160548210144 2023-01-23 07:59:34.841334: step: 1172/1545, loss: 0.2617518901824951 2023-01-23 07:59:35.735666: step: 1174/1545, loss: 4.004936218261719 2023-01-23 07:59:36.612161: step: 1176/1545, loss: 0.4584878087043762 2023-01-23 07:59:37.470923: step: 1178/1545, loss: 1.0045195817947388 2023-01-23 07:59:38.328904: step: 1180/1545, loss: 6.809510231018066 2023-01-23 07:59:39.204293: step: 1182/1545, loss: 0.49881452322006226 2023-01-23 07:59:40.105358: step: 1184/1545, loss: 0.25426769256591797 2023-01-23 07:59:40.968094: step: 1186/1545, loss: 2.079399347305298 2023-01-23 07:59:41.852744: step: 1188/1545, loss: 0.658267080783844 2023-01-23 07:59:42.755536: step: 1190/1545, loss: 0.933098554611206 2023-01-23 07:59:43.602986: step: 1192/1545, loss: 0.14982245862483978 2023-01-23 07:59:44.530165: step: 1194/1545, loss: 7.672451972961426 2023-01-23 07:59:45.411517: step: 1196/1545, loss: 2.4539754390716553 2023-01-23 07:59:46.276298: step: 1198/1545, loss: 0.30488938093185425 2023-01-23 07:59:47.183294: step: 1200/1545, loss: 0.7775976657867432 2023-01-23 07:59:48.025674: step: 1202/1545, loss: 0.5333508253097534 2023-01-23 07:59:48.858572: step: 1204/1545, loss: 0.4197847545146942 2023-01-23 07:59:49.713339: step: 1206/1545, loss: 1.0793260335922241 2023-01-23 07:59:50.638394: step: 1208/1545, loss: 0.2540283501148224 2023-01-23 07:59:51.496826: step: 1210/1545, loss: 0.07565677911043167 2023-01-23 07:59:52.364288: step: 1212/1545, loss: 0.2258690446615219 2023-01-23 07:59:53.231639: step: 1214/1545, loss: 1.172662377357483 2023-01-23 07:59:54.142372: step: 1216/1545, loss: 0.31660762429237366 2023-01-23 07:59:54.984082: step: 1218/1545, loss: 1.5505372285842896 2023-01-23 07:59:55.859091: step: 1220/1545, loss: 0.6881072521209717 2023-01-23 07:59:56.728748: step: 1222/1545, loss: 0.364967405796051 2023-01-23 07:59:57.593403: step: 1224/1545, loss: 0.35908597707748413 2023-01-23 07:59:58.472587: step: 1226/1545, loss: 0.18260402977466583 2023-01-23 07:59:59.471030: step: 1228/1545, loss: 3.584430694580078 2023-01-23 08:00:00.349548: step: 1230/1545, loss: 0.1319102644920349 2023-01-23 08:00:01.308434: step: 1232/1545, loss: 0.1644141525030136 2023-01-23 08:00:02.196048: step: 1234/1545, loss: 0.30599918961524963 2023-01-23 08:00:03.107497: step: 1236/1545, loss: 0.35782599449157715 2023-01-23 08:00:03.958833: step: 1238/1545, loss: 0.90040522813797 2023-01-23 08:00:04.886861: step: 1240/1545, loss: 1.111182451248169 2023-01-23 08:00:05.787386: step: 1242/1545, loss: 0.8413252830505371 2023-01-23 08:00:06.678570: step: 1244/1545, loss: 0.5763461589813232 2023-01-23 08:00:07.533609: step: 1246/1545, loss: 0.14090915024280548 2023-01-23 08:00:08.373117: step: 1248/1545, loss: 1.0231176614761353 2023-01-23 08:00:09.335792: step: 1250/1545, loss: 1.647229790687561 2023-01-23 08:00:10.241354: step: 1252/1545, loss: 0.7001235485076904 2023-01-23 08:00:11.123711: step: 1254/1545, loss: 1.3524940013885498 2023-01-23 08:00:12.001360: step: 1256/1545, loss: 0.842399537563324 2023-01-23 08:00:12.892558: step: 1258/1545, loss: 0.9972829222679138 2023-01-23 08:00:13.756954: step: 1260/1545, loss: 0.3444434404373169 2023-01-23 08:00:14.615626: step: 1262/1545, loss: 0.6134513020515442 2023-01-23 08:00:15.495491: step: 1264/1545, loss: 0.5744442343711853 2023-01-23 08:00:16.308496: step: 1266/1545, loss: 0.5068559646606445 2023-01-23 08:00:17.262542: step: 1268/1545, loss: 0.24501344561576843 2023-01-23 08:00:18.193881: step: 1270/1545, loss: 0.16032536327838898 2023-01-23 08:00:19.052012: step: 1272/1545, loss: 0.4467489421367645 2023-01-23 08:00:19.898711: step: 1274/1545, loss: 0.3472120463848114 2023-01-23 08:00:20.772233: step: 1276/1545, loss: 0.06445571035146713 2023-01-23 08:00:21.626460: step: 1278/1545, loss: 0.3363689184188843 2023-01-23 08:00:22.529481: step: 1280/1545, loss: 0.6440752744674683 2023-01-23 08:00:23.388007: step: 1282/1545, loss: 0.1837836354970932 2023-01-23 08:00:24.238803: step: 1284/1545, loss: 1.2689006328582764 2023-01-23 08:00:25.096164: step: 1286/1545, loss: 0.2843743860721588 2023-01-23 08:00:25.969631: step: 1288/1545, loss: 0.2488975077867508 2023-01-23 08:00:26.844503: step: 1290/1545, loss: 0.2620489001274109 2023-01-23 08:00:27.695964: step: 1292/1545, loss: 0.14215373992919922 2023-01-23 08:00:28.547225: step: 1294/1545, loss: 0.48645487427711487 2023-01-23 08:00:29.438831: step: 1296/1545, loss: 0.06372972577810287 2023-01-23 08:00:30.309733: step: 1298/1545, loss: 0.31254348158836365 2023-01-23 08:00:31.169934: step: 1300/1545, loss: 0.5267704129219055 2023-01-23 08:00:32.036236: step: 1302/1545, loss: 0.18141070008277893 2023-01-23 08:00:32.932271: step: 1304/1545, loss: 0.4040048122406006 2023-01-23 08:00:33.789051: step: 1306/1545, loss: 0.4033665060997009 2023-01-23 08:00:34.668064: step: 1308/1545, loss: 0.27257123589515686 2023-01-23 08:00:35.587299: step: 1310/1545, loss: 0.2774605453014374 2023-01-23 08:00:36.457963: step: 1312/1545, loss: 0.6135367751121521 2023-01-23 08:00:37.323879: step: 1314/1545, loss: 0.5054558515548706 2023-01-23 08:00:38.177924: step: 1316/1545, loss: 0.1854265183210373 2023-01-23 08:00:39.050715: step: 1318/1545, loss: 0.33428075909614563 2023-01-23 08:00:39.912897: step: 1320/1545, loss: 0.2072816789150238 2023-01-23 08:00:40.734831: step: 1322/1545, loss: 1.754745602607727 2023-01-23 08:00:41.597180: step: 1324/1545, loss: 0.08464325964450836 2023-01-23 08:00:42.507641: step: 1326/1545, loss: 0.25192469358444214 2023-01-23 08:00:43.405285: step: 1328/1545, loss: 0.7098214626312256 2023-01-23 08:00:44.251397: step: 1330/1545, loss: 0.3725895881652832 2023-01-23 08:00:45.151866: step: 1332/1545, loss: 0.4322948157787323 2023-01-23 08:00:46.050832: step: 1334/1545, loss: 0.28511738777160645 2023-01-23 08:00:46.896727: step: 1336/1545, loss: 0.30873408913612366 2023-01-23 08:00:47.799082: step: 1338/1545, loss: 0.40474602580070496 2023-01-23 08:00:48.669224: step: 1340/1545, loss: 0.4140719473361969 2023-01-23 08:00:49.536846: step: 1342/1545, loss: 1.967509150505066 2023-01-23 08:00:50.392883: step: 1344/1545, loss: 0.6370604634284973 2023-01-23 08:00:51.287162: step: 1346/1545, loss: 0.2987436354160309 2023-01-23 08:00:52.157002: step: 1348/1545, loss: 0.3400908410549164 2023-01-23 08:00:53.042093: step: 1350/1545, loss: 0.7348279356956482 2023-01-23 08:00:53.897268: step: 1352/1545, loss: 0.21120896935462952 2023-01-23 08:00:54.756562: step: 1354/1545, loss: 0.23557622730731964 2023-01-23 08:00:55.615467: step: 1356/1545, loss: 0.321340411901474 2023-01-23 08:00:56.533320: step: 1358/1545, loss: 0.04885168373584747 2023-01-23 08:00:57.560001: step: 1360/1545, loss: 3.1764657497406006 2023-01-23 08:00:58.477222: step: 1362/1545, loss: 0.5257919430732727 2023-01-23 08:00:59.355649: step: 1364/1545, loss: 0.5432024002075195 2023-01-23 08:01:00.337743: step: 1366/1545, loss: 0.401362806558609 2023-01-23 08:01:01.212381: step: 1368/1545, loss: 0.9258185625076294 2023-01-23 08:01:02.093547: step: 1370/1545, loss: 0.4592907726764679 2023-01-23 08:01:02.961517: step: 1372/1545, loss: 0.4227958619594574 2023-01-23 08:01:03.822662: step: 1374/1545, loss: 6.944357872009277 2023-01-23 08:01:04.693059: step: 1376/1545, loss: 0.6551820039749146 2023-01-23 08:01:05.548362: step: 1378/1545, loss: 0.22133761644363403 2023-01-23 08:01:06.391357: step: 1380/1545, loss: 0.17342200875282288 2023-01-23 08:01:07.303102: step: 1382/1545, loss: 0.06444686651229858 2023-01-23 08:01:08.230963: step: 1384/1545, loss: 0.1371002495288849 2023-01-23 08:01:09.098263: step: 1386/1545, loss: 1.9340572357177734 2023-01-23 08:01:09.956301: step: 1388/1545, loss: 0.9990019202232361 2023-01-23 08:01:10.823530: step: 1390/1545, loss: 0.4770146906375885 2023-01-23 08:01:11.716690: step: 1392/1545, loss: 0.9071723818778992 2023-01-23 08:01:12.587412: step: 1394/1545, loss: 1.2058582305908203 2023-01-23 08:01:13.468788: step: 1396/1545, loss: 0.6639576554298401 2023-01-23 08:01:14.368854: step: 1398/1545, loss: 0.9754886627197266 2023-01-23 08:01:15.232015: step: 1400/1545, loss: 0.4723021388053894 2023-01-23 08:01:16.096417: step: 1402/1545, loss: 0.27438902854919434 2023-01-23 08:01:17.009686: step: 1404/1545, loss: 0.412171870470047 2023-01-23 08:01:17.897182: step: 1406/1545, loss: 0.6654778122901917 2023-01-23 08:01:18.807976: step: 1408/1545, loss: 1.1903246641159058 2023-01-23 08:01:19.751043: step: 1410/1545, loss: 0.3179055452346802 2023-01-23 08:01:20.654039: step: 1412/1545, loss: 0.8222936391830444 2023-01-23 08:01:21.570209: step: 1414/1545, loss: 0.6644474267959595 2023-01-23 08:01:22.444862: step: 1416/1545, loss: 0.1162375956773758 2023-01-23 08:01:23.381099: step: 1418/1545, loss: 0.6393159627914429 2023-01-23 08:01:24.236032: step: 1420/1545, loss: 0.18076273798942566 2023-01-23 08:01:25.110493: step: 1422/1545, loss: 0.27635979652404785 2023-01-23 08:01:26.001860: step: 1424/1545, loss: 0.4063706696033478 2023-01-23 08:01:26.972777: step: 1426/1545, loss: 0.38397300243377686 2023-01-23 08:01:27.906529: step: 1428/1545, loss: 0.1563931107521057 2023-01-23 08:01:28.791136: step: 1430/1545, loss: 0.11762725561857224 2023-01-23 08:01:29.680254: step: 1432/1545, loss: 0.4334096312522888 2023-01-23 08:01:30.515783: step: 1434/1545, loss: 0.20092125236988068 2023-01-23 08:01:31.412582: step: 1436/1545, loss: 0.34379100799560547 2023-01-23 08:01:32.285451: step: 1438/1545, loss: 0.4149066209793091 2023-01-23 08:01:33.161833: step: 1440/1545, loss: 0.42617619037628174 2023-01-23 08:01:34.036531: step: 1442/1545, loss: 0.35504505038261414 2023-01-23 08:01:34.902394: step: 1444/1545, loss: 0.4269604980945587 2023-01-23 08:01:35.767118: step: 1446/1545, loss: 0.2101532369852066 2023-01-23 08:01:36.704370: step: 1448/1545, loss: 0.3682049810886383 2023-01-23 08:01:37.649440: step: 1450/1545, loss: 0.10956692695617676 2023-01-23 08:01:38.508672: step: 1452/1545, loss: 0.3175249993801117 2023-01-23 08:01:39.379474: step: 1454/1545, loss: 0.7767260074615479 2023-01-23 08:01:40.252139: step: 1456/1545, loss: 0.5663359761238098 2023-01-23 08:01:41.126691: step: 1458/1545, loss: 0.17585615813732147 2023-01-23 08:01:42.006805: step: 1460/1545, loss: 0.4926985800266266 2023-01-23 08:01:42.878090: step: 1462/1545, loss: 7.561738014221191 2023-01-23 08:01:43.748456: step: 1464/1545, loss: 0.4086282551288605 2023-01-23 08:01:44.622520: step: 1466/1545, loss: 0.11819774657487869 2023-01-23 08:01:45.457779: step: 1468/1545, loss: 0.36804261803627014 2023-01-23 08:01:46.368183: step: 1470/1545, loss: 4.50480318069458 2023-01-23 08:01:47.229199: step: 1472/1545, loss: 0.39879122376441956 2023-01-23 08:01:48.072699: step: 1474/1545, loss: 0.5218179225921631 2023-01-23 08:01:48.948895: step: 1476/1545, loss: 0.34901291131973267 2023-01-23 08:01:49.810280: step: 1478/1545, loss: 0.22789831459522247 2023-01-23 08:01:50.680945: step: 1480/1545, loss: 0.5614581108093262 2023-01-23 08:01:51.525643: step: 1482/1545, loss: 0.45445534586906433 2023-01-23 08:01:52.400182: step: 1484/1545, loss: 0.6947613954544067 2023-01-23 08:01:53.288420: step: 1486/1545, loss: 0.5165805816650391 2023-01-23 08:01:54.235495: step: 1488/1545, loss: 0.12821447849273682 2023-01-23 08:01:55.161851: step: 1490/1545, loss: 0.6064152121543884 2023-01-23 08:01:56.055936: step: 1492/1545, loss: 0.3262031376361847 2023-01-23 08:01:56.944013: step: 1494/1545, loss: 0.2024487853050232 2023-01-23 08:01:57.825622: step: 1496/1545, loss: 0.14175042510032654 2023-01-23 08:01:58.736230: step: 1498/1545, loss: 0.34535741806030273 2023-01-23 08:01:59.576197: step: 1500/1545, loss: 0.6192042827606201 2023-01-23 08:02:00.459898: step: 1502/1545, loss: 0.1534086912870407 2023-01-23 08:02:01.341407: step: 1504/1545, loss: 0.6670498251914978 2023-01-23 08:02:02.224964: step: 1506/1545, loss: 0.45001161098480225 2023-01-23 08:02:03.121156: step: 1508/1545, loss: 0.4501190185546875 2023-01-23 08:02:03.984132: step: 1510/1545, loss: 1.4934828281402588 2023-01-23 08:02:04.923649: step: 1512/1545, loss: 0.785094678401947 2023-01-23 08:02:05.794812: step: 1514/1545, loss: 1.7096765041351318 2023-01-23 08:02:06.692479: step: 1516/1545, loss: 0.2682779133319855 2023-01-23 08:02:07.556351: step: 1518/1545, loss: 0.34578877687454224 2023-01-23 08:02:08.432376: step: 1520/1545, loss: 0.4365029036998749 2023-01-23 08:02:09.332990: step: 1522/1545, loss: 0.7508137822151184 2023-01-23 08:02:10.237005: step: 1524/1545, loss: 0.2775323688983917 2023-01-23 08:02:11.123005: step: 1526/1545, loss: 0.6292914748191833 2023-01-23 08:02:11.994366: step: 1528/1545, loss: 0.23635649681091309 2023-01-23 08:02:12.918199: step: 1530/1545, loss: 1.3585599660873413 2023-01-23 08:02:13.926541: step: 1532/1545, loss: 0.6561755537986755 2023-01-23 08:02:14.787591: step: 1534/1545, loss: 0.2310895025730133 2023-01-23 08:02:15.708595: step: 1536/1545, loss: 1.5344330072402954 2023-01-23 08:02:16.573666: step: 1538/1545, loss: 0.35295817255973816 2023-01-23 08:02:17.434455: step: 1540/1545, loss: 0.3414914608001709 2023-01-23 08:02:18.314183: step: 1542/1545, loss: 0.7247438430786133 2023-01-23 08:02:19.300360: step: 1544/1545, loss: 0.2872445583343506 2023-01-23 08:02:20.170036: step: 1546/1545, loss: 0.525357723236084 2023-01-23 08:02:21.089159: step: 1548/1545, loss: 0.6605287194252014 2023-01-23 08:02:22.054417: step: 1550/1545, loss: 0.06832069903612137 2023-01-23 08:02:22.906103: step: 1552/1545, loss: 0.4085310697555542 2023-01-23 08:02:23.804223: step: 1554/1545, loss: 0.9033966064453125 2023-01-23 08:02:24.677960: step: 1556/1545, loss: 0.3822226822376251 2023-01-23 08:02:25.624980: step: 1558/1545, loss: 0.40453988313674927 2023-01-23 08:02:26.487539: step: 1560/1545, loss: 0.20885249972343445 2023-01-23 08:02:27.358712: step: 1562/1545, loss: 0.7199554443359375 2023-01-23 08:02:28.210621: step: 1564/1545, loss: 0.17381685972213745 2023-01-23 08:02:29.052576: step: 1566/1545, loss: 0.3668120205402374 2023-01-23 08:02:29.911383: step: 1568/1545, loss: 0.9271381497383118 2023-01-23 08:02:30.770106: step: 1570/1545, loss: 0.7585287094116211 2023-01-23 08:02:31.743639: step: 1572/1545, loss: 0.6589794158935547 2023-01-23 08:02:32.611290: step: 1574/1545, loss: 0.4067190885543823 2023-01-23 08:02:33.532770: step: 1576/1545, loss: 0.4362223744392395 2023-01-23 08:02:34.440893: step: 1578/1545, loss: 0.40715375542640686 2023-01-23 08:02:35.313561: step: 1580/1545, loss: 0.7111895680427551 2023-01-23 08:02:36.206729: step: 1582/1545, loss: 0.2463301122188568 2023-01-23 08:02:37.045759: step: 1584/1545, loss: 0.6070336103439331 2023-01-23 08:02:37.920581: step: 1586/1545, loss: 0.45170289278030396 2023-01-23 08:02:38.800685: step: 1588/1545, loss: 0.1116415336728096 2023-01-23 08:02:39.681374: step: 1590/1545, loss: 0.4030029773712158 2023-01-23 08:02:40.541104: step: 1592/1545, loss: 0.28234973549842834 2023-01-23 08:02:41.376459: step: 1594/1545, loss: 0.43447673320770264 2023-01-23 08:02:42.260840: step: 1596/1545, loss: 0.671194851398468 2023-01-23 08:02:43.127179: step: 1598/1545, loss: 0.3511171042919159 2023-01-23 08:02:43.968120: step: 1600/1545, loss: 0.4074452817440033 2023-01-23 08:02:44.842376: step: 1602/1545, loss: 0.5868220925331116 2023-01-23 08:02:45.714534: step: 1604/1545, loss: 0.23340092599391937 2023-01-23 08:02:46.546611: step: 1606/1545, loss: 0.36336183547973633 2023-01-23 08:02:47.484181: step: 1608/1545, loss: 0.7654551267623901 2023-01-23 08:02:48.391169: step: 1610/1545, loss: 0.43149229884147644 2023-01-23 08:02:49.302947: step: 1612/1545, loss: 0.8334680199623108 2023-01-23 08:02:50.172385: step: 1614/1545, loss: 0.3299385607242584 2023-01-23 08:02:51.020133: step: 1616/1545, loss: 3.1045844554901123 2023-01-23 08:02:51.922332: step: 1618/1545, loss: 0.8811644315719604 2023-01-23 08:02:52.774137: step: 1620/1545, loss: 6.999966621398926 2023-01-23 08:02:53.646368: step: 1622/1545, loss: 0.15187573432922363 2023-01-23 08:02:54.500374: step: 1624/1545, loss: 0.7957649230957031 2023-01-23 08:02:55.470970: step: 1626/1545, loss: 0.4476804733276367 2023-01-23 08:02:56.340564: step: 1628/1545, loss: 0.43275994062423706 2023-01-23 08:02:57.240207: step: 1630/1545, loss: 0.3181563913822174 2023-01-23 08:02:58.132132: step: 1632/1545, loss: 0.4555060565471649 2023-01-23 08:02:59.046870: step: 1634/1545, loss: 0.9129276871681213 2023-01-23 08:02:59.970503: step: 1636/1545, loss: 1.1693058013916016 2023-01-23 08:03:00.839090: step: 1638/1545, loss: 0.20522765815258026 2023-01-23 08:03:01.698423: step: 1640/1545, loss: 0.5600032806396484 2023-01-23 08:03:02.596662: step: 1642/1545, loss: 1.2521142959594727 2023-01-23 08:03:03.438928: step: 1644/1545, loss: 0.23376578092575073 2023-01-23 08:03:04.288532: step: 1646/1545, loss: 0.36579716205596924 2023-01-23 08:03:05.140985: step: 1648/1545, loss: 0.40746834874153137 2023-01-23 08:03:06.069209: step: 1650/1545, loss: 0.6353170275688171 2023-01-23 08:03:06.943171: step: 1652/1545, loss: 0.31785741448402405 2023-01-23 08:03:07.799002: step: 1654/1545, loss: 2.2981417179107666 2023-01-23 08:03:08.730538: step: 1656/1545, loss: 0.5657248497009277 2023-01-23 08:03:09.697433: step: 1658/1545, loss: 0.2669614851474762 2023-01-23 08:03:10.570069: step: 1660/1545, loss: 0.12298958748579025 2023-01-23 08:03:11.457514: step: 1662/1545, loss: 0.18451592326164246 2023-01-23 08:03:12.348197: step: 1664/1545, loss: 0.4526512026786804 2023-01-23 08:03:13.229647: step: 1666/1545, loss: 0.5401333570480347 2023-01-23 08:03:14.093622: step: 1668/1545, loss: 0.47518423199653625 2023-01-23 08:03:14.976341: step: 1670/1545, loss: 0.36572176218032837 2023-01-23 08:03:15.840150: step: 1672/1545, loss: 0.4639853537082672 2023-01-23 08:03:16.775555: step: 1674/1545, loss: 0.1333247274160385 2023-01-23 08:03:17.650328: step: 1676/1545, loss: 0.42510318756103516 2023-01-23 08:03:18.535438: step: 1678/1545, loss: 0.14835120737552643 2023-01-23 08:03:19.404247: step: 1680/1545, loss: 0.23021426796913147 2023-01-23 08:03:20.268405: step: 1682/1545, loss: 0.1465182602405548 2023-01-23 08:03:21.193992: step: 1684/1545, loss: 0.3232196271419525 2023-01-23 08:03:22.123581: step: 1686/1545, loss: 0.8019142746925354 2023-01-23 08:03:23.025824: step: 1688/1545, loss: 0.9921790361404419 2023-01-23 08:03:23.881846: step: 1690/1545, loss: 0.20269621908664703 2023-01-23 08:03:24.781502: step: 1692/1545, loss: 1.1889257431030273 2023-01-23 08:03:25.712021: step: 1694/1545, loss: 0.19985395669937134 2023-01-23 08:03:26.636709: step: 1696/1545, loss: 0.20145553350448608 2023-01-23 08:03:27.499098: step: 1698/1545, loss: 0.3451605439186096 2023-01-23 08:03:28.401949: step: 1700/1545, loss: 0.26948082447052 2023-01-23 08:03:29.254938: step: 1702/1545, loss: 1.7908649444580078 2023-01-23 08:03:30.137402: step: 1704/1545, loss: 0.548702597618103 2023-01-23 08:03:30.963849: step: 1706/1545, loss: 0.3226747512817383 2023-01-23 08:03:31.901061: step: 1708/1545, loss: 1.037063717842102 2023-01-23 08:03:32.837408: step: 1710/1545, loss: 0.725175142288208 2023-01-23 08:03:33.698105: step: 1712/1545, loss: 0.4671768546104431 2023-01-23 08:03:34.609289: step: 1714/1545, loss: 0.5224639177322388 2023-01-23 08:03:35.444578: step: 1716/1545, loss: 0.094324991106987 2023-01-23 08:03:36.318330: step: 1718/1545, loss: 0.3441852927207947 2023-01-23 08:03:37.223749: step: 1720/1545, loss: 0.24229846894741058 2023-01-23 08:03:38.155458: step: 1722/1545, loss: 0.4663034677505493 2023-01-23 08:03:39.039574: step: 1724/1545, loss: 0.14810706675052643 2023-01-23 08:03:39.926381: step: 1726/1545, loss: 0.26257404685020447 2023-01-23 08:03:40.786051: step: 1728/1545, loss: 0.3072377145290375 2023-01-23 08:03:41.661120: step: 1730/1545, loss: 0.4253166913986206 2023-01-23 08:03:42.525021: step: 1732/1545, loss: 0.6096609234809875 2023-01-23 08:03:43.379342: step: 1734/1545, loss: 0.33601489663124084 2023-01-23 08:03:44.289952: step: 1736/1545, loss: 0.9471601843833923 2023-01-23 08:03:45.189061: step: 1738/1545, loss: 2.4109673500061035 2023-01-23 08:03:46.048999: step: 1740/1545, loss: 0.3683886229991913 2023-01-23 08:03:46.904040: step: 1742/1545, loss: 1.5415016412734985 2023-01-23 08:03:47.741849: step: 1744/1545, loss: 3.335667133331299 2023-01-23 08:03:48.639364: step: 1746/1545, loss: 0.6500527262687683 2023-01-23 08:03:49.531944: step: 1748/1545, loss: 0.5121464729309082 2023-01-23 08:03:50.432160: step: 1750/1545, loss: 0.4590710997581482 2023-01-23 08:03:51.336247: step: 1752/1545, loss: 0.26127496361732483 2023-01-23 08:03:52.198365: step: 1754/1545, loss: 0.2654963731765747 2023-01-23 08:03:53.072566: step: 1756/1545, loss: 0.23055410385131836 2023-01-23 08:03:54.028151: step: 1758/1545, loss: 1.0463974475860596 2023-01-23 08:03:54.895625: step: 1760/1545, loss: 0.6192747950553894 2023-01-23 08:03:55.825537: step: 1762/1545, loss: 0.7550055980682373 2023-01-23 08:03:56.726004: step: 1764/1545, loss: 0.92693030834198 2023-01-23 08:03:57.632223: step: 1766/1545, loss: 0.33598726987838745 2023-01-23 08:03:58.513654: step: 1768/1545, loss: 0.07792799919843674 2023-01-23 08:03:59.404320: step: 1770/1545, loss: 0.34214767813682556 2023-01-23 08:04:00.244570: step: 1772/1545, loss: 0.4673987627029419 2023-01-23 08:04:01.114918: step: 1774/1545, loss: 0.44754141569137573 2023-01-23 08:04:01.984759: step: 1776/1545, loss: 0.6707843542098999 2023-01-23 08:04:02.848760: step: 1778/1545, loss: 0.32439351081848145 2023-01-23 08:04:03.707435: step: 1780/1545, loss: 0.2081480175256729 2023-01-23 08:04:04.615275: step: 1782/1545, loss: 0.1955837458372116 2023-01-23 08:04:05.511266: step: 1784/1545, loss: 0.2348591834306717 2023-01-23 08:04:06.368064: step: 1786/1545, loss: 0.5283893942832947 2023-01-23 08:04:07.324330: step: 1788/1545, loss: 0.5712062120437622 2023-01-23 08:04:08.181901: step: 1790/1545, loss: 0.24471673369407654 2023-01-23 08:04:09.011200: step: 1792/1545, loss: 1.3375171422958374 2023-01-23 08:04:09.883899: step: 1794/1545, loss: 0.30157244205474854 2023-01-23 08:04:10.746257: step: 1796/1545, loss: 0.4614214301109314 2023-01-23 08:04:11.736308: step: 1798/1545, loss: 0.8452558517456055 2023-01-23 08:04:12.606640: step: 1800/1545, loss: 0.2455800175666809 2023-01-23 08:04:13.467722: step: 1802/1545, loss: 0.6523135900497437 2023-01-23 08:04:14.359402: step: 1804/1545, loss: 1.2956715822219849 2023-01-23 08:04:15.208771: step: 1806/1545, loss: 0.16606661677360535 2023-01-23 08:04:16.092740: step: 1808/1545, loss: 0.11526764929294586 2023-01-23 08:04:16.941472: step: 1810/1545, loss: 0.43787214159965515 2023-01-23 08:04:17.812863: step: 1812/1545, loss: 0.8095476627349854 2023-01-23 08:04:18.649722: step: 1814/1545, loss: 0.28897812962532043 2023-01-23 08:04:19.637959: step: 1816/1545, loss: 0.24530839920043945 2023-01-23 08:04:20.541452: step: 1818/1545, loss: 0.5834485292434692 2023-01-23 08:04:21.445649: step: 1820/1545, loss: 0.6732205152511597 2023-01-23 08:04:22.402129: step: 1822/1545, loss: 0.8382012248039246 2023-01-23 08:04:23.271364: step: 1824/1545, loss: 0.6038566827774048 2023-01-23 08:04:24.141616: step: 1826/1545, loss: 0.7653955817222595 2023-01-23 08:04:25.004100: step: 1828/1545, loss: 0.3126436173915863 2023-01-23 08:04:25.829999: step: 1830/1545, loss: 0.34047913551330566 2023-01-23 08:04:26.757809: step: 1832/1545, loss: 0.14636284112930298 2023-01-23 08:04:27.614936: step: 1834/1545, loss: 0.7658228278160095 2023-01-23 08:04:28.469074: step: 1836/1545, loss: 0.47826457023620605 2023-01-23 08:04:29.398386: step: 1838/1545, loss: 0.3158186078071594 2023-01-23 08:04:30.250183: step: 1840/1545, loss: 0.8175420165061951 2023-01-23 08:04:31.136651: step: 1842/1545, loss: 0.6282866597175598 2023-01-23 08:04:32.055451: step: 1844/1545, loss: 0.6554979085922241 2023-01-23 08:04:32.950523: step: 1846/1545, loss: 1.0932871103286743 2023-01-23 08:04:33.871131: step: 1848/1545, loss: 0.3576827943325043 2023-01-23 08:04:34.853745: step: 1850/1545, loss: 0.5506663918495178 2023-01-23 08:04:35.777991: step: 1852/1545, loss: 0.29199886322021484 2023-01-23 08:04:36.691924: step: 1854/1545, loss: 0.3596583604812622 2023-01-23 08:04:37.595503: step: 1856/1545, loss: 0.7231918573379517 2023-01-23 08:04:38.452404: step: 1858/1545, loss: 0.21893340349197388 2023-01-23 08:04:39.355013: step: 1860/1545, loss: 0.3050219714641571 2023-01-23 08:04:40.262589: step: 1862/1545, loss: 2.988884449005127 2023-01-23 08:04:41.146214: step: 1864/1545, loss: 0.8797486424446106 2023-01-23 08:04:42.030745: step: 1866/1545, loss: 0.5037282109260559 2023-01-23 08:04:42.926906: step: 1868/1545, loss: 0.5991165637969971 2023-01-23 08:04:43.794647: step: 1870/1545, loss: 0.8043527603149414 2023-01-23 08:04:44.628454: step: 1872/1545, loss: 0.11379861831665039 2023-01-23 08:04:45.509208: step: 1874/1545, loss: 0.5494753122329712 2023-01-23 08:04:46.396611: step: 1876/1545, loss: 0.3827890157699585 2023-01-23 08:04:47.294355: step: 1878/1545, loss: 0.26982980966567993 2023-01-23 08:04:48.177619: step: 1880/1545, loss: 0.32305678725242615 2023-01-23 08:04:49.085293: step: 1882/1545, loss: 0.2706146240234375 2023-01-23 08:04:49.953357: step: 1884/1545, loss: 0.36159783601760864 2023-01-23 08:04:50.811768: step: 1886/1545, loss: 1.1998401880264282 2023-01-23 08:04:51.717998: step: 1888/1545, loss: 1.8305822610855103 2023-01-23 08:04:52.620283: step: 1890/1545, loss: 0.20128664374351501 2023-01-23 08:04:53.462768: step: 1892/1545, loss: 0.2954941689968109 2023-01-23 08:04:54.401750: step: 1894/1545, loss: 1.5238699913024902 2023-01-23 08:04:55.279391: step: 1896/1545, loss: 0.9974828362464905 2023-01-23 08:04:56.138663: step: 1898/1545, loss: 0.2562970519065857 2023-01-23 08:04:57.024753: step: 1900/1545, loss: 0.16619902849197388 2023-01-23 08:04:57.936311: step: 1902/1545, loss: 1.0284920930862427 2023-01-23 08:04:58.828776: step: 1904/1545, loss: 0.24952927231788635 2023-01-23 08:04:59.673984: step: 1906/1545, loss: 1.7981361150741577 2023-01-23 08:05:00.553962: step: 1908/1545, loss: 0.38498231768608093 2023-01-23 08:05:01.445463: step: 1910/1545, loss: 0.39543670415878296 2023-01-23 08:05:02.358188: step: 1912/1545, loss: 6.323651313781738 2023-01-23 08:05:03.202640: step: 1914/1545, loss: 0.3085078299045563 2023-01-23 08:05:04.091528: step: 1916/1545, loss: 0.7599089741706848 2023-01-23 08:05:05.002766: step: 1918/1545, loss: 0.3417283296585083 2023-01-23 08:05:05.895058: step: 1920/1545, loss: 0.23992234468460083 2023-01-23 08:05:06.765707: step: 1922/1545, loss: 0.5240028500556946 2023-01-23 08:05:07.637130: step: 1924/1545, loss: 0.7444913983345032 2023-01-23 08:05:08.556770: step: 1926/1545, loss: 0.3137192130088806 2023-01-23 08:05:09.413275: step: 1928/1545, loss: 1.0256149768829346 2023-01-23 08:05:10.261130: step: 1930/1545, loss: 0.6023955345153809 2023-01-23 08:05:11.118672: step: 1932/1545, loss: 0.651060163974762 2023-01-23 08:05:11.969863: step: 1934/1545, loss: 1.4994133710861206 2023-01-23 08:05:12.807971: step: 1936/1545, loss: 1.5404444932937622 2023-01-23 08:05:13.665521: step: 1938/1545, loss: 0.43042951822280884 2023-01-23 08:05:14.531735: step: 1940/1545, loss: 0.15435796976089478 2023-01-23 08:05:15.441580: step: 1942/1545, loss: 0.749308705329895 2023-01-23 08:05:16.379341: step: 1944/1545, loss: 0.6544196605682373 2023-01-23 08:05:17.333346: step: 1946/1545, loss: 0.8040733337402344 2023-01-23 08:05:18.220633: step: 1948/1545, loss: 1.4806827306747437 2023-01-23 08:05:19.101881: step: 1950/1545, loss: 0.10017047822475433 2023-01-23 08:05:19.970350: step: 1952/1545, loss: 0.2728743553161621 2023-01-23 08:05:20.838745: step: 1954/1545, loss: 1.312851071357727 2023-01-23 08:05:21.670929: step: 1956/1545, loss: 0.1615997701883316 2023-01-23 08:05:22.519662: step: 1958/1545, loss: 0.41044050455093384 2023-01-23 08:05:23.400372: step: 1960/1545, loss: 0.21077607572078705 2023-01-23 08:05:24.304366: step: 1962/1545, loss: 0.2237754464149475 2023-01-23 08:05:25.175702: step: 1964/1545, loss: 0.5171796083450317 2023-01-23 08:05:26.075276: step: 1966/1545, loss: 0.17377927899360657 2023-01-23 08:05:26.928516: step: 1968/1545, loss: 0.45206305384635925 2023-01-23 08:05:27.818408: step: 1970/1545, loss: 0.5368967652320862 2023-01-23 08:05:28.689497: step: 1972/1545, loss: 0.4272622764110565 2023-01-23 08:05:29.564049: step: 1974/1545, loss: 0.5855303406715393 2023-01-23 08:05:30.418003: step: 1976/1545, loss: 0.5203524231910706 2023-01-23 08:05:31.285063: step: 1978/1545, loss: 0.39201048016548157 2023-01-23 08:05:32.155662: step: 1980/1545, loss: 0.23980259895324707 2023-01-23 08:05:33.026382: step: 1982/1545, loss: 0.7129153609275818 2023-01-23 08:05:33.967977: step: 1984/1545, loss: 0.49240171909332275 2023-01-23 08:05:34.827856: step: 1986/1545, loss: 0.7000752687454224 2023-01-23 08:05:35.692372: step: 1988/1545, loss: 0.23825310170650482 2023-01-23 08:05:36.724654: step: 1990/1545, loss: 0.41700586676597595 2023-01-23 08:05:37.643625: step: 1992/1545, loss: 0.3441615402698517 2023-01-23 08:05:38.500375: step: 1994/1545, loss: 0.7144019603729248 2023-01-23 08:05:39.423547: step: 1996/1545, loss: 0.25653061270713806 2023-01-23 08:05:40.313541: step: 1998/1545, loss: 0.5615672469139099 2023-01-23 08:05:41.164047: step: 2000/1545, loss: 0.7433584332466125 2023-01-23 08:05:42.035459: step: 2002/1545, loss: 1.3300751447677612 2023-01-23 08:05:42.934536: step: 2004/1545, loss: 0.8194835782051086 2023-01-23 08:05:43.829754: step: 2006/1545, loss: 0.21718019247055054 2023-01-23 08:05:44.768963: step: 2008/1545, loss: 0.21691691875457764 2023-01-23 08:05:45.690292: step: 2010/1545, loss: 0.21842560172080994 2023-01-23 08:05:46.532675: step: 2012/1545, loss: 0.3559845983982086 2023-01-23 08:05:47.405263: step: 2014/1545, loss: 0.643208920955658 2023-01-23 08:05:48.292168: step: 2016/1545, loss: 0.26401230692863464 2023-01-23 08:05:49.205106: step: 2018/1545, loss: 0.43305349349975586 2023-01-23 08:05:50.113748: step: 2020/1545, loss: 0.28167375922203064 2023-01-23 08:05:50.967380: step: 2022/1545, loss: 0.22604498267173767 2023-01-23 08:05:51.861245: step: 2024/1545, loss: 0.4742332398891449 2023-01-23 08:05:52.769324: step: 2026/1545, loss: 0.4920612871646881 2023-01-23 08:05:53.652981: step: 2028/1545, loss: 0.4272274672985077 2023-01-23 08:05:54.535506: step: 2030/1545, loss: 0.4363206923007965 2023-01-23 08:05:55.416853: step: 2032/1545, loss: 0.6387261152267456 2023-01-23 08:05:56.296812: step: 2034/1545, loss: 0.8461610078811646 2023-01-23 08:05:57.179751: step: 2036/1545, loss: 0.5480588674545288 2023-01-23 08:05:58.148834: step: 2038/1545, loss: 0.6145603656768799 2023-01-23 08:05:59.026625: step: 2040/1545, loss: 0.13860611617565155 2023-01-23 08:05:59.874517: step: 2042/1545, loss: 0.6433369517326355 2023-01-23 08:06:00.808094: step: 2044/1545, loss: 0.5293874144554138 2023-01-23 08:06:01.662083: step: 2046/1545, loss: 0.5226569771766663 2023-01-23 08:06:02.574142: step: 2048/1545, loss: 0.5913416743278503 2023-01-23 08:06:03.421805: step: 2050/1545, loss: 0.5468235015869141 2023-01-23 08:06:04.317524: step: 2052/1545, loss: 0.4776953458786011 2023-01-23 08:06:05.268444: step: 2054/1545, loss: 0.7238322496414185 2023-01-23 08:06:06.079426: step: 2056/1545, loss: 1.1389862298965454 2023-01-23 08:06:06.947134: step: 2058/1545, loss: 0.13650675117969513 2023-01-23 08:06:07.826074: step: 2060/1545, loss: 0.6674661636352539 2023-01-23 08:06:08.681704: step: 2062/1545, loss: 0.9922289252281189 2023-01-23 08:06:09.637981: step: 2064/1545, loss: 0.4139391779899597 2023-01-23 08:06:10.480797: step: 2066/1545, loss: 2.174936294555664 2023-01-23 08:06:11.364863: step: 2068/1545, loss: 0.4032418429851532 2023-01-23 08:06:12.259043: step: 2070/1545, loss: 0.38096511363983154 2023-01-23 08:06:13.120531: step: 2072/1545, loss: 0.8107117414474487 2023-01-23 08:06:14.004503: step: 2074/1545, loss: 0.43979912996292114 2023-01-23 08:06:14.892163: step: 2076/1545, loss: 0.22352153062820435 2023-01-23 08:06:15.832845: step: 2078/1545, loss: 0.05845778062939644 2023-01-23 08:06:16.714839: step: 2080/1545, loss: 0.7667948603630066 2023-01-23 08:06:17.588637: step: 2082/1545, loss: 0.26814302802085876 2023-01-23 08:06:18.495074: step: 2084/1545, loss: 0.3240758180618286 2023-01-23 08:06:19.365501: step: 2086/1545, loss: 0.08961416035890579 2023-01-23 08:06:20.256179: step: 2088/1545, loss: 0.4747132658958435 2023-01-23 08:06:21.147978: step: 2090/1545, loss: 0.5024534463882446 2023-01-23 08:06:22.009485: step: 2092/1545, loss: 0.6317158341407776 2023-01-23 08:06:22.877721: step: 2094/1545, loss: 1.4984846115112305 2023-01-23 08:06:23.757881: step: 2096/1545, loss: 0.5795938372612 2023-01-23 08:06:24.640626: step: 2098/1545, loss: 0.4707084596157074 2023-01-23 08:06:25.492677: step: 2100/1545, loss: 1.5686734914779663 2023-01-23 08:06:26.467014: step: 2102/1545, loss: 0.7553789019584656 2023-01-23 08:06:27.368896: step: 2104/1545, loss: 0.3677537143230438 2023-01-23 08:06:28.280107: step: 2106/1545, loss: 0.8038370609283447 2023-01-23 08:06:29.212529: step: 2108/1545, loss: 0.5161668062210083 2023-01-23 08:06:30.065017: step: 2110/1545, loss: 0.729657769203186 2023-01-23 08:06:30.991512: step: 2112/1545, loss: 0.3679538667201996 2023-01-23 08:06:31.868929: step: 2114/1545, loss: 0.5155043005943298 2023-01-23 08:06:32.787868: step: 2116/1545, loss: 0.5819834470748901 2023-01-23 08:06:33.666251: step: 2118/1545, loss: 0.2159772664308548 2023-01-23 08:06:34.518051: step: 2120/1545, loss: 0.7571650743484497 2023-01-23 08:06:35.410586: step: 2122/1545, loss: 1.0195409059524536 2023-01-23 08:06:36.284400: step: 2124/1545, loss: 0.3198526203632355 2023-01-23 08:06:37.126435: step: 2126/1545, loss: 0.6216602325439453 2023-01-23 08:06:37.965699: step: 2128/1545, loss: 0.7639923691749573 2023-01-23 08:06:38.847744: step: 2130/1545, loss: 0.5169540047645569 2023-01-23 08:06:39.696478: step: 2132/1545, loss: 0.35278114676475525 2023-01-23 08:06:40.610579: step: 2134/1545, loss: 0.4231337904930115 2023-01-23 08:06:41.501869: step: 2136/1545, loss: 0.4725189208984375 2023-01-23 08:06:42.368280: step: 2138/1545, loss: 0.5322712659835815 2023-01-23 08:06:43.260967: step: 2140/1545, loss: 0.4270559251308441 2023-01-23 08:06:44.124704: step: 2142/1545, loss: 0.2993146479129791 2023-01-23 08:06:44.984143: step: 2144/1545, loss: 1.0722299814224243 2023-01-23 08:06:45.875557: step: 2146/1545, loss: 0.2772303521633148 2023-01-23 08:06:46.768121: step: 2148/1545, loss: 0.44186246395111084 2023-01-23 08:06:47.627396: step: 2150/1545, loss: 0.867034375667572 2023-01-23 08:06:48.472638: step: 2152/1545, loss: 0.4065079987049103 2023-01-23 08:06:49.345397: step: 2154/1545, loss: 0.7903989553451538 2023-01-23 08:06:50.231931: step: 2156/1545, loss: 0.24230077862739563 2023-01-23 08:06:51.087520: step: 2158/1545, loss: 0.30352458357810974 2023-01-23 08:06:51.973762: step: 2160/1545, loss: 1.0369497537612915 2023-01-23 08:06:52.882655: step: 2162/1545, loss: 0.3519015312194824 2023-01-23 08:06:53.738494: step: 2164/1545, loss: 0.09210123866796494 2023-01-23 08:06:54.600460: step: 2166/1545, loss: 0.3280676305294037 2023-01-23 08:06:55.563895: step: 2168/1545, loss: 1.0266834497451782 2023-01-23 08:06:56.512896: step: 2170/1545, loss: 0.5832578539848328 2023-01-23 08:06:57.454291: step: 2172/1545, loss: 0.3740251064300537 2023-01-23 08:06:58.358952: step: 2174/1545, loss: 0.25829461216926575 2023-01-23 08:06:59.267451: step: 2176/1545, loss: 0.2920958995819092 2023-01-23 08:07:00.129218: step: 2178/1545, loss: 0.24920521676540375 2023-01-23 08:07:00.987620: step: 2180/1545, loss: 0.20325669646263123 2023-01-23 08:07:01.853175: step: 2182/1545, loss: 0.871116578578949 2023-01-23 08:07:02.729887: step: 2184/1545, loss: 3.2786061763763428 2023-01-23 08:07:03.612359: step: 2186/1545, loss: 0.32483649253845215 2023-01-23 08:07:04.464876: step: 2188/1545, loss: 0.1330711543560028 2023-01-23 08:07:05.353672: step: 2190/1545, loss: 0.8427660465240479 2023-01-23 08:07:06.226088: step: 2192/1545, loss: 0.546819806098938 2023-01-23 08:07:07.075615: step: 2194/1545, loss: 0.19076219201087952 2023-01-23 08:07:07.929347: step: 2196/1545, loss: 0.3735845386981964 2023-01-23 08:07:08.832361: step: 2198/1545, loss: 0.9547893404960632 2023-01-23 08:07:09.703811: step: 2200/1545, loss: 0.20262357592582703 2023-01-23 08:07:10.618198: step: 2202/1545, loss: 4.1498823165893555 2023-01-23 08:07:11.479042: step: 2204/1545, loss: 0.5137289762496948 2023-01-23 08:07:12.315472: step: 2206/1545, loss: 0.21542717516422272 2023-01-23 08:07:13.162651: step: 2208/1545, loss: 0.9321954846382141 2023-01-23 08:07:14.069489: step: 2210/1545, loss: 0.5949555039405823 2023-01-23 08:07:14.947924: step: 2212/1545, loss: 0.6952348351478577 2023-01-23 08:07:15.837682: step: 2214/1545, loss: 0.6347119808197021 2023-01-23 08:07:16.698529: step: 2216/1545, loss: 3.0875658988952637 2023-01-23 08:07:17.551200: step: 2218/1545, loss: 1.7193564176559448 2023-01-23 08:07:18.437127: step: 2220/1545, loss: 0.3484136462211609 2023-01-23 08:07:19.319296: step: 2222/1545, loss: 0.7811133861541748 2023-01-23 08:07:20.221966: step: 2224/1545, loss: 0.2981072962284088 2023-01-23 08:07:21.132152: step: 2226/1545, loss: 0.5067556500434875 2023-01-23 08:07:22.014216: step: 2228/1545, loss: 0.2204836755990982 2023-01-23 08:07:22.883741: step: 2230/1545, loss: 0.47976580262184143 2023-01-23 08:07:23.804113: step: 2232/1545, loss: 0.37279778718948364 2023-01-23 08:07:24.703293: step: 2234/1545, loss: 0.2206306755542755 2023-01-23 08:07:25.617938: step: 2236/1545, loss: 0.2730996906757355 2023-01-23 08:07:26.498556: step: 2238/1545, loss: 0.583288311958313 2023-01-23 08:07:27.358118: step: 2240/1545, loss: 0.9316550493240356 2023-01-23 08:07:28.243636: step: 2242/1545, loss: 1.177998423576355 2023-01-23 08:07:29.116173: step: 2244/1545, loss: 0.270785391330719 2023-01-23 08:07:30.032017: step: 2246/1545, loss: 0.4687075912952423 2023-01-23 08:07:30.930205: step: 2248/1545, loss: 0.2320677936077118 2023-01-23 08:07:31.795068: step: 2250/1545, loss: 0.42443686723709106 2023-01-23 08:07:32.687330: step: 2252/1545, loss: 0.27332934737205505 2023-01-23 08:07:33.518529: step: 2254/1545, loss: 0.416520893573761 2023-01-23 08:07:34.374271: step: 2256/1545, loss: 0.48401832580566406 2023-01-23 08:07:35.257462: step: 2258/1545, loss: 0.9650379419326782 2023-01-23 08:07:36.194572: step: 2260/1545, loss: 0.41207921504974365 2023-01-23 08:07:37.055347: step: 2262/1545, loss: 0.2323266714811325 2023-01-23 08:07:37.931902: step: 2264/1545, loss: 0.5554035902023315 2023-01-23 08:07:38.890991: step: 2266/1545, loss: 0.3275366723537445 2023-01-23 08:07:39.735637: step: 2268/1545, loss: 0.18929608166217804 2023-01-23 08:07:40.700797: step: 2270/1545, loss: 0.3940448760986328 2023-01-23 08:07:41.568500: step: 2272/1545, loss: 0.2023790329694748 2023-01-23 08:07:42.478946: step: 2274/1545, loss: 0.49425050616264343 2023-01-23 08:07:43.323412: step: 2276/1545, loss: 0.25710535049438477 2023-01-23 08:07:44.171031: step: 2278/1545, loss: 0.21154600381851196 2023-01-23 08:07:45.055008: step: 2280/1545, loss: 1.1944653987884521 2023-01-23 08:07:45.900997: step: 2282/1545, loss: 0.2201235592365265 2023-01-23 08:07:46.771275: step: 2284/1545, loss: 0.6887783408164978 2023-01-23 08:07:47.702782: step: 2286/1545, loss: 0.3986945152282715 2023-01-23 08:07:48.587806: step: 2288/1545, loss: 0.44515231251716614 2023-01-23 08:07:49.464087: step: 2290/1545, loss: 1.2844269275665283 2023-01-23 08:07:50.377436: step: 2292/1545, loss: 0.28705132007598877 2023-01-23 08:07:51.310931: step: 2294/1545, loss: 0.3460872769355774 2023-01-23 08:07:52.196564: step: 2296/1545, loss: 2.740001916885376 2023-01-23 08:07:53.062150: step: 2298/1545, loss: 0.4055355191230774 2023-01-23 08:07:53.927408: step: 2300/1545, loss: 0.7426335215568542 2023-01-23 08:07:54.820157: step: 2302/1545, loss: 0.5747886896133423 2023-01-23 08:07:55.662049: step: 2304/1545, loss: 1.139530897140503 2023-01-23 08:07:56.524473: step: 2306/1545, loss: 0.2995152473449707 2023-01-23 08:07:57.413557: step: 2308/1545, loss: 0.4015512466430664 2023-01-23 08:07:58.302422: step: 2310/1545, loss: 0.43876194953918457 2023-01-23 08:07:59.199698: step: 2312/1545, loss: 0.334739089012146 2023-01-23 08:08:00.100982: step: 2314/1545, loss: 0.8957246541976929 2023-01-23 08:08:00.971526: step: 2316/1545, loss: 0.31700676679611206 2023-01-23 08:08:01.956378: step: 2318/1545, loss: 0.23444023728370667 2023-01-23 08:08:02.803115: step: 2320/1545, loss: 0.31014129519462585 2023-01-23 08:08:03.676702: step: 2322/1545, loss: 0.6600484848022461 2023-01-23 08:08:04.572713: step: 2324/1545, loss: 0.4027738571166992 2023-01-23 08:08:05.520484: step: 2326/1545, loss: 0.5201845169067383 2023-01-23 08:08:06.406942: step: 2328/1545, loss: 0.24576149880886078 2023-01-23 08:08:07.276354: step: 2330/1545, loss: 0.7079619765281677 2023-01-23 08:08:08.173847: step: 2332/1545, loss: 0.6681681275367737 2023-01-23 08:08:09.035317: step: 2334/1545, loss: 0.3501468896865845 2023-01-23 08:08:09.890342: step: 2336/1545, loss: 2.7743961811065674 2023-01-23 08:08:10.838667: step: 2338/1545, loss: 0.19110415875911713 2023-01-23 08:08:11.728821: step: 2340/1545, loss: 0.48358285427093506 2023-01-23 08:08:12.592469: step: 2342/1545, loss: 0.2154185175895691 2023-01-23 08:08:13.461887: step: 2344/1545, loss: 3.778259038925171 2023-01-23 08:08:14.345348: step: 2346/1545, loss: 0.3519861400127411 2023-01-23 08:08:15.237723: step: 2348/1545, loss: 0.23283907771110535 2023-01-23 08:08:16.124356: step: 2350/1545, loss: 0.36112919449806213 2023-01-23 08:08:17.027697: step: 2352/1545, loss: 0.29284852743148804 2023-01-23 08:08:17.902983: step: 2354/1545, loss: 0.1821126639842987 2023-01-23 08:08:18.763361: step: 2356/1545, loss: 0.17749710381031036 2023-01-23 08:08:19.680093: step: 2358/1545, loss: 0.555435836315155 2023-01-23 08:08:20.617444: step: 2360/1545, loss: 0.699608325958252 2023-01-23 08:08:21.547111: step: 2362/1545, loss: 1.2772578001022339 2023-01-23 08:08:22.414934: step: 2364/1545, loss: 0.8084828853607178 2023-01-23 08:08:23.306240: step: 2366/1545, loss: 0.43507909774780273 2023-01-23 08:08:24.197007: step: 2368/1545, loss: 0.8847543597221375 2023-01-23 08:08:25.101080: step: 2370/1545, loss: 0.5091647505760193 2023-01-23 08:08:26.044190: step: 2372/1545, loss: 1.0326002836227417 2023-01-23 08:08:27.107795: step: 2374/1545, loss: 2.9561524391174316 2023-01-23 08:08:27.988890: step: 2376/1545, loss: 0.38539791107177734 2023-01-23 08:08:28.843300: step: 2378/1545, loss: 0.404249906539917 2023-01-23 08:08:29.675729: step: 2380/1545, loss: 0.32002320885658264 2023-01-23 08:08:30.545124: step: 2382/1545, loss: 0.31335383653640747 2023-01-23 08:08:31.448005: step: 2384/1545, loss: 0.3315211236476898 2023-01-23 08:08:32.406070: step: 2386/1545, loss: 0.1875743716955185 2023-01-23 08:08:33.292110: step: 2388/1545, loss: 0.21017035841941833 2023-01-23 08:08:34.173648: step: 2390/1545, loss: 0.2890740633010864 2023-01-23 08:08:35.048212: step: 2392/1545, loss: 0.45666152238845825 2023-01-23 08:08:35.936731: step: 2394/1545, loss: 0.41205894947052 2023-01-23 08:08:36.841080: step: 2396/1545, loss: 0.6684973835945129 2023-01-23 08:08:37.675124: step: 2398/1545, loss: 0.32786616683006287 2023-01-23 08:08:38.544849: step: 2400/1545, loss: 0.7240588068962097 2023-01-23 08:08:39.428952: step: 2402/1545, loss: 0.6007377505302429 2023-01-23 08:08:40.288146: step: 2404/1545, loss: 0.36655017733573914 2023-01-23 08:08:41.159876: step: 2406/1545, loss: 1.2800812721252441 2023-01-23 08:08:42.058787: step: 2408/1545, loss: 0.6400125622749329 2023-01-23 08:08:42.933167: step: 2410/1545, loss: 0.11123257875442505 2023-01-23 08:08:43.851105: step: 2412/1545, loss: 0.3103351593017578 2023-01-23 08:08:44.692289: step: 2414/1545, loss: 0.44809794425964355 2023-01-23 08:08:45.575782: step: 2416/1545, loss: 1.1548357009887695 2023-01-23 08:08:46.460865: step: 2418/1545, loss: 0.5127334594726562 2023-01-23 08:08:47.319968: step: 2420/1545, loss: 0.7914659976959229 2023-01-23 08:08:48.243629: step: 2422/1545, loss: 0.583675742149353 2023-01-23 08:08:49.124953: step: 2424/1545, loss: 0.2613760828971863 2023-01-23 08:08:50.033387: step: 2426/1545, loss: 0.8319109082221985 2023-01-23 08:08:50.933889: step: 2428/1545, loss: 0.4364238679409027 2023-01-23 08:08:51.805455: step: 2430/1545, loss: 0.6028064489364624 2023-01-23 08:08:52.668214: step: 2432/1545, loss: 0.3847280740737915 2023-01-23 08:08:53.606448: step: 2434/1545, loss: 0.5303886532783508 2023-01-23 08:08:54.484107: step: 2436/1545, loss: 0.5228855609893799 2023-01-23 08:08:55.353803: step: 2438/1545, loss: 1.5088729858398438 2023-01-23 08:08:56.215978: step: 2440/1545, loss: 0.32076603174209595 2023-01-23 08:08:57.088137: step: 2442/1545, loss: 0.6925079822540283 2023-01-23 08:08:57.948093: step: 2444/1545, loss: 0.4920763373374939 2023-01-23 08:08:58.830336: step: 2446/1545, loss: 0.4989759624004364 2023-01-23 08:08:59.714143: step: 2448/1545, loss: 0.6024590730667114 2023-01-23 08:09:00.554349: step: 2450/1545, loss: 0.9968345761299133 2023-01-23 08:09:01.410736: step: 2452/1545, loss: 0.28575244545936584 2023-01-23 08:09:02.291519: step: 2454/1545, loss: 0.29443758726119995 2023-01-23 08:09:03.169679: step: 2456/1545, loss: 0.2523357570171356 2023-01-23 08:09:04.053400: step: 2458/1545, loss: 0.6780051589012146 2023-01-23 08:09:04.914045: step: 2460/1545, loss: 0.457629531621933 2023-01-23 08:09:05.762708: step: 2462/1545, loss: 0.28060823678970337 2023-01-23 08:09:06.623397: step: 2464/1545, loss: 0.5705301761627197 2023-01-23 08:09:07.517397: step: 2466/1545, loss: 0.2985728979110718 2023-01-23 08:09:08.452113: step: 2468/1545, loss: 0.6792222857475281 2023-01-23 08:09:09.367814: step: 2470/1545, loss: 0.6967118382453918 2023-01-23 08:09:10.287675: step: 2472/1545, loss: 0.14412294328212738 2023-01-23 08:09:11.225321: step: 2474/1545, loss: 0.27929437160491943 2023-01-23 08:09:12.127412: step: 2476/1545, loss: 0.34235116839408875 2023-01-23 08:09:12.966942: step: 2478/1545, loss: 0.3210333287715912 2023-01-23 08:09:13.834263: step: 2480/1545, loss: 0.44670921564102173 2023-01-23 08:09:14.717239: step: 2482/1545, loss: 0.21822993457317352 2023-01-23 08:09:15.609481: step: 2484/1545, loss: 0.6252852082252502 2023-01-23 08:09:16.520121: step: 2486/1545, loss: 0.3080562353134155 2023-01-23 08:09:17.452718: step: 2488/1545, loss: 0.7946759462356567 2023-01-23 08:09:18.338465: step: 2490/1545, loss: 0.38149213790893555 2023-01-23 08:09:19.239381: step: 2492/1545, loss: 0.7087546586990356 2023-01-23 08:09:20.185902: step: 2494/1545, loss: 0.6126781702041626 2023-01-23 08:09:21.154105: step: 2496/1545, loss: 1.1875094175338745 2023-01-23 08:09:22.071357: step: 2498/1545, loss: 0.6619083285331726 2023-01-23 08:09:22.931622: step: 2500/1545, loss: 0.31270068883895874 2023-01-23 08:09:23.869632: step: 2502/1545, loss: 1.1876368522644043 2023-01-23 08:09:24.801112: step: 2504/1545, loss: 2.257437229156494 2023-01-23 08:09:25.701113: step: 2506/1545, loss: 0.12710028886795044 2023-01-23 08:09:26.562760: step: 2508/1545, loss: 0.07582174241542816 2023-01-23 08:09:27.468973: step: 2510/1545, loss: 0.8334082961082458 2023-01-23 08:09:28.381147: step: 2512/1545, loss: 0.5614126324653625 2023-01-23 08:09:29.322618: step: 2514/1545, loss: 0.31813105940818787 2023-01-23 08:09:30.274474: step: 2516/1545, loss: 0.6149862408638 2023-01-23 08:09:31.180617: step: 2518/1545, loss: 0.15549370646476746 2023-01-23 08:09:32.035720: step: 2520/1545, loss: 0.22288839519023895 2023-01-23 08:09:32.887368: step: 2522/1545, loss: 0.6340639591217041 2023-01-23 08:09:33.780873: step: 2524/1545, loss: 0.6020305752754211 2023-01-23 08:09:34.701220: step: 2526/1545, loss: 0.17555256187915802 2023-01-23 08:09:35.607593: step: 2528/1545, loss: 0.18710553646087646 2023-01-23 08:09:36.474755: step: 2530/1545, loss: 0.27377140522003174 2023-01-23 08:09:37.378070: step: 2532/1545, loss: 0.43925613164901733 2023-01-23 08:09:38.258065: step: 2534/1545, loss: 0.22649486362934113 2023-01-23 08:09:39.139706: step: 2536/1545, loss: 0.2564629018306732 2023-01-23 08:09:40.029196: step: 2538/1545, loss: 0.429670125246048 2023-01-23 08:09:40.893298: step: 2540/1545, loss: 0.4796021580696106 2023-01-23 08:09:41.751802: step: 2542/1545, loss: 0.679962694644928 2023-01-23 08:09:42.592162: step: 2544/1545, loss: 0.30579692125320435 2023-01-23 08:09:43.451459: step: 2546/1545, loss: 0.40624091029167175 2023-01-23 08:09:44.318500: step: 2548/1545, loss: 0.5148165822029114 2023-01-23 08:09:45.234131: step: 2550/1545, loss: 0.31119295954704285 2023-01-23 08:09:46.097684: step: 2552/1545, loss: 0.2967483103275299 2023-01-23 08:09:46.973969: step: 2554/1545, loss: 0.499645859003067 2023-01-23 08:09:47.885555: step: 2556/1545, loss: 0.6696829199790955 2023-01-23 08:09:48.780995: step: 2558/1545, loss: 0.45885682106018066 2023-01-23 08:09:49.690009: step: 2560/1545, loss: 0.2150074988603592 2023-01-23 08:09:50.591738: step: 2562/1545, loss: 0.24877354502677917 2023-01-23 08:09:51.468396: step: 2564/1545, loss: 0.805320143699646 2023-01-23 08:09:52.341214: step: 2566/1545, loss: 0.16212129592895508 2023-01-23 08:09:53.283086: step: 2568/1545, loss: 2.5771358013153076 2023-01-23 08:09:54.153300: step: 2570/1545, loss: 0.07154956459999084 2023-01-23 08:09:55.048996: step: 2572/1545, loss: 0.604378879070282 2023-01-23 08:09:55.958944: step: 2574/1545, loss: 0.3856963813304901 2023-01-23 08:09:56.843350: step: 2576/1545, loss: 1.3072415590286255 2023-01-23 08:09:57.720269: step: 2578/1545, loss: 0.15698665380477905 2023-01-23 08:09:58.582635: step: 2580/1545, loss: 0.22075046598911285 2023-01-23 08:09:59.458844: step: 2582/1545, loss: 0.368988960981369 2023-01-23 08:10:00.388596: step: 2584/1545, loss: 0.295969158411026 2023-01-23 08:10:01.240869: step: 2586/1545, loss: 0.5449420809745789 2023-01-23 08:10:02.107461: step: 2588/1545, loss: 0.39022693037986755 2023-01-23 08:10:02.935816: step: 2590/1545, loss: 0.49704110622406006 2023-01-23 08:10:03.819129: step: 2592/1545, loss: 0.1486627161502838 2023-01-23 08:10:04.687330: step: 2594/1545, loss: 0.6309340596199036 2023-01-23 08:10:05.542537: step: 2596/1545, loss: 0.2849844694137573 2023-01-23 08:10:06.432022: step: 2598/1545, loss: 0.14137886464595795 2023-01-23 08:10:07.324328: step: 2600/1545, loss: 0.49827146530151367 2023-01-23 08:10:08.213555: step: 2602/1545, loss: 0.6454100608825684 2023-01-23 08:10:09.043843: step: 2604/1545, loss: 0.908422589302063 2023-01-23 08:10:09.889658: step: 2606/1545, loss: 0.22018299996852875 2023-01-23 08:10:10.792429: step: 2608/1545, loss: 0.5179662108421326 2023-01-23 08:10:11.716591: step: 2610/1545, loss: 3.1012074947357178 2023-01-23 08:10:12.605922: step: 2612/1545, loss: 0.390948623418808 2023-01-23 08:10:13.467017: step: 2614/1545, loss: 0.8401234149932861 2023-01-23 08:10:14.293589: step: 2616/1545, loss: 1.0921838283538818 2023-01-23 08:10:15.189466: step: 2618/1545, loss: 0.8931487798690796 2023-01-23 08:10:16.040724: step: 2620/1545, loss: 2.416810989379883 2023-01-23 08:10:16.925433: step: 2622/1545, loss: 0.869184136390686 2023-01-23 08:10:17.809988: step: 2624/1545, loss: 0.36496180295944214 2023-01-23 08:10:18.672561: step: 2626/1545, loss: 0.3313943147659302 2023-01-23 08:10:19.567770: step: 2628/1545, loss: 0.2155396044254303 2023-01-23 08:10:20.430906: step: 2630/1545, loss: 0.24502074718475342 2023-01-23 08:10:21.306619: step: 2632/1545, loss: 0.2811429798603058 2023-01-23 08:10:22.174773: step: 2634/1545, loss: 0.8476285338401794 2023-01-23 08:10:23.059303: step: 2636/1545, loss: 0.826545000076294 2023-01-23 08:10:23.944335: step: 2638/1545, loss: 0.19579185545444489 2023-01-23 08:10:24.863999: step: 2640/1545, loss: 0.24082690477371216 2023-01-23 08:10:25.727276: step: 2642/1545, loss: 1.9759719371795654 2023-01-23 08:10:26.598142: step: 2644/1545, loss: 0.9096161127090454 2023-01-23 08:10:27.508238: step: 2646/1545, loss: 0.8888848423957825 2023-01-23 08:10:28.405926: step: 2648/1545, loss: 0.18425466120243073 2023-01-23 08:10:29.321205: step: 2650/1545, loss: 1.6749422550201416 2023-01-23 08:10:30.191218: step: 2652/1545, loss: 0.2026849389076233 2023-01-23 08:10:31.091822: step: 2654/1545, loss: 0.3088648021221161 2023-01-23 08:10:31.993278: step: 2656/1545, loss: 2.0218231678009033 2023-01-23 08:10:32.862091: step: 2658/1545, loss: 0.5876920223236084 2023-01-23 08:10:33.744072: step: 2660/1545, loss: 0.3472779393196106 2023-01-23 08:10:34.622933: step: 2662/1545, loss: 0.26362961530685425 2023-01-23 08:10:35.522836: step: 2664/1545, loss: 6.862603664398193 2023-01-23 08:10:36.445704: step: 2666/1545, loss: 0.39922329783439636 2023-01-23 08:10:37.300491: step: 2668/1545, loss: 0.3392201364040375 2023-01-23 08:10:38.161505: step: 2670/1545, loss: 0.34689101576805115 2023-01-23 08:10:39.059168: step: 2672/1545, loss: 0.7020685076713562 2023-01-23 08:10:39.983924: step: 2674/1545, loss: 0.29529500007629395 2023-01-23 08:10:40.874894: step: 2676/1545, loss: 0.5760347247123718 2023-01-23 08:10:41.810140: step: 2678/1545, loss: 0.33697786927223206 2023-01-23 08:10:42.666478: step: 2680/1545, loss: 0.4609076678752899 2023-01-23 08:10:43.524061: step: 2682/1545, loss: 0.45856526494026184 2023-01-23 08:10:44.414567: step: 2684/1545, loss: 0.496099591255188 2023-01-23 08:10:45.287471: step: 2686/1545, loss: 0.432359904050827 2023-01-23 08:10:46.135923: step: 2688/1545, loss: 0.6763859987258911 2023-01-23 08:10:47.001283: step: 2690/1545, loss: 1.3465594053268433 2023-01-23 08:10:47.875263: step: 2692/1545, loss: 0.4135010540485382 2023-01-23 08:10:48.801814: step: 2694/1545, loss: 0.6633883714675903 2023-01-23 08:10:49.684079: step: 2696/1545, loss: 0.5184212327003479 2023-01-23 08:10:50.556240: step: 2698/1545, loss: 0.2369467169046402 2023-01-23 08:10:51.449234: step: 2700/1545, loss: 0.33310428261756897 2023-01-23 08:10:52.311394: step: 2702/1545, loss: 0.21409553289413452 2023-01-23 08:10:53.208978: step: 2704/1545, loss: 0.4564021825790405 2023-01-23 08:10:54.063249: step: 2706/1545, loss: 0.6696026921272278 2023-01-23 08:10:54.961972: step: 2708/1545, loss: 0.8135010004043579 2023-01-23 08:10:55.832228: step: 2710/1545, loss: 0.48704081773757935 2023-01-23 08:10:56.699939: step: 2712/1545, loss: 0.231070414185524 2023-01-23 08:10:57.596629: step: 2714/1545, loss: 0.8940271139144897 2023-01-23 08:10:58.457068: step: 2716/1545, loss: 0.32340654730796814 2023-01-23 08:10:59.311340: step: 2718/1545, loss: 0.5719681978225708 2023-01-23 08:11:00.231467: step: 2720/1545, loss: 0.3858630061149597 2023-01-23 08:11:01.113801: step: 2722/1545, loss: 0.7775252461433411 2023-01-23 08:11:01.975952: step: 2724/1545, loss: 1.081076979637146 2023-01-23 08:11:02.897679: step: 2726/1545, loss: 0.35564079880714417 2023-01-23 08:11:03.759783: step: 2728/1545, loss: 0.7247061133384705 2023-01-23 08:11:04.699649: step: 2730/1545, loss: 0.5787925124168396 2023-01-23 08:11:05.579084: step: 2732/1545, loss: 0.11565843224525452 2023-01-23 08:11:06.423190: step: 2734/1545, loss: 0.9984157085418701 2023-01-23 08:11:07.282485: step: 2736/1545, loss: 0.27726835012435913 2023-01-23 08:11:08.151352: step: 2738/1545, loss: 0.42686131596565247 2023-01-23 08:11:09.003958: step: 2740/1545, loss: 0.43372809886932373 2023-01-23 08:11:09.933040: step: 2742/1545, loss: 0.20771484076976776 2023-01-23 08:11:10.832889: step: 2744/1545, loss: 0.1258438527584076 2023-01-23 08:11:11.728769: step: 2746/1545, loss: 0.27295878529548645 2023-01-23 08:11:12.599178: step: 2748/1545, loss: 0.7645711302757263 2023-01-23 08:11:13.477771: step: 2750/1545, loss: 0.8776463270187378 2023-01-23 08:11:14.312520: step: 2752/1545, loss: 0.4951235055923462 2023-01-23 08:11:15.221850: step: 2754/1545, loss: 0.1100906953215599 2023-01-23 08:11:16.085736: step: 2756/1545, loss: 1.2564641237258911 2023-01-23 08:11:16.947157: step: 2758/1545, loss: 0.9197106957435608 2023-01-23 08:11:17.852095: step: 2760/1545, loss: 0.47157061100006104 2023-01-23 08:11:18.685598: step: 2762/1545, loss: 0.42509445548057556 2023-01-23 08:11:19.554269: step: 2764/1545, loss: 0.40742436051368713 2023-01-23 08:11:20.449706: step: 2766/1545, loss: 0.15583619475364685 2023-01-23 08:11:21.371837: step: 2768/1545, loss: 0.1969388723373413 2023-01-23 08:11:22.274421: step: 2770/1545, loss: 0.38046470284461975 2023-01-23 08:11:23.151062: step: 2772/1545, loss: 0.3310929536819458 2023-01-23 08:11:24.009995: step: 2774/1545, loss: 0.168183833360672 2023-01-23 08:11:24.894343: step: 2776/1545, loss: 0.399352103471756 2023-01-23 08:11:25.755519: step: 2778/1545, loss: 0.4808962643146515 2023-01-23 08:11:26.637482: step: 2780/1545, loss: 1.0028319358825684 2023-01-23 08:11:27.479440: step: 2782/1545, loss: 0.36388325691223145 2023-01-23 08:11:28.369535: step: 2784/1545, loss: 0.13979072868824005 2023-01-23 08:11:29.319667: step: 2786/1545, loss: 0.32128196954727173 2023-01-23 08:11:30.164554: step: 2788/1545, loss: 0.48988696932792664 2023-01-23 08:11:31.018353: step: 2790/1545, loss: 2.1998720169067383 2023-01-23 08:11:31.872909: step: 2792/1545, loss: 0.7883911728858948 2023-01-23 08:11:32.727950: step: 2794/1545, loss: 0.22403326630592346 2023-01-23 08:11:33.573416: step: 2796/1545, loss: 1.2859159708023071 2023-01-23 08:11:34.413955: step: 2798/1545, loss: 0.08713977783918381 2023-01-23 08:11:35.275332: step: 2800/1545, loss: 0.867530882358551 2023-01-23 08:11:36.158303: step: 2802/1545, loss: 1.2646524906158447 2023-01-23 08:11:37.060732: step: 2804/1545, loss: 0.10048557072877884 2023-01-23 08:11:37.883029: step: 2806/1545, loss: 0.1834588497877121 2023-01-23 08:11:38.733013: step: 2808/1545, loss: 0.8290423154830933 2023-01-23 08:11:39.601585: step: 2810/1545, loss: 0.4367981553077698 2023-01-23 08:11:40.559136: step: 2812/1545, loss: 0.2810156047344208 2023-01-23 08:11:41.427316: step: 2814/1545, loss: 0.5830733180046082 2023-01-23 08:11:42.311634: step: 2816/1545, loss: 0.38050219416618347 2023-01-23 08:11:43.163217: step: 2818/1545, loss: 0.6189324259757996 2023-01-23 08:11:44.057060: step: 2820/1545, loss: 0.8403902053833008 2023-01-23 08:11:44.930556: step: 2822/1545, loss: 0.2886037230491638 2023-01-23 08:11:45.846532: step: 2824/1545, loss: 2.7787997722625732 2023-01-23 08:11:46.707342: step: 2826/1545, loss: 0.13877561688423157 2023-01-23 08:11:47.575834: step: 2828/1545, loss: 1.2980071306228638 2023-01-23 08:11:48.432386: step: 2830/1545, loss: 0.348649263381958 2023-01-23 08:11:49.323497: step: 2832/1545, loss: 0.5225182175636292 2023-01-23 08:11:50.201493: step: 2834/1545, loss: 0.5369823575019836 2023-01-23 08:11:51.094880: step: 2836/1545, loss: 0.15100882947444916 2023-01-23 08:11:51.973134: step: 2838/1545, loss: 0.6563972234725952 2023-01-23 08:11:52.866698: step: 2840/1545, loss: 1.687192678451538 2023-01-23 08:11:53.738975: step: 2842/1545, loss: 0.21777766942977905 2023-01-23 08:11:54.634893: step: 2844/1545, loss: 2.133340835571289 2023-01-23 08:11:55.478090: step: 2846/1545, loss: 3.4056265354156494 2023-01-23 08:11:56.338700: step: 2848/1545, loss: 0.22155167162418365 2023-01-23 08:11:57.208903: step: 2850/1545, loss: 0.7502689957618713 2023-01-23 08:11:58.097949: step: 2852/1545, loss: 0.40376541018486023 2023-01-23 08:11:58.954950: step: 2854/1545, loss: 0.21924374997615814 2023-01-23 08:11:59.857010: step: 2856/1545, loss: 0.5994628071784973 2023-01-23 08:12:00.757315: step: 2858/1545, loss: 0.2532216012477875 2023-01-23 08:12:01.722607: step: 2860/1545, loss: 0.673291802406311 2023-01-23 08:12:02.566662: step: 2862/1545, loss: 0.5745694041252136 2023-01-23 08:12:03.462453: step: 2864/1545, loss: 0.4935591518878937 2023-01-23 08:12:04.311709: step: 2866/1545, loss: 0.3599497377872467 2023-01-23 08:12:05.259573: step: 2868/1545, loss: 0.5995855927467346 2023-01-23 08:12:06.152831: step: 2870/1545, loss: 0.7369902729988098 2023-01-23 08:12:07.027402: step: 2872/1545, loss: 0.41380271315574646 2023-01-23 08:12:07.891902: step: 2874/1545, loss: 0.12680786848068237 2023-01-23 08:12:08.791401: step: 2876/1545, loss: 6.889461994171143 2023-01-23 08:12:09.673546: step: 2878/1545, loss: 0.4328662157058716 2023-01-23 08:12:10.566554: step: 2880/1545, loss: 1.1579822301864624 2023-01-23 08:12:11.442818: step: 2882/1545, loss: 0.3501102924346924 2023-01-23 08:12:12.298347: step: 2884/1545, loss: 0.705026388168335 2023-01-23 08:12:13.169926: step: 2886/1545, loss: 0.32413777709007263 2023-01-23 08:12:14.054892: step: 2888/1545, loss: 0.43900105357170105 2023-01-23 08:12:14.895145: step: 2890/1545, loss: 0.14900775253772736 2023-01-23 08:12:15.770331: step: 2892/1545, loss: 0.3209279179573059 2023-01-23 08:12:16.673886: step: 2894/1545, loss: 0.44361427426338196 2023-01-23 08:12:17.551268: step: 2896/1545, loss: 0.3008551299571991 2023-01-23 08:12:18.445806: step: 2898/1545, loss: 2.0749735832214355 2023-01-23 08:12:19.341539: step: 2900/1545, loss: 0.10724175721406937 2023-01-23 08:12:20.226026: step: 2902/1545, loss: 0.39564207196235657 2023-01-23 08:12:21.127991: step: 2904/1545, loss: 0.32011809945106506 2023-01-23 08:12:21.976297: step: 2906/1545, loss: 0.24947114288806915 2023-01-23 08:12:22.844763: step: 2908/1545, loss: 0.24394813179969788 2023-01-23 08:12:23.742451: step: 2910/1545, loss: 0.20457778871059418 2023-01-23 08:12:24.601808: step: 2912/1545, loss: 0.7187395095825195 2023-01-23 08:12:25.512983: step: 2914/1545, loss: 1.1350468397140503 2023-01-23 08:12:26.403012: step: 2916/1545, loss: 0.17032980918884277 2023-01-23 08:12:27.269319: step: 2918/1545, loss: 0.1739853024482727 2023-01-23 08:12:28.156486: step: 2920/1545, loss: 0.5025991201400757 2023-01-23 08:12:28.997082: step: 2922/1545, loss: 1.2289018630981445 2023-01-23 08:12:29.874242: step: 2924/1545, loss: 0.5634085536003113 2023-01-23 08:12:30.775801: step: 2926/1545, loss: 0.46694475412368774 2023-01-23 08:12:31.678082: step: 2928/1545, loss: 0.18096065521240234 2023-01-23 08:12:32.550222: step: 2930/1545, loss: 0.32020115852355957 2023-01-23 08:12:33.431771: step: 2932/1545, loss: 0.38108643889427185 2023-01-23 08:12:34.332409: step: 2934/1545, loss: 0.5795118808746338 2023-01-23 08:12:35.200511: step: 2936/1545, loss: 1.5237685441970825 2023-01-23 08:12:36.135253: step: 2938/1545, loss: 0.3060426115989685 2023-01-23 08:12:37.015169: step: 2940/1545, loss: 0.7615238428115845 2023-01-23 08:12:37.891964: step: 2942/1545, loss: 0.2868329882621765 2023-01-23 08:12:38.772582: step: 2944/1545, loss: 1.1458162069320679 2023-01-23 08:12:39.675050: step: 2946/1545, loss: 0.27138298749923706 2023-01-23 08:12:40.525890: step: 2948/1545, loss: 0.41891032457351685 2023-01-23 08:12:41.421478: step: 2950/1545, loss: 0.7434131503105164 2023-01-23 08:12:42.282099: step: 2952/1545, loss: 0.8492541909217834 2023-01-23 08:12:43.154166: step: 2954/1545, loss: 0.36909428238868713 2023-01-23 08:12:44.049689: step: 2956/1545, loss: 0.5140973925590515 2023-01-23 08:12:44.957013: step: 2958/1545, loss: 0.19029465317726135 2023-01-23 08:12:45.812537: step: 2960/1545, loss: 0.2513241171836853 2023-01-23 08:12:46.717210: step: 2962/1545, loss: 1.109758973121643 2023-01-23 08:12:47.608471: step: 2964/1545, loss: 0.20061592757701874 2023-01-23 08:12:48.477219: step: 2966/1545, loss: 0.5377641320228577 2023-01-23 08:12:49.324672: step: 2968/1545, loss: 1.6701147556304932 2023-01-23 08:12:50.222364: step: 2970/1545, loss: 0.16841816902160645 2023-01-23 08:12:51.113919: step: 2972/1545, loss: 0.5664592981338501 2023-01-23 08:12:51.988661: step: 2974/1545, loss: 0.6433917284011841 2023-01-23 08:12:52.919282: step: 2976/1545, loss: 0.24791236221790314 2023-01-23 08:12:53.768326: step: 2978/1545, loss: 0.3810882568359375 2023-01-23 08:12:54.660445: step: 2980/1545, loss: 0.5354710817337036 2023-01-23 08:12:55.554373: step: 2982/1545, loss: 0.31395459175109863 2023-01-23 08:12:56.502979: step: 2984/1545, loss: 0.314371258020401 2023-01-23 08:12:57.366761: step: 2986/1545, loss: 0.8636536598205566 2023-01-23 08:12:58.252859: step: 2988/1545, loss: 0.45233091711997986 2023-01-23 08:12:59.096186: step: 2990/1545, loss: 0.4125690460205078 2023-01-23 08:12:59.965120: step: 2992/1545, loss: 0.6421444416046143 2023-01-23 08:13:00.877424: step: 2994/1545, loss: 1.0647389888763428 2023-01-23 08:13:01.817497: step: 2996/1545, loss: 0.36577218770980835 2023-01-23 08:13:02.717208: step: 2998/1545, loss: 0.2060784250497818 2023-01-23 08:13:03.611740: step: 3000/1545, loss: 0.16032907366752625 2023-01-23 08:13:04.482978: step: 3002/1545, loss: 0.3560481369495392 2023-01-23 08:13:05.372352: step: 3004/1545, loss: 0.8099218010902405 2023-01-23 08:13:06.244957: step: 3006/1545, loss: 0.32188478112220764 2023-01-23 08:13:07.124240: step: 3008/1545, loss: 1.183534860610962 2023-01-23 08:13:08.014547: step: 3010/1545, loss: 1.3509100675582886 2023-01-23 08:13:08.904154: step: 3012/1545, loss: 1.0701816082000732 2023-01-23 08:13:09.775444: step: 3014/1545, loss: 0.6177808046340942 2023-01-23 08:13:10.612721: step: 3016/1545, loss: 0.5441433191299438 2023-01-23 08:13:11.472437: step: 3018/1545, loss: 0.9864305853843689 2023-01-23 08:13:12.352997: step: 3020/1545, loss: 0.4722293019294739 2023-01-23 08:13:13.219023: step: 3022/1545, loss: 0.736264705657959 2023-01-23 08:13:14.055608: step: 3024/1545, loss: 1.235386610031128 2023-01-23 08:13:14.928773: step: 3026/1545, loss: 0.28244340419769287 2023-01-23 08:13:15.794756: step: 3028/1545, loss: 0.24712292850017548 2023-01-23 08:13:16.669737: step: 3030/1545, loss: 0.47761598229408264 2023-01-23 08:13:17.561454: step: 3032/1545, loss: 0.38470330834388733 2023-01-23 08:13:18.408771: step: 3034/1545, loss: 0.26418545842170715 2023-01-23 08:13:19.328946: step: 3036/1545, loss: 0.7729030251502991 2023-01-23 08:13:20.247678: step: 3038/1545, loss: 0.22061869502067566 2023-01-23 08:13:21.134560: step: 3040/1545, loss: 0.2555069923400879 2023-01-23 08:13:22.011026: step: 3042/1545, loss: 0.8556168675422668 2023-01-23 08:13:22.896368: step: 3044/1545, loss: 0.9508212208747864 2023-01-23 08:13:23.762995: step: 3046/1545, loss: 0.2195708155632019 2023-01-23 08:13:24.617571: step: 3048/1545, loss: 0.2377624809741974 2023-01-23 08:13:25.501543: step: 3050/1545, loss: 0.13781575858592987 2023-01-23 08:13:26.327600: step: 3052/1545, loss: 1.9899916648864746 2023-01-23 08:13:27.163531: step: 3054/1545, loss: 0.14137807488441467 2023-01-23 08:13:28.064050: step: 3056/1545, loss: 0.45795395970344543 2023-01-23 08:13:28.953758: step: 3058/1545, loss: 0.21209581196308136 2023-01-23 08:13:29.881341: step: 3060/1545, loss: 0.5315919518470764 2023-01-23 08:13:30.749612: step: 3062/1545, loss: 1.9455170631408691 2023-01-23 08:13:31.639404: step: 3064/1545, loss: 0.6504956483840942 2023-01-23 08:13:32.526294: step: 3066/1545, loss: 0.4391360580921173 2023-01-23 08:13:33.418755: step: 3068/1545, loss: 0.21356239914894104 2023-01-23 08:13:34.309835: step: 3070/1545, loss: 0.37470680475234985 2023-01-23 08:13:35.230675: step: 3072/1545, loss: 0.2610272169113159 2023-01-23 08:13:36.107450: step: 3074/1545, loss: 1.2676811218261719 2023-01-23 08:13:36.974746: step: 3076/1545, loss: 0.6555976271629333 2023-01-23 08:13:37.880972: step: 3078/1545, loss: 0.19203104078769684 2023-01-23 08:13:38.761461: step: 3080/1545, loss: 0.6987700462341309 2023-01-23 08:13:39.641805: step: 3082/1545, loss: 0.2909243106842041 2023-01-23 08:13:40.530564: step: 3084/1545, loss: 0.7305033802986145 2023-01-23 08:13:41.388926: step: 3086/1545, loss: 0.8046038746833801 2023-01-23 08:13:42.289023: step: 3088/1545, loss: 0.4006190001964569 2023-01-23 08:13:43.147333: step: 3090/1545, loss: 0.2105856090784073 ================================================== Loss: 0.615 -------------------- Dev Chinese: {'event': {'p': 0.5954198473282443, 'r': 0.7270306258322237, 'f1': 0.6546762589928057}, 'argument': {'p': 0.6799690518533097, 'r': 0.6413171087412293, 'f1': 0.6600777323995562}, 'combined': 0.43213722049179576, 'epoch': 6} Test Chinese: {'event': {'p': 0.6408751334044824, 'r': 0.7679028132992327, 'f1': 0.6986620127981384}, 'argument': {'p': 0.7187725442920168, 'r': 0.6932491206115442, 'f1': 0.7057801542785751}, 'combined': 0.49310178318125, 'epoch': 6} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6762623994878489, 'r': 0.6457543213154647, 'f1': 0.6606563441150525}, 'combined': 0.4420247251316327, 'epoch': 6} Test Korean: {'event': {'p': 0.6322751322751323, 'r': 0.7640664961636828, 'f1': 0.6919513607411696}, 'argument': {'p': 0.7171651136399282, 'r': 0.6930310677507069, 'f1': 0.7048915761058339}, 'combined': 0.48775068526141946, 'epoch': 6} Dev Russian: {'event': {'p': 0.562992125984252, 'r': 0.7616511318242344, 'f1': 0.6474250141482739}, 'argument': {'p': 0.6801431975961602, 'r': 0.6485199444890426, 'f1': 0.6639552415933222}, 'combined': 0.4298612316823773, 'epoch': 6} Test Russian: {'event': {'p': 0.6268061783756851, 'r': 0.8043478260869565, 'f1': 0.7045645477457295}, 'argument': {'p': 0.723251864631154, 'r': 0.6999648334225133, 'f1': 0.7114178348826229}, 'combined': 0.5012397850923213, 'epoch': 6} Chinese: {'event': {'p': 0.5512820512820513, 'r': 0.7962962962962963, 'f1': 0.6515151515151515}, 'argument': {'p': 0.6279018252702463, 'r': 0.5915769262876701, 'f1': 0.6091983666451751}, 'combined': 0.3969019661476141, 'epoch': 6} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6901455026455027, 'r': 0.34507275132275134, 'f1': 0.46009700176366847}, 'combined': 0.2825157028373403, 'epoch': 6} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5399046555296555, 'r': 0.462775419025419, 'f1': 0.49837352818122044}, 'combined': 0.2775751296199202, 'epoch': 6} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6964114198955085, 'r': 0.6234341752956798, 'f1': 0.657905259237779}, 'combined': 0.43308151957019264, 'epoch': 5} Test for Chinese: {'event': {'p': 0.6350053361792957, 'r': 0.7608695652173914, 'f1': 0.692262943571844}, 'argument': {'p': 0.7272924330941487, 'r': 0.6900381570870325, 'f1': 0.708175684166213}, 'combined': 0.4902437836869072, 'epoch': 5} Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.6753413767302655, 'r': 0.6027840387344519, 'f1': 0.6370032199726521}, 'combined': 0.4632750690710198, 'epoch': 5} -------------------- Dev for Korean: {'event': {'p': 0.6105032822757112, 'r': 0.7430093209054593, 'f1': 0.6702702702702702}, 'argument': {'p': 0.6914323890031635, 'r': 0.6157583794121126, 'f1': 0.651404978696081}, 'combined': 0.4366173911260218, 'epoch': 5} Test for Korean: {'event': {'p': 0.6253968253968254, 'r': 0.7557544757033248, 'f1': 0.6844238563983787}, 'argument': {'p': 0.7217273465797566, 'r': 0.6830584493271099, 'f1': 0.7018606874131883}, 'combined': 0.48037019833375133, 'epoch': 5} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6556681954409226, 'r': 0.3951972684849397, 'f1': 0.49315214699830073}, 'combined': 0.31146451389366364, 'epoch': 5} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 7 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 08:18:59.092089: step: 2/1545, loss: 0.4041239619255066 2023-01-23 08:18:59.961051: step: 4/1545, loss: 0.28341972827911377 2023-01-23 08:19:00.869477: step: 6/1545, loss: 0.568026602268219 2023-01-23 08:19:01.724388: step: 8/1545, loss: 0.7369042634963989 2023-01-23 08:19:02.646395: step: 10/1545, loss: 0.2275206297636032 2023-01-23 08:19:03.510076: step: 12/1545, loss: 0.4988446533679962 2023-01-23 08:19:04.409600: step: 14/1545, loss: 0.338201105594635 2023-01-23 08:19:05.315076: step: 16/1545, loss: 0.549683153629303 2023-01-23 08:19:06.265469: step: 18/1545, loss: 0.18487265706062317 2023-01-23 08:19:07.147971: step: 20/1545, loss: 9.131342887878418 2023-01-23 08:19:08.016890: step: 22/1545, loss: 0.36875590682029724 2023-01-23 08:19:08.847823: step: 24/1545, loss: 0.3671025335788727 2023-01-23 08:19:09.701624: step: 26/1545, loss: 0.3911002576351166 2023-01-23 08:19:10.638349: step: 28/1545, loss: 0.36337029933929443 2023-01-23 08:19:11.549379: step: 30/1545, loss: 0.45357438921928406 2023-01-23 08:19:12.412909: step: 32/1545, loss: 0.11020668596029282 2023-01-23 08:19:13.270705: step: 34/1545, loss: 0.1589524745941162 2023-01-23 08:19:14.111093: step: 36/1545, loss: 0.6211010813713074 2023-01-23 08:19:15.003803: step: 38/1545, loss: 0.20554015040397644 2023-01-23 08:19:15.874775: step: 40/1545, loss: 1.2801038026809692 2023-01-23 08:19:16.821739: step: 42/1545, loss: 0.43509235978126526 2023-01-23 08:19:17.680250: step: 44/1545, loss: 0.3469502329826355 2023-01-23 08:19:18.548570: step: 46/1545, loss: 0.1685309112071991 2023-01-23 08:19:19.405494: step: 48/1545, loss: 0.2943612039089203 2023-01-23 08:19:20.281793: step: 50/1545, loss: 0.15996097028255463 2023-01-23 08:19:21.143491: step: 52/1545, loss: 0.40896889567375183 2023-01-23 08:19:22.085086: step: 54/1545, loss: 0.25088536739349365 2023-01-23 08:19:22.947264: step: 56/1545, loss: 0.08042289316654205 2023-01-23 08:19:23.848396: step: 58/1545, loss: 0.3432498872280121 2023-01-23 08:19:24.697094: step: 60/1545, loss: 0.20633092522621155 2023-01-23 08:19:25.581821: step: 62/1545, loss: 2.193833589553833 2023-01-23 08:19:26.565108: step: 64/1545, loss: 0.13832034170627594 2023-01-23 08:19:27.412633: step: 66/1545, loss: 0.7464310526847839 2023-01-23 08:19:28.295687: step: 68/1545, loss: 0.06693465262651443 2023-01-23 08:19:29.181715: step: 70/1545, loss: 0.28423863649368286 2023-01-23 08:19:30.025176: step: 72/1545, loss: 0.22072269022464752 2023-01-23 08:19:30.914988: step: 74/1545, loss: 0.6160585284233093 2023-01-23 08:19:31.763104: step: 76/1545, loss: 0.7393354773521423 2023-01-23 08:19:32.647562: step: 78/1545, loss: 0.11291489005088806 2023-01-23 08:19:33.542668: step: 80/1545, loss: 0.4372977018356323 2023-01-23 08:19:34.411363: step: 82/1545, loss: 0.24948391318321228 2023-01-23 08:19:35.354460: step: 84/1545, loss: 0.315878689289093 2023-01-23 08:19:36.246678: step: 86/1545, loss: 0.1436893194913864 2023-01-23 08:19:37.121402: step: 88/1545, loss: 0.31851664185523987 2023-01-23 08:19:38.032009: step: 90/1545, loss: 0.5056915283203125 2023-01-23 08:19:38.986837: step: 92/1545, loss: 0.21178792417049408 2023-01-23 08:19:39.915228: step: 94/1545, loss: 0.11951310187578201 2023-01-23 08:19:40.767612: step: 96/1545, loss: 0.30850934982299805 2023-01-23 08:19:41.752350: step: 98/1545, loss: 1.9515068531036377 2023-01-23 08:19:42.647341: step: 100/1545, loss: 0.36133459210395813 2023-01-23 08:19:43.510674: step: 102/1545, loss: 0.05289671942591667 2023-01-23 08:19:44.385739: step: 104/1545, loss: 0.3526700437068939 2023-01-23 08:19:45.270161: step: 106/1545, loss: 0.5773923993110657 2023-01-23 08:19:46.148368: step: 108/1545, loss: 0.46634048223495483 2023-01-23 08:19:47.012626: step: 110/1545, loss: 0.5308939814567566 2023-01-23 08:19:47.868988: step: 112/1545, loss: 0.5067607164382935 2023-01-23 08:19:48.733684: step: 114/1545, loss: 0.28969600796699524 2023-01-23 08:19:49.663869: step: 116/1545, loss: 0.4000491797924042 2023-01-23 08:19:50.563004: step: 118/1545, loss: 0.4676966965198517 2023-01-23 08:19:51.454431: step: 120/1545, loss: 1.2172077894210815 2023-01-23 08:19:52.385913: step: 122/1545, loss: 0.6267189979553223 2023-01-23 08:19:53.245534: step: 124/1545, loss: 0.5253638625144958 2023-01-23 08:19:54.117807: step: 126/1545, loss: 0.23200884461402893 2023-01-23 08:19:55.045141: step: 128/1545, loss: 0.4211517870426178 2023-01-23 08:19:55.935850: step: 130/1545, loss: 0.11486546695232391 2023-01-23 08:19:56.810225: step: 132/1545, loss: 0.14339952170848846 2023-01-23 08:19:57.695108: step: 134/1545, loss: 0.22956086695194244 2023-01-23 08:19:58.594538: step: 136/1545, loss: 0.8977214097976685 2023-01-23 08:19:59.469788: step: 138/1545, loss: 0.31237760186195374 2023-01-23 08:20:00.389829: step: 140/1545, loss: 0.37387657165527344 2023-01-23 08:20:01.272868: step: 142/1545, loss: 0.32751622796058655 2023-01-23 08:20:02.117314: step: 144/1545, loss: 0.2258111834526062 2023-01-23 08:20:03.025230: step: 146/1545, loss: 0.20309701561927795 2023-01-23 08:20:03.911478: step: 148/1545, loss: 0.5062355995178223 2023-01-23 08:20:04.752144: step: 150/1545, loss: 0.13424097001552582 2023-01-23 08:20:05.665163: step: 152/1545, loss: 0.2834642827510834 2023-01-23 08:20:06.627967: step: 154/1545, loss: 0.15680213272571564 2023-01-23 08:20:07.464140: step: 156/1545, loss: 7.928518295288086 2023-01-23 08:20:08.347517: step: 158/1545, loss: 0.48007264733314514 2023-01-23 08:20:09.272245: step: 160/1545, loss: 0.5975199341773987 2023-01-23 08:20:10.140729: step: 162/1545, loss: 3.0155553817749023 2023-01-23 08:20:11.029583: step: 164/1545, loss: 0.269753634929657 2023-01-23 08:20:11.926073: step: 166/1545, loss: 0.2092115581035614 2023-01-23 08:20:12.862054: step: 168/1545, loss: 4.282368183135986 2023-01-23 08:20:13.779916: step: 170/1545, loss: 0.16290298104286194 2023-01-23 08:20:14.717006: step: 172/1545, loss: 0.1804242879152298 2023-01-23 08:20:15.673440: step: 174/1545, loss: 0.10771670937538147 2023-01-23 08:20:16.550452: step: 176/1545, loss: 0.27523210644721985 2023-01-23 08:20:17.451119: step: 178/1545, loss: 0.5440077185630798 2023-01-23 08:20:18.350223: step: 180/1545, loss: 0.3898657560348511 2023-01-23 08:20:19.265100: step: 182/1545, loss: 0.3443761169910431 2023-01-23 08:20:20.159795: step: 184/1545, loss: 0.3111061453819275 2023-01-23 08:20:21.069822: step: 186/1545, loss: 0.23353460431098938 2023-01-23 08:20:21.921849: step: 188/1545, loss: 0.40584278106689453 2023-01-23 08:20:22.765371: step: 190/1545, loss: 0.290246844291687 2023-01-23 08:20:23.650150: step: 192/1545, loss: 0.19568854570388794 2023-01-23 08:20:24.588709: step: 194/1545, loss: 0.3521953523159027 2023-01-23 08:20:25.468163: step: 196/1545, loss: 0.28228437900543213 2023-01-23 08:20:26.334805: step: 198/1545, loss: 0.5855199098587036 2023-01-23 08:20:27.220689: step: 200/1545, loss: 0.4733498990535736 2023-01-23 08:20:28.098265: step: 202/1545, loss: 0.41601505875587463 2023-01-23 08:20:28.962132: step: 204/1545, loss: 0.388114869594574 2023-01-23 08:20:29.846390: step: 206/1545, loss: 0.17505688965320587 2023-01-23 08:20:30.680864: step: 208/1545, loss: 0.26163461804389954 2023-01-23 08:20:31.607192: step: 210/1545, loss: 0.34543511271476746 2023-01-23 08:20:32.562338: step: 212/1545, loss: 0.6984533667564392 2023-01-23 08:20:33.451360: step: 214/1545, loss: 0.12916679680347443 2023-01-23 08:20:34.404075: step: 216/1545, loss: 0.2019418329000473 2023-01-23 08:20:35.265835: step: 218/1545, loss: 0.19473926723003387 2023-01-23 08:20:36.196072: step: 220/1545, loss: 0.4511163532733917 2023-01-23 08:20:37.123624: step: 222/1545, loss: 0.7309891581535339 2023-01-23 08:20:38.014904: step: 224/1545, loss: 0.3933642506599426 2023-01-23 08:20:38.848850: step: 226/1545, loss: 0.45716509222984314 2023-01-23 08:20:39.796525: step: 228/1545, loss: 2.663705825805664 2023-01-23 08:20:40.654545: step: 230/1545, loss: 0.3589136600494385 2023-01-23 08:20:41.536530: step: 232/1545, loss: 0.27096235752105713 2023-01-23 08:20:42.436774: step: 234/1545, loss: 0.1526026874780655 2023-01-23 08:20:43.310540: step: 236/1545, loss: 1.0272960662841797 2023-01-23 08:20:44.204397: step: 238/1545, loss: 0.42596369981765747 2023-01-23 08:20:45.070135: step: 240/1545, loss: 0.31105202436447144 2023-01-23 08:20:45.942632: step: 242/1545, loss: 0.22394584119319916 2023-01-23 08:20:46.840320: step: 244/1545, loss: 0.7703842520713806 2023-01-23 08:20:47.752569: step: 246/1545, loss: 0.3386981785297394 2023-01-23 08:20:48.618607: step: 248/1545, loss: 0.3140385150909424 2023-01-23 08:20:49.479375: step: 250/1545, loss: 0.13450884819030762 2023-01-23 08:20:50.386311: step: 252/1545, loss: 0.18253806233406067 2023-01-23 08:20:51.261545: step: 254/1545, loss: 0.16122491657733917 2023-01-23 08:20:52.166579: step: 256/1545, loss: 0.14230188727378845 2023-01-23 08:20:53.010999: step: 258/1545, loss: 0.19600710272789001 2023-01-23 08:20:53.893796: step: 260/1545, loss: 0.5990116000175476 2023-01-23 08:20:54.806020: step: 262/1545, loss: 0.2504024803638458 2023-01-23 08:20:55.683091: step: 264/1545, loss: 0.2556428611278534 2023-01-23 08:20:56.554674: step: 266/1545, loss: 0.282534122467041 2023-01-23 08:20:57.409602: step: 268/1545, loss: 0.38011524081230164 2023-01-23 08:20:58.303195: step: 270/1545, loss: 0.9457808136940002 2023-01-23 08:20:59.187197: step: 272/1545, loss: 0.2748299837112427 2023-01-23 08:21:00.057420: step: 274/1545, loss: 0.6572811007499695 2023-01-23 08:21:00.899964: step: 276/1545, loss: 0.5328799486160278 2023-01-23 08:21:01.780068: step: 278/1545, loss: 0.2170770764350891 2023-01-23 08:21:02.672433: step: 280/1545, loss: 0.30857354402542114 2023-01-23 08:21:03.557381: step: 282/1545, loss: 0.16155411303043365 2023-01-23 08:21:04.436493: step: 284/1545, loss: 0.27376362681388855 2023-01-23 08:21:05.328599: step: 286/1545, loss: 0.8367546796798706 2023-01-23 08:21:06.227965: step: 288/1545, loss: 0.43237948417663574 2023-01-23 08:21:07.109933: step: 290/1545, loss: 0.49732521176338196 2023-01-23 08:21:08.033171: step: 292/1545, loss: 0.22893081605434418 2023-01-23 08:21:08.903807: step: 294/1545, loss: 0.15069769322872162 2023-01-23 08:21:09.874090: step: 296/1545, loss: 0.4059661030769348 2023-01-23 08:21:10.764918: step: 298/1545, loss: 0.47410067915916443 2023-01-23 08:21:11.641317: step: 300/1545, loss: 0.35550346970558167 2023-01-23 08:21:12.544418: step: 302/1545, loss: 0.3348022997379303 2023-01-23 08:21:13.461838: step: 304/1545, loss: 0.4000483751296997 2023-01-23 08:21:14.383544: step: 306/1545, loss: 0.5089818835258484 2023-01-23 08:21:15.249916: step: 308/1545, loss: 0.1291661262512207 2023-01-23 08:21:16.107482: step: 310/1545, loss: 0.6907273530960083 2023-01-23 08:21:16.979886: step: 312/1545, loss: 1.4550185203552246 2023-01-23 08:21:17.870720: step: 314/1545, loss: 0.2867397665977478 2023-01-23 08:21:18.795486: step: 316/1545, loss: 0.3916524350643158 2023-01-23 08:21:19.694804: step: 318/1545, loss: 0.366146445274353 2023-01-23 08:21:20.574169: step: 320/1545, loss: 0.24477030336856842 2023-01-23 08:21:21.470640: step: 322/1545, loss: 0.8778076767921448 2023-01-23 08:21:22.416851: step: 324/1545, loss: 0.4212344288825989 2023-01-23 08:21:23.297768: step: 326/1545, loss: 0.17538976669311523 2023-01-23 08:21:24.155122: step: 328/1545, loss: 1.358402132987976 2023-01-23 08:21:25.086370: step: 330/1545, loss: 0.12947633862495422 2023-01-23 08:21:25.954842: step: 332/1545, loss: 0.43378251791000366 2023-01-23 08:21:26.834997: step: 334/1545, loss: 0.24383829534053802 2023-01-23 08:21:27.716877: step: 336/1545, loss: 0.4550533592700958 2023-01-23 08:21:28.579203: step: 338/1545, loss: 0.20158296823501587 2023-01-23 08:21:29.437822: step: 340/1545, loss: 0.43600162863731384 2023-01-23 08:21:30.342810: step: 342/1545, loss: 0.18055365979671478 2023-01-23 08:21:31.226230: step: 344/1545, loss: 0.13053974509239197 2023-01-23 08:21:32.105658: step: 346/1545, loss: 0.37990647554397583 2023-01-23 08:21:32.986471: step: 348/1545, loss: 0.15792778134346008 2023-01-23 08:21:33.833700: step: 350/1545, loss: 0.4784216284751892 2023-01-23 08:21:34.703915: step: 352/1545, loss: 0.32931986451148987 2023-01-23 08:21:35.590608: step: 354/1545, loss: 1.2963578701019287 2023-01-23 08:21:36.478300: step: 356/1545, loss: 0.1513565182685852 2023-01-23 08:21:37.309373: step: 358/1545, loss: 1.4293328523635864 2023-01-23 08:21:38.180848: step: 360/1545, loss: 0.1219719648361206 2023-01-23 08:21:39.094630: step: 362/1545, loss: 0.3248288631439209 2023-01-23 08:21:39.966828: step: 364/1545, loss: 0.29588717222213745 2023-01-23 08:21:40.974302: step: 366/1545, loss: 0.33955124020576477 2023-01-23 08:21:41.845037: step: 368/1545, loss: 0.08777730166912079 2023-01-23 08:21:42.759990: step: 370/1545, loss: 0.3968829810619354 2023-01-23 08:21:43.619909: step: 372/1545, loss: 0.21716400980949402 2023-01-23 08:21:44.509484: step: 374/1545, loss: 0.16004449129104614 2023-01-23 08:21:45.352907: step: 376/1545, loss: 0.4979340732097626 2023-01-23 08:21:46.236281: step: 378/1545, loss: 0.08235219120979309 2023-01-23 08:21:47.127544: step: 380/1545, loss: 0.5362815856933594 2023-01-23 08:21:47.999557: step: 382/1545, loss: 0.2996653914451599 2023-01-23 08:21:48.938270: step: 384/1545, loss: 0.8654786944389343 2023-01-23 08:21:49.831550: step: 386/1545, loss: 0.813632607460022 2023-01-23 08:21:50.732464: step: 388/1545, loss: 0.09940853714942932 2023-01-23 08:21:51.667641: step: 390/1545, loss: 0.9699210524559021 2023-01-23 08:21:52.572687: step: 392/1545, loss: 0.5119604468345642 2023-01-23 08:21:53.460739: step: 394/1545, loss: 0.026607520878314972 2023-01-23 08:21:54.340194: step: 396/1545, loss: 0.21276232600212097 2023-01-23 08:21:55.235794: step: 398/1545, loss: 0.08093996345996857 2023-01-23 08:21:56.165655: step: 400/1545, loss: 0.3485443592071533 2023-01-23 08:21:57.066755: step: 402/1545, loss: 0.8147988319396973 2023-01-23 08:21:57.914506: step: 404/1545, loss: 0.1825101226568222 2023-01-23 08:21:58.786436: step: 406/1545, loss: 0.3214655816555023 2023-01-23 08:21:59.692090: step: 408/1545, loss: 0.34784966707229614 2023-01-23 08:22:00.579333: step: 410/1545, loss: 0.18788030743598938 2023-01-23 08:22:01.539799: step: 412/1545, loss: 0.23863226175308228 2023-01-23 08:22:02.498828: step: 414/1545, loss: 0.09217280894517899 2023-01-23 08:22:03.520373: step: 416/1545, loss: 0.45619818568229675 2023-01-23 08:22:04.398417: step: 418/1545, loss: 0.5989810824394226 2023-01-23 08:22:05.288045: step: 420/1545, loss: 0.18452318012714386 2023-01-23 08:22:06.164939: step: 422/1545, loss: 0.25292110443115234 2023-01-23 08:22:07.048946: step: 424/1545, loss: 0.4685977101325989 2023-01-23 08:22:07.933310: step: 426/1545, loss: 0.19180703163146973 2023-01-23 08:22:08.874586: step: 428/1545, loss: 0.1450890600681305 2023-01-23 08:22:09.733370: step: 430/1545, loss: 0.1722019761800766 2023-01-23 08:22:10.605315: step: 432/1545, loss: 0.3086729049682617 2023-01-23 08:22:11.549786: step: 434/1545, loss: 0.37826499342918396 2023-01-23 08:22:12.450995: step: 436/1545, loss: 0.22279676795005798 2023-01-23 08:22:13.388741: step: 438/1545, loss: 0.67807537317276 2023-01-23 08:22:14.289764: step: 440/1545, loss: 0.21931739151477814 2023-01-23 08:22:15.188435: step: 442/1545, loss: 0.3788734972476959 2023-01-23 08:22:16.073454: step: 444/1545, loss: 0.1685865968465805 2023-01-23 08:22:16.984372: step: 446/1545, loss: 1.314451813697815 2023-01-23 08:22:17.908390: step: 448/1545, loss: 0.2935316264629364 2023-01-23 08:22:18.746814: step: 450/1545, loss: 0.15532925724983215 2023-01-23 08:22:19.627835: step: 452/1545, loss: 0.2334822714328766 2023-01-23 08:22:20.499627: step: 454/1545, loss: 0.2185971736907959 2023-01-23 08:22:21.366940: step: 456/1545, loss: 0.0797761008143425 2023-01-23 08:22:22.293461: step: 458/1545, loss: 0.4309309422969818 2023-01-23 08:22:23.158323: step: 460/1545, loss: 0.34395232796669006 2023-01-23 08:22:24.041289: step: 462/1545, loss: 0.35891738533973694 2023-01-23 08:22:24.930089: step: 464/1545, loss: 0.37563619017601013 2023-01-23 08:22:25.817858: step: 466/1545, loss: 0.1976485252380371 2023-01-23 08:22:26.699737: step: 468/1545, loss: 0.271317720413208 2023-01-23 08:22:27.537166: step: 470/1545, loss: 0.19130700826644897 2023-01-23 08:22:28.478916: step: 472/1545, loss: 0.2949894964694977 2023-01-23 08:22:29.355640: step: 474/1545, loss: 3.0095250606536865 2023-01-23 08:22:30.243025: step: 476/1545, loss: 0.1155543327331543 2023-01-23 08:22:31.137350: step: 478/1545, loss: 0.5026673078536987 2023-01-23 08:22:32.070835: step: 480/1545, loss: 4.554783821105957 2023-01-23 08:22:32.978118: step: 482/1545, loss: 0.24759769439697266 2023-01-23 08:22:33.848952: step: 484/1545, loss: 0.4433257579803467 2023-01-23 08:22:34.701843: step: 486/1545, loss: 0.22002194821834564 2023-01-23 08:22:35.584451: step: 488/1545, loss: 0.29508984088897705 2023-01-23 08:22:36.444186: step: 490/1545, loss: 0.39481082558631897 2023-01-23 08:22:37.354616: step: 492/1545, loss: 0.8078441023826599 2023-01-23 08:22:38.293475: step: 494/1545, loss: 0.7548355460166931 2023-01-23 08:22:39.190468: step: 496/1545, loss: 0.271702378988266 2023-01-23 08:22:40.107480: step: 498/1545, loss: 2.9561824798583984 2023-01-23 08:22:41.016894: step: 500/1545, loss: 0.17816178500652313 2023-01-23 08:22:41.928014: step: 502/1545, loss: 0.09086893498897552 2023-01-23 08:22:42.788214: step: 504/1545, loss: 0.15006570518016815 2023-01-23 08:22:43.651340: step: 506/1545, loss: 0.2892053425312042 2023-01-23 08:22:44.554356: step: 508/1545, loss: 0.6940097808837891 2023-01-23 08:22:45.409966: step: 510/1545, loss: 0.19321133196353912 2023-01-23 08:22:46.269209: step: 512/1545, loss: 1.735052466392517 2023-01-23 08:22:47.233956: step: 514/1545, loss: 0.17822982370853424 2023-01-23 08:22:48.135694: step: 516/1545, loss: 0.3178365230560303 2023-01-23 08:22:49.004059: step: 518/1545, loss: 0.16732989251613617 2023-01-23 08:22:49.875845: step: 520/1545, loss: 3.5950238704681396 2023-01-23 08:22:50.762266: step: 522/1545, loss: 0.09664679318666458 2023-01-23 08:22:51.663077: step: 524/1545, loss: 1.3194677829742432 2023-01-23 08:22:52.570309: step: 526/1545, loss: 0.3382568657398224 2023-01-23 08:22:53.451575: step: 528/1545, loss: 0.45003217458724976 2023-01-23 08:22:54.313890: step: 530/1545, loss: 0.09179405122995377 2023-01-23 08:22:55.181034: step: 532/1545, loss: 0.30432233214378357 2023-01-23 08:22:56.067470: step: 534/1545, loss: 0.36302152276039124 2023-01-23 08:22:56.959468: step: 536/1545, loss: 0.27628204226493835 2023-01-23 08:22:57.884320: step: 538/1545, loss: 0.5969740152359009 2023-01-23 08:22:58.754333: step: 540/1545, loss: 0.8543252944946289 2023-01-23 08:22:59.680882: step: 542/1545, loss: 0.19717533886432648 2023-01-23 08:23:00.567751: step: 544/1545, loss: 0.18443843722343445 2023-01-23 08:23:01.448727: step: 546/1545, loss: 0.19269797205924988 2023-01-23 08:23:02.345381: step: 548/1545, loss: 0.32254311442375183 2023-01-23 08:23:03.228501: step: 550/1545, loss: 0.29777565598487854 2023-01-23 08:23:04.116516: step: 552/1545, loss: 1.99502432346344 2023-01-23 08:23:04.991008: step: 554/1545, loss: 0.3078978955745697 2023-01-23 08:23:05.872659: step: 556/1545, loss: 0.23863238096237183 2023-01-23 08:23:06.787611: step: 558/1545, loss: 0.4138348400592804 2023-01-23 08:23:07.683155: step: 560/1545, loss: 0.13182492554187775 2023-01-23 08:23:08.562397: step: 562/1545, loss: 0.12464401125907898 2023-01-23 08:23:09.433139: step: 564/1545, loss: 0.2392706722021103 2023-01-23 08:23:10.314385: step: 566/1545, loss: 0.671091616153717 2023-01-23 08:23:11.183227: step: 568/1545, loss: 0.7055193185806274 2023-01-23 08:23:12.084015: step: 570/1545, loss: 0.07363168895244598 2023-01-23 08:23:12.947655: step: 572/1545, loss: 0.5336834192276001 2023-01-23 08:23:13.787620: step: 574/1545, loss: 0.161874458193779 2023-01-23 08:23:14.619599: step: 576/1545, loss: 0.25544115900993347 2023-01-23 08:23:15.505193: step: 578/1545, loss: 0.41013655066490173 2023-01-23 08:23:16.464684: step: 580/1545, loss: 0.5980459451675415 2023-01-23 08:23:17.332377: step: 582/1545, loss: 0.20159444212913513 2023-01-23 08:23:18.205784: step: 584/1545, loss: 0.1554691195487976 2023-01-23 08:23:19.057410: step: 586/1545, loss: 0.8187537789344788 2023-01-23 08:23:19.890738: step: 588/1545, loss: 0.08502721786499023 2023-01-23 08:23:20.774006: step: 590/1545, loss: 0.24438133835792542 2023-01-23 08:23:21.640824: step: 592/1545, loss: 0.24939188361167908 2023-01-23 08:23:22.516544: step: 594/1545, loss: 0.47804179787635803 2023-01-23 08:23:23.429593: step: 596/1545, loss: 0.34373289346694946 2023-01-23 08:23:24.321166: step: 598/1545, loss: 0.1107393428683281 2023-01-23 08:23:25.249314: step: 600/1545, loss: 0.6151449680328369 2023-01-23 08:23:26.100001: step: 602/1545, loss: 0.4280276894569397 2023-01-23 08:23:27.016712: step: 604/1545, loss: 0.9031237959861755 2023-01-23 08:23:27.868238: step: 606/1545, loss: 0.3798249661922455 2023-01-23 08:23:28.813078: step: 608/1545, loss: 0.23448777198791504 2023-01-23 08:23:29.685839: step: 610/1545, loss: 2.708590507507324 2023-01-23 08:23:30.532526: step: 612/1545, loss: 0.644227147102356 2023-01-23 08:23:31.409253: step: 614/1545, loss: 0.22611096501350403 2023-01-23 08:23:32.263167: step: 616/1545, loss: 0.14572462439537048 2023-01-23 08:23:33.148047: step: 618/1545, loss: 0.2606574296951294 2023-01-23 08:23:34.069441: step: 620/1545, loss: 0.22870570421218872 2023-01-23 08:23:34.959396: step: 622/1545, loss: 0.4133188724517822 2023-01-23 08:23:35.822348: step: 624/1545, loss: 0.04520371928811073 2023-01-23 08:23:36.729788: step: 626/1545, loss: 0.1304684579372406 2023-01-23 08:23:37.616505: step: 628/1545, loss: 0.45211881399154663 2023-01-23 08:23:38.495479: step: 630/1545, loss: 0.20895041525363922 2023-01-23 08:23:39.358513: step: 632/1545, loss: 0.17085225880146027 2023-01-23 08:23:40.249365: step: 634/1545, loss: 0.18040676414966583 2023-01-23 08:23:41.083009: step: 636/1545, loss: 0.07872554659843445 2023-01-23 08:23:42.001708: step: 638/1545, loss: 0.2443261295557022 2023-01-23 08:23:42.873847: step: 640/1545, loss: 0.3983054459095001 2023-01-23 08:23:43.713596: step: 642/1545, loss: 0.46343734860420227 2023-01-23 08:23:44.571303: step: 644/1545, loss: 0.17729230225086212 2023-01-23 08:23:45.502418: step: 646/1545, loss: 0.0360853374004364 2023-01-23 08:23:46.362896: step: 648/1545, loss: 0.32079070806503296 2023-01-23 08:23:47.217829: step: 650/1545, loss: 0.2464536428451538 2023-01-23 08:23:48.067944: step: 652/1545, loss: 0.5350982546806335 2023-01-23 08:23:48.979689: step: 654/1545, loss: 0.27216246724128723 2023-01-23 08:23:49.863774: step: 656/1545, loss: 0.2782670259475708 2023-01-23 08:23:50.716674: step: 658/1545, loss: 0.28375643491744995 2023-01-23 08:23:51.578689: step: 660/1545, loss: 0.5511950850486755 2023-01-23 08:23:52.458960: step: 662/1545, loss: 0.3501667380332947 2023-01-23 08:23:53.365064: step: 664/1545, loss: 0.6190996170043945 2023-01-23 08:23:54.237573: step: 666/1545, loss: 0.1894877552986145 2023-01-23 08:23:55.200673: step: 668/1545, loss: 0.2753450870513916 2023-01-23 08:23:56.104199: step: 670/1545, loss: 0.3671140670776367 2023-01-23 08:23:56.962343: step: 672/1545, loss: 0.16735824942588806 2023-01-23 08:23:57.882967: step: 674/1545, loss: 0.49928322434425354 2023-01-23 08:23:58.780915: step: 676/1545, loss: 0.39998871088027954 2023-01-23 08:23:59.657017: step: 678/1545, loss: 0.6281168460845947 2023-01-23 08:24:00.538808: step: 680/1545, loss: 0.2712298035621643 2023-01-23 08:24:01.444688: step: 682/1545, loss: 0.3196486532688141 2023-01-23 08:24:02.312489: step: 684/1545, loss: 2.538546562194824 2023-01-23 08:24:03.211196: step: 686/1545, loss: 0.22070570290088654 2023-01-23 08:24:04.058339: step: 688/1545, loss: 0.6907129883766174 2023-01-23 08:24:04.963210: step: 690/1545, loss: 0.2347116470336914 2023-01-23 08:24:05.879222: step: 692/1545, loss: 0.11070369929075241 2023-01-23 08:24:06.774881: step: 694/1545, loss: 0.19090035557746887 2023-01-23 08:24:07.653597: step: 696/1545, loss: 0.46647828817367554 2023-01-23 08:24:08.513873: step: 698/1545, loss: 0.33648326992988586 2023-01-23 08:24:09.429355: step: 700/1545, loss: 0.31569957733154297 2023-01-23 08:24:10.323884: step: 702/1545, loss: 2.8327083587646484 2023-01-23 08:24:11.258732: step: 704/1545, loss: 0.8492652177810669 2023-01-23 08:24:12.128260: step: 706/1545, loss: 0.24865590035915375 2023-01-23 08:24:13.013465: step: 708/1545, loss: 0.3654765188694 2023-01-23 08:24:13.909767: step: 710/1545, loss: 0.3648513853549957 2023-01-23 08:24:14.759548: step: 712/1545, loss: 0.31060367822647095 2023-01-23 08:24:15.645025: step: 714/1545, loss: 0.2529959976673126 2023-01-23 08:24:16.607012: step: 716/1545, loss: 1.3220323324203491 2023-01-23 08:24:17.483500: step: 718/1545, loss: 0.18269377946853638 2023-01-23 08:24:18.459399: step: 720/1545, loss: 1.2233153581619263 2023-01-23 08:24:19.369031: step: 722/1545, loss: 0.46530094742774963 2023-01-23 08:24:20.221721: step: 724/1545, loss: 0.27648603916168213 2023-01-23 08:24:21.075729: step: 726/1545, loss: 0.21584579348564148 2023-01-23 08:24:21.941866: step: 728/1545, loss: 0.29350969195365906 2023-01-23 08:24:22.813154: step: 730/1545, loss: 0.20242297649383545 2023-01-23 08:24:23.724584: step: 732/1545, loss: 0.605048418045044 2023-01-23 08:24:24.596560: step: 734/1545, loss: 0.413739413022995 2023-01-23 08:24:25.556014: step: 736/1545, loss: 0.37795618176460266 2023-01-23 08:24:26.437908: step: 738/1545, loss: 0.4325467646121979 2023-01-23 08:24:27.459460: step: 740/1545, loss: 0.27147039771080017 2023-01-23 08:24:28.339644: step: 742/1545, loss: 0.15954725444316864 2023-01-23 08:24:29.231809: step: 744/1545, loss: 0.37121474742889404 2023-01-23 08:24:30.069473: step: 746/1545, loss: 0.4823002815246582 2023-01-23 08:24:30.944564: step: 748/1545, loss: 0.3644842803478241 2023-01-23 08:24:31.817386: step: 750/1545, loss: 0.7386829257011414 2023-01-23 08:24:32.742219: step: 752/1545, loss: 0.40806278586387634 2023-01-23 08:24:33.630762: step: 754/1545, loss: 2.7354869842529297 2023-01-23 08:24:34.521234: step: 756/1545, loss: 0.7082183361053467 2023-01-23 08:24:35.376472: step: 758/1545, loss: 0.16911616921424866 2023-01-23 08:24:36.317347: step: 760/1545, loss: 0.4321542978286743 2023-01-23 08:24:37.219707: step: 762/1545, loss: 1.4642561674118042 2023-01-23 08:24:38.162021: step: 764/1545, loss: 0.3726235330104828 2023-01-23 08:24:39.053290: step: 766/1545, loss: 0.10920976847410202 2023-01-23 08:24:39.974411: step: 768/1545, loss: 0.324703186750412 2023-01-23 08:24:40.861010: step: 770/1545, loss: 0.30696091055870056 2023-01-23 08:24:41.793367: step: 772/1545, loss: 0.22582973539829254 2023-01-23 08:24:42.846361: step: 774/1545, loss: 0.2513984441757202 2023-01-23 08:24:43.780153: step: 776/1545, loss: 0.24284018576145172 2023-01-23 08:24:44.700932: step: 778/1545, loss: 0.47364187240600586 2023-01-23 08:24:45.630424: step: 780/1545, loss: 0.4611397385597229 2023-01-23 08:24:46.590097: step: 782/1545, loss: 0.30679085850715637 2023-01-23 08:24:47.428478: step: 784/1545, loss: 0.16375842690467834 2023-01-23 08:24:48.307295: step: 786/1545, loss: 0.7849260568618774 2023-01-23 08:24:49.245491: step: 788/1545, loss: 0.30824971199035645 2023-01-23 08:24:50.096569: step: 790/1545, loss: 0.769131064414978 2023-01-23 08:24:51.047594: step: 792/1545, loss: 0.19879955053329468 2023-01-23 08:24:51.928005: step: 794/1545, loss: 0.6715943813323975 2023-01-23 08:24:52.844245: step: 796/1545, loss: 0.2445518970489502 2023-01-23 08:24:53.709607: step: 798/1545, loss: 0.2187676578760147 2023-01-23 08:24:54.612994: step: 800/1545, loss: 0.4287286102771759 2023-01-23 08:24:55.521654: step: 802/1545, loss: 0.37334251403808594 2023-01-23 08:24:56.370302: step: 804/1545, loss: 0.2736855149269104 2023-01-23 08:24:57.243197: step: 806/1545, loss: 0.10532509535551071 2023-01-23 08:24:58.140900: step: 808/1545, loss: 6.6627678871154785 2023-01-23 08:24:59.066397: step: 810/1545, loss: 0.3762513995170593 2023-01-23 08:24:59.926781: step: 812/1545, loss: 0.43923160433769226 2023-01-23 08:25:00.930406: step: 814/1545, loss: 0.3974834978580475 2023-01-23 08:25:01.861160: step: 816/1545, loss: 0.12065061181783676 2023-01-23 08:25:02.711328: step: 818/1545, loss: 0.2048652470111847 2023-01-23 08:25:03.634293: step: 820/1545, loss: 0.3987833857536316 2023-01-23 08:25:04.502243: step: 822/1545, loss: 0.2374114990234375 2023-01-23 08:25:05.366903: step: 824/1545, loss: 0.4028421938419342 2023-01-23 08:25:06.233197: step: 826/1545, loss: 0.12609492242336273 2023-01-23 08:25:07.123176: step: 828/1545, loss: 0.05895567312836647 2023-01-23 08:25:07.992787: step: 830/1545, loss: 0.526795506477356 2023-01-23 08:25:08.852088: step: 832/1545, loss: 0.2233232706785202 2023-01-23 08:25:09.755294: step: 834/1545, loss: 0.695853590965271 2023-01-23 08:25:10.675765: step: 836/1545, loss: 0.65350341796875 2023-01-23 08:25:11.529857: step: 838/1545, loss: 0.7119008302688599 2023-01-23 08:25:12.412415: step: 840/1545, loss: 0.3192494213581085 2023-01-23 08:25:13.305532: step: 842/1545, loss: 1.749097228050232 2023-01-23 08:25:14.153458: step: 844/1545, loss: 0.15266506373882294 2023-01-23 08:25:15.019310: step: 846/1545, loss: 0.16974841058254242 2023-01-23 08:25:15.898310: step: 848/1545, loss: 0.18600207567214966 2023-01-23 08:25:16.782051: step: 850/1545, loss: 0.6196693778038025 2023-01-23 08:25:17.631020: step: 852/1545, loss: 0.20173394680023193 2023-01-23 08:25:18.560019: step: 854/1545, loss: 0.6433372497558594 2023-01-23 08:25:19.429682: step: 856/1545, loss: 0.1133861318230629 2023-01-23 08:25:20.295078: step: 858/1545, loss: 0.2416609227657318 2023-01-23 08:25:21.218952: step: 860/1545, loss: 0.14307686686515808 2023-01-23 08:25:22.133543: step: 862/1545, loss: 0.5626336932182312 2023-01-23 08:25:23.029608: step: 864/1545, loss: 0.19931818544864655 2023-01-23 08:25:23.888769: step: 866/1545, loss: 0.24470332264900208 2023-01-23 08:25:24.826567: step: 868/1545, loss: 0.24789534509181976 2023-01-23 08:25:25.747659: step: 870/1545, loss: 0.3471439480781555 2023-01-23 08:25:26.649684: step: 872/1545, loss: 0.29216673970222473 2023-01-23 08:25:27.510656: step: 874/1545, loss: 0.6967616081237793 2023-01-23 08:25:28.385384: step: 876/1545, loss: 0.23198236525058746 2023-01-23 08:25:29.245927: step: 878/1545, loss: 0.3274419903755188 2023-01-23 08:25:30.094564: step: 880/1545, loss: 0.31802642345428467 2023-01-23 08:25:31.082737: step: 882/1545, loss: 0.4455302655696869 2023-01-23 08:25:32.001900: step: 884/1545, loss: 0.47699642181396484 2023-01-23 08:25:32.898028: step: 886/1545, loss: 0.5427494645118713 2023-01-23 08:25:33.755823: step: 888/1545, loss: 0.2492489367723465 2023-01-23 08:25:34.655445: step: 890/1545, loss: 0.2665265202522278 2023-01-23 08:25:35.603426: step: 892/1545, loss: 0.5205220580101013 2023-01-23 08:25:36.447164: step: 894/1545, loss: 0.13009609282016754 2023-01-23 08:25:37.331861: step: 896/1545, loss: 0.32035988569259644 2023-01-23 08:25:38.197861: step: 898/1545, loss: 0.3693698048591614 2023-01-23 08:25:39.036776: step: 900/1545, loss: 0.2570876479148865 2023-01-23 08:25:39.895967: step: 902/1545, loss: 0.32051774859428406 2023-01-23 08:25:40.798047: step: 904/1545, loss: 1.4271271228790283 2023-01-23 08:25:41.708835: step: 906/1545, loss: 0.20251227915287018 2023-01-23 08:25:42.578211: step: 908/1545, loss: 0.1615048497915268 2023-01-23 08:25:43.530078: step: 910/1545, loss: 2.7765276432037354 2023-01-23 08:25:44.437896: step: 912/1545, loss: 0.5170301198959351 2023-01-23 08:25:45.339591: step: 914/1545, loss: 0.6563223004341125 2023-01-23 08:25:46.260511: step: 916/1545, loss: 0.3662705719470978 2023-01-23 08:25:47.180654: step: 918/1545, loss: 0.1457379013299942 2023-01-23 08:25:48.116891: step: 920/1545, loss: 0.4727739691734314 2023-01-23 08:25:48.989217: step: 922/1545, loss: 0.3043230175971985 2023-01-23 08:25:49.876736: step: 924/1545, loss: 0.43938636779785156 2023-01-23 08:25:50.788096: step: 926/1545, loss: 0.2754463851451874 2023-01-23 08:25:51.757150: step: 928/1545, loss: 0.2532011568546295 2023-01-23 08:25:52.643930: step: 930/1545, loss: 0.34244832396507263 2023-01-23 08:25:53.561320: step: 932/1545, loss: 0.9868752956390381 2023-01-23 08:25:54.524095: step: 934/1545, loss: 0.7347595691680908 2023-01-23 08:25:55.431742: step: 936/1545, loss: 0.3756832480430603 2023-01-23 08:25:56.323949: step: 938/1545, loss: 0.42481034994125366 2023-01-23 08:25:57.205842: step: 940/1545, loss: 0.21591122448444366 2023-01-23 08:25:58.108923: step: 942/1545, loss: 0.22632884979248047 2023-01-23 08:25:59.013366: step: 944/1545, loss: 0.27358773350715637 2023-01-23 08:25:59.950099: step: 946/1545, loss: 0.7955116629600525 2023-01-23 08:26:00.905443: step: 948/1545, loss: 0.282259076833725 2023-01-23 08:26:01.786819: step: 950/1545, loss: 0.45364540815353394 2023-01-23 08:26:02.660242: step: 952/1545, loss: 0.2494903951883316 2023-01-23 08:26:03.583182: step: 954/1545, loss: 0.19640757143497467 2023-01-23 08:26:04.453055: step: 956/1545, loss: 0.1795770227909088 2023-01-23 08:26:05.359027: step: 958/1545, loss: 0.4381137490272522 2023-01-23 08:26:06.213604: step: 960/1545, loss: 0.2722416818141937 2023-01-23 08:26:07.055392: step: 962/1545, loss: 0.17753103375434875 2023-01-23 08:26:07.945462: step: 964/1545, loss: 0.18297111988067627 2023-01-23 08:26:08.863590: step: 966/1545, loss: 0.672457218170166 2023-01-23 08:26:09.739205: step: 968/1545, loss: 0.5781657695770264 2023-01-23 08:26:10.598507: step: 970/1545, loss: 0.39891287684440613 2023-01-23 08:26:11.544084: step: 972/1545, loss: 0.27788618206977844 2023-01-23 08:26:12.445828: step: 974/1545, loss: 0.24124662578105927 2023-01-23 08:26:13.294807: step: 976/1545, loss: 0.10175706446170807 2023-01-23 08:26:14.169458: step: 978/1545, loss: 0.19563546776771545 2023-01-23 08:26:15.097389: step: 980/1545, loss: 0.26407137513160706 2023-01-23 08:26:15.972585: step: 982/1545, loss: 0.37429600954055786 2023-01-23 08:26:16.826716: step: 984/1545, loss: 0.5651313066482544 2023-01-23 08:26:17.787813: step: 986/1545, loss: 0.31697627902030945 2023-01-23 08:26:18.657606: step: 988/1545, loss: 0.7279863953590393 2023-01-23 08:26:19.539668: step: 990/1545, loss: 0.4686671793460846 2023-01-23 08:26:20.418820: step: 992/1545, loss: 0.15238678455352783 2023-01-23 08:26:21.322848: step: 994/1545, loss: 0.5358596444129944 2023-01-23 08:26:22.234117: step: 996/1545, loss: 3.120999813079834 2023-01-23 08:26:23.133545: step: 998/1545, loss: 0.17685958743095398 2023-01-23 08:26:24.009459: step: 1000/1545, loss: 0.963981032371521 2023-01-23 08:26:24.904218: step: 1002/1545, loss: 0.11194866895675659 2023-01-23 08:26:25.755700: step: 1004/1545, loss: 0.15568940341472626 2023-01-23 08:26:26.633907: step: 1006/1545, loss: 0.4612118601799011 2023-01-23 08:26:27.507112: step: 1008/1545, loss: 0.18685759603977203 2023-01-23 08:26:28.382589: step: 1010/1545, loss: 0.3894011974334717 2023-01-23 08:26:29.290051: step: 1012/1545, loss: 0.7254198789596558 2023-01-23 08:26:30.193687: step: 1014/1545, loss: 0.33113083243370056 2023-01-23 08:26:31.080188: step: 1016/1545, loss: 0.09983427822589874 2023-01-23 08:26:31.986014: step: 1018/1545, loss: 0.5184084177017212 2023-01-23 08:26:32.853342: step: 1020/1545, loss: 0.5219588279724121 2023-01-23 08:26:33.762226: step: 1022/1545, loss: 0.9367364645004272 2023-01-23 08:26:34.614127: step: 1024/1545, loss: 0.15589508414268494 2023-01-23 08:26:35.504756: step: 1026/1545, loss: 0.11246653646230698 2023-01-23 08:26:36.428608: step: 1028/1545, loss: 0.0438506044447422 2023-01-23 08:26:37.342879: step: 1030/1545, loss: 1.0832380056381226 2023-01-23 08:26:38.229769: step: 1032/1545, loss: 0.16701897978782654 2023-01-23 08:26:39.081148: step: 1034/1545, loss: 0.4095134437084198 2023-01-23 08:26:39.954491: step: 1036/1545, loss: 5.729809284210205 2023-01-23 08:26:40.849499: step: 1038/1545, loss: 0.2712983191013336 2023-01-23 08:26:41.728751: step: 1040/1545, loss: 0.22819097340106964 2023-01-23 08:26:42.674308: step: 1042/1545, loss: 0.12558600306510925 2023-01-23 08:26:43.627437: step: 1044/1545, loss: 0.2116725742816925 2023-01-23 08:26:44.537501: step: 1046/1545, loss: 0.3933785855770111 2023-01-23 08:26:45.446526: step: 1048/1545, loss: 0.6478051543235779 2023-01-23 08:26:46.338742: step: 1050/1545, loss: 0.22254040837287903 2023-01-23 08:26:47.202947: step: 1052/1545, loss: 0.4075830578804016 2023-01-23 08:26:48.035066: step: 1054/1545, loss: 0.1092291995882988 2023-01-23 08:26:48.900189: step: 1056/1545, loss: 0.3822938799858093 2023-01-23 08:26:49.782788: step: 1058/1545, loss: 0.453023761510849 2023-01-23 08:26:50.702785: step: 1060/1545, loss: 2.216118812561035 2023-01-23 08:26:51.547603: step: 1062/1545, loss: 0.4551454484462738 2023-01-23 08:26:52.457662: step: 1064/1545, loss: 0.23388229310512543 2023-01-23 08:26:53.338844: step: 1066/1545, loss: 0.504848062992096 2023-01-23 08:26:54.179362: step: 1068/1545, loss: 0.2408318817615509 2023-01-23 08:26:55.080138: step: 1070/1545, loss: 0.3189663290977478 2023-01-23 08:26:55.948799: step: 1072/1545, loss: 1.4144494533538818 2023-01-23 08:26:56.821921: step: 1074/1545, loss: 0.35618147253990173 2023-01-23 08:26:57.670523: step: 1076/1545, loss: 0.3714698553085327 2023-01-23 08:26:58.561014: step: 1078/1545, loss: 1.3478798866271973 2023-01-23 08:26:59.480590: step: 1080/1545, loss: 0.4780733287334442 2023-01-23 08:27:00.362159: step: 1082/1545, loss: 0.21797627210617065 2023-01-23 08:27:01.270294: step: 1084/1545, loss: 0.09050456434488297 2023-01-23 08:27:02.141560: step: 1086/1545, loss: 0.5036405324935913 2023-01-23 08:27:03.071064: step: 1088/1545, loss: 0.35064682364463806 2023-01-23 08:27:03.951149: step: 1090/1545, loss: 0.3711889386177063 2023-01-23 08:27:04.816592: step: 1092/1545, loss: 0.6919298768043518 2023-01-23 08:27:05.715116: step: 1094/1545, loss: 0.4398505389690399 2023-01-23 08:27:06.598978: step: 1096/1545, loss: 0.2501225769519806 2023-01-23 08:27:07.504510: step: 1098/1545, loss: 0.3305271565914154 2023-01-23 08:27:08.478166: step: 1100/1545, loss: 1.3416153192520142 2023-01-23 08:27:09.415962: step: 1102/1545, loss: 3.1311824321746826 2023-01-23 08:27:10.313556: step: 1104/1545, loss: 0.2298327535390854 2023-01-23 08:27:11.183035: step: 1106/1545, loss: 0.3062640130519867 2023-01-23 08:27:12.048662: step: 1108/1545, loss: 0.5623946785926819 2023-01-23 08:27:13.026585: step: 1110/1545, loss: 0.6248477101325989 2023-01-23 08:27:13.885259: step: 1112/1545, loss: 0.26635897159576416 2023-01-23 08:27:14.828998: step: 1114/1545, loss: 0.876929521560669 2023-01-23 08:27:15.686878: step: 1116/1545, loss: 0.055387090891599655 2023-01-23 08:27:16.550134: step: 1118/1545, loss: 0.13754050433635712 2023-01-23 08:27:17.418273: step: 1120/1545, loss: 0.25294020771980286 2023-01-23 08:27:18.389945: step: 1122/1545, loss: 0.834295392036438 2023-01-23 08:27:19.344985: step: 1124/1545, loss: 0.26352444291114807 2023-01-23 08:27:20.194834: step: 1126/1545, loss: 0.4496830999851227 2023-01-23 08:27:21.092363: step: 1128/1545, loss: 0.5590044856071472 2023-01-23 08:27:21.995624: step: 1130/1545, loss: 0.23533323407173157 2023-01-23 08:27:22.870358: step: 1132/1545, loss: 0.5383021235466003 2023-01-23 08:27:23.775515: step: 1134/1545, loss: 0.3162176311016083 2023-01-23 08:27:24.654138: step: 1136/1545, loss: 0.48424264788627625 2023-01-23 08:27:25.576084: step: 1138/1545, loss: 0.1775815784931183 2023-01-23 08:27:26.455668: step: 1140/1545, loss: 0.08179203420877457 2023-01-23 08:27:27.394338: step: 1142/1545, loss: 0.43006864190101624 2023-01-23 08:27:28.328475: step: 1144/1545, loss: 0.43992990255355835 2023-01-23 08:27:29.276653: step: 1146/1545, loss: 0.19610054790973663 2023-01-23 08:27:30.129662: step: 1148/1545, loss: 0.22202131152153015 2023-01-23 08:27:30.996857: step: 1150/1545, loss: 0.34211522340774536 2023-01-23 08:27:31.902085: step: 1152/1545, loss: 0.35190311074256897 2023-01-23 08:27:32.779470: step: 1154/1545, loss: 0.7809068560600281 2023-01-23 08:27:33.619464: step: 1156/1545, loss: 0.280566930770874 2023-01-23 08:27:34.510801: step: 1158/1545, loss: 2.883193254470825 2023-01-23 08:27:35.369356: step: 1160/1545, loss: 0.6329807639122009 2023-01-23 08:27:36.374406: step: 1162/1545, loss: 0.30264151096343994 2023-01-23 08:27:37.273712: step: 1164/1545, loss: 0.3383519947528839 2023-01-23 08:27:38.172092: step: 1166/1545, loss: 2.24971342086792 2023-01-23 08:27:39.039558: step: 1168/1545, loss: 0.49039027094841003 2023-01-23 08:27:39.895047: step: 1170/1545, loss: 0.22881212830543518 2023-01-23 08:27:40.830169: step: 1172/1545, loss: 0.762097179889679 2023-01-23 08:27:41.784408: step: 1174/1545, loss: 0.39664900302886963 2023-01-23 08:27:42.659239: step: 1176/1545, loss: 0.4269060790538788 2023-01-23 08:27:43.538220: step: 1178/1545, loss: 0.4248223900794983 2023-01-23 08:27:44.437001: step: 1180/1545, loss: 0.8526577353477478 2023-01-23 08:27:45.353280: step: 1182/1545, loss: 0.7908011078834534 2023-01-23 08:27:46.236833: step: 1184/1545, loss: 0.5969349145889282 2023-01-23 08:27:47.117363: step: 1186/1545, loss: 0.5182632207870483 2023-01-23 08:27:48.019297: step: 1188/1545, loss: 0.15284237265586853 2023-01-23 08:27:48.878780: step: 1190/1545, loss: 0.20810042321681976 2023-01-23 08:27:49.728948: step: 1192/1545, loss: 0.12590010464191437 2023-01-23 08:27:50.598655: step: 1194/1545, loss: 0.43526288866996765 2023-01-23 08:27:51.450004: step: 1196/1545, loss: 0.27411240339279175 2023-01-23 08:27:52.324192: step: 1198/1545, loss: 0.1568247526884079 2023-01-23 08:27:53.175400: step: 1200/1545, loss: 0.2314402312040329 2023-01-23 08:27:54.020285: step: 1202/1545, loss: 0.8148378133773804 2023-01-23 08:27:54.902839: step: 1204/1545, loss: 0.970531702041626 2023-01-23 08:27:55.802037: step: 1206/1545, loss: 0.5433219075202942 2023-01-23 08:27:56.696812: step: 1208/1545, loss: 0.3946722745895386 2023-01-23 08:27:57.573949: step: 1210/1545, loss: 0.38500693440437317 2023-01-23 08:27:58.460114: step: 1212/1545, loss: 0.44176459312438965 2023-01-23 08:27:59.360809: step: 1214/1545, loss: 0.37546226382255554 2023-01-23 08:28:00.308426: step: 1216/1545, loss: 0.2665597200393677 2023-01-23 08:28:01.188750: step: 1218/1545, loss: 0.7076751589775085 2023-01-23 08:28:02.064498: step: 1220/1545, loss: 0.5331651568412781 2023-01-23 08:28:02.907541: step: 1222/1545, loss: 0.40876996517181396 2023-01-23 08:28:03.802690: step: 1224/1545, loss: 0.3359563946723938 2023-01-23 08:28:04.655737: step: 1226/1545, loss: 0.0971842035651207 2023-01-23 08:28:05.541191: step: 1228/1545, loss: 0.19419120252132416 2023-01-23 08:28:06.394077: step: 1230/1545, loss: 0.4263826012611389 2023-01-23 08:28:07.282612: step: 1232/1545, loss: 0.3156161308288574 2023-01-23 08:28:08.184662: step: 1234/1545, loss: 0.09292511641979218 2023-01-23 08:28:09.027199: step: 1236/1545, loss: 0.20628996193408966 2023-01-23 08:28:09.930549: step: 1238/1545, loss: 0.11047109216451645 2023-01-23 08:28:10.802560: step: 1240/1545, loss: 0.40907877683639526 2023-01-23 08:28:11.752769: step: 1242/1545, loss: 0.4283140003681183 2023-01-23 08:28:12.627857: step: 1244/1545, loss: 5.575591564178467 2023-01-23 08:28:13.493423: step: 1246/1545, loss: 0.036222510039806366 2023-01-23 08:28:14.359748: step: 1248/1545, loss: 0.519174337387085 2023-01-23 08:28:15.246242: step: 1250/1545, loss: 0.3612343370914459 2023-01-23 08:28:16.145884: step: 1252/1545, loss: 0.7220928072929382 2023-01-23 08:28:17.065540: step: 1254/1545, loss: 0.33631429076194763 2023-01-23 08:28:17.968565: step: 1256/1545, loss: 0.43594446778297424 2023-01-23 08:28:18.857284: step: 1258/1545, loss: 0.8627870678901672 2023-01-23 08:28:19.724660: step: 1260/1545, loss: 0.3080085813999176 2023-01-23 08:28:20.670122: step: 1262/1545, loss: 0.16681325435638428 2023-01-23 08:28:21.577034: step: 1264/1545, loss: 0.8239082098007202 2023-01-23 08:28:22.469516: step: 1266/1545, loss: 0.2366814911365509 2023-01-23 08:28:23.389630: step: 1268/1545, loss: 0.6784024834632874 2023-01-23 08:28:24.331587: step: 1270/1545, loss: 0.17201992869377136 2023-01-23 08:28:25.161864: step: 1272/1545, loss: 0.12193867564201355 2023-01-23 08:28:26.044093: step: 1274/1545, loss: 0.05422961339354515 2023-01-23 08:28:27.037746: step: 1276/1545, loss: 0.24605655670166016 2023-01-23 08:28:27.930507: step: 1278/1545, loss: 0.2080211490392685 2023-01-23 08:28:28.842201: step: 1280/1545, loss: 0.06938716769218445 2023-01-23 08:28:29.716435: step: 1282/1545, loss: 1.0451397895812988 2023-01-23 08:28:30.681179: step: 1284/1545, loss: 0.2255082130432129 2023-01-23 08:28:31.534241: step: 1286/1545, loss: 0.794059157371521 2023-01-23 08:28:32.410228: step: 1288/1545, loss: 0.27115005254745483 2023-01-23 08:28:33.277073: step: 1290/1545, loss: 0.4167213439941406 2023-01-23 08:28:34.130863: step: 1292/1545, loss: 0.17999346554279327 2023-01-23 08:28:34.995312: step: 1294/1545, loss: 0.9710525274276733 2023-01-23 08:28:35.895646: step: 1296/1545, loss: 0.3539856970310211 2023-01-23 08:28:36.793253: step: 1298/1545, loss: 0.4259068965911865 2023-01-23 08:28:37.655879: step: 1300/1545, loss: 0.3059183955192566 2023-01-23 08:28:38.585100: step: 1302/1545, loss: 0.0886099711060524 2023-01-23 08:28:39.489733: step: 1304/1545, loss: 0.6809391379356384 2023-01-23 08:28:40.381797: step: 1306/1545, loss: 0.19563426077365875 2023-01-23 08:28:41.269030: step: 1308/1545, loss: 0.13815933465957642 2023-01-23 08:28:42.172518: step: 1310/1545, loss: 0.32050973176956177 2023-01-23 08:28:43.015075: step: 1312/1545, loss: 0.5525563359260559 2023-01-23 08:28:43.886331: step: 1314/1545, loss: 0.38559943437576294 2023-01-23 08:28:44.799306: step: 1316/1545, loss: 0.4587639272212982 2023-01-23 08:28:45.709818: step: 1318/1545, loss: 1.3129873275756836 2023-01-23 08:28:46.585885: step: 1320/1545, loss: 0.28983017802238464 2023-01-23 08:28:47.437530: step: 1322/1545, loss: 0.16898326575756073 2023-01-23 08:28:48.283347: step: 1324/1545, loss: 0.7484732866287231 2023-01-23 08:28:49.228127: step: 1326/1545, loss: 2.9308230876922607 2023-01-23 08:28:50.104986: step: 1328/1545, loss: 0.17765367031097412 2023-01-23 08:28:51.008273: step: 1330/1545, loss: 0.10197895020246506 2023-01-23 08:28:51.930015: step: 1332/1545, loss: 0.5182150602340698 2023-01-23 08:28:52.776812: step: 1334/1545, loss: 0.15203291177749634 2023-01-23 08:28:53.642261: step: 1336/1545, loss: 0.3019307553768158 2023-01-23 08:28:54.527360: step: 1338/1545, loss: 0.35165145993232727 2023-01-23 08:28:55.397529: step: 1340/1545, loss: 0.17178452014923096 2023-01-23 08:28:56.342202: step: 1342/1545, loss: 2.0448215007781982 2023-01-23 08:28:57.202393: step: 1344/1545, loss: 0.24007603526115417 2023-01-23 08:28:58.067122: step: 1346/1545, loss: 0.3831716477870941 2023-01-23 08:28:58.984708: step: 1348/1545, loss: 0.8544678688049316 2023-01-23 08:28:59.854617: step: 1350/1545, loss: 0.3862138092517853 2023-01-23 08:29:00.749695: step: 1352/1545, loss: 1.0167016983032227 2023-01-23 08:29:01.645062: step: 1354/1545, loss: 0.13172169029712677 2023-01-23 08:29:02.526459: step: 1356/1545, loss: 0.7490949630737305 2023-01-23 08:29:03.415781: step: 1358/1545, loss: 0.3235318660736084 2023-01-23 08:29:04.331222: step: 1360/1545, loss: 5.281076908111572 2023-01-23 08:29:05.203152: step: 1362/1545, loss: 0.3850027620792389 2023-01-23 08:29:06.076650: step: 1364/1545, loss: 0.4355004131793976 2023-01-23 08:29:06.952435: step: 1366/1545, loss: 0.1892947554588318 2023-01-23 08:29:07.843276: step: 1368/1545, loss: 0.3690386414527893 2023-01-23 08:29:08.763030: step: 1370/1545, loss: 0.6830748915672302 2023-01-23 08:29:09.645495: step: 1372/1545, loss: 0.4011932611465454 2023-01-23 08:29:10.492473: step: 1374/1545, loss: 0.2047203928232193 2023-01-23 08:29:11.439060: step: 1376/1545, loss: 0.3441754877567291 2023-01-23 08:29:12.270510: step: 1378/1545, loss: 0.8767154216766357 2023-01-23 08:29:13.175432: step: 1380/1545, loss: 0.682643473148346 2023-01-23 08:29:14.067953: step: 1382/1545, loss: 0.3464193344116211 2023-01-23 08:29:14.934904: step: 1384/1545, loss: 0.7150097489356995 2023-01-23 08:29:15.839281: step: 1386/1545, loss: 0.2749432325363159 2023-01-23 08:29:16.829724: step: 1388/1545, loss: 0.36729907989501953 2023-01-23 08:29:17.701865: step: 1390/1545, loss: 0.4674486517906189 2023-01-23 08:29:18.592115: step: 1392/1545, loss: 0.10982564091682434 2023-01-23 08:29:19.491487: step: 1394/1545, loss: 0.05218447372317314 2023-01-23 08:29:20.394167: step: 1396/1545, loss: 0.07562847435474396 2023-01-23 08:29:21.251200: step: 1398/1545, loss: 0.07120746374130249 2023-01-23 08:29:22.165263: step: 1400/1545, loss: 0.4637283980846405 2023-01-23 08:29:23.035268: step: 1402/1545, loss: 0.06988713145256042 2023-01-23 08:29:23.918572: step: 1404/1545, loss: 2.505280017852783 2023-01-23 08:29:24.801354: step: 1406/1545, loss: 0.1775033175945282 2023-01-23 08:29:25.661541: step: 1408/1545, loss: 0.47069698572158813 2023-01-23 08:29:26.547673: step: 1410/1545, loss: 1.7309584617614746 2023-01-23 08:29:27.422226: step: 1412/1545, loss: 0.16719205677509308 2023-01-23 08:29:28.312493: step: 1414/1545, loss: 0.2722145915031433 2023-01-23 08:29:29.203010: step: 1416/1545, loss: 0.1899244785308838 2023-01-23 08:29:30.083932: step: 1418/1545, loss: 0.2065485268831253 2023-01-23 08:29:30.991806: step: 1420/1545, loss: 0.7734096050262451 2023-01-23 08:29:31.886862: step: 1422/1545, loss: 0.42861154675483704 2023-01-23 08:29:32.766584: step: 1424/1545, loss: 0.31967484951019287 2023-01-23 08:29:33.617593: step: 1426/1545, loss: 0.2930915057659149 2023-01-23 08:29:34.509061: step: 1428/1545, loss: 0.28880006074905396 2023-01-23 08:29:35.364445: step: 1430/1545, loss: 0.3365599513053894 2023-01-23 08:29:36.265992: step: 1432/1545, loss: 0.5676490664482117 2023-01-23 08:29:37.121442: step: 1434/1545, loss: 0.137400284409523 2023-01-23 08:29:38.036346: step: 1436/1545, loss: 0.3700002431869507 2023-01-23 08:29:38.910357: step: 1438/1545, loss: 0.7843899726867676 2023-01-23 08:29:39.821817: step: 1440/1545, loss: 0.5607635378837585 2023-01-23 08:29:40.716740: step: 1442/1545, loss: 0.4579419493675232 2023-01-23 08:29:41.550786: step: 1444/1545, loss: 0.12996181845664978 2023-01-23 08:29:42.478978: step: 1446/1545, loss: 0.2614392042160034 2023-01-23 08:29:43.369949: step: 1448/1545, loss: 0.1270938515663147 2023-01-23 08:29:44.274184: step: 1450/1545, loss: 0.05677678808569908 2023-01-23 08:29:45.214331: step: 1452/1545, loss: 0.9298884868621826 2023-01-23 08:29:46.106801: step: 1454/1545, loss: 0.10583580285310745 2023-01-23 08:29:47.041879: step: 1456/1545, loss: 0.48084357380867004 2023-01-23 08:29:48.003481: step: 1458/1545, loss: 0.08323872834444046 2023-01-23 08:29:48.991491: step: 1460/1545, loss: 0.36920467019081116 2023-01-23 08:29:49.923566: step: 1462/1545, loss: 0.2782581150531769 2023-01-23 08:29:50.804151: step: 1464/1545, loss: 0.23947802186012268 2023-01-23 08:29:51.683417: step: 1466/1545, loss: 0.17934134602546692 2023-01-23 08:29:52.619631: step: 1468/1545, loss: 0.0761217251420021 2023-01-23 08:29:53.512160: step: 1470/1545, loss: 0.5088447332382202 2023-01-23 08:29:54.470468: step: 1472/1545, loss: 0.6064578890800476 2023-01-23 08:29:55.334871: step: 1474/1545, loss: 0.8488333225250244 2023-01-23 08:29:56.216376: step: 1476/1545, loss: 0.5435126423835754 2023-01-23 08:29:57.062237: step: 1478/1545, loss: 0.9786497950553894 2023-01-23 08:29:57.924270: step: 1480/1545, loss: 0.37922874093055725 2023-01-23 08:29:58.807826: step: 1482/1545, loss: 0.16684916615486145 2023-01-23 08:29:59.691919: step: 1484/1545, loss: 0.18730232119560242 2023-01-23 08:30:00.581306: step: 1486/1545, loss: 0.19084855914115906 2023-01-23 08:30:01.499093: step: 1488/1545, loss: 0.2444625198841095 2023-01-23 08:30:02.511193: step: 1490/1545, loss: 0.54426509141922 2023-01-23 08:30:03.399276: step: 1492/1545, loss: 0.5860215425491333 2023-01-23 08:30:04.268529: step: 1494/1545, loss: 0.401969313621521 2023-01-23 08:30:05.195567: step: 1496/1545, loss: 1.92153000831604 2023-01-23 08:30:06.062271: step: 1498/1545, loss: 0.33714744448661804 2023-01-23 08:30:06.907091: step: 1500/1545, loss: 0.28392866253852844 2023-01-23 08:30:07.817212: step: 1502/1545, loss: 0.5535476803779602 2023-01-23 08:30:08.703633: step: 1504/1545, loss: 0.4547085165977478 2023-01-23 08:30:09.527844: step: 1506/1545, loss: 0.08705982565879822 2023-01-23 08:30:10.427661: step: 1508/1545, loss: 0.5015043020248413 2023-01-23 08:30:11.282258: step: 1510/1545, loss: 1.0682607889175415 2023-01-23 08:30:12.177792: step: 1512/1545, loss: 0.3174704909324646 2023-01-23 08:30:13.063449: step: 1514/1545, loss: 0.1193285584449768 2023-01-23 08:30:13.997032: step: 1516/1545, loss: 0.541621744632721 2023-01-23 08:30:14.869299: step: 1518/1545, loss: 0.2118980586528778 2023-01-23 08:30:15.827685: step: 1520/1545, loss: 0.49133774638175964 2023-01-23 08:30:16.716568: step: 1522/1545, loss: 0.3936287462711334 2023-01-23 08:30:17.624230: step: 1524/1545, loss: 0.6154956817626953 2023-01-23 08:30:18.560863: step: 1526/1545, loss: 0.23640437424182892 2023-01-23 08:30:19.467664: step: 1528/1545, loss: 0.5423440337181091 2023-01-23 08:30:20.344364: step: 1530/1545, loss: 0.2957538068294525 2023-01-23 08:30:21.221899: step: 1532/1545, loss: 0.6034313440322876 2023-01-23 08:30:22.153764: step: 1534/1545, loss: 1.5534018278121948 2023-01-23 08:30:22.996442: step: 1536/1545, loss: 0.7240605354309082 2023-01-23 08:30:23.893263: step: 1538/1545, loss: 0.7999169826507568 2023-01-23 08:30:24.792103: step: 1540/1545, loss: 0.7069104909896851 2023-01-23 08:30:25.681899: step: 1542/1545, loss: 0.45954880118370056 2023-01-23 08:30:26.586717: step: 1544/1545, loss: 0.5391502380371094 2023-01-23 08:30:27.447059: step: 1546/1545, loss: 0.34855714440345764 2023-01-23 08:30:28.326917: step: 1548/1545, loss: 0.7073237299919128 2023-01-23 08:30:29.177666: step: 1550/1545, loss: 0.1507645845413208 2023-01-23 08:30:30.093588: step: 1552/1545, loss: 0.964219331741333 2023-01-23 08:30:31.040858: step: 1554/1545, loss: 0.0588802844285965 2023-01-23 08:30:31.975385: step: 1556/1545, loss: 0.08994530141353607 2023-01-23 08:30:32.845702: step: 1558/1545, loss: 0.17583173513412476 2023-01-23 08:30:33.692749: step: 1560/1545, loss: 0.313689649105072 2023-01-23 08:30:34.628558: step: 1562/1545, loss: 0.4569994807243347 2023-01-23 08:30:35.483632: step: 1564/1545, loss: 0.9388561844825745 2023-01-23 08:30:36.342970: step: 1566/1545, loss: 0.26872310042381287 2023-01-23 08:30:37.202967: step: 1568/1545, loss: 0.42477402091026306 2023-01-23 08:30:38.079905: step: 1570/1545, loss: 0.3546316921710968 2023-01-23 08:30:39.007237: step: 1572/1545, loss: 0.42437949776649475 2023-01-23 08:30:39.868147: step: 1574/1545, loss: 0.4589148461818695 2023-01-23 08:30:40.750892: step: 1576/1545, loss: 0.25550878047943115 2023-01-23 08:30:41.729518: step: 1578/1545, loss: 0.1008772999048233 2023-01-23 08:30:42.640917: step: 1580/1545, loss: 0.7242051959037781 2023-01-23 08:30:43.501220: step: 1582/1545, loss: 0.5006153583526611 2023-01-23 08:30:44.377142: step: 1584/1545, loss: 0.16180694103240967 2023-01-23 08:30:45.269613: step: 1586/1545, loss: 0.28834232687950134 2023-01-23 08:30:46.122601: step: 1588/1545, loss: 0.1384730339050293 2023-01-23 08:30:46.979537: step: 1590/1545, loss: 0.3050568103790283 2023-01-23 08:30:47.914980: step: 1592/1545, loss: 0.41241493821144104 2023-01-23 08:30:48.808105: step: 1594/1545, loss: 0.5449260473251343 2023-01-23 08:30:49.722748: step: 1596/1545, loss: 0.3950086236000061 2023-01-23 08:30:50.635752: step: 1598/1545, loss: 0.35421988368034363 2023-01-23 08:30:51.531758: step: 1600/1545, loss: 0.8241080641746521 2023-01-23 08:30:52.441505: step: 1602/1545, loss: 0.2454034388065338 2023-01-23 08:30:53.363040: step: 1604/1545, loss: 0.2618311643600464 2023-01-23 08:30:54.270571: step: 1606/1545, loss: 0.24415922164916992 2023-01-23 08:30:55.201126: step: 1608/1545, loss: 0.43660110235214233 2023-01-23 08:30:56.158927: step: 1610/1545, loss: 1.251936435699463 2023-01-23 08:30:57.061712: step: 1612/1545, loss: 0.21916046738624573 2023-01-23 08:30:57.997910: step: 1614/1545, loss: 0.37099123001098633 2023-01-23 08:30:58.861607: step: 1616/1545, loss: 0.1335848718881607 2023-01-23 08:30:59.735795: step: 1618/1545, loss: 0.6253269910812378 2023-01-23 08:31:00.668732: step: 1620/1545, loss: 0.5952563881874084 2023-01-23 08:31:01.537666: step: 1622/1545, loss: 2.634460926055908 2023-01-23 08:31:02.504351: step: 1624/1545, loss: 0.04699806869029999 2023-01-23 08:31:03.403355: step: 1626/1545, loss: 0.44582346081733704 2023-01-23 08:31:04.307290: step: 1628/1545, loss: 0.2102256417274475 2023-01-23 08:31:05.199324: step: 1630/1545, loss: 0.30284446477890015 2023-01-23 08:31:06.084212: step: 1632/1545, loss: 0.5526414513587952 2023-01-23 08:31:06.976986: step: 1634/1545, loss: 0.0822056457400322 2023-01-23 08:31:07.867483: step: 1636/1545, loss: 0.1654355525970459 2023-01-23 08:31:08.852884: step: 1638/1545, loss: 0.3631817698478699 2023-01-23 08:31:09.833412: step: 1640/1545, loss: 0.08929415047168732 2023-01-23 08:31:10.722466: step: 1642/1545, loss: 0.9517233371734619 2023-01-23 08:31:11.585601: step: 1644/1545, loss: 2.9214694499969482 2023-01-23 08:31:12.497116: step: 1646/1545, loss: 0.4336951971054077 2023-01-23 08:31:13.370508: step: 1648/1545, loss: 0.35554206371307373 2023-01-23 08:31:14.292952: step: 1650/1545, loss: 0.4780307412147522 2023-01-23 08:31:15.202093: step: 1652/1545, loss: 0.1298612505197525 2023-01-23 08:31:16.169565: step: 1654/1545, loss: 0.2924569547176361 2023-01-23 08:31:17.082755: step: 1656/1545, loss: 2.7921838760375977 2023-01-23 08:31:17.974599: step: 1658/1545, loss: 0.1575631946325302 2023-01-23 08:31:18.900940: step: 1660/1545, loss: 0.4339899718761444 2023-01-23 08:31:19.798219: step: 1662/1545, loss: 0.614652156829834 2023-01-23 08:31:20.672917: step: 1664/1545, loss: 0.5709084272384644 2023-01-23 08:31:21.571806: step: 1666/1545, loss: 0.3782070577144623 2023-01-23 08:31:22.426945: step: 1668/1545, loss: 0.24370457231998444 2023-01-23 08:31:23.319042: step: 1670/1545, loss: 0.32794302701950073 2023-01-23 08:31:24.205800: step: 1672/1545, loss: 1.2895636558532715 2023-01-23 08:31:25.090494: step: 1674/1545, loss: 0.1662495881319046 2023-01-23 08:31:26.000614: step: 1676/1545, loss: 0.7491455674171448 2023-01-23 08:31:26.894267: step: 1678/1545, loss: 0.634160041809082 2023-01-23 08:31:27.770693: step: 1680/1545, loss: 0.4070400893688202 2023-01-23 08:31:28.673207: step: 1682/1545, loss: 2.8561131954193115 2023-01-23 08:31:29.590846: step: 1684/1545, loss: 0.5055651664733887 2023-01-23 08:31:30.481906: step: 1686/1545, loss: 0.23373159766197205 2023-01-23 08:31:31.360812: step: 1688/1545, loss: 0.1842181384563446 2023-01-23 08:31:32.236871: step: 1690/1545, loss: 0.2896323800086975 2023-01-23 08:31:33.146498: step: 1692/1545, loss: 4.7669291496276855 2023-01-23 08:31:34.024818: step: 1694/1545, loss: 0.4190753996372223 2023-01-23 08:31:34.924330: step: 1696/1545, loss: 0.05252259969711304 2023-01-23 08:31:35.841858: step: 1698/1545, loss: 0.3601316213607788 2023-01-23 08:31:36.740874: step: 1700/1545, loss: 0.21522125601768494 2023-01-23 08:31:37.664009: step: 1702/1545, loss: 0.5579380393028259 2023-01-23 08:31:38.542174: step: 1704/1545, loss: 0.9414897561073303 2023-01-23 08:31:39.431351: step: 1706/1545, loss: 0.2714986801147461 2023-01-23 08:31:40.329041: step: 1708/1545, loss: 0.7040773034095764 2023-01-23 08:31:41.205712: step: 1710/1545, loss: 1.879573941230774 2023-01-23 08:31:42.128300: step: 1712/1545, loss: 0.2836983799934387 2023-01-23 08:31:43.027625: step: 1714/1545, loss: 0.14432987570762634 2023-01-23 08:31:43.986246: step: 1716/1545, loss: 0.20014508068561554 2023-01-23 08:31:44.861644: step: 1718/1545, loss: 0.13993503153324127 2023-01-23 08:31:45.812763: step: 1720/1545, loss: 0.24849604070186615 2023-01-23 08:31:46.656477: step: 1722/1545, loss: 0.1923559308052063 2023-01-23 08:31:47.550591: step: 1724/1545, loss: 0.3529544174671173 2023-01-23 08:31:48.468136: step: 1726/1545, loss: 0.2051343470811844 2023-01-23 08:31:49.372360: step: 1728/1545, loss: 0.22266806662082672 2023-01-23 08:31:50.256566: step: 1730/1545, loss: 0.31569185853004456 2023-01-23 08:31:51.120298: step: 1732/1545, loss: 0.33237767219543457 2023-01-23 08:31:52.028189: step: 1734/1545, loss: 0.39889612793922424 2023-01-23 08:31:52.910381: step: 1736/1545, loss: 0.25567030906677246 2023-01-23 08:31:53.787086: step: 1738/1545, loss: 0.40433427691459656 2023-01-23 08:31:54.665588: step: 1740/1545, loss: 0.6525630354881287 2023-01-23 08:31:55.509745: step: 1742/1545, loss: 0.11679816246032715 2023-01-23 08:31:56.367580: step: 1744/1545, loss: 0.12685997784137726 2023-01-23 08:31:57.233719: step: 1746/1545, loss: 0.15588660538196564 2023-01-23 08:31:58.060319: step: 1748/1545, loss: 0.09217926859855652 2023-01-23 08:31:58.938643: step: 1750/1545, loss: 0.36673060059547424 2023-01-23 08:31:59.797833: step: 1752/1545, loss: 0.46860501170158386 2023-01-23 08:32:00.663907: step: 1754/1545, loss: 0.49892085790634155 2023-01-23 08:32:01.523604: step: 1756/1545, loss: 0.7959874272346497 2023-01-23 08:32:02.424108: step: 1758/1545, loss: 0.3302808105945587 2023-01-23 08:32:03.347145: step: 1760/1545, loss: 0.7368432879447937 2023-01-23 08:32:04.271304: step: 1762/1545, loss: 0.40025123953819275 2023-01-23 08:32:05.179145: step: 1764/1545, loss: 0.8892374634742737 2023-01-23 08:32:06.102170: step: 1766/1545, loss: 0.36344125866889954 2023-01-23 08:32:06.975827: step: 1768/1545, loss: 0.48972249031066895 2023-01-23 08:32:07.854540: step: 1770/1545, loss: 2.2901558876037598 2023-01-23 08:32:08.727375: step: 1772/1545, loss: 0.589095413684845 2023-01-23 08:32:09.652286: step: 1774/1545, loss: 0.18358449637889862 2023-01-23 08:32:10.520505: step: 1776/1545, loss: 0.29299676418304443 2023-01-23 08:32:11.386329: step: 1778/1545, loss: 0.4941585063934326 2023-01-23 08:32:12.322014: step: 1780/1545, loss: 0.2673589587211609 2023-01-23 08:32:13.225206: step: 1782/1545, loss: 0.5363835692405701 2023-01-23 08:32:14.107832: step: 1784/1545, loss: 0.07440346479415894 2023-01-23 08:32:14.982862: step: 1786/1545, loss: 0.4756576716899872 2023-01-23 08:32:15.851592: step: 1788/1545, loss: 0.14901305735111237 2023-01-23 08:32:16.727205: step: 1790/1545, loss: 0.32089725136756897 2023-01-23 08:32:17.623574: step: 1792/1545, loss: 0.2654234766960144 2023-01-23 08:32:18.506802: step: 1794/1545, loss: 0.37411054968833923 2023-01-23 08:32:19.376696: step: 1796/1545, loss: 0.16853134334087372 2023-01-23 08:32:20.276998: step: 1798/1545, loss: 0.4980587065219879 2023-01-23 08:32:21.220125: step: 1800/1545, loss: 0.45340415835380554 2023-01-23 08:32:22.114722: step: 1802/1545, loss: 0.4352666437625885 2023-01-23 08:32:22.983817: step: 1804/1545, loss: 0.10552399605512619 2023-01-23 08:32:23.843562: step: 1806/1545, loss: 0.5430054664611816 2023-01-23 08:32:24.722200: step: 1808/1545, loss: 0.1700058877468109 2023-01-23 08:32:25.578744: step: 1810/1545, loss: 0.07653462141752243 2023-01-23 08:32:26.465359: step: 1812/1545, loss: 0.22087591886520386 2023-01-23 08:32:27.325139: step: 1814/1545, loss: 0.6741632223129272 2023-01-23 08:32:28.269769: step: 1816/1545, loss: 0.3524929881095886 2023-01-23 08:32:29.162794: step: 1818/1545, loss: 0.5040004253387451 2023-01-23 08:32:30.075018: step: 1820/1545, loss: 0.8791853785514832 2023-01-23 08:32:30.938322: step: 1822/1545, loss: 0.8868711590766907 2023-01-23 08:32:31.842688: step: 1824/1545, loss: 0.39312079548835754 2023-01-23 08:32:32.701572: step: 1826/1545, loss: 0.7050928473472595 2023-01-23 08:32:33.573624: step: 1828/1545, loss: 0.17900989949703217 2023-01-23 08:32:34.467680: step: 1830/1545, loss: 0.2265441119670868 2023-01-23 08:32:35.366953: step: 1832/1545, loss: 0.25600025057792664 2023-01-23 08:32:36.243449: step: 1834/1545, loss: 0.07655231654644012 2023-01-23 08:32:37.107593: step: 1836/1545, loss: 0.2949051856994629 2023-01-23 08:32:37.968305: step: 1838/1545, loss: 0.39507925510406494 2023-01-23 08:32:38.830334: step: 1840/1545, loss: 0.8352583050727844 2023-01-23 08:32:39.728114: step: 1842/1545, loss: 0.37273532152175903 2023-01-23 08:32:40.567820: step: 1844/1545, loss: 0.5559253096580505 2023-01-23 08:32:41.567417: step: 1846/1545, loss: 0.32203227281570435 2023-01-23 08:32:42.465545: step: 1848/1545, loss: 0.36440593004226685 2023-01-23 08:32:43.349043: step: 1850/1545, loss: 0.5630235075950623 2023-01-23 08:32:44.247323: step: 1852/1545, loss: 0.7457210421562195 2023-01-23 08:32:45.113434: step: 1854/1545, loss: 0.260562002658844 2023-01-23 08:32:46.005105: step: 1856/1545, loss: 0.31718477606773376 2023-01-23 08:32:46.897560: step: 1858/1545, loss: 0.27221471071243286 2023-01-23 08:32:47.854517: step: 1860/1545, loss: 1.061109185218811 2023-01-23 08:32:48.750820: step: 1862/1545, loss: 0.5114107728004456 2023-01-23 08:32:49.674304: step: 1864/1545, loss: 0.36392104625701904 2023-01-23 08:32:50.574684: step: 1866/1545, loss: 0.3094428777694702 2023-01-23 08:32:51.460419: step: 1868/1545, loss: 0.30004945397377014 2023-01-23 08:32:52.380754: step: 1870/1545, loss: 0.25994014739990234 2023-01-23 08:32:53.276228: step: 1872/1545, loss: 0.12531575560569763 2023-01-23 08:32:54.180995: step: 1874/1545, loss: 0.2244582623243332 2023-01-23 08:32:55.129464: step: 1876/1545, loss: 0.3576008975505829 2023-01-23 08:32:56.009875: step: 1878/1545, loss: 0.26799166202545166 2023-01-23 08:32:56.847915: step: 1880/1545, loss: 0.10675633698701859 2023-01-23 08:32:57.727822: step: 1882/1545, loss: 0.3117300570011139 2023-01-23 08:32:58.615132: step: 1884/1545, loss: 0.18128612637519836 2023-01-23 08:32:59.510514: step: 1886/1545, loss: 0.1400579810142517 2023-01-23 08:33:00.365955: step: 1888/1545, loss: 0.5786576867103577 2023-01-23 08:33:01.214151: step: 1890/1545, loss: 0.12416060268878937 2023-01-23 08:33:02.063829: step: 1892/1545, loss: 0.3345988094806671 2023-01-23 08:33:03.025285: step: 1894/1545, loss: 0.24354606866836548 2023-01-23 08:33:03.927695: step: 1896/1545, loss: 0.4680173695087433 2023-01-23 08:33:04.780747: step: 1898/1545, loss: 0.3653857409954071 2023-01-23 08:33:05.706221: step: 1900/1545, loss: 0.38267073035240173 2023-01-23 08:33:06.568086: step: 1902/1545, loss: 0.43884578347206116 2023-01-23 08:33:07.494330: step: 1904/1545, loss: 0.2191569209098816 2023-01-23 08:33:08.465591: step: 1906/1545, loss: 0.3236025869846344 2023-01-23 08:33:09.357376: step: 1908/1545, loss: 0.11901763081550598 2023-01-23 08:33:10.232686: step: 1910/1545, loss: 0.6803143620491028 2023-01-23 08:33:11.091399: step: 1912/1545, loss: 0.32763218879699707 2023-01-23 08:33:12.007357: step: 1914/1545, loss: 0.15634234249591827 2023-01-23 08:33:12.884208: step: 1916/1545, loss: 0.22047610580921173 2023-01-23 08:33:13.755460: step: 1918/1545, loss: 0.3323979377746582 2023-01-23 08:33:14.637183: step: 1920/1545, loss: 1.689882516860962 2023-01-23 08:33:15.523076: step: 1922/1545, loss: 1.414337396621704 2023-01-23 08:33:16.419006: step: 1924/1545, loss: 0.05981006845831871 2023-01-23 08:33:17.346960: step: 1926/1545, loss: 0.13115884363651276 2023-01-23 08:33:18.262842: step: 1928/1545, loss: 0.2764453589916229 2023-01-23 08:33:19.258343: step: 1930/1545, loss: 1.127987265586853 2023-01-23 08:33:20.175389: step: 1932/1545, loss: 0.08079655468463898 2023-01-23 08:33:21.048809: step: 1934/1545, loss: 0.667818009853363 2023-01-23 08:33:21.899250: step: 1936/1545, loss: 0.44165167212486267 2023-01-23 08:33:22.849843: step: 1938/1545, loss: 0.6329492330551147 2023-01-23 08:33:23.752764: step: 1940/1545, loss: 0.08849284797906876 2023-01-23 08:33:24.612859: step: 1942/1545, loss: 2.3356966972351074 2023-01-23 08:33:25.485506: step: 1944/1545, loss: 0.22714143991470337 2023-01-23 08:33:26.349338: step: 1946/1545, loss: 0.06711484491825104 2023-01-23 08:33:27.300683: step: 1948/1545, loss: 0.4910135269165039 2023-01-23 08:33:28.185553: step: 1950/1545, loss: 0.2532384395599365 2023-01-23 08:33:29.070085: step: 1952/1545, loss: 0.12303671985864639 2023-01-23 08:33:29.938346: step: 1954/1545, loss: 0.5581288933753967 2023-01-23 08:33:30.907343: step: 1956/1545, loss: 1.4424736499786377 2023-01-23 08:33:31.811277: step: 1958/1545, loss: 2.9253838062286377 2023-01-23 08:33:32.697487: step: 1960/1545, loss: 0.26580512523651123 2023-01-23 08:33:33.557672: step: 1962/1545, loss: 0.48098787665367126 2023-01-23 08:33:34.444868: step: 1964/1545, loss: 0.43322837352752686 2023-01-23 08:33:35.319806: step: 1966/1545, loss: 0.5928956270217896 2023-01-23 08:33:36.225950: step: 1968/1545, loss: 0.2793073058128357 2023-01-23 08:33:37.116246: step: 1970/1545, loss: 0.7042447924613953 2023-01-23 08:33:37.987900: step: 1972/1545, loss: 0.26522690057754517 2023-01-23 08:33:38.864815: step: 1974/1545, loss: 0.3183589279651642 2023-01-23 08:33:39.720728: step: 1976/1545, loss: 1.3460038900375366 2023-01-23 08:33:40.616727: step: 1978/1545, loss: 0.3204728066921234 2023-01-23 08:33:41.511320: step: 1980/1545, loss: 0.3189583718776703 2023-01-23 08:33:42.407087: step: 1982/1545, loss: 0.3165222406387329 2023-01-23 08:33:43.287975: step: 1984/1545, loss: 0.6059372425079346 2023-01-23 08:33:44.179561: step: 1986/1545, loss: 0.19028829038143158 2023-01-23 08:33:45.107031: step: 1988/1545, loss: 0.8903343677520752 2023-01-23 08:33:45.985115: step: 1990/1545, loss: 0.41821029782295227 2023-01-23 08:33:46.935611: step: 1992/1545, loss: 0.19405362010002136 2023-01-23 08:33:47.808806: step: 1994/1545, loss: 0.15108951926231384 2023-01-23 08:33:48.710585: step: 1996/1545, loss: 0.31840819120407104 2023-01-23 08:33:49.638478: step: 1998/1545, loss: 3.03584885597229 2023-01-23 08:33:50.515494: step: 2000/1545, loss: 0.23205888271331787 2023-01-23 08:33:51.451322: step: 2002/1545, loss: 0.2667649984359741 2023-01-23 08:33:52.360333: step: 2004/1545, loss: 0.31683117151260376 2023-01-23 08:33:53.260797: step: 2006/1545, loss: 0.36569225788116455 2023-01-23 08:33:54.141761: step: 2008/1545, loss: 0.3869408965110779 2023-01-23 08:33:55.029486: step: 2010/1545, loss: 0.13159994781017303 2023-01-23 08:33:55.937026: step: 2012/1545, loss: 0.14247138798236847 2023-01-23 08:33:56.810166: step: 2014/1545, loss: 0.5796231627464294 2023-01-23 08:33:57.708198: step: 2016/1545, loss: 0.8513138890266418 2023-01-23 08:33:58.634771: step: 2018/1545, loss: 0.23525214195251465 2023-01-23 08:33:59.494484: step: 2020/1545, loss: 0.25348448753356934 2023-01-23 08:34:00.402886: step: 2022/1545, loss: 0.9982126951217651 2023-01-23 08:34:01.276833: step: 2024/1545, loss: 0.3193005323410034 2023-01-23 08:34:02.185865: step: 2026/1545, loss: 0.2905658483505249 2023-01-23 08:34:03.070445: step: 2028/1545, loss: 0.7621567249298096 2023-01-23 08:34:03.964246: step: 2030/1545, loss: 0.34580034017562866 2023-01-23 08:34:04.801857: step: 2032/1545, loss: 0.30523985624313354 2023-01-23 08:34:05.720627: step: 2034/1545, loss: 0.8354257941246033 2023-01-23 08:34:06.728233: step: 2036/1545, loss: 2.9632537364959717 2023-01-23 08:34:07.650675: step: 2038/1545, loss: 0.1530783474445343 2023-01-23 08:34:08.526786: step: 2040/1545, loss: 0.33178213238716125 2023-01-23 08:34:09.416703: step: 2042/1545, loss: 0.29343685507774353 2023-01-23 08:34:10.294512: step: 2044/1545, loss: 0.1743965893983841 2023-01-23 08:34:11.314979: step: 2046/1545, loss: 0.5497103929519653 2023-01-23 08:34:12.203068: step: 2048/1545, loss: 0.6020735502243042 2023-01-23 08:34:13.082237: step: 2050/1545, loss: 0.3362950086593628 2023-01-23 08:34:13.953309: step: 2052/1545, loss: 0.28290119767189026 2023-01-23 08:34:14.843334: step: 2054/1545, loss: 0.7175193428993225 2023-01-23 08:34:15.744486: step: 2056/1545, loss: 0.627920925617218 2023-01-23 08:34:16.607608: step: 2058/1545, loss: 0.1842297613620758 2023-01-23 08:34:17.530249: step: 2060/1545, loss: 0.2942078411579132 2023-01-23 08:34:18.393140: step: 2062/1545, loss: 0.7126579880714417 2023-01-23 08:34:19.345221: step: 2064/1545, loss: 0.8818048238754272 2023-01-23 08:34:20.248245: step: 2066/1545, loss: 0.18346169590950012 2023-01-23 08:34:21.106477: step: 2068/1545, loss: 1.465394139289856 2023-01-23 08:34:22.011467: step: 2070/1545, loss: 0.29484593868255615 2023-01-23 08:34:22.937416: step: 2072/1545, loss: 0.47821471095085144 2023-01-23 08:34:23.784397: step: 2074/1545, loss: 0.1347244828939438 2023-01-23 08:34:24.668535: step: 2076/1545, loss: 0.5965219736099243 2023-01-23 08:34:25.548003: step: 2078/1545, loss: 0.24109773337841034 2023-01-23 08:34:26.483238: step: 2080/1545, loss: 0.23215767741203308 2023-01-23 08:34:27.405961: step: 2082/1545, loss: 0.2707422077655792 2023-01-23 08:34:28.336518: step: 2084/1545, loss: 0.2581014931201935 2023-01-23 08:34:29.268197: step: 2086/1545, loss: 0.28476178646087646 2023-01-23 08:34:30.177973: step: 2088/1545, loss: 0.3497712314128876 2023-01-23 08:34:31.034484: step: 2090/1545, loss: 0.7254995107650757 2023-01-23 08:34:31.928789: step: 2092/1545, loss: 0.7529520988464355 2023-01-23 08:34:32.799056: step: 2094/1545, loss: 0.48562031984329224 2023-01-23 08:34:33.664519: step: 2096/1545, loss: 0.1238483116030693 2023-01-23 08:34:34.494782: step: 2098/1545, loss: 0.14800097048282623 2023-01-23 08:34:35.395427: step: 2100/1545, loss: 3.1355059146881104 2023-01-23 08:34:36.308394: step: 2102/1545, loss: 0.1647946536540985 2023-01-23 08:34:37.215082: step: 2104/1545, loss: 0.2388586401939392 2023-01-23 08:34:38.079285: step: 2106/1545, loss: 0.1750774383544922 2023-01-23 08:34:38.916128: step: 2108/1545, loss: 0.12628448009490967 2023-01-23 08:34:39.766967: step: 2110/1545, loss: 0.2830861210823059 2023-01-23 08:34:40.641540: step: 2112/1545, loss: 0.1395934373140335 2023-01-23 08:34:41.554502: step: 2114/1545, loss: 0.5704901218414307 2023-01-23 08:34:42.403954: step: 2116/1545, loss: 0.2780601978302002 2023-01-23 08:34:43.270959: step: 2118/1545, loss: 2.5559120178222656 2023-01-23 08:34:44.134001: step: 2120/1545, loss: 0.19909067451953888 2023-01-23 08:34:45.002754: step: 2122/1545, loss: 0.6118868589401245 2023-01-23 08:34:45.891037: step: 2124/1545, loss: 0.1683284044265747 2023-01-23 08:34:46.757084: step: 2126/1545, loss: 0.3812193274497986 2023-01-23 08:34:47.692313: step: 2128/1545, loss: 0.13178038597106934 2023-01-23 08:34:48.585562: step: 2130/1545, loss: 0.22049960494041443 2023-01-23 08:34:49.501146: step: 2132/1545, loss: 0.7019105553627014 2023-01-23 08:34:50.361882: step: 2134/1545, loss: 0.19590550661087036 2023-01-23 08:34:51.240074: step: 2136/1545, loss: 0.08188004046678543 2023-01-23 08:34:52.085893: step: 2138/1545, loss: 0.3705763518810272 2023-01-23 08:34:52.944460: step: 2140/1545, loss: 0.22976501286029816 2023-01-23 08:34:53.809949: step: 2142/1545, loss: 0.31033292412757874 2023-01-23 08:34:54.678215: step: 2144/1545, loss: 0.2174348533153534 2023-01-23 08:34:55.546513: step: 2146/1545, loss: 0.3210236132144928 2023-01-23 08:34:56.462143: step: 2148/1545, loss: 0.26639094948768616 2023-01-23 08:34:57.342935: step: 2150/1545, loss: 0.26632678508758545 2023-01-23 08:34:58.259824: step: 2152/1545, loss: 0.196893110871315 2023-01-23 08:34:59.136900: step: 2154/1545, loss: 0.446384996175766 2023-01-23 08:35:00.012134: step: 2156/1545, loss: 0.36976346373558044 2023-01-23 08:35:00.878802: step: 2158/1545, loss: 0.5281317234039307 2023-01-23 08:35:01.806702: step: 2160/1545, loss: 0.5200373530387878 2023-01-23 08:35:02.670468: step: 2162/1545, loss: 0.2393725961446762 2023-01-23 08:35:03.574931: step: 2164/1545, loss: 1.4707247018814087 2023-01-23 08:35:04.472288: step: 2166/1545, loss: 0.4942226707935333 2023-01-23 08:35:05.343146: step: 2168/1545, loss: 0.31645724177360535 2023-01-23 08:35:06.219030: step: 2170/1545, loss: 0.2080734670162201 2023-01-23 08:35:07.110421: step: 2172/1545, loss: 0.3344162106513977 2023-01-23 08:35:07.953674: step: 2174/1545, loss: 0.6329668164253235 2023-01-23 08:35:08.826992: step: 2176/1545, loss: 0.40225863456726074 2023-01-23 08:35:09.712886: step: 2178/1545, loss: 0.2711006700992584 2023-01-23 08:35:10.600953: step: 2180/1545, loss: 0.2385564148426056 2023-01-23 08:35:11.493708: step: 2182/1545, loss: 1.95521879196167 2023-01-23 08:35:12.426192: step: 2184/1545, loss: 0.6793960332870483 2023-01-23 08:35:13.318464: step: 2186/1545, loss: 0.31237611174583435 2023-01-23 08:35:14.186670: step: 2188/1545, loss: 0.9006342887878418 2023-01-23 08:35:15.100167: step: 2190/1545, loss: 0.5690205693244934 2023-01-23 08:35:15.999779: step: 2192/1545, loss: 0.9234403371810913 2023-01-23 08:35:16.878604: step: 2194/1545, loss: 0.3767612874507904 2023-01-23 08:35:17.765054: step: 2196/1545, loss: 0.28769394755363464 2023-01-23 08:35:18.621217: step: 2198/1545, loss: 6.522437572479248 2023-01-23 08:35:19.484590: step: 2200/1545, loss: 0.2566065192222595 2023-01-23 08:35:20.398516: step: 2202/1545, loss: 0.3164023160934448 2023-01-23 08:35:21.300150: step: 2204/1545, loss: 0.15676985681056976 2023-01-23 08:35:22.271927: step: 2206/1545, loss: 0.15349732339382172 2023-01-23 08:35:23.124923: step: 2208/1545, loss: 0.12625841796398163 2023-01-23 08:35:23.988594: step: 2210/1545, loss: 0.26450011134147644 2023-01-23 08:35:24.861329: step: 2212/1545, loss: 0.11242910474538803 2023-01-23 08:35:25.725930: step: 2214/1545, loss: 0.7579221725463867 2023-01-23 08:35:26.585786: step: 2216/1545, loss: 0.17857348918914795 2023-01-23 08:35:27.482707: step: 2218/1545, loss: 1.1328519582748413 2023-01-23 08:35:28.393980: step: 2220/1545, loss: 0.21622131764888763 2023-01-23 08:35:29.308435: step: 2222/1545, loss: 0.6218855977058411 2023-01-23 08:35:30.183923: step: 2224/1545, loss: 0.1669331043958664 2023-01-23 08:35:31.111601: step: 2226/1545, loss: 0.27403706312179565 2023-01-23 08:35:32.024022: step: 2228/1545, loss: 0.3125420808792114 2023-01-23 08:35:32.954487: step: 2230/1545, loss: 0.46251410245895386 2023-01-23 08:35:33.799238: step: 2232/1545, loss: 0.2981663644313812 2023-01-23 08:35:34.720473: step: 2234/1545, loss: 0.5567458868026733 2023-01-23 08:35:35.596403: step: 2236/1545, loss: 0.4731910824775696 2023-01-23 08:35:36.504357: step: 2238/1545, loss: 0.10487526655197144 2023-01-23 08:35:37.422097: step: 2240/1545, loss: 0.11852466315031052 2023-01-23 08:35:38.287898: step: 2242/1545, loss: 0.17782792448997498 2023-01-23 08:35:39.222804: step: 2244/1545, loss: 0.755280613899231 2023-01-23 08:35:40.136725: step: 2246/1545, loss: 0.976179838180542 2023-01-23 08:35:41.058300: step: 2248/1545, loss: 1.9751659631729126 2023-01-23 08:35:42.048526: step: 2250/1545, loss: 0.24158430099487305 2023-01-23 08:35:42.939834: step: 2252/1545, loss: 0.6312291622161865 2023-01-23 08:35:43.842239: step: 2254/1545, loss: 0.31622904539108276 2023-01-23 08:35:44.710522: step: 2256/1545, loss: 0.4321838319301605 2023-01-23 08:35:45.628461: step: 2258/1545, loss: 0.22508522868156433 2023-01-23 08:35:46.528812: step: 2260/1545, loss: 0.5792362093925476 2023-01-23 08:35:47.382983: step: 2262/1545, loss: 0.21881423890590668 2023-01-23 08:35:48.294928: step: 2264/1545, loss: 1.064307689666748 2023-01-23 08:35:49.221905: step: 2266/1545, loss: 0.10526758432388306 2023-01-23 08:35:50.146173: step: 2268/1545, loss: 0.25799664855003357 2023-01-23 08:35:51.035699: step: 2270/1545, loss: 0.37706196308135986 2023-01-23 08:35:51.927647: step: 2272/1545, loss: 0.3094189167022705 2023-01-23 08:35:52.863801: step: 2274/1545, loss: 0.24302580952644348 2023-01-23 08:35:53.790683: step: 2276/1545, loss: 0.1940077692270279 2023-01-23 08:35:54.676556: step: 2278/1545, loss: 0.24956738948822021 2023-01-23 08:35:55.611150: step: 2280/1545, loss: 0.32700327038764954 2023-01-23 08:35:56.523767: step: 2282/1545, loss: 0.3949473202228546 2023-01-23 08:35:57.408203: step: 2284/1545, loss: 0.4184161424636841 2023-01-23 08:35:58.270764: step: 2286/1545, loss: 0.5575487017631531 2023-01-23 08:35:59.241080: step: 2288/1545, loss: 0.8871608376502991 2023-01-23 08:36:00.146335: step: 2290/1545, loss: 0.4708923101425171 2023-01-23 08:36:01.012199: step: 2292/1545, loss: 0.26625144481658936 2023-01-23 08:36:01.880105: step: 2294/1545, loss: 0.18392983078956604 2023-01-23 08:36:02.809000: step: 2296/1545, loss: 0.4294697642326355 2023-01-23 08:36:03.674694: step: 2298/1545, loss: 0.20741137862205505 2023-01-23 08:36:04.584548: step: 2300/1545, loss: 0.3396788239479065 2023-01-23 08:36:05.465399: step: 2302/1545, loss: 0.14501169323921204 2023-01-23 08:36:06.333955: step: 2304/1545, loss: 0.263757586479187 2023-01-23 08:36:07.221852: step: 2306/1545, loss: 0.09539245069026947 2023-01-23 08:36:08.073179: step: 2308/1545, loss: 0.23497752845287323 2023-01-23 08:36:08.934146: step: 2310/1545, loss: 0.12845100462436676 2023-01-23 08:36:09.796961: step: 2312/1545, loss: 0.5356913208961487 2023-01-23 08:36:10.726093: step: 2314/1545, loss: 0.5334619283676147 2023-01-23 08:36:11.680205: step: 2316/1545, loss: 0.25315728783607483 2023-01-23 08:36:12.532577: step: 2318/1545, loss: 0.1314220130443573 2023-01-23 08:36:13.427153: step: 2320/1545, loss: 0.11685459315776825 2023-01-23 08:36:14.295629: step: 2322/1545, loss: 0.6002278923988342 2023-01-23 08:36:15.136472: step: 2324/1545, loss: 0.15979968011379242 2023-01-23 08:36:16.026129: step: 2326/1545, loss: 0.6090109944343567 2023-01-23 08:36:16.941709: step: 2328/1545, loss: 0.6542982459068298 2023-01-23 08:36:17.873443: step: 2330/1545, loss: 0.29002636671066284 2023-01-23 08:36:18.767820: step: 2332/1545, loss: 0.25635668635368347 2023-01-23 08:36:19.649444: step: 2334/1545, loss: 0.25304824113845825 2023-01-23 08:36:20.536774: step: 2336/1545, loss: 0.2785501182079315 2023-01-23 08:36:21.457134: step: 2338/1545, loss: 0.07742616534233093 2023-01-23 08:36:22.319263: step: 2340/1545, loss: 0.1848553866147995 2023-01-23 08:36:23.218627: step: 2342/1545, loss: 0.20906633138656616 2023-01-23 08:36:24.131705: step: 2344/1545, loss: 0.1099766343832016 2023-01-23 08:36:25.020076: step: 2346/1545, loss: 0.23139110207557678 2023-01-23 08:36:25.904201: step: 2348/1545, loss: 0.8551774621009827 2023-01-23 08:36:26.769311: step: 2350/1545, loss: 1.099772572517395 2023-01-23 08:36:27.629961: step: 2352/1545, loss: 0.18619173765182495 2023-01-23 08:36:28.527198: step: 2354/1545, loss: 0.17441578209400177 2023-01-23 08:36:29.416777: step: 2356/1545, loss: 0.2224341630935669 2023-01-23 08:36:30.302340: step: 2358/1545, loss: 0.4831257462501526 2023-01-23 08:36:31.293774: step: 2360/1545, loss: 0.510312020778656 2023-01-23 08:36:32.186219: step: 2362/1545, loss: 0.05189252644777298 2023-01-23 08:36:33.071173: step: 2364/1545, loss: 1.0477815866470337 2023-01-23 08:36:34.009397: step: 2366/1545, loss: 0.49057507514953613 2023-01-23 08:36:34.945619: step: 2368/1545, loss: 0.4864954650402069 2023-01-23 08:36:35.915774: step: 2370/1545, loss: 0.39316967129707336 2023-01-23 08:36:36.806286: step: 2372/1545, loss: 0.44329574704170227 2023-01-23 08:36:37.717305: step: 2374/1545, loss: 0.31970730423927307 2023-01-23 08:36:38.609950: step: 2376/1545, loss: 0.14344191551208496 2023-01-23 08:36:39.514259: step: 2378/1545, loss: 0.6297988891601562 2023-01-23 08:36:40.380601: step: 2380/1545, loss: 0.23825393617153168 2023-01-23 08:36:41.299382: step: 2382/1545, loss: 0.1995876431465149 2023-01-23 08:36:42.156899: step: 2384/1545, loss: 0.3640498220920563 2023-01-23 08:36:43.072962: step: 2386/1545, loss: 0.18072378635406494 2023-01-23 08:36:43.989907: step: 2388/1545, loss: 0.48089998960494995 2023-01-23 08:36:44.891723: step: 2390/1545, loss: 0.37507617473602295 2023-01-23 08:36:45.789379: step: 2392/1545, loss: 0.7119318842887878 2023-01-23 08:36:46.655166: step: 2394/1545, loss: 0.24498391151428223 2023-01-23 08:36:47.525290: step: 2396/1545, loss: 0.2520785331726074 2023-01-23 08:36:48.426986: step: 2398/1545, loss: 0.23881055414676666 2023-01-23 08:36:49.312905: step: 2400/1545, loss: 0.1485067903995514 2023-01-23 08:36:50.211075: step: 2402/1545, loss: 0.10371602326631546 2023-01-23 08:36:51.103033: step: 2404/1545, loss: 0.29580581188201904 2023-01-23 08:36:51.962789: step: 2406/1545, loss: 0.364288866519928 2023-01-23 08:36:52.827038: step: 2408/1545, loss: 0.44105401635169983 2023-01-23 08:36:53.718684: step: 2410/1545, loss: 2.55157732963562 2023-01-23 08:36:54.601049: step: 2412/1545, loss: 0.3387576639652252 2023-01-23 08:36:55.524236: step: 2414/1545, loss: 0.11447996646165848 2023-01-23 08:36:56.393130: step: 2416/1545, loss: 0.12914018332958221 2023-01-23 08:36:57.287371: step: 2418/1545, loss: 0.43861624598503113 2023-01-23 08:36:58.167930: step: 2420/1545, loss: 0.20965075492858887 2023-01-23 08:36:59.143595: step: 2422/1545, loss: 0.6554023623466492 2023-01-23 08:37:00.060163: step: 2424/1545, loss: 0.8001495599746704 2023-01-23 08:37:00.918220: step: 2426/1545, loss: 0.34447991847991943 2023-01-23 08:37:01.808586: step: 2428/1545, loss: 0.6852647662162781 2023-01-23 08:37:02.719947: step: 2430/1545, loss: 0.409679114818573 2023-01-23 08:37:03.606002: step: 2432/1545, loss: 0.37400102615356445 2023-01-23 08:37:04.517486: step: 2434/1545, loss: 0.2839294970035553 2023-01-23 08:37:05.378969: step: 2436/1545, loss: 0.29712778329849243 2023-01-23 08:37:06.265876: step: 2438/1545, loss: 0.21627774834632874 2023-01-23 08:37:07.122372: step: 2440/1545, loss: 0.304929256439209 2023-01-23 08:37:07.983899: step: 2442/1545, loss: 0.0880715399980545 2023-01-23 08:37:08.882743: step: 2444/1545, loss: 0.6760117411613464 2023-01-23 08:37:09.763841: step: 2446/1545, loss: 0.28000161051750183 2023-01-23 08:37:10.659158: step: 2448/1545, loss: 0.25196948647499084 2023-01-23 08:37:11.667326: step: 2450/1545, loss: 0.13287782669067383 2023-01-23 08:37:12.642595: step: 2452/1545, loss: 0.3234691917896271 2023-01-23 08:37:13.543480: step: 2454/1545, loss: 0.4727632403373718 2023-01-23 08:37:14.435695: step: 2456/1545, loss: 0.31706058979034424 2023-01-23 08:37:15.303224: step: 2458/1545, loss: 0.42796507477760315 2023-01-23 08:37:16.146959: step: 2460/1545, loss: 2.258349895477295 2023-01-23 08:37:17.022113: step: 2462/1545, loss: 0.5609802007675171 2023-01-23 08:37:17.900913: step: 2464/1545, loss: 0.4741229712963104 2023-01-23 08:37:18.800735: step: 2466/1545, loss: 0.08431258052587509 2023-01-23 08:37:19.711097: step: 2468/1545, loss: 0.6385121941566467 2023-01-23 08:37:20.604476: step: 2470/1545, loss: 0.42613765597343445 2023-01-23 08:37:21.508226: step: 2472/1545, loss: 0.3934774696826935 2023-01-23 08:37:22.374875: step: 2474/1545, loss: 0.17202596366405487 2023-01-23 08:37:23.260322: step: 2476/1545, loss: 0.17601516842842102 2023-01-23 08:37:24.209958: step: 2478/1545, loss: 0.3350512981414795 2023-01-23 08:37:25.058984: step: 2480/1545, loss: 1.0221092700958252 2023-01-23 08:37:25.926650: step: 2482/1545, loss: 0.12164126336574554 2023-01-23 08:37:26.817322: step: 2484/1545, loss: 0.1167769730091095 2023-01-23 08:37:27.719774: step: 2486/1545, loss: 1.0836368799209595 2023-01-23 08:37:28.577475: step: 2488/1545, loss: 0.36529240012168884 2023-01-23 08:37:29.500545: step: 2490/1545, loss: 0.36608269810676575 2023-01-23 08:37:30.395315: step: 2492/1545, loss: 0.7996227145195007 2023-01-23 08:37:31.284805: step: 2494/1545, loss: 0.24018244445323944 2023-01-23 08:37:32.144766: step: 2496/1545, loss: 0.1567060351371765 2023-01-23 08:37:33.018119: step: 2498/1545, loss: 0.5648781061172485 2023-01-23 08:37:33.960275: step: 2500/1545, loss: 0.1560364067554474 2023-01-23 08:37:34.876310: step: 2502/1545, loss: 0.1680637001991272 2023-01-23 08:37:35.752473: step: 2504/1545, loss: 0.14992354810237885 2023-01-23 08:37:36.644904: step: 2506/1545, loss: 3.14593768119812 2023-01-23 08:37:37.493499: step: 2508/1545, loss: 0.1634482592344284 2023-01-23 08:37:38.440402: step: 2510/1545, loss: 0.18268045783042908 2023-01-23 08:37:39.325832: step: 2512/1545, loss: 0.34293338656425476 2023-01-23 08:37:40.251288: step: 2514/1545, loss: 0.7532274723052979 2023-01-23 08:37:41.212557: step: 2516/1545, loss: 1.1071677207946777 2023-01-23 08:37:42.117780: step: 2518/1545, loss: 0.40233850479125977 2023-01-23 08:37:43.012847: step: 2520/1545, loss: 0.2346947193145752 2023-01-23 08:37:43.884832: step: 2522/1545, loss: 0.5205928087234497 2023-01-23 08:37:44.753720: step: 2524/1545, loss: 0.4071599543094635 2023-01-23 08:37:45.621961: step: 2526/1545, loss: 0.12876957654953003 2023-01-23 08:37:46.488587: step: 2528/1545, loss: 0.361022412776947 2023-01-23 08:37:47.363759: step: 2530/1545, loss: 0.425467848777771 2023-01-23 08:37:48.251215: step: 2532/1545, loss: 0.297812819480896 2023-01-23 08:37:49.104068: step: 2534/1545, loss: 0.32273954153060913 2023-01-23 08:37:49.971411: step: 2536/1545, loss: 1.0887032747268677 2023-01-23 08:37:50.929583: step: 2538/1545, loss: 0.28491753339767456 2023-01-23 08:37:51.842872: step: 2540/1545, loss: 0.5061849355697632 2023-01-23 08:37:52.720311: step: 2542/1545, loss: 0.07278735935688019 2023-01-23 08:37:53.587314: step: 2544/1545, loss: 3.324153184890747 2023-01-23 08:37:54.462306: step: 2546/1545, loss: 0.5023140907287598 2023-01-23 08:37:55.306008: step: 2548/1545, loss: 0.0964415892958641 2023-01-23 08:37:56.197758: step: 2550/1545, loss: 0.5618253946304321 2023-01-23 08:37:57.073098: step: 2552/1545, loss: 0.26046666502952576 2023-01-23 08:37:57.950268: step: 2554/1545, loss: 0.43344253301620483 2023-01-23 08:37:58.815422: step: 2556/1545, loss: 0.09790154546499252 2023-01-23 08:37:59.695921: step: 2558/1545, loss: 0.34186115860939026 2023-01-23 08:38:00.569840: step: 2560/1545, loss: 0.3369000256061554 2023-01-23 08:38:01.449602: step: 2562/1545, loss: 0.11425051838159561 2023-01-23 08:38:02.396219: step: 2564/1545, loss: 0.3615480065345764 2023-01-23 08:38:03.333016: step: 2566/1545, loss: 0.18831183016300201 2023-01-23 08:38:04.196238: step: 2568/1545, loss: 0.3473758101463318 2023-01-23 08:38:05.063903: step: 2570/1545, loss: 2.9862658977508545 2023-01-23 08:38:05.997076: step: 2572/1545, loss: 0.7558547854423523 2023-01-23 08:38:06.876894: step: 2574/1545, loss: 0.26895973086357117 2023-01-23 08:38:07.767741: step: 2576/1545, loss: 0.27130061388015747 2023-01-23 08:38:08.616617: step: 2578/1545, loss: 0.23723334074020386 2023-01-23 08:38:09.510479: step: 2580/1545, loss: 0.5529184937477112 2023-01-23 08:38:10.389476: step: 2582/1545, loss: 0.47730058431625366 2023-01-23 08:38:11.264722: step: 2584/1545, loss: 0.5404495596885681 2023-01-23 08:38:12.131034: step: 2586/1545, loss: 1.9239840507507324 2023-01-23 08:38:13.001908: step: 2588/1545, loss: 0.49065685272216797 2023-01-23 08:38:13.871899: step: 2590/1545, loss: 0.1126057431101799 2023-01-23 08:38:14.760779: step: 2592/1545, loss: 0.09342120587825775 2023-01-23 08:38:15.649316: step: 2594/1545, loss: 0.2855013608932495 2023-01-23 08:38:16.495956: step: 2596/1545, loss: 0.5075112581253052 2023-01-23 08:38:17.350105: step: 2598/1545, loss: 0.3145652711391449 2023-01-23 08:38:18.231078: step: 2600/1545, loss: 0.19342689216136932 2023-01-23 08:38:19.092772: step: 2602/1545, loss: 0.21746571362018585 2023-01-23 08:38:19.950852: step: 2604/1545, loss: 0.6425729393959045 2023-01-23 08:38:20.928392: step: 2606/1545, loss: 0.4684218764305115 2023-01-23 08:38:21.836696: step: 2608/1545, loss: 0.33531177043914795 2023-01-23 08:38:22.773558: step: 2610/1545, loss: 0.1607791781425476 2023-01-23 08:38:23.621488: step: 2612/1545, loss: 0.22167515754699707 2023-01-23 08:38:24.534873: step: 2614/1545, loss: 0.2577415108680725 2023-01-23 08:38:25.503681: step: 2616/1545, loss: 0.1316491961479187 2023-01-23 08:38:26.411901: step: 2618/1545, loss: 2.6022799015045166 2023-01-23 08:38:27.278184: step: 2620/1545, loss: 0.055353064090013504 2023-01-23 08:38:28.241705: step: 2622/1545, loss: 0.3169553875923157 2023-01-23 08:38:29.135653: step: 2624/1545, loss: 0.11460867524147034 2023-01-23 08:38:30.033218: step: 2626/1545, loss: 0.6784752011299133 2023-01-23 08:38:30.915316: step: 2628/1545, loss: 0.13584432005882263 2023-01-23 08:38:31.789747: step: 2630/1545, loss: 0.14253073930740356 2023-01-23 08:38:32.690808: step: 2632/1545, loss: 0.32218748331069946 2023-01-23 08:38:33.537353: step: 2634/1545, loss: 0.09729640185832977 2023-01-23 08:38:34.408050: step: 2636/1545, loss: 0.10519906133413315 2023-01-23 08:38:35.298492: step: 2638/1545, loss: 0.5002958178520203 2023-01-23 08:38:36.194631: step: 2640/1545, loss: 0.6826447248458862 2023-01-23 08:38:37.066312: step: 2642/1545, loss: 0.36196112632751465 2023-01-23 08:38:37.934880: step: 2644/1545, loss: 1.0484044551849365 2023-01-23 08:38:38.805478: step: 2646/1545, loss: 0.4072161912918091 2023-01-23 08:38:39.771663: step: 2648/1545, loss: 0.56516432762146 2023-01-23 08:38:40.680848: step: 2650/1545, loss: 0.22092588245868683 2023-01-23 08:38:41.559840: step: 2652/1545, loss: 3.3183112144470215 2023-01-23 08:38:42.468743: step: 2654/1545, loss: 0.6509688496589661 2023-01-23 08:38:43.347904: step: 2656/1545, loss: 0.9424840211868286 2023-01-23 08:38:44.211578: step: 2658/1545, loss: 0.11463765054941177 2023-01-23 08:38:45.088673: step: 2660/1545, loss: 0.08176524937152863 2023-01-23 08:38:45.963200: step: 2662/1545, loss: 0.34468528628349304 2023-01-23 08:38:46.847055: step: 2664/1545, loss: 0.5177945494651794 2023-01-23 08:38:47.721134: step: 2666/1545, loss: 0.31026458740234375 2023-01-23 08:38:48.612055: step: 2668/1545, loss: 0.1400061696767807 2023-01-23 08:38:49.510633: step: 2670/1545, loss: 0.48662933707237244 2023-01-23 08:38:50.368245: step: 2672/1545, loss: 0.3813518285751343 2023-01-23 08:38:51.264571: step: 2674/1545, loss: 0.34991326928138733 2023-01-23 08:38:52.145860: step: 2676/1545, loss: 1.3980330228805542 2023-01-23 08:38:53.053530: step: 2678/1545, loss: 0.31582173705101013 2023-01-23 08:38:53.951657: step: 2680/1545, loss: 0.31905069947242737 2023-01-23 08:38:54.852102: step: 2682/1545, loss: 0.19629128277301788 2023-01-23 08:38:55.747680: step: 2684/1545, loss: 0.21448220312595367 2023-01-23 08:38:56.691567: step: 2686/1545, loss: 0.6908661127090454 2023-01-23 08:38:57.565239: step: 2688/1545, loss: 0.24316905438899994 2023-01-23 08:38:58.418820: step: 2690/1545, loss: 0.505577802658081 2023-01-23 08:38:59.291186: step: 2692/1545, loss: 0.5861568450927734 2023-01-23 08:39:00.234930: step: 2694/1545, loss: 1.3238595724105835 2023-01-23 08:39:01.095276: step: 2696/1545, loss: 0.5118181705474854 2023-01-23 08:39:01.951831: step: 2698/1545, loss: 0.5518743395805359 2023-01-23 08:39:02.845521: step: 2700/1545, loss: 0.2962649464607239 2023-01-23 08:39:03.795499: step: 2702/1545, loss: 0.18715479969978333 2023-01-23 08:39:04.664997: step: 2704/1545, loss: 0.22921904921531677 2023-01-23 08:39:05.557607: step: 2706/1545, loss: 0.17330437898635864 2023-01-23 08:39:06.418049: step: 2708/1545, loss: 0.26563602685928345 2023-01-23 08:39:07.339472: step: 2710/1545, loss: 0.3462293744087219 2023-01-23 08:39:08.218589: step: 2712/1545, loss: 0.564167857170105 2023-01-23 08:39:09.090980: step: 2714/1545, loss: 0.6459358930587769 2023-01-23 08:39:09.959006: step: 2716/1545, loss: 0.5866448283195496 2023-01-23 08:39:10.817885: step: 2718/1545, loss: 0.36034879088401794 2023-01-23 08:39:11.721421: step: 2720/1545, loss: 0.49020493030548096 2023-01-23 08:39:12.601791: step: 2722/1545, loss: 0.27977412939071655 2023-01-23 08:39:13.472939: step: 2724/1545, loss: 0.2736617624759674 2023-01-23 08:39:14.398495: step: 2726/1545, loss: 0.23073723912239075 2023-01-23 08:39:15.348952: step: 2728/1545, loss: 0.7409504055976868 2023-01-23 08:39:16.186909: step: 2730/1545, loss: 0.23525260388851166 2023-01-23 08:39:17.073726: step: 2732/1545, loss: 0.3641035258769989 2023-01-23 08:39:17.976420: step: 2734/1545, loss: 0.5295257568359375 2023-01-23 08:39:18.822680: step: 2736/1545, loss: 0.3231867551803589 2023-01-23 08:39:19.727157: step: 2738/1545, loss: 0.3536699116230011 2023-01-23 08:39:20.567999: step: 2740/1545, loss: 0.3054916262626648 2023-01-23 08:39:21.491424: step: 2742/1545, loss: 0.13541452586650848 2023-01-23 08:39:22.349070: step: 2744/1545, loss: 0.628015398979187 2023-01-23 08:39:23.257381: step: 2746/1545, loss: 0.4365645945072174 2023-01-23 08:39:24.155451: step: 2748/1545, loss: 0.2699894309043884 2023-01-23 08:39:25.021708: step: 2750/1545, loss: 1.1924413442611694 2023-01-23 08:39:25.907771: step: 2752/1545, loss: 0.4493762254714966 2023-01-23 08:39:26.779264: step: 2754/1545, loss: 0.10903038084506989 2023-01-23 08:39:27.671348: step: 2756/1545, loss: 0.4490754306316376 2023-01-23 08:39:28.583563: step: 2758/1545, loss: 0.2940487265586853 2023-01-23 08:39:29.523142: step: 2760/1545, loss: 0.06051337718963623 2023-01-23 08:39:30.424355: step: 2762/1545, loss: 0.370237797498703 2023-01-23 08:39:31.308341: step: 2764/1545, loss: 0.4368787109851837 2023-01-23 08:39:32.153205: step: 2766/1545, loss: 0.33301326632499695 2023-01-23 08:39:33.057271: step: 2768/1545, loss: 0.2562171220779419 2023-01-23 08:39:34.005868: step: 2770/1545, loss: 0.3960954546928406 2023-01-23 08:39:34.875849: step: 2772/1545, loss: 0.5111529231071472 2023-01-23 08:39:35.799656: step: 2774/1545, loss: 0.8487581014633179 2023-01-23 08:39:36.669335: step: 2776/1545, loss: 0.23686398565769196 2023-01-23 08:39:37.584471: step: 2778/1545, loss: 0.5492487549781799 2023-01-23 08:39:38.481766: step: 2780/1545, loss: 0.3252779543399811 2023-01-23 08:39:39.375532: step: 2782/1545, loss: 1.0557795763015747 2023-01-23 08:39:40.288400: step: 2784/1545, loss: 0.9025304913520813 2023-01-23 08:39:41.155450: step: 2786/1545, loss: 2.4090404510498047 2023-01-23 08:39:42.019567: step: 2788/1545, loss: 0.22427116334438324 2023-01-23 08:39:42.883360: step: 2790/1545, loss: 0.1033024862408638 2023-01-23 08:39:43.789536: step: 2792/1545, loss: 0.7175958156585693 2023-01-23 08:39:44.647661: step: 2794/1545, loss: 0.2400181144475937 2023-01-23 08:39:45.569254: step: 2796/1545, loss: 0.3825403153896332 2023-01-23 08:39:46.489374: step: 2798/1545, loss: 0.5201146602630615 2023-01-23 08:39:47.323660: step: 2800/1545, loss: 0.41211819648742676 2023-01-23 08:39:48.187839: step: 2802/1545, loss: 0.28886449337005615 2023-01-23 08:39:49.119428: step: 2804/1545, loss: 0.43827301263809204 2023-01-23 08:39:50.028749: step: 2806/1545, loss: 0.5937488079071045 2023-01-23 08:39:50.874114: step: 2808/1545, loss: 0.2336656153202057 2023-01-23 08:39:51.746697: step: 2810/1545, loss: 1.1133406162261963 2023-01-23 08:39:52.589093: step: 2812/1545, loss: 2.780418872833252 2023-01-23 08:39:53.450833: step: 2814/1545, loss: 0.1674015074968338 2023-01-23 08:39:54.353685: step: 2816/1545, loss: 0.4572094976902008 2023-01-23 08:39:55.205085: step: 2818/1545, loss: 0.8645620942115784 2023-01-23 08:39:56.063179: step: 2820/1545, loss: 0.5984087586402893 2023-01-23 08:39:56.957351: step: 2822/1545, loss: 0.21288377046585083 2023-01-23 08:39:57.859821: step: 2824/1545, loss: 0.32172054052352905 2023-01-23 08:39:58.806129: step: 2826/1545, loss: 0.23672859370708466 2023-01-23 08:39:59.737842: step: 2828/1545, loss: 0.49288615584373474 2023-01-23 08:40:00.639325: step: 2830/1545, loss: 0.44800227880477905 2023-01-23 08:40:01.513582: step: 2832/1545, loss: 0.3620457947254181 2023-01-23 08:40:02.384627: step: 2834/1545, loss: 0.13029071688652039 2023-01-23 08:40:03.237321: step: 2836/1545, loss: 0.5326482057571411 2023-01-23 08:40:04.163915: step: 2838/1545, loss: 0.43695229291915894 2023-01-23 08:40:05.113686: step: 2840/1545, loss: 0.1118612214922905 2023-01-23 08:40:06.000801: step: 2842/1545, loss: 0.7844799757003784 2023-01-23 08:40:06.876487: step: 2844/1545, loss: 0.40942347049713135 2023-01-23 08:40:07.782765: step: 2846/1545, loss: 0.10684061050415039 2023-01-23 08:40:08.655874: step: 2848/1545, loss: 0.14189141988754272 2023-01-23 08:40:09.558119: step: 2850/1545, loss: 0.28105825185775757 2023-01-23 08:40:10.457994: step: 2852/1545, loss: 0.20405586063861847 2023-01-23 08:40:11.331092: step: 2854/1545, loss: 0.5509905219078064 2023-01-23 08:40:12.228561: step: 2856/1545, loss: 0.3070296347141266 2023-01-23 08:40:13.104962: step: 2858/1545, loss: 0.19118469953536987 2023-01-23 08:40:13.962298: step: 2860/1545, loss: 0.31636443734169006 2023-01-23 08:40:14.847736: step: 2862/1545, loss: 0.4187897741794586 2023-01-23 08:40:15.730106: step: 2864/1545, loss: 0.49646875262260437 2023-01-23 08:40:16.586161: step: 2866/1545, loss: 0.38891345262527466 2023-01-23 08:40:17.439914: step: 2868/1545, loss: 0.2327471226453781 2023-01-23 08:40:18.371988: step: 2870/1545, loss: 0.5182396173477173 2023-01-23 08:40:19.270629: step: 2872/1545, loss: 0.14642015099525452 2023-01-23 08:40:20.174243: step: 2874/1545, loss: 0.7516852021217346 2023-01-23 08:40:21.030311: step: 2876/1545, loss: 0.9867640733718872 2023-01-23 08:40:21.920530: step: 2878/1545, loss: 0.41826778650283813 2023-01-23 08:40:22.796476: step: 2880/1545, loss: 0.17595162987709045 2023-01-23 08:40:23.660690: step: 2882/1545, loss: 0.24864979088306427 2023-01-23 08:40:24.569778: step: 2884/1545, loss: 0.3706109821796417 2023-01-23 08:40:25.519143: step: 2886/1545, loss: 2.555469036102295 2023-01-23 08:40:26.378316: step: 2888/1545, loss: 0.45825108885765076 2023-01-23 08:40:27.256015: step: 2890/1545, loss: 0.24599173665046692 2023-01-23 08:40:28.160342: step: 2892/1545, loss: 0.15606321394443512 2023-01-23 08:40:29.045355: step: 2894/1545, loss: 0.2588331699371338 2023-01-23 08:40:29.923081: step: 2896/1545, loss: 0.40128859877586365 2023-01-23 08:40:30.854052: step: 2898/1545, loss: 0.2579162120819092 2023-01-23 08:40:31.733128: step: 2900/1545, loss: 0.31294435262680054 2023-01-23 08:40:32.634168: step: 2902/1545, loss: 0.24558089673519135 2023-01-23 08:40:33.536655: step: 2904/1545, loss: 0.275642067193985 2023-01-23 08:40:34.412461: step: 2906/1545, loss: 0.13617351651191711 2023-01-23 08:40:35.326312: step: 2908/1545, loss: 0.37309902906417847 2023-01-23 08:40:36.211740: step: 2910/1545, loss: 0.41510477662086487 2023-01-23 08:40:37.139214: step: 2912/1545, loss: 0.5879859328269958 2023-01-23 08:40:38.057181: step: 2914/1545, loss: 0.33153659105300903 2023-01-23 08:40:38.942410: step: 2916/1545, loss: 0.5245899558067322 2023-01-23 08:40:39.836885: step: 2918/1545, loss: 0.37960532307624817 2023-01-23 08:40:40.762757: step: 2920/1545, loss: 0.24187971651554108 2023-01-23 08:40:41.643673: step: 2922/1545, loss: 0.26055917143821716 2023-01-23 08:40:42.562248: step: 2924/1545, loss: 0.23629626631736755 2023-01-23 08:40:43.407915: step: 2926/1545, loss: 0.11559534072875977 2023-01-23 08:40:44.301051: step: 2928/1545, loss: 0.9246115684509277 2023-01-23 08:40:45.162164: step: 2930/1545, loss: 0.5556251406669617 2023-01-23 08:40:46.128411: step: 2932/1545, loss: 0.7404360771179199 2023-01-23 08:40:47.020215: step: 2934/1545, loss: 0.06303810328245163 2023-01-23 08:40:47.918340: step: 2936/1545, loss: 2.632941961288452 2023-01-23 08:40:48.817352: step: 2938/1545, loss: 1.3709887266159058 2023-01-23 08:40:49.731300: step: 2940/1545, loss: 0.13946202397346497 2023-01-23 08:40:50.621175: step: 2942/1545, loss: 0.29626238346099854 2023-01-23 08:40:51.481015: step: 2944/1545, loss: 0.3867088258266449 2023-01-23 08:40:52.363676: step: 2946/1545, loss: 0.41810715198516846 2023-01-23 08:40:53.272633: step: 2948/1545, loss: 0.48044833540916443 2023-01-23 08:40:54.123730: step: 2950/1545, loss: 0.3365609347820282 2023-01-23 08:40:54.988119: step: 2952/1545, loss: 0.5275640487670898 2023-01-23 08:40:55.883293: step: 2954/1545, loss: 0.5326180458068848 2023-01-23 08:40:56.751350: step: 2956/1545, loss: 0.7417859435081482 2023-01-23 08:40:57.627933: step: 2958/1545, loss: 0.3499543070793152 2023-01-23 08:40:58.489649: step: 2960/1545, loss: 0.6060578227043152 2023-01-23 08:40:59.406751: step: 2962/1545, loss: 0.42924684286117554 2023-01-23 08:41:00.286618: step: 2964/1545, loss: 2.2496297359466553 2023-01-23 08:41:01.157622: step: 2966/1545, loss: 0.17194554209709167 2023-01-23 08:41:02.042773: step: 2968/1545, loss: 1.0365164279937744 2023-01-23 08:41:02.928021: step: 2970/1545, loss: 0.27181828022003174 2023-01-23 08:41:03.784946: step: 2972/1545, loss: 0.24414178729057312 2023-01-23 08:41:04.672250: step: 2974/1545, loss: 0.23439881205558777 2023-01-23 08:41:05.530584: step: 2976/1545, loss: 0.5235244631767273 2023-01-23 08:41:06.385005: step: 2978/1545, loss: 0.3534613847732544 2023-01-23 08:41:07.315457: step: 2980/1545, loss: 0.3463631570339203 2023-01-23 08:41:08.273836: step: 2982/1545, loss: 0.5791162848472595 2023-01-23 08:41:09.139519: step: 2984/1545, loss: 0.4138411283493042 2023-01-23 08:41:10.043816: step: 2986/1545, loss: 0.2994731068611145 2023-01-23 08:41:10.979430: step: 2988/1545, loss: 0.16134856641292572 2023-01-23 08:41:11.880310: step: 2990/1545, loss: 0.33218464255332947 2023-01-23 08:41:12.737922: step: 2992/1545, loss: 0.7149696946144104 2023-01-23 08:41:13.631949: step: 2994/1545, loss: 2.80721116065979 2023-01-23 08:41:14.546184: step: 2996/1545, loss: 1.02922523021698 2023-01-23 08:41:15.449168: step: 2998/1545, loss: 1.10219144821167 2023-01-23 08:41:16.305879: step: 3000/1545, loss: 0.34622716903686523 2023-01-23 08:41:17.197342: step: 3002/1545, loss: 0.3246159255504608 2023-01-23 08:41:18.119172: step: 3004/1545, loss: 0.43670862913131714 2023-01-23 08:41:19.025484: step: 3006/1545, loss: 0.2781078815460205 2023-01-23 08:41:19.919023: step: 3008/1545, loss: 0.23646332323551178 2023-01-23 08:41:20.797006: step: 3010/1545, loss: 0.3011329472064972 2023-01-23 08:41:21.656623: step: 3012/1545, loss: 0.31521889567375183 2023-01-23 08:41:22.655960: step: 3014/1545, loss: 0.28949853777885437 2023-01-23 08:41:23.554766: step: 3016/1545, loss: 0.34387943148612976 2023-01-23 08:41:24.417309: step: 3018/1545, loss: 0.18367840349674225 2023-01-23 08:41:25.326267: step: 3020/1545, loss: 0.2056223601102829 2023-01-23 08:41:26.187587: step: 3022/1545, loss: 0.843325674533844 2023-01-23 08:41:27.023872: step: 3024/1545, loss: 0.45266127586364746 2023-01-23 08:41:27.849435: step: 3026/1545, loss: 2.9738903045654297 2023-01-23 08:41:28.734556: step: 3028/1545, loss: 0.3120085597038269 2023-01-23 08:41:29.600052: step: 3030/1545, loss: 0.2519685626029968 2023-01-23 08:41:30.480781: step: 3032/1545, loss: 0.48713237047195435 2023-01-23 08:41:31.367977: step: 3034/1545, loss: 0.23531635105609894 2023-01-23 08:41:32.237596: step: 3036/1545, loss: 0.47304826974868774 2023-01-23 08:41:33.120904: step: 3038/1545, loss: 0.564221978187561 2023-01-23 08:41:33.995896: step: 3040/1545, loss: 0.389661967754364 2023-01-23 08:41:34.881661: step: 3042/1545, loss: 0.14690200984477997 2023-01-23 08:41:35.760264: step: 3044/1545, loss: 0.5500127077102661 2023-01-23 08:41:36.646606: step: 3046/1545, loss: 0.21153044700622559 2023-01-23 08:41:37.555695: step: 3048/1545, loss: 0.05409565940499306 2023-01-23 08:41:38.496126: step: 3050/1545, loss: 0.13063684105873108 2023-01-23 08:41:39.382523: step: 3052/1545, loss: 0.12499170750379562 2023-01-23 08:41:40.329186: step: 3054/1545, loss: 0.2204098105430603 2023-01-23 08:41:41.261173: step: 3056/1545, loss: 0.27219727635383606 2023-01-23 08:41:42.172666: step: 3058/1545, loss: 0.5469717979431152 2023-01-23 08:41:43.092746: step: 3060/1545, loss: 0.162039652466774 2023-01-23 08:41:43.986128: step: 3062/1545, loss: 0.09439050406217575 2023-01-23 08:41:44.917625: step: 3064/1545, loss: 0.482547402381897 2023-01-23 08:41:45.794712: step: 3066/1545, loss: 0.8519209623336792 2023-01-23 08:41:46.656372: step: 3068/1545, loss: 0.6042469143867493 2023-01-23 08:41:47.529539: step: 3070/1545, loss: 0.3002115786075592 2023-01-23 08:41:48.417711: step: 3072/1545, loss: 0.13840261101722717 2023-01-23 08:41:49.332582: step: 3074/1545, loss: 0.6735842227935791 2023-01-23 08:41:50.193305: step: 3076/1545, loss: 1.4960224628448486 2023-01-23 08:41:51.049867: step: 3078/1545, loss: 0.09330213069915771 2023-01-23 08:41:51.914855: step: 3080/1545, loss: 0.8314270377159119 2023-01-23 08:41:52.776788: step: 3082/1545, loss: 0.26191216707229614 2023-01-23 08:41:53.649601: step: 3084/1545, loss: 0.1639241874217987 2023-01-23 08:41:54.547784: step: 3086/1545, loss: 0.26092329621315 2023-01-23 08:41:55.449749: step: 3088/1545, loss: 0.3997573256492615 2023-01-23 08:41:56.320427: step: 3090/1545, loss: 0.25390711426734924 ================================================== Loss: 0.502 -------------------- Dev Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Dev Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.662984814123997, 'r': 0.6580037110877536, 'f1': 0.6604848713859729}, 'combined': 0.4442901236950689, 'epoch': 7} Test Korean: {'event': {'p': 0.6317460317460317, 'r': 0.7634271099744245, 'f1': 0.6913723219455704}, 'argument': {'p': 0.697622599900428, 'r': 0.7136353604184179, 'f1': 0.7055381362079215}, 'combined': 0.48778953945122083, 'epoch': 7} Dev Russian: {'event': {'p': 0.5708661417322834, 'r': 0.7723035952063915, 'f1': 0.656479909451047}, 'argument': {'p': 0.6611753521292184, 'r': 0.6607024083866366, 'f1': 0.6609387956526069}, 'combined': 0.4338930407227074, 'epoch': 7} Test Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7036865752196788, 'r': 0.7218649255342268, 'f1': 0.7126598470160488}, 'combined': 0.5029131376310397, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6358730158730159, 'r': 0.43552946292672323, 'f1': 0.5169699316040779}, 'combined': 0.3174376773007496, 'epoch': 7} Russian: {'event': {'p': 0.46511627906976744, 'r': 0.5555555555555556, 'f1': 0.5063291139240507}, 'argument': {'p': 0.5833514236099365, 'r': 0.5521004544879756, 'f1': 0.5672958798408557}, 'combined': 0.2872384201725852, 'epoch': 7} New best chinese model... New best korean model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.662984814123997, 'r': 0.6580037110877536, 'f1': 0.6604848713859729}, 'combined': 0.4442901236950689, 'epoch': 7} Test for Korean: {'event': {'p': 0.6317460317460317, 'r': 0.7634271099744245, 'f1': 0.6913723219455704}, 'argument': {'p': 0.697622599900428, 'r': 0.7136353604184179, 'f1': 0.7055381362079215}, 'combined': 0.48778953945122083, 'epoch': 7} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6358730158730159, 'r': 0.43552946292672323, 'f1': 0.5169699316040779}, 'combined': 0.3174376773007496, 'epoch': 7} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 8 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 08:47:30.455464: step: 2/1545, loss: 0.12301982939243317 2023-01-23 08:47:31.404822: step: 4/1545, loss: 0.1908537894487381 2023-01-23 08:47:32.281846: step: 6/1545, loss: 2.248039960861206 2023-01-23 08:47:33.214799: step: 8/1545, loss: 0.43347322940826416 2023-01-23 08:47:34.142329: step: 10/1545, loss: 0.35731634497642517 2023-01-23 08:47:34.995529: step: 12/1545, loss: 0.07601306587457657 2023-01-23 08:47:35.890065: step: 14/1545, loss: 0.2769399881362915 2023-01-23 08:47:36.776099: step: 16/1545, loss: 0.32039129734039307 2023-01-23 08:47:37.683142: step: 18/1545, loss: 0.07539264857769012 2023-01-23 08:47:38.535655: step: 20/1545, loss: 0.4349536597728729 2023-01-23 08:47:39.421526: step: 22/1545, loss: 0.17268700897693634 2023-01-23 08:47:40.301059: step: 24/1545, loss: 0.2248406708240509 2023-01-23 08:47:41.140282: step: 26/1545, loss: 0.08320359140634537 2023-01-23 08:47:42.027858: step: 28/1545, loss: 0.04067187383770943 2023-01-23 08:47:42.909919: step: 30/1545, loss: 0.3132098317146301 2023-01-23 08:47:43.793539: step: 32/1545, loss: 0.16001136600971222 2023-01-23 08:47:44.658054: step: 34/1545, loss: 0.03164321929216385 2023-01-23 08:47:45.502404: step: 36/1545, loss: 0.07329991459846497 2023-01-23 08:47:46.336158: step: 38/1545, loss: 0.3653850555419922 2023-01-23 08:47:47.218418: step: 40/1545, loss: 0.09506211429834366 2023-01-23 08:47:48.057374: step: 42/1545, loss: 0.13525794446468353 2023-01-23 08:47:48.978000: step: 44/1545, loss: 0.350798100233078 2023-01-23 08:47:49.876835: step: 46/1545, loss: 0.26865074038505554 2023-01-23 08:47:50.810483: step: 48/1545, loss: 1.1528868675231934 2023-01-23 08:47:51.659555: step: 50/1545, loss: 0.016598116606473923 2023-01-23 08:47:52.509231: step: 52/1545, loss: 0.2577950656414032 2023-01-23 08:47:53.389031: step: 54/1545, loss: 0.12548744678497314 2023-01-23 08:47:54.293214: step: 56/1545, loss: 0.3911651074886322 2023-01-23 08:47:55.224445: step: 58/1545, loss: 0.17560820281505585 2023-01-23 08:47:56.111024: step: 60/1545, loss: 0.6549379825592041 2023-01-23 08:47:56.995530: step: 62/1545, loss: 3.0695841312408447 2023-01-23 08:47:57.910988: step: 64/1545, loss: 0.10876511037349701 2023-01-23 08:47:58.801034: step: 66/1545, loss: 0.43812963366508484 2023-01-23 08:47:59.693420: step: 68/1545, loss: 0.3804892897605896 2023-01-23 08:48:00.588701: step: 70/1545, loss: 2.045886754989624 2023-01-23 08:48:01.475464: step: 72/1545, loss: 0.2562215328216553 2023-01-23 08:48:02.350585: step: 74/1545, loss: 0.3153550624847412 2023-01-23 08:48:03.244240: step: 76/1545, loss: 0.045290250331163406 2023-01-23 08:48:04.159531: step: 78/1545, loss: 0.3642245829105377 2023-01-23 08:48:05.125358: step: 80/1545, loss: 0.10331294685602188 2023-01-23 08:48:06.007887: step: 82/1545, loss: 0.27399107813835144 2023-01-23 08:48:06.941711: step: 84/1545, loss: 0.9538237452507019 2023-01-23 08:48:07.868140: step: 86/1545, loss: 0.07751163840293884 2023-01-23 08:48:08.772692: step: 88/1545, loss: 0.7600157856941223 2023-01-23 08:48:09.705279: step: 90/1545, loss: 0.3539997339248657 2023-01-23 08:48:10.623332: step: 92/1545, loss: 0.09176309406757355 2023-01-23 08:48:11.497980: step: 94/1545, loss: 0.2979675531387329 2023-01-23 08:48:12.447549: step: 96/1545, loss: 0.39060720801353455 2023-01-23 08:48:13.327151: step: 98/1545, loss: 0.21748220920562744 2023-01-23 08:48:14.199911: step: 100/1545, loss: 0.13733834028244019 2023-01-23 08:48:15.076507: step: 102/1545, loss: 0.1512412428855896 2023-01-23 08:48:15.914333: step: 104/1545, loss: 0.43547675013542175 2023-01-23 08:48:16.759790: step: 106/1545, loss: 0.10845392197370529 2023-01-23 08:48:17.659683: step: 108/1545, loss: 0.06967204064130783 2023-01-23 08:48:18.548496: step: 110/1545, loss: 0.1075751855969429 2023-01-23 08:48:19.414329: step: 112/1545, loss: 0.031152766197919846 2023-01-23 08:48:20.303482: step: 114/1545, loss: 0.3844972550868988 2023-01-23 08:48:21.168840: step: 116/1545, loss: 0.17488260567188263 2023-01-23 08:48:22.077729: step: 118/1545, loss: 0.18131259083747864 2023-01-23 08:48:22.963892: step: 120/1545, loss: 0.35996347665786743 2023-01-23 08:48:23.909857: step: 122/1545, loss: 0.46810704469680786 2023-01-23 08:48:24.770617: step: 124/1545, loss: 0.4441145658493042 2023-01-23 08:48:25.610566: step: 126/1545, loss: 0.0890277549624443 2023-01-23 08:48:26.499263: step: 128/1545, loss: 0.3330049216747284 2023-01-23 08:48:27.426196: step: 130/1545, loss: 0.9788362979888916 2023-01-23 08:48:28.331435: step: 132/1545, loss: 0.1284547746181488 2023-01-23 08:48:29.188419: step: 134/1545, loss: 0.12931422889232635 2023-01-23 08:48:30.085876: step: 136/1545, loss: 0.2922745645046234 2023-01-23 08:48:30.968692: step: 138/1545, loss: 0.07835470139980316 2023-01-23 08:48:31.831686: step: 140/1545, loss: 0.09245221316814423 2023-01-23 08:48:32.693813: step: 142/1545, loss: 0.0656980574131012 2023-01-23 08:48:33.556344: step: 144/1545, loss: 0.33878225088119507 2023-01-23 08:48:34.438966: step: 146/1545, loss: 0.2225721925497055 2023-01-23 08:48:35.318020: step: 148/1545, loss: 0.12871573865413666 2023-01-23 08:48:36.241098: step: 150/1545, loss: 0.1840311884880066 2023-01-23 08:48:37.154092: step: 152/1545, loss: 0.30550673604011536 2023-01-23 08:48:38.049086: step: 154/1545, loss: 0.33793988823890686 2023-01-23 08:48:38.961549: step: 156/1545, loss: 0.12197869271039963 2023-01-23 08:48:39.857412: step: 158/1545, loss: 0.08423814177513123 2023-01-23 08:48:40.846273: step: 160/1545, loss: 0.4911837875843048 2023-01-23 08:48:41.755522: step: 162/1545, loss: 0.9225647449493408 2023-01-23 08:48:42.661922: step: 164/1545, loss: 0.1506667584180832 2023-01-23 08:48:43.573635: step: 166/1545, loss: 0.3845895230770111 2023-01-23 08:48:44.425833: step: 168/1545, loss: 0.07903057336807251 2023-01-23 08:48:45.315051: step: 170/1545, loss: 0.29541778564453125 2023-01-23 08:48:46.204499: step: 172/1545, loss: 0.19813412427902222 2023-01-23 08:48:47.078868: step: 174/1545, loss: 0.19795525074005127 2023-01-23 08:48:47.967448: step: 176/1545, loss: 0.352999746799469 2023-01-23 08:48:48.824988: step: 178/1545, loss: 0.09015057981014252 2023-01-23 08:48:49.732411: step: 180/1545, loss: 0.2483784556388855 2023-01-23 08:48:50.616057: step: 182/1545, loss: 5.015138149261475 2023-01-23 08:48:51.495891: step: 184/1545, loss: 0.10622483491897583 2023-01-23 08:48:52.449914: step: 186/1545, loss: 0.07590457051992416 2023-01-23 08:48:53.320789: step: 188/1545, loss: 0.20268915593624115 2023-01-23 08:48:54.163358: step: 190/1545, loss: 0.15023483335971832 2023-01-23 08:48:54.996716: step: 192/1545, loss: 0.1266862452030182 2023-01-23 08:48:55.880658: step: 194/1545, loss: 0.07519681751728058 2023-01-23 08:48:56.787074: step: 196/1545, loss: 0.3552381992340088 2023-01-23 08:48:57.702457: step: 198/1545, loss: 0.16098742187023163 2023-01-23 08:48:58.564406: step: 200/1545, loss: 1.0131902694702148 2023-01-23 08:48:59.413777: step: 202/1545, loss: 0.0162276029586792 2023-01-23 08:49:00.325948: step: 204/1545, loss: 0.27640366554260254 2023-01-23 08:49:01.230940: step: 206/1545, loss: 1.4472204446792603 2023-01-23 08:49:02.118761: step: 208/1545, loss: 0.23344145715236664 2023-01-23 08:49:02.993268: step: 210/1545, loss: 0.1424480527639389 2023-01-23 08:49:03.870537: step: 212/1545, loss: 0.42806750535964966 2023-01-23 08:49:04.708642: step: 214/1545, loss: 0.15510210394859314 2023-01-23 08:49:05.596230: step: 216/1545, loss: 0.14755205810070038 2023-01-23 08:49:06.477883: step: 218/1545, loss: 0.13542871177196503 2023-01-23 08:49:07.373513: step: 220/1545, loss: 0.06580528616905212 2023-01-23 08:49:08.241187: step: 222/1545, loss: 0.4713000953197479 2023-01-23 08:49:09.177568: step: 224/1545, loss: 0.15700633823871613 2023-01-23 08:49:10.172207: step: 226/1545, loss: 0.1137005016207695 2023-01-23 08:49:11.114575: step: 228/1545, loss: 0.05205943435430527 2023-01-23 08:49:12.000283: step: 230/1545, loss: 0.13716496527194977 2023-01-23 08:49:12.914853: step: 232/1545, loss: 0.22315211594104767 2023-01-23 08:49:13.771086: step: 234/1545, loss: 0.4598740041255951 2023-01-23 08:49:14.643129: step: 236/1545, loss: 0.16761693358421326 2023-01-23 08:49:15.512988: step: 238/1545, loss: 0.14080628752708435 2023-01-23 08:49:16.428584: step: 240/1545, loss: 0.4679512679576874 2023-01-23 08:49:17.361681: step: 242/1545, loss: 0.2915019690990448 2023-01-23 08:49:18.320373: step: 244/1545, loss: 0.08556777983903885 2023-01-23 08:49:19.212559: step: 246/1545, loss: 0.11237834393978119 2023-01-23 08:49:20.116738: step: 248/1545, loss: 0.017547672614455223 2023-01-23 08:49:20.987432: step: 250/1545, loss: 0.053137242794036865 2023-01-23 08:49:21.894333: step: 252/1545, loss: 0.7815772294998169 2023-01-23 08:49:22.748178: step: 254/1545, loss: 0.19768530130386353 2023-01-23 08:49:23.669241: step: 256/1545, loss: 0.2462644726037979 2023-01-23 08:49:24.568686: step: 258/1545, loss: 0.028957579284906387 2023-01-23 08:49:25.475158: step: 260/1545, loss: 0.08568602800369263 2023-01-23 08:49:26.338865: step: 262/1545, loss: 0.27260372042655945 2023-01-23 08:49:27.324295: step: 264/1545, loss: 0.11004646867513657 2023-01-23 08:49:28.253565: step: 266/1545, loss: 0.34060433506965637 2023-01-23 08:49:29.102245: step: 268/1545, loss: 0.20189236104488373 2023-01-23 08:49:29.970373: step: 270/1545, loss: 0.13940967619419098 2023-01-23 08:49:30.838795: step: 272/1545, loss: 0.30422043800354004 2023-01-23 08:49:31.700547: step: 274/1545, loss: 0.3560512959957123 2023-01-23 08:49:32.645709: step: 276/1545, loss: 2.7090840339660645 2023-01-23 08:49:33.596182: step: 278/1545, loss: 0.015855975449085236 2023-01-23 08:49:34.459201: step: 280/1545, loss: 0.25766921043395996 2023-01-23 08:49:35.391723: step: 282/1545, loss: 0.39759549498558044 2023-01-23 08:49:36.271801: step: 284/1545, loss: 0.5417835712432861 2023-01-23 08:49:37.146784: step: 286/1545, loss: 0.09865330904722214 2023-01-23 08:49:38.087867: step: 288/1545, loss: 0.35055625438690186 2023-01-23 08:49:38.977409: step: 290/1545, loss: 0.14087778329849243 2023-01-23 08:49:39.838267: step: 292/1545, loss: 0.29869669675827026 2023-01-23 08:49:40.694146: step: 294/1545, loss: 0.021125145256519318 2023-01-23 08:49:41.556589: step: 296/1545, loss: 0.17923346161842346 2023-01-23 08:49:42.415558: step: 298/1545, loss: 0.12683357298374176 2023-01-23 08:49:43.297220: step: 300/1545, loss: 0.09291046857833862 2023-01-23 08:49:44.177403: step: 302/1545, loss: 0.10938555747270584 2023-01-23 08:49:45.078567: step: 304/1545, loss: 0.10784865915775299 2023-01-23 08:49:45.990136: step: 306/1545, loss: 0.21351757645606995 2023-01-23 08:49:46.919739: step: 308/1545, loss: 0.17948926985263824 2023-01-23 08:49:47.804172: step: 310/1545, loss: 0.43092381954193115 2023-01-23 08:49:48.766165: step: 312/1545, loss: 0.06671202927827835 2023-01-23 08:49:49.624914: step: 314/1545, loss: 0.3256629705429077 2023-01-23 08:49:50.489069: step: 316/1545, loss: 0.7352334856987 2023-01-23 08:49:51.416651: step: 318/1545, loss: 0.09562356770038605 2023-01-23 08:49:52.329812: step: 320/1545, loss: 0.1058964878320694 2023-01-23 08:49:53.209686: step: 322/1545, loss: 0.30734068155288696 2023-01-23 08:49:54.077843: step: 324/1545, loss: 0.21060091257095337 2023-01-23 08:49:54.942047: step: 326/1545, loss: 0.7254253029823303 2023-01-23 08:49:55.865832: step: 328/1545, loss: 0.4553363621234894 2023-01-23 08:49:56.821509: step: 330/1545, loss: 0.24245227873325348 2023-01-23 08:49:57.703187: step: 332/1545, loss: 0.26536619663238525 2023-01-23 08:49:58.590563: step: 334/1545, loss: 0.34126850962638855 2023-01-23 08:49:59.494928: step: 336/1545, loss: 0.733404278755188 2023-01-23 08:50:00.344112: step: 338/1545, loss: 0.0630069300532341 2023-01-23 08:50:01.234733: step: 340/1545, loss: 0.7262266278266907 2023-01-23 08:50:02.171519: step: 342/1545, loss: 0.20504142343997955 2023-01-23 08:50:03.112368: step: 344/1545, loss: 0.11407797038555145 2023-01-23 08:50:03.965813: step: 346/1545, loss: 2.693936347961426 2023-01-23 08:50:04.845556: step: 348/1545, loss: 0.24153046309947968 2023-01-23 08:50:05.763315: step: 350/1545, loss: 0.14713813364505768 2023-01-23 08:50:06.642258: step: 352/1545, loss: 0.16694387793540955 2023-01-23 08:50:07.522075: step: 354/1545, loss: 0.42460963129997253 2023-01-23 08:50:08.379586: step: 356/1545, loss: 0.3266555368900299 2023-01-23 08:50:09.264353: step: 358/1545, loss: 0.47656792402267456 2023-01-23 08:50:10.111052: step: 360/1545, loss: 0.033363040536642075 2023-01-23 08:50:10.997481: step: 362/1545, loss: 0.27978676557540894 2023-01-23 08:50:11.864829: step: 364/1545, loss: 0.25302308797836304 2023-01-23 08:50:12.755853: step: 366/1545, loss: 0.48421695828437805 2023-01-23 08:50:13.621103: step: 368/1545, loss: 0.04453570768237114 2023-01-23 08:50:14.474043: step: 370/1545, loss: 0.1462133824825287 2023-01-23 08:50:15.358674: step: 372/1545, loss: 0.1612199991941452 2023-01-23 08:50:16.243813: step: 374/1545, loss: 0.19931161403656006 2023-01-23 08:50:17.121043: step: 376/1545, loss: 0.21467460691928864 2023-01-23 08:50:17.983987: step: 378/1545, loss: 0.157389834523201 2023-01-23 08:50:18.827937: step: 380/1545, loss: 0.08595369011163712 2023-01-23 08:50:19.753752: step: 382/1545, loss: 0.21115635335445404 2023-01-23 08:50:20.699519: step: 384/1545, loss: 0.22739757597446442 2023-01-23 08:50:21.574320: step: 386/1545, loss: 0.2841663360595703 2023-01-23 08:50:22.460554: step: 388/1545, loss: 0.4312552213668823 2023-01-23 08:50:23.347509: step: 390/1545, loss: 0.5009002685546875 2023-01-23 08:50:24.225704: step: 392/1545, loss: 0.24804671108722687 2023-01-23 08:50:25.270578: step: 394/1545, loss: 0.2388426512479782 2023-01-23 08:50:26.135346: step: 396/1545, loss: 0.4500732719898224 2023-01-23 08:50:27.012522: step: 398/1545, loss: 0.24010899662971497 2023-01-23 08:50:27.928226: step: 400/1545, loss: 0.43488824367523193 2023-01-23 08:50:28.823518: step: 402/1545, loss: 0.035395074635744095 2023-01-23 08:50:29.707537: step: 404/1545, loss: 0.14110282063484192 2023-01-23 08:50:30.672571: step: 406/1545, loss: 0.04309004917740822 2023-01-23 08:50:31.544432: step: 408/1545, loss: 0.08924233913421631 2023-01-23 08:50:32.435990: step: 410/1545, loss: 0.10169419646263123 2023-01-23 08:50:33.296486: step: 412/1545, loss: 0.0834883451461792 2023-01-23 08:50:34.174517: step: 414/1545, loss: 0.42170703411102295 2023-01-23 08:50:35.150087: step: 416/1545, loss: 0.4786008298397064 2023-01-23 08:50:36.059154: step: 418/1545, loss: 0.3936458230018616 2023-01-23 08:50:36.952026: step: 420/1545, loss: 0.15572930872440338 2023-01-23 08:50:37.820822: step: 422/1545, loss: 0.13440904021263123 2023-01-23 08:50:38.684118: step: 424/1545, loss: 0.39407098293304443 2023-01-23 08:50:39.572259: step: 426/1545, loss: 0.26732999086380005 2023-01-23 08:50:40.438178: step: 428/1545, loss: 2.087700366973877 2023-01-23 08:50:41.321791: step: 430/1545, loss: 1.1798162460327148 2023-01-23 08:50:42.238526: step: 432/1545, loss: 0.10974960774183273 2023-01-23 08:50:43.108728: step: 434/1545, loss: 0.5081357359886169 2023-01-23 08:50:43.979320: step: 436/1545, loss: 0.08418796956539154 2023-01-23 08:50:44.825106: step: 438/1545, loss: 0.5784751176834106 2023-01-23 08:50:45.696364: step: 440/1545, loss: 0.1307479739189148 2023-01-23 08:50:46.570134: step: 442/1545, loss: 0.6021875739097595 2023-01-23 08:50:47.434412: step: 444/1545, loss: 0.16120751202106476 2023-01-23 08:50:48.357900: step: 446/1545, loss: 0.2464054375886917 2023-01-23 08:50:49.241680: step: 448/1545, loss: 0.297833651304245 2023-01-23 08:50:50.157883: step: 450/1545, loss: 0.17136593163013458 2023-01-23 08:50:51.008557: step: 452/1545, loss: 0.19053557515144348 2023-01-23 08:50:51.907653: step: 454/1545, loss: 0.4702270030975342 2023-01-23 08:50:52.777988: step: 456/1545, loss: 0.4166325628757477 2023-01-23 08:50:53.680227: step: 458/1545, loss: 0.6727341413497925 2023-01-23 08:50:54.592676: step: 460/1545, loss: 0.3354860544204712 2023-01-23 08:50:55.507755: step: 462/1545, loss: 0.7947321534156799 2023-01-23 08:50:56.371110: step: 464/1545, loss: 0.19814424216747284 2023-01-23 08:50:57.339425: step: 466/1545, loss: 0.35449641942977905 2023-01-23 08:50:58.214173: step: 468/1545, loss: 0.17337395250797272 2023-01-23 08:50:59.160394: step: 470/1545, loss: 0.14043448865413666 2023-01-23 08:51:00.057782: step: 472/1545, loss: 0.15402567386627197 2023-01-23 08:51:00.995052: step: 474/1545, loss: 0.17596133053302765 2023-01-23 08:51:01.890567: step: 476/1545, loss: 0.3001476526260376 2023-01-23 08:51:02.758839: step: 478/1545, loss: 0.0945432111620903 2023-01-23 08:51:03.620360: step: 480/1545, loss: 0.5806198120117188 2023-01-23 08:51:04.510673: step: 482/1545, loss: 0.36353349685668945 2023-01-23 08:51:05.356204: step: 484/1545, loss: 0.18575893342494965 2023-01-23 08:51:06.212179: step: 486/1545, loss: 0.12265595048666 2023-01-23 08:51:07.092042: step: 488/1545, loss: 0.15941262245178223 2023-01-23 08:51:07.932729: step: 490/1545, loss: 0.45399990677833557 2023-01-23 08:51:08.846156: step: 492/1545, loss: 0.3735991418361664 2023-01-23 08:51:09.769787: step: 494/1545, loss: 0.6055878400802612 2023-01-23 08:51:10.672521: step: 496/1545, loss: 0.2923453748226166 2023-01-23 08:51:11.539732: step: 498/1545, loss: 0.1354076862335205 2023-01-23 08:51:12.398420: step: 500/1545, loss: 0.6857957243919373 2023-01-23 08:51:13.341298: step: 502/1545, loss: 0.29586127400398254 2023-01-23 08:51:14.245097: step: 504/1545, loss: 0.11823783814907074 2023-01-23 08:51:15.244420: step: 506/1545, loss: 0.045809417963027954 2023-01-23 08:51:16.116163: step: 508/1545, loss: 0.271489679813385 2023-01-23 08:51:17.045583: step: 510/1545, loss: 0.18508732318878174 2023-01-23 08:51:17.967540: step: 512/1545, loss: 0.324552983045578 2023-01-23 08:51:18.883040: step: 514/1545, loss: 0.3346085846424103 2023-01-23 08:51:19.743237: step: 516/1545, loss: 0.1841658651828766 2023-01-23 08:51:20.607556: step: 518/1545, loss: 0.4130609631538391 2023-01-23 08:51:21.455425: step: 520/1545, loss: 0.06333788484334946 2023-01-23 08:51:22.328380: step: 522/1545, loss: 0.22890643775463104 2023-01-23 08:51:23.187288: step: 524/1545, loss: 0.04877788946032524 2023-01-23 08:51:24.079694: step: 526/1545, loss: 0.32851991057395935 2023-01-23 08:51:24.987188: step: 528/1545, loss: 0.17466169595718384 2023-01-23 08:51:25.844065: step: 530/1545, loss: 0.202004075050354 2023-01-23 08:51:26.724477: step: 532/1545, loss: 0.2843574583530426 2023-01-23 08:51:27.612257: step: 534/1545, loss: 0.14511878788471222 2023-01-23 08:51:28.514134: step: 536/1545, loss: 0.265993595123291 2023-01-23 08:51:29.380545: step: 538/1545, loss: 0.19184763729572296 2023-01-23 08:51:30.212808: step: 540/1545, loss: 0.44698038697242737 2023-01-23 08:51:31.123168: step: 542/1545, loss: 0.2531091868877411 2023-01-23 08:51:32.100328: step: 544/1545, loss: 1.2452421188354492 2023-01-23 08:51:32.986164: step: 546/1545, loss: 0.16074618697166443 2023-01-23 08:51:33.883707: step: 548/1545, loss: 0.29693105816841125 2023-01-23 08:51:34.762496: step: 550/1545, loss: 0.6582170724868774 2023-01-23 08:51:35.643665: step: 552/1545, loss: 0.2714564800262451 2023-01-23 08:51:36.538557: step: 554/1545, loss: 0.4410172402858734 2023-01-23 08:51:37.409255: step: 556/1545, loss: 0.12357531487941742 2023-01-23 08:51:38.295257: step: 558/1545, loss: 0.2215677797794342 2023-01-23 08:51:39.221418: step: 560/1545, loss: 0.2359950840473175 2023-01-23 08:51:40.064064: step: 562/1545, loss: 0.05981723964214325 2023-01-23 08:51:40.969704: step: 564/1545, loss: 0.3466012477874756 2023-01-23 08:51:41.861787: step: 566/1545, loss: 0.04326138272881508 2023-01-23 08:51:42.834335: step: 568/1545, loss: 0.1335943341255188 2023-01-23 08:51:43.730073: step: 570/1545, loss: 0.10483723878860474 2023-01-23 08:51:44.634559: step: 572/1545, loss: 0.33138176798820496 2023-01-23 08:51:45.502823: step: 574/1545, loss: 0.8391335606575012 2023-01-23 08:51:46.390653: step: 576/1545, loss: 0.3294579088687897 2023-01-23 08:51:47.292909: step: 578/1545, loss: 0.1129116341471672 2023-01-23 08:51:48.289380: step: 580/1545, loss: 0.19060258567333221 2023-01-23 08:51:49.155027: step: 582/1545, loss: 0.318411648273468 2023-01-23 08:51:50.051092: step: 584/1545, loss: 0.10091009736061096 2023-01-23 08:51:50.905085: step: 586/1545, loss: 0.232728973031044 2023-01-23 08:51:51.888978: step: 588/1545, loss: 0.10851234197616577 2023-01-23 08:51:52.736786: step: 590/1545, loss: 0.3419320285320282 2023-01-23 08:51:53.624917: step: 592/1545, loss: 0.5185362100601196 2023-01-23 08:51:54.515761: step: 594/1545, loss: 0.3459123373031616 2023-01-23 08:51:55.404581: step: 596/1545, loss: 0.10064958781003952 2023-01-23 08:51:56.329877: step: 598/1545, loss: 0.13636158406734467 2023-01-23 08:51:57.211500: step: 600/1545, loss: 0.4787054657936096 2023-01-23 08:51:58.047156: step: 602/1545, loss: 0.14525039494037628 2023-01-23 08:51:58.905468: step: 604/1545, loss: 0.5405306816101074 2023-01-23 08:51:59.819281: step: 606/1545, loss: 0.2027362585067749 2023-01-23 08:52:00.691185: step: 608/1545, loss: 0.13987651467323303 2023-01-23 08:52:01.592987: step: 610/1545, loss: 0.2066032737493515 2023-01-23 08:52:02.486583: step: 612/1545, loss: 0.7480338215827942 2023-01-23 08:52:03.359198: step: 614/1545, loss: 0.7611439228057861 2023-01-23 08:52:04.246427: step: 616/1545, loss: 0.05580361559987068 2023-01-23 08:52:05.152478: step: 618/1545, loss: 0.0914791077375412 2023-01-23 08:52:06.030498: step: 620/1545, loss: 0.5585664510726929 2023-01-23 08:52:06.892892: step: 622/1545, loss: 0.28779059648513794 2023-01-23 08:52:07.828877: step: 624/1545, loss: 3.9535446166992188 2023-01-23 08:52:08.753958: step: 626/1545, loss: 0.08569090813398361 2023-01-23 08:52:09.634170: step: 628/1545, loss: 0.6696035861968994 2023-01-23 08:52:10.516495: step: 630/1545, loss: 0.19411128759384155 2023-01-23 08:52:11.404852: step: 632/1545, loss: 0.38966870307922363 2023-01-23 08:52:12.306986: step: 634/1545, loss: 0.48714587092399597 2023-01-23 08:52:13.179512: step: 636/1545, loss: 0.27065980434417725 2023-01-23 08:52:14.039358: step: 638/1545, loss: 0.055060748010873795 2023-01-23 08:52:14.887625: step: 640/1545, loss: 0.33408427238464355 2023-01-23 08:52:15.776681: step: 642/1545, loss: 0.22090858221054077 2023-01-23 08:52:16.640364: step: 644/1545, loss: 0.2742220163345337 2023-01-23 08:52:17.515302: step: 646/1545, loss: 0.08428129553794861 2023-01-23 08:52:18.386350: step: 648/1545, loss: 0.5847083926200867 2023-01-23 08:52:19.305298: step: 650/1545, loss: 0.0947953537106514 2023-01-23 08:52:20.166023: step: 652/1545, loss: 0.6186466217041016 2023-01-23 08:52:21.070478: step: 654/1545, loss: 0.08505742251873016 2023-01-23 08:52:21.966022: step: 656/1545, loss: 0.47325432300567627 2023-01-23 08:52:22.870779: step: 658/1545, loss: 0.1646055430173874 2023-01-23 08:52:23.727780: step: 660/1545, loss: 0.20058152079582214 2023-01-23 08:52:24.577755: step: 662/1545, loss: 0.33006078004837036 2023-01-23 08:52:25.465140: step: 664/1545, loss: 0.31143903732299805 2023-01-23 08:52:26.361620: step: 666/1545, loss: 0.3795795440673828 2023-01-23 08:52:27.347749: step: 668/1545, loss: 0.36537402868270874 2023-01-23 08:52:28.223128: step: 670/1545, loss: 0.2048669010400772 2023-01-23 08:52:29.112104: step: 672/1545, loss: 0.31476497650146484 2023-01-23 08:52:29.987907: step: 674/1545, loss: 0.40448546409606934 2023-01-23 08:52:30.853161: step: 676/1545, loss: 0.1260116994380951 2023-01-23 08:52:31.715050: step: 678/1545, loss: 0.050017908215522766 2023-01-23 08:52:32.593163: step: 680/1545, loss: 0.28526440262794495 2023-01-23 08:52:33.445073: step: 682/1545, loss: 0.2271435260772705 2023-01-23 08:52:34.308511: step: 684/1545, loss: 0.12173396348953247 2023-01-23 08:52:35.220542: step: 686/1545, loss: 0.15423402190208435 2023-01-23 08:52:36.125723: step: 688/1545, loss: 0.17422547936439514 2023-01-23 08:52:37.004047: step: 690/1545, loss: 0.3605009913444519 2023-01-23 08:52:37.874180: step: 692/1545, loss: 0.5005402565002441 2023-01-23 08:52:38.753915: step: 694/1545, loss: 0.17384453117847443 2023-01-23 08:52:39.678413: step: 696/1545, loss: 0.17272458970546722 2023-01-23 08:52:40.624807: step: 698/1545, loss: 0.231843501329422 2023-01-23 08:52:41.577831: step: 700/1545, loss: 0.1704099029302597 2023-01-23 08:52:42.529854: step: 702/1545, loss: 0.20708541572093964 2023-01-23 08:52:43.425834: step: 704/1545, loss: 0.17495962977409363 2023-01-23 08:52:44.362293: step: 706/1545, loss: 0.1943361908197403 2023-01-23 08:52:45.233582: step: 708/1545, loss: 0.9520679712295532 2023-01-23 08:52:46.080212: step: 710/1545, loss: 0.0355604849755764 2023-01-23 08:52:46.926944: step: 712/1545, loss: 0.2745896279811859 2023-01-23 08:52:47.780310: step: 714/1545, loss: 0.2670464515686035 2023-01-23 08:52:48.713062: step: 716/1545, loss: 0.3082897365093231 2023-01-23 08:52:49.636934: step: 718/1545, loss: 0.34994691610336304 2023-01-23 08:52:50.522887: step: 720/1545, loss: 0.17339955270290375 2023-01-23 08:52:51.393896: step: 722/1545, loss: 0.08027800172567368 2023-01-23 08:52:52.285060: step: 724/1545, loss: 0.3775012195110321 2023-01-23 08:52:53.162477: step: 726/1545, loss: 0.373534232378006 2023-01-23 08:52:54.142426: step: 728/1545, loss: 0.16656242311000824 2023-01-23 08:52:54.983296: step: 730/1545, loss: 0.3453470468521118 2023-01-23 08:52:55.859190: step: 732/1545, loss: 0.3407958447933197 2023-01-23 08:52:56.733707: step: 734/1545, loss: 0.23960620164871216 2023-01-23 08:52:57.714356: step: 736/1545, loss: 0.19251985847949982 2023-01-23 08:52:58.598229: step: 738/1545, loss: 0.2217465341091156 2023-01-23 08:52:59.469305: step: 740/1545, loss: 0.647799015045166 2023-01-23 08:53:00.401613: step: 742/1545, loss: 0.27553340792655945 2023-01-23 08:53:01.331751: step: 744/1545, loss: 0.3554830849170685 2023-01-23 08:53:02.201718: step: 746/1545, loss: 0.13080202043056488 2023-01-23 08:53:03.102040: step: 748/1545, loss: 0.2226332128047943 2023-01-23 08:53:03.981650: step: 750/1545, loss: 0.2792576253414154 2023-01-23 08:53:04.885415: step: 752/1545, loss: 0.38351303339004517 2023-01-23 08:53:05.767794: step: 754/1545, loss: 0.3319891393184662 2023-01-23 08:53:06.673487: step: 756/1545, loss: 0.2692292332649231 2023-01-23 08:53:07.625303: step: 758/1545, loss: 0.4914631247520447 2023-01-23 08:53:08.584399: step: 760/1545, loss: 0.21141420304775238 2023-01-23 08:53:09.525157: step: 762/1545, loss: 0.1737441122531891 2023-01-23 08:53:10.487160: step: 764/1545, loss: 0.4089789092540741 2023-01-23 08:53:11.368134: step: 766/1545, loss: 0.08778546005487442 2023-01-23 08:53:12.246590: step: 768/1545, loss: 0.17828117311000824 2023-01-23 08:53:13.098645: step: 770/1545, loss: 0.26189684867858887 2023-01-23 08:53:13.996419: step: 772/1545, loss: 0.5645584464073181 2023-01-23 08:53:14.900574: step: 774/1545, loss: 0.8701507449150085 2023-01-23 08:53:15.791288: step: 776/1545, loss: 2.7538998126983643 2023-01-23 08:53:16.671847: step: 778/1545, loss: 0.3496715724468231 2023-01-23 08:53:17.532241: step: 780/1545, loss: 0.38902315497398376 2023-01-23 08:53:18.388308: step: 782/1545, loss: 0.17107781767845154 2023-01-23 08:53:19.288767: step: 784/1545, loss: 0.18452727794647217 2023-01-23 08:53:20.127491: step: 786/1545, loss: 0.12353092432022095 2023-01-23 08:53:21.006280: step: 788/1545, loss: 0.4668964743614197 2023-01-23 08:53:21.864736: step: 790/1545, loss: 0.40902501344680786 2023-01-23 08:53:22.753998: step: 792/1545, loss: 2.5094668865203857 2023-01-23 08:53:23.608891: step: 794/1545, loss: 0.3126695454120636 2023-01-23 08:53:24.476737: step: 796/1545, loss: 0.06261889636516571 2023-01-23 08:53:25.369450: step: 798/1545, loss: 0.2757878303527832 2023-01-23 08:53:26.276404: step: 800/1545, loss: 0.12141063809394836 2023-01-23 08:53:27.209732: step: 802/1545, loss: 0.6756105422973633 2023-01-23 08:53:28.104722: step: 804/1545, loss: 0.20878192782402039 2023-01-23 08:53:28.991790: step: 806/1545, loss: 0.12649637460708618 2023-01-23 08:53:29.885747: step: 808/1545, loss: 0.06476473063230515 2023-01-23 08:53:30.755714: step: 810/1545, loss: 0.23551560938358307 2023-01-23 08:53:31.617296: step: 812/1545, loss: 0.658815324306488 2023-01-23 08:53:32.493863: step: 814/1545, loss: 0.3286498785018921 2023-01-23 08:53:33.437032: step: 816/1545, loss: 0.9682584404945374 2023-01-23 08:53:34.287806: step: 818/1545, loss: 0.2852967083454132 2023-01-23 08:53:35.354768: step: 820/1545, loss: 0.0825304314494133 2023-01-23 08:53:36.348589: step: 822/1545, loss: 0.1271580159664154 2023-01-23 08:53:37.239159: step: 824/1545, loss: 0.09308131784200668 2023-01-23 08:53:38.119861: step: 826/1545, loss: 0.46375277638435364 2023-01-23 08:53:39.048910: step: 828/1545, loss: 1.1453380584716797 2023-01-23 08:53:39.889938: step: 830/1545, loss: 0.12123806774616241 2023-01-23 08:53:40.772682: step: 832/1545, loss: 0.7339867949485779 2023-01-23 08:53:41.638718: step: 834/1545, loss: 0.314779132604599 2023-01-23 08:53:42.544231: step: 836/1545, loss: 0.05192382633686066 2023-01-23 08:53:43.506278: step: 838/1545, loss: 0.08346232771873474 2023-01-23 08:53:44.372753: step: 840/1545, loss: 0.22118167579174042 2023-01-23 08:53:45.293434: step: 842/1545, loss: 0.1156841367483139 2023-01-23 08:53:46.189222: step: 844/1545, loss: 0.40977922081947327 2023-01-23 08:53:47.075437: step: 846/1545, loss: 0.13781775534152985 2023-01-23 08:53:47.967517: step: 848/1545, loss: 0.31970855593681335 2023-01-23 08:53:48.916471: step: 850/1545, loss: 0.1486825942993164 2023-01-23 08:53:49.835098: step: 852/1545, loss: 0.12706951797008514 2023-01-23 08:53:50.690072: step: 854/1545, loss: 0.2508913576602936 2023-01-23 08:53:51.537613: step: 856/1545, loss: 0.06518743932247162 2023-01-23 08:53:52.435758: step: 858/1545, loss: 0.5738097429275513 2023-01-23 08:53:53.345302: step: 860/1545, loss: 0.1351061463356018 2023-01-23 08:53:54.228733: step: 862/1545, loss: 0.36763331294059753 2023-01-23 08:53:55.147884: step: 864/1545, loss: 0.2247169464826584 2023-01-23 08:53:56.044094: step: 866/1545, loss: 0.37028318643569946 2023-01-23 08:53:56.909310: step: 868/1545, loss: 0.024714119732379913 2023-01-23 08:53:57.760842: step: 870/1545, loss: 0.3915970027446747 2023-01-23 08:53:58.628906: step: 872/1545, loss: 0.6152401566505432 2023-01-23 08:53:59.487683: step: 874/1545, loss: 0.5140848159790039 2023-01-23 08:54:00.346062: step: 876/1545, loss: 0.18635284900665283 2023-01-23 08:54:01.200516: step: 878/1545, loss: 0.7109348773956299 2023-01-23 08:54:02.082868: step: 880/1545, loss: 0.5744399428367615 2023-01-23 08:54:02.967084: step: 882/1545, loss: 0.4573860466480255 2023-01-23 08:54:03.874854: step: 884/1545, loss: 0.07064896821975708 2023-01-23 08:54:04.727760: step: 886/1545, loss: 0.22601726651191711 2023-01-23 08:54:05.602304: step: 888/1545, loss: 0.305537611246109 2023-01-23 08:54:06.479037: step: 890/1545, loss: 0.06339703500270844 2023-01-23 08:54:07.367055: step: 892/1545, loss: 0.28011056780815125 2023-01-23 08:54:08.221897: step: 894/1545, loss: 0.08352690190076828 2023-01-23 08:54:09.158964: step: 896/1545, loss: 0.7296658158302307 2023-01-23 08:54:10.009592: step: 898/1545, loss: 0.26546141505241394 2023-01-23 08:54:10.878030: step: 900/1545, loss: 0.20248112082481384 2023-01-23 08:54:11.785875: step: 902/1545, loss: 0.29611122608184814 2023-01-23 08:54:12.685991: step: 904/1545, loss: 0.2984022796154022 2023-01-23 08:54:13.570699: step: 906/1545, loss: 0.0645172968506813 2023-01-23 08:54:14.461631: step: 908/1545, loss: 0.2383728176355362 2023-01-23 08:54:15.325432: step: 910/1545, loss: 0.25648242235183716 2023-01-23 08:54:16.255304: step: 912/1545, loss: 0.34322425723075867 2023-01-23 08:54:17.230862: step: 914/1545, loss: 0.2861354649066925 2023-01-23 08:54:18.113819: step: 916/1545, loss: 0.22601045668125153 2023-01-23 08:54:19.025605: step: 918/1545, loss: 0.13885007798671722 2023-01-23 08:54:19.901016: step: 920/1545, loss: 1.573026418685913 2023-01-23 08:54:20.820767: step: 922/1545, loss: 0.1876649111509323 2023-01-23 08:54:21.730030: step: 924/1545, loss: 2.7077572345733643 2023-01-23 08:54:22.618689: step: 926/1545, loss: 0.06940925866365433 2023-01-23 08:54:23.485445: step: 928/1545, loss: 0.11817624419927597 2023-01-23 08:54:24.356564: step: 930/1545, loss: 0.015421097166836262 2023-01-23 08:54:25.193999: step: 932/1545, loss: 0.1574385017156601 2023-01-23 08:54:26.072194: step: 934/1545, loss: 0.19604243338108063 2023-01-23 08:54:26.926735: step: 936/1545, loss: 0.19176830351352692 2023-01-23 08:54:27.841931: step: 938/1545, loss: 0.23049898445606232 2023-01-23 08:54:28.788658: step: 940/1545, loss: 2.516570568084717 2023-01-23 08:54:29.615931: step: 942/1545, loss: 0.2585635781288147 2023-01-23 08:54:30.488868: step: 944/1545, loss: 0.15396863222122192 2023-01-23 08:54:31.395737: step: 946/1545, loss: 0.18088530004024506 2023-01-23 08:54:32.406389: step: 948/1545, loss: 0.07822807878255844 2023-01-23 08:54:33.282557: step: 950/1545, loss: 0.35604894161224365 2023-01-23 08:54:34.211635: step: 952/1545, loss: 2.8144614696502686 2023-01-23 08:54:35.152070: step: 954/1545, loss: 0.05320236086845398 2023-01-23 08:54:36.055971: step: 956/1545, loss: 0.21634209156036377 2023-01-23 08:54:36.941699: step: 958/1545, loss: 0.22396887838840485 2023-01-23 08:54:37.807599: step: 960/1545, loss: 0.11094971001148224 2023-01-23 08:54:38.691349: step: 962/1545, loss: 0.13462506234645844 2023-01-23 08:54:39.543153: step: 964/1545, loss: 0.5460572838783264 2023-01-23 08:54:40.414495: step: 966/1545, loss: 0.3970370888710022 2023-01-23 08:54:41.288944: step: 968/1545, loss: 0.7071719169616699 2023-01-23 08:54:42.194114: step: 970/1545, loss: 0.9581939578056335 2023-01-23 08:54:43.083636: step: 972/1545, loss: 0.23893755674362183 2023-01-23 08:54:43.910651: step: 974/1545, loss: 2.3288493156433105 2023-01-23 08:54:44.782611: step: 976/1545, loss: 0.27934542298316956 2023-01-23 08:54:45.654863: step: 978/1545, loss: 0.42929962277412415 2023-01-23 08:54:46.560195: step: 980/1545, loss: 0.10308903455734253 2023-01-23 08:54:47.443678: step: 982/1545, loss: 0.3819594979286194 2023-01-23 08:54:48.403460: step: 984/1545, loss: 0.6758444309234619 2023-01-23 08:54:49.360005: step: 986/1545, loss: 0.056272853165864944 2023-01-23 08:54:50.236778: step: 988/1545, loss: 0.3956097960472107 2023-01-23 08:54:51.070073: step: 990/1545, loss: 0.381502628326416 2023-01-23 08:54:51.924393: step: 992/1545, loss: 0.7234383225440979 2023-01-23 08:54:52.741275: step: 994/1545, loss: 0.37628573179244995 2023-01-23 08:54:53.640681: step: 996/1545, loss: 0.26070693135261536 2023-01-23 08:54:54.488861: step: 998/1545, loss: 0.5731749534606934 2023-01-23 08:54:55.374601: step: 1000/1545, loss: 0.09536433964967728 2023-01-23 08:54:56.243368: step: 1002/1545, loss: 0.45315513014793396 2023-01-23 08:54:57.114058: step: 1004/1545, loss: 0.20186525583267212 2023-01-23 08:54:57.981417: step: 1006/1545, loss: 0.5067227482795715 2023-01-23 08:54:58.845022: step: 1008/1545, loss: 0.14070725440979004 2023-01-23 08:54:59.694389: step: 1010/1545, loss: 1.1043405532836914 2023-01-23 08:55:00.564523: step: 1012/1545, loss: 0.5340753793716431 2023-01-23 08:55:01.408612: step: 1014/1545, loss: 0.9201992154121399 2023-01-23 08:55:02.337955: step: 1016/1545, loss: 0.2620474398136139 2023-01-23 08:55:03.178154: step: 1018/1545, loss: 0.3381551206111908 2023-01-23 08:55:04.092668: step: 1020/1545, loss: 0.286687433719635 2023-01-23 08:55:04.976379: step: 1022/1545, loss: 0.07621041685342789 2023-01-23 08:55:05.974401: step: 1024/1545, loss: 0.2183920443058014 2023-01-23 08:55:06.842872: step: 1026/1545, loss: 0.16305527091026306 2023-01-23 08:55:07.748778: step: 1028/1545, loss: 0.11740562319755554 2023-01-23 08:55:08.637305: step: 1030/1545, loss: 0.23754480481147766 2023-01-23 08:55:09.480763: step: 1032/1545, loss: 0.07359511405229568 2023-01-23 08:55:10.366988: step: 1034/1545, loss: 0.24092133343219757 2023-01-23 08:55:11.269184: step: 1036/1545, loss: 0.1878308206796646 2023-01-23 08:55:12.152907: step: 1038/1545, loss: 2.1640846729278564 2023-01-23 08:55:13.054751: step: 1040/1545, loss: 0.3071461617946625 2023-01-23 08:55:13.945239: step: 1042/1545, loss: 0.29157906770706177 2023-01-23 08:55:14.791327: step: 1044/1545, loss: 0.19402460753917694 2023-01-23 08:55:15.687728: step: 1046/1545, loss: 1.0022505521774292 2023-01-23 08:55:16.576854: step: 1048/1545, loss: 0.2996233403682709 2023-01-23 08:55:17.423187: step: 1050/1545, loss: 0.08144727349281311 2023-01-23 08:55:18.295544: step: 1052/1545, loss: 0.09884683787822723 2023-01-23 08:55:19.232286: step: 1054/1545, loss: 0.08221828192472458 2023-01-23 08:55:20.096262: step: 1056/1545, loss: 0.4473716616630554 2023-01-23 08:55:20.980916: step: 1058/1545, loss: 0.21411845088005066 2023-01-23 08:55:21.893022: step: 1060/1545, loss: 0.16903512179851532 2023-01-23 08:55:22.779185: step: 1062/1545, loss: 0.22081813216209412 2023-01-23 08:55:23.651597: step: 1064/1545, loss: 0.0637081041932106 2023-01-23 08:55:24.536752: step: 1066/1545, loss: 0.11767128854990005 2023-01-23 08:55:25.418614: step: 1068/1545, loss: 0.8512082695960999 2023-01-23 08:55:26.274700: step: 1070/1545, loss: 0.23393887281417847 2023-01-23 08:55:27.108206: step: 1072/1545, loss: 0.243085578083992 2023-01-23 08:55:28.003339: step: 1074/1545, loss: 0.21362271904945374 2023-01-23 08:55:28.888126: step: 1076/1545, loss: 0.2983669638633728 2023-01-23 08:55:29.819360: step: 1078/1545, loss: 0.40620413422584534 2023-01-23 08:55:30.711430: step: 1080/1545, loss: 1.0813137292861938 2023-01-23 08:55:31.630508: step: 1082/1545, loss: 0.5596564412117004 2023-01-23 08:55:32.601443: step: 1084/1545, loss: 0.2219012975692749 2023-01-23 08:55:33.499091: step: 1086/1545, loss: 0.6855616569519043 2023-01-23 08:55:34.367703: step: 1088/1545, loss: 0.3376293480396271 2023-01-23 08:55:35.234603: step: 1090/1545, loss: 0.3569219708442688 2023-01-23 08:55:36.098834: step: 1092/1545, loss: 0.1572640985250473 2023-01-23 08:55:36.973133: step: 1094/1545, loss: 0.3660506308078766 2023-01-23 08:55:37.827616: step: 1096/1545, loss: 0.284585565328598 2023-01-23 08:55:38.713759: step: 1098/1545, loss: 0.2640952169895172 2023-01-23 08:55:39.595336: step: 1100/1545, loss: 0.10955388098955154 2023-01-23 08:55:40.508399: step: 1102/1545, loss: 0.12587594985961914 2023-01-23 08:55:41.372567: step: 1104/1545, loss: 0.2687681317329407 2023-01-23 08:55:42.247393: step: 1106/1545, loss: 0.2334587723016739 2023-01-23 08:55:43.131980: step: 1108/1545, loss: 0.07361749559640884 2023-01-23 08:55:43.991403: step: 1110/1545, loss: 0.7600837349891663 2023-01-23 08:55:44.824136: step: 1112/1545, loss: 0.3097490668296814 2023-01-23 08:55:45.661768: step: 1114/1545, loss: 0.2227100431919098 2023-01-23 08:55:46.576733: step: 1116/1545, loss: 0.1507774293422699 2023-01-23 08:55:47.464884: step: 1118/1545, loss: 0.09009647369384766 2023-01-23 08:55:48.382252: step: 1120/1545, loss: 1.9840822219848633 2023-01-23 08:55:49.277643: step: 1122/1545, loss: 0.18754282593727112 2023-01-23 08:55:50.124116: step: 1124/1545, loss: 2.713682174682617 2023-01-23 08:55:50.981652: step: 1126/1545, loss: 0.7988501787185669 2023-01-23 08:55:51.872259: step: 1128/1545, loss: 0.01193973608314991 2023-01-23 08:55:52.714834: step: 1130/1545, loss: 3.0124568939208984 2023-01-23 08:55:53.583817: step: 1132/1545, loss: 0.24942991137504578 2023-01-23 08:55:54.432041: step: 1134/1545, loss: 0.36691591143608093 2023-01-23 08:55:55.323793: step: 1136/1545, loss: 0.07816297560930252 2023-01-23 08:55:56.174703: step: 1138/1545, loss: 0.25557219982147217 2023-01-23 08:55:57.077563: step: 1140/1545, loss: 0.24675379693508148 2023-01-23 08:55:57.977770: step: 1142/1545, loss: 0.29726049304008484 2023-01-23 08:55:58.830653: step: 1144/1545, loss: 0.5218531489372253 2023-01-23 08:55:59.693124: step: 1146/1545, loss: 0.2840462028980255 2023-01-23 08:56:00.594793: step: 1148/1545, loss: 0.09715114533901215 2023-01-23 08:56:01.555223: step: 1150/1545, loss: 0.10818146914243698 2023-01-23 08:56:02.442223: step: 1152/1545, loss: 0.5898352265357971 2023-01-23 08:56:03.283145: step: 1154/1545, loss: 4.879297256469727 2023-01-23 08:56:04.126254: step: 1156/1545, loss: 0.0441315732896328 2023-01-23 08:56:05.082819: step: 1158/1545, loss: 0.23272478580474854 2023-01-23 08:56:05.993564: step: 1160/1545, loss: 0.40315109491348267 2023-01-23 08:56:06.854763: step: 1162/1545, loss: 0.4461365342140198 2023-01-23 08:56:07.744251: step: 1164/1545, loss: 0.24497829377651215 2023-01-23 08:56:08.600750: step: 1166/1545, loss: 0.1829637885093689 2023-01-23 08:56:09.545970: step: 1168/1545, loss: 0.9518768191337585 2023-01-23 08:56:10.420282: step: 1170/1545, loss: 0.08087217807769775 2023-01-23 08:56:11.307246: step: 1172/1545, loss: 0.8868212699890137 2023-01-23 08:56:12.174526: step: 1174/1545, loss: 0.06260967254638672 2023-01-23 08:56:13.033514: step: 1176/1545, loss: 0.6838334202766418 2023-01-23 08:56:13.945435: step: 1178/1545, loss: 2.6138837337493896 2023-01-23 08:56:14.799330: step: 1180/1545, loss: 0.1816074252128601 2023-01-23 08:56:15.709791: step: 1182/1545, loss: 0.16709297895431519 2023-01-23 08:56:16.593713: step: 1184/1545, loss: 0.18759512901306152 2023-01-23 08:56:17.442145: step: 1186/1545, loss: 2.3500888347625732 2023-01-23 08:56:18.332133: step: 1188/1545, loss: 0.4530513286590576 2023-01-23 08:56:19.258860: step: 1190/1545, loss: 0.6516766548156738 2023-01-23 08:56:20.217220: step: 1192/1545, loss: 0.3897666335105896 2023-01-23 08:56:21.127592: step: 1194/1545, loss: 0.1025029644370079 2023-01-23 08:56:21.985170: step: 1196/1545, loss: 0.33328956365585327 2023-01-23 08:56:22.946057: step: 1198/1545, loss: 0.2835051715373993 2023-01-23 08:56:23.816705: step: 1200/1545, loss: 0.18535026907920837 2023-01-23 08:56:24.674891: step: 1202/1545, loss: 0.09853672981262207 2023-01-23 08:56:25.551219: step: 1204/1545, loss: 0.15724964439868927 2023-01-23 08:56:26.418952: step: 1206/1545, loss: 0.11789411306381226 2023-01-23 08:56:27.301464: step: 1208/1545, loss: 0.3944205343723297 2023-01-23 08:56:28.183749: step: 1210/1545, loss: 0.2703903019428253 2023-01-23 08:56:29.041799: step: 1212/1545, loss: 0.08267482370138168 2023-01-23 08:56:29.915782: step: 1214/1545, loss: 0.04202794283628464 2023-01-23 08:56:30.845017: step: 1216/1545, loss: 0.10923971980810165 2023-01-23 08:56:31.695459: step: 1218/1545, loss: 0.38970834016799927 2023-01-23 08:56:32.596811: step: 1220/1545, loss: 0.5514360666275024 2023-01-23 08:56:33.486549: step: 1222/1545, loss: 0.5176461338996887 2023-01-23 08:56:34.456648: step: 1224/1545, loss: 0.3673034906387329 2023-01-23 08:56:35.392914: step: 1226/1545, loss: 0.10734511911869049 2023-01-23 08:56:36.298034: step: 1228/1545, loss: 0.20209954679012299 2023-01-23 08:56:37.176449: step: 1230/1545, loss: 0.4070742130279541 2023-01-23 08:56:38.030646: step: 1232/1545, loss: 0.11918948590755463 2023-01-23 08:56:38.909588: step: 1234/1545, loss: 0.2815551161766052 2023-01-23 08:56:39.777030: step: 1236/1545, loss: 0.20933163166046143 2023-01-23 08:56:40.683786: step: 1238/1545, loss: 0.21590304374694824 2023-01-23 08:56:41.564088: step: 1240/1545, loss: 1.1909332275390625 2023-01-23 08:56:42.481761: step: 1242/1545, loss: 0.4063425660133362 2023-01-23 08:56:43.338180: step: 1244/1545, loss: 0.12349645048379898 2023-01-23 08:56:44.283575: step: 1246/1545, loss: 0.3495135009288788 2023-01-23 08:56:45.167785: step: 1248/1545, loss: 0.2877219319343567 2023-01-23 08:56:46.043594: step: 1250/1545, loss: 0.3776133954524994 2023-01-23 08:56:46.887437: step: 1252/1545, loss: 0.17109733819961548 2023-01-23 08:56:47.776069: step: 1254/1545, loss: 0.34722602367401123 2023-01-23 08:56:48.680788: step: 1256/1545, loss: 0.13870322704315186 2023-01-23 08:56:49.547946: step: 1258/1545, loss: 0.472972571849823 2023-01-23 08:56:50.434497: step: 1260/1545, loss: 0.3813697397708893 2023-01-23 08:56:51.273539: step: 1262/1545, loss: 0.18886816501617432 2023-01-23 08:56:52.105140: step: 1264/1545, loss: 0.32110273838043213 2023-01-23 08:56:52.984708: step: 1266/1545, loss: 0.17045842111110687 2023-01-23 08:56:53.890291: step: 1268/1545, loss: 0.48504742980003357 2023-01-23 08:56:54.784542: step: 1270/1545, loss: 0.20730140805244446 2023-01-23 08:56:55.650933: step: 1272/1545, loss: 6.562617778778076 2023-01-23 08:56:56.536568: step: 1274/1545, loss: 0.3762318789958954 2023-01-23 08:56:57.402247: step: 1276/1545, loss: 0.4946528971195221 2023-01-23 08:56:58.275245: step: 1278/1545, loss: 1.1494327783584595 2023-01-23 08:56:59.179277: step: 1280/1545, loss: 0.2188582867383957 2023-01-23 08:57:00.123632: step: 1282/1545, loss: 0.08344849199056625 2023-01-23 08:57:01.045539: step: 1284/1545, loss: 0.1753528118133545 2023-01-23 08:57:01.934372: step: 1286/1545, loss: 0.1058976799249649 2023-01-23 08:57:02.808584: step: 1288/1545, loss: 0.14248979091644287 2023-01-23 08:57:03.726426: step: 1290/1545, loss: 0.28727826476097107 2023-01-23 08:57:04.629265: step: 1292/1545, loss: 0.4676329493522644 2023-01-23 08:57:05.511045: step: 1294/1545, loss: 0.47708234190940857 2023-01-23 08:57:06.381120: step: 1296/1545, loss: 0.5487504601478577 2023-01-23 08:57:07.247851: step: 1298/1545, loss: 0.26382631063461304 2023-01-23 08:57:08.120691: step: 1300/1545, loss: 0.43596962094306946 2023-01-23 08:57:09.002180: step: 1302/1545, loss: 0.2786056399345398 2023-01-23 08:57:09.879559: step: 1304/1545, loss: 0.8175201416015625 2023-01-23 08:57:10.753209: step: 1306/1545, loss: 0.12531915307044983 2023-01-23 08:57:11.668974: step: 1308/1545, loss: 0.1973882019519806 2023-01-23 08:57:12.510172: step: 1310/1545, loss: 0.8747791647911072 2023-01-23 08:57:13.433894: step: 1312/1545, loss: 0.06009799242019653 2023-01-23 08:57:14.304672: step: 1314/1545, loss: 0.24584843218326569 2023-01-23 08:57:15.140643: step: 1316/1545, loss: 0.08606717735528946 2023-01-23 08:57:16.013576: step: 1318/1545, loss: 0.26520684361457825 2023-01-23 08:57:16.960651: step: 1320/1545, loss: 0.1902732253074646 2023-01-23 08:57:17.805263: step: 1322/1545, loss: 0.17821484804153442 2023-01-23 08:57:18.667010: step: 1324/1545, loss: 0.22017967700958252 2023-01-23 08:57:19.509167: step: 1326/1545, loss: 0.11519358307123184 2023-01-23 08:57:20.377734: step: 1328/1545, loss: 0.47620806097984314 2023-01-23 08:57:21.280187: step: 1330/1545, loss: 0.09556516259908676 2023-01-23 08:57:22.204415: step: 1332/1545, loss: 0.3026179075241089 2023-01-23 08:57:23.110690: step: 1334/1545, loss: 0.12387540191411972 2023-01-23 08:57:24.017436: step: 1336/1545, loss: 0.2394547015428543 2023-01-23 08:57:24.932039: step: 1338/1545, loss: 0.9752334952354431 2023-01-23 08:57:25.815936: step: 1340/1545, loss: 0.2749769389629364 2023-01-23 08:57:26.744330: step: 1342/1545, loss: 0.27166450023651123 2023-01-23 08:57:27.613292: step: 1344/1545, loss: 0.3827020227909088 2023-01-23 08:57:28.512179: step: 1346/1545, loss: 0.2779489755630493 2023-01-23 08:57:29.369958: step: 1348/1545, loss: 0.148095041513443 2023-01-23 08:57:30.215911: step: 1350/1545, loss: 0.1619405448436737 2023-01-23 08:57:31.064620: step: 1352/1545, loss: 0.28846243023872375 2023-01-23 08:57:31.936688: step: 1354/1545, loss: 0.23786696791648865 2023-01-23 08:57:32.955111: step: 1356/1545, loss: 2.4642391204833984 2023-01-23 08:57:33.872317: step: 1358/1545, loss: 0.2366701364517212 2023-01-23 08:57:34.722992: step: 1360/1545, loss: 0.629868745803833 2023-01-23 08:57:35.566396: step: 1362/1545, loss: 0.12949144840240479 2023-01-23 08:57:36.421865: step: 1364/1545, loss: 0.18949155509471893 2023-01-23 08:57:37.294791: step: 1366/1545, loss: 0.29440268874168396 2023-01-23 08:57:38.145284: step: 1368/1545, loss: 0.0630917027592659 2023-01-23 08:57:39.072166: step: 1370/1545, loss: 0.5103744268417358 2023-01-23 08:57:39.963021: step: 1372/1545, loss: 0.18397165834903717 2023-01-23 08:57:40.819558: step: 1374/1545, loss: 0.9274455904960632 2023-01-23 08:57:41.714547: step: 1376/1545, loss: 0.1686970293521881 2023-01-23 08:57:42.600507: step: 1378/1545, loss: 0.11398803442716599 2023-01-23 08:57:43.460981: step: 1380/1545, loss: 0.678417980670929 2023-01-23 08:57:44.370405: step: 1382/1545, loss: 0.1958814412355423 2023-01-23 08:57:45.243967: step: 1384/1545, loss: 0.37499678134918213 2023-01-23 08:57:46.131587: step: 1386/1545, loss: 0.3189307749271393 2023-01-23 08:57:47.108147: step: 1388/1545, loss: 0.06399369239807129 2023-01-23 08:57:47.985037: step: 1390/1545, loss: 0.23094533383846283 2023-01-23 08:57:48.865180: step: 1392/1545, loss: 0.580696165561676 2023-01-23 08:57:49.774338: step: 1394/1545, loss: 0.08589472621679306 2023-01-23 08:57:50.652478: step: 1396/1545, loss: 0.29371076822280884 2023-01-23 08:57:51.556587: step: 1398/1545, loss: 0.2655004560947418 2023-01-23 08:57:52.432842: step: 1400/1545, loss: 0.0955013632774353 2023-01-23 08:57:53.329180: step: 1402/1545, loss: 0.36652442812919617 2023-01-23 08:57:54.232285: step: 1404/1545, loss: 0.3518719971179962 2023-01-23 08:57:55.071681: step: 1406/1545, loss: 0.40800002217292786 2023-01-23 08:57:55.930165: step: 1408/1545, loss: 0.2785654067993164 2023-01-23 08:57:56.777719: step: 1410/1545, loss: 0.6015329360961914 2023-01-23 08:57:57.658996: step: 1412/1545, loss: 1.0913649797439575 2023-01-23 08:57:58.542343: step: 1414/1545, loss: 0.6072200536727905 2023-01-23 08:57:59.413856: step: 1416/1545, loss: 0.13165435194969177 2023-01-23 08:58:00.304910: step: 1418/1545, loss: 0.10983403772115707 2023-01-23 08:58:01.215120: step: 1420/1545, loss: 0.11195584386587143 2023-01-23 08:58:02.154296: step: 1422/1545, loss: 0.13565711677074432 2023-01-23 08:58:03.075567: step: 1424/1545, loss: 0.203398659825325 2023-01-23 08:58:03.954061: step: 1426/1545, loss: 0.18119099736213684 2023-01-23 08:58:04.813406: step: 1428/1545, loss: 0.2045772522687912 2023-01-23 08:58:05.735524: step: 1430/1545, loss: 0.43905431032180786 2023-01-23 08:58:06.639277: step: 1432/1545, loss: 0.6630629301071167 2023-01-23 08:58:07.532198: step: 1434/1545, loss: 0.03029375895857811 2023-01-23 08:58:08.416066: step: 1436/1545, loss: 0.43553444743156433 2023-01-23 08:58:09.284413: step: 1438/1545, loss: 2.9492368698120117 2023-01-23 08:58:10.181953: step: 1440/1545, loss: 0.3607364296913147 2023-01-23 08:58:11.072111: step: 1442/1545, loss: 0.3896859288215637 2023-01-23 08:58:11.930536: step: 1444/1545, loss: 0.2173030972480774 2023-01-23 08:58:12.872364: step: 1446/1545, loss: 0.45692864060401917 2023-01-23 08:58:13.720453: step: 1448/1545, loss: 0.1561679244041443 2023-01-23 08:58:14.584938: step: 1450/1545, loss: 0.22958904504776 2023-01-23 08:58:15.470988: step: 1452/1545, loss: 0.4525075852870941 2023-01-23 08:58:16.338091: step: 1454/1545, loss: 0.09085973352193832 2023-01-23 08:58:17.215014: step: 1456/1545, loss: 0.2754790186882019 2023-01-23 08:58:18.084234: step: 1458/1545, loss: 0.5326736569404602 2023-01-23 08:58:18.980099: step: 1460/1545, loss: 0.29134422540664673 2023-01-23 08:58:19.866438: step: 1462/1545, loss: 0.5681074857711792 2023-01-23 08:58:20.731284: step: 1464/1545, loss: 4.035022258758545 2023-01-23 08:58:21.599378: step: 1466/1545, loss: 0.9275387525558472 2023-01-23 08:58:22.488891: step: 1468/1545, loss: 0.08541927486658096 2023-01-23 08:58:23.334156: step: 1470/1545, loss: 0.07450944185256958 2023-01-23 08:58:24.204105: step: 1472/1545, loss: 0.18936774134635925 2023-01-23 08:58:25.078543: step: 1474/1545, loss: 0.27172398567199707 2023-01-23 08:58:25.943468: step: 1476/1545, loss: 0.4171726107597351 2023-01-23 08:58:26.872681: step: 1478/1545, loss: 0.209006205201149 2023-01-23 08:58:27.734455: step: 1480/1545, loss: 0.728950023651123 2023-01-23 08:58:28.645291: step: 1482/1545, loss: 0.6733201742172241 2023-01-23 08:58:29.495083: step: 1484/1545, loss: 0.07545918226242065 2023-01-23 08:58:30.416559: step: 1486/1545, loss: 0.31292057037353516 2023-01-23 08:58:31.310231: step: 1488/1545, loss: 0.11106933653354645 2023-01-23 08:58:32.192368: step: 1490/1545, loss: 0.41208913922309875 2023-01-23 08:58:33.074416: step: 1492/1545, loss: 0.10761360079050064 2023-01-23 08:58:34.003816: step: 1494/1545, loss: 0.30603641271591187 2023-01-23 08:58:34.884432: step: 1496/1545, loss: 0.1303160935640335 2023-01-23 08:58:35.755644: step: 1498/1545, loss: 0.3719464838504791 2023-01-23 08:58:36.683665: step: 1500/1545, loss: 0.45368361473083496 2023-01-23 08:58:37.531910: step: 1502/1545, loss: 2.7107620239257812 2023-01-23 08:58:38.391228: step: 1504/1545, loss: 0.5068657994270325 2023-01-23 08:58:39.289453: step: 1506/1545, loss: 0.7872833013534546 2023-01-23 08:58:40.147756: step: 1508/1545, loss: 0.45140039920806885 2023-01-23 08:58:41.025013: step: 1510/1545, loss: 3.0907013416290283 2023-01-23 08:58:41.866163: step: 1512/1545, loss: 0.2943306863307953 2023-01-23 08:58:42.792619: step: 1514/1545, loss: 0.18694619834423065 2023-01-23 08:58:43.716879: step: 1516/1545, loss: 0.21137934923171997 2023-01-23 08:58:44.632271: step: 1518/1545, loss: 0.05488034337759018 2023-01-23 08:58:45.562636: step: 1520/1545, loss: 3.6773159503936768 2023-01-23 08:58:46.426203: step: 1522/1545, loss: 0.31143686175346375 2023-01-23 08:58:47.326427: step: 1524/1545, loss: 0.5689182877540588 2023-01-23 08:58:48.224043: step: 1526/1545, loss: 0.17175640165805817 2023-01-23 08:58:49.113377: step: 1528/1545, loss: 0.05980518087744713 2023-01-23 08:58:49.953486: step: 1530/1545, loss: 0.18684172630310059 2023-01-23 08:58:50.843000: step: 1532/1545, loss: 0.2820129990577698 2023-01-23 08:58:51.742484: step: 1534/1545, loss: 0.34178850054740906 2023-01-23 08:58:52.615690: step: 1536/1545, loss: 0.12385091185569763 2023-01-23 08:58:53.455931: step: 1538/1545, loss: 6.840346813201904 2023-01-23 08:58:54.336824: step: 1540/1545, loss: 0.34467849135398865 2023-01-23 08:58:55.196026: step: 1542/1545, loss: 0.19361208379268646 2023-01-23 08:58:56.092658: step: 1544/1545, loss: 0.17486143112182617 2023-01-23 08:58:56.960125: step: 1546/1545, loss: 0.3528921902179718 2023-01-23 08:58:57.830849: step: 1548/1545, loss: 0.32394009828567505 2023-01-23 08:58:58.721185: step: 1550/1545, loss: 0.13970622420310974 2023-01-23 08:58:59.610800: step: 1552/1545, loss: 0.41344141960144043 2023-01-23 08:59:00.530972: step: 1554/1545, loss: 0.9795382618904114 2023-01-23 08:59:01.358574: step: 1556/1545, loss: 0.22918587923049927 2023-01-23 08:59:02.216410: step: 1558/1545, loss: 0.4372389316558838 2023-01-23 08:59:03.121324: step: 1560/1545, loss: 0.0827159732580185 2023-01-23 08:59:04.004296: step: 1562/1545, loss: 0.021094296127557755 2023-01-23 08:59:04.876984: step: 1564/1545, loss: 0.47089579701423645 2023-01-23 08:59:05.769570: step: 1566/1545, loss: 0.20808301866054535 2023-01-23 08:59:06.618514: step: 1568/1545, loss: 0.3706645369529724 2023-01-23 08:59:07.498319: step: 1570/1545, loss: 0.7223496437072754 2023-01-23 08:59:08.399831: step: 1572/1545, loss: 0.29498526453971863 2023-01-23 08:59:09.279153: step: 1574/1545, loss: 0.6004750728607178 2023-01-23 08:59:10.183281: step: 1576/1545, loss: 0.2849287986755371 2023-01-23 08:59:11.071205: step: 1578/1545, loss: 0.101283498108387 2023-01-23 08:59:11.978173: step: 1580/1545, loss: 0.2882613241672516 2023-01-23 08:59:12.839132: step: 1582/1545, loss: 0.3869587779045105 2023-01-23 08:59:13.738420: step: 1584/1545, loss: 0.5650004744529724 2023-01-23 08:59:14.639133: step: 1586/1545, loss: 0.281335711479187 2023-01-23 08:59:15.553092: step: 1588/1545, loss: 0.16036860644817352 2023-01-23 08:59:16.422402: step: 1590/1545, loss: 2.2856194972991943 2023-01-23 08:59:17.305302: step: 1592/1545, loss: 0.08903612196445465 2023-01-23 08:59:18.189827: step: 1594/1545, loss: 0.040903668850660324 2023-01-23 08:59:19.049542: step: 1596/1545, loss: 0.16194573044776917 2023-01-23 08:59:19.930627: step: 1598/1545, loss: 0.24536384642124176 2023-01-23 08:59:20.840599: step: 1600/1545, loss: 0.3451600968837738 2023-01-23 08:59:21.695319: step: 1602/1545, loss: 0.17464539408683777 2023-01-23 08:59:22.585392: step: 1604/1545, loss: 0.3376254439353943 2023-01-23 08:59:23.506065: step: 1606/1545, loss: 0.0842321589589119 2023-01-23 08:59:24.378455: step: 1608/1545, loss: 0.09827974438667297 2023-01-23 08:59:25.206857: step: 1610/1545, loss: 0.09075426310300827 2023-01-23 08:59:26.028628: step: 1612/1545, loss: 0.04622714966535568 2023-01-23 08:59:26.894700: step: 1614/1545, loss: 0.11601636558771133 2023-01-23 08:59:27.824140: step: 1616/1545, loss: 0.3692101538181305 2023-01-23 08:59:28.710221: step: 1618/1545, loss: 0.1933562010526657 2023-01-23 08:59:29.576174: step: 1620/1545, loss: 0.13601359724998474 2023-01-23 08:59:30.440714: step: 1622/1545, loss: 0.1656074970960617 2023-01-23 08:59:31.326926: step: 1624/1545, loss: 1.0875904560089111 2023-01-23 08:59:32.230687: step: 1626/1545, loss: 0.08128786087036133 2023-01-23 08:59:33.099570: step: 1628/1545, loss: 0.4116640090942383 2023-01-23 08:59:33.966988: step: 1630/1545, loss: 0.12236636132001877 2023-01-23 08:59:34.836682: step: 1632/1545, loss: 0.09920679777860641 2023-01-23 08:59:35.725159: step: 1634/1545, loss: 0.2776467204093933 2023-01-23 08:59:36.647542: step: 1636/1545, loss: 0.052907489240169525 2023-01-23 08:59:37.571042: step: 1638/1545, loss: 0.02776382863521576 2023-01-23 08:59:38.411562: step: 1640/1545, loss: 0.08290567994117737 2023-01-23 08:59:39.292392: step: 1642/1545, loss: 0.0637950450181961 2023-01-23 08:59:40.158661: step: 1644/1545, loss: 0.46255820989608765 2023-01-23 08:59:41.038383: step: 1646/1545, loss: 0.10436293482780457 2023-01-23 08:59:41.974976: step: 1648/1545, loss: 0.3367187976837158 2023-01-23 08:59:42.906522: step: 1650/1545, loss: 0.1071736067533493 2023-01-23 08:59:43.836948: step: 1652/1545, loss: 0.20660650730133057 2023-01-23 08:59:44.764166: step: 1654/1545, loss: 0.6788154244422913 2023-01-23 08:59:45.634721: step: 1656/1545, loss: 0.6566699147224426 2023-01-23 08:59:46.582807: step: 1658/1545, loss: 0.2574554681777954 2023-01-23 08:59:47.502247: step: 1660/1545, loss: 0.29981666803359985 2023-01-23 08:59:48.367944: step: 1662/1545, loss: 0.12522296607494354 2023-01-23 08:59:49.264637: step: 1664/1545, loss: 0.44523465633392334 2023-01-23 08:59:50.121443: step: 1666/1545, loss: 0.7788404226303101 2023-01-23 08:59:51.001665: step: 1668/1545, loss: 0.0782768726348877 2023-01-23 08:59:51.897257: step: 1670/1545, loss: 0.17009086906909943 2023-01-23 08:59:52.739051: step: 1672/1545, loss: 0.15956825017929077 2023-01-23 08:59:53.633373: step: 1674/1545, loss: 0.3066919445991516 2023-01-23 08:59:54.508447: step: 1676/1545, loss: 1.406913161277771 2023-01-23 08:59:55.416165: step: 1678/1545, loss: 0.1684807538986206 2023-01-23 08:59:56.286261: step: 1680/1545, loss: 0.15534242987632751 2023-01-23 08:59:57.165053: step: 1682/1545, loss: 0.3046383857727051 2023-01-23 08:59:58.055837: step: 1684/1545, loss: 0.07660331577062607 2023-01-23 08:59:58.956376: step: 1686/1545, loss: 2.2418665885925293 2023-01-23 08:59:59.842785: step: 1688/1545, loss: 0.2775978147983551 2023-01-23 09:00:00.733496: step: 1690/1545, loss: 0.5286983251571655 2023-01-23 09:00:01.639138: step: 1692/1545, loss: 0.1575942039489746 2023-01-23 09:00:02.570283: step: 1694/1545, loss: 0.2028668075799942 2023-01-23 09:00:03.473775: step: 1696/1545, loss: 0.23020349442958832 2023-01-23 09:00:04.384990: step: 1698/1545, loss: 0.18540962040424347 2023-01-23 09:00:05.258866: step: 1700/1545, loss: 0.12480401992797852 2023-01-23 09:00:06.126341: step: 1702/1545, loss: 0.07543863356113434 2023-01-23 09:00:07.068864: step: 1704/1545, loss: 0.5915486812591553 2023-01-23 09:00:07.993044: step: 1706/1545, loss: 0.4259943664073944 2023-01-23 09:00:08.870045: step: 1708/1545, loss: 0.8847298622131348 2023-01-23 09:00:09.715514: step: 1710/1545, loss: 0.5611486434936523 2023-01-23 09:00:10.562207: step: 1712/1545, loss: 0.15927782654762268 2023-01-23 09:00:11.451398: step: 1714/1545, loss: 0.04141367971897125 2023-01-23 09:00:12.316952: step: 1716/1545, loss: 0.3148588538169861 2023-01-23 09:00:13.219309: step: 1718/1545, loss: 0.12946966290473938 2023-01-23 09:00:14.119086: step: 1720/1545, loss: 0.10206527262926102 2023-01-23 09:00:14.998867: step: 1722/1545, loss: 0.12232968211174011 2023-01-23 09:00:15.888223: step: 1724/1545, loss: 0.2721730172634125 2023-01-23 09:00:16.790379: step: 1726/1545, loss: 0.20394086837768555 2023-01-23 09:00:17.633114: step: 1728/1545, loss: 0.09526707231998444 2023-01-23 09:00:18.521726: step: 1730/1545, loss: 0.466913640499115 2023-01-23 09:00:19.450261: step: 1732/1545, loss: 0.0896066427230835 2023-01-23 09:00:20.344362: step: 1734/1545, loss: 0.516869306564331 2023-01-23 09:00:21.203173: step: 1736/1545, loss: 0.2208784520626068 2023-01-23 09:00:22.067737: step: 1738/1545, loss: 1.3343868255615234 2023-01-23 09:00:22.939814: step: 1740/1545, loss: 0.5558851361274719 2023-01-23 09:00:23.814595: step: 1742/1545, loss: 0.22470445930957794 2023-01-23 09:00:24.685820: step: 1744/1545, loss: 0.17932575941085815 2023-01-23 09:00:25.556234: step: 1746/1545, loss: 0.1931845247745514 2023-01-23 09:00:26.425618: step: 1748/1545, loss: 0.5564557313919067 2023-01-23 09:00:27.390055: step: 1750/1545, loss: 0.3714187443256378 2023-01-23 09:00:28.248008: step: 1752/1545, loss: 0.11532696336507797 2023-01-23 09:00:29.116032: step: 1754/1545, loss: 0.5050486326217651 2023-01-23 09:00:30.029330: step: 1756/1545, loss: 0.5912686586380005 2023-01-23 09:00:30.909092: step: 1758/1545, loss: 0.36966678500175476 2023-01-23 09:00:31.761453: step: 1760/1545, loss: 0.1323947161436081 2023-01-23 09:00:32.629406: step: 1762/1545, loss: 0.46763360500335693 2023-01-23 09:00:33.486154: step: 1764/1545, loss: 0.5923994779586792 2023-01-23 09:00:34.362337: step: 1766/1545, loss: 0.3328493535518646 2023-01-23 09:00:35.337725: step: 1768/1545, loss: 0.7264915108680725 2023-01-23 09:00:36.304820: step: 1770/1545, loss: 0.4358140826225281 2023-01-23 09:00:37.201852: step: 1772/1545, loss: 0.27160295844078064 2023-01-23 09:00:38.112942: step: 1774/1545, loss: 0.36519452929496765 2023-01-23 09:00:39.021328: step: 1776/1545, loss: 0.8887308835983276 2023-01-23 09:00:39.887235: step: 1778/1545, loss: 0.2855035066604614 2023-01-23 09:00:40.874978: step: 1780/1545, loss: 0.567388117313385 2023-01-23 09:00:41.768810: step: 1782/1545, loss: 0.32588836550712585 2023-01-23 09:00:42.616297: step: 1784/1545, loss: 0.2555874288082123 2023-01-23 09:00:43.495475: step: 1786/1545, loss: 0.29061996936798096 2023-01-23 09:00:44.443322: step: 1788/1545, loss: 0.270763099193573 2023-01-23 09:00:45.308428: step: 1790/1545, loss: 0.5519542694091797 2023-01-23 09:00:46.213507: step: 1792/1545, loss: 0.5256237983703613 2023-01-23 09:00:47.076520: step: 1794/1545, loss: 0.8233523368835449 2023-01-23 09:00:47.954425: step: 1796/1545, loss: 0.1444837749004364 2023-01-23 09:00:48.873665: step: 1798/1545, loss: 0.2944161295890808 2023-01-23 09:00:49.819942: step: 1800/1545, loss: 0.5243064165115356 2023-01-23 09:00:50.693708: step: 1802/1545, loss: 1.9911434650421143 2023-01-23 09:00:51.597423: step: 1804/1545, loss: 0.3495015799999237 2023-01-23 09:00:52.540497: step: 1806/1545, loss: 0.7388490438461304 2023-01-23 09:00:53.448492: step: 1808/1545, loss: 0.3640514314174652 2023-01-23 09:00:54.351076: step: 1810/1545, loss: 0.32936590909957886 2023-01-23 09:00:55.303809: step: 1812/1545, loss: 0.4765537977218628 2023-01-23 09:00:56.179512: step: 1814/1545, loss: 0.3917340040206909 2023-01-23 09:00:57.051601: step: 1816/1545, loss: 0.24674029648303986 2023-01-23 09:00:57.922089: step: 1818/1545, loss: 0.30130264163017273 2023-01-23 09:00:58.796452: step: 1820/1545, loss: 0.18274618685245514 2023-01-23 09:00:59.740703: step: 1822/1545, loss: 0.34505653381347656 2023-01-23 09:01:00.593690: step: 1824/1545, loss: 0.2328956574201584 2023-01-23 09:01:01.488401: step: 1826/1545, loss: 1.017493486404419 2023-01-23 09:01:02.329018: step: 1828/1545, loss: 0.24533343315124512 2023-01-23 09:01:03.215020: step: 1830/1545, loss: 0.3141672611236572 2023-01-23 09:01:04.084666: step: 1832/1545, loss: 0.13601668179035187 2023-01-23 09:01:04.932210: step: 1834/1545, loss: 0.2811749577522278 2023-01-23 09:01:05.768917: step: 1836/1545, loss: 0.1991429328918457 2023-01-23 09:01:06.695597: step: 1838/1545, loss: 0.27496781945228577 2023-01-23 09:01:07.597221: step: 1840/1545, loss: 0.2119235396385193 2023-01-23 09:01:08.524268: step: 1842/1545, loss: 0.42450806498527527 2023-01-23 09:01:09.392895: step: 1844/1545, loss: 0.45790261030197144 2023-01-23 09:01:10.263941: step: 1846/1545, loss: 0.1486605703830719 2023-01-23 09:01:11.186610: step: 1848/1545, loss: 1.0099700689315796 2023-01-23 09:01:12.118867: step: 1850/1545, loss: 0.212266206741333 2023-01-23 09:01:12.999347: step: 1852/1545, loss: 0.32463282346725464 2023-01-23 09:01:13.896484: step: 1854/1545, loss: 0.23414064943790436 2023-01-23 09:01:14.752463: step: 1856/1545, loss: 0.3527577519416809 2023-01-23 09:01:15.649354: step: 1858/1545, loss: 0.15388253331184387 2023-01-23 09:01:16.549061: step: 1860/1545, loss: 0.3783142566680908 2023-01-23 09:01:17.428624: step: 1862/1545, loss: 0.5424695611000061 2023-01-23 09:01:18.332269: step: 1864/1545, loss: 0.6787643432617188 2023-01-23 09:01:19.274185: step: 1866/1545, loss: 0.08142131567001343 2023-01-23 09:01:20.152394: step: 1868/1545, loss: 0.0649607703089714 2023-01-23 09:01:21.023675: step: 1870/1545, loss: 0.11993945389986038 2023-01-23 09:01:21.868289: step: 1872/1545, loss: 0.0780516043305397 2023-01-23 09:01:22.727271: step: 1874/1545, loss: 0.37582629919052124 2023-01-23 09:01:23.633432: step: 1876/1545, loss: 0.5389973521232605 2023-01-23 09:01:24.519580: step: 1878/1545, loss: 6.35817289352417 2023-01-23 09:01:25.410213: step: 1880/1545, loss: 0.14645157754421234 2023-01-23 09:01:26.299581: step: 1882/1545, loss: 0.4002348482608795 2023-01-23 09:01:27.248197: step: 1884/1545, loss: 0.3414851129055023 2023-01-23 09:01:28.162034: step: 1886/1545, loss: 0.16203846037387848 2023-01-23 09:01:29.032503: step: 1888/1545, loss: 0.07452452927827835 2023-01-23 09:01:29.928804: step: 1890/1545, loss: 0.30310681462287903 2023-01-23 09:01:30.803306: step: 1892/1545, loss: 0.2634528875350952 2023-01-23 09:01:31.696230: step: 1894/1545, loss: 0.6404256224632263 2023-01-23 09:01:32.606201: step: 1896/1545, loss: 0.3326953053474426 2023-01-23 09:01:33.547313: step: 1898/1545, loss: 0.5536810159683228 2023-01-23 09:01:34.449816: step: 1900/1545, loss: 0.6732789278030396 2023-01-23 09:01:35.345513: step: 1902/1545, loss: 0.3995976746082306 2023-01-23 09:01:36.213255: step: 1904/1545, loss: 0.6772052645683289 2023-01-23 09:01:37.119191: step: 1906/1545, loss: 0.1542484015226364 2023-01-23 09:01:38.018858: step: 1908/1545, loss: 0.28043001890182495 2023-01-23 09:01:38.906794: step: 1910/1545, loss: 0.5832952260971069 2023-01-23 09:01:39.778235: step: 1912/1545, loss: 0.7473793625831604 2023-01-23 09:01:40.649134: step: 1914/1545, loss: 0.20072925090789795 2023-01-23 09:01:41.541977: step: 1916/1545, loss: 0.16888433694839478 2023-01-23 09:01:42.428860: step: 1918/1545, loss: 0.24683460593223572 2023-01-23 09:01:43.337214: step: 1920/1545, loss: 0.0836622342467308 2023-01-23 09:01:44.215184: step: 1922/1545, loss: 0.07548367977142334 2023-01-23 09:01:45.090196: step: 1924/1545, loss: 0.46058058738708496 2023-01-23 09:01:45.937997: step: 1926/1545, loss: 0.31883105635643005 2023-01-23 09:01:46.826853: step: 1928/1545, loss: 0.9305574297904968 2023-01-23 09:01:47.698090: step: 1930/1545, loss: 0.21462339162826538 2023-01-23 09:01:48.604335: step: 1932/1545, loss: 0.5957673788070679 2023-01-23 09:01:49.464533: step: 1934/1545, loss: 0.5552412867546082 2023-01-23 09:01:50.348248: step: 1936/1545, loss: 0.8171197772026062 2023-01-23 09:01:51.260749: step: 1938/1545, loss: 0.72760009765625 2023-01-23 09:01:52.198105: step: 1940/1545, loss: 0.262548565864563 2023-01-23 09:01:53.050601: step: 1942/1545, loss: 0.1033421978354454 2023-01-23 09:01:53.987449: step: 1944/1545, loss: 0.4170435667037964 2023-01-23 09:01:54.931306: step: 1946/1545, loss: 0.5082689523696899 2023-01-23 09:01:55.812166: step: 1948/1545, loss: 0.3763576149940491 2023-01-23 09:01:56.790515: step: 1950/1545, loss: 0.1694308966398239 2023-01-23 09:01:57.657976: step: 1952/1545, loss: 0.04898345470428467 2023-01-23 09:01:58.562175: step: 1954/1545, loss: 0.2704649567604065 2023-01-23 09:01:59.516481: step: 1956/1545, loss: 0.023919694125652313 2023-01-23 09:02:00.363145: step: 1958/1545, loss: 0.6528205871582031 2023-01-23 09:02:01.236221: step: 1960/1545, loss: 0.30484580993652344 2023-01-23 09:02:02.138184: step: 1962/1545, loss: 0.238102525472641 2023-01-23 09:02:03.044195: step: 1964/1545, loss: 0.246507465839386 2023-01-23 09:02:03.927287: step: 1966/1545, loss: 2.230196952819824 2023-01-23 09:02:04.828729: step: 1968/1545, loss: 0.23100624978542328 2023-01-23 09:02:05.677670: step: 1970/1545, loss: 0.07027740776538849 2023-01-23 09:02:06.556212: step: 1972/1545, loss: 0.5279038548469543 2023-01-23 09:02:07.447568: step: 1974/1545, loss: 0.1486964076757431 2023-01-23 09:02:08.352446: step: 1976/1545, loss: 0.1511400043964386 2023-01-23 09:02:09.224737: step: 1978/1545, loss: 0.11710445582866669 2023-01-23 09:02:10.087477: step: 1980/1545, loss: 0.26779618859291077 2023-01-23 09:02:10.950104: step: 1982/1545, loss: 0.2017059177160263 2023-01-23 09:02:11.822516: step: 1984/1545, loss: 0.4187805950641632 2023-01-23 09:02:12.753634: step: 1986/1545, loss: 0.22769764065742493 2023-01-23 09:02:13.629171: step: 1988/1545, loss: 0.07655912637710571 2023-01-23 09:02:14.506620: step: 1990/1545, loss: 0.06788978725671768 2023-01-23 09:02:15.415627: step: 1992/1545, loss: 0.07294570654630661 2023-01-23 09:02:16.291537: step: 1994/1545, loss: 0.7420796751976013 2023-01-23 09:02:17.239499: step: 1996/1545, loss: 0.07948604971170425 2023-01-23 09:02:18.077195: step: 1998/1545, loss: 0.22471719980239868 2023-01-23 09:02:18.942094: step: 2000/1545, loss: 0.15203416347503662 2023-01-23 09:02:19.795608: step: 2002/1545, loss: 0.03362646698951721 2023-01-23 09:02:20.668021: step: 2004/1545, loss: 0.6535087823867798 2023-01-23 09:02:21.712799: step: 2006/1545, loss: 3.170653820037842 2023-01-23 09:02:22.615051: step: 2008/1545, loss: 0.055284980684518814 2023-01-23 09:02:23.489528: step: 2010/1545, loss: 1.122514247894287 2023-01-23 09:02:24.371631: step: 2012/1545, loss: 0.12855717539787292 2023-01-23 09:02:25.273259: step: 2014/1545, loss: 0.3384564518928528 2023-01-23 09:02:26.154176: step: 2016/1545, loss: 0.3870719373226166 2023-01-23 09:02:26.988876: step: 2018/1545, loss: 0.5115275979042053 2023-01-23 09:02:27.854666: step: 2020/1545, loss: 0.2176666110754013 2023-01-23 09:02:28.717881: step: 2022/1545, loss: 0.3718230724334717 2023-01-23 09:02:29.625144: step: 2024/1545, loss: 0.18447795510292053 2023-01-23 09:02:30.497471: step: 2026/1545, loss: 0.2134237438440323 2023-01-23 09:02:31.380194: step: 2028/1545, loss: 0.2813681364059448 2023-01-23 09:02:32.245986: step: 2030/1545, loss: 0.7696828842163086 2023-01-23 09:02:33.089640: step: 2032/1545, loss: 0.10889481008052826 2023-01-23 09:02:34.000640: step: 2034/1545, loss: 0.5215455889701843 2023-01-23 09:02:34.904953: step: 2036/1545, loss: 0.3938731849193573 2023-01-23 09:02:35.802344: step: 2038/1545, loss: 0.24488034844398499 2023-01-23 09:02:36.661162: step: 2040/1545, loss: 0.36768004298210144 2023-01-23 09:02:37.576460: step: 2042/1545, loss: 0.6535195112228394 2023-01-23 09:02:38.445978: step: 2044/1545, loss: 0.17555701732635498 2023-01-23 09:02:39.353151: step: 2046/1545, loss: 0.14074768126010895 2023-01-23 09:02:40.246739: step: 2048/1545, loss: 0.31716233491897583 2023-01-23 09:02:41.142997: step: 2050/1545, loss: 0.527344822883606 2023-01-23 09:02:42.057569: step: 2052/1545, loss: 0.2211778163909912 2023-01-23 09:02:42.910659: step: 2054/1545, loss: 0.16073930263519287 2023-01-23 09:02:43.835512: step: 2056/1545, loss: 0.14739815890789032 2023-01-23 09:02:44.737048: step: 2058/1545, loss: 0.5829073190689087 2023-01-23 09:02:45.610292: step: 2060/1545, loss: 0.029798856005072594 2023-01-23 09:02:46.516525: step: 2062/1545, loss: 0.2946540117263794 2023-01-23 09:02:47.440085: step: 2064/1545, loss: 0.7114197015762329 2023-01-23 09:02:48.326737: step: 2066/1545, loss: 0.13144496083259583 2023-01-23 09:02:49.230949: step: 2068/1545, loss: 0.45060038566589355 2023-01-23 09:02:50.115254: step: 2070/1545, loss: 0.34780746698379517 2023-01-23 09:02:50.981703: step: 2072/1545, loss: 0.2259366661310196 2023-01-23 09:02:51.919463: step: 2074/1545, loss: 0.8385545015335083 2023-01-23 09:02:52.788119: step: 2076/1545, loss: 0.13768112659454346 2023-01-23 09:02:53.693685: step: 2078/1545, loss: 0.09305545687675476 2023-01-23 09:02:54.590033: step: 2080/1545, loss: 0.32892969250679016 2023-01-23 09:02:55.484800: step: 2082/1545, loss: 0.15716399252414703 2023-01-23 09:02:56.371529: step: 2084/1545, loss: 0.28403404355049133 2023-01-23 09:02:57.249354: step: 2086/1545, loss: 0.5104863047599792 2023-01-23 09:02:58.165175: step: 2088/1545, loss: 0.10785526037216187 2023-01-23 09:02:59.065162: step: 2090/1545, loss: 0.3233899474143982 2023-01-23 09:02:59.930455: step: 2092/1545, loss: 0.027507523074746132 2023-01-23 09:03:00.858858: step: 2094/1545, loss: 0.14017197489738464 2023-01-23 09:03:01.737478: step: 2096/1545, loss: 0.6385505795478821 2023-01-23 09:03:02.606288: step: 2098/1545, loss: 0.31260451674461365 2023-01-23 09:03:03.495394: step: 2100/1545, loss: 0.1532115638256073 2023-01-23 09:03:04.368524: step: 2102/1545, loss: 0.6048650145530701 2023-01-23 09:03:05.239189: step: 2104/1545, loss: 0.16250869631767273 2023-01-23 09:03:06.150056: step: 2106/1545, loss: 0.3083535134792328 2023-01-23 09:03:07.016606: step: 2108/1545, loss: 0.3170003592967987 2023-01-23 09:03:07.902183: step: 2110/1545, loss: 0.5365141034126282 2023-01-23 09:03:08.768597: step: 2112/1545, loss: 0.11619582027196884 2023-01-23 09:03:09.734824: step: 2114/1545, loss: 0.10224557667970657 2023-01-23 09:03:10.598229: step: 2116/1545, loss: 0.4536534249782562 2023-01-23 09:03:11.505415: step: 2118/1545, loss: 0.4197104573249817 2023-01-23 09:03:12.383584: step: 2120/1545, loss: 0.24915596842765808 2023-01-23 09:03:13.254366: step: 2122/1545, loss: 0.26057615876197815 2023-01-23 09:03:14.144090: step: 2124/1545, loss: 0.6677549481391907 2023-01-23 09:03:15.013614: step: 2126/1545, loss: 0.151658296585083 2023-01-23 09:03:15.860337: step: 2128/1545, loss: 0.25798752903938293 2023-01-23 09:03:16.708740: step: 2130/1545, loss: 0.04390345886349678 2023-01-23 09:03:17.548488: step: 2132/1545, loss: 0.8362454175949097 2023-01-23 09:03:18.429980: step: 2134/1545, loss: 0.07837693393230438 2023-01-23 09:03:19.401665: step: 2136/1545, loss: 0.4433780014514923 2023-01-23 09:03:20.269452: step: 2138/1545, loss: 0.3373364508152008 2023-01-23 09:03:21.146253: step: 2140/1545, loss: 0.14491073787212372 2023-01-23 09:03:22.018999: step: 2142/1545, loss: 0.0959417000412941 2023-01-23 09:03:22.932702: step: 2144/1545, loss: 0.5041589140892029 2023-01-23 09:03:23.824468: step: 2146/1545, loss: 0.0700465515255928 2023-01-23 09:03:24.702897: step: 2148/1545, loss: 0.11085733771324158 2023-01-23 09:03:25.573859: step: 2150/1545, loss: 0.34737488627433777 2023-01-23 09:03:26.531364: step: 2152/1545, loss: 1.9376956224441528 2023-01-23 09:03:27.418349: step: 2154/1545, loss: 3.509957790374756 2023-01-23 09:03:28.340710: step: 2156/1545, loss: 0.39817938208580017 2023-01-23 09:03:29.219951: step: 2158/1545, loss: 0.48857381939888 2023-01-23 09:03:30.103233: step: 2160/1545, loss: 1.2428478002548218 2023-01-23 09:03:31.001320: step: 2162/1545, loss: 0.0633971244096756 2023-01-23 09:03:31.837550: step: 2164/1545, loss: 0.2680327892303467 2023-01-23 09:03:32.714985: step: 2166/1545, loss: 0.07452717423439026 2023-01-23 09:03:33.620677: step: 2168/1545, loss: 0.44767481088638306 2023-01-23 09:03:34.502746: step: 2170/1545, loss: 0.6987946033477783 2023-01-23 09:03:35.425769: step: 2172/1545, loss: 0.5721264481544495 2023-01-23 09:03:36.299428: step: 2174/1545, loss: 0.17582321166992188 2023-01-23 09:03:37.196824: step: 2176/1545, loss: 0.24340954422950745 2023-01-23 09:03:38.036204: step: 2178/1545, loss: 0.2848335802555084 2023-01-23 09:03:38.920104: step: 2180/1545, loss: 0.6546412110328674 2023-01-23 09:03:39.756400: step: 2182/1545, loss: 0.34367337822914124 2023-01-23 09:03:40.636907: step: 2184/1545, loss: 0.09294544160366058 2023-01-23 09:03:41.498886: step: 2186/1545, loss: 0.4001411497592926 2023-01-23 09:03:42.415864: step: 2188/1545, loss: 0.17334477603435516 2023-01-23 09:03:43.333088: step: 2190/1545, loss: 0.8155339956283569 2023-01-23 09:03:44.254366: step: 2192/1545, loss: 0.4223194420337677 2023-01-23 09:03:45.133003: step: 2194/1545, loss: 0.45055094361305237 2023-01-23 09:03:46.013604: step: 2196/1545, loss: 0.13716882467269897 2023-01-23 09:03:46.896805: step: 2198/1545, loss: 0.2860254645347595 2023-01-23 09:03:47.760722: step: 2200/1545, loss: 0.23349422216415405 2023-01-23 09:03:48.614340: step: 2202/1545, loss: 0.13580633699893951 2023-01-23 09:03:49.566813: step: 2204/1545, loss: 0.3260820806026459 2023-01-23 09:03:50.457246: step: 2206/1545, loss: 0.8362269401550293 2023-01-23 09:03:51.378292: step: 2208/1545, loss: 0.24612422287464142 2023-01-23 09:03:52.261468: step: 2210/1545, loss: 0.25992512702941895 2023-01-23 09:03:53.246477: step: 2212/1545, loss: 0.4371446967124939 2023-01-23 09:03:54.139239: step: 2214/1545, loss: 0.24526192247867584 2023-01-23 09:03:55.047162: step: 2216/1545, loss: 0.03592981398105621 2023-01-23 09:03:55.992841: step: 2218/1545, loss: 0.4600570797920227 2023-01-23 09:03:56.862947: step: 2220/1545, loss: 0.16546432673931122 2023-01-23 09:03:57.755757: step: 2222/1545, loss: 0.24753326177597046 2023-01-23 09:03:58.697084: step: 2224/1545, loss: 0.3336641788482666 2023-01-23 09:03:59.543288: step: 2226/1545, loss: 0.5096156001091003 2023-01-23 09:04:00.412683: step: 2228/1545, loss: 0.25308316946029663 2023-01-23 09:04:01.336906: step: 2230/1545, loss: 1.8917442560195923 2023-01-23 09:04:02.179872: step: 2232/1545, loss: 0.13693474233150482 2023-01-23 09:04:03.084187: step: 2234/1545, loss: 0.23434101045131683 2023-01-23 09:04:04.031457: step: 2236/1545, loss: 0.6238957047462463 2023-01-23 09:04:04.888756: step: 2238/1545, loss: 0.5756121277809143 2023-01-23 09:04:05.807088: step: 2240/1545, loss: 0.5333827137947083 2023-01-23 09:04:06.664819: step: 2242/1545, loss: 0.24925054609775543 2023-01-23 09:04:07.626542: step: 2244/1545, loss: 0.16862265765666962 2023-01-23 09:04:08.532033: step: 2246/1545, loss: 0.4244217872619629 2023-01-23 09:04:09.411046: step: 2248/1545, loss: 0.25717854499816895 2023-01-23 09:04:10.280074: step: 2250/1545, loss: 0.1900501400232315 2023-01-23 09:04:11.184067: step: 2252/1545, loss: 0.19323299825191498 2023-01-23 09:04:12.052361: step: 2254/1545, loss: 0.33306607604026794 2023-01-23 09:04:12.929844: step: 2256/1545, loss: 1.1679396629333496 2023-01-23 09:04:13.819152: step: 2258/1545, loss: 0.4387299418449402 2023-01-23 09:04:14.708558: step: 2260/1545, loss: 0.20498037338256836 2023-01-23 09:04:15.674512: step: 2262/1545, loss: 0.2951584756374359 2023-01-23 09:04:16.612463: step: 2264/1545, loss: 0.4608154594898224 2023-01-23 09:04:17.529945: step: 2266/1545, loss: 0.5234968066215515 2023-01-23 09:04:18.394814: step: 2268/1545, loss: 0.18762488663196564 2023-01-23 09:04:19.336547: step: 2270/1545, loss: 0.13360445201396942 2023-01-23 09:04:20.200214: step: 2272/1545, loss: 0.86257404088974 2023-01-23 09:04:21.084424: step: 2274/1545, loss: 0.16133205592632294 2023-01-23 09:04:21.988604: step: 2276/1545, loss: 0.24023586511611938 2023-01-23 09:04:22.886890: step: 2278/1545, loss: 0.2556407153606415 2023-01-23 09:04:23.791474: step: 2280/1545, loss: 0.08146043121814728 2023-01-23 09:04:24.661222: step: 2282/1545, loss: 0.22824880480766296 2023-01-23 09:04:25.502677: step: 2284/1545, loss: 0.26498955488204956 2023-01-23 09:04:26.391084: step: 2286/1545, loss: 0.20487117767333984 2023-01-23 09:04:27.226513: step: 2288/1545, loss: 0.1174672544002533 2023-01-23 09:04:28.088598: step: 2290/1545, loss: 0.20577959716320038 2023-01-23 09:04:29.008054: step: 2292/1545, loss: 0.17507699131965637 2023-01-23 09:04:29.850047: step: 2294/1545, loss: 0.3563384413719177 2023-01-23 09:04:30.706520: step: 2296/1545, loss: 1.0529699325561523 2023-01-23 09:04:31.667528: step: 2298/1545, loss: 0.3914697766304016 2023-01-23 09:04:32.576093: step: 2300/1545, loss: 0.3833116590976715 2023-01-23 09:04:33.450589: step: 2302/1545, loss: 0.233865424990654 2023-01-23 09:04:34.389337: step: 2304/1545, loss: 0.49492347240448 2023-01-23 09:04:35.243722: step: 2306/1545, loss: 0.41460439562797546 2023-01-23 09:04:36.153402: step: 2308/1545, loss: 0.2726374864578247 2023-01-23 09:04:37.015417: step: 2310/1545, loss: 0.08469873666763306 2023-01-23 09:04:37.885242: step: 2312/1545, loss: 0.874904990196228 2023-01-23 09:04:38.774973: step: 2314/1545, loss: 0.05140285938978195 2023-01-23 09:04:39.629885: step: 2316/1545, loss: 2.6916494369506836 2023-01-23 09:04:40.474000: step: 2318/1545, loss: 0.12804289162158966 2023-01-23 09:04:41.336348: step: 2320/1545, loss: 0.17136390507221222 2023-01-23 09:04:42.267869: step: 2322/1545, loss: 0.01646510325372219 2023-01-23 09:04:43.171839: step: 2324/1545, loss: 0.33286774158477783 2023-01-23 09:04:44.065504: step: 2326/1545, loss: 0.4751622974872589 2023-01-23 09:04:44.953885: step: 2328/1545, loss: 0.2291475385427475 2023-01-23 09:04:45.827634: step: 2330/1545, loss: 0.21360233426094055 2023-01-23 09:04:46.699928: step: 2332/1545, loss: 0.237545907497406 2023-01-23 09:04:47.637615: step: 2334/1545, loss: 0.13823482394218445 2023-01-23 09:04:48.528095: step: 2336/1545, loss: 0.4470503330230713 2023-01-23 09:04:49.426258: step: 2338/1545, loss: 0.2905338406562805 2023-01-23 09:04:50.322988: step: 2340/1545, loss: 0.2661225497722626 2023-01-23 09:04:51.220296: step: 2342/1545, loss: 0.22174020111560822 2023-01-23 09:04:52.059455: step: 2344/1545, loss: 0.3242529630661011 2023-01-23 09:04:52.925535: step: 2346/1545, loss: 0.20740669965744019 2023-01-23 09:04:53.852061: step: 2348/1545, loss: 1.4114189147949219 2023-01-23 09:04:54.727485: step: 2350/1545, loss: 0.4032846987247467 2023-01-23 09:04:55.597957: step: 2352/1545, loss: 0.5626896023750305 2023-01-23 09:04:56.523780: step: 2354/1545, loss: 0.2537306249141693 2023-01-23 09:04:57.425822: step: 2356/1545, loss: 1.891879916191101 2023-01-23 09:04:58.304567: step: 2358/1545, loss: 0.30221909284591675 2023-01-23 09:04:59.173175: step: 2360/1545, loss: 0.6616085171699524 2023-01-23 09:05:00.112701: step: 2362/1545, loss: 1.595580816268921 2023-01-23 09:05:00.995421: step: 2364/1545, loss: 0.26630154252052307 2023-01-23 09:05:01.870676: step: 2366/1545, loss: 0.18203146755695343 2023-01-23 09:05:02.823855: step: 2368/1545, loss: 0.2737891674041748 2023-01-23 09:05:03.696125: step: 2370/1545, loss: 0.21540772914886475 2023-01-23 09:05:04.673386: step: 2372/1545, loss: 0.45452338457107544 2023-01-23 09:05:05.536680: step: 2374/1545, loss: 0.2582295536994934 2023-01-23 09:05:06.437562: step: 2376/1545, loss: 1.5475618839263916 2023-01-23 09:05:07.382971: step: 2378/1545, loss: 0.5372886657714844 2023-01-23 09:05:08.293022: step: 2380/1545, loss: 0.6369513869285583 2023-01-23 09:05:09.263351: step: 2382/1545, loss: 0.7064332962036133 2023-01-23 09:05:10.158548: step: 2384/1545, loss: 0.2300502061843872 2023-01-23 09:05:11.016610: step: 2386/1545, loss: 0.41750991344451904 2023-01-23 09:05:11.886040: step: 2388/1545, loss: 0.14044147729873657 2023-01-23 09:05:12.765387: step: 2390/1545, loss: 0.1732192039489746 2023-01-23 09:05:13.640746: step: 2392/1545, loss: 0.3037037253379822 2023-01-23 09:05:14.520748: step: 2394/1545, loss: 0.20321038365364075 2023-01-23 09:05:15.406373: step: 2396/1545, loss: 0.8737007975578308 2023-01-23 09:05:16.282705: step: 2398/1545, loss: 0.33643755316734314 2023-01-23 09:05:17.123141: step: 2400/1545, loss: 0.22028093039989471 2023-01-23 09:05:18.023891: step: 2402/1545, loss: 0.1891990751028061 2023-01-23 09:05:18.912761: step: 2404/1545, loss: 0.690614640712738 2023-01-23 09:05:19.830333: step: 2406/1545, loss: 0.4902906119823456 2023-01-23 09:05:20.745976: step: 2408/1545, loss: 0.25831329822540283 2023-01-23 09:05:21.657387: step: 2410/1545, loss: 0.33256351947784424 2023-01-23 09:05:22.538354: step: 2412/1545, loss: 0.4732978343963623 2023-01-23 09:05:23.449524: step: 2414/1545, loss: 0.9668818712234497 2023-01-23 09:05:24.391314: step: 2416/1545, loss: 0.21681495010852814 2023-01-23 09:05:25.286314: step: 2418/1545, loss: 0.1574009507894516 2023-01-23 09:05:26.172369: step: 2420/1545, loss: 0.6563541293144226 2023-01-23 09:05:27.040520: step: 2422/1545, loss: 0.4335458278656006 2023-01-23 09:05:27.924178: step: 2424/1545, loss: 0.18701262772083282 2023-01-23 09:05:28.794854: step: 2426/1545, loss: 0.18815383315086365 2023-01-23 09:05:29.742343: step: 2428/1545, loss: 1.6396520137786865 2023-01-23 09:05:30.594404: step: 2430/1545, loss: 0.03028237819671631 2023-01-23 09:05:31.453852: step: 2432/1545, loss: 0.5972143411636353 2023-01-23 09:05:32.343601: step: 2434/1545, loss: 0.7799199223518372 2023-01-23 09:05:33.253772: step: 2436/1545, loss: 0.7847913503646851 2023-01-23 09:05:34.124923: step: 2438/1545, loss: 0.2954867482185364 2023-01-23 09:05:35.050242: step: 2440/1545, loss: 0.25704213976860046 2023-01-23 09:05:35.923961: step: 2442/1545, loss: 0.2200101613998413 2023-01-23 09:05:36.813250: step: 2444/1545, loss: 0.21875673532485962 2023-01-23 09:05:37.748497: step: 2446/1545, loss: 1.0871630907058716 2023-01-23 09:05:38.601868: step: 2448/1545, loss: 0.12330228835344315 2023-01-23 09:05:39.537414: step: 2450/1545, loss: 0.24786745011806488 2023-01-23 09:05:40.402123: step: 2452/1545, loss: 0.08866502344608307 2023-01-23 09:05:41.263789: step: 2454/1545, loss: 0.6066341400146484 2023-01-23 09:05:42.143837: step: 2456/1545, loss: 0.591704785823822 2023-01-23 09:05:42.990440: step: 2458/1545, loss: 0.36552944779396057 2023-01-23 09:05:44.003966: step: 2460/1545, loss: 0.5135773420333862 2023-01-23 09:05:44.897622: step: 2462/1545, loss: 0.2537902891635895 2023-01-23 09:05:45.773806: step: 2464/1545, loss: 0.5706337690353394 2023-01-23 09:05:46.645553: step: 2466/1545, loss: 0.18971611559391022 2023-01-23 09:05:47.558723: step: 2468/1545, loss: 0.15013307332992554 2023-01-23 09:05:48.440583: step: 2470/1545, loss: 0.1263432651758194 2023-01-23 09:05:49.329627: step: 2472/1545, loss: 0.29311448335647583 2023-01-23 09:05:50.214955: step: 2474/1545, loss: 0.319047749042511 2023-01-23 09:05:51.084594: step: 2476/1545, loss: 0.15870891511440277 2023-01-23 09:05:51.944082: step: 2478/1545, loss: 0.3263445198535919 2023-01-23 09:05:52.802048: step: 2480/1545, loss: 0.3055492043495178 2023-01-23 09:05:53.700554: step: 2482/1545, loss: 0.08804921060800552 2023-01-23 09:05:54.558771: step: 2484/1545, loss: 0.3995138108730316 2023-01-23 09:05:55.418948: step: 2486/1545, loss: 0.4857023060321808 2023-01-23 09:05:56.325344: step: 2488/1545, loss: 0.4821222126483917 2023-01-23 09:05:57.240789: step: 2490/1545, loss: 0.18457800149917603 2023-01-23 09:05:58.114141: step: 2492/1545, loss: 0.22223173081874847 2023-01-23 09:05:59.035786: step: 2494/1545, loss: 0.40164074301719666 2023-01-23 09:05:59.901614: step: 2496/1545, loss: 0.572391927242279 2023-01-23 09:06:00.782326: step: 2498/1545, loss: 0.27909520268440247 2023-01-23 09:06:01.670201: step: 2500/1545, loss: 1.0468579530715942 2023-01-23 09:06:02.494658: step: 2502/1545, loss: 0.2734859883785248 2023-01-23 09:06:03.421355: step: 2504/1545, loss: 0.13946543633937836 2023-01-23 09:06:04.328249: step: 2506/1545, loss: 0.0711037740111351 2023-01-23 09:06:05.169935: step: 2508/1545, loss: 2.9204487800598145 2023-01-23 09:06:06.116304: step: 2510/1545, loss: 0.059696659445762634 2023-01-23 09:06:06.987424: step: 2512/1545, loss: 0.10369150340557098 2023-01-23 09:06:07.879820: step: 2514/1545, loss: 0.8708714842796326 2023-01-23 09:06:08.770366: step: 2516/1545, loss: 0.3055100739002228 2023-01-23 09:06:09.642732: step: 2518/1545, loss: 0.26735037565231323 2023-01-23 09:06:10.528137: step: 2520/1545, loss: 0.1877836436033249 2023-01-23 09:06:11.507983: step: 2522/1545, loss: 0.22110077738761902 2023-01-23 09:06:12.398052: step: 2524/1545, loss: 0.37632834911346436 2023-01-23 09:06:13.239572: step: 2526/1545, loss: 0.2393750250339508 2023-01-23 09:06:14.153046: step: 2528/1545, loss: 0.6321592926979065 2023-01-23 09:06:15.014554: step: 2530/1545, loss: 0.25629714131355286 2023-01-23 09:06:15.881823: step: 2532/1545, loss: 0.0701720118522644 2023-01-23 09:06:16.743879: step: 2534/1545, loss: 0.21084730327129364 2023-01-23 09:06:17.624253: step: 2536/1545, loss: 0.33554568886756897 2023-01-23 09:06:18.465637: step: 2538/1545, loss: 0.198194682598114 2023-01-23 09:06:19.365745: step: 2540/1545, loss: 0.3793100118637085 2023-01-23 09:06:20.243039: step: 2542/1545, loss: 0.16399192810058594 2023-01-23 09:06:21.111564: step: 2544/1545, loss: 0.1465441882610321 2023-01-23 09:06:21.969396: step: 2546/1545, loss: 0.44003790616989136 2023-01-23 09:06:22.874233: step: 2548/1545, loss: 0.5565683245658875 2023-01-23 09:06:23.717248: step: 2550/1545, loss: 0.17233897745609283 2023-01-23 09:06:24.587000: step: 2552/1545, loss: 0.6059810519218445 2023-01-23 09:06:25.458868: step: 2554/1545, loss: 0.12600229680538177 2023-01-23 09:06:26.353442: step: 2556/1545, loss: 1.289865493774414 2023-01-23 09:06:27.229571: step: 2558/1545, loss: 0.6130979061126709 2023-01-23 09:06:28.217236: step: 2560/1545, loss: 0.27813807129859924 2023-01-23 09:06:29.075951: step: 2562/1545, loss: 0.4498378038406372 2023-01-23 09:06:29.966728: step: 2564/1545, loss: 0.21020855009555817 2023-01-23 09:06:30.900986: step: 2566/1545, loss: 0.6347945928573608 2023-01-23 09:06:31.808793: step: 2568/1545, loss: 0.5261128544807434 2023-01-23 09:06:32.676258: step: 2570/1545, loss: 0.28057733178138733 2023-01-23 09:06:33.538989: step: 2572/1545, loss: 1.1947622299194336 2023-01-23 09:06:34.418402: step: 2574/1545, loss: 0.4577893912792206 2023-01-23 09:06:35.323376: step: 2576/1545, loss: 0.16706115007400513 2023-01-23 09:06:36.205161: step: 2578/1545, loss: 0.24409475922584534 2023-01-23 09:06:37.102102: step: 2580/1545, loss: 0.2892731726169586 2023-01-23 09:06:38.016217: step: 2582/1545, loss: 0.5573827624320984 2023-01-23 09:06:38.918008: step: 2584/1545, loss: 0.19468125700950623 2023-01-23 09:06:39.819219: step: 2586/1545, loss: 0.36818239092826843 2023-01-23 09:06:40.707335: step: 2588/1545, loss: 0.5598602890968323 2023-01-23 09:06:41.608124: step: 2590/1545, loss: 0.3203437626361847 2023-01-23 09:06:42.491952: step: 2592/1545, loss: 0.37553757429122925 2023-01-23 09:06:43.377080: step: 2594/1545, loss: 0.315813809633255 2023-01-23 09:06:44.281449: step: 2596/1545, loss: 0.25044727325439453 2023-01-23 09:06:45.145183: step: 2598/1545, loss: 0.16554923355579376 2023-01-23 09:06:46.035117: step: 2600/1545, loss: 0.1074271947145462 2023-01-23 09:06:46.913998: step: 2602/1545, loss: 0.17562875151634216 2023-01-23 09:06:47.844394: step: 2604/1545, loss: 0.28497186303138733 2023-01-23 09:06:48.736606: step: 2606/1545, loss: 0.4090667963027954 2023-01-23 09:06:49.714390: step: 2608/1545, loss: 0.21255578100681305 2023-01-23 09:06:50.661026: step: 2610/1545, loss: 1.0264630317687988 2023-01-23 09:06:51.600379: step: 2612/1545, loss: 0.17291858792304993 2023-01-23 09:06:52.490071: step: 2614/1545, loss: 0.4787440896034241 2023-01-23 09:06:53.463258: step: 2616/1545, loss: 0.1155119240283966 2023-01-23 09:06:54.330300: step: 2618/1545, loss: 0.12340657413005829 2023-01-23 09:06:55.296358: step: 2620/1545, loss: 0.4209531247615814 2023-01-23 09:06:56.276209: step: 2622/1545, loss: 0.21335411071777344 2023-01-23 09:06:57.162113: step: 2624/1545, loss: 0.2616844177246094 2023-01-23 09:06:58.046865: step: 2626/1545, loss: 0.07464933395385742 2023-01-23 09:06:58.898704: step: 2628/1545, loss: 0.3443094789981842 2023-01-23 09:06:59.786582: step: 2630/1545, loss: 0.4956565201282501 2023-01-23 09:07:00.678409: step: 2632/1545, loss: 0.4291119873523712 2023-01-23 09:07:01.544214: step: 2634/1545, loss: 0.15433940291404724 2023-01-23 09:07:02.418597: step: 2636/1545, loss: 0.2416343092918396 2023-01-23 09:07:03.259205: step: 2638/1545, loss: 0.09557095915079117 2023-01-23 09:07:04.156685: step: 2640/1545, loss: 0.043074388056993484 2023-01-23 09:07:05.071164: step: 2642/1545, loss: 1.9948822259902954 2023-01-23 09:07:06.049829: step: 2644/1545, loss: 0.32739076018333435 2023-01-23 09:07:06.945344: step: 2646/1545, loss: 0.17447929084300995 2023-01-23 09:07:07.836305: step: 2648/1545, loss: 0.014055445790290833 2023-01-23 09:07:08.817601: step: 2650/1545, loss: 0.38120079040527344 2023-01-23 09:07:09.862687: step: 2652/1545, loss: 0.33362919092178345 2023-01-23 09:07:10.725465: step: 2654/1545, loss: 0.14872685074806213 2023-01-23 09:07:11.637349: step: 2656/1545, loss: 0.5520341396331787 2023-01-23 09:07:12.537247: step: 2658/1545, loss: 0.3654029071331024 2023-01-23 09:07:13.436048: step: 2660/1545, loss: 0.986118495464325 2023-01-23 09:07:14.341572: step: 2662/1545, loss: 0.2819024622440338 2023-01-23 09:07:15.242059: step: 2664/1545, loss: 0.269903302192688 2023-01-23 09:07:16.158179: step: 2666/1545, loss: 0.24967347085475922 2023-01-23 09:07:17.026156: step: 2668/1545, loss: 0.18273621797561646 2023-01-23 09:07:17.894394: step: 2670/1545, loss: 0.2745531499385834 2023-01-23 09:07:18.785273: step: 2672/1545, loss: 0.22059819102287292 2023-01-23 09:07:19.733863: step: 2674/1545, loss: 0.4661960005760193 2023-01-23 09:07:20.589245: step: 2676/1545, loss: 0.5892472863197327 2023-01-23 09:07:21.427644: step: 2678/1545, loss: 0.4863867163658142 2023-01-23 09:07:22.293341: step: 2680/1545, loss: 0.42690515518188477 2023-01-23 09:07:23.271078: step: 2682/1545, loss: 0.615317702293396 2023-01-23 09:07:24.154067: step: 2684/1545, loss: 0.3778002858161926 2023-01-23 09:07:25.047834: step: 2686/1545, loss: 0.15704631805419922 2023-01-23 09:07:25.897459: step: 2688/1545, loss: 0.2146253138780594 2023-01-23 09:07:26.772033: step: 2690/1545, loss: 0.15519772469997406 2023-01-23 09:07:27.669888: step: 2692/1545, loss: 0.2798343002796173 2023-01-23 09:07:28.540783: step: 2694/1545, loss: 1.5664918422698975 2023-01-23 09:07:29.404773: step: 2696/1545, loss: 0.48558735847473145 2023-01-23 09:07:30.296396: step: 2698/1545, loss: 0.11731070280075073 2023-01-23 09:07:31.168516: step: 2700/1545, loss: 0.3983696699142456 2023-01-23 09:07:32.075997: step: 2702/1545, loss: 0.09989159554243088 2023-01-23 09:07:32.942096: step: 2704/1545, loss: 0.16084396839141846 2023-01-23 09:07:33.897152: step: 2706/1545, loss: 0.3612079918384552 2023-01-23 09:07:34.765733: step: 2708/1545, loss: 0.2126610279083252 2023-01-23 09:07:35.625150: step: 2710/1545, loss: 0.463870644569397 2023-01-23 09:07:36.471111: step: 2712/1545, loss: 0.2833934724330902 2023-01-23 09:07:37.326376: step: 2714/1545, loss: 0.26535266637802124 2023-01-23 09:07:38.179015: step: 2716/1545, loss: 0.2137427181005478 2023-01-23 09:07:39.069311: step: 2718/1545, loss: 0.40376219153404236 2023-01-23 09:07:39.945080: step: 2720/1545, loss: 0.5243787169456482 2023-01-23 09:07:40.798846: step: 2722/1545, loss: 0.37876731157302856 2023-01-23 09:07:41.666129: step: 2724/1545, loss: 0.21053153276443481 2023-01-23 09:07:42.535298: step: 2726/1545, loss: 0.18295708298683167 2023-01-23 09:07:43.406498: step: 2728/1545, loss: 0.13437491655349731 2023-01-23 09:07:44.263059: step: 2730/1545, loss: 0.2661322057247162 2023-01-23 09:07:45.128996: step: 2732/1545, loss: 0.20333002507686615 2023-01-23 09:07:46.005265: step: 2734/1545, loss: 0.3572978675365448 2023-01-23 09:07:46.882706: step: 2736/1545, loss: 0.2020401507616043 2023-01-23 09:07:47.783458: step: 2738/1545, loss: 0.4270890951156616 2023-01-23 09:07:48.695165: step: 2740/1545, loss: 0.09739044308662415 2023-01-23 09:07:49.637148: step: 2742/1545, loss: 0.4432922899723053 2023-01-23 09:07:50.569595: step: 2744/1545, loss: 0.30310362577438354 2023-01-23 09:07:51.456118: step: 2746/1545, loss: 0.033016979694366455 2023-01-23 09:07:52.333214: step: 2748/1545, loss: 0.31391292810440063 2023-01-23 09:07:53.189385: step: 2750/1545, loss: 0.19166502356529236 2023-01-23 09:07:54.082997: step: 2752/1545, loss: 0.23682855069637299 2023-01-23 09:07:55.008152: step: 2754/1545, loss: 0.1961880773305893 2023-01-23 09:07:55.926109: step: 2756/1545, loss: 0.3462640345096588 2023-01-23 09:07:56.846307: step: 2758/1545, loss: 0.47817686200141907 2023-01-23 09:07:57.752932: step: 2760/1545, loss: 0.413373738527298 2023-01-23 09:07:58.644916: step: 2762/1545, loss: 0.3697853684425354 2023-01-23 09:07:59.610788: step: 2764/1545, loss: 5.446779727935791 2023-01-23 09:08:00.475098: step: 2766/1545, loss: 0.07342781871557236 2023-01-23 09:08:01.339811: step: 2768/1545, loss: 0.40789899230003357 2023-01-23 09:08:02.223550: step: 2770/1545, loss: 0.7171815633773804 2023-01-23 09:08:03.167958: step: 2772/1545, loss: 0.4208141565322876 2023-01-23 09:08:04.072458: step: 2774/1545, loss: 0.2082262933254242 2023-01-23 09:08:04.961924: step: 2776/1545, loss: 0.3034626543521881 2023-01-23 09:08:05.848113: step: 2778/1545, loss: 0.3248635530471802 2023-01-23 09:08:06.784177: step: 2780/1545, loss: 0.2928670346736908 2023-01-23 09:08:07.766911: step: 2782/1545, loss: 0.18089984357357025 2023-01-23 09:08:08.666477: step: 2784/1545, loss: 0.14934900403022766 2023-01-23 09:08:09.581869: step: 2786/1545, loss: 0.4942561388015747 2023-01-23 09:08:10.489963: step: 2788/1545, loss: 0.5019599199295044 2023-01-23 09:08:11.366103: step: 2790/1545, loss: 0.2994033098220825 2023-01-23 09:08:12.222721: step: 2792/1545, loss: 0.3467260003089905 2023-01-23 09:08:13.111259: step: 2794/1545, loss: 0.14829924702644348 2023-01-23 09:08:14.063960: step: 2796/1545, loss: 0.116130530834198 2023-01-23 09:08:14.951272: step: 2798/1545, loss: 0.06205311417579651 2023-01-23 09:08:15.796058: step: 2800/1545, loss: 0.11774852871894836 2023-01-23 09:08:16.676467: step: 2802/1545, loss: 0.5319661498069763 2023-01-23 09:08:17.584263: step: 2804/1545, loss: 0.07517092674970627 2023-01-23 09:08:18.495709: step: 2806/1545, loss: 0.26981988549232483 2023-01-23 09:08:19.415963: step: 2808/1545, loss: 0.5226172804832458 2023-01-23 09:08:20.322143: step: 2810/1545, loss: 0.5051575899124146 2023-01-23 09:08:21.186691: step: 2812/1545, loss: 0.38824522495269775 2023-01-23 09:08:22.059894: step: 2814/1545, loss: 0.31361207365989685 2023-01-23 09:08:22.921130: step: 2816/1545, loss: 0.15694734454154968 2023-01-23 09:08:23.828388: step: 2818/1545, loss: 0.18699929118156433 2023-01-23 09:08:24.745155: step: 2820/1545, loss: 0.11666211485862732 2023-01-23 09:08:25.648371: step: 2822/1545, loss: 0.8735978603363037 2023-01-23 09:08:26.517094: step: 2824/1545, loss: 0.3877529501914978 2023-01-23 09:08:27.399918: step: 2826/1545, loss: 0.31765925884246826 2023-01-23 09:08:28.340141: step: 2828/1545, loss: 0.42359259724617004 2023-01-23 09:08:29.199557: step: 2830/1545, loss: 0.13083282113075256 2023-01-23 09:08:30.108682: step: 2832/1545, loss: 0.22889916598796844 2023-01-23 09:08:31.018953: step: 2834/1545, loss: 0.14314518868923187 2023-01-23 09:08:31.842874: step: 2836/1545, loss: 0.040382739156484604 2023-01-23 09:08:32.750932: step: 2838/1545, loss: 0.9174996018409729 2023-01-23 09:08:33.672920: step: 2840/1545, loss: 0.16034285724163055 2023-01-23 09:08:34.561488: step: 2842/1545, loss: 0.9185309410095215 2023-01-23 09:08:35.433386: step: 2844/1545, loss: 0.03848511353135109 2023-01-23 09:08:36.315893: step: 2846/1545, loss: 0.13421814143657684 2023-01-23 09:08:37.247545: step: 2848/1545, loss: 0.48578065633773804 2023-01-23 09:08:38.115612: step: 2850/1545, loss: 0.08287527412176132 2023-01-23 09:08:38.962721: step: 2852/1545, loss: 0.10651175677776337 2023-01-23 09:08:39.889114: step: 2854/1545, loss: 0.17215994000434875 2023-01-23 09:08:40.763520: step: 2856/1545, loss: 0.21938590705394745 2023-01-23 09:08:41.661114: step: 2858/1545, loss: 0.13855494558811188 2023-01-23 09:08:42.598926: step: 2860/1545, loss: 0.36065301299095154 2023-01-23 09:08:43.456922: step: 2862/1545, loss: 0.22978909313678741 2023-01-23 09:08:44.389118: step: 2864/1545, loss: 0.3988795876502991 2023-01-23 09:08:45.263454: step: 2866/1545, loss: 0.1770377904176712 2023-01-23 09:08:46.118894: step: 2868/1545, loss: 1.1290888786315918 2023-01-23 09:08:47.025226: step: 2870/1545, loss: 0.18171191215515137 2023-01-23 09:08:47.911965: step: 2872/1545, loss: 0.09420587122440338 2023-01-23 09:08:48.790373: step: 2874/1545, loss: 2.2675254344940186 2023-01-23 09:08:49.700984: step: 2876/1545, loss: 0.3706302046775818 2023-01-23 09:08:50.581249: step: 2878/1545, loss: 0.05084835737943649 2023-01-23 09:08:51.455846: step: 2880/1545, loss: 0.07893166691064835 2023-01-23 09:08:52.360304: step: 2882/1545, loss: 0.23456911742687225 2023-01-23 09:08:53.264944: step: 2884/1545, loss: 0.3452005684375763 2023-01-23 09:08:54.157899: step: 2886/1545, loss: 0.24099406599998474 2023-01-23 09:08:55.044849: step: 2888/1545, loss: 0.8243703246116638 2023-01-23 09:08:55.902781: step: 2890/1545, loss: 0.47431638836860657 2023-01-23 09:08:56.780279: step: 2892/1545, loss: 0.6521734595298767 2023-01-23 09:08:57.692993: step: 2894/1545, loss: 0.25881922245025635 2023-01-23 09:08:58.630627: step: 2896/1545, loss: 0.36460933089256287 2023-01-23 09:08:59.559205: step: 2898/1545, loss: 0.4230916500091553 2023-01-23 09:09:00.438376: step: 2900/1545, loss: 0.20798282325267792 2023-01-23 09:09:01.380507: step: 2902/1545, loss: 0.5511693954467773 2023-01-23 09:09:02.313716: step: 2904/1545, loss: 0.1815248429775238 2023-01-23 09:09:03.181385: step: 2906/1545, loss: 0.11990208923816681 2023-01-23 09:09:04.060588: step: 2908/1545, loss: 0.16428370773792267 2023-01-23 09:09:04.994903: step: 2910/1545, loss: 0.34962892532348633 2023-01-23 09:09:05.861790: step: 2912/1545, loss: 0.29033198952674866 2023-01-23 09:09:06.820604: step: 2914/1545, loss: 0.21536363661289215 2023-01-23 09:09:07.762915: step: 2916/1545, loss: 1.0245503187179565 2023-01-23 09:09:08.671907: step: 2918/1545, loss: 0.6838626265525818 2023-01-23 09:09:09.519897: step: 2920/1545, loss: 0.2849915623664856 2023-01-23 09:09:10.395491: step: 2922/1545, loss: 0.6160687804222107 2023-01-23 09:09:11.284104: step: 2924/1545, loss: 0.22545506060123444 2023-01-23 09:09:12.136688: step: 2926/1545, loss: 0.4535219669342041 2023-01-23 09:09:13.034965: step: 2928/1545, loss: 0.5049307346343994 2023-01-23 09:09:13.898053: step: 2930/1545, loss: 0.18930532038211823 2023-01-23 09:09:14.778567: step: 2932/1545, loss: 0.46788814663887024 2023-01-23 09:09:15.674957: step: 2934/1545, loss: 0.1907670646905899 2023-01-23 09:09:16.562716: step: 2936/1545, loss: 0.04264683648943901 2023-01-23 09:09:17.502790: step: 2938/1545, loss: 0.20033147931098938 2023-01-23 09:09:18.386838: step: 2940/1545, loss: 0.16307948529720306 2023-01-23 09:09:19.308859: step: 2942/1545, loss: 0.3507327735424042 2023-01-23 09:09:20.201128: step: 2944/1545, loss: 2.5855143070220947 2023-01-23 09:09:21.082847: step: 2946/1545, loss: 0.10393182933330536 2023-01-23 09:09:21.941647: step: 2948/1545, loss: 0.5898094773292542 2023-01-23 09:09:22.826792: step: 2950/1545, loss: 0.3379412591457367 2023-01-23 09:09:23.709960: step: 2952/1545, loss: 0.6334208250045776 2023-01-23 09:09:24.645533: step: 2954/1545, loss: 0.1483861804008484 2023-01-23 09:09:25.519255: step: 2956/1545, loss: 0.38153237104415894 2023-01-23 09:09:26.414878: step: 2958/1545, loss: 0.04291531443595886 2023-01-23 09:09:27.265600: step: 2960/1545, loss: 0.2618396580219269 2023-01-23 09:09:28.136746: step: 2962/1545, loss: 0.21964670717716217 2023-01-23 09:09:29.067985: step: 2964/1545, loss: 0.2587604522705078 2023-01-23 09:09:30.001161: step: 2966/1545, loss: 0.45515525341033936 2023-01-23 09:09:30.935942: step: 2968/1545, loss: 0.15913690626621246 2023-01-23 09:09:31.831050: step: 2970/1545, loss: 0.17081625759601593 2023-01-23 09:09:32.706777: step: 2972/1545, loss: 0.14836397767066956 2023-01-23 09:09:33.575904: step: 2974/1545, loss: 0.35013681650161743 2023-01-23 09:09:34.436527: step: 2976/1545, loss: 0.03972862660884857 2023-01-23 09:09:35.321260: step: 2978/1545, loss: 0.3233809471130371 2023-01-23 09:09:36.186542: step: 2980/1545, loss: 0.4181249737739563 2023-01-23 09:09:37.086954: step: 2982/1545, loss: 0.36007580161094666 2023-01-23 09:09:38.003037: step: 2984/1545, loss: 1.4718533754348755 2023-01-23 09:09:38.902685: step: 2986/1545, loss: 0.4669070243835449 2023-01-23 09:09:39.815918: step: 2988/1545, loss: 0.25330737233161926 2023-01-23 09:09:40.737686: step: 2990/1545, loss: 0.32422682642936707 2023-01-23 09:09:41.696721: step: 2992/1545, loss: 5.999259948730469 2023-01-23 09:09:42.589278: step: 2994/1545, loss: 0.2901303172111511 2023-01-23 09:09:43.476580: step: 2996/1545, loss: 0.28808411955833435 2023-01-23 09:09:44.374595: step: 2998/1545, loss: 0.23180420696735382 2023-01-23 09:09:45.247627: step: 3000/1545, loss: 0.25351396203041077 2023-01-23 09:09:46.134769: step: 3002/1545, loss: 0.09444966912269592 2023-01-23 09:09:47.085906: step: 3004/1545, loss: 0.23299796879291534 2023-01-23 09:09:47.983640: step: 3006/1545, loss: 0.2177639901638031 2023-01-23 09:09:48.831371: step: 3008/1545, loss: 0.4090840220451355 2023-01-23 09:09:49.715818: step: 3010/1545, loss: 0.45616692304611206 2023-01-23 09:09:50.610262: step: 3012/1545, loss: 0.19116194546222687 2023-01-23 09:09:51.515050: step: 3014/1545, loss: 0.7905855774879456 2023-01-23 09:09:52.412749: step: 3016/1545, loss: 0.11046860367059708 2023-01-23 09:09:53.307457: step: 3018/1545, loss: 0.37424129247665405 2023-01-23 09:09:54.148288: step: 3020/1545, loss: 0.09326035529375076 2023-01-23 09:09:55.079962: step: 3022/1545, loss: 0.26139482855796814 2023-01-23 09:09:56.008375: step: 3024/1545, loss: 0.559288740158081 2023-01-23 09:09:56.853355: step: 3026/1545, loss: 1.6436103582382202 2023-01-23 09:09:57.706630: step: 3028/1545, loss: 0.1934981346130371 2023-01-23 09:09:58.591514: step: 3030/1545, loss: 0.41308778524398804 2023-01-23 09:09:59.495598: step: 3032/1545, loss: 0.14661414921283722 2023-01-23 09:10:00.392427: step: 3034/1545, loss: 0.12585003674030304 2023-01-23 09:10:01.328027: step: 3036/1545, loss: 1.3803644180297852 2023-01-23 09:10:02.314046: step: 3038/1545, loss: 0.2617345452308655 2023-01-23 09:10:03.220105: step: 3040/1545, loss: 0.1817092001438141 2023-01-23 09:10:04.088472: step: 3042/1545, loss: 0.6230143308639526 2023-01-23 09:10:04.959223: step: 3044/1545, loss: 0.25865474343299866 2023-01-23 09:10:05.825291: step: 3046/1545, loss: 0.23140670359134674 2023-01-23 09:10:06.768595: step: 3048/1545, loss: 0.2088082879781723 2023-01-23 09:10:07.646395: step: 3050/1545, loss: 0.19069227576255798 2023-01-23 09:10:08.498844: step: 3052/1545, loss: 0.13226796686649323 2023-01-23 09:10:09.356054: step: 3054/1545, loss: 0.39199790358543396 2023-01-23 09:10:10.221657: step: 3056/1545, loss: 0.07733239978551865 2023-01-23 09:10:11.104931: step: 3058/1545, loss: 0.2388821840286255 2023-01-23 09:10:11.999704: step: 3060/1545, loss: 0.2988239526748657 2023-01-23 09:10:12.900057: step: 3062/1545, loss: 0.5706073045730591 2023-01-23 09:10:13.834587: step: 3064/1545, loss: 0.2186816781759262 2023-01-23 09:10:14.690508: step: 3066/1545, loss: 0.4637545347213745 2023-01-23 09:10:15.530805: step: 3068/1545, loss: 0.19968324899673462 2023-01-23 09:10:16.418607: step: 3070/1545, loss: 1.0724693536758423 2023-01-23 09:10:17.320033: step: 3072/1545, loss: 0.6312372088432312 2023-01-23 09:10:18.197381: step: 3074/1545, loss: 0.3806561827659607 2023-01-23 09:10:19.163393: step: 3076/1545, loss: 0.37776321172714233 2023-01-23 09:10:20.025298: step: 3078/1545, loss: 0.8443906307220459 2023-01-23 09:10:20.934912: step: 3080/1545, loss: 0.5476025938987732 2023-01-23 09:10:21.850549: step: 3082/1545, loss: 0.2333299219608307 2023-01-23 09:10:22.705620: step: 3084/1545, loss: 0.16710446774959564 2023-01-23 09:10:23.616878: step: 3086/1545, loss: 0.5646357536315918 2023-01-23 09:10:24.506827: step: 3088/1545, loss: 0.186584934592247 2023-01-23 09:10:25.396913: step: 3090/1545, loss: 0.3787005841732025 ================================================== Loss: 0.403 -------------------- Dev Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.658083880362888, 'r': 0.6492241123400518, 'f1': 0.6536239745471757}, 'combined': 0.4310469856126458, 'epoch': 8} Test Chinese: {'event': {'p': 0.6387406616862327, 'r': 0.7653452685421995, 'f1': 0.6963350785340314}, 'argument': {'p': 0.7105799845148731, 'r': 0.7122097551215586, 'f1': 0.7113939363871696}, 'combined': 0.49536855256279355, 'epoch': 8} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6577124920673522, 'r': 0.6517871543009796, 'f1': 0.654736417442613}, 'combined': 0.43806388530394647, 'epoch': 8} Test Korean: {'event': {'p': 0.6280423280423281, 'r': 0.7589514066496164, 'f1': 0.6873190503763752}, 'argument': {'p': 0.707702090430235, 'r': 0.7112229963527735, 'f1': 0.7094581750218732}, 'combined': 0.48762411913779014, 'epoch': 8} Dev Russian: {'event': {'p': 0.5679133858267716, 'r': 0.7683089214380826, 'f1': 0.653084323712507}, 'argument': {'p': 0.6501582658436547, 'r': 0.6589944654509718, 'f1': 0.6545465454354946}, 'combined': 0.42747408796409775, 'epoch': 8} Test Russian: {'event': {'p': 0.6238166417538615, 'r': 0.8005115089514067, 'f1': 0.7012041444973396}, 'argument': {'p': 0.7119859522076413, 'r': 0.7226484149887367, 'f1': 0.7172775609197011}, 'combined': 0.5029579984718374, 'epoch': 8} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.68475665748393, 'r': 0.6225060522581182, 'f1': 0.6521491976037429}, 'combined': 0.4545282286329118, 'epoch': 8} Korean: {'event': {'p': 0.6666666666666666, 'r': 0.5396825396825397, 'f1': 0.5964912280701754}, 'argument': {'p': 0.6637820512820513, 'r': 0.36876780626780625, 'f1': 0.4741300366300366}, 'combined': 0.2828144078144078, 'epoch': 8} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5913205745636086, 'r': 0.5385240946918579, 'f1': 0.5636887720139073}, 'combined': 0.31395324010901166, 'epoch': 8} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.662984814123997, 'r': 0.6580037110877536, 'f1': 0.6604848713859729}, 'combined': 0.4442901236950689, 'epoch': 7} Test for Korean: {'event': {'p': 0.6317460317460317, 'r': 0.7634271099744245, 'f1': 0.6913723219455704}, 'argument': {'p': 0.697622599900428, 'r': 0.7136353604184179, 'f1': 0.7055381362079215}, 'combined': 0.48778953945122083, 'epoch': 7} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6358730158730159, 'r': 0.43552946292672323, 'f1': 0.5169699316040779}, 'combined': 0.3174376773007496, 'epoch': 7} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 9 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 09:15:38.440906: step: 2/1545, loss: 0.18555378913879395 2023-01-23 09:15:39.338845: step: 4/1545, loss: 0.16183839738368988 2023-01-23 09:15:40.264457: step: 6/1545, loss: 0.12861491739749908 2023-01-23 09:15:41.233327: step: 8/1545, loss: 0.12324485182762146 2023-01-23 09:15:42.132741: step: 10/1545, loss: 0.17686064541339874 2023-01-23 09:15:43.037115: step: 12/1545, loss: 0.08496680110692978 2023-01-23 09:15:43.903185: step: 14/1545, loss: 0.2579628527164459 2023-01-23 09:15:44.762312: step: 16/1545, loss: 0.13385805487632751 2023-01-23 09:15:45.634392: step: 18/1545, loss: 0.20973585546016693 2023-01-23 09:15:46.483824: step: 20/1545, loss: 0.510250449180603 2023-01-23 09:15:47.331159: step: 22/1545, loss: 0.24645286798477173 2023-01-23 09:15:48.198192: step: 24/1545, loss: 0.8993829488754272 2023-01-23 09:15:49.085264: step: 26/1545, loss: 0.22410090267658234 2023-01-23 09:15:49.979496: step: 28/1545, loss: 0.37467867136001587 2023-01-23 09:15:50.864472: step: 30/1545, loss: 1.4405430555343628 2023-01-23 09:15:51.739348: step: 32/1545, loss: 0.11764224618673325 2023-01-23 09:15:52.654242: step: 34/1545, loss: 0.07080256938934326 2023-01-23 09:15:53.514244: step: 36/1545, loss: 0.1718008667230606 2023-01-23 09:15:54.372640: step: 38/1545, loss: 0.2421642541885376 2023-01-23 09:15:55.276085: step: 40/1545, loss: 0.38426831364631653 2023-01-23 09:15:56.129491: step: 42/1545, loss: 0.07076086848974228 2023-01-23 09:15:56.962171: step: 44/1545, loss: 0.23832842707633972 2023-01-23 09:15:57.836234: step: 46/1545, loss: 0.0726805105805397 2023-01-23 09:15:58.742891: step: 48/1545, loss: 0.07946839183568954 2023-01-23 09:15:59.679213: step: 50/1545, loss: 0.14852091670036316 2023-01-23 09:16:00.603659: step: 52/1545, loss: 0.15861135721206665 2023-01-23 09:16:01.517178: step: 54/1545, loss: 0.1258552372455597 2023-01-23 09:16:02.401455: step: 56/1545, loss: 0.12486445158720016 2023-01-23 09:16:03.308441: step: 58/1545, loss: 0.12544941902160645 2023-01-23 09:16:04.155330: step: 60/1545, loss: 0.014775867573916912 2023-01-23 09:16:05.061209: step: 62/1545, loss: 0.11922839283943176 2023-01-23 09:16:05.923602: step: 64/1545, loss: 0.5334920883178711 2023-01-23 09:16:06.825659: step: 66/1545, loss: 1.0571215152740479 2023-01-23 09:16:07.661561: step: 68/1545, loss: 0.9282435178756714 2023-01-23 09:16:08.497775: step: 70/1545, loss: 0.015213994309306145 2023-01-23 09:16:09.335214: step: 72/1545, loss: 0.11276799440383911 2023-01-23 09:16:10.236862: step: 74/1545, loss: 0.2613033950328827 2023-01-23 09:16:11.175719: step: 76/1545, loss: 0.5203862190246582 2023-01-23 09:16:12.049243: step: 78/1545, loss: 0.40769505500793457 2023-01-23 09:16:12.950690: step: 80/1545, loss: 0.5124332904815674 2023-01-23 09:16:13.824229: step: 82/1545, loss: 0.18092215061187744 2023-01-23 09:16:14.707055: step: 84/1545, loss: 0.6690289378166199 2023-01-23 09:16:15.567796: step: 86/1545, loss: 0.028025459498167038 2023-01-23 09:16:16.474798: step: 88/1545, loss: 0.05303230136632919 2023-01-23 09:16:17.336404: step: 90/1545, loss: 0.08359446376562119 2023-01-23 09:16:18.194297: step: 92/1545, loss: 0.05269846320152283 2023-01-23 09:16:19.175762: step: 94/1545, loss: 0.17231981456279755 2023-01-23 09:16:20.027562: step: 96/1545, loss: 0.1733875721693039 2023-01-23 09:16:20.871752: step: 98/1545, loss: 0.08614473789930344 2023-01-23 09:16:21.770977: step: 100/1545, loss: 0.11927317827939987 2023-01-23 09:16:22.650407: step: 102/1545, loss: 0.10039463639259338 2023-01-23 09:16:23.475983: step: 104/1545, loss: 0.16789613664150238 2023-01-23 09:16:24.458694: step: 106/1545, loss: 0.5476901531219482 2023-01-23 09:16:25.329522: step: 108/1545, loss: 0.16048625111579895 2023-01-23 09:16:26.215039: step: 110/1545, loss: 0.3777097463607788 2023-01-23 09:16:27.060830: step: 112/1545, loss: 0.01451326534152031 2023-01-23 09:16:27.936360: step: 114/1545, loss: 0.2568473219871521 2023-01-23 09:16:28.868091: step: 116/1545, loss: 0.09732093662023544 2023-01-23 09:16:29.767870: step: 118/1545, loss: 0.9675180912017822 2023-01-23 09:16:30.680171: step: 120/1545, loss: 0.19676454365253448 2023-01-23 09:16:31.584031: step: 122/1545, loss: 0.2990510165691376 2023-01-23 09:16:32.469623: step: 124/1545, loss: 0.08394216001033783 2023-01-23 09:16:33.377022: step: 126/1545, loss: 0.0723486840724945 2023-01-23 09:16:34.247424: step: 128/1545, loss: 0.17964619398117065 2023-01-23 09:16:35.167671: step: 130/1545, loss: 0.103665791451931 2023-01-23 09:16:36.089889: step: 132/1545, loss: 0.167580246925354 2023-01-23 09:16:36.999424: step: 134/1545, loss: 0.21599026024341583 2023-01-23 09:16:37.885776: step: 136/1545, loss: 0.29610252380371094 2023-01-23 09:16:38.773842: step: 138/1545, loss: 0.09556730091571808 2023-01-23 09:16:39.628260: step: 140/1545, loss: 0.08640267699956894 2023-01-23 09:16:40.546844: step: 142/1545, loss: 0.49543601274490356 2023-01-23 09:16:41.414434: step: 144/1545, loss: 0.09307414293289185 2023-01-23 09:16:42.305286: step: 146/1545, loss: 0.10883461683988571 2023-01-23 09:16:43.155806: step: 148/1545, loss: 0.32663577795028687 2023-01-23 09:16:44.016419: step: 150/1545, loss: 0.10219576954841614 2023-01-23 09:16:44.875424: step: 152/1545, loss: 0.6795295476913452 2023-01-23 09:16:45.827053: step: 154/1545, loss: 0.1038745790719986 2023-01-23 09:16:46.730633: step: 156/1545, loss: 0.15965299308300018 2023-01-23 09:16:47.598011: step: 158/1545, loss: 0.35921797156333923 2023-01-23 09:16:48.503448: step: 160/1545, loss: 0.07543372362852097 2023-01-23 09:16:49.365410: step: 162/1545, loss: 2.4997472763061523 2023-01-23 09:16:50.232583: step: 164/1545, loss: 0.2351977676153183 2023-01-23 09:16:51.174654: step: 166/1545, loss: 0.2794044613838196 2023-01-23 09:16:52.041059: step: 168/1545, loss: 3.6020355224609375 2023-01-23 09:16:52.912975: step: 170/1545, loss: 0.33996614813804626 2023-01-23 09:16:53.770208: step: 172/1545, loss: 0.050888791680336 2023-01-23 09:16:54.688436: step: 174/1545, loss: 0.47638264298439026 2023-01-23 09:16:55.626673: step: 176/1545, loss: 0.04679132625460625 2023-01-23 09:16:56.534365: step: 178/1545, loss: 0.08713648468255997 2023-01-23 09:16:57.404259: step: 180/1545, loss: 0.21356678009033203 2023-01-23 09:16:58.278506: step: 182/1545, loss: 0.6925128102302551 2023-01-23 09:16:59.110254: step: 184/1545, loss: 0.32585540413856506 2023-01-23 09:17:00.009943: step: 186/1545, loss: 0.30883732438087463 2023-01-23 09:17:00.938641: step: 188/1545, loss: 0.7892729043960571 2023-01-23 09:17:01.810419: step: 190/1545, loss: 0.09067854285240173 2023-01-23 09:17:02.667476: step: 192/1545, loss: 0.10143920034170151 2023-01-23 09:17:03.552703: step: 194/1545, loss: 0.19324667751789093 2023-01-23 09:17:04.411465: step: 196/1545, loss: 0.26237112283706665 2023-01-23 09:17:05.269535: step: 198/1545, loss: 0.3374515771865845 2023-01-23 09:17:06.141447: step: 200/1545, loss: 0.3840138018131256 2023-01-23 09:17:07.028405: step: 202/1545, loss: 0.45123112201690674 2023-01-23 09:17:07.881460: step: 204/1545, loss: 0.06785878539085388 2023-01-23 09:17:08.779945: step: 206/1545, loss: 0.1852598339319229 2023-01-23 09:17:09.655670: step: 208/1545, loss: 0.4489602744579315 2023-01-23 09:17:10.521768: step: 210/1545, loss: 0.13168691098690033 2023-01-23 09:17:11.407424: step: 212/1545, loss: 0.16297709941864014 2023-01-23 09:17:12.262038: step: 214/1545, loss: 0.09204889833927155 2023-01-23 09:17:13.139774: step: 216/1545, loss: 0.5621699690818787 2023-01-23 09:17:14.062146: step: 218/1545, loss: 0.3067109286785126 2023-01-23 09:17:14.954268: step: 220/1545, loss: 0.10573972016572952 2023-01-23 09:17:15.800533: step: 222/1545, loss: 0.3122578561306 2023-01-23 09:17:16.659698: step: 224/1545, loss: 0.17409907281398773 2023-01-23 09:17:17.526738: step: 226/1545, loss: 0.11177520453929901 2023-01-23 09:17:18.405490: step: 228/1545, loss: 0.17852389812469482 2023-01-23 09:17:19.369517: step: 230/1545, loss: 0.3217432200908661 2023-01-23 09:17:20.232145: step: 232/1545, loss: 0.13810713589191437 2023-01-23 09:17:21.144626: step: 234/1545, loss: 0.19667384028434753 2023-01-23 09:17:22.025048: step: 236/1545, loss: 0.0875408723950386 2023-01-23 09:17:22.973003: step: 238/1545, loss: 0.055681098252534866 2023-01-23 09:17:23.815766: step: 240/1545, loss: 0.12514391541481018 2023-01-23 09:17:24.711692: step: 242/1545, loss: 0.08734505623579025 2023-01-23 09:17:25.570945: step: 244/1545, loss: 0.377053827047348 2023-01-23 09:17:26.443968: step: 246/1545, loss: 0.04120993986725807 2023-01-23 09:17:27.314530: step: 248/1545, loss: 0.2564614415168762 2023-01-23 09:17:28.240173: step: 250/1545, loss: 0.13985739648342133 2023-01-23 09:17:29.141326: step: 252/1545, loss: 0.1315830498933792 2023-01-23 09:17:30.016513: step: 254/1545, loss: 0.10029762238264084 2023-01-23 09:17:30.896574: step: 256/1545, loss: 0.07992920279502869 2023-01-23 09:17:31.744991: step: 258/1545, loss: 0.3428382873535156 2023-01-23 09:17:32.673719: step: 260/1545, loss: 0.09575937688350677 2023-01-23 09:17:33.595342: step: 262/1545, loss: 0.057040952146053314 2023-01-23 09:17:34.490831: step: 264/1545, loss: 0.14156198501586914 2023-01-23 09:17:35.391922: step: 266/1545, loss: 0.18286682665348053 2023-01-23 09:17:36.247519: step: 268/1545, loss: 0.11476410925388336 2023-01-23 09:17:37.132985: step: 270/1545, loss: 0.2210964858531952 2023-01-23 09:17:37.999359: step: 272/1545, loss: 0.37076422572135925 2023-01-23 09:17:38.889180: step: 274/1545, loss: 0.2196112722158432 2023-01-23 09:17:39.817165: step: 276/1545, loss: 0.11668571829795837 2023-01-23 09:17:40.669312: step: 278/1545, loss: 0.1112198755145073 2023-01-23 09:17:41.526798: step: 280/1545, loss: 0.2595735490322113 2023-01-23 09:17:42.366346: step: 282/1545, loss: 0.2721351981163025 2023-01-23 09:17:43.211764: step: 284/1545, loss: 0.32128918170928955 2023-01-23 09:17:44.092181: step: 286/1545, loss: 0.26305630803108215 2023-01-23 09:17:44.956272: step: 288/1545, loss: 0.22603048384189606 2023-01-23 09:17:45.825938: step: 290/1545, loss: 0.4133221507072449 2023-01-23 09:17:46.730955: step: 292/1545, loss: 0.4021722078323364 2023-01-23 09:17:47.589571: step: 294/1545, loss: 0.10210777074098587 2023-01-23 09:17:48.455738: step: 296/1545, loss: 0.19563773274421692 2023-01-23 09:17:49.335147: step: 298/1545, loss: 0.2735564112663269 2023-01-23 09:17:50.279081: step: 300/1545, loss: 0.1585467904806137 2023-01-23 09:17:51.123447: step: 302/1545, loss: 2.079836368560791 2023-01-23 09:17:51.970015: step: 304/1545, loss: 0.07330500334501266 2023-01-23 09:17:52.830360: step: 306/1545, loss: 0.534014880657196 2023-01-23 09:17:53.716177: step: 308/1545, loss: 0.6460593938827515 2023-01-23 09:17:54.616776: step: 310/1545, loss: 0.10761226713657379 2023-01-23 09:17:55.523487: step: 312/1545, loss: 0.18496033549308777 2023-01-23 09:17:56.398492: step: 314/1545, loss: 2.2818450927734375 2023-01-23 09:17:57.264564: step: 316/1545, loss: 0.1799093335866928 2023-01-23 09:17:58.135129: step: 318/1545, loss: 0.12397132068872452 2023-01-23 09:17:59.079094: step: 320/1545, loss: 0.7030129432678223 2023-01-23 09:17:59.924899: step: 322/1545, loss: 0.23764577507972717 2023-01-23 09:18:00.807363: step: 324/1545, loss: 0.10043831169605255 2023-01-23 09:18:01.675913: step: 326/1545, loss: 0.3042449355125427 2023-01-23 09:18:02.534868: step: 328/1545, loss: 0.0899479016661644 2023-01-23 09:18:03.446890: step: 330/1545, loss: 3.177893877029419 2023-01-23 09:18:04.325961: step: 332/1545, loss: 0.33100026845932007 2023-01-23 09:18:05.230308: step: 334/1545, loss: 0.1789308339357376 2023-01-23 09:18:06.106118: step: 336/1545, loss: 0.16923770308494568 2023-01-23 09:18:06.987953: step: 338/1545, loss: 0.5551774501800537 2023-01-23 09:18:07.883373: step: 340/1545, loss: 0.18993639945983887 2023-01-23 09:18:08.773076: step: 342/1545, loss: 0.15298409759998322 2023-01-23 09:18:09.643652: step: 344/1545, loss: 0.13329024612903595 2023-01-23 09:18:10.533833: step: 346/1545, loss: 0.35093915462493896 2023-01-23 09:18:11.489244: step: 348/1545, loss: 0.1004541739821434 2023-01-23 09:18:12.332558: step: 350/1545, loss: 0.09902094304561615 2023-01-23 09:18:13.187732: step: 352/1545, loss: 0.06147279217839241 2023-01-23 09:18:14.055648: step: 354/1545, loss: 0.3329398036003113 2023-01-23 09:18:14.931396: step: 356/1545, loss: 0.2659587562084198 2023-01-23 09:18:15.843949: step: 358/1545, loss: 0.13785377144813538 2023-01-23 09:18:16.722810: step: 360/1545, loss: 0.26358532905578613 2023-01-23 09:18:17.609878: step: 362/1545, loss: 1.5417536497116089 2023-01-23 09:18:18.476743: step: 364/1545, loss: 0.01299478393048048 2023-01-23 09:18:19.415562: step: 366/1545, loss: 0.6378090381622314 2023-01-23 09:18:20.288686: step: 368/1545, loss: 0.058458223938941956 2023-01-23 09:18:21.163411: step: 370/1545, loss: 0.5145393013954163 2023-01-23 09:18:22.017170: step: 372/1545, loss: 0.09282959252595901 2023-01-23 09:18:22.884497: step: 374/1545, loss: 0.24043166637420654 2023-01-23 09:18:23.886746: step: 376/1545, loss: 0.5469396114349365 2023-01-23 09:18:24.753460: step: 378/1545, loss: 0.20989865064620972 2023-01-23 09:18:25.694867: step: 380/1545, loss: 0.5877894163131714 2023-01-23 09:18:26.563003: step: 382/1545, loss: 0.45939990878105164 2023-01-23 09:18:27.450537: step: 384/1545, loss: 0.11462842673063278 2023-01-23 09:18:28.335892: step: 386/1545, loss: 0.10641203075647354 2023-01-23 09:18:29.205033: step: 388/1545, loss: 0.2392698973417282 2023-01-23 09:18:30.108951: step: 390/1545, loss: 0.43197035789489746 2023-01-23 09:18:30.999072: step: 392/1545, loss: 0.2845804989337921 2023-01-23 09:18:31.851036: step: 394/1545, loss: 0.1536618024110794 2023-01-23 09:18:32.800051: step: 396/1545, loss: 0.249936044216156 2023-01-23 09:18:33.714120: step: 398/1545, loss: 0.6510719060897827 2023-01-23 09:18:34.564778: step: 400/1545, loss: 0.08619977533817291 2023-01-23 09:18:35.427097: step: 402/1545, loss: 0.031162520870566368 2023-01-23 09:18:36.274727: step: 404/1545, loss: 0.4509209096431732 2023-01-23 09:18:37.165888: step: 406/1545, loss: 0.2340548038482666 2023-01-23 09:18:38.051441: step: 408/1545, loss: 0.24467459321022034 2023-01-23 09:18:38.907101: step: 410/1545, loss: 0.07813505083322525 2023-01-23 09:18:39.763728: step: 412/1545, loss: 0.5267096161842346 2023-01-23 09:18:40.643525: step: 414/1545, loss: 0.09308312088251114 2023-01-23 09:18:41.512572: step: 416/1545, loss: 0.24247276782989502 2023-01-23 09:18:42.401357: step: 418/1545, loss: 0.12546975910663605 2023-01-23 09:18:43.277530: step: 420/1545, loss: 0.7961620092391968 2023-01-23 09:18:44.147048: step: 422/1545, loss: 0.24041515588760376 2023-01-23 09:18:45.005446: step: 424/1545, loss: 0.16198456287384033 2023-01-23 09:18:45.851166: step: 426/1545, loss: 0.24149470031261444 2023-01-23 09:18:46.759416: step: 428/1545, loss: 0.22733838856220245 2023-01-23 09:18:47.646467: step: 430/1545, loss: 0.2506996691226959 2023-01-23 09:18:48.492248: step: 432/1545, loss: 0.15882815420627594 2023-01-23 09:18:49.376114: step: 434/1545, loss: 0.1968187838792801 2023-01-23 09:18:50.267770: step: 436/1545, loss: 0.24606305360794067 2023-01-23 09:18:51.215296: step: 438/1545, loss: 0.5850979685783386 2023-01-23 09:18:52.092437: step: 440/1545, loss: 0.10838150233030319 2023-01-23 09:18:52.952741: step: 442/1545, loss: 0.14939925074577332 2023-01-23 09:18:53.832052: step: 444/1545, loss: 0.7809923887252808 2023-01-23 09:18:54.705722: step: 446/1545, loss: 0.08632402122020721 2023-01-23 09:18:55.615809: step: 448/1545, loss: 0.20733542740345 2023-01-23 09:18:56.492122: step: 450/1545, loss: 0.11751464754343033 2023-01-23 09:18:57.368883: step: 452/1545, loss: 0.40290409326553345 2023-01-23 09:18:58.280279: step: 454/1545, loss: 0.5591716766357422 2023-01-23 09:18:59.156133: step: 456/1545, loss: 0.2840496003627777 2023-01-23 09:19:00.096203: step: 458/1545, loss: 0.02894452027976513 2023-01-23 09:19:00.978632: step: 460/1545, loss: 0.13463428616523743 2023-01-23 09:19:01.875874: step: 462/1545, loss: 0.22090354561805725 2023-01-23 09:19:02.810159: step: 464/1545, loss: 0.24199245870113373 2023-01-23 09:19:03.662704: step: 466/1545, loss: 0.35716596245765686 2023-01-23 09:19:04.538906: step: 468/1545, loss: 0.09341037273406982 2023-01-23 09:19:05.479585: step: 470/1545, loss: 0.08246206492185593 2023-01-23 09:19:06.339612: step: 472/1545, loss: 0.14216411113739014 2023-01-23 09:19:07.197518: step: 474/1545, loss: 0.24164652824401855 2023-01-23 09:19:08.061410: step: 476/1545, loss: 0.12092717736959457 2023-01-23 09:19:08.935399: step: 478/1545, loss: 0.08919494599103928 2023-01-23 09:19:09.829704: step: 480/1545, loss: 0.3800196945667267 2023-01-23 09:19:10.711003: step: 482/1545, loss: 0.24234835803508759 2023-01-23 09:19:11.579674: step: 484/1545, loss: 0.3896390199661255 2023-01-23 09:19:12.560150: step: 486/1545, loss: 0.11170732975006104 2023-01-23 09:19:13.451521: step: 488/1545, loss: 0.1667056828737259 2023-01-23 09:19:14.385561: step: 490/1545, loss: 0.1727074235677719 2023-01-23 09:19:15.238757: step: 492/1545, loss: 0.04162459447979927 2023-01-23 09:19:16.125298: step: 494/1545, loss: 0.10566289722919464 2023-01-23 09:19:17.004566: step: 496/1545, loss: 0.3852492570877075 2023-01-23 09:19:17.935328: step: 498/1545, loss: 3.553253650665283 2023-01-23 09:19:18.807588: step: 500/1545, loss: 0.34832724928855896 2023-01-23 09:19:19.725103: step: 502/1545, loss: 0.158103346824646 2023-01-23 09:19:20.646372: step: 504/1545, loss: 0.03331279382109642 2023-01-23 09:19:21.521105: step: 506/1545, loss: 0.27282819151878357 2023-01-23 09:19:22.395322: step: 508/1545, loss: 0.26294973492622375 2023-01-23 09:19:23.270669: step: 510/1545, loss: 0.1931324005126953 2023-01-23 09:19:24.138927: step: 512/1545, loss: 0.22859647870063782 2023-01-23 09:19:24.984419: step: 514/1545, loss: 0.31194910407066345 2023-01-23 09:19:25.909389: step: 516/1545, loss: 0.1295371651649475 2023-01-23 09:19:26.775469: step: 518/1545, loss: 0.02246713452041149 2023-01-23 09:19:27.635677: step: 520/1545, loss: 0.0251520536839962 2023-01-23 09:19:28.541669: step: 522/1545, loss: 0.3693244457244873 2023-01-23 09:19:29.425146: step: 524/1545, loss: 0.05003846436738968 2023-01-23 09:19:30.293953: step: 526/1545, loss: 0.4791333079338074 2023-01-23 09:19:31.172201: step: 528/1545, loss: 0.32696837186813354 2023-01-23 09:19:32.060302: step: 530/1545, loss: 0.47257497906684875 2023-01-23 09:19:32.934107: step: 532/1545, loss: 0.21093463897705078 2023-01-23 09:19:33.800591: step: 534/1545, loss: 0.2615148425102234 2023-01-23 09:19:34.693361: step: 536/1545, loss: 0.042577072978019714 2023-01-23 09:19:35.548909: step: 538/1545, loss: 0.1227363720536232 2023-01-23 09:19:36.403953: step: 540/1545, loss: 0.20422987639904022 2023-01-23 09:19:37.327319: step: 542/1545, loss: 0.25299662351608276 2023-01-23 09:19:38.242379: step: 544/1545, loss: 0.14214663207530975 2023-01-23 09:19:39.186377: step: 546/1545, loss: 0.12400183826684952 2023-01-23 09:19:40.055766: step: 548/1545, loss: 0.09666579216718674 2023-01-23 09:19:40.920463: step: 550/1545, loss: 0.6304965019226074 2023-01-23 09:19:41.796377: step: 552/1545, loss: 0.18057194352149963 2023-01-23 09:19:42.672996: step: 554/1545, loss: 0.4546671211719513 2023-01-23 09:19:43.545015: step: 556/1545, loss: 0.20400339365005493 2023-01-23 09:19:44.411692: step: 558/1545, loss: 0.11353770643472672 2023-01-23 09:19:45.257384: step: 560/1545, loss: 0.09210114181041718 2023-01-23 09:19:46.094089: step: 562/1545, loss: 0.08834873139858246 2023-01-23 09:19:46.948089: step: 564/1545, loss: 0.13303814828395844 2023-01-23 09:19:47.823613: step: 566/1545, loss: 0.15040992200374603 2023-01-23 09:19:48.706667: step: 568/1545, loss: 0.15066826343536377 2023-01-23 09:19:49.550737: step: 570/1545, loss: 0.11390776932239532 2023-01-23 09:19:50.393244: step: 572/1545, loss: 0.24318814277648926 2023-01-23 09:19:51.340965: step: 574/1545, loss: 0.18184088170528412 2023-01-23 09:19:52.218289: step: 576/1545, loss: 0.21033576130867004 2023-01-23 09:19:53.136309: step: 578/1545, loss: 0.28010985255241394 2023-01-23 09:19:53.998944: step: 580/1545, loss: 0.315926194190979 2023-01-23 09:19:54.850723: step: 582/1545, loss: 0.003268127329647541 2023-01-23 09:19:55.739454: step: 584/1545, loss: 0.21137669682502747 2023-01-23 09:19:56.682353: step: 586/1545, loss: 0.22991763055324554 2023-01-23 09:19:57.587192: step: 588/1545, loss: 0.5550011396408081 2023-01-23 09:19:58.454844: step: 590/1545, loss: 0.3791936933994293 2023-01-23 09:19:59.304463: step: 592/1545, loss: 0.1202237606048584 2023-01-23 09:20:00.198107: step: 594/1545, loss: 0.7250041365623474 2023-01-23 09:20:01.199902: step: 596/1545, loss: 0.1178581491112709 2023-01-23 09:20:02.135151: step: 598/1545, loss: 0.27304020524024963 2023-01-23 09:20:03.041234: step: 600/1545, loss: 0.16895103454589844 2023-01-23 09:20:03.932098: step: 602/1545, loss: 0.14470072090625763 2023-01-23 09:20:04.792458: step: 604/1545, loss: 0.2779329717159271 2023-01-23 09:20:05.696759: step: 606/1545, loss: 0.19372010231018066 2023-01-23 09:20:06.609630: step: 608/1545, loss: 1.0367577075958252 2023-01-23 09:20:07.456823: step: 610/1545, loss: 0.2653152644634247 2023-01-23 09:20:08.414060: step: 612/1545, loss: 0.3812713921070099 2023-01-23 09:20:09.280851: step: 614/1545, loss: 0.22914890944957733 2023-01-23 09:20:10.153869: step: 616/1545, loss: 0.41644325852394104 2023-01-23 09:20:11.003843: step: 618/1545, loss: 0.17747288942337036 2023-01-23 09:20:11.892357: step: 620/1545, loss: 0.2847757637500763 2023-01-23 09:20:12.774794: step: 622/1545, loss: 0.23859655857086182 2023-01-23 09:20:13.631967: step: 624/1545, loss: 0.3695431351661682 2023-01-23 09:20:14.508163: step: 626/1545, loss: 0.3970063626766205 2023-01-23 09:20:15.380093: step: 628/1545, loss: 0.2361532300710678 2023-01-23 09:20:16.262174: step: 630/1545, loss: 0.11417880654335022 2023-01-23 09:20:17.149889: step: 632/1545, loss: 0.1450076699256897 2023-01-23 09:20:17.982855: step: 634/1545, loss: 0.2100858986377716 2023-01-23 09:20:18.874373: step: 636/1545, loss: 0.7256118059158325 2023-01-23 09:20:19.774936: step: 638/1545, loss: 0.039403464645147324 2023-01-23 09:20:20.769747: step: 640/1545, loss: 0.08923228830099106 2023-01-23 09:20:21.629012: step: 642/1545, loss: 0.2667831778526306 2023-01-23 09:20:22.504503: step: 644/1545, loss: 0.3587047755718231 2023-01-23 09:20:23.393592: step: 646/1545, loss: 0.13328927755355835 2023-01-23 09:20:24.285303: step: 648/1545, loss: 0.36197367310523987 2023-01-23 09:20:25.217459: step: 650/1545, loss: 0.7897734642028809 2023-01-23 09:20:26.057025: step: 652/1545, loss: 0.09649008512496948 2023-01-23 09:20:26.899651: step: 654/1545, loss: 0.12055520713329315 2023-01-23 09:20:27.732576: step: 656/1545, loss: 0.9877873063087463 2023-01-23 09:20:28.624090: step: 658/1545, loss: 0.25301027297973633 2023-01-23 09:20:29.475991: step: 660/1545, loss: 0.10035055130720139 2023-01-23 09:20:30.351114: step: 662/1545, loss: 0.16545550525188446 2023-01-23 09:20:31.261621: step: 664/1545, loss: 0.4743242561817169 2023-01-23 09:20:32.166037: step: 666/1545, loss: 0.8783048987388611 2023-01-23 09:20:33.048245: step: 668/1545, loss: 0.056931234896183014 2023-01-23 09:20:33.969146: step: 670/1545, loss: 0.04669944569468498 2023-01-23 09:20:34.862045: step: 672/1545, loss: 0.38296401500701904 2023-01-23 09:20:35.713974: step: 674/1545, loss: 0.856085479259491 2023-01-23 09:20:36.586536: step: 676/1545, loss: 0.13090156018733978 2023-01-23 09:20:37.500292: step: 678/1545, loss: 1.924963116645813 2023-01-23 09:20:38.354964: step: 680/1545, loss: 0.3401787281036377 2023-01-23 09:20:39.208494: step: 682/1545, loss: 0.07357164472341537 2023-01-23 09:20:40.115342: step: 684/1545, loss: 0.1304720640182495 2023-01-23 09:20:40.986665: step: 686/1545, loss: 0.17549309134483337 2023-01-23 09:20:41.867747: step: 688/1545, loss: 0.16162842512130737 2023-01-23 09:20:42.738814: step: 690/1545, loss: 0.12056275457143784 2023-01-23 09:20:43.592417: step: 692/1545, loss: 0.3224853277206421 2023-01-23 09:20:44.468132: step: 694/1545, loss: 0.15131619572639465 2023-01-23 09:20:45.379967: step: 696/1545, loss: 0.22118501365184784 2023-01-23 09:20:46.316621: step: 698/1545, loss: 0.2673843204975128 2023-01-23 09:20:47.192069: step: 700/1545, loss: 0.16780927777290344 2023-01-23 09:20:48.101326: step: 702/1545, loss: 0.10432460904121399 2023-01-23 09:20:49.038015: step: 704/1545, loss: 0.15738093852996826 2023-01-23 09:20:49.983822: step: 706/1545, loss: 0.1403452754020691 2023-01-23 09:20:50.867146: step: 708/1545, loss: 0.267062783241272 2023-01-23 09:20:51.718608: step: 710/1545, loss: 0.21009564399719238 2023-01-23 09:20:52.602366: step: 712/1545, loss: 0.9455676674842834 2023-01-23 09:20:53.472010: step: 714/1545, loss: 0.2633027732372284 2023-01-23 09:20:54.410810: step: 716/1545, loss: 0.46359196305274963 2023-01-23 09:20:55.294860: step: 718/1545, loss: 0.04287852346897125 2023-01-23 09:20:56.184212: step: 720/1545, loss: 0.6044282913208008 2023-01-23 09:20:57.101250: step: 722/1545, loss: 0.11551183462142944 2023-01-23 09:20:57.946488: step: 724/1545, loss: 0.19096724689006805 2023-01-23 09:20:58.809201: step: 726/1545, loss: 0.372304767370224 2023-01-23 09:20:59.683513: step: 728/1545, loss: 0.1647479236125946 2023-01-23 09:21:00.558191: step: 730/1545, loss: 0.3073461651802063 2023-01-23 09:21:01.478830: step: 732/1545, loss: 0.5946463346481323 2023-01-23 09:21:02.366022: step: 734/1545, loss: 0.059177152812480927 2023-01-23 09:21:03.262826: step: 736/1545, loss: 0.10912037640810013 2023-01-23 09:21:04.131861: step: 738/1545, loss: 0.18778161704540253 2023-01-23 09:21:04.998261: step: 740/1545, loss: 0.1586310714483261 2023-01-23 09:21:05.895683: step: 742/1545, loss: 0.10788623243570328 2023-01-23 09:21:06.790727: step: 744/1545, loss: 0.30845463275909424 2023-01-23 09:21:07.698353: step: 746/1545, loss: 0.03475823998451233 2023-01-23 09:21:08.553265: step: 748/1545, loss: 0.22700920701026917 2023-01-23 09:21:09.465357: step: 750/1545, loss: 0.07149609178304672 2023-01-23 09:21:10.324906: step: 752/1545, loss: 0.5307685136795044 2023-01-23 09:21:11.213198: step: 754/1545, loss: 0.06599247455596924 2023-01-23 09:21:12.097321: step: 756/1545, loss: 0.05401204526424408 2023-01-23 09:21:12.994678: step: 758/1545, loss: 0.12547451257705688 2023-01-23 09:21:13.889885: step: 760/1545, loss: 0.2566615343093872 2023-01-23 09:21:14.784807: step: 762/1545, loss: 0.08079693466424942 2023-01-23 09:21:15.675143: step: 764/1545, loss: 0.07991024106740952 2023-01-23 09:21:16.570900: step: 766/1545, loss: 0.19938872754573822 2023-01-23 09:21:17.474130: step: 768/1545, loss: 0.43854209780693054 2023-01-23 09:21:18.351246: step: 770/1545, loss: 0.25147852301597595 2023-01-23 09:21:19.232966: step: 772/1545, loss: 0.6658242344856262 2023-01-23 09:21:20.094685: step: 774/1545, loss: 0.2061169445514679 2023-01-23 09:21:20.982122: step: 776/1545, loss: 0.25458940863609314 2023-01-23 09:21:21.851717: step: 778/1545, loss: 0.24859371781349182 2023-01-23 09:21:22.763068: step: 780/1545, loss: 0.24125055968761444 2023-01-23 09:21:23.679463: step: 782/1545, loss: 0.038110751658678055 2023-01-23 09:21:24.557647: step: 784/1545, loss: 0.17495065927505493 2023-01-23 09:21:25.484597: step: 786/1545, loss: 0.7548238039016724 2023-01-23 09:21:26.357919: step: 788/1545, loss: 0.24076759815216064 2023-01-23 09:21:27.248271: step: 790/1545, loss: 0.38595592975616455 2023-01-23 09:21:28.126040: step: 792/1545, loss: 0.1296469122171402 2023-01-23 09:21:29.039366: step: 794/1545, loss: 0.17394199967384338 2023-01-23 09:21:29.898477: step: 796/1545, loss: 0.2380363792181015 2023-01-23 09:21:30.805528: step: 798/1545, loss: 0.2701243758201599 2023-01-23 09:21:31.666111: step: 800/1545, loss: 0.4953869879245758 2023-01-23 09:21:32.572864: step: 802/1545, loss: 0.04962087795138359 2023-01-23 09:21:33.435249: step: 804/1545, loss: 0.21278567612171173 2023-01-23 09:21:34.330536: step: 806/1545, loss: 0.2915862202644348 2023-01-23 09:21:35.256726: step: 808/1545, loss: 0.20487956702709198 2023-01-23 09:21:36.107737: step: 810/1545, loss: 0.39474472403526306 2023-01-23 09:21:36.982969: step: 812/1545, loss: 0.1807134598493576 2023-01-23 09:21:37.877242: step: 814/1545, loss: 0.10636457800865173 2023-01-23 09:21:38.747952: step: 816/1545, loss: 0.8430641293525696 2023-01-23 09:21:39.653852: step: 818/1545, loss: 0.2872612476348877 2023-01-23 09:21:40.544689: step: 820/1545, loss: 0.1381978541612625 2023-01-23 09:21:41.425787: step: 822/1545, loss: 0.40964943170547485 2023-01-23 09:21:42.320608: step: 824/1545, loss: 0.029171224683523178 2023-01-23 09:21:43.170840: step: 826/1545, loss: 0.1757713258266449 2023-01-23 09:21:44.068570: step: 828/1545, loss: 0.5029629468917847 2023-01-23 09:21:44.943803: step: 830/1545, loss: 0.3208688795566559 2023-01-23 09:21:45.858599: step: 832/1545, loss: 0.18434160947799683 2023-01-23 09:21:46.731186: step: 834/1545, loss: 0.2970764935016632 2023-01-23 09:21:47.628220: step: 836/1545, loss: 2.1108622550964355 2023-01-23 09:21:48.550119: step: 838/1545, loss: 0.11624883860349655 2023-01-23 09:21:49.437835: step: 840/1545, loss: 0.1763991415500641 2023-01-23 09:21:50.342758: step: 842/1545, loss: 0.2731495499610901 2023-01-23 09:21:51.249200: step: 844/1545, loss: 0.3398609161376953 2023-01-23 09:21:52.110763: step: 846/1545, loss: 0.14306002855300903 2023-01-23 09:21:52.981925: step: 848/1545, loss: 0.2682810425758362 2023-01-23 09:21:53.866515: step: 850/1545, loss: 0.034507960081100464 2023-01-23 09:21:54.764839: step: 852/1545, loss: 0.31559064984321594 2023-01-23 09:21:55.770159: step: 854/1545, loss: 0.6111562252044678 2023-01-23 09:21:56.677665: step: 856/1545, loss: 0.2744770348072052 2023-01-23 09:21:57.555981: step: 858/1545, loss: 0.03480809926986694 2023-01-23 09:21:58.533858: step: 860/1545, loss: 0.26828160881996155 2023-01-23 09:21:59.390004: step: 862/1545, loss: 0.2788515090942383 2023-01-23 09:22:00.287727: step: 864/1545, loss: 0.8515164852142334 2023-01-23 09:22:01.177240: step: 866/1545, loss: 0.11455120891332626 2023-01-23 09:22:02.111721: step: 868/1545, loss: 0.15126246213912964 2023-01-23 09:22:02.979397: step: 870/1545, loss: 0.423806369304657 2023-01-23 09:22:03.847794: step: 872/1545, loss: 0.18982112407684326 2023-01-23 09:22:04.765949: step: 874/1545, loss: 0.3637125790119171 2023-01-23 09:22:05.600475: step: 876/1545, loss: 0.14486919343471527 2023-01-23 09:22:06.462786: step: 878/1545, loss: 0.12243432551622391 2023-01-23 09:22:07.350497: step: 880/1545, loss: 0.43301934003829956 2023-01-23 09:22:08.231819: step: 882/1545, loss: 0.14506295323371887 2023-01-23 09:22:09.115534: step: 884/1545, loss: 0.493637353181839 2023-01-23 09:22:10.030656: step: 886/1545, loss: 0.6758822202682495 2023-01-23 09:22:10.957536: step: 888/1545, loss: 0.3143945634365082 2023-01-23 09:22:11.843073: step: 890/1545, loss: 0.24148564040660858 2023-01-23 09:22:12.776012: step: 892/1545, loss: 0.14018313586711884 2023-01-23 09:22:13.617920: step: 894/1545, loss: 0.1404740810394287 2023-01-23 09:22:14.490542: step: 896/1545, loss: 0.07962705940008163 2023-01-23 09:22:15.395272: step: 898/1545, loss: 1.1002881526947021 2023-01-23 09:22:16.255645: step: 900/1545, loss: 1.0898066759109497 2023-01-23 09:22:17.175875: step: 902/1545, loss: 0.04929979145526886 2023-01-23 09:22:18.137858: step: 904/1545, loss: 0.42742592096328735 2023-01-23 09:22:19.028264: step: 906/1545, loss: 0.3602258861064911 2023-01-23 09:22:19.920754: step: 908/1545, loss: 0.23761622607707977 2023-01-23 09:22:20.824908: step: 910/1545, loss: 0.05764050409197807 2023-01-23 09:22:21.692402: step: 912/1545, loss: 0.14603549242019653 2023-01-23 09:22:22.602425: step: 914/1545, loss: 0.4741182327270508 2023-01-23 09:22:23.508842: step: 916/1545, loss: 0.12144406884908676 2023-01-23 09:22:24.410313: step: 918/1545, loss: 0.08065242320299149 2023-01-23 09:22:25.277062: step: 920/1545, loss: 0.04348285123705864 2023-01-23 09:22:26.188505: step: 922/1545, loss: 0.17655614018440247 2023-01-23 09:22:27.050337: step: 924/1545, loss: 0.16870816051959991 2023-01-23 09:22:28.040911: step: 926/1545, loss: 0.1726066768169403 2023-01-23 09:22:28.916404: step: 928/1545, loss: 0.07282774895429611 2023-01-23 09:22:29.852211: step: 930/1545, loss: 0.0736250951886177 2023-01-23 09:22:30.736069: step: 932/1545, loss: 0.15615548193454742 2023-01-23 09:22:31.573379: step: 934/1545, loss: 0.39513063430786133 2023-01-23 09:22:32.436579: step: 936/1545, loss: 0.467062771320343 2023-01-23 09:22:33.281287: step: 938/1545, loss: 0.011670081876218319 2023-01-23 09:22:34.165700: step: 940/1545, loss: 0.10388150811195374 2023-01-23 09:22:35.016149: step: 942/1545, loss: 0.2934090793132782 2023-01-23 09:22:35.874335: step: 944/1545, loss: 0.1674482822418213 2023-01-23 09:22:36.788464: step: 946/1545, loss: 0.325108140707016 2023-01-23 09:22:37.689209: step: 948/1545, loss: 0.009969351813197136 2023-01-23 09:22:38.553380: step: 950/1545, loss: 0.5155916810035706 2023-01-23 09:22:39.467618: step: 952/1545, loss: 0.10847121477127075 2023-01-23 09:22:40.380711: step: 954/1545, loss: 0.12262903153896332 2023-01-23 09:22:41.310666: step: 956/1545, loss: 0.19439852237701416 2023-01-23 09:22:42.160888: step: 958/1545, loss: 0.08882608264684677 2023-01-23 09:22:43.054156: step: 960/1545, loss: 0.05461302399635315 2023-01-23 09:22:43.919355: step: 962/1545, loss: 0.22895659506320953 2023-01-23 09:22:44.763457: step: 964/1545, loss: 0.1080237627029419 2023-01-23 09:22:45.629998: step: 966/1545, loss: 0.3730701208114624 2023-01-23 09:22:46.525949: step: 968/1545, loss: 0.088625967502594 2023-01-23 09:22:47.396959: step: 970/1545, loss: 0.1729268878698349 2023-01-23 09:22:48.268934: step: 972/1545, loss: 0.4781000316143036 2023-01-23 09:22:49.117936: step: 974/1545, loss: 0.9761648774147034 2023-01-23 09:22:50.013721: step: 976/1545, loss: 0.26290181279182434 2023-01-23 09:22:50.923975: step: 978/1545, loss: 0.46136194467544556 2023-01-23 09:22:51.823038: step: 980/1545, loss: 0.2980634868144989 2023-01-23 09:22:52.732045: step: 982/1545, loss: 0.0812329351902008 2023-01-23 09:22:53.628585: step: 984/1545, loss: 0.21797391772270203 2023-01-23 09:22:54.507476: step: 986/1545, loss: 0.1333567351102829 2023-01-23 09:22:55.366868: step: 988/1545, loss: 0.21515195071697235 2023-01-23 09:22:56.222066: step: 990/1545, loss: 0.21690985560417175 2023-01-23 09:22:57.110497: step: 992/1545, loss: 0.7373893857002258 2023-01-23 09:22:57.980513: step: 994/1545, loss: 0.06529528647661209 2023-01-23 09:22:58.861989: step: 996/1545, loss: 0.1552785187959671 2023-01-23 09:22:59.753711: step: 998/1545, loss: 0.19696231186389923 2023-01-23 09:23:00.631066: step: 1000/1545, loss: 0.24281945824623108 2023-01-23 09:23:01.493520: step: 1002/1545, loss: 0.0512617789208889 2023-01-23 09:23:02.359371: step: 1004/1545, loss: 0.28936854004859924 2023-01-23 09:23:03.286255: step: 1006/1545, loss: 0.2782406508922577 2023-01-23 09:23:04.158980: step: 1008/1545, loss: 0.39869198203086853 2023-01-23 09:23:05.038047: step: 1010/1545, loss: 0.2817986309528351 2023-01-23 09:23:05.956432: step: 1012/1545, loss: 0.03614528477191925 2023-01-23 09:23:06.836331: step: 1014/1545, loss: 0.20912322402000427 2023-01-23 09:23:07.689451: step: 1016/1545, loss: 0.2026079297065735 2023-01-23 09:23:08.540349: step: 1018/1545, loss: 1.1688597202301025 2023-01-23 09:23:09.393005: step: 1020/1545, loss: 0.3547900915145874 2023-01-23 09:23:10.323306: step: 1022/1545, loss: 0.1142640933394432 2023-01-23 09:23:11.174705: step: 1024/1545, loss: 0.24467268586158752 2023-01-23 09:23:12.053915: step: 1026/1545, loss: 0.3208484947681427 2023-01-23 09:23:12.907377: step: 1028/1545, loss: 0.051884349435567856 2023-01-23 09:23:13.838254: step: 1030/1545, loss: 0.145600363612175 2023-01-23 09:23:14.723645: step: 1032/1545, loss: 0.3968297839164734 2023-01-23 09:23:15.615722: step: 1034/1545, loss: 0.14485381543636322 2023-01-23 09:23:16.487144: step: 1036/1545, loss: 0.15167342126369476 2023-01-23 09:23:17.366469: step: 1038/1545, loss: 0.08187258243560791 2023-01-23 09:23:18.274910: step: 1040/1545, loss: 0.1815337836742401 2023-01-23 09:23:19.173168: step: 1042/1545, loss: 0.2009604424238205 2023-01-23 09:23:20.215537: step: 1044/1545, loss: 0.11590059846639633 2023-01-23 09:23:21.183669: step: 1046/1545, loss: 0.2832444906234741 2023-01-23 09:23:22.173743: step: 1048/1545, loss: 0.06013726443052292 2023-01-23 09:23:23.028479: step: 1050/1545, loss: 0.07994534075260162 2023-01-23 09:23:23.890723: step: 1052/1545, loss: 0.10755712538957596 2023-01-23 09:23:24.797668: step: 1054/1545, loss: 0.1902315318584442 2023-01-23 09:23:25.664611: step: 1056/1545, loss: 0.017733871936798096 2023-01-23 09:23:26.509306: step: 1058/1545, loss: 0.365112841129303 2023-01-23 09:23:27.456820: step: 1060/1545, loss: 0.3453044891357422 2023-01-23 09:23:28.351737: step: 1062/1545, loss: 0.23311355710029602 2023-01-23 09:23:29.244508: step: 1064/1545, loss: 0.04392494261264801 2023-01-23 09:23:30.154270: step: 1066/1545, loss: 0.28060927987098694 2023-01-23 09:23:31.006772: step: 1068/1545, loss: 1.7696040868759155 2023-01-23 09:23:31.912349: step: 1070/1545, loss: 0.097067691385746 2023-01-23 09:23:32.771391: step: 1072/1545, loss: 0.022261913865804672 2023-01-23 09:23:33.668110: step: 1074/1545, loss: 0.3305610120296478 2023-01-23 09:23:34.592178: step: 1076/1545, loss: 0.16459688544273376 2023-01-23 09:23:35.504010: step: 1078/1545, loss: 0.1543467789888382 2023-01-23 09:23:36.386435: step: 1080/1545, loss: 0.3757169246673584 2023-01-23 09:23:37.276461: step: 1082/1545, loss: 0.1714969277381897 2023-01-23 09:23:38.163785: step: 1084/1545, loss: 0.4722357392311096 2023-01-23 09:23:38.993467: step: 1086/1545, loss: 0.12149813026189804 2023-01-23 09:23:39.918680: step: 1088/1545, loss: 0.31050920486450195 2023-01-23 09:23:40.800983: step: 1090/1545, loss: 0.34925422072410583 2023-01-23 09:23:41.691988: step: 1092/1545, loss: 0.03781769424676895 2023-01-23 09:23:42.664011: step: 1094/1545, loss: 0.8445343971252441 2023-01-23 09:23:43.639717: step: 1096/1545, loss: 0.008070419542491436 2023-01-23 09:23:44.602616: step: 1098/1545, loss: 0.765707790851593 2023-01-23 09:23:45.511866: step: 1100/1545, loss: 0.15956541895866394 2023-01-23 09:23:46.428373: step: 1102/1545, loss: 0.10802474617958069 2023-01-23 09:23:47.281337: step: 1104/1545, loss: 0.3138367533683777 2023-01-23 09:23:48.114858: step: 1106/1545, loss: 0.11298195272684097 2023-01-23 09:23:49.030872: step: 1108/1545, loss: 0.1892750859260559 2023-01-23 09:23:49.933274: step: 1110/1545, loss: 0.27507463097572327 2023-01-23 09:23:50.783740: step: 1112/1545, loss: 0.24188144505023956 2023-01-23 09:23:51.701402: step: 1114/1545, loss: 0.13830429315567017 2023-01-23 09:23:52.581153: step: 1116/1545, loss: 2.236804485321045 2023-01-23 09:23:53.465208: step: 1118/1545, loss: 0.2730568051338196 2023-01-23 09:23:54.378260: step: 1120/1545, loss: 0.9331108331680298 2023-01-23 09:23:55.229550: step: 1122/1545, loss: 0.16396184265613556 2023-01-23 09:23:56.100615: step: 1124/1545, loss: 0.0913836881518364 2023-01-23 09:23:57.000807: step: 1126/1545, loss: 0.5759335160255432 2023-01-23 09:23:57.874163: step: 1128/1545, loss: 0.05498358607292175 2023-01-23 09:23:58.722160: step: 1130/1545, loss: 0.2675064206123352 2023-01-23 09:23:59.611747: step: 1132/1545, loss: 0.25821220874786377 2023-01-23 09:24:00.484079: step: 1134/1545, loss: 0.2234259694814682 2023-01-23 09:24:01.308127: step: 1136/1545, loss: 0.48696020245552063 2023-01-23 09:24:02.202511: step: 1138/1545, loss: 0.14437216520309448 2023-01-23 09:24:03.113793: step: 1140/1545, loss: 0.6292654871940613 2023-01-23 09:24:04.005032: step: 1142/1545, loss: 0.23877383768558502 2023-01-23 09:24:04.870868: step: 1144/1545, loss: 0.2891310155391693 2023-01-23 09:24:05.758977: step: 1146/1545, loss: 0.08684385567903519 2023-01-23 09:24:06.652186: step: 1148/1545, loss: 0.3610924482345581 2023-01-23 09:24:07.524124: step: 1150/1545, loss: 0.13807573914527893 2023-01-23 09:24:08.414224: step: 1152/1545, loss: 0.5871561169624329 2023-01-23 09:24:09.296478: step: 1154/1545, loss: 0.20667244493961334 2023-01-23 09:24:10.168523: step: 1156/1545, loss: 0.3086998760700226 2023-01-23 09:24:11.017718: step: 1158/1545, loss: 0.0899287536740303 2023-01-23 09:24:11.902589: step: 1160/1545, loss: 0.12869474291801453 2023-01-23 09:24:12.765554: step: 1162/1545, loss: 0.3696833848953247 2023-01-23 09:24:13.620068: step: 1164/1545, loss: 0.3431278467178345 2023-01-23 09:24:14.546033: step: 1166/1545, loss: 0.32930657267570496 2023-01-23 09:24:15.420738: step: 1168/1545, loss: 0.02790532074868679 2023-01-23 09:24:16.335581: step: 1170/1545, loss: 0.3893347382545471 2023-01-23 09:24:17.207596: step: 1172/1545, loss: 0.12988519668579102 2023-01-23 09:24:18.175521: step: 1174/1545, loss: 0.18921628594398499 2023-01-23 09:24:19.055423: step: 1176/1545, loss: 0.04087434709072113 2023-01-23 09:24:19.950186: step: 1178/1545, loss: 0.40256741642951965 2023-01-23 09:24:20.826401: step: 1180/1545, loss: 0.3069118559360504 2023-01-23 09:24:21.713687: step: 1182/1545, loss: 0.7682957649230957 2023-01-23 09:24:22.611397: step: 1184/1545, loss: 0.04315758869051933 2023-01-23 09:24:23.486947: step: 1186/1545, loss: 0.3200272023677826 2023-01-23 09:24:24.423523: step: 1188/1545, loss: 0.009816973470151424 2023-01-23 09:24:25.335747: step: 1190/1545, loss: 0.5818014740943909 2023-01-23 09:24:26.223737: step: 1192/1545, loss: 0.0871647447347641 2023-01-23 09:24:27.211588: step: 1194/1545, loss: 0.0051394179463386536 2023-01-23 09:24:28.095753: step: 1196/1545, loss: 0.1651100069284439 2023-01-23 09:24:28.972978: step: 1198/1545, loss: 0.14556190371513367 2023-01-23 09:24:29.893814: step: 1200/1545, loss: 1.65781569480896 2023-01-23 09:24:30.797867: step: 1202/1545, loss: 0.1860218495130539 2023-01-23 09:24:31.746488: step: 1204/1545, loss: 0.7819387316703796 2023-01-23 09:24:32.612728: step: 1206/1545, loss: 0.22839295864105225 2023-01-23 09:24:33.522439: step: 1208/1545, loss: 0.06890344619750977 2023-01-23 09:24:34.377037: step: 1210/1545, loss: 0.36069291830062866 2023-01-23 09:24:35.258418: step: 1212/1545, loss: 0.04539823159575462 2023-01-23 09:24:36.182397: step: 1214/1545, loss: 0.051090359687805176 2023-01-23 09:24:37.059013: step: 1216/1545, loss: 0.4123610258102417 2023-01-23 09:24:37.980124: step: 1218/1545, loss: 5.45521354675293 2023-01-23 09:24:38.948031: step: 1220/1545, loss: 0.14484436810016632 2023-01-23 09:24:39.830185: step: 1222/1545, loss: 0.31100738048553467 2023-01-23 09:24:40.709415: step: 1224/1545, loss: 0.4411674737930298 2023-01-23 09:24:41.605745: step: 1226/1545, loss: 0.6024028062820435 2023-01-23 09:24:42.520350: step: 1228/1545, loss: 0.14156226813793182 2023-01-23 09:24:43.369713: step: 1230/1545, loss: 6.413145065307617 2023-01-23 09:24:44.228188: step: 1232/1545, loss: 0.10292511433362961 2023-01-23 09:24:45.120441: step: 1234/1545, loss: 0.22414827346801758 2023-01-23 09:24:45.976348: step: 1236/1545, loss: 0.11492066830396652 2023-01-23 09:24:46.850067: step: 1238/1545, loss: 0.21603788435459137 2023-01-23 09:24:47.757743: step: 1240/1545, loss: 0.08755086362361908 2023-01-23 09:24:48.630728: step: 1242/1545, loss: 0.19410008192062378 2023-01-23 09:24:49.489472: step: 1244/1545, loss: 0.4724108874797821 2023-01-23 09:24:50.378016: step: 1246/1545, loss: 0.12962941825389862 2023-01-23 09:24:51.281478: step: 1248/1545, loss: 0.08298275619745255 2023-01-23 09:24:52.203330: step: 1250/1545, loss: 0.30687960982322693 2023-01-23 09:24:53.103378: step: 1252/1545, loss: 0.13875697553157806 2023-01-23 09:24:53.963887: step: 1254/1545, loss: 0.7215366363525391 2023-01-23 09:24:54.881923: step: 1256/1545, loss: 1.1639620065689087 2023-01-23 09:24:55.806887: step: 1258/1545, loss: 0.15795224905014038 2023-01-23 09:24:56.715501: step: 1260/1545, loss: 0.156381756067276 2023-01-23 09:24:57.594373: step: 1262/1545, loss: 0.10292984545230865 2023-01-23 09:24:58.520935: step: 1264/1545, loss: 0.31291061639785767 2023-01-23 09:24:59.445207: step: 1266/1545, loss: 0.27058976888656616 2023-01-23 09:25:00.376166: step: 1268/1545, loss: 0.6834228038787842 2023-01-23 09:25:01.271461: step: 1270/1545, loss: 0.06222428381443024 2023-01-23 09:25:02.186378: step: 1272/1545, loss: 0.21029584109783173 2023-01-23 09:25:03.064532: step: 1274/1545, loss: 0.27938634157180786 2023-01-23 09:25:03.936173: step: 1276/1545, loss: 0.5665014386177063 2023-01-23 09:25:04.788521: step: 1278/1545, loss: 0.040647100657224655 2023-01-23 09:25:05.781228: step: 1280/1545, loss: 0.19199468195438385 2023-01-23 09:25:06.649047: step: 1282/1545, loss: 0.10753127187490463 2023-01-23 09:25:07.567739: step: 1284/1545, loss: 0.6592968106269836 2023-01-23 09:25:08.484274: step: 1286/1545, loss: 0.15418338775634766 2023-01-23 09:25:09.347245: step: 1288/1545, loss: 0.18022555112838745 2023-01-23 09:25:10.270505: step: 1290/1545, loss: 0.2443779706954956 2023-01-23 09:25:11.164255: step: 1292/1545, loss: 0.49659931659698486 2023-01-23 09:25:12.174217: step: 1294/1545, loss: 0.4929041564464569 2023-01-23 09:25:13.073895: step: 1296/1545, loss: 0.21449880301952362 2023-01-23 09:25:13.971215: step: 1298/1545, loss: 0.8397761583328247 2023-01-23 09:25:14.833405: step: 1300/1545, loss: 0.11996248364448547 2023-01-23 09:25:15.735289: step: 1302/1545, loss: 0.05382118001580238 2023-01-23 09:25:16.605133: step: 1304/1545, loss: 0.11812083423137665 2023-01-23 09:25:17.518161: step: 1306/1545, loss: 0.2969096302986145 2023-01-23 09:25:18.421385: step: 1308/1545, loss: 0.23014792799949646 2023-01-23 09:25:19.309183: step: 1310/1545, loss: 0.7169567346572876 2023-01-23 09:25:20.212785: step: 1312/1545, loss: 0.44780242443084717 2023-01-23 09:25:21.126517: step: 1314/1545, loss: 0.17680665850639343 2023-01-23 09:25:22.045109: step: 1316/1545, loss: 0.3338886797428131 2023-01-23 09:25:22.931827: step: 1318/1545, loss: 0.12573525309562683 2023-01-23 09:25:23.788746: step: 1320/1545, loss: 0.12423907965421677 2023-01-23 09:25:24.653805: step: 1322/1545, loss: 0.315727174282074 2023-01-23 09:25:25.536795: step: 1324/1545, loss: 1.4902631044387817 2023-01-23 09:25:26.425766: step: 1326/1545, loss: 0.12416237592697144 2023-01-23 09:25:27.274441: step: 1328/1545, loss: 0.17278669774532318 2023-01-23 09:25:28.135443: step: 1330/1545, loss: 0.04781598597764969 2023-01-23 09:25:29.078136: step: 1332/1545, loss: 0.2934792637825012 2023-01-23 09:25:29.979048: step: 1334/1545, loss: 0.3141665458679199 2023-01-23 09:25:30.860704: step: 1336/1545, loss: 0.2120354324579239 2023-01-23 09:25:31.774469: step: 1338/1545, loss: 0.17977136373519897 2023-01-23 09:25:32.650174: step: 1340/1545, loss: 0.15205919742584229 2023-01-23 09:25:33.526822: step: 1342/1545, loss: 0.10099346935749054 2023-01-23 09:25:34.413212: step: 1344/1545, loss: 0.23171283304691315 2023-01-23 09:25:35.364501: step: 1346/1545, loss: 0.10225928574800491 2023-01-23 09:25:36.288300: step: 1348/1545, loss: 0.07675014436244965 2023-01-23 09:25:37.165304: step: 1350/1545, loss: 0.3756645917892456 2023-01-23 09:25:38.092871: step: 1352/1545, loss: 0.7917506098747253 2023-01-23 09:25:38.989535: step: 1354/1545, loss: 0.1931735724210739 2023-01-23 09:25:39.859206: step: 1356/1545, loss: 0.05957669019699097 2023-01-23 09:25:40.722994: step: 1358/1545, loss: 0.1716451793909073 2023-01-23 09:25:41.625972: step: 1360/1545, loss: 1.7945237159729004 2023-01-23 09:25:42.578301: step: 1362/1545, loss: 0.09605691581964493 2023-01-23 09:25:43.529429: step: 1364/1545, loss: 0.6036599278450012 2023-01-23 09:25:44.370533: step: 1366/1545, loss: 0.18133537471294403 2023-01-23 09:25:45.258322: step: 1368/1545, loss: 0.36334696412086487 2023-01-23 09:25:46.114061: step: 1370/1545, loss: 0.3052136301994324 2023-01-23 09:25:47.044997: step: 1372/1545, loss: 0.13405679166316986 2023-01-23 09:25:47.938654: step: 1374/1545, loss: 0.015107745304703712 2023-01-23 09:25:48.837952: step: 1376/1545, loss: 0.2574778199195862 2023-01-23 09:25:49.712414: step: 1378/1545, loss: 0.2638324201107025 2023-01-23 09:25:50.619112: step: 1380/1545, loss: 0.4744669497013092 2023-01-23 09:25:51.475304: step: 1382/1545, loss: 0.29473167657852173 2023-01-23 09:25:52.365774: step: 1384/1545, loss: 0.07049079239368439 2023-01-23 09:25:53.234650: step: 1386/1545, loss: 0.831699013710022 2023-01-23 09:25:54.117454: step: 1388/1545, loss: 0.2400115579366684 2023-01-23 09:25:55.040901: step: 1390/1545, loss: 0.38839223980903625 2023-01-23 09:25:55.924784: step: 1392/1545, loss: 0.2426988035440445 2023-01-23 09:25:56.809077: step: 1394/1545, loss: 0.3581274747848511 2023-01-23 09:25:57.689428: step: 1396/1545, loss: 0.23517951369285583 2023-01-23 09:25:58.642324: step: 1398/1545, loss: 0.09869841486215591 2023-01-23 09:25:59.514800: step: 1400/1545, loss: 0.6072993278503418 2023-01-23 09:26:00.413275: step: 1402/1545, loss: 0.18751317262649536 2023-01-23 09:26:01.330998: step: 1404/1545, loss: 0.223279669880867 2023-01-23 09:26:02.210503: step: 1406/1545, loss: 0.3341796100139618 2023-01-23 09:26:03.125640: step: 1408/1545, loss: 0.3991125822067261 2023-01-23 09:26:04.066573: step: 1410/1545, loss: 0.7588622570037842 2023-01-23 09:26:04.927087: step: 1412/1545, loss: 0.2272554636001587 2023-01-23 09:26:05.869241: step: 1414/1545, loss: 0.12237764894962311 2023-01-23 09:26:06.776589: step: 1416/1545, loss: 0.1283463090658188 2023-01-23 09:26:07.725729: step: 1418/1545, loss: 0.18166230618953705 2023-01-23 09:26:08.623571: step: 1420/1545, loss: 0.5442965030670166 2023-01-23 09:26:09.484018: step: 1422/1545, loss: 0.11282326281070709 2023-01-23 09:26:10.397615: step: 1424/1545, loss: 0.23582415282726288 2023-01-23 09:26:11.303307: step: 1426/1545, loss: 0.16297771036624908 2023-01-23 09:26:12.162276: step: 1428/1545, loss: 0.20227862894535065 2023-01-23 09:26:13.040758: step: 1430/1545, loss: 0.2876380980014801 2023-01-23 09:26:13.884080: step: 1432/1545, loss: 0.07766098529100418 2023-01-23 09:26:14.749748: step: 1434/1545, loss: 0.04492401331663132 2023-01-23 09:26:15.608678: step: 1436/1545, loss: 0.1059352308511734 2023-01-23 09:26:16.516363: step: 1438/1545, loss: 0.123325876891613 2023-01-23 09:26:17.407873: step: 1440/1545, loss: 0.29711368680000305 2023-01-23 09:26:18.294847: step: 1442/1545, loss: 0.09197649359703064 2023-01-23 09:26:19.231206: step: 1444/1545, loss: 0.3047095239162445 2023-01-23 09:26:20.157093: step: 1446/1545, loss: 0.9531908631324768 2023-01-23 09:26:21.070564: step: 1448/1545, loss: 0.16461291909217834 2023-01-23 09:26:21.951057: step: 1450/1545, loss: 1.660630226135254 2023-01-23 09:26:22.832433: step: 1452/1545, loss: 0.18686872720718384 2023-01-23 09:26:23.700063: step: 1454/1545, loss: 0.36468249559402466 2023-01-23 09:26:24.549774: step: 1456/1545, loss: 0.3978292644023895 2023-01-23 09:26:25.421116: step: 1458/1545, loss: 0.043541304767131805 2023-01-23 09:26:26.313940: step: 1460/1545, loss: 0.024652699008584023 2023-01-23 09:26:27.189140: step: 1462/1545, loss: 0.041709136217832565 2023-01-23 09:26:28.064285: step: 1464/1545, loss: 0.25206801295280457 2023-01-23 09:26:28.924703: step: 1466/1545, loss: 0.7803692817687988 2023-01-23 09:26:29.840497: step: 1468/1545, loss: 0.3664976954460144 2023-01-23 09:26:30.759255: step: 1470/1545, loss: 0.073951356112957 2023-01-23 09:26:31.595285: step: 1472/1545, loss: 0.34525415301322937 2023-01-23 09:26:32.506535: step: 1474/1545, loss: 0.05159476026892662 2023-01-23 09:26:33.408939: step: 1476/1545, loss: 0.15686006844043732 2023-01-23 09:26:34.292935: step: 1478/1545, loss: 0.11306621134281158 2023-01-23 09:26:35.189657: step: 1480/1545, loss: 0.5035045742988586 2023-01-23 09:26:36.110185: step: 1482/1545, loss: 0.033021703362464905 2023-01-23 09:26:36.992022: step: 1484/1545, loss: 0.27012550830841064 2023-01-23 09:26:37.889422: step: 1486/1545, loss: 0.4269635081291199 2023-01-23 09:26:38.787987: step: 1488/1545, loss: 0.8025995492935181 2023-01-23 09:26:39.660128: step: 1490/1545, loss: 0.1145225390791893 2023-01-23 09:26:40.557658: step: 1492/1545, loss: 0.5701571106910706 2023-01-23 09:26:41.507735: step: 1494/1545, loss: 0.7969382405281067 2023-01-23 09:26:42.379949: step: 1496/1545, loss: 0.06886592507362366 2023-01-23 09:26:43.241170: step: 1498/1545, loss: 0.2585694193840027 2023-01-23 09:26:44.118483: step: 1500/1545, loss: 0.05716216564178467 2023-01-23 09:26:44.985231: step: 1502/1545, loss: 0.43626919388771057 2023-01-23 09:26:45.896555: step: 1504/1545, loss: 0.29359304904937744 2023-01-23 09:26:46.820508: step: 1506/1545, loss: 0.311320424079895 2023-01-23 09:26:47.660950: step: 1508/1545, loss: 0.15151354670524597 2023-01-23 09:26:48.520442: step: 1510/1545, loss: 0.3957826793193817 2023-01-23 09:26:49.524427: step: 1512/1545, loss: 0.16735075414180756 2023-01-23 09:26:50.428598: step: 1514/1545, loss: 0.23348188400268555 2023-01-23 09:26:51.292930: step: 1516/1545, loss: 0.4927249550819397 2023-01-23 09:26:52.168188: step: 1518/1545, loss: 0.1644173115491867 2023-01-23 09:26:53.010435: step: 1520/1545, loss: 0.2761913239955902 2023-01-23 09:26:53.869845: step: 1522/1545, loss: 0.5522730946540833 2023-01-23 09:26:54.749768: step: 1524/1545, loss: 0.09516961872577667 2023-01-23 09:26:55.712595: step: 1526/1545, loss: 0.3884410262107849 2023-01-23 09:26:56.633015: step: 1528/1545, loss: 0.0719079002737999 2023-01-23 09:26:57.494352: step: 1530/1545, loss: 0.5489869117736816 2023-01-23 09:26:58.357332: step: 1532/1545, loss: 0.15648333728313446 2023-01-23 09:26:59.242984: step: 1534/1545, loss: 0.4582580626010895 2023-01-23 09:27:00.145324: step: 1536/1545, loss: 0.369819700717926 2023-01-23 09:27:01.017810: step: 1538/1545, loss: 0.17835430800914764 2023-01-23 09:27:01.898481: step: 1540/1545, loss: 2.3379344940185547 2023-01-23 09:27:02.717201: step: 1542/1545, loss: 0.39667409658432007 2023-01-23 09:27:03.623903: step: 1544/1545, loss: 0.13655713200569153 2023-01-23 09:27:04.488033: step: 1546/1545, loss: 0.09663831442594528 2023-01-23 09:27:05.380815: step: 1548/1545, loss: 0.22934897243976593 2023-01-23 09:27:06.248040: step: 1550/1545, loss: 0.22292964160442352 2023-01-23 09:27:07.126416: step: 1552/1545, loss: 0.44014331698417664 2023-01-23 09:27:08.046329: step: 1554/1545, loss: 0.08457792550325394 2023-01-23 09:27:08.923205: step: 1556/1545, loss: 0.6196712851524353 2023-01-23 09:27:09.754200: step: 1558/1545, loss: 0.35964158177375793 2023-01-23 09:27:10.631850: step: 1560/1545, loss: 0.07584228366613388 2023-01-23 09:27:11.483960: step: 1562/1545, loss: 1.49190354347229 2023-01-23 09:27:12.394273: step: 1564/1545, loss: 0.1131456047296524 2023-01-23 09:27:13.274117: step: 1566/1545, loss: 0.2009011059999466 2023-01-23 09:27:14.121323: step: 1568/1545, loss: 0.10799933224916458 2023-01-23 09:27:15.021305: step: 1570/1545, loss: 0.26565712690353394 2023-01-23 09:27:15.892329: step: 1572/1545, loss: 0.24568641185760498 2023-01-23 09:27:16.745762: step: 1574/1545, loss: 0.13336554169654846 2023-01-23 09:27:17.645642: step: 1576/1545, loss: 0.05312513932585716 2023-01-23 09:27:18.505485: step: 1578/1545, loss: 0.144779771566391 2023-01-23 09:27:19.466051: step: 1580/1545, loss: 0.35941964387893677 2023-01-23 09:27:20.363273: step: 1582/1545, loss: 0.02346915192902088 2023-01-23 09:27:21.272815: step: 1584/1545, loss: 0.23650610446929932 2023-01-23 09:27:22.145498: step: 1586/1545, loss: 0.09045109897851944 2023-01-23 09:27:23.041846: step: 1588/1545, loss: 0.13224007189273834 2023-01-23 09:27:23.915486: step: 1590/1545, loss: 0.4277893602848053 2023-01-23 09:27:24.774092: step: 1592/1545, loss: 0.3890940845012665 2023-01-23 09:27:25.660442: step: 1594/1545, loss: 0.1235148087143898 2023-01-23 09:27:26.535488: step: 1596/1545, loss: 0.258074015378952 2023-01-23 09:27:27.455019: step: 1598/1545, loss: 0.05015483498573303 2023-01-23 09:27:28.349261: step: 1600/1545, loss: 0.9869722723960876 2023-01-23 09:27:29.191529: step: 1602/1545, loss: 0.28235188126564026 2023-01-23 09:27:30.080668: step: 1604/1545, loss: 0.15757688879966736 2023-01-23 09:27:30.993143: step: 1606/1545, loss: 0.10365618765354156 2023-01-23 09:27:31.899765: step: 1608/1545, loss: 0.029668709263205528 2023-01-23 09:27:32.839173: step: 1610/1545, loss: 0.09498624503612518 2023-01-23 09:27:33.790666: step: 1612/1545, loss: 1.089363932609558 2023-01-23 09:27:34.662794: step: 1614/1545, loss: 0.09522341936826706 2023-01-23 09:27:35.555907: step: 1616/1545, loss: 0.36526864767074585 2023-01-23 09:27:36.449054: step: 1618/1545, loss: 0.08040711283683777 2023-01-23 09:27:37.324414: step: 1620/1545, loss: 0.1055271178483963 2023-01-23 09:27:38.225637: step: 1622/1545, loss: 0.09242430329322815 2023-01-23 09:27:39.120779: step: 1624/1545, loss: 0.1857723444700241 2023-01-23 09:27:40.026174: step: 1626/1545, loss: 0.24230420589447021 2023-01-23 09:27:40.905879: step: 1628/1545, loss: 0.08236391842365265 2023-01-23 09:27:41.761889: step: 1630/1545, loss: 0.23886002600193024 2023-01-23 09:27:42.669259: step: 1632/1545, loss: 0.07280014455318451 2023-01-23 09:27:43.558282: step: 1634/1545, loss: 0.13819041848182678 2023-01-23 09:27:44.441958: step: 1636/1545, loss: 0.4988771080970764 2023-01-23 09:27:45.320252: step: 1638/1545, loss: 0.10557513684034348 2023-01-23 09:27:46.188334: step: 1640/1545, loss: 0.5512645244598389 2023-01-23 09:27:47.094937: step: 1642/1545, loss: 0.15223053097724915 2023-01-23 09:27:48.065832: step: 1644/1545, loss: 0.4941749572753906 2023-01-23 09:27:48.975784: step: 1646/1545, loss: 0.581170916557312 2023-01-23 09:27:49.881850: step: 1648/1545, loss: 0.10942372679710388 2023-01-23 09:27:50.729913: step: 1650/1545, loss: 0.22760549187660217 2023-01-23 09:27:51.626927: step: 1652/1545, loss: 0.8455329537391663 2023-01-23 09:27:52.528761: step: 1654/1545, loss: 0.3626834452152252 2023-01-23 09:27:53.412463: step: 1656/1545, loss: 0.7174060940742493 2023-01-23 09:27:54.279296: step: 1658/1545, loss: 0.17253170907497406 2023-01-23 09:27:55.165354: step: 1660/1545, loss: 0.23657342791557312 2023-01-23 09:27:56.086765: step: 1662/1545, loss: 0.38599035143852234 2023-01-23 09:27:56.990347: step: 1664/1545, loss: 0.3294515907764435 2023-01-23 09:27:57.830416: step: 1666/1545, loss: 0.16114574670791626 2023-01-23 09:27:58.760510: step: 1668/1545, loss: 0.18398723006248474 2023-01-23 09:27:59.630681: step: 1670/1545, loss: 0.10069724172353745 2023-01-23 09:28:00.565161: step: 1672/1545, loss: 0.1046617329120636 2023-01-23 09:28:01.454579: step: 1674/1545, loss: 0.10080517828464508 2023-01-23 09:28:02.344635: step: 1676/1545, loss: 1.0188997983932495 2023-01-23 09:28:03.269753: step: 1678/1545, loss: 0.1661248654127121 2023-01-23 09:28:04.123707: step: 1680/1545, loss: 0.1467106193304062 2023-01-23 09:28:05.025573: step: 1682/1545, loss: 0.21272312104701996 2023-01-23 09:28:05.912707: step: 1684/1545, loss: 0.2935137450695038 2023-01-23 09:28:06.801348: step: 1686/1545, loss: 0.14167964458465576 2023-01-23 09:28:07.729277: step: 1688/1545, loss: 0.11880733072757721 2023-01-23 09:28:08.617780: step: 1690/1545, loss: 0.11052766442298889 2023-01-23 09:28:09.472716: step: 1692/1545, loss: 0.2176465094089508 2023-01-23 09:28:10.465251: step: 1694/1545, loss: 0.774523913860321 2023-01-23 09:28:11.342293: step: 1696/1545, loss: 0.040187958627939224 2023-01-23 09:28:12.349645: step: 1698/1545, loss: 0.154363751411438 2023-01-23 09:28:13.237248: step: 1700/1545, loss: 0.09216596186161041 2023-01-23 09:28:14.093186: step: 1702/1545, loss: 0.09351345151662827 2023-01-23 09:28:15.034957: step: 1704/1545, loss: 0.7907295823097229 2023-01-23 09:28:15.883259: step: 1706/1545, loss: 0.24716216325759888 2023-01-23 09:28:16.793962: step: 1708/1545, loss: 0.6204774975776672 2023-01-23 09:28:17.655220: step: 1710/1545, loss: 0.34676048159599304 2023-01-23 09:28:18.522130: step: 1712/1545, loss: 0.1528121381998062 2023-01-23 09:28:19.373060: step: 1714/1545, loss: 0.4844621419906616 2023-01-23 09:28:20.265345: step: 1716/1545, loss: 0.30713364481925964 2023-01-23 09:28:21.151757: step: 1718/1545, loss: 0.1397143304347992 2023-01-23 09:28:22.013761: step: 1720/1545, loss: 0.08636561036109924 2023-01-23 09:28:22.927419: step: 1722/1545, loss: 0.4837630093097687 2023-01-23 09:28:23.805536: step: 1724/1545, loss: 0.04745065048336983 2023-01-23 09:28:24.663099: step: 1726/1545, loss: 0.1478525549173355 2023-01-23 09:28:25.506377: step: 1728/1545, loss: 0.19503754377365112 2023-01-23 09:28:26.443972: step: 1730/1545, loss: 0.083857960999012 2023-01-23 09:28:27.307489: step: 1732/1545, loss: 0.1522139310836792 2023-01-23 09:28:28.222233: step: 1734/1545, loss: 0.0986645296216011 2023-01-23 09:28:29.060916: step: 1736/1545, loss: 0.1738540232181549 2023-01-23 09:28:29.895012: step: 1738/1545, loss: 0.16605186462402344 2023-01-23 09:28:30.740819: step: 1740/1545, loss: 0.12272694706916809 2023-01-23 09:28:31.590685: step: 1742/1545, loss: 0.1766967475414276 2023-01-23 09:28:32.458155: step: 1744/1545, loss: 0.6182535290718079 2023-01-23 09:28:33.463285: step: 1746/1545, loss: 0.12957167625427246 2023-01-23 09:28:34.359428: step: 1748/1545, loss: 0.40923011302948 2023-01-23 09:28:35.228426: step: 1750/1545, loss: 0.012561098672449589 2023-01-23 09:28:36.111868: step: 1752/1545, loss: 0.5517724752426147 2023-01-23 09:28:36.974251: step: 1754/1545, loss: 4.745154857635498 2023-01-23 09:28:37.890295: step: 1756/1545, loss: 0.7900039553642273 2023-01-23 09:28:38.781534: step: 1758/1545, loss: 0.09224063158035278 2023-01-23 09:28:39.657545: step: 1760/1545, loss: 0.1993810087442398 2023-01-23 09:28:40.575590: step: 1762/1545, loss: 0.31566503643989563 2023-01-23 09:28:41.460475: step: 1764/1545, loss: 0.4170590937137604 2023-01-23 09:28:42.319121: step: 1766/1545, loss: 0.32485389709472656 2023-01-23 09:28:43.182309: step: 1768/1545, loss: 1.175197958946228 2023-01-23 09:28:44.089409: step: 1770/1545, loss: 0.2655772566795349 2023-01-23 09:28:44.955290: step: 1772/1545, loss: 0.196236714720726 2023-01-23 09:28:45.943747: step: 1774/1545, loss: 0.03593083843588829 2023-01-23 09:28:46.801149: step: 1776/1545, loss: 0.06908766180276871 2023-01-23 09:28:47.650178: step: 1778/1545, loss: 0.09357254207134247 2023-01-23 09:28:48.524765: step: 1780/1545, loss: 0.045362185686826706 2023-01-23 09:28:49.415618: step: 1782/1545, loss: 0.21664360165596008 2023-01-23 09:28:50.388991: step: 1784/1545, loss: 0.36093538999557495 2023-01-23 09:28:51.258037: step: 1786/1545, loss: 0.07889547944068909 2023-01-23 09:28:52.180085: step: 1788/1545, loss: 0.14045558869838715 2023-01-23 09:28:53.047314: step: 1790/1545, loss: 0.16579148173332214 2023-01-23 09:28:53.947442: step: 1792/1545, loss: 0.4531308114528656 2023-01-23 09:28:54.930786: step: 1794/1545, loss: 0.4593137502670288 2023-01-23 09:28:55.828603: step: 1796/1545, loss: 0.1051393449306488 2023-01-23 09:28:56.802174: step: 1798/1545, loss: 0.05527481809258461 2023-01-23 09:28:57.682200: step: 1800/1545, loss: 0.16119834780693054 2023-01-23 09:28:58.598125: step: 1802/1545, loss: 0.010470505803823471 2023-01-23 09:28:59.471140: step: 1804/1545, loss: 0.0402369350194931 2023-01-23 09:29:00.361360: step: 1806/1545, loss: 0.07824454456567764 2023-01-23 09:29:01.238467: step: 1808/1545, loss: 0.18816407024860382 2023-01-23 09:29:02.109843: step: 1810/1545, loss: 0.03351513668894768 2023-01-23 09:29:02.978153: step: 1812/1545, loss: 0.18195350468158722 2023-01-23 09:29:03.873562: step: 1814/1545, loss: 0.06762514263391495 2023-01-23 09:29:04.749671: step: 1816/1545, loss: 0.30872204899787903 2023-01-23 09:29:05.636464: step: 1818/1545, loss: 0.2492986023426056 2023-01-23 09:29:06.499373: step: 1820/1545, loss: 0.11969560384750366 2023-01-23 09:29:07.370419: step: 1822/1545, loss: 0.5633683800697327 2023-01-23 09:29:08.241976: step: 1824/1545, loss: 0.6338139772415161 2023-01-23 09:29:09.127607: step: 1826/1545, loss: 0.07070859521627426 2023-01-23 09:29:10.012554: step: 1828/1545, loss: 0.2797108590602875 2023-01-23 09:29:10.922633: step: 1830/1545, loss: 0.0537983700633049 2023-01-23 09:29:11.824166: step: 1832/1545, loss: 0.20486561954021454 2023-01-23 09:29:12.696453: step: 1834/1545, loss: 0.29013925790786743 2023-01-23 09:29:13.667680: step: 1836/1545, loss: 0.2629092037677765 2023-01-23 09:29:14.545768: step: 1838/1545, loss: 0.6615031957626343 2023-01-23 09:29:15.448018: step: 1840/1545, loss: 0.4904261529445648 2023-01-23 09:29:16.339767: step: 1842/1545, loss: 0.458401083946228 2023-01-23 09:29:17.260203: step: 1844/1545, loss: 0.0675802230834961 2023-01-23 09:29:18.162264: step: 1846/1545, loss: 0.27372655272483826 2023-01-23 09:29:19.055780: step: 1848/1545, loss: 0.11083004623651505 2023-01-23 09:29:19.936335: step: 1850/1545, loss: 0.4020179212093353 2023-01-23 09:29:20.879388: step: 1852/1545, loss: 0.22337645292282104 2023-01-23 09:29:21.756742: step: 1854/1545, loss: 0.48155611753463745 2023-01-23 09:29:22.688162: step: 1856/1545, loss: 0.1755906045436859 2023-01-23 09:29:23.557576: step: 1858/1545, loss: 0.22423388063907623 2023-01-23 09:29:24.427948: step: 1860/1545, loss: 0.5380028486251831 2023-01-23 09:29:25.284790: step: 1862/1545, loss: 0.11603806912899017 2023-01-23 09:29:26.163934: step: 1864/1545, loss: 0.11500846594572067 2023-01-23 09:29:27.042513: step: 1866/1545, loss: 0.3590594530105591 2023-01-23 09:29:27.933143: step: 1868/1545, loss: 0.46375590562820435 2023-01-23 09:29:28.795614: step: 1870/1545, loss: 0.1825937032699585 2023-01-23 09:29:29.700632: step: 1872/1545, loss: 0.6340041160583496 2023-01-23 09:29:30.607559: step: 1874/1545, loss: 0.25112393498420715 2023-01-23 09:29:31.519788: step: 1876/1545, loss: 0.19133415818214417 2023-01-23 09:29:32.424605: step: 1878/1545, loss: 0.847925066947937 2023-01-23 09:29:33.370724: step: 1880/1545, loss: 0.2635538876056671 2023-01-23 09:29:34.216755: step: 1882/1545, loss: 0.0810680016875267 2023-01-23 09:29:35.119872: step: 1884/1545, loss: 0.07543909549713135 2023-01-23 09:29:36.064764: step: 1886/1545, loss: 0.13787317276000977 2023-01-23 09:29:36.943161: step: 1888/1545, loss: 0.6678589582443237 2023-01-23 09:29:37.826910: step: 1890/1545, loss: 0.38842353224754333 2023-01-23 09:29:38.717532: step: 1892/1545, loss: 0.13084490597248077 2023-01-23 09:29:39.561278: step: 1894/1545, loss: 0.1702706217765808 2023-01-23 09:29:40.416932: step: 1896/1545, loss: 0.13104932010173798 2023-01-23 09:29:41.285395: step: 1898/1545, loss: 0.13461832702159882 2023-01-23 09:29:42.143361: step: 1900/1545, loss: 0.21881353855133057 2023-01-23 09:29:43.020974: step: 1902/1545, loss: 0.0479353629052639 2023-01-23 09:29:43.904457: step: 1904/1545, loss: 0.31334057450294495 2023-01-23 09:29:44.786672: step: 1906/1545, loss: 0.46950864791870117 2023-01-23 09:29:45.738802: step: 1908/1545, loss: 0.8708383440971375 2023-01-23 09:29:46.622606: step: 1910/1545, loss: 0.15250453352928162 2023-01-23 09:29:47.530508: step: 1912/1545, loss: 0.44885656237602234 2023-01-23 09:29:48.432385: step: 1914/1545, loss: 0.36271631717681885 2023-01-23 09:29:49.356157: step: 1916/1545, loss: 0.49726346135139465 2023-01-23 09:29:50.258312: step: 1918/1545, loss: 0.0982663482427597 2023-01-23 09:29:51.180692: step: 1920/1545, loss: 0.38085588812828064 2023-01-23 09:29:52.042349: step: 1922/1545, loss: 0.062155090272426605 2023-01-23 09:29:52.887575: step: 1924/1545, loss: 0.038833700120449066 2023-01-23 09:29:53.797141: step: 1926/1545, loss: 0.1935727596282959 2023-01-23 09:29:54.673145: step: 1928/1545, loss: 0.03169981390237808 2023-01-23 09:29:55.529621: step: 1930/1545, loss: 0.19706863164901733 2023-01-23 09:29:56.458241: step: 1932/1545, loss: 0.14474982023239136 2023-01-23 09:29:57.396913: step: 1934/1545, loss: 0.1919374167919159 2023-01-23 09:29:58.284695: step: 1936/1545, loss: 0.13568034768104553 2023-01-23 09:29:59.174579: step: 1938/1545, loss: 2.965444326400757 2023-01-23 09:30:00.138705: step: 1940/1545, loss: 0.10847485065460205 2023-01-23 09:30:01.061520: step: 1942/1545, loss: 0.5299394130706787 2023-01-23 09:30:01.930932: step: 1944/1545, loss: 0.07857977598905563 2023-01-23 09:30:02.910386: step: 1946/1545, loss: 0.2842761278152466 2023-01-23 09:30:03.789546: step: 1948/1545, loss: 0.1789565086364746 2023-01-23 09:30:04.701040: step: 1950/1545, loss: 0.18721354007720947 2023-01-23 09:30:05.542755: step: 1952/1545, loss: 0.23737595975399017 2023-01-23 09:30:06.418470: step: 1954/1545, loss: 0.47549161314964294 2023-01-23 09:30:07.295910: step: 1956/1545, loss: 0.026641279458999634 2023-01-23 09:30:08.124855: step: 1958/1545, loss: 0.34837451577186584 2023-01-23 09:30:08.988755: step: 1960/1545, loss: 0.16450117528438568 2023-01-23 09:30:09.830524: step: 1962/1545, loss: 0.4620497524738312 2023-01-23 09:30:10.788308: step: 1964/1545, loss: 0.2612203359603882 2023-01-23 09:30:11.677297: step: 1966/1545, loss: 0.0373142845928669 2023-01-23 09:30:12.563047: step: 1968/1545, loss: 0.13818420469760895 2023-01-23 09:30:13.522098: step: 1970/1545, loss: 0.2672330439090729 2023-01-23 09:30:14.422328: step: 1972/1545, loss: 0.4556442201137543 2023-01-23 09:30:15.270591: step: 1974/1545, loss: 0.3521571755409241 2023-01-23 09:30:16.128879: step: 1976/1545, loss: 0.24543607234954834 2023-01-23 09:30:17.019112: step: 1978/1545, loss: 0.2705160975456238 2023-01-23 09:30:17.878808: step: 1980/1545, loss: 0.5638939738273621 2023-01-23 09:30:18.791725: step: 1982/1545, loss: 0.1887575089931488 2023-01-23 09:30:19.699112: step: 1984/1545, loss: 0.4563397467136383 2023-01-23 09:30:20.639800: step: 1986/1545, loss: 0.5206612944602966 2023-01-23 09:30:21.487370: step: 1988/1545, loss: 0.21610145270824432 2023-01-23 09:30:22.353664: step: 1990/1545, loss: 0.17826035618782043 2023-01-23 09:30:23.216149: step: 1992/1545, loss: 0.15675358474254608 2023-01-23 09:30:24.063441: step: 1994/1545, loss: 0.43154123425483704 2023-01-23 09:30:24.910378: step: 1996/1545, loss: 0.07503438740968704 2023-01-23 09:30:25.784259: step: 1998/1545, loss: 0.4165355861186981 2023-01-23 09:30:26.720962: step: 2000/1545, loss: 0.09295164048671722 2023-01-23 09:30:27.580410: step: 2002/1545, loss: 0.2824287712574005 2023-01-23 09:30:28.434672: step: 2004/1545, loss: 0.285849928855896 2023-01-23 09:30:29.303270: step: 2006/1545, loss: 0.20730708539485931 2023-01-23 09:30:30.166293: step: 2008/1545, loss: 0.1922067254781723 2023-01-23 09:30:31.075703: step: 2010/1545, loss: 0.10888604074716568 2023-01-23 09:30:32.023335: step: 2012/1545, loss: 0.0869499072432518 2023-01-23 09:30:32.894238: step: 2014/1545, loss: 0.1970578283071518 2023-01-23 09:30:33.766103: step: 2016/1545, loss: 0.3088712990283966 2023-01-23 09:30:34.613861: step: 2018/1545, loss: 0.11725685745477676 2023-01-23 09:30:35.475041: step: 2020/1545, loss: 0.27822619676589966 2023-01-23 09:30:36.339167: step: 2022/1545, loss: 0.42679476737976074 2023-01-23 09:30:37.192564: step: 2024/1545, loss: 0.187703475356102 2023-01-23 09:30:38.019779: step: 2026/1545, loss: 4.455015659332275 2023-01-23 09:30:38.907563: step: 2028/1545, loss: 0.41972652077674866 2023-01-23 09:30:39.797924: step: 2030/1545, loss: 0.5342257022857666 2023-01-23 09:30:40.684897: step: 2032/1545, loss: 0.13245519995689392 2023-01-23 09:30:41.589785: step: 2034/1545, loss: 0.45708489418029785 2023-01-23 09:30:42.437619: step: 2036/1545, loss: 0.17084351181983948 2023-01-23 09:30:43.305692: step: 2038/1545, loss: 0.11160959303379059 2023-01-23 09:30:44.220252: step: 2040/1545, loss: 0.6114465594291687 2023-01-23 09:30:45.173047: step: 2042/1545, loss: 0.16357114911079407 2023-01-23 09:30:46.038960: step: 2044/1545, loss: 0.39794501662254333 2023-01-23 09:30:46.931707: step: 2046/1545, loss: 0.3126729726791382 2023-01-23 09:30:47.796925: step: 2048/1545, loss: 0.38675814867019653 2023-01-23 09:30:48.728556: step: 2050/1545, loss: 0.09317699819803238 2023-01-23 09:30:49.691680: step: 2052/1545, loss: 0.048648785799741745 2023-01-23 09:30:50.546307: step: 2054/1545, loss: 0.08697722107172012 2023-01-23 09:30:51.425899: step: 2056/1545, loss: 0.06810984015464783 2023-01-23 09:30:52.274188: step: 2058/1545, loss: 0.5814861059188843 2023-01-23 09:30:53.108414: step: 2060/1545, loss: 0.046227116137742996 2023-01-23 09:30:53.958376: step: 2062/1545, loss: 0.26253578066825867 2023-01-23 09:30:54.774312: step: 2064/1545, loss: 0.4192332625389099 2023-01-23 09:30:55.667095: step: 2066/1545, loss: 0.16245946288108826 2023-01-23 09:30:56.577853: step: 2068/1545, loss: 0.3069435656070709 2023-01-23 09:30:57.476456: step: 2070/1545, loss: 0.07227160781621933 2023-01-23 09:30:58.316539: step: 2072/1545, loss: 0.1250995397567749 2023-01-23 09:30:59.192882: step: 2074/1545, loss: 0.18680532276630402 2023-01-23 09:31:00.098273: step: 2076/1545, loss: 0.40742629766464233 2023-01-23 09:31:01.013726: step: 2078/1545, loss: 0.46206533908843994 2023-01-23 09:31:01.894881: step: 2080/1545, loss: 0.12647368013858795 2023-01-23 09:31:02.857841: step: 2082/1545, loss: 0.01955106295645237 2023-01-23 09:31:03.751132: step: 2084/1545, loss: 0.08152515441179276 2023-01-23 09:31:04.600303: step: 2086/1545, loss: 0.154326394200325 2023-01-23 09:31:05.506045: step: 2088/1545, loss: 0.2299145758152008 2023-01-23 09:31:06.383965: step: 2090/1545, loss: 0.5696729421615601 2023-01-23 09:31:07.268461: step: 2092/1545, loss: 0.12449556589126587 2023-01-23 09:31:08.161632: step: 2094/1545, loss: 0.11037997901439667 2023-01-23 09:31:09.032785: step: 2096/1545, loss: 0.38651740550994873 2023-01-23 09:31:09.900211: step: 2098/1545, loss: 2.332434892654419 2023-01-23 09:31:10.792496: step: 2100/1545, loss: 0.8397091031074524 2023-01-23 09:31:11.656524: step: 2102/1545, loss: 0.31311917304992676 2023-01-23 09:31:12.551192: step: 2104/1545, loss: 0.12644003331661224 2023-01-23 09:31:13.450946: step: 2106/1545, loss: 0.493975430727005 2023-01-23 09:31:14.337178: step: 2108/1545, loss: 0.032210659235715866 2023-01-23 09:31:15.204487: step: 2110/1545, loss: 0.2880593240261078 2023-01-23 09:31:16.127655: step: 2112/1545, loss: 0.19978445768356323 2023-01-23 09:31:16.998081: step: 2114/1545, loss: 0.2753847539424896 2023-01-23 09:31:17.899277: step: 2116/1545, loss: 0.5984543561935425 2023-01-23 09:31:18.757804: step: 2118/1545, loss: 0.10293962806463242 2023-01-23 09:31:19.652793: step: 2120/1545, loss: 0.2869337797164917 2023-01-23 09:31:20.578228: step: 2122/1545, loss: 0.28631654381752014 2023-01-23 09:31:21.459392: step: 2124/1545, loss: 0.04476248845458031 2023-01-23 09:31:22.314792: step: 2126/1545, loss: 0.49668455123901367 2023-01-23 09:31:23.263406: step: 2128/1545, loss: 0.40792182087898254 2023-01-23 09:31:24.134837: step: 2130/1545, loss: 0.13729804754257202 2023-01-23 09:31:24.979852: step: 2132/1545, loss: 0.5170784592628479 2023-01-23 09:31:25.855221: step: 2134/1545, loss: 0.19602496922016144 2023-01-23 09:31:26.694267: step: 2136/1545, loss: 0.015659093856811523 2023-01-23 09:31:27.574267: step: 2138/1545, loss: 0.09647313505411148 2023-01-23 09:31:28.465323: step: 2140/1545, loss: 0.682837963104248 2023-01-23 09:31:29.334668: step: 2142/1545, loss: 0.2295311689376831 2023-01-23 09:31:30.213511: step: 2144/1545, loss: 0.4096371531486511 2023-01-23 09:31:31.084088: step: 2146/1545, loss: 0.3441687822341919 2023-01-23 09:31:32.006655: step: 2148/1545, loss: 0.9430943727493286 2023-01-23 09:31:32.905773: step: 2150/1545, loss: 0.06871059536933899 2023-01-23 09:31:33.817909: step: 2152/1545, loss: 0.12841731309890747 2023-01-23 09:31:34.678063: step: 2154/1545, loss: 0.2226756066083908 2023-01-23 09:31:35.556112: step: 2156/1545, loss: 0.3030893802642822 2023-01-23 09:31:36.391423: step: 2158/1545, loss: 0.5696045756340027 2023-01-23 09:31:37.310092: step: 2160/1545, loss: 0.3509417772293091 2023-01-23 09:31:38.199084: step: 2162/1545, loss: 0.510861337184906 2023-01-23 09:31:39.078400: step: 2164/1545, loss: 0.27010348439216614 2023-01-23 09:31:40.002448: step: 2166/1545, loss: 0.47977033257484436 2023-01-23 09:31:40.914583: step: 2168/1545, loss: 1.9002104997634888 2023-01-23 09:31:41.785765: step: 2170/1545, loss: 0.10397801548242569 2023-01-23 09:31:42.673096: step: 2172/1545, loss: 0.21761317551136017 2023-01-23 09:31:43.585423: step: 2174/1545, loss: 0.4466794431209564 2023-01-23 09:31:44.452075: step: 2176/1545, loss: 0.4559510350227356 2023-01-23 09:31:45.336790: step: 2178/1545, loss: 1.084928274154663 2023-01-23 09:31:46.245371: step: 2180/1545, loss: 0.8021806478500366 2023-01-23 09:31:47.111830: step: 2182/1545, loss: 0.1836692839860916 2023-01-23 09:31:48.001726: step: 2184/1545, loss: 0.21511253714561462 2023-01-23 09:31:48.899137: step: 2186/1545, loss: 0.19153015315532684 2023-01-23 09:31:49.756768: step: 2188/1545, loss: 0.1203644722700119 2023-01-23 09:31:50.629143: step: 2190/1545, loss: 0.06837262213230133 2023-01-23 09:31:51.486108: step: 2192/1545, loss: 0.29364511370658875 2023-01-23 09:31:52.324362: step: 2194/1545, loss: 0.16548104584217072 2023-01-23 09:31:53.218915: step: 2196/1545, loss: 0.34678977727890015 2023-01-23 09:31:54.094712: step: 2198/1545, loss: 0.1089029610157013 2023-01-23 09:31:54.965385: step: 2200/1545, loss: 0.2653081715106964 2023-01-23 09:31:55.858544: step: 2202/1545, loss: 0.9088156819343567 2023-01-23 09:31:56.768285: step: 2204/1545, loss: 2.130197525024414 2023-01-23 09:31:57.654435: step: 2206/1545, loss: 0.3860646188259125 2023-01-23 09:31:58.532315: step: 2208/1545, loss: 0.1534666121006012 2023-01-23 09:31:59.402240: step: 2210/1545, loss: 0.27399778366088867 2023-01-23 09:32:00.313069: step: 2212/1545, loss: 0.32444462180137634 2023-01-23 09:32:01.194349: step: 2214/1545, loss: 0.2926602065563202 2023-01-23 09:32:02.078428: step: 2216/1545, loss: 1.0470010042190552 2023-01-23 09:32:02.969716: step: 2218/1545, loss: 1.0947377681732178 2023-01-23 09:32:03.845013: step: 2220/1545, loss: 0.18754583597183228 2023-01-23 09:32:04.728101: step: 2222/1545, loss: 0.2138533890247345 2023-01-23 09:32:05.649237: step: 2224/1545, loss: 0.1862240731716156 2023-01-23 09:32:06.510492: step: 2226/1545, loss: 0.19095349311828613 2023-01-23 09:32:07.414464: step: 2228/1545, loss: 0.18612971901893616 2023-01-23 09:32:08.264122: step: 2230/1545, loss: 0.08750026673078537 2023-01-23 09:32:09.149873: step: 2232/1545, loss: 0.12516658008098602 2023-01-23 09:32:10.066255: step: 2234/1545, loss: 0.3039245903491974 2023-01-23 09:32:10.930649: step: 2236/1545, loss: 0.08492045104503632 2023-01-23 09:32:11.791892: step: 2238/1545, loss: 0.48516371846199036 2023-01-23 09:32:12.717086: step: 2240/1545, loss: 0.09309857338666916 2023-01-23 09:32:13.599264: step: 2242/1545, loss: 0.1349712461233139 2023-01-23 09:32:14.456367: step: 2244/1545, loss: 0.03982292488217354 2023-01-23 09:32:15.327715: step: 2246/1545, loss: 0.08442036807537079 2023-01-23 09:32:16.233100: step: 2248/1545, loss: 0.1867607980966568 2023-01-23 09:32:17.112694: step: 2250/1545, loss: 0.18252919614315033 2023-01-23 09:32:18.032895: step: 2252/1545, loss: 0.023323383182287216 2023-01-23 09:32:18.939201: step: 2254/1545, loss: 0.2626844048500061 2023-01-23 09:32:19.800792: step: 2256/1545, loss: 0.6664127111434937 2023-01-23 09:32:20.662283: step: 2258/1545, loss: 0.13968968391418457 2023-01-23 09:32:21.601159: step: 2260/1545, loss: 0.5923768281936646 2023-01-23 09:32:22.518428: step: 2262/1545, loss: 0.5089990496635437 2023-01-23 09:32:23.467475: step: 2264/1545, loss: 0.304817795753479 2023-01-23 09:32:24.323782: step: 2266/1545, loss: 0.12532392144203186 2023-01-23 09:32:25.229834: step: 2268/1545, loss: 0.21441501379013062 2023-01-23 09:32:26.094094: step: 2270/1545, loss: 0.0643862709403038 2023-01-23 09:32:27.022239: step: 2272/1545, loss: 0.1768820881843567 2023-01-23 09:32:27.908406: step: 2274/1545, loss: 0.26929113268852234 2023-01-23 09:32:28.780421: step: 2276/1545, loss: 0.6050578355789185 2023-01-23 09:32:29.642980: step: 2278/1545, loss: 0.017471764236688614 2023-01-23 09:32:30.534569: step: 2280/1545, loss: 0.42595648765563965 2023-01-23 09:32:31.399939: step: 2282/1545, loss: 0.22366350889205933 2023-01-23 09:32:32.314185: step: 2284/1545, loss: 0.3954249322414398 2023-01-23 09:32:33.157563: step: 2286/1545, loss: 0.182229682803154 2023-01-23 09:32:34.077681: step: 2288/1545, loss: 0.10286934673786163 2023-01-23 09:32:34.968937: step: 2290/1545, loss: 0.2745765149593353 2023-01-23 09:32:35.911792: step: 2292/1545, loss: 0.12047302722930908 2023-01-23 09:32:36.763808: step: 2294/1545, loss: 0.3041881322860718 2023-01-23 09:32:37.608447: step: 2296/1545, loss: 0.48818913102149963 2023-01-23 09:32:38.478824: step: 2298/1545, loss: 0.11909982562065125 2023-01-23 09:32:39.365915: step: 2300/1545, loss: 0.3705032467842102 2023-01-23 09:32:40.226457: step: 2302/1545, loss: 0.171094611287117 2023-01-23 09:32:41.142592: step: 2304/1545, loss: 0.10609891265630722 2023-01-23 09:32:42.031841: step: 2306/1545, loss: 0.1548842489719391 2023-01-23 09:32:42.919014: step: 2308/1545, loss: 0.7171480059623718 2023-01-23 09:32:43.794507: step: 2310/1545, loss: 0.05488675460219383 2023-01-23 09:32:44.657862: step: 2312/1545, loss: 0.22879961133003235 2023-01-23 09:32:45.525008: step: 2314/1545, loss: 0.17697271704673767 2023-01-23 09:32:46.454197: step: 2316/1545, loss: 0.37901046872138977 2023-01-23 09:32:47.351811: step: 2318/1545, loss: 0.46275094151496887 2023-01-23 09:32:48.217560: step: 2320/1545, loss: 0.1576026827096939 2023-01-23 09:32:49.115285: step: 2322/1545, loss: 0.5811273455619812 2023-01-23 09:32:49.996489: step: 2324/1545, loss: 0.06274568289518356 2023-01-23 09:32:50.865785: step: 2326/1545, loss: 0.26249435544013977 2023-01-23 09:32:51.760367: step: 2328/1545, loss: 0.22303961217403412 2023-01-23 09:32:52.698852: step: 2330/1545, loss: 0.8193695545196533 2023-01-23 09:32:53.609578: step: 2332/1545, loss: 0.08518242090940475 2023-01-23 09:32:54.512339: step: 2334/1545, loss: 0.1333097219467163 2023-01-23 09:32:55.371574: step: 2336/1545, loss: 0.19779813289642334 2023-01-23 09:32:56.305980: step: 2338/1545, loss: 1.4942822456359863 2023-01-23 09:32:57.217185: step: 2340/1545, loss: 0.18788087368011475 2023-01-23 09:32:58.089956: step: 2342/1545, loss: 0.15470166504383087 2023-01-23 09:32:58.922537: step: 2344/1545, loss: 0.09690716862678528 2023-01-23 09:32:59.745069: step: 2346/1545, loss: 0.0966927781701088 2023-01-23 09:33:00.628437: step: 2348/1545, loss: 0.33439069986343384 2023-01-23 09:33:01.536423: step: 2350/1545, loss: 0.417915940284729 2023-01-23 09:33:02.455863: step: 2352/1545, loss: 0.03723393380641937 2023-01-23 09:33:03.327500: step: 2354/1545, loss: 0.21982091665267944 2023-01-23 09:33:04.229214: step: 2356/1545, loss: 0.10524137318134308 2023-01-23 09:33:05.106816: step: 2358/1545, loss: 0.1692325472831726 2023-01-23 09:33:05.965040: step: 2360/1545, loss: 0.0759868323802948 2023-01-23 09:33:06.950202: step: 2362/1545, loss: 0.23946145176887512 2023-01-23 09:33:07.851388: step: 2364/1545, loss: 0.41160479187965393 2023-01-23 09:33:08.704758: step: 2366/1545, loss: 0.16369909048080444 2023-01-23 09:33:09.559765: step: 2368/1545, loss: 0.6318075060844421 2023-01-23 09:33:10.451919: step: 2370/1545, loss: 0.0116350669413805 2023-01-23 09:33:11.384126: step: 2372/1545, loss: 0.2936699390411377 2023-01-23 09:33:12.268227: step: 2374/1545, loss: 0.20514769852161407 2023-01-23 09:33:13.146201: step: 2376/1545, loss: 1.3585798740386963 2023-01-23 09:33:14.036804: step: 2378/1545, loss: 0.3474280536174774 2023-01-23 09:33:14.942586: step: 2380/1545, loss: 0.5334355235099792 2023-01-23 09:33:15.836017: step: 2382/1545, loss: 0.06051474064588547 2023-01-23 09:33:16.703928: step: 2384/1545, loss: 0.271817147731781 2023-01-23 09:33:17.599212: step: 2386/1545, loss: 0.14510150253772736 2023-01-23 09:33:18.502008: step: 2388/1545, loss: 0.4106338918209076 2023-01-23 09:33:19.380304: step: 2390/1545, loss: 0.15021812915802002 2023-01-23 09:33:20.238292: step: 2392/1545, loss: 0.30811524391174316 2023-01-23 09:33:21.129055: step: 2394/1545, loss: 0.2796861529350281 2023-01-23 09:33:22.068044: step: 2396/1545, loss: 2.483010768890381 2023-01-23 09:33:23.002041: step: 2398/1545, loss: 0.06064307317137718 2023-01-23 09:33:23.922914: step: 2400/1545, loss: 0.1974048614501953 2023-01-23 09:33:24.813207: step: 2402/1545, loss: 0.17675286531448364 2023-01-23 09:33:25.694745: step: 2404/1545, loss: 0.3339158594608307 2023-01-23 09:33:26.605325: step: 2406/1545, loss: 0.3402028977870941 2023-01-23 09:33:27.488781: step: 2408/1545, loss: 0.18145151436328888 2023-01-23 09:33:28.370600: step: 2410/1545, loss: 0.06341899931430817 2023-01-23 09:33:29.252059: step: 2412/1545, loss: 0.20764656364917755 2023-01-23 09:33:30.205257: step: 2414/1545, loss: 0.4489692151546478 2023-01-23 09:33:31.099805: step: 2416/1545, loss: 0.30499908328056335 2023-01-23 09:33:31.986880: step: 2418/1545, loss: 2.521660327911377 2023-01-23 09:33:32.852185: step: 2420/1545, loss: 0.24439287185668945 2023-01-23 09:33:33.723903: step: 2422/1545, loss: 0.07793699204921722 2023-01-23 09:33:34.631946: step: 2424/1545, loss: 0.21556073427200317 2023-01-23 09:33:35.551577: step: 2426/1545, loss: 2.5276455879211426 2023-01-23 09:33:36.395168: step: 2428/1545, loss: 0.1994098722934723 2023-01-23 09:33:37.344517: step: 2430/1545, loss: 0.24021016061306 2023-01-23 09:33:38.261156: step: 2432/1545, loss: 0.1967020332813263 2023-01-23 09:33:39.163791: step: 2434/1545, loss: 0.192681685090065 2023-01-23 09:33:40.033936: step: 2436/1545, loss: 0.13826420903205872 2023-01-23 09:33:40.930065: step: 2438/1545, loss: 0.24667774140834808 2023-01-23 09:33:41.821612: step: 2440/1545, loss: 0.3782289922237396 2023-01-23 09:33:42.683939: step: 2442/1545, loss: 0.3782356381416321 2023-01-23 09:33:43.548618: step: 2444/1545, loss: 0.17600645124912262 2023-01-23 09:33:44.429960: step: 2446/1545, loss: 0.4433894753456116 2023-01-23 09:33:45.322521: step: 2448/1545, loss: 0.3933270573616028 2023-01-23 09:33:46.183093: step: 2450/1545, loss: 0.09732239693403244 2023-01-23 09:33:47.054503: step: 2452/1545, loss: 0.06584746390581131 2023-01-23 09:33:47.959845: step: 2454/1545, loss: 0.4256119728088379 2023-01-23 09:33:48.820256: step: 2456/1545, loss: 0.08527995645999908 2023-01-23 09:33:49.716754: step: 2458/1545, loss: 0.2355041652917862 2023-01-23 09:33:50.592041: step: 2460/1545, loss: 0.41047751903533936 2023-01-23 09:33:51.552659: step: 2462/1545, loss: 1.0884321928024292 2023-01-23 09:33:52.434985: step: 2464/1545, loss: 0.2094132900238037 2023-01-23 09:33:53.284772: step: 2466/1545, loss: 0.5896067023277283 2023-01-23 09:33:54.138159: step: 2468/1545, loss: 0.17564301192760468 2023-01-23 09:33:54.976656: step: 2470/1545, loss: 0.3126284182071686 2023-01-23 09:33:55.884695: step: 2472/1545, loss: 0.06402400135993958 2023-01-23 09:33:56.725140: step: 2474/1545, loss: 0.3254428803920746 2023-01-23 09:33:57.608560: step: 2476/1545, loss: 0.13403008878231049 2023-01-23 09:33:58.553101: step: 2478/1545, loss: 0.20890213549137115 2023-01-23 09:33:59.577500: step: 2480/1545, loss: 0.1545865833759308 2023-01-23 09:34:00.481368: step: 2482/1545, loss: 0.17019590735435486 2023-01-23 09:34:01.390095: step: 2484/1545, loss: 0.3697734475135803 2023-01-23 09:34:02.275055: step: 2486/1545, loss: 0.7718888521194458 2023-01-23 09:34:03.215444: step: 2488/1545, loss: 0.197622612118721 2023-01-23 09:34:04.074673: step: 2490/1545, loss: 0.08534526079893112 2023-01-23 09:34:04.968090: step: 2492/1545, loss: 0.05826425552368164 2023-01-23 09:34:05.905855: step: 2494/1545, loss: 0.03628667816519737 2023-01-23 09:34:06.805680: step: 2496/1545, loss: 0.5374911427497864 2023-01-23 09:34:07.678185: step: 2498/1545, loss: 0.8005020022392273 2023-01-23 09:34:08.602157: step: 2500/1545, loss: 0.3813817799091339 2023-01-23 09:34:09.451134: step: 2502/1545, loss: 0.9266161322593689 2023-01-23 09:34:10.332963: step: 2504/1545, loss: 0.3074163496494293 2023-01-23 09:34:11.204610: step: 2506/1545, loss: 0.04803372919559479 2023-01-23 09:34:12.075278: step: 2508/1545, loss: 0.4809933304786682 2023-01-23 09:34:12.953437: step: 2510/1545, loss: 0.19879375398159027 2023-01-23 09:34:13.871280: step: 2512/1545, loss: 0.5263739228248596 2023-01-23 09:34:14.760935: step: 2514/1545, loss: 0.19163364171981812 2023-01-23 09:34:15.636281: step: 2516/1545, loss: 0.4538610875606537 2023-01-23 09:34:16.511146: step: 2518/1545, loss: 0.29084163904190063 2023-01-23 09:34:17.376415: step: 2520/1545, loss: 0.0471189022064209 2023-01-23 09:34:18.277406: step: 2522/1545, loss: 0.5145006775856018 2023-01-23 09:34:19.235788: step: 2524/1545, loss: 0.14363886415958405 2023-01-23 09:34:20.144317: step: 2526/1545, loss: 0.48970210552215576 2023-01-23 09:34:20.998622: step: 2528/1545, loss: 0.1487240344285965 2023-01-23 09:34:21.877403: step: 2530/1545, loss: 0.20290516316890717 2023-01-23 09:34:22.806161: step: 2532/1545, loss: 0.23610392212867737 2023-01-23 09:34:23.686132: step: 2534/1545, loss: 0.135778546333313 2023-01-23 09:34:24.534000: step: 2536/1545, loss: 0.17792220413684845 2023-01-23 09:34:25.472710: step: 2538/1545, loss: 0.2682631015777588 2023-01-23 09:34:26.349428: step: 2540/1545, loss: 0.22435639798641205 2023-01-23 09:34:27.234894: step: 2542/1545, loss: 0.3594028949737549 2023-01-23 09:34:28.103192: step: 2544/1545, loss: 0.31160464882850647 2023-01-23 09:34:28.982825: step: 2546/1545, loss: 0.6817674040794373 2023-01-23 09:34:29.863316: step: 2548/1545, loss: 0.13500940799713135 2023-01-23 09:34:30.710897: step: 2550/1545, loss: 0.28561827540397644 2023-01-23 09:34:31.665843: step: 2552/1545, loss: 0.1999066323041916 2023-01-23 09:34:32.514119: step: 2554/1545, loss: 0.420179158449173 2023-01-23 09:34:33.463632: step: 2556/1545, loss: 0.07693294435739517 2023-01-23 09:34:34.390982: step: 2558/1545, loss: 0.202084019780159 2023-01-23 09:34:35.244301: step: 2560/1545, loss: 0.17425552010536194 2023-01-23 09:34:36.146434: step: 2562/1545, loss: 0.3051266372203827 2023-01-23 09:34:36.992012: step: 2564/1545, loss: 0.1779366433620453 2023-01-23 09:34:37.920366: step: 2566/1545, loss: 0.30245232582092285 2023-01-23 09:34:38.794124: step: 2568/1545, loss: 0.2881760001182556 2023-01-23 09:34:39.687514: step: 2570/1545, loss: 0.27753138542175293 2023-01-23 09:34:40.559334: step: 2572/1545, loss: 0.3648349642753601 2023-01-23 09:34:41.540863: step: 2574/1545, loss: 0.3179299235343933 2023-01-23 09:34:42.566184: step: 2576/1545, loss: 2.3465163707733154 2023-01-23 09:34:43.428195: step: 2578/1545, loss: 0.3882977068424225 2023-01-23 09:34:44.291711: step: 2580/1545, loss: 0.32984742522239685 2023-01-23 09:34:45.180339: step: 2582/1545, loss: 0.19811226427555084 2023-01-23 09:34:46.055905: step: 2584/1545, loss: 0.020122483372688293 2023-01-23 09:34:46.898935: step: 2586/1545, loss: 0.041797228157520294 2023-01-23 09:34:47.773946: step: 2588/1545, loss: 0.2398110032081604 2023-01-23 09:34:48.601734: step: 2590/1545, loss: 0.1565779447555542 2023-01-23 09:34:49.439139: step: 2592/1545, loss: 0.15177702903747559 2023-01-23 09:34:50.316168: step: 2594/1545, loss: 0.09008333086967468 2023-01-23 09:34:51.170132: step: 2596/1545, loss: 0.3305948078632355 2023-01-23 09:34:52.077622: step: 2598/1545, loss: 0.7395685315132141 2023-01-23 09:34:52.945377: step: 2600/1545, loss: 0.5719389915466309 2023-01-23 09:34:53.918030: step: 2602/1545, loss: 0.3809151351451874 2023-01-23 09:34:54.786252: step: 2604/1545, loss: 0.1567869484424591 2023-01-23 09:34:55.661713: step: 2606/1545, loss: 0.5776960849761963 2023-01-23 09:34:56.566461: step: 2608/1545, loss: 0.1959751397371292 2023-01-23 09:34:57.484748: step: 2610/1545, loss: 0.1154671385884285 2023-01-23 09:34:58.354206: step: 2612/1545, loss: 0.14713911712169647 2023-01-23 09:34:59.242473: step: 2614/1545, loss: 0.6197167634963989 2023-01-23 09:35:00.104061: step: 2616/1545, loss: 0.1171158030629158 2023-01-23 09:35:01.029148: step: 2618/1545, loss: 0.1276485025882721 2023-01-23 09:35:01.922209: step: 2620/1545, loss: 0.3948957920074463 2023-01-23 09:35:02.830632: step: 2622/1545, loss: 0.35482603311538696 2023-01-23 09:35:03.715060: step: 2624/1545, loss: 0.23568814992904663 2023-01-23 09:35:04.587080: step: 2626/1545, loss: 0.7054057717323303 2023-01-23 09:35:05.494376: step: 2628/1545, loss: 0.7010064721107483 2023-01-23 09:35:06.374998: step: 2630/1545, loss: 1.091962456703186 2023-01-23 09:35:07.238879: step: 2632/1545, loss: 0.1427815854549408 2023-01-23 09:35:08.082842: step: 2634/1545, loss: 0.13687197864055634 2023-01-23 09:35:08.980733: step: 2636/1545, loss: 0.10111657530069351 2023-01-23 09:35:09.926913: step: 2638/1545, loss: 0.18624337017536163 2023-01-23 09:35:10.797925: step: 2640/1545, loss: 0.18162508308887482 2023-01-23 09:35:11.707010: step: 2642/1545, loss: 0.3791206479072571 2023-01-23 09:35:12.578353: step: 2644/1545, loss: 2.2012221813201904 2023-01-23 09:35:13.453139: step: 2646/1545, loss: 0.3822105824947357 2023-01-23 09:35:14.366519: step: 2648/1545, loss: 0.04311956837773323 2023-01-23 09:35:15.245787: step: 2650/1545, loss: 0.19511468708515167 2023-01-23 09:35:16.145695: step: 2652/1545, loss: 0.16409170627593994 2023-01-23 09:35:17.014825: step: 2654/1545, loss: 0.17148755490779877 2023-01-23 09:35:17.939807: step: 2656/1545, loss: 0.3694727122783661 2023-01-23 09:35:18.812469: step: 2658/1545, loss: 0.39054974913597107 2023-01-23 09:35:19.703801: step: 2660/1545, loss: 1.0983959436416626 2023-01-23 09:35:20.586960: step: 2662/1545, loss: 0.33915701508522034 2023-01-23 09:35:21.474668: step: 2664/1545, loss: 0.30498701333999634 2023-01-23 09:35:22.362623: step: 2666/1545, loss: 0.612468957901001 2023-01-23 09:35:23.274061: step: 2668/1545, loss: 0.23791703581809998 2023-01-23 09:35:24.180578: step: 2670/1545, loss: 0.146235391497612 2023-01-23 09:35:25.074515: step: 2672/1545, loss: 0.17742595076560974 2023-01-23 09:35:26.007707: step: 2674/1545, loss: 0.6135358810424805 2023-01-23 09:35:26.916306: step: 2676/1545, loss: 0.08435416221618652 2023-01-23 09:35:27.802677: step: 2678/1545, loss: 0.49623996019363403 2023-01-23 09:35:28.672906: step: 2680/1545, loss: 0.18202179670333862 2023-01-23 09:35:29.516957: step: 2682/1545, loss: 0.29654252529144287 2023-01-23 09:35:30.416209: step: 2684/1545, loss: 0.12510471045970917 2023-01-23 09:35:31.273443: step: 2686/1545, loss: 2.379674196243286 2023-01-23 09:35:32.142863: step: 2688/1545, loss: 0.12147531658411026 2023-01-23 09:35:33.031964: step: 2690/1545, loss: 0.6761528253555298 2023-01-23 09:35:33.908315: step: 2692/1545, loss: 0.3113643527030945 2023-01-23 09:35:34.770932: step: 2694/1545, loss: 0.5802344679832458 2023-01-23 09:35:35.648704: step: 2696/1545, loss: 0.5161349177360535 2023-01-23 09:35:36.576931: step: 2698/1545, loss: 0.12137418985366821 2023-01-23 09:35:37.460638: step: 2700/1545, loss: 0.7648671269416809 2023-01-23 09:35:38.376729: step: 2702/1545, loss: 0.3356553614139557 2023-01-23 09:35:39.238778: step: 2704/1545, loss: 0.1267363429069519 2023-01-23 09:35:40.101460: step: 2706/1545, loss: 1.6762018203735352 2023-01-23 09:35:40.969966: step: 2708/1545, loss: 0.07643601298332214 2023-01-23 09:35:41.871524: step: 2710/1545, loss: 0.3447220027446747 2023-01-23 09:35:42.759630: step: 2712/1545, loss: 0.25747165083885193 2023-01-23 09:35:43.631453: step: 2714/1545, loss: 0.22516897320747375 2023-01-23 09:35:44.512928: step: 2716/1545, loss: 0.1681402623653412 2023-01-23 09:35:45.339649: step: 2718/1545, loss: 0.20060013234615326 2023-01-23 09:35:46.265524: step: 2720/1545, loss: 0.2796858251094818 2023-01-23 09:35:47.181538: step: 2722/1545, loss: 0.15068043768405914 2023-01-23 09:35:48.055215: step: 2724/1545, loss: 0.5612637400627136 2023-01-23 09:35:49.024201: step: 2726/1545, loss: 0.4397897720336914 2023-01-23 09:35:49.937877: step: 2728/1545, loss: 0.22870773077011108 2023-01-23 09:35:50.867550: step: 2730/1545, loss: 0.26048120856285095 2023-01-23 09:35:51.750000: step: 2732/1545, loss: 0.398993581533432 2023-01-23 09:35:52.605313: step: 2734/1545, loss: 0.17269587516784668 2023-01-23 09:35:53.506893: step: 2736/1545, loss: 0.4774293005466461 2023-01-23 09:35:54.373043: step: 2738/1545, loss: 0.6259652972221375 2023-01-23 09:35:55.338001: step: 2740/1545, loss: 0.16905245184898376 2023-01-23 09:35:56.196486: step: 2742/1545, loss: 0.1772032082080841 2023-01-23 09:35:57.051199: step: 2744/1545, loss: 0.3400598466396332 2023-01-23 09:35:57.984004: step: 2746/1545, loss: 0.2944470942020416 2023-01-23 09:35:58.870835: step: 2748/1545, loss: 0.46231991052627563 2023-01-23 09:35:59.789236: step: 2750/1545, loss: 0.08897478133440018 2023-01-23 09:36:00.660143: step: 2752/1545, loss: 1.2250866889953613 2023-01-23 09:36:01.532712: step: 2754/1545, loss: 0.17294663190841675 2023-01-23 09:36:02.376204: step: 2756/1545, loss: 0.19901852309703827 2023-01-23 09:36:03.321497: step: 2758/1545, loss: 0.1460406333208084 2023-01-23 09:36:04.182950: step: 2760/1545, loss: 0.2513817846775055 2023-01-23 09:36:05.047408: step: 2762/1545, loss: 0.06685879081487656 2023-01-23 09:36:05.883248: step: 2764/1545, loss: 0.045796651393175125 2023-01-23 09:36:06.754248: step: 2766/1545, loss: 0.2831486761569977 2023-01-23 09:36:07.664244: step: 2768/1545, loss: 0.1544470489025116 2023-01-23 09:36:08.513612: step: 2770/1545, loss: 0.5794212222099304 2023-01-23 09:36:09.390483: step: 2772/1545, loss: 0.2223491221666336 2023-01-23 09:36:10.259315: step: 2774/1545, loss: 0.27373284101486206 2023-01-23 09:36:11.165058: step: 2776/1545, loss: 0.06481891870498657 2023-01-23 09:36:12.031931: step: 2778/1545, loss: 0.05433753505349159 2023-01-23 09:36:12.944873: step: 2780/1545, loss: 0.11695392429828644 2023-01-23 09:36:13.880154: step: 2782/1545, loss: 0.24396131932735443 2023-01-23 09:36:14.794624: step: 2784/1545, loss: 0.04838293790817261 2023-01-23 09:36:15.691300: step: 2786/1545, loss: 0.16660022735595703 2023-01-23 09:36:16.594871: step: 2788/1545, loss: 0.2420181930065155 2023-01-23 09:36:17.479941: step: 2790/1545, loss: 0.09632392972707748 2023-01-23 09:36:18.367525: step: 2792/1545, loss: 0.07741091400384903 2023-01-23 09:36:19.288613: step: 2794/1545, loss: 0.11378278583288193 2023-01-23 09:36:20.171452: step: 2796/1545, loss: 0.6900817155838013 2023-01-23 09:36:21.031679: step: 2798/1545, loss: 0.11070514470338821 2023-01-23 09:36:21.941295: step: 2800/1545, loss: 0.0649803951382637 2023-01-23 09:36:22.821363: step: 2802/1545, loss: 0.1191982626914978 2023-01-23 09:36:23.708950: step: 2804/1545, loss: 0.5060907602310181 2023-01-23 09:36:24.628340: step: 2806/1545, loss: 0.4190937280654907 2023-01-23 09:36:25.575253: step: 2808/1545, loss: 0.12375641614198685 2023-01-23 09:36:26.484272: step: 2810/1545, loss: 0.07932568341493607 2023-01-23 09:36:27.363706: step: 2812/1545, loss: 0.14788851141929626 2023-01-23 09:36:28.194954: step: 2814/1545, loss: 0.25285226106643677 2023-01-23 09:36:29.056335: step: 2816/1545, loss: 0.12505066394805908 2023-01-23 09:36:29.931602: step: 2818/1545, loss: 0.14058256149291992 2023-01-23 09:36:30.862328: step: 2820/1545, loss: 0.49702081084251404 2023-01-23 09:36:31.734488: step: 2822/1545, loss: 0.11946362257003784 2023-01-23 09:36:32.663077: step: 2824/1545, loss: 0.16382034122943878 2023-01-23 09:36:33.575008: step: 2826/1545, loss: 0.9129332900047302 2023-01-23 09:36:34.487634: step: 2828/1545, loss: 0.09889057278633118 2023-01-23 09:36:35.403046: step: 2830/1545, loss: 0.07686563581228256 2023-01-23 09:36:36.362415: step: 2832/1545, loss: 0.4146934151649475 2023-01-23 09:36:37.234692: step: 2834/1545, loss: 0.25501152873039246 2023-01-23 09:36:38.118164: step: 2836/1545, loss: 0.3624454438686371 2023-01-23 09:36:39.005948: step: 2838/1545, loss: 0.2143089771270752 2023-01-23 09:36:39.896490: step: 2840/1545, loss: 1.2503576278686523 2023-01-23 09:36:40.754505: step: 2842/1545, loss: 0.03302012011408806 2023-01-23 09:36:41.649057: step: 2844/1545, loss: 0.16981711983680725 2023-01-23 09:36:42.542995: step: 2846/1545, loss: 0.2518406808376312 2023-01-23 09:36:43.552546: step: 2848/1545, loss: 0.2986615300178528 2023-01-23 09:36:44.441601: step: 2850/1545, loss: 0.23077596724033356 2023-01-23 09:36:45.294085: step: 2852/1545, loss: 0.37582263350486755 2023-01-23 09:36:46.166707: step: 2854/1545, loss: 0.8287343978881836 2023-01-23 09:36:47.026201: step: 2856/1545, loss: 0.2325880080461502 2023-01-23 09:36:47.905358: step: 2858/1545, loss: 0.24400267004966736 2023-01-23 09:36:48.745291: step: 2860/1545, loss: 0.15764984488487244 2023-01-23 09:36:49.657922: step: 2862/1545, loss: 0.045316897332668304 2023-01-23 09:36:50.558216: step: 2864/1545, loss: 0.08233912289142609 2023-01-23 09:36:51.466149: step: 2866/1545, loss: 0.4233894944190979 2023-01-23 09:36:52.446917: step: 2868/1545, loss: 0.4267309904098511 2023-01-23 09:36:53.382789: step: 2870/1545, loss: 0.19228008389472961 2023-01-23 09:36:54.216263: step: 2872/1545, loss: 0.5909847617149353 2023-01-23 09:36:55.142162: step: 2874/1545, loss: 0.22543354332447052 2023-01-23 09:36:56.057704: step: 2876/1545, loss: 0.1424710601568222 2023-01-23 09:36:56.929578: step: 2878/1545, loss: 0.30540698766708374 2023-01-23 09:36:57.928571: step: 2880/1545, loss: 0.7250127792358398 2023-01-23 09:36:58.788546: step: 2882/1545, loss: 0.2647997736930847 2023-01-23 09:36:59.679700: step: 2884/1545, loss: 0.20671208202838898 2023-01-23 09:37:00.560372: step: 2886/1545, loss: 0.9463754892349243 2023-01-23 09:37:01.442940: step: 2888/1545, loss: 0.2904534339904785 2023-01-23 09:37:02.358700: step: 2890/1545, loss: 0.48899045586586 2023-01-23 09:37:03.227845: step: 2892/1545, loss: 0.1481349617242813 2023-01-23 09:37:04.088670: step: 2894/1545, loss: 0.1463150978088379 2023-01-23 09:37:04.963375: step: 2896/1545, loss: 0.03582246974110603 2023-01-23 09:37:05.854402: step: 2898/1545, loss: 3.268392324447632 2023-01-23 09:37:06.735747: step: 2900/1545, loss: 0.1630924642086029 2023-01-23 09:37:07.585263: step: 2902/1545, loss: 0.221281036734581 2023-01-23 09:37:08.462279: step: 2904/1545, loss: 0.15900784730911255 2023-01-23 09:37:09.346661: step: 2906/1545, loss: 0.14493359625339508 2023-01-23 09:37:10.229258: step: 2908/1545, loss: 0.2748918831348419 2023-01-23 09:37:11.098215: step: 2910/1545, loss: 0.4807839095592499 2023-01-23 09:37:11.967031: step: 2912/1545, loss: 0.9233506917953491 2023-01-23 09:37:12.837328: step: 2914/1545, loss: 0.3490581512451172 2023-01-23 09:37:13.749299: step: 2916/1545, loss: 0.8267192840576172 2023-01-23 09:37:14.722075: step: 2918/1545, loss: 0.14905193448066711 2023-01-23 09:37:15.616655: step: 2920/1545, loss: 0.26622137427330017 2023-01-23 09:37:16.533866: step: 2922/1545, loss: 0.48440685868263245 2023-01-23 09:37:17.407198: step: 2924/1545, loss: 0.40575921535491943 2023-01-23 09:37:18.322698: step: 2926/1545, loss: 0.1251031756401062 2023-01-23 09:37:19.176282: step: 2928/1545, loss: 0.23263773322105408 2023-01-23 09:37:20.064888: step: 2930/1545, loss: 0.11449583619832993 2023-01-23 09:37:20.939875: step: 2932/1545, loss: 0.09014110267162323 2023-01-23 09:37:21.811904: step: 2934/1545, loss: 0.2563266158103943 2023-01-23 09:37:22.692079: step: 2936/1545, loss: 0.34858259558677673 2023-01-23 09:37:23.543769: step: 2938/1545, loss: 0.3053193688392639 2023-01-23 09:37:24.411852: step: 2940/1545, loss: 0.30797693133354187 2023-01-23 09:37:25.316431: step: 2942/1545, loss: 0.302338570356369 2023-01-23 09:37:26.211838: step: 2944/1545, loss: 0.4166620075702667 2023-01-23 09:37:27.070968: step: 2946/1545, loss: 0.3939908742904663 2023-01-23 09:37:27.975245: step: 2948/1545, loss: 0.2619481682777405 2023-01-23 09:37:28.889061: step: 2950/1545, loss: 0.17957566678524017 2023-01-23 09:37:29.768232: step: 2952/1545, loss: 0.4165964424610138 2023-01-23 09:37:30.632911: step: 2954/1545, loss: 0.1994829922914505 2023-01-23 09:37:31.511211: step: 2956/1545, loss: 0.0230842437595129 2023-01-23 09:37:32.367288: step: 2958/1545, loss: 0.12701651453971863 2023-01-23 09:37:33.207507: step: 2960/1545, loss: 0.13711389899253845 2023-01-23 09:37:34.062142: step: 2962/1545, loss: 0.16641061007976532 2023-01-23 09:37:34.951934: step: 2964/1545, loss: 2.754988670349121 2023-01-23 09:37:35.867949: step: 2966/1545, loss: 0.18497465550899506 2023-01-23 09:37:36.745642: step: 2968/1545, loss: 0.05413166806101799 2023-01-23 09:37:37.621025: step: 2970/1545, loss: 0.8626705408096313 2023-01-23 09:37:38.549644: step: 2972/1545, loss: 1.321999430656433 2023-01-23 09:37:39.464569: step: 2974/1545, loss: 0.727834939956665 2023-01-23 09:37:40.349763: step: 2976/1545, loss: 0.0377594418823719 2023-01-23 09:37:41.242997: step: 2978/1545, loss: 0.20179307460784912 2023-01-23 09:37:42.120216: step: 2980/1545, loss: 0.09698822349309921 2023-01-23 09:37:42.945464: step: 2982/1545, loss: 0.28014883399009705 2023-01-23 09:37:43.845101: step: 2984/1545, loss: 0.34473538398742676 2023-01-23 09:37:44.708974: step: 2986/1545, loss: 0.37663722038269043 2023-01-23 09:37:45.610929: step: 2988/1545, loss: 0.19637688994407654 2023-01-23 09:37:46.485531: step: 2990/1545, loss: 0.6136249303817749 2023-01-23 09:37:47.383279: step: 2992/1545, loss: 0.22161084413528442 2023-01-23 09:37:48.261068: step: 2994/1545, loss: 0.6196271777153015 2023-01-23 09:37:49.215038: step: 2996/1545, loss: 0.862572431564331 2023-01-23 09:37:50.122152: step: 2998/1545, loss: 0.3305358588695526 2023-01-23 09:37:50.983430: step: 3000/1545, loss: 0.07791075855493546 2023-01-23 09:37:51.939969: step: 3002/1545, loss: 0.3797198235988617 2023-01-23 09:37:52.827948: step: 3004/1545, loss: 0.21190465986728668 2023-01-23 09:37:53.703138: step: 3006/1545, loss: 0.10390128940343857 2023-01-23 09:37:54.583007: step: 3008/1545, loss: 0.35087698698043823 2023-01-23 09:37:55.476238: step: 3010/1545, loss: 0.3538755774497986 2023-01-23 09:37:56.420525: step: 3012/1545, loss: 0.6332515478134155 2023-01-23 09:37:57.326970: step: 3014/1545, loss: 0.19076083600521088 2023-01-23 09:37:58.203152: step: 3016/1545, loss: 0.16808128356933594 2023-01-23 09:37:59.100940: step: 3018/1545, loss: 0.18302254378795624 2023-01-23 09:37:59.971996: step: 3020/1545, loss: 0.3831569254398346 2023-01-23 09:38:00.848097: step: 3022/1545, loss: 0.23215539753437042 2023-01-23 09:38:01.783281: step: 3024/1545, loss: 0.06485788524150848 2023-01-23 09:38:02.701446: step: 3026/1545, loss: 0.38673242926597595 2023-01-23 09:38:03.551498: step: 3028/1545, loss: 0.7384246587753296 2023-01-23 09:38:04.429583: step: 3030/1545, loss: 0.14341622591018677 2023-01-23 09:38:05.318963: step: 3032/1545, loss: 0.10756228119134903 2023-01-23 09:38:06.196596: step: 3034/1545, loss: 0.323989599943161 2023-01-23 09:38:07.095916: step: 3036/1545, loss: 0.06874735653400421 2023-01-23 09:38:07.948434: step: 3038/1545, loss: 0.12080999463796616 2023-01-23 09:38:08.852637: step: 3040/1545, loss: 0.46652424335479736 2023-01-23 09:38:09.730096: step: 3042/1545, loss: 0.30383700132369995 2023-01-23 09:38:10.618162: step: 3044/1545, loss: 0.10033892095088959 2023-01-23 09:38:11.510051: step: 3046/1545, loss: 0.08330690115690231 2023-01-23 09:38:12.448781: step: 3048/1545, loss: 0.2710379362106323 2023-01-23 09:38:13.326874: step: 3050/1545, loss: 0.6327111721038818 2023-01-23 09:38:14.209217: step: 3052/1545, loss: 0.03860614821314812 2023-01-23 09:38:15.077170: step: 3054/1545, loss: 0.409522145986557 2023-01-23 09:38:15.946165: step: 3056/1545, loss: 2.3607420921325684 2023-01-23 09:38:16.788683: step: 3058/1545, loss: 0.19092294573783875 2023-01-23 09:38:17.663714: step: 3060/1545, loss: 0.1779520958662033 2023-01-23 09:38:18.598608: step: 3062/1545, loss: 0.2521376609802246 2023-01-23 09:38:19.502279: step: 3064/1545, loss: 0.24471420049667358 2023-01-23 09:38:20.364180: step: 3066/1545, loss: 0.48744750022888184 2023-01-23 09:38:21.265160: step: 3068/1545, loss: 0.6624106764793396 2023-01-23 09:38:22.156688: step: 3070/1545, loss: 0.13263757526874542 2023-01-23 09:38:22.994453: step: 3072/1545, loss: 0.9954245686531067 2023-01-23 09:38:23.876500: step: 3074/1545, loss: 0.0771937444806099 2023-01-23 09:38:24.790236: step: 3076/1545, loss: 0.18825960159301758 2023-01-23 09:38:25.688996: step: 3078/1545, loss: 0.08376037329435349 2023-01-23 09:38:26.553963: step: 3080/1545, loss: 0.4205624461174011 2023-01-23 09:38:27.439450: step: 3082/1545, loss: 0.17245371639728546 2023-01-23 09:38:28.339873: step: 3084/1545, loss: 0.053444311022758484 2023-01-23 09:38:29.174599: step: 3086/1545, loss: 0.3919764757156372 2023-01-23 09:38:30.035376: step: 3088/1545, loss: 6.344491004943848 2023-01-23 09:38:30.892004: step: 3090/1545, loss: 0.10561300814151764 ================================================== Loss: 0.330 -------------------- Dev Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.651816810178987, 'r': 0.645970919504736, 'f1': 0.648880698421424}, 'combined': 0.42791892581748586, 'epoch': 9} Test Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7159741031102995, 'r': 0.7088554313394132, 'f1': 0.71239698422466}, 'combined': 0.497310285671665, 'epoch': 9} Dev Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.6540410788569386, 'r': 0.6466702177127959, 'f1': 0.6503347637141906}, 'combined': 0.4374624236395757, 'epoch': 9} Test Korean: {'event': {'p': 0.6354497354497355, 'r': 0.7679028132992327, 'f1': 0.6954255935147655}, 'argument': {'p': 0.7132062904851311, 'r': 0.7077515578619179, 'f1': 0.7104684544372034}, 'combined': 0.4940779466005103, 'epoch': 9} Dev Russian: {'event': {'p': 0.5708661417322834, 'r': 0.7723035952063915, 'f1': 0.656479909451047}, 'argument': {'p': 0.6537343970311752, 'r': 0.6579429875700025, 'f1': 0.6558319405510614}, 'combined': 0.43054049294806523, 'epoch': 9} Test Russian: {'event': {'p': 0.6273044344793224, 'r': 0.8049872122762148, 'f1': 0.7051246149537944}, 'argument': {'p': 0.7177230819877092, 'r': 0.7201423732753082, 'f1': 0.7189306923331735}, 'combined': 0.5069357276098938, 'epoch': 9} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6557547956630525, 'r': 0.5907212622088654, 'f1': 0.6215415019762845}, 'combined': 0.43319559228650145, 'epoch': 9} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6633986928104574, 'r': 0.46990740740740733, 'f1': 0.5501355013550133}, 'combined': 0.3474540008557979, 'epoch': 9} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5830037357738188, 'r': 0.5934145167697799, 'f1': 0.5881630608691624}, 'combined': 0.32758448959801445, 'epoch': 9} New best korean model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.6540410788569386, 'r': 0.6466702177127959, 'f1': 0.6503347637141906}, 'combined': 0.4374624236395757, 'epoch': 9} Test for Korean: {'event': {'p': 0.6354497354497355, 'r': 0.7679028132992327, 'f1': 0.6954255935147655}, 'argument': {'p': 0.7132062904851311, 'r': 0.7077515578619179, 'f1': 0.7104684544372034}, 'combined': 0.4940779466005103, 'epoch': 9} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6633986928104574, 'r': 0.46990740740740733, 'f1': 0.5501355013550133}, 'combined': 0.3474540008557979, 'epoch': 9} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 10 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 09:43:52.846525: step: 2/1545, loss: 0.22413606941699982 2023-01-23 09:43:53.789671: step: 4/1545, loss: 0.1654912382364273 2023-01-23 09:43:54.662071: step: 6/1545, loss: 0.5259726643562317 2023-01-23 09:43:55.524713: step: 8/1545, loss: 0.20014390349388123 2023-01-23 09:43:56.459836: step: 10/1545, loss: 0.056576140224933624 2023-01-23 09:43:57.340912: step: 12/1545, loss: 0.1031387597322464 2023-01-23 09:43:58.176176: step: 14/1545, loss: 0.13945038616657257 2023-01-23 09:43:58.998596: step: 16/1545, loss: 0.04875738173723221 2023-01-23 09:43:59.921146: step: 18/1545, loss: 0.15284600853919983 2023-01-23 09:44:00.800187: step: 20/1545, loss: 0.1575302630662918 2023-01-23 09:44:01.638932: step: 22/1545, loss: 0.11245477199554443 2023-01-23 09:44:02.502348: step: 24/1545, loss: 0.42231547832489014 2023-01-23 09:44:03.419496: step: 26/1545, loss: 0.2130451500415802 2023-01-23 09:44:04.333620: step: 28/1545, loss: 0.24116511642932892 2023-01-23 09:44:05.192339: step: 30/1545, loss: 0.06253056973218918 2023-01-23 09:44:06.145546: step: 32/1545, loss: 0.014589548110961914 2023-01-23 09:44:06.998333: step: 34/1545, loss: 0.0625946894288063 2023-01-23 09:44:07.880723: step: 36/1545, loss: 0.04938957095146179 2023-01-23 09:44:08.789924: step: 38/1545, loss: 0.11658162623643875 2023-01-23 09:44:09.683040: step: 40/1545, loss: 0.15219423174858093 2023-01-23 09:44:10.581785: step: 42/1545, loss: 0.4169021248817444 2023-01-23 09:44:11.447013: step: 44/1545, loss: 0.23590271174907684 2023-01-23 09:44:12.313581: step: 46/1545, loss: 0.2966994047164917 2023-01-23 09:44:13.141577: step: 48/1545, loss: 0.3088845908641815 2023-01-23 09:44:13.998236: step: 50/1545, loss: 0.1092364639043808 2023-01-23 09:44:14.862219: step: 52/1545, loss: 0.09574355185031891 2023-01-23 09:44:15.782803: step: 54/1545, loss: 0.11545682698488235 2023-01-23 09:44:16.696923: step: 56/1545, loss: 0.7047093510627747 2023-01-23 09:44:17.652111: step: 58/1545, loss: 0.046057216823101044 2023-01-23 09:44:18.505755: step: 60/1545, loss: 0.3647226393222809 2023-01-23 09:44:19.382697: step: 62/1545, loss: 0.4933687746524811 2023-01-23 09:44:20.245595: step: 64/1545, loss: 0.06283893436193466 2023-01-23 09:44:21.086604: step: 66/1545, loss: 0.36179181933403015 2023-01-23 09:44:21.921791: step: 68/1545, loss: 0.03957710042595863 2023-01-23 09:44:22.824135: step: 70/1545, loss: 0.09525591880083084 2023-01-23 09:44:23.753148: step: 72/1545, loss: 0.12230558693408966 2023-01-23 09:44:24.613879: step: 74/1545, loss: 0.04613501951098442 2023-01-23 09:44:25.513879: step: 76/1545, loss: 0.09982896596193314 2023-01-23 09:44:26.380743: step: 78/1545, loss: 0.41594696044921875 2023-01-23 09:44:27.270396: step: 80/1545, loss: 0.020095499232411385 2023-01-23 09:44:28.134379: step: 82/1545, loss: 2.6910994052886963 2023-01-23 09:44:29.007796: step: 84/1545, loss: 0.5042444467544556 2023-01-23 09:44:29.922732: step: 86/1545, loss: 2.000436782836914 2023-01-23 09:44:30.821175: step: 88/1545, loss: 0.09649036079645157 2023-01-23 09:44:31.701493: step: 90/1545, loss: 0.3595271408557892 2023-01-23 09:44:32.544104: step: 92/1545, loss: 0.06577525287866592 2023-01-23 09:44:33.444865: step: 94/1545, loss: 0.07238951325416565 2023-01-23 09:44:34.356712: step: 96/1545, loss: 0.3049885928630829 2023-01-23 09:44:35.231739: step: 98/1545, loss: 0.1950405091047287 2023-01-23 09:44:36.091282: step: 100/1545, loss: 0.04625900089740753 2023-01-23 09:44:36.934627: step: 102/1545, loss: 0.15728074312210083 2023-01-23 09:44:37.794396: step: 104/1545, loss: 0.4332473874092102 2023-01-23 09:44:38.717629: step: 106/1545, loss: 0.1965021938085556 2023-01-23 09:44:39.573633: step: 108/1545, loss: 4.926476955413818 2023-01-23 09:44:40.420606: step: 110/1545, loss: 0.11345233023166656 2023-01-23 09:44:41.301603: step: 112/1545, loss: 0.032391395419836044 2023-01-23 09:44:42.161565: step: 114/1545, loss: 0.5319706201553345 2023-01-23 09:44:43.136589: step: 116/1545, loss: 0.2848682105541229 2023-01-23 09:44:44.058896: step: 118/1545, loss: 0.2541237473487854 2023-01-23 09:44:44.911381: step: 120/1545, loss: 0.13458764553070068 2023-01-23 09:44:45.786892: step: 122/1545, loss: 0.135095477104187 2023-01-23 09:44:46.657060: step: 124/1545, loss: 0.45172759890556335 2023-01-23 09:44:47.528184: step: 126/1545, loss: 0.1639406979084015 2023-01-23 09:44:48.435989: step: 128/1545, loss: 0.05179377272725105 2023-01-23 09:44:49.338353: step: 130/1545, loss: 0.49966153502464294 2023-01-23 09:44:50.203389: step: 132/1545, loss: 0.18270038068294525 2023-01-23 09:44:51.056384: step: 134/1545, loss: 0.2528958320617676 2023-01-23 09:44:51.958829: step: 136/1545, loss: 0.4919145107269287 2023-01-23 09:44:52.839739: step: 138/1545, loss: 0.18548743426799774 2023-01-23 09:44:53.755493: step: 140/1545, loss: 0.07282200455665588 2023-01-23 09:44:54.672373: step: 142/1545, loss: 0.33273452520370483 2023-01-23 09:44:55.578421: step: 144/1545, loss: 0.035969533026218414 2023-01-23 09:44:56.429616: step: 146/1545, loss: 0.14807556569576263 2023-01-23 09:44:57.279108: step: 148/1545, loss: 0.3227521479129791 2023-01-23 09:44:58.198048: step: 150/1545, loss: 0.1395292729139328 2023-01-23 09:44:59.057625: step: 152/1545, loss: 0.1869668811559677 2023-01-23 09:44:59.954951: step: 154/1545, loss: 0.2687244415283203 2023-01-23 09:45:00.824719: step: 156/1545, loss: 0.10729986429214478 2023-01-23 09:45:01.723959: step: 158/1545, loss: 0.265912801027298 2023-01-23 09:45:02.576570: step: 160/1545, loss: 0.06842370331287384 2023-01-23 09:45:03.495314: step: 162/1545, loss: 0.1684257984161377 2023-01-23 09:45:04.516216: step: 164/1545, loss: 0.3615742623806 2023-01-23 09:45:05.379580: step: 166/1545, loss: 0.5007614493370056 2023-01-23 09:45:06.259276: step: 168/1545, loss: 0.2625722885131836 2023-01-23 09:45:07.136117: step: 170/1545, loss: 0.1705288589000702 2023-01-23 09:45:07.996154: step: 172/1545, loss: 0.0359283871948719 2023-01-23 09:45:08.863040: step: 174/1545, loss: 0.08891551196575165 2023-01-23 09:45:09.784505: step: 176/1545, loss: 0.5180286765098572 2023-01-23 09:45:10.651687: step: 178/1545, loss: 0.157057523727417 2023-01-23 09:45:11.591388: step: 180/1545, loss: 0.12866152822971344 2023-01-23 09:45:12.461848: step: 182/1545, loss: 0.4800706207752228 2023-01-23 09:45:13.308736: step: 184/1545, loss: 0.12945595383644104 2023-01-23 09:45:14.181469: step: 186/1545, loss: 0.4420894980430603 2023-01-23 09:45:15.075441: step: 188/1545, loss: 0.16585727035999298 2023-01-23 09:45:15.987915: step: 190/1545, loss: 0.20374378561973572 2023-01-23 09:45:16.825780: step: 192/1545, loss: 0.5605695247650146 2023-01-23 09:45:17.715962: step: 194/1545, loss: 0.1728794425725937 2023-01-23 09:45:18.558143: step: 196/1545, loss: 0.9544681310653687 2023-01-23 09:45:19.416336: step: 198/1545, loss: 0.2926648259162903 2023-01-23 09:45:20.335073: step: 200/1545, loss: 0.25254932045936584 2023-01-23 09:45:21.190492: step: 202/1545, loss: 0.20214420557022095 2023-01-23 09:45:22.077912: step: 204/1545, loss: 0.1095895916223526 2023-01-23 09:45:22.983776: step: 206/1545, loss: 0.16983814537525177 2023-01-23 09:45:23.905026: step: 208/1545, loss: 0.19698438048362732 2023-01-23 09:45:24.778644: step: 210/1545, loss: 0.27746590971946716 2023-01-23 09:45:25.626359: step: 212/1545, loss: 0.04964081570506096 2023-01-23 09:45:26.562869: step: 214/1545, loss: 0.07039184868335724 2023-01-23 09:45:27.447776: step: 216/1545, loss: 0.16060300171375275 2023-01-23 09:45:28.361024: step: 218/1545, loss: 2.5055794715881348 2023-01-23 09:45:29.239713: step: 220/1545, loss: 0.11091627180576324 2023-01-23 09:45:30.135457: step: 222/1545, loss: 0.14091306924819946 2023-01-23 09:45:30.983063: step: 224/1545, loss: 0.11115027219057083 2023-01-23 09:45:31.874315: step: 226/1545, loss: 2.325676441192627 2023-01-23 09:45:32.768424: step: 228/1545, loss: 0.18309016525745392 2023-01-23 09:45:33.639886: step: 230/1545, loss: 0.18050681054592133 2023-01-23 09:45:34.525572: step: 232/1545, loss: 0.13467375934123993 2023-01-23 09:45:35.470395: step: 234/1545, loss: 0.05286553502082825 2023-01-23 09:45:36.351027: step: 236/1545, loss: 0.1400039941072464 2023-01-23 09:45:37.210642: step: 238/1545, loss: 0.03538915514945984 2023-01-23 09:45:38.070505: step: 240/1545, loss: 0.2198851853609085 2023-01-23 09:45:38.960693: step: 242/1545, loss: 0.42499834299087524 2023-01-23 09:45:39.830209: step: 244/1545, loss: 0.27581536769866943 2023-01-23 09:45:40.718429: step: 246/1545, loss: 0.07128126174211502 2023-01-23 09:45:41.597323: step: 248/1545, loss: 0.8708692193031311 2023-01-23 09:45:42.490233: step: 250/1545, loss: 0.17612192034721375 2023-01-23 09:45:43.403305: step: 252/1545, loss: 0.17751267552375793 2023-01-23 09:45:44.268387: step: 254/1545, loss: 0.08833629637956619 2023-01-23 09:45:45.146072: step: 256/1545, loss: 0.0394461527466774 2023-01-23 09:45:45.956008: step: 258/1545, loss: 0.1129598319530487 2023-01-23 09:45:46.859702: step: 260/1545, loss: 0.39430665969848633 2023-01-23 09:45:47.788513: step: 262/1545, loss: 1.1068536043167114 2023-01-23 09:45:48.686649: step: 264/1545, loss: 0.12975506484508514 2023-01-23 09:45:49.620174: step: 266/1545, loss: 0.06849966198205948 2023-01-23 09:45:50.517197: step: 268/1545, loss: 0.12395086884498596 2023-01-23 09:45:51.415870: step: 270/1545, loss: 0.22972825169563293 2023-01-23 09:45:52.282396: step: 272/1545, loss: 0.159546360373497 2023-01-23 09:45:53.215568: step: 274/1545, loss: 0.4212409555912018 2023-01-23 09:45:54.056306: step: 276/1545, loss: 0.142861008644104 2023-01-23 09:45:54.955104: step: 278/1545, loss: 0.35549214482307434 2023-01-23 09:45:55.808149: step: 280/1545, loss: 0.07721778750419617 2023-01-23 09:45:56.702662: step: 282/1545, loss: 0.053015194833278656 2023-01-23 09:45:57.553899: step: 284/1545, loss: 0.08982907235622406 2023-01-23 09:45:58.474574: step: 286/1545, loss: 0.4695724546909332 2023-01-23 09:45:59.414057: step: 288/1545, loss: 0.06483037024736404 2023-01-23 09:46:00.306928: step: 290/1545, loss: 0.10365156829357147 2023-01-23 09:46:01.213182: step: 292/1545, loss: 0.3267495334148407 2023-01-23 09:46:02.045479: step: 294/1545, loss: 0.2538785934448242 2023-01-23 09:46:02.961154: step: 296/1545, loss: 0.10514795780181885 2023-01-23 09:46:03.871063: step: 298/1545, loss: 0.8250225186347961 2023-01-23 09:46:04.738190: step: 300/1545, loss: 0.040155429393053055 2023-01-23 09:46:05.646295: step: 302/1545, loss: 0.19543024897575378 2023-01-23 09:46:06.523297: step: 304/1545, loss: 0.14168643951416016 2023-01-23 09:46:07.419626: step: 306/1545, loss: 0.10945162177085876 2023-01-23 09:46:08.306303: step: 308/1545, loss: 0.06387783586978912 2023-01-23 09:46:09.187739: step: 310/1545, loss: 0.17981502413749695 2023-01-23 09:46:10.052660: step: 312/1545, loss: 0.16173167526721954 2023-01-23 09:46:10.953917: step: 314/1545, loss: 0.14282260835170746 2023-01-23 09:46:11.851217: step: 316/1545, loss: 0.13824579119682312 2023-01-23 09:46:12.726814: step: 318/1545, loss: 0.2832813858985901 2023-01-23 09:46:13.612709: step: 320/1545, loss: 0.32478535175323486 2023-01-23 09:46:14.474787: step: 322/1545, loss: 0.15287315845489502 2023-01-23 09:46:15.374656: step: 324/1545, loss: 0.16169582307338715 2023-01-23 09:46:16.233120: step: 326/1545, loss: 0.06374470144510269 2023-01-23 09:46:17.121231: step: 328/1545, loss: 0.39501282572746277 2023-01-23 09:46:18.037066: step: 330/1545, loss: 0.1408875733613968 2023-01-23 09:46:18.980450: step: 332/1545, loss: 0.1974254548549652 2023-01-23 09:46:19.861970: step: 334/1545, loss: 0.03759607672691345 2023-01-23 09:46:20.734744: step: 336/1545, loss: 0.12670670449733734 2023-01-23 09:46:21.638514: step: 338/1545, loss: 0.013917584903538227 2023-01-23 09:46:22.515328: step: 340/1545, loss: 0.14532244205474854 2023-01-23 09:46:23.401901: step: 342/1545, loss: 0.1292668879032135 2023-01-23 09:46:24.290618: step: 344/1545, loss: 0.38692766427993774 2023-01-23 09:46:25.224980: step: 346/1545, loss: 0.2834950387477875 2023-01-23 09:46:26.114645: step: 348/1545, loss: 0.169884592294693 2023-01-23 09:46:26.988302: step: 350/1545, loss: 0.9327663779258728 2023-01-23 09:46:27.935280: step: 352/1545, loss: 0.17832380533218384 2023-01-23 09:46:28.840283: step: 354/1545, loss: 0.10555922240018845 2023-01-23 09:46:29.719181: step: 356/1545, loss: 0.3906588852405548 2023-01-23 09:46:30.601908: step: 358/1545, loss: 0.0308969896286726 2023-01-23 09:46:31.498545: step: 360/1545, loss: 0.5994752645492554 2023-01-23 09:46:32.364234: step: 362/1545, loss: 1.4714093208312988 2023-01-23 09:46:33.238209: step: 364/1545, loss: 0.13591642677783966 2023-01-23 09:46:34.116186: step: 366/1545, loss: 0.11053771525621414 2023-01-23 09:46:34.996772: step: 368/1545, loss: 0.08485499024391174 2023-01-23 09:46:35.891348: step: 370/1545, loss: 0.36844369769096375 2023-01-23 09:46:36.802589: step: 372/1545, loss: 0.47647830843925476 2023-01-23 09:46:37.645176: step: 374/1545, loss: 0.02997061051428318 2023-01-23 09:46:38.513085: step: 376/1545, loss: 0.2814804017543793 2023-01-23 09:46:39.335787: step: 378/1545, loss: 0.2659453749656677 2023-01-23 09:46:40.189365: step: 380/1545, loss: 0.4621703028678894 2023-01-23 09:46:41.034495: step: 382/1545, loss: 0.047183796763420105 2023-01-23 09:46:41.903651: step: 384/1545, loss: 0.24317683279514313 2023-01-23 09:46:42.821960: step: 386/1545, loss: 0.0525372289121151 2023-01-23 09:46:43.662790: step: 388/1545, loss: 0.23967383801937103 2023-01-23 09:46:44.581487: step: 390/1545, loss: 0.11611214280128479 2023-01-23 09:46:45.551100: step: 392/1545, loss: 0.29865124821662903 2023-01-23 09:46:46.428130: step: 394/1545, loss: 1.9190356731414795 2023-01-23 09:46:47.326665: step: 396/1545, loss: 0.3367970287799835 2023-01-23 09:46:48.197153: step: 398/1545, loss: 0.3835631012916565 2023-01-23 09:46:49.093837: step: 400/1545, loss: 0.4071699380874634 2023-01-23 09:46:49.990745: step: 402/1545, loss: 0.3303014636039734 2023-01-23 09:46:50.930590: step: 404/1545, loss: 0.06770122796297073 2023-01-23 09:46:51.809204: step: 406/1545, loss: 0.11104317754507065 2023-01-23 09:46:52.639445: step: 408/1545, loss: 0.1410769671201706 2023-01-23 09:46:53.553561: step: 410/1545, loss: 0.32906755805015564 2023-01-23 09:46:54.401976: step: 412/1545, loss: 0.07317489385604858 2023-01-23 09:46:55.263329: step: 414/1545, loss: 0.035415273159742355 2023-01-23 09:46:56.190622: step: 416/1545, loss: 0.3485484719276428 2023-01-23 09:46:57.070793: step: 418/1545, loss: 0.06291449815034866 2023-01-23 09:46:58.025081: step: 420/1545, loss: 0.1646093726158142 2023-01-23 09:46:58.883557: step: 422/1545, loss: 0.2176506370306015 2023-01-23 09:46:59.821626: step: 424/1545, loss: 0.08935494720935822 2023-01-23 09:47:00.740124: step: 426/1545, loss: 0.44023093581199646 2023-01-23 09:47:01.602139: step: 428/1545, loss: 0.04880579188466072 2023-01-23 09:47:02.459600: step: 430/1545, loss: 0.03279292583465576 2023-01-23 09:47:03.304996: step: 432/1545, loss: 0.5874313712120056 2023-01-23 09:47:04.208631: step: 434/1545, loss: 0.5562793016433716 2023-01-23 09:47:05.069984: step: 436/1545, loss: 0.12211448699235916 2023-01-23 09:47:05.920440: step: 438/1545, loss: 0.405303418636322 2023-01-23 09:47:06.767662: step: 440/1545, loss: 0.3346354365348816 2023-01-23 09:47:07.655807: step: 442/1545, loss: 0.38091322779655457 2023-01-23 09:47:08.522383: step: 444/1545, loss: 0.18250678479671478 2023-01-23 09:47:09.402405: step: 446/1545, loss: 0.267074853181839 2023-01-23 09:47:10.277097: step: 448/1545, loss: 0.08239283412694931 2023-01-23 09:47:11.168222: step: 450/1545, loss: 0.05623785778880119 2023-01-23 09:47:12.070619: step: 452/1545, loss: 0.09391635656356812 2023-01-23 09:47:12.985026: step: 454/1545, loss: 0.40936487913131714 2023-01-23 09:47:13.829642: step: 456/1545, loss: 0.0638638362288475 2023-01-23 09:47:14.714797: step: 458/1545, loss: 0.08874884247779846 2023-01-23 09:47:15.599771: step: 460/1545, loss: 0.06663109362125397 2023-01-23 09:47:16.526935: step: 462/1545, loss: 0.256089448928833 2023-01-23 09:47:17.407954: step: 464/1545, loss: 0.30096006393432617 2023-01-23 09:47:18.337401: step: 466/1545, loss: 0.03555159270763397 2023-01-23 09:47:19.251743: step: 468/1545, loss: 0.3534572720527649 2023-01-23 09:47:20.228659: step: 470/1545, loss: 0.10899006575345993 2023-01-23 09:47:21.148952: step: 472/1545, loss: 0.0774589478969574 2023-01-23 09:47:22.014538: step: 474/1545, loss: 0.27185940742492676 2023-01-23 09:47:22.939259: step: 476/1545, loss: 0.09121567755937576 2023-01-23 09:47:23.782752: step: 478/1545, loss: 0.06995400041341782 2023-01-23 09:47:24.665555: step: 480/1545, loss: 0.08627286553382874 2023-01-23 09:47:25.483732: step: 482/1545, loss: 0.19065719842910767 2023-01-23 09:47:26.339313: step: 484/1545, loss: 0.1557469218969345 2023-01-23 09:47:27.244537: step: 486/1545, loss: 0.22576838731765747 2023-01-23 09:47:28.114136: step: 488/1545, loss: 1.0493669509887695 2023-01-23 09:47:28.963589: step: 490/1545, loss: 0.06645886600017548 2023-01-23 09:47:29.826283: step: 492/1545, loss: 0.10778074711561203 2023-01-23 09:47:30.695542: step: 494/1545, loss: 0.1484874039888382 2023-01-23 09:47:31.577430: step: 496/1545, loss: 0.11800988763570786 2023-01-23 09:47:32.626793: step: 498/1545, loss: 0.04364119470119476 2023-01-23 09:47:33.529766: step: 500/1545, loss: 0.16245196759700775 2023-01-23 09:47:34.405885: step: 502/1545, loss: 0.06028962880373001 2023-01-23 09:47:35.310024: step: 504/1545, loss: 0.22289270162582397 2023-01-23 09:47:36.199490: step: 506/1545, loss: 0.11597734689712524 2023-01-23 09:47:37.163854: step: 508/1545, loss: 0.054420024156570435 2023-01-23 09:47:38.057212: step: 510/1545, loss: 0.40920522809028625 2023-01-23 09:47:38.958516: step: 512/1545, loss: 0.07464943826198578 2023-01-23 09:47:39.879707: step: 514/1545, loss: 0.07427520304918289 2023-01-23 09:47:40.761253: step: 516/1545, loss: 0.17616836726665497 2023-01-23 09:47:41.603799: step: 518/1545, loss: 0.13074633479118347 2023-01-23 09:47:42.456718: step: 520/1545, loss: 0.05590437352657318 2023-01-23 09:47:43.350006: step: 522/1545, loss: 0.14663255214691162 2023-01-23 09:47:44.206199: step: 524/1545, loss: 0.4608725607395172 2023-01-23 09:47:45.137309: step: 526/1545, loss: 0.7020610570907593 2023-01-23 09:47:46.018643: step: 528/1545, loss: 0.03417757898569107 2023-01-23 09:47:46.911378: step: 530/1545, loss: 0.015806378796696663 2023-01-23 09:47:47.804310: step: 532/1545, loss: 0.4685588479042053 2023-01-23 09:47:48.679451: step: 534/1545, loss: 0.222885861992836 2023-01-23 09:47:49.659976: step: 536/1545, loss: 0.10857963562011719 2023-01-23 09:47:50.540045: step: 538/1545, loss: 0.15205077826976776 2023-01-23 09:47:51.488446: step: 540/1545, loss: 0.1098686084151268 2023-01-23 09:47:52.347018: step: 542/1545, loss: 0.24867157638072968 2023-01-23 09:47:53.235271: step: 544/1545, loss: 0.3353719115257263 2023-01-23 09:47:54.102932: step: 546/1545, loss: 0.8373434543609619 2023-01-23 09:47:54.962763: step: 548/1545, loss: 0.024988442659378052 2023-01-23 09:47:55.868161: step: 550/1545, loss: 0.29556137323379517 2023-01-23 09:47:56.713575: step: 552/1545, loss: 0.0864701122045517 2023-01-23 09:47:57.614323: step: 554/1545, loss: 0.17794211208820343 2023-01-23 09:47:58.503058: step: 556/1545, loss: 0.18282775580883026 2023-01-23 09:47:59.377912: step: 558/1545, loss: 0.06584662944078445 2023-01-23 09:48:00.232099: step: 560/1545, loss: 0.19915629923343658 2023-01-23 09:48:01.136076: step: 562/1545, loss: 0.04990807920694351 2023-01-23 09:48:02.047569: step: 564/1545, loss: 0.363076776266098 2023-01-23 09:48:02.930774: step: 566/1545, loss: 0.09713584184646606 2023-01-23 09:48:03.865342: step: 568/1545, loss: 0.0901791974902153 2023-01-23 09:48:04.747265: step: 570/1545, loss: 0.4554300904273987 2023-01-23 09:48:05.610033: step: 572/1545, loss: 0.052882228046655655 2023-01-23 09:48:06.525235: step: 574/1545, loss: 0.05074668303132057 2023-01-23 09:48:07.458687: step: 576/1545, loss: 0.02773766778409481 2023-01-23 09:48:08.354404: step: 578/1545, loss: 0.07936025410890579 2023-01-23 09:48:09.222136: step: 580/1545, loss: 0.1400427669286728 2023-01-23 09:48:10.086581: step: 582/1545, loss: 0.1571771502494812 2023-01-23 09:48:10.938275: step: 584/1545, loss: 0.2109903246164322 2023-01-23 09:48:11.819986: step: 586/1545, loss: 0.1483229547739029 2023-01-23 09:48:12.728995: step: 588/1545, loss: 0.10630834847688675 2023-01-23 09:48:13.662870: step: 590/1545, loss: 0.06655430793762207 2023-01-23 09:48:14.540447: step: 592/1545, loss: 0.05085672438144684 2023-01-23 09:48:15.431861: step: 594/1545, loss: 3.155658006668091 2023-01-23 09:48:16.383829: step: 596/1545, loss: 0.49311724305152893 2023-01-23 09:48:17.267502: step: 598/1545, loss: 0.20791788399219513 2023-01-23 09:48:18.125086: step: 600/1545, loss: 0.2877371907234192 2023-01-23 09:48:18.986902: step: 602/1545, loss: 0.1611207276582718 2023-01-23 09:48:19.872985: step: 604/1545, loss: 0.221498042345047 2023-01-23 09:48:20.753397: step: 606/1545, loss: 0.07402794063091278 2023-01-23 09:48:21.638363: step: 608/1545, loss: 0.2535630464553833 2023-01-23 09:48:22.575067: step: 610/1545, loss: 0.11928143352270126 2023-01-23 09:48:23.506061: step: 612/1545, loss: 0.08949633687734604 2023-01-23 09:48:24.382333: step: 614/1545, loss: 0.3098211884498596 2023-01-23 09:48:25.263666: step: 616/1545, loss: 0.11064571142196655 2023-01-23 09:48:26.117625: step: 618/1545, loss: 0.0888923928141594 2023-01-23 09:48:27.014333: step: 620/1545, loss: 0.1755247265100479 2023-01-23 09:48:27.887654: step: 622/1545, loss: 0.07520002871751785 2023-01-23 09:48:28.762056: step: 624/1545, loss: 0.012724173255264759 2023-01-23 09:48:29.597193: step: 626/1545, loss: 0.033409420400857925 2023-01-23 09:48:30.464880: step: 628/1545, loss: 0.19494999945163727 2023-01-23 09:48:31.353254: step: 630/1545, loss: 0.13640189170837402 2023-01-23 09:48:32.230308: step: 632/1545, loss: 0.34317082166671753 2023-01-23 09:48:33.182344: step: 634/1545, loss: 0.12827928364276886 2023-01-23 09:48:34.060079: step: 636/1545, loss: 0.2092057764530182 2023-01-23 09:48:34.959548: step: 638/1545, loss: 0.023640546947717667 2023-01-23 09:48:35.862782: step: 640/1545, loss: 0.45848947763442993 2023-01-23 09:48:36.749575: step: 642/1545, loss: 0.09377706050872803 2023-01-23 09:48:37.580433: step: 644/1545, loss: 0.06396675109863281 2023-01-23 09:48:38.439119: step: 646/1545, loss: 0.4036923944950104 2023-01-23 09:48:39.309002: step: 648/1545, loss: 0.01588532142341137 2023-01-23 09:48:40.186597: step: 650/1545, loss: 0.14069512486457825 2023-01-23 09:48:41.055457: step: 652/1545, loss: 0.22240079939365387 2023-01-23 09:48:41.948305: step: 654/1545, loss: 0.18027323484420776 2023-01-23 09:48:42.829603: step: 656/1545, loss: 0.21678519248962402 2023-01-23 09:48:43.698636: step: 658/1545, loss: 0.19712162017822266 2023-01-23 09:48:44.601340: step: 660/1545, loss: 0.2611413896083832 2023-01-23 09:48:45.505081: step: 662/1545, loss: 0.0816437229514122 2023-01-23 09:48:46.379592: step: 664/1545, loss: 0.1241762638092041 2023-01-23 09:48:47.227261: step: 666/1545, loss: 2.4521021842956543 2023-01-23 09:48:48.074083: step: 668/1545, loss: 0.23062440752983093 2023-01-23 09:48:48.964572: step: 670/1545, loss: 0.1451677829027176 2023-01-23 09:48:49.816874: step: 672/1545, loss: 0.09715922921895981 2023-01-23 09:48:50.722227: step: 674/1545, loss: 0.4367333948612213 2023-01-23 09:48:51.645676: step: 676/1545, loss: 0.0773543268442154 2023-01-23 09:48:52.613069: step: 678/1545, loss: 0.20099864900112152 2023-01-23 09:48:53.499980: step: 680/1545, loss: 0.10262434184551239 2023-01-23 09:48:54.388458: step: 682/1545, loss: 0.47436100244522095 2023-01-23 09:48:55.257029: step: 684/1545, loss: 0.6298038363456726 2023-01-23 09:48:56.235212: step: 686/1545, loss: 0.3444722294807434 2023-01-23 09:48:57.097648: step: 688/1545, loss: 0.09477539360523224 2023-01-23 09:48:58.067404: step: 690/1545, loss: 0.0774192363023758 2023-01-23 09:48:58.951248: step: 692/1545, loss: 0.11644609272480011 2023-01-23 09:48:59.801162: step: 694/1545, loss: 0.05890214815735817 2023-01-23 09:49:00.667399: step: 696/1545, loss: 0.15386050939559937 2023-01-23 09:49:01.520228: step: 698/1545, loss: 0.3318123519420624 2023-01-23 09:49:02.391694: step: 700/1545, loss: 0.08981697261333466 2023-01-23 09:49:03.293900: step: 702/1545, loss: 0.23085154592990875 2023-01-23 09:49:04.176918: step: 704/1545, loss: 0.14592188596725464 2023-01-23 09:49:05.017053: step: 706/1545, loss: 1.0403410196304321 2023-01-23 09:49:05.893005: step: 708/1545, loss: 0.14385174214839935 2023-01-23 09:49:06.765605: step: 710/1545, loss: 0.2285742312669754 2023-01-23 09:49:07.630049: step: 712/1545, loss: 0.09056959301233292 2023-01-23 09:49:08.509049: step: 714/1545, loss: 0.24010255932807922 2023-01-23 09:49:09.352780: step: 716/1545, loss: 0.11638287454843521 2023-01-23 09:49:10.225874: step: 718/1545, loss: 0.2748422920703888 2023-01-23 09:49:11.044587: step: 720/1545, loss: 0.07453149557113647 2023-01-23 09:49:11.955944: step: 722/1545, loss: 0.3137589991092682 2023-01-23 09:49:12.839900: step: 724/1545, loss: 0.024162236601114273 2023-01-23 09:49:13.706626: step: 726/1545, loss: 0.1564832478761673 2023-01-23 09:49:14.565715: step: 728/1545, loss: 0.26233789324760437 2023-01-23 09:49:15.458417: step: 730/1545, loss: 0.0646611675620079 2023-01-23 09:49:16.347021: step: 732/1545, loss: 0.2345549762248993 2023-01-23 09:49:17.276687: step: 734/1545, loss: 0.0947190374135971 2023-01-23 09:49:18.152771: step: 736/1545, loss: 0.06679324060678482 2023-01-23 09:49:19.034444: step: 738/1545, loss: 0.3188512325286865 2023-01-23 09:49:19.893623: step: 740/1545, loss: 0.028612259775400162 2023-01-23 09:49:20.776874: step: 742/1545, loss: 0.11214342713356018 2023-01-23 09:49:21.717356: step: 744/1545, loss: 0.43010392785072327 2023-01-23 09:49:22.619170: step: 746/1545, loss: 0.06756579130887985 2023-01-23 09:49:23.477070: step: 748/1545, loss: 0.10442841053009033 2023-01-23 09:49:24.332548: step: 750/1545, loss: 0.11731813848018646 2023-01-23 09:49:25.208326: step: 752/1545, loss: 0.13695700466632843 2023-01-23 09:49:26.072099: step: 754/1545, loss: 0.09363440424203873 2023-01-23 09:49:26.947407: step: 756/1545, loss: 0.22473503649234772 2023-01-23 09:49:27.837102: step: 758/1545, loss: 1.2216911315917969 2023-01-23 09:49:28.682701: step: 760/1545, loss: 0.158397376537323 2023-01-23 09:49:29.539539: step: 762/1545, loss: 0.1888786405324936 2023-01-23 09:49:30.455179: step: 764/1545, loss: 1.2978465557098389 2023-01-23 09:49:31.352642: step: 766/1545, loss: 0.6846345663070679 2023-01-23 09:49:32.180349: step: 768/1545, loss: 0.39274317026138306 2023-01-23 09:49:33.033688: step: 770/1545, loss: 0.05356745049357414 2023-01-23 09:49:33.912851: step: 772/1545, loss: 0.05112805590033531 2023-01-23 09:49:34.781969: step: 774/1545, loss: 0.10555528104305267 2023-01-23 09:49:35.655399: step: 776/1545, loss: 0.11812632530927658 2023-01-23 09:49:36.561297: step: 778/1545, loss: 0.20517393946647644 2023-01-23 09:49:37.419038: step: 780/1545, loss: 0.16371756792068481 2023-01-23 09:49:38.301619: step: 782/1545, loss: 0.08279559761285782 2023-01-23 09:49:39.201771: step: 784/1545, loss: 0.9480527639389038 2023-01-23 09:49:40.172719: step: 786/1545, loss: 0.23719744384288788 2023-01-23 09:49:41.112728: step: 788/1545, loss: 0.041883453726768494 2023-01-23 09:49:42.013930: step: 790/1545, loss: 0.4172106981277466 2023-01-23 09:49:42.961191: step: 792/1545, loss: 0.30001989006996155 2023-01-23 09:49:43.878847: step: 794/1545, loss: 0.38774511218070984 2023-01-23 09:49:44.720025: step: 796/1545, loss: 0.20197971165180206 2023-01-23 09:49:45.587935: step: 798/1545, loss: 0.617996871471405 2023-01-23 09:49:46.500634: step: 800/1545, loss: 0.2960008382797241 2023-01-23 09:49:47.389542: step: 802/1545, loss: 0.2525210976600647 2023-01-23 09:49:48.243350: step: 804/1545, loss: 0.3643510341644287 2023-01-23 09:49:49.115508: step: 806/1545, loss: 0.12686893343925476 2023-01-23 09:49:49.981274: step: 808/1545, loss: 0.25497716665267944 2023-01-23 09:49:50.827665: step: 810/1545, loss: 0.0935625284910202 2023-01-23 09:49:51.716126: step: 812/1545, loss: 0.5753313302993774 2023-01-23 09:49:52.626522: step: 814/1545, loss: 0.0592942014336586 2023-01-23 09:49:53.496377: step: 816/1545, loss: 0.12289700657129288 2023-01-23 09:49:54.343471: step: 818/1545, loss: 0.053908828645944595 2023-01-23 09:49:55.193701: step: 820/1545, loss: 0.3333522081375122 2023-01-23 09:49:56.067205: step: 822/1545, loss: 0.08739233016967773 2023-01-23 09:49:56.918250: step: 824/1545, loss: 0.4040329158306122 2023-01-23 09:49:57.818055: step: 826/1545, loss: 0.11870425939559937 2023-01-23 09:49:58.691480: step: 828/1545, loss: 0.21990564465522766 2023-01-23 09:49:59.569604: step: 830/1545, loss: 0.29547974467277527 2023-01-23 09:50:00.416473: step: 832/1545, loss: 0.1741231083869934 2023-01-23 09:50:01.276572: step: 834/1545, loss: 0.05888361111283302 2023-01-23 09:50:02.119900: step: 836/1545, loss: 0.008773651905357838 2023-01-23 09:50:02.998726: step: 838/1545, loss: 0.29820314049720764 2023-01-23 09:50:03.864009: step: 840/1545, loss: 0.07206528633832932 2023-01-23 09:50:04.736813: step: 842/1545, loss: 0.39738866686820984 2023-01-23 09:50:05.619242: step: 844/1545, loss: 0.18193362653255463 2023-01-23 09:50:06.473507: step: 846/1545, loss: 0.24998433887958527 2023-01-23 09:50:07.304991: step: 848/1545, loss: 0.15720942616462708 2023-01-23 09:50:08.162177: step: 850/1545, loss: 0.2067270129919052 2023-01-23 09:50:09.032285: step: 852/1545, loss: 0.11943956464529037 2023-01-23 09:50:09.914709: step: 854/1545, loss: 0.10134723037481308 2023-01-23 09:50:10.813505: step: 856/1545, loss: 0.21667064726352692 2023-01-23 09:50:11.736380: step: 858/1545, loss: 0.12751398980617523 2023-01-23 09:50:12.595269: step: 860/1545, loss: 0.03856692463159561 2023-01-23 09:50:13.463558: step: 862/1545, loss: 0.0850222036242485 2023-01-23 09:50:14.363841: step: 864/1545, loss: 0.1902507096529007 2023-01-23 09:50:15.187250: step: 866/1545, loss: 0.4546566605567932 2023-01-23 09:50:16.055765: step: 868/1545, loss: 0.40417760610580444 2023-01-23 09:50:17.019856: step: 870/1545, loss: 0.24522191286087036 2023-01-23 09:50:17.880379: step: 872/1545, loss: 0.18602710962295532 2023-01-23 09:50:18.827349: step: 874/1545, loss: 0.06378944218158722 2023-01-23 09:50:19.757835: step: 876/1545, loss: 0.3007725477218628 2023-01-23 09:50:20.605989: step: 878/1545, loss: 0.16485439240932465 2023-01-23 09:50:21.469505: step: 880/1545, loss: 0.09540756791830063 2023-01-23 09:50:22.348982: step: 882/1545, loss: 0.15466630458831787 2023-01-23 09:50:23.262851: step: 884/1545, loss: 0.258244127035141 2023-01-23 09:50:24.172216: step: 886/1545, loss: 0.15584975481033325 2023-01-23 09:50:25.110101: step: 888/1545, loss: 0.18836967647075653 2023-01-23 09:50:25.974241: step: 890/1545, loss: 0.1270005702972412 2023-01-23 09:50:26.881366: step: 892/1545, loss: 0.7554982304573059 2023-01-23 09:50:27.722982: step: 894/1545, loss: 0.5259968042373657 2023-01-23 09:50:28.620068: step: 896/1545, loss: 0.1164795458316803 2023-01-23 09:50:29.528375: step: 898/1545, loss: 0.05384000390768051 2023-01-23 09:50:30.426393: step: 900/1545, loss: 0.558724582195282 2023-01-23 09:50:31.341042: step: 902/1545, loss: 0.08421194553375244 2023-01-23 09:50:32.204958: step: 904/1545, loss: 0.32080063223838806 2023-01-23 09:50:33.086091: step: 906/1545, loss: 0.07252885401248932 2023-01-23 09:50:33.959084: step: 908/1545, loss: 2.0492048263549805 2023-01-23 09:50:34.999477: step: 910/1545, loss: 0.2225046008825302 2023-01-23 09:50:35.856485: step: 912/1545, loss: 0.06979121267795563 2023-01-23 09:50:36.711529: step: 914/1545, loss: 0.0842965766787529 2023-01-23 09:50:37.557411: step: 916/1545, loss: 0.18467305600643158 2023-01-23 09:50:38.476960: step: 918/1545, loss: 0.05277809500694275 2023-01-23 09:50:39.311855: step: 920/1545, loss: 0.32687556743621826 2023-01-23 09:50:40.148091: step: 922/1545, loss: 0.43137118220329285 2023-01-23 09:50:41.032441: step: 924/1545, loss: 0.15682938694953918 2023-01-23 09:50:41.912242: step: 926/1545, loss: 0.1132759377360344 2023-01-23 09:50:42.851353: step: 928/1545, loss: 0.04798581823706627 2023-01-23 09:50:43.747388: step: 930/1545, loss: 0.14700153470039368 2023-01-23 09:50:44.601813: step: 932/1545, loss: 0.024960417300462723 2023-01-23 09:50:45.496815: step: 934/1545, loss: 0.0771644115447998 2023-01-23 09:50:46.388130: step: 936/1545, loss: 0.07221198827028275 2023-01-23 09:50:47.387288: step: 938/1545, loss: 0.9658187627792358 2023-01-23 09:50:48.216169: step: 940/1545, loss: 0.09256359934806824 2023-01-23 09:50:49.148558: step: 942/1545, loss: 2.036885976791382 2023-01-23 09:50:50.031661: step: 944/1545, loss: 0.12357216328382492 2023-01-23 09:50:50.959628: step: 946/1545, loss: 2.2750136852264404 2023-01-23 09:50:51.827630: step: 948/1545, loss: 0.48829877376556396 2023-01-23 09:50:52.731703: step: 950/1545, loss: 0.12262541055679321 2023-01-23 09:50:53.594459: step: 952/1545, loss: 0.11218830198049545 2023-01-23 09:50:54.433993: step: 954/1545, loss: 0.15377362072467804 2023-01-23 09:50:55.272209: step: 956/1545, loss: 0.23774683475494385 2023-01-23 09:50:56.127036: step: 958/1545, loss: 0.2191321849822998 2023-01-23 09:50:56.986267: step: 960/1545, loss: 0.37133145332336426 2023-01-23 09:50:57.857404: step: 962/1545, loss: 0.23738393187522888 2023-01-23 09:50:58.757765: step: 964/1545, loss: 0.09851116687059402 2023-01-23 09:50:59.636083: step: 966/1545, loss: 0.09650295972824097 2023-01-23 09:51:00.548553: step: 968/1545, loss: 0.21542011201381683 2023-01-23 09:51:01.435485: step: 970/1545, loss: 0.011989695020020008 2023-01-23 09:51:02.291821: step: 972/1545, loss: 0.1814127266407013 2023-01-23 09:51:03.224960: step: 974/1545, loss: 0.12111364305019379 2023-01-23 09:51:04.073822: step: 976/1545, loss: 0.276781290769577 2023-01-23 09:51:05.010228: step: 978/1545, loss: 0.09506957232952118 2023-01-23 09:51:05.899793: step: 980/1545, loss: 0.5367242097854614 2023-01-23 09:51:06.805007: step: 982/1545, loss: 0.45424020290374756 2023-01-23 09:51:07.703343: step: 984/1545, loss: 0.4265139698982239 2023-01-23 09:51:08.600656: step: 986/1545, loss: 0.765913188457489 2023-01-23 09:51:09.483376: step: 988/1545, loss: 0.4071747660636902 2023-01-23 09:51:10.352637: step: 990/1545, loss: 0.4405004680156708 2023-01-23 09:51:11.226410: step: 992/1545, loss: 0.3749566376209259 2023-01-23 09:51:12.126557: step: 994/1545, loss: 0.4444880187511444 2023-01-23 09:51:13.045587: step: 996/1545, loss: 0.08482740074396133 2023-01-23 09:51:13.961320: step: 998/1545, loss: 0.05316659435629845 2023-01-23 09:51:14.854112: step: 1000/1545, loss: 0.044545724987983704 2023-01-23 09:51:15.772301: step: 1002/1545, loss: 0.0939553901553154 2023-01-23 09:51:16.645001: step: 1004/1545, loss: 0.07930154353380203 2023-01-23 09:51:17.552656: step: 1006/1545, loss: 0.14162343740463257 2023-01-23 09:51:18.389981: step: 1008/1545, loss: 0.37069252133369446 2023-01-23 09:51:19.321726: step: 1010/1545, loss: 0.35277315974235535 2023-01-23 09:51:20.221172: step: 1012/1545, loss: 0.14838877320289612 2023-01-23 09:51:21.180621: step: 1014/1545, loss: 0.06681276857852936 2023-01-23 09:51:22.050020: step: 1016/1545, loss: 0.22266022861003876 2023-01-23 09:51:22.936635: step: 1018/1545, loss: 0.7662255167961121 2023-01-23 09:51:23.835360: step: 1020/1545, loss: 0.09172698855400085 2023-01-23 09:51:24.743842: step: 1022/1545, loss: 0.11172795295715332 2023-01-23 09:51:25.595971: step: 1024/1545, loss: 0.19525398313999176 2023-01-23 09:51:26.483035: step: 1026/1545, loss: 0.050737183541059494 2023-01-23 09:51:27.352932: step: 1028/1545, loss: 0.06830945611000061 2023-01-23 09:51:28.224984: step: 1030/1545, loss: 0.0925215482711792 2023-01-23 09:51:29.081431: step: 1032/1545, loss: 0.04097803682088852 2023-01-23 09:51:29.948216: step: 1034/1545, loss: 0.3160296678543091 2023-01-23 09:51:30.813963: step: 1036/1545, loss: 0.12974156439304352 2023-01-23 09:51:31.673170: step: 1038/1545, loss: 0.3991544544696808 2023-01-23 09:51:32.536761: step: 1040/1545, loss: 0.43504858016967773 2023-01-23 09:51:33.396312: step: 1042/1545, loss: 0.06114913895726204 2023-01-23 09:51:34.361615: step: 1044/1545, loss: 0.12738625705242157 2023-01-23 09:51:35.242386: step: 1046/1545, loss: 0.01530403085052967 2023-01-23 09:51:36.123473: step: 1048/1545, loss: 0.135097935795784 2023-01-23 09:51:37.004702: step: 1050/1545, loss: 0.563129186630249 2023-01-23 09:51:37.914355: step: 1052/1545, loss: 0.609795868396759 2023-01-23 09:51:38.778092: step: 1054/1545, loss: 0.15653198957443237 2023-01-23 09:51:39.660312: step: 1056/1545, loss: 0.2378876805305481 2023-01-23 09:51:40.602119: step: 1058/1545, loss: 0.02627347782254219 2023-01-23 09:51:41.482692: step: 1060/1545, loss: 0.7427673935890198 2023-01-23 09:51:42.380665: step: 1062/1545, loss: 0.1412818729877472 2023-01-23 09:51:43.252328: step: 1064/1545, loss: 5.934506893157959 2023-01-23 09:51:44.144372: step: 1066/1545, loss: 0.07582971453666687 2023-01-23 09:51:45.015769: step: 1068/1545, loss: 0.07352655380964279 2023-01-23 09:51:45.887643: step: 1070/1545, loss: 0.13506875932216644 2023-01-23 09:51:46.794839: step: 1072/1545, loss: 0.4062909185886383 2023-01-23 09:51:47.673624: step: 1074/1545, loss: 0.18241402506828308 2023-01-23 09:51:48.577086: step: 1076/1545, loss: 0.009195919148623943 2023-01-23 09:51:49.483317: step: 1078/1545, loss: 0.11104276031255722 2023-01-23 09:51:50.370899: step: 1080/1545, loss: 0.6993560194969177 2023-01-23 09:51:51.254534: step: 1082/1545, loss: 0.7419421076774597 2023-01-23 09:51:52.178336: step: 1084/1545, loss: 0.4177963435649872 2023-01-23 09:51:53.038578: step: 1086/1545, loss: 0.13998155295848846 2023-01-23 09:51:53.877731: step: 1088/1545, loss: 0.26786327362060547 2023-01-23 09:51:54.790018: step: 1090/1545, loss: 0.1143965870141983 2023-01-23 09:51:55.718232: step: 1092/1545, loss: 0.025519657880067825 2023-01-23 09:51:56.612689: step: 1094/1545, loss: 0.19616705179214478 2023-01-23 09:51:57.573946: step: 1096/1545, loss: 0.24631009995937347 2023-01-23 09:51:58.464947: step: 1098/1545, loss: 0.19926755130290985 2023-01-23 09:51:59.323207: step: 1100/1545, loss: 0.01695140078663826 2023-01-23 09:52:00.182992: step: 1102/1545, loss: 0.26661184430122375 2023-01-23 09:52:01.041727: step: 1104/1545, loss: 0.10236451029777527 2023-01-23 09:52:01.932386: step: 1106/1545, loss: 0.7085244655609131 2023-01-23 09:52:02.851065: step: 1108/1545, loss: 0.07061704993247986 2023-01-23 09:52:03.725894: step: 1110/1545, loss: 0.31914880871772766 2023-01-23 09:52:04.648367: step: 1112/1545, loss: 0.2893867790699005 2023-01-23 09:52:05.499908: step: 1114/1545, loss: 0.250966340303421 2023-01-23 09:52:06.410995: step: 1116/1545, loss: 0.24718236923217773 2023-01-23 09:52:07.304410: step: 1118/1545, loss: 0.47495412826538086 2023-01-23 09:52:08.259406: step: 1120/1545, loss: 0.12108512222766876 2023-01-23 09:52:09.185360: step: 1122/1545, loss: 0.10128625482320786 2023-01-23 09:52:10.087896: step: 1124/1545, loss: 0.2211536467075348 2023-01-23 09:52:10.986963: step: 1126/1545, loss: 0.30029985308647156 2023-01-23 09:52:11.864975: step: 1128/1545, loss: 0.6472306847572327 2023-01-23 09:52:12.755148: step: 1130/1545, loss: 0.48145154118537903 2023-01-23 09:52:13.635057: step: 1132/1545, loss: 0.14199873805046082 2023-01-23 09:52:14.485733: step: 1134/1545, loss: 0.08791358768939972 2023-01-23 09:52:15.371098: step: 1136/1545, loss: 0.8151964545249939 2023-01-23 09:52:16.274708: step: 1138/1545, loss: 0.34674808382987976 2023-01-23 09:52:17.160191: step: 1140/1545, loss: 0.1859254539012909 2023-01-23 09:52:18.021977: step: 1142/1545, loss: 0.11788716167211533 2023-01-23 09:52:18.880917: step: 1144/1545, loss: 0.2534332275390625 2023-01-23 09:52:19.766517: step: 1146/1545, loss: 0.41307753324508667 2023-01-23 09:52:20.614418: step: 1148/1545, loss: 0.09238946437835693 2023-01-23 09:52:21.532249: step: 1150/1545, loss: 0.22017525136470795 2023-01-23 09:52:22.420247: step: 1152/1545, loss: 0.6242523193359375 2023-01-23 09:52:23.293420: step: 1154/1545, loss: 0.11768274009227753 2023-01-23 09:52:24.190148: step: 1156/1545, loss: 0.18441970646381378 2023-01-23 09:52:25.098575: step: 1158/1545, loss: 0.5800139904022217 2023-01-23 09:52:25.997689: step: 1160/1545, loss: 0.27778923511505127 2023-01-23 09:52:26.891273: step: 1162/1545, loss: 0.05783011391758919 2023-01-23 09:52:27.778319: step: 1164/1545, loss: 0.06633739173412323 2023-01-23 09:52:28.653990: step: 1166/1545, loss: 0.15193670988082886 2023-01-23 09:52:29.554142: step: 1168/1545, loss: 0.3481646180152893 2023-01-23 09:52:30.452644: step: 1170/1545, loss: 0.2120029479265213 2023-01-23 09:52:31.383324: step: 1172/1545, loss: 0.2801949679851532 2023-01-23 09:52:32.248739: step: 1174/1545, loss: 0.23687744140625 2023-01-23 09:52:33.108546: step: 1176/1545, loss: 0.2728184461593628 2023-01-23 09:52:33.979100: step: 1178/1545, loss: 0.6653518080711365 2023-01-23 09:52:34.878425: step: 1180/1545, loss: 0.3066277801990509 2023-01-23 09:52:35.796107: step: 1182/1545, loss: 0.3044016361236572 2023-01-23 09:52:36.671285: step: 1184/1545, loss: 0.10661576688289642 2023-01-23 09:52:37.535932: step: 1186/1545, loss: 0.7401520609855652 2023-01-23 09:52:38.418784: step: 1188/1545, loss: 0.09759176522493362 2023-01-23 09:52:39.300977: step: 1190/1545, loss: 0.19612377882003784 2023-01-23 09:52:40.150283: step: 1192/1545, loss: 0.9802459478378296 2023-01-23 09:52:41.047748: step: 1194/1545, loss: 0.12434669584035873 2023-01-23 09:52:41.950507: step: 1196/1545, loss: 0.3218129873275757 2023-01-23 09:52:42.847063: step: 1198/1545, loss: 0.18747805058956146 2023-01-23 09:52:43.735938: step: 1200/1545, loss: 0.19597993791103363 2023-01-23 09:52:44.614203: step: 1202/1545, loss: 0.10090210288763046 2023-01-23 09:52:45.537650: step: 1204/1545, loss: 0.2965194582939148 2023-01-23 09:52:46.404698: step: 1206/1545, loss: 0.11687730997800827 2023-01-23 09:52:47.277821: step: 1208/1545, loss: 0.03354199230670929 2023-01-23 09:52:48.153422: step: 1210/1545, loss: 0.10799103230237961 2023-01-23 09:52:49.098926: step: 1212/1545, loss: 0.36197975277900696 2023-01-23 09:52:49.960169: step: 1214/1545, loss: 0.1880297064781189 2023-01-23 09:52:50.835894: step: 1216/1545, loss: 0.341112345457077 2023-01-23 09:52:51.794233: step: 1218/1545, loss: 0.5560734272003174 2023-01-23 09:52:52.667030: step: 1220/1545, loss: 0.04559678956866264 2023-01-23 09:52:53.543559: step: 1222/1545, loss: 0.1673353910446167 2023-01-23 09:52:54.441549: step: 1224/1545, loss: 0.10238341242074966 2023-01-23 09:52:55.334996: step: 1226/1545, loss: 0.11780264973640442 2023-01-23 09:52:56.204477: step: 1228/1545, loss: 0.12210790067911148 2023-01-23 09:52:57.134293: step: 1230/1545, loss: 0.4577423632144928 2023-01-23 09:52:57.989589: step: 1232/1545, loss: 1.0322319269180298 2023-01-23 09:52:58.835748: step: 1234/1545, loss: 0.2373347282409668 2023-01-23 09:52:59.702887: step: 1236/1545, loss: 1.83096444606781 2023-01-23 09:53:00.592349: step: 1238/1545, loss: 0.1514764279127121 2023-01-23 09:53:01.442924: step: 1240/1545, loss: 0.6487229466438293 2023-01-23 09:53:02.304653: step: 1242/1545, loss: 0.3662278950214386 2023-01-23 09:53:03.176692: step: 1244/1545, loss: 0.19442659616470337 2023-01-23 09:53:04.065694: step: 1246/1545, loss: 0.13573147356510162 2023-01-23 09:53:04.985206: step: 1248/1545, loss: 0.048991136252880096 2023-01-23 09:53:05.874267: step: 1250/1545, loss: 0.19510968029499054 2023-01-23 09:53:06.730705: step: 1252/1545, loss: 0.16183793544769287 2023-01-23 09:53:07.603905: step: 1254/1545, loss: 0.4126248061656952 2023-01-23 09:53:08.495513: step: 1256/1545, loss: 0.49562981724739075 2023-01-23 09:53:09.363024: step: 1258/1545, loss: 0.06975411623716354 2023-01-23 09:53:10.225760: step: 1260/1545, loss: 0.8349406123161316 2023-01-23 09:53:11.099940: step: 1262/1545, loss: 0.2592886984348297 2023-01-23 09:53:12.032399: step: 1264/1545, loss: 0.10384708642959595 2023-01-23 09:53:13.048699: step: 1266/1545, loss: 0.510991096496582 2023-01-23 09:53:13.923398: step: 1268/1545, loss: 0.12965266406536102 2023-01-23 09:53:14.777867: step: 1270/1545, loss: 0.02222329005599022 2023-01-23 09:53:15.668333: step: 1272/1545, loss: 0.10251089930534363 2023-01-23 09:53:16.615566: step: 1274/1545, loss: 0.11839431524276733 2023-01-23 09:53:17.497932: step: 1276/1545, loss: 0.6090249419212341 2023-01-23 09:53:18.385784: step: 1278/1545, loss: 0.2160201221704483 2023-01-23 09:53:19.267489: step: 1280/1545, loss: 0.41780808568000793 2023-01-23 09:53:20.204242: step: 1282/1545, loss: 0.1789105087518692 2023-01-23 09:53:21.053410: step: 1284/1545, loss: 0.05598347634077072 2023-01-23 09:53:21.970433: step: 1286/1545, loss: 0.19786642491817474 2023-01-23 09:53:22.867771: step: 1288/1545, loss: 0.9287869930267334 2023-01-23 09:53:23.745863: step: 1290/1545, loss: 0.09555385261774063 2023-01-23 09:53:24.617116: step: 1292/1545, loss: 0.18713396787643433 2023-01-23 09:53:25.482117: step: 1294/1545, loss: 0.2918212413787842 2023-01-23 09:53:26.351748: step: 1296/1545, loss: 0.2620607018470764 2023-01-23 09:53:27.222896: step: 1298/1545, loss: 0.31774085760116577 2023-01-23 09:53:28.126208: step: 1300/1545, loss: 0.04086881875991821 2023-01-23 09:53:28.987879: step: 1302/1545, loss: 0.43148675560951233 2023-01-23 09:53:29.860155: step: 1304/1545, loss: 0.2115756869316101 2023-01-23 09:53:30.771702: step: 1306/1545, loss: 0.24964600801467896 2023-01-23 09:53:31.630809: step: 1308/1545, loss: 0.47406139969825745 2023-01-23 09:53:32.478878: step: 1310/1545, loss: 0.536533534526825 2023-01-23 09:53:33.359067: step: 1312/1545, loss: 0.2356109768152237 2023-01-23 09:53:34.209649: step: 1314/1545, loss: 0.5381606817245483 2023-01-23 09:53:35.137434: step: 1316/1545, loss: 0.6907851099967957 2023-01-23 09:53:36.018974: step: 1318/1545, loss: 0.12161478400230408 2023-01-23 09:53:36.926454: step: 1320/1545, loss: 0.7013038396835327 2023-01-23 09:53:37.829330: step: 1322/1545, loss: 0.04467488452792168 2023-01-23 09:53:38.718436: step: 1324/1545, loss: 0.4995390772819519 2023-01-23 09:53:39.626391: step: 1326/1545, loss: 0.021455850452184677 2023-01-23 09:53:40.502929: step: 1328/1545, loss: 0.19676721096038818 2023-01-23 09:53:41.377879: step: 1330/1545, loss: 0.15945768356323242 2023-01-23 09:53:42.272036: step: 1332/1545, loss: 0.22261624038219452 2023-01-23 09:53:43.149348: step: 1334/1545, loss: 0.6219706535339355 2023-01-23 09:53:43.986771: step: 1336/1545, loss: 0.12500551342964172 2023-01-23 09:53:44.833779: step: 1338/1545, loss: 0.05080866441130638 2023-01-23 09:53:45.729271: step: 1340/1545, loss: 0.316581130027771 2023-01-23 09:53:46.599448: step: 1342/1545, loss: 0.719047486782074 2023-01-23 09:53:47.544192: step: 1344/1545, loss: 0.6407564282417297 2023-01-23 09:53:48.434175: step: 1346/1545, loss: 0.10879874974489212 2023-01-23 09:53:49.299857: step: 1348/1545, loss: 0.02275857701897621 2023-01-23 09:53:50.213467: step: 1350/1545, loss: 0.16883297264575958 2023-01-23 09:53:51.071049: step: 1352/1545, loss: 0.029838789254426956 2023-01-23 09:53:51.987337: step: 1354/1545, loss: 0.309527724981308 2023-01-23 09:53:52.929960: step: 1356/1545, loss: 0.07709617912769318 2023-01-23 09:53:53.843849: step: 1358/1545, loss: 0.3196481764316559 2023-01-23 09:53:54.696984: step: 1360/1545, loss: 0.43855494260787964 2023-01-23 09:53:55.569614: step: 1362/1545, loss: 0.06366539001464844 2023-01-23 09:53:56.504828: step: 1364/1545, loss: 0.7472255229949951 2023-01-23 09:53:57.389118: step: 1366/1545, loss: 0.185067817568779 2023-01-23 09:53:58.292632: step: 1368/1545, loss: 0.09217368066310883 2023-01-23 09:53:59.172264: step: 1370/1545, loss: 0.09423625469207764 2023-01-23 09:54:00.099143: step: 1372/1545, loss: 0.208847314119339 2023-01-23 09:54:00.974369: step: 1374/1545, loss: 0.14398592710494995 2023-01-23 09:54:01.921604: step: 1376/1545, loss: 0.2948940396308899 2023-01-23 09:54:02.800912: step: 1378/1545, loss: 0.22961696982383728 2023-01-23 09:54:03.703656: step: 1380/1545, loss: 0.12447268515825272 2023-01-23 09:54:04.618266: step: 1382/1545, loss: 0.08284784853458405 2023-01-23 09:54:05.480640: step: 1384/1545, loss: 0.0919078066945076 2023-01-23 09:54:06.382327: step: 1386/1545, loss: 0.22905659675598145 2023-01-23 09:54:07.275454: step: 1388/1545, loss: 0.07961796224117279 2023-01-23 09:54:08.162808: step: 1390/1545, loss: 0.03525760769844055 2023-01-23 09:54:09.046082: step: 1392/1545, loss: 0.1315993368625641 2023-01-23 09:54:09.943588: step: 1394/1545, loss: 0.6416105628013611 2023-01-23 09:54:10.855807: step: 1396/1545, loss: 0.1855001300573349 2023-01-23 09:54:11.772582: step: 1398/1545, loss: 0.5558663606643677 2023-01-23 09:54:12.657928: step: 1400/1545, loss: 0.13266023993492126 2023-01-23 09:54:13.529225: step: 1402/1545, loss: 0.12078522145748138 2023-01-23 09:54:14.414452: step: 1404/1545, loss: 0.17020876705646515 2023-01-23 09:54:15.316099: step: 1406/1545, loss: 0.3923831582069397 2023-01-23 09:54:16.225964: step: 1408/1545, loss: 0.12320742756128311 2023-01-23 09:54:17.100808: step: 1410/1545, loss: 0.1257704198360443 2023-01-23 09:54:18.032778: step: 1412/1545, loss: 0.27073776721954346 2023-01-23 09:54:18.948291: step: 1414/1545, loss: 0.49776679277420044 2023-01-23 09:54:19.945306: step: 1416/1545, loss: 0.09764069318771362 2023-01-23 09:54:20.855597: step: 1418/1545, loss: 0.2552294135093689 2023-01-23 09:54:21.826182: step: 1420/1545, loss: 0.422243595123291 2023-01-23 09:54:22.707697: step: 1422/1545, loss: 0.25860947370529175 2023-01-23 09:54:23.598696: step: 1424/1545, loss: 0.1324351280927658 2023-01-23 09:54:24.478475: step: 1426/1545, loss: 0.2949124574661255 2023-01-23 09:54:25.390077: step: 1428/1545, loss: 0.21143566071987152 2023-01-23 09:54:26.275975: step: 1430/1545, loss: 0.36048421263694763 2023-01-23 09:54:27.141049: step: 1432/1545, loss: 0.576430082321167 2023-01-23 09:54:28.014401: step: 1434/1545, loss: 0.11313194036483765 2023-01-23 09:54:28.906820: step: 1436/1545, loss: 0.14428521692752838 2023-01-23 09:54:29.802982: step: 1438/1545, loss: 0.14165014028549194 2023-01-23 09:54:30.722783: step: 1440/1545, loss: 0.10925358533859253 2023-01-23 09:54:31.568714: step: 1442/1545, loss: 0.034456055611371994 2023-01-23 09:54:32.459505: step: 1444/1545, loss: 0.07611629366874695 2023-01-23 09:54:33.364441: step: 1446/1545, loss: 2.811715841293335 2023-01-23 09:54:34.218196: step: 1448/1545, loss: 0.09224793314933777 2023-01-23 09:54:35.137886: step: 1450/1545, loss: 2.301396131515503 2023-01-23 09:54:36.016579: step: 1452/1545, loss: 0.08034278452396393 2023-01-23 09:54:36.929090: step: 1454/1545, loss: 0.07464747875928879 2023-01-23 09:54:37.881342: step: 1456/1545, loss: 1.1296530961990356 2023-01-23 09:54:38.780843: step: 1458/1545, loss: 0.1297171711921692 2023-01-23 09:54:39.646777: step: 1460/1545, loss: 0.1121256873011589 2023-01-23 09:54:40.526263: step: 1462/1545, loss: 0.28543224930763245 2023-01-23 09:54:41.393180: step: 1464/1545, loss: 0.17807216942310333 2023-01-23 09:54:42.273263: step: 1466/1545, loss: 0.21115674078464508 2023-01-23 09:54:43.171465: step: 1468/1545, loss: 0.1434832364320755 2023-01-23 09:54:44.033411: step: 1470/1545, loss: 0.13755419850349426 2023-01-23 09:54:44.913128: step: 1472/1545, loss: 0.31732189655303955 2023-01-23 09:54:45.804536: step: 1474/1545, loss: 0.3840424418449402 2023-01-23 09:54:46.684595: step: 1476/1545, loss: 0.2652337849140167 2023-01-23 09:54:47.612304: step: 1478/1545, loss: 0.08333520591259003 2023-01-23 09:54:48.517492: step: 1480/1545, loss: 0.18744172155857086 2023-01-23 09:54:49.451965: step: 1482/1545, loss: 0.2329428493976593 2023-01-23 09:54:50.422770: step: 1484/1545, loss: 0.4247441589832306 2023-01-23 09:54:51.314603: step: 1486/1545, loss: 0.04543725773692131 2023-01-23 09:54:52.177312: step: 1488/1545, loss: 0.3946085572242737 2023-01-23 09:54:53.098784: step: 1490/1545, loss: 0.22755710780620575 2023-01-23 09:54:53.972945: step: 1492/1545, loss: 0.41890472173690796 2023-01-23 09:54:54.936895: step: 1494/1545, loss: 0.8066261410713196 2023-01-23 09:54:55.907030: step: 1496/1545, loss: 0.008366219699382782 2023-01-23 09:54:56.809903: step: 1498/1545, loss: 0.2838629484176636 2023-01-23 09:54:57.733602: step: 1500/1545, loss: 0.06125662475824356 2023-01-23 09:54:58.616176: step: 1502/1545, loss: 0.2619270086288452 2023-01-23 09:54:59.478025: step: 1504/1545, loss: 0.30585095286369324 2023-01-23 09:55:00.350491: step: 1506/1545, loss: 6.541038990020752 2023-01-23 09:55:01.228842: step: 1508/1545, loss: 0.22674019634723663 2023-01-23 09:55:02.099518: step: 1510/1545, loss: 0.7720720767974854 2023-01-23 09:55:03.043058: step: 1512/1545, loss: 2.1364762783050537 2023-01-23 09:55:03.922662: step: 1514/1545, loss: 0.8293927311897278 2023-01-23 09:55:04.834456: step: 1516/1545, loss: 0.28615251183509827 2023-01-23 09:55:05.722576: step: 1518/1545, loss: 0.20056656002998352 2023-01-23 09:55:06.646756: step: 1520/1545, loss: 0.28963738679885864 2023-01-23 09:55:07.554441: step: 1522/1545, loss: 0.13932833075523376 2023-01-23 09:55:08.426131: step: 1524/1545, loss: 0.49326613545417786 2023-01-23 09:55:09.345304: step: 1526/1545, loss: 0.6973947286605835 2023-01-23 09:55:10.318407: step: 1528/1545, loss: 0.2378760427236557 2023-01-23 09:55:11.190633: step: 1530/1545, loss: 0.23703601956367493 2023-01-23 09:55:12.117480: step: 1532/1545, loss: 0.5173571109771729 2023-01-23 09:55:12.984819: step: 1534/1545, loss: 0.04466173052787781 2023-01-23 09:55:13.845387: step: 1536/1545, loss: 0.04931686446070671 2023-01-23 09:55:14.745057: step: 1538/1545, loss: 0.17629475891590118 2023-01-23 09:55:15.583837: step: 1540/1545, loss: 0.1114923357963562 2023-01-23 09:55:16.432282: step: 1542/1545, loss: 0.5917818546295166 2023-01-23 09:55:17.295965: step: 1544/1545, loss: 0.054258935153484344 2023-01-23 09:55:18.167758: step: 1546/1545, loss: 0.5314664244651794 2023-01-23 09:55:19.060194: step: 1548/1545, loss: 0.3544684946537018 2023-01-23 09:55:19.936084: step: 1550/1545, loss: 0.029198097065091133 2023-01-23 09:55:20.808422: step: 1552/1545, loss: 0.8132318258285522 2023-01-23 09:55:21.708465: step: 1554/1545, loss: 0.05037108063697815 2023-01-23 09:55:22.543598: step: 1556/1545, loss: 0.4517727792263031 2023-01-23 09:55:23.396125: step: 1558/1545, loss: 0.10972468554973602 2023-01-23 09:55:24.257364: step: 1560/1545, loss: 0.024534007534384727 2023-01-23 09:55:25.225426: step: 1562/1545, loss: 4.633054256439209 2023-01-23 09:55:26.112422: step: 1564/1545, loss: 0.07761193066835403 2023-01-23 09:55:27.036987: step: 1566/1545, loss: 0.20368413627147675 2023-01-23 09:55:27.988029: step: 1568/1545, loss: 0.23230218887329102 2023-01-23 09:55:28.830227: step: 1570/1545, loss: 0.08870789408683777 2023-01-23 09:55:29.699116: step: 1572/1545, loss: 0.06720099598169327 2023-01-23 09:55:30.603747: step: 1574/1545, loss: 0.7781236171722412 2023-01-23 09:55:31.477419: step: 1576/1545, loss: 0.11416664719581604 2023-01-23 09:55:32.382271: step: 1578/1545, loss: 0.3410182297229767 2023-01-23 09:55:33.297433: step: 1580/1545, loss: 0.06078844144940376 2023-01-23 09:55:34.156239: step: 1582/1545, loss: 0.1633652299642563 2023-01-23 09:55:35.097850: step: 1584/1545, loss: 0.1302580088376999 2023-01-23 09:55:36.020976: step: 1586/1545, loss: 0.34295135736465454 2023-01-23 09:55:36.952034: step: 1588/1545, loss: 0.21332553029060364 2023-01-23 09:55:37.833860: step: 1590/1545, loss: 0.05098632723093033 2023-01-23 09:55:38.748277: step: 1592/1545, loss: 0.6278259754180908 2023-01-23 09:55:39.644019: step: 1594/1545, loss: 0.19745676219463348 2023-01-23 09:55:40.569306: step: 1596/1545, loss: 0.030822735279798508 2023-01-23 09:55:41.462386: step: 1598/1545, loss: 1.04299795627594 2023-01-23 09:55:42.337079: step: 1600/1545, loss: 0.03648628666996956 2023-01-23 09:55:43.241234: step: 1602/1545, loss: 0.13001514971256256 2023-01-23 09:55:44.101095: step: 1604/1545, loss: 0.18728309869766235 2023-01-23 09:55:44.975699: step: 1606/1545, loss: 0.44369667768478394 2023-01-23 09:55:45.849629: step: 1608/1545, loss: 0.07840204238891602 2023-01-23 09:55:46.768214: step: 1610/1545, loss: 0.2242952585220337 2023-01-23 09:55:47.709609: step: 1612/1545, loss: 0.1876651644706726 2023-01-23 09:55:48.651765: step: 1614/1545, loss: 0.23081831634044647 2023-01-23 09:55:49.506356: step: 1616/1545, loss: 0.17877155542373657 2023-01-23 09:55:50.409196: step: 1618/1545, loss: 0.3400028347969055 2023-01-23 09:55:51.280271: step: 1620/1545, loss: 0.4142024517059326 2023-01-23 09:55:52.251176: step: 1622/1545, loss: 0.20946469902992249 2023-01-23 09:55:53.156280: step: 1624/1545, loss: 0.4947831928730011 2023-01-23 09:55:54.047747: step: 1626/1545, loss: 0.16490647196769714 2023-01-23 09:55:54.911908: step: 1628/1545, loss: 0.22282594442367554 2023-01-23 09:55:55.782568: step: 1630/1545, loss: 0.40725114941596985 2023-01-23 09:55:56.677555: step: 1632/1545, loss: 0.08100433647632599 2023-01-23 09:55:57.544161: step: 1634/1545, loss: 0.09293993562459946 2023-01-23 09:55:58.425052: step: 1636/1545, loss: 0.0570952445268631 2023-01-23 09:55:59.302203: step: 1638/1545, loss: 0.1281924545764923 2023-01-23 09:56:00.172485: step: 1640/1545, loss: 0.16096752882003784 2023-01-23 09:56:01.052495: step: 1642/1545, loss: 0.880086362361908 2023-01-23 09:56:01.913520: step: 1644/1545, loss: 0.15164010226726532 2023-01-23 09:56:02.764421: step: 1646/1545, loss: 0.07106205821037292 2023-01-23 09:56:03.654203: step: 1648/1545, loss: 0.0685451328754425 2023-01-23 09:56:04.506609: step: 1650/1545, loss: 0.37095242738723755 2023-01-23 09:56:05.383950: step: 1652/1545, loss: 0.14993272721767426 2023-01-23 09:56:06.259492: step: 1654/1545, loss: 0.20281043648719788 2023-01-23 09:56:07.109473: step: 1656/1545, loss: 0.9100499749183655 2023-01-23 09:56:07.990165: step: 1658/1545, loss: 0.322668194770813 2023-01-23 09:56:08.842948: step: 1660/1545, loss: 0.36130353808403015 2023-01-23 09:56:09.760042: step: 1662/1545, loss: 0.03274496644735336 2023-01-23 09:56:10.653341: step: 1664/1545, loss: 0.17109733819961548 2023-01-23 09:56:11.528623: step: 1666/1545, loss: 0.6398758292198181 2023-01-23 09:56:12.502896: step: 1668/1545, loss: 0.10358507931232452 2023-01-23 09:56:13.382855: step: 1670/1545, loss: 0.17035570740699768 2023-01-23 09:56:14.214029: step: 1672/1545, loss: 0.11314209550619125 2023-01-23 09:56:15.089349: step: 1674/1545, loss: 0.02762415073812008 2023-01-23 09:56:15.913696: step: 1676/1545, loss: 0.5391638278961182 2023-01-23 09:56:16.772960: step: 1678/1545, loss: 0.16927658021450043 2023-01-23 09:56:17.682702: step: 1680/1545, loss: 0.21007511019706726 2023-01-23 09:56:18.566400: step: 1682/1545, loss: 0.02045181766152382 2023-01-23 09:56:19.446576: step: 1684/1545, loss: 0.11953142285346985 2023-01-23 09:56:20.430118: step: 1686/1545, loss: 0.0254724882543087 2023-01-23 09:56:21.309200: step: 1688/1545, loss: 0.3769163489341736 2023-01-23 09:56:22.198060: step: 1690/1545, loss: 0.9076735377311707 2023-01-23 09:56:23.096119: step: 1692/1545, loss: 0.4565848112106323 2023-01-23 09:56:23.988977: step: 1694/1545, loss: 0.18565180897712708 2023-01-23 09:56:24.847418: step: 1696/1545, loss: 0.03625381737947464 2023-01-23 09:56:25.701135: step: 1698/1545, loss: 0.17863139510154724 2023-01-23 09:56:26.575655: step: 1700/1545, loss: 0.15582844614982605 2023-01-23 09:56:27.426314: step: 1702/1545, loss: 0.10330966860055923 2023-01-23 09:56:28.319185: step: 1704/1545, loss: 0.19916795194149017 2023-01-23 09:56:29.216140: step: 1706/1545, loss: 0.18115192651748657 2023-01-23 09:56:30.070187: step: 1708/1545, loss: 0.0830615907907486 2023-01-23 09:56:31.015528: step: 1710/1545, loss: 0.19792553782463074 2023-01-23 09:56:31.889583: step: 1712/1545, loss: 0.1332898885011673 2023-01-23 09:56:32.799405: step: 1714/1545, loss: 0.15151137113571167 2023-01-23 09:56:33.657596: step: 1716/1545, loss: 0.1690499484539032 2023-01-23 09:56:34.543370: step: 1718/1545, loss: 0.22180110216140747 2023-01-23 09:56:35.393802: step: 1720/1545, loss: 0.3123606741428375 2023-01-23 09:56:36.250486: step: 1722/1545, loss: 0.2601504325866699 2023-01-23 09:56:37.160670: step: 1724/1545, loss: 0.14716608822345734 2023-01-23 09:56:38.065221: step: 1726/1545, loss: 0.8113551735877991 2023-01-23 09:56:38.946689: step: 1728/1545, loss: 0.4479050636291504 2023-01-23 09:56:39.857416: step: 1730/1545, loss: 0.3879424035549164 2023-01-23 09:56:40.766431: step: 1732/1545, loss: 0.19990451633930206 2023-01-23 09:56:41.623489: step: 1734/1545, loss: 0.15677042305469513 2023-01-23 09:56:42.538206: step: 1736/1545, loss: 0.1925104856491089 2023-01-23 09:56:43.393445: step: 1738/1545, loss: 0.06803086400032043 2023-01-23 09:56:44.245928: step: 1740/1545, loss: 0.13981518149375916 2023-01-23 09:56:45.181581: step: 1742/1545, loss: 0.01522564236074686 2023-01-23 09:56:46.047798: step: 1744/1545, loss: 0.14457838237285614 2023-01-23 09:56:46.925018: step: 1746/1545, loss: 0.18936185538768768 2023-01-23 09:56:47.759763: step: 1748/1545, loss: 0.33532142639160156 2023-01-23 09:56:48.652451: step: 1750/1545, loss: 0.1264258325099945 2023-01-23 09:56:49.629504: step: 1752/1545, loss: 0.8284778594970703 2023-01-23 09:56:50.533539: step: 1754/1545, loss: 0.09695004671812057 2023-01-23 09:56:51.424620: step: 1756/1545, loss: 0.13330335915088654 2023-01-23 09:56:52.363971: step: 1758/1545, loss: 0.06410066038370132 2023-01-23 09:56:53.211324: step: 1760/1545, loss: 0.11586557328701019 2023-01-23 09:56:54.115099: step: 1762/1545, loss: 0.46061697602272034 2023-01-23 09:56:55.001156: step: 1764/1545, loss: 0.812545120716095 2023-01-23 09:56:55.934988: step: 1766/1545, loss: 0.30384519696235657 2023-01-23 09:56:56.835379: step: 1768/1545, loss: 0.4573407471179962 2023-01-23 09:56:57.720050: step: 1770/1545, loss: 0.13557536900043488 2023-01-23 09:56:58.601362: step: 1772/1545, loss: 1.4760714769363403 2023-01-23 09:56:59.457455: step: 1774/1545, loss: 0.38694581389427185 2023-01-23 09:57:00.350082: step: 1776/1545, loss: 0.24933774769306183 2023-01-23 09:57:01.219460: step: 1778/1545, loss: 0.6289429068565369 2023-01-23 09:57:02.087471: step: 1780/1545, loss: 0.10019762068986893 2023-01-23 09:57:02.982905: step: 1782/1545, loss: 0.09578386694192886 2023-01-23 09:57:03.852422: step: 1784/1545, loss: 0.07977620512247086 2023-01-23 09:57:04.739572: step: 1786/1545, loss: 0.2761746644973755 2023-01-23 09:57:05.714216: step: 1788/1545, loss: 0.12133725732564926 2023-01-23 09:57:06.627367: step: 1790/1545, loss: 0.3110346794128418 2023-01-23 09:57:07.503569: step: 1792/1545, loss: 0.07352639734745026 2023-01-23 09:57:08.434152: step: 1794/1545, loss: 0.19737154245376587 2023-01-23 09:57:09.321994: step: 1796/1545, loss: 0.12045413255691528 2023-01-23 09:57:10.242841: step: 1798/1545, loss: 0.738518238067627 2023-01-23 09:57:11.118596: step: 1800/1545, loss: 0.28243038058280945 2023-01-23 09:57:12.008652: step: 1802/1545, loss: 2.2912237644195557 2023-01-23 09:57:12.871066: step: 1804/1545, loss: 0.18233194947242737 2023-01-23 09:57:13.834280: step: 1806/1545, loss: 0.38538113236427307 2023-01-23 09:57:14.711024: step: 1808/1545, loss: 0.047727204859256744 2023-01-23 09:57:15.584314: step: 1810/1545, loss: 0.32688266038894653 2023-01-23 09:57:16.466529: step: 1812/1545, loss: 0.0748453289270401 2023-01-23 09:57:17.383652: step: 1814/1545, loss: 0.12724541127681732 2023-01-23 09:57:18.376465: step: 1816/1545, loss: 0.17279565334320068 2023-01-23 09:57:19.293861: step: 1818/1545, loss: 0.1913885772228241 2023-01-23 09:57:20.218936: step: 1820/1545, loss: 0.14725317060947418 2023-01-23 09:57:21.084069: step: 1822/1545, loss: 0.274164617061615 2023-01-23 09:57:21.962338: step: 1824/1545, loss: 0.11996302753686905 2023-01-23 09:57:22.890467: step: 1826/1545, loss: 0.23412267863750458 2023-01-23 09:57:23.803791: step: 1828/1545, loss: 0.2952623963356018 2023-01-23 09:57:24.655293: step: 1830/1545, loss: 0.2227180302143097 2023-01-23 09:57:25.566768: step: 1832/1545, loss: 0.17146998643875122 2023-01-23 09:57:26.460810: step: 1834/1545, loss: 0.1694348007440567 2023-01-23 09:57:27.319253: step: 1836/1545, loss: 0.2675098478794098 2023-01-23 09:57:28.241755: step: 1838/1545, loss: 0.1135445088148117 2023-01-23 09:57:29.097522: step: 1840/1545, loss: 0.699152410030365 2023-01-23 09:57:30.031642: step: 1842/1545, loss: 0.05168994143605232 2023-01-23 09:57:30.951556: step: 1844/1545, loss: 0.7761492133140564 2023-01-23 09:57:31.842227: step: 1846/1545, loss: 0.04476729780435562 2023-01-23 09:57:32.757859: step: 1848/1545, loss: 0.17325636744499207 2023-01-23 09:57:33.636334: step: 1850/1545, loss: 0.21631556749343872 2023-01-23 09:57:34.494339: step: 1852/1545, loss: 5.4845685958862305 2023-01-23 09:57:35.465468: step: 1854/1545, loss: 0.0922984629869461 2023-01-23 09:57:36.339524: step: 1856/1545, loss: 0.10046009719371796 2023-01-23 09:57:37.265223: step: 1858/1545, loss: 0.19553953409194946 2023-01-23 09:57:38.166749: step: 1860/1545, loss: 0.09995634853839874 2023-01-23 09:57:39.071142: step: 1862/1545, loss: 0.08779892325401306 2023-01-23 09:57:40.025518: step: 1864/1545, loss: 0.13718518614768982 2023-01-23 09:57:40.896623: step: 1866/1545, loss: 0.09689021110534668 2023-01-23 09:57:41.808880: step: 1868/1545, loss: 0.02138015627861023 2023-01-23 09:57:42.723992: step: 1870/1545, loss: 0.03801896050572395 2023-01-23 09:57:43.588222: step: 1872/1545, loss: 0.2741774022579193 2023-01-23 09:57:44.466533: step: 1874/1545, loss: 0.8660350441932678 2023-01-23 09:57:45.351034: step: 1876/1545, loss: 0.24639375507831573 2023-01-23 09:57:46.232258: step: 1878/1545, loss: 0.873584508895874 2023-01-23 09:57:47.134600: step: 1880/1545, loss: 0.1340789645910263 2023-01-23 09:57:48.019260: step: 1882/1545, loss: 0.582624077796936 2023-01-23 09:57:48.946408: step: 1884/1545, loss: 0.20527902245521545 2023-01-23 09:57:49.823010: step: 1886/1545, loss: 0.2562726140022278 2023-01-23 09:57:50.702684: step: 1888/1545, loss: 0.03459378331899643 2023-01-23 09:57:51.602467: step: 1890/1545, loss: 0.12754584848880768 2023-01-23 09:57:52.447848: step: 1892/1545, loss: 0.03470969200134277 2023-01-23 09:57:53.301923: step: 1894/1545, loss: 0.08270835131406784 2023-01-23 09:57:54.229001: step: 1896/1545, loss: 0.14247773587703705 2023-01-23 09:57:55.103531: step: 1898/1545, loss: 0.047650985419750214 2023-01-23 09:57:56.037911: step: 1900/1545, loss: 0.06957710534334183 2023-01-23 09:57:56.918236: step: 1902/1545, loss: 0.11767491698265076 2023-01-23 09:57:57.780781: step: 1904/1545, loss: 0.13238555192947388 2023-01-23 09:57:58.674127: step: 1906/1545, loss: 0.309653639793396 2023-01-23 09:57:59.544701: step: 1908/1545, loss: 0.10145408660173416 2023-01-23 09:58:00.452755: step: 1910/1545, loss: 0.06609632074832916 2023-01-23 09:58:01.327630: step: 1912/1545, loss: 0.3952852785587311 2023-01-23 09:58:02.178192: step: 1914/1545, loss: 1.000066876411438 2023-01-23 09:58:03.054913: step: 1916/1545, loss: 0.736926257610321 2023-01-23 09:58:03.926641: step: 1918/1545, loss: 0.018256789073348045 2023-01-23 09:58:04.797105: step: 1920/1545, loss: 0.16140562295913696 2023-01-23 09:58:05.717202: step: 1922/1545, loss: 0.017739811912178993 2023-01-23 09:58:06.603197: step: 1924/1545, loss: 0.3483337163925171 2023-01-23 09:58:07.455066: step: 1926/1545, loss: 0.32606470584869385 2023-01-23 09:58:08.394483: step: 1928/1545, loss: 0.3102877736091614 2023-01-23 09:58:09.264804: step: 1930/1545, loss: 0.14937415719032288 2023-01-23 09:58:10.168254: step: 1932/1545, loss: 0.25736039876937866 2023-01-23 09:58:11.058511: step: 1934/1545, loss: 0.17761433124542236 2023-01-23 09:58:11.950069: step: 1936/1545, loss: 0.24756915867328644 2023-01-23 09:58:12.859918: step: 1938/1545, loss: 0.6898348331451416 2023-01-23 09:58:13.764632: step: 1940/1545, loss: 0.09189227968454361 2023-01-23 09:58:14.672727: step: 1942/1545, loss: 0.31041163206100464 2023-01-23 09:58:15.538288: step: 1944/1545, loss: 0.09395788609981537 2023-01-23 09:58:16.540392: step: 1946/1545, loss: 0.1788339614868164 2023-01-23 09:58:17.388297: step: 1948/1545, loss: 0.2952938377857208 2023-01-23 09:58:18.241990: step: 1950/1545, loss: 0.23926876485347748 2023-01-23 09:58:19.160707: step: 1952/1545, loss: 0.30701854825019836 2023-01-23 09:58:20.004211: step: 1954/1545, loss: 0.10315623134374619 2023-01-23 09:58:20.906352: step: 1956/1545, loss: 0.39395007491111755 2023-01-23 09:58:21.809088: step: 1958/1545, loss: 0.5703107118606567 2023-01-23 09:58:22.709261: step: 1960/1545, loss: 0.4821055829524994 2023-01-23 09:58:23.666600: step: 1962/1545, loss: 0.16669949889183044 2023-01-23 09:58:24.514954: step: 1964/1545, loss: 0.05762326344847679 2023-01-23 09:58:25.425774: step: 1966/1545, loss: 0.20990699529647827 2023-01-23 09:58:26.300545: step: 1968/1545, loss: 0.10079986602067947 2023-01-23 09:58:27.192520: step: 1970/1545, loss: 0.21650700271129608 2023-01-23 09:58:28.088597: step: 1972/1545, loss: 0.07209628075361252 2023-01-23 09:58:28.951752: step: 1974/1545, loss: 0.5404503345489502 2023-01-23 09:58:29.795667: step: 1976/1545, loss: 0.1946268528699875 2023-01-23 09:58:30.720303: step: 1978/1545, loss: 0.12401088327169418 2023-01-23 09:58:31.606686: step: 1980/1545, loss: 0.2959287464618683 2023-01-23 09:58:32.468538: step: 1982/1545, loss: 0.06214843690395355 2023-01-23 09:58:33.327998: step: 1984/1545, loss: 0.3567017614841461 2023-01-23 09:58:34.193895: step: 1986/1545, loss: 0.11974462866783142 2023-01-23 09:58:35.048075: step: 1988/1545, loss: 0.06977969408035278 2023-01-23 09:58:35.934011: step: 1990/1545, loss: 0.26367029547691345 2023-01-23 09:58:36.823694: step: 1992/1545, loss: 0.16162678599357605 2023-01-23 09:58:37.811906: step: 1994/1545, loss: 0.04474397748708725 2023-01-23 09:58:38.689905: step: 1996/1545, loss: 0.35710081458091736 2023-01-23 09:58:39.541758: step: 1998/1545, loss: 0.9680347442626953 2023-01-23 09:58:40.475598: step: 2000/1545, loss: 0.44083526730537415 2023-01-23 09:58:41.351829: step: 2002/1545, loss: 0.052225980907678604 2023-01-23 09:58:42.250526: step: 2004/1545, loss: 0.09758912771940231 2023-01-23 09:58:43.122941: step: 2006/1545, loss: 0.5586450695991516 2023-01-23 09:58:44.024466: step: 2008/1545, loss: 0.183965265750885 2023-01-23 09:58:44.910856: step: 2010/1545, loss: 0.05348842963576317 2023-01-23 09:58:45.837582: step: 2012/1545, loss: 0.17833851277828217 2023-01-23 09:58:46.719824: step: 2014/1545, loss: 0.2595626711845398 2023-01-23 09:58:47.620346: step: 2016/1545, loss: 0.018221087753772736 2023-01-23 09:58:48.512377: step: 2018/1545, loss: 0.49986350536346436 2023-01-23 09:58:49.352646: step: 2020/1545, loss: 0.40600118041038513 2023-01-23 09:58:50.229869: step: 2022/1545, loss: 0.4036569595336914 2023-01-23 09:58:51.121823: step: 2024/1545, loss: 0.07844430208206177 2023-01-23 09:58:51.969057: step: 2026/1545, loss: 0.16979527473449707 2023-01-23 09:58:52.858973: step: 2028/1545, loss: 0.022671816870570183 2023-01-23 09:58:53.740533: step: 2030/1545, loss: 0.08949236571788788 2023-01-23 09:58:54.615032: step: 2032/1545, loss: 0.15547320246696472 2023-01-23 09:58:55.486856: step: 2034/1545, loss: 0.24390721321105957 2023-01-23 09:58:56.311271: step: 2036/1545, loss: 0.06884121894836426 2023-01-23 09:58:57.198654: step: 2038/1545, loss: 0.215147465467453 2023-01-23 09:58:58.096135: step: 2040/1545, loss: 0.3386414349079132 2023-01-23 09:58:58.993804: step: 2042/1545, loss: 0.8700670599937439 2023-01-23 09:58:59.862514: step: 2044/1545, loss: 0.08481474220752716 2023-01-23 09:59:00.737071: step: 2046/1545, loss: 0.14963814616203308 2023-01-23 09:59:01.631763: step: 2048/1545, loss: 0.2917928099632263 2023-01-23 09:59:02.554634: step: 2050/1545, loss: 0.09744786471128464 2023-01-23 09:59:03.412912: step: 2052/1545, loss: 0.07456306368112564 2023-01-23 09:59:04.302834: step: 2054/1545, loss: 0.1385369896888733 2023-01-23 09:59:05.199132: step: 2056/1545, loss: 0.2731947898864746 2023-01-23 09:59:06.059317: step: 2058/1545, loss: 0.3847559094429016 2023-01-23 09:59:06.952418: step: 2060/1545, loss: 0.11818287521600723 2023-01-23 09:59:07.918109: step: 2062/1545, loss: 0.7690199017524719 2023-01-23 09:59:08.800332: step: 2064/1545, loss: 0.1785440593957901 2023-01-23 09:59:09.680030: step: 2066/1545, loss: 0.42510145902633667 2023-01-23 09:59:10.553946: step: 2068/1545, loss: 0.820014476776123 2023-01-23 09:59:11.418756: step: 2070/1545, loss: 0.24543312191963196 2023-01-23 09:59:12.261193: step: 2072/1545, loss: 0.17484408617019653 2023-01-23 09:59:13.127966: step: 2074/1545, loss: 0.11982833594083786 2023-01-23 09:59:13.983924: step: 2076/1545, loss: 0.10251857340335846 2023-01-23 09:59:14.872931: step: 2078/1545, loss: 0.4057924747467041 2023-01-23 09:59:15.734276: step: 2080/1545, loss: 0.35320499539375305 2023-01-23 09:59:16.651062: step: 2082/1545, loss: 0.23159942030906677 2023-01-23 09:59:17.522759: step: 2084/1545, loss: 0.2979941666126251 2023-01-23 09:59:18.387768: step: 2086/1545, loss: 0.11734684556722641 2023-01-23 09:59:19.292974: step: 2088/1545, loss: 0.5430904626846313 2023-01-23 09:59:20.173728: step: 2090/1545, loss: 0.08728598803281784 2023-01-23 09:59:21.080615: step: 2092/1545, loss: 0.11622761934995651 2023-01-23 09:59:21.955111: step: 2094/1545, loss: 0.10378836840391159 2023-01-23 09:59:22.835362: step: 2096/1545, loss: 0.056387390941381454 2023-01-23 09:59:23.741419: step: 2098/1545, loss: 0.13444292545318604 2023-01-23 09:59:24.580267: step: 2100/1545, loss: 0.5875914096832275 2023-01-23 09:59:25.451222: step: 2102/1545, loss: 0.26239776611328125 2023-01-23 09:59:26.367039: step: 2104/1545, loss: 0.05868140980601311 2023-01-23 09:59:27.242690: step: 2106/1545, loss: 0.09503047913312912 2023-01-23 09:59:28.134329: step: 2108/1545, loss: 2.67697811126709 2023-01-23 09:59:29.048794: step: 2110/1545, loss: 0.14701738953590393 2023-01-23 09:59:29.934739: step: 2112/1545, loss: 0.11407049000263214 2023-01-23 09:59:30.816480: step: 2114/1545, loss: 0.12901748716831207 2023-01-23 09:59:31.719959: step: 2116/1545, loss: 1.3142681121826172 2023-01-23 09:59:32.605629: step: 2118/1545, loss: 0.23412977159023285 2023-01-23 09:59:33.552043: step: 2120/1545, loss: 0.3466350734233856 2023-01-23 09:59:34.408921: step: 2122/1545, loss: 0.3856540024280548 2023-01-23 09:59:35.297799: step: 2124/1545, loss: 0.7607623338699341 2023-01-23 09:59:36.153452: step: 2126/1545, loss: 0.3932538628578186 2023-01-23 09:59:37.114545: step: 2128/1545, loss: 0.09161273390054703 2023-01-23 09:59:38.108044: step: 2130/1545, loss: 0.333916574716568 2023-01-23 09:59:39.020571: step: 2132/1545, loss: 0.46467381715774536 2023-01-23 09:59:39.901859: step: 2134/1545, loss: 0.3857404291629791 2023-01-23 09:59:40.793498: step: 2136/1545, loss: 0.24184608459472656 2023-01-23 09:59:41.690396: step: 2138/1545, loss: 0.5123496055603027 2023-01-23 09:59:42.609045: step: 2140/1545, loss: 0.06657437980175018 2023-01-23 09:59:43.493845: step: 2142/1545, loss: 0.20396168529987335 2023-01-23 09:59:44.360389: step: 2144/1545, loss: 0.36888229846954346 2023-01-23 09:59:45.276375: step: 2146/1545, loss: 0.07107686996459961 2023-01-23 09:59:46.165856: step: 2148/1545, loss: 0.25158557295799255 2023-01-23 09:59:47.058618: step: 2150/1545, loss: 0.42573392391204834 2023-01-23 09:59:47.934055: step: 2152/1545, loss: 0.13156002759933472 2023-01-23 09:59:48.811578: step: 2154/1545, loss: 0.712155282497406 2023-01-23 09:59:49.745866: step: 2156/1545, loss: 0.09908366203308105 2023-01-23 09:59:50.630442: step: 2158/1545, loss: 1.8127187490463257 2023-01-23 09:59:51.523290: step: 2160/1545, loss: 0.16289278864860535 2023-01-23 09:59:52.389499: step: 2162/1545, loss: 0.520825982093811 2023-01-23 09:59:53.228374: step: 2164/1545, loss: 0.1822068989276886 2023-01-23 09:59:54.068173: step: 2166/1545, loss: 0.1083059310913086 2023-01-23 09:59:54.977487: step: 2168/1545, loss: 0.20475055277347565 2023-01-23 09:59:55.825226: step: 2170/1545, loss: 0.26198720932006836 2023-01-23 09:59:56.703214: step: 2172/1545, loss: 0.061662621796131134 2023-01-23 09:59:57.567891: step: 2174/1545, loss: 0.10676874220371246 2023-01-23 09:59:58.427671: step: 2176/1545, loss: 0.07284319400787354 2023-01-23 09:59:59.350085: step: 2178/1545, loss: 1.5502558946609497 2023-01-23 10:00:00.198862: step: 2180/1545, loss: 0.08804422616958618 2023-01-23 10:00:01.182696: step: 2182/1545, loss: 0.08964142948389053 2023-01-23 10:00:02.042383: step: 2184/1545, loss: 0.2142515480518341 2023-01-23 10:00:02.893963: step: 2186/1545, loss: 0.8298312425613403 2023-01-23 10:00:03.808639: step: 2188/1545, loss: 0.20873460173606873 2023-01-23 10:00:04.690504: step: 2190/1545, loss: 0.42550981044769287 2023-01-23 10:00:05.567246: step: 2192/1545, loss: 0.1339634656906128 2023-01-23 10:00:06.451728: step: 2194/1545, loss: 0.3756290376186371 2023-01-23 10:00:07.328519: step: 2196/1545, loss: 0.008594604209065437 2023-01-23 10:00:08.181681: step: 2198/1545, loss: 0.47670888900756836 2023-01-23 10:00:09.072084: step: 2200/1545, loss: 0.03665042296051979 2023-01-23 10:00:10.018925: step: 2202/1545, loss: 0.3848963975906372 2023-01-23 10:00:10.885814: step: 2204/1545, loss: 0.06620657444000244 2023-01-23 10:00:11.739138: step: 2206/1545, loss: 0.10824138671159744 2023-01-23 10:00:12.656360: step: 2208/1545, loss: 0.16546796262264252 2023-01-23 10:00:13.644716: step: 2210/1545, loss: 0.2612743377685547 2023-01-23 10:00:14.534306: step: 2212/1545, loss: 0.4700738489627838 2023-01-23 10:00:15.397226: step: 2214/1545, loss: 0.07283470779657364 2023-01-23 10:00:16.249580: step: 2216/1545, loss: 0.4521257281303406 2023-01-23 10:00:17.105626: step: 2218/1545, loss: 0.2600874900817871 2023-01-23 10:00:17.997150: step: 2220/1545, loss: 0.07282604277133942 2023-01-23 10:00:18.897109: step: 2222/1545, loss: 0.2882455289363861 2023-01-23 10:00:19.775949: step: 2224/1545, loss: 0.2131074070930481 2023-01-23 10:00:20.620140: step: 2226/1545, loss: 0.7555181980133057 2023-01-23 10:00:21.543093: step: 2228/1545, loss: 0.21097755432128906 2023-01-23 10:00:22.393044: step: 2230/1545, loss: 0.016953006386756897 2023-01-23 10:00:23.260416: step: 2232/1545, loss: 0.11303991079330444 2023-01-23 10:00:24.170998: step: 2234/1545, loss: 0.012995108030736446 2023-01-23 10:00:25.066549: step: 2236/1545, loss: 0.3338698148727417 2023-01-23 10:00:25.945713: step: 2238/1545, loss: 0.0872613936662674 2023-01-23 10:00:26.815603: step: 2240/1545, loss: 0.12923650443553925 2023-01-23 10:00:27.690214: step: 2242/1545, loss: 0.15486125648021698 2023-01-23 10:00:28.554101: step: 2244/1545, loss: 0.10483682155609131 2023-01-23 10:00:29.493025: step: 2246/1545, loss: 0.11622840911149979 2023-01-23 10:00:30.413331: step: 2248/1545, loss: 0.5024546980857849 2023-01-23 10:00:31.280760: step: 2250/1545, loss: 0.2529546022415161 2023-01-23 10:00:32.167439: step: 2252/1545, loss: 0.1629527360200882 2023-01-23 10:00:33.015643: step: 2254/1545, loss: 0.13197557628154755 2023-01-23 10:00:33.854274: step: 2256/1545, loss: 0.09789741784334183 2023-01-23 10:00:34.813065: step: 2258/1545, loss: 0.035646408796310425 2023-01-23 10:00:35.650961: step: 2260/1545, loss: 0.11621452867984772 2023-01-23 10:00:36.549881: step: 2262/1545, loss: 0.07047975063323975 2023-01-23 10:00:37.413039: step: 2264/1545, loss: 0.2317795753479004 2023-01-23 10:00:38.285492: step: 2266/1545, loss: 0.0955725833773613 2023-01-23 10:00:39.218778: step: 2268/1545, loss: 0.19979795813560486 2023-01-23 10:00:40.128669: step: 2270/1545, loss: 0.08793260157108307 2023-01-23 10:00:41.027895: step: 2272/1545, loss: 0.3139190971851349 2023-01-23 10:00:41.935648: step: 2274/1545, loss: 0.17736564576625824 2023-01-23 10:00:42.789088: step: 2276/1545, loss: 0.14189885556697845 2023-01-23 10:00:43.672628: step: 2278/1545, loss: 0.025398187339305878 2023-01-23 10:00:44.571725: step: 2280/1545, loss: 0.387199729681015 2023-01-23 10:00:45.435897: step: 2282/1545, loss: 0.07908624410629272 2023-01-23 10:00:46.303167: step: 2284/1545, loss: 0.6372178196907043 2023-01-23 10:00:47.182172: step: 2286/1545, loss: 0.09282833337783813 2023-01-23 10:00:48.053130: step: 2288/1545, loss: 0.12049394845962524 2023-01-23 10:00:48.977447: step: 2290/1545, loss: 0.24468719959259033 2023-01-23 10:00:49.893972: step: 2292/1545, loss: 0.08026043325662613 2023-01-23 10:00:50.786036: step: 2294/1545, loss: 0.23442354798316956 2023-01-23 10:00:51.660648: step: 2296/1545, loss: 0.1961275339126587 2023-01-23 10:00:52.524243: step: 2298/1545, loss: 0.024331379681825638 2023-01-23 10:00:53.386521: step: 2300/1545, loss: 0.09497994929552078 2023-01-23 10:00:54.346062: step: 2302/1545, loss: 0.3409135937690735 2023-01-23 10:00:55.242019: step: 2304/1545, loss: 0.17333760857582092 2023-01-23 10:00:56.119790: step: 2306/1545, loss: 0.23936788737773895 2023-01-23 10:00:56.993915: step: 2308/1545, loss: 0.21117401123046875 2023-01-23 10:00:57.901870: step: 2310/1545, loss: 0.08614733070135117 2023-01-23 10:00:58.821094: step: 2312/1545, loss: 0.05854404717683792 2023-01-23 10:00:59.689290: step: 2314/1545, loss: 0.49275484681129456 2023-01-23 10:01:00.570040: step: 2316/1545, loss: 0.29109281301498413 2023-01-23 10:01:01.450339: step: 2318/1545, loss: 0.4143298864364624 2023-01-23 10:01:02.312465: step: 2320/1545, loss: 0.08556590229272842 2023-01-23 10:01:03.189239: step: 2322/1545, loss: 0.04239175468683243 2023-01-23 10:01:04.090690: step: 2324/1545, loss: 0.3695359230041504 2023-01-23 10:01:05.025376: step: 2326/1545, loss: 0.38054919242858887 2023-01-23 10:01:05.909964: step: 2328/1545, loss: 0.12378327548503876 2023-01-23 10:01:06.793394: step: 2330/1545, loss: 0.11304765194654465 2023-01-23 10:01:07.660410: step: 2332/1545, loss: 0.17450745403766632 2023-01-23 10:01:08.506003: step: 2334/1545, loss: 0.3979561924934387 2023-01-23 10:01:09.399743: step: 2336/1545, loss: 0.1597398966550827 2023-01-23 10:01:10.298072: step: 2338/1545, loss: 0.4126761853694916 2023-01-23 10:01:11.214247: step: 2340/1545, loss: 0.13545432686805725 2023-01-23 10:01:12.086066: step: 2342/1545, loss: 0.052114684134721756 2023-01-23 10:01:12.937609: step: 2344/1545, loss: 0.049497440457344055 2023-01-23 10:01:13.860630: step: 2346/1545, loss: 0.22830753028392792 2023-01-23 10:01:14.724842: step: 2348/1545, loss: 0.05872216820716858 2023-01-23 10:01:15.670391: step: 2350/1545, loss: 1.5853745937347412 2023-01-23 10:01:16.557200: step: 2352/1545, loss: 0.11300350725650787 2023-01-23 10:01:17.419119: step: 2354/1545, loss: 0.10051222145557404 2023-01-23 10:01:18.283053: step: 2356/1545, loss: 0.19812814891338348 2023-01-23 10:01:19.139506: step: 2358/1545, loss: 0.3641332685947418 2023-01-23 10:01:20.065400: step: 2360/1545, loss: 0.5596973896026611 2023-01-23 10:01:20.965933: step: 2362/1545, loss: 0.3235463798046112 2023-01-23 10:01:21.822223: step: 2364/1545, loss: 0.07767634093761444 2023-01-23 10:01:22.718368: step: 2366/1545, loss: 0.15033532679080963 2023-01-23 10:01:23.610926: step: 2368/1545, loss: 0.13206812739372253 2023-01-23 10:01:24.494534: step: 2370/1545, loss: 0.17973653972148895 2023-01-23 10:01:25.333366: step: 2372/1545, loss: 0.13922196626663208 2023-01-23 10:01:26.164499: step: 2374/1545, loss: 0.038083963096141815 2023-01-23 10:01:27.075628: step: 2376/1545, loss: 0.5987203121185303 2023-01-23 10:01:27.949968: step: 2378/1545, loss: 0.025611087679862976 2023-01-23 10:01:28.799829: step: 2380/1545, loss: 0.5915336012840271 2023-01-23 10:01:29.703740: step: 2382/1545, loss: 0.17880168557167053 2023-01-23 10:01:30.589654: step: 2384/1545, loss: 0.2637990117073059 2023-01-23 10:01:31.453066: step: 2386/1545, loss: 0.06594423949718475 2023-01-23 10:01:32.327942: step: 2388/1545, loss: 0.35084840655326843 2023-01-23 10:01:33.197734: step: 2390/1545, loss: 0.09534156322479248 2023-01-23 10:01:34.079948: step: 2392/1545, loss: 0.36092349886894226 2023-01-23 10:01:34.925415: step: 2394/1545, loss: 0.14808839559555054 2023-01-23 10:01:35.813154: step: 2396/1545, loss: 0.2593366503715515 2023-01-23 10:01:36.671351: step: 2398/1545, loss: 0.04006950184702873 2023-01-23 10:01:37.573890: step: 2400/1545, loss: 0.37523046135902405 2023-01-23 10:01:38.480346: step: 2402/1545, loss: 0.5827690362930298 2023-01-23 10:01:39.399737: step: 2404/1545, loss: 0.3648459315299988 2023-01-23 10:01:40.290322: step: 2406/1545, loss: 0.25263693928718567 2023-01-23 10:01:41.167544: step: 2408/1545, loss: 0.5789121985435486 2023-01-23 10:01:42.033520: step: 2410/1545, loss: 0.0885443240404129 2023-01-23 10:01:42.965611: step: 2412/1545, loss: 0.1587020754814148 2023-01-23 10:01:43.842848: step: 2414/1545, loss: 0.19732190668582916 2023-01-23 10:01:44.772955: step: 2416/1545, loss: 0.19446344673633575 2023-01-23 10:01:45.631440: step: 2418/1545, loss: 0.11115509271621704 2023-01-23 10:01:46.518369: step: 2420/1545, loss: 0.013931404799222946 2023-01-23 10:01:47.412933: step: 2422/1545, loss: 0.93448406457901 2023-01-23 10:01:48.304350: step: 2424/1545, loss: 0.44086557626724243 2023-01-23 10:01:49.178894: step: 2426/1545, loss: 0.03509553521871567 2023-01-23 10:01:50.036611: step: 2428/1545, loss: 0.17098760604858398 2023-01-23 10:01:50.907167: step: 2430/1545, loss: 0.4363130033016205 2023-01-23 10:01:51.759724: step: 2432/1545, loss: 0.38999369740486145 2023-01-23 10:01:52.612004: step: 2434/1545, loss: 0.04264898970723152 2023-01-23 10:01:53.447274: step: 2436/1545, loss: 0.3687853515148163 2023-01-23 10:01:54.306593: step: 2438/1545, loss: 0.07049684971570969 2023-01-23 10:01:55.157627: step: 2440/1545, loss: 0.02302643656730652 2023-01-23 10:01:56.058528: step: 2442/1545, loss: 0.38120436668395996 2023-01-23 10:01:56.959348: step: 2444/1545, loss: 0.36206451058387756 2023-01-23 10:01:57.841979: step: 2446/1545, loss: 0.19720686972141266 2023-01-23 10:01:58.705405: step: 2448/1545, loss: 0.3258715569972992 2023-01-23 10:01:59.624117: step: 2450/1545, loss: 0.12429197877645493 2023-01-23 10:02:00.530732: step: 2452/1545, loss: 0.18496139347553253 2023-01-23 10:02:01.388070: step: 2454/1545, loss: 0.7006912231445312 2023-01-23 10:02:02.252169: step: 2456/1545, loss: 0.039044108241796494 2023-01-23 10:02:03.150949: step: 2458/1545, loss: 0.0840994119644165 2023-01-23 10:02:04.000235: step: 2460/1545, loss: 0.695303201675415 2023-01-23 10:02:04.902539: step: 2462/1545, loss: 0.015629548579454422 2023-01-23 10:02:05.797880: step: 2464/1545, loss: 0.2989507019519806 2023-01-23 10:02:06.699559: step: 2466/1545, loss: 0.8816298246383667 2023-01-23 10:02:07.568296: step: 2468/1545, loss: 0.22551634907722473 2023-01-23 10:02:08.445075: step: 2470/1545, loss: 0.23768484592437744 2023-01-23 10:02:09.334057: step: 2472/1545, loss: 0.2792137563228607 2023-01-23 10:02:10.232990: step: 2474/1545, loss: 0.1720990538597107 2023-01-23 10:02:11.217056: step: 2476/1545, loss: 0.3773709833621979 2023-01-23 10:02:12.122365: step: 2478/1545, loss: 0.38144242763519287 2023-01-23 10:02:13.026133: step: 2480/1545, loss: 0.19037480652332306 2023-01-23 10:02:13.892921: step: 2482/1545, loss: 0.05721434950828552 2023-01-23 10:02:14.755610: step: 2484/1545, loss: 0.15092715620994568 2023-01-23 10:02:15.621437: step: 2486/1545, loss: 0.1697162538766861 2023-01-23 10:02:16.482663: step: 2488/1545, loss: 0.1437535583972931 2023-01-23 10:02:17.352799: step: 2490/1545, loss: 0.11820938438177109 2023-01-23 10:02:18.262558: step: 2492/1545, loss: 0.10983359068632126 2023-01-23 10:02:19.152950: step: 2494/1545, loss: 0.07506762444972992 2023-01-23 10:02:20.023225: step: 2496/1545, loss: 0.22599591314792633 2023-01-23 10:02:20.909649: step: 2498/1545, loss: 0.17383727431297302 2023-01-23 10:02:21.789874: step: 2500/1545, loss: 0.05701519548892975 2023-01-23 10:02:22.719257: step: 2502/1545, loss: 0.09730126708745956 2023-01-23 10:02:23.576017: step: 2504/1545, loss: 0.023448161780834198 2023-01-23 10:02:24.473546: step: 2506/1545, loss: 0.07160903513431549 2023-01-23 10:02:25.377355: step: 2508/1545, loss: 0.4382886588573456 2023-01-23 10:02:26.280661: step: 2510/1545, loss: 0.3964068591594696 2023-01-23 10:02:27.168927: step: 2512/1545, loss: 0.16645821928977966 2023-01-23 10:02:28.014560: step: 2514/1545, loss: 0.30287614464759827 2023-01-23 10:02:28.908434: step: 2516/1545, loss: 0.1579212099313736 2023-01-23 10:02:29.807782: step: 2518/1545, loss: 0.5368465781211853 2023-01-23 10:02:30.693823: step: 2520/1545, loss: 0.07309797406196594 2023-01-23 10:02:31.563071: step: 2522/1545, loss: 0.08824826776981354 2023-01-23 10:02:32.463898: step: 2524/1545, loss: 0.06700529158115387 2023-01-23 10:02:33.538714: step: 2526/1545, loss: 0.2967647910118103 2023-01-23 10:02:34.380893: step: 2528/1545, loss: 0.22613494098186493 2023-01-23 10:02:35.314501: step: 2530/1545, loss: 0.1994054764509201 2023-01-23 10:02:36.224309: step: 2532/1545, loss: 0.06260000914335251 2023-01-23 10:02:37.089651: step: 2534/1545, loss: 0.3286110758781433 2023-01-23 10:02:37.970862: step: 2536/1545, loss: 0.3853886127471924 2023-01-23 10:02:38.859323: step: 2538/1545, loss: 0.014384310692548752 2023-01-23 10:02:39.739128: step: 2540/1545, loss: 0.35947173833847046 2023-01-23 10:02:40.612387: step: 2542/1545, loss: 0.06761647015810013 2023-01-23 10:02:41.476439: step: 2544/1545, loss: 0.11927850544452667 2023-01-23 10:02:42.329593: step: 2546/1545, loss: 0.22648577392101288 2023-01-23 10:02:43.246998: step: 2548/1545, loss: 1.0135139226913452 2023-01-23 10:02:44.104093: step: 2550/1545, loss: 0.01600613445043564 2023-01-23 10:02:44.982904: step: 2552/1545, loss: 0.36736157536506653 2023-01-23 10:02:45.855966: step: 2554/1545, loss: 0.12592220306396484 2023-01-23 10:02:46.730296: step: 2556/1545, loss: 0.4516007900238037 2023-01-23 10:02:47.596972: step: 2558/1545, loss: 0.3645114600658417 2023-01-23 10:02:48.445469: step: 2560/1545, loss: 0.11762834340333939 2023-01-23 10:02:49.312287: step: 2562/1545, loss: 0.10297880321741104 2023-01-23 10:02:50.222447: step: 2564/1545, loss: 0.2124924659729004 2023-01-23 10:02:51.134161: step: 2566/1545, loss: 0.16052581369876862 2023-01-23 10:02:51.987824: step: 2568/1545, loss: 0.24977418780326843 2023-01-23 10:02:52.870470: step: 2570/1545, loss: 0.5232319235801697 2023-01-23 10:02:53.735739: step: 2572/1545, loss: 0.11141058057546616 2023-01-23 10:02:54.667211: step: 2574/1545, loss: 0.16000449657440186 2023-01-23 10:02:55.510113: step: 2576/1545, loss: 0.23391930758953094 2023-01-23 10:02:56.450175: step: 2578/1545, loss: 0.2591186761856079 2023-01-23 10:02:57.334850: step: 2580/1545, loss: 1.2148411273956299 2023-01-23 10:02:58.184068: step: 2582/1545, loss: 0.06748829782009125 2023-01-23 10:02:59.102734: step: 2584/1545, loss: 0.014444150030612946 2023-01-23 10:03:00.036373: step: 2586/1545, loss: 0.042508598417043686 2023-01-23 10:03:00.892666: step: 2588/1545, loss: 0.18617938458919525 2023-01-23 10:03:01.779856: step: 2590/1545, loss: 0.05534401163458824 2023-01-23 10:03:02.656417: step: 2592/1545, loss: 0.08991237729787827 2023-01-23 10:03:03.541129: step: 2594/1545, loss: 0.13531506061553955 2023-01-23 10:03:04.464593: step: 2596/1545, loss: 0.5310258269309998 2023-01-23 10:03:05.360516: step: 2598/1545, loss: 0.41299766302108765 2023-01-23 10:03:06.241115: step: 2600/1545, loss: 0.1970861256122589 2023-01-23 10:03:07.055056: step: 2602/1545, loss: 1.0473026037216187 2023-01-23 10:03:07.973420: step: 2604/1545, loss: 0.23318947851657867 2023-01-23 10:03:08.866494: step: 2606/1545, loss: 0.12863998115062714 2023-01-23 10:03:09.756066: step: 2608/1545, loss: 0.07396143674850464 2023-01-23 10:03:10.645938: step: 2610/1545, loss: 0.26504871249198914 2023-01-23 10:03:11.516231: step: 2612/1545, loss: 0.13874566555023193 2023-01-23 10:03:12.398016: step: 2614/1545, loss: 0.20328423380851746 2023-01-23 10:03:13.280699: step: 2616/1545, loss: 0.212502121925354 2023-01-23 10:03:14.177008: step: 2618/1545, loss: 0.35190510749816895 2023-01-23 10:03:15.035118: step: 2620/1545, loss: 0.08498432487249374 2023-01-23 10:03:15.909938: step: 2622/1545, loss: 0.07640992105007172 2023-01-23 10:03:16.767966: step: 2624/1545, loss: 0.07646885514259338 2023-01-23 10:03:17.710772: step: 2626/1545, loss: 0.29743245244026184 2023-01-23 10:03:18.555611: step: 2628/1545, loss: 0.3353312611579895 2023-01-23 10:03:19.434807: step: 2630/1545, loss: 0.10221441835165024 2023-01-23 10:03:20.321258: step: 2632/1545, loss: 0.21373054385185242 2023-01-23 10:03:21.199572: step: 2634/1545, loss: 0.1916959583759308 2023-01-23 10:03:22.076571: step: 2636/1545, loss: 0.02907436154782772 2023-01-23 10:03:22.991541: step: 2638/1545, loss: 0.24911002814769745 2023-01-23 10:03:23.914379: step: 2640/1545, loss: 0.21974331140518188 2023-01-23 10:03:24.866366: step: 2642/1545, loss: 0.14072033762931824 2023-01-23 10:03:25.748122: step: 2644/1545, loss: 0.19846127927303314 2023-01-23 10:03:26.673866: step: 2646/1545, loss: 0.1491399109363556 2023-01-23 10:03:27.562186: step: 2648/1545, loss: 0.3083391785621643 2023-01-23 10:03:28.484697: step: 2650/1545, loss: 0.03418372943997383 2023-01-23 10:03:29.363839: step: 2652/1545, loss: 0.07709850370883942 2023-01-23 10:03:30.232712: step: 2654/1545, loss: 0.34871891140937805 2023-01-23 10:03:31.096684: step: 2656/1545, loss: 0.26131200790405273 2023-01-23 10:03:31.959333: step: 2658/1545, loss: 0.1714751422405243 2023-01-23 10:03:32.823304: step: 2660/1545, loss: 0.5722329616546631 2023-01-23 10:03:33.761794: step: 2662/1545, loss: 0.11745967715978622 2023-01-23 10:03:34.642700: step: 2664/1545, loss: 0.26456740498542786 2023-01-23 10:03:35.563073: step: 2666/1545, loss: 0.5160056352615356 2023-01-23 10:03:36.424436: step: 2668/1545, loss: 0.3020809590816498 2023-01-23 10:03:37.338963: step: 2670/1545, loss: 0.11090290546417236 2023-01-23 10:03:38.254629: step: 2672/1545, loss: 0.3161694407463074 2023-01-23 10:03:39.138821: step: 2674/1545, loss: 0.8782378435134888 2023-01-23 10:03:40.022863: step: 2676/1545, loss: 0.04465484619140625 2023-01-23 10:03:40.933680: step: 2678/1545, loss: 0.28751519322395325 2023-01-23 10:03:41.789089: step: 2680/1545, loss: 0.1427566409111023 2023-01-23 10:03:42.734117: step: 2682/1545, loss: 0.13681094348430634 2023-01-23 10:03:43.642544: step: 2684/1545, loss: 0.5035967826843262 2023-01-23 10:03:44.529303: step: 2686/1545, loss: 1.1747554540634155 2023-01-23 10:03:45.470295: step: 2688/1545, loss: 0.39332231879234314 2023-01-23 10:03:46.347117: step: 2690/1545, loss: 0.32050013542175293 2023-01-23 10:03:47.216642: step: 2692/1545, loss: 0.1643168330192566 2023-01-23 10:03:48.146116: step: 2694/1545, loss: 0.4202285408973694 2023-01-23 10:03:49.031035: step: 2696/1545, loss: 0.20736637711524963 2023-01-23 10:03:49.913656: step: 2698/1545, loss: 0.23733526468276978 2023-01-23 10:03:50.788051: step: 2700/1545, loss: 0.08715471625328064 2023-01-23 10:03:51.688153: step: 2702/1545, loss: 0.31827718019485474 2023-01-23 10:03:52.588803: step: 2704/1545, loss: 0.07596474140882492 2023-01-23 10:03:53.469786: step: 2706/1545, loss: 0.6769480109214783 2023-01-23 10:03:54.290482: step: 2708/1545, loss: 0.3696799874305725 2023-01-23 10:03:55.225477: step: 2710/1545, loss: 0.18656975030899048 2023-01-23 10:03:56.078137: step: 2712/1545, loss: 0.5129173994064331 2023-01-23 10:03:56.983537: step: 2714/1545, loss: 0.3140868842601776 2023-01-23 10:03:57.862252: step: 2716/1545, loss: 0.08021247386932373 2023-01-23 10:03:58.749958: step: 2718/1545, loss: 0.36967670917510986 2023-01-23 10:03:59.654775: step: 2720/1545, loss: 0.09857621788978577 2023-01-23 10:04:00.524797: step: 2722/1545, loss: 0.5954079627990723 2023-01-23 10:04:01.454227: step: 2724/1545, loss: 0.22313839197158813 2023-01-23 10:04:02.321451: step: 2726/1545, loss: 0.1130603477358818 2023-01-23 10:04:03.214707: step: 2728/1545, loss: 0.10026776790618896 2023-01-23 10:04:04.130259: step: 2730/1545, loss: 0.5687301158905029 2023-01-23 10:04:05.000850: step: 2732/1545, loss: 0.21099384129047394 2023-01-23 10:04:05.937413: step: 2734/1545, loss: 0.29985013604164124 2023-01-23 10:04:06.836829: step: 2736/1545, loss: 0.027612853795289993 2023-01-23 10:04:07.705083: step: 2738/1545, loss: 0.024269763380289078 2023-01-23 10:04:08.597681: step: 2740/1545, loss: 1.9706159830093384 2023-01-23 10:04:09.484700: step: 2742/1545, loss: 0.1988903284072876 2023-01-23 10:04:10.361775: step: 2744/1545, loss: 0.13504034280776978 2023-01-23 10:04:11.217402: step: 2746/1545, loss: 1.357703685760498 2023-01-23 10:04:12.077798: step: 2748/1545, loss: 0.289815753698349 2023-01-23 10:04:12.918388: step: 2750/1545, loss: 0.25419771671295166 2023-01-23 10:04:13.776635: step: 2752/1545, loss: 0.24007689952850342 2023-01-23 10:04:14.614067: step: 2754/1545, loss: 1.3179261684417725 2023-01-23 10:04:15.491887: step: 2756/1545, loss: 0.1413724720478058 2023-01-23 10:04:16.416117: step: 2758/1545, loss: 0.09193288534879684 2023-01-23 10:04:17.284336: step: 2760/1545, loss: 0.18609236180782318 2023-01-23 10:04:18.170509: step: 2762/1545, loss: 0.15275560319423676 2023-01-23 10:04:19.034908: step: 2764/1545, loss: 0.06563057005405426 2023-01-23 10:04:19.914832: step: 2766/1545, loss: 0.4543851613998413 2023-01-23 10:04:20.819661: step: 2768/1545, loss: 0.09353683888912201 2023-01-23 10:04:21.655398: step: 2770/1545, loss: 0.5018640756607056 2023-01-23 10:04:22.496539: step: 2772/1545, loss: 0.10593091696500778 2023-01-23 10:04:23.343205: step: 2774/1545, loss: 0.05560331046581268 2023-01-23 10:04:24.270779: step: 2776/1545, loss: 0.19305889308452606 2023-01-23 10:04:25.145893: step: 2778/1545, loss: 0.7009789943695068 2023-01-23 10:04:26.061698: step: 2780/1545, loss: 0.7272673845291138 2023-01-23 10:04:26.929693: step: 2782/1545, loss: 0.12514226138591766 2023-01-23 10:04:27.815816: step: 2784/1545, loss: 0.791958212852478 2023-01-23 10:04:28.677864: step: 2786/1545, loss: 0.11804547905921936 2023-01-23 10:04:29.566573: step: 2788/1545, loss: 0.03354499489068985 2023-01-23 10:04:30.451182: step: 2790/1545, loss: 0.03984803333878517 2023-01-23 10:04:31.304458: step: 2792/1545, loss: 0.12391681969165802 2023-01-23 10:04:32.206381: step: 2794/1545, loss: 0.13388791680335999 2023-01-23 10:04:33.112466: step: 2796/1545, loss: 3.616699695587158 2023-01-23 10:04:33.986337: step: 2798/1545, loss: 0.10325486958026886 2023-01-23 10:04:34.866397: step: 2800/1545, loss: 0.11123818904161453 2023-01-23 10:04:35.755156: step: 2802/1545, loss: 0.1481286734342575 2023-01-23 10:04:36.650545: step: 2804/1545, loss: 0.23664376139640808 2023-01-23 10:04:37.532341: step: 2806/1545, loss: 0.7093136310577393 2023-01-23 10:04:38.432143: step: 2808/1545, loss: 0.11947132647037506 2023-01-23 10:04:39.309121: step: 2810/1545, loss: 0.7989013195037842 2023-01-23 10:04:40.175900: step: 2812/1545, loss: 0.08804773539304733 2023-01-23 10:04:41.055754: step: 2814/1545, loss: 0.028649678453803062 2023-01-23 10:04:41.950656: step: 2816/1545, loss: 0.1460576206445694 2023-01-23 10:04:42.862228: step: 2818/1545, loss: 0.35849806666374207 2023-01-23 10:04:43.742659: step: 2820/1545, loss: 0.3644145131111145 2023-01-23 10:04:44.642341: step: 2822/1545, loss: 4.965322017669678 2023-01-23 10:04:45.484279: step: 2824/1545, loss: 0.23409877717494965 2023-01-23 10:04:46.340508: step: 2826/1545, loss: 0.08700628578662872 2023-01-23 10:04:47.213579: step: 2828/1545, loss: 0.05879773944616318 2023-01-23 10:04:48.072973: step: 2830/1545, loss: 0.03087928704917431 2023-01-23 10:04:48.971801: step: 2832/1545, loss: 0.09574186056852341 2023-01-23 10:04:49.860737: step: 2834/1545, loss: 0.11367160826921463 2023-01-23 10:04:50.747654: step: 2836/1545, loss: 0.3104091286659241 2023-01-23 10:04:51.617781: step: 2838/1545, loss: 0.1000162810087204 2023-01-23 10:04:52.461166: step: 2840/1545, loss: 0.09887375682592392 2023-01-23 10:04:53.386550: step: 2842/1545, loss: 0.460750937461853 2023-01-23 10:04:54.250901: step: 2844/1545, loss: 0.22485390305519104 2023-01-23 10:04:55.180723: step: 2846/1545, loss: 0.31059446930885315 2023-01-23 10:04:56.086546: step: 2848/1545, loss: 0.21566784381866455 2023-01-23 10:04:56.956925: step: 2850/1545, loss: 0.03009358048439026 2023-01-23 10:04:57.852612: step: 2852/1545, loss: 0.13116584718227386 2023-01-23 10:04:58.707515: step: 2854/1545, loss: 0.07602986693382263 2023-01-23 10:04:59.570520: step: 2856/1545, loss: 0.37257447838783264 2023-01-23 10:05:00.459975: step: 2858/1545, loss: 0.36127156019210815 2023-01-23 10:05:01.340064: step: 2860/1545, loss: 0.1687329262495041 2023-01-23 10:05:02.223156: step: 2862/1545, loss: 0.5185651779174805 2023-01-23 10:05:03.133780: step: 2864/1545, loss: 0.061085883527994156 2023-01-23 10:05:04.014024: step: 2866/1545, loss: 0.5599331259727478 2023-01-23 10:05:04.884593: step: 2868/1545, loss: 0.07951407134532928 2023-01-23 10:05:05.741235: step: 2870/1545, loss: 0.16004295647144318 2023-01-23 10:05:06.611076: step: 2872/1545, loss: 2.326834201812744 2023-01-23 10:05:07.471503: step: 2874/1545, loss: 0.07037684321403503 2023-01-23 10:05:08.406979: step: 2876/1545, loss: 0.349616676568985 2023-01-23 10:05:09.294896: step: 2878/1545, loss: 0.2660280764102936 2023-01-23 10:05:10.163390: step: 2880/1545, loss: 0.0177761223167181 2023-01-23 10:05:11.036939: step: 2882/1545, loss: 0.139408677816391 2023-01-23 10:05:11.902480: step: 2884/1545, loss: 1.0473830699920654 2023-01-23 10:05:12.763544: step: 2886/1545, loss: 0.20565462112426758 2023-01-23 10:05:13.638962: step: 2888/1545, loss: 0.4049035608768463 2023-01-23 10:05:14.565248: step: 2890/1545, loss: 0.142790749669075 2023-01-23 10:05:15.464815: step: 2892/1545, loss: 0.15463928878307343 2023-01-23 10:05:16.391600: step: 2894/1545, loss: 0.4260641932487488 2023-01-23 10:05:17.394543: step: 2896/1545, loss: 0.1586771160364151 2023-01-23 10:05:18.259809: step: 2898/1545, loss: 1.2519088983535767 2023-01-23 10:05:19.150006: step: 2900/1545, loss: 0.0877327024936676 2023-01-23 10:05:20.154161: step: 2902/1545, loss: 0.2876488268375397 2023-01-23 10:05:21.011220: step: 2904/1545, loss: 0.11007966101169586 2023-01-23 10:05:21.828721: step: 2906/1545, loss: 0.134658545255661 2023-01-23 10:05:22.736539: step: 2908/1545, loss: 0.4262595772743225 2023-01-23 10:05:23.606207: step: 2910/1545, loss: 0.2983650863170624 2023-01-23 10:05:24.468944: step: 2912/1545, loss: 0.1067735031247139 2023-01-23 10:05:25.333830: step: 2914/1545, loss: 0.3878510296344757 2023-01-23 10:05:26.205137: step: 2916/1545, loss: 0.4948276877403259 2023-01-23 10:05:27.186573: step: 2918/1545, loss: 1.6209369897842407 2023-01-23 10:05:28.060959: step: 2920/1545, loss: 0.08570791035890579 2023-01-23 10:05:28.956723: step: 2922/1545, loss: 0.1540173888206482 2023-01-23 10:05:29.843659: step: 2924/1545, loss: 0.16752514243125916 2023-01-23 10:05:30.746184: step: 2926/1545, loss: 0.11994846165180206 2023-01-23 10:05:31.646131: step: 2928/1545, loss: 0.2846011519432068 2023-01-23 10:05:32.528839: step: 2930/1545, loss: 0.22901904582977295 2023-01-23 10:05:33.429053: step: 2932/1545, loss: 0.25508037209510803 2023-01-23 10:05:34.326862: step: 2934/1545, loss: 0.21859391033649445 2023-01-23 10:05:35.205474: step: 2936/1545, loss: 0.0604173019528389 2023-01-23 10:05:36.069804: step: 2938/1545, loss: 0.48985210061073303 2023-01-23 10:05:37.029641: step: 2940/1545, loss: 0.31674808263778687 2023-01-23 10:05:37.881056: step: 2942/1545, loss: 0.11606435477733612 2023-01-23 10:05:38.768634: step: 2944/1545, loss: 0.27907994389533997 2023-01-23 10:05:39.737722: step: 2946/1545, loss: 0.08312419801950455 2023-01-23 10:05:40.622770: step: 2948/1545, loss: 0.8664381504058838 2023-01-23 10:05:41.518865: step: 2950/1545, loss: 0.2986077070236206 2023-01-23 10:05:42.434177: step: 2952/1545, loss: 0.18006955087184906 2023-01-23 10:05:43.333594: step: 2954/1545, loss: 0.1733064502477646 2023-01-23 10:05:44.202756: step: 2956/1545, loss: 0.6959344148635864 2023-01-23 10:05:45.087392: step: 2958/1545, loss: 0.10099910199642181 2023-01-23 10:05:45.943232: step: 2960/1545, loss: 0.2424258589744568 2023-01-23 10:05:46.844395: step: 2962/1545, loss: 0.05222016200423241 2023-01-23 10:05:47.739124: step: 2964/1545, loss: 0.17106813192367554 2023-01-23 10:05:48.607828: step: 2966/1545, loss: 0.15247975289821625 2023-01-23 10:05:49.493806: step: 2968/1545, loss: 0.09612004458904266 2023-01-23 10:05:50.388842: step: 2970/1545, loss: 0.06617099046707153 2023-01-23 10:05:51.262283: step: 2972/1545, loss: 0.5889201164245605 2023-01-23 10:05:52.130151: step: 2974/1545, loss: 0.05811433494091034 2023-01-23 10:05:53.028294: step: 2976/1545, loss: 0.18760453164577484 2023-01-23 10:05:53.995716: step: 2978/1545, loss: 0.2748467028141022 2023-01-23 10:05:54.916816: step: 2980/1545, loss: 1.4618175029754639 2023-01-23 10:05:55.853715: step: 2982/1545, loss: 0.19521552324295044 2023-01-23 10:05:56.730525: step: 2984/1545, loss: 2.2850563526153564 2023-01-23 10:05:57.635246: step: 2986/1545, loss: 0.15630130469799042 2023-01-23 10:05:58.488317: step: 2988/1545, loss: 0.02186872623860836 2023-01-23 10:05:59.326618: step: 2990/1545, loss: 0.11887580156326294 2023-01-23 10:06:00.231396: step: 2992/1545, loss: 0.9849172830581665 2023-01-23 10:06:01.143150: step: 2994/1545, loss: 0.19748170673847198 2023-01-23 10:06:02.072742: step: 2996/1545, loss: 0.18369486927986145 2023-01-23 10:06:02.942815: step: 2998/1545, loss: 0.4111422896385193 2023-01-23 10:06:03.819171: step: 3000/1545, loss: 0.24901898205280304 2023-01-23 10:06:04.723156: step: 3002/1545, loss: 0.29696765542030334 2023-01-23 10:06:05.576003: step: 3004/1545, loss: 0.1553475260734558 2023-01-23 10:06:06.457960: step: 3006/1545, loss: 0.30469927191734314 2023-01-23 10:06:07.334624: step: 3008/1545, loss: 0.0357186459004879 2023-01-23 10:06:08.195949: step: 3010/1545, loss: 0.11721387505531311 2023-01-23 10:06:09.056290: step: 3012/1545, loss: 0.2298157811164856 2023-01-23 10:06:09.943502: step: 3014/1545, loss: 0.6135212182998657 2023-01-23 10:06:10.785073: step: 3016/1545, loss: 0.15895558893680573 2023-01-23 10:06:11.710335: step: 3018/1545, loss: 0.15486791729927063 2023-01-23 10:06:12.634956: step: 3020/1545, loss: 0.10272879898548126 2023-01-23 10:06:13.495810: step: 3022/1545, loss: 0.15617215633392334 2023-01-23 10:06:14.357440: step: 3024/1545, loss: 0.10346294194459915 2023-01-23 10:06:15.266481: step: 3026/1545, loss: 0.44380712509155273 2023-01-23 10:06:16.161664: step: 3028/1545, loss: 0.40427467226982117 2023-01-23 10:06:17.021329: step: 3030/1545, loss: 0.10800359398126602 2023-01-23 10:06:17.894133: step: 3032/1545, loss: 0.09850993752479553 2023-01-23 10:06:18.801803: step: 3034/1545, loss: 0.22676993906497955 2023-01-23 10:06:19.751641: step: 3036/1545, loss: 0.17820614576339722 2023-01-23 10:06:20.662104: step: 3038/1545, loss: 0.13939674198627472 2023-01-23 10:06:21.517781: step: 3040/1545, loss: 0.10054019093513489 2023-01-23 10:06:22.411505: step: 3042/1545, loss: 0.25881925225257874 2023-01-23 10:06:23.273306: step: 3044/1545, loss: 0.3743974268436432 2023-01-23 10:06:24.187745: step: 3046/1545, loss: 0.23757325112819672 2023-01-23 10:06:25.058336: step: 3048/1545, loss: 0.0641946941614151 2023-01-23 10:06:25.895838: step: 3050/1545, loss: 0.1846778392791748 2023-01-23 10:06:26.723755: step: 3052/1545, loss: 0.9238994717597961 2023-01-23 10:06:27.635384: step: 3054/1545, loss: 0.13959157466888428 2023-01-23 10:06:28.573483: step: 3056/1545, loss: 0.36869439482688904 2023-01-23 10:06:29.445272: step: 3058/1545, loss: 1.0777555704116821 2023-01-23 10:06:30.351922: step: 3060/1545, loss: 0.268562912940979 2023-01-23 10:06:31.242474: step: 3062/1545, loss: 0.18689218163490295 2023-01-23 10:06:32.085467: step: 3064/1545, loss: 0.325800359249115 2023-01-23 10:06:32.980251: step: 3066/1545, loss: 0.21042200922966003 2023-01-23 10:06:33.937620: step: 3068/1545, loss: 0.015766138210892677 2023-01-23 10:06:34.806350: step: 3070/1545, loss: 0.1733100414276123 2023-01-23 10:06:35.709462: step: 3072/1545, loss: 0.40262582898139954 2023-01-23 10:06:36.666280: step: 3074/1545, loss: 0.2236873358488083 2023-01-23 10:06:37.550685: step: 3076/1545, loss: 0.5853238701820374 2023-01-23 10:06:38.420573: step: 3078/1545, loss: 0.1905457079410553 2023-01-23 10:06:39.300022: step: 3080/1545, loss: 0.13180792331695557 2023-01-23 10:06:40.151092: step: 3082/1545, loss: 0.0819525346159935 2023-01-23 10:06:41.046892: step: 3084/1545, loss: 0.4032060503959656 2023-01-23 10:06:41.945045: step: 3086/1545, loss: 0.07920178025960922 2023-01-23 10:06:42.819209: step: 3088/1545, loss: 0.28814783692359924 2023-01-23 10:06:43.672149: step: 3090/1545, loss: 0.09629587084054947 ================================================== Loss: 0.297 -------------------- Dev Chinese: {'event': {'p': 0.5932388222464559, 'r': 0.7243675099866844, 'f1': 0.6522781774580336}, 'argument': {'p': 0.6456739634692049, 'r': 0.6703401598264555, 'f1': 0.6577759010424976}, 'combined': 0.4290528659078162, 'epoch': 10} Test Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6888905035480135, 'r': 0.7304184316520144, 'f1': 0.7090469293925666}, 'combined': 0.4933217728641709, 'epoch': 10} Dev Korean: {'event': {'p': 0.6017505470459519, 'r': 0.7323568575233023, 'f1': 0.6606606606606608}, 'argument': {'p': 0.6407581917570931, 'r': 0.6686800363265232, 'f1': 0.6544214179048546}, 'combined': 0.43235048630350764, 'epoch': 10} Test Korean: {'event': {'p': 0.6312169312169312, 'r': 0.7627877237851662, 'f1': 0.6907932831499711}, 'argument': {'p': 0.6799729567320546, 'r': 0.7262048842715144, 'f1': 0.7023289202153028}, 'combined': 0.4851641006467031, 'epoch': 10} Dev Russian: {'event': {'p': 0.562007874015748, 'r': 0.7603195739014648, 'f1': 0.6462931522354273}, 'argument': {'p': 0.6402602479328566, 'r': 0.6750669566902938, 'f1': 0.6572030678642276}, 'combined': 0.42474584238876506, 'epoch': 10} Test Russian: {'event': {'p': 0.6233183856502242, 'r': 0.7998721227621484, 'f1': 0.7006440772892747}, 'argument': {'p': 0.6896732799106262, 'r': 0.7407984425546936, 'f1': 0.7143222527305366}, 'combined': 0.5004856556515829, 'epoch': 10} Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.6304924242424242, 'r': 0.6252817430503381, 'f1': 0.6278762731044889}, 'combined': 0.42809745893487877, 'epoch': 10} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.5476190476190477, 'r': 0.4350945857795173, 'f1': 0.48491457651763004}, 'combined': 0.3062618378006085, 'epoch': 10} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5592347339448142, 'r': 0.5891937375490006, 'f1': 0.5738234661346789}, 'combined': 0.3195978798724794, 'epoch': 10} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.6540410788569386, 'r': 0.6466702177127959, 'f1': 0.6503347637141906}, 'combined': 0.4374624236395757, 'epoch': 9} Test for Korean: {'event': {'p': 0.6354497354497355, 'r': 0.7679028132992327, 'f1': 0.6954255935147655}, 'argument': {'p': 0.7132062904851311, 'r': 0.7077515578619179, 'f1': 0.7104684544372034}, 'combined': 0.4940779466005103, 'epoch': 9} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6633986928104574, 'r': 0.46990740740740733, 'f1': 0.5501355013550133}, 'combined': 0.3474540008557979, 'epoch': 9} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 11 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 10:12:03.216746: step: 2/1545, loss: 0.04014342650771141 2023-01-23 10:12:04.134287: step: 4/1545, loss: 0.07143139094114304 2023-01-23 10:12:05.033438: step: 6/1545, loss: 0.15557004511356354 2023-01-23 10:12:05.946169: step: 8/1545, loss: 2.186062812805176 2023-01-23 10:12:06.841992: step: 10/1545, loss: 0.14414379000663757 2023-01-23 10:12:07.752369: step: 12/1545, loss: 0.21252873539924622 2023-01-23 10:12:08.695274: step: 14/1545, loss: 0.06222350895404816 2023-01-23 10:12:09.552274: step: 16/1545, loss: 0.8934947848320007 2023-01-23 10:12:10.463858: step: 18/1545, loss: 0.2921135127544403 2023-01-23 10:12:11.362239: step: 20/1545, loss: 0.22296912968158722 2023-01-23 10:12:12.223556: step: 22/1545, loss: 0.4899011552333832 2023-01-23 10:12:13.127658: step: 24/1545, loss: 0.3855225443840027 2023-01-23 10:12:14.024354: step: 26/1545, loss: 0.06214413791894913 2023-01-23 10:12:15.009798: step: 28/1545, loss: 0.1552390307188034 2023-01-23 10:12:15.971616: step: 30/1545, loss: 0.16652998328208923 2023-01-23 10:12:16.894946: step: 32/1545, loss: 0.14551115036010742 2023-01-23 10:12:17.768820: step: 34/1545, loss: 0.4521622061729431 2023-01-23 10:12:18.619674: step: 36/1545, loss: 0.03793266415596008 2023-01-23 10:12:19.525604: step: 38/1545, loss: 0.09853722900152206 2023-01-23 10:12:20.417467: step: 40/1545, loss: 0.6115421056747437 2023-01-23 10:12:21.288931: step: 42/1545, loss: 0.10913262516260147 2023-01-23 10:12:22.154372: step: 44/1545, loss: 0.9879986643791199 2023-01-23 10:12:23.037422: step: 46/1545, loss: 0.2717334032058716 2023-01-23 10:12:24.022532: step: 48/1545, loss: 1.7605535984039307 2023-01-23 10:12:24.909279: step: 50/1545, loss: 0.0570431686937809 2023-01-23 10:12:25.785765: step: 52/1545, loss: 2.0799202919006348 2023-01-23 10:12:26.624808: step: 54/1545, loss: 0.06264974921941757 2023-01-23 10:12:27.546422: step: 56/1545, loss: 0.22270677983760834 2023-01-23 10:12:28.496369: step: 58/1545, loss: 0.014545346610248089 2023-01-23 10:12:29.405775: step: 60/1545, loss: 0.106283038854599 2023-01-23 10:12:30.317326: step: 62/1545, loss: 0.17022186517715454 2023-01-23 10:12:31.170643: step: 64/1545, loss: 0.1933789700269699 2023-01-23 10:12:32.044434: step: 66/1545, loss: 0.37894749641418457 2023-01-23 10:12:32.935561: step: 68/1545, loss: 0.6780000329017639 2023-01-23 10:12:33.815046: step: 70/1545, loss: 0.5036174058914185 2023-01-23 10:12:34.699607: step: 72/1545, loss: 0.5601022839546204 2023-01-23 10:12:35.616774: step: 74/1545, loss: 0.322042316198349 2023-01-23 10:12:36.505404: step: 76/1545, loss: 0.256497859954834 2023-01-23 10:12:37.409848: step: 78/1545, loss: 0.0461115837097168 2023-01-23 10:12:38.262602: step: 80/1545, loss: 0.050027020275592804 2023-01-23 10:12:39.114342: step: 82/1545, loss: 0.05785990133881569 2023-01-23 10:12:39.965322: step: 84/1545, loss: 0.6557408571243286 2023-01-23 10:12:40.928085: step: 86/1545, loss: 0.08775666356086731 2023-01-23 10:12:41.777289: step: 88/1545, loss: 0.44698983430862427 2023-01-23 10:12:42.648673: step: 90/1545, loss: 0.04995016008615494 2023-01-23 10:12:43.526760: step: 92/1545, loss: 0.05694561451673508 2023-01-23 10:12:44.470156: step: 94/1545, loss: 0.012755701318383217 2023-01-23 10:12:45.348395: step: 96/1545, loss: 0.4539891183376312 2023-01-23 10:12:46.253917: step: 98/1545, loss: 0.04533366113901138 2023-01-23 10:12:47.121646: step: 100/1545, loss: 0.1808157116174698 2023-01-23 10:12:48.051501: step: 102/1545, loss: 0.3669765889644623 2023-01-23 10:12:48.971066: step: 104/1545, loss: 0.24968542158603668 2023-01-23 10:12:49.825851: step: 106/1545, loss: 0.3550250232219696 2023-01-23 10:12:50.704386: step: 108/1545, loss: 0.011286837980151176 2023-01-23 10:12:51.557930: step: 110/1545, loss: 0.020458439365029335 2023-01-23 10:12:52.478479: step: 112/1545, loss: 0.049642596393823624 2023-01-23 10:12:53.350587: step: 114/1545, loss: 0.17256617546081543 2023-01-23 10:12:54.291083: step: 116/1545, loss: 0.14380311965942383 2023-01-23 10:12:55.173920: step: 118/1545, loss: 0.019968055188655853 2023-01-23 10:12:56.060732: step: 120/1545, loss: 0.040341246873140335 2023-01-23 10:12:56.919454: step: 122/1545, loss: 0.17087629437446594 2023-01-23 10:12:57.819704: step: 124/1545, loss: 0.04204714298248291 2023-01-23 10:12:58.666585: step: 126/1545, loss: 0.02625419571995735 2023-01-23 10:12:59.589203: step: 128/1545, loss: 0.05811196565628052 2023-01-23 10:13:00.523451: step: 130/1545, loss: 0.17766359448432922 2023-01-23 10:13:01.393300: step: 132/1545, loss: 0.07817760854959488 2023-01-23 10:13:02.276008: step: 134/1545, loss: 0.007651959545910358 2023-01-23 10:13:03.138263: step: 136/1545, loss: 0.09512097388505936 2023-01-23 10:13:04.031530: step: 138/1545, loss: 0.1894119530916214 2023-01-23 10:13:04.891887: step: 140/1545, loss: 0.19300055503845215 2023-01-23 10:13:05.792580: step: 142/1545, loss: 0.3288572430610657 2023-01-23 10:13:06.718722: step: 144/1545, loss: 0.02416257932782173 2023-01-23 10:13:07.616682: step: 146/1545, loss: 0.017126692458987236 2023-01-23 10:13:08.486428: step: 148/1545, loss: 0.01934344694018364 2023-01-23 10:13:09.353971: step: 150/1545, loss: 0.11333464831113815 2023-01-23 10:13:10.329263: step: 152/1545, loss: 0.36238738894462585 2023-01-23 10:13:11.205654: step: 154/1545, loss: 0.04919072240591049 2023-01-23 10:13:12.088772: step: 156/1545, loss: 0.044921305030584335 2023-01-23 10:13:12.993054: step: 158/1545, loss: 0.4826953113079071 2023-01-23 10:13:13.869202: step: 160/1545, loss: 0.08241688460111618 2023-01-23 10:13:14.728353: step: 162/1545, loss: 0.024926939979195595 2023-01-23 10:13:15.612265: step: 164/1545, loss: 0.3063265085220337 2023-01-23 10:13:16.475930: step: 166/1545, loss: 0.025813817977905273 2023-01-23 10:13:17.380380: step: 168/1545, loss: 0.10006082057952881 2023-01-23 10:13:18.248111: step: 170/1545, loss: 0.06641159951686859 2023-01-23 10:13:19.123228: step: 172/1545, loss: 0.03877966105937958 2023-01-23 10:13:19.986944: step: 174/1545, loss: 0.07096943259239197 2023-01-23 10:13:20.942261: step: 176/1545, loss: 0.28951379656791687 2023-01-23 10:13:21.809186: step: 178/1545, loss: 0.029330728575587273 2023-01-23 10:13:22.737438: step: 180/1545, loss: 0.013904628343880177 2023-01-23 10:13:23.606450: step: 182/1545, loss: 0.08870216459035873 2023-01-23 10:13:24.601347: step: 184/1545, loss: 0.09999038279056549 2023-01-23 10:13:25.473652: step: 186/1545, loss: 0.14570164680480957 2023-01-23 10:13:26.369013: step: 188/1545, loss: 0.12305819243192673 2023-01-23 10:13:27.264676: step: 190/1545, loss: 0.08991983532905579 2023-01-23 10:13:28.150512: step: 192/1545, loss: 0.010487725958228111 2023-01-23 10:13:29.042319: step: 194/1545, loss: 2.972480535507202 2023-01-23 10:13:29.945834: step: 196/1545, loss: 0.3869366943836212 2023-01-23 10:13:30.841546: step: 198/1545, loss: 0.17855505645275116 2023-01-23 10:13:31.678094: step: 200/1545, loss: 0.18983399868011475 2023-01-23 10:13:32.560841: step: 202/1545, loss: 0.30089378356933594 2023-01-23 10:13:33.503027: step: 204/1545, loss: 0.7184596657752991 2023-01-23 10:13:34.386664: step: 206/1545, loss: 0.014206452295184135 2023-01-23 10:13:35.279468: step: 208/1545, loss: 0.018055720254778862 2023-01-23 10:13:36.190808: step: 210/1545, loss: 0.258335143327713 2023-01-23 10:13:37.099446: step: 212/1545, loss: 0.12116244435310364 2023-01-23 10:13:38.004922: step: 214/1545, loss: 0.21062469482421875 2023-01-23 10:13:38.919016: step: 216/1545, loss: 0.13233882188796997 2023-01-23 10:13:39.774666: step: 218/1545, loss: 0.31170454621315 2023-01-23 10:13:40.720969: step: 220/1545, loss: 0.043682292103767395 2023-01-23 10:13:41.578255: step: 222/1545, loss: 0.3753443956375122 2023-01-23 10:13:42.490031: step: 224/1545, loss: 0.5679621696472168 2023-01-23 10:13:43.414404: step: 226/1545, loss: 0.26570433378219604 2023-01-23 10:13:44.278721: step: 228/1545, loss: 0.19525013864040375 2023-01-23 10:13:45.163786: step: 230/1545, loss: 0.07567707449197769 2023-01-23 10:13:46.109948: step: 232/1545, loss: 0.24298782646656036 2023-01-23 10:13:46.993114: step: 234/1545, loss: 0.06268639862537384 2023-01-23 10:13:47.856030: step: 236/1545, loss: 0.03603706136345863 2023-01-23 10:13:48.725903: step: 238/1545, loss: 0.055502768605947495 2023-01-23 10:13:49.628745: step: 240/1545, loss: 0.2903207540512085 2023-01-23 10:13:50.490201: step: 242/1545, loss: 0.24337154626846313 2023-01-23 10:13:51.345055: step: 244/1545, loss: 0.20228806138038635 2023-01-23 10:13:52.255719: step: 246/1545, loss: 0.02275710739195347 2023-01-23 10:13:53.145436: step: 248/1545, loss: 0.13508979976177216 2023-01-23 10:13:54.006179: step: 250/1545, loss: 0.0630536749958992 2023-01-23 10:13:54.872963: step: 252/1545, loss: 0.15929841995239258 2023-01-23 10:13:55.730706: step: 254/1545, loss: 0.07740262895822525 2023-01-23 10:13:56.601104: step: 256/1545, loss: 0.13031604886054993 2023-01-23 10:13:57.457572: step: 258/1545, loss: 0.09979123622179031 2023-01-23 10:13:58.315702: step: 260/1545, loss: 0.19906161725521088 2023-01-23 10:13:59.183416: step: 262/1545, loss: 0.11472014337778091 2023-01-23 10:14:00.088996: step: 264/1545, loss: 0.0031153077725321054 2023-01-23 10:14:00.945814: step: 266/1545, loss: 0.07914786040782928 2023-01-23 10:14:01.799182: step: 268/1545, loss: 0.1371527463197708 2023-01-23 10:14:02.652085: step: 270/1545, loss: 0.07277031242847443 2023-01-23 10:14:03.573975: step: 272/1545, loss: 0.3129587769508362 2023-01-23 10:14:04.466086: step: 274/1545, loss: 0.3344613313674927 2023-01-23 10:14:05.435173: step: 276/1545, loss: 0.26263225078582764 2023-01-23 10:14:06.317342: step: 278/1545, loss: 0.20487084984779358 2023-01-23 10:14:07.234412: step: 280/1545, loss: 0.2725612223148346 2023-01-23 10:14:08.183453: step: 282/1545, loss: 0.0688352882862091 2023-01-23 10:14:09.083363: step: 284/1545, loss: 0.3362616002559662 2023-01-23 10:14:09.953177: step: 286/1545, loss: 1.3038138151168823 2023-01-23 10:14:10.839095: step: 288/1545, loss: 0.021890802308917046 2023-01-23 10:14:11.727101: step: 290/1545, loss: 0.07818721234798431 2023-01-23 10:14:12.631167: step: 292/1545, loss: 0.016091689467430115 2023-01-23 10:14:13.506091: step: 294/1545, loss: 0.13082405924797058 2023-01-23 10:14:14.436430: step: 296/1545, loss: 0.05437992513179779 2023-01-23 10:14:15.329963: step: 298/1545, loss: 0.16271305084228516 2023-01-23 10:14:16.220349: step: 300/1545, loss: 0.04957836866378784 2023-01-23 10:14:17.116309: step: 302/1545, loss: 0.4934139549732208 2023-01-23 10:14:18.009855: step: 304/1545, loss: 0.10183632373809814 2023-01-23 10:14:18.904716: step: 306/1545, loss: 0.1857481598854065 2023-01-23 10:14:19.839436: step: 308/1545, loss: 0.3504602313041687 2023-01-23 10:14:20.806187: step: 310/1545, loss: 0.21876953542232513 2023-01-23 10:14:21.685432: step: 312/1545, loss: 0.5965149402618408 2023-01-23 10:14:22.562457: step: 314/1545, loss: 0.5613508224487305 2023-01-23 10:14:23.473447: step: 316/1545, loss: 0.045287806540727615 2023-01-23 10:14:24.387291: step: 318/1545, loss: 0.18200735747814178 2023-01-23 10:14:25.274448: step: 320/1545, loss: 0.3684264123439789 2023-01-23 10:14:26.131971: step: 322/1545, loss: 0.08982886373996735 2023-01-23 10:14:26.995875: step: 324/1545, loss: 0.12591835856437683 2023-01-23 10:14:27.879468: step: 326/1545, loss: 0.16280564665794373 2023-01-23 10:14:28.755850: step: 328/1545, loss: 0.18423210084438324 2023-01-23 10:14:29.660345: step: 330/1545, loss: 0.10816965252161026 2023-01-23 10:14:30.648805: step: 332/1545, loss: 0.3775467872619629 2023-01-23 10:14:31.531680: step: 334/1545, loss: 0.4247531592845917 2023-01-23 10:14:32.403842: step: 336/1545, loss: 0.928400993347168 2023-01-23 10:14:33.314102: step: 338/1545, loss: 0.02780265361070633 2023-01-23 10:14:34.211688: step: 340/1545, loss: 1.1220592260360718 2023-01-23 10:14:35.047048: step: 342/1545, loss: 2.480376720428467 2023-01-23 10:14:35.895624: step: 344/1545, loss: 0.018823670223355293 2023-01-23 10:14:36.754302: step: 346/1545, loss: 0.13355252146720886 2023-01-23 10:14:37.607606: step: 348/1545, loss: 0.014678267762064934 2023-01-23 10:14:38.470693: step: 350/1545, loss: 0.04755902290344238 2023-01-23 10:14:39.389001: step: 352/1545, loss: 0.05593062937259674 2023-01-23 10:14:40.259990: step: 354/1545, loss: 0.11178126931190491 2023-01-23 10:14:41.205366: step: 356/1545, loss: 0.3745991587638855 2023-01-23 10:14:42.121923: step: 358/1545, loss: 0.023351317271590233 2023-01-23 10:14:43.032007: step: 360/1545, loss: 0.13387832045555115 2023-01-23 10:14:43.958771: step: 362/1545, loss: 0.0020322478376328945 2023-01-23 10:14:44.843755: step: 364/1545, loss: 0.33494117856025696 2023-01-23 10:14:45.729412: step: 366/1545, loss: 0.4350924491882324 2023-01-23 10:14:46.610316: step: 368/1545, loss: 0.3575108051300049 2023-01-23 10:14:47.471462: step: 370/1545, loss: 0.0224200040102005 2023-01-23 10:14:48.350038: step: 372/1545, loss: 0.24062858521938324 2023-01-23 10:14:49.267705: step: 374/1545, loss: 0.4739886224269867 2023-01-23 10:14:50.128543: step: 376/1545, loss: 0.05572623759508133 2023-01-23 10:14:51.004129: step: 378/1545, loss: 0.4777128994464874 2023-01-23 10:14:51.851108: step: 380/1545, loss: 0.48052412271499634 2023-01-23 10:14:52.731938: step: 382/1545, loss: 0.07321647554636002 2023-01-23 10:14:53.613221: step: 384/1545, loss: 0.014700740575790405 2023-01-23 10:14:54.570578: step: 386/1545, loss: 0.09433899074792862 2023-01-23 10:14:55.478893: step: 388/1545, loss: 0.05475657060742378 2023-01-23 10:14:56.340174: step: 390/1545, loss: 0.6859056353569031 2023-01-23 10:14:57.202548: step: 392/1545, loss: 0.2199087142944336 2023-01-23 10:14:58.091230: step: 394/1545, loss: 0.20070315897464752 2023-01-23 10:14:58.994709: step: 396/1545, loss: 0.040287088602781296 2023-01-23 10:14:59.873310: step: 398/1545, loss: 0.43269312381744385 2023-01-23 10:15:00.724281: step: 400/1545, loss: 0.05115266516804695 2023-01-23 10:15:01.606409: step: 402/1545, loss: 0.0805835872888565 2023-01-23 10:15:02.478622: step: 404/1545, loss: 0.11232724040746689 2023-01-23 10:15:03.350232: step: 406/1545, loss: 0.04596197232604027 2023-01-23 10:15:04.297039: step: 408/1545, loss: 0.14296714961528778 2023-01-23 10:15:05.206656: step: 410/1545, loss: 0.016520507633686066 2023-01-23 10:15:06.107381: step: 412/1545, loss: 0.07698415219783783 2023-01-23 10:15:06.979746: step: 414/1545, loss: 0.03983712196350098 2023-01-23 10:15:07.846528: step: 416/1545, loss: 0.10447759926319122 2023-01-23 10:15:08.735289: step: 418/1545, loss: 0.21705269813537598 2023-01-23 10:15:09.627197: step: 420/1545, loss: 0.05542994290590286 2023-01-23 10:15:10.512036: step: 422/1545, loss: 0.050405360758304596 2023-01-23 10:15:11.411844: step: 424/1545, loss: 0.09972617775201797 2023-01-23 10:15:12.334735: step: 426/1545, loss: 0.12254173308610916 2023-01-23 10:15:13.213002: step: 428/1545, loss: 0.7031221985816956 2023-01-23 10:15:14.079003: step: 430/1545, loss: 0.16092607378959656 2023-01-23 10:15:14.991505: step: 432/1545, loss: 0.18379327654838562 2023-01-23 10:15:15.854031: step: 434/1545, loss: 0.03842099756002426 2023-01-23 10:15:16.729956: step: 436/1545, loss: 0.6628451943397522 2023-01-23 10:15:17.618730: step: 438/1545, loss: 0.09217113256454468 2023-01-23 10:15:18.477248: step: 440/1545, loss: 0.25692492723464966 2023-01-23 10:15:19.355909: step: 442/1545, loss: 0.232340008020401 2023-01-23 10:15:20.245697: step: 444/1545, loss: 0.463071346282959 2023-01-23 10:15:21.168215: step: 446/1545, loss: 0.24174851179122925 2023-01-23 10:15:22.051636: step: 448/1545, loss: 0.3062349855899811 2023-01-23 10:15:22.949172: step: 450/1545, loss: 0.1278958022594452 2023-01-23 10:15:23.809654: step: 452/1545, loss: 0.14548085629940033 2023-01-23 10:15:24.733811: step: 454/1545, loss: 0.02691483497619629 2023-01-23 10:15:25.613725: step: 456/1545, loss: 0.10112547874450684 2023-01-23 10:15:26.468851: step: 458/1545, loss: 0.3128092288970947 2023-01-23 10:15:27.383361: step: 460/1545, loss: 0.3079269230365753 2023-01-23 10:15:28.260353: step: 462/1545, loss: 0.12788358330726624 2023-01-23 10:15:29.140456: step: 464/1545, loss: 0.03701731562614441 2023-01-23 10:15:30.018958: step: 466/1545, loss: 0.2604561746120453 2023-01-23 10:15:30.912835: step: 468/1545, loss: 0.24411913752555847 2023-01-23 10:15:31.800778: step: 470/1545, loss: 0.028187986463308334 2023-01-23 10:15:32.689772: step: 472/1545, loss: 0.43053293228149414 2023-01-23 10:15:33.587113: step: 474/1545, loss: 0.07911556959152222 2023-01-23 10:15:34.459335: step: 476/1545, loss: 0.036243733018636703 2023-01-23 10:15:35.331981: step: 478/1545, loss: 0.10944204032421112 2023-01-23 10:15:36.174966: step: 480/1545, loss: 0.2117765247821808 2023-01-23 10:15:37.030368: step: 482/1545, loss: 0.09737265110015869 2023-01-23 10:15:37.876647: step: 484/1545, loss: 0.7650327086448669 2023-01-23 10:15:38.753779: step: 486/1545, loss: 0.13722802698612213 2023-01-23 10:15:39.660240: step: 488/1545, loss: 0.15237726271152496 2023-01-23 10:15:40.502667: step: 490/1545, loss: 0.22730880975723267 2023-01-23 10:15:41.420534: step: 492/1545, loss: 0.1194930374622345 2023-01-23 10:15:42.322791: step: 494/1545, loss: 0.06475329399108887 2023-01-23 10:15:43.171955: step: 496/1545, loss: 0.5046523213386536 2023-01-23 10:15:44.063832: step: 498/1545, loss: 0.4009684920310974 2023-01-23 10:15:44.963229: step: 500/1545, loss: 0.09859469532966614 2023-01-23 10:15:45.890016: step: 502/1545, loss: 0.05893256142735481 2023-01-23 10:15:46.795787: step: 504/1545, loss: 0.21036413311958313 2023-01-23 10:15:47.657574: step: 506/1545, loss: 0.04734252020716667 2023-01-23 10:15:48.513414: step: 508/1545, loss: 0.022607892751693726 2023-01-23 10:15:49.395239: step: 510/1545, loss: 0.2115461379289627 2023-01-23 10:15:50.238631: step: 512/1545, loss: 0.1730680912733078 2023-01-23 10:15:51.158609: step: 514/1545, loss: 0.10647064447402954 2023-01-23 10:15:52.031689: step: 516/1545, loss: 0.14849314093589783 2023-01-23 10:15:52.895680: step: 518/1545, loss: 0.5077329874038696 2023-01-23 10:15:53.792607: step: 520/1545, loss: 0.04134420305490494 2023-01-23 10:15:54.659523: step: 522/1545, loss: 0.2130393087863922 2023-01-23 10:15:55.507269: step: 524/1545, loss: 0.24638968706130981 2023-01-23 10:15:56.376370: step: 526/1545, loss: 0.03794407472014427 2023-01-23 10:15:57.273430: step: 528/1545, loss: 0.07358318567276001 2023-01-23 10:15:58.216922: step: 530/1545, loss: 0.14781329035758972 2023-01-23 10:15:59.118741: step: 532/1545, loss: 0.21413502097129822 2023-01-23 10:16:00.011202: step: 534/1545, loss: 0.1665346622467041 2023-01-23 10:16:00.923914: step: 536/1545, loss: 0.08775873482227325 2023-01-23 10:16:01.833723: step: 538/1545, loss: 0.0603054016828537 2023-01-23 10:16:02.678866: step: 540/1545, loss: 0.18769855797290802 2023-01-23 10:16:03.603611: step: 542/1545, loss: 0.21195071935653687 2023-01-23 10:16:04.507862: step: 544/1545, loss: 0.05639468878507614 2023-01-23 10:16:05.357804: step: 546/1545, loss: 0.06821363419294357 2023-01-23 10:16:06.270453: step: 548/1545, loss: 0.12061681598424911 2023-01-23 10:16:07.157952: step: 550/1545, loss: 0.14699895679950714 2023-01-23 10:16:08.038307: step: 552/1545, loss: 0.03423203155398369 2023-01-23 10:16:08.929815: step: 554/1545, loss: 0.08622286468744278 2023-01-23 10:16:09.789175: step: 556/1545, loss: 0.9413260817527771 2023-01-23 10:16:10.682831: step: 558/1545, loss: 0.11469950526952744 2023-01-23 10:16:11.600068: step: 560/1545, loss: 0.07768712192773819 2023-01-23 10:16:12.507125: step: 562/1545, loss: 0.03968902677297592 2023-01-23 10:16:13.392880: step: 564/1545, loss: 0.11230774223804474 2023-01-23 10:16:14.240546: step: 566/1545, loss: 0.0877915546298027 2023-01-23 10:16:15.111706: step: 568/1545, loss: 0.1802252233028412 2023-01-23 10:16:15.957903: step: 570/1545, loss: 0.2470577210187912 2023-01-23 10:16:16.830958: step: 572/1545, loss: 0.04065435752272606 2023-01-23 10:16:17.712103: step: 574/1545, loss: 0.07451257854700089 2023-01-23 10:16:18.561615: step: 576/1545, loss: 0.01460997574031353 2023-01-23 10:16:19.448230: step: 578/1545, loss: 0.14767126739025116 2023-01-23 10:16:20.404587: step: 580/1545, loss: 0.10057936608791351 2023-01-23 10:16:21.262230: step: 582/1545, loss: 0.2646211087703705 2023-01-23 10:16:22.148305: step: 584/1545, loss: 0.08973012864589691 2023-01-23 10:16:23.044505: step: 586/1545, loss: 0.026395732536911964 2023-01-23 10:16:23.938767: step: 588/1545, loss: 0.09789500385522842 2023-01-23 10:16:24.829254: step: 590/1545, loss: 0.021299464628100395 2023-01-23 10:16:25.704056: step: 592/1545, loss: 0.2893742620944977 2023-01-23 10:16:26.597912: step: 594/1545, loss: 0.04140535742044449 2023-01-23 10:16:27.500287: step: 596/1545, loss: 0.08157998323440552 2023-01-23 10:16:28.388449: step: 598/1545, loss: 0.18455976247787476 2023-01-23 10:16:29.248701: step: 600/1545, loss: 0.4041471481323242 2023-01-23 10:16:30.163731: step: 602/1545, loss: 0.15090960264205933 2023-01-23 10:16:31.089606: step: 604/1545, loss: 0.09689167886972427 2023-01-23 10:16:31.993733: step: 606/1545, loss: 0.052868835628032684 2023-01-23 10:16:32.885889: step: 608/1545, loss: 0.021098904311656952 2023-01-23 10:16:33.780045: step: 610/1545, loss: 0.02961798943579197 2023-01-23 10:16:34.656075: step: 612/1545, loss: 0.0734543651342392 2023-01-23 10:16:35.549478: step: 614/1545, loss: 0.16292129456996918 2023-01-23 10:16:36.459662: step: 616/1545, loss: 0.10717454552650452 2023-01-23 10:16:37.348850: step: 618/1545, loss: 0.07551711797714233 2023-01-23 10:16:38.277015: step: 620/1545, loss: 0.138997882604599 2023-01-23 10:16:39.212549: step: 622/1545, loss: 0.2112351357936859 2023-01-23 10:16:40.063197: step: 624/1545, loss: 0.03258301317691803 2023-01-23 10:16:40.965405: step: 626/1545, loss: 1.2603706121444702 2023-01-23 10:16:41.858742: step: 628/1545, loss: 0.22544893622398376 2023-01-23 10:16:42.729362: step: 630/1545, loss: 0.03864756226539612 2023-01-23 10:16:43.580005: step: 632/1545, loss: 0.19070850312709808 2023-01-23 10:16:44.425826: step: 634/1545, loss: 0.3833830654621124 2023-01-23 10:16:45.295052: step: 636/1545, loss: 0.8715497851371765 2023-01-23 10:16:46.159362: step: 638/1545, loss: 0.13622313737869263 2023-01-23 10:16:47.002751: step: 640/1545, loss: 0.09807684272527695 2023-01-23 10:16:47.903318: step: 642/1545, loss: 0.18262222409248352 2023-01-23 10:16:48.806358: step: 644/1545, loss: 0.11895094811916351 2023-01-23 10:16:49.672980: step: 646/1545, loss: 0.08909676969051361 2023-01-23 10:16:50.555417: step: 648/1545, loss: 0.33063995838165283 2023-01-23 10:16:51.425636: step: 650/1545, loss: 1.3394901752471924 2023-01-23 10:16:52.324353: step: 652/1545, loss: 0.037362854927778244 2023-01-23 10:16:53.186862: step: 654/1545, loss: 0.15349075198173523 2023-01-23 10:16:54.142865: step: 656/1545, loss: 0.22255918383598328 2023-01-23 10:16:55.076428: step: 658/1545, loss: 0.21345846354961395 2023-01-23 10:16:55.990373: step: 660/1545, loss: 0.09000129252672195 2023-01-23 10:16:56.940474: step: 662/1545, loss: 0.013961417600512505 2023-01-23 10:16:57.824778: step: 664/1545, loss: 0.04050341993570328 2023-01-23 10:16:58.723137: step: 666/1545, loss: 0.5936319828033447 2023-01-23 10:16:59.631379: step: 668/1545, loss: 0.3215804100036621 2023-01-23 10:17:00.536451: step: 670/1545, loss: 0.31269994378089905 2023-01-23 10:17:01.469481: step: 672/1545, loss: 0.2150198519229889 2023-01-23 10:17:02.370171: step: 674/1545, loss: 0.006822837516665459 2023-01-23 10:17:03.335516: step: 676/1545, loss: 0.1242760568857193 2023-01-23 10:17:04.235820: step: 678/1545, loss: 0.289103239774704 2023-01-23 10:17:05.168612: step: 680/1545, loss: 0.2323266565799713 2023-01-23 10:17:06.018703: step: 682/1545, loss: 0.06980843096971512 2023-01-23 10:17:06.878150: step: 684/1545, loss: 0.1494358777999878 2023-01-23 10:17:07.751675: step: 686/1545, loss: 0.1775542050600052 2023-01-23 10:17:08.674314: step: 688/1545, loss: 0.13297976553440094 2023-01-23 10:17:09.563747: step: 690/1545, loss: 0.15817956626415253 2023-01-23 10:17:10.424938: step: 692/1545, loss: 0.2157527208328247 2023-01-23 10:17:11.376877: step: 694/1545, loss: 0.17123965919017792 2023-01-23 10:17:12.332945: step: 696/1545, loss: 0.21225251257419586 2023-01-23 10:17:13.193915: step: 698/1545, loss: 1.3727144002914429 2023-01-23 10:17:14.056304: step: 700/1545, loss: 0.03243999183177948 2023-01-23 10:17:14.933573: step: 702/1545, loss: 0.1162019819021225 2023-01-23 10:17:15.837450: step: 704/1545, loss: 0.16005507111549377 2023-01-23 10:17:16.712351: step: 706/1545, loss: 0.05289842560887337 2023-01-23 10:17:17.624304: step: 708/1545, loss: 0.2594303488731384 2023-01-23 10:17:18.527759: step: 710/1545, loss: 0.44919297099113464 2023-01-23 10:17:19.435050: step: 712/1545, loss: 0.04376264661550522 2023-01-23 10:17:20.313748: step: 714/1545, loss: 0.12645752727985382 2023-01-23 10:17:21.174997: step: 716/1545, loss: 0.11182264238595963 2023-01-23 10:17:22.074088: step: 718/1545, loss: 0.15093883872032166 2023-01-23 10:17:23.040461: step: 720/1545, loss: 0.147536039352417 2023-01-23 10:17:23.966775: step: 722/1545, loss: 0.21783024072647095 2023-01-23 10:17:24.830785: step: 724/1545, loss: 0.23817801475524902 2023-01-23 10:17:25.762469: step: 726/1545, loss: 0.21084313094615936 2023-01-23 10:17:26.658895: step: 728/1545, loss: 0.17063379287719727 2023-01-23 10:17:27.605618: step: 730/1545, loss: 0.23767666518688202 2023-01-23 10:17:28.509489: step: 732/1545, loss: 0.3888539671897888 2023-01-23 10:17:29.473260: step: 734/1545, loss: 0.5956157445907593 2023-01-23 10:17:30.331555: step: 736/1545, loss: 0.05065333470702171 2023-01-23 10:17:31.235468: step: 738/1545, loss: 0.14049629867076874 2023-01-23 10:17:32.106917: step: 740/1545, loss: 0.2755783498287201 2023-01-23 10:17:32.977475: step: 742/1545, loss: 0.018856897950172424 2023-01-23 10:17:33.912764: step: 744/1545, loss: 0.059574007987976074 2023-01-23 10:17:34.804261: step: 746/1545, loss: 0.04071751981973648 2023-01-23 10:17:35.678977: step: 748/1545, loss: 0.4476124942302704 2023-01-23 10:17:36.576400: step: 750/1545, loss: 0.017528507858514786 2023-01-23 10:17:37.423205: step: 752/1545, loss: 0.7276184558868408 2023-01-23 10:17:38.300716: step: 754/1545, loss: 0.21071243286132812 2023-01-23 10:17:39.218939: step: 756/1545, loss: 0.13131441175937653 2023-01-23 10:17:40.108827: step: 758/1545, loss: 0.3205363154411316 2023-01-23 10:17:40.966008: step: 760/1545, loss: 0.30027222633361816 2023-01-23 10:17:41.836698: step: 762/1545, loss: 0.18591046333312988 2023-01-23 10:17:42.774583: step: 764/1545, loss: 0.03808589652180672 2023-01-23 10:17:43.628712: step: 766/1545, loss: 0.17655135691165924 2023-01-23 10:17:44.523433: step: 768/1545, loss: 0.08013907819986343 2023-01-23 10:17:45.491657: step: 770/1545, loss: 0.05092478170990944 2023-01-23 10:17:46.346357: step: 772/1545, loss: 0.41091203689575195 2023-01-23 10:17:47.266318: step: 774/1545, loss: 0.41270095109939575 2023-01-23 10:17:48.243802: step: 776/1545, loss: 0.39648139476776123 2023-01-23 10:17:49.179275: step: 778/1545, loss: 0.08653075993061066 2023-01-23 10:17:50.046299: step: 780/1545, loss: 0.3892866373062134 2023-01-23 10:17:50.968247: step: 782/1545, loss: 0.10372015833854675 2023-01-23 10:17:51.880468: step: 784/1545, loss: 0.012689310126006603 2023-01-23 10:17:52.761287: step: 786/1545, loss: 0.3290103077888489 2023-01-23 10:17:53.635319: step: 788/1545, loss: 0.47038546204566956 2023-01-23 10:17:54.485202: step: 790/1545, loss: 0.0390813909471035 2023-01-23 10:17:55.395992: step: 792/1545, loss: 0.06442432105541229 2023-01-23 10:17:56.241647: step: 794/1545, loss: 0.006591795478016138 2023-01-23 10:17:57.125465: step: 796/1545, loss: 0.20515084266662598 2023-01-23 10:17:57.982834: step: 798/1545, loss: 0.0972667783498764 2023-01-23 10:17:58.874323: step: 800/1545, loss: 0.32561177015304565 2023-01-23 10:17:59.727041: step: 802/1545, loss: 0.18636102974414825 2023-01-23 10:18:00.682825: step: 804/1545, loss: 0.6401407718658447 2023-01-23 10:18:01.556865: step: 806/1545, loss: 0.27517393231391907 2023-01-23 10:18:02.447973: step: 808/1545, loss: 0.15028995275497437 2023-01-23 10:18:03.294203: step: 810/1545, loss: 0.12972743809223175 2023-01-23 10:18:04.198589: step: 812/1545, loss: 0.30143222212791443 2023-01-23 10:18:05.048761: step: 814/1545, loss: 0.09857571125030518 2023-01-23 10:18:05.909063: step: 816/1545, loss: 0.5058132410049438 2023-01-23 10:18:06.826625: step: 818/1545, loss: 0.18285934627056122 2023-01-23 10:18:07.740677: step: 820/1545, loss: 0.12107641249895096 2023-01-23 10:18:08.612164: step: 822/1545, loss: 0.29012638330459595 2023-01-23 10:18:09.493931: step: 824/1545, loss: 0.07483745366334915 2023-01-23 10:18:10.467251: step: 826/1545, loss: 0.03228284418582916 2023-01-23 10:18:11.341083: step: 828/1545, loss: 0.037588488310575485 2023-01-23 10:18:12.255592: step: 830/1545, loss: 0.29276445508003235 2023-01-23 10:18:13.150857: step: 832/1545, loss: 0.0163306575268507 2023-01-23 10:18:14.058294: step: 834/1545, loss: 0.34440040588378906 2023-01-23 10:18:14.932223: step: 836/1545, loss: 0.19798097014427185 2023-01-23 10:18:15.785637: step: 838/1545, loss: 0.0369550846517086 2023-01-23 10:18:16.708262: step: 840/1545, loss: 0.103181853890419 2023-01-23 10:18:17.596372: step: 842/1545, loss: 0.12246803939342499 2023-01-23 10:18:18.545054: step: 844/1545, loss: 0.30178722739219666 2023-01-23 10:18:19.419283: step: 846/1545, loss: 0.05579486861824989 2023-01-23 10:18:20.314570: step: 848/1545, loss: 0.0745958685874939 2023-01-23 10:18:21.193856: step: 850/1545, loss: 0.13708177208900452 2023-01-23 10:18:22.067218: step: 852/1545, loss: 0.6593519449234009 2023-01-23 10:18:22.946893: step: 854/1545, loss: 0.16173477470874786 2023-01-23 10:18:23.775030: step: 856/1545, loss: 0.10291898250579834 2023-01-23 10:18:24.671161: step: 858/1545, loss: 0.03548277169466019 2023-01-23 10:18:25.550646: step: 860/1545, loss: 0.11606267094612122 2023-01-23 10:18:26.389482: step: 862/1545, loss: 0.1898966282606125 2023-01-23 10:18:27.276488: step: 864/1545, loss: 0.06522780656814575 2023-01-23 10:18:28.174336: step: 866/1545, loss: 0.029161004349589348 2023-01-23 10:18:29.095389: step: 868/1545, loss: 0.031988997012376785 2023-01-23 10:18:29.935713: step: 870/1545, loss: 0.17869509756565094 2023-01-23 10:18:30.817079: step: 872/1545, loss: 0.021390758454799652 2023-01-23 10:18:31.689762: step: 874/1545, loss: 0.08390441536903381 2023-01-23 10:18:32.557736: step: 876/1545, loss: 0.09714295715093613 2023-01-23 10:18:33.434030: step: 878/1545, loss: 0.08903615176677704 2023-01-23 10:18:34.296022: step: 880/1545, loss: 0.11336556077003479 2023-01-23 10:18:35.193122: step: 882/1545, loss: 0.019154267385601997 2023-01-23 10:18:36.072405: step: 884/1545, loss: 0.2014022022485733 2023-01-23 10:18:37.009764: step: 886/1545, loss: 0.16959524154663086 2023-01-23 10:18:37.875288: step: 888/1545, loss: 0.17083457112312317 2023-01-23 10:18:38.751865: step: 890/1545, loss: 0.34999993443489075 2023-01-23 10:18:39.633842: step: 892/1545, loss: 0.15670518577098846 2023-01-23 10:18:40.489773: step: 894/1545, loss: 0.07949803024530411 2023-01-23 10:18:41.380587: step: 896/1545, loss: 0.18200083076953888 2023-01-23 10:18:42.259237: step: 898/1545, loss: 0.046576354652643204 2023-01-23 10:18:43.162727: step: 900/1545, loss: 0.07259261608123779 2023-01-23 10:18:44.056211: step: 902/1545, loss: 0.10068847984075546 2023-01-23 10:18:45.005600: step: 904/1545, loss: 0.49479660391807556 2023-01-23 10:18:45.913084: step: 906/1545, loss: 1.9320497512817383 2023-01-23 10:18:46.799295: step: 908/1545, loss: 0.28861793875694275 2023-01-23 10:18:47.682235: step: 910/1545, loss: 0.0890030637383461 2023-01-23 10:18:48.563805: step: 912/1545, loss: 0.01535065658390522 2023-01-23 10:18:49.449196: step: 914/1545, loss: 0.05047157034277916 2023-01-23 10:18:50.343577: step: 916/1545, loss: 0.10385952889919281 2023-01-23 10:18:51.216278: step: 918/1545, loss: 0.4364052414894104 2023-01-23 10:18:52.140839: step: 920/1545, loss: 0.06749647110700607 2023-01-23 10:18:53.010232: step: 922/1545, loss: 0.14745496213436127 2023-01-23 10:18:53.861976: step: 924/1545, loss: 0.5178443789482117 2023-01-23 10:18:54.773184: step: 926/1545, loss: 0.0253860205411911 2023-01-23 10:18:55.632275: step: 928/1545, loss: 0.20956633985042572 2023-01-23 10:18:56.457972: step: 930/1545, loss: 0.19007669389247894 2023-01-23 10:18:57.302481: step: 932/1545, loss: 0.06148112192749977 2023-01-23 10:18:58.184381: step: 934/1545, loss: 0.06833260506391525 2023-01-23 10:18:59.153104: step: 936/1545, loss: 0.028587907552719116 2023-01-23 10:19:00.022078: step: 938/1545, loss: 0.12668876349925995 2023-01-23 10:19:00.889488: step: 940/1545, loss: 0.08935616165399551 2023-01-23 10:19:01.770798: step: 942/1545, loss: 0.05786930024623871 2023-01-23 10:19:02.631390: step: 944/1545, loss: 0.07418571412563324 2023-01-23 10:19:03.505677: step: 946/1545, loss: 0.18373416364192963 2023-01-23 10:19:04.374176: step: 948/1545, loss: 0.523963212966919 2023-01-23 10:19:05.225476: step: 950/1545, loss: 0.5464245676994324 2023-01-23 10:19:06.114430: step: 952/1545, loss: 0.03507412225008011 2023-01-23 10:19:06.987539: step: 954/1545, loss: 0.5732685327529907 2023-01-23 10:19:07.877190: step: 956/1545, loss: 0.02254493348300457 2023-01-23 10:19:08.726884: step: 958/1545, loss: 0.10479357838630676 2023-01-23 10:19:09.558397: step: 960/1545, loss: 0.10375514626502991 2023-01-23 10:19:10.493155: step: 962/1545, loss: 0.005164246540516615 2023-01-23 10:19:11.358228: step: 964/1545, loss: 0.1339787095785141 2023-01-23 10:19:12.256977: step: 966/1545, loss: 0.1372518688440323 2023-01-23 10:19:13.137667: step: 968/1545, loss: 0.03880685940384865 2023-01-23 10:19:14.003106: step: 970/1545, loss: 0.061853643506765366 2023-01-23 10:19:14.919941: step: 972/1545, loss: 0.1099848523736 2023-01-23 10:19:15.873125: step: 974/1545, loss: 0.04278534650802612 2023-01-23 10:19:16.742095: step: 976/1545, loss: 0.01077307015657425 2023-01-23 10:19:17.584675: step: 978/1545, loss: 0.1366042196750641 2023-01-23 10:19:18.532954: step: 980/1545, loss: 0.10592838376760483 2023-01-23 10:19:19.440655: step: 982/1545, loss: 0.043569184839725494 2023-01-23 10:19:20.299303: step: 984/1545, loss: 0.17796693742275238 2023-01-23 10:19:21.213264: step: 986/1545, loss: 0.04523087665438652 2023-01-23 10:19:22.069503: step: 988/1545, loss: 0.31567731499671936 2023-01-23 10:19:23.021030: step: 990/1545, loss: 0.14546430110931396 2023-01-23 10:19:23.906988: step: 992/1545, loss: 0.6545915603637695 2023-01-23 10:19:24.802854: step: 994/1545, loss: 0.02263597398996353 2023-01-23 10:19:25.693356: step: 996/1545, loss: 0.08773521333932877 2023-01-23 10:19:26.598090: step: 998/1545, loss: 0.19499507546424866 2023-01-23 10:19:27.490505: step: 1000/1545, loss: 0.18474352359771729 2023-01-23 10:19:28.337013: step: 1002/1545, loss: 0.34029117226600647 2023-01-23 10:19:29.227112: step: 1004/1545, loss: 0.08377737551927567 2023-01-23 10:19:30.127995: step: 1006/1545, loss: 0.11866053193807602 2023-01-23 10:19:31.016857: step: 1008/1545, loss: 0.2454073578119278 2023-01-23 10:19:31.915740: step: 1010/1545, loss: 0.07988305389881134 2023-01-23 10:19:32.780699: step: 1012/1545, loss: 0.14328277111053467 2023-01-23 10:19:33.751286: step: 1014/1545, loss: 0.3443351089954376 2023-01-23 10:19:34.617782: step: 1016/1545, loss: 0.040100306272506714 2023-01-23 10:19:35.493493: step: 1018/1545, loss: 0.41754698753356934 2023-01-23 10:19:36.376849: step: 1020/1545, loss: 0.0740717276930809 2023-01-23 10:19:37.260191: step: 1022/1545, loss: 0.059311963617801666 2023-01-23 10:19:38.131961: step: 1024/1545, loss: 0.15748460590839386 2023-01-23 10:19:39.102462: step: 1026/1545, loss: 0.3148912191390991 2023-01-23 10:19:40.009227: step: 1028/1545, loss: 0.13302502036094666 2023-01-23 10:19:40.932716: step: 1030/1545, loss: 0.017141684889793396 2023-01-23 10:19:41.801708: step: 1032/1545, loss: 2.6067001819610596 2023-01-23 10:19:42.668984: step: 1034/1545, loss: 0.4714709222316742 2023-01-23 10:19:43.604166: step: 1036/1545, loss: 0.2868139445781708 2023-01-23 10:19:44.535539: step: 1038/1545, loss: 0.07119959592819214 2023-01-23 10:19:45.427648: step: 1040/1545, loss: 0.5275798439979553 2023-01-23 10:19:46.319474: step: 1042/1545, loss: 0.19547393918037415 2023-01-23 10:19:47.195470: step: 1044/1545, loss: 0.024601496756076813 2023-01-23 10:19:48.177541: step: 1046/1545, loss: 0.19581039249897003 2023-01-23 10:19:49.070970: step: 1048/1545, loss: 0.05567983537912369 2023-01-23 10:19:50.037160: step: 1050/1545, loss: 0.3322344124317169 2023-01-23 10:19:50.902464: step: 1052/1545, loss: 0.09558024257421494 2023-01-23 10:19:51.838226: step: 1054/1545, loss: 0.059872888028621674 2023-01-23 10:19:52.703164: step: 1056/1545, loss: 0.44822606444358826 2023-01-23 10:19:53.560829: step: 1058/1545, loss: 0.14847351610660553 2023-01-23 10:19:54.452548: step: 1060/1545, loss: 0.14051879942417145 2023-01-23 10:19:55.344076: step: 1062/1545, loss: 0.16735774278640747 2023-01-23 10:19:56.344259: step: 1064/1545, loss: 0.06410670280456543 2023-01-23 10:19:57.229122: step: 1066/1545, loss: 0.3800036311149597 2023-01-23 10:19:58.153754: step: 1068/1545, loss: 0.0898996889591217 2023-01-23 10:19:59.056754: step: 1070/1545, loss: 0.2336605340242386 2023-01-23 10:19:59.961867: step: 1072/1545, loss: 0.1700274497270584 2023-01-23 10:20:00.834733: step: 1074/1545, loss: 0.17449480295181274 2023-01-23 10:20:01.736680: step: 1076/1545, loss: 0.12207741290330887 2023-01-23 10:20:02.604674: step: 1078/1545, loss: 0.07889048010110855 2023-01-23 10:20:03.523209: step: 1080/1545, loss: 0.12109242379665375 2023-01-23 10:20:04.478323: step: 1082/1545, loss: 0.052190475165843964 2023-01-23 10:20:05.382871: step: 1084/1545, loss: 0.08586884289979935 2023-01-23 10:20:06.250353: step: 1086/1545, loss: 1.7189936637878418 2023-01-23 10:20:07.129978: step: 1088/1545, loss: 0.13277113437652588 2023-01-23 10:20:08.036542: step: 1090/1545, loss: 0.3281916379928589 2023-01-23 10:20:08.890580: step: 1092/1545, loss: 0.35854488611221313 2023-01-23 10:20:09.813651: step: 1094/1545, loss: 0.24286183714866638 2023-01-23 10:20:10.758713: step: 1096/1545, loss: 0.44894012808799744 2023-01-23 10:20:11.674657: step: 1098/1545, loss: 0.1425808072090149 2023-01-23 10:20:12.597663: step: 1100/1545, loss: 0.2316390424966812 2023-01-23 10:20:13.496676: step: 1102/1545, loss: 0.12114723026752472 2023-01-23 10:20:14.449415: step: 1104/1545, loss: 0.20601855218410492 2023-01-23 10:20:15.415785: step: 1106/1545, loss: 0.1833256632089615 2023-01-23 10:20:16.354030: step: 1108/1545, loss: 0.34924787282943726 2023-01-23 10:20:17.273996: step: 1110/1545, loss: 0.13770678639411926 2023-01-23 10:20:18.140835: step: 1112/1545, loss: 0.05212082713842392 2023-01-23 10:20:19.029881: step: 1114/1545, loss: 0.023243146017193794 2023-01-23 10:20:19.998156: step: 1116/1545, loss: 0.3447129726409912 2023-01-23 10:20:20.963271: step: 1118/1545, loss: 0.2665499448776245 2023-01-23 10:20:21.857824: step: 1120/1545, loss: 0.1912338137626648 2023-01-23 10:20:22.726089: step: 1122/1545, loss: 0.07325243949890137 2023-01-23 10:20:23.659777: step: 1124/1545, loss: 0.0880013257265091 2023-01-23 10:20:24.529293: step: 1126/1545, loss: 0.12737293541431427 2023-01-23 10:20:25.440432: step: 1128/1545, loss: 0.0728408470749855 2023-01-23 10:20:26.306940: step: 1130/1545, loss: 0.41515031456947327 2023-01-23 10:20:27.240839: step: 1132/1545, loss: 0.045308977365493774 2023-01-23 10:20:28.153609: step: 1134/1545, loss: 0.05947122722864151 2023-01-23 10:20:29.012185: step: 1136/1545, loss: 0.09657763689756393 2023-01-23 10:20:29.885607: step: 1138/1545, loss: 0.23008613288402557 2023-01-23 10:20:30.750682: step: 1140/1545, loss: 0.12173470854759216 2023-01-23 10:20:31.644309: step: 1142/1545, loss: 0.1697675883769989 2023-01-23 10:20:32.516346: step: 1144/1545, loss: 0.04978427290916443 2023-01-23 10:20:33.380136: step: 1146/1545, loss: 0.3820434510707855 2023-01-23 10:20:34.332271: step: 1148/1545, loss: 0.2036513090133667 2023-01-23 10:20:35.236866: step: 1150/1545, loss: 0.08761774003505707 2023-01-23 10:20:36.097337: step: 1152/1545, loss: 0.06353381276130676 2023-01-23 10:20:36.997962: step: 1154/1545, loss: 0.046861618757247925 2023-01-23 10:20:37.903700: step: 1156/1545, loss: 0.025035005062818527 2023-01-23 10:20:38.797382: step: 1158/1545, loss: 0.1288110464811325 2023-01-23 10:20:39.659646: step: 1160/1545, loss: 0.06709317862987518 2023-01-23 10:20:40.537395: step: 1162/1545, loss: 0.14732491970062256 2023-01-23 10:20:41.434211: step: 1164/1545, loss: 0.18506231904029846 2023-01-23 10:20:42.290883: step: 1166/1545, loss: 0.20081180334091187 2023-01-23 10:20:43.186433: step: 1168/1545, loss: 0.2714856266975403 2023-01-23 10:20:44.040187: step: 1170/1545, loss: 0.06476305425167084 2023-01-23 10:20:44.916014: step: 1172/1545, loss: 0.10160429775714874 2023-01-23 10:20:45.764132: step: 1174/1545, loss: 0.1638529747724533 2023-01-23 10:20:46.656075: step: 1176/1545, loss: 0.12146418541669846 2023-01-23 10:20:47.534209: step: 1178/1545, loss: 0.08075126260519028 2023-01-23 10:20:48.478332: step: 1180/1545, loss: 0.0925830826163292 2023-01-23 10:20:49.366658: step: 1182/1545, loss: 0.021699490025639534 2023-01-23 10:20:50.257373: step: 1184/1545, loss: 0.11556185036897659 2023-01-23 10:20:51.171472: step: 1186/1545, loss: 0.17717888951301575 2023-01-23 10:20:52.166730: step: 1188/1545, loss: 0.6368057131767273 2023-01-23 10:20:53.082923: step: 1190/1545, loss: 0.4599306881427765 2023-01-23 10:20:53.979720: step: 1192/1545, loss: 0.6401190757751465 2023-01-23 10:20:54.839998: step: 1194/1545, loss: 0.70536208152771 2023-01-23 10:20:55.737902: step: 1196/1545, loss: 0.9512845873832703 2023-01-23 10:20:56.619457: step: 1198/1545, loss: 0.32608217000961304 2023-01-23 10:20:57.495965: step: 1200/1545, loss: 0.05573105812072754 2023-01-23 10:20:58.428027: step: 1202/1545, loss: 0.09531103074550629 2023-01-23 10:20:59.314034: step: 1204/1545, loss: 0.03707973659038544 2023-01-23 10:21:00.194562: step: 1206/1545, loss: 0.09096013754606247 2023-01-23 10:21:01.096147: step: 1208/1545, loss: 1.0979628562927246 2023-01-23 10:21:01.973997: step: 1210/1545, loss: 0.030872594565153122 2023-01-23 10:21:02.854351: step: 1212/1545, loss: 0.06864959001541138 2023-01-23 10:21:03.823213: step: 1214/1545, loss: 0.02203390747308731 2023-01-23 10:21:04.683169: step: 1216/1545, loss: 0.16114704310894012 2023-01-23 10:21:05.590777: step: 1218/1545, loss: 0.06058112904429436 2023-01-23 10:21:06.548855: step: 1220/1545, loss: 0.05186332389712334 2023-01-23 10:21:07.438338: step: 1222/1545, loss: 0.030190683901309967 2023-01-23 10:21:08.344680: step: 1224/1545, loss: 0.19217823445796967 2023-01-23 10:21:09.256214: step: 1226/1545, loss: 0.30535703897476196 2023-01-23 10:21:10.151298: step: 1228/1545, loss: 0.11742342263460159 2023-01-23 10:21:11.003514: step: 1230/1545, loss: 0.08685634285211563 2023-01-23 10:21:11.872051: step: 1232/1545, loss: 0.182167649269104 2023-01-23 10:21:12.734725: step: 1234/1545, loss: 0.2206500768661499 2023-01-23 10:21:13.658841: step: 1236/1545, loss: 0.031423307955265045 2023-01-23 10:21:14.547854: step: 1238/1545, loss: 0.05427732318639755 2023-01-23 10:21:15.436086: step: 1240/1545, loss: 0.8188803791999817 2023-01-23 10:21:16.309451: step: 1242/1545, loss: 0.06492701172828674 2023-01-23 10:21:17.176480: step: 1244/1545, loss: 0.28999781608581543 2023-01-23 10:21:18.105589: step: 1246/1545, loss: 0.07832857966423035 2023-01-23 10:21:18.980083: step: 1248/1545, loss: 0.054705020040273666 2023-01-23 10:21:19.856847: step: 1250/1545, loss: 0.07263551652431488 2023-01-23 10:21:20.739516: step: 1252/1545, loss: 0.100204236805439 2023-01-23 10:21:21.638993: step: 1254/1545, loss: 0.25951746106147766 2023-01-23 10:21:22.550130: step: 1256/1545, loss: 0.039900168776512146 2023-01-23 10:21:23.404764: step: 1258/1545, loss: 0.1322605311870575 2023-01-23 10:21:24.332746: step: 1260/1545, loss: 0.27607807517051697 2023-01-23 10:21:25.233822: step: 1262/1545, loss: 0.21772445738315582 2023-01-23 10:21:26.156279: step: 1264/1545, loss: 0.004835532512515783 2023-01-23 10:21:27.045657: step: 1266/1545, loss: 0.13920441269874573 2023-01-23 10:21:27.912057: step: 1268/1545, loss: 0.19483503699302673 2023-01-23 10:21:28.765987: step: 1270/1545, loss: 0.10213758051395416 2023-01-23 10:21:29.635457: step: 1272/1545, loss: 0.28042861819267273 2023-01-23 10:21:30.508379: step: 1274/1545, loss: 0.1037595272064209 2023-01-23 10:21:31.409396: step: 1276/1545, loss: 2.702944278717041 2023-01-23 10:21:32.333151: step: 1278/1545, loss: 1.5542993545532227 2023-01-23 10:21:33.253619: step: 1280/1545, loss: 0.01365874707698822 2023-01-23 10:21:34.135696: step: 1282/1545, loss: 0.2457064837217331 2023-01-23 10:21:35.050192: step: 1284/1545, loss: 0.42613810300827026 2023-01-23 10:21:35.974990: step: 1286/1545, loss: 0.17525580525398254 2023-01-23 10:21:36.819483: step: 1288/1545, loss: 0.04536457359790802 2023-01-23 10:21:37.666084: step: 1290/1545, loss: 0.3540354371070862 2023-01-23 10:21:38.538286: step: 1292/1545, loss: 0.08590198308229446 2023-01-23 10:21:39.428908: step: 1294/1545, loss: 0.03092677891254425 2023-01-23 10:21:40.321923: step: 1296/1545, loss: 0.30580854415893555 2023-01-23 10:21:41.345836: step: 1298/1545, loss: 0.2630528509616852 2023-01-23 10:21:42.234512: step: 1300/1545, loss: 0.475960910320282 2023-01-23 10:21:43.106754: step: 1302/1545, loss: 0.05815981328487396 2023-01-23 10:21:43.968378: step: 1304/1545, loss: 0.04756145551800728 2023-01-23 10:21:44.820902: step: 1306/1545, loss: 0.20405858755111694 2023-01-23 10:21:45.727820: step: 1308/1545, loss: 0.0140079902485013 2023-01-23 10:21:46.590848: step: 1310/1545, loss: 0.601554274559021 2023-01-23 10:21:47.466954: step: 1312/1545, loss: 0.06368033587932587 2023-01-23 10:21:48.333627: step: 1314/1545, loss: 0.06116378307342529 2023-01-23 10:21:49.249160: step: 1316/1545, loss: 0.029811270534992218 2023-01-23 10:21:50.179390: step: 1318/1545, loss: 0.1211933046579361 2023-01-23 10:21:51.009792: step: 1320/1545, loss: 0.18291814625263214 2023-01-23 10:21:51.900479: step: 1322/1545, loss: 0.08258885145187378 2023-01-23 10:21:52.770817: step: 1324/1545, loss: 0.02735167182981968 2023-01-23 10:21:53.631298: step: 1326/1545, loss: 0.19270028173923492 2023-01-23 10:21:54.527271: step: 1328/1545, loss: 0.009592265821993351 2023-01-23 10:21:55.412829: step: 1330/1545, loss: 0.30095553398132324 2023-01-23 10:21:56.299376: step: 1332/1545, loss: 0.6700937151908875 2023-01-23 10:21:57.185247: step: 1334/1545, loss: 0.267877459526062 2023-01-23 10:21:58.071492: step: 1336/1545, loss: 4.395442485809326 2023-01-23 10:21:58.973230: step: 1338/1545, loss: 0.08806236833333969 2023-01-23 10:21:59.867009: step: 1340/1545, loss: 0.10911451280117035 2023-01-23 10:22:00.743192: step: 1342/1545, loss: 0.30769577622413635 2023-01-23 10:22:01.622323: step: 1344/1545, loss: 0.42810848355293274 2023-01-23 10:22:02.523603: step: 1346/1545, loss: 0.09931886196136475 2023-01-23 10:22:03.386925: step: 1348/1545, loss: 0.03717546537518501 2023-01-23 10:22:04.275460: step: 1350/1545, loss: 0.4361334443092346 2023-01-23 10:22:05.146053: step: 1352/1545, loss: 0.0532694049179554 2023-01-23 10:22:06.036173: step: 1354/1545, loss: 0.04637719690799713 2023-01-23 10:22:06.919122: step: 1356/1545, loss: 0.13431821763515472 2023-01-23 10:22:07.825522: step: 1358/1545, loss: 0.44261595606803894 2023-01-23 10:22:08.713367: step: 1360/1545, loss: 0.32564064860343933 2023-01-23 10:22:09.554455: step: 1362/1545, loss: 0.03181454539299011 2023-01-23 10:22:10.460092: step: 1364/1545, loss: 0.30334603786468506 2023-01-23 10:22:11.334769: step: 1366/1545, loss: 0.18527032434940338 2023-01-23 10:22:12.209408: step: 1368/1545, loss: 0.3322140872478485 2023-01-23 10:22:13.134839: step: 1370/1545, loss: 0.02043464407324791 2023-01-23 10:22:13.994043: step: 1372/1545, loss: 0.18122661113739014 2023-01-23 10:22:14.907664: step: 1374/1545, loss: 0.17409983277320862 2023-01-23 10:22:15.782733: step: 1376/1545, loss: 0.15304720401763916 2023-01-23 10:22:16.738902: step: 1378/1545, loss: 0.13978861272335052 2023-01-23 10:22:17.615412: step: 1380/1545, loss: 0.15107329189777374 2023-01-23 10:22:18.496684: step: 1382/1545, loss: 0.14682312309741974 2023-01-23 10:22:19.416107: step: 1384/1545, loss: 0.11597197502851486 2023-01-23 10:22:20.288664: step: 1386/1545, loss: 0.2523036003112793 2023-01-23 10:22:21.149625: step: 1388/1545, loss: 0.7131558656692505 2023-01-23 10:22:22.006528: step: 1390/1545, loss: 0.17121626436710358 2023-01-23 10:22:22.937482: step: 1392/1545, loss: 0.2787787616252899 2023-01-23 10:22:23.815595: step: 1394/1545, loss: 0.5178627967834473 2023-01-23 10:22:24.732579: step: 1396/1545, loss: 0.2775634825229645 2023-01-23 10:22:25.621070: step: 1398/1545, loss: 0.22775018215179443 2023-01-23 10:22:26.538498: step: 1400/1545, loss: 0.5381023287773132 2023-01-23 10:22:27.460023: step: 1402/1545, loss: 0.16882291436195374 2023-01-23 10:22:28.332626: step: 1404/1545, loss: 0.1384950876235962 2023-01-23 10:22:29.217358: step: 1406/1545, loss: 0.4823545217514038 2023-01-23 10:22:30.098902: step: 1408/1545, loss: 0.043625637888908386 2023-01-23 10:22:31.031738: step: 1410/1545, loss: 0.14319197833538055 2023-01-23 10:22:31.887590: step: 1412/1545, loss: 0.04487334564328194 2023-01-23 10:22:32.735764: step: 1414/1545, loss: 0.09861267358064651 2023-01-23 10:22:33.657515: step: 1416/1545, loss: 0.15025584399700165 2023-01-23 10:22:34.530875: step: 1418/1545, loss: 0.10952974855899811 2023-01-23 10:22:35.443702: step: 1420/1545, loss: 0.04662590101361275 2023-01-23 10:22:36.339594: step: 1422/1545, loss: 0.163483664393425 2023-01-23 10:22:37.216022: step: 1424/1545, loss: 0.14463485777378082 2023-01-23 10:22:38.077867: step: 1426/1545, loss: 0.15989889204502106 2023-01-23 10:22:38.977479: step: 1428/1545, loss: 0.6026065945625305 2023-01-23 10:22:39.890017: step: 1430/1545, loss: 0.28889188170433044 2023-01-23 10:22:40.805449: step: 1432/1545, loss: 2.626981258392334 2023-01-23 10:22:41.714858: step: 1434/1545, loss: 0.30098462104797363 2023-01-23 10:22:42.602506: step: 1436/1545, loss: 0.07736773788928986 2023-01-23 10:22:43.539849: step: 1438/1545, loss: 0.008270163089036942 2023-01-23 10:22:44.541082: step: 1440/1545, loss: 0.1643056869506836 2023-01-23 10:22:45.433864: step: 1442/1545, loss: 0.09360016137361526 2023-01-23 10:22:46.304949: step: 1444/1545, loss: 0.05875087529420853 2023-01-23 10:22:47.212767: step: 1446/1545, loss: 0.2686541974544525 2023-01-23 10:22:48.136341: step: 1448/1545, loss: 0.13253465294837952 2023-01-23 10:22:49.027481: step: 1450/1545, loss: 0.29764002561569214 2023-01-23 10:22:49.950977: step: 1452/1545, loss: 0.12366224825382233 2023-01-23 10:22:50.827431: step: 1454/1545, loss: 0.19769400358200073 2023-01-23 10:22:51.763321: step: 1456/1545, loss: 0.10012727975845337 2023-01-23 10:22:52.626085: step: 1458/1545, loss: 0.20894865691661835 2023-01-23 10:22:53.548146: step: 1460/1545, loss: 0.18903319537639618 2023-01-23 10:22:54.409692: step: 1462/1545, loss: 0.09393482655286789 2023-01-23 10:22:55.340463: step: 1464/1545, loss: 0.11184251308441162 2023-01-23 10:22:56.234637: step: 1466/1545, loss: 0.10657737404108047 2023-01-23 10:22:57.135718: step: 1468/1545, loss: 0.13854147493839264 2023-01-23 10:22:58.021313: step: 1470/1545, loss: 0.20811539888381958 2023-01-23 10:22:58.910936: step: 1472/1545, loss: 0.4556336998939514 2023-01-23 10:22:59.763469: step: 1474/1545, loss: 0.4468444585800171 2023-01-23 10:23:00.689828: step: 1476/1545, loss: 0.5215574502944946 2023-01-23 10:23:01.538463: step: 1478/1545, loss: 0.1461370885372162 2023-01-23 10:23:02.435025: step: 1480/1545, loss: 0.13774238526821136 2023-01-23 10:23:03.297313: step: 1482/1545, loss: 0.08928771317005157 2023-01-23 10:23:04.192250: step: 1484/1545, loss: 0.22820496559143066 2023-01-23 10:23:05.018142: step: 1486/1545, loss: 0.35529541969299316 2023-01-23 10:23:05.846059: step: 1488/1545, loss: 0.057554230093955994 2023-01-23 10:23:06.758989: step: 1490/1545, loss: 0.022949786856770515 2023-01-23 10:23:07.643883: step: 1492/1545, loss: 0.465893030166626 2023-01-23 10:23:08.485309: step: 1494/1545, loss: 0.2728728652000427 2023-01-23 10:23:09.366467: step: 1496/1545, loss: 0.07054316997528076 2023-01-23 10:23:10.237372: step: 1498/1545, loss: 0.899635374546051 2023-01-23 10:23:11.142401: step: 1500/1545, loss: 0.1840648353099823 2023-01-23 10:23:12.043457: step: 1502/1545, loss: 0.28034329414367676 2023-01-23 10:23:12.923538: step: 1504/1545, loss: 0.7520467638969421 2023-01-23 10:23:13.783959: step: 1506/1545, loss: 0.10604976117610931 2023-01-23 10:23:14.656212: step: 1508/1545, loss: 0.7794259786605835 2023-01-23 10:23:15.539623: step: 1510/1545, loss: 0.11400637775659561 2023-01-23 10:23:16.444066: step: 1512/1545, loss: 0.5120715498924255 2023-01-23 10:23:17.298773: step: 1514/1545, loss: 0.12792010605335236 2023-01-23 10:23:18.156236: step: 1516/1545, loss: 0.21065117418766022 2023-01-23 10:23:19.031479: step: 1518/1545, loss: 0.1970359832048416 2023-01-23 10:23:19.902516: step: 1520/1545, loss: 0.17489176988601685 2023-01-23 10:23:20.819363: step: 1522/1545, loss: 0.32711467146873474 2023-01-23 10:23:21.710731: step: 1524/1545, loss: 0.23552855849266052 2023-01-23 10:23:22.591894: step: 1526/1545, loss: 0.004853324964642525 2023-01-23 10:23:23.503890: step: 1528/1545, loss: 0.23608005046844482 2023-01-23 10:23:24.371014: step: 1530/1545, loss: 0.08813082426786423 2023-01-23 10:23:25.231532: step: 1532/1545, loss: 0.17319521307945251 2023-01-23 10:23:26.164625: step: 1534/1545, loss: 0.026393666863441467 2023-01-23 10:23:27.067479: step: 1536/1545, loss: 0.5137208104133606 2023-01-23 10:23:28.001908: step: 1538/1545, loss: 0.030834531411528587 2023-01-23 10:23:28.924624: step: 1540/1545, loss: 0.03745318949222565 2023-01-23 10:23:29.786788: step: 1542/1545, loss: 0.0921873226761818 2023-01-23 10:23:30.716869: step: 1544/1545, loss: 0.45064982771873474 2023-01-23 10:23:31.587240: step: 1546/1545, loss: 0.1450381875038147 2023-01-23 10:23:32.460241: step: 1548/1545, loss: 0.43091556429862976 2023-01-23 10:23:33.384155: step: 1550/1545, loss: 0.18955795466899872 2023-01-23 10:23:34.228590: step: 1552/1545, loss: 0.08214981853961945 2023-01-23 10:23:35.091915: step: 1554/1545, loss: 0.14934688806533813 2023-01-23 10:23:35.988319: step: 1556/1545, loss: 0.040049854665994644 2023-01-23 10:23:36.837468: step: 1558/1545, loss: 0.09764816612005234 2023-01-23 10:23:37.718767: step: 1560/1545, loss: 0.03632544353604317 2023-01-23 10:23:38.602194: step: 1562/1545, loss: 0.2248467653989792 2023-01-23 10:23:39.480413: step: 1564/1545, loss: 0.05138825252652168 2023-01-23 10:23:40.373871: step: 1566/1545, loss: 0.17238739132881165 2023-01-23 10:23:41.250766: step: 1568/1545, loss: 0.05338800325989723 2023-01-23 10:23:42.140672: step: 1570/1545, loss: 0.1611386090517044 2023-01-23 10:23:43.065004: step: 1572/1545, loss: 0.12548397481441498 2023-01-23 10:23:43.938672: step: 1574/1545, loss: 0.0811956375837326 2023-01-23 10:23:44.812146: step: 1576/1545, loss: 0.3126809000968933 2023-01-23 10:23:45.640726: step: 1578/1545, loss: 0.07719734311103821 2023-01-23 10:23:46.502496: step: 1580/1545, loss: 0.20973731577396393 2023-01-23 10:23:47.491368: step: 1582/1545, loss: 0.22219300270080566 2023-01-23 10:23:48.390537: step: 1584/1545, loss: 0.16498209536075592 2023-01-23 10:23:49.276160: step: 1586/1545, loss: 0.12103438377380371 2023-01-23 10:23:50.153580: step: 1588/1545, loss: 0.019078155979514122 2023-01-23 10:23:51.077567: step: 1590/1545, loss: 0.47804465889930725 2023-01-23 10:23:52.012321: step: 1592/1545, loss: 0.3503510057926178 2023-01-23 10:23:52.897114: step: 1594/1545, loss: 0.269288033246994 2023-01-23 10:23:53.771532: step: 1596/1545, loss: 0.4532582461833954 2023-01-23 10:23:54.667076: step: 1598/1545, loss: 0.09273360669612885 2023-01-23 10:23:55.510607: step: 1600/1545, loss: 0.118672676384449 2023-01-23 10:23:56.377938: step: 1602/1545, loss: 0.6741965413093567 2023-01-23 10:23:57.236240: step: 1604/1545, loss: 0.04155907779932022 2023-01-23 10:23:58.114863: step: 1606/1545, loss: 0.02188475988805294 2023-01-23 10:23:59.046597: step: 1608/1545, loss: 0.37831613421440125 2023-01-23 10:23:59.923092: step: 1610/1545, loss: 1.7642767429351807 2023-01-23 10:24:00.795959: step: 1612/1545, loss: 0.30820727348327637 2023-01-23 10:24:01.689042: step: 1614/1545, loss: 0.2742846608161926 2023-01-23 10:24:02.588953: step: 1616/1545, loss: 0.05809812992811203 2023-01-23 10:24:03.430395: step: 1618/1545, loss: 0.06307113170623779 2023-01-23 10:24:04.335360: step: 1620/1545, loss: 0.2710683345794678 2023-01-23 10:24:05.225695: step: 1622/1545, loss: 0.12734496593475342 2023-01-23 10:24:06.104470: step: 1624/1545, loss: 0.2585013806819916 2023-01-23 10:24:06.978454: step: 1626/1545, loss: 0.1947760283946991 2023-01-23 10:24:07.841062: step: 1628/1545, loss: 0.09445422887802124 2023-01-23 10:24:08.742637: step: 1630/1545, loss: 0.09683550894260406 2023-01-23 10:24:09.652422: step: 1632/1545, loss: 0.10543128848075867 2023-01-23 10:24:10.577944: step: 1634/1545, loss: 0.0800812765955925 2023-01-23 10:24:11.465317: step: 1636/1545, loss: 0.040008094161748886 2023-01-23 10:24:12.343738: step: 1638/1545, loss: 0.0795944407582283 2023-01-23 10:24:13.201333: step: 1640/1545, loss: 0.16294856369495392 2023-01-23 10:24:14.066603: step: 1642/1545, loss: 0.05345412343740463 2023-01-23 10:24:14.951147: step: 1644/1545, loss: 0.06271637231111526 2023-01-23 10:24:15.830073: step: 1646/1545, loss: 0.1525399088859558 2023-01-23 10:24:16.750339: step: 1648/1545, loss: 0.08357726782560349 2023-01-23 10:24:17.682854: step: 1650/1545, loss: 0.06287720054388046 2023-01-23 10:24:18.609359: step: 1652/1545, loss: 0.5664100050926208 2023-01-23 10:24:19.462978: step: 1654/1545, loss: 0.12521323561668396 2023-01-23 10:24:20.496036: step: 1656/1545, loss: 0.24026480317115784 2023-01-23 10:24:21.409781: step: 1658/1545, loss: 0.062967449426651 2023-01-23 10:24:22.299618: step: 1660/1545, loss: 0.08548028022050858 2023-01-23 10:24:23.157247: step: 1662/1545, loss: 0.014919957146048546 2023-01-23 10:24:24.066006: step: 1664/1545, loss: 0.21871966123580933 2023-01-23 10:24:24.932926: step: 1666/1545, loss: 0.44865211844444275 2023-01-23 10:24:25.806768: step: 1668/1545, loss: 0.288697212934494 2023-01-23 10:24:26.691154: step: 1670/1545, loss: 0.03305763378739357 2023-01-23 10:24:27.564790: step: 1672/1545, loss: 0.02442505955696106 2023-01-23 10:24:28.467226: step: 1674/1545, loss: 0.019853871315717697 2023-01-23 10:24:29.460975: step: 1676/1545, loss: 2.5352530479431152 2023-01-23 10:24:30.341364: step: 1678/1545, loss: 0.045137349516153336 2023-01-23 10:24:31.245138: step: 1680/1545, loss: 0.08548775315284729 2023-01-23 10:24:32.109893: step: 1682/1545, loss: 0.6004215478897095 2023-01-23 10:24:33.003450: step: 1684/1545, loss: 0.04214603453874588 2023-01-23 10:24:33.862973: step: 1686/1545, loss: 0.273251473903656 2023-01-23 10:24:34.776937: step: 1688/1545, loss: 0.45540890097618103 2023-01-23 10:24:35.699338: step: 1690/1545, loss: 0.9319784045219421 2023-01-23 10:24:36.530270: step: 1692/1545, loss: 0.1576906442642212 2023-01-23 10:24:37.401195: step: 1694/1545, loss: 0.2504744827747345 2023-01-23 10:24:38.266781: step: 1696/1545, loss: 0.18299834430217743 2023-01-23 10:24:39.163190: step: 1698/1545, loss: 0.15104469656944275 2023-01-23 10:24:40.087336: step: 1700/1545, loss: 0.33970391750335693 2023-01-23 10:24:40.944877: step: 1702/1545, loss: 0.9110267162322998 2023-01-23 10:24:41.817085: step: 1704/1545, loss: 0.1865571290254593 2023-01-23 10:24:42.673698: step: 1706/1545, loss: 0.035850975662469864 2023-01-23 10:24:43.572122: step: 1708/1545, loss: 0.03404875099658966 2023-01-23 10:24:44.469132: step: 1710/1545, loss: 0.11664019525051117 2023-01-23 10:24:45.313064: step: 1712/1545, loss: 0.2341068983078003 2023-01-23 10:24:46.207109: step: 1714/1545, loss: 0.010905524715781212 2023-01-23 10:24:47.115206: step: 1716/1545, loss: 0.05085424333810806 2023-01-23 10:24:48.010932: step: 1718/1545, loss: 0.10267537087202072 2023-01-23 10:24:48.964301: step: 1720/1545, loss: 1.5535138845443726 2023-01-23 10:24:49.828576: step: 1722/1545, loss: 0.22327649593353271 2023-01-23 10:24:50.744869: step: 1724/1545, loss: 0.0284391101449728 2023-01-23 10:24:51.642023: step: 1726/1545, loss: 0.34051206707954407 2023-01-23 10:24:52.638118: step: 1728/1545, loss: 0.16789919137954712 2023-01-23 10:24:53.494462: step: 1730/1545, loss: 0.6672630906105042 2023-01-23 10:24:54.368487: step: 1732/1545, loss: 0.22752436995506287 2023-01-23 10:24:55.190495: step: 1734/1545, loss: 0.058734409511089325 2023-01-23 10:24:56.045662: step: 1736/1545, loss: 0.04826437681913376 2023-01-23 10:24:56.927663: step: 1738/1545, loss: 2.306040048599243 2023-01-23 10:24:57.817389: step: 1740/1545, loss: 0.26094481348991394 2023-01-23 10:24:58.717808: step: 1742/1545, loss: 0.4225926399230957 2023-01-23 10:24:59.602486: step: 1744/1545, loss: 0.13551785051822662 2023-01-23 10:25:00.479200: step: 1746/1545, loss: 0.08693133294582367 2023-01-23 10:25:01.366818: step: 1748/1545, loss: 0.42355862259864807 2023-01-23 10:25:02.291119: step: 1750/1545, loss: 0.32746848464012146 2023-01-23 10:25:03.134769: step: 1752/1545, loss: 0.43532758951187134 2023-01-23 10:25:04.014201: step: 1754/1545, loss: 0.16249462962150574 2023-01-23 10:25:04.897395: step: 1756/1545, loss: 0.06641770899295807 2023-01-23 10:25:05.830672: step: 1758/1545, loss: 0.34067919850349426 2023-01-23 10:25:06.696797: step: 1760/1545, loss: 0.05773051828145981 2023-01-23 10:25:07.593081: step: 1762/1545, loss: 0.058558642864227295 2023-01-23 10:25:08.471664: step: 1764/1545, loss: 0.09301603585481644 2023-01-23 10:25:09.328771: step: 1766/1545, loss: 0.06062939763069153 2023-01-23 10:25:10.264714: step: 1768/1545, loss: 0.1505497395992279 2023-01-23 10:25:11.197986: step: 1770/1545, loss: 0.5453197360038757 2023-01-23 10:25:12.143352: step: 1772/1545, loss: 0.32768526673316956 2023-01-23 10:25:13.022615: step: 1774/1545, loss: 0.1747119277715683 2023-01-23 10:25:13.929216: step: 1776/1545, loss: 0.30384397506713867 2023-01-23 10:25:14.835135: step: 1778/1545, loss: 0.0455736443400383 2023-01-23 10:25:15.781527: step: 1780/1545, loss: 0.17154532670974731 2023-01-23 10:25:16.681478: step: 1782/1545, loss: 0.12864388525485992 2023-01-23 10:25:17.557154: step: 1784/1545, loss: 0.0705786794424057 2023-01-23 10:25:18.433687: step: 1786/1545, loss: 0.14489799737930298 2023-01-23 10:25:19.339189: step: 1788/1545, loss: 0.11514443159103394 2023-01-23 10:25:20.214171: step: 1790/1545, loss: 0.0674237534403801 2023-01-23 10:25:21.112245: step: 1792/1545, loss: 0.08031972497701645 2023-01-23 10:25:21.966891: step: 1794/1545, loss: 0.2976181209087372 2023-01-23 10:25:22.876376: step: 1796/1545, loss: 0.05557245761156082 2023-01-23 10:25:23.806843: step: 1798/1545, loss: 0.10147421061992645 2023-01-23 10:25:24.704784: step: 1800/1545, loss: 0.10783866047859192 2023-01-23 10:25:25.602540: step: 1802/1545, loss: 0.3000413477420807 2023-01-23 10:25:26.490491: step: 1804/1545, loss: 0.33908867835998535 2023-01-23 10:25:27.411562: step: 1806/1545, loss: 0.08095486462116241 2023-01-23 10:25:28.309217: step: 1808/1545, loss: 0.1845768392086029 2023-01-23 10:25:29.220587: step: 1810/1545, loss: 0.015677135437726974 2023-01-23 10:25:30.132488: step: 1812/1545, loss: 0.6317877173423767 2023-01-23 10:25:31.021281: step: 1814/1545, loss: 0.1632547527551651 2023-01-23 10:25:31.900979: step: 1816/1545, loss: 0.20788681507110596 2023-01-23 10:25:32.792923: step: 1818/1545, loss: 0.026062335819005966 2023-01-23 10:25:33.684628: step: 1820/1545, loss: 0.11650554835796356 2023-01-23 10:25:34.586299: step: 1822/1545, loss: 0.04967876523733139 2023-01-23 10:25:35.452791: step: 1824/1545, loss: 0.06316525489091873 2023-01-23 10:25:36.315464: step: 1826/1545, loss: 0.2361053079366684 2023-01-23 10:25:37.175621: step: 1828/1545, loss: 0.06119522452354431 2023-01-23 10:25:38.101650: step: 1830/1545, loss: 0.1781792938709259 2023-01-23 10:25:38.991227: step: 1832/1545, loss: 0.0544947013258934 2023-01-23 10:25:39.876207: step: 1834/1545, loss: 0.2854681611061096 2023-01-23 10:25:40.727878: step: 1836/1545, loss: 1.6046754121780396 2023-01-23 10:25:41.606565: step: 1838/1545, loss: 0.2463199943304062 2023-01-23 10:25:42.554824: step: 1840/1545, loss: 0.03788495063781738 2023-01-23 10:25:43.452200: step: 1842/1545, loss: 0.5387389063835144 2023-01-23 10:25:44.322317: step: 1844/1545, loss: 0.38988372683525085 2023-01-23 10:25:45.199275: step: 1846/1545, loss: 0.5280689597129822 2023-01-23 10:25:46.127237: step: 1848/1545, loss: 0.3301081359386444 2023-01-23 10:25:47.038701: step: 1850/1545, loss: 0.11723432689905167 2023-01-23 10:25:47.916436: step: 1852/1545, loss: 0.2433653175830841 2023-01-23 10:25:48.795672: step: 1854/1545, loss: 0.4251123070716858 2023-01-23 10:25:49.730726: step: 1856/1545, loss: 0.048854514956474304 2023-01-23 10:25:50.690000: step: 1858/1545, loss: 0.1364012509584427 2023-01-23 10:25:51.537608: step: 1860/1545, loss: 0.14070501923561096 2023-01-23 10:25:52.418267: step: 1862/1545, loss: 0.0749664306640625 2023-01-23 10:25:53.306925: step: 1864/1545, loss: 0.5062174797058105 2023-01-23 10:25:54.224705: step: 1866/1545, loss: 0.14335530996322632 2023-01-23 10:25:55.136588: step: 1868/1545, loss: 0.08313216269016266 2023-01-23 10:25:56.012210: step: 1870/1545, loss: 0.23668807744979858 2023-01-23 10:25:56.882392: step: 1872/1545, loss: 0.24680140614509583 2023-01-23 10:25:57.822011: step: 1874/1545, loss: 0.059806205332279205 2023-01-23 10:25:58.696000: step: 1876/1545, loss: 0.1658177673816681 2023-01-23 10:25:59.594301: step: 1878/1545, loss: 0.19069501757621765 2023-01-23 10:26:00.473603: step: 1880/1545, loss: 0.05869382619857788 2023-01-23 10:26:01.370039: step: 1882/1545, loss: 0.14051565527915955 2023-01-23 10:26:02.260002: step: 1884/1545, loss: 0.2188083827495575 2023-01-23 10:26:03.145150: step: 1886/1545, loss: 0.09341535717248917 2023-01-23 10:26:04.010090: step: 1888/1545, loss: 0.20655757188796997 2023-01-23 10:26:04.855067: step: 1890/1545, loss: 0.3827051818370819 2023-01-23 10:26:05.731146: step: 1892/1545, loss: 0.09284865856170654 2023-01-23 10:26:06.599236: step: 1894/1545, loss: 0.29654714465141296 2023-01-23 10:26:07.501088: step: 1896/1545, loss: 0.17337556183338165 2023-01-23 10:26:08.380115: step: 1898/1545, loss: 0.009668429382145405 2023-01-23 10:26:09.250401: step: 1900/1545, loss: 0.12737877666950226 2023-01-23 10:26:10.158033: step: 1902/1545, loss: 0.012185693718492985 2023-01-23 10:26:11.089564: step: 1904/1545, loss: 0.11408533900976181 2023-01-23 10:26:11.977755: step: 1906/1545, loss: 0.0497363843023777 2023-01-23 10:26:12.838931: step: 1908/1545, loss: 0.2735179364681244 2023-01-23 10:26:13.712627: step: 1910/1545, loss: 0.3767337501049042 2023-01-23 10:26:14.628008: step: 1912/1545, loss: 0.23503006994724274 2023-01-23 10:26:15.497819: step: 1914/1545, loss: 0.04918767511844635 2023-01-23 10:26:16.438204: step: 1916/1545, loss: 0.594159722328186 2023-01-23 10:26:17.302011: step: 1918/1545, loss: 0.10050569474697113 2023-01-23 10:26:18.185485: step: 1920/1545, loss: 0.03443310037255287 2023-01-23 10:26:19.107957: step: 1922/1545, loss: 0.08844995498657227 2023-01-23 10:26:20.003318: step: 1924/1545, loss: 0.20638342201709747 2023-01-23 10:26:20.907861: step: 1926/1545, loss: 0.22383558750152588 2023-01-23 10:26:21.729138: step: 1928/1545, loss: 0.32743528485298157 2023-01-23 10:26:22.629814: step: 1930/1545, loss: 0.12185811251401901 2023-01-23 10:26:23.534143: step: 1932/1545, loss: 0.08263392001390457 2023-01-23 10:26:24.403957: step: 1934/1545, loss: 0.0970015823841095 2023-01-23 10:26:25.244214: step: 1936/1545, loss: 0.004230804741382599 2023-01-23 10:26:26.103616: step: 1938/1545, loss: 0.15494143962860107 2023-01-23 10:26:27.066313: step: 1940/1545, loss: 0.07937239110469818 2023-01-23 10:26:27.875396: step: 1942/1545, loss: 0.4008931815624237 2023-01-23 10:26:28.763249: step: 1944/1545, loss: 0.05112741142511368 2023-01-23 10:26:29.641109: step: 1946/1545, loss: 0.15583209693431854 2023-01-23 10:26:30.517522: step: 1948/1545, loss: 0.393243670463562 2023-01-23 10:26:31.420083: step: 1950/1545, loss: 0.2720860242843628 2023-01-23 10:26:32.278500: step: 1952/1545, loss: 0.6098942756652832 2023-01-23 10:26:33.167481: step: 1954/1545, loss: 0.018336428329348564 2023-01-23 10:26:34.097272: step: 1956/1545, loss: 0.07104049623012543 2023-01-23 10:26:35.024863: step: 1958/1545, loss: 0.1360255777835846 2023-01-23 10:26:35.976631: step: 1960/1545, loss: 3.2514407634735107 2023-01-23 10:26:36.932826: step: 1962/1545, loss: 0.021722014993429184 2023-01-23 10:26:37.805362: step: 1964/1545, loss: 0.480300635099411 2023-01-23 10:26:38.708808: step: 1966/1545, loss: 0.01981036737561226 2023-01-23 10:26:39.584252: step: 1968/1545, loss: 0.2781981825828552 2023-01-23 10:26:40.504384: step: 1970/1545, loss: 0.06129930168390274 2023-01-23 10:26:41.455306: step: 1972/1545, loss: 1.0154364109039307 2023-01-23 10:26:42.291608: step: 1974/1545, loss: 0.03845203295350075 2023-01-23 10:26:43.139897: step: 1976/1545, loss: 0.07483780384063721 2023-01-23 10:26:43.991570: step: 1978/1545, loss: 0.10618777573108673 2023-01-23 10:26:44.913368: step: 1980/1545, loss: 0.08184368908405304 2023-01-23 10:26:45.773117: step: 1982/1545, loss: 0.11152075231075287 2023-01-23 10:26:46.660418: step: 1984/1545, loss: 0.1684691160917282 2023-01-23 10:26:47.661146: step: 1986/1545, loss: 0.6540692448616028 2023-01-23 10:26:48.509924: step: 1988/1545, loss: 0.0977398157119751 2023-01-23 10:26:49.450705: step: 1990/1545, loss: 0.05269133299589157 2023-01-23 10:26:50.304405: step: 1992/1545, loss: 0.1282581090927124 2023-01-23 10:26:51.279064: step: 1994/1545, loss: 0.35140272974967957 2023-01-23 10:26:52.178452: step: 1996/1545, loss: 0.16897204518318176 2023-01-23 10:26:53.092730: step: 1998/1545, loss: 0.27733084559440613 2023-01-23 10:26:53.993012: step: 2000/1545, loss: 0.12936058640480042 2023-01-23 10:26:54.882548: step: 2002/1545, loss: 0.2906654477119446 2023-01-23 10:26:55.756830: step: 2004/1545, loss: 0.3487892150878906 2023-01-23 10:26:56.604287: step: 2006/1545, loss: 0.07323138415813446 2023-01-23 10:26:57.566910: step: 2008/1545, loss: 0.03801019489765167 2023-01-23 10:26:58.429393: step: 2010/1545, loss: 0.040871791541576385 2023-01-23 10:26:59.358528: step: 2012/1545, loss: 0.040444955229759216 2023-01-23 10:27:00.220299: step: 2014/1545, loss: 0.01921680010855198 2023-01-23 10:27:01.148994: step: 2016/1545, loss: 0.1367163509130478 2023-01-23 10:27:02.034058: step: 2018/1545, loss: 0.2220880538225174 2023-01-23 10:27:02.919699: step: 2020/1545, loss: 0.055826544761657715 2023-01-23 10:27:03.780168: step: 2022/1545, loss: 0.12003655731678009 2023-01-23 10:27:04.625723: step: 2024/1545, loss: 0.08015906065702438 2023-01-23 10:27:05.492113: step: 2026/1545, loss: 0.0606965646147728 2023-01-23 10:27:06.328636: step: 2028/1545, loss: 0.1656867414712906 2023-01-23 10:27:07.211360: step: 2030/1545, loss: 0.15055891871452332 2023-01-23 10:27:08.118110: step: 2032/1545, loss: 0.02442130260169506 2023-01-23 10:27:09.036759: step: 2034/1545, loss: 0.147928386926651 2023-01-23 10:27:09.870474: step: 2036/1545, loss: 0.2436867505311966 2023-01-23 10:27:10.724545: step: 2038/1545, loss: 0.04895005375146866 2023-01-23 10:27:11.602846: step: 2040/1545, loss: 0.025258922949433327 2023-01-23 10:27:12.464061: step: 2042/1545, loss: 0.026485055685043335 2023-01-23 10:27:13.317579: step: 2044/1545, loss: 0.16412176191806793 2023-01-23 10:27:14.274828: step: 2046/1545, loss: 0.2094874382019043 2023-01-23 10:27:15.178290: step: 2048/1545, loss: 0.14162279665470123 2023-01-23 10:27:16.046358: step: 2050/1545, loss: 0.18474936485290527 2023-01-23 10:27:16.990430: step: 2052/1545, loss: 0.03409741818904877 2023-01-23 10:27:17.836333: step: 2054/1545, loss: 0.1702648103237152 2023-01-23 10:27:18.759808: step: 2056/1545, loss: 0.07389029860496521 2023-01-23 10:27:19.668805: step: 2058/1545, loss: 0.08747202157974243 2023-01-23 10:27:20.541119: step: 2060/1545, loss: 0.3427310287952423 2023-01-23 10:27:21.452419: step: 2062/1545, loss: 0.05234888568520546 2023-01-23 10:27:22.350985: step: 2064/1545, loss: 0.1819634586572647 2023-01-23 10:27:23.217809: step: 2066/1545, loss: 0.32829752564430237 2023-01-23 10:27:24.111355: step: 2068/1545, loss: 0.47878605127334595 2023-01-23 10:27:24.994504: step: 2070/1545, loss: 0.31498393416404724 2023-01-23 10:27:25.878295: step: 2072/1545, loss: 0.36184751987457275 2023-01-23 10:27:26.778915: step: 2074/1545, loss: 0.028949609026312828 2023-01-23 10:27:27.665136: step: 2076/1545, loss: 0.13795962929725647 2023-01-23 10:27:28.537131: step: 2078/1545, loss: 1.2929714918136597 2023-01-23 10:27:29.374509: step: 2080/1545, loss: 0.023951096460223198 2023-01-23 10:27:30.237500: step: 2082/1545, loss: 0.35228365659713745 2023-01-23 10:27:31.158120: step: 2084/1545, loss: 0.19067198038101196 2023-01-23 10:27:32.038904: step: 2086/1545, loss: 0.5342564582824707 2023-01-23 10:27:32.895720: step: 2088/1545, loss: 0.14339801669120789 2023-01-23 10:27:33.777026: step: 2090/1545, loss: 0.20017769932746887 2023-01-23 10:27:34.652891: step: 2092/1545, loss: 0.09619048982858658 2023-01-23 10:27:35.525718: step: 2094/1545, loss: 0.06622795760631561 2023-01-23 10:27:36.396293: step: 2096/1545, loss: 0.2546331286430359 2023-01-23 10:27:37.289877: step: 2098/1545, loss: 0.10554137080907822 2023-01-23 10:27:38.194771: step: 2100/1545, loss: 0.12146059423685074 2023-01-23 10:27:39.058351: step: 2102/1545, loss: 0.16747786104679108 2023-01-23 10:27:39.898174: step: 2104/1545, loss: 0.30022746324539185 2023-01-23 10:27:40.734554: step: 2106/1545, loss: 0.24572941660881042 2023-01-23 10:27:41.602053: step: 2108/1545, loss: 0.2782001495361328 2023-01-23 10:27:42.476408: step: 2110/1545, loss: 0.12202446162700653 2023-01-23 10:27:43.361269: step: 2112/1545, loss: 0.23972198367118835 2023-01-23 10:27:44.252934: step: 2114/1545, loss: 0.11362875998020172 2023-01-23 10:27:45.146338: step: 2116/1545, loss: 0.0652194619178772 2023-01-23 10:27:46.035246: step: 2118/1545, loss: 0.0415930412709713 2023-01-23 10:27:46.903719: step: 2120/1545, loss: 0.14021612703800201 2023-01-23 10:27:47.853715: step: 2122/1545, loss: 0.12234184145927429 2023-01-23 10:27:48.753725: step: 2124/1545, loss: 0.8873676061630249 2023-01-23 10:27:49.696503: step: 2126/1545, loss: 0.11263653635978699 2023-01-23 10:27:50.569816: step: 2128/1545, loss: 0.03288806974887848 2023-01-23 10:27:51.506595: step: 2130/1545, loss: 0.21217788755893707 2023-01-23 10:27:52.392702: step: 2132/1545, loss: 0.09354539960622787 2023-01-23 10:27:53.264957: step: 2134/1545, loss: 0.3130837678909302 2023-01-23 10:27:54.159303: step: 2136/1545, loss: 0.1859295815229416 2023-01-23 10:27:55.056223: step: 2138/1545, loss: 0.29248541593551636 2023-01-23 10:27:55.905855: step: 2140/1545, loss: 0.05216030031442642 2023-01-23 10:27:56.761239: step: 2142/1545, loss: 0.0473451167345047 2023-01-23 10:27:57.662390: step: 2144/1545, loss: 0.23604044318199158 2023-01-23 10:27:58.506804: step: 2146/1545, loss: 0.1488945037126541 2023-01-23 10:27:59.416056: step: 2148/1545, loss: 0.038554079830646515 2023-01-23 10:28:00.283570: step: 2150/1545, loss: 0.10056571662425995 2023-01-23 10:28:01.113927: step: 2152/1545, loss: 0.12309318035840988 2023-01-23 10:28:01.986108: step: 2154/1545, loss: 0.07616162300109863 2023-01-23 10:28:02.843412: step: 2156/1545, loss: 0.031875383108854294 2023-01-23 10:28:03.698891: step: 2158/1545, loss: 0.38738781213760376 2023-01-23 10:28:04.599885: step: 2160/1545, loss: 0.05316061154007912 2023-01-23 10:28:05.469380: step: 2162/1545, loss: 0.16971082985401154 2023-01-23 10:28:06.368296: step: 2164/1545, loss: 0.07045567035675049 2023-01-23 10:28:07.263772: step: 2166/1545, loss: 0.08325408399105072 2023-01-23 10:28:08.142042: step: 2168/1545, loss: 0.4587385654449463 2023-01-23 10:28:09.000015: step: 2170/1545, loss: 0.132361501455307 2023-01-23 10:28:09.908901: step: 2172/1545, loss: 0.2860807776451111 2023-01-23 10:28:10.772276: step: 2174/1545, loss: 0.12514927983283997 2023-01-23 10:28:11.649974: step: 2176/1545, loss: 0.05750380456447601 2023-01-23 10:28:12.536290: step: 2178/1545, loss: 0.14312763512134552 2023-01-23 10:28:13.416828: step: 2180/1545, loss: 0.04483320191502571 2023-01-23 10:28:14.324310: step: 2182/1545, loss: 0.10367520898580551 2023-01-23 10:28:15.182094: step: 2184/1545, loss: 0.7864925861358643 2023-01-23 10:28:16.145818: step: 2186/1545, loss: 0.4130042791366577 2023-01-23 10:28:17.099896: step: 2188/1545, loss: 0.30517444014549255 2023-01-23 10:28:18.024411: step: 2190/1545, loss: 0.06969477236270905 2023-01-23 10:28:18.909298: step: 2192/1545, loss: 0.10085892677307129 2023-01-23 10:28:19.809807: step: 2194/1545, loss: 0.172892227768898 2023-01-23 10:28:20.673218: step: 2196/1545, loss: 0.0828005000948906 2023-01-23 10:28:21.483951: step: 2198/1545, loss: 0.023671932518482208 2023-01-23 10:28:22.356863: step: 2200/1545, loss: 0.16218513250350952 2023-01-23 10:28:23.200535: step: 2202/1545, loss: 0.03404352813959122 2023-01-23 10:28:24.061356: step: 2204/1545, loss: 0.02977347932755947 2023-01-23 10:28:24.951453: step: 2206/1545, loss: 2.3542821407318115 2023-01-23 10:28:25.820232: step: 2208/1545, loss: 0.17754919826984406 2023-01-23 10:28:26.706880: step: 2210/1545, loss: 0.49008050560951233 2023-01-23 10:28:27.593024: step: 2212/1545, loss: 0.1907252073287964 2023-01-23 10:28:28.485584: step: 2214/1545, loss: 0.016692515462636948 2023-01-23 10:28:29.377320: step: 2216/1545, loss: 0.0671432837843895 2023-01-23 10:28:30.232782: step: 2218/1545, loss: 0.16512496769428253 2023-01-23 10:28:31.096762: step: 2220/1545, loss: 0.29571083188056946 2023-01-23 10:28:31.977292: step: 2222/1545, loss: 0.25031036138534546 2023-01-23 10:28:32.874780: step: 2224/1545, loss: 0.11104394495487213 2023-01-23 10:28:33.759519: step: 2226/1545, loss: 0.31790292263031006 2023-01-23 10:28:34.642862: step: 2228/1545, loss: 0.44200605154037476 2023-01-23 10:28:35.515330: step: 2230/1545, loss: 1.4992514848709106 2023-01-23 10:28:36.360660: step: 2232/1545, loss: 0.12299904227256775 2023-01-23 10:28:37.236241: step: 2234/1545, loss: 0.2582312226295471 2023-01-23 10:28:38.131940: step: 2236/1545, loss: 0.10988833010196686 2023-01-23 10:28:39.095743: step: 2238/1545, loss: 0.14468593895435333 2023-01-23 10:28:39.992801: step: 2240/1545, loss: 0.14602002501487732 2023-01-23 10:28:40.899269: step: 2242/1545, loss: 0.32652366161346436 2023-01-23 10:28:41.795210: step: 2244/1545, loss: 1.9250117540359497 2023-01-23 10:28:42.644775: step: 2246/1545, loss: 0.09991706907749176 2023-01-23 10:28:43.495165: step: 2248/1545, loss: 0.6017943620681763 2023-01-23 10:28:44.358498: step: 2250/1545, loss: 0.5285472869873047 2023-01-23 10:28:45.243761: step: 2252/1545, loss: 0.11261803656816483 2023-01-23 10:28:46.112850: step: 2254/1545, loss: 0.20370826125144958 2023-01-23 10:28:47.020027: step: 2256/1545, loss: 0.11826731264591217 2023-01-23 10:28:47.874112: step: 2258/1545, loss: 4.299729824066162 2023-01-23 10:28:48.780728: step: 2260/1545, loss: 0.13949021697044373 2023-01-23 10:28:49.722049: step: 2262/1545, loss: 0.08330540359020233 2023-01-23 10:28:50.601618: step: 2264/1545, loss: 0.18828415870666504 2023-01-23 10:28:51.477697: step: 2266/1545, loss: 0.35584044456481934 2023-01-23 10:28:52.414087: step: 2268/1545, loss: 0.07569175213575363 2023-01-23 10:28:53.321900: step: 2270/1545, loss: 0.09256436675786972 2023-01-23 10:28:54.189201: step: 2272/1545, loss: 0.31213951110839844 2023-01-23 10:28:55.025317: step: 2274/1545, loss: 0.4869716763496399 2023-01-23 10:28:55.917506: step: 2276/1545, loss: 0.13318300247192383 2023-01-23 10:28:56.779179: step: 2278/1545, loss: 0.05936247110366821 2023-01-23 10:28:57.669863: step: 2280/1545, loss: 0.20371568202972412 2023-01-23 10:28:58.539614: step: 2282/1545, loss: 0.38653215765953064 2023-01-23 10:28:59.419772: step: 2284/1545, loss: 0.06999566406011581 2023-01-23 10:29:00.313936: step: 2286/1545, loss: 0.44321662187576294 2023-01-23 10:29:01.191824: step: 2288/1545, loss: 0.21907363831996918 2023-01-23 10:29:02.074608: step: 2290/1545, loss: 0.12665507197380066 2023-01-23 10:29:02.920591: step: 2292/1545, loss: 0.14455068111419678 2023-01-23 10:29:03.793395: step: 2294/1545, loss: 0.09091220796108246 2023-01-23 10:29:04.657705: step: 2296/1545, loss: 0.05470842495560646 2023-01-23 10:29:05.502589: step: 2298/1545, loss: 0.18832799792289734 2023-01-23 10:29:06.401414: step: 2300/1545, loss: 0.10457954555749893 2023-01-23 10:29:07.291329: step: 2302/1545, loss: 0.1340547651052475 2023-01-23 10:29:08.209963: step: 2304/1545, loss: 0.1140829548239708 2023-01-23 10:29:09.037669: step: 2306/1545, loss: 0.1075819730758667 2023-01-23 10:29:09.920029: step: 2308/1545, loss: 0.1354234367609024 2023-01-23 10:29:10.745056: step: 2310/1545, loss: 0.03820960968732834 2023-01-23 10:29:11.570051: step: 2312/1545, loss: 0.24757404625415802 2023-01-23 10:29:12.427851: step: 2314/1545, loss: 0.046422071754932404 2023-01-23 10:29:13.307782: step: 2316/1545, loss: 0.43404996395111084 2023-01-23 10:29:14.203566: step: 2318/1545, loss: 0.3356502056121826 2023-01-23 10:29:15.043556: step: 2320/1545, loss: 0.04771643131971359 2023-01-23 10:29:15.909037: step: 2322/1545, loss: 0.41955727338790894 2023-01-23 10:29:16.776331: step: 2324/1545, loss: 0.0369425006210804 2023-01-23 10:29:17.685183: step: 2326/1545, loss: 0.18972600996494293 2023-01-23 10:29:18.627768: step: 2328/1545, loss: 0.5852469801902771 2023-01-23 10:29:19.500929: step: 2330/1545, loss: 0.2903122901916504 2023-01-23 10:29:20.411874: step: 2332/1545, loss: 0.08112280070781708 2023-01-23 10:29:21.360472: step: 2334/1545, loss: 0.2671123147010803 2023-01-23 10:29:22.204487: step: 2336/1545, loss: 0.1399632841348648 2023-01-23 10:29:23.176840: step: 2338/1545, loss: 0.11684556305408478 2023-01-23 10:29:24.114888: step: 2340/1545, loss: 0.20046867430210114 2023-01-23 10:29:25.089701: step: 2342/1545, loss: 0.5053622722625732 2023-01-23 10:29:26.002385: step: 2344/1545, loss: 0.1996249407529831 2023-01-23 10:29:26.863181: step: 2346/1545, loss: 0.07479039579629898 2023-01-23 10:29:27.798214: step: 2348/1545, loss: 0.06980028748512268 2023-01-23 10:29:28.747851: step: 2350/1545, loss: 0.2362028807401657 2023-01-23 10:29:29.626842: step: 2352/1545, loss: 0.11520465463399887 2023-01-23 10:29:30.532199: step: 2354/1545, loss: 0.15523965656757355 2023-01-23 10:29:31.389117: step: 2356/1545, loss: 0.23688596487045288 2023-01-23 10:29:32.308450: step: 2358/1545, loss: 0.22332121431827545 2023-01-23 10:29:33.166473: step: 2360/1545, loss: 0.03683929145336151 2023-01-23 10:29:34.000540: step: 2362/1545, loss: 0.3651537597179413 2023-01-23 10:29:34.882431: step: 2364/1545, loss: 0.10302776843309402 2023-01-23 10:29:35.773815: step: 2366/1545, loss: 2.3429863452911377 2023-01-23 10:29:36.673004: step: 2368/1545, loss: 0.2949092388153076 2023-01-23 10:29:37.522544: step: 2370/1545, loss: 0.0826229676604271 2023-01-23 10:29:38.422300: step: 2372/1545, loss: 0.27088862657546997 2023-01-23 10:29:39.278331: step: 2374/1545, loss: 0.21663713455200195 2023-01-23 10:29:40.226985: step: 2376/1545, loss: 0.44413328170776367 2023-01-23 10:29:41.165438: step: 2378/1545, loss: 0.3643803596496582 2023-01-23 10:29:42.064540: step: 2380/1545, loss: 0.11921613663434982 2023-01-23 10:29:42.954742: step: 2382/1545, loss: 0.05427361652255058 2023-01-23 10:29:43.827340: step: 2384/1545, loss: 0.3072882890701294 2023-01-23 10:29:44.719028: step: 2386/1545, loss: 0.2910974323749542 2023-01-23 10:29:45.634762: step: 2388/1545, loss: 0.3082900941371918 2023-01-23 10:29:46.536967: step: 2390/1545, loss: 0.16422811150550842 2023-01-23 10:29:47.421520: step: 2392/1545, loss: 0.27282240986824036 2023-01-23 10:29:48.324242: step: 2394/1545, loss: 0.08405601233243942 2023-01-23 10:29:49.300608: step: 2396/1545, loss: 0.12769341468811035 2023-01-23 10:29:50.182099: step: 2398/1545, loss: 0.3665779232978821 2023-01-23 10:29:51.030810: step: 2400/1545, loss: 0.04209422692656517 2023-01-23 10:29:51.914037: step: 2402/1545, loss: 0.03252614289522171 2023-01-23 10:29:52.889773: step: 2404/1545, loss: 0.28330251574516296 2023-01-23 10:29:53.775564: step: 2406/1545, loss: 0.35881534218788147 2023-01-23 10:29:54.633780: step: 2408/1545, loss: 0.039533667266368866 2023-01-23 10:29:55.517403: step: 2410/1545, loss: 0.1795000433921814 2023-01-23 10:29:56.487310: step: 2412/1545, loss: 0.3140994906425476 2023-01-23 10:29:57.373691: step: 2414/1545, loss: 0.5338383913040161 2023-01-23 10:29:58.281250: step: 2416/1545, loss: 0.19204822182655334 2023-01-23 10:29:59.208102: step: 2418/1545, loss: 0.032936133444309235 2023-01-23 10:30:00.053459: step: 2420/1545, loss: 0.05128278583288193 2023-01-23 10:30:00.912091: step: 2422/1545, loss: 0.1095811054110527 2023-01-23 10:30:01.830960: step: 2424/1545, loss: 0.12382109463214874 2023-01-23 10:30:02.702045: step: 2426/1545, loss: 0.015558050945401192 2023-01-23 10:30:03.627481: step: 2428/1545, loss: 0.14156390726566315 2023-01-23 10:30:04.553961: step: 2430/1545, loss: 0.19579283893108368 2023-01-23 10:30:05.490049: step: 2432/1545, loss: 0.20970827341079712 2023-01-23 10:30:06.360204: step: 2434/1545, loss: 0.11265265941619873 2023-01-23 10:30:07.273295: step: 2436/1545, loss: 0.21402250230312347 2023-01-23 10:30:08.121320: step: 2438/1545, loss: 0.047807276248931885 2023-01-23 10:30:08.965523: step: 2440/1545, loss: 0.26385095715522766 2023-01-23 10:30:09.858078: step: 2442/1545, loss: 0.04168909043073654 2023-01-23 10:30:10.747926: step: 2444/1545, loss: 0.0300314761698246 2023-01-23 10:30:11.596985: step: 2446/1545, loss: 0.458762526512146 2023-01-23 10:30:12.430902: step: 2448/1545, loss: 0.1233978271484375 2023-01-23 10:30:13.318868: step: 2450/1545, loss: 0.08662142604589462 2023-01-23 10:30:14.155611: step: 2452/1545, loss: 0.03507004305720329 2023-01-23 10:30:14.998370: step: 2454/1545, loss: 0.10201217234134674 2023-01-23 10:30:15.903386: step: 2456/1545, loss: 0.11257792264223099 2023-01-23 10:30:16.787733: step: 2458/1545, loss: 0.08575411140918732 2023-01-23 10:30:17.649433: step: 2460/1545, loss: 0.15804339945316315 2023-01-23 10:30:18.555084: step: 2462/1545, loss: 0.06551187485456467 2023-01-23 10:30:19.412059: step: 2464/1545, loss: 0.08874615281820297 2023-01-23 10:30:20.303719: step: 2466/1545, loss: 0.37518763542175293 2023-01-23 10:30:21.167018: step: 2468/1545, loss: 0.11889047175645828 2023-01-23 10:30:22.049754: step: 2470/1545, loss: 0.14483220875263214 2023-01-23 10:30:22.943958: step: 2472/1545, loss: 0.19669239223003387 2023-01-23 10:30:23.844125: step: 2474/1545, loss: 0.0744338184595108 2023-01-23 10:30:24.699721: step: 2476/1545, loss: 0.40351542830467224 2023-01-23 10:30:25.659098: step: 2478/1545, loss: 0.22478827834129333 2023-01-23 10:30:26.547273: step: 2480/1545, loss: 0.13898636400699615 2023-01-23 10:30:27.426501: step: 2482/1545, loss: 0.2357250452041626 2023-01-23 10:30:28.280522: step: 2484/1545, loss: 0.38391658663749695 2023-01-23 10:30:29.144040: step: 2486/1545, loss: 0.055922236293554306 2023-01-23 10:30:30.095968: step: 2488/1545, loss: 0.11409219354391098 2023-01-23 10:30:30.945274: step: 2490/1545, loss: 0.05267127603292465 2023-01-23 10:30:31.781874: step: 2492/1545, loss: 1.3336338996887207 2023-01-23 10:30:32.664362: step: 2494/1545, loss: 0.14897999167442322 2023-01-23 10:30:33.580152: step: 2496/1545, loss: 0.23345313966274261 2023-01-23 10:30:34.460893: step: 2498/1545, loss: 0.2918543517589569 2023-01-23 10:30:35.357122: step: 2500/1545, loss: 0.36019447445869446 2023-01-23 10:30:36.230863: step: 2502/1545, loss: 0.16575270891189575 2023-01-23 10:30:37.092617: step: 2504/1545, loss: 0.0925760418176651 2023-01-23 10:30:37.974703: step: 2506/1545, loss: 0.589850664138794 2023-01-23 10:30:38.902492: step: 2508/1545, loss: 0.024621354416012764 2023-01-23 10:30:39.811797: step: 2510/1545, loss: 0.5720778703689575 2023-01-23 10:30:40.688860: step: 2512/1545, loss: 0.4204178750514984 2023-01-23 10:30:41.526839: step: 2514/1545, loss: 0.07172700017690659 2023-01-23 10:30:42.409563: step: 2516/1545, loss: 0.5949006080627441 2023-01-23 10:30:43.308359: step: 2518/1545, loss: 0.06685494631528854 2023-01-23 10:30:44.160033: step: 2520/1545, loss: 0.040468428283929825 2023-01-23 10:30:45.056238: step: 2522/1545, loss: 0.04849158599972725 2023-01-23 10:30:45.910874: step: 2524/1545, loss: 0.03267531841993332 2023-01-23 10:30:46.850603: step: 2526/1545, loss: 0.017571818083524704 2023-01-23 10:30:47.703479: step: 2528/1545, loss: 0.33769822120666504 2023-01-23 10:30:48.584779: step: 2530/1545, loss: 0.032371636480093 2023-01-23 10:30:49.471718: step: 2532/1545, loss: 0.7405819296836853 2023-01-23 10:30:50.324255: step: 2534/1545, loss: 0.20705777406692505 2023-01-23 10:30:51.184562: step: 2536/1545, loss: 0.21837261319160461 2023-01-23 10:30:52.104207: step: 2538/1545, loss: 0.010371861048042774 2023-01-23 10:30:52.957983: step: 2540/1545, loss: 0.13702458143234253 2023-01-23 10:30:53.829371: step: 2542/1545, loss: 0.18719445168972015 2023-01-23 10:30:54.763117: step: 2544/1545, loss: 0.29204967617988586 2023-01-23 10:30:55.638905: step: 2546/1545, loss: 0.06463343650102615 2023-01-23 10:30:56.545601: step: 2548/1545, loss: 0.2009667456150055 2023-01-23 10:30:57.406224: step: 2550/1545, loss: 0.07641840726137161 2023-01-23 10:30:58.353361: step: 2552/1545, loss: 0.22188334167003632 2023-01-23 10:30:59.238804: step: 2554/1545, loss: 0.1303827315568924 2023-01-23 10:31:00.127026: step: 2556/1545, loss: 0.28938743472099304 2023-01-23 10:31:00.965981: step: 2558/1545, loss: 1.164156436920166 2023-01-23 10:31:01.841691: step: 2560/1545, loss: 0.3549422323703766 2023-01-23 10:31:02.684650: step: 2562/1545, loss: 0.12989899516105652 2023-01-23 10:31:03.555043: step: 2564/1545, loss: 0.33900055289268494 2023-01-23 10:31:04.429054: step: 2566/1545, loss: 0.15939463675022125 2023-01-23 10:31:05.298257: step: 2568/1545, loss: 0.10008522868156433 2023-01-23 10:31:06.168943: step: 2570/1545, loss: 0.13383452594280243 2023-01-23 10:31:07.010631: step: 2572/1545, loss: 0.27090638875961304 2023-01-23 10:31:07.893002: step: 2574/1545, loss: 0.1278979629278183 2023-01-23 10:31:08.803103: step: 2576/1545, loss: 0.3593437373638153 2023-01-23 10:31:09.678458: step: 2578/1545, loss: 0.15317220985889435 2023-01-23 10:31:10.547347: step: 2580/1545, loss: 0.03159880265593529 2023-01-23 10:31:11.436657: step: 2582/1545, loss: 0.09858006983995438 2023-01-23 10:31:12.380732: step: 2584/1545, loss: 0.1802070438861847 2023-01-23 10:31:13.325759: step: 2586/1545, loss: 0.12107828259468079 2023-01-23 10:31:14.190172: step: 2588/1545, loss: 0.03855518251657486 2023-01-23 10:31:15.065768: step: 2590/1545, loss: 0.04963134229183197 2023-01-23 10:31:15.960771: step: 2592/1545, loss: 0.010817556641995907 2023-01-23 10:31:16.837009: step: 2594/1545, loss: 0.3302210867404938 2023-01-23 10:31:17.736374: step: 2596/1545, loss: 0.15159155428409576 2023-01-23 10:31:18.660063: step: 2598/1545, loss: 0.13100682199001312 2023-01-23 10:31:19.599905: step: 2600/1545, loss: 0.0268704891204834 2023-01-23 10:31:20.469377: step: 2602/1545, loss: 0.17473311722278595 2023-01-23 10:31:21.370046: step: 2604/1545, loss: 0.11354752629995346 2023-01-23 10:31:22.272113: step: 2606/1545, loss: 0.28300297260284424 2023-01-23 10:31:23.181028: step: 2608/1545, loss: 0.45335716009140015 2023-01-23 10:31:24.132548: step: 2610/1545, loss: 0.08168087899684906 2023-01-23 10:31:24.969823: step: 2612/1545, loss: 0.0860031396150589 2023-01-23 10:31:25.881819: step: 2614/1545, loss: 0.030159834772348404 2023-01-23 10:31:26.767729: step: 2616/1545, loss: 0.17037974298000336 2023-01-23 10:31:27.620225: step: 2618/1545, loss: 0.11997198313474655 2023-01-23 10:31:28.465736: step: 2620/1545, loss: 0.22954125702381134 2023-01-23 10:31:29.360523: step: 2622/1545, loss: 0.394194096326828 2023-01-23 10:31:30.253805: step: 2624/1545, loss: 0.1494249403476715 2023-01-23 10:31:31.120451: step: 2626/1545, loss: 0.4775102138519287 2023-01-23 10:31:31.981742: step: 2628/1545, loss: 1.1392700672149658 2023-01-23 10:31:32.813619: step: 2630/1545, loss: 0.10220594704151154 2023-01-23 10:31:33.666438: step: 2632/1545, loss: 0.047063786536455154 2023-01-23 10:31:34.529106: step: 2634/1545, loss: 0.15694518387317657 2023-01-23 10:31:35.389533: step: 2636/1545, loss: 0.05712513625621796 2023-01-23 10:31:36.279641: step: 2638/1545, loss: 0.10167070478200912 2023-01-23 10:31:37.204009: step: 2640/1545, loss: 0.29248544573783875 2023-01-23 10:31:38.076842: step: 2642/1545, loss: 0.06048344075679779 2023-01-23 10:31:38.960491: step: 2644/1545, loss: 0.1151539534330368 2023-01-23 10:31:39.855819: step: 2646/1545, loss: 0.14510686695575714 2023-01-23 10:31:40.713307: step: 2648/1545, loss: 0.14647850394248962 2023-01-23 10:31:41.584301: step: 2650/1545, loss: 0.33374255895614624 2023-01-23 10:31:42.504774: step: 2652/1545, loss: 0.02088136598467827 2023-01-23 10:31:43.363350: step: 2654/1545, loss: 0.04678932577371597 2023-01-23 10:31:44.227490: step: 2656/1545, loss: 0.13877737522125244 2023-01-23 10:31:45.097416: step: 2658/1545, loss: 0.1737689971923828 2023-01-23 10:31:45.947780: step: 2660/1545, loss: 0.11724904924631119 2023-01-23 10:31:46.835000: step: 2662/1545, loss: 0.03978339582681656 2023-01-23 10:31:47.698229: step: 2664/1545, loss: 0.11079270392656326 2023-01-23 10:31:48.542831: step: 2666/1545, loss: 0.7007766962051392 2023-01-23 10:31:49.424267: step: 2668/1545, loss: 0.13625144958496094 2023-01-23 10:31:50.309900: step: 2670/1545, loss: 0.027799388393759727 2023-01-23 10:31:51.175651: step: 2672/1545, loss: 0.08098427206277847 2023-01-23 10:31:52.089112: step: 2674/1545, loss: 0.18515156209468842 2023-01-23 10:31:52.959458: step: 2676/1545, loss: 0.15958844125270844 2023-01-23 10:31:53.814369: step: 2678/1545, loss: 0.23124977946281433 2023-01-23 10:31:54.720590: step: 2680/1545, loss: 0.0372956246137619 2023-01-23 10:31:55.596426: step: 2682/1545, loss: 0.10824030637741089 2023-01-23 10:31:56.432481: step: 2684/1545, loss: 0.026706624776124954 2023-01-23 10:31:57.326479: step: 2686/1545, loss: 0.914122998714447 2023-01-23 10:31:58.224045: step: 2688/1545, loss: 0.08846300840377808 2023-01-23 10:31:59.119504: step: 2690/1545, loss: 0.22803445160388947 2023-01-23 10:31:59.992145: step: 2692/1545, loss: 0.02400849387049675 2023-01-23 10:32:00.841147: step: 2694/1545, loss: 0.06633806973695755 2023-01-23 10:32:01.699892: step: 2696/1545, loss: 0.49513131380081177 2023-01-23 10:32:02.665463: step: 2698/1545, loss: 1.3942495584487915 2023-01-23 10:32:03.546875: step: 2700/1545, loss: 0.35984182357788086 2023-01-23 10:32:04.413917: step: 2702/1545, loss: 0.7592338919639587 2023-01-23 10:32:05.282068: step: 2704/1545, loss: 0.17263354361057281 2023-01-23 10:32:06.161179: step: 2706/1545, loss: 0.3519775867462158 2023-01-23 10:32:07.032934: step: 2708/1545, loss: 0.36826053261756897 2023-01-23 10:32:07.888369: step: 2710/1545, loss: 0.19015496969223022 2023-01-23 10:32:08.756209: step: 2712/1545, loss: 0.025497598573565483 2023-01-23 10:32:09.643220: step: 2714/1545, loss: 0.2797609567642212 2023-01-23 10:32:10.541968: step: 2716/1545, loss: 0.0739515870809555 2023-01-23 10:32:11.418720: step: 2718/1545, loss: 0.557025134563446 2023-01-23 10:32:12.325837: step: 2720/1545, loss: 0.19082938134670258 2023-01-23 10:32:13.199661: step: 2722/1545, loss: 0.14137697219848633 2023-01-23 10:32:14.058968: step: 2724/1545, loss: 0.24330398440361023 2023-01-23 10:32:14.945350: step: 2726/1545, loss: 0.16837580502033234 2023-01-23 10:32:15.787638: step: 2728/1545, loss: 0.12336364388465881 2023-01-23 10:32:16.646596: step: 2730/1545, loss: 0.1220722496509552 2023-01-23 10:32:17.502788: step: 2732/1545, loss: 0.14895795285701752 2023-01-23 10:32:18.352183: step: 2734/1545, loss: 0.040088292211294174 2023-01-23 10:32:19.232122: step: 2736/1545, loss: 0.2431192398071289 2023-01-23 10:32:20.092453: step: 2738/1545, loss: 0.13763611018657684 2023-01-23 10:32:20.964623: step: 2740/1545, loss: 0.2259570062160492 2023-01-23 10:32:21.815865: step: 2742/1545, loss: 0.27526891231536865 2023-01-23 10:32:22.801313: step: 2744/1545, loss: 0.15909449756145477 2023-01-23 10:32:23.636337: step: 2746/1545, loss: 0.20714369416236877 2023-01-23 10:32:24.548931: step: 2748/1545, loss: 0.15686893463134766 2023-01-23 10:32:25.393233: step: 2750/1545, loss: 0.032559655606746674 2023-01-23 10:32:26.233711: step: 2752/1545, loss: 0.034320686012506485 2023-01-23 10:32:27.087795: step: 2754/1545, loss: 0.09702244400978088 2023-01-23 10:32:27.937557: step: 2756/1545, loss: 0.2921508252620697 2023-01-23 10:32:28.831956: step: 2758/1545, loss: 0.07908087968826294 2023-01-23 10:32:29.729565: step: 2760/1545, loss: 0.28396275639533997 2023-01-23 10:32:30.603115: step: 2762/1545, loss: 0.1032809242606163 2023-01-23 10:32:31.469726: step: 2764/1545, loss: 0.0186090636998415 2023-01-23 10:32:32.354292: step: 2766/1545, loss: 0.16974923014640808 2023-01-23 10:32:33.260289: step: 2768/1545, loss: 0.26036539673805237 2023-01-23 10:32:34.172215: step: 2770/1545, loss: 0.21560676395893097 2023-01-23 10:32:35.039995: step: 2772/1545, loss: 0.10213703662157059 2023-01-23 10:32:35.887864: step: 2774/1545, loss: 0.5203930735588074 2023-01-23 10:32:36.825740: step: 2776/1545, loss: 0.3590530455112457 2023-01-23 10:32:37.720526: step: 2778/1545, loss: 0.08716321736574173 2023-01-23 10:32:38.615159: step: 2780/1545, loss: 0.09117714315652847 2023-01-23 10:32:39.488728: step: 2782/1545, loss: 0.026625357568264008 2023-01-23 10:32:40.351455: step: 2784/1545, loss: 0.09160789847373962 2023-01-23 10:32:41.203823: step: 2786/1545, loss: 0.11589521914720535 2023-01-23 10:32:42.051956: step: 2788/1545, loss: 1.8367971181869507 2023-01-23 10:32:42.959584: step: 2790/1545, loss: 0.2651931345462799 2023-01-23 10:32:43.927405: step: 2792/1545, loss: 0.049715228378772736 2023-01-23 10:32:44.807636: step: 2794/1545, loss: 0.11262203007936478 2023-01-23 10:32:45.749910: step: 2796/1545, loss: 0.098775714635849 2023-01-23 10:32:46.659086: step: 2798/1545, loss: 0.018432462587952614 2023-01-23 10:32:47.564589: step: 2800/1545, loss: 0.06795850396156311 2023-01-23 10:32:48.424034: step: 2802/1545, loss: 0.09678575396537781 2023-01-23 10:32:49.303081: step: 2804/1545, loss: 0.20059026777744293 2023-01-23 10:32:50.184132: step: 2806/1545, loss: 0.1692877858877182 2023-01-23 10:32:51.013134: step: 2808/1545, loss: 0.16329073905944824 2023-01-23 10:32:51.858368: step: 2810/1545, loss: 0.3799462914466858 2023-01-23 10:32:52.806780: step: 2812/1545, loss: 0.2632485628128052 2023-01-23 10:32:53.681125: step: 2814/1545, loss: 0.2265959233045578 2023-01-23 10:32:54.547063: step: 2816/1545, loss: 0.10800500214099884 2023-01-23 10:32:55.445159: step: 2818/1545, loss: 0.2356504648923874 2023-01-23 10:32:56.318526: step: 2820/1545, loss: 0.08587070554494858 2023-01-23 10:32:57.220587: step: 2822/1545, loss: 0.20267769694328308 2023-01-23 10:32:58.055987: step: 2824/1545, loss: 0.14506608247756958 2023-01-23 10:32:58.892898: step: 2826/1545, loss: 0.35936978459358215 2023-01-23 10:32:59.739372: step: 2828/1545, loss: 0.08702077716588974 2023-01-23 10:33:00.607453: step: 2830/1545, loss: 2.1605632305145264 2023-01-23 10:33:01.504851: step: 2832/1545, loss: 0.21790474653244019 2023-01-23 10:33:02.347425: step: 2834/1545, loss: 0.035557352006435394 2023-01-23 10:33:03.196083: step: 2836/1545, loss: 0.03225294500589371 2023-01-23 10:33:04.091473: step: 2838/1545, loss: 0.13868892192840576 2023-01-23 10:33:04.916615: step: 2840/1545, loss: 0.21281175315380096 2023-01-23 10:33:05.819858: step: 2842/1545, loss: 0.1397722214460373 2023-01-23 10:33:06.658087: step: 2844/1545, loss: 0.03282090276479721 2023-01-23 10:33:07.505301: step: 2846/1545, loss: 0.13425949215888977 2023-01-23 10:33:08.422544: step: 2848/1545, loss: 0.6183334589004517 2023-01-23 10:33:09.328514: step: 2850/1545, loss: 0.2402011901140213 2023-01-23 10:33:10.175780: step: 2852/1545, loss: 0.015380971133708954 2023-01-23 10:33:10.991762: step: 2854/1545, loss: 0.31216946244239807 2023-01-23 10:33:11.859693: step: 2856/1545, loss: 0.13073033094406128 2023-01-23 10:33:12.732699: step: 2858/1545, loss: 0.2148032933473587 2023-01-23 10:33:13.624841: step: 2860/1545, loss: 0.26649031043052673 2023-01-23 10:33:14.466058: step: 2862/1545, loss: 0.4013385474681854 2023-01-23 10:33:15.350132: step: 2864/1545, loss: 0.21388988196849823 2023-01-23 10:33:16.201612: step: 2866/1545, loss: 0.5274110436439514 2023-01-23 10:33:17.083815: step: 2868/1545, loss: 0.19556209444999695 2023-01-23 10:33:17.965255: step: 2870/1545, loss: 0.20251238346099854 2023-01-23 10:33:18.826320: step: 2872/1545, loss: 0.35438278317451477 2023-01-23 10:33:19.666441: step: 2874/1545, loss: 0.09759951382875443 2023-01-23 10:33:20.549343: step: 2876/1545, loss: 0.11142764985561371 2023-01-23 10:33:21.458473: step: 2878/1545, loss: 0.6712213158607483 2023-01-23 10:33:22.368394: step: 2880/1545, loss: 0.08473905920982361 2023-01-23 10:33:23.255614: step: 2882/1545, loss: 0.16803935170173645 2023-01-23 10:33:24.120280: step: 2884/1545, loss: 0.013331843540072441 2023-01-23 10:33:24.987058: step: 2886/1545, loss: 0.1553374081850052 2023-01-23 10:33:25.868880: step: 2888/1545, loss: 0.13607975840568542 2023-01-23 10:33:26.702797: step: 2890/1545, loss: 0.10202202200889587 2023-01-23 10:33:27.591636: step: 2892/1545, loss: 0.04222773388028145 2023-01-23 10:33:28.463005: step: 2894/1545, loss: 0.3558162748813629 2023-01-23 10:33:29.334296: step: 2896/1545, loss: 0.0707322508096695 2023-01-23 10:33:30.278126: step: 2898/1545, loss: 0.07966190576553345 2023-01-23 10:33:31.142646: step: 2900/1545, loss: 0.30962613224983215 2023-01-23 10:33:31.996598: step: 2902/1545, loss: 0.19599317014217377 2023-01-23 10:33:32.846960: step: 2904/1545, loss: 0.07939484715461731 2023-01-23 10:33:33.720309: step: 2906/1545, loss: 0.04490091651678085 2023-01-23 10:33:34.618350: step: 2908/1545, loss: 0.06509064137935638 2023-01-23 10:33:35.486497: step: 2910/1545, loss: 5.245967864990234 2023-01-23 10:33:36.418331: step: 2912/1545, loss: 0.18198300898075104 2023-01-23 10:33:37.275059: step: 2914/1545, loss: 0.022515835240483284 2023-01-23 10:33:38.172137: step: 2916/1545, loss: 0.22322745621204376 2023-01-23 10:33:39.029899: step: 2918/1545, loss: 0.3186718821525574 2023-01-23 10:33:39.910519: step: 2920/1545, loss: 0.03808358684182167 2023-01-23 10:33:40.881723: step: 2922/1545, loss: 0.18919697403907776 2023-01-23 10:33:41.765440: step: 2924/1545, loss: 0.1603713035583496 2023-01-23 10:33:42.651751: step: 2926/1545, loss: 0.20056484639644623 2023-01-23 10:33:43.517351: step: 2928/1545, loss: 0.19610074162483215 2023-01-23 10:33:44.391530: step: 2930/1545, loss: 0.017982242628932 2023-01-23 10:33:45.302426: step: 2932/1545, loss: 0.12053991854190826 2023-01-23 10:33:46.174525: step: 2934/1545, loss: 0.020720895379781723 2023-01-23 10:33:47.077017: step: 2936/1545, loss: 0.2521475851535797 2023-01-23 10:33:47.949761: step: 2938/1545, loss: 0.15865039825439453 2023-01-23 10:33:48.820242: step: 2940/1545, loss: 0.14353111386299133 2023-01-23 10:33:49.701501: step: 2942/1545, loss: 0.1221589669585228 2023-01-23 10:33:50.601977: step: 2944/1545, loss: 0.8897018432617188 2023-01-23 10:33:51.461542: step: 2946/1545, loss: 0.22744427621364594 2023-01-23 10:33:52.313524: step: 2948/1545, loss: 0.02520948275923729 2023-01-23 10:33:53.197821: step: 2950/1545, loss: 0.4641224443912506 2023-01-23 10:33:54.093785: step: 2952/1545, loss: 0.14682643115520477 2023-01-23 10:33:54.934278: step: 2954/1545, loss: 0.5794500112533569 2023-01-23 10:33:55.854363: step: 2956/1545, loss: 0.15408505499362946 2023-01-23 10:33:56.751542: step: 2958/1545, loss: 0.06479325890541077 2023-01-23 10:33:57.650788: step: 2960/1545, loss: 0.02620217390358448 2023-01-23 10:33:58.506490: step: 2962/1545, loss: 0.34433260560035706 2023-01-23 10:33:59.350441: step: 2964/1545, loss: 0.3540707230567932 2023-01-23 10:34:00.301513: step: 2966/1545, loss: 0.13474509119987488 2023-01-23 10:34:01.154041: step: 2968/1545, loss: 0.1554216593503952 2023-01-23 10:34:02.120755: step: 2970/1545, loss: 0.008829980157315731 2023-01-23 10:34:02.997135: step: 2972/1545, loss: 0.16370262205600739 2023-01-23 10:34:03.883775: step: 2974/1545, loss: 0.09936106950044632 2023-01-23 10:34:04.789930: step: 2976/1545, loss: 0.5866878032684326 2023-01-23 10:34:05.644103: step: 2978/1545, loss: 0.15756595134735107 2023-01-23 10:34:06.503337: step: 2980/1545, loss: 0.21076470613479614 2023-01-23 10:34:07.352640: step: 2982/1545, loss: 0.05554831400513649 2023-01-23 10:34:08.203775: step: 2984/1545, loss: 0.028767026960849762 2023-01-23 10:34:09.061652: step: 2986/1545, loss: 0.5086148381233215 2023-01-23 10:34:09.947710: step: 2988/1545, loss: 0.1702318787574768 2023-01-23 10:34:10.813520: step: 2990/1545, loss: 0.04433443024754524 2023-01-23 10:34:11.727509: step: 2992/1545, loss: 0.07123823463916779 2023-01-23 10:34:12.628540: step: 2994/1545, loss: 0.054047755897045135 2023-01-23 10:34:13.499884: step: 2996/1545, loss: 0.24729034304618835 2023-01-23 10:34:14.446305: step: 2998/1545, loss: 0.3845740258693695 2023-01-23 10:34:15.272572: step: 3000/1545, loss: 0.17323042452335358 2023-01-23 10:34:16.179248: step: 3002/1545, loss: 0.018433330580592155 2023-01-23 10:34:17.066406: step: 3004/1545, loss: 0.011664392426609993 2023-01-23 10:34:17.975451: step: 3006/1545, loss: 0.11220928281545639 2023-01-23 10:34:18.849495: step: 3008/1545, loss: 0.12551186978816986 2023-01-23 10:34:19.710756: step: 3010/1545, loss: 2.3097879886627197 2023-01-23 10:34:20.611770: step: 3012/1545, loss: 0.0529126338660717 2023-01-23 10:34:21.487218: step: 3014/1545, loss: 0.22769707441329956 2023-01-23 10:34:22.418484: step: 3016/1545, loss: 0.15742012858390808 2023-01-23 10:34:23.273429: step: 3018/1545, loss: 0.18357545137405396 2023-01-23 10:34:24.118693: step: 3020/1545, loss: 0.10668855160474777 2023-01-23 10:34:24.992994: step: 3022/1545, loss: 0.0703214630484581 2023-01-23 10:34:25.924272: step: 3024/1545, loss: 0.27553561329841614 2023-01-23 10:34:26.809645: step: 3026/1545, loss: 0.5095561146736145 2023-01-23 10:34:27.816759: step: 3028/1545, loss: 0.17356711626052856 2023-01-23 10:34:28.655942: step: 3030/1545, loss: 0.325371652841568 2023-01-23 10:34:29.517598: step: 3032/1545, loss: 0.09184642881155014 2023-01-23 10:34:30.417436: step: 3034/1545, loss: 0.12509049475193024 2023-01-23 10:34:31.299848: step: 3036/1545, loss: 0.016907531768083572 2023-01-23 10:34:32.227730: step: 3038/1545, loss: 0.11527521163225174 2023-01-23 10:34:33.088004: step: 3040/1545, loss: 0.11083860695362091 2023-01-23 10:34:33.976414: step: 3042/1545, loss: 1.7099905014038086 2023-01-23 10:34:34.857373: step: 3044/1545, loss: 0.5764642953872681 2023-01-23 10:34:35.746778: step: 3046/1545, loss: 0.11923100054264069 2023-01-23 10:34:36.608258: step: 3048/1545, loss: 0.023973023518919945 2023-01-23 10:34:37.524050: step: 3050/1545, loss: 0.3195376992225647 2023-01-23 10:34:38.393576: step: 3052/1545, loss: 0.6875075697898865 2023-01-23 10:34:39.264304: step: 3054/1545, loss: 0.43584612011909485 2023-01-23 10:34:40.133033: step: 3056/1545, loss: 0.11593977361917496 2023-01-23 10:34:40.996305: step: 3058/1545, loss: 0.8110937476158142 2023-01-23 10:34:41.834323: step: 3060/1545, loss: 0.09069546312093735 2023-01-23 10:34:42.706137: step: 3062/1545, loss: 0.23248246312141418 2023-01-23 10:34:43.645137: step: 3064/1545, loss: 0.22917470335960388 2023-01-23 10:34:44.478271: step: 3066/1545, loss: 0.4616136848926544 2023-01-23 10:34:45.341901: step: 3068/1545, loss: 0.09648532420396805 2023-01-23 10:34:46.209652: step: 3070/1545, loss: 0.9363669157028198 2023-01-23 10:34:47.054051: step: 3072/1545, loss: 0.03772367909550667 2023-01-23 10:34:47.926878: step: 3074/1545, loss: 0.29715853929519653 2023-01-23 10:34:48.827417: step: 3076/1545, loss: 0.33905670046806335 2023-01-23 10:34:49.748183: step: 3078/1545, loss: 0.29481080174446106 2023-01-23 10:34:50.622322: step: 3080/1545, loss: 0.3345867097377777 2023-01-23 10:34:51.484278: step: 3082/1545, loss: 0.10901489853858948 2023-01-23 10:34:52.380453: step: 3084/1545, loss: 0.1869598627090454 2023-01-23 10:34:53.299216: step: 3086/1545, loss: 0.18876010179519653 2023-01-23 10:34:54.168837: step: 3088/1545, loss: 0.15691612660884857 2023-01-23 10:34:55.044665: step: 3090/1545, loss: 0.07026205211877823 ================================================== Loss: 0.237 -------------------- Dev Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6646509869560432, 'r': 0.6397763242705625, 'f1': 0.6519764830095129}, 'combined': 0.4291787639954708, 'epoch': 11} Test Chinese: {'event': {'p': 0.6414087513340448, 'r': 0.768542199488491, 'f1': 0.6992437463641652}, 'argument': {'p': 0.7169484890275156, 'r': 0.6862651757791084, 'f1': 0.7012713647067265}, 'combined': 0.4903596162754422, 'epoch': 11} Dev Korean: {'event': {'p': 0.611597374179431, 'r': 0.7443408788282291, 'f1': 0.6714714714714715}, 'argument': {'p': 0.665808631000232, 'r': 0.6417975008063844, 'f1': 0.6535826117622782}, 'combined': 0.4388620780481844, 'epoch': 11} Test Korean: {'event': {'p': 0.6312169312169312, 'r': 0.7627877237851662, 'f1': 0.6907932831499711}, 'argument': {'p': 0.7129914922238261, 'r': 0.6881324018819225, 'f1': 0.7003414189556707}, 'combined': 0.4837911481262972, 'epoch': 11} Dev Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6645260284596569, 'r': 0.644547436337033, 'f1': 0.6543842794788046}, 'combined': 0.4303308051807419, 'epoch': 11} Test Russian: {'event': {'p': 0.6292974588938715, 'r': 0.8075447570332481, 'f1': 0.7073648837860543}, 'argument': {'p': 0.7211792065906051, 'r': 0.6960688860316661, 'f1': 0.7084015982436961}, 'combined': 0.5010984142155073, 'epoch': 11} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6943722943722943, 'r': 0.6025544703230653, 'f1': 0.6452131938857603}, 'combined': 0.44969404422340875, 'epoch': 11} Korean: {'event': {'p': 0.6666666666666666, 'r': 0.5396825396825397, 'f1': 0.5964912280701754}, 'argument': {'p': 0.7074468085106383, 'r': 0.4618055555555556, 'f1': 0.5588235294117648}, 'combined': 0.33333333333333337, 'epoch': 11} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5857649368175684, 'r': 0.5753048486601118, 'f1': 0.5804877752246173}, 'combined': 0.3233096469605463, 'epoch': 11} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.6540410788569386, 'r': 0.6466702177127959, 'f1': 0.6503347637141906}, 'combined': 0.4374624236395757, 'epoch': 9} Test for Korean: {'event': {'p': 0.6354497354497355, 'r': 0.7679028132992327, 'f1': 0.6954255935147655}, 'argument': {'p': 0.7132062904851311, 'r': 0.7077515578619179, 'f1': 0.7104684544372034}, 'combined': 0.4940779466005103, 'epoch': 9} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6633986928104574, 'r': 0.46990740740740733, 'f1': 0.5501355013550133}, 'combined': 0.3474540008557979, 'epoch': 9} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 12 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 10:40:06.583907: step: 2/1545, loss: 0.1562499850988388 2023-01-23 10:40:07.433109: step: 4/1545, loss: 0.035915445536375046 2023-01-23 10:40:08.309011: step: 6/1545, loss: 0.14506079256534576 2023-01-23 10:40:09.179360: step: 8/1545, loss: 0.2843743860721588 2023-01-23 10:40:10.127857: step: 10/1545, loss: 0.14781531691551208 2023-01-23 10:40:10.962542: step: 12/1545, loss: 0.08458472788333893 2023-01-23 10:40:11.858378: step: 14/1545, loss: 0.1690298318862915 2023-01-23 10:40:12.742162: step: 16/1545, loss: 0.06861727684736252 2023-01-23 10:40:13.642684: step: 18/1545, loss: 0.037395723164081573 2023-01-23 10:40:14.499509: step: 20/1545, loss: 0.03848591446876526 2023-01-23 10:40:15.379631: step: 22/1545, loss: 0.09606104344129562 2023-01-23 10:40:16.211647: step: 24/1545, loss: 0.020849494263529778 2023-01-23 10:40:17.193941: step: 26/1545, loss: 0.15553662180900574 2023-01-23 10:40:18.084030: step: 28/1545, loss: 0.04034928232431412 2023-01-23 10:40:18.992105: step: 30/1545, loss: 0.21807461977005005 2023-01-23 10:40:19.914078: step: 32/1545, loss: 0.20453773438930511 2023-01-23 10:40:20.787537: step: 34/1545, loss: 0.11975450068712234 2023-01-23 10:40:21.625627: step: 36/1545, loss: 0.09307748824357986 2023-01-23 10:40:22.505796: step: 38/1545, loss: 1.9881573915481567 2023-01-23 10:40:23.424572: step: 40/1545, loss: 0.358429491519928 2023-01-23 10:40:24.285043: step: 42/1545, loss: 0.024005185812711716 2023-01-23 10:40:25.167871: step: 44/1545, loss: 0.19384269416332245 2023-01-23 10:40:26.079688: step: 46/1545, loss: 0.07992392033338547 2023-01-23 10:40:26.940644: step: 48/1545, loss: 0.04471094533801079 2023-01-23 10:40:27.823358: step: 50/1545, loss: 0.09922834485769272 2023-01-23 10:40:28.704902: step: 52/1545, loss: 0.17297092080116272 2023-01-23 10:40:29.581127: step: 54/1545, loss: 0.03205789998173714 2023-01-23 10:40:30.460086: step: 56/1545, loss: 0.016337774693965912 2023-01-23 10:40:31.328520: step: 58/1545, loss: 0.10371656715869904 2023-01-23 10:40:32.219879: step: 60/1545, loss: 0.5523324608802795 2023-01-23 10:40:33.062379: step: 62/1545, loss: 0.17322397232055664 2023-01-23 10:40:33.938436: step: 64/1545, loss: 0.22462554275989532 2023-01-23 10:40:34.800389: step: 66/1545, loss: 0.12548589706420898 2023-01-23 10:40:35.661643: step: 68/1545, loss: 0.016188111156225204 2023-01-23 10:40:36.507988: step: 70/1545, loss: 0.23159119486808777 2023-01-23 10:40:37.422022: step: 72/1545, loss: 0.243643656373024 2023-01-23 10:40:38.323165: step: 74/1545, loss: 0.027342533692717552 2023-01-23 10:40:39.195911: step: 76/1545, loss: 0.07247870415449142 2023-01-23 10:40:40.090234: step: 78/1545, loss: 0.15720234811306 2023-01-23 10:40:40.931213: step: 80/1545, loss: 0.04613209888339043 2023-01-23 10:40:41.816704: step: 82/1545, loss: 0.1759391874074936 2023-01-23 10:40:42.694234: step: 84/1545, loss: 0.6124508380889893 2023-01-23 10:40:43.587883: step: 86/1545, loss: 0.5240759253501892 2023-01-23 10:40:44.476711: step: 88/1545, loss: 0.0510803759098053 2023-01-23 10:40:45.325480: step: 90/1545, loss: 0.5446738004684448 2023-01-23 10:40:46.155079: step: 92/1545, loss: 0.17180101573467255 2023-01-23 10:40:47.035328: step: 94/1545, loss: 0.23695705831050873 2023-01-23 10:40:47.892413: step: 96/1545, loss: 0.05689464509487152 2023-01-23 10:40:48.749838: step: 98/1545, loss: 0.23588696122169495 2023-01-23 10:40:49.586091: step: 100/1545, loss: 0.06383833289146423 2023-01-23 10:40:50.451015: step: 102/1545, loss: 0.1917693018913269 2023-01-23 10:40:51.326853: step: 104/1545, loss: 0.1713952273130417 2023-01-23 10:40:52.178820: step: 106/1545, loss: 0.10940779000520706 2023-01-23 10:40:53.115849: step: 108/1545, loss: 0.03621545433998108 2023-01-23 10:40:53.994595: step: 110/1545, loss: 0.15868020057678223 2023-01-23 10:40:54.838830: step: 112/1545, loss: 0.14430436491966248 2023-01-23 10:40:55.707205: step: 114/1545, loss: 0.3690498173236847 2023-01-23 10:40:56.626162: step: 116/1545, loss: 0.17598649859428406 2023-01-23 10:40:57.550385: step: 118/1545, loss: 0.14312687516212463 2023-01-23 10:40:58.375420: step: 120/1545, loss: 0.07913149148225784 2023-01-23 10:40:59.232619: step: 122/1545, loss: 0.052533671259880066 2023-01-23 10:41:00.130180: step: 124/1545, loss: 0.19230912625789642 2023-01-23 10:41:00.992276: step: 126/1545, loss: 0.047947052866220474 2023-01-23 10:41:01.861848: step: 128/1545, loss: 0.056054528802633286 2023-01-23 10:41:02.741252: step: 130/1545, loss: 0.23612917959690094 2023-01-23 10:41:03.606067: step: 132/1545, loss: 0.10238128155469894 2023-01-23 10:41:04.511834: step: 134/1545, loss: 0.330459326505661 2023-01-23 10:41:05.348963: step: 136/1545, loss: 0.36475831270217896 2023-01-23 10:41:06.204064: step: 138/1545, loss: 0.32025593519210815 2023-01-23 10:41:07.147112: step: 140/1545, loss: 0.7199198603630066 2023-01-23 10:41:07.981990: step: 142/1545, loss: 0.2276706099510193 2023-01-23 10:41:08.884671: step: 144/1545, loss: 0.18163837492465973 2023-01-23 10:41:09.738590: step: 146/1545, loss: 0.0426727831363678 2023-01-23 10:41:10.630249: step: 148/1545, loss: 0.11541416496038437 2023-01-23 10:41:11.501681: step: 150/1545, loss: 0.0344231054186821 2023-01-23 10:41:12.378039: step: 152/1545, loss: 0.13084524869918823 2023-01-23 10:41:13.316714: step: 154/1545, loss: 0.2687857747077942 2023-01-23 10:41:14.169190: step: 156/1545, loss: 0.35070306062698364 2023-01-23 10:41:15.093747: step: 158/1545, loss: 0.2176288664340973 2023-01-23 10:41:16.002892: step: 160/1545, loss: 0.08767326921224594 2023-01-23 10:41:16.838449: step: 162/1545, loss: 0.012331978417932987 2023-01-23 10:41:17.744321: step: 164/1545, loss: 0.18165451288223267 2023-01-23 10:41:18.614731: step: 166/1545, loss: 0.003919296432286501 2023-01-23 10:41:19.487462: step: 168/1545, loss: 0.04465055093169212 2023-01-23 10:41:20.346451: step: 170/1545, loss: 0.11014503985643387 2023-01-23 10:41:21.225165: step: 172/1545, loss: 0.12450257688760757 2023-01-23 10:41:22.104773: step: 174/1545, loss: 0.04929687827825546 2023-01-23 10:41:22.991285: step: 176/1545, loss: 0.042156118899583817 2023-01-23 10:41:23.843231: step: 178/1545, loss: 0.006123444996774197 2023-01-23 10:41:24.721839: step: 180/1545, loss: 0.19093972444534302 2023-01-23 10:41:25.677481: step: 182/1545, loss: 0.08341266959905624 2023-01-23 10:41:26.541217: step: 184/1545, loss: 0.04573282599449158 2023-01-23 10:41:27.423643: step: 186/1545, loss: 0.06418510526418686 2023-01-23 10:41:28.293057: step: 188/1545, loss: 0.009438854642212391 2023-01-23 10:41:29.222060: step: 190/1545, loss: 0.05814586207270622 2023-01-23 10:41:30.166462: step: 192/1545, loss: 0.0016346105840057135 2023-01-23 10:41:31.045641: step: 194/1545, loss: 0.3288941979408264 2023-01-23 10:41:31.903795: step: 196/1545, loss: 0.18286681175231934 2023-01-23 10:41:32.769443: step: 198/1545, loss: 0.22150665521621704 2023-01-23 10:41:33.780630: step: 200/1545, loss: 0.23282842338085175 2023-01-23 10:41:34.663740: step: 202/1545, loss: 0.1213168054819107 2023-01-23 10:41:35.511341: step: 204/1545, loss: 0.06068116053938866 2023-01-23 10:41:36.450401: step: 206/1545, loss: 0.0826503336429596 2023-01-23 10:41:37.310300: step: 208/1545, loss: 0.060181036591529846 2023-01-23 10:41:38.181842: step: 210/1545, loss: 0.03490152209997177 2023-01-23 10:41:39.052598: step: 212/1545, loss: 0.0029232308734208345 2023-01-23 10:41:39.916798: step: 214/1545, loss: 0.2077334076166153 2023-01-23 10:41:40.787193: step: 216/1545, loss: 0.012289450503885746 2023-01-23 10:41:41.640636: step: 218/1545, loss: 0.18986114859580994 2023-01-23 10:41:42.529277: step: 220/1545, loss: 0.8711205720901489 2023-01-23 10:41:43.391196: step: 222/1545, loss: 0.02772432751953602 2023-01-23 10:41:44.239613: step: 224/1545, loss: 0.0645223930478096 2023-01-23 10:41:45.130731: step: 226/1545, loss: 0.47634002566337585 2023-01-23 10:41:46.040073: step: 228/1545, loss: 0.0073715439066290855 2023-01-23 10:41:46.907621: step: 230/1545, loss: 1.0086888074874878 2023-01-23 10:41:47.762434: step: 232/1545, loss: 0.16205158829689026 2023-01-23 10:41:48.643011: step: 234/1545, loss: 0.030590776354074478 2023-01-23 10:41:49.547791: step: 236/1545, loss: 0.46021345257759094 2023-01-23 10:41:50.427640: step: 238/1545, loss: 0.060278862714767456 2023-01-23 10:41:51.324512: step: 240/1545, loss: 0.06422626972198486 2023-01-23 10:41:52.195519: step: 242/1545, loss: 0.00433820765465498 2023-01-23 10:41:53.084966: step: 244/1545, loss: 0.06645409017801285 2023-01-23 10:41:53.920310: step: 246/1545, loss: 0.006990027613937855 2023-01-23 10:41:54.791095: step: 248/1545, loss: 0.05399450659751892 2023-01-23 10:41:55.688628: step: 250/1545, loss: 0.20203247666358948 2023-01-23 10:41:56.640973: step: 252/1545, loss: 0.6657914519309998 2023-01-23 10:41:57.557517: step: 254/1545, loss: 0.08043374866247177 2023-01-23 10:41:58.419847: step: 256/1545, loss: 0.06768644601106644 2023-01-23 10:41:59.309537: step: 258/1545, loss: 0.08992812037467957 2023-01-23 10:42:00.170229: step: 260/1545, loss: 0.5471957921981812 2023-01-23 10:42:01.099978: step: 262/1545, loss: 0.009252123534679413 2023-01-23 10:42:01.959131: step: 264/1545, loss: 0.00631085317581892 2023-01-23 10:42:02.809361: step: 266/1545, loss: 0.44918492436408997 2023-01-23 10:42:03.757362: step: 268/1545, loss: 0.576960027217865 2023-01-23 10:42:04.627366: step: 270/1545, loss: 0.32406964898109436 2023-01-23 10:42:05.524420: step: 272/1545, loss: 0.03340286761522293 2023-01-23 10:42:06.424328: step: 274/1545, loss: 0.023895172402262688 2023-01-23 10:42:07.317729: step: 276/1545, loss: 0.20255804061889648 2023-01-23 10:42:08.213702: step: 278/1545, loss: 0.12029165029525757 2023-01-23 10:42:09.128089: step: 280/1545, loss: 0.11378832161426544 2023-01-23 10:42:09.998451: step: 282/1545, loss: 0.5304400324821472 2023-01-23 10:42:10.841938: step: 284/1545, loss: 0.0048623960465192795 2023-01-23 10:42:11.746977: step: 286/1545, loss: 0.40374836325645447 2023-01-23 10:42:12.603873: step: 288/1545, loss: 0.17617002129554749 2023-01-23 10:42:13.503499: step: 290/1545, loss: 0.05048731714487076 2023-01-23 10:42:14.374891: step: 292/1545, loss: 0.01405271701514721 2023-01-23 10:42:15.255234: step: 294/1545, loss: 0.1034347265958786 2023-01-23 10:42:16.135540: step: 296/1545, loss: 0.11185552924871445 2023-01-23 10:42:17.072766: step: 298/1545, loss: 0.027505777776241302 2023-01-23 10:42:17.928558: step: 300/1545, loss: 0.4708738327026367 2023-01-23 10:42:18.827596: step: 302/1545, loss: 0.11314406991004944 2023-01-23 10:42:19.686775: step: 304/1545, loss: 0.09104783087968826 2023-01-23 10:42:20.601788: step: 306/1545, loss: 0.05646038055419922 2023-01-23 10:42:21.476545: step: 308/1545, loss: 0.1852109432220459 2023-01-23 10:42:22.400466: step: 310/1545, loss: 0.17661908268928528 2023-01-23 10:42:23.335188: step: 312/1545, loss: 0.19350656867027283 2023-01-23 10:42:24.218434: step: 314/1545, loss: 0.10638198256492615 2023-01-23 10:42:25.097168: step: 316/1545, loss: 0.1463502198457718 2023-01-23 10:42:26.030492: step: 318/1545, loss: 0.060617510229349136 2023-01-23 10:42:26.884295: step: 320/1545, loss: 0.0933590829372406 2023-01-23 10:42:27.806474: step: 322/1545, loss: 0.15972751379013062 2023-01-23 10:42:28.690324: step: 324/1545, loss: 0.733714759349823 2023-01-23 10:42:29.590797: step: 326/1545, loss: 0.11651904881000519 2023-01-23 10:42:30.520235: step: 328/1545, loss: 1.2789543867111206 2023-01-23 10:42:31.378621: step: 330/1545, loss: 0.2359181046485901 2023-01-23 10:42:32.230266: step: 332/1545, loss: 0.02174401469528675 2023-01-23 10:42:33.096746: step: 334/1545, loss: 0.09448850899934769 2023-01-23 10:42:33.989482: step: 336/1545, loss: 0.10006482154130936 2023-01-23 10:42:34.859623: step: 338/1545, loss: 0.19002793729305267 2023-01-23 10:42:35.734635: step: 340/1545, loss: 0.03384484723210335 2023-01-23 10:42:36.588315: step: 342/1545, loss: 0.21503345668315887 2023-01-23 10:42:37.489020: step: 344/1545, loss: 0.036011066287755966 2023-01-23 10:42:38.382040: step: 346/1545, loss: 0.059810515493154526 2023-01-23 10:42:39.251902: step: 348/1545, loss: 0.03392203524708748 2023-01-23 10:42:40.119516: step: 350/1545, loss: 0.5676494836807251 2023-01-23 10:42:40.999204: step: 352/1545, loss: 0.22610054910182953 2023-01-23 10:42:41.850754: step: 354/1545, loss: 0.1757286638021469 2023-01-23 10:42:42.749576: step: 356/1545, loss: 0.04192151501774788 2023-01-23 10:42:43.663978: step: 358/1545, loss: 0.24393852055072784 2023-01-23 10:42:44.523886: step: 360/1545, loss: 0.03262175992131233 2023-01-23 10:42:45.463886: step: 362/1545, loss: 0.2274034470319748 2023-01-23 10:42:46.349358: step: 364/1545, loss: 0.01729390397667885 2023-01-23 10:42:47.290218: step: 366/1545, loss: 0.1838994324207306 2023-01-23 10:42:48.199510: step: 368/1545, loss: 0.6063197255134583 2023-01-23 10:42:49.142927: step: 370/1545, loss: 0.058299798518419266 2023-01-23 10:42:50.048322: step: 372/1545, loss: 0.02866293303668499 2023-01-23 10:42:50.890042: step: 374/1545, loss: 0.092339888215065 2023-01-23 10:42:51.766956: step: 376/1545, loss: 0.047138430178165436 2023-01-23 10:42:52.648311: step: 378/1545, loss: 0.10874354094266891 2023-01-23 10:42:53.500185: step: 380/1545, loss: 0.044926613569259644 2023-01-23 10:42:54.348304: step: 382/1545, loss: 0.09318573772907257 2023-01-23 10:42:55.273502: step: 384/1545, loss: 0.12621060013771057 2023-01-23 10:42:56.189846: step: 386/1545, loss: 0.16553138196468353 2023-01-23 10:42:57.089334: step: 388/1545, loss: 0.004121578298509121 2023-01-23 10:42:58.014917: step: 390/1545, loss: 0.6949927806854248 2023-01-23 10:42:58.905022: step: 392/1545, loss: 0.06538782268762589 2023-01-23 10:42:59.795779: step: 394/1545, loss: 0.18357212841510773 2023-01-23 10:43:00.683725: step: 396/1545, loss: 0.15811029076576233 2023-01-23 10:43:01.622397: step: 398/1545, loss: 0.0998455360531807 2023-01-23 10:43:02.520398: step: 400/1545, loss: 0.024130893871188164 2023-01-23 10:43:03.447887: step: 402/1545, loss: 0.2001524418592453 2023-01-23 10:43:04.383496: step: 404/1545, loss: 0.47289425134658813 2023-01-23 10:43:05.271573: step: 406/1545, loss: 0.0882214605808258 2023-01-23 10:43:06.168170: step: 408/1545, loss: 0.05517994239926338 2023-01-23 10:43:07.036118: step: 410/1545, loss: 0.30135640501976013 2023-01-23 10:43:07.902726: step: 412/1545, loss: 0.019631385803222656 2023-01-23 10:43:08.784060: step: 414/1545, loss: 0.0240495465695858 2023-01-23 10:43:09.624303: step: 416/1545, loss: 0.2728230953216553 2023-01-23 10:43:10.532989: step: 418/1545, loss: 0.6037935018539429 2023-01-23 10:43:11.497816: step: 420/1545, loss: 0.14580033719539642 2023-01-23 10:43:12.385989: step: 422/1545, loss: 0.06904225051403046 2023-01-23 10:43:13.265839: step: 424/1545, loss: 0.2470163106918335 2023-01-23 10:43:14.157600: step: 426/1545, loss: 0.24551306664943695 2023-01-23 10:43:15.017830: step: 428/1545, loss: 0.24947912991046906 2023-01-23 10:43:15.911585: step: 430/1545, loss: 0.35105475783348083 2023-01-23 10:43:16.806437: step: 432/1545, loss: 0.5391350984573364 2023-01-23 10:43:17.674921: step: 434/1545, loss: 0.03825559839606285 2023-01-23 10:43:18.554181: step: 436/1545, loss: 0.1547735333442688 2023-01-23 10:43:19.471500: step: 438/1545, loss: 0.28802499175071716 2023-01-23 10:43:20.364100: step: 440/1545, loss: 0.2913253605365753 2023-01-23 10:43:21.233304: step: 442/1545, loss: 0.3705393373966217 2023-01-23 10:43:22.152209: step: 444/1545, loss: 0.5728766918182373 2023-01-23 10:43:23.034370: step: 446/1545, loss: 0.19334280490875244 2023-01-23 10:43:23.939458: step: 448/1545, loss: 0.05162042751908302 2023-01-23 10:43:24.875955: step: 450/1545, loss: 0.07989327609539032 2023-01-23 10:43:25.730445: step: 452/1545, loss: 0.13558541238307953 2023-01-23 10:43:26.645244: step: 454/1545, loss: 0.12437885254621506 2023-01-23 10:43:27.522481: step: 456/1545, loss: 0.09185931086540222 2023-01-23 10:43:28.401130: step: 458/1545, loss: 0.1697617918252945 2023-01-23 10:43:29.286808: step: 460/1545, loss: 0.061147116124629974 2023-01-23 10:43:30.142514: step: 462/1545, loss: 0.01565389335155487 2023-01-23 10:43:31.006738: step: 464/1545, loss: 0.09145089983940125 2023-01-23 10:43:31.869935: step: 466/1545, loss: 0.12153708934783936 2023-01-23 10:43:32.734818: step: 468/1545, loss: 0.15150269865989685 2023-01-23 10:43:33.633678: step: 470/1545, loss: 0.07266850769519806 2023-01-23 10:43:34.511975: step: 472/1545, loss: 0.6580782532691956 2023-01-23 10:43:35.395480: step: 474/1545, loss: 0.25904369354248047 2023-01-23 10:43:36.254347: step: 476/1545, loss: 0.04054490849375725 2023-01-23 10:43:37.156679: step: 478/1545, loss: 0.12943370640277863 2023-01-23 10:43:38.068685: step: 480/1545, loss: 0.07216274738311768 2023-01-23 10:43:38.968163: step: 482/1545, loss: 0.03330943360924721 2023-01-23 10:43:39.878341: step: 484/1545, loss: 0.11115116626024246 2023-01-23 10:43:40.741007: step: 486/1545, loss: 0.018685804679989815 2023-01-23 10:43:41.620816: step: 488/1545, loss: 0.12153179198503494 2023-01-23 10:43:42.497681: step: 490/1545, loss: 0.1092318445444107 2023-01-23 10:43:43.356565: step: 492/1545, loss: 0.1562870442867279 2023-01-23 10:43:44.238888: step: 494/1545, loss: 0.22328130900859833 2023-01-23 10:43:45.136195: step: 496/1545, loss: 0.02652183175086975 2023-01-23 10:43:46.004942: step: 498/1545, loss: 0.05847034603357315 2023-01-23 10:43:46.845074: step: 500/1545, loss: 0.06666114181280136 2023-01-23 10:43:47.786729: step: 502/1545, loss: 0.10279010981321335 2023-01-23 10:43:48.619260: step: 504/1545, loss: 0.9375239610671997 2023-01-23 10:43:49.515104: step: 506/1545, loss: 0.02492539957165718 2023-01-23 10:43:50.363783: step: 508/1545, loss: 0.2664085030555725 2023-01-23 10:43:51.274285: step: 510/1545, loss: 0.26060226559638977 2023-01-23 10:43:52.173605: step: 512/1545, loss: 0.017760541290044785 2023-01-23 10:43:53.020248: step: 514/1545, loss: 0.06908965110778809 2023-01-23 10:43:53.910391: step: 516/1545, loss: 0.028562389314174652 2023-01-23 10:43:54.766740: step: 518/1545, loss: 0.09925144165754318 2023-01-23 10:43:55.614112: step: 520/1545, loss: 0.02343660779297352 2023-01-23 10:43:56.491199: step: 522/1545, loss: 0.26583194732666016 2023-01-23 10:43:57.414308: step: 524/1545, loss: 0.08280736207962036 2023-01-23 10:43:58.267853: step: 526/1545, loss: 0.19308391213417053 2023-01-23 10:43:59.135657: step: 528/1545, loss: 0.18016482889652252 2023-01-23 10:44:00.050970: step: 530/1545, loss: 0.03882424160838127 2023-01-23 10:44:00.944613: step: 532/1545, loss: 0.6090295314788818 2023-01-23 10:44:01.845860: step: 534/1545, loss: 0.15878212451934814 2023-01-23 10:44:02.760960: step: 536/1545, loss: 0.3151499927043915 2023-01-23 10:44:03.605100: step: 538/1545, loss: 0.49422168731689453 2023-01-23 10:44:04.503377: step: 540/1545, loss: 0.21158988773822784 2023-01-23 10:44:05.354234: step: 542/1545, loss: 0.17159491777420044 2023-01-23 10:44:06.234507: step: 544/1545, loss: 0.02758614346385002 2023-01-23 10:44:07.142182: step: 546/1545, loss: 0.11956464499235153 2023-01-23 10:44:08.009649: step: 548/1545, loss: 0.13330985605716705 2023-01-23 10:44:08.897549: step: 550/1545, loss: 0.34723129868507385 2023-01-23 10:44:09.780945: step: 552/1545, loss: 0.11084771156311035 2023-01-23 10:44:10.626657: step: 554/1545, loss: 0.11203928291797638 2023-01-23 10:44:11.473891: step: 556/1545, loss: 0.7721484899520874 2023-01-23 10:44:12.367616: step: 558/1545, loss: 0.2997151017189026 2023-01-23 10:44:13.222200: step: 560/1545, loss: 0.15303918719291687 2023-01-23 10:44:14.097033: step: 562/1545, loss: 0.6599956154823303 2023-01-23 10:44:14.967821: step: 564/1545, loss: 0.1825283169746399 2023-01-23 10:44:15.879237: step: 566/1545, loss: 0.15262308716773987 2023-01-23 10:44:16.772212: step: 568/1545, loss: 0.11109761148691177 2023-01-23 10:44:17.663395: step: 570/1545, loss: 0.039257220923900604 2023-01-23 10:44:18.544614: step: 572/1545, loss: 0.5962992310523987 2023-01-23 10:44:19.428053: step: 574/1545, loss: 0.21319089829921722 2023-01-23 10:44:20.268016: step: 576/1545, loss: 0.021264100447297096 2023-01-23 10:44:21.138195: step: 578/1545, loss: 0.1734010875225067 2023-01-23 10:44:22.016982: step: 580/1545, loss: 0.29048389196395874 2023-01-23 10:44:22.910794: step: 582/1545, loss: 0.09185294061899185 2023-01-23 10:44:23.781362: step: 584/1545, loss: 0.22239090502262115 2023-01-23 10:44:24.671583: step: 586/1545, loss: 0.33425524830818176 2023-01-23 10:44:25.546069: step: 588/1545, loss: 0.08489878475666046 2023-01-23 10:44:26.435498: step: 590/1545, loss: 0.2891117334365845 2023-01-23 10:44:27.340424: step: 592/1545, loss: 0.6069730520248413 2023-01-23 10:44:28.251653: step: 594/1545, loss: 0.36139360070228577 2023-01-23 10:44:29.104977: step: 596/1545, loss: 2.265172004699707 2023-01-23 10:44:29.962816: step: 598/1545, loss: 0.043998777866363525 2023-01-23 10:44:30.801749: step: 600/1545, loss: 0.054083894938230515 2023-01-23 10:44:31.719404: step: 602/1545, loss: 0.12227029353380203 2023-01-23 10:44:32.590490: step: 604/1545, loss: 0.08767030388116837 2023-01-23 10:44:33.566315: step: 606/1545, loss: 0.3089577853679657 2023-01-23 10:44:34.456539: step: 608/1545, loss: 0.14768391847610474 2023-01-23 10:44:35.371932: step: 610/1545, loss: 0.33251914381980896 2023-01-23 10:44:36.254142: step: 612/1545, loss: 0.06612774729728699 2023-01-23 10:44:37.115325: step: 614/1545, loss: 0.034049563109874725 2023-01-23 10:44:37.979287: step: 616/1545, loss: 0.495789110660553 2023-01-23 10:44:38.805257: step: 618/1545, loss: 0.44784554839134216 2023-01-23 10:44:39.690328: step: 620/1545, loss: 0.9288913011550903 2023-01-23 10:44:40.620143: step: 622/1545, loss: 0.23110753297805786 2023-01-23 10:44:41.487141: step: 624/1545, loss: 0.5966107249259949 2023-01-23 10:44:42.356320: step: 626/1545, loss: 0.4674954414367676 2023-01-23 10:44:43.193052: step: 628/1545, loss: 0.1902688443660736 2023-01-23 10:44:44.054051: step: 630/1545, loss: 0.21246401965618134 2023-01-23 10:44:44.955564: step: 632/1545, loss: 0.1712322235107422 2023-01-23 10:44:45.826169: step: 634/1545, loss: 0.14161503314971924 2023-01-23 10:44:46.695261: step: 636/1545, loss: 0.12256073206663132 2023-01-23 10:44:47.598745: step: 638/1545, loss: 0.06725777685642242 2023-01-23 10:44:48.511768: step: 640/1545, loss: 0.10898817330598831 2023-01-23 10:44:49.396538: step: 642/1545, loss: 0.17096753418445587 2023-01-23 10:44:50.279929: step: 644/1545, loss: 0.11129222810268402 2023-01-23 10:44:51.183006: step: 646/1545, loss: 0.15610376000404358 2023-01-23 10:44:52.066994: step: 648/1545, loss: 0.05777014046907425 2023-01-23 10:44:52.975178: step: 650/1545, loss: 0.19117921590805054 2023-01-23 10:44:53.810893: step: 652/1545, loss: 0.0670681893825531 2023-01-23 10:44:54.708420: step: 654/1545, loss: 0.27320143580436707 2023-01-23 10:44:55.646705: step: 656/1545, loss: 0.10477243363857269 2023-01-23 10:44:56.520701: step: 658/1545, loss: 0.08180558681488037 2023-01-23 10:44:57.498253: step: 660/1545, loss: 0.021796852350234985 2023-01-23 10:44:58.378205: step: 662/1545, loss: 0.10340067744255066 2023-01-23 10:44:59.254369: step: 664/1545, loss: 0.21326744556427002 2023-01-23 10:45:00.119132: step: 666/1545, loss: 0.18201549351215363 2023-01-23 10:45:01.049910: step: 668/1545, loss: 0.05499117821455002 2023-01-23 10:45:01.950844: step: 670/1545, loss: 0.1735425889492035 2023-01-23 10:45:02.846949: step: 672/1545, loss: 0.0496370829641819 2023-01-23 10:45:03.717340: step: 674/1545, loss: 1.4268718957901 2023-01-23 10:45:04.593149: step: 676/1545, loss: 0.15397171676158905 2023-01-23 10:45:05.534847: step: 678/1545, loss: 0.07901658117771149 2023-01-23 10:45:06.447155: step: 680/1545, loss: 0.07057316601276398 2023-01-23 10:45:07.342123: step: 682/1545, loss: 0.19744133949279785 2023-01-23 10:45:08.209617: step: 684/1545, loss: 0.24916741251945496 2023-01-23 10:45:09.094724: step: 686/1545, loss: 0.026916222646832466 2023-01-23 10:45:10.034057: step: 688/1545, loss: 0.0515768826007843 2023-01-23 10:45:10.945212: step: 690/1545, loss: 0.07418452203273773 2023-01-23 10:45:11.831473: step: 692/1545, loss: 0.41043567657470703 2023-01-23 10:45:12.757200: step: 694/1545, loss: 0.15640348196029663 2023-01-23 10:45:13.655999: step: 696/1545, loss: 0.20983055233955383 2023-01-23 10:45:14.589345: step: 698/1545, loss: 0.2285514771938324 2023-01-23 10:45:15.470026: step: 700/1545, loss: 0.16815218329429626 2023-01-23 10:45:16.303054: step: 702/1545, loss: 0.046759478747844696 2023-01-23 10:45:17.180282: step: 704/1545, loss: 0.11611854285001755 2023-01-23 10:45:18.039745: step: 706/1545, loss: 0.08823790401220322 2023-01-23 10:45:18.890753: step: 708/1545, loss: 0.29789507389068604 2023-01-23 10:45:19.743970: step: 710/1545, loss: 0.061955951154232025 2023-01-23 10:45:20.611366: step: 712/1545, loss: 0.051693469285964966 2023-01-23 10:45:21.573036: step: 714/1545, loss: 0.31798887252807617 2023-01-23 10:45:22.468786: step: 716/1545, loss: 0.07502835243940353 2023-01-23 10:45:23.383424: step: 718/1545, loss: 0.37439587712287903 2023-01-23 10:45:24.231099: step: 720/1545, loss: 0.15720534324645996 2023-01-23 10:45:25.152112: step: 722/1545, loss: 0.6720844507217407 2023-01-23 10:45:26.119902: step: 724/1545, loss: 0.05822482332587242 2023-01-23 10:45:27.048536: step: 726/1545, loss: 0.16107118129730225 2023-01-23 10:45:27.914085: step: 728/1545, loss: 0.09209316968917847 2023-01-23 10:45:28.811394: step: 730/1545, loss: 0.07593747228384018 2023-01-23 10:45:29.705649: step: 732/1545, loss: 0.7805700302124023 2023-01-23 10:45:30.582964: step: 734/1545, loss: 0.7363200783729553 2023-01-23 10:45:31.410150: step: 736/1545, loss: 0.03789549320936203 2023-01-23 10:45:32.329785: step: 738/1545, loss: 0.07987383753061295 2023-01-23 10:45:33.243956: step: 740/1545, loss: 0.24356722831726074 2023-01-23 10:45:34.132607: step: 742/1545, loss: 0.10927072167396545 2023-01-23 10:45:35.044138: step: 744/1545, loss: 0.059417035430669785 2023-01-23 10:45:35.979634: step: 746/1545, loss: 0.812924325466156 2023-01-23 10:45:36.893162: step: 748/1545, loss: 0.06956075876951218 2023-01-23 10:45:37.746721: step: 750/1545, loss: 0.395862877368927 2023-01-23 10:45:38.628292: step: 752/1545, loss: 0.007404631469398737 2023-01-23 10:45:39.491191: step: 754/1545, loss: 0.07717002928256989 2023-01-23 10:45:40.464080: step: 756/1545, loss: 0.10830237716436386 2023-01-23 10:45:41.349185: step: 758/1545, loss: 0.003418874694034457 2023-01-23 10:45:42.217211: step: 760/1545, loss: 0.021999798715114594 2023-01-23 10:45:43.063082: step: 762/1545, loss: 0.12128666788339615 2023-01-23 10:45:43.917463: step: 764/1545, loss: 0.01986837200820446 2023-01-23 10:45:44.801354: step: 766/1545, loss: 0.10715574771165848 2023-01-23 10:45:45.668214: step: 768/1545, loss: 0.08481615036725998 2023-01-23 10:45:46.527612: step: 770/1545, loss: 0.09584704041481018 2023-01-23 10:45:47.404776: step: 772/1545, loss: 0.4253103733062744 2023-01-23 10:45:48.326569: step: 774/1545, loss: 0.021926404908299446 2023-01-23 10:45:49.321626: step: 776/1545, loss: 0.019756939262151718 2023-01-23 10:45:50.208025: step: 778/1545, loss: 0.06451843678951263 2023-01-23 10:45:51.071402: step: 780/1545, loss: 4.747983455657959 2023-01-23 10:45:51.960816: step: 782/1545, loss: 0.042641934007406235 2023-01-23 10:45:52.813932: step: 784/1545, loss: 0.05323838070034981 2023-01-23 10:45:53.647274: step: 786/1545, loss: 0.04383375495672226 2023-01-23 10:45:54.483539: step: 788/1545, loss: 0.015425434336066246 2023-01-23 10:45:55.342826: step: 790/1545, loss: 0.08230629563331604 2023-01-23 10:45:56.237934: step: 792/1545, loss: 0.17630696296691895 2023-01-23 10:45:57.093998: step: 794/1545, loss: 0.16928468644618988 2023-01-23 10:45:58.005625: step: 796/1545, loss: 0.04056607559323311 2023-01-23 10:45:58.897624: step: 798/1545, loss: 0.0402052216231823 2023-01-23 10:45:59.753376: step: 800/1545, loss: 0.37685367465019226 2023-01-23 10:46:00.650672: step: 802/1545, loss: 0.6025742888450623 2023-01-23 10:46:01.537364: step: 804/1545, loss: 0.02636805921792984 2023-01-23 10:46:02.456502: step: 806/1545, loss: 0.15755142271518707 2023-01-23 10:46:03.344116: step: 808/1545, loss: 0.05231111869215965 2023-01-23 10:46:04.230583: step: 810/1545, loss: 0.19225618243217468 2023-01-23 10:46:05.140681: step: 812/1545, loss: 0.03625142574310303 2023-01-23 10:46:06.040761: step: 814/1545, loss: 0.29920318722724915 2023-01-23 10:46:06.911571: step: 816/1545, loss: 0.627677321434021 2023-01-23 10:46:07.815695: step: 818/1545, loss: 0.13222748041152954 2023-01-23 10:46:08.713020: step: 820/1545, loss: 0.07632468640804291 2023-01-23 10:46:09.628049: step: 822/1545, loss: 0.12949685752391815 2023-01-23 10:46:10.524527: step: 824/1545, loss: 0.25713109970092773 2023-01-23 10:46:11.390439: step: 826/1545, loss: 0.24837294220924377 2023-01-23 10:46:12.365092: step: 828/1545, loss: 0.3873412609100342 2023-01-23 10:46:13.251942: step: 830/1545, loss: 0.24217084050178528 2023-01-23 10:46:14.158325: step: 832/1545, loss: 0.3259783983230591 2023-01-23 10:46:15.041092: step: 834/1545, loss: 0.09939302504062653 2023-01-23 10:46:15.961094: step: 836/1545, loss: 0.4193718433380127 2023-01-23 10:46:16.871483: step: 838/1545, loss: 0.7762535810470581 2023-01-23 10:46:17.762887: step: 840/1545, loss: 0.27322691679000854 2023-01-23 10:46:18.677375: step: 842/1545, loss: 0.5366849303245544 2023-01-23 10:46:19.543680: step: 844/1545, loss: 1.029628038406372 2023-01-23 10:46:20.401619: step: 846/1545, loss: 0.36609894037246704 2023-01-23 10:46:21.247430: step: 848/1545, loss: 0.028463270515203476 2023-01-23 10:46:22.098945: step: 850/1545, loss: 0.054565440863370895 2023-01-23 10:46:22.964335: step: 852/1545, loss: 0.08880956470966339 2023-01-23 10:46:23.849805: step: 854/1545, loss: 0.07153777033090591 2023-01-23 10:46:24.764332: step: 856/1545, loss: 0.11482289433479309 2023-01-23 10:46:25.623957: step: 858/1545, loss: 0.13349227607250214 2023-01-23 10:46:26.534689: step: 860/1545, loss: 0.021728109568357468 2023-01-23 10:46:27.406724: step: 862/1545, loss: 0.11281432956457138 2023-01-23 10:46:28.301936: step: 864/1545, loss: 0.0550556443631649 2023-01-23 10:46:29.165254: step: 866/1545, loss: 0.1450781226158142 2023-01-23 10:46:30.156835: step: 868/1545, loss: 0.2986937463283539 2023-01-23 10:46:31.118588: step: 870/1545, loss: 0.09298703074455261 2023-01-23 10:46:32.010533: step: 872/1545, loss: 0.20472906529903412 2023-01-23 10:46:32.909888: step: 874/1545, loss: 0.06689397990703583 2023-01-23 10:46:33.827065: step: 876/1545, loss: 0.3158801198005676 2023-01-23 10:46:34.787259: step: 878/1545, loss: 0.1106848493218422 2023-01-23 10:46:35.688295: step: 880/1545, loss: 0.4899005591869354 2023-01-23 10:46:36.643367: step: 882/1545, loss: 0.05152769014239311 2023-01-23 10:46:37.599989: step: 884/1545, loss: 0.023361552506685257 2023-01-23 10:46:38.553326: step: 886/1545, loss: 0.1705232560634613 2023-01-23 10:46:39.420978: step: 888/1545, loss: 1.1213105916976929 2023-01-23 10:46:40.303644: step: 890/1545, loss: 0.0871860608458519 2023-01-23 10:46:41.234792: step: 892/1545, loss: 0.028020456433296204 2023-01-23 10:46:42.140206: step: 894/1545, loss: 0.11947396397590637 2023-01-23 10:46:43.067902: step: 896/1545, loss: 0.15546809136867523 2023-01-23 10:46:43.955934: step: 898/1545, loss: 0.022138306871056557 2023-01-23 10:46:44.856972: step: 900/1545, loss: 0.02166057378053665 2023-01-23 10:46:45.773346: step: 902/1545, loss: 0.23811285197734833 2023-01-23 10:46:46.631163: step: 904/1545, loss: 0.13568708300590515 2023-01-23 10:46:47.480053: step: 906/1545, loss: 0.36634561419487 2023-01-23 10:46:48.339575: step: 908/1545, loss: 0.22666490077972412 2023-01-23 10:46:49.180983: step: 910/1545, loss: 0.021555637940764427 2023-01-23 10:46:50.091534: step: 912/1545, loss: 0.22730296850204468 2023-01-23 10:46:50.924486: step: 914/1545, loss: 0.005661219358444214 2023-01-23 10:46:51.831320: step: 916/1545, loss: 0.14670294523239136 2023-01-23 10:46:52.710878: step: 918/1545, loss: 0.0899505466222763 2023-01-23 10:46:53.570850: step: 920/1545, loss: 0.1664920151233673 2023-01-23 10:46:54.456662: step: 922/1545, loss: 1.081982135772705 2023-01-23 10:46:55.320068: step: 924/1545, loss: 0.12820746004581451 2023-01-23 10:46:56.191837: step: 926/1545, loss: 0.014747636392712593 2023-01-23 10:46:57.143323: step: 928/1545, loss: 0.15795037150382996 2023-01-23 10:46:57.989150: step: 930/1545, loss: 0.3090760111808777 2023-01-23 10:46:58.864839: step: 932/1545, loss: 0.07717663049697876 2023-01-23 10:46:59.706594: step: 934/1545, loss: 0.1972779929637909 2023-01-23 10:47:00.579099: step: 936/1545, loss: 0.2324075549840927 2023-01-23 10:47:01.432529: step: 938/1545, loss: 0.10829249024391174 2023-01-23 10:47:02.292537: step: 940/1545, loss: 0.020682236179709435 2023-01-23 10:47:03.138168: step: 942/1545, loss: 0.006150990258902311 2023-01-23 10:47:04.004940: step: 944/1545, loss: 0.050024569034576416 2023-01-23 10:47:04.868749: step: 946/1545, loss: 0.15452300012111664 2023-01-23 10:47:05.744249: step: 948/1545, loss: 0.08003779500722885 2023-01-23 10:47:06.610395: step: 950/1545, loss: 0.7623299956321716 2023-01-23 10:47:07.460927: step: 952/1545, loss: 0.4763824939727783 2023-01-23 10:47:08.343564: step: 954/1545, loss: 0.04511499032378197 2023-01-23 10:47:09.233125: step: 956/1545, loss: 0.12039642781019211 2023-01-23 10:47:10.144519: step: 958/1545, loss: 0.597996711730957 2023-01-23 10:47:11.025728: step: 960/1545, loss: 0.2871462106704712 2023-01-23 10:47:11.892196: step: 962/1545, loss: 0.0565854050219059 2023-01-23 10:47:12.782559: step: 964/1545, loss: 0.08328259736299515 2023-01-23 10:47:13.677903: step: 966/1545, loss: 0.12707391381263733 2023-01-23 10:47:14.531305: step: 968/1545, loss: 0.031802766025066376 2023-01-23 10:47:15.424536: step: 970/1545, loss: 0.0977935940027237 2023-01-23 10:47:16.297276: step: 972/1545, loss: 0.5861715078353882 2023-01-23 10:47:17.170167: step: 974/1545, loss: 0.020538080483675003 2023-01-23 10:47:18.122504: step: 976/1545, loss: 0.0256073996424675 2023-01-23 10:47:19.032054: step: 978/1545, loss: 0.030265195295214653 2023-01-23 10:47:19.932294: step: 980/1545, loss: 0.02833118475973606 2023-01-23 10:47:20.817002: step: 982/1545, loss: 0.006426076404750347 2023-01-23 10:47:21.707575: step: 984/1545, loss: 0.10639692842960358 2023-01-23 10:47:22.571071: step: 986/1545, loss: 0.12373357266187668 2023-01-23 10:47:23.460351: step: 988/1545, loss: 0.14158575236797333 2023-01-23 10:47:24.365063: step: 990/1545, loss: 0.045699410140514374 2023-01-23 10:47:25.260629: step: 992/1545, loss: 0.033705491572618484 2023-01-23 10:47:26.140437: step: 994/1545, loss: 0.6520119905471802 2023-01-23 10:47:27.044876: step: 996/1545, loss: 0.6738756895065308 2023-01-23 10:47:27.904721: step: 998/1545, loss: 0.01406482607126236 2023-01-23 10:47:28.780513: step: 1000/1545, loss: 0.21043798327445984 2023-01-23 10:47:29.656864: step: 1002/1545, loss: 0.014485495164990425 2023-01-23 10:47:30.543030: step: 1004/1545, loss: 0.3839234709739685 2023-01-23 10:47:31.421572: step: 1006/1545, loss: 0.14583376049995422 2023-01-23 10:47:32.285243: step: 1008/1545, loss: 0.1079716682434082 2023-01-23 10:47:33.139597: step: 1010/1545, loss: 0.05395532771945 2023-01-23 10:47:34.052863: step: 1012/1545, loss: 0.026852834969758987 2023-01-23 10:47:34.954690: step: 1014/1545, loss: 0.05409039556980133 2023-01-23 10:47:35.973163: step: 1016/1545, loss: 0.19685614109039307 2023-01-23 10:47:36.886364: step: 1018/1545, loss: 0.05186844244599342 2023-01-23 10:47:37.774161: step: 1020/1545, loss: 0.3345677852630615 2023-01-23 10:47:38.699041: step: 1022/1545, loss: 0.03182194009423256 2023-01-23 10:47:39.544482: step: 1024/1545, loss: 0.24594531953334808 2023-01-23 10:47:40.458214: step: 1026/1545, loss: 0.2753466069698334 2023-01-23 10:47:41.337872: step: 1028/1545, loss: 0.04109932854771614 2023-01-23 10:47:42.246199: step: 1030/1545, loss: 0.3523411154747009 2023-01-23 10:47:43.115939: step: 1032/1545, loss: 0.254260390996933 2023-01-23 10:47:44.012155: step: 1034/1545, loss: 0.11975132673978806 2023-01-23 10:47:44.854194: step: 1036/1545, loss: 0.14844049513339996 2023-01-23 10:47:45.732459: step: 1038/1545, loss: 0.027651861310005188 2023-01-23 10:47:46.582976: step: 1040/1545, loss: 0.18921035528182983 2023-01-23 10:47:47.555231: step: 1042/1545, loss: 0.09766751527786255 2023-01-23 10:47:48.465491: step: 1044/1545, loss: 0.6173105239868164 2023-01-23 10:47:49.368869: step: 1046/1545, loss: 0.08030281960964203 2023-01-23 10:47:50.223999: step: 1048/1545, loss: 0.01785493642091751 2023-01-23 10:47:51.078697: step: 1050/1545, loss: 0.08068116009235382 2023-01-23 10:47:51.947706: step: 1052/1545, loss: 0.5443794131278992 2023-01-23 10:47:52.811059: step: 1054/1545, loss: 0.27141889929771423 2023-01-23 10:47:53.695749: step: 1056/1545, loss: 0.33908551931381226 2023-01-23 10:47:54.542174: step: 1058/1545, loss: 0.15063360333442688 2023-01-23 10:47:55.415245: step: 1060/1545, loss: 2.72711443901062 2023-01-23 10:47:56.273970: step: 1062/1545, loss: 0.0030742736998945475 2023-01-23 10:47:57.144540: step: 1064/1545, loss: 0.0592770017683506 2023-01-23 10:47:58.047909: step: 1066/1545, loss: 0.011605418287217617 2023-01-23 10:47:58.892502: step: 1068/1545, loss: 0.34896308183670044 2023-01-23 10:47:59.768833: step: 1070/1545, loss: 0.17551270127296448 2023-01-23 10:48:00.715146: step: 1072/1545, loss: 0.2983841001987457 2023-01-23 10:48:01.572031: step: 1074/1545, loss: 0.05249158293008804 2023-01-23 10:48:02.423186: step: 1076/1545, loss: 0.03222619742155075 2023-01-23 10:48:03.313870: step: 1078/1545, loss: 0.12470049411058426 2023-01-23 10:48:04.229421: step: 1080/1545, loss: 0.4940590262413025 2023-01-23 10:48:05.072217: step: 1082/1545, loss: 0.18256698548793793 2023-01-23 10:48:05.978645: step: 1084/1545, loss: 0.05369129404425621 2023-01-23 10:48:06.871749: step: 1086/1545, loss: 0.17916341125965118 2023-01-23 10:48:07.724008: step: 1088/1545, loss: 0.12296727299690247 2023-01-23 10:48:08.603905: step: 1090/1545, loss: 0.10964559018611908 2023-01-23 10:48:09.505272: step: 1092/1545, loss: 0.2777101695537567 2023-01-23 10:48:10.370143: step: 1094/1545, loss: 0.6299142241477966 2023-01-23 10:48:11.227962: step: 1096/1545, loss: 0.10368047654628754 2023-01-23 10:48:12.044738: step: 1098/1545, loss: 0.11502324044704437 2023-01-23 10:48:12.948964: step: 1100/1545, loss: 0.07662833482027054 2023-01-23 10:48:13.852135: step: 1102/1545, loss: 0.20932552218437195 2023-01-23 10:48:14.726258: step: 1104/1545, loss: 0.14579297602176666 2023-01-23 10:48:15.648015: step: 1106/1545, loss: 0.0977618396282196 2023-01-23 10:48:16.533800: step: 1108/1545, loss: 0.4984371066093445 2023-01-23 10:48:17.407325: step: 1110/1545, loss: 0.010507985949516296 2023-01-23 10:48:18.252703: step: 1112/1545, loss: 0.3699570298194885 2023-01-23 10:48:19.114005: step: 1114/1545, loss: 0.021586425602436066 2023-01-23 10:48:19.979270: step: 1116/1545, loss: 0.01787412166595459 2023-01-23 10:48:20.859045: step: 1118/1545, loss: 0.33368155360221863 2023-01-23 10:48:21.715570: step: 1120/1545, loss: 0.18297594785690308 2023-01-23 10:48:22.627528: step: 1122/1545, loss: 0.09074918925762177 2023-01-23 10:48:23.552467: step: 1124/1545, loss: 0.22395770251750946 2023-01-23 10:48:24.466916: step: 1126/1545, loss: 0.420682430267334 2023-01-23 10:48:25.380053: step: 1128/1545, loss: 0.14923939108848572 2023-01-23 10:48:26.277016: step: 1130/1545, loss: 0.1974366158246994 2023-01-23 10:48:27.178520: step: 1132/1545, loss: 0.1388818323612213 2023-01-23 10:48:28.041445: step: 1134/1545, loss: 0.12963835895061493 2023-01-23 10:48:28.893557: step: 1136/1545, loss: 0.12001348286867142 2023-01-23 10:48:29.760433: step: 1138/1545, loss: 0.09318520128726959 2023-01-23 10:48:30.615149: step: 1140/1545, loss: 0.01568232849240303 2023-01-23 10:48:31.517112: step: 1142/1545, loss: 2.2711119651794434 2023-01-23 10:48:32.431573: step: 1144/1545, loss: 0.15647399425506592 2023-01-23 10:48:33.312603: step: 1146/1545, loss: 0.4561799466609955 2023-01-23 10:48:34.231652: step: 1148/1545, loss: 0.18109014630317688 2023-01-23 10:48:35.115147: step: 1150/1545, loss: 0.4057160019874573 2023-01-23 10:48:36.016395: step: 1152/1545, loss: 0.09768715500831604 2023-01-23 10:48:36.909598: step: 1154/1545, loss: 0.13977159559726715 2023-01-23 10:48:37.765581: step: 1156/1545, loss: 0.8149703741073608 2023-01-23 10:48:38.662429: step: 1158/1545, loss: 0.049173954874277115 2023-01-23 10:48:39.517692: step: 1160/1545, loss: 0.6990249752998352 2023-01-23 10:48:40.396024: step: 1162/1545, loss: 0.9441866874694824 2023-01-23 10:48:41.282795: step: 1164/1545, loss: 0.27546870708465576 2023-01-23 10:48:42.191393: step: 1166/1545, loss: 0.1175830215215683 2023-01-23 10:48:43.033468: step: 1168/1545, loss: 0.035633303225040436 2023-01-23 10:48:43.882416: step: 1170/1545, loss: 0.08376729488372803 2023-01-23 10:48:44.770157: step: 1172/1545, loss: 0.0921168327331543 2023-01-23 10:48:45.620814: step: 1174/1545, loss: 0.012845954857766628 2023-01-23 10:48:46.486847: step: 1176/1545, loss: 0.08381951600313187 2023-01-23 10:48:47.359109: step: 1178/1545, loss: 0.06310522556304932 2023-01-23 10:48:48.232725: step: 1180/1545, loss: 0.42965424060821533 2023-01-23 10:48:49.144658: step: 1182/1545, loss: 0.1684338003396988 2023-01-23 10:48:49.999630: step: 1184/1545, loss: 0.20532989501953125 2023-01-23 10:48:50.863640: step: 1186/1545, loss: 0.041738785803318024 2023-01-23 10:48:51.746051: step: 1188/1545, loss: 0.21701954305171967 2023-01-23 10:48:52.630736: step: 1190/1545, loss: 0.13126249611377716 2023-01-23 10:48:53.501887: step: 1192/1545, loss: 0.08272882550954819 2023-01-23 10:48:54.426269: step: 1194/1545, loss: 0.10760984569787979 2023-01-23 10:48:55.296729: step: 1196/1545, loss: 0.30664438009262085 2023-01-23 10:48:56.218103: step: 1198/1545, loss: 0.02013891190290451 2023-01-23 10:48:57.104892: step: 1200/1545, loss: 0.3396497368812561 2023-01-23 10:48:58.009252: step: 1202/1545, loss: 0.046696800738573074 2023-01-23 10:48:58.942673: step: 1204/1545, loss: 0.09053434431552887 2023-01-23 10:48:59.806605: step: 1206/1545, loss: 0.2048947960138321 2023-01-23 10:49:00.714182: step: 1208/1545, loss: 0.038978420197963715 2023-01-23 10:49:01.629562: step: 1210/1545, loss: 0.11929744482040405 2023-01-23 10:49:02.544380: step: 1212/1545, loss: 0.3403880298137665 2023-01-23 10:49:03.419752: step: 1214/1545, loss: 0.024824582040309906 2023-01-23 10:49:04.278722: step: 1216/1545, loss: 0.06477256119251251 2023-01-23 10:49:05.135791: step: 1218/1545, loss: 0.06813871115446091 2023-01-23 10:49:05.973187: step: 1220/1545, loss: 0.1183391809463501 2023-01-23 10:49:06.836320: step: 1222/1545, loss: 0.15293149650096893 2023-01-23 10:49:07.695663: step: 1224/1545, loss: 0.10262683033943176 2023-01-23 10:49:08.585323: step: 1226/1545, loss: 0.2248912900686264 2023-01-23 10:49:09.445762: step: 1228/1545, loss: 0.1060650497674942 2023-01-23 10:49:10.359364: step: 1230/1545, loss: 0.00773539487272501 2023-01-23 10:49:11.232175: step: 1232/1545, loss: 0.19153887033462524 2023-01-23 10:49:12.109596: step: 1234/1545, loss: 0.11557233333587646 2023-01-23 10:49:12.957924: step: 1236/1545, loss: 0.023550527170300484 2023-01-23 10:49:13.823025: step: 1238/1545, loss: 0.033119894564151764 2023-01-23 10:49:14.689180: step: 1240/1545, loss: 0.41936635971069336 2023-01-23 10:49:15.558874: step: 1242/1545, loss: 0.15519081056118011 2023-01-23 10:49:16.522472: step: 1244/1545, loss: 0.2488207221031189 2023-01-23 10:49:17.387720: step: 1246/1545, loss: 0.0347001738846302 2023-01-23 10:49:18.270491: step: 1248/1545, loss: 0.006173140835016966 2023-01-23 10:49:19.139140: step: 1250/1545, loss: 0.051432110369205475 2023-01-23 10:49:19.982453: step: 1252/1545, loss: 0.11952049285173416 2023-01-23 10:49:20.861577: step: 1254/1545, loss: 0.04552818834781647 2023-01-23 10:49:21.751338: step: 1256/1545, loss: 0.14652687311172485 2023-01-23 10:49:22.592774: step: 1258/1545, loss: 0.01211837213486433 2023-01-23 10:49:23.562405: step: 1260/1545, loss: 0.052914343774318695 2023-01-23 10:49:24.461495: step: 1262/1545, loss: 0.24084565043449402 2023-01-23 10:49:25.325941: step: 1264/1545, loss: 0.01073424331843853 2023-01-23 10:49:26.177219: step: 1266/1545, loss: 0.14809854328632355 2023-01-23 10:49:27.030495: step: 1268/1545, loss: 0.012869241647422314 2023-01-23 10:49:27.894123: step: 1270/1545, loss: 0.11393636465072632 2023-01-23 10:49:28.746654: step: 1272/1545, loss: 0.14261001348495483 2023-01-23 10:49:29.604700: step: 1274/1545, loss: 0.05094063654541969 2023-01-23 10:49:30.454258: step: 1276/1545, loss: 0.01495719887316227 2023-01-23 10:49:31.406777: step: 1278/1545, loss: 0.005840167868882418 2023-01-23 10:49:32.313099: step: 1280/1545, loss: 0.3683263063430786 2023-01-23 10:49:33.270832: step: 1282/1545, loss: 0.11389447748661041 2023-01-23 10:49:34.163191: step: 1284/1545, loss: 0.08226615190505981 2023-01-23 10:49:35.058082: step: 1286/1545, loss: 0.5025759935379028 2023-01-23 10:49:35.935570: step: 1288/1545, loss: 0.022860713303089142 2023-01-23 10:49:36.832838: step: 1290/1545, loss: 0.12327791750431061 2023-01-23 10:49:37.694827: step: 1292/1545, loss: 0.039619628340005875 2023-01-23 10:49:38.573643: step: 1294/1545, loss: 0.1088523268699646 2023-01-23 10:49:39.460137: step: 1296/1545, loss: 0.0997895821928978 2023-01-23 10:49:40.338346: step: 1298/1545, loss: 0.39946138858795166 2023-01-23 10:49:41.200355: step: 1300/1545, loss: 0.347023069858551 2023-01-23 10:49:42.084773: step: 1302/1545, loss: 0.09310219436883926 2023-01-23 10:49:42.962255: step: 1304/1545, loss: 0.06930804997682571 2023-01-23 10:49:43.855944: step: 1306/1545, loss: 0.425446093082428 2023-01-23 10:49:44.737985: step: 1308/1545, loss: 0.001839558477513492 2023-01-23 10:49:45.597440: step: 1310/1545, loss: 1.0366687774658203 2023-01-23 10:49:46.576067: step: 1312/1545, loss: 2.1424596309661865 2023-01-23 10:49:47.421391: step: 1314/1545, loss: 0.17784839868545532 2023-01-23 10:49:48.270287: step: 1316/1545, loss: 0.23701287806034088 2023-01-23 10:49:49.132657: step: 1318/1545, loss: 0.2417774349451065 2023-01-23 10:49:49.986397: step: 1320/1545, loss: 0.11501295864582062 2023-01-23 10:49:50.868505: step: 1322/1545, loss: 0.12892040610313416 2023-01-23 10:49:51.738334: step: 1324/1545, loss: 0.10387277603149414 2023-01-23 10:49:52.586145: step: 1326/1545, loss: 0.21874754130840302 2023-01-23 10:49:53.480327: step: 1328/1545, loss: 0.16323967278003693 2023-01-23 10:49:54.357644: step: 1330/1545, loss: 0.29508739709854126 2023-01-23 10:49:55.260728: step: 1332/1545, loss: 0.10183871537446976 2023-01-23 10:49:56.118183: step: 1334/1545, loss: 0.07710304856300354 2023-01-23 10:49:56.965637: step: 1336/1545, loss: 0.09989860653877258 2023-01-23 10:49:57.803825: step: 1338/1545, loss: 0.2942432761192322 2023-01-23 10:49:58.682509: step: 1340/1545, loss: 0.03678811341524124 2023-01-23 10:49:59.531010: step: 1342/1545, loss: 0.12983979284763336 2023-01-23 10:50:00.381612: step: 1344/1545, loss: 0.07184762507677078 2023-01-23 10:50:01.273581: step: 1346/1545, loss: 0.16978873312473297 2023-01-23 10:50:02.130975: step: 1348/1545, loss: 0.14210255444049835 2023-01-23 10:50:02.978462: step: 1350/1545, loss: 0.0754556655883789 2023-01-23 10:50:03.865632: step: 1352/1545, loss: 0.029411043971776962 2023-01-23 10:50:04.778961: step: 1354/1545, loss: 0.055557459592819214 2023-01-23 10:50:05.691355: step: 1356/1545, loss: 0.1887856125831604 2023-01-23 10:50:06.606940: step: 1358/1545, loss: 0.3512841761112213 2023-01-23 10:50:07.491950: step: 1360/1545, loss: 0.14930610358715057 2023-01-23 10:50:08.395147: step: 1362/1545, loss: 0.028708379715681076 2023-01-23 10:50:09.357561: step: 1364/1545, loss: 0.36073485016822815 2023-01-23 10:50:10.249265: step: 1366/1545, loss: 0.09543167799711227 2023-01-23 10:50:11.136617: step: 1368/1545, loss: 0.024144142866134644 2023-01-23 10:50:12.007741: step: 1370/1545, loss: 0.5395368337631226 2023-01-23 10:50:12.924474: step: 1372/1545, loss: 0.3947713375091553 2023-01-23 10:50:13.776826: step: 1374/1545, loss: 0.0908321663737297 2023-01-23 10:50:14.645046: step: 1376/1545, loss: 0.052750878036022186 2023-01-23 10:50:15.506224: step: 1378/1545, loss: 0.12276726216077805 2023-01-23 10:50:16.348386: step: 1380/1545, loss: 0.002978372387588024 2023-01-23 10:50:17.223454: step: 1382/1545, loss: 0.24788810312747955 2023-01-23 10:50:18.164963: step: 1384/1545, loss: 0.1469326764345169 2023-01-23 10:50:19.038590: step: 1386/1545, loss: 0.2872702479362488 2023-01-23 10:50:19.927186: step: 1388/1545, loss: 0.06882841885089874 2023-01-23 10:50:20.814041: step: 1390/1545, loss: 0.12385180592536926 2023-01-23 10:50:21.662280: step: 1392/1545, loss: 0.23491494357585907 2023-01-23 10:50:22.514201: step: 1394/1545, loss: 0.42113032937049866 2023-01-23 10:50:23.381855: step: 1396/1545, loss: 0.07654958963394165 2023-01-23 10:50:24.240784: step: 1398/1545, loss: 0.11980531364679337 2023-01-23 10:50:25.115313: step: 1400/1545, loss: 0.5254432559013367 2023-01-23 10:50:26.020122: step: 1402/1545, loss: 0.1378765106201172 2023-01-23 10:50:26.920512: step: 1404/1545, loss: 0.05556077882647514 2023-01-23 10:50:27.766911: step: 1406/1545, loss: 0.36571204662323 2023-01-23 10:50:28.646819: step: 1408/1545, loss: 0.0334189236164093 2023-01-23 10:50:29.503308: step: 1410/1545, loss: 0.12204132229089737 2023-01-23 10:50:30.365234: step: 1412/1545, loss: 0.09203049540519714 2023-01-23 10:50:31.284662: step: 1414/1545, loss: 0.1252344250679016 2023-01-23 10:50:32.160059: step: 1416/1545, loss: 0.13003653287887573 2023-01-23 10:50:33.047684: step: 1418/1545, loss: 0.22474125027656555 2023-01-23 10:50:33.944992: step: 1420/1545, loss: 0.01897096447646618 2023-01-23 10:50:34.789657: step: 1422/1545, loss: 0.0892842710018158 2023-01-23 10:50:35.758745: step: 1424/1545, loss: 0.04727935418486595 2023-01-23 10:50:36.635203: step: 1426/1545, loss: 0.32467296719551086 2023-01-23 10:50:37.487255: step: 1428/1545, loss: 0.04111817851662636 2023-01-23 10:50:38.350710: step: 1430/1545, loss: 0.22757233679294586 2023-01-23 10:50:39.244425: step: 1432/1545, loss: 0.2553316652774811 2023-01-23 10:50:40.122100: step: 1434/1545, loss: 0.04287828132510185 2023-01-23 10:50:40.956485: step: 1436/1545, loss: 0.062034279108047485 2023-01-23 10:50:41.806541: step: 1438/1545, loss: 0.2297535091638565 2023-01-23 10:50:42.719476: step: 1440/1545, loss: 0.08686458319425583 2023-01-23 10:50:43.571199: step: 1442/1545, loss: 0.09960455447435379 2023-01-23 10:50:44.506340: step: 1444/1545, loss: 0.2364366501569748 2023-01-23 10:50:45.381099: step: 1446/1545, loss: 0.09104219079017639 2023-01-23 10:50:46.320394: step: 1448/1545, loss: 0.470257431268692 2023-01-23 10:50:47.158625: step: 1450/1545, loss: 0.016456130892038345 2023-01-23 10:50:48.030184: step: 1452/1545, loss: 0.3422631025314331 2023-01-23 10:50:48.916582: step: 1454/1545, loss: 0.29464900493621826 2023-01-23 10:50:49.806403: step: 1456/1545, loss: 0.18381644785404205 2023-01-23 10:50:50.657810: step: 1458/1545, loss: 0.09296223521232605 2023-01-23 10:50:51.596098: step: 1460/1545, loss: 0.38457736372947693 2023-01-23 10:50:52.458039: step: 1462/1545, loss: 0.23728379607200623 2023-01-23 10:50:53.330476: step: 1464/1545, loss: 0.18595421314239502 2023-01-23 10:50:54.211499: step: 1466/1545, loss: 0.024775460362434387 2023-01-23 10:50:55.116691: step: 1468/1545, loss: 0.15038222074508667 2023-01-23 10:50:56.025719: step: 1470/1545, loss: 0.006526385899633169 2023-01-23 10:50:56.885380: step: 1472/1545, loss: 0.08702627569437027 2023-01-23 10:50:57.766148: step: 1474/1545, loss: 0.024570053443312645 2023-01-23 10:50:58.684788: step: 1476/1545, loss: 0.19418881833553314 2023-01-23 10:50:59.564224: step: 1478/1545, loss: 0.38157376646995544 2023-01-23 10:51:00.533085: step: 1480/1545, loss: 0.02436145767569542 2023-01-23 10:51:01.446646: step: 1482/1545, loss: 0.04816872254014015 2023-01-23 10:51:02.316894: step: 1484/1545, loss: 0.010684576816856861 2023-01-23 10:51:03.189228: step: 1486/1545, loss: 0.0529177188873291 2023-01-23 10:51:04.030273: step: 1488/1545, loss: 0.119786337018013 2023-01-23 10:51:04.898739: step: 1490/1545, loss: 0.18613263964653015 2023-01-23 10:51:05.815992: step: 1492/1545, loss: 0.30136340856552124 2023-01-23 10:51:06.800048: step: 1494/1545, loss: 0.007642327807843685 2023-01-23 10:51:07.689347: step: 1496/1545, loss: 0.46340808272361755 2023-01-23 10:51:08.549487: step: 1498/1545, loss: 0.11896035075187683 2023-01-23 10:51:09.513114: step: 1500/1545, loss: 0.08694973587989807 2023-01-23 10:51:10.477006: step: 1502/1545, loss: 0.34978991746902466 2023-01-23 10:51:11.342528: step: 1504/1545, loss: 0.04841485247015953 2023-01-23 10:51:12.235823: step: 1506/1545, loss: 0.26419875025749207 2023-01-23 10:51:13.075620: step: 1508/1545, loss: 0.08722369372844696 2023-01-23 10:51:13.966252: step: 1510/1545, loss: 0.1340101808309555 2023-01-23 10:51:14.808644: step: 1512/1545, loss: 3.333409070968628 2023-01-23 10:51:15.669350: step: 1514/1545, loss: 0.12505179643630981 2023-01-23 10:51:16.537896: step: 1516/1545, loss: 2.504923105239868 2023-01-23 10:51:17.457049: step: 1518/1545, loss: 0.10223422199487686 2023-01-23 10:51:18.344981: step: 1520/1545, loss: 0.04593050107359886 2023-01-23 10:51:19.269498: step: 1522/1545, loss: 0.12314081192016602 2023-01-23 10:51:20.112588: step: 1524/1545, loss: 0.2120770812034607 2023-01-23 10:51:21.020340: step: 1526/1545, loss: 1.6681419610977173 2023-01-23 10:51:21.898772: step: 1528/1545, loss: 0.29684877395629883 2023-01-23 10:51:22.756709: step: 1530/1545, loss: 0.9238758683204651 2023-01-23 10:51:23.567140: step: 1532/1545, loss: 0.6579253673553467 2023-01-23 10:51:24.471493: step: 1534/1545, loss: 0.052818041294813156 2023-01-23 10:51:25.317061: step: 1536/1545, loss: 0.20075951516628265 2023-01-23 10:51:26.146637: step: 1538/1545, loss: 0.01794307306408882 2023-01-23 10:51:27.017345: step: 1540/1545, loss: 0.06526148319244385 2023-01-23 10:51:27.857931: step: 1542/1545, loss: 0.08330380916595459 2023-01-23 10:51:28.733495: step: 1544/1545, loss: 0.28306224942207336 2023-01-23 10:51:29.594886: step: 1546/1545, loss: 0.18895114958286285 2023-01-23 10:51:30.482286: step: 1548/1545, loss: 0.03424037992954254 2023-01-23 10:51:31.352243: step: 1550/1545, loss: 0.10241147875785828 2023-01-23 10:51:32.233772: step: 1552/1545, loss: 0.05070999637246132 2023-01-23 10:51:33.106057: step: 1554/1545, loss: 0.09096434712409973 2023-01-23 10:51:33.999747: step: 1556/1545, loss: 0.10389794409275055 2023-01-23 10:51:34.877165: step: 1558/1545, loss: 0.17336787283420563 2023-01-23 10:51:35.760423: step: 1560/1545, loss: 0.332508385181427 2023-01-23 10:51:36.608199: step: 1562/1545, loss: 0.14394895732402802 2023-01-23 10:51:37.494912: step: 1564/1545, loss: 0.02569602057337761 2023-01-23 10:51:38.336257: step: 1566/1545, loss: 0.19251421093940735 2023-01-23 10:51:39.195893: step: 1568/1545, loss: 0.006647496484220028 2023-01-23 10:51:40.041738: step: 1570/1545, loss: 0.026774663478136063 2023-01-23 10:51:40.932089: step: 1572/1545, loss: 0.1268036663532257 2023-01-23 10:51:41.786938: step: 1574/1545, loss: 0.046008653938770294 2023-01-23 10:51:42.660152: step: 1576/1545, loss: 0.5854476094245911 2023-01-23 10:51:43.545082: step: 1578/1545, loss: 0.0858207419514656 2023-01-23 10:51:44.465278: step: 1580/1545, loss: 0.06510494649410248 2023-01-23 10:51:45.356870: step: 1582/1545, loss: 1.4280290603637695 2023-01-23 10:51:46.232145: step: 1584/1545, loss: 0.09233391284942627 2023-01-23 10:51:47.109790: step: 1586/1545, loss: 0.036137502640485764 2023-01-23 10:51:47.968188: step: 1588/1545, loss: 1.4542837142944336 2023-01-23 10:51:48.873239: step: 1590/1545, loss: 0.26964741945266724 2023-01-23 10:51:49.807385: step: 1592/1545, loss: 0.023865748196840286 2023-01-23 10:51:50.734287: step: 1594/1545, loss: 0.40113991498947144 2023-01-23 10:51:51.609179: step: 1596/1545, loss: 0.30148470401763916 2023-01-23 10:51:52.499254: step: 1598/1545, loss: 0.17676803469657898 2023-01-23 10:51:53.359744: step: 1600/1545, loss: 0.2651788592338562 2023-01-23 10:51:54.217171: step: 1602/1545, loss: 0.1676502227783203 2023-01-23 10:51:55.060847: step: 1604/1545, loss: 0.1410423070192337 2023-01-23 10:51:55.935132: step: 1606/1545, loss: 0.04028482735157013 2023-01-23 10:51:56.850632: step: 1608/1545, loss: 0.017844555899500847 2023-01-23 10:51:57.713741: step: 1610/1545, loss: 0.19672904908657074 2023-01-23 10:51:58.570210: step: 1612/1545, loss: 0.17115241289138794 2023-01-23 10:51:59.442771: step: 1614/1545, loss: 0.10842551290988922 2023-01-23 10:52:00.336943: step: 1616/1545, loss: 0.15440435707569122 2023-01-23 10:52:01.264749: step: 1618/1545, loss: 0.06878197193145752 2023-01-23 10:52:02.105739: step: 1620/1545, loss: 0.2882252335548401 2023-01-23 10:52:02.990789: step: 1622/1545, loss: 0.644147515296936 2023-01-23 10:52:03.851648: step: 1624/1545, loss: 0.028622636571526527 2023-01-23 10:52:04.757944: step: 1626/1545, loss: 0.16467221081256866 2023-01-23 10:52:05.640438: step: 1628/1545, loss: 0.02514764294028282 2023-01-23 10:52:06.509525: step: 1630/1545, loss: 0.004993747919797897 2023-01-23 10:52:07.348222: step: 1632/1545, loss: 0.1378524750471115 2023-01-23 10:52:08.234510: step: 1634/1545, loss: 0.10259269177913666 2023-01-23 10:52:09.116628: step: 1636/1545, loss: 0.18845157325267792 2023-01-23 10:52:09.986392: step: 1638/1545, loss: 0.32731640338897705 2023-01-23 10:52:10.862939: step: 1640/1545, loss: 0.03369147330522537 2023-01-23 10:52:11.699629: step: 1642/1545, loss: 0.26694029569625854 2023-01-23 10:52:12.562707: step: 1644/1545, loss: 0.048107363283634186 2023-01-23 10:52:13.453262: step: 1646/1545, loss: 0.10517263412475586 2023-01-23 10:52:14.400895: step: 1648/1545, loss: 0.23087960481643677 2023-01-23 10:52:15.245252: step: 1650/1545, loss: 0.1140194684267044 2023-01-23 10:52:16.137263: step: 1652/1545, loss: 0.02246912382543087 2023-01-23 10:52:17.025072: step: 1654/1545, loss: 0.1744593381881714 2023-01-23 10:52:17.879415: step: 1656/1545, loss: 0.047598373144865036 2023-01-23 10:52:18.775799: step: 1658/1545, loss: 0.15949782729148865 2023-01-23 10:52:19.702869: step: 1660/1545, loss: 0.3526821732521057 2023-01-23 10:52:20.552648: step: 1662/1545, loss: 0.1079583466053009 2023-01-23 10:52:21.543508: step: 1664/1545, loss: 0.06058346852660179 2023-01-23 10:52:22.479587: step: 1666/1545, loss: 0.1460295021533966 2023-01-23 10:52:23.387177: step: 1668/1545, loss: 0.003273341804742813 2023-01-23 10:52:24.256389: step: 1670/1545, loss: 0.019816337153315544 2023-01-23 10:52:25.109805: step: 1672/1545, loss: 0.133244127035141 2023-01-23 10:52:25.932113: step: 1674/1545, loss: 0.1577533483505249 2023-01-23 10:52:26.824555: step: 1676/1545, loss: 0.0675070583820343 2023-01-23 10:52:27.716538: step: 1678/1545, loss: 0.11469486355781555 2023-01-23 10:52:28.641839: step: 1680/1545, loss: 0.35733747482299805 2023-01-23 10:52:29.481929: step: 1682/1545, loss: 0.9444344639778137 2023-01-23 10:52:30.363035: step: 1684/1545, loss: 0.35680729150772095 2023-01-23 10:52:31.234533: step: 1686/1545, loss: 0.03290446475148201 2023-01-23 10:52:32.120031: step: 1688/1545, loss: 0.03781856223940849 2023-01-23 10:52:32.991360: step: 1690/1545, loss: 0.4960143268108368 2023-01-23 10:52:33.905239: step: 1692/1545, loss: 0.05389027297496796 2023-01-23 10:52:34.791545: step: 1694/1545, loss: 0.007944798097014427 2023-01-23 10:52:35.678029: step: 1696/1545, loss: 0.3223969042301178 2023-01-23 10:52:36.574221: step: 1698/1545, loss: 0.5474286079406738 2023-01-23 10:52:37.432998: step: 1700/1545, loss: 0.20712143182754517 2023-01-23 10:52:38.441285: step: 1702/1545, loss: 0.9661803841590881 2023-01-23 10:52:39.360523: step: 1704/1545, loss: 0.3842148184776306 2023-01-23 10:52:40.211186: step: 1706/1545, loss: 0.09235967695713043 2023-01-23 10:52:41.064251: step: 1708/1545, loss: 0.1316673904657364 2023-01-23 10:52:42.001284: step: 1710/1545, loss: 0.22657307982444763 2023-01-23 10:52:42.873774: step: 1712/1545, loss: 0.14420509338378906 2023-01-23 10:52:43.746768: step: 1714/1545, loss: 0.14994020760059357 2023-01-23 10:52:44.591007: step: 1716/1545, loss: 0.265802800655365 2023-01-23 10:52:45.471035: step: 1718/1545, loss: 0.2888800799846649 2023-01-23 10:52:46.431916: step: 1720/1545, loss: 0.14080071449279785 2023-01-23 10:52:47.329611: step: 1722/1545, loss: 0.13027407228946686 2023-01-23 10:52:48.205078: step: 1724/1545, loss: 0.03475591167807579 2023-01-23 10:52:49.052363: step: 1726/1545, loss: 0.30767664313316345 2023-01-23 10:52:49.909613: step: 1728/1545, loss: 2.339498996734619 2023-01-23 10:52:50.773989: step: 1730/1545, loss: 0.45082277059555054 2023-01-23 10:52:51.639771: step: 1732/1545, loss: 0.04596323519945145 2023-01-23 10:52:52.534840: step: 1734/1545, loss: 0.0862942487001419 2023-01-23 10:52:53.428673: step: 1736/1545, loss: 0.13712294399738312 2023-01-23 10:52:54.278039: step: 1738/1545, loss: 0.6105416417121887 2023-01-23 10:52:55.223905: step: 1740/1545, loss: 0.20770448446273804 2023-01-23 10:52:56.108729: step: 1742/1545, loss: 0.5604795217514038 2023-01-23 10:52:56.985220: step: 1744/1545, loss: 0.1189456433057785 2023-01-23 10:52:57.888497: step: 1746/1545, loss: 0.24054411053657532 2023-01-23 10:52:58.753970: step: 1748/1545, loss: 0.12973640859127045 2023-01-23 10:52:59.691296: step: 1750/1545, loss: 0.18769632279872894 2023-01-23 10:53:00.596630: step: 1752/1545, loss: 0.05578475072979927 2023-01-23 10:53:01.430666: step: 1754/1545, loss: 0.2177894115447998 2023-01-23 10:53:02.406378: step: 1756/1545, loss: 0.20334909856319427 2023-01-23 10:53:03.294689: step: 1758/1545, loss: 0.4088483452796936 2023-01-23 10:53:04.133772: step: 1760/1545, loss: 0.03235188126564026 2023-01-23 10:53:05.036071: step: 1762/1545, loss: 0.21350222826004028 2023-01-23 10:53:05.941097: step: 1764/1545, loss: 0.24735018610954285 2023-01-23 10:53:06.791681: step: 1766/1545, loss: 0.049456387758255005 2023-01-23 10:53:07.662016: step: 1768/1545, loss: 0.3615403175354004 2023-01-23 10:53:08.573112: step: 1770/1545, loss: 0.027832727879285812 2023-01-23 10:53:09.458475: step: 1772/1545, loss: 0.5912564992904663 2023-01-23 10:53:10.346366: step: 1774/1545, loss: 0.04408779367804527 2023-01-23 10:53:11.212919: step: 1776/1545, loss: 0.3120920658111572 2023-01-23 10:53:12.080949: step: 1778/1545, loss: 0.01741122081875801 2023-01-23 10:53:12.985791: step: 1780/1545, loss: 0.0740959495306015 2023-01-23 10:53:13.880977: step: 1782/1545, loss: 0.02823742665350437 2023-01-23 10:53:14.774326: step: 1784/1545, loss: 0.10951659828424454 2023-01-23 10:53:15.647166: step: 1786/1545, loss: 0.0855918824672699 2023-01-23 10:53:16.517323: step: 1788/1545, loss: 0.14262385666370392 2023-01-23 10:53:17.349161: step: 1790/1545, loss: 0.16098296642303467 2023-01-23 10:53:18.269503: step: 1792/1545, loss: 0.06796704977750778 2023-01-23 10:53:19.145798: step: 1794/1545, loss: 0.04913291335105896 2023-01-23 10:53:20.020165: step: 1796/1545, loss: 0.30852019786834717 2023-01-23 10:53:20.863542: step: 1798/1545, loss: 0.14347071945667267 2023-01-23 10:53:21.776785: step: 1800/1545, loss: 0.15765511989593506 2023-01-23 10:53:22.640403: step: 1802/1545, loss: 0.09773958474397659 2023-01-23 10:53:23.513117: step: 1804/1545, loss: 0.22607512772083282 2023-01-23 10:53:24.417418: step: 1806/1545, loss: 0.08039455860853195 2023-01-23 10:53:25.358048: step: 1808/1545, loss: 0.14417630434036255 2023-01-23 10:53:26.192038: step: 1810/1545, loss: 0.4281651973724365 2023-01-23 10:53:27.070437: step: 1812/1545, loss: 0.01724288798868656 2023-01-23 10:53:27.941285: step: 1814/1545, loss: 0.025559157133102417 2023-01-23 10:53:28.834615: step: 1816/1545, loss: 0.29052653908729553 2023-01-23 10:53:29.676287: step: 1818/1545, loss: 0.10327082127332687 2023-01-23 10:53:30.543075: step: 1820/1545, loss: 0.1591634750366211 2023-01-23 10:53:31.407165: step: 1822/1545, loss: 0.060598086565732956 2023-01-23 10:53:32.430398: step: 1824/1545, loss: 0.4794832766056061 2023-01-23 10:53:33.275868: step: 1826/1545, loss: 0.6106585264205933 2023-01-23 10:53:34.117444: step: 1828/1545, loss: 0.015227708965539932 2023-01-23 10:53:35.016331: step: 1830/1545, loss: 0.07440082728862762 2023-01-23 10:53:35.917445: step: 1832/1545, loss: 0.07745897769927979 2023-01-23 10:53:36.865328: step: 1834/1545, loss: 0.04316175729036331 2023-01-23 10:53:37.768764: step: 1836/1545, loss: 0.19726380705833435 2023-01-23 10:53:38.646711: step: 1838/1545, loss: 0.4970238208770752 2023-01-23 10:53:39.576198: step: 1840/1545, loss: 0.16012929379940033 2023-01-23 10:53:40.518042: step: 1842/1545, loss: 0.24604284763336182 2023-01-23 10:53:41.449502: step: 1844/1545, loss: 0.2551649212837219 2023-01-23 10:53:42.299126: step: 1846/1545, loss: 0.12806515395641327 2023-01-23 10:53:43.217791: step: 1848/1545, loss: 0.07024385780096054 2023-01-23 10:53:44.085459: step: 1850/1545, loss: 0.4963791072368622 2023-01-23 10:53:44.925231: step: 1852/1545, loss: 0.14484739303588867 2023-01-23 10:53:45.820365: step: 1854/1545, loss: 0.08817173540592194 2023-01-23 10:53:46.739293: step: 1856/1545, loss: 0.1531466543674469 2023-01-23 10:53:47.587890: step: 1858/1545, loss: 0.06967775523662567 2023-01-23 10:53:48.450111: step: 1860/1545, loss: 0.05909954011440277 2023-01-23 10:53:49.315825: step: 1862/1545, loss: 0.06504201143980026 2023-01-23 10:53:50.177590: step: 1864/1545, loss: 0.1605861783027649 2023-01-23 10:53:51.030004: step: 1866/1545, loss: 0.07809390127658844 2023-01-23 10:53:51.908053: step: 1868/1545, loss: 0.16447727382183075 2023-01-23 10:53:52.796732: step: 1870/1545, loss: 0.12696005403995514 2023-01-23 10:53:53.630120: step: 1872/1545, loss: 0.06383437663316727 2023-01-23 10:53:54.475325: step: 1874/1545, loss: 0.03692580386996269 2023-01-23 10:53:55.448274: step: 1876/1545, loss: 0.06753044575452805 2023-01-23 10:53:56.292834: step: 1878/1545, loss: 0.19959867000579834 2023-01-23 10:53:57.146717: step: 1880/1545, loss: 0.046173639595508575 2023-01-23 10:53:57.992325: step: 1882/1545, loss: 0.056989576667547226 2023-01-23 10:53:58.835262: step: 1884/1545, loss: 0.17223548889160156 2023-01-23 10:53:59.717856: step: 1886/1545, loss: 0.18487779796123505 2023-01-23 10:54:00.590129: step: 1888/1545, loss: 0.43625935912132263 2023-01-23 10:54:01.473046: step: 1890/1545, loss: 0.12927058339118958 2023-01-23 10:54:02.350462: step: 1892/1545, loss: 0.3004794418811798 2023-01-23 10:54:03.194689: step: 1894/1545, loss: 0.07368839532136917 2023-01-23 10:54:04.145068: step: 1896/1545, loss: 0.07328841835260391 2023-01-23 10:54:04.986792: step: 1898/1545, loss: 0.0717148408293724 2023-01-23 10:54:05.836298: step: 1900/1545, loss: 0.04994390159845352 2023-01-23 10:54:06.711360: step: 1902/1545, loss: 0.7104142308235168 2023-01-23 10:54:07.584012: step: 1904/1545, loss: 0.08754487335681915 2023-01-23 10:54:08.424933: step: 1906/1545, loss: 0.021734584122896194 2023-01-23 10:54:09.324335: step: 1908/1545, loss: 0.04481344297528267 2023-01-23 10:54:10.174420: step: 1910/1545, loss: 0.07562758028507233 2023-01-23 10:54:11.038879: step: 1912/1545, loss: 0.019743716344237328 2023-01-23 10:54:11.876714: step: 1914/1545, loss: 0.33550146222114563 2023-01-23 10:54:12.718117: step: 1916/1545, loss: 0.19596987962722778 2023-01-23 10:54:13.569153: step: 1918/1545, loss: 0.18561579287052155 2023-01-23 10:54:14.473140: step: 1920/1545, loss: 0.20048677921295166 2023-01-23 10:54:15.369044: step: 1922/1545, loss: 0.19895440340042114 2023-01-23 10:54:16.299405: step: 1924/1545, loss: 0.0133209228515625 2023-01-23 10:54:17.160911: step: 1926/1545, loss: 0.44495296478271484 2023-01-23 10:54:18.075064: step: 1928/1545, loss: 0.015463907271623611 2023-01-23 10:54:18.907284: step: 1930/1545, loss: 0.09995878487825394 2023-01-23 10:54:19.739648: step: 1932/1545, loss: 0.23601751029491425 2023-01-23 10:54:20.643320: step: 1934/1545, loss: 0.18249905109405518 2023-01-23 10:54:21.530222: step: 1936/1545, loss: 0.06647241860628128 2023-01-23 10:54:22.398339: step: 1938/1545, loss: 0.06053733453154564 2023-01-23 10:54:23.262472: step: 1940/1545, loss: 0.04492510110139847 2023-01-23 10:54:24.103152: step: 1942/1545, loss: 0.011475078761577606 2023-01-23 10:54:24.986356: step: 1944/1545, loss: 0.126685231924057 2023-01-23 10:54:25.844736: step: 1946/1545, loss: 0.45809224247932434 2023-01-23 10:54:26.825780: step: 1948/1545, loss: 0.0431797131896019 2023-01-23 10:54:27.698984: step: 1950/1545, loss: 1.2071200609207153 2023-01-23 10:54:28.559751: step: 1952/1545, loss: 0.059287820011377335 2023-01-23 10:54:29.441745: step: 1954/1545, loss: 0.22419388592243195 2023-01-23 10:54:30.401471: step: 1956/1545, loss: 0.14178341627120972 2023-01-23 10:54:31.330160: step: 1958/1545, loss: 0.17145003378391266 2023-01-23 10:54:32.208383: step: 1960/1545, loss: 0.08005154132843018 2023-01-23 10:54:33.060914: step: 1962/1545, loss: 0.06061055138707161 2023-01-23 10:54:33.984034: step: 1964/1545, loss: 0.21618425846099854 2023-01-23 10:54:34.880112: step: 1966/1545, loss: 0.1477632075548172 2023-01-23 10:54:35.750137: step: 1968/1545, loss: 0.3111944794654846 2023-01-23 10:54:36.630386: step: 1970/1545, loss: 0.22293312847614288 2023-01-23 10:54:37.608886: step: 1972/1545, loss: 0.3745018243789673 2023-01-23 10:54:38.485144: step: 1974/1545, loss: 0.06990665942430496 2023-01-23 10:54:39.366763: step: 1976/1545, loss: 0.21669843792915344 2023-01-23 10:54:40.282788: step: 1978/1545, loss: 0.11507657170295715 2023-01-23 10:54:41.138615: step: 1980/1545, loss: 1.8718138933181763 2023-01-23 10:54:42.008747: step: 1982/1545, loss: 0.1951746791601181 2023-01-23 10:54:42.871875: step: 1984/1545, loss: 0.09517177939414978 2023-01-23 10:54:43.764007: step: 1986/1545, loss: 0.152260884642601 2023-01-23 10:54:44.642174: step: 1988/1545, loss: 0.012943744659423828 2023-01-23 10:54:45.536495: step: 1990/1545, loss: 0.07315818220376968 2023-01-23 10:54:46.379868: step: 1992/1545, loss: 0.05441782623529434 2023-01-23 10:54:47.327097: step: 1994/1545, loss: 0.11333324015140533 2023-01-23 10:54:48.213152: step: 1996/1545, loss: 0.05122899264097214 2023-01-23 10:54:49.124533: step: 1998/1545, loss: 0.11342310905456543 2023-01-23 10:54:50.054287: step: 2000/1545, loss: 0.05336520075798035 2023-01-23 10:54:50.923018: step: 2002/1545, loss: 0.05646739900112152 2023-01-23 10:54:51.817867: step: 2004/1545, loss: 0.13228562474250793 2023-01-23 10:54:52.669650: step: 2006/1545, loss: 0.11237658560276031 2023-01-23 10:54:53.534609: step: 2008/1545, loss: 0.22734302282333374 2023-01-23 10:54:54.391320: step: 2010/1545, loss: 0.07779275625944138 2023-01-23 10:54:55.269691: step: 2012/1545, loss: 0.15461383759975433 2023-01-23 10:54:56.126793: step: 2014/1545, loss: 0.08453530818223953 2023-01-23 10:54:56.970112: step: 2016/1545, loss: 0.1060369536280632 2023-01-23 10:54:57.828871: step: 2018/1545, loss: 0.04731428623199463 2023-01-23 10:54:58.694918: step: 2020/1545, loss: 0.043986670672893524 2023-01-23 10:54:59.558398: step: 2022/1545, loss: 0.42879733443260193 2023-01-23 10:55:00.420808: step: 2024/1545, loss: 0.055999308824539185 2023-01-23 10:55:01.253466: step: 2026/1545, loss: 0.23977437615394592 2023-01-23 10:55:02.197686: step: 2028/1545, loss: 0.065322145819664 2023-01-23 10:55:03.228329: step: 2030/1545, loss: 0.021866051480174065 2023-01-23 10:55:04.100795: step: 2032/1545, loss: 0.21850471198558807 2023-01-23 10:55:05.015805: step: 2034/1545, loss: 0.28480732440948486 2023-01-23 10:55:05.920941: step: 2036/1545, loss: 0.27129969000816345 2023-01-23 10:55:06.775057: step: 2038/1545, loss: 0.07594038546085358 2023-01-23 10:55:07.652889: step: 2040/1545, loss: 0.03167295455932617 2023-01-23 10:55:08.561285: step: 2042/1545, loss: 0.6158677339553833 2023-01-23 10:55:09.433575: step: 2044/1545, loss: 0.06645409762859344 2023-01-23 10:55:10.294501: step: 2046/1545, loss: 0.01971299760043621 2023-01-23 10:55:11.122778: step: 2048/1545, loss: 0.225682333111763 2023-01-23 10:55:12.003534: step: 2050/1545, loss: 0.12692871689796448 2023-01-23 10:55:12.884401: step: 2052/1545, loss: 0.10831314325332642 2023-01-23 10:55:13.768671: step: 2054/1545, loss: 0.05212222412228584 2023-01-23 10:55:14.638695: step: 2056/1545, loss: 0.02896752953529358 2023-01-23 10:55:15.512849: step: 2058/1545, loss: 0.027855869382619858 2023-01-23 10:55:16.375647: step: 2060/1545, loss: 0.3993055820465088 2023-01-23 10:55:17.240894: step: 2062/1545, loss: 0.2326444387435913 2023-01-23 10:55:18.103296: step: 2064/1545, loss: 0.19672603905200958 2023-01-23 10:55:19.034376: step: 2066/1545, loss: 0.26658928394317627 2023-01-23 10:55:19.965285: step: 2068/1545, loss: 0.0246023777872324 2023-01-23 10:55:20.811726: step: 2070/1545, loss: 0.19133850932121277 2023-01-23 10:55:21.710860: step: 2072/1545, loss: 0.4009232223033905 2023-01-23 10:55:22.619969: step: 2074/1545, loss: 0.033971190452575684 2023-01-23 10:55:23.498279: step: 2076/1545, loss: 0.049572836607694626 2023-01-23 10:55:24.357961: step: 2078/1545, loss: 0.09451092779636383 2023-01-23 10:55:25.239613: step: 2080/1545, loss: 0.008934760466217995 2023-01-23 10:55:26.159688: step: 2082/1545, loss: 0.30696603655815125 2023-01-23 10:55:27.057142: step: 2084/1545, loss: 0.04343978688120842 2023-01-23 10:55:27.937034: step: 2086/1545, loss: 0.13464169204235077 2023-01-23 10:55:28.766594: step: 2088/1545, loss: 0.02756524831056595 2023-01-23 10:55:29.631788: step: 2090/1545, loss: 0.005307345185428858 2023-01-23 10:55:30.537504: step: 2092/1545, loss: 0.05066047981381416 2023-01-23 10:55:31.440890: step: 2094/1545, loss: 0.053066227585077286 2023-01-23 10:55:32.276742: step: 2096/1545, loss: 0.21209421753883362 2023-01-23 10:55:33.107600: step: 2098/1545, loss: 0.02653619460761547 2023-01-23 10:55:33.973059: step: 2100/1545, loss: 0.021103909239172935 2023-01-23 10:55:34.798775: step: 2102/1545, loss: 0.17339175939559937 2023-01-23 10:55:35.699382: step: 2104/1545, loss: 0.1239938735961914 2023-01-23 10:55:36.644021: step: 2106/1545, loss: 0.0829649418592453 2023-01-23 10:55:37.528503: step: 2108/1545, loss: 0.04712098464369774 2023-01-23 10:55:38.415636: step: 2110/1545, loss: 0.0876198559999466 2023-01-23 10:55:39.292181: step: 2112/1545, loss: 0.1963973045349121 2023-01-23 10:55:40.243289: step: 2114/1545, loss: 0.2523183226585388 2023-01-23 10:55:41.111224: step: 2116/1545, loss: 1.0216469764709473 2023-01-23 10:55:41.965034: step: 2118/1545, loss: 0.09656599909067154 2023-01-23 10:55:42.818595: step: 2120/1545, loss: 0.04162181168794632 2023-01-23 10:55:43.716174: step: 2122/1545, loss: 0.004020593129098415 2023-01-23 10:55:44.544890: step: 2124/1545, loss: 0.07621195912361145 2023-01-23 10:55:45.484735: step: 2126/1545, loss: 0.25383445620536804 2023-01-23 10:55:46.381213: step: 2128/1545, loss: 0.07027877867221832 2023-01-23 10:55:47.266406: step: 2130/1545, loss: 0.0415547713637352 2023-01-23 10:55:48.150192: step: 2132/1545, loss: 0.019768228754401207 2023-01-23 10:55:49.053124: step: 2134/1545, loss: 0.7608658075332642 2023-01-23 10:55:49.914285: step: 2136/1545, loss: 0.02044004574418068 2023-01-23 10:55:50.765444: step: 2138/1545, loss: 1.0136730670928955 2023-01-23 10:55:51.648810: step: 2140/1545, loss: 0.25707751512527466 2023-01-23 10:55:52.564420: step: 2142/1545, loss: 0.24301066994667053 2023-01-23 10:55:53.456543: step: 2144/1545, loss: 0.05567147582769394 2023-01-23 10:55:54.317754: step: 2146/1545, loss: 3.7207212448120117 2023-01-23 10:55:55.208741: step: 2148/1545, loss: 0.2668556571006775 2023-01-23 10:55:56.110612: step: 2150/1545, loss: 0.06980127841234207 2023-01-23 10:55:56.958708: step: 2152/1545, loss: 0.15736185014247894 2023-01-23 10:55:57.860481: step: 2154/1545, loss: 0.5853856801986694 2023-01-23 10:55:58.736480: step: 2156/1545, loss: 0.4238274097442627 2023-01-23 10:55:59.614015: step: 2158/1545, loss: 0.3244608938694 2023-01-23 10:56:00.505785: step: 2160/1545, loss: 0.16509640216827393 2023-01-23 10:56:01.410722: step: 2162/1545, loss: 0.17348524928092957 2023-01-23 10:56:02.301093: step: 2164/1545, loss: 0.20987266302108765 2023-01-23 10:56:03.172391: step: 2166/1545, loss: 0.13721878826618195 2023-01-23 10:56:04.063496: step: 2168/1545, loss: 0.028664885088801384 2023-01-23 10:56:04.932546: step: 2170/1545, loss: 0.03169791400432587 2023-01-23 10:56:05.790770: step: 2172/1545, loss: 0.02824264205992222 2023-01-23 10:56:06.681658: step: 2174/1545, loss: 0.3692040741443634 2023-01-23 10:56:07.589855: step: 2176/1545, loss: 0.10400136560201645 2023-01-23 10:56:08.474014: step: 2178/1545, loss: 0.0408191941678524 2023-01-23 10:56:09.356261: step: 2180/1545, loss: 0.009260366670787334 2023-01-23 10:56:10.263340: step: 2182/1545, loss: 0.23391826450824738 2023-01-23 10:56:11.135616: step: 2184/1545, loss: 0.35185739398002625 2023-01-23 10:56:12.060403: step: 2186/1545, loss: 0.06030428409576416 2023-01-23 10:56:12.942574: step: 2188/1545, loss: 0.035107873380184174 2023-01-23 10:56:13.854966: step: 2190/1545, loss: 0.09421141445636749 2023-01-23 10:56:14.725371: step: 2192/1545, loss: 0.01872287318110466 2023-01-23 10:56:15.635481: step: 2194/1545, loss: 0.20027391612529755 2023-01-23 10:56:16.503395: step: 2196/1545, loss: 0.18286164104938507 2023-01-23 10:56:17.360984: step: 2198/1545, loss: 0.5948849320411682 2023-01-23 10:56:18.248795: step: 2200/1545, loss: 0.16220398247241974 2023-01-23 10:56:19.110023: step: 2202/1545, loss: 0.16218477487564087 2023-01-23 10:56:19.979803: step: 2204/1545, loss: 0.19969366490840912 2023-01-23 10:56:20.848016: step: 2206/1545, loss: 0.11987358331680298 2023-01-23 10:56:21.734425: step: 2208/1545, loss: 0.30771404504776 2023-01-23 10:56:22.603542: step: 2210/1545, loss: 2.5216126441955566 2023-01-23 10:56:23.507675: step: 2212/1545, loss: 0.23353250324726105 2023-01-23 10:56:24.382207: step: 2214/1545, loss: 0.3412806987762451 2023-01-23 10:56:25.242887: step: 2216/1545, loss: 0.1609877049922943 2023-01-23 10:56:26.190322: step: 2218/1545, loss: 0.9568969011306763 2023-01-23 10:56:27.064511: step: 2220/1545, loss: 0.0554172620177269 2023-01-23 10:56:27.918655: step: 2222/1545, loss: 0.01363922655582428 2023-01-23 10:56:28.807055: step: 2224/1545, loss: 0.20660819113254547 2023-01-23 10:56:29.730378: step: 2226/1545, loss: 0.47240063548088074 2023-01-23 10:56:30.623121: step: 2228/1545, loss: 0.2713354527950287 2023-01-23 10:56:31.491852: step: 2230/1545, loss: 0.023172970861196518 2023-01-23 10:56:32.359189: step: 2232/1545, loss: 0.07455596327781677 2023-01-23 10:56:33.212007: step: 2234/1545, loss: 0.1279992163181305 2023-01-23 10:56:34.050427: step: 2236/1545, loss: 0.003999503329396248 2023-01-23 10:56:34.933260: step: 2238/1545, loss: 0.09700507670640945 2023-01-23 10:56:35.790481: step: 2240/1545, loss: 0.4847480058670044 2023-01-23 10:56:36.654627: step: 2242/1545, loss: 0.09611845016479492 2023-01-23 10:56:37.522349: step: 2244/1545, loss: 0.11109881848096848 2023-01-23 10:56:38.383415: step: 2246/1545, loss: 0.30831658840179443 2023-01-23 10:56:39.260779: step: 2248/1545, loss: 0.020742405205965042 2023-01-23 10:56:40.129098: step: 2250/1545, loss: 0.1166352778673172 2023-01-23 10:56:40.977699: step: 2252/1545, loss: 0.10257146507501602 2023-01-23 10:56:41.810248: step: 2254/1545, loss: 0.15653763711452484 2023-01-23 10:56:42.685421: step: 2256/1545, loss: 0.771988570690155 2023-01-23 10:56:43.537266: step: 2258/1545, loss: 0.042579539120197296 2023-01-23 10:56:44.400612: step: 2260/1545, loss: 0.18812887370586395 2023-01-23 10:56:45.262474: step: 2262/1545, loss: 0.07070037722587585 2023-01-23 10:56:46.141212: step: 2264/1545, loss: 0.1787072718143463 2023-01-23 10:56:46.986719: step: 2266/1545, loss: 0.10126897692680359 2023-01-23 10:56:47.883887: step: 2268/1545, loss: 0.1492457240819931 2023-01-23 10:56:48.722114: step: 2270/1545, loss: 0.09548220038414001 2023-01-23 10:56:49.624556: step: 2272/1545, loss: 0.05825010687112808 2023-01-23 10:56:50.480536: step: 2274/1545, loss: 0.010283847339451313 2023-01-23 10:56:51.369712: step: 2276/1545, loss: 0.031010879203677177 2023-01-23 10:56:52.263649: step: 2278/1545, loss: 0.029313888400793076 2023-01-23 10:56:53.162921: step: 2280/1545, loss: 0.058799196034669876 2023-01-23 10:56:54.035605: step: 2282/1545, loss: 0.09027199447154999 2023-01-23 10:56:54.954420: step: 2284/1545, loss: 0.143488347530365 2023-01-23 10:56:55.835034: step: 2286/1545, loss: 0.49149665236473083 2023-01-23 10:56:56.691837: step: 2288/1545, loss: 0.15203692018985748 2023-01-23 10:56:57.552357: step: 2290/1545, loss: 0.12348543107509613 2023-01-23 10:56:58.488600: step: 2292/1545, loss: 0.19893977046012878 2023-01-23 10:56:59.368669: step: 2294/1545, loss: 0.20746685564517975 2023-01-23 10:57:00.206477: step: 2296/1545, loss: 0.08251852542161942 2023-01-23 10:57:01.107743: step: 2298/1545, loss: 0.039269693195819855 2023-01-23 10:57:01.967829: step: 2300/1545, loss: 0.417495995759964 2023-01-23 10:57:02.842543: step: 2302/1545, loss: 0.07737669348716736 2023-01-23 10:57:03.673347: step: 2304/1545, loss: 0.041467826813459396 2023-01-23 10:57:04.596825: step: 2306/1545, loss: 0.03669990599155426 2023-01-23 10:57:05.522803: step: 2308/1545, loss: 0.11606460064649582 2023-01-23 10:57:06.352511: step: 2310/1545, loss: 0.6690393686294556 2023-01-23 10:57:07.195957: step: 2312/1545, loss: 0.6206034421920776 2023-01-23 10:57:08.094448: step: 2314/1545, loss: 0.21799519658088684 2023-01-23 10:57:08.927078: step: 2316/1545, loss: 0.007432656362652779 2023-01-23 10:57:09.847227: step: 2318/1545, loss: 0.38671261072158813 2023-01-23 10:57:10.735322: step: 2320/1545, loss: 0.09779118001461029 2023-01-23 10:57:11.612870: step: 2322/1545, loss: 0.13528607785701752 2023-01-23 10:57:12.452396: step: 2324/1545, loss: 0.5514011979103088 2023-01-23 10:57:13.322544: step: 2326/1545, loss: 0.08170479536056519 2023-01-23 10:57:14.187370: step: 2328/1545, loss: 0.35025614500045776 2023-01-23 10:57:15.052636: step: 2330/1545, loss: 0.058066364377737045 2023-01-23 10:57:15.897809: step: 2332/1545, loss: 0.5110107660293579 2023-01-23 10:57:16.807239: step: 2334/1545, loss: 0.3428419530391693 2023-01-23 10:57:17.672818: step: 2336/1545, loss: 0.2033497840166092 2023-01-23 10:57:18.557953: step: 2338/1545, loss: 0.04287150502204895 2023-01-23 10:57:19.439016: step: 2340/1545, loss: 0.1761319637298584 2023-01-23 10:57:20.279675: step: 2342/1545, loss: 0.030444864183664322 2023-01-23 10:57:21.137772: step: 2344/1545, loss: 0.06916683912277222 2023-01-23 10:57:21.992084: step: 2346/1545, loss: 0.07088036090135574 2023-01-23 10:57:22.888569: step: 2348/1545, loss: 0.4213440716266632 2023-01-23 10:57:23.794192: step: 2350/1545, loss: 0.10987069457769394 2023-01-23 10:57:24.646197: step: 2352/1545, loss: 0.012562771327793598 2023-01-23 10:57:25.549633: step: 2354/1545, loss: 0.04748089239001274 2023-01-23 10:57:26.486366: step: 2356/1545, loss: 0.064075767993927 2023-01-23 10:57:27.366500: step: 2358/1545, loss: 0.04255906492471695 2023-01-23 10:57:28.230277: step: 2360/1545, loss: 0.12511911988258362 2023-01-23 10:57:29.093538: step: 2362/1545, loss: 0.2915050685405731 2023-01-23 10:57:30.006310: step: 2364/1545, loss: 0.12310797721147537 2023-01-23 10:57:30.844889: step: 2366/1545, loss: 0.2519255578517914 2023-01-23 10:57:31.710963: step: 2368/1545, loss: 0.19691328704357147 2023-01-23 10:57:32.574710: step: 2370/1545, loss: 0.10745351761579514 2023-01-23 10:57:33.464005: step: 2372/1545, loss: 0.057093627750873566 2023-01-23 10:57:34.319106: step: 2374/1545, loss: 0.028881531208753586 2023-01-23 10:57:35.176612: step: 2376/1545, loss: 0.1638222336769104 2023-01-23 10:57:36.047261: step: 2378/1545, loss: 0.18761339783668518 2023-01-23 10:57:36.921495: step: 2380/1545, loss: 0.09167627990245819 2023-01-23 10:57:37.818826: step: 2382/1545, loss: 0.27029046416282654 2023-01-23 10:57:38.632799: step: 2384/1545, loss: 0.06447099894285202 2023-01-23 10:57:39.497737: step: 2386/1545, loss: 0.1567087024450302 2023-01-23 10:57:40.355785: step: 2388/1545, loss: 0.22515563666820526 2023-01-23 10:57:41.262730: step: 2390/1545, loss: 0.04068266600370407 2023-01-23 10:57:42.125639: step: 2392/1545, loss: 0.07941121608018875 2023-01-23 10:57:43.033422: step: 2394/1545, loss: 0.07403723895549774 2023-01-23 10:57:43.910173: step: 2396/1545, loss: 0.2624139189720154 2023-01-23 10:57:44.790616: step: 2398/1545, loss: 0.09848491847515106 2023-01-23 10:57:45.650486: step: 2400/1545, loss: 0.2116512805223465 2023-01-23 10:57:46.546908: step: 2402/1545, loss: 0.1554577797651291 2023-01-23 10:57:47.405183: step: 2404/1545, loss: 0.08075405657291412 2023-01-23 10:57:48.270457: step: 2406/1545, loss: 0.14221781492233276 2023-01-23 10:57:49.111283: step: 2408/1545, loss: 0.5372649431228638 2023-01-23 10:57:50.039708: step: 2410/1545, loss: 0.021073440089821815 2023-01-23 10:57:50.948458: step: 2412/1545, loss: 0.05958184227347374 2023-01-23 10:57:51.770363: step: 2414/1545, loss: 0.4697031080722809 2023-01-23 10:57:52.640419: step: 2416/1545, loss: 0.2524557411670685 2023-01-23 10:57:53.503811: step: 2418/1545, loss: 0.057292867451906204 2023-01-23 10:57:54.424159: step: 2420/1545, loss: 0.09991487860679626 2023-01-23 10:57:55.329724: step: 2422/1545, loss: 0.08791433274745941 2023-01-23 10:57:56.186537: step: 2424/1545, loss: 0.035103946924209595 2023-01-23 10:57:57.038085: step: 2426/1545, loss: 0.013014056719839573 2023-01-23 10:57:57.898217: step: 2428/1545, loss: 0.1564154326915741 2023-01-23 10:57:58.749283: step: 2430/1545, loss: 0.12785491347312927 2023-01-23 10:57:59.614872: step: 2432/1545, loss: 0.027000853791832924 2023-01-23 10:58:00.481120: step: 2434/1545, loss: 0.008619822561740875 2023-01-23 10:58:01.363140: step: 2436/1545, loss: 0.1705513447523117 2023-01-23 10:58:02.203351: step: 2438/1545, loss: 0.14279881119728088 2023-01-23 10:58:03.060767: step: 2440/1545, loss: 0.22419138252735138 2023-01-23 10:58:03.924500: step: 2442/1545, loss: 0.0711510181427002 2023-01-23 10:58:04.789466: step: 2444/1545, loss: 0.17213869094848633 2023-01-23 10:58:05.666209: step: 2446/1545, loss: 0.09479262679815292 2023-01-23 10:58:06.546207: step: 2448/1545, loss: 0.32503074407577515 2023-01-23 10:58:07.457295: step: 2450/1545, loss: 0.1808588206768036 2023-01-23 10:58:08.327969: step: 2452/1545, loss: 0.21144159138202667 2023-01-23 10:58:09.230279: step: 2454/1545, loss: 0.11702225357294083 2023-01-23 10:58:10.114908: step: 2456/1545, loss: 0.10122152417898178 2023-01-23 10:58:11.020101: step: 2458/1545, loss: 0.5873245000839233 2023-01-23 10:58:11.916500: step: 2460/1545, loss: 0.02348802238702774 2023-01-23 10:58:12.797179: step: 2462/1545, loss: 2.940211296081543 2023-01-23 10:58:13.660945: step: 2464/1545, loss: 0.17960990965366364 2023-01-23 10:58:14.537520: step: 2466/1545, loss: 0.2836279571056366 2023-01-23 10:58:15.390495: step: 2468/1545, loss: 0.2168453335762024 2023-01-23 10:58:16.263329: step: 2470/1545, loss: 0.12920235097408295 2023-01-23 10:58:17.127633: step: 2472/1545, loss: 0.06560137867927551 2023-01-23 10:58:18.012877: step: 2474/1545, loss: 0.25051599740982056 2023-01-23 10:58:18.898278: step: 2476/1545, loss: 0.04365336522459984 2023-01-23 10:58:19.755910: step: 2478/1545, loss: 0.20104235410690308 2023-01-23 10:58:20.628461: step: 2480/1545, loss: 0.05170662701129913 2023-01-23 10:58:21.455512: step: 2482/1545, loss: 0.1858503371477127 2023-01-23 10:58:22.321043: step: 2484/1545, loss: 0.056700561195611954 2023-01-23 10:58:23.199735: step: 2486/1545, loss: 1.0890206098556519 2023-01-23 10:58:24.032340: step: 2488/1545, loss: 0.04471071809530258 2023-01-23 10:58:24.871588: step: 2490/1545, loss: 0.2816740572452545 2023-01-23 10:58:25.752615: step: 2492/1545, loss: 0.23287752270698547 2023-01-23 10:58:26.619786: step: 2494/1545, loss: 0.2998887300491333 2023-01-23 10:58:27.472908: step: 2496/1545, loss: 0.028191475197672844 2023-01-23 10:58:28.333766: step: 2498/1545, loss: 0.2449941784143448 2023-01-23 10:58:29.218215: step: 2500/1545, loss: 3.544171094894409 2023-01-23 10:58:30.057593: step: 2502/1545, loss: 0.134810671210289 2023-01-23 10:58:30.913810: step: 2504/1545, loss: 0.04476572945713997 2023-01-23 10:58:31.760644: step: 2506/1545, loss: 0.5341181755065918 2023-01-23 10:58:32.633952: step: 2508/1545, loss: 0.31839460134506226 2023-01-23 10:58:33.558342: step: 2510/1545, loss: 0.19886896014213562 2023-01-23 10:58:34.394221: step: 2512/1545, loss: 0.09776630252599716 2023-01-23 10:58:35.256382: step: 2514/1545, loss: 0.2270529419183731 2023-01-23 10:58:36.226438: step: 2516/1545, loss: 0.081657275557518 2023-01-23 10:58:37.075540: step: 2518/1545, loss: 0.0825704038143158 2023-01-23 10:58:37.990680: step: 2520/1545, loss: 0.08655750006437302 2023-01-23 10:58:38.861449: step: 2522/1545, loss: 0.08998209983110428 2023-01-23 10:58:39.724177: step: 2524/1545, loss: 0.02480034902691841 2023-01-23 10:58:40.584947: step: 2526/1545, loss: 0.20549529790878296 2023-01-23 10:58:41.441842: step: 2528/1545, loss: 0.07695522159337997 2023-01-23 10:58:42.335786: step: 2530/1545, loss: 0.019868729636073112 2023-01-23 10:58:43.184005: step: 2532/1545, loss: 0.03439265862107277 2023-01-23 10:58:44.059747: step: 2534/1545, loss: 0.06314612925052643 2023-01-23 10:58:44.990090: step: 2536/1545, loss: 0.15689170360565186 2023-01-23 10:58:45.881334: step: 2538/1545, loss: 0.10013313591480255 2023-01-23 10:58:46.771650: step: 2540/1545, loss: 0.281441867351532 2023-01-23 10:58:47.668082: step: 2542/1545, loss: 0.11184051632881165 2023-01-23 10:58:48.590090: step: 2544/1545, loss: 0.30507808923721313 2023-01-23 10:58:49.484674: step: 2546/1545, loss: 0.1245112419128418 2023-01-23 10:58:50.329183: step: 2548/1545, loss: 0.01555390190333128 2023-01-23 10:58:51.173811: step: 2550/1545, loss: 0.1380378007888794 2023-01-23 10:58:52.027459: step: 2552/1545, loss: 0.05526627227663994 2023-01-23 10:58:52.890556: step: 2554/1545, loss: 0.13159862160682678 2023-01-23 10:58:53.742512: step: 2556/1545, loss: 0.11433085799217224 2023-01-23 10:58:54.614040: step: 2558/1545, loss: 0.11724182218313217 2023-01-23 10:58:55.459530: step: 2560/1545, loss: 0.5256533622741699 2023-01-23 10:58:56.336937: step: 2562/1545, loss: 0.028069403022527695 2023-01-23 10:58:57.205837: step: 2564/1545, loss: 0.10784953087568283 2023-01-23 10:58:58.118829: step: 2566/1545, loss: 0.003888143226504326 2023-01-23 10:58:59.020124: step: 2568/1545, loss: 0.12248656153678894 2023-01-23 10:58:59.924617: step: 2570/1545, loss: 0.10137717425823212 2023-01-23 10:59:00.794745: step: 2572/1545, loss: 0.10218463838100433 2023-01-23 10:59:01.668956: step: 2574/1545, loss: 0.013764775358140469 2023-01-23 10:59:02.504256: step: 2576/1545, loss: 0.23873518407344818 2023-01-23 10:59:03.395586: step: 2578/1545, loss: 0.047872528433799744 2023-01-23 10:59:04.300792: step: 2580/1545, loss: 0.24830378592014313 2023-01-23 10:59:05.168653: step: 2582/1545, loss: 0.10471987724304199 2023-01-23 10:59:06.072872: step: 2584/1545, loss: 0.1140463650226593 2023-01-23 10:59:06.983593: step: 2586/1545, loss: 0.08637721836566925 2023-01-23 10:59:07.853846: step: 2588/1545, loss: 0.02950075827538967 2023-01-23 10:59:08.743709: step: 2590/1545, loss: 0.1138596385717392 2023-01-23 10:59:09.647957: step: 2592/1545, loss: 0.3242953419685364 2023-01-23 10:59:10.518897: step: 2594/1545, loss: 0.09179172664880753 2023-01-23 10:59:11.356775: step: 2596/1545, loss: 0.07283948361873627 2023-01-23 10:59:12.297411: step: 2598/1545, loss: 0.08750785887241364 2023-01-23 10:59:13.182132: step: 2600/1545, loss: 0.02403864450752735 2023-01-23 10:59:14.089729: step: 2602/1545, loss: 0.19234606623649597 2023-01-23 10:59:14.992875: step: 2604/1545, loss: 0.2815100848674774 2023-01-23 10:59:15.849902: step: 2606/1545, loss: 0.23839472234249115 2023-01-23 10:59:16.714087: step: 2608/1545, loss: 0.0180143304169178 2023-01-23 10:59:17.590198: step: 2610/1545, loss: 0.08105205744504929 2023-01-23 10:59:18.482646: step: 2612/1545, loss: 0.1662280261516571 2023-01-23 10:59:19.347781: step: 2614/1545, loss: 0.15638954937458038 2023-01-23 10:59:20.267792: step: 2616/1545, loss: 0.4005281925201416 2023-01-23 10:59:21.197794: step: 2618/1545, loss: 0.028812281787395477 2023-01-23 10:59:22.100926: step: 2620/1545, loss: 4.405580520629883 2023-01-23 10:59:22.948577: step: 2622/1545, loss: 0.12152273207902908 2023-01-23 10:59:23.815460: step: 2624/1545, loss: 0.004215839318931103 2023-01-23 10:59:24.701026: step: 2626/1545, loss: 0.04924517124891281 2023-01-23 10:59:25.657971: step: 2628/1545, loss: 0.08422737568616867 2023-01-23 10:59:26.536693: step: 2630/1545, loss: 0.1653354912996292 2023-01-23 10:59:27.457463: step: 2632/1545, loss: 0.18706171214580536 2023-01-23 10:59:28.309164: step: 2634/1545, loss: 0.028517261147499084 2023-01-23 10:59:29.229168: step: 2636/1545, loss: 0.13307525217533112 2023-01-23 10:59:30.095178: step: 2638/1545, loss: 0.08933725953102112 2023-01-23 10:59:30.918544: step: 2640/1545, loss: 0.05637699365615845 2023-01-23 10:59:31.767265: step: 2642/1545, loss: 0.009085522033274174 2023-01-23 10:59:32.782903: step: 2644/1545, loss: 0.22335240244865417 2023-01-23 10:59:33.664389: step: 2646/1545, loss: 0.014606114476919174 2023-01-23 10:59:34.539315: step: 2648/1545, loss: 0.17738716304302216 2023-01-23 10:59:35.406116: step: 2650/1545, loss: 0.0361933708190918 2023-01-23 10:59:36.310899: step: 2652/1545, loss: 0.005441867746412754 2023-01-23 10:59:37.177953: step: 2654/1545, loss: 0.04530623182654381 2023-01-23 10:59:38.049071: step: 2656/1545, loss: 0.029920998960733414 2023-01-23 10:59:38.945737: step: 2658/1545, loss: 0.04918977990746498 2023-01-23 10:59:39.884158: step: 2660/1545, loss: 0.37316185235977173 2023-01-23 10:59:40.760444: step: 2662/1545, loss: 0.008061758242547512 2023-01-23 10:59:41.598628: step: 2664/1545, loss: 0.03364373743534088 2023-01-23 10:59:42.507186: step: 2666/1545, loss: 0.10207605361938477 2023-01-23 10:59:43.362909: step: 2668/1545, loss: 0.08366349339485168 2023-01-23 10:59:44.240093: step: 2670/1545, loss: 0.10635700821876526 2023-01-23 10:59:45.126457: step: 2672/1545, loss: 0.11891213804483414 2023-01-23 10:59:45.977534: step: 2674/1545, loss: 0.48403581976890564 2023-01-23 10:59:46.855616: step: 2676/1545, loss: 0.12072310596704483 2023-01-23 10:59:47.695617: step: 2678/1545, loss: 0.05165985971689224 2023-01-23 10:59:48.533987: step: 2680/1545, loss: 0.04193328693509102 2023-01-23 10:59:49.446110: step: 2682/1545, loss: 0.2139553725719452 2023-01-23 10:59:50.301073: step: 2684/1545, loss: 0.14403456449508667 2023-01-23 10:59:51.187787: step: 2686/1545, loss: 0.15607577562332153 2023-01-23 10:59:52.037427: step: 2688/1545, loss: 0.15754728019237518 2023-01-23 10:59:52.900546: step: 2690/1545, loss: 0.5171934366226196 2023-01-23 10:59:53.756297: step: 2692/1545, loss: 0.3097294569015503 2023-01-23 10:59:54.622770: step: 2694/1545, loss: 0.08410054445266724 2023-01-23 10:59:55.509474: step: 2696/1545, loss: 0.36744439601898193 2023-01-23 10:59:56.396058: step: 2698/1545, loss: 0.08624767512083054 2023-01-23 10:59:57.270544: step: 2700/1545, loss: 0.08509784936904907 2023-01-23 10:59:58.178841: step: 2702/1545, loss: 0.048277221620082855 2023-01-23 10:59:59.050081: step: 2704/1545, loss: 0.15777617692947388 2023-01-23 10:59:59.928858: step: 2706/1545, loss: 0.2267438769340515 2023-01-23 11:00:00.901321: step: 2708/1545, loss: 0.4196932315826416 2023-01-23 11:00:01.835764: step: 2710/1545, loss: 0.7350226640701294 2023-01-23 11:00:02.741543: step: 2712/1545, loss: 0.38961952924728394 2023-01-23 11:00:03.612557: step: 2714/1545, loss: 0.1259668618440628 2023-01-23 11:00:04.481604: step: 2716/1545, loss: 0.08282651752233505 2023-01-23 11:00:05.364344: step: 2718/1545, loss: 0.12945562601089478 2023-01-23 11:00:06.253918: step: 2720/1545, loss: 0.2708849608898163 2023-01-23 11:00:07.172142: step: 2722/1545, loss: 0.2370302826166153 2023-01-23 11:00:08.048254: step: 2724/1545, loss: 0.22648417949676514 2023-01-23 11:00:08.905426: step: 2726/1545, loss: 0.10698883980512619 2023-01-23 11:00:09.756819: step: 2728/1545, loss: 0.4615204334259033 2023-01-23 11:00:10.700064: step: 2730/1545, loss: 0.07059646397829056 2023-01-23 11:00:11.589773: step: 2732/1545, loss: 0.13197079300880432 2023-01-23 11:00:12.460078: step: 2734/1545, loss: 0.21663740277290344 2023-01-23 11:00:13.305035: step: 2736/1545, loss: 0.09300187975168228 2023-01-23 11:00:14.192195: step: 2738/1545, loss: 0.32484638690948486 2023-01-23 11:00:15.077332: step: 2740/1545, loss: 0.06372299790382385 2023-01-23 11:00:15.989572: step: 2742/1545, loss: 0.030922500416636467 2023-01-23 11:00:16.885574: step: 2744/1545, loss: 0.5811036825180054 2023-01-23 11:00:17.735037: step: 2746/1545, loss: 0.01575193926692009 2023-01-23 11:00:18.626976: step: 2748/1545, loss: 0.054984670132398605 2023-01-23 11:00:19.590296: step: 2750/1545, loss: 0.03825785964727402 2023-01-23 11:00:20.426585: step: 2752/1545, loss: 0.4949163794517517 2023-01-23 11:00:21.261104: step: 2754/1545, loss: 0.2067398726940155 2023-01-23 11:00:22.131315: step: 2756/1545, loss: 0.1762910634279251 2023-01-23 11:00:22.980091: step: 2758/1545, loss: 0.034380264580249786 2023-01-23 11:00:23.898135: step: 2760/1545, loss: 5.893333911895752 2023-01-23 11:00:24.743805: step: 2762/1545, loss: 0.00980309396982193 2023-01-23 11:00:25.618482: step: 2764/1545, loss: 0.31290024518966675 2023-01-23 11:00:26.502217: step: 2766/1545, loss: 0.13944301009178162 2023-01-23 11:00:27.374126: step: 2768/1545, loss: 0.0812324658036232 2023-01-23 11:00:28.229022: step: 2770/1545, loss: 0.14154288172721863 2023-01-23 11:00:29.086550: step: 2772/1545, loss: 0.11291476339101791 2023-01-23 11:00:29.982821: step: 2774/1545, loss: 0.13587486743927002 2023-01-23 11:00:30.860175: step: 2776/1545, loss: 0.3524692952632904 2023-01-23 11:00:31.818345: step: 2778/1545, loss: 0.060317642986774445 2023-01-23 11:00:32.786519: step: 2780/1545, loss: 0.3026040494441986 2023-01-23 11:00:33.709261: step: 2782/1545, loss: 0.06554433703422546 2023-01-23 11:00:34.609687: step: 2784/1545, loss: 0.09431126713752747 2023-01-23 11:00:35.530196: step: 2786/1545, loss: 0.11267884820699692 2023-01-23 11:00:36.416272: step: 2788/1545, loss: 0.6065691709518433 2023-01-23 11:00:37.318445: step: 2790/1545, loss: 0.16161543130874634 2023-01-23 11:00:38.235197: step: 2792/1545, loss: 0.001180193736217916 2023-01-23 11:00:39.069918: step: 2794/1545, loss: 0.021989785134792328 2023-01-23 11:00:39.936182: step: 2796/1545, loss: 0.1420309841632843 2023-01-23 11:00:40.819717: step: 2798/1545, loss: 0.0013174552004784346 2023-01-23 11:00:41.654102: step: 2800/1545, loss: 0.021589195355772972 2023-01-23 11:00:42.541187: step: 2802/1545, loss: 0.11864092946052551 2023-01-23 11:00:43.416252: step: 2804/1545, loss: 0.0937255248427391 2023-01-23 11:00:44.289168: step: 2806/1545, loss: 0.06194150820374489 2023-01-23 11:00:45.183464: step: 2808/1545, loss: 0.14440187811851501 2023-01-23 11:00:46.081633: step: 2810/1545, loss: 0.22861962020397186 2023-01-23 11:00:46.945327: step: 2812/1545, loss: 0.39815154671669006 2023-01-23 11:00:47.814688: step: 2814/1545, loss: 0.11073613911867142 2023-01-23 11:00:48.650409: step: 2816/1545, loss: 0.34612250328063965 2023-01-23 11:00:49.547312: step: 2818/1545, loss: 0.20904503762722015 2023-01-23 11:00:50.436676: step: 2820/1545, loss: 0.05791353061795235 2023-01-23 11:00:51.323261: step: 2822/1545, loss: 0.22195248305797577 2023-01-23 11:00:52.225917: step: 2824/1545, loss: 0.12792089581489563 2023-01-23 11:00:53.152607: step: 2826/1545, loss: 0.16060057282447815 2023-01-23 11:00:54.045702: step: 2828/1545, loss: 0.054503511637449265 2023-01-23 11:00:54.956428: step: 2830/1545, loss: 0.216461643576622 2023-01-23 11:00:55.808987: step: 2832/1545, loss: 0.19360756874084473 2023-01-23 11:00:56.679023: step: 2834/1545, loss: 0.04602107033133507 2023-01-23 11:00:57.531179: step: 2836/1545, loss: 0.12852323055267334 2023-01-23 11:00:58.398442: step: 2838/1545, loss: 0.22813059389591217 2023-01-23 11:00:59.257388: step: 2840/1545, loss: 0.04773131385445595 2023-01-23 11:01:00.120706: step: 2842/1545, loss: 0.03707600384950638 2023-01-23 11:01:01.002118: step: 2844/1545, loss: 0.007169210817664862 2023-01-23 11:01:01.872736: step: 2846/1545, loss: 0.006167606916278601 2023-01-23 11:01:02.724415: step: 2848/1545, loss: 0.18832877278327942 2023-01-23 11:01:03.587930: step: 2850/1545, loss: 0.20691002905368805 2023-01-23 11:01:04.486225: step: 2852/1545, loss: 0.029416657984256744 2023-01-23 11:01:05.385099: step: 2854/1545, loss: 0.09524115920066833 2023-01-23 11:01:06.269122: step: 2856/1545, loss: 0.04452939331531525 2023-01-23 11:01:07.157812: step: 2858/1545, loss: 0.26347190141677856 2023-01-23 11:01:08.057347: step: 2860/1545, loss: 0.17552511394023895 2023-01-23 11:01:08.896736: step: 2862/1545, loss: 0.1707857847213745 2023-01-23 11:01:09.765680: step: 2864/1545, loss: 0.1618756204843521 2023-01-23 11:01:10.598776: step: 2866/1545, loss: 0.18266333639621735 2023-01-23 11:01:11.497375: step: 2868/1545, loss: 0.2065809965133667 2023-01-23 11:01:12.456915: step: 2870/1545, loss: 0.3344622254371643 2023-01-23 11:01:13.374979: step: 2872/1545, loss: 0.5918017625808716 2023-01-23 11:01:14.261302: step: 2874/1545, loss: 0.07836538553237915 2023-01-23 11:01:15.120593: step: 2876/1545, loss: 0.2512196898460388 2023-01-23 11:01:15.972265: step: 2878/1545, loss: 0.019510824233293533 2023-01-23 11:01:16.953448: step: 2880/1545, loss: 0.34678152203559875 2023-01-23 11:01:17.810461: step: 2882/1545, loss: 0.10562096536159515 2023-01-23 11:01:18.680440: step: 2884/1545, loss: 0.023889200761914253 2023-01-23 11:01:19.516310: step: 2886/1545, loss: 0.2252410650253296 2023-01-23 11:01:20.367588: step: 2888/1545, loss: 0.07157012820243835 2023-01-23 11:01:21.278779: step: 2890/1545, loss: 0.32527440786361694 2023-01-23 11:01:22.166304: step: 2892/1545, loss: 0.10552124679088593 2023-01-23 11:01:23.050581: step: 2894/1545, loss: 0.1452438235282898 2023-01-23 11:01:23.876282: step: 2896/1545, loss: 0.5578891634941101 2023-01-23 11:01:24.735578: step: 2898/1545, loss: 0.10250954329967499 2023-01-23 11:01:25.657742: step: 2900/1545, loss: 0.29670074582099915 2023-01-23 11:01:26.510900: step: 2902/1545, loss: 0.38482460379600525 2023-01-23 11:01:27.360689: step: 2904/1545, loss: 0.7860326766967773 2023-01-23 11:01:28.303190: step: 2906/1545, loss: 0.026315651834011078 2023-01-23 11:01:29.180438: step: 2908/1545, loss: 0.29437124729156494 2023-01-23 11:01:30.072724: step: 2910/1545, loss: 0.051086850464344025 2023-01-23 11:01:31.010851: step: 2912/1545, loss: 0.19120383262634277 2023-01-23 11:01:31.909648: step: 2914/1545, loss: 0.3138431906700134 2023-01-23 11:01:32.767748: step: 2916/1545, loss: 0.2542749345302582 2023-01-23 11:01:33.700573: step: 2918/1545, loss: 0.6759483814239502 2023-01-23 11:01:34.677083: step: 2920/1545, loss: 0.21734824776649475 2023-01-23 11:01:35.529112: step: 2922/1545, loss: 0.4703770875930786 2023-01-23 11:01:36.391818: step: 2924/1545, loss: 0.4690750539302826 2023-01-23 11:01:37.247175: step: 2926/1545, loss: 0.013738861307501793 2023-01-23 11:01:38.093830: step: 2928/1545, loss: 0.1083323210477829 2023-01-23 11:01:38.954531: step: 2930/1545, loss: 0.42755618691444397 2023-01-23 11:01:39.884513: step: 2932/1545, loss: 0.19214178621768951 2023-01-23 11:01:40.850146: step: 2934/1545, loss: 0.114520363509655 2023-01-23 11:01:41.703924: step: 2936/1545, loss: 0.06556771695613861 2023-01-23 11:01:42.602603: step: 2938/1545, loss: 0.10269840061664581 2023-01-23 11:01:43.497918: step: 2940/1545, loss: 0.1825113147497177 2023-01-23 11:01:44.363496: step: 2942/1545, loss: 0.17150147259235382 2023-01-23 11:01:45.305711: step: 2944/1545, loss: 0.07141683995723724 2023-01-23 11:01:46.196991: step: 2946/1545, loss: 0.2162082940340042 2023-01-23 11:01:47.116745: step: 2948/1545, loss: 0.17707423865795135 2023-01-23 11:01:48.011910: step: 2950/1545, loss: 0.4434318542480469 2023-01-23 11:01:49.032362: step: 2952/1545, loss: 0.24754256010055542 2023-01-23 11:01:49.901250: step: 2954/1545, loss: 0.10817382484674454 2023-01-23 11:01:50.778000: step: 2956/1545, loss: 0.15644077956676483 2023-01-23 11:01:51.619519: step: 2958/1545, loss: 0.10329315066337585 2023-01-23 11:01:52.499815: step: 2960/1545, loss: 0.3695840537548065 2023-01-23 11:01:53.455645: step: 2962/1545, loss: 0.0128881074488163 2023-01-23 11:01:54.341486: step: 2964/1545, loss: 0.051628224551677704 2023-01-23 11:01:55.288746: step: 2966/1545, loss: 0.17381809651851654 2023-01-23 11:01:56.181335: step: 2968/1545, loss: 0.17664101719856262 2023-01-23 11:01:57.040916: step: 2970/1545, loss: 0.09461930394172668 2023-01-23 11:01:57.951472: step: 2972/1545, loss: 0.028020044788718224 2023-01-23 11:01:58.810144: step: 2974/1545, loss: 0.03949938714504242 2023-01-23 11:01:59.666409: step: 2976/1545, loss: 0.06803597509860992 2023-01-23 11:02:00.552258: step: 2978/1545, loss: 0.10336723178625107 2023-01-23 11:02:01.378312: step: 2980/1545, loss: 0.38471701741218567 2023-01-23 11:02:02.284135: step: 2982/1545, loss: 0.03406229242682457 2023-01-23 11:02:03.214887: step: 2984/1545, loss: 0.024936141446232796 2023-01-23 11:02:04.117219: step: 2986/1545, loss: 0.21934111416339874 2023-01-23 11:02:04.983422: step: 2988/1545, loss: 0.06515052169561386 2023-01-23 11:02:05.849666: step: 2990/1545, loss: 1.292410135269165 2023-01-23 11:02:06.768044: step: 2992/1545, loss: 0.1775396168231964 2023-01-23 11:02:07.647762: step: 2994/1545, loss: 0.01050809770822525 2023-01-23 11:02:08.548847: step: 2996/1545, loss: 0.14966243505477905 2023-01-23 11:02:09.434381: step: 2998/1545, loss: 0.26438456773757935 2023-01-23 11:02:10.292297: step: 3000/1545, loss: 0.06410093605518341 2023-01-23 11:02:11.153567: step: 3002/1545, loss: 0.15384478867053986 2023-01-23 11:02:12.052214: step: 3004/1545, loss: 0.4449976086616516 2023-01-23 11:02:13.056706: step: 3006/1545, loss: 0.1283779740333557 2023-01-23 11:02:13.943378: step: 3008/1545, loss: 1.3127710819244385 2023-01-23 11:02:14.830933: step: 3010/1545, loss: 0.2974792718887329 2023-01-23 11:02:15.653695: step: 3012/1545, loss: 0.1037006601691246 2023-01-23 11:02:16.569291: step: 3014/1545, loss: 0.1738566756248474 2023-01-23 11:02:17.489509: step: 3016/1545, loss: 0.3032686412334442 2023-01-23 11:02:18.366817: step: 3018/1545, loss: 0.04107609763741493 2023-01-23 11:02:19.244346: step: 3020/1545, loss: 0.12007495760917664 2023-01-23 11:02:20.114725: step: 3022/1545, loss: 0.19886787235736847 2023-01-23 11:02:20.979361: step: 3024/1545, loss: 0.4644087255001068 2023-01-23 11:02:21.848312: step: 3026/1545, loss: 0.50710529088974 2023-01-23 11:02:22.742952: step: 3028/1545, loss: 1.239241361618042 2023-01-23 11:02:23.601388: step: 3030/1545, loss: 0.11152245104312897 2023-01-23 11:02:24.455213: step: 3032/1545, loss: 0.48733648657798767 2023-01-23 11:02:25.309900: step: 3034/1545, loss: 0.06688202917575836 2023-01-23 11:02:26.173178: step: 3036/1545, loss: 0.21635636687278748 2023-01-23 11:02:27.045360: step: 3038/1545, loss: 0.017141100019216537 2023-01-23 11:02:27.921299: step: 3040/1545, loss: 0.16549856960773468 2023-01-23 11:02:28.818062: step: 3042/1545, loss: 0.3728017807006836 2023-01-23 11:02:29.646679: step: 3044/1545, loss: 0.0849568098783493 2023-01-23 11:02:30.520028: step: 3046/1545, loss: 0.06144231930375099 2023-01-23 11:02:31.370678: step: 3048/1545, loss: 0.1684572547674179 2023-01-23 11:02:32.211500: step: 3050/1545, loss: 0.8173079490661621 2023-01-23 11:02:33.088340: step: 3052/1545, loss: 0.026369288563728333 2023-01-23 11:02:33.950667: step: 3054/1545, loss: 0.40448835492134094 2023-01-23 11:02:34.866313: step: 3056/1545, loss: 0.16704541444778442 2023-01-23 11:02:35.724287: step: 3058/1545, loss: 0.09818306565284729 2023-01-23 11:02:36.556208: step: 3060/1545, loss: 0.14051203429698944 2023-01-23 11:02:37.468758: step: 3062/1545, loss: 0.2403344064950943 2023-01-23 11:02:38.345536: step: 3064/1545, loss: 0.13835808634757996 2023-01-23 11:02:39.216278: step: 3066/1545, loss: 0.5825642347335815 2023-01-23 11:02:40.073122: step: 3068/1545, loss: 0.2941594123840332 2023-01-23 11:02:40.962110: step: 3070/1545, loss: 0.4434814751148224 2023-01-23 11:02:41.845292: step: 3072/1545, loss: 0.27075856924057007 2023-01-23 11:02:42.708004: step: 3074/1545, loss: 0.22023098170757294 2023-01-23 11:02:43.580058: step: 3076/1545, loss: 0.17548677325248718 2023-01-23 11:02:44.460395: step: 3078/1545, loss: 0.06448586285114288 2023-01-23 11:02:45.332687: step: 3080/1545, loss: 0.4523734748363495 2023-01-23 11:02:46.206205: step: 3082/1545, loss: 0.26473894715309143 2023-01-23 11:02:47.057434: step: 3084/1545, loss: 0.18567205965518951 2023-01-23 11:02:47.942736: step: 3086/1545, loss: 0.16029933094978333 2023-01-23 11:02:48.866334: step: 3088/1545, loss: 0.15424858033657074 2023-01-23 11:02:49.774295: step: 3090/1545, loss: 0.06495800614356995 ================================================== Loss: 0.214 -------------------- Dev Chinese: {'event': {'p': 0.6019629225736096, 'r': 0.7350199733688415, 'f1': 0.6618705035971223}, 'argument': {'p': 0.6525858486705476, 'r': 0.6506319988242286, 'f1': 0.651607459092331}, 'combined': 0.4312797570970824, 'epoch': 12} Test Chinese: {'event': {'p': 0.6398078975453575, 'r': 0.7666240409207161, 'f1': 0.6974985456660848}, 'argument': {'p': 0.6989886500288407, 'r': 0.7224571739519761, 'f1': 0.7105291755827877}, 'combined': 0.49559306662231667, 'epoch': 12} Dev Korean: {'event': {'p': 0.6083150984682714, 'r': 0.7403462050599201, 'f1': 0.667867867867868}, 'argument': {'p': 0.6567437110319474, 'r': 0.6528022634038487, 'f1': 0.6547670557692479}, 'combined': 0.437297877486729, 'epoch': 12} Test Korean: {'event': {'p': 0.6306878306878307, 'r': 0.7621483375959079, 'f1': 0.6902142443543717}, 'argument': {'p': 0.6938558610878542, 'r': 0.7238160109934436, 'f1': 0.708519356936541}, 'combined': 0.48903015255840004, 'epoch': 12} Dev Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6513734211734282, 'r': 0.6555728200205349, 'f1': 0.6534663739726289}, 'combined': 0.43120644711493217, 'epoch': 12} Test Russian: {'event': {'p': 0.6263079222720478, 'r': 0.8037084398976982, 'f1': 0.7040044805376645}, 'argument': {'p': 0.6984572049417093, 'r': 0.7308706381051718, 'f1': 0.714296395397593}, 'combined': 0.5028678627918087, 'epoch': 12} Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.662396694214876, 'r': 0.6021788129226145, 'f1': 0.6308539944903582}, 'combined': 0.45880290508389693, 'epoch': 12} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6986772486772487, 'r': 0.4306914546640574, 'f1': 0.5328894269572236}, 'combined': 0.33656174334140443, 'epoch': 12} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5741057386463273, 'r': 0.6048614032166663, 'f1': 0.589082410089275}, 'combined': 0.3280965322016215, 'epoch': 12} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.6540410788569386, 'r': 0.6466702177127959, 'f1': 0.6503347637141906}, 'combined': 0.4374624236395757, 'epoch': 9} Test for Korean: {'event': {'p': 0.6354497354497355, 'r': 0.7679028132992327, 'f1': 0.6954255935147655}, 'argument': {'p': 0.7132062904851311, 'r': 0.7077515578619179, 'f1': 0.7104684544372034}, 'combined': 0.4940779466005103, 'epoch': 9} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6633986928104574, 'r': 0.46990740740740733, 'f1': 0.5501355013550133}, 'combined': 0.3474540008557979, 'epoch': 9} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 13 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 11:08:05.089702: step: 2/1545, loss: 0.2650952935218811 2023-01-23 11:08:06.001628: step: 4/1545, loss: 0.11336169391870499 2023-01-23 11:08:06.847092: step: 6/1545, loss: 0.007640642113983631 2023-01-23 11:08:07.715204: step: 8/1545, loss: 0.05110339820384979 2023-01-23 11:08:08.620762: step: 10/1545, loss: 0.34863001108169556 2023-01-23 11:08:09.497908: step: 12/1545, loss: 0.03923430293798447 2023-01-23 11:08:10.403037: step: 14/1545, loss: 0.1127215027809143 2023-01-23 11:08:11.224597: step: 16/1545, loss: 0.12899243831634521 2023-01-23 11:08:12.128645: step: 18/1545, loss: 0.047122497111558914 2023-01-23 11:08:13.018961: step: 20/1545, loss: 0.028216572478413582 2023-01-23 11:08:13.929725: step: 22/1545, loss: 0.2164919078350067 2023-01-23 11:08:14.794580: step: 24/1545, loss: 0.2775958776473999 2023-01-23 11:08:15.658690: step: 26/1545, loss: 0.0247493963688612 2023-01-23 11:08:16.556099: step: 28/1545, loss: 0.01908091828227043 2023-01-23 11:08:17.438869: step: 30/1545, loss: 0.10973580181598663 2023-01-23 11:08:18.330287: step: 32/1545, loss: 0.1742604523897171 2023-01-23 11:08:19.210895: step: 34/1545, loss: 0.07421572506427765 2023-01-23 11:08:20.117391: step: 36/1545, loss: 0.2677278518676758 2023-01-23 11:08:20.970872: step: 38/1545, loss: 0.19399401545524597 2023-01-23 11:08:21.847776: step: 40/1545, loss: 0.00839682575315237 2023-01-23 11:08:22.832732: step: 42/1545, loss: 0.1995135247707367 2023-01-23 11:08:23.754719: step: 44/1545, loss: 0.2138742059469223 2023-01-23 11:08:24.646933: step: 46/1545, loss: 0.15787404775619507 2023-01-23 11:08:25.508728: step: 48/1545, loss: 0.018212884664535522 2023-01-23 11:08:26.367910: step: 50/1545, loss: 0.03911793977022171 2023-01-23 11:08:27.236218: step: 52/1545, loss: 0.036809805780649185 2023-01-23 11:08:28.129470: step: 54/1545, loss: 0.37845203280448914 2023-01-23 11:08:29.016576: step: 56/1545, loss: 0.140603169798851 2023-01-23 11:08:29.913981: step: 58/1545, loss: 0.10879741609096527 2023-01-23 11:08:30.804061: step: 60/1545, loss: 0.16150368750095367 2023-01-23 11:08:31.665239: step: 62/1545, loss: 0.008931486867368221 2023-01-23 11:08:32.528730: step: 64/1545, loss: 0.08922833949327469 2023-01-23 11:08:33.397783: step: 66/1545, loss: 0.07890450954437256 2023-01-23 11:08:34.277310: step: 68/1545, loss: 0.7128326892852783 2023-01-23 11:08:35.103904: step: 70/1545, loss: 0.0879664197564125 2023-01-23 11:08:35.987618: step: 72/1545, loss: 0.001953547354787588 2023-01-23 11:08:36.887246: step: 74/1545, loss: 0.030949603766202927 2023-01-23 11:08:37.778842: step: 76/1545, loss: 0.022989090532064438 2023-01-23 11:08:38.657977: step: 78/1545, loss: 0.9395110011100769 2023-01-23 11:08:39.552736: step: 80/1545, loss: 0.09172400832176208 2023-01-23 11:08:40.437587: step: 82/1545, loss: 0.03608107939362526 2023-01-23 11:08:41.321364: step: 84/1545, loss: 0.3420991003513336 2023-01-23 11:08:42.153818: step: 86/1545, loss: 0.02599211223423481 2023-01-23 11:08:43.041194: step: 88/1545, loss: 0.0057207513600587845 2023-01-23 11:08:43.930842: step: 90/1545, loss: 0.12216345220804214 2023-01-23 11:08:44.763933: step: 92/1545, loss: 0.009499647654592991 2023-01-23 11:08:45.684587: step: 94/1545, loss: 0.0046482873149216175 2023-01-23 11:08:46.626729: step: 96/1545, loss: 0.0773310512304306 2023-01-23 11:08:47.495186: step: 98/1545, loss: 0.0049242787063121796 2023-01-23 11:08:48.368847: step: 100/1545, loss: 0.003191802417859435 2023-01-23 11:08:49.224415: step: 102/1545, loss: 0.11461427062749863 2023-01-23 11:08:50.086549: step: 104/1545, loss: 0.05645401030778885 2023-01-23 11:08:51.036097: step: 106/1545, loss: 0.054646190255880356 2023-01-23 11:08:51.903582: step: 108/1545, loss: 0.07200039178133011 2023-01-23 11:08:52.863713: step: 110/1545, loss: 0.24597901105880737 2023-01-23 11:08:53.720641: step: 112/1545, loss: 0.06764189898967743 2023-01-23 11:08:54.576049: step: 114/1545, loss: 0.29342183470726013 2023-01-23 11:08:55.502139: step: 116/1545, loss: 0.13761872053146362 2023-01-23 11:08:56.429856: step: 118/1545, loss: 0.022573865950107574 2023-01-23 11:08:57.346267: step: 120/1545, loss: 0.47513270378112793 2023-01-23 11:08:58.249848: step: 122/1545, loss: 0.04357355833053589 2023-01-23 11:08:59.101134: step: 124/1545, loss: 0.010267864912748337 2023-01-23 11:08:59.952363: step: 126/1545, loss: 0.07450372725725174 2023-01-23 11:09:00.867099: step: 128/1545, loss: 0.09804683923721313 2023-01-23 11:09:01.762001: step: 130/1545, loss: 0.11111482232809067 2023-01-23 11:09:02.688489: step: 132/1545, loss: 0.10609982907772064 2023-01-23 11:09:03.619949: step: 134/1545, loss: 0.5955633521080017 2023-01-23 11:09:04.449479: step: 136/1545, loss: 0.19203384220600128 2023-01-23 11:09:05.321466: step: 138/1545, loss: 0.06005379557609558 2023-01-23 11:09:06.345468: step: 140/1545, loss: 0.15612861514091492 2023-01-23 11:09:07.229262: step: 142/1545, loss: 0.1691902130842209 2023-01-23 11:09:08.124603: step: 144/1545, loss: 0.07969827204942703 2023-01-23 11:09:09.012954: step: 146/1545, loss: 0.09170115739107132 2023-01-23 11:09:09.934576: step: 148/1545, loss: 0.08630425482988358 2023-01-23 11:09:10.758154: step: 150/1545, loss: 0.11293970793485641 2023-01-23 11:09:11.720155: step: 152/1545, loss: 0.0709942951798439 2023-01-23 11:09:12.581956: step: 154/1545, loss: 0.004340431187301874 2023-01-23 11:09:13.477113: step: 156/1545, loss: 0.021768705919384956 2023-01-23 11:09:14.342597: step: 158/1545, loss: 0.15230390429496765 2023-01-23 11:09:15.203380: step: 160/1545, loss: 0.1714644730091095 2023-01-23 11:09:16.048648: step: 162/1545, loss: 0.002766928868368268 2023-01-23 11:09:16.990096: step: 164/1545, loss: 0.10909625887870789 2023-01-23 11:09:17.858822: step: 166/1545, loss: 0.012903328984975815 2023-01-23 11:09:18.718864: step: 168/1545, loss: 0.04030296951532364 2023-01-23 11:09:19.598596: step: 170/1545, loss: 0.009875640273094177 2023-01-23 11:09:20.459542: step: 172/1545, loss: 0.29988253116607666 2023-01-23 11:09:21.359455: step: 174/1545, loss: 0.09811881184577942 2023-01-23 11:09:22.277688: step: 176/1545, loss: 0.15820631384849548 2023-01-23 11:09:23.194863: step: 178/1545, loss: 0.4008590579032898 2023-01-23 11:09:24.074091: step: 180/1545, loss: 0.07336855679750443 2023-01-23 11:09:24.971532: step: 182/1545, loss: 0.016699640080332756 2023-01-23 11:09:25.876216: step: 184/1545, loss: 0.043165646493434906 2023-01-23 11:09:26.704661: step: 186/1545, loss: 0.0035142514389008284 2023-01-23 11:09:27.598965: step: 188/1545, loss: 0.17287449538707733 2023-01-23 11:09:28.553780: step: 190/1545, loss: 0.04969726502895355 2023-01-23 11:09:29.449587: step: 192/1545, loss: 0.11299370974302292 2023-01-23 11:09:30.349504: step: 194/1545, loss: 0.007623228244483471 2023-01-23 11:09:31.252218: step: 196/1545, loss: 0.09706763923168182 2023-01-23 11:09:32.147766: step: 198/1545, loss: 0.020679084584116936 2023-01-23 11:09:33.007147: step: 200/1545, loss: 0.14303207397460938 2023-01-23 11:09:33.885947: step: 202/1545, loss: 0.02751821093261242 2023-01-23 11:09:34.769478: step: 204/1545, loss: 0.027058294042944908 2023-01-23 11:09:35.686866: step: 206/1545, loss: 0.16422061622142792 2023-01-23 11:09:36.635669: step: 208/1545, loss: 0.20363286137580872 2023-01-23 11:09:37.554314: step: 210/1545, loss: 0.5158545970916748 2023-01-23 11:09:38.425159: step: 212/1545, loss: 0.0053368196822702885 2023-01-23 11:09:39.303536: step: 214/1545, loss: 0.0395430289208889 2023-01-23 11:09:40.235794: step: 216/1545, loss: 0.23099584877490997 2023-01-23 11:09:41.076682: step: 218/1545, loss: 0.025865677744150162 2023-01-23 11:09:41.975094: step: 220/1545, loss: 0.03878919407725334 2023-01-23 11:09:42.858378: step: 222/1545, loss: 0.023043058812618256 2023-01-23 11:09:43.732637: step: 224/1545, loss: 0.04715663939714432 2023-01-23 11:09:44.655490: step: 226/1545, loss: 0.12669813632965088 2023-01-23 11:09:45.530572: step: 228/1545, loss: 0.04731643572449684 2023-01-23 11:09:46.401812: step: 230/1545, loss: 0.11274822801351547 2023-01-23 11:09:47.292936: step: 232/1545, loss: 0.15377381443977356 2023-01-23 11:09:48.191040: step: 234/1545, loss: 0.18133385479450226 2023-01-23 11:09:49.064824: step: 236/1545, loss: 0.0040604909881949425 2023-01-23 11:09:49.952136: step: 238/1545, loss: 0.09859035909175873 2023-01-23 11:09:50.841988: step: 240/1545, loss: 0.0023751952685415745 2023-01-23 11:09:51.715285: step: 242/1545, loss: 0.04007389396429062 2023-01-23 11:09:52.634490: step: 244/1545, loss: 0.03828546777367592 2023-01-23 11:09:53.507965: step: 246/1545, loss: 0.07209935039281845 2023-01-23 11:09:54.375119: step: 248/1545, loss: 0.12237395346164703 2023-01-23 11:09:55.207924: step: 250/1545, loss: 0.008336061611771584 2023-01-23 11:09:56.123454: step: 252/1545, loss: 0.46450233459472656 2023-01-23 11:09:56.947941: step: 254/1545, loss: 0.23565763235092163 2023-01-23 11:09:57.834927: step: 256/1545, loss: 0.05185512825846672 2023-01-23 11:09:58.775334: step: 258/1545, loss: 0.008539539761841297 2023-01-23 11:09:59.649397: step: 260/1545, loss: 0.32805800437927246 2023-01-23 11:10:00.512170: step: 262/1545, loss: 0.29660406708717346 2023-01-23 11:10:01.372401: step: 264/1545, loss: 0.3192097544670105 2023-01-23 11:10:02.258408: step: 266/1545, loss: 0.5662559270858765 2023-01-23 11:10:03.119132: step: 268/1545, loss: 0.01032013725489378 2023-01-23 11:10:04.012790: step: 270/1545, loss: 0.00833909958600998 2023-01-23 11:10:04.878546: step: 272/1545, loss: 0.005549934227019548 2023-01-23 11:10:05.746009: step: 274/1545, loss: 0.03976556286215782 2023-01-23 11:10:06.609792: step: 276/1545, loss: 0.004405789542943239 2023-01-23 11:10:07.531305: step: 278/1545, loss: 0.035754989832639694 2023-01-23 11:10:08.397309: step: 280/1545, loss: 0.08648505806922913 2023-01-23 11:10:09.248936: step: 282/1545, loss: 0.012480491772294044 2023-01-23 11:10:10.107980: step: 284/1545, loss: 0.17219167947769165 2023-01-23 11:10:10.980096: step: 286/1545, loss: 0.31183576583862305 2023-01-23 11:10:11.902080: step: 288/1545, loss: 0.09087549895048141 2023-01-23 11:10:12.831114: step: 290/1545, loss: 0.721778154373169 2023-01-23 11:10:13.687968: step: 292/1545, loss: 0.07088863104581833 2023-01-23 11:10:14.517514: step: 294/1545, loss: 0.06779972463846207 2023-01-23 11:10:15.384279: step: 296/1545, loss: 0.04142181575298309 2023-01-23 11:10:16.238352: step: 298/1545, loss: 0.007796541787683964 2023-01-23 11:10:17.078611: step: 300/1545, loss: 0.9636869430541992 2023-01-23 11:10:17.939749: step: 302/1545, loss: 0.29815855622291565 2023-01-23 11:10:18.795364: step: 304/1545, loss: 0.02181580662727356 2023-01-23 11:10:19.704056: step: 306/1545, loss: 0.012651507742702961 2023-01-23 11:10:20.612860: step: 308/1545, loss: 0.07414400577545166 2023-01-23 11:10:21.510415: step: 310/1545, loss: 0.13577301800251007 2023-01-23 11:10:22.392305: step: 312/1545, loss: 0.19366343319416046 2023-01-23 11:10:23.295023: step: 314/1545, loss: 0.14293858408927917 2023-01-23 11:10:24.225483: step: 316/1545, loss: 0.050994712859392166 2023-01-23 11:10:25.069170: step: 318/1545, loss: 0.019944656640291214 2023-01-23 11:10:25.998729: step: 320/1545, loss: 0.3357393443584442 2023-01-23 11:10:26.881781: step: 322/1545, loss: 0.07202067971229553 2023-01-23 11:10:27.767693: step: 324/1545, loss: 0.22834992408752441 2023-01-23 11:10:28.641199: step: 326/1545, loss: 0.03809785842895508 2023-01-23 11:10:29.536853: step: 328/1545, loss: 0.03765934705734253 2023-01-23 11:10:30.434222: step: 330/1545, loss: 0.4527841806411743 2023-01-23 11:10:31.318223: step: 332/1545, loss: 0.06549650430679321 2023-01-23 11:10:32.197379: step: 334/1545, loss: 0.07292316854000092 2023-01-23 11:10:33.054177: step: 336/1545, loss: 0.041889891028404236 2023-01-23 11:10:33.979348: step: 338/1545, loss: 0.034304942935705185 2023-01-23 11:10:34.841486: step: 340/1545, loss: 0.19519127905368805 2023-01-23 11:10:35.717050: step: 342/1545, loss: 0.022831402719020844 2023-01-23 11:10:36.603743: step: 344/1545, loss: 0.07561147212982178 2023-01-23 11:10:37.565615: step: 346/1545, loss: 0.04916762933135033 2023-01-23 11:10:38.435156: step: 348/1545, loss: 0.0370321199297905 2023-01-23 11:10:39.295969: step: 350/1545, loss: 0.04884282872080803 2023-01-23 11:10:40.197983: step: 352/1545, loss: 0.11063123494386673 2023-01-23 11:10:41.189943: step: 354/1545, loss: 0.1548367142677307 2023-01-23 11:10:42.059850: step: 356/1545, loss: 0.033966466784477234 2023-01-23 11:10:42.944729: step: 358/1545, loss: 0.1042485162615776 2023-01-23 11:10:43.840073: step: 360/1545, loss: 0.13225583732128143 2023-01-23 11:10:44.727805: step: 362/1545, loss: 0.08577161282300949 2023-01-23 11:10:45.600234: step: 364/1545, loss: 0.12954111397266388 2023-01-23 11:10:46.447007: step: 366/1545, loss: 0.2603593170642853 2023-01-23 11:10:47.307660: step: 368/1545, loss: 0.35674044489860535 2023-01-23 11:10:48.173434: step: 370/1545, loss: 0.12632769346237183 2023-01-23 11:10:49.078432: step: 372/1545, loss: 0.10316209495067596 2023-01-23 11:10:49.973616: step: 374/1545, loss: 0.11718666553497314 2023-01-23 11:10:50.865690: step: 376/1545, loss: 0.5039945840835571 2023-01-23 11:10:51.697211: step: 378/1545, loss: 0.31556493043899536 2023-01-23 11:10:52.577214: step: 380/1545, loss: 0.47154220938682556 2023-01-23 11:10:53.437826: step: 382/1545, loss: 0.008362218737602234 2023-01-23 11:10:54.305082: step: 384/1545, loss: 0.12830808758735657 2023-01-23 11:10:55.157389: step: 386/1545, loss: 0.11176803708076477 2023-01-23 11:10:56.037578: step: 388/1545, loss: 0.07030132412910461 2023-01-23 11:10:56.950770: step: 390/1545, loss: 0.20021018385887146 2023-01-23 11:10:57.861488: step: 392/1545, loss: 0.14166438579559326 2023-01-23 11:10:58.728662: step: 394/1545, loss: 0.3653390407562256 2023-01-23 11:10:59.578059: step: 396/1545, loss: 0.10315822809934616 2023-01-23 11:11:00.410095: step: 398/1545, loss: 0.010068248957395554 2023-01-23 11:11:01.278927: step: 400/1545, loss: 0.40305331349372864 2023-01-23 11:11:02.186620: step: 402/1545, loss: 0.07096836715936661 2023-01-23 11:11:03.044009: step: 404/1545, loss: 0.31669381260871887 2023-01-23 11:11:03.888820: step: 406/1545, loss: 0.003708884119987488 2023-01-23 11:11:04.772693: step: 408/1545, loss: 0.04225245863199234 2023-01-23 11:11:05.681475: step: 410/1545, loss: 0.014897583983838558 2023-01-23 11:11:06.558564: step: 412/1545, loss: 0.035997211933135986 2023-01-23 11:11:07.488146: step: 414/1545, loss: 0.16311565041542053 2023-01-23 11:11:08.370931: step: 416/1545, loss: 2.2662312984466553 2023-01-23 11:11:09.385320: step: 418/1545, loss: 0.20975343883037567 2023-01-23 11:11:10.243823: step: 420/1545, loss: 0.48554566502571106 2023-01-23 11:11:11.129752: step: 422/1545, loss: 0.22371196746826172 2023-01-23 11:11:12.090072: step: 424/1545, loss: 1.2276256084442139 2023-01-23 11:11:12.958180: step: 426/1545, loss: 0.4474470317363739 2023-01-23 11:11:13.835973: step: 428/1545, loss: 0.3724086582660675 2023-01-23 11:11:14.716229: step: 430/1545, loss: 0.13945166766643524 2023-01-23 11:11:15.640345: step: 432/1545, loss: 0.05473262071609497 2023-01-23 11:11:16.556478: step: 434/1545, loss: 0.14966413378715515 2023-01-23 11:11:17.448966: step: 436/1545, loss: 0.002545001218095422 2023-01-23 11:11:18.350592: step: 438/1545, loss: 0.43300139904022217 2023-01-23 11:11:19.230249: step: 440/1545, loss: 0.02624848298728466 2023-01-23 11:11:20.129617: step: 442/1545, loss: 0.37883588671684265 2023-01-23 11:11:20.985097: step: 444/1545, loss: 0.009101910516619682 2023-01-23 11:11:21.866988: step: 446/1545, loss: 0.03264676779508591 2023-01-23 11:11:22.733473: step: 448/1545, loss: 0.0986451730132103 2023-01-23 11:11:23.590886: step: 450/1545, loss: 0.008665716275572777 2023-01-23 11:11:24.483004: step: 452/1545, loss: 0.07768312096595764 2023-01-23 11:11:25.331636: step: 454/1545, loss: 0.2694220244884491 2023-01-23 11:11:26.223624: step: 456/1545, loss: 0.030413031578063965 2023-01-23 11:11:27.176008: step: 458/1545, loss: 0.14545175433158875 2023-01-23 11:11:28.047278: step: 460/1545, loss: 0.14808174967765808 2023-01-23 11:11:28.950428: step: 462/1545, loss: 0.006923200562596321 2023-01-23 11:11:29.828013: step: 464/1545, loss: 0.023927249014377594 2023-01-23 11:11:30.715460: step: 466/1545, loss: 0.48693808913230896 2023-01-23 11:11:31.569837: step: 468/1545, loss: 0.04498835280537605 2023-01-23 11:11:32.419832: step: 470/1545, loss: 0.12864793837070465 2023-01-23 11:11:33.306526: step: 472/1545, loss: 0.016887865960597992 2023-01-23 11:11:34.210846: step: 474/1545, loss: 0.08125024288892746 2023-01-23 11:11:35.067575: step: 476/1545, loss: 0.036960769444704056 2023-01-23 11:11:35.953695: step: 478/1545, loss: 0.10587982833385468 2023-01-23 11:11:36.820452: step: 480/1545, loss: 0.08367984741926193 2023-01-23 11:11:37.684496: step: 482/1545, loss: 0.024721359834074974 2023-01-23 11:11:38.673036: step: 484/1545, loss: 0.038945283740758896 2023-01-23 11:11:39.595375: step: 486/1545, loss: 0.7379871010780334 2023-01-23 11:11:40.516633: step: 488/1545, loss: 0.0015341724501922727 2023-01-23 11:11:41.392133: step: 490/1545, loss: 0.0799059122800827 2023-01-23 11:11:42.288126: step: 492/1545, loss: 0.11368568241596222 2023-01-23 11:11:43.183761: step: 494/1545, loss: 0.010673398151993752 2023-01-23 11:11:44.042468: step: 496/1545, loss: 0.2748812437057495 2023-01-23 11:11:44.934531: step: 498/1545, loss: 0.08164329826831818 2023-01-23 11:11:45.905920: step: 500/1545, loss: 0.1941554695367813 2023-01-23 11:11:46.747989: step: 502/1545, loss: 0.2311743199825287 2023-01-23 11:11:47.635734: step: 504/1545, loss: 0.3848164677619934 2023-01-23 11:11:48.498935: step: 506/1545, loss: 0.13564036786556244 2023-01-23 11:11:49.352777: step: 508/1545, loss: 0.11427643150091171 2023-01-23 11:11:50.271957: step: 510/1545, loss: 0.12121862173080444 2023-01-23 11:11:51.116333: step: 512/1545, loss: 0.6367402076721191 2023-01-23 11:11:52.006129: step: 514/1545, loss: 0.0772535428404808 2023-01-23 11:11:52.876228: step: 516/1545, loss: 0.0870659202337265 2023-01-23 11:11:53.764500: step: 518/1545, loss: 0.20471499860286713 2023-01-23 11:11:54.638533: step: 520/1545, loss: 0.4872450530529022 2023-01-23 11:11:55.537224: step: 522/1545, loss: 3.003889799118042 2023-01-23 11:11:56.427978: step: 524/1545, loss: 0.13512440025806427 2023-01-23 11:11:57.303424: step: 526/1545, loss: 0.10078264772891998 2023-01-23 11:11:58.193266: step: 528/1545, loss: 0.2113860547542572 2023-01-23 11:11:59.055034: step: 530/1545, loss: 0.09888746589422226 2023-01-23 11:11:59.973088: step: 532/1545, loss: 0.04083392024040222 2023-01-23 11:12:00.853277: step: 534/1545, loss: 0.1761673539876938 2023-01-23 11:12:01.773926: step: 536/1545, loss: 0.21384641528129578 2023-01-23 11:12:02.628986: step: 538/1545, loss: 0.011142227798700333 2023-01-23 11:12:03.515912: step: 540/1545, loss: 0.19572684168815613 2023-01-23 11:12:04.373479: step: 542/1545, loss: 0.3281787931919098 2023-01-23 11:12:05.285469: step: 544/1545, loss: 0.08286109566688538 2023-01-23 11:12:06.167644: step: 546/1545, loss: 0.013071143999695778 2023-01-23 11:12:07.090230: step: 548/1545, loss: 0.06983869522809982 2023-01-23 11:12:07.939410: step: 550/1545, loss: 0.057715415954589844 2023-01-23 11:12:08.783870: step: 552/1545, loss: 0.06606537103652954 2023-01-23 11:12:09.727854: step: 554/1545, loss: 0.07725880295038223 2023-01-23 11:12:10.581487: step: 556/1545, loss: 0.028401900082826614 2023-01-23 11:12:11.460709: step: 558/1545, loss: 0.17156560719013214 2023-01-23 11:12:12.339464: step: 560/1545, loss: 0.041561782360076904 2023-01-23 11:12:13.186539: step: 562/1545, loss: 0.09588243812322617 2023-01-23 11:12:14.103951: step: 564/1545, loss: 0.038203705102205276 2023-01-23 11:12:14.985081: step: 566/1545, loss: 0.014682924374938011 2023-01-23 11:12:15.914229: step: 568/1545, loss: 0.1300286054611206 2023-01-23 11:12:16.807260: step: 570/1545, loss: 0.47607874870300293 2023-01-23 11:12:17.691414: step: 572/1545, loss: 0.13305962085723877 2023-01-23 11:12:18.556026: step: 574/1545, loss: 0.07140754908323288 2023-01-23 11:12:19.442203: step: 576/1545, loss: 0.1463322639465332 2023-01-23 11:12:20.298831: step: 578/1545, loss: 0.21686851978302002 2023-01-23 11:12:21.153564: step: 580/1545, loss: 0.05087195336818695 2023-01-23 11:12:22.090686: step: 582/1545, loss: 0.31600770354270935 2023-01-23 11:12:22.985788: step: 584/1545, loss: 0.033785510808229446 2023-01-23 11:12:23.991945: step: 586/1545, loss: 0.4946995675563812 2023-01-23 11:12:24.830859: step: 588/1545, loss: 0.1903795301914215 2023-01-23 11:12:25.730536: step: 590/1545, loss: 0.031767748296260834 2023-01-23 11:12:26.609628: step: 592/1545, loss: 0.004868737421929836 2023-01-23 11:12:27.499063: step: 594/1545, loss: 0.006789929233491421 2023-01-23 11:12:28.391077: step: 596/1545, loss: 0.19513890147209167 2023-01-23 11:12:29.275745: step: 598/1545, loss: 0.0851873978972435 2023-01-23 11:12:30.159574: step: 600/1545, loss: 0.08827164769172668 2023-01-23 11:12:31.091587: step: 602/1545, loss: 0.05158533155918121 2023-01-23 11:12:31.968054: step: 604/1545, loss: 0.03287786617875099 2023-01-23 11:12:32.788549: step: 606/1545, loss: 0.1489631086587906 2023-01-23 11:12:33.662354: step: 608/1545, loss: 0.0675390288233757 2023-01-23 11:12:34.534994: step: 610/1545, loss: 0.009599191136658192 2023-01-23 11:12:35.509796: step: 612/1545, loss: 0.3304363489151001 2023-01-23 11:12:36.422196: step: 614/1545, loss: 0.03734515607357025 2023-01-23 11:12:37.351884: step: 616/1545, loss: 0.40316295623779297 2023-01-23 11:12:38.226455: step: 618/1545, loss: 0.08253365010023117 2023-01-23 11:12:39.141538: step: 620/1545, loss: 0.13492369651794434 2023-01-23 11:12:40.032472: step: 622/1545, loss: 0.08892790973186493 2023-01-23 11:12:40.966898: step: 624/1545, loss: 0.032828330993652344 2023-01-23 11:12:41.887344: step: 626/1545, loss: 0.006632897071540356 2023-01-23 11:12:42.732367: step: 628/1545, loss: 0.03721248731017113 2023-01-23 11:12:43.671162: step: 630/1545, loss: 0.0323525071144104 2023-01-23 11:12:44.525291: step: 632/1545, loss: 0.14120137691497803 2023-01-23 11:12:45.406884: step: 634/1545, loss: 0.1941104233264923 2023-01-23 11:12:46.272895: step: 636/1545, loss: 0.017538990825414658 2023-01-23 11:12:47.127707: step: 638/1545, loss: 0.12880045175552368 2023-01-23 11:12:48.007530: step: 640/1545, loss: 0.13854166865348816 2023-01-23 11:12:48.958682: step: 642/1545, loss: 0.10738556832075119 2023-01-23 11:12:49.838940: step: 644/1545, loss: 0.0357610248029232 2023-01-23 11:12:50.723645: step: 646/1545, loss: 0.18611018359661102 2023-01-23 11:12:51.626062: step: 648/1545, loss: 0.18801558017730713 2023-01-23 11:12:52.497162: step: 650/1545, loss: 0.059677448123693466 2023-01-23 11:12:53.339681: step: 652/1545, loss: 0.04303755238652229 2023-01-23 11:12:54.197276: step: 654/1545, loss: 0.08988326787948608 2023-01-23 11:12:55.050836: step: 656/1545, loss: 0.6501333117485046 2023-01-23 11:12:55.968960: step: 658/1545, loss: 0.08410674333572388 2023-01-23 11:12:56.897828: step: 660/1545, loss: 0.25233250856399536 2023-01-23 11:12:57.807850: step: 662/1545, loss: 0.05266822129487991 2023-01-23 11:12:58.717466: step: 664/1545, loss: 0.16605937480926514 2023-01-23 11:12:59.562025: step: 666/1545, loss: 0.08240962028503418 2023-01-23 11:13:00.419950: step: 668/1545, loss: 0.07672220468521118 2023-01-23 11:13:01.295119: step: 670/1545, loss: 0.10517778992652893 2023-01-23 11:13:02.177520: step: 672/1545, loss: 0.42727670073509216 2023-01-23 11:13:03.137003: step: 674/1545, loss: 0.2106468379497528 2023-01-23 11:13:04.052688: step: 676/1545, loss: 0.2096925526857376 2023-01-23 11:13:04.908895: step: 678/1545, loss: 0.01704092137515545 2023-01-23 11:13:05.767960: step: 680/1545, loss: 0.16294081509113312 2023-01-23 11:13:06.709763: step: 682/1545, loss: 0.31913480162620544 2023-01-23 11:13:07.616253: step: 684/1545, loss: 0.03468220680952072 2023-01-23 11:13:08.493223: step: 686/1545, loss: 0.054979532957077026 2023-01-23 11:13:09.432108: step: 688/1545, loss: 0.20547564327716827 2023-01-23 11:13:10.268569: step: 690/1545, loss: 0.4822363555431366 2023-01-23 11:13:11.224665: step: 692/1545, loss: 0.04030156135559082 2023-01-23 11:13:12.117202: step: 694/1545, loss: 0.04686526954174042 2023-01-23 11:13:13.092042: step: 696/1545, loss: 0.21007314324378967 2023-01-23 11:13:13.953528: step: 698/1545, loss: 0.21245117485523224 2023-01-23 11:13:14.827833: step: 700/1545, loss: 0.2113896906375885 2023-01-23 11:13:15.745663: step: 702/1545, loss: 0.21778473258018494 2023-01-23 11:13:16.668930: step: 704/1545, loss: 0.0950431153178215 2023-01-23 11:13:17.545975: step: 706/1545, loss: 0.38941338658332825 2023-01-23 11:13:18.410999: step: 708/1545, loss: 0.1352226883172989 2023-01-23 11:13:19.298485: step: 710/1545, loss: 0.025278344750404358 2023-01-23 11:13:20.166703: step: 712/1545, loss: 0.13293305039405823 2023-01-23 11:13:21.060985: step: 714/1545, loss: 0.5556831359863281 2023-01-23 11:13:22.024410: step: 716/1545, loss: 0.023291314020752907 2023-01-23 11:13:22.898505: step: 718/1545, loss: 0.10716941952705383 2023-01-23 11:13:23.798948: step: 720/1545, loss: 0.07969678193330765 2023-01-23 11:13:24.685472: step: 722/1545, loss: 0.25742435455322266 2023-01-23 11:13:25.627163: step: 724/1545, loss: 0.004476648755371571 2023-01-23 11:13:26.496284: step: 726/1545, loss: 0.3428897559642792 2023-01-23 11:13:27.383697: step: 728/1545, loss: 0.2167242020368576 2023-01-23 11:13:28.278477: step: 730/1545, loss: 0.23379425704479218 2023-01-23 11:13:29.183043: step: 732/1545, loss: 0.261472225189209 2023-01-23 11:13:30.043041: step: 734/1545, loss: 0.01767835207283497 2023-01-23 11:13:30.928554: step: 736/1545, loss: 0.18986088037490845 2023-01-23 11:13:31.806866: step: 738/1545, loss: 0.02032504975795746 2023-01-23 11:13:32.649829: step: 740/1545, loss: 0.039623960852622986 2023-01-23 11:13:33.554383: step: 742/1545, loss: 0.023272119462490082 2023-01-23 11:13:34.495940: step: 744/1545, loss: 0.04926418885588646 2023-01-23 11:13:35.353657: step: 746/1545, loss: 0.039546746760606766 2023-01-23 11:13:36.222686: step: 748/1545, loss: 0.02852335385978222 2023-01-23 11:13:37.106628: step: 750/1545, loss: 0.10827310383319855 2023-01-23 11:13:37.985674: step: 752/1545, loss: 0.22941012680530548 2023-01-23 11:13:38.842155: step: 754/1545, loss: 0.1857902854681015 2023-01-23 11:13:39.705586: step: 756/1545, loss: 0.13635048270225525 2023-01-23 11:13:40.580727: step: 758/1545, loss: 1.4221762418746948 2023-01-23 11:13:41.418640: step: 760/1545, loss: 0.19707687199115753 2023-01-23 11:13:42.283279: step: 762/1545, loss: 0.04860560595989227 2023-01-23 11:13:43.108994: step: 764/1545, loss: 0.3645841181278229 2023-01-23 11:13:43.969651: step: 766/1545, loss: 0.19550292193889618 2023-01-23 11:13:44.802748: step: 768/1545, loss: 0.9555543065071106 2023-01-23 11:13:45.696964: step: 770/1545, loss: 0.07378409057855606 2023-01-23 11:13:46.571797: step: 772/1545, loss: 0.2167089283466339 2023-01-23 11:13:47.449389: step: 774/1545, loss: 0.28483855724334717 2023-01-23 11:13:48.339489: step: 776/1545, loss: 0.1041065976023674 2023-01-23 11:13:49.206114: step: 778/1545, loss: 0.2162691056728363 2023-01-23 11:13:50.071869: step: 780/1545, loss: 0.04233953729271889 2023-01-23 11:13:50.918436: step: 782/1545, loss: 0.137476846575737 2023-01-23 11:13:51.802706: step: 784/1545, loss: 0.047542061656713486 2023-01-23 11:13:52.660284: step: 786/1545, loss: 0.10367608815431595 2023-01-23 11:13:53.513975: step: 788/1545, loss: 0.03451948240399361 2023-01-23 11:13:54.422520: step: 790/1545, loss: 0.21402892470359802 2023-01-23 11:13:55.270039: step: 792/1545, loss: 0.06897831708192825 2023-01-23 11:13:56.143091: step: 794/1545, loss: 0.2860962450504303 2023-01-23 11:13:57.026217: step: 796/1545, loss: 0.016417719423770905 2023-01-23 11:13:57.940187: step: 798/1545, loss: 0.40273165702819824 2023-01-23 11:13:58.829321: step: 800/1545, loss: 0.2931528687477112 2023-01-23 11:13:59.686208: step: 802/1545, loss: 0.08580625057220459 2023-01-23 11:14:00.543793: step: 804/1545, loss: 0.21715578436851501 2023-01-23 11:14:01.422187: step: 806/1545, loss: 0.18315710127353668 2023-01-23 11:14:02.295014: step: 808/1545, loss: 0.13382600247859955 2023-01-23 11:14:03.222947: step: 810/1545, loss: 0.011296266689896584 2023-01-23 11:14:04.071469: step: 812/1545, loss: 0.005141225643455982 2023-01-23 11:14:04.923917: step: 814/1545, loss: 0.10832922905683517 2023-01-23 11:14:05.802314: step: 816/1545, loss: 0.08632265776395798 2023-01-23 11:14:06.661806: step: 818/1545, loss: 0.68695068359375 2023-01-23 11:14:07.647930: step: 820/1545, loss: 0.07980053126811981 2023-01-23 11:14:08.541922: step: 822/1545, loss: 0.05922772362828255 2023-01-23 11:14:09.404523: step: 824/1545, loss: 0.12614905834197998 2023-01-23 11:14:10.301827: step: 826/1545, loss: 0.011050507426261902 2023-01-23 11:14:11.157592: step: 828/1545, loss: 0.1574024260044098 2023-01-23 11:14:11.983052: step: 830/1545, loss: 0.08168588578701019 2023-01-23 11:14:12.939563: step: 832/1545, loss: 0.023349303752183914 2023-01-23 11:14:13.806176: step: 834/1545, loss: 0.34355494379997253 2023-01-23 11:14:14.704186: step: 836/1545, loss: 0.22448554635047913 2023-01-23 11:14:15.595368: step: 838/1545, loss: 0.15034478902816772 2023-01-23 11:14:16.436406: step: 840/1545, loss: 0.1547023504972458 2023-01-23 11:14:17.312328: step: 842/1545, loss: 0.15550613403320312 2023-01-23 11:14:18.208738: step: 844/1545, loss: 0.033354103565216064 2023-01-23 11:14:19.117806: step: 846/1545, loss: 0.07851845026016235 2023-01-23 11:14:20.017474: step: 848/1545, loss: 0.029631957411766052 2023-01-23 11:14:20.941574: step: 850/1545, loss: 0.035180747509002686 2023-01-23 11:14:21.831188: step: 852/1545, loss: 0.027974236756563187 2023-01-23 11:14:22.769991: step: 854/1545, loss: 0.017526548355817795 2023-01-23 11:14:23.628928: step: 856/1545, loss: 0.0018667055992409587 2023-01-23 11:14:24.481428: step: 858/1545, loss: 0.0900861918926239 2023-01-23 11:14:25.351924: step: 860/1545, loss: 0.23965072631835938 2023-01-23 11:14:26.220179: step: 862/1545, loss: 0.027904199436306953 2023-01-23 11:14:27.124595: step: 864/1545, loss: 0.1469879001379013 2023-01-23 11:14:27.991186: step: 866/1545, loss: 0.13223940134048462 2023-01-23 11:14:28.904294: step: 868/1545, loss: 0.05071950703859329 2023-01-23 11:14:29.757615: step: 870/1545, loss: 0.42720043659210205 2023-01-23 11:14:30.689540: step: 872/1545, loss: 0.49632811546325684 2023-01-23 11:14:31.600253: step: 874/1545, loss: 0.02342596836388111 2023-01-23 11:14:32.480912: step: 876/1545, loss: 0.26079344749450684 2023-01-23 11:14:33.331174: step: 878/1545, loss: 0.016414664685726166 2023-01-23 11:14:34.249861: step: 880/1545, loss: 0.7508044838905334 2023-01-23 11:14:35.126021: step: 882/1545, loss: 0.19761539995670319 2023-01-23 11:14:36.060332: step: 884/1545, loss: 0.0947355255484581 2023-01-23 11:14:36.937677: step: 886/1545, loss: 0.10605277866125107 2023-01-23 11:14:37.786758: step: 888/1545, loss: 0.04027430713176727 2023-01-23 11:14:38.632392: step: 890/1545, loss: 0.31451502442359924 2023-01-23 11:14:39.519006: step: 892/1545, loss: 0.14070077240467072 2023-01-23 11:14:40.395660: step: 894/1545, loss: 0.10286014527082443 2023-01-23 11:14:41.262416: step: 896/1545, loss: 0.028246507048606873 2023-01-23 11:14:42.143790: step: 898/1545, loss: 0.3340989947319031 2023-01-23 11:14:43.024708: step: 900/1545, loss: 0.11708532273769379 2023-01-23 11:14:43.897604: step: 902/1545, loss: 0.07461297512054443 2023-01-23 11:14:44.845153: step: 904/1545, loss: 0.18374690413475037 2023-01-23 11:14:45.684705: step: 906/1545, loss: 0.2073172628879547 2023-01-23 11:14:46.523777: step: 908/1545, loss: 0.1748826503753662 2023-01-23 11:14:47.425049: step: 910/1545, loss: 0.12695734202861786 2023-01-23 11:14:48.337123: step: 912/1545, loss: 0.012667284347116947 2023-01-23 11:14:49.173884: step: 914/1545, loss: 0.1945423185825348 2023-01-23 11:14:50.028520: step: 916/1545, loss: 0.012820537202060223 2023-01-23 11:14:50.931047: step: 918/1545, loss: 0.45718538761138916 2023-01-23 11:14:51.785148: step: 920/1545, loss: 0.055163316428661346 2023-01-23 11:14:52.648230: step: 922/1545, loss: 0.06657776236534119 2023-01-23 11:14:53.514817: step: 924/1545, loss: 0.08373470604419708 2023-01-23 11:14:54.419307: step: 926/1545, loss: 0.09333854913711548 2023-01-23 11:14:55.320918: step: 928/1545, loss: 0.01634370908141136 2023-01-23 11:14:56.202393: step: 930/1545, loss: 0.302001416683197 2023-01-23 11:14:57.078630: step: 932/1545, loss: 0.17306581139564514 2023-01-23 11:14:57.945918: step: 934/1545, loss: 0.16734065115451813 2023-01-23 11:14:58.816862: step: 936/1545, loss: 0.024854231625795364 2023-01-23 11:14:59.679218: step: 938/1545, loss: 0.1333828717470169 2023-01-23 11:15:00.516396: step: 940/1545, loss: 0.03376948460936546 2023-01-23 11:15:01.376738: step: 942/1545, loss: 0.06823398917913437 2023-01-23 11:15:02.295379: step: 944/1545, loss: 0.011505573987960815 2023-01-23 11:15:03.163071: step: 946/1545, loss: 0.1239728331565857 2023-01-23 11:15:04.019496: step: 948/1545, loss: 0.06011119484901428 2023-01-23 11:15:04.902674: step: 950/1545, loss: 0.06463977694511414 2023-01-23 11:15:05.759650: step: 952/1545, loss: 0.19963134825229645 2023-01-23 11:15:06.704047: step: 954/1545, loss: 0.422184556722641 2023-01-23 11:15:07.547232: step: 956/1545, loss: 0.056134965270757675 2023-01-23 11:15:08.400772: step: 958/1545, loss: 0.017846964299678802 2023-01-23 11:15:09.322187: step: 960/1545, loss: 0.10315492004156113 2023-01-23 11:15:10.189099: step: 962/1545, loss: 0.2719258666038513 2023-01-23 11:15:11.044557: step: 964/1545, loss: 0.010393880307674408 2023-01-23 11:15:11.917899: step: 966/1545, loss: 0.10454224795103073 2023-01-23 11:15:12.769857: step: 968/1545, loss: 0.03890397399663925 2023-01-23 11:15:13.655170: step: 970/1545, loss: 0.20240963995456696 2023-01-23 11:15:14.543256: step: 972/1545, loss: 0.1645590215921402 2023-01-23 11:15:15.391966: step: 974/1545, loss: 0.0279763825237751 2023-01-23 11:15:16.324012: step: 976/1545, loss: 0.23431235551834106 2023-01-23 11:15:17.234253: step: 978/1545, loss: 0.13724370300769806 2023-01-23 11:15:18.095436: step: 980/1545, loss: 0.46212852001190186 2023-01-23 11:15:18.990798: step: 982/1545, loss: 0.06945483386516571 2023-01-23 11:15:19.879366: step: 984/1545, loss: 0.09822395443916321 2023-01-23 11:15:20.766724: step: 986/1545, loss: 0.0436883382499218 2023-01-23 11:15:21.664532: step: 988/1545, loss: 0.11223756521940231 2023-01-23 11:15:22.527590: step: 990/1545, loss: 0.6194398999214172 2023-01-23 11:15:23.400775: step: 992/1545, loss: 0.01929832063615322 2023-01-23 11:15:24.258043: step: 994/1545, loss: 0.620954692363739 2023-01-23 11:15:25.154960: step: 996/1545, loss: 0.019447896629571915 2023-01-23 11:15:26.003354: step: 998/1545, loss: 0.008665762841701508 2023-01-23 11:15:26.870380: step: 1000/1545, loss: 0.17516978085041046 2023-01-23 11:15:27.730425: step: 1002/1545, loss: 0.10035520046949387 2023-01-23 11:15:28.671642: step: 1004/1545, loss: 0.02225865237414837 2023-01-23 11:15:29.577884: step: 1006/1545, loss: 0.11413529515266418 2023-01-23 11:15:30.477166: step: 1008/1545, loss: 0.03255247697234154 2023-01-23 11:15:31.371369: step: 1010/1545, loss: 0.07833828777074814 2023-01-23 11:15:32.259889: step: 1012/1545, loss: 0.0620344839990139 2023-01-23 11:15:33.119115: step: 1014/1545, loss: 0.21966007351875305 2023-01-23 11:15:34.023354: step: 1016/1545, loss: 0.1451462060213089 2023-01-23 11:15:34.890173: step: 1018/1545, loss: 0.1095099225640297 2023-01-23 11:15:35.783720: step: 1020/1545, loss: 0.2225726693868637 2023-01-23 11:15:36.645983: step: 1022/1545, loss: 0.049324922263622284 2023-01-23 11:15:37.531604: step: 1024/1545, loss: 0.016494734212756157 2023-01-23 11:15:38.399455: step: 1026/1545, loss: 0.2572135329246521 2023-01-23 11:15:39.292965: step: 1028/1545, loss: 0.08101215213537216 2023-01-23 11:15:40.175441: step: 1030/1545, loss: 0.014855846762657166 2023-01-23 11:15:41.034875: step: 1032/1545, loss: 0.3740232586860657 2023-01-23 11:15:41.927860: step: 1034/1545, loss: 0.09132156521081924 2023-01-23 11:15:42.817645: step: 1036/1545, loss: 0.26274171471595764 2023-01-23 11:15:43.659121: step: 1038/1545, loss: 0.09928664565086365 2023-01-23 11:15:44.555300: step: 1040/1545, loss: 0.06899759918451309 2023-01-23 11:15:45.535708: step: 1042/1545, loss: 0.10853227227926254 2023-01-23 11:15:46.463534: step: 1044/1545, loss: 0.17870071530342102 2023-01-23 11:15:47.329755: step: 1046/1545, loss: 0.058609575033187866 2023-01-23 11:15:48.186273: step: 1048/1545, loss: 0.020629342645406723 2023-01-23 11:15:49.046255: step: 1050/1545, loss: 0.017457393929362297 2023-01-23 11:15:49.899260: step: 1052/1545, loss: 0.1165604367852211 2023-01-23 11:15:50.762598: step: 1054/1545, loss: 0.15187138319015503 2023-01-23 11:15:51.692155: step: 1056/1545, loss: 0.11733736842870712 2023-01-23 11:15:52.573669: step: 1058/1545, loss: 0.09895311295986176 2023-01-23 11:15:53.450784: step: 1060/1545, loss: 0.010673842392861843 2023-01-23 11:15:54.307104: step: 1062/1545, loss: 0.006190137937664986 2023-01-23 11:15:55.169176: step: 1064/1545, loss: 0.041343942284584045 2023-01-23 11:15:56.029165: step: 1066/1545, loss: 0.06999295949935913 2023-01-23 11:15:56.880659: step: 1068/1545, loss: 0.39502060413360596 2023-01-23 11:15:57.763567: step: 1070/1545, loss: 0.10739730298519135 2023-01-23 11:15:58.652703: step: 1072/1545, loss: 0.07758968323469162 2023-01-23 11:15:59.534530: step: 1074/1545, loss: 0.1680116504430771 2023-01-23 11:16:00.401152: step: 1076/1545, loss: 0.06651654094457626 2023-01-23 11:16:01.307227: step: 1078/1545, loss: 0.3749375343322754 2023-01-23 11:16:02.171589: step: 1080/1545, loss: 0.0008708712994121015 2023-01-23 11:16:03.065851: step: 1082/1545, loss: 0.20151081681251526 2023-01-23 11:16:03.938238: step: 1084/1545, loss: 0.08241753280162811 2023-01-23 11:16:04.800840: step: 1086/1545, loss: 0.14877864718437195 2023-01-23 11:16:05.686466: step: 1088/1545, loss: 0.16331465542316437 2023-01-23 11:16:06.585557: step: 1090/1545, loss: 0.3698332905769348 2023-01-23 11:16:07.447470: step: 1092/1545, loss: 0.02083229273557663 2023-01-23 11:16:08.329582: step: 1094/1545, loss: 0.015338077209889889 2023-01-23 11:16:09.256581: step: 1096/1545, loss: 0.08250236511230469 2023-01-23 11:16:10.168319: step: 1098/1545, loss: 0.015649208799004555 2023-01-23 11:16:11.143423: step: 1100/1545, loss: 0.012374330312013626 2023-01-23 11:16:12.021399: step: 1102/1545, loss: 0.05276254937052727 2023-01-23 11:16:12.879261: step: 1104/1545, loss: 0.054598256945610046 2023-01-23 11:16:13.789233: step: 1106/1545, loss: 0.4655459523200989 2023-01-23 11:16:14.659865: step: 1108/1545, loss: 0.31059324741363525 2023-01-23 11:16:15.552737: step: 1110/1545, loss: 0.26249778270721436 2023-01-23 11:16:16.448209: step: 1112/1545, loss: 0.0029943466652184725 2023-01-23 11:16:17.307101: step: 1114/1545, loss: 0.11557217687368393 2023-01-23 11:16:18.154788: step: 1116/1545, loss: 0.2866608798503876 2023-01-23 11:16:19.032073: step: 1118/1545, loss: 0.045597732067108154 2023-01-23 11:16:19.965630: step: 1120/1545, loss: 0.011357072740793228 2023-01-23 11:16:20.852885: step: 1122/1545, loss: 0.21159592270851135 2023-01-23 11:16:21.791397: step: 1124/1545, loss: 0.035383887588977814 2023-01-23 11:16:22.695761: step: 1126/1545, loss: 0.009799524210393429 2023-01-23 11:16:23.583304: step: 1128/1545, loss: 0.23597048223018646 2023-01-23 11:16:24.446352: step: 1130/1545, loss: 0.15553507208824158 2023-01-23 11:16:25.276108: step: 1132/1545, loss: 0.15483029186725616 2023-01-23 11:16:26.127378: step: 1134/1545, loss: 0.039455436170101166 2023-01-23 11:16:26.998846: step: 1136/1545, loss: 0.23172859847545624 2023-01-23 11:16:27.896560: step: 1138/1545, loss: 0.33119112253189087 2023-01-23 11:16:28.744621: step: 1140/1545, loss: 0.10864441841840744 2023-01-23 11:16:29.608298: step: 1142/1545, loss: 0.003980394918471575 2023-01-23 11:16:30.452629: step: 1144/1545, loss: 0.7844619154930115 2023-01-23 11:16:31.377714: step: 1146/1545, loss: 0.057876162230968475 2023-01-23 11:16:32.265122: step: 1148/1545, loss: 0.31182989478111267 2023-01-23 11:16:33.106798: step: 1150/1545, loss: 0.09544779360294342 2023-01-23 11:16:33.973231: step: 1152/1545, loss: 1.7350687980651855 2023-01-23 11:16:34.842931: step: 1154/1545, loss: 0.19038331508636475 2023-01-23 11:16:35.765449: step: 1156/1545, loss: 0.14931832253932953 2023-01-23 11:16:36.639057: step: 1158/1545, loss: 0.32004886865615845 2023-01-23 11:16:37.546240: step: 1160/1545, loss: 0.11638114601373672 2023-01-23 11:16:38.419458: step: 1162/1545, loss: 0.06149587407708168 2023-01-23 11:16:39.340707: step: 1164/1545, loss: 0.05409860610961914 2023-01-23 11:16:40.203254: step: 1166/1545, loss: 0.020946254953742027 2023-01-23 11:16:41.118756: step: 1168/1545, loss: 0.1267639547586441 2023-01-23 11:16:41.994087: step: 1170/1545, loss: 0.12625627219676971 2023-01-23 11:16:42.934563: step: 1172/1545, loss: 0.18511024117469788 2023-01-23 11:16:43.788185: step: 1174/1545, loss: 0.10080572217702866 2023-01-23 11:16:44.666164: step: 1176/1545, loss: 0.10364317893981934 2023-01-23 11:16:45.553922: step: 1178/1545, loss: 0.013958100229501724 2023-01-23 11:16:46.426012: step: 1180/1545, loss: 0.3535335063934326 2023-01-23 11:16:47.327912: step: 1182/1545, loss: 0.10893089324235916 2023-01-23 11:16:48.197669: step: 1184/1545, loss: 0.0809602439403534 2023-01-23 11:16:49.033842: step: 1186/1545, loss: 0.39206868410110474 2023-01-23 11:16:49.863115: step: 1188/1545, loss: 0.10611270368099213 2023-01-23 11:16:50.712884: step: 1190/1545, loss: 0.24174146354198456 2023-01-23 11:16:51.567504: step: 1192/1545, loss: 0.37044206261634827 2023-01-23 11:16:52.453523: step: 1194/1545, loss: 0.04239824414253235 2023-01-23 11:16:53.345690: step: 1196/1545, loss: 0.5564045906066895 2023-01-23 11:16:54.222525: step: 1198/1545, loss: 0.16712138056755066 2023-01-23 11:16:55.094880: step: 1200/1545, loss: 0.09282877296209335 2023-01-23 11:16:55.966281: step: 1202/1545, loss: 0.08275050669908524 2023-01-23 11:16:56.815541: step: 1204/1545, loss: 0.10304221510887146 2023-01-23 11:16:57.714910: step: 1206/1545, loss: 0.006306109484285116 2023-01-23 11:16:58.556290: step: 1208/1545, loss: 0.10891981422901154 2023-01-23 11:16:59.410232: step: 1210/1545, loss: 0.08808955550193787 2023-01-23 11:17:00.314798: step: 1212/1545, loss: 0.365999698638916 2023-01-23 11:17:01.186016: step: 1214/1545, loss: 0.7343482971191406 2023-01-23 11:17:02.009119: step: 1216/1545, loss: 0.21154366433620453 2023-01-23 11:17:02.883866: step: 1218/1545, loss: 0.06640321016311646 2023-01-23 11:17:03.791119: step: 1220/1545, loss: 0.11563145369291306 2023-01-23 11:17:04.659053: step: 1222/1545, loss: 0.030897358432412148 2023-01-23 11:17:05.534924: step: 1224/1545, loss: 0.2159613072872162 2023-01-23 11:17:06.384556: step: 1226/1545, loss: 0.18824413418769836 2023-01-23 11:17:07.237762: step: 1228/1545, loss: 0.08274410665035248 2023-01-23 11:17:08.122589: step: 1230/1545, loss: 0.2625105679035187 2023-01-23 11:17:08.990147: step: 1232/1545, loss: 0.4913251996040344 2023-01-23 11:17:09.942923: step: 1234/1545, loss: 0.10360889136791229 2023-01-23 11:17:10.795092: step: 1236/1545, loss: 0.056666407734155655 2023-01-23 11:17:11.677302: step: 1238/1545, loss: 0.11749307811260223 2023-01-23 11:17:12.650847: step: 1240/1545, loss: 0.06017636880278587 2023-01-23 11:17:13.521734: step: 1242/1545, loss: 0.15612758696079254 2023-01-23 11:17:14.426965: step: 1244/1545, loss: 0.06760764122009277 2023-01-23 11:17:15.288080: step: 1246/1545, loss: 0.09157752245664597 2023-01-23 11:17:16.192950: step: 1248/1545, loss: 0.6892033815383911 2023-01-23 11:17:17.136650: step: 1250/1545, loss: 0.030992435291409492 2023-01-23 11:17:18.030723: step: 1252/1545, loss: 0.08347000181674957 2023-01-23 11:17:18.916254: step: 1254/1545, loss: 0.07196782529354095 2023-01-23 11:17:19.825404: step: 1256/1545, loss: 0.19195280969142914 2023-01-23 11:17:20.797013: step: 1258/1545, loss: 0.16451607644557953 2023-01-23 11:17:21.686130: step: 1260/1545, loss: 0.14811627566814423 2023-01-23 11:17:22.570739: step: 1262/1545, loss: 0.25732722878456116 2023-01-23 11:17:23.513614: step: 1264/1545, loss: 0.1878247708082199 2023-01-23 11:17:24.401571: step: 1266/1545, loss: 0.08699698001146317 2023-01-23 11:17:25.254004: step: 1268/1545, loss: 0.537592351436615 2023-01-23 11:17:26.150466: step: 1270/1545, loss: 0.2327297180891037 2023-01-23 11:17:27.052775: step: 1272/1545, loss: 0.11256994307041168 2023-01-23 11:17:28.056625: step: 1274/1545, loss: 0.31149935722351074 2023-01-23 11:17:28.967279: step: 1276/1545, loss: 0.062147125601768494 2023-01-23 11:17:29.828592: step: 1278/1545, loss: 0.021258454769849777 2023-01-23 11:17:30.718478: step: 1280/1545, loss: 0.2620702385902405 2023-01-23 11:17:31.618884: step: 1282/1545, loss: 0.05982333794236183 2023-01-23 11:17:32.504840: step: 1284/1545, loss: 0.5745018720626831 2023-01-23 11:17:33.384408: step: 1286/1545, loss: 0.06619583070278168 2023-01-23 11:17:34.256092: step: 1288/1545, loss: 0.03611734136939049 2023-01-23 11:17:35.107226: step: 1290/1545, loss: 0.1400676667690277 2023-01-23 11:17:35.954131: step: 1292/1545, loss: 0.05899372324347496 2023-01-23 11:17:36.821258: step: 1294/1545, loss: 0.04795757308602333 2023-01-23 11:17:37.728694: step: 1296/1545, loss: 0.05157911777496338 2023-01-23 11:17:38.620330: step: 1298/1545, loss: 0.051534783095121384 2023-01-23 11:17:39.492971: step: 1300/1545, loss: 0.14338384568691254 2023-01-23 11:17:40.417574: step: 1302/1545, loss: 0.29507699608802795 2023-01-23 11:17:41.295744: step: 1304/1545, loss: 0.005819431506097317 2023-01-23 11:17:42.185424: step: 1306/1545, loss: 0.19906070828437805 2023-01-23 11:17:43.092462: step: 1308/1545, loss: 0.210285022854805 2023-01-23 11:17:43.954605: step: 1310/1545, loss: 0.06163962185382843 2023-01-23 11:17:44.893169: step: 1312/1545, loss: 0.07197873294353485 2023-01-23 11:17:45.800812: step: 1314/1545, loss: 0.6183467507362366 2023-01-23 11:17:46.726933: step: 1316/1545, loss: 0.2386784851551056 2023-01-23 11:17:47.615117: step: 1318/1545, loss: 0.01895933598279953 2023-01-23 11:17:48.511626: step: 1320/1545, loss: 0.3966755270957947 2023-01-23 11:17:49.350454: step: 1322/1545, loss: 0.1416349858045578 2023-01-23 11:17:50.251284: step: 1324/1545, loss: 0.04974187910556793 2023-01-23 11:17:51.110962: step: 1326/1545, loss: 0.017580438405275345 2023-01-23 11:17:51.975114: step: 1328/1545, loss: 0.13330964744091034 2023-01-23 11:17:52.855740: step: 1330/1545, loss: 0.07521162182092667 2023-01-23 11:17:53.733052: step: 1332/1545, loss: 0.496235191822052 2023-01-23 11:17:54.611999: step: 1334/1545, loss: 0.3488885760307312 2023-01-23 11:17:55.499257: step: 1336/1545, loss: 0.14272931218147278 2023-01-23 11:17:56.355770: step: 1338/1545, loss: 0.07417437434196472 2023-01-23 11:17:57.238240: step: 1340/1545, loss: 0.09155886620283127 2023-01-23 11:17:58.141392: step: 1342/1545, loss: 0.3449767529964447 2023-01-23 11:17:59.005594: step: 1344/1545, loss: 0.3450646698474884 2023-01-23 11:17:59.874957: step: 1346/1545, loss: 0.010285316035151482 2023-01-23 11:18:00.746454: step: 1348/1545, loss: 0.09496025741100311 2023-01-23 11:18:01.618363: step: 1350/1545, loss: 0.12634287774562836 2023-01-23 11:18:02.521941: step: 1352/1545, loss: 0.13793911039829254 2023-01-23 11:18:03.436164: step: 1354/1545, loss: 0.03847800940275192 2023-01-23 11:18:04.301272: step: 1356/1545, loss: 0.07410001754760742 2023-01-23 11:18:05.148871: step: 1358/1545, loss: 0.039048533886671066 2023-01-23 11:18:06.022765: step: 1360/1545, loss: 0.0499277263879776 2023-01-23 11:18:06.895208: step: 1362/1545, loss: 0.1782938688993454 2023-01-23 11:18:07.802009: step: 1364/1545, loss: 0.7013855576515198 2023-01-23 11:18:08.701860: step: 1366/1545, loss: 0.06970935314893723 2023-01-23 11:18:09.593191: step: 1368/1545, loss: 0.07753366231918335 2023-01-23 11:18:10.478932: step: 1370/1545, loss: 0.35329529643058777 2023-01-23 11:18:11.340793: step: 1372/1545, loss: 0.03011961840093136 2023-01-23 11:18:12.285649: step: 1374/1545, loss: 0.002610130701214075 2023-01-23 11:18:13.157028: step: 1376/1545, loss: 0.17152754962444305 2023-01-23 11:18:14.041084: step: 1378/1545, loss: 0.3956810534000397 2023-01-23 11:18:14.898483: step: 1380/1545, loss: 0.32705503702163696 2023-01-23 11:18:15.805018: step: 1382/1545, loss: 0.1752057820558548 2023-01-23 11:18:16.662618: step: 1384/1545, loss: 0.057797349989414215 2023-01-23 11:18:17.558247: step: 1386/1545, loss: 0.14061012864112854 2023-01-23 11:18:18.476913: step: 1388/1545, loss: 0.1788717657327652 2023-01-23 11:18:19.314447: step: 1390/1545, loss: 0.03527061268687248 2023-01-23 11:18:20.183001: step: 1392/1545, loss: 1.0440680980682373 2023-01-23 11:18:21.034988: step: 1394/1545, loss: 0.7723804712295532 2023-01-23 11:18:21.902327: step: 1396/1545, loss: 0.0686454027891159 2023-01-23 11:18:22.885504: step: 1398/1545, loss: 0.03339575603604317 2023-01-23 11:18:23.777178: step: 1400/1545, loss: 2.437680959701538 2023-01-23 11:18:24.653703: step: 1402/1545, loss: 0.2579818665981293 2023-01-23 11:18:25.495085: step: 1404/1545, loss: 0.11691048741340637 2023-01-23 11:18:26.334909: step: 1406/1545, loss: 0.01153666339814663 2023-01-23 11:18:27.200098: step: 1408/1545, loss: 0.07937304675579071 2023-01-23 11:18:28.077867: step: 1410/1545, loss: 0.18387629091739655 2023-01-23 11:18:28.939910: step: 1412/1545, loss: 0.23072806000709534 2023-01-23 11:18:29.780604: step: 1414/1545, loss: 0.6657022833824158 2023-01-23 11:18:30.646634: step: 1416/1545, loss: 0.17946934700012207 2023-01-23 11:18:31.509219: step: 1418/1545, loss: 0.059706393629312515 2023-01-23 11:18:32.401114: step: 1420/1545, loss: 0.004473702050745487 2023-01-23 11:18:33.230236: step: 1422/1545, loss: 0.08594992756843567 2023-01-23 11:18:34.085304: step: 1424/1545, loss: 0.04941766709089279 2023-01-23 11:18:34.989130: step: 1426/1545, loss: 0.01941639930009842 2023-01-23 11:18:35.833089: step: 1428/1545, loss: 0.08536592125892639 2023-01-23 11:18:36.817782: step: 1430/1545, loss: 0.08176523447036743 2023-01-23 11:18:37.682944: step: 1432/1545, loss: 0.07163221389055252 2023-01-23 11:18:38.561920: step: 1434/1545, loss: 0.200797900557518 2023-01-23 11:18:39.473500: step: 1436/1545, loss: 0.675132691860199 2023-01-23 11:18:40.346389: step: 1438/1545, loss: 0.15857526659965515 2023-01-23 11:18:41.237126: step: 1440/1545, loss: 0.12524738907814026 2023-01-23 11:18:42.122332: step: 1442/1545, loss: 0.06620360910892487 2023-01-23 11:18:43.049497: step: 1444/1545, loss: 0.1291964054107666 2023-01-23 11:18:43.905918: step: 1446/1545, loss: 0.3365703225135803 2023-01-23 11:18:44.800285: step: 1448/1545, loss: 0.10520412772893906 2023-01-23 11:18:45.703034: step: 1450/1545, loss: 0.28965574502944946 2023-01-23 11:18:46.597559: step: 1452/1545, loss: 0.1672804355621338 2023-01-23 11:18:47.494007: step: 1454/1545, loss: 0.1074119582772255 2023-01-23 11:18:48.372681: step: 1456/1545, loss: 0.011604640632867813 2023-01-23 11:18:49.241286: step: 1458/1545, loss: 0.050805769860744476 2023-01-23 11:18:50.195057: step: 1460/1545, loss: 0.01317674107849598 2023-01-23 11:18:51.059121: step: 1462/1545, loss: 0.3184013366699219 2023-01-23 11:18:51.960248: step: 1464/1545, loss: 0.31225574016571045 2023-01-23 11:18:52.807166: step: 1466/1545, loss: 0.07022140920162201 2023-01-23 11:18:53.668115: step: 1468/1545, loss: 0.661004364490509 2023-01-23 11:18:54.574501: step: 1470/1545, loss: 0.015941383317112923 2023-01-23 11:18:55.423731: step: 1472/1545, loss: 0.0711943507194519 2023-01-23 11:18:56.270078: step: 1474/1545, loss: 0.29031383991241455 2023-01-23 11:18:57.264337: step: 1476/1545, loss: 0.34888389706611633 2023-01-23 11:18:58.177208: step: 1478/1545, loss: 0.10206065326929092 2023-01-23 11:18:59.051246: step: 1480/1545, loss: 0.1597728133201599 2023-01-23 11:18:59.893327: step: 1482/1545, loss: 0.36824920773506165 2023-01-23 11:19:00.797488: step: 1484/1545, loss: 0.05949471890926361 2023-01-23 11:19:01.663674: step: 1486/1545, loss: 0.33479467034339905 2023-01-23 11:19:02.564867: step: 1488/1545, loss: 0.18008488416671753 2023-01-23 11:19:03.436421: step: 1490/1545, loss: 0.1853393316268921 2023-01-23 11:19:04.337046: step: 1492/1545, loss: 0.12346750497817993 2023-01-23 11:19:05.271674: step: 1494/1545, loss: 0.09488669782876968 2023-01-23 11:19:06.155218: step: 1496/1545, loss: 0.09307991713285446 2023-01-23 11:19:07.076808: step: 1498/1545, loss: 0.3900120258331299 2023-01-23 11:19:07.987136: step: 1500/1545, loss: 0.2302122265100479 2023-01-23 11:19:08.857177: step: 1502/1545, loss: 0.012674215249717236 2023-01-23 11:19:09.736476: step: 1504/1545, loss: 0.23106135427951813 2023-01-23 11:19:10.652687: step: 1506/1545, loss: 0.20778317749500275 2023-01-23 11:19:11.499324: step: 1508/1545, loss: 0.14732025563716888 2023-01-23 11:19:12.360123: step: 1510/1545, loss: 0.00764873344451189 2023-01-23 11:19:13.264325: step: 1512/1545, loss: 0.02141628786921501 2023-01-23 11:19:14.106494: step: 1514/1545, loss: 0.08648137748241425 2023-01-23 11:19:15.023679: step: 1516/1545, loss: 0.08328159898519516 2023-01-23 11:19:15.898099: step: 1518/1545, loss: 0.10721823573112488 2023-01-23 11:19:16.784397: step: 1520/1545, loss: 0.04648386687040329 2023-01-23 11:19:17.624846: step: 1522/1545, loss: 0.05414997413754463 2023-01-23 11:19:18.503193: step: 1524/1545, loss: 0.3656679689884186 2023-01-23 11:19:19.344035: step: 1526/1545, loss: 0.2676163911819458 2023-01-23 11:19:20.198414: step: 1528/1545, loss: 0.3224344849586487 2023-01-23 11:19:21.080971: step: 1530/1545, loss: 0.36692941188812256 2023-01-23 11:19:21.965661: step: 1532/1545, loss: 4.0515241622924805 2023-01-23 11:19:22.947890: step: 1534/1545, loss: 0.1056252047419548 2023-01-23 11:19:23.829868: step: 1536/1545, loss: 0.06463490426540375 2023-01-23 11:19:24.700418: step: 1538/1545, loss: 0.23544804751873016 2023-01-23 11:19:25.603335: step: 1540/1545, loss: 4.889988422393799 2023-01-23 11:19:26.504939: step: 1542/1545, loss: 0.11662309616804123 2023-01-23 11:19:27.409295: step: 1544/1545, loss: 0.04334191977977753 2023-01-23 11:19:28.267753: step: 1546/1545, loss: 0.07824886590242386 2023-01-23 11:19:29.153032: step: 1548/1545, loss: 0.22667628526687622 2023-01-23 11:19:30.035362: step: 1550/1545, loss: 0.10440349578857422 2023-01-23 11:19:30.889067: step: 1552/1545, loss: 0.011297273449599743 2023-01-23 11:19:31.772487: step: 1554/1545, loss: 0.18003806471824646 2023-01-23 11:19:32.649204: step: 1556/1545, loss: 0.09142467379570007 2023-01-23 11:19:33.514446: step: 1558/1545, loss: 0.2836964428424835 2023-01-23 11:19:34.383794: step: 1560/1545, loss: 0.14344801008701324 2023-01-23 11:19:35.324259: step: 1562/1545, loss: 0.04025230184197426 2023-01-23 11:19:36.182374: step: 1564/1545, loss: 0.07152590155601501 2023-01-23 11:19:37.016243: step: 1566/1545, loss: 0.14110001921653748 2023-01-23 11:19:37.905509: step: 1568/1545, loss: 0.025456583127379417 2023-01-23 11:19:38.790928: step: 1570/1545, loss: 0.09790746122598648 2023-01-23 11:19:39.679095: step: 1572/1545, loss: 0.02651010826230049 2023-01-23 11:19:40.580375: step: 1574/1545, loss: 0.05618423968553543 2023-01-23 11:19:41.442453: step: 1576/1545, loss: 0.2649983763694763 2023-01-23 11:19:42.323533: step: 1578/1545, loss: 0.07084587216377258 2023-01-23 11:19:43.193277: step: 1580/1545, loss: 0.04338439553976059 2023-01-23 11:19:44.109873: step: 1582/1545, loss: 0.058506663888692856 2023-01-23 11:19:44.984972: step: 1584/1545, loss: 2.663027048110962 2023-01-23 11:19:45.872906: step: 1586/1545, loss: 0.07357798516750336 2023-01-23 11:19:46.792265: step: 1588/1545, loss: 0.009879733435809612 2023-01-23 11:19:47.681836: step: 1590/1545, loss: 0.03180819749832153 2023-01-23 11:19:48.557738: step: 1592/1545, loss: 0.22525066137313843 2023-01-23 11:19:49.480885: step: 1594/1545, loss: 0.3656003177165985 2023-01-23 11:19:50.352242: step: 1596/1545, loss: 0.008519924245774746 2023-01-23 11:19:51.265358: step: 1598/1545, loss: 0.04522452503442764 2023-01-23 11:19:52.126596: step: 1600/1545, loss: 0.0016058383043855429 2023-01-23 11:19:53.054240: step: 1602/1545, loss: 0.057472601532936096 2023-01-23 11:19:53.972574: step: 1604/1545, loss: 0.15369288623332977 2023-01-23 11:19:54.895276: step: 1606/1545, loss: 0.06347525864839554 2023-01-23 11:19:55.788747: step: 1608/1545, loss: 0.008158356882631779 2023-01-23 11:19:56.637071: step: 1610/1545, loss: 0.00926191546022892 2023-01-23 11:19:57.505340: step: 1612/1545, loss: 0.45660215616226196 2023-01-23 11:19:58.396869: step: 1614/1545, loss: 0.0450708381831646 2023-01-23 11:19:59.321125: step: 1616/1545, loss: 0.14620162546634674 2023-01-23 11:20:00.190316: step: 1618/1545, loss: 0.051372312009334564 2023-01-23 11:20:01.113040: step: 1620/1545, loss: 0.03217701241374016 2023-01-23 11:20:01.992977: step: 1622/1545, loss: 0.16491852700710297 2023-01-23 11:20:02.891103: step: 1624/1545, loss: 0.009742600843310356 2023-01-23 11:20:03.772926: step: 1626/1545, loss: 2.104743480682373 2023-01-23 11:20:04.692275: step: 1628/1545, loss: 0.11780115216970444 2023-01-23 11:20:05.581303: step: 1630/1545, loss: 0.0202245581895113 2023-01-23 11:20:06.466736: step: 1632/1545, loss: 0.005623314063996077 2023-01-23 11:20:07.413912: step: 1634/1545, loss: 0.1509280800819397 2023-01-23 11:20:08.334067: step: 1636/1545, loss: 0.8110417127609253 2023-01-23 11:20:09.274683: step: 1638/1545, loss: 0.1542409509420395 2023-01-23 11:20:10.193876: step: 1640/1545, loss: 0.11449718475341797 2023-01-23 11:20:11.110384: step: 1642/1545, loss: 0.11510486900806427 2023-01-23 11:20:11.950260: step: 1644/1545, loss: 0.09799018502235413 2023-01-23 11:20:12.810288: step: 1646/1545, loss: 0.15926896035671234 2023-01-23 11:20:13.713994: step: 1648/1545, loss: 0.031529344618320465 2023-01-23 11:20:14.590439: step: 1650/1545, loss: 0.280290812253952 2023-01-23 11:20:15.472021: step: 1652/1545, loss: 0.06821714341640472 2023-01-23 11:20:16.434642: step: 1654/1545, loss: 0.13080227375030518 2023-01-23 11:20:17.308645: step: 1656/1545, loss: 0.03709367290139198 2023-01-23 11:20:18.191921: step: 1658/1545, loss: 0.21305084228515625 2023-01-23 11:20:19.227153: step: 1660/1545, loss: 0.2707383334636688 2023-01-23 11:20:20.153505: step: 1662/1545, loss: 2.042834997177124 2023-01-23 11:20:21.027089: step: 1664/1545, loss: 0.025893770158290863 2023-01-23 11:20:21.936489: step: 1666/1545, loss: 0.3862035870552063 2023-01-23 11:20:22.808005: step: 1668/1545, loss: 0.567467212677002 2023-01-23 11:20:23.672341: step: 1670/1545, loss: 0.11050562560558319 2023-01-23 11:20:24.521187: step: 1672/1545, loss: 0.028506401926279068 2023-01-23 11:20:25.390937: step: 1674/1545, loss: 0.033025506883859634 2023-01-23 11:20:26.271390: step: 1676/1545, loss: 0.16265444457530975 2023-01-23 11:20:27.150839: step: 1678/1545, loss: 0.19371499121189117 2023-01-23 11:20:28.134972: step: 1680/1545, loss: 0.30519840121269226 2023-01-23 11:20:29.004986: step: 1682/1545, loss: 0.09984268993139267 2023-01-23 11:20:29.953943: step: 1684/1545, loss: 0.43248939514160156 2023-01-23 11:20:30.830477: step: 1686/1545, loss: 0.19797676801681519 2023-01-23 11:20:31.662711: step: 1688/1545, loss: 0.1149730384349823 2023-01-23 11:20:32.586862: step: 1690/1545, loss: 2.240852117538452 2023-01-23 11:20:33.448463: step: 1692/1545, loss: 0.024218814447522163 2023-01-23 11:20:34.317411: step: 1694/1545, loss: 0.024242524057626724 2023-01-23 11:20:35.211496: step: 1696/1545, loss: 0.011755157262086868 2023-01-23 11:20:36.074301: step: 1698/1545, loss: 0.11633750051259995 2023-01-23 11:20:36.948045: step: 1700/1545, loss: 0.02916310355067253 2023-01-23 11:20:37.834404: step: 1702/1545, loss: 0.11564049124717712 2023-01-23 11:20:38.721183: step: 1704/1545, loss: 0.0442652627825737 2023-01-23 11:20:39.597908: step: 1706/1545, loss: 0.04223073646426201 2023-01-23 11:20:40.495968: step: 1708/1545, loss: 0.13937775790691376 2023-01-23 11:20:41.395243: step: 1710/1545, loss: 0.49845632910728455 2023-01-23 11:20:42.266676: step: 1712/1545, loss: 0.026848746463656425 2023-01-23 11:20:43.181816: step: 1714/1545, loss: 0.014910825528204441 2023-01-23 11:20:44.081499: step: 1716/1545, loss: 1.0282634496688843 2023-01-23 11:20:44.986606: step: 1718/1545, loss: 0.07475672662258148 2023-01-23 11:20:45.869659: step: 1720/1545, loss: 0.09008663147687912 2023-01-23 11:20:46.800559: step: 1722/1545, loss: 0.13651759922504425 2023-01-23 11:20:47.712242: step: 1724/1545, loss: 0.1994124799966812 2023-01-23 11:20:48.583497: step: 1726/1545, loss: 0.1407235562801361 2023-01-23 11:20:49.525976: step: 1728/1545, loss: 0.14100424945354462 2023-01-23 11:20:50.426309: step: 1730/1545, loss: 0.857018232345581 2023-01-23 11:20:51.356034: step: 1732/1545, loss: 0.12683966755867004 2023-01-23 11:20:52.301814: step: 1734/1545, loss: 0.020884627476334572 2023-01-23 11:20:53.164954: step: 1736/1545, loss: 0.05202209949493408 2023-01-23 11:20:54.068620: step: 1738/1545, loss: 0.10219048708677292 2023-01-23 11:20:54.943466: step: 1740/1545, loss: 0.43247655034065247 2023-01-23 11:20:55.797186: step: 1742/1545, loss: 0.14433889091014862 2023-01-23 11:20:56.728137: step: 1744/1545, loss: 0.963221549987793 2023-01-23 11:20:57.617031: step: 1746/1545, loss: 0.14190539717674255 2023-01-23 11:20:58.560685: step: 1748/1545, loss: 0.027334729209542274 2023-01-23 11:20:59.432501: step: 1750/1545, loss: 0.3137202560901642 2023-01-23 11:21:00.302492: step: 1752/1545, loss: 0.12189028412103653 2023-01-23 11:21:01.203923: step: 1754/1545, loss: 0.26432034373283386 2023-01-23 11:21:02.042897: step: 1756/1545, loss: 0.3044678270816803 2023-01-23 11:21:02.929626: step: 1758/1545, loss: 0.5051147937774658 2023-01-23 11:21:03.818834: step: 1760/1545, loss: 0.06812983751296997 2023-01-23 11:21:04.693658: step: 1762/1545, loss: 0.0738978460431099 2023-01-23 11:21:05.591205: step: 1764/1545, loss: 0.1987527757883072 2023-01-23 11:21:06.469944: step: 1766/1545, loss: 0.0199319776147604 2023-01-23 11:21:07.325983: step: 1768/1545, loss: 0.022665394470095634 2023-01-23 11:21:08.159784: step: 1770/1545, loss: 0.220389261841774 2023-01-23 11:21:09.034504: step: 1772/1545, loss: 0.4419068694114685 2023-01-23 11:21:09.890044: step: 1774/1545, loss: 0.1164030209183693 2023-01-23 11:21:10.760273: step: 1776/1545, loss: 0.044714733958244324 2023-01-23 11:21:11.629138: step: 1778/1545, loss: 0.02521512098610401 2023-01-23 11:21:12.555466: step: 1780/1545, loss: 0.11788319051265717 2023-01-23 11:21:13.429683: step: 1782/1545, loss: 0.018065787851810455 2023-01-23 11:21:14.357288: step: 1784/1545, loss: 0.032931309193372726 2023-01-23 11:21:15.231989: step: 1786/1545, loss: 0.16859571635723114 2023-01-23 11:21:16.123912: step: 1788/1545, loss: 0.2468736320734024 2023-01-23 11:21:17.059948: step: 1790/1545, loss: 0.04490666091442108 2023-01-23 11:21:17.966872: step: 1792/1545, loss: 0.3926309645175934 2023-01-23 11:21:18.849701: step: 1794/1545, loss: 0.11787243187427521 2023-01-23 11:21:19.708316: step: 1796/1545, loss: 0.10759830474853516 2023-01-23 11:21:20.548701: step: 1798/1545, loss: 0.04753368720412254 2023-01-23 11:21:21.511934: step: 1800/1545, loss: 0.24833106994628906 2023-01-23 11:21:22.391701: step: 1802/1545, loss: 0.08476249873638153 2023-01-23 11:21:23.294840: step: 1804/1545, loss: 0.43206125497817993 2023-01-23 11:21:24.155885: step: 1806/1545, loss: 0.18784978985786438 2023-01-23 11:21:25.013542: step: 1808/1545, loss: 1.2467879056930542 2023-01-23 11:21:25.934498: step: 1810/1545, loss: 0.10931690037250519 2023-01-23 11:21:26.818374: step: 1812/1545, loss: 0.3675006926059723 2023-01-23 11:21:27.669653: step: 1814/1545, loss: 0.04915890097618103 2023-01-23 11:21:28.552893: step: 1816/1545, loss: 0.1068059578537941 2023-01-23 11:21:29.458626: step: 1818/1545, loss: 0.009578291326761246 2023-01-23 11:21:30.326603: step: 1820/1545, loss: 0.16717752814292908 2023-01-23 11:21:31.177671: step: 1822/1545, loss: 0.015405984595417976 2023-01-23 11:21:32.108702: step: 1824/1545, loss: 0.02407028153538704 2023-01-23 11:21:32.993305: step: 1826/1545, loss: 0.09847232699394226 2023-01-23 11:21:33.902651: step: 1828/1545, loss: 0.103370800614357 2023-01-23 11:21:34.819865: step: 1830/1545, loss: 0.07654448598623276 2023-01-23 11:21:35.716418: step: 1832/1545, loss: 0.2426523119211197 2023-01-23 11:21:36.572208: step: 1834/1545, loss: 0.09021808952093124 2023-01-23 11:21:37.545000: step: 1836/1545, loss: 0.041898906230926514 2023-01-23 11:21:38.428986: step: 1838/1545, loss: 0.019565295428037643 2023-01-23 11:21:39.338456: step: 1840/1545, loss: 0.13655395805835724 2023-01-23 11:21:40.219247: step: 1842/1545, loss: 0.1460031121969223 2023-01-23 11:21:41.110591: step: 1844/1545, loss: 0.18393802642822266 2023-01-23 11:21:41.982223: step: 1846/1545, loss: 0.024025248363614082 2023-01-23 11:21:42.847349: step: 1848/1545, loss: 0.014342193491756916 2023-01-23 11:21:43.701675: step: 1850/1545, loss: 0.03982246667146683 2023-01-23 11:21:44.550016: step: 1852/1545, loss: 0.3685028851032257 2023-01-23 11:21:45.413782: step: 1854/1545, loss: 0.5842685699462891 2023-01-23 11:21:46.292603: step: 1856/1545, loss: 0.10046792775392532 2023-01-23 11:21:47.193980: step: 1858/1545, loss: 0.08070335537195206 2023-01-23 11:21:48.072747: step: 1860/1545, loss: 0.021533865481615067 2023-01-23 11:21:48.973187: step: 1862/1545, loss: 0.024506960064172745 2023-01-23 11:21:49.791002: step: 1864/1545, loss: 0.08191532641649246 2023-01-23 11:21:50.659319: step: 1866/1545, loss: 0.38037368655204773 2023-01-23 11:21:51.533391: step: 1868/1545, loss: 0.08385811746120453 2023-01-23 11:21:52.411321: step: 1870/1545, loss: 0.03502016142010689 2023-01-23 11:21:53.292446: step: 1872/1545, loss: 0.07327618449926376 2023-01-23 11:21:54.195061: step: 1874/1545, loss: 0.5228950381278992 2023-01-23 11:21:55.074359: step: 1876/1545, loss: 0.14467132091522217 2023-01-23 11:21:55.952181: step: 1878/1545, loss: 0.3345205783843994 2023-01-23 11:21:56.822133: step: 1880/1545, loss: 0.11931797862052917 2023-01-23 11:21:57.690482: step: 1882/1545, loss: 0.10843902081251144 2023-01-23 11:21:58.656925: step: 1884/1545, loss: 0.0023323767818510532 2023-01-23 11:21:59.533856: step: 1886/1545, loss: 0.1706053614616394 2023-01-23 11:22:00.500336: step: 1888/1545, loss: 0.6557533740997314 2023-01-23 11:22:01.384337: step: 1890/1545, loss: 0.027284448966383934 2023-01-23 11:22:02.287105: step: 1892/1545, loss: 0.0377008281648159 2023-01-23 11:22:03.193838: step: 1894/1545, loss: 0.24489572644233704 2023-01-23 11:22:04.132798: step: 1896/1545, loss: 0.0284318495541811 2023-01-23 11:22:05.048053: step: 1898/1545, loss: 0.34000441431999207 2023-01-23 11:22:05.898341: step: 1900/1545, loss: 0.054156262427568436 2023-01-23 11:22:06.800108: step: 1902/1545, loss: 0.04853926971554756 2023-01-23 11:22:07.687203: step: 1904/1545, loss: 0.005464877467602491 2023-01-23 11:22:08.555414: step: 1906/1545, loss: 0.2316383719444275 2023-01-23 11:22:09.454462: step: 1908/1545, loss: 0.6551426649093628 2023-01-23 11:22:10.345935: step: 1910/1545, loss: 0.13533355295658112 2023-01-23 11:22:11.213559: step: 1912/1545, loss: 0.19465261697769165 2023-01-23 11:22:12.137849: step: 1914/1545, loss: 0.046516302973032 2023-01-23 11:22:12.982156: step: 1916/1545, loss: 0.058674950152635574 2023-01-23 11:22:13.845042: step: 1918/1545, loss: 0.30343279242515564 2023-01-23 11:22:14.725657: step: 1920/1545, loss: 0.015408757142722607 2023-01-23 11:22:15.647275: step: 1922/1545, loss: 0.06797265261411667 2023-01-23 11:22:16.498652: step: 1924/1545, loss: 0.003638335270807147 2023-01-23 11:22:17.414261: step: 1926/1545, loss: 0.08623646944761276 2023-01-23 11:22:18.265268: step: 1928/1545, loss: 0.3141322731971741 2023-01-23 11:22:19.113509: step: 1930/1545, loss: 0.02012776955962181 2023-01-23 11:22:19.986515: step: 1932/1545, loss: 0.009044429287314415 2023-01-23 11:22:20.887032: step: 1934/1545, loss: 0.29496100544929504 2023-01-23 11:22:21.737891: step: 1936/1545, loss: 0.4552564024925232 2023-01-23 11:22:22.583079: step: 1938/1545, loss: 0.005233215633779764 2023-01-23 11:22:23.467023: step: 1940/1545, loss: 0.012727257795631886 2023-01-23 11:22:24.349455: step: 1942/1545, loss: 0.12268735468387604 2023-01-23 11:22:25.262157: step: 1944/1545, loss: 0.009329603984951973 2023-01-23 11:22:26.130666: step: 1946/1545, loss: 0.5538170337677002 2023-01-23 11:22:27.043105: step: 1948/1545, loss: 0.04317677393555641 2023-01-23 11:22:27.903294: step: 1950/1545, loss: 1.2371948957443237 2023-01-23 11:22:28.838209: step: 1952/1545, loss: 0.12836971879005432 2023-01-23 11:22:29.739304: step: 1954/1545, loss: 0.001959314802661538 2023-01-23 11:22:30.636183: step: 1956/1545, loss: 0.02751171588897705 2023-01-23 11:22:31.511865: step: 1958/1545, loss: 0.07382615655660629 2023-01-23 11:22:32.427478: step: 1960/1545, loss: 0.025603359565138817 2023-01-23 11:22:33.371047: step: 1962/1545, loss: 0.5757325291633606 2023-01-23 11:22:34.251356: step: 1964/1545, loss: 0.06756383180618286 2023-01-23 11:22:35.109745: step: 1966/1545, loss: 0.026507308706641197 2023-01-23 11:22:35.989498: step: 1968/1545, loss: 0.16584324836730957 2023-01-23 11:22:36.926069: step: 1970/1545, loss: 1.9952278137207031 2023-01-23 11:22:37.852936: step: 1972/1545, loss: 0.2552463114261627 2023-01-23 11:22:38.716948: step: 1974/1545, loss: 0.10201231390237808 2023-01-23 11:22:39.618876: step: 1976/1545, loss: 0.023760728538036346 2023-01-23 11:22:40.493638: step: 1978/1545, loss: 0.5849248766899109 2023-01-23 11:22:41.379398: step: 1980/1545, loss: 0.02849910594522953 2023-01-23 11:22:42.246483: step: 1982/1545, loss: 0.08150648325681686 2023-01-23 11:22:43.104348: step: 1984/1545, loss: 0.1497337967157364 2023-01-23 11:22:44.008763: step: 1986/1545, loss: 0.38192516565322876 2023-01-23 11:22:44.901287: step: 1988/1545, loss: 0.05423690751194954 2023-01-23 11:22:45.774679: step: 1990/1545, loss: 0.15125949680805206 2023-01-23 11:22:46.697192: step: 1992/1545, loss: 0.2709033191204071 2023-01-23 11:22:47.551024: step: 1994/1545, loss: 0.16457964479923248 2023-01-23 11:22:48.450728: step: 1996/1545, loss: 0.15853825211524963 2023-01-23 11:22:49.326935: step: 1998/1545, loss: 0.36389580368995667 2023-01-23 11:22:50.207844: step: 2000/1545, loss: 0.023270970210433006 2023-01-23 11:22:51.076901: step: 2002/1545, loss: 0.029048211872577667 2023-01-23 11:22:51.981568: step: 2004/1545, loss: 0.03631158173084259 2023-01-23 11:22:52.871400: step: 2006/1545, loss: 0.43419262766838074 2023-01-23 11:22:53.796668: step: 2008/1545, loss: 0.42669257521629333 2023-01-23 11:22:54.699529: step: 2010/1545, loss: 0.04985503852367401 2023-01-23 11:22:55.577402: step: 2012/1545, loss: 0.026156406849622726 2023-01-23 11:22:56.451828: step: 2014/1545, loss: 0.07761839032173157 2023-01-23 11:22:57.340179: step: 2016/1545, loss: 0.08499129116535187 2023-01-23 11:22:58.188661: step: 2018/1545, loss: 0.010779541917145252 2023-01-23 11:22:59.059420: step: 2020/1545, loss: 0.15209060907363892 2023-01-23 11:22:59.906823: step: 2022/1545, loss: 0.02016158029437065 2023-01-23 11:23:00.804407: step: 2024/1545, loss: 0.08232312649488449 2023-01-23 11:23:01.661677: step: 2026/1545, loss: 0.045776113867759705 2023-01-23 11:23:02.578207: step: 2028/1545, loss: 0.05239386484026909 2023-01-23 11:23:03.453348: step: 2030/1545, loss: 0.024581603705883026 2023-01-23 11:23:04.330785: step: 2032/1545, loss: 0.18666556477546692 2023-01-23 11:23:05.170806: step: 2034/1545, loss: 0.03179696202278137 2023-01-23 11:23:06.053143: step: 2036/1545, loss: 0.10857199132442474 2023-01-23 11:23:06.918678: step: 2038/1545, loss: 0.009040262550115585 2023-01-23 11:23:07.773405: step: 2040/1545, loss: 0.15410375595092773 2023-01-23 11:23:08.632979: step: 2042/1545, loss: 0.43878620862960815 2023-01-23 11:23:09.513109: step: 2044/1545, loss: 0.04057235270738602 2023-01-23 11:23:10.349146: step: 2046/1545, loss: 0.19051493704319 2023-01-23 11:23:11.223301: step: 2048/1545, loss: 0.06508894264698029 2023-01-23 11:23:12.103662: step: 2050/1545, loss: 0.19346092641353607 2023-01-23 11:23:12.975690: step: 2052/1545, loss: 0.07657162845134735 2023-01-23 11:23:13.813677: step: 2054/1545, loss: 0.03386952728033066 2023-01-23 11:23:14.778999: step: 2056/1545, loss: 0.7319716215133667 2023-01-23 11:23:15.695169: step: 2058/1545, loss: 0.15703842043876648 2023-01-23 11:23:16.554227: step: 2060/1545, loss: 0.11847065389156342 2023-01-23 11:23:17.431471: step: 2062/1545, loss: 0.008420957252383232 2023-01-23 11:23:18.300554: step: 2064/1545, loss: 0.017789702862501144 2023-01-23 11:23:19.179746: step: 2066/1545, loss: 0.02805737964808941 2023-01-23 11:23:20.059206: step: 2068/1545, loss: 0.09457064419984818 2023-01-23 11:23:20.922511: step: 2070/1545, loss: 0.0565740130841732 2023-01-23 11:23:21.810885: step: 2072/1545, loss: 0.021190224215388298 2023-01-23 11:23:22.667206: step: 2074/1545, loss: 0.16025173664093018 2023-01-23 11:23:23.530810: step: 2076/1545, loss: 0.05287015438079834 2023-01-23 11:23:24.363738: step: 2078/1545, loss: 0.17189441621303558 2023-01-23 11:23:25.276398: step: 2080/1545, loss: 1.0266610383987427 2023-01-23 11:23:26.253517: step: 2082/1545, loss: 0.13860008120536804 2023-01-23 11:23:27.234947: step: 2084/1545, loss: 0.3935418426990509 2023-01-23 11:23:28.115413: step: 2086/1545, loss: 0.13327890634536743 2023-01-23 11:23:28.964786: step: 2088/1545, loss: 0.01964983344078064 2023-01-23 11:23:29.809986: step: 2090/1545, loss: 0.11671268939971924 2023-01-23 11:23:30.673666: step: 2092/1545, loss: 0.5478305220603943 2023-01-23 11:23:31.598311: step: 2094/1545, loss: 0.5960099101066589 2023-01-23 11:23:32.478226: step: 2096/1545, loss: 0.16863587498664856 2023-01-23 11:23:33.375083: step: 2098/1545, loss: 0.17451761662960052 2023-01-23 11:23:34.260188: step: 2100/1545, loss: 0.06584902852773666 2023-01-23 11:23:35.121179: step: 2102/1545, loss: 0.6501022577285767 2023-01-23 11:23:35.977265: step: 2104/1545, loss: 0.2824886739253998 2023-01-23 11:23:36.867615: step: 2106/1545, loss: 0.15667974948883057 2023-01-23 11:23:37.739676: step: 2108/1545, loss: 0.18267706036567688 2023-01-23 11:23:38.601303: step: 2110/1545, loss: 0.021281085908412933 2023-01-23 11:23:39.462200: step: 2112/1545, loss: 0.010844524949789047 2023-01-23 11:23:40.325193: step: 2114/1545, loss: 0.08186770975589752 2023-01-23 11:23:41.194999: step: 2116/1545, loss: 0.015129676088690758 2023-01-23 11:23:42.078248: step: 2118/1545, loss: 0.4641135036945343 2023-01-23 11:23:42.943177: step: 2120/1545, loss: 0.056812919676303864 2023-01-23 11:23:43.850235: step: 2122/1545, loss: 0.2666860520839691 2023-01-23 11:23:44.733795: step: 2124/1545, loss: 0.11750480532646179 2023-01-23 11:23:45.557124: step: 2126/1545, loss: 0.11143170297145844 2023-01-23 11:23:46.403060: step: 2128/1545, loss: 0.44211211800575256 2023-01-23 11:23:47.369648: step: 2130/1545, loss: 0.009720039553940296 2023-01-23 11:23:48.263026: step: 2132/1545, loss: 0.05795746296644211 2023-01-23 11:23:49.208816: step: 2134/1545, loss: 0.41436707973480225 2023-01-23 11:23:50.114746: step: 2136/1545, loss: 0.0978400781750679 2023-01-23 11:23:51.064921: step: 2138/1545, loss: 0.12342862784862518 2023-01-23 11:23:51.930621: step: 2140/1545, loss: 0.06057223305106163 2023-01-23 11:23:52.804316: step: 2142/1545, loss: 0.06032651290297508 2023-01-23 11:23:53.668635: step: 2144/1545, loss: 0.5564168095588684 2023-01-23 11:23:54.549428: step: 2146/1545, loss: 0.09571721404790878 2023-01-23 11:23:55.420914: step: 2148/1545, loss: 0.0032900217920541763 2023-01-23 11:23:56.312265: step: 2150/1545, loss: 1.9673588275909424 2023-01-23 11:23:57.191274: step: 2152/1545, loss: 0.04831739142537117 2023-01-23 11:23:58.118237: step: 2154/1545, loss: 0.13490283489227295 2023-01-23 11:23:59.018492: step: 2156/1545, loss: 0.17846538126468658 2023-01-23 11:23:59.881439: step: 2158/1545, loss: 0.04501872882246971 2023-01-23 11:24:00.763391: step: 2160/1545, loss: 0.12314652651548386 2023-01-23 11:24:01.612626: step: 2162/1545, loss: 0.3435099124908447 2023-01-23 11:24:02.476066: step: 2164/1545, loss: 0.05821801722049713 2023-01-23 11:24:03.445212: step: 2166/1545, loss: 0.4274342358112335 2023-01-23 11:24:04.294967: step: 2168/1545, loss: 0.2826959192752838 2023-01-23 11:24:05.153775: step: 2170/1545, loss: 0.031006740406155586 2023-01-23 11:24:06.011672: step: 2172/1545, loss: 0.12310849130153656 2023-01-23 11:24:06.893734: step: 2174/1545, loss: 0.27184000611305237 2023-01-23 11:24:07.752212: step: 2176/1545, loss: 0.19084309041500092 2023-01-23 11:24:08.633644: step: 2178/1545, loss: 0.13629576563835144 2023-01-23 11:24:09.522726: step: 2180/1545, loss: 0.40574735403060913 2023-01-23 11:24:10.429131: step: 2182/1545, loss: 0.15962277352809906 2023-01-23 11:24:11.304014: step: 2184/1545, loss: 0.2643161416053772 2023-01-23 11:24:12.171149: step: 2186/1545, loss: 0.2083752155303955 2023-01-23 11:24:13.068870: step: 2188/1545, loss: 0.35880014300346375 2023-01-23 11:24:13.960035: step: 2190/1545, loss: 0.016380004584789276 2023-01-23 11:24:14.832348: step: 2192/1545, loss: 0.03742345795035362 2023-01-23 11:24:15.691770: step: 2194/1545, loss: 0.4766467809677124 2023-01-23 11:24:16.610036: step: 2196/1545, loss: 0.20348383486270905 2023-01-23 11:24:17.521705: step: 2198/1545, loss: 0.13846136629581451 2023-01-23 11:24:18.388697: step: 2200/1545, loss: 0.015071502886712551 2023-01-23 11:24:19.335446: step: 2202/1545, loss: 0.21262238919734955 2023-01-23 11:24:20.191880: step: 2204/1545, loss: 0.06928171962499619 2023-01-23 11:24:21.050994: step: 2206/1545, loss: 0.8503268957138062 2023-01-23 11:24:21.981823: step: 2208/1545, loss: 0.30463507771492004 2023-01-23 11:24:22.870191: step: 2210/1545, loss: 0.021734923124313354 2023-01-23 11:24:23.703969: step: 2212/1545, loss: 0.06858538091182709 2023-01-23 11:24:24.588975: step: 2214/1545, loss: 0.4441465735435486 2023-01-23 11:24:25.501479: step: 2216/1545, loss: 0.17393027245998383 2023-01-23 11:24:26.375837: step: 2218/1545, loss: 0.03382989391684532 2023-01-23 11:24:27.278643: step: 2220/1545, loss: 0.39130720496177673 2023-01-23 11:24:28.153804: step: 2222/1545, loss: 0.27893632650375366 2023-01-23 11:24:28.999512: step: 2224/1545, loss: 0.03631449490785599 2023-01-23 11:24:29.880764: step: 2226/1545, loss: 0.39539578557014465 2023-01-23 11:24:30.808364: step: 2228/1545, loss: 0.04805435612797737 2023-01-23 11:24:31.684780: step: 2230/1545, loss: 0.16968731582164764 2023-01-23 11:24:32.655328: step: 2232/1545, loss: 0.029322339221835136 2023-01-23 11:24:33.511649: step: 2234/1545, loss: 0.13979804515838623 2023-01-23 11:24:34.397759: step: 2236/1545, loss: 0.05112878978252411 2023-01-23 11:24:35.279482: step: 2238/1545, loss: 0.8958701491355896 2023-01-23 11:24:36.135919: step: 2240/1545, loss: 0.0452367439866066 2023-01-23 11:24:37.006018: step: 2242/1545, loss: 0.13629019260406494 2023-01-23 11:24:37.863012: step: 2244/1545, loss: 0.037696722894907 2023-01-23 11:24:38.718280: step: 2246/1545, loss: 0.25037872791290283 2023-01-23 11:24:39.616740: step: 2248/1545, loss: 0.035028763115406036 2023-01-23 11:24:40.470708: step: 2250/1545, loss: 0.12632395327091217 2023-01-23 11:24:41.347854: step: 2252/1545, loss: 0.0808316022157669 2023-01-23 11:24:42.189956: step: 2254/1545, loss: 0.028956295922398567 2023-01-23 11:24:43.049682: step: 2256/1545, loss: 0.016366997733712196 2023-01-23 11:24:43.913251: step: 2258/1545, loss: 0.17251600325107574 2023-01-23 11:24:44.778081: step: 2260/1545, loss: 0.00696976576000452 2023-01-23 11:24:45.607432: step: 2262/1545, loss: 0.0021822811104357243 2023-01-23 11:24:46.580935: step: 2264/1545, loss: 0.03673626855015755 2023-01-23 11:24:47.527959: step: 2266/1545, loss: 0.790118932723999 2023-01-23 11:24:48.381130: step: 2268/1545, loss: 0.008629962801933289 2023-01-23 11:24:49.290569: step: 2270/1545, loss: 0.06348156183958054 2023-01-23 11:24:50.183261: step: 2272/1545, loss: 0.018480073660612106 2023-01-23 11:24:51.072840: step: 2274/1545, loss: 0.018560126423835754 2023-01-23 11:24:51.960536: step: 2276/1545, loss: 0.2984691560268402 2023-01-23 11:24:52.887539: step: 2278/1545, loss: 0.06043613329529762 2023-01-23 11:24:53.753847: step: 2280/1545, loss: 0.013838722370564938 2023-01-23 11:24:54.628009: step: 2282/1545, loss: 0.275826632976532 2023-01-23 11:24:55.453533: step: 2284/1545, loss: 2.8987133502960205 2023-01-23 11:24:56.361076: step: 2286/1545, loss: 0.38280126452445984 2023-01-23 11:24:57.257758: step: 2288/1545, loss: 0.01916579157114029 2023-01-23 11:24:58.156682: step: 2290/1545, loss: 0.20494931936264038 2023-01-23 11:24:58.995802: step: 2292/1545, loss: 0.0038627791218459606 2023-01-23 11:24:59.968679: step: 2294/1545, loss: 0.2637316584587097 2023-01-23 11:25:00.865124: step: 2296/1545, loss: 0.013345668092370033 2023-01-23 11:25:01.710926: step: 2298/1545, loss: 0.020334094762802124 2023-01-23 11:25:02.545235: step: 2300/1545, loss: 0.0104140006005764 2023-01-23 11:25:03.425130: step: 2302/1545, loss: 0.015538197942078114 2023-01-23 11:25:04.315765: step: 2304/1545, loss: 0.0031903046183288097 2023-01-23 11:25:05.195295: step: 2306/1545, loss: 0.017082292586565018 2023-01-23 11:25:06.080799: step: 2308/1545, loss: 0.3995087742805481 2023-01-23 11:25:06.938274: step: 2310/1545, loss: 0.1262468546628952 2023-01-23 11:25:07.799114: step: 2312/1545, loss: 0.4143095016479492 2023-01-23 11:25:08.755135: step: 2314/1545, loss: 0.10602787137031555 2023-01-23 11:25:09.638651: step: 2316/1545, loss: 0.02657477557659149 2023-01-23 11:25:10.479299: step: 2318/1545, loss: 0.12747222185134888 2023-01-23 11:25:11.398299: step: 2320/1545, loss: 0.22348974645137787 2023-01-23 11:25:12.260069: step: 2322/1545, loss: 0.006362147629261017 2023-01-23 11:25:13.167190: step: 2324/1545, loss: 0.18468865752220154 2023-01-23 11:25:14.031970: step: 2326/1545, loss: 0.12723308801651 2023-01-23 11:25:14.913106: step: 2328/1545, loss: 0.24086861312389374 2023-01-23 11:25:15.825026: step: 2330/1545, loss: 0.37333327531814575 2023-01-23 11:25:16.739311: step: 2332/1545, loss: 0.6795191764831543 2023-01-23 11:25:17.614740: step: 2334/1545, loss: 0.011438841931521893 2023-01-23 11:25:18.519462: step: 2336/1545, loss: 0.4968429505825043 2023-01-23 11:25:19.427308: step: 2338/1545, loss: 0.08281490206718445 2023-01-23 11:25:20.292366: step: 2340/1545, loss: 0.1091906875371933 2023-01-23 11:25:21.178618: step: 2342/1545, loss: 0.15061268210411072 2023-01-23 11:25:22.109195: step: 2344/1545, loss: 0.05325337499380112 2023-01-23 11:25:22.997459: step: 2346/1545, loss: 0.2841002643108368 2023-01-23 11:25:23.953261: step: 2348/1545, loss: 0.14737509191036224 2023-01-23 11:25:24.809122: step: 2350/1545, loss: 0.080660879611969 2023-01-23 11:25:25.681309: step: 2352/1545, loss: 0.020293977111577988 2023-01-23 11:25:26.603523: step: 2354/1545, loss: 0.13096071779727936 2023-01-23 11:25:27.466647: step: 2356/1545, loss: 0.18970990180969238 2023-01-23 11:25:28.373219: step: 2358/1545, loss: 0.0334545262157917 2023-01-23 11:25:29.240994: step: 2360/1545, loss: 0.07491947710514069 2023-01-23 11:25:30.104234: step: 2362/1545, loss: 1.270280122756958 2023-01-23 11:25:30.993055: step: 2364/1545, loss: 0.05612998455762863 2023-01-23 11:25:31.843281: step: 2366/1545, loss: 0.07567767798900604 2023-01-23 11:25:32.749430: step: 2368/1545, loss: 0.10498792678117752 2023-01-23 11:25:33.670386: step: 2370/1545, loss: 1.4301385879516602 2023-01-23 11:25:34.589376: step: 2372/1545, loss: 0.47958338260650635 2023-01-23 11:25:35.476138: step: 2374/1545, loss: 0.42127370834350586 2023-01-23 11:25:36.334537: step: 2376/1545, loss: 0.03487387299537659 2023-01-23 11:25:37.222325: step: 2378/1545, loss: 0.08913761377334595 2023-01-23 11:25:38.134332: step: 2380/1545, loss: 0.04448162019252777 2023-01-23 11:25:39.002328: step: 2382/1545, loss: 0.07260057330131531 2023-01-23 11:25:39.864707: step: 2384/1545, loss: 0.17731374502182007 2023-01-23 11:25:40.739277: step: 2386/1545, loss: 0.17821580171585083 2023-01-23 11:25:41.637165: step: 2388/1545, loss: 0.2096172571182251 2023-01-23 11:25:42.561469: step: 2390/1545, loss: 0.05946841463446617 2023-01-23 11:25:43.436544: step: 2392/1545, loss: 0.009299690835177898 2023-01-23 11:25:44.290634: step: 2394/1545, loss: 0.016815949231386185 2023-01-23 11:25:45.207886: step: 2396/1545, loss: 0.3568492531776428 2023-01-23 11:25:46.074102: step: 2398/1545, loss: 1.628433108329773 2023-01-23 11:25:46.951352: step: 2400/1545, loss: 0.21322846412658691 2023-01-23 11:25:47.845830: step: 2402/1545, loss: 0.1900506466627121 2023-01-23 11:25:48.739423: step: 2404/1545, loss: 0.019159993156790733 2023-01-23 11:25:49.673324: step: 2406/1545, loss: 0.23539960384368896 2023-01-23 11:25:50.528943: step: 2408/1545, loss: 0.18381689488887787 2023-01-23 11:25:51.425555: step: 2410/1545, loss: 0.11099985241889954 2023-01-23 11:25:52.280104: step: 2412/1545, loss: 0.05515953153371811 2023-01-23 11:25:53.157627: step: 2414/1545, loss: 0.08670021593570709 2023-01-23 11:25:54.066178: step: 2416/1545, loss: 0.34237438440322876 2023-01-23 11:25:54.939784: step: 2418/1545, loss: 0.06340879201889038 2023-01-23 11:25:55.805019: step: 2420/1545, loss: 0.20700785517692566 2023-01-23 11:25:56.678175: step: 2422/1545, loss: 0.2274090051651001 2023-01-23 11:25:57.593448: step: 2424/1545, loss: 0.10171425342559814 2023-01-23 11:25:58.491935: step: 2426/1545, loss: 0.359398752450943 2023-01-23 11:25:59.361729: step: 2428/1545, loss: 0.5320033431053162 2023-01-23 11:26:00.342809: step: 2430/1545, loss: 0.020311105996370316 2023-01-23 11:26:01.201122: step: 2432/1545, loss: 0.23272477090358734 2023-01-23 11:26:02.085455: step: 2434/1545, loss: 0.030147220939397812 2023-01-23 11:26:03.030577: step: 2436/1545, loss: 0.075690358877182 2023-01-23 11:26:03.896857: step: 2438/1545, loss: 0.047036994248628616 2023-01-23 11:26:04.761128: step: 2440/1545, loss: 0.0510273240506649 2023-01-23 11:26:05.637041: step: 2442/1545, loss: 0.0840969905257225 2023-01-23 11:26:06.508365: step: 2444/1545, loss: 0.13048972189426422 2023-01-23 11:26:07.436475: step: 2446/1545, loss: 0.14082932472229004 2023-01-23 11:26:08.485681: step: 2448/1545, loss: 0.2056446373462677 2023-01-23 11:26:09.362319: step: 2450/1545, loss: 0.13344570994377136 2023-01-23 11:26:10.205969: step: 2452/1545, loss: 0.2127375602722168 2023-01-23 11:26:11.109394: step: 2454/1545, loss: 0.2681744694709778 2023-01-23 11:26:12.027603: step: 2456/1545, loss: 0.09694194048643112 2023-01-23 11:26:12.876602: step: 2458/1545, loss: 0.2255769670009613 2023-01-23 11:26:13.736521: step: 2460/1545, loss: 0.344806969165802 2023-01-23 11:26:14.609400: step: 2462/1545, loss: 0.1063259020447731 2023-01-23 11:26:15.466708: step: 2464/1545, loss: 0.31991156935691833 2023-01-23 11:26:16.348544: step: 2466/1545, loss: 0.04846334084868431 2023-01-23 11:26:17.283519: step: 2468/1545, loss: 0.3082723915576935 2023-01-23 11:26:18.149923: step: 2470/1545, loss: 0.08136214315891266 2023-01-23 11:26:19.021048: step: 2472/1545, loss: 0.09241413325071335 2023-01-23 11:26:19.880177: step: 2474/1545, loss: 0.17857137322425842 2023-01-23 11:26:20.759490: step: 2476/1545, loss: 0.06990231573581696 2023-01-23 11:26:21.662396: step: 2478/1545, loss: 0.4434625506401062 2023-01-23 11:26:22.550486: step: 2480/1545, loss: 0.05345826596021652 2023-01-23 11:26:23.416132: step: 2482/1545, loss: 0.6971046924591064 2023-01-23 11:26:24.262845: step: 2484/1545, loss: 0.4642654061317444 2023-01-23 11:26:25.137082: step: 2486/1545, loss: 0.03324200212955475 2023-01-23 11:26:26.017618: step: 2488/1545, loss: 0.11627136170864105 2023-01-23 11:26:26.909014: step: 2490/1545, loss: 0.01230075117200613 2023-01-23 11:26:27.812355: step: 2492/1545, loss: 0.09627532213926315 2023-01-23 11:26:28.707744: step: 2494/1545, loss: 0.5205594897270203 2023-01-23 11:26:29.686613: step: 2496/1545, loss: 0.01858139969408512 2023-01-23 11:26:30.529718: step: 2498/1545, loss: 0.021420903503894806 2023-01-23 11:26:31.378617: step: 2500/1545, loss: 0.1357726752758026 2023-01-23 11:26:32.259887: step: 2502/1545, loss: 0.41846364736557007 2023-01-23 11:26:33.140543: step: 2504/1545, loss: 0.1472259759902954 2023-01-23 11:26:33.992151: step: 2506/1545, loss: 0.20117321610450745 2023-01-23 11:26:34.840305: step: 2508/1545, loss: 0.00402471236884594 2023-01-23 11:26:35.680140: step: 2510/1545, loss: 0.18841521441936493 2023-01-23 11:26:36.563238: step: 2512/1545, loss: 0.16828253865242004 2023-01-23 11:26:37.432620: step: 2514/1545, loss: 0.13281479477882385 2023-01-23 11:26:38.458953: step: 2516/1545, loss: 0.025943797081708908 2023-01-23 11:26:39.313714: step: 2518/1545, loss: 0.35222259163856506 2023-01-23 11:26:40.206303: step: 2520/1545, loss: 0.006041430402547121 2023-01-23 11:26:41.043493: step: 2522/1545, loss: 0.38563764095306396 2023-01-23 11:26:41.931404: step: 2524/1545, loss: 0.07307898998260498 2023-01-23 11:26:42.853207: step: 2526/1545, loss: 0.7903827428817749 2023-01-23 11:26:43.736168: step: 2528/1545, loss: 0.23547090590000153 2023-01-23 11:26:44.682377: step: 2530/1545, loss: 0.010768629610538483 2023-01-23 11:26:45.617200: step: 2532/1545, loss: 1.8534880876541138 2023-01-23 11:26:46.486385: step: 2534/1545, loss: 0.22749732434749603 2023-01-23 11:26:47.456556: step: 2536/1545, loss: 0.13447266817092896 2023-01-23 11:26:48.381453: step: 2538/1545, loss: 0.10120230168104172 2023-01-23 11:26:49.286309: step: 2540/1545, loss: 0.009226173162460327 2023-01-23 11:26:50.203628: step: 2542/1545, loss: 0.09555378556251526 2023-01-23 11:26:51.075130: step: 2544/1545, loss: 0.09600082039833069 2023-01-23 11:26:51.950436: step: 2546/1545, loss: 1.8641449213027954 2023-01-23 11:26:52.825911: step: 2548/1545, loss: 0.036013055592775345 2023-01-23 11:26:53.727263: step: 2550/1545, loss: 0.019300583750009537 2023-01-23 11:26:54.630008: step: 2552/1545, loss: 0.12410455197095871 2023-01-23 11:26:55.477683: step: 2554/1545, loss: 0.10338949412107468 2023-01-23 11:26:56.375445: step: 2556/1545, loss: 0.06814178079366684 2023-01-23 11:26:57.218897: step: 2558/1545, loss: 0.06135035306215286 2023-01-23 11:26:58.062646: step: 2560/1545, loss: 0.18271639943122864 2023-01-23 11:26:58.945006: step: 2562/1545, loss: 0.16259390115737915 2023-01-23 11:26:59.833252: step: 2564/1545, loss: 0.05763224884867668 2023-01-23 11:27:00.702318: step: 2566/1545, loss: 0.05450760945677757 2023-01-23 11:27:01.582254: step: 2568/1545, loss: 0.016496567055583 2023-01-23 11:27:02.480568: step: 2570/1545, loss: 0.2822597622871399 2023-01-23 11:27:03.371051: step: 2572/1545, loss: 0.023246221244335175 2023-01-23 11:27:04.292821: step: 2574/1545, loss: 0.22128826379776 2023-01-23 11:27:05.191434: step: 2576/1545, loss: 0.35396963357925415 2023-01-23 11:27:06.210189: step: 2578/1545, loss: 0.12276677787303925 2023-01-23 11:27:07.132482: step: 2580/1545, loss: 0.29502904415130615 2023-01-23 11:27:08.020672: step: 2582/1545, loss: 0.06760579347610474 2023-01-23 11:27:08.882748: step: 2584/1545, loss: 0.0435585081577301 2023-01-23 11:27:09.749504: step: 2586/1545, loss: 0.13106389343738556 2023-01-23 11:27:10.644272: step: 2588/1545, loss: 0.1443098783493042 2023-01-23 11:27:11.505535: step: 2590/1545, loss: 0.1367458701133728 2023-01-23 11:27:12.388846: step: 2592/1545, loss: 0.029175665229558945 2023-01-23 11:27:13.239242: step: 2594/1545, loss: 0.004665694665163755 2023-01-23 11:27:14.103969: step: 2596/1545, loss: 0.17720213532447815 2023-01-23 11:27:14.953885: step: 2598/1545, loss: 0.6269025802612305 2023-01-23 11:27:15.799057: step: 2600/1545, loss: 0.0196831077337265 2023-01-23 11:27:16.652048: step: 2602/1545, loss: 0.34813380241394043 2023-01-23 11:27:17.589676: step: 2604/1545, loss: 0.1223883107304573 2023-01-23 11:27:18.458514: step: 2606/1545, loss: 0.26710209250450134 2023-01-23 11:27:19.332914: step: 2608/1545, loss: 0.021236758679151535 2023-01-23 11:27:20.337513: step: 2610/1545, loss: 0.34704697132110596 2023-01-23 11:27:21.241097: step: 2612/1545, loss: 0.020148050040006638 2023-01-23 11:27:22.088260: step: 2614/1545, loss: 0.01850336417555809 2023-01-23 11:27:22.999211: step: 2616/1545, loss: 0.015345025807619095 2023-01-23 11:27:23.860255: step: 2618/1545, loss: 0.11332573741674423 2023-01-23 11:27:24.720637: step: 2620/1545, loss: 0.0847434550523758 2023-01-23 11:27:25.590369: step: 2622/1545, loss: 0.15420792996883392 2023-01-23 11:27:26.450012: step: 2624/1545, loss: 0.5361351370811462 2023-01-23 11:27:27.298317: step: 2626/1545, loss: 0.24309542775154114 2023-01-23 11:27:28.194983: step: 2628/1545, loss: 0.04948791489005089 2023-01-23 11:27:29.093712: step: 2630/1545, loss: 0.22467045485973358 2023-01-23 11:27:29.997086: step: 2632/1545, loss: 0.0760752260684967 2023-01-23 11:27:30.904791: step: 2634/1545, loss: 0.3065381646156311 2023-01-23 11:27:31.837963: step: 2636/1545, loss: 0.0569138377904892 2023-01-23 11:27:32.730803: step: 2638/1545, loss: 0.1737370789051056 2023-01-23 11:27:33.626342: step: 2640/1545, loss: 0.42173779010772705 2023-01-23 11:27:34.487638: step: 2642/1545, loss: 0.28111082315444946 2023-01-23 11:27:35.406879: step: 2644/1545, loss: 0.1655413806438446 2023-01-23 11:27:36.279564: step: 2646/1545, loss: 0.04673590138554573 2023-01-23 11:27:37.161700: step: 2648/1545, loss: 0.5569331645965576 2023-01-23 11:27:38.000334: step: 2650/1545, loss: 0.026086919009685516 2023-01-23 11:27:38.890969: step: 2652/1545, loss: 0.12552966177463531 2023-01-23 11:27:39.739864: step: 2654/1545, loss: 0.15010304749011993 2023-01-23 11:27:40.581530: step: 2656/1545, loss: 0.06699605286121368 2023-01-23 11:27:41.496614: step: 2658/1545, loss: 0.20029300451278687 2023-01-23 11:27:42.326060: step: 2660/1545, loss: 0.03919779509305954 2023-01-23 11:27:43.168328: step: 2662/1545, loss: 0.030018292367458344 2023-01-23 11:27:44.059348: step: 2664/1545, loss: 0.04713034629821777 2023-01-23 11:27:44.943345: step: 2666/1545, loss: 0.02683386765420437 2023-01-23 11:27:45.869509: step: 2668/1545, loss: 0.24402199685573578 2023-01-23 11:27:46.766563: step: 2670/1545, loss: 0.2810838222503662 2023-01-23 11:27:47.685448: step: 2672/1545, loss: 0.14553259313106537 2023-01-23 11:27:48.569657: step: 2674/1545, loss: 0.03411759063601494 2023-01-23 11:27:49.430810: step: 2676/1545, loss: 0.43631336092948914 2023-01-23 11:27:50.299452: step: 2678/1545, loss: 0.03843654692173004 2023-01-23 11:27:51.172446: step: 2680/1545, loss: 0.08017434924840927 2023-01-23 11:27:52.065932: step: 2682/1545, loss: 0.1169573962688446 2023-01-23 11:27:52.921686: step: 2684/1545, loss: 0.16597510874271393 2023-01-23 11:27:53.781205: step: 2686/1545, loss: 0.12438300251960754 2023-01-23 11:27:54.628451: step: 2688/1545, loss: 0.028168227523565292 2023-01-23 11:27:55.512231: step: 2690/1545, loss: 0.3043159246444702 2023-01-23 11:27:56.385828: step: 2692/1545, loss: 0.6134644150733948 2023-01-23 11:27:57.305812: step: 2694/1545, loss: 0.23982279002666473 2023-01-23 11:27:58.181268: step: 2696/1545, loss: 0.03745351731777191 2023-01-23 11:27:59.053567: step: 2698/1545, loss: 0.25441136956214905 2023-01-23 11:27:59.956409: step: 2700/1545, loss: 0.5874008536338806 2023-01-23 11:28:00.879629: step: 2702/1545, loss: 0.3917026221752167 2023-01-23 11:28:01.747059: step: 2704/1545, loss: 0.19491782784461975 2023-01-23 11:28:02.628595: step: 2706/1545, loss: 0.13188016414642334 2023-01-23 11:28:03.502699: step: 2708/1545, loss: 0.04618342965841293 2023-01-23 11:28:04.373393: step: 2710/1545, loss: 0.007462706882506609 2023-01-23 11:28:05.206008: step: 2712/1545, loss: 0.06308666616678238 2023-01-23 11:28:06.131739: step: 2714/1545, loss: 0.054653674364089966 2023-01-23 11:28:07.029042: step: 2716/1545, loss: 0.013380572199821472 2023-01-23 11:28:07.898512: step: 2718/1545, loss: 0.11941493302583694 2023-01-23 11:28:08.829083: step: 2720/1545, loss: 0.49692755937576294 2023-01-23 11:28:09.730896: step: 2722/1545, loss: 0.11685381829738617 2023-01-23 11:28:10.648735: step: 2724/1545, loss: 0.6670247912406921 2023-01-23 11:28:11.494742: step: 2726/1545, loss: 0.04199987277388573 2023-01-23 11:28:12.379934: step: 2728/1545, loss: 0.28230640292167664 2023-01-23 11:28:13.280606: step: 2730/1545, loss: 0.2756193280220032 2023-01-23 11:28:14.190504: step: 2732/1545, loss: 0.21802783012390137 2023-01-23 11:28:15.086098: step: 2734/1545, loss: 0.1785835325717926 2023-01-23 11:28:16.043722: step: 2736/1545, loss: 0.07526519894599915 2023-01-23 11:28:16.904105: step: 2738/1545, loss: 0.41403526067733765 2023-01-23 11:28:17.782618: step: 2740/1545, loss: 0.15489517152309418 2023-01-23 11:28:18.617807: step: 2742/1545, loss: 0.06544665992259979 2023-01-23 11:28:19.511619: step: 2744/1545, loss: 0.10954686999320984 2023-01-23 11:28:20.364872: step: 2746/1545, loss: 0.008544725365936756 2023-01-23 11:28:21.211688: step: 2748/1545, loss: 0.024703683331608772 2023-01-23 11:28:22.095779: step: 2750/1545, loss: 0.5955158472061157 2023-01-23 11:28:22.998586: step: 2752/1545, loss: 0.05442619323730469 2023-01-23 11:28:23.897232: step: 2754/1545, loss: 0.17095904052257538 2023-01-23 11:28:24.769250: step: 2756/1545, loss: 0.6932860612869263 2023-01-23 11:28:25.630405: step: 2758/1545, loss: 0.015731703490018845 2023-01-23 11:28:26.519001: step: 2760/1545, loss: 0.07202526181936264 2023-01-23 11:28:27.421677: step: 2762/1545, loss: 0.008058613166213036 2023-01-23 11:28:28.296576: step: 2764/1545, loss: 0.11050399392843246 2023-01-23 11:28:29.174411: step: 2766/1545, loss: 0.5121269822120667 2023-01-23 11:28:30.015864: step: 2768/1545, loss: 0.13847200572490692 2023-01-23 11:28:30.860311: step: 2770/1545, loss: 0.037806566804647446 2023-01-23 11:28:31.759355: step: 2772/1545, loss: 0.3412270247936249 2023-01-23 11:28:32.629875: step: 2774/1545, loss: 0.42811062932014465 2023-01-23 11:28:33.513723: step: 2776/1545, loss: 2.5938987731933594 2023-01-23 11:28:34.413650: step: 2778/1545, loss: 0.06645350158214569 2023-01-23 11:28:35.268604: step: 2780/1545, loss: 0.19436338543891907 2023-01-23 11:28:36.189369: step: 2782/1545, loss: 0.09546060115098953 2023-01-23 11:28:37.082361: step: 2784/1545, loss: 0.12722072005271912 2023-01-23 11:28:37.974677: step: 2786/1545, loss: 0.09920283406972885 2023-01-23 11:28:38.862534: step: 2788/1545, loss: 0.20708392560482025 2023-01-23 11:28:39.712737: step: 2790/1545, loss: 0.01372375339269638 2023-01-23 11:28:40.591152: step: 2792/1545, loss: 0.1251046061515808 2023-01-23 11:28:41.438084: step: 2794/1545, loss: 0.15836575627326965 2023-01-23 11:28:42.338403: step: 2796/1545, loss: 0.09772246330976486 2023-01-23 11:28:43.245997: step: 2798/1545, loss: 0.03954977169632912 2023-01-23 11:28:44.139797: step: 2800/1545, loss: 0.1979857087135315 2023-01-23 11:28:45.035197: step: 2802/1545, loss: 0.06893550604581833 2023-01-23 11:28:45.930951: step: 2804/1545, loss: 0.25075316429138184 2023-01-23 11:28:46.801689: step: 2806/1545, loss: 0.3422166705131531 2023-01-23 11:28:47.683752: step: 2808/1545, loss: 0.12279824167490005 2023-01-23 11:28:48.533404: step: 2810/1545, loss: 0.013042447157204151 2023-01-23 11:28:49.419300: step: 2812/1545, loss: 0.2901524603366852 2023-01-23 11:28:50.287674: step: 2814/1545, loss: 0.20501738786697388 2023-01-23 11:28:51.210968: step: 2816/1545, loss: 0.2091774344444275 2023-01-23 11:28:52.111683: step: 2818/1545, loss: 0.04312713071703911 2023-01-23 11:28:52.995446: step: 2820/1545, loss: 0.22425365447998047 2023-01-23 11:28:53.900796: step: 2822/1545, loss: 0.011496889404952526 2023-01-23 11:28:54.922166: step: 2824/1545, loss: 0.2779731750488281 2023-01-23 11:28:55.795259: step: 2826/1545, loss: 0.0915469229221344 2023-01-23 11:28:56.613639: step: 2828/1545, loss: 0.09302966296672821 2023-01-23 11:28:57.518858: step: 2830/1545, loss: 0.13122670352458954 2023-01-23 11:28:58.394859: step: 2832/1545, loss: 0.25727707147598267 2023-01-23 11:28:59.288282: step: 2834/1545, loss: 0.052768394351005554 2023-01-23 11:29:00.161289: step: 2836/1545, loss: 0.152016282081604 2023-01-23 11:29:01.020884: step: 2838/1545, loss: 0.04004056006669998 2023-01-23 11:29:01.899972: step: 2840/1545, loss: 0.014626171439886093 2023-01-23 11:29:02.791524: step: 2842/1545, loss: 0.6901261806488037 2023-01-23 11:29:03.694188: step: 2844/1545, loss: 0.04271680861711502 2023-01-23 11:29:04.543271: step: 2846/1545, loss: 0.010210683569312096 2023-01-23 11:29:05.420751: step: 2848/1545, loss: 0.4212300777435303 2023-01-23 11:29:06.296833: step: 2850/1545, loss: 0.040207233279943466 2023-01-23 11:29:07.158314: step: 2852/1545, loss: 0.051949191838502884 2023-01-23 11:29:08.031922: step: 2854/1545, loss: 0.03728858381509781 2023-01-23 11:29:08.909226: step: 2856/1545, loss: 0.027666758745908737 2023-01-23 11:29:09.773075: step: 2858/1545, loss: 0.019704751670360565 2023-01-23 11:29:10.646188: step: 2860/1545, loss: 0.03532098978757858 2023-01-23 11:29:11.553293: step: 2862/1545, loss: 0.29553890228271484 2023-01-23 11:29:12.397280: step: 2864/1545, loss: 0.1259785294532776 2023-01-23 11:29:13.262720: step: 2866/1545, loss: 1.5531482696533203 2023-01-23 11:29:14.125349: step: 2868/1545, loss: 0.2003544569015503 2023-01-23 11:29:14.978846: step: 2870/1545, loss: 0.8322744369506836 2023-01-23 11:29:15.839461: step: 2872/1545, loss: 0.06988724321126938 2023-01-23 11:29:16.706027: step: 2874/1545, loss: 0.03633534908294678 2023-01-23 11:29:17.584630: step: 2876/1545, loss: 0.012549812905490398 2023-01-23 11:29:18.465410: step: 2878/1545, loss: 0.15008939802646637 2023-01-23 11:29:19.331842: step: 2880/1545, loss: 0.06290047615766525 2023-01-23 11:29:20.208518: step: 2882/1545, loss: 0.32743820548057556 2023-01-23 11:29:21.113409: step: 2884/1545, loss: 0.04564771428704262 2023-01-23 11:29:21.961883: step: 2886/1545, loss: 0.03196852281689644 2023-01-23 11:29:22.832501: step: 2888/1545, loss: 0.03688516095280647 2023-01-23 11:29:23.675002: step: 2890/1545, loss: 0.04433676600456238 2023-01-23 11:29:24.584404: step: 2892/1545, loss: 0.36018019914627075 2023-01-23 11:29:25.426455: step: 2894/1545, loss: 0.37417784333229065 2023-01-23 11:29:26.263557: step: 2896/1545, loss: 0.05271763354539871 2023-01-23 11:29:27.112543: step: 2898/1545, loss: 0.037768103182315826 2023-01-23 11:29:28.005126: step: 2900/1545, loss: 0.1868891417980194 2023-01-23 11:29:28.866266: step: 2902/1545, loss: 0.20018145442008972 2023-01-23 11:29:29.751356: step: 2904/1545, loss: 0.2463027983903885 2023-01-23 11:29:30.725723: step: 2906/1545, loss: 0.0347551591694355 2023-01-23 11:29:31.613960: step: 2908/1545, loss: 0.11852424591779709 2023-01-23 11:29:32.516145: step: 2910/1545, loss: 0.074366994202137 2023-01-23 11:29:33.357519: step: 2912/1545, loss: 0.0927998274564743 2023-01-23 11:29:34.267756: step: 2914/1545, loss: 0.26381275057792664 2023-01-23 11:29:35.158219: step: 2916/1545, loss: 0.14413125813007355 2023-01-23 11:29:36.039772: step: 2918/1545, loss: 0.03450058028101921 2023-01-23 11:29:36.926900: step: 2920/1545, loss: 0.152401402592659 2023-01-23 11:29:37.762169: step: 2922/1545, loss: 0.05282019451260567 2023-01-23 11:29:38.607195: step: 2924/1545, loss: 0.1345463991165161 2023-01-23 11:29:39.472383: step: 2926/1545, loss: 0.027872733771800995 2023-01-23 11:29:40.434337: step: 2928/1545, loss: 0.007185585331171751 2023-01-23 11:29:41.343479: step: 2930/1545, loss: 0.016416113823652267 2023-01-23 11:29:42.224678: step: 2932/1545, loss: 0.21191814541816711 2023-01-23 11:29:43.130089: step: 2934/1545, loss: 0.7159196734428406 2023-01-23 11:29:43.968359: step: 2936/1545, loss: 0.08856172114610672 2023-01-23 11:29:44.827687: step: 2938/1545, loss: 0.2974794805049896 2023-01-23 11:29:45.670564: step: 2940/1545, loss: 0.005747451446950436 2023-01-23 11:29:46.505680: step: 2942/1545, loss: 0.2440984547138214 2023-01-23 11:29:47.346148: step: 2944/1545, loss: 0.1578090786933899 2023-01-23 11:29:48.201694: step: 2946/1545, loss: 0.34194496273994446 2023-01-23 11:29:49.055800: step: 2948/1545, loss: 0.07829339057207108 2023-01-23 11:29:49.936672: step: 2950/1545, loss: 0.4019671380519867 2023-01-23 11:29:50.824600: step: 2952/1545, loss: 0.020404968410730362 2023-01-23 11:29:51.666744: step: 2954/1545, loss: 0.03522970527410507 2023-01-23 11:29:52.529493: step: 2956/1545, loss: 0.015883397310972214 2023-01-23 11:29:53.412140: step: 2958/1545, loss: 0.010858788155019283 2023-01-23 11:29:54.290386: step: 2960/1545, loss: 0.04971304535865784 2023-01-23 11:29:55.240337: step: 2962/1545, loss: 0.011356957256793976 2023-01-23 11:29:56.103822: step: 2964/1545, loss: 0.0967102199792862 2023-01-23 11:29:57.015170: step: 2966/1545, loss: 0.027241704985499382 2023-01-23 11:29:57.905468: step: 2968/1545, loss: 0.3244020938873291 2023-01-23 11:29:58.760172: step: 2970/1545, loss: 0.08849582076072693 2023-01-23 11:29:59.647669: step: 2972/1545, loss: 0.11370997875928879 2023-01-23 11:30:00.526082: step: 2974/1545, loss: 0.15154363214969635 2023-01-23 11:30:01.437836: step: 2976/1545, loss: 0.025715110823512077 2023-01-23 11:30:02.370116: step: 2978/1545, loss: 0.25705432891845703 2023-01-23 11:30:03.261437: step: 2980/1545, loss: 0.048289451748132706 2023-01-23 11:30:04.101002: step: 2982/1545, loss: 0.1316668540239334 2023-01-23 11:30:05.029614: step: 2984/1545, loss: 0.05478305369615555 2023-01-23 11:30:05.923251: step: 2986/1545, loss: 0.14477317035198212 2023-01-23 11:30:06.844257: step: 2988/1545, loss: 0.003688064869493246 2023-01-23 11:30:07.745406: step: 2990/1545, loss: 0.22039435803890228 2023-01-23 11:30:08.619277: step: 2992/1545, loss: 0.22748643159866333 2023-01-23 11:30:09.503380: step: 2994/1545, loss: 0.20670512318611145 2023-01-23 11:30:10.389003: step: 2996/1545, loss: 0.5674944519996643 2023-01-23 11:30:11.281237: step: 2998/1545, loss: 0.1148262619972229 2023-01-23 11:30:12.154010: step: 3000/1545, loss: 0.022990446537733078 2023-01-23 11:30:13.031409: step: 3002/1545, loss: 0.3595642149448395 2023-01-23 11:30:13.924135: step: 3004/1545, loss: 0.2151157110929489 2023-01-23 11:30:14.833071: step: 3006/1545, loss: 0.01868995651602745 2023-01-23 11:30:15.676861: step: 3008/1545, loss: 0.1251114159822464 2023-01-23 11:30:16.542157: step: 3010/1545, loss: 0.15359820425510406 2023-01-23 11:30:17.381916: step: 3012/1545, loss: 0.10844888538122177 2023-01-23 11:30:18.288547: step: 3014/1545, loss: 1.6432465314865112 2023-01-23 11:30:19.162881: step: 3016/1545, loss: 0.4351157248020172 2023-01-23 11:30:20.049706: step: 3018/1545, loss: 0.05780434608459473 2023-01-23 11:30:20.953300: step: 3020/1545, loss: 0.056313518434762955 2023-01-23 11:30:21.804216: step: 3022/1545, loss: 0.19208350777626038 2023-01-23 11:30:22.650648: step: 3024/1545, loss: 0.8950188159942627 2023-01-23 11:30:23.575190: step: 3026/1545, loss: 0.10609223693609238 2023-01-23 11:30:24.431815: step: 3028/1545, loss: 0.09798232465982437 2023-01-23 11:30:25.304837: step: 3030/1545, loss: 0.17282314598560333 2023-01-23 11:30:26.210549: step: 3032/1545, loss: 0.4519149959087372 2023-01-23 11:30:27.101212: step: 3034/1545, loss: 0.14152899384498596 2023-01-23 11:30:27.970767: step: 3036/1545, loss: 0.031974710524082184 2023-01-23 11:30:28.820700: step: 3038/1545, loss: 0.31361597776412964 2023-01-23 11:30:29.697968: step: 3040/1545, loss: 0.10197693854570389 2023-01-23 11:30:30.594455: step: 3042/1545, loss: 0.06844789534807205 2023-01-23 11:30:31.453149: step: 3044/1545, loss: 0.009273229166865349 2023-01-23 11:30:32.306171: step: 3046/1545, loss: 0.1362425684928894 2023-01-23 11:30:33.157285: step: 3048/1545, loss: 0.09942422807216644 2023-01-23 11:30:34.060321: step: 3050/1545, loss: 0.016376901417970657 2023-01-23 11:30:34.919937: step: 3052/1545, loss: 0.24126677215099335 2023-01-23 11:30:35.822271: step: 3054/1545, loss: 0.06800902634859085 2023-01-23 11:30:36.681884: step: 3056/1545, loss: 0.004815108608454466 2023-01-23 11:30:37.577661: step: 3058/1545, loss: 0.08609342575073242 2023-01-23 11:30:38.450472: step: 3060/1545, loss: 0.1078401654958725 2023-01-23 11:30:39.362333: step: 3062/1545, loss: 0.1480996012687683 2023-01-23 11:30:40.210844: step: 3064/1545, loss: 0.06171584874391556 2023-01-23 11:30:41.062297: step: 3066/1545, loss: 0.033827122300863266 2023-01-23 11:30:41.942228: step: 3068/1545, loss: 0.007416061125695705 2023-01-23 11:30:42.812224: step: 3070/1545, loss: 0.04758735001087189 2023-01-23 11:30:43.700274: step: 3072/1545, loss: 0.11441349238157272 2023-01-23 11:30:44.607863: step: 3074/1545, loss: 0.2238311767578125 2023-01-23 11:30:45.482002: step: 3076/1545, loss: 0.09947868436574936 2023-01-23 11:30:46.440590: step: 3078/1545, loss: 0.7284571528434753 2023-01-23 11:30:47.307115: step: 3080/1545, loss: 0.14294518530368805 2023-01-23 11:30:48.183368: step: 3082/1545, loss: 0.12489154934883118 2023-01-23 11:30:49.036505: step: 3084/1545, loss: 0.13840357959270477 2023-01-23 11:30:49.929736: step: 3086/1545, loss: 0.03521205112338066 2023-01-23 11:30:50.805148: step: 3088/1545, loss: 0.20819436013698578 2023-01-23 11:30:51.665606: step: 3090/1545, loss: 0.14433418214321136 ================================================== Loss: 0.189 -------------------- Dev Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6712254768413644, 'r': 0.6536409770738136, 'f1': 0.6623165304289838}, 'combined': 0.43598534197303607, 'epoch': 13} Test Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7075100625542532, 'r': 0.7242590598350336, 'f1': 0.7157865953614917}, 'combined': 0.4996765063605527, 'epoch': 13} Dev Korean: {'event': {'p': 0.6137855579868708, 'r': 0.7470039946737683, 'f1': 0.6738738738738739}, 'argument': {'p': 0.6690091520011272, 'r': 0.655950414799904, 'f1': 0.6624154302604034}, 'combined': 0.446384452103407, 'epoch': 13} Test Korean: {'event': {'p': 0.6338624338624339, 'r': 0.7659846547314578, 'f1': 0.6936884771279677}, 'argument': {'p': 0.7011231647409775, 'r': 0.7214999756474074, 'f1': 0.7111656375114853}, 'combined': 0.4933274080710825, 'epoch': 13} Dev Russian: {'event': {'p': 0.5748031496062992, 'r': 0.7776298268974701, 'f1': 0.6610073571024335}, 'argument': {'p': 0.6672747326469398, 'r': 0.6644088425997805, 'f1': 0.6658387038105403}, 'combined': 0.4401242818623153, 'epoch': 13} Test Russian: {'event': {'p': 0.6258096661684106, 'r': 0.80306905370844, 'f1': 0.7034444133295996}, 'argument': {'p': 0.7109982329063265, 'r': 0.7357540680468313, 'f1': 0.7231643480232148}, 'combined': 0.5087059205360728, 'epoch': 13} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6697240259740259, 'r': 0.6199098422238918, 'f1': 0.643854857588763}, 'combined': 0.4585027016162403, 'epoch': 13} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.7052910052910053, 'r': 0.44080687830687837, 'f1': 0.5425315425315426}, 'combined': 0.33313340330884195, 'epoch': 13} Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.6177016825623637, 'r': 0.5625497466192956, 'f1': 0.5888371179566457}, 'combined': 0.3130526449896091, 'epoch': 13} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.612691466083151, 'r': 0.7456724367509987, 'f1': 0.6726726726726727}, 'argument': {'p': 0.6540410788569386, 'r': 0.6466702177127959, 'f1': 0.6503347637141906}, 'combined': 0.4374624236395757, 'epoch': 9} Test for Korean: {'event': {'p': 0.6354497354497355, 'r': 0.7679028132992327, 'f1': 0.6954255935147655}, 'argument': {'p': 0.7132062904851311, 'r': 0.7077515578619179, 'f1': 0.7104684544372034}, 'combined': 0.4940779466005103, 'epoch': 9} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6633986928104574, 'r': 0.46990740740740733, 'f1': 0.5501355013550133}, 'combined': 0.3474540008557979, 'epoch': 9} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 14 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 11:36:05.139001: step: 2/1545, loss: 0.03652255982160568 2023-01-23 11:36:06.030267: step: 4/1545, loss: 0.17792992293834686 2023-01-23 11:36:06.924602: step: 6/1545, loss: 0.04200435057282448 2023-01-23 11:36:07.808612: step: 8/1545, loss: 0.10593477636575699 2023-01-23 11:36:08.637952: step: 10/1545, loss: 0.03455491364002228 2023-01-23 11:36:09.533816: step: 12/1545, loss: 0.010998308658599854 2023-01-23 11:36:10.464125: step: 14/1545, loss: 0.18473827838897705 2023-01-23 11:36:11.330120: step: 16/1545, loss: 0.07160024344921112 2023-01-23 11:36:12.177225: step: 18/1545, loss: 0.07539868354797363 2023-01-23 11:36:13.102038: step: 20/1545, loss: 0.20069913566112518 2023-01-23 11:36:14.035001: step: 22/1545, loss: 0.01947086863219738 2023-01-23 11:36:14.906109: step: 24/1545, loss: 0.04089647904038429 2023-01-23 11:36:15.805202: step: 26/1545, loss: 0.016023928299546242 2023-01-23 11:36:16.702303: step: 28/1545, loss: 0.034166958183050156 2023-01-23 11:36:17.542048: step: 30/1545, loss: 0.05992329120635986 2023-01-23 11:36:18.427515: step: 32/1545, loss: 0.11314645409584045 2023-01-23 11:36:19.300616: step: 34/1545, loss: 0.12256868928670883 2023-01-23 11:36:20.255515: step: 36/1545, loss: 0.013479769229888916 2023-01-23 11:36:21.143392: step: 38/1545, loss: 0.1901022344827652 2023-01-23 11:36:22.018521: step: 40/1545, loss: 0.06247361749410629 2023-01-23 11:36:22.843929: step: 42/1545, loss: 0.37358546257019043 2023-01-23 11:36:23.767325: step: 44/1545, loss: 0.13545480370521545 2023-01-23 11:36:24.628649: step: 46/1545, loss: 0.1657964289188385 2023-01-23 11:36:25.511359: step: 48/1545, loss: 0.288277804851532 2023-01-23 11:36:26.376377: step: 50/1545, loss: 0.00665578618645668 2023-01-23 11:36:27.265949: step: 52/1545, loss: 0.07739531248807907 2023-01-23 11:36:28.118123: step: 54/1545, loss: 0.12291377782821655 2023-01-23 11:36:29.007439: step: 56/1545, loss: 0.015592662617564201 2023-01-23 11:36:29.902000: step: 58/1545, loss: 0.22965100407600403 2023-01-23 11:36:30.796115: step: 60/1545, loss: 0.0018614527070894837 2023-01-23 11:36:31.635492: step: 62/1545, loss: 0.02131732925772667 2023-01-23 11:36:32.563592: step: 64/1545, loss: 0.5792679786682129 2023-01-23 11:36:33.427206: step: 66/1545, loss: 0.022733647376298904 2023-01-23 11:36:34.316391: step: 68/1545, loss: 0.2905402183532715 2023-01-23 11:36:35.172878: step: 70/1545, loss: 0.10420656204223633 2023-01-23 11:36:36.042724: step: 72/1545, loss: 0.008125727996230125 2023-01-23 11:36:36.966742: step: 74/1545, loss: 0.09526309370994568 2023-01-23 11:36:37.888966: step: 76/1545, loss: 0.03320086747407913 2023-01-23 11:36:38.759276: step: 78/1545, loss: 0.053857579827308655 2023-01-23 11:36:39.681061: step: 80/1545, loss: 0.030296677723526955 2023-01-23 11:36:40.589788: step: 82/1545, loss: 0.1189260482788086 2023-01-23 11:36:41.478858: step: 84/1545, loss: 0.20815427601337433 2023-01-23 11:36:42.371199: step: 86/1545, loss: 0.001650615013204515 2023-01-23 11:36:43.405164: step: 88/1545, loss: 0.07103627920150757 2023-01-23 11:36:44.291490: step: 90/1545, loss: 0.17900046706199646 2023-01-23 11:36:45.116101: step: 92/1545, loss: 0.0681886151432991 2023-01-23 11:36:45.950439: step: 94/1545, loss: 0.00598481809720397 2023-01-23 11:36:46.811290: step: 96/1545, loss: 0.07601652294397354 2023-01-23 11:36:47.683570: step: 98/1545, loss: 0.10417607426643372 2023-01-23 11:36:48.592003: step: 100/1545, loss: 0.19643299281597137 2023-01-23 11:36:49.435423: step: 102/1545, loss: 0.006212486885488033 2023-01-23 11:36:50.302132: step: 104/1545, loss: 0.011816345155239105 2023-01-23 11:36:51.199465: step: 106/1545, loss: 0.053850408643484116 2023-01-23 11:36:52.112150: step: 108/1545, loss: 0.01844884268939495 2023-01-23 11:36:53.013365: step: 110/1545, loss: 0.021734662353992462 2023-01-23 11:36:53.861785: step: 112/1545, loss: 0.10715346783399582 2023-01-23 11:36:54.754370: step: 114/1545, loss: 0.10116056352853775 2023-01-23 11:36:55.673317: step: 116/1545, loss: 0.061065997928380966 2023-01-23 11:36:56.578158: step: 118/1545, loss: 0.06167691946029663 2023-01-23 11:36:57.430053: step: 120/1545, loss: 0.04001905024051666 2023-01-23 11:36:58.248828: step: 122/1545, loss: 0.16836851835250854 2023-01-23 11:36:59.127562: step: 124/1545, loss: 0.11880809813737869 2023-01-23 11:37:00.038975: step: 126/1545, loss: 0.0938057079911232 2023-01-23 11:37:00.895622: step: 128/1545, loss: 0.03280377388000488 2023-01-23 11:37:01.769916: step: 130/1545, loss: 0.11621730774641037 2023-01-23 11:37:02.649267: step: 132/1545, loss: 0.13832853734493256 2023-01-23 11:37:03.553743: step: 134/1545, loss: 0.13170138001441956 2023-01-23 11:37:04.489268: step: 136/1545, loss: 0.20191626250743866 2023-01-23 11:37:05.357251: step: 138/1545, loss: 0.09147945046424866 2023-01-23 11:37:06.237139: step: 140/1545, loss: 0.03581760823726654 2023-01-23 11:37:07.173232: step: 142/1545, loss: 0.24115388095378876 2023-01-23 11:37:08.077604: step: 144/1545, loss: 0.1196509450674057 2023-01-23 11:37:08.970775: step: 146/1545, loss: 0.017667077481746674 2023-01-23 11:37:09.824159: step: 148/1545, loss: 0.05604900047183037 2023-01-23 11:37:10.713458: step: 150/1545, loss: 0.12549085915088654 2023-01-23 11:37:11.578557: step: 152/1545, loss: 0.16578425467014313 2023-01-23 11:37:12.498177: step: 154/1545, loss: 0.09541573375463486 2023-01-23 11:37:13.356909: step: 156/1545, loss: 0.04485519975423813 2023-01-23 11:37:14.271436: step: 158/1545, loss: 0.040441613644361496 2023-01-23 11:37:15.151888: step: 160/1545, loss: 0.03953808173537254 2023-01-23 11:37:16.006580: step: 162/1545, loss: 2.4613113403320312 2023-01-23 11:37:16.890911: step: 164/1545, loss: 0.5256133675575256 2023-01-23 11:37:17.764584: step: 166/1545, loss: 0.049031972885131836 2023-01-23 11:37:18.667957: step: 168/1545, loss: 0.08309455960988998 2023-01-23 11:37:19.532517: step: 170/1545, loss: 0.00816335529088974 2023-01-23 11:37:20.452094: step: 172/1545, loss: 0.0350966677069664 2023-01-23 11:37:21.329592: step: 174/1545, loss: 0.07304281741380692 2023-01-23 11:37:22.194107: step: 176/1545, loss: 0.004819054156541824 2023-01-23 11:37:23.098129: step: 178/1545, loss: 0.09330432116985321 2023-01-23 11:37:23.983829: step: 180/1545, loss: 0.38651809096336365 2023-01-23 11:37:24.852660: step: 182/1545, loss: 0.2071416825056076 2023-01-23 11:37:25.715874: step: 184/1545, loss: 0.02109035663306713 2023-01-23 11:37:26.584141: step: 186/1545, loss: 0.054330974817276 2023-01-23 11:37:27.582917: step: 188/1545, loss: 0.3029995262622833 2023-01-23 11:37:28.483511: step: 190/1545, loss: 0.1825103461742401 2023-01-23 11:37:29.358891: step: 192/1545, loss: 0.21499238908290863 2023-01-23 11:37:30.251131: step: 194/1545, loss: 0.008083311840891838 2023-01-23 11:37:31.150210: step: 196/1545, loss: 0.004167546518146992 2023-01-23 11:37:32.026457: step: 198/1545, loss: 0.20974527299404144 2023-01-23 11:37:32.970197: step: 200/1545, loss: 0.06417790800333023 2023-01-23 11:37:33.889644: step: 202/1545, loss: 0.19434261322021484 2023-01-23 11:37:34.756254: step: 204/1545, loss: 0.011719825677573681 2023-01-23 11:37:35.644921: step: 206/1545, loss: 0.05302472785115242 2023-01-23 11:37:36.490432: step: 208/1545, loss: 0.08569539338350296 2023-01-23 11:37:37.366334: step: 210/1545, loss: 0.02826061099767685 2023-01-23 11:37:38.224857: step: 212/1545, loss: 0.028431955724954605 2023-01-23 11:37:39.116774: step: 214/1545, loss: 0.039773955941200256 2023-01-23 11:37:40.041737: step: 216/1545, loss: 0.012938518077135086 2023-01-23 11:37:40.929451: step: 218/1545, loss: 0.05388975515961647 2023-01-23 11:37:41.822403: step: 220/1545, loss: 0.021082796156406403 2023-01-23 11:37:42.689314: step: 222/1545, loss: 0.1298072785139084 2023-01-23 11:37:43.545605: step: 224/1545, loss: 0.2942875921726227 2023-01-23 11:37:44.399747: step: 226/1545, loss: 0.04482579976320267 2023-01-23 11:37:45.273590: step: 228/1545, loss: 0.006863659247756004 2023-01-23 11:37:46.147615: step: 230/1545, loss: 0.08913171291351318 2023-01-23 11:37:47.034450: step: 232/1545, loss: 0.001136143459007144 2023-01-23 11:37:47.881415: step: 234/1545, loss: 0.1565164476633072 2023-01-23 11:37:48.731757: step: 236/1545, loss: 0.05486207827925682 2023-01-23 11:37:49.661663: step: 238/1545, loss: 0.24686814844608307 2023-01-23 11:37:50.573181: step: 240/1545, loss: 0.15003031492233276 2023-01-23 11:37:51.484820: step: 242/1545, loss: 0.07124331593513489 2023-01-23 11:37:52.418677: step: 244/1545, loss: 0.09139705449342728 2023-01-23 11:37:53.395959: step: 246/1545, loss: 0.03809200972318649 2023-01-23 11:37:54.360204: step: 248/1545, loss: 0.0189126655459404 2023-01-23 11:37:55.217910: step: 250/1545, loss: 0.05694146454334259 2023-01-23 11:37:56.098442: step: 252/1545, loss: 0.16035062074661255 2023-01-23 11:37:56.957123: step: 254/1545, loss: 0.004276975989341736 2023-01-23 11:37:57.843833: step: 256/1545, loss: 0.38901615142822266 2023-01-23 11:37:58.689922: step: 258/1545, loss: 0.1498115062713623 2023-01-23 11:37:59.574224: step: 260/1545, loss: 0.07206601649522781 2023-01-23 11:38:00.528821: step: 262/1545, loss: 0.3404773473739624 2023-01-23 11:38:01.451598: step: 264/1545, loss: 0.07659581303596497 2023-01-23 11:38:02.315601: step: 266/1545, loss: 0.58623206615448 2023-01-23 11:38:03.226984: step: 268/1545, loss: 0.005132636055350304 2023-01-23 11:38:04.106808: step: 270/1545, loss: 0.019182683899998665 2023-01-23 11:38:04.973890: step: 272/1545, loss: 0.10124436020851135 2023-01-23 11:38:05.855697: step: 274/1545, loss: 0.005373950581997633 2023-01-23 11:38:06.759418: step: 276/1545, loss: 0.24668392539024353 2023-01-23 11:38:07.642185: step: 278/1545, loss: 0.04162349924445152 2023-01-23 11:38:08.525833: step: 280/1545, loss: 0.14055490493774414 2023-01-23 11:38:09.426070: step: 282/1545, loss: 0.14502468705177307 2023-01-23 11:38:10.328891: step: 284/1545, loss: 0.13705867528915405 2023-01-23 11:38:11.239808: step: 286/1545, loss: 0.5085384249687195 2023-01-23 11:38:12.126980: step: 288/1545, loss: 0.30471494793891907 2023-01-23 11:38:12.989583: step: 290/1545, loss: 0.03219117596745491 2023-01-23 11:38:13.909016: step: 292/1545, loss: 0.07641368359327316 2023-01-23 11:38:14.743076: step: 294/1545, loss: 0.16972234845161438 2023-01-23 11:38:15.594713: step: 296/1545, loss: 0.9176649451255798 2023-01-23 11:38:16.513947: step: 298/1545, loss: 0.022585393860936165 2023-01-23 11:38:17.406508: step: 300/1545, loss: 0.13755808770656586 2023-01-23 11:38:18.333025: step: 302/1545, loss: 0.06353577971458435 2023-01-23 11:38:19.257774: step: 304/1545, loss: 0.6779203414916992 2023-01-23 11:38:20.143636: step: 306/1545, loss: 0.04292275011539459 2023-01-23 11:38:21.021432: step: 308/1545, loss: 0.14161328971385956 2023-01-23 11:38:21.927929: step: 310/1545, loss: 0.005702459719032049 2023-01-23 11:38:22.804011: step: 312/1545, loss: 0.039268482476472855 2023-01-23 11:38:23.795967: step: 314/1545, loss: 0.11563275754451752 2023-01-23 11:38:24.658748: step: 316/1545, loss: 0.06823942810297012 2023-01-23 11:38:25.581435: step: 318/1545, loss: 0.04696081951260567 2023-01-23 11:38:26.445991: step: 320/1545, loss: 0.012410356663167477 2023-01-23 11:38:27.337801: step: 322/1545, loss: 0.456810861825943 2023-01-23 11:38:28.236011: step: 324/1545, loss: 0.17976580560207367 2023-01-23 11:38:29.131590: step: 326/1545, loss: 0.38690170645713806 2023-01-23 11:38:30.003766: step: 328/1545, loss: 0.5114243030548096 2023-01-23 11:38:30.934577: step: 330/1545, loss: 0.0031263292767107487 2023-01-23 11:38:31.793688: step: 332/1545, loss: 0.4599090814590454 2023-01-23 11:38:32.646776: step: 334/1545, loss: 0.02572144754230976 2023-01-23 11:38:33.532980: step: 336/1545, loss: 0.16097256541252136 2023-01-23 11:38:34.446326: step: 338/1545, loss: 0.016469569876790047 2023-01-23 11:38:35.323356: step: 340/1545, loss: 0.44949835538864136 2023-01-23 11:38:36.205579: step: 342/1545, loss: 0.025919048115611076 2023-01-23 11:38:37.134184: step: 344/1545, loss: 0.20086249709129333 2023-01-23 11:38:37.971426: step: 346/1545, loss: 0.31360918283462524 2023-01-23 11:38:38.907724: step: 348/1545, loss: 0.14988018572330475 2023-01-23 11:38:39.757815: step: 350/1545, loss: 0.01581527292728424 2023-01-23 11:38:40.700515: step: 352/1545, loss: 0.25850555300712585 2023-01-23 11:38:41.551140: step: 354/1545, loss: 0.07661242038011551 2023-01-23 11:38:42.402959: step: 356/1545, loss: 0.08584248274564743 2023-01-23 11:38:43.310980: step: 358/1545, loss: 0.0449678897857666 2023-01-23 11:38:44.201980: step: 360/1545, loss: 0.1060965284705162 2023-01-23 11:38:45.080175: step: 362/1545, loss: 0.06809655576944351 2023-01-23 11:38:45.941870: step: 364/1545, loss: 0.129148930311203 2023-01-23 11:38:46.787896: step: 366/1545, loss: 0.051800936460494995 2023-01-23 11:38:47.668492: step: 368/1545, loss: 0.15259984135627747 2023-01-23 11:38:48.547601: step: 370/1545, loss: 0.0664445087313652 2023-01-23 11:38:49.427844: step: 372/1545, loss: 0.0022854446433484554 2023-01-23 11:38:50.325858: step: 374/1545, loss: 0.018341895192861557 2023-01-23 11:38:51.228706: step: 376/1545, loss: 0.06135450303554535 2023-01-23 11:38:52.100946: step: 378/1545, loss: 0.2546072006225586 2023-01-23 11:38:53.019574: step: 380/1545, loss: 0.15037672221660614 2023-01-23 11:38:53.890113: step: 382/1545, loss: 0.13893604278564453 2023-01-23 11:38:54.792003: step: 384/1545, loss: 0.013406100682914257 2023-01-23 11:38:55.664289: step: 386/1545, loss: 0.05671563744544983 2023-01-23 11:38:56.552442: step: 388/1545, loss: 0.1459679752588272 2023-01-23 11:38:57.426565: step: 390/1545, loss: 0.05987754464149475 2023-01-23 11:38:58.278418: step: 392/1545, loss: 0.002842889167368412 2023-01-23 11:38:59.182302: step: 394/1545, loss: 0.17933858931064606 2023-01-23 11:39:00.030793: step: 396/1545, loss: 0.09157386422157288 2023-01-23 11:39:00.935897: step: 398/1545, loss: 0.24358868598937988 2023-01-23 11:39:01.808341: step: 400/1545, loss: 0.018828747794032097 2023-01-23 11:39:02.665457: step: 402/1545, loss: 0.40086066722869873 2023-01-23 11:39:03.546450: step: 404/1545, loss: 0.2022174894809723 2023-01-23 11:39:04.471696: step: 406/1545, loss: 0.133168026804924 2023-01-23 11:39:05.370934: step: 408/1545, loss: 0.15368913114070892 2023-01-23 11:39:06.265332: step: 410/1545, loss: 0.08901898562908173 2023-01-23 11:39:07.113878: step: 412/1545, loss: 0.10534460097551346 2023-01-23 11:39:08.041616: step: 414/1545, loss: 0.26576969027519226 2023-01-23 11:39:08.935598: step: 416/1545, loss: 0.008911043405532837 2023-01-23 11:39:09.788870: step: 418/1545, loss: 0.09796183556318283 2023-01-23 11:39:10.697889: step: 420/1545, loss: 0.015117190778255463 2023-01-23 11:39:11.561637: step: 422/1545, loss: 0.26663318276405334 2023-01-23 11:39:12.443904: step: 424/1545, loss: 0.10302358865737915 2023-01-23 11:39:13.348773: step: 426/1545, loss: 0.07548078894615173 2023-01-23 11:39:14.214750: step: 428/1545, loss: 0.1255113184452057 2023-01-23 11:39:15.107979: step: 430/1545, loss: 0.021636171266436577 2023-01-23 11:39:15.988857: step: 432/1545, loss: 0.003530431305989623 2023-01-23 11:39:16.895575: step: 434/1545, loss: 0.1741829514503479 2023-01-23 11:39:17.750699: step: 436/1545, loss: 0.008884062059223652 2023-01-23 11:39:18.625890: step: 438/1545, loss: 0.07273736596107483 2023-01-23 11:39:19.474269: step: 440/1545, loss: 0.00999489240348339 2023-01-23 11:39:20.340153: step: 442/1545, loss: 1.1924934387207031 2023-01-23 11:39:21.245696: step: 444/1545, loss: 0.21899424493312836 2023-01-23 11:39:22.107821: step: 446/1545, loss: 0.053519777953624725 2023-01-23 11:39:23.000909: step: 448/1545, loss: 0.16060508787631989 2023-01-23 11:39:23.914825: step: 450/1545, loss: 0.021525077521800995 2023-01-23 11:39:24.814888: step: 452/1545, loss: 0.02014918066561222 2023-01-23 11:39:25.842585: step: 454/1545, loss: 0.08836115896701813 2023-01-23 11:39:26.719055: step: 456/1545, loss: 0.035027261823415756 2023-01-23 11:39:27.614282: step: 458/1545, loss: 0.2610650658607483 2023-01-23 11:39:28.504924: step: 460/1545, loss: 0.05500461906194687 2023-01-23 11:39:29.350934: step: 462/1545, loss: 0.12631286680698395 2023-01-23 11:39:30.267146: step: 464/1545, loss: 0.1113598421216011 2023-01-23 11:39:31.151909: step: 466/1545, loss: 0.06522683799266815 2023-01-23 11:39:32.038740: step: 468/1545, loss: 0.047571126371622086 2023-01-23 11:39:32.959712: step: 470/1545, loss: 0.020629072561860085 2023-01-23 11:39:33.873362: step: 472/1545, loss: 0.23369057476520538 2023-01-23 11:39:34.760367: step: 474/1545, loss: 0.12293398380279541 2023-01-23 11:39:35.633839: step: 476/1545, loss: 0.07176116853952408 2023-01-23 11:39:36.548091: step: 478/1545, loss: 0.17750969529151917 2023-01-23 11:39:37.397213: step: 480/1545, loss: 0.038678769022226334 2023-01-23 11:39:38.250760: step: 482/1545, loss: 0.09668350219726562 2023-01-23 11:39:39.148584: step: 484/1545, loss: 0.023567425087094307 2023-01-23 11:39:40.026917: step: 486/1545, loss: 0.15173877775669098 2023-01-23 11:39:40.948346: step: 488/1545, loss: 0.045280955731868744 2023-01-23 11:39:41.874946: step: 490/1545, loss: 0.010479239746928215 2023-01-23 11:39:42.712728: step: 492/1545, loss: 0.0456882081925869 2023-01-23 11:39:43.611524: step: 494/1545, loss: 0.5788729190826416 2023-01-23 11:39:44.450993: step: 496/1545, loss: 0.12318767607212067 2023-01-23 11:39:45.298992: step: 498/1545, loss: 0.22076036036014557 2023-01-23 11:39:46.153058: step: 500/1545, loss: 0.1632501482963562 2023-01-23 11:39:47.061296: step: 502/1545, loss: 0.013270133174955845 2023-01-23 11:39:47.929474: step: 504/1545, loss: 0.10986588895320892 2023-01-23 11:39:48.846665: step: 506/1545, loss: 0.019450556486845016 2023-01-23 11:39:49.750726: step: 508/1545, loss: 0.16516919434070587 2023-01-23 11:39:50.613488: step: 510/1545, loss: 0.09579393267631531 2023-01-23 11:39:51.458129: step: 512/1545, loss: 0.03782643750309944 2023-01-23 11:39:52.324864: step: 514/1545, loss: 0.08609794825315475 2023-01-23 11:39:53.185201: step: 516/1545, loss: 0.0008705080836080015 2023-01-23 11:39:54.032889: step: 518/1545, loss: 0.052539218217134476 2023-01-23 11:39:54.885265: step: 520/1545, loss: 0.03147021308541298 2023-01-23 11:39:55.791815: step: 522/1545, loss: 0.07749134302139282 2023-01-23 11:39:56.670332: step: 524/1545, loss: 0.07828196883201599 2023-01-23 11:39:57.557419: step: 526/1545, loss: 0.04152714088559151 2023-01-23 11:39:58.421378: step: 528/1545, loss: 0.16964004933834076 2023-01-23 11:39:59.361623: step: 530/1545, loss: 0.12343478202819824 2023-01-23 11:40:00.231056: step: 532/1545, loss: 0.0025903431233018637 2023-01-23 11:40:01.126665: step: 534/1545, loss: 0.020132016390562057 2023-01-23 11:40:02.030541: step: 536/1545, loss: 0.11258068680763245 2023-01-23 11:40:02.999864: step: 538/1545, loss: 0.0034998597111552954 2023-01-23 11:40:03.970988: step: 540/1545, loss: 0.15131695568561554 2023-01-23 11:40:04.838184: step: 542/1545, loss: 0.08684311807155609 2023-01-23 11:40:05.736229: step: 544/1545, loss: 0.012559459544718266 2023-01-23 11:40:06.579824: step: 546/1545, loss: 0.03376865014433861 2023-01-23 11:40:07.449554: step: 548/1545, loss: 0.1375025510787964 2023-01-23 11:40:08.314199: step: 550/1545, loss: 0.18348738551139832 2023-01-23 11:40:09.192039: step: 552/1545, loss: 0.2372051328420639 2023-01-23 11:40:10.114070: step: 554/1545, loss: 0.008099488914012909 2023-01-23 11:40:11.022089: step: 556/1545, loss: 0.0030260623898357153 2023-01-23 11:40:11.915617: step: 558/1545, loss: 0.017051560804247856 2023-01-23 11:40:12.820112: step: 560/1545, loss: 0.22738957405090332 2023-01-23 11:40:13.704310: step: 562/1545, loss: 0.0037624542601406574 2023-01-23 11:40:14.607089: step: 564/1545, loss: 0.09098148345947266 2023-01-23 11:40:15.473408: step: 566/1545, loss: 0.025563985109329224 2023-01-23 11:40:16.346863: step: 568/1545, loss: 0.13230518996715546 2023-01-23 11:40:17.215392: step: 570/1545, loss: 0.016047412529587746 2023-01-23 11:40:18.091642: step: 572/1545, loss: 0.13326993584632874 2023-01-23 11:40:18.952516: step: 574/1545, loss: 0.016157634556293488 2023-01-23 11:40:19.858585: step: 576/1545, loss: 0.3477570116519928 2023-01-23 11:40:20.724643: step: 578/1545, loss: 0.0022143658716231585 2023-01-23 11:40:21.582190: step: 580/1545, loss: 0.010084748268127441 2023-01-23 11:40:22.465773: step: 582/1545, loss: 0.11307692527770996 2023-01-23 11:40:23.334322: step: 584/1545, loss: 0.14102338254451752 2023-01-23 11:40:24.300280: step: 586/1545, loss: 0.14403901994228363 2023-01-23 11:40:25.165291: step: 588/1545, loss: 0.005325914826244116 2023-01-23 11:40:26.050436: step: 590/1545, loss: 0.2821836769580841 2023-01-23 11:40:26.918410: step: 592/1545, loss: 0.08806350082159042 2023-01-23 11:40:27.766896: step: 594/1545, loss: 0.061019740998744965 2023-01-23 11:40:28.644036: step: 596/1545, loss: 0.343747079372406 2023-01-23 11:40:29.537342: step: 598/1545, loss: 0.12570279836654663 2023-01-23 11:40:30.418362: step: 600/1545, loss: 0.007540874648839235 2023-01-23 11:40:31.343984: step: 602/1545, loss: 0.019228091463446617 2023-01-23 11:40:32.210136: step: 604/1545, loss: 0.05567120015621185 2023-01-23 11:40:33.131521: step: 606/1545, loss: 0.09606596827507019 2023-01-23 11:40:34.056367: step: 608/1545, loss: 0.18615774810314178 2023-01-23 11:40:35.040720: step: 610/1545, loss: 0.42156854271888733 2023-01-23 11:40:35.874139: step: 612/1545, loss: 0.18567505478858948 2023-01-23 11:40:36.727353: step: 614/1545, loss: 0.04115995392203331 2023-01-23 11:40:37.605709: step: 616/1545, loss: 0.1584262102842331 2023-01-23 11:40:38.476452: step: 618/1545, loss: 0.06596477329730988 2023-01-23 11:40:39.353493: step: 620/1545, loss: 0.05315161868929863 2023-01-23 11:40:40.182751: step: 622/1545, loss: 0.272551029920578 2023-01-23 11:40:41.080489: step: 624/1545, loss: 0.0812923014163971 2023-01-23 11:40:41.968622: step: 626/1545, loss: 0.05090684816241264 2023-01-23 11:40:42.819623: step: 628/1545, loss: 0.006897393148392439 2023-01-23 11:40:43.735165: step: 630/1545, loss: 0.01541812252253294 2023-01-23 11:40:44.584242: step: 632/1545, loss: 0.6146430969238281 2023-01-23 11:40:45.479833: step: 634/1545, loss: 0.5123615860939026 2023-01-23 11:40:46.387857: step: 636/1545, loss: 0.04712062329053879 2023-01-23 11:40:47.233736: step: 638/1545, loss: 0.40115952491760254 2023-01-23 11:40:48.078744: step: 640/1545, loss: 0.14387452602386475 2023-01-23 11:40:48.969304: step: 642/1545, loss: 0.09419039636850357 2023-01-23 11:40:49.859781: step: 644/1545, loss: 0.010648672468960285 2023-01-23 11:40:50.775376: step: 646/1545, loss: 0.4425545036792755 2023-01-23 11:40:51.656150: step: 648/1545, loss: 0.039979808032512665 2023-01-23 11:40:52.553199: step: 650/1545, loss: 0.5784032940864563 2023-01-23 11:40:53.398009: step: 652/1545, loss: 0.01955193281173706 2023-01-23 11:40:54.266708: step: 654/1545, loss: 0.016317348927259445 2023-01-23 11:40:55.107209: step: 656/1545, loss: 0.010516982525587082 2023-01-23 11:40:56.021665: step: 658/1545, loss: 0.09510944783687592 2023-01-23 11:40:56.933662: step: 660/1545, loss: 0.3637007772922516 2023-01-23 11:40:57.887531: step: 662/1545, loss: 0.02586318738758564 2023-01-23 11:40:58.772871: step: 664/1545, loss: 0.5451586246490479 2023-01-23 11:40:59.646733: step: 666/1545, loss: 0.15776997804641724 2023-01-23 11:41:00.487068: step: 668/1545, loss: 0.17964918911457062 2023-01-23 11:41:01.364670: step: 670/1545, loss: 0.10879777371883392 2023-01-23 11:41:02.217643: step: 672/1545, loss: 0.08235792815685272 2023-01-23 11:41:03.137755: step: 674/1545, loss: 0.4110102653503418 2023-01-23 11:41:03.998544: step: 676/1545, loss: 0.2130197137594223 2023-01-23 11:41:04.874333: step: 678/1545, loss: 0.04000922292470932 2023-01-23 11:41:05.799865: step: 680/1545, loss: 0.13170914351940155 2023-01-23 11:41:06.634494: step: 682/1545, loss: 0.003692259779199958 2023-01-23 11:41:07.557165: step: 684/1545, loss: 0.1857830435037613 2023-01-23 11:41:08.413011: step: 686/1545, loss: 0.2014140635728836 2023-01-23 11:41:09.292132: step: 688/1545, loss: 0.35164952278137207 2023-01-23 11:41:10.188858: step: 690/1545, loss: 0.013281423598527908 2023-01-23 11:41:11.057497: step: 692/1545, loss: 0.061923395842313766 2023-01-23 11:41:11.889582: step: 694/1545, loss: 0.1524088829755783 2023-01-23 11:41:12.749295: step: 696/1545, loss: 0.2364778369665146 2023-01-23 11:41:13.580885: step: 698/1545, loss: 0.021423224359750748 2023-01-23 11:41:14.469812: step: 700/1545, loss: 0.2284613400697708 2023-01-23 11:41:15.370275: step: 702/1545, loss: 0.03973148390650749 2023-01-23 11:41:16.220326: step: 704/1545, loss: 0.028458986431360245 2023-01-23 11:41:17.080636: step: 706/1545, loss: 0.10055427998304367 2023-01-23 11:41:17.946501: step: 708/1545, loss: 0.2578425705432892 2023-01-23 11:41:18.829698: step: 710/1545, loss: 2.529008388519287 2023-01-23 11:41:19.707748: step: 712/1545, loss: 0.292753666639328 2023-01-23 11:41:20.640256: step: 714/1545, loss: 0.03610288351774216 2023-01-23 11:41:21.502056: step: 716/1545, loss: 0.1525265872478485 2023-01-23 11:41:22.356637: step: 718/1545, loss: 1.1261630058288574 2023-01-23 11:41:23.280006: step: 720/1545, loss: 0.33219799399375916 2023-01-23 11:41:24.165444: step: 722/1545, loss: 0.03120272234082222 2023-01-23 11:41:25.110758: step: 724/1545, loss: 0.10423988103866577 2023-01-23 11:41:25.990219: step: 726/1545, loss: 0.1264990121126175 2023-01-23 11:41:26.840829: step: 728/1545, loss: 0.09169457852840424 2023-01-23 11:41:27.723241: step: 730/1545, loss: 0.042682185769081116 2023-01-23 11:41:28.582992: step: 732/1545, loss: 0.08345647156238556 2023-01-23 11:41:29.439965: step: 734/1545, loss: 0.1666518598794937 2023-01-23 11:41:30.302322: step: 736/1545, loss: 0.20238250494003296 2023-01-23 11:41:31.178753: step: 738/1545, loss: 0.03799188882112503 2023-01-23 11:41:32.043074: step: 740/1545, loss: 0.0905580073595047 2023-01-23 11:41:32.890162: step: 742/1545, loss: 0.1820918172597885 2023-01-23 11:41:33.820006: step: 744/1545, loss: 0.3206615746021271 2023-01-23 11:41:34.716598: step: 746/1545, loss: 0.021722353994846344 2023-01-23 11:41:35.572362: step: 748/1545, loss: 0.05705463886260986 2023-01-23 11:41:36.458585: step: 750/1545, loss: 0.155982106924057 2023-01-23 11:41:37.309723: step: 752/1545, loss: 0.1312805414199829 2023-01-23 11:41:38.171471: step: 754/1545, loss: 0.009939491748809814 2023-01-23 11:41:39.106884: step: 756/1545, loss: 0.04067915678024292 2023-01-23 11:41:40.006571: step: 758/1545, loss: 0.5172926187515259 2023-01-23 11:41:40.893537: step: 760/1545, loss: 0.2530652582645416 2023-01-23 11:41:41.766814: step: 762/1545, loss: 0.43924233317375183 2023-01-23 11:41:42.645960: step: 764/1545, loss: 0.14321018755435944 2023-01-23 11:41:43.500745: step: 766/1545, loss: 0.061088450253009796 2023-01-23 11:41:44.412064: step: 768/1545, loss: 0.002584001049399376 2023-01-23 11:41:45.269452: step: 770/1545, loss: 0.14025713503360748 2023-01-23 11:41:46.160228: step: 772/1545, loss: 0.14722940325737 2023-01-23 11:41:47.017872: step: 774/1545, loss: 0.17522121965885162 2023-01-23 11:41:47.905261: step: 776/1545, loss: 0.017322301864624023 2023-01-23 11:41:48.768482: step: 778/1545, loss: 0.41625550389289856 2023-01-23 11:41:49.648461: step: 780/1545, loss: 0.03532171621918678 2023-01-23 11:41:50.493418: step: 782/1545, loss: 0.28287598490715027 2023-01-23 11:41:51.376678: step: 784/1545, loss: 0.3282768428325653 2023-01-23 11:41:52.246253: step: 786/1545, loss: 0.12164561450481415 2023-01-23 11:41:53.103188: step: 788/1545, loss: 0.836478590965271 2023-01-23 11:41:53.998014: step: 790/1545, loss: 0.014651551842689514 2023-01-23 11:41:54.836696: step: 792/1545, loss: 0.12925899028778076 2023-01-23 11:41:55.713200: step: 794/1545, loss: 0.24189332127571106 2023-01-23 11:41:56.584273: step: 796/1545, loss: 0.07075168937444687 2023-01-23 11:41:57.416034: step: 798/1545, loss: 0.051845282316207886 2023-01-23 11:41:58.339503: step: 800/1545, loss: 0.033150654286146164 2023-01-23 11:41:59.209740: step: 802/1545, loss: 0.13828125596046448 2023-01-23 11:42:00.091746: step: 804/1545, loss: 0.0415467694401741 2023-01-23 11:42:01.110519: step: 806/1545, loss: 0.0018980293534696102 2023-01-23 11:42:01.993347: step: 808/1545, loss: 0.062181733548641205 2023-01-23 11:42:02.871432: step: 810/1545, loss: 0.7462218403816223 2023-01-23 11:42:03.791470: step: 812/1545, loss: 0.048818886280059814 2023-01-23 11:42:04.682497: step: 814/1545, loss: 0.2758501470088959 2023-01-23 11:42:05.565347: step: 816/1545, loss: 0.33361002802848816 2023-01-23 11:42:06.491155: step: 818/1545, loss: 0.27173617482185364 2023-01-23 11:42:07.331794: step: 820/1545, loss: 0.27739307284355164 2023-01-23 11:42:08.210142: step: 822/1545, loss: 0.044894762337207794 2023-01-23 11:42:09.135464: step: 824/1545, loss: 0.21813364326953888 2023-01-23 11:42:10.061358: step: 826/1545, loss: 0.04847170040011406 2023-01-23 11:42:10.974248: step: 828/1545, loss: 0.1375865638256073 2023-01-23 11:42:11.831264: step: 830/1545, loss: 0.10910674184560776 2023-01-23 11:42:12.724078: step: 832/1545, loss: 0.14156821370124817 2023-01-23 11:42:13.589270: step: 834/1545, loss: 0.06736429035663605 2023-01-23 11:42:14.452929: step: 836/1545, loss: 0.03616301342844963 2023-01-23 11:42:15.343751: step: 838/1545, loss: 0.14737875759601593 2023-01-23 11:42:16.190509: step: 840/1545, loss: 0.034708622843027115 2023-01-23 11:42:17.043952: step: 842/1545, loss: 0.24231651425361633 2023-01-23 11:42:17.998021: step: 844/1545, loss: 0.326324462890625 2023-01-23 11:42:18.853240: step: 846/1545, loss: 0.32346436381340027 2023-01-23 11:42:19.781225: step: 848/1545, loss: 1.020760416984558 2023-01-23 11:42:20.638431: step: 850/1545, loss: 0.20659399032592773 2023-01-23 11:42:21.538891: step: 852/1545, loss: 0.029214730486273766 2023-01-23 11:42:22.409244: step: 854/1545, loss: 0.041646938771009445 2023-01-23 11:42:23.277977: step: 856/1545, loss: 0.28803756833076477 2023-01-23 11:42:24.179624: step: 858/1545, loss: 0.14115498960018158 2023-01-23 11:42:25.101097: step: 860/1545, loss: 0.06430037319660187 2023-01-23 11:42:26.093733: step: 862/1545, loss: 0.005419222172349691 2023-01-23 11:42:26.961698: step: 864/1545, loss: 0.15813447535037994 2023-01-23 11:42:27.849619: step: 866/1545, loss: 0.33060675859451294 2023-01-23 11:42:28.774299: step: 868/1545, loss: 0.16204923391342163 2023-01-23 11:42:29.662863: step: 870/1545, loss: 0.07200753688812256 2023-01-23 11:42:30.513691: step: 872/1545, loss: 0.04747208580374718 2023-01-23 11:42:31.373250: step: 874/1545, loss: 0.03801136091351509 2023-01-23 11:42:32.262415: step: 876/1545, loss: 0.06924354285001755 2023-01-23 11:42:33.140478: step: 878/1545, loss: 0.02498973347246647 2023-01-23 11:42:34.021029: step: 880/1545, loss: 0.2410212755203247 2023-01-23 11:42:34.955393: step: 882/1545, loss: 0.20410294830799103 2023-01-23 11:42:35.863593: step: 884/1545, loss: 0.17355035245418549 2023-01-23 11:42:36.794316: step: 886/1545, loss: 0.06367688626050949 2023-01-23 11:42:37.707461: step: 888/1545, loss: 0.034052103757858276 2023-01-23 11:42:38.617332: step: 890/1545, loss: 0.00402365205809474 2023-01-23 11:42:39.497109: step: 892/1545, loss: 0.07030560821294785 2023-01-23 11:42:40.374362: step: 894/1545, loss: 0.001112689613364637 2023-01-23 11:42:41.236105: step: 896/1545, loss: 0.6177750825881958 2023-01-23 11:42:42.140875: step: 898/1545, loss: 0.04445751756429672 2023-01-23 11:42:43.028654: step: 900/1545, loss: 0.1735098958015442 2023-01-23 11:42:43.940572: step: 902/1545, loss: 0.05977710708975792 2023-01-23 11:42:44.806804: step: 904/1545, loss: 0.3846838176250458 2023-01-23 11:42:45.688842: step: 906/1545, loss: 0.1033397912979126 2023-01-23 11:42:46.551748: step: 908/1545, loss: 0.04153677076101303 2023-01-23 11:42:47.479046: step: 910/1545, loss: 0.02035677805542946 2023-01-23 11:42:48.371230: step: 912/1545, loss: 0.003174571553245187 2023-01-23 11:42:49.244732: step: 914/1545, loss: 0.20125505328178406 2023-01-23 11:42:50.161212: step: 916/1545, loss: 0.04440450668334961 2023-01-23 11:42:51.100123: step: 918/1545, loss: 0.14589248597621918 2023-01-23 11:42:51.984810: step: 920/1545, loss: 0.034753601998090744 2023-01-23 11:42:52.839508: step: 922/1545, loss: 0.03509156033396721 2023-01-23 11:42:53.712727: step: 924/1545, loss: 0.9689508080482483 2023-01-23 11:42:54.642097: step: 926/1545, loss: 0.025724226608872414 2023-01-23 11:42:55.523567: step: 928/1545, loss: 0.06949104368686676 2023-01-23 11:42:56.466556: step: 930/1545, loss: 0.01647411286830902 2023-01-23 11:42:57.402961: step: 932/1545, loss: 0.40564829111099243 2023-01-23 11:42:58.330921: step: 934/1545, loss: 0.08171495795249939 2023-01-23 11:42:59.209748: step: 936/1545, loss: 0.19453346729278564 2023-01-23 11:43:00.144972: step: 938/1545, loss: 2.0384628772735596 2023-01-23 11:43:00.999902: step: 940/1545, loss: 0.06359417736530304 2023-01-23 11:43:01.897262: step: 942/1545, loss: 0.06240306794643402 2023-01-23 11:43:02.764299: step: 944/1545, loss: 0.25485891103744507 2023-01-23 11:43:03.622852: step: 946/1545, loss: 0.06311722844839096 2023-01-23 11:43:04.479050: step: 948/1545, loss: 1.7973791360855103 2023-01-23 11:43:05.328024: step: 950/1545, loss: 0.02193007618188858 2023-01-23 11:43:06.283627: step: 952/1545, loss: 1.8723400831222534 2023-01-23 11:43:07.226371: step: 954/1545, loss: 0.20408344268798828 2023-01-23 11:43:08.146616: step: 956/1545, loss: 0.07331980764865875 2023-01-23 11:43:09.052410: step: 958/1545, loss: 0.04212402179837227 2023-01-23 11:43:09.963631: step: 960/1545, loss: 0.06135086342692375 2023-01-23 11:43:10.831895: step: 962/1545, loss: 0.2942703366279602 2023-01-23 11:43:11.723804: step: 964/1545, loss: 0.2411705106496811 2023-01-23 11:43:12.580125: step: 966/1545, loss: 0.1320338100194931 2023-01-23 11:43:13.455413: step: 968/1545, loss: 0.007850037887692451 2023-01-23 11:43:14.339744: step: 970/1545, loss: 0.09585995972156525 2023-01-23 11:43:15.198449: step: 972/1545, loss: 0.1473761796951294 2023-01-23 11:43:16.064541: step: 974/1545, loss: 0.2030617892742157 2023-01-23 11:43:16.996473: step: 976/1545, loss: 0.06252621114253998 2023-01-23 11:43:17.904617: step: 978/1545, loss: 0.23839959502220154 2023-01-23 11:43:18.792074: step: 980/1545, loss: 1.292514681816101 2023-01-23 11:43:19.683879: step: 982/1545, loss: 0.046758875250816345 2023-01-23 11:43:20.570993: step: 984/1545, loss: 0.027274446561932564 2023-01-23 11:43:21.484621: step: 986/1545, loss: 0.02875787392258644 2023-01-23 11:43:22.347166: step: 988/1545, loss: 1.2082310914993286 2023-01-23 11:43:23.251123: step: 990/1545, loss: 0.07198583334684372 2023-01-23 11:43:24.165279: step: 992/1545, loss: 0.09400470554828644 2023-01-23 11:43:25.023674: step: 994/1545, loss: 0.008582388050854206 2023-01-23 11:43:25.941066: step: 996/1545, loss: 0.09345106035470963 2023-01-23 11:43:26.811835: step: 998/1545, loss: 0.08555662631988525 2023-01-23 11:43:27.697908: step: 1000/1545, loss: 0.029148826375603676 2023-01-23 11:43:28.530172: step: 1002/1545, loss: 0.016259467229247093 2023-01-23 11:43:29.456499: step: 1004/1545, loss: 0.12546104192733765 2023-01-23 11:43:30.316789: step: 1006/1545, loss: 0.03270981088280678 2023-01-23 11:43:31.240894: step: 1008/1545, loss: 0.43758854269981384 2023-01-23 11:43:32.104556: step: 1010/1545, loss: 0.290366530418396 2023-01-23 11:43:33.000355: step: 1012/1545, loss: 0.0756334438920021 2023-01-23 11:43:33.847047: step: 1014/1545, loss: 0.5762349367141724 2023-01-23 11:43:34.716762: step: 1016/1545, loss: 0.08191195875406265 2023-01-23 11:43:35.590470: step: 1018/1545, loss: 0.5704522132873535 2023-01-23 11:43:36.468824: step: 1020/1545, loss: 0.12956494092941284 2023-01-23 11:43:37.341141: step: 1022/1545, loss: 0.14050820469856262 2023-01-23 11:43:38.241187: step: 1024/1545, loss: 0.5927176475524902 2023-01-23 11:43:39.104974: step: 1026/1545, loss: 0.07803908735513687 2023-01-23 11:43:39.971887: step: 1028/1545, loss: 0.20598363876342773 2023-01-23 11:43:40.807211: step: 1030/1545, loss: 0.07223193347454071 2023-01-23 11:43:41.685833: step: 1032/1545, loss: 0.16261416673660278 2023-01-23 11:43:42.554882: step: 1034/1545, loss: 0.05071386322379112 2023-01-23 11:43:43.449041: step: 1036/1545, loss: 0.02711545303463936 2023-01-23 11:43:44.343510: step: 1038/1545, loss: 0.07031847536563873 2023-01-23 11:43:45.224158: step: 1040/1545, loss: 0.04280237853527069 2023-01-23 11:43:46.080127: step: 1042/1545, loss: 0.03740398585796356 2023-01-23 11:43:47.015566: step: 1044/1545, loss: 0.03791961446404457 2023-01-23 11:43:47.902367: step: 1046/1545, loss: 0.3479978144168854 2023-01-23 11:43:48.781672: step: 1048/1545, loss: 0.05605677515268326 2023-01-23 11:43:49.710910: step: 1050/1545, loss: 0.009523900225758553 2023-01-23 11:43:50.631335: step: 1052/1545, loss: 0.02892315573990345 2023-01-23 11:43:51.508659: step: 1054/1545, loss: 0.059923045337200165 2023-01-23 11:43:52.388630: step: 1056/1545, loss: 0.20455314218997955 2023-01-23 11:43:53.334356: step: 1058/1545, loss: 0.028133641928434372 2023-01-23 11:43:54.217099: step: 1060/1545, loss: 0.09134788811206818 2023-01-23 11:43:55.102810: step: 1062/1545, loss: 0.4433060586452484 2023-01-23 11:43:55.984280: step: 1064/1545, loss: 0.05472775548696518 2023-01-23 11:43:56.914207: step: 1066/1545, loss: 0.22125297784805298 2023-01-23 11:43:57.792453: step: 1068/1545, loss: 0.2120422124862671 2023-01-23 11:43:58.697290: step: 1070/1545, loss: 0.303297758102417 2023-01-23 11:43:59.544100: step: 1072/1545, loss: 0.013721683993935585 2023-01-23 11:44:00.457897: step: 1074/1545, loss: 0.11163118481636047 2023-01-23 11:44:01.399035: step: 1076/1545, loss: 0.09505406767129898 2023-01-23 11:44:02.260102: step: 1078/1545, loss: 0.1220763549208641 2023-01-23 11:44:03.167020: step: 1080/1545, loss: 0.09009771794080734 2023-01-23 11:44:04.036997: step: 1082/1545, loss: 0.05818995088338852 2023-01-23 11:44:04.893374: step: 1084/1545, loss: 0.02632896788418293 2023-01-23 11:44:05.795365: step: 1086/1545, loss: 0.025075621902942657 2023-01-23 11:44:06.711501: step: 1088/1545, loss: 0.2624628245830536 2023-01-23 11:44:07.634306: step: 1090/1545, loss: 0.17474493384361267 2023-01-23 11:44:08.478201: step: 1092/1545, loss: 0.05122911185026169 2023-01-23 11:44:09.430355: step: 1094/1545, loss: 0.1285880208015442 2023-01-23 11:44:10.287065: step: 1096/1545, loss: 0.1793408840894699 2023-01-23 11:44:11.242313: step: 1098/1545, loss: 0.0807972177863121 2023-01-23 11:44:12.153425: step: 1100/1545, loss: 0.14231213927268982 2023-01-23 11:44:13.011467: step: 1102/1545, loss: 0.1263533979654312 2023-01-23 11:44:13.920493: step: 1104/1545, loss: 0.019856618717312813 2023-01-23 11:44:14.793778: step: 1106/1545, loss: 0.02009287290275097 2023-01-23 11:44:15.656541: step: 1108/1545, loss: 0.06835600733757019 2023-01-23 11:44:16.541718: step: 1110/1545, loss: 0.4596266746520996 2023-01-23 11:44:17.480953: step: 1112/1545, loss: 0.3104422986507416 2023-01-23 11:44:18.356132: step: 1114/1545, loss: 0.02871105819940567 2023-01-23 11:44:19.309058: step: 1116/1545, loss: 0.09251769632101059 2023-01-23 11:44:20.169918: step: 1118/1545, loss: 0.0915183573961258 2023-01-23 11:44:20.990220: step: 1120/1545, loss: 0.09454239159822464 2023-01-23 11:44:21.883314: step: 1122/1545, loss: 0.14316967129707336 2023-01-23 11:44:22.759078: step: 1124/1545, loss: 0.26482024788856506 2023-01-23 11:44:23.674625: step: 1126/1545, loss: 0.12006357312202454 2023-01-23 11:44:24.598303: step: 1128/1545, loss: 0.039158374071121216 2023-01-23 11:44:25.490171: step: 1130/1545, loss: 0.15032793581485748 2023-01-23 11:44:26.380454: step: 1132/1545, loss: 0.11477896571159363 2023-01-23 11:44:27.286942: step: 1134/1545, loss: 0.21479715406894684 2023-01-23 11:44:28.150316: step: 1136/1545, loss: 0.1943606436252594 2023-01-23 11:44:29.076599: step: 1138/1545, loss: 0.06985866278409958 2023-01-23 11:44:29.943450: step: 1140/1545, loss: 0.10422254353761673 2023-01-23 11:44:30.797040: step: 1142/1545, loss: 0.0690564438700676 2023-01-23 11:44:31.701711: step: 1144/1545, loss: 0.061070095747709274 2023-01-23 11:44:32.581451: step: 1146/1545, loss: 0.07975007593631744 2023-01-23 11:44:33.444897: step: 1148/1545, loss: 0.02055283635854721 2023-01-23 11:44:34.379998: step: 1150/1545, loss: 0.18832817673683167 2023-01-23 11:44:35.230649: step: 1152/1545, loss: 0.08828914165496826 2023-01-23 11:44:36.128483: step: 1154/1545, loss: 0.08045478910207748 2023-01-23 11:44:37.042941: step: 1156/1545, loss: 0.0652739480137825 2023-01-23 11:44:37.886549: step: 1158/1545, loss: 0.060362134128808975 2023-01-23 11:44:38.757331: step: 1160/1545, loss: 0.09952295571565628 2023-01-23 11:44:39.695889: step: 1162/1545, loss: 0.22265830636024475 2023-01-23 11:44:40.577818: step: 1164/1545, loss: 0.21287207305431366 2023-01-23 11:44:41.458166: step: 1166/1545, loss: 0.4022146761417389 2023-01-23 11:44:42.341007: step: 1168/1545, loss: 0.18100018799304962 2023-01-23 11:44:43.194044: step: 1170/1545, loss: 0.011758345179259777 2023-01-23 11:44:44.110639: step: 1172/1545, loss: 0.15511691570281982 2023-01-23 11:44:45.039565: step: 1174/1545, loss: 0.20652879774570465 2023-01-23 11:44:45.937966: step: 1176/1545, loss: 0.29802894592285156 2023-01-23 11:44:46.822839: step: 1178/1545, loss: 0.21592526137828827 2023-01-23 11:44:47.752072: step: 1180/1545, loss: 0.01822143793106079 2023-01-23 11:44:48.642298: step: 1182/1545, loss: 0.17444783449172974 2023-01-23 11:44:49.485040: step: 1184/1545, loss: 0.032574597746133804 2023-01-23 11:44:50.380772: step: 1186/1545, loss: 0.025846518576145172 2023-01-23 11:44:51.265788: step: 1188/1545, loss: 0.3152395486831665 2023-01-23 11:44:52.149756: step: 1190/1545, loss: 0.027408618479967117 2023-01-23 11:44:53.025942: step: 1192/1545, loss: 0.011259762570261955 2023-01-23 11:44:53.909260: step: 1194/1545, loss: 0.40314188599586487 2023-01-23 11:44:54.806110: step: 1196/1545, loss: 0.5169201493263245 2023-01-23 11:44:55.683299: step: 1198/1545, loss: 0.07776713371276855 2023-01-23 11:44:56.549775: step: 1200/1545, loss: 0.06531316787004471 2023-01-23 11:44:57.454913: step: 1202/1545, loss: 0.11700902134180069 2023-01-23 11:44:58.363375: step: 1204/1545, loss: 0.021247699856758118 2023-01-23 11:44:59.302791: step: 1206/1545, loss: 0.12851549685001373 2023-01-23 11:45:00.158178: step: 1208/1545, loss: 0.13848094642162323 2023-01-23 11:45:01.053507: step: 1210/1545, loss: 0.006773453205823898 2023-01-23 11:45:01.988087: step: 1212/1545, loss: 0.01987508498132229 2023-01-23 11:45:02.920473: step: 1214/1545, loss: 0.03966393694281578 2023-01-23 11:45:03.818265: step: 1216/1545, loss: 0.22273829579353333 2023-01-23 11:45:04.710895: step: 1218/1545, loss: 0.23464246094226837 2023-01-23 11:45:05.695392: step: 1220/1545, loss: 0.7439002990722656 2023-01-23 11:45:06.592228: step: 1222/1545, loss: 0.1296771615743637 2023-01-23 11:45:07.460591: step: 1224/1545, loss: 0.10946096479892731 2023-01-23 11:45:08.324649: step: 1226/1545, loss: 0.11368586868047714 2023-01-23 11:45:09.189232: step: 1228/1545, loss: 0.5000763535499573 2023-01-23 11:45:10.072711: step: 1230/1545, loss: 0.12785442173480988 2023-01-23 11:45:10.921613: step: 1232/1545, loss: 0.028649287298321724 2023-01-23 11:45:11.808206: step: 1234/1545, loss: 0.09706389158964157 2023-01-23 11:45:12.690302: step: 1236/1545, loss: 0.2906825840473175 2023-01-23 11:45:13.579229: step: 1238/1545, loss: 0.13235853612422943 2023-01-23 11:45:14.442875: step: 1240/1545, loss: 0.0459018312394619 2023-01-23 11:45:15.317854: step: 1242/1545, loss: 0.17735454440116882 2023-01-23 11:45:16.261724: step: 1244/1545, loss: 0.7609478235244751 2023-01-23 11:45:17.177930: step: 1246/1545, loss: 0.2622400224208832 2023-01-23 11:45:18.030740: step: 1248/1545, loss: 0.05505068600177765 2023-01-23 11:45:18.887941: step: 1250/1545, loss: 0.09322401881217957 2023-01-23 11:45:19.831694: step: 1252/1545, loss: 0.17097821831703186 2023-01-23 11:45:20.738760: step: 1254/1545, loss: 0.0009564640931785107 2023-01-23 11:45:21.667066: step: 1256/1545, loss: 0.10221439599990845 2023-01-23 11:45:22.604839: step: 1258/1545, loss: 0.0663127601146698 2023-01-23 11:45:23.475296: step: 1260/1545, loss: 0.02333252876996994 2023-01-23 11:45:24.398316: step: 1262/1545, loss: 0.02839113213121891 2023-01-23 11:45:25.268111: step: 1264/1545, loss: 0.017292333766818047 2023-01-23 11:45:26.199794: step: 1266/1545, loss: 0.04587513208389282 2023-01-23 11:45:27.111071: step: 1268/1545, loss: 0.16089847683906555 2023-01-23 11:45:28.020106: step: 1270/1545, loss: 0.500154435634613 2023-01-23 11:45:28.925561: step: 1272/1545, loss: 0.26717907190322876 2023-01-23 11:45:29.792477: step: 1274/1545, loss: 0.052288271486759186 2023-01-23 11:45:30.697430: step: 1276/1545, loss: 0.32814115285873413 2023-01-23 11:45:31.586164: step: 1278/1545, loss: 0.03622037544846535 2023-01-23 11:45:32.438975: step: 1280/1545, loss: 0.06100651994347572 2023-01-23 11:45:33.383573: step: 1282/1545, loss: 0.10319267958402634 2023-01-23 11:45:34.262572: step: 1284/1545, loss: 0.05026305466890335 2023-01-23 11:45:35.120259: step: 1286/1545, loss: 0.13787716627120972 2023-01-23 11:45:36.042979: step: 1288/1545, loss: 0.07151483744382858 2023-01-23 11:45:36.888593: step: 1290/1545, loss: 0.024651112034916878 2023-01-23 11:45:37.729567: step: 1292/1545, loss: 0.302789568901062 2023-01-23 11:45:38.621879: step: 1294/1545, loss: 0.2622428238391876 2023-01-23 11:45:39.477826: step: 1296/1545, loss: 0.15950633585453033 2023-01-23 11:45:40.355700: step: 1298/1545, loss: 0.09067942202091217 2023-01-23 11:45:41.266775: step: 1300/1545, loss: 0.21194268763065338 2023-01-23 11:45:42.137890: step: 1302/1545, loss: 0.10554791241884232 2023-01-23 11:45:43.054616: step: 1304/1545, loss: 0.15709401667118073 2023-01-23 11:45:43.999059: step: 1306/1545, loss: 0.24521003663539886 2023-01-23 11:45:44.859701: step: 1308/1545, loss: 0.07446299493312836 2023-01-23 11:45:45.732708: step: 1310/1545, loss: 0.039019875228405 2023-01-23 11:45:46.644253: step: 1312/1545, loss: 0.42608779668807983 2023-01-23 11:45:47.546692: step: 1314/1545, loss: 0.14767323434352875 2023-01-23 11:45:48.395971: step: 1316/1545, loss: 0.0356205552816391 2023-01-23 11:45:49.309999: step: 1318/1545, loss: 0.031104233115911484 2023-01-23 11:45:50.240062: step: 1320/1545, loss: 0.007432934828102589 2023-01-23 11:45:51.088799: step: 1322/1545, loss: 0.10575148463249207 2023-01-23 11:45:51.980366: step: 1324/1545, loss: 0.09441857039928436 2023-01-23 11:45:52.871635: step: 1326/1545, loss: 0.17360033094882965 2023-01-23 11:45:53.720035: step: 1328/1545, loss: 0.05655708163976669 2023-01-23 11:45:54.548292: step: 1330/1545, loss: 0.05911114811897278 2023-01-23 11:45:55.388697: step: 1332/1545, loss: 0.026159662753343582 2023-01-23 11:45:56.295032: step: 1334/1545, loss: 0.094667449593544 2023-01-23 11:45:57.164719: step: 1336/1545, loss: 0.33619505167007446 2023-01-23 11:45:58.052282: step: 1338/1545, loss: 0.6770415306091309 2023-01-23 11:45:58.938557: step: 1340/1545, loss: 0.017421547323465347 2023-01-23 11:45:59.907971: step: 1342/1545, loss: 0.0788678526878357 2023-01-23 11:46:00.780229: step: 1344/1545, loss: 0.18749023973941803 2023-01-23 11:46:01.627134: step: 1346/1545, loss: 0.20946235954761505 2023-01-23 11:46:02.465350: step: 1348/1545, loss: 0.07502925395965576 2023-01-23 11:46:03.314238: step: 1350/1545, loss: 0.05802641436457634 2023-01-23 11:46:04.220554: step: 1352/1545, loss: 0.027752786874771118 2023-01-23 11:46:05.159166: step: 1354/1545, loss: 0.10785166174173355 2023-01-23 11:46:06.018759: step: 1356/1545, loss: 0.022909313440322876 2023-01-23 11:46:06.874196: step: 1358/1545, loss: 0.08145175874233246 2023-01-23 11:46:07.744348: step: 1360/1545, loss: 0.1572841852903366 2023-01-23 11:46:08.655063: step: 1362/1545, loss: 0.2188904881477356 2023-01-23 11:46:09.516866: step: 1364/1545, loss: 0.013264315202832222 2023-01-23 11:46:10.431490: step: 1366/1545, loss: 0.5447069406509399 2023-01-23 11:46:11.361081: step: 1368/1545, loss: 0.09551229327917099 2023-01-23 11:46:12.214055: step: 1370/1545, loss: 0.10213521867990494 2023-01-23 11:46:13.123837: step: 1372/1545, loss: 0.042745720595121384 2023-01-23 11:46:14.096434: step: 1374/1545, loss: 0.39173445105552673 2023-01-23 11:46:15.131798: step: 1376/1545, loss: 0.054463982582092285 2023-01-23 11:46:16.047194: step: 1378/1545, loss: 0.053253162652254105 2023-01-23 11:46:17.006268: step: 1380/1545, loss: 0.5782994627952576 2023-01-23 11:46:17.884600: step: 1382/1545, loss: 0.05969727411866188 2023-01-23 11:46:18.760465: step: 1384/1545, loss: 0.21548745036125183 2023-01-23 11:46:19.678138: step: 1386/1545, loss: 0.02001599594950676 2023-01-23 11:46:20.556831: step: 1388/1545, loss: 0.12187028676271439 2023-01-23 11:46:21.452749: step: 1390/1545, loss: 0.07537834346294403 2023-01-23 11:46:22.366921: step: 1392/1545, loss: 0.2308988720178604 2023-01-23 11:46:23.238636: step: 1394/1545, loss: 0.10165353864431381 2023-01-23 11:46:24.120703: step: 1396/1545, loss: 0.15392741560935974 2023-01-23 11:46:25.010808: step: 1398/1545, loss: 0.23417219519615173 2023-01-23 11:46:25.881560: step: 1400/1545, loss: 0.1489250659942627 2023-01-23 11:46:26.739418: step: 1402/1545, loss: 2.2556071281433105 2023-01-23 11:46:27.646567: step: 1404/1545, loss: 0.0624791644513607 2023-01-23 11:46:28.498804: step: 1406/1545, loss: 0.37187254428863525 2023-01-23 11:46:29.378637: step: 1408/1545, loss: 0.7894768118858337 2023-01-23 11:46:30.272267: step: 1410/1545, loss: 0.007600031793117523 2023-01-23 11:46:31.158568: step: 1412/1545, loss: 0.031060922890901566 2023-01-23 11:46:32.017089: step: 1414/1545, loss: 0.006911647506058216 2023-01-23 11:46:32.892162: step: 1416/1545, loss: 0.35244837403297424 2023-01-23 11:46:33.797488: step: 1418/1545, loss: 0.4308457672595978 2023-01-23 11:46:34.824137: step: 1420/1545, loss: 0.1653880774974823 2023-01-23 11:46:35.709358: step: 1422/1545, loss: 0.08632779121398926 2023-01-23 11:46:36.583065: step: 1424/1545, loss: 0.5338087677955627 2023-01-23 11:46:37.528973: step: 1426/1545, loss: 0.4754752218723297 2023-01-23 11:46:38.454537: step: 1428/1545, loss: 0.02178121916949749 2023-01-23 11:46:39.300506: step: 1430/1545, loss: 0.010770426131784916 2023-01-23 11:46:40.215769: step: 1432/1545, loss: 0.009609951637685299 2023-01-23 11:46:41.143327: step: 1434/1545, loss: 0.017077084630727768 2023-01-23 11:46:42.065970: step: 1436/1545, loss: 0.22484977543354034 2023-01-23 11:46:42.930260: step: 1438/1545, loss: 0.012857147492468357 2023-01-23 11:46:43.849017: step: 1440/1545, loss: 0.013501863926649094 2023-01-23 11:46:44.702752: step: 1442/1545, loss: 0.1456456184387207 2023-01-23 11:46:45.588307: step: 1444/1545, loss: 0.04141848906874657 2023-01-23 11:46:46.464142: step: 1446/1545, loss: 0.15944591164588928 2023-01-23 11:46:47.350829: step: 1448/1545, loss: 0.02036888524889946 2023-01-23 11:46:48.218215: step: 1450/1545, loss: 0.11497169733047485 2023-01-23 11:46:49.115420: step: 1452/1545, loss: 0.006376830395311117 2023-01-23 11:46:50.014149: step: 1454/1545, loss: 2.216304302215576 2023-01-23 11:46:50.880619: step: 1456/1545, loss: 0.10343553870916367 2023-01-23 11:46:51.725752: step: 1458/1545, loss: 0.03761671483516693 2023-01-23 11:46:52.619720: step: 1460/1545, loss: 0.009717801585793495 2023-01-23 11:46:53.524329: step: 1462/1545, loss: 0.01398779172450304 2023-01-23 11:46:54.426016: step: 1464/1545, loss: 0.33193156123161316 2023-01-23 11:46:55.300109: step: 1466/1545, loss: 0.003421219764277339 2023-01-23 11:46:56.179162: step: 1468/1545, loss: 0.057076346129179 2023-01-23 11:46:57.033979: step: 1470/1545, loss: 0.13808515667915344 2023-01-23 11:46:57.902306: step: 1472/1545, loss: 0.04523222893476486 2023-01-23 11:46:58.783183: step: 1474/1545, loss: 0.0011129812337458134 2023-01-23 11:46:59.718835: step: 1476/1545, loss: 0.09530597180128098 2023-01-23 11:47:00.608074: step: 1478/1545, loss: 0.04468034207820892 2023-01-23 11:47:01.601558: step: 1480/1545, loss: 0.018836693838238716 2023-01-23 11:47:02.501985: step: 1482/1545, loss: 0.15909825265407562 2023-01-23 11:47:03.374047: step: 1484/1545, loss: 0.03909902647137642 2023-01-23 11:47:04.288114: step: 1486/1545, loss: 0.0424896739423275 2023-01-23 11:47:05.140282: step: 1488/1545, loss: 0.01292773149907589 2023-01-23 11:47:06.048216: step: 1490/1545, loss: 0.08838529884815216 2023-01-23 11:47:06.927731: step: 1492/1545, loss: 0.0010841983603313565 2023-01-23 11:47:07.779846: step: 1494/1545, loss: 0.014276192523539066 2023-01-23 11:47:08.712130: step: 1496/1545, loss: 0.3318135738372803 2023-01-23 11:47:09.583614: step: 1498/1545, loss: 0.3029809594154358 2023-01-23 11:47:10.431099: step: 1500/1545, loss: 0.07033845782279968 2023-01-23 11:47:11.402090: step: 1502/1545, loss: 0.006104234140366316 2023-01-23 11:47:12.286387: step: 1504/1545, loss: 0.11963239312171936 2023-01-23 11:47:13.174053: step: 1506/1545, loss: 0.16980141401290894 2023-01-23 11:47:14.196483: step: 1508/1545, loss: 0.49122387170791626 2023-01-23 11:47:15.157404: step: 1510/1545, loss: 0.03832703083753586 2023-01-23 11:47:16.040710: step: 1512/1545, loss: 0.09404351562261581 2023-01-23 11:47:16.927491: step: 1514/1545, loss: 0.04731011390686035 2023-01-23 11:47:17.819818: step: 1516/1545, loss: 0.24124440550804138 2023-01-23 11:47:18.709666: step: 1518/1545, loss: 0.821953535079956 2023-01-23 11:47:19.616312: step: 1520/1545, loss: 0.10879410058259964 2023-01-23 11:47:20.519437: step: 1522/1545, loss: 0.1175515279173851 2023-01-23 11:47:21.385592: step: 1524/1545, loss: 0.06300653517246246 2023-01-23 11:47:22.277629: step: 1526/1545, loss: 0.01959695667028427 2023-01-23 11:47:23.131873: step: 1528/1545, loss: 0.3351617157459259 2023-01-23 11:47:24.026003: step: 1530/1545, loss: 0.14889691770076752 2023-01-23 11:47:24.901420: step: 1532/1545, loss: 0.29678282141685486 2023-01-23 11:47:25.791679: step: 1534/1545, loss: 0.1423550546169281 2023-01-23 11:47:26.670668: step: 1536/1545, loss: 0.14282052218914032 2023-01-23 11:47:27.557504: step: 1538/1545, loss: 0.09717866778373718 2023-01-23 11:47:28.446786: step: 1540/1545, loss: 0.04813922196626663 2023-01-23 11:47:29.343872: step: 1542/1545, loss: 0.07632748782634735 2023-01-23 11:47:30.263203: step: 1544/1545, loss: 0.08864279091358185 2023-01-23 11:47:31.149346: step: 1546/1545, loss: 0.0646291971206665 2023-01-23 11:47:32.138073: step: 1548/1545, loss: 0.052613288164138794 2023-01-23 11:47:32.993636: step: 1550/1545, loss: 0.43582117557525635 2023-01-23 11:47:33.863640: step: 1552/1545, loss: 0.4668709933757782 2023-01-23 11:47:34.702585: step: 1554/1545, loss: 0.15141911804676056 2023-01-23 11:47:35.574102: step: 1556/1545, loss: 0.25275132060050964 2023-01-23 11:47:36.479507: step: 1558/1545, loss: 0.021579142659902573 2023-01-23 11:47:37.402821: step: 1560/1545, loss: 0.04499562829732895 2023-01-23 11:47:38.273075: step: 1562/1545, loss: 0.08591829240322113 2023-01-23 11:47:39.136958: step: 1564/1545, loss: 0.18724855780601501 2023-01-23 11:47:40.017895: step: 1566/1545, loss: 0.010623447597026825 2023-01-23 11:47:40.899537: step: 1568/1545, loss: 0.0037527901586145163 2023-01-23 11:47:41.767284: step: 1570/1545, loss: 0.03978515416383743 2023-01-23 11:47:42.629799: step: 1572/1545, loss: 0.11401369422674179 2023-01-23 11:47:43.522599: step: 1574/1545, loss: 0.25100311636924744 2023-01-23 11:47:44.384806: step: 1576/1545, loss: 0.10034669935703278 2023-01-23 11:47:45.283665: step: 1578/1545, loss: 0.06552257388830185 2023-01-23 11:47:46.149295: step: 1580/1545, loss: 0.044973134994506836 2023-01-23 11:47:47.015210: step: 1582/1545, loss: 0.3299606740474701 2023-01-23 11:47:47.897425: step: 1584/1545, loss: 0.0736444890499115 2023-01-23 11:47:48.803660: step: 1586/1545, loss: 0.15760695934295654 2023-01-23 11:47:49.726286: step: 1588/1545, loss: 0.014665809459984303 2023-01-23 11:47:50.582418: step: 1590/1545, loss: 0.09386681020259857 2023-01-23 11:47:51.538172: step: 1592/1545, loss: 0.0772874504327774 2023-01-23 11:47:52.382708: step: 1594/1545, loss: 0.0060947127640247345 2023-01-23 11:47:53.232275: step: 1596/1545, loss: 0.26057207584381104 2023-01-23 11:47:54.093991: step: 1598/1545, loss: 0.03672093525528908 2023-01-23 11:47:54.980295: step: 1600/1545, loss: 0.013716919347643852 2023-01-23 11:47:55.921913: step: 1602/1545, loss: 0.05362842231988907 2023-01-23 11:47:56.769259: step: 1604/1545, loss: 0.008270319551229477 2023-01-23 11:47:57.633930: step: 1606/1545, loss: 0.20807932317256927 2023-01-23 11:47:58.499788: step: 1608/1545, loss: 0.15484245121479034 2023-01-23 11:47:59.364994: step: 1610/1545, loss: 0.024306772276759148 2023-01-23 11:48:00.230600: step: 1612/1545, loss: 0.03632465749979019 2023-01-23 11:48:01.103884: step: 1614/1545, loss: 0.12018921226263046 2023-01-23 11:48:01.986037: step: 1616/1545, loss: 0.24523305892944336 2023-01-23 11:48:02.833265: step: 1618/1545, loss: 0.08772644400596619 2023-01-23 11:48:03.716548: step: 1620/1545, loss: 0.30687153339385986 2023-01-23 11:48:04.571350: step: 1622/1545, loss: 0.2794191539287567 2023-01-23 11:48:05.448150: step: 1624/1545, loss: 0.3926382064819336 2023-01-23 11:48:06.316050: step: 1626/1545, loss: 0.17428261041641235 2023-01-23 11:48:07.210066: step: 1628/1545, loss: 0.07768170535564423 2023-01-23 11:48:08.106077: step: 1630/1545, loss: 0.17320971190929413 2023-01-23 11:48:08.971134: step: 1632/1545, loss: 0.029642179608345032 2023-01-23 11:48:09.840042: step: 1634/1545, loss: 0.0255526565015316 2023-01-23 11:48:10.703758: step: 1636/1545, loss: 0.28104862570762634 2023-01-23 11:48:11.571208: step: 1638/1545, loss: 0.32072657346725464 2023-01-23 11:48:12.425618: step: 1640/1545, loss: 0.05331794545054436 2023-01-23 11:48:13.389371: step: 1642/1545, loss: 0.20640185475349426 2023-01-23 11:48:14.325384: step: 1644/1545, loss: 0.019743477925658226 2023-01-23 11:48:15.199065: step: 1646/1545, loss: 0.01035173051059246 2023-01-23 11:48:16.100137: step: 1648/1545, loss: 0.05189211294054985 2023-01-23 11:48:16.955881: step: 1650/1545, loss: 0.17865702509880066 2023-01-23 11:48:17.849082: step: 1652/1545, loss: 0.03861941769719124 2023-01-23 11:48:18.719633: step: 1654/1545, loss: 0.19038531184196472 2023-01-23 11:48:19.706288: step: 1656/1545, loss: 0.1033705398440361 2023-01-23 11:48:20.558532: step: 1658/1545, loss: 0.051820240914821625 2023-01-23 11:48:21.413846: step: 1660/1545, loss: 0.03121848776936531 2023-01-23 11:48:22.327791: step: 1662/1545, loss: 0.44551458954811096 2023-01-23 11:48:23.183697: step: 1664/1545, loss: 0.01141161099076271 2023-01-23 11:48:24.109823: step: 1666/1545, loss: 0.2962316572666168 2023-01-23 11:48:24.940221: step: 1668/1545, loss: 0.08852405846118927 2023-01-23 11:48:25.774752: step: 1670/1545, loss: 0.1196833923459053 2023-01-23 11:48:26.627529: step: 1672/1545, loss: 0.0324321873486042 2023-01-23 11:48:27.591615: step: 1674/1545, loss: 0.008398720994591713 2023-01-23 11:48:28.493267: step: 1676/1545, loss: 0.056868087500333786 2023-01-23 11:48:29.385358: step: 1678/1545, loss: 0.17744554579257965 2023-01-23 11:48:30.225347: step: 1680/1545, loss: 0.20964108407497406 2023-01-23 11:48:31.108278: step: 1682/1545, loss: 0.21435706317424774 2023-01-23 11:48:31.985963: step: 1684/1545, loss: 0.103178471326828 2023-01-23 11:48:32.849316: step: 1686/1545, loss: 0.05424509197473526 2023-01-23 11:48:33.723732: step: 1688/1545, loss: 0.13381583988666534 2023-01-23 11:48:34.593370: step: 1690/1545, loss: 0.04015275835990906 2023-01-23 11:48:35.426376: step: 1692/1545, loss: 0.05505862832069397 2023-01-23 11:48:36.331139: step: 1694/1545, loss: 0.13479828834533691 2023-01-23 11:48:37.193353: step: 1696/1545, loss: 0.6058473587036133 2023-01-23 11:48:38.050453: step: 1698/1545, loss: 0.03277287632226944 2023-01-23 11:48:38.886256: step: 1700/1545, loss: 0.0392361655831337 2023-01-23 11:48:39.794120: step: 1702/1545, loss: 0.04756106808781624 2023-01-23 11:48:40.663960: step: 1704/1545, loss: 0.186336487531662 2023-01-23 11:48:41.532297: step: 1706/1545, loss: 0.05286752060055733 2023-01-23 11:48:42.417852: step: 1708/1545, loss: 0.005231224931776524 2023-01-23 11:48:43.306334: step: 1710/1545, loss: 0.05845538526773453 2023-01-23 11:48:44.219110: step: 1712/1545, loss: 0.07067682594060898 2023-01-23 11:48:45.151399: step: 1714/1545, loss: 0.08290761709213257 2023-01-23 11:48:46.018795: step: 1716/1545, loss: 0.02572343498468399 2023-01-23 11:48:46.917770: step: 1718/1545, loss: 0.16479036211967468 2023-01-23 11:48:47.765683: step: 1720/1545, loss: 0.7115756273269653 2023-01-23 11:48:48.638598: step: 1722/1545, loss: 0.36954960227012634 2023-01-23 11:48:49.527583: step: 1724/1545, loss: 0.03558993339538574 2023-01-23 11:48:50.388278: step: 1726/1545, loss: 0.10782609134912491 2023-01-23 11:48:51.274888: step: 1728/1545, loss: 0.33432480692863464 2023-01-23 11:48:52.124889: step: 1730/1545, loss: 0.02362143248319626 2023-01-23 11:48:53.019149: step: 1732/1545, loss: 0.1723932921886444 2023-01-23 11:48:53.901978: step: 1734/1545, loss: 0.11245188862085342 2023-01-23 11:48:54.758854: step: 1736/1545, loss: 0.14052005112171173 2023-01-23 11:48:55.638240: step: 1738/1545, loss: 0.013627774082124233 2023-01-23 11:48:56.492097: step: 1740/1545, loss: 2.7157347202301025 2023-01-23 11:48:57.349992: step: 1742/1545, loss: 0.4730890691280365 2023-01-23 11:48:58.251166: step: 1744/1545, loss: 0.010030054487287998 2023-01-23 11:48:59.103599: step: 1746/1545, loss: 0.07874312996864319 2023-01-23 11:49:00.010212: step: 1748/1545, loss: 0.13238945603370667 2023-01-23 11:49:00.891984: step: 1750/1545, loss: 0.023154394701123238 2023-01-23 11:49:01.843938: step: 1752/1545, loss: 0.1975378841161728 2023-01-23 11:49:02.751582: step: 1754/1545, loss: 0.10979141294956207 2023-01-23 11:49:03.697412: step: 1756/1545, loss: 0.05578620731830597 2023-01-23 11:49:04.535548: step: 1758/1545, loss: 0.0516321063041687 2023-01-23 11:49:05.394249: step: 1760/1545, loss: 0.24829310178756714 2023-01-23 11:49:06.260849: step: 1762/1545, loss: 0.26360324025154114 2023-01-23 11:49:07.147184: step: 1764/1545, loss: 0.26354750990867615 2023-01-23 11:49:08.008973: step: 1766/1545, loss: 0.1955999732017517 2023-01-23 11:49:08.865471: step: 1768/1545, loss: 0.02539515495300293 2023-01-23 11:49:09.757506: step: 1770/1545, loss: 0.042182546108961105 2023-01-23 11:49:10.631033: step: 1772/1545, loss: 0.04488621652126312 2023-01-23 11:49:11.519808: step: 1774/1545, loss: 0.02438698150217533 2023-01-23 11:49:12.387701: step: 1776/1545, loss: 0.24542424082756042 2023-01-23 11:49:13.254121: step: 1778/1545, loss: 0.1403665989637375 2023-01-23 11:49:14.160532: step: 1780/1545, loss: 0.08628973364830017 2023-01-23 11:49:15.029072: step: 1782/1545, loss: 0.04407850652933121 2023-01-23 11:49:15.935713: step: 1784/1545, loss: 0.21499279141426086 2023-01-23 11:49:16.816853: step: 1786/1545, loss: 0.07935013622045517 2023-01-23 11:49:17.742390: step: 1788/1545, loss: 0.3345983326435089 2023-01-23 11:49:18.712314: step: 1790/1545, loss: 0.09530486911535263 2023-01-23 11:49:19.579295: step: 1792/1545, loss: 0.2281709909439087 2023-01-23 11:49:20.466871: step: 1794/1545, loss: 0.005774654448032379 2023-01-23 11:49:21.352039: step: 1796/1545, loss: 0.017618339508771896 2023-01-23 11:49:22.217913: step: 1798/1545, loss: 0.014012833125889301 2023-01-23 11:49:23.083239: step: 1800/1545, loss: 0.1875622719526291 2023-01-23 11:49:23.984370: step: 1802/1545, loss: 0.24248884618282318 2023-01-23 11:49:24.870149: step: 1804/1545, loss: 0.42437443137168884 2023-01-23 11:49:25.740827: step: 1806/1545, loss: 0.036288149654865265 2023-01-23 11:49:26.585431: step: 1808/1545, loss: 0.002657857956364751 2023-01-23 11:49:27.468174: step: 1810/1545, loss: 1.6360714435577393 2023-01-23 11:49:28.325297: step: 1812/1545, loss: 0.11983116716146469 2023-01-23 11:49:29.219115: step: 1814/1545, loss: 0.01997772417962551 2023-01-23 11:49:30.056022: step: 1816/1545, loss: 0.02590828575193882 2023-01-23 11:49:30.984775: step: 1818/1545, loss: 0.5103062391281128 2023-01-23 11:49:31.863331: step: 1820/1545, loss: 0.12844449281692505 2023-01-23 11:49:32.769092: step: 1822/1545, loss: 0.05086255446076393 2023-01-23 11:49:33.596935: step: 1824/1545, loss: 0.589637041091919 2023-01-23 11:49:34.450262: step: 1826/1545, loss: 0.1496858447790146 2023-01-23 11:49:35.336992: step: 1828/1545, loss: 0.014813048765063286 2023-01-23 11:49:36.228644: step: 1830/1545, loss: 0.5532963275909424 2023-01-23 11:49:37.088483: step: 1832/1545, loss: 0.016013065353035927 2023-01-23 11:49:37.975006: step: 1834/1545, loss: 0.055173344910144806 2023-01-23 11:49:38.912805: step: 1836/1545, loss: 0.13238629698753357 2023-01-23 11:49:39.787824: step: 1838/1545, loss: 0.113488107919693 2023-01-23 11:49:40.645819: step: 1840/1545, loss: 0.1540309190750122 2023-01-23 11:49:41.489327: step: 1842/1545, loss: 0.09836690872907639 2023-01-23 11:49:42.351160: step: 1844/1545, loss: 0.1345483958721161 2023-01-23 11:49:43.212006: step: 1846/1545, loss: 0.29070672392845154 2023-01-23 11:49:44.057736: step: 1848/1545, loss: 0.047026392072439194 2023-01-23 11:49:44.959638: step: 1850/1545, loss: 0.017872333526611328 2023-01-23 11:49:45.865895: step: 1852/1545, loss: 0.18530510365962982 2023-01-23 11:49:46.780438: step: 1854/1545, loss: 0.14414268732070923 2023-01-23 11:49:47.642210: step: 1856/1545, loss: 0.6599441170692444 2023-01-23 11:49:48.479673: step: 1858/1545, loss: 0.030488217249512672 2023-01-23 11:49:49.407859: step: 1860/1545, loss: 0.1154203936457634 2023-01-23 11:49:50.283628: step: 1862/1545, loss: 0.1291615217924118 2023-01-23 11:49:51.164716: step: 1864/1545, loss: 0.0340130478143692 2023-01-23 11:49:52.019939: step: 1866/1545, loss: 0.05320620536804199 2023-01-23 11:49:52.931149: step: 1868/1545, loss: 0.30610185861587524 2023-01-23 11:49:53.799491: step: 1870/1545, loss: 0.1911371648311615 2023-01-23 11:49:54.707553: step: 1872/1545, loss: 0.04513733834028244 2023-01-23 11:49:55.618024: step: 1874/1545, loss: 0.13803941011428833 2023-01-23 11:49:56.498150: step: 1876/1545, loss: 0.11966385692358017 2023-01-23 11:49:57.392212: step: 1878/1545, loss: 0.014963846653699875 2023-01-23 11:49:58.225821: step: 1880/1545, loss: 0.32114189863204956 2023-01-23 11:49:59.081305: step: 1882/1545, loss: 0.0597081258893013 2023-01-23 11:49:59.976756: step: 1884/1545, loss: 0.1399778425693512 2023-01-23 11:50:00.898145: step: 1886/1545, loss: 0.024541573598980904 2023-01-23 11:50:01.802106: step: 1888/1545, loss: 0.046864915639162064 2023-01-23 11:50:02.639208: step: 1890/1545, loss: 0.34550464153289795 2023-01-23 11:50:03.517747: step: 1892/1545, loss: 0.05051928758621216 2023-01-23 11:50:04.487977: step: 1894/1545, loss: 0.05303790047764778 2023-01-23 11:50:05.381445: step: 1896/1545, loss: 0.4859361946582794 2023-01-23 11:50:06.215839: step: 1898/1545, loss: 0.027080627158284187 2023-01-23 11:50:07.102846: step: 1900/1545, loss: 0.040833644568920135 2023-01-23 11:50:07.994400: step: 1902/1545, loss: 0.018063925206661224 2023-01-23 11:50:08.843669: step: 1904/1545, loss: 0.7264902591705322 2023-01-23 11:50:09.706624: step: 1906/1545, loss: 0.24055597186088562 2023-01-23 11:50:10.583220: step: 1908/1545, loss: 0.031525202095508575 2023-01-23 11:50:11.581432: step: 1910/1545, loss: 0.05102863162755966 2023-01-23 11:50:12.473560: step: 1912/1545, loss: 0.11200686544179916 2023-01-23 11:50:13.367267: step: 1914/1545, loss: 0.4398540258407593 2023-01-23 11:50:14.241540: step: 1916/1545, loss: 0.07670795172452927 2023-01-23 11:50:15.174562: step: 1918/1545, loss: 0.010512097738683224 2023-01-23 11:50:16.028951: step: 1920/1545, loss: 0.015435192734003067 2023-01-23 11:50:16.882596: step: 1922/1545, loss: 6.426128387451172 2023-01-23 11:50:17.769202: step: 1924/1545, loss: 0.03263922035694122 2023-01-23 11:50:18.723623: step: 1926/1545, loss: 0.1960565745830536 2023-01-23 11:50:19.579350: step: 1928/1545, loss: 0.007235835772007704 2023-01-23 11:50:20.489590: step: 1930/1545, loss: 0.002930897055193782 2023-01-23 11:50:21.359580: step: 1932/1545, loss: 0.024907248094677925 2023-01-23 11:50:22.210848: step: 1934/1545, loss: 5.162595272064209 2023-01-23 11:50:23.118151: step: 1936/1545, loss: 0.14661937952041626 2023-01-23 11:50:24.049404: step: 1938/1545, loss: 0.04539528489112854 2023-01-23 11:50:24.926879: step: 1940/1545, loss: 0.18164272606372833 2023-01-23 11:50:25.940027: step: 1942/1545, loss: 0.22946204245090485 2023-01-23 11:50:26.795114: step: 1944/1545, loss: 0.028675450012087822 2023-01-23 11:50:27.736974: step: 1946/1545, loss: 0.5826070308685303 2023-01-23 11:50:28.607124: step: 1948/1545, loss: 0.17417234182357788 2023-01-23 11:50:29.507973: step: 1950/1545, loss: 0.05009632185101509 2023-01-23 11:50:30.435576: step: 1952/1545, loss: 0.012201973237097263 2023-01-23 11:50:31.282266: step: 1954/1545, loss: 0.033902738243341446 2023-01-23 11:50:32.139227: step: 1956/1545, loss: 0.25546249747276306 2023-01-23 11:50:32.988709: step: 1958/1545, loss: 0.0724739208817482 2023-01-23 11:50:33.869357: step: 1960/1545, loss: 0.2390459179878235 2023-01-23 11:50:34.729917: step: 1962/1545, loss: 0.022890884429216385 2023-01-23 11:50:35.656461: step: 1964/1545, loss: 0.3597373366355896 2023-01-23 11:50:36.544703: step: 1966/1545, loss: 0.08952007442712784 2023-01-23 11:50:37.434050: step: 1968/1545, loss: 0.009975165128707886 2023-01-23 11:50:38.342219: step: 1970/1545, loss: 0.12420574575662613 2023-01-23 11:50:39.215453: step: 1972/1545, loss: 0.06441482156515121 2023-01-23 11:50:40.104342: step: 1974/1545, loss: 0.13495729863643646 2023-01-23 11:50:40.956154: step: 1976/1545, loss: 0.2955613136291504 2023-01-23 11:50:41.845091: step: 1978/1545, loss: 0.22162261605262756 2023-01-23 11:50:42.688610: step: 1980/1545, loss: 0.27509042620658875 2023-01-23 11:50:43.549559: step: 1982/1545, loss: 0.024514665827155113 2023-01-23 11:50:44.416416: step: 1984/1545, loss: 0.02716333605349064 2023-01-23 11:50:45.328179: step: 1986/1545, loss: 0.08417638391256332 2023-01-23 11:50:46.196083: step: 1988/1545, loss: 0.005795902572572231 2023-01-23 11:50:47.108562: step: 1990/1545, loss: 0.6935113072395325 2023-01-23 11:50:47.962744: step: 1992/1545, loss: 0.18556582927703857 2023-01-23 11:50:48.868052: step: 1994/1545, loss: 0.17939552664756775 2023-01-23 11:50:49.779538: step: 1996/1545, loss: 0.1335403323173523 2023-01-23 11:50:50.737914: step: 1998/1545, loss: 0.17811468243598938 2023-01-23 11:50:51.625223: step: 2000/1545, loss: 0.38675305247306824 2023-01-23 11:50:52.513305: step: 2002/1545, loss: 0.05472046881914139 2023-01-23 11:50:53.437741: step: 2004/1545, loss: 0.02157558873295784 2023-01-23 11:50:54.312084: step: 2006/1545, loss: 0.12832264602184296 2023-01-23 11:50:55.217103: step: 2008/1545, loss: 0.061984989792108536 2023-01-23 11:50:56.095323: step: 2010/1545, loss: 0.3261896073818207 2023-01-23 11:50:56.965981: step: 2012/1545, loss: 0.010096331126987934 2023-01-23 11:50:57.881351: step: 2014/1545, loss: 0.2874072194099426 2023-01-23 11:50:58.774624: step: 2016/1545, loss: 0.12112389504909515 2023-01-23 11:50:59.691585: step: 2018/1545, loss: 0.005412326660007238 2023-01-23 11:51:00.547303: step: 2020/1545, loss: 0.023143909871578217 2023-01-23 11:51:01.493172: step: 2022/1545, loss: 0.08468398451805115 2023-01-23 11:51:02.351162: step: 2024/1545, loss: 0.8166345357894897 2023-01-23 11:51:03.199498: step: 2026/1545, loss: 0.03133625164628029 2023-01-23 11:51:04.026015: step: 2028/1545, loss: 0.0077155157923698425 2023-01-23 11:51:04.944008: step: 2030/1545, loss: 0.24697661399841309 2023-01-23 11:51:05.831781: step: 2032/1545, loss: 0.030348628759384155 2023-01-23 11:51:06.721490: step: 2034/1545, loss: 0.001084688352420926 2023-01-23 11:51:07.590088: step: 2036/1545, loss: 0.2626418471336365 2023-01-23 11:51:08.490496: step: 2038/1545, loss: 0.050177354365587234 2023-01-23 11:51:09.351070: step: 2040/1545, loss: 0.9192071557044983 2023-01-23 11:51:10.225879: step: 2042/1545, loss: 0.04488825798034668 2023-01-23 11:51:11.091759: step: 2044/1545, loss: 0.16092905402183533 2023-01-23 11:51:11.933062: step: 2046/1545, loss: 2.5112926959991455 2023-01-23 11:51:12.827631: step: 2048/1545, loss: 0.018089428544044495 2023-01-23 11:51:13.699876: step: 2050/1545, loss: 0.03618122264742851 2023-01-23 11:51:14.577926: step: 2052/1545, loss: 0.021438781172037125 2023-01-23 11:51:15.439699: step: 2054/1545, loss: 0.16941270232200623 2023-01-23 11:51:16.411901: step: 2056/1545, loss: 0.03935908526182175 2023-01-23 11:51:17.258754: step: 2058/1545, loss: 0.23115140199661255 2023-01-23 11:51:18.122120: step: 2060/1545, loss: 0.011903874576091766 2023-01-23 11:51:19.034895: step: 2062/1545, loss: 0.02304108813405037 2023-01-23 11:51:19.944575: step: 2064/1545, loss: 0.055930428206920624 2023-01-23 11:51:20.815588: step: 2066/1545, loss: 0.13025231659412384 2023-01-23 11:51:21.682798: step: 2068/1545, loss: 0.16733615100383759 2023-01-23 11:51:22.595188: step: 2070/1545, loss: 0.35443806648254395 2023-01-23 11:51:23.439506: step: 2072/1545, loss: 0.03808506578207016 2023-01-23 11:51:24.394829: step: 2074/1545, loss: 0.046068619936704636 2023-01-23 11:51:25.324314: step: 2076/1545, loss: 0.07735052704811096 2023-01-23 11:51:26.169833: step: 2078/1545, loss: 0.09128536283969879 2023-01-23 11:51:27.127584: step: 2080/1545, loss: 0.04808066040277481 2023-01-23 11:51:27.990121: step: 2082/1545, loss: 0.25340965390205383 2023-01-23 11:51:28.882377: step: 2084/1545, loss: 0.01993958093225956 2023-01-23 11:51:29.801096: step: 2086/1545, loss: 0.06943102180957794 2023-01-23 11:51:30.695354: step: 2088/1545, loss: 0.09981722384691238 2023-01-23 11:51:31.565702: step: 2090/1545, loss: 0.20735915005207062 2023-01-23 11:51:32.442230: step: 2092/1545, loss: 0.19057071208953857 2023-01-23 11:51:33.282946: step: 2094/1545, loss: 0.3199634552001953 2023-01-23 11:51:34.161335: step: 2096/1545, loss: 0.45675358176231384 2023-01-23 11:51:35.064388: step: 2098/1545, loss: 0.040340594947338104 2023-01-23 11:51:35.949450: step: 2100/1545, loss: 0.1878724992275238 2023-01-23 11:51:36.802529: step: 2102/1545, loss: 0.14904524385929108 2023-01-23 11:51:37.633290: step: 2104/1545, loss: 0.013808329589664936 2023-01-23 11:51:38.534936: step: 2106/1545, loss: 0.13787724077701569 2023-01-23 11:51:39.423829: step: 2108/1545, loss: 0.23379939794540405 2023-01-23 11:51:40.304971: step: 2110/1545, loss: 0.038328491151332855 2023-01-23 11:51:41.177153: step: 2112/1545, loss: 0.02809947356581688 2023-01-23 11:51:42.085976: step: 2114/1545, loss: 0.25748398900032043 2023-01-23 11:51:43.019270: step: 2116/1545, loss: 0.15338584780693054 2023-01-23 11:51:43.880316: step: 2118/1545, loss: 0.13330815732479095 2023-01-23 11:51:44.743027: step: 2120/1545, loss: 0.20793786644935608 2023-01-23 11:51:45.589600: step: 2122/1545, loss: 0.16405797004699707 2023-01-23 11:51:46.493912: step: 2124/1545, loss: 0.03997752442955971 2023-01-23 11:51:47.352330: step: 2126/1545, loss: 0.25881022214889526 2023-01-23 11:51:48.278433: step: 2128/1545, loss: 0.044170085340738297 2023-01-23 11:51:49.122580: step: 2130/1545, loss: 0.8829326033592224 2023-01-23 11:51:50.013827: step: 2132/1545, loss: 0.08307939767837524 2023-01-23 11:51:50.899395: step: 2134/1545, loss: 0.342763751745224 2023-01-23 11:51:51.747811: step: 2136/1545, loss: 0.221769779920578 2023-01-23 11:51:52.607723: step: 2138/1545, loss: 0.16236935555934906 2023-01-23 11:51:53.478394: step: 2140/1545, loss: 0.07892071455717087 2023-01-23 11:51:54.341480: step: 2142/1545, loss: 0.42412975430488586 2023-01-23 11:51:55.203679: step: 2144/1545, loss: 0.061448436230421066 2023-01-23 11:51:56.081708: step: 2146/1545, loss: 0.019931074231863022 2023-01-23 11:51:56.937790: step: 2148/1545, loss: 0.014743979088962078 2023-01-23 11:51:57.833083: step: 2150/1545, loss: 0.2403343915939331 2023-01-23 11:51:58.711775: step: 2152/1545, loss: 0.1315828561782837 2023-01-23 11:51:59.630749: step: 2154/1545, loss: 0.03765735775232315 2023-01-23 11:52:00.462387: step: 2156/1545, loss: 0.004558788146823645 2023-01-23 11:52:01.412465: step: 2158/1545, loss: 0.1438240110874176 2023-01-23 11:52:02.250838: step: 2160/1545, loss: 0.30447620153427124 2023-01-23 11:52:03.213797: step: 2162/1545, loss: 0.18383188545703888 2023-01-23 11:52:04.082086: step: 2164/1545, loss: 0.4000873863697052 2023-01-23 11:52:04.973177: step: 2166/1545, loss: 0.06182229891419411 2023-01-23 11:52:05.817801: step: 2168/1545, loss: 0.02111922763288021 2023-01-23 11:52:06.684771: step: 2170/1545, loss: 0.15486732125282288 2023-01-23 11:52:07.546267: step: 2172/1545, loss: 0.03172405809164047 2023-01-23 11:52:08.451981: step: 2174/1545, loss: 0.0338558666408062 2023-01-23 11:52:09.409521: step: 2176/1545, loss: 0.02374090999364853 2023-01-23 11:52:10.282276: step: 2178/1545, loss: 0.022792208939790726 2023-01-23 11:52:11.155683: step: 2180/1545, loss: 0.09016961604356766 2023-01-23 11:52:12.063592: step: 2182/1545, loss: 0.28287360072135925 2023-01-23 11:52:13.041042: step: 2184/1545, loss: 0.18729543685913086 2023-01-23 11:52:13.899446: step: 2186/1545, loss: 0.016202187165617943 2023-01-23 11:52:14.793537: step: 2188/1545, loss: 0.060865696519613266 2023-01-23 11:52:15.676489: step: 2190/1545, loss: 0.02017628587782383 2023-01-23 11:52:16.599226: step: 2192/1545, loss: 0.3877640962600708 2023-01-23 11:52:17.506461: step: 2194/1545, loss: 0.06802016496658325 2023-01-23 11:52:18.359190: step: 2196/1545, loss: 0.2024165838956833 2023-01-23 11:52:19.273518: step: 2198/1545, loss: 0.40397489070892334 2023-01-23 11:52:20.167009: step: 2200/1545, loss: 0.019233103841543198 2023-01-23 11:52:21.072563: step: 2202/1545, loss: 0.35497334599494934 2023-01-23 11:52:21.958262: step: 2204/1545, loss: 0.00538095086812973 2023-01-23 11:52:22.841091: step: 2206/1545, loss: 0.09624847024679184 2023-01-23 11:52:23.706113: step: 2208/1545, loss: 0.21620036661624908 2023-01-23 11:52:24.578719: step: 2210/1545, loss: 0.0759163498878479 2023-01-23 11:52:25.444969: step: 2212/1545, loss: 2.270925998687744 2023-01-23 11:52:26.335489: step: 2214/1545, loss: 0.4106130003929138 2023-01-23 11:52:27.194902: step: 2216/1545, loss: 0.1616418957710266 2023-01-23 11:52:28.059706: step: 2218/1545, loss: 0.029683619737625122 2023-01-23 11:52:28.940945: step: 2220/1545, loss: 0.047803059220314026 2023-01-23 11:52:29.866056: step: 2222/1545, loss: 0.02336370199918747 2023-01-23 11:52:30.743864: step: 2224/1545, loss: 0.0940021276473999 2023-01-23 11:52:31.606304: step: 2226/1545, loss: 0.06361500918865204 2023-01-23 11:52:32.480064: step: 2228/1545, loss: 0.04037611931562424 2023-01-23 11:52:33.380371: step: 2230/1545, loss: 0.2044798880815506 2023-01-23 11:52:34.274985: step: 2232/1545, loss: 0.4970194101333618 2023-01-23 11:52:35.155522: step: 2234/1545, loss: 2.408693790435791 2023-01-23 11:52:36.033653: step: 2236/1545, loss: 0.002609919523820281 2023-01-23 11:52:36.920937: step: 2238/1545, loss: 0.032935671508312225 2023-01-23 11:52:37.806986: step: 2240/1545, loss: 0.011557511053979397 2023-01-23 11:52:38.693236: step: 2242/1545, loss: 0.12707233428955078 2023-01-23 11:52:39.554582: step: 2244/1545, loss: 0.07619379460811615 2023-01-23 11:52:40.473817: step: 2246/1545, loss: 0.18950127065181732 2023-01-23 11:52:41.413578: step: 2248/1545, loss: 0.2469164878129959 2023-01-23 11:52:42.297309: step: 2250/1545, loss: 8.775497436523438 2023-01-23 11:52:43.176994: step: 2252/1545, loss: 0.0032727045472711325 2023-01-23 11:52:44.048561: step: 2254/1545, loss: 0.06826654076576233 2023-01-23 11:52:44.942970: step: 2256/1545, loss: 0.13627666234970093 2023-01-23 11:52:45.846291: step: 2258/1545, loss: 0.04737745597958565 2023-01-23 11:52:46.721625: step: 2260/1545, loss: 0.055670030415058136 2023-01-23 11:52:47.582004: step: 2262/1545, loss: 0.31435075402259827 2023-01-23 11:52:48.473414: step: 2264/1545, loss: 0.048648376017808914 2023-01-23 11:52:49.337403: step: 2266/1545, loss: 0.2175847440958023 2023-01-23 11:52:50.243319: step: 2268/1545, loss: 0.1278710663318634 2023-01-23 11:52:51.107431: step: 2270/1545, loss: 0.014635702595114708 2023-01-23 11:52:51.975374: step: 2272/1545, loss: 0.11014404892921448 2023-01-23 11:52:52.893026: step: 2274/1545, loss: 0.9766997694969177 2023-01-23 11:52:53.758581: step: 2276/1545, loss: 0.13871058821678162 2023-01-23 11:52:54.637785: step: 2278/1545, loss: 0.025187866762280464 2023-01-23 11:52:55.522548: step: 2280/1545, loss: 0.09854158759117126 2023-01-23 11:52:56.398788: step: 2282/1545, loss: 0.04593781754374504 2023-01-23 11:52:57.252839: step: 2284/1545, loss: 0.15422798693180084 2023-01-23 11:52:58.115919: step: 2286/1545, loss: 0.26443782448768616 2023-01-23 11:52:59.009699: step: 2288/1545, loss: 0.11974800378084183 2023-01-23 11:52:59.918995: step: 2290/1545, loss: 0.006333441473543644 2023-01-23 11:53:00.830352: step: 2292/1545, loss: 2.0719027519226074 2023-01-23 11:53:01.733604: step: 2294/1545, loss: 1.3061083555221558 2023-01-23 11:53:02.633676: step: 2296/1545, loss: 0.2791323661804199 2023-01-23 11:53:03.485403: step: 2298/1545, loss: 0.068905770778656 2023-01-23 11:53:04.473333: step: 2300/1545, loss: 0.2868182957172394 2023-01-23 11:53:05.392158: step: 2302/1545, loss: 0.06146794557571411 2023-01-23 11:53:06.281536: step: 2304/1545, loss: 0.08681268244981766 2023-01-23 11:53:07.113922: step: 2306/1545, loss: 0.2890169620513916 2023-01-23 11:53:08.012293: step: 2308/1545, loss: 0.23702549934387207 2023-01-23 11:53:08.885967: step: 2310/1545, loss: 1.5105112791061401 2023-01-23 11:53:09.824015: step: 2312/1545, loss: 0.17563331127166748 2023-01-23 11:53:10.681765: step: 2314/1545, loss: 0.2869972586631775 2023-01-23 11:53:11.572329: step: 2316/1545, loss: 0.03759574145078659 2023-01-23 11:53:12.438764: step: 2318/1545, loss: 0.011633503250777721 2023-01-23 11:53:13.313380: step: 2320/1545, loss: 0.36321741342544556 2023-01-23 11:53:14.221557: step: 2322/1545, loss: 0.12653090059757233 2023-01-23 11:53:15.077365: step: 2324/1545, loss: 0.07790914177894592 2023-01-23 11:53:16.006401: step: 2326/1545, loss: 0.1495288759469986 2023-01-23 11:53:16.894113: step: 2328/1545, loss: 0.36033546924591064 2023-01-23 11:53:17.823456: step: 2330/1545, loss: 0.10989907383918762 2023-01-23 11:53:18.722959: step: 2332/1545, loss: 0.022377360612154007 2023-01-23 11:53:19.626568: step: 2334/1545, loss: 0.06800462305545807 2023-01-23 11:53:20.467139: step: 2336/1545, loss: 0.015972387045621872 2023-01-23 11:53:21.340701: step: 2338/1545, loss: 0.1273665428161621 2023-01-23 11:53:22.214221: step: 2340/1545, loss: 0.1391424685716629 2023-01-23 11:53:23.060240: step: 2342/1545, loss: 0.028803864493966103 2023-01-23 11:53:23.900947: step: 2344/1545, loss: 1.5005838871002197 2023-01-23 11:53:24.774454: step: 2346/1545, loss: 0.07584697008132935 2023-01-23 11:53:25.641657: step: 2348/1545, loss: 0.08122886717319489 2023-01-23 11:53:26.466961: step: 2350/1545, loss: 0.030212169513106346 2023-01-23 11:53:27.335330: step: 2352/1545, loss: 0.17788441479206085 2023-01-23 11:53:28.216815: step: 2354/1545, loss: 0.8209651112556458 2023-01-23 11:53:29.050398: step: 2356/1545, loss: 1.6156283617019653 2023-01-23 11:53:29.938065: step: 2358/1545, loss: 0.06240483745932579 2023-01-23 11:53:30.804676: step: 2360/1545, loss: 0.06784485280513763 2023-01-23 11:53:31.697811: step: 2362/1545, loss: 0.27632004022598267 2023-01-23 11:53:32.556695: step: 2364/1545, loss: 0.0896114856004715 2023-01-23 11:53:33.421981: step: 2366/1545, loss: 0.05287705361843109 2023-01-23 11:53:34.300824: step: 2368/1545, loss: 0.298959344625473 2023-01-23 11:53:35.231158: step: 2370/1545, loss: 0.10063256323337555 2023-01-23 11:53:36.107302: step: 2372/1545, loss: 0.2488819658756256 2023-01-23 11:53:36.935833: step: 2374/1545, loss: 0.3132553994655609 2023-01-23 11:53:37.809936: step: 2376/1545, loss: 0.027105914428830147 2023-01-23 11:53:38.775942: step: 2378/1545, loss: 0.1077762320637703 2023-01-23 11:53:39.699908: step: 2380/1545, loss: 0.04630240425467491 2023-01-23 11:53:40.625272: step: 2382/1545, loss: 0.2216997593641281 2023-01-23 11:53:41.472555: step: 2384/1545, loss: 0.02979203313589096 2023-01-23 11:53:42.336557: step: 2386/1545, loss: 0.01632491499185562 2023-01-23 11:53:43.220569: step: 2388/1545, loss: 0.3461952805519104 2023-01-23 11:53:44.065721: step: 2390/1545, loss: 0.15819965302944183 2023-01-23 11:53:44.947369: step: 2392/1545, loss: 0.02560720033943653 2023-01-23 11:53:45.887860: step: 2394/1545, loss: 0.5430819392204285 2023-01-23 11:53:46.799631: step: 2396/1545, loss: 0.0322752371430397 2023-01-23 11:53:47.634924: step: 2398/1545, loss: 0.04870925843715668 2023-01-23 11:53:48.560791: step: 2400/1545, loss: 0.016513168811798096 2023-01-23 11:53:49.437163: step: 2402/1545, loss: 0.07631739974021912 2023-01-23 11:53:50.365287: step: 2404/1545, loss: 0.7829717397689819 2023-01-23 11:53:51.261867: step: 2406/1545, loss: 0.05498460307717323 2023-01-23 11:53:52.116563: step: 2408/1545, loss: 0.026204602792859077 2023-01-23 11:53:52.999348: step: 2410/1545, loss: 0.17603445053100586 2023-01-23 11:53:53.892645: step: 2412/1545, loss: 0.10285847634077072 2023-01-23 11:53:54.779986: step: 2414/1545, loss: 0.012786905281245708 2023-01-23 11:53:55.672395: step: 2416/1545, loss: 0.002962213708087802 2023-01-23 11:53:56.575961: step: 2418/1545, loss: 0.004780248738825321 2023-01-23 11:53:57.459256: step: 2420/1545, loss: 0.030918288975954056 2023-01-23 11:53:58.328506: step: 2422/1545, loss: 0.11034808307886124 2023-01-23 11:53:59.210343: step: 2424/1545, loss: 1.5872400999069214 2023-01-23 11:54:00.078527: step: 2426/1545, loss: 0.21639575064182281 2023-01-23 11:54:00.952146: step: 2428/1545, loss: 0.270201176404953 2023-01-23 11:54:01.821496: step: 2430/1545, loss: 0.12910565733909607 2023-01-23 11:54:02.724574: step: 2432/1545, loss: 0.059641286730766296 2023-01-23 11:54:03.647887: step: 2434/1545, loss: 0.031006595119833946 2023-01-23 11:54:04.521932: step: 2436/1545, loss: 0.15305215120315552 2023-01-23 11:54:05.380745: step: 2438/1545, loss: 0.0498797670006752 2023-01-23 11:54:06.250914: step: 2440/1545, loss: 0.03015715815126896 2023-01-23 11:54:07.173814: step: 2442/1545, loss: 0.6298016309738159 2023-01-23 11:54:08.068796: step: 2444/1545, loss: 0.015893470495939255 2023-01-23 11:54:08.946291: step: 2446/1545, loss: 0.010421953164041042 2023-01-23 11:54:09.895201: step: 2448/1545, loss: 0.15764819085597992 2023-01-23 11:54:10.779569: step: 2450/1545, loss: 0.10755784064531326 2023-01-23 11:54:11.683464: step: 2452/1545, loss: 0.05617932975292206 2023-01-23 11:54:12.558786: step: 2454/1545, loss: 0.29616841673851013 2023-01-23 11:54:13.439137: step: 2456/1545, loss: 0.04122791811823845 2023-01-23 11:54:14.339971: step: 2458/1545, loss: 0.042373914271593094 2023-01-23 11:54:15.216814: step: 2460/1545, loss: 0.0744188129901886 2023-01-23 11:54:16.063634: step: 2462/1545, loss: 0.12218619883060455 2023-01-23 11:54:16.932672: step: 2464/1545, loss: 0.009897255338728428 2023-01-23 11:54:17.828181: step: 2466/1545, loss: 2.251150608062744 2023-01-23 11:54:18.732958: step: 2468/1545, loss: 0.07401526719331741 2023-01-23 11:54:19.599451: step: 2470/1545, loss: 0.39979496598243713 2023-01-23 11:54:20.444894: step: 2472/1545, loss: 0.035611025989055634 2023-01-23 11:54:21.344900: step: 2474/1545, loss: 0.09335949271917343 2023-01-23 11:54:22.224401: step: 2476/1545, loss: 0.34541746973991394 2023-01-23 11:54:23.134511: step: 2478/1545, loss: 0.07436314225196838 2023-01-23 11:54:24.108796: step: 2480/1545, loss: 0.05408798158168793 2023-01-23 11:54:24.983262: step: 2482/1545, loss: 0.14772193133831024 2023-01-23 11:54:25.852603: step: 2484/1545, loss: 0.11803075671195984 2023-01-23 11:54:26.726694: step: 2486/1545, loss: 0.0906863585114479 2023-01-23 11:54:27.617148: step: 2488/1545, loss: 0.03768124431371689 2023-01-23 11:54:28.466514: step: 2490/1545, loss: 0.2623758912086487 2023-01-23 11:54:29.346603: step: 2492/1545, loss: 0.5974736213684082 2023-01-23 11:54:30.240622: step: 2494/1545, loss: 1.1321200132369995 2023-01-23 11:54:31.108029: step: 2496/1545, loss: 0.0789785161614418 2023-01-23 11:54:31.986819: step: 2498/1545, loss: 0.17447564005851746 2023-01-23 11:54:32.875049: step: 2500/1545, loss: 0.3182694911956787 2023-01-23 11:54:33.730963: step: 2502/1545, loss: 0.3044869601726532 2023-01-23 11:54:34.596192: step: 2504/1545, loss: 0.04000750556588173 2023-01-23 11:54:35.473766: step: 2506/1545, loss: 0.01574869453907013 2023-01-23 11:54:36.346426: step: 2508/1545, loss: 0.3900916576385498 2023-01-23 11:54:37.222760: step: 2510/1545, loss: 0.10452277213335037 2023-01-23 11:54:38.053462: step: 2512/1545, loss: 0.26305365562438965 2023-01-23 11:54:38.913236: step: 2514/1545, loss: 0.15450817346572876 2023-01-23 11:54:39.802974: step: 2516/1545, loss: 0.17651155591011047 2023-01-23 11:54:40.651185: step: 2518/1545, loss: 0.3417407274246216 2023-01-23 11:54:41.496834: step: 2520/1545, loss: 0.18276260793209076 2023-01-23 11:54:42.349069: step: 2522/1545, loss: 0.005685196723788977 2023-01-23 11:54:43.192838: step: 2524/1545, loss: 0.012414466589689255 2023-01-23 11:54:44.093638: step: 2526/1545, loss: 0.22121740877628326 2023-01-23 11:54:45.006530: step: 2528/1545, loss: 0.015056133270263672 2023-01-23 11:54:45.864761: step: 2530/1545, loss: 0.0628989040851593 2023-01-23 11:54:46.767876: step: 2532/1545, loss: 0.03486818075180054 2023-01-23 11:54:47.638350: step: 2534/1545, loss: 0.2675532102584839 2023-01-23 11:54:48.584430: step: 2536/1545, loss: 0.012940553948283195 2023-01-23 11:54:49.471428: step: 2538/1545, loss: 0.03599172085523605 2023-01-23 11:54:50.371788: step: 2540/1545, loss: 0.08449085801839828 2023-01-23 11:54:51.280395: step: 2542/1545, loss: 0.39276474714279175 2023-01-23 11:54:52.177385: step: 2544/1545, loss: 0.011320114135742188 2023-01-23 11:54:53.051169: step: 2546/1545, loss: 0.1334676891565323 2023-01-23 11:54:53.982110: step: 2548/1545, loss: 0.397188663482666 2023-01-23 11:54:54.967956: step: 2550/1545, loss: 0.06455187499523163 2023-01-23 11:54:55.853635: step: 2552/1545, loss: 0.08534157276153564 2023-01-23 11:54:56.724996: step: 2554/1545, loss: 0.17299015820026398 2023-01-23 11:54:57.579249: step: 2556/1545, loss: 0.10103726387023926 2023-01-23 11:54:58.481289: step: 2558/1545, loss: 0.08664367347955704 2023-01-23 11:54:59.348771: step: 2560/1545, loss: 0.37765437364578247 2023-01-23 11:55:00.234376: step: 2562/1545, loss: 0.11220381408929825 2023-01-23 11:55:01.140539: step: 2564/1545, loss: 0.14612442255020142 2023-01-23 11:55:02.068053: step: 2566/1545, loss: 0.03133369982242584 2023-01-23 11:55:02.977129: step: 2568/1545, loss: 0.1288585066795349 2023-01-23 11:55:03.829572: step: 2570/1545, loss: 0.09860022366046906 2023-01-23 11:55:04.700974: step: 2572/1545, loss: 0.051146749407052994 2023-01-23 11:55:05.595412: step: 2574/1545, loss: 0.1380731612443924 2023-01-23 11:55:06.500795: step: 2576/1545, loss: 0.05881770700216293 2023-01-23 11:55:07.359387: step: 2578/1545, loss: 0.04689207300543785 2023-01-23 11:55:08.227366: step: 2580/1545, loss: 0.06054191291332245 2023-01-23 11:55:09.109492: step: 2582/1545, loss: 0.15072180330753326 2023-01-23 11:55:09.981751: step: 2584/1545, loss: 0.02133909799158573 2023-01-23 11:55:10.860656: step: 2586/1545, loss: 0.08547599613666534 2023-01-23 11:55:11.759737: step: 2588/1545, loss: 0.0757441520690918 2023-01-23 11:55:12.595733: step: 2590/1545, loss: 0.034994032233953476 2023-01-23 11:55:13.451844: step: 2592/1545, loss: 0.3190513849258423 2023-01-23 11:55:14.313484: step: 2594/1545, loss: 0.09078241139650345 2023-01-23 11:55:15.318147: step: 2596/1545, loss: 0.4525410532951355 2023-01-23 11:55:16.224056: step: 2598/1545, loss: 0.03296938166022301 2023-01-23 11:55:17.099228: step: 2600/1545, loss: 0.2044607549905777 2023-01-23 11:55:17.989355: step: 2602/1545, loss: 0.5933957099914551 2023-01-23 11:55:18.868899: step: 2604/1545, loss: 0.5676665306091309 2023-01-23 11:55:19.769959: step: 2606/1545, loss: 0.014218921773135662 2023-01-23 11:55:20.616390: step: 2608/1545, loss: 0.06851214915513992 2023-01-23 11:55:21.535703: step: 2610/1545, loss: 0.07730571925640106 2023-01-23 11:55:22.399404: step: 2612/1545, loss: 0.025006219744682312 2023-01-23 11:55:23.281376: step: 2614/1545, loss: 0.05231132358312607 2023-01-23 11:55:24.182513: step: 2616/1545, loss: 0.10644152760505676 2023-01-23 11:55:25.025118: step: 2618/1545, loss: 0.06395360082387924 2023-01-23 11:55:25.911657: step: 2620/1545, loss: 0.19715194404125214 2023-01-23 11:55:26.791085: step: 2622/1545, loss: 0.10157027840614319 2023-01-23 11:55:27.709099: step: 2624/1545, loss: 0.04292112961411476 2023-01-23 11:55:28.628019: step: 2626/1545, loss: 0.6087756752967834 2023-01-23 11:55:29.498479: step: 2628/1545, loss: 0.71189284324646 2023-01-23 11:55:30.390162: step: 2630/1545, loss: 0.03174101561307907 2023-01-23 11:55:31.270059: step: 2632/1545, loss: 0.22344137728214264 2023-01-23 11:55:32.198350: step: 2634/1545, loss: 0.042256731539964676 2023-01-23 11:55:33.117514: step: 2636/1545, loss: 0.40419498085975647 2023-01-23 11:55:34.010813: step: 2638/1545, loss: 0.4482432007789612 2023-01-23 11:55:34.899400: step: 2640/1545, loss: 0.03174338862299919 2023-01-23 11:55:35.788626: step: 2642/1545, loss: 0.07032527774572372 2023-01-23 11:55:36.704698: step: 2644/1545, loss: 0.2321559488773346 2023-01-23 11:55:37.608189: step: 2646/1545, loss: 0.12633134424686432 2023-01-23 11:55:38.456058: step: 2648/1545, loss: 0.244013249874115 2023-01-23 11:55:39.313340: step: 2650/1545, loss: 0.11653508245944977 2023-01-23 11:55:40.216282: step: 2652/1545, loss: 0.19962474703788757 2023-01-23 11:55:41.096937: step: 2654/1545, loss: 0.04607456550002098 2023-01-23 11:55:41.967133: step: 2656/1545, loss: 0.008144581690430641 2023-01-23 11:55:42.891803: step: 2658/1545, loss: 0.1947455257177353 2023-01-23 11:55:43.772874: step: 2660/1545, loss: 0.026318829506635666 2023-01-23 11:55:44.629487: step: 2662/1545, loss: 0.029388708993792534 2023-01-23 11:55:45.536007: step: 2664/1545, loss: 0.057864394038915634 2023-01-23 11:55:46.435260: step: 2666/1545, loss: 0.07005845755338669 2023-01-23 11:55:47.306259: step: 2668/1545, loss: 0.037299126386642456 2023-01-23 11:55:48.189920: step: 2670/1545, loss: 0.13204079866409302 2023-01-23 11:55:49.034740: step: 2672/1545, loss: 0.44853416085243225 2023-01-23 11:55:49.888308: step: 2674/1545, loss: 0.10183632373809814 2023-01-23 11:55:50.779592: step: 2676/1545, loss: 0.03885606676340103 2023-01-23 11:55:51.690479: step: 2678/1545, loss: 0.24534697830677032 2023-01-23 11:55:52.601491: step: 2680/1545, loss: 0.1946764886379242 2023-01-23 11:55:53.487333: step: 2682/1545, loss: 0.02442789264023304 2023-01-23 11:55:54.406807: step: 2684/1545, loss: 0.052983492612838745 2023-01-23 11:55:55.330093: step: 2686/1545, loss: 0.08910101652145386 2023-01-23 11:55:56.201606: step: 2688/1545, loss: 0.06512413173913956 2023-01-23 11:55:57.152385: step: 2690/1545, loss: 0.09062376618385315 2023-01-23 11:55:58.023299: step: 2692/1545, loss: 2.5079054832458496 2023-01-23 11:55:58.911282: step: 2694/1545, loss: 0.07333024591207504 2023-01-23 11:55:59.807536: step: 2696/1545, loss: 0.11894141137599945 2023-01-23 11:56:00.689604: step: 2698/1545, loss: 0.0167715884745121 2023-01-23 11:56:01.562385: step: 2700/1545, loss: 0.23088088631629944 2023-01-23 11:56:02.402390: step: 2702/1545, loss: 0.014344858005642891 2023-01-23 11:56:03.265528: step: 2704/1545, loss: 0.07194594293832779 2023-01-23 11:56:04.175602: step: 2706/1545, loss: 0.03274448215961456 2023-01-23 11:56:05.053628: step: 2708/1545, loss: 0.026555350050330162 2023-01-23 11:56:05.961378: step: 2710/1545, loss: 0.05154778063297272 2023-01-23 11:56:06.836052: step: 2712/1545, loss: 0.15747229754924774 2023-01-23 11:56:07.754399: step: 2714/1545, loss: 0.1431109607219696 2023-01-23 11:56:08.626354: step: 2716/1545, loss: 0.4349004328250885 2023-01-23 11:56:09.486058: step: 2718/1545, loss: 0.012313123792409897 2023-01-23 11:56:10.354577: step: 2720/1545, loss: 0.022824570536613464 2023-01-23 11:56:11.365014: step: 2722/1545, loss: 0.09766329079866409 2023-01-23 11:56:12.259127: step: 2724/1545, loss: 0.09180835634469986 2023-01-23 11:56:13.124819: step: 2726/1545, loss: 0.10898464918136597 2023-01-23 11:56:14.009713: step: 2728/1545, loss: 0.13533128798007965 2023-01-23 11:56:14.908895: step: 2730/1545, loss: 0.2398664355278015 2023-01-23 11:56:15.776542: step: 2732/1545, loss: 0.0027235993184149265 2023-01-23 11:56:16.666407: step: 2734/1545, loss: 0.03296738490462303 2023-01-23 11:56:17.541182: step: 2736/1545, loss: 0.2811059057712555 2023-01-23 11:56:18.437657: step: 2738/1545, loss: 0.06559780985116959 2023-01-23 11:56:19.381672: step: 2740/1545, loss: 0.06996332108974457 2023-01-23 11:56:20.234838: step: 2742/1545, loss: 0.12448038160800934 2023-01-23 11:56:21.091791: step: 2744/1545, loss: 0.01260080374777317 2023-01-23 11:56:21.994659: step: 2746/1545, loss: 0.06195181980729103 2023-01-23 11:56:22.891793: step: 2748/1545, loss: 0.11176984012126923 2023-01-23 11:56:23.807658: step: 2750/1545, loss: 0.07115835696458817 2023-01-23 11:56:24.699362: step: 2752/1545, loss: 0.047373753041028976 2023-01-23 11:56:25.609788: step: 2754/1545, loss: 0.020211711525917053 2023-01-23 11:56:26.519955: step: 2756/1545, loss: 0.013724847696721554 2023-01-23 11:56:27.376310: step: 2758/1545, loss: 0.05936983600258827 2023-01-23 11:56:28.218932: step: 2760/1545, loss: 0.3885411024093628 2023-01-23 11:56:29.149193: step: 2762/1545, loss: 0.23803448677062988 2023-01-23 11:56:30.000774: step: 2764/1545, loss: 0.07508194446563721 2023-01-23 11:56:30.967630: step: 2766/1545, loss: 0.05815362185239792 2023-01-23 11:56:31.860855: step: 2768/1545, loss: 0.046067263931035995 2023-01-23 11:56:32.791124: step: 2770/1545, loss: 0.04766946658492088 2023-01-23 11:56:33.712874: step: 2772/1545, loss: 0.20594295859336853 2023-01-23 11:56:34.595715: step: 2774/1545, loss: 0.1734422892332077 2023-01-23 11:56:35.514441: step: 2776/1545, loss: 0.06689197570085526 2023-01-23 11:56:36.415424: step: 2778/1545, loss: 0.3438919186592102 2023-01-23 11:56:37.281893: step: 2780/1545, loss: 0.7308434844017029 2023-01-23 11:56:38.119707: step: 2782/1545, loss: 0.007390038575977087 2023-01-23 11:56:39.001614: step: 2784/1545, loss: 0.1754058599472046 2023-01-23 11:56:39.878434: step: 2786/1545, loss: 0.22462770342826843 2023-01-23 11:56:40.731516: step: 2788/1545, loss: 0.04382097348570824 2023-01-23 11:56:41.625383: step: 2790/1545, loss: 0.40198230743408203 2023-01-23 11:56:42.503372: step: 2792/1545, loss: 0.15188062191009521 2023-01-23 11:56:43.371097: step: 2794/1545, loss: 0.0713474228978157 2023-01-23 11:56:44.244841: step: 2796/1545, loss: 0.12150763720273972 2023-01-23 11:56:45.144082: step: 2798/1545, loss: 0.1314534991979599 2023-01-23 11:56:46.030896: step: 2800/1545, loss: 0.029994085431098938 2023-01-23 11:56:46.886476: step: 2802/1545, loss: 0.009963992983102798 2023-01-23 11:56:47.745890: step: 2804/1545, loss: 0.0275906752794981 2023-01-23 11:56:48.632960: step: 2806/1545, loss: 0.8761850595474243 2023-01-23 11:56:49.507071: step: 2808/1545, loss: 0.12047252058982849 2023-01-23 11:56:50.380646: step: 2810/1545, loss: 0.010578115470707417 2023-01-23 11:56:51.264054: step: 2812/1545, loss: 0.36278218030929565 2023-01-23 11:56:52.168167: step: 2814/1545, loss: 0.14439323544502258 2023-01-23 11:56:53.067616: step: 2816/1545, loss: 0.09101508557796478 2023-01-23 11:56:53.943573: step: 2818/1545, loss: 0.007119865622371435 2023-01-23 11:56:54.805820: step: 2820/1545, loss: 0.024107616394758224 2023-01-23 11:56:55.724806: step: 2822/1545, loss: 0.0072586373426020145 2023-01-23 11:56:56.579710: step: 2824/1545, loss: 0.11517880111932755 2023-01-23 11:56:57.444056: step: 2826/1545, loss: 0.28269222378730774 2023-01-23 11:56:58.325531: step: 2828/1545, loss: 0.05781544744968414 2023-01-23 11:56:59.231574: step: 2830/1545, loss: 0.007486548274755478 2023-01-23 11:57:00.082561: step: 2832/1545, loss: 0.19946222007274628 2023-01-23 11:57:00.941324: step: 2834/1545, loss: 0.38750189542770386 2023-01-23 11:57:01.798447: step: 2836/1545, loss: 0.02293379232287407 2023-01-23 11:57:02.712947: step: 2838/1545, loss: 0.02111176773905754 2023-01-23 11:57:03.590015: step: 2840/1545, loss: 0.06344122439622879 2023-01-23 11:57:04.464584: step: 2842/1545, loss: 0.08132415264844894 2023-01-23 11:57:05.337460: step: 2844/1545, loss: 0.12222611159086227 2023-01-23 11:57:06.219231: step: 2846/1545, loss: 0.04226146638393402 2023-01-23 11:57:07.152934: step: 2848/1545, loss: 0.032940030097961426 2023-01-23 11:57:08.028105: step: 2850/1545, loss: 0.011330089531838894 2023-01-23 11:57:08.949823: step: 2852/1545, loss: 0.4919010400772095 2023-01-23 11:57:09.866845: step: 2854/1545, loss: 0.43193528056144714 2023-01-23 11:57:10.798594: step: 2856/1545, loss: 0.08695199340581894 2023-01-23 11:57:11.663495: step: 2858/1545, loss: 0.01753365620970726 2023-01-23 11:57:12.530115: step: 2860/1545, loss: 0.4571155905723572 2023-01-23 11:57:13.408496: step: 2862/1545, loss: 0.05452701076865196 2023-01-23 11:57:14.311464: step: 2864/1545, loss: 0.02063305675983429 2023-01-23 11:57:15.165836: step: 2866/1545, loss: 0.03638027608394623 2023-01-23 11:57:16.066697: step: 2868/1545, loss: 0.5360283851623535 2023-01-23 11:57:17.019928: step: 2870/1545, loss: 0.045742228627204895 2023-01-23 11:57:17.867370: step: 2872/1545, loss: 0.14079146087169647 2023-01-23 11:57:18.745810: step: 2874/1545, loss: 0.4145126938819885 2023-01-23 11:57:19.619600: step: 2876/1545, loss: 0.07316887378692627 2023-01-23 11:57:20.526613: step: 2878/1545, loss: 0.03268082067370415 2023-01-23 11:57:21.434789: step: 2880/1545, loss: 0.07337770611047745 2023-01-23 11:57:22.332794: step: 2882/1545, loss: 0.013959735631942749 2023-01-23 11:57:23.185169: step: 2884/1545, loss: 0.12603263556957245 2023-01-23 11:57:24.071259: step: 2886/1545, loss: 0.030935347080230713 2023-01-23 11:57:24.971900: step: 2888/1545, loss: 0.19935065507888794 2023-01-23 11:57:25.901699: step: 2890/1545, loss: 0.05766339227557182 2023-01-23 11:57:26.771860: step: 2892/1545, loss: 0.11781742423772812 2023-01-23 11:57:27.621359: step: 2894/1545, loss: 0.19226746261119843 2023-01-23 11:57:28.502439: step: 2896/1545, loss: 0.0519200935959816 2023-01-23 11:57:29.463514: step: 2898/1545, loss: 0.3164742887020111 2023-01-23 11:57:30.356524: step: 2900/1545, loss: 0.09180410951375961 2023-01-23 11:57:31.250019: step: 2902/1545, loss: 0.4167798161506653 2023-01-23 11:57:32.116631: step: 2904/1545, loss: 0.0733208954334259 2023-01-23 11:57:33.108724: step: 2906/1545, loss: 0.03793787583708763 2023-01-23 11:57:33.944535: step: 2908/1545, loss: 0.092568539083004 2023-01-23 11:57:34.814951: step: 2910/1545, loss: 0.24592292308807373 2023-01-23 11:57:35.698541: step: 2912/1545, loss: 0.15034261345863342 2023-01-23 11:57:36.585182: step: 2914/1545, loss: 0.3239230811595917 2023-01-23 11:57:37.450982: step: 2916/1545, loss: 0.42816027998924255 2023-01-23 11:57:38.349546: step: 2918/1545, loss: 0.20548664033412933 2023-01-23 11:57:39.245802: step: 2920/1545, loss: 0.3175826072692871 2023-01-23 11:57:40.174767: step: 2922/1545, loss: 0.14891870319843292 2023-01-23 11:57:41.062035: step: 2924/1545, loss: 0.009426447562873363 2023-01-23 11:57:41.949025: step: 2926/1545, loss: 1.0754523277282715 2023-01-23 11:57:42.829335: step: 2928/1545, loss: 0.06605208665132523 2023-01-23 11:57:43.708820: step: 2930/1545, loss: 0.030706243589520454 2023-01-23 11:57:44.633413: step: 2932/1545, loss: 0.021418506279587746 2023-01-23 11:57:45.521457: step: 2934/1545, loss: 0.043718304485082626 2023-01-23 11:57:46.381673: step: 2936/1545, loss: 0.00613532867282629 2023-01-23 11:57:47.261531: step: 2938/1545, loss: 0.07216400653123856 2023-01-23 11:57:48.164776: step: 2940/1545, loss: 0.24314765632152557 2023-01-23 11:57:49.060592: step: 2942/1545, loss: 0.013404019176959991 2023-01-23 11:57:49.943223: step: 2944/1545, loss: 0.02371581643819809 2023-01-23 11:57:50.812090: step: 2946/1545, loss: 0.03243868425488472 2023-01-23 11:57:51.654145: step: 2948/1545, loss: 0.05991656705737114 2023-01-23 11:57:52.494177: step: 2950/1545, loss: 0.06636186689138412 2023-01-23 11:57:53.353140: step: 2952/1545, loss: 0.053642790764570236 2023-01-23 11:57:54.267790: step: 2954/1545, loss: 0.3712708652019501 2023-01-23 11:57:55.191497: step: 2956/1545, loss: 0.011774597689509392 2023-01-23 11:57:56.073477: step: 2958/1545, loss: 0.2554360628128052 2023-01-23 11:57:56.972776: step: 2960/1545, loss: 0.06801389902830124 2023-01-23 11:57:57.894000: step: 2962/1545, loss: 0.04618604853749275 2023-01-23 11:57:58.766166: step: 2964/1545, loss: 0.17818965017795563 2023-01-23 11:57:59.670588: step: 2966/1545, loss: 0.3072521984577179 2023-01-23 11:58:00.622546: step: 2968/1545, loss: 0.8680093288421631 2023-01-23 11:58:01.521075: step: 2970/1545, loss: 0.0374913327395916 2023-01-23 11:58:02.402293: step: 2972/1545, loss: 0.0939754769206047 2023-01-23 11:58:03.306464: step: 2974/1545, loss: 0.08872532844543457 2023-01-23 11:58:04.171765: step: 2976/1545, loss: 0.044707901775836945 2023-01-23 11:58:05.018002: step: 2978/1545, loss: 0.019881699234247208 2023-01-23 11:58:05.964673: step: 2980/1545, loss: 0.05800957232713699 2023-01-23 11:58:06.808705: step: 2982/1545, loss: 0.1686992049217224 2023-01-23 11:58:07.743381: step: 2984/1545, loss: 0.012044863775372505 2023-01-23 11:58:08.695591: step: 2986/1545, loss: 0.07517586648464203 2023-01-23 11:58:09.530388: step: 2988/1545, loss: 0.004129424691200256 2023-01-23 11:58:10.420819: step: 2990/1545, loss: 0.16868042945861816 2023-01-23 11:58:11.269988: step: 2992/1545, loss: 0.13683991134166718 2023-01-23 11:58:12.141837: step: 2994/1545, loss: 0.028261873871088028 2023-01-23 11:58:13.024978: step: 2996/1545, loss: 0.04789767786860466 2023-01-23 11:58:13.890533: step: 2998/1545, loss: 0.04529837891459465 2023-01-23 11:58:14.781050: step: 3000/1545, loss: 0.16784201562404633 2023-01-23 11:58:15.620473: step: 3002/1545, loss: 0.08653553575277328 2023-01-23 11:58:16.436818: step: 3004/1545, loss: 0.03180668503046036 2023-01-23 11:58:17.300014: step: 3006/1545, loss: 0.26633861660957336 2023-01-23 11:58:18.175652: step: 3008/1545, loss: 0.15563273429870605 2023-01-23 11:58:19.031496: step: 3010/1545, loss: 0.21512001752853394 2023-01-23 11:58:19.889265: step: 3012/1545, loss: 0.2719022333621979 2023-01-23 11:58:20.793440: step: 3014/1545, loss: 0.08097556233406067 2023-01-23 11:58:21.720788: step: 3016/1545, loss: 0.1065378412604332 2023-01-23 11:58:22.588371: step: 3018/1545, loss: 0.07787059247493744 2023-01-23 11:58:23.440557: step: 3020/1545, loss: 0.37924227118492126 2023-01-23 11:58:24.371794: step: 3022/1545, loss: 0.05881712958216667 2023-01-23 11:58:25.236282: step: 3024/1545, loss: 0.2543192505836487 2023-01-23 11:58:26.104931: step: 3026/1545, loss: 0.03617478162050247 2023-01-23 11:58:27.025351: step: 3028/1545, loss: 0.023419398814439774 2023-01-23 11:58:27.954544: step: 3030/1545, loss: 0.07478725165128708 2023-01-23 11:58:28.868001: step: 3032/1545, loss: 0.03961937129497528 2023-01-23 11:58:29.791924: step: 3034/1545, loss: 0.026681574061512947 2023-01-23 11:58:30.655838: step: 3036/1545, loss: 0.07988888025283813 2023-01-23 11:58:31.499060: step: 3038/1545, loss: 0.034100454300642014 2023-01-23 11:58:32.404864: step: 3040/1545, loss: 0.03327617421746254 2023-01-23 11:58:33.281612: step: 3042/1545, loss: 0.051018502563238144 2023-01-23 11:58:34.131495: step: 3044/1545, loss: 0.6488561034202576 2023-01-23 11:58:35.049850: step: 3046/1545, loss: 0.2332966923713684 2023-01-23 11:58:35.928278: step: 3048/1545, loss: 0.18026141822338104 2023-01-23 11:58:36.795268: step: 3050/1545, loss: 0.13409605622291565 2023-01-23 11:58:37.650569: step: 3052/1545, loss: 0.09567118436098099 2023-01-23 11:58:38.501629: step: 3054/1545, loss: 0.01010538823902607 2023-01-23 11:58:39.366463: step: 3056/1545, loss: 0.10505056381225586 2023-01-23 11:58:40.266510: step: 3058/1545, loss: 0.014099744148552418 2023-01-23 11:58:41.217086: step: 3060/1545, loss: 0.2893584966659546 2023-01-23 11:58:42.106887: step: 3062/1545, loss: 0.025309910997748375 2023-01-23 11:58:43.002657: step: 3064/1545, loss: 0.4685612618923187 2023-01-23 11:58:43.879356: step: 3066/1545, loss: 0.3257543742656708 2023-01-23 11:58:44.792651: step: 3068/1545, loss: 0.144112229347229 2023-01-23 11:58:45.685522: step: 3070/1545, loss: 0.7146734595298767 2023-01-23 11:58:46.564332: step: 3072/1545, loss: 0.005441037006676197 2023-01-23 11:58:47.386760: step: 3074/1545, loss: 0.3792535662651062 2023-01-23 11:58:48.292153: step: 3076/1545, loss: 0.30328691005706787 2023-01-23 11:58:49.158020: step: 3078/1545, loss: 0.17781934142112732 2023-01-23 11:58:50.037088: step: 3080/1545, loss: 0.5631574392318726 2023-01-23 11:58:50.913925: step: 3082/1545, loss: 0.05015713721513748 2023-01-23 11:58:51.816735: step: 3084/1545, loss: 0.2479032427072525 2023-01-23 11:58:52.739928: step: 3086/1545, loss: 0.7046509981155396 2023-01-23 11:58:53.622221: step: 3088/1545, loss: 0.019892292097210884 2023-01-23 11:58:54.514589: step: 3090/1545, loss: 0.0974901095032692 ================================================== Loss: 0.183 -------------------- Dev Chinese: {'event': {'p': 0.608505997818975, 'r': 0.7430093209054593, 'f1': 0.6690647482014388}, 'argument': {'p': 0.6648547066556879, 'r': 0.6419630026840101, 'f1': 0.6532083561202113}, 'combined': 0.43703868431064496, 'epoch': 14} Test Chinese: {'event': {'p': 0.6451440768409819, 'r': 0.7730179028132992, 'f1': 0.7033158813263525}, 'argument': {'p': 0.7171363992606675, 'r': 0.7081003163375663, 'f1': 0.7125897131558447}, 'combined': 0.5011756621322957, 'epoch': 14} Dev Korean: {'event': {'p': 0.6192560175054704, 'r': 0.7536617842876165, 'f1': 0.6798798798798799}, 'argument': {'p': 0.6632184815074122, 'r': 0.6433020105912738, 'f1': 0.6531084436795553}, 'combined': 0.44403529023739136, 'epoch': 14} Test Korean: {'event': {'p': 0.6343915343915344, 'r': 0.7666240409207161, 'f1': 0.694267515923567}, 'argument': {'p': 0.7134384328444346, 'r': 0.7077112894615091, 'f1': 0.7105633211403983}, 'combined': 0.4933210318745441, 'epoch': 14} Dev Russian: {'event': {'p': 0.5787401574803149, 'r': 0.7829560585885486, 'f1': 0.66553480475382}, 'argument': {'p': 0.6663333620967928, 'r': 0.6491499802662165, 'f1': 0.6576294429982861}, 'combined': 0.4376752829462277, 'epoch': 14} Test Russian: {'event': {'p': 0.6307922272047832, 'r': 0.809462915601023, 'f1': 0.7090450854102492}, 'argument': {'p': 0.7232622949848798, 'r': 0.719740793174092, 'f1': 0.7214972471465462}, 'combined': 0.5115740772262826, 'epoch': 14} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6799915038232794, 'r': 0.6013148009015777, 'f1': 0.6382376395534289}, 'combined': 0.45450256150016904, 'epoch': 14} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6992753623188407, 'r': 0.44063926940639275, 'f1': 0.5406162464985995}, 'combined': 0.34144183989385235, 'epoch': 14} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.6076806456298288, 'r': 0.5968292055292962, 'f1': 0.6022060452187493}, 'combined': 0.3354058986028477, 'epoch': 14} New best korean model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6192560175054704, 'r': 0.7536617842876165, 'f1': 0.6798798798798799}, 'argument': {'p': 0.6632184815074122, 'r': 0.6433020105912738, 'f1': 0.6531084436795553}, 'combined': 0.44403529023739136, 'epoch': 14} Test for Korean: {'event': {'p': 0.6343915343915344, 'r': 0.7666240409207161, 'f1': 0.694267515923567}, 'argument': {'p': 0.7134384328444346, 'r': 0.7077112894615091, 'f1': 0.7105633211403983}, 'combined': 0.4933210318745441, 'epoch': 14} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6992753623188407, 'r': 0.44063926940639275, 'f1': 0.5406162464985995}, 'combined': 0.34144183989385235, 'epoch': 14} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 15 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 12:04:15.546604: step: 2/1545, loss: 0.0013476546155288815 2023-01-23 12:04:16.401534: step: 4/1545, loss: 0.037594765424728394 2023-01-23 12:04:17.331981: step: 6/1545, loss: 0.059747036546468735 2023-01-23 12:04:18.265098: step: 8/1545, loss: 0.02641235664486885 2023-01-23 12:04:19.146740: step: 10/1545, loss: 0.30819520354270935 2023-01-23 12:04:20.026064: step: 12/1545, loss: 0.11620435118675232 2023-01-23 12:04:20.925913: step: 14/1545, loss: 0.30587926506996155 2023-01-23 12:04:21.913228: step: 16/1545, loss: 0.03525476157665253 2023-01-23 12:04:22.756524: step: 18/1545, loss: 0.5916844010353088 2023-01-23 12:04:23.660105: step: 20/1545, loss: 0.0142198596149683 2023-01-23 12:04:24.576643: step: 22/1545, loss: 0.17853248119354248 2023-01-23 12:04:25.504607: step: 24/1545, loss: 0.04333733394742012 2023-01-23 12:04:26.399590: step: 26/1545, loss: 0.10769418627023697 2023-01-23 12:04:27.285393: step: 28/1545, loss: 0.04826340079307556 2023-01-23 12:04:28.176174: step: 30/1545, loss: 0.11701168864965439 2023-01-23 12:04:29.031828: step: 32/1545, loss: 0.19048023223876953 2023-01-23 12:04:29.934459: step: 34/1545, loss: 0.30793359875679016 2023-01-23 12:04:30.815797: step: 36/1545, loss: 0.05701754614710808 2023-01-23 12:04:31.717332: step: 38/1545, loss: 0.12450957298278809 2023-01-23 12:04:32.622217: step: 40/1545, loss: 0.01039912924170494 2023-01-23 12:04:33.636529: step: 42/1545, loss: 0.07111277431249619 2023-01-23 12:04:34.523972: step: 44/1545, loss: 0.17385436594486237 2023-01-23 12:04:35.409880: step: 46/1545, loss: 0.04323463886976242 2023-01-23 12:04:36.381420: step: 48/1545, loss: 0.25857624411582947 2023-01-23 12:04:37.235240: step: 50/1545, loss: 0.030139409005641937 2023-01-23 12:04:38.109059: step: 52/1545, loss: 0.004791277926415205 2023-01-23 12:04:38.978195: step: 54/1545, loss: 0.12290073931217194 2023-01-23 12:04:39.896518: step: 56/1545, loss: 0.15375317633152008 2023-01-23 12:04:40.767219: step: 58/1545, loss: 0.10047002136707306 2023-01-23 12:04:41.615358: step: 60/1545, loss: 0.026745013892650604 2023-01-23 12:04:42.506373: step: 62/1545, loss: 0.9714770317077637 2023-01-23 12:04:43.417303: step: 64/1545, loss: 0.012349214404821396 2023-01-23 12:04:44.294675: step: 66/1545, loss: 0.11085543781518936 2023-01-23 12:04:45.199330: step: 68/1545, loss: 0.6854000687599182 2023-01-23 12:04:46.112769: step: 70/1545, loss: 0.555492639541626 2023-01-23 12:04:46.984192: step: 72/1545, loss: 0.02037198841571808 2023-01-23 12:04:47.900614: step: 74/1545, loss: 0.09109040349721909 2023-01-23 12:04:48.754492: step: 76/1545, loss: 0.14548660814762115 2023-01-23 12:04:49.706238: step: 78/1545, loss: 0.14222411811351776 2023-01-23 12:04:50.627417: step: 80/1545, loss: 0.3307708203792572 2023-01-23 12:04:51.544899: step: 82/1545, loss: 0.14066289365291595 2023-01-23 12:04:52.447823: step: 84/1545, loss: 0.20529749989509583 2023-01-23 12:04:53.288487: step: 86/1545, loss: 0.007173202931880951 2023-01-23 12:04:54.156742: step: 88/1545, loss: 0.08161193877458572 2023-01-23 12:04:55.004782: step: 90/1545, loss: 0.03621673211455345 2023-01-23 12:04:55.895718: step: 92/1545, loss: 0.18485336005687714 2023-01-23 12:04:56.822256: step: 94/1545, loss: 0.5345950722694397 2023-01-23 12:04:57.680776: step: 96/1545, loss: 0.11254468560218811 2023-01-23 12:04:58.556717: step: 98/1545, loss: 0.1320042610168457 2023-01-23 12:04:59.457849: step: 100/1545, loss: 0.022658443078398705 2023-01-23 12:05:00.320139: step: 102/1545, loss: 0.1225116103887558 2023-01-23 12:05:01.178843: step: 104/1545, loss: 0.011236735619604588 2023-01-23 12:05:02.074192: step: 106/1545, loss: 0.16182619333267212 2023-01-23 12:05:02.955080: step: 108/1545, loss: 0.016222387552261353 2023-01-23 12:05:03.813196: step: 110/1545, loss: 0.0072084651328623295 2023-01-23 12:05:04.687713: step: 112/1545, loss: 0.05454745516180992 2023-01-23 12:05:05.607970: step: 114/1545, loss: 0.04537610709667206 2023-01-23 12:05:06.466351: step: 116/1545, loss: 0.005549905821681023 2023-01-23 12:05:07.376833: step: 118/1545, loss: 0.005535791162401438 2023-01-23 12:05:08.284578: step: 120/1545, loss: 0.03176992014050484 2023-01-23 12:05:09.169372: step: 122/1545, loss: 0.035644982010126114 2023-01-23 12:05:10.045246: step: 124/1545, loss: 0.028849750757217407 2023-01-23 12:05:10.957237: step: 126/1545, loss: 0.006222320720553398 2023-01-23 12:05:11.853141: step: 128/1545, loss: 0.02854001708328724 2023-01-23 12:05:12.766848: step: 130/1545, loss: 0.10420220345258713 2023-01-23 12:05:13.635320: step: 132/1545, loss: 0.02538367547094822 2023-01-23 12:05:14.498761: step: 134/1545, loss: 0.20361429452896118 2023-01-23 12:05:15.342015: step: 136/1545, loss: 0.2710818648338318 2023-01-23 12:05:16.212011: step: 138/1545, loss: 0.03556552156805992 2023-01-23 12:05:17.088316: step: 140/1545, loss: 0.7823125720024109 2023-01-23 12:05:18.008453: step: 142/1545, loss: 0.3482443690299988 2023-01-23 12:05:18.948475: step: 144/1545, loss: 0.18373733758926392 2023-01-23 12:05:19.827405: step: 146/1545, loss: 0.029545985162258148 2023-01-23 12:05:20.744526: step: 148/1545, loss: 0.007111165206879377 2023-01-23 12:05:21.592288: step: 150/1545, loss: 0.02773587964475155 2023-01-23 12:05:22.435283: step: 152/1545, loss: 0.002529778750613332 2023-01-23 12:05:23.330004: step: 154/1545, loss: 0.35706767439842224 2023-01-23 12:05:24.187484: step: 156/1545, loss: 0.06615418940782547 2023-01-23 12:05:25.071433: step: 158/1545, loss: 0.014854876324534416 2023-01-23 12:05:25.995202: step: 160/1545, loss: 0.010798994451761246 2023-01-23 12:05:26.845390: step: 162/1545, loss: 0.15419340133666992 2023-01-23 12:05:27.748470: step: 164/1545, loss: 0.020786333829164505 2023-01-23 12:05:28.581341: step: 166/1545, loss: 0.0006727450527250767 2023-01-23 12:05:29.492869: step: 168/1545, loss: 0.021239418536424637 2023-01-23 12:05:30.382400: step: 170/1545, loss: 0.06126372888684273 2023-01-23 12:05:31.245769: step: 172/1545, loss: 0.018161730840802193 2023-01-23 12:05:32.133777: step: 174/1545, loss: 0.050090182572603226 2023-01-23 12:05:32.964677: step: 176/1545, loss: 0.004781062249094248 2023-01-23 12:05:33.833801: step: 178/1545, loss: 0.0677650049328804 2023-01-23 12:05:34.714788: step: 180/1545, loss: 0.028370600193738937 2023-01-23 12:05:35.582524: step: 182/1545, loss: 0.00814344547688961 2023-01-23 12:05:36.481458: step: 184/1545, loss: 0.2563069760799408 2023-01-23 12:05:37.368962: step: 186/1545, loss: 0.019516440108418465 2023-01-23 12:05:38.244695: step: 188/1545, loss: 0.0020019442308694124 2023-01-23 12:05:39.220238: step: 190/1545, loss: 0.2582069933414459 2023-01-23 12:05:40.122993: step: 192/1545, loss: 0.26235121488571167 2023-01-23 12:05:41.004883: step: 194/1545, loss: 0.7715438604354858 2023-01-23 12:05:41.980953: step: 196/1545, loss: 0.7317526340484619 2023-01-23 12:05:42.856290: step: 198/1545, loss: 0.040506165474653244 2023-01-23 12:05:43.716153: step: 200/1545, loss: 0.0415261946618557 2023-01-23 12:05:44.553966: step: 202/1545, loss: 0.010032976046204567 2023-01-23 12:05:45.419884: step: 204/1545, loss: 0.04024891555309296 2023-01-23 12:05:46.331373: step: 206/1545, loss: 0.026751123368740082 2023-01-23 12:05:47.176665: step: 208/1545, loss: 0.01861075684428215 2023-01-23 12:05:48.019474: step: 210/1545, loss: 0.2351425588130951 2023-01-23 12:05:48.887424: step: 212/1545, loss: 0.35727745294570923 2023-01-23 12:05:49.753992: step: 214/1545, loss: 0.045907095074653625 2023-01-23 12:05:50.625450: step: 216/1545, loss: 0.018467780202627182 2023-01-23 12:05:51.506966: step: 218/1545, loss: 0.0620904378592968 2023-01-23 12:05:52.402981: step: 220/1545, loss: 0.0038725989870727062 2023-01-23 12:05:53.362028: step: 222/1545, loss: 0.08811628073453903 2023-01-23 12:05:54.218146: step: 224/1545, loss: 0.1743784099817276 2023-01-23 12:05:55.131158: step: 226/1545, loss: 0.015612494200468063 2023-01-23 12:05:56.039801: step: 228/1545, loss: 0.06488323211669922 2023-01-23 12:05:56.908857: step: 230/1545, loss: 0.080943264067173 2023-01-23 12:05:57.797343: step: 232/1545, loss: 0.030300326645374298 2023-01-23 12:05:58.702512: step: 234/1545, loss: 0.02654270827770233 2023-01-23 12:05:59.568187: step: 236/1545, loss: 0.2559153735637665 2023-01-23 12:06:00.422875: step: 238/1545, loss: 0.02702377177774906 2023-01-23 12:06:01.313814: step: 240/1545, loss: 0.27458491921424866 2023-01-23 12:06:02.208362: step: 242/1545, loss: 0.18893614411354065 2023-01-23 12:06:03.068569: step: 244/1545, loss: 0.033335812389850616 2023-01-23 12:06:03.977864: step: 246/1545, loss: 0.018112756311893463 2023-01-23 12:06:04.854890: step: 248/1545, loss: 0.235935240983963 2023-01-23 12:06:05.738692: step: 250/1545, loss: 0.301260381937027 2023-01-23 12:06:06.621119: step: 252/1545, loss: 0.1841086596250534 2023-01-23 12:06:07.504921: step: 254/1545, loss: 0.09499021619558334 2023-01-23 12:06:08.361670: step: 256/1545, loss: 0.05153575539588928 2023-01-23 12:06:09.326256: step: 258/1545, loss: 0.3669170141220093 2023-01-23 12:06:10.256183: step: 260/1545, loss: 0.14766502380371094 2023-01-23 12:06:11.169698: step: 262/1545, loss: 0.1674768179655075 2023-01-23 12:06:12.071958: step: 264/1545, loss: 0.00587266031652689 2023-01-23 12:06:12.970039: step: 266/1545, loss: 0.022493509575724602 2023-01-23 12:06:13.833520: step: 268/1545, loss: 0.06001432612538338 2023-01-23 12:06:14.759986: step: 270/1545, loss: 0.1360822319984436 2023-01-23 12:06:15.672665: step: 272/1545, loss: 1.784605622291565 2023-01-23 12:06:16.564999: step: 274/1545, loss: 0.1363440752029419 2023-01-23 12:06:17.533809: step: 276/1545, loss: 0.03377304971218109 2023-01-23 12:06:18.431642: step: 278/1545, loss: 0.08284812420606613 2023-01-23 12:06:19.383948: step: 280/1545, loss: 0.005678198765963316 2023-01-23 12:06:20.277129: step: 282/1545, loss: 0.5841253399848938 2023-01-23 12:06:21.148297: step: 284/1545, loss: 0.007642976939678192 2023-01-23 12:06:22.037476: step: 286/1545, loss: 0.16287535429000854 2023-01-23 12:06:22.958860: step: 288/1545, loss: 0.003710915334522724 2023-01-23 12:06:23.861197: step: 290/1545, loss: 0.07295409590005875 2023-01-23 12:06:24.768878: step: 292/1545, loss: 0.07779514044523239 2023-01-23 12:06:25.647428: step: 294/1545, loss: 0.21389378607273102 2023-01-23 12:06:26.501658: step: 296/1545, loss: 0.011982009746134281 2023-01-23 12:06:27.362794: step: 298/1545, loss: 2.1511082649230957 2023-01-23 12:06:28.283738: step: 300/1545, loss: 0.04191197454929352 2023-01-23 12:06:29.152992: step: 302/1545, loss: 0.0024197916500270367 2023-01-23 12:06:30.050070: step: 304/1545, loss: 0.10736977308988571 2023-01-23 12:06:30.888246: step: 306/1545, loss: 0.24275749921798706 2023-01-23 12:06:31.749030: step: 308/1545, loss: 0.15399238467216492 2023-01-23 12:06:32.632938: step: 310/1545, loss: 0.3233316242694855 2023-01-23 12:06:33.528852: step: 312/1545, loss: 0.020227858796715736 2023-01-23 12:06:34.402418: step: 314/1545, loss: 0.04871093109250069 2023-01-23 12:06:35.281649: step: 316/1545, loss: 0.01992856152355671 2023-01-23 12:06:36.222966: step: 318/1545, loss: 0.1253679245710373 2023-01-23 12:06:37.065612: step: 320/1545, loss: 0.009608584456145763 2023-01-23 12:06:37.911093: step: 322/1545, loss: 0.083977110683918 2023-01-23 12:06:38.779764: step: 324/1545, loss: 0.12454359233379364 2023-01-23 12:06:39.676956: step: 326/1545, loss: 0.014037682674825191 2023-01-23 12:06:40.524988: step: 328/1545, loss: 0.03679845482110977 2023-01-23 12:06:41.426839: step: 330/1545, loss: 0.8941762447357178 2023-01-23 12:06:42.308851: step: 332/1545, loss: 0.06852895021438599 2023-01-23 12:06:43.166174: step: 334/1545, loss: 0.07407231628894806 2023-01-23 12:06:44.067719: step: 336/1545, loss: 1.2326525449752808 2023-01-23 12:06:44.917830: step: 338/1545, loss: 0.04399728775024414 2023-01-23 12:06:45.829320: step: 340/1545, loss: 0.051313627511262894 2023-01-23 12:06:46.785892: step: 342/1545, loss: 0.010414756834506989 2023-01-23 12:06:47.687587: step: 344/1545, loss: 0.1377389132976532 2023-01-23 12:06:48.549103: step: 346/1545, loss: 0.042813096195459366 2023-01-23 12:06:49.418661: step: 348/1545, loss: 0.13711264729499817 2023-01-23 12:06:50.311825: step: 350/1545, loss: 0.049768105149269104 2023-01-23 12:06:51.227044: step: 352/1545, loss: 0.07341037690639496 2023-01-23 12:06:52.095927: step: 354/1545, loss: 0.14901481568813324 2023-01-23 12:06:52.951367: step: 356/1545, loss: 0.19062693417072296 2023-01-23 12:06:53.860613: step: 358/1545, loss: 0.08871453255414963 2023-01-23 12:06:54.745796: step: 360/1545, loss: 0.019499599933624268 2023-01-23 12:06:55.649461: step: 362/1545, loss: 0.10342562943696976 2023-01-23 12:06:56.512603: step: 364/1545, loss: 0.019668154418468475 2023-01-23 12:06:57.395657: step: 366/1545, loss: 0.09771554917097092 2023-01-23 12:06:58.276563: step: 368/1545, loss: 0.023456046357750893 2023-01-23 12:06:59.175978: step: 370/1545, loss: 0.04222026467323303 2023-01-23 12:07:00.060844: step: 372/1545, loss: 0.3101290166378021 2023-01-23 12:07:00.945477: step: 374/1545, loss: 0.0075126164592802525 2023-01-23 12:07:01.814059: step: 376/1545, loss: 0.02006765455007553 2023-01-23 12:07:02.777326: step: 378/1545, loss: 0.333167165517807 2023-01-23 12:07:03.697873: step: 380/1545, loss: 0.008959888480603695 2023-01-23 12:07:04.565880: step: 382/1545, loss: 0.00556429848074913 2023-01-23 12:07:05.425678: step: 384/1545, loss: 0.1039133295416832 2023-01-23 12:07:06.325076: step: 386/1545, loss: 0.29314565658569336 2023-01-23 12:07:07.240338: step: 388/1545, loss: 0.20633544027805328 2023-01-23 12:07:08.121766: step: 390/1545, loss: 0.24829646944999695 2023-01-23 12:07:09.000800: step: 392/1545, loss: 0.3352699875831604 2023-01-23 12:07:09.898084: step: 394/1545, loss: 0.45928776264190674 2023-01-23 12:07:10.777766: step: 396/1545, loss: 0.12002340704202652 2023-01-23 12:07:11.703941: step: 398/1545, loss: 0.2501097023487091 2023-01-23 12:07:12.544393: step: 400/1545, loss: 0.01967160589993 2023-01-23 12:07:13.393379: step: 402/1545, loss: 0.0187107864767313 2023-01-23 12:07:14.291875: step: 404/1545, loss: 0.02008504793047905 2023-01-23 12:07:15.181262: step: 406/1545, loss: 0.09383419156074524 2023-01-23 12:07:16.201153: step: 408/1545, loss: 0.009696940891444683 2023-01-23 12:07:17.080625: step: 410/1545, loss: 0.013262497261166573 2023-01-23 12:07:17.917277: step: 412/1545, loss: 0.005374636966735125 2023-01-23 12:07:18.857507: step: 414/1545, loss: 0.14580439031124115 2023-01-23 12:07:19.774213: step: 416/1545, loss: 0.23254747688770294 2023-01-23 12:07:20.635963: step: 418/1545, loss: 0.064616359770298 2023-01-23 12:07:21.544520: step: 420/1545, loss: 0.0203473549336195 2023-01-23 12:07:22.424389: step: 422/1545, loss: 0.008312426507472992 2023-01-23 12:07:23.322430: step: 424/1545, loss: 0.2752986252307892 2023-01-23 12:07:24.248556: step: 426/1545, loss: 0.0021638923790305853 2023-01-23 12:07:25.131838: step: 428/1545, loss: 0.15105892717838287 2023-01-23 12:07:26.005062: step: 430/1545, loss: 0.05649128183722496 2023-01-23 12:07:26.847955: step: 432/1545, loss: 0.006112077739089727 2023-01-23 12:07:27.721176: step: 434/1545, loss: 0.027336129918694496 2023-01-23 12:07:28.637175: step: 436/1545, loss: 0.04285421222448349 2023-01-23 12:07:29.562206: step: 438/1545, loss: 0.12074360251426697 2023-01-23 12:07:30.463843: step: 440/1545, loss: 0.06309237331151962 2023-01-23 12:07:31.388760: step: 442/1545, loss: 0.38744738698005676 2023-01-23 12:07:32.241572: step: 444/1545, loss: 0.14397533237934113 2023-01-23 12:07:33.126752: step: 446/1545, loss: 0.058830127120018005 2023-01-23 12:07:34.033385: step: 448/1545, loss: 0.029273640364408493 2023-01-23 12:07:34.914842: step: 450/1545, loss: 0.19063428044319153 2023-01-23 12:07:35.885817: step: 452/1545, loss: 0.009095905348658562 2023-01-23 12:07:36.769718: step: 454/1545, loss: 0.691679835319519 2023-01-23 12:07:37.637314: step: 456/1545, loss: 0.055959347635507584 2023-01-23 12:07:38.498314: step: 458/1545, loss: 0.28324955701828003 2023-01-23 12:07:39.356183: step: 460/1545, loss: 0.20582988858222961 2023-01-23 12:07:40.290064: step: 462/1545, loss: 0.4323142170906067 2023-01-23 12:07:41.132537: step: 464/1545, loss: 0.18222235143184662 2023-01-23 12:07:42.057723: step: 466/1545, loss: 0.00249508791603148 2023-01-23 12:07:42.995863: step: 468/1545, loss: 0.010443825274705887 2023-01-23 12:07:43.966640: step: 470/1545, loss: 0.14278411865234375 2023-01-23 12:07:44.875847: step: 472/1545, loss: 0.016283653676509857 2023-01-23 12:07:45.735961: step: 474/1545, loss: 0.050004880875349045 2023-01-23 12:07:46.660495: step: 476/1545, loss: 0.013630765490233898 2023-01-23 12:07:47.560387: step: 478/1545, loss: 0.05741105228662491 2023-01-23 12:07:48.444151: step: 480/1545, loss: 0.0938187837600708 2023-01-23 12:07:49.338254: step: 482/1545, loss: 0.11881090700626373 2023-01-23 12:07:50.226169: step: 484/1545, loss: 0.11685379594564438 2023-01-23 12:07:51.175784: step: 486/1545, loss: 0.0352787971496582 2023-01-23 12:07:52.141633: step: 488/1545, loss: 0.025045868009328842 2023-01-23 12:07:53.028625: step: 490/1545, loss: 0.21079793572425842 2023-01-23 12:07:53.876905: step: 492/1545, loss: 0.0012505031190812588 2023-01-23 12:07:54.757515: step: 494/1545, loss: 0.01130636129528284 2023-01-23 12:07:55.641818: step: 496/1545, loss: 0.043431900441646576 2023-01-23 12:07:56.568425: step: 498/1545, loss: 0.5884175300598145 2023-01-23 12:07:57.438150: step: 500/1545, loss: 0.07095037400722504 2023-01-23 12:07:58.333727: step: 502/1545, loss: 0.009971466846764088 2023-01-23 12:07:59.189925: step: 504/1545, loss: 0.30435559153556824 2023-01-23 12:08:00.067068: step: 506/1545, loss: 0.1481526792049408 2023-01-23 12:08:00.935527: step: 508/1545, loss: 0.31241706013679504 2023-01-23 12:08:01.809430: step: 510/1545, loss: 0.009774323552846909 2023-01-23 12:08:02.714042: step: 512/1545, loss: 0.0918465331196785 2023-01-23 12:08:03.585883: step: 514/1545, loss: 0.08643462508916855 2023-01-23 12:08:04.483811: step: 516/1545, loss: 0.033035289496183395 2023-01-23 12:08:05.473843: step: 518/1545, loss: 0.0023444946855306625 2023-01-23 12:08:06.373804: step: 520/1545, loss: 0.05034654960036278 2023-01-23 12:08:07.291924: step: 522/1545, loss: 0.011868121102452278 2023-01-23 12:08:08.170778: step: 524/1545, loss: 0.10816611349582672 2023-01-23 12:08:09.070349: step: 526/1545, loss: 0.24101725220680237 2023-01-23 12:08:09.950397: step: 528/1545, loss: 0.12712928652763367 2023-01-23 12:08:10.870024: step: 530/1545, loss: 0.5493521690368652 2023-01-23 12:08:11.746198: step: 532/1545, loss: 0.0503493994474411 2023-01-23 12:08:12.605584: step: 534/1545, loss: 0.03086749278008938 2023-01-23 12:08:13.485774: step: 536/1545, loss: 0.06172382831573486 2023-01-23 12:08:14.396101: step: 538/1545, loss: 2.4979970455169678 2023-01-23 12:08:15.259625: step: 540/1545, loss: 0.11743699759244919 2023-01-23 12:08:16.151432: step: 542/1545, loss: 0.006222069263458252 2023-01-23 12:08:17.022228: step: 544/1545, loss: 0.004976976662874222 2023-01-23 12:08:17.879430: step: 546/1545, loss: 0.4693315923213959 2023-01-23 12:08:18.751702: step: 548/1545, loss: 0.014388971030712128 2023-01-23 12:08:19.619661: step: 550/1545, loss: 0.007263473235070705 2023-01-23 12:08:20.469399: step: 552/1545, loss: 0.13282962143421173 2023-01-23 12:08:21.340293: step: 554/1545, loss: 0.06482832878828049 2023-01-23 12:08:22.187055: step: 556/1545, loss: 0.17418251931667328 2023-01-23 12:08:23.081362: step: 558/1545, loss: 0.26424989104270935 2023-01-23 12:08:24.019376: step: 560/1545, loss: 0.5455248951911926 2023-01-23 12:08:24.928464: step: 562/1545, loss: 0.0640653669834137 2023-01-23 12:08:25.791071: step: 564/1545, loss: 0.10200919955968857 2023-01-23 12:08:26.676070: step: 566/1545, loss: 0.3797912001609802 2023-01-23 12:08:27.529682: step: 568/1545, loss: 0.056637149304151535 2023-01-23 12:08:28.396113: step: 570/1545, loss: 0.11926056444644928 2023-01-23 12:08:29.308857: step: 572/1545, loss: 0.2195446491241455 2023-01-23 12:08:30.167929: step: 574/1545, loss: 0.0240420401096344 2023-01-23 12:08:31.063560: step: 576/1545, loss: 0.0857568085193634 2023-01-23 12:08:31.908000: step: 578/1545, loss: 0.16759102046489716 2023-01-23 12:08:32.781690: step: 580/1545, loss: 0.4210711717605591 2023-01-23 12:08:33.634996: step: 582/1545, loss: 0.006295739207416773 2023-01-23 12:08:34.508131: step: 584/1545, loss: 0.05603625997900963 2023-01-23 12:08:35.441926: step: 586/1545, loss: 0.04114653170108795 2023-01-23 12:08:36.299965: step: 588/1545, loss: 0.016293082386255264 2023-01-23 12:08:37.200808: step: 590/1545, loss: 0.012588481418788433 2023-01-23 12:08:38.060610: step: 592/1545, loss: 0.03517945110797882 2023-01-23 12:08:38.942372: step: 594/1545, loss: 0.10290699452161789 2023-01-23 12:08:39.813532: step: 596/1545, loss: 0.012931878678500652 2023-01-23 12:08:40.668852: step: 598/1545, loss: 0.16953173279762268 2023-01-23 12:08:41.565351: step: 600/1545, loss: 0.07233825325965881 2023-01-23 12:08:42.417981: step: 602/1545, loss: 0.03768961876630783 2023-01-23 12:08:43.266865: step: 604/1545, loss: 0.20750616490840912 2023-01-23 12:08:44.134853: step: 606/1545, loss: 0.07937739044427872 2023-01-23 12:08:45.017232: step: 608/1545, loss: 0.03730171546339989 2023-01-23 12:08:45.948999: step: 610/1545, loss: 0.005916393827646971 2023-01-23 12:08:46.808730: step: 612/1545, loss: 0.05800379440188408 2023-01-23 12:08:47.669700: step: 614/1545, loss: 0.0008088697795756161 2023-01-23 12:08:48.521791: step: 616/1545, loss: 0.009398328140377998 2023-01-23 12:08:49.426463: step: 618/1545, loss: 0.04484543576836586 2023-01-23 12:08:50.304409: step: 620/1545, loss: 0.16798938810825348 2023-01-23 12:08:51.199866: step: 622/1545, loss: 0.08238926529884338 2023-01-23 12:08:52.100490: step: 624/1545, loss: 0.5331108570098877 2023-01-23 12:08:52.951204: step: 626/1545, loss: 0.051764845848083496 2023-01-23 12:08:53.848337: step: 628/1545, loss: 0.01210363581776619 2023-01-23 12:08:54.738706: step: 630/1545, loss: 0.21716980636119843 2023-01-23 12:08:55.629685: step: 632/1545, loss: 0.0067825340665876865 2023-01-23 12:08:56.515179: step: 634/1545, loss: 0.12013725191354752 2023-01-23 12:08:57.353357: step: 636/1545, loss: 0.202895388007164 2023-01-23 12:08:58.228157: step: 638/1545, loss: 0.00561870913952589 2023-01-23 12:08:59.101326: step: 640/1545, loss: 0.12109708786010742 2023-01-23 12:08:59.982570: step: 642/1545, loss: 0.07060202211141586 2023-01-23 12:09:00.927073: step: 644/1545, loss: 0.14287124574184418 2023-01-23 12:09:01.827065: step: 646/1545, loss: 0.1023586317896843 2023-01-23 12:09:02.717481: step: 648/1545, loss: 0.09460823237895966 2023-01-23 12:09:03.583737: step: 650/1545, loss: 0.11464620381593704 2023-01-23 12:09:04.534591: step: 652/1545, loss: 0.3438287675380707 2023-01-23 12:09:05.429756: step: 654/1545, loss: 0.018046313896775246 2023-01-23 12:09:06.312167: step: 656/1545, loss: 0.005866283550858498 2023-01-23 12:09:07.200915: step: 658/1545, loss: 0.13012614846229553 2023-01-23 12:09:08.083286: step: 660/1545, loss: 0.1780157834291458 2023-01-23 12:09:08.944729: step: 662/1545, loss: 0.34349480271339417 2023-01-23 12:09:09.827455: step: 664/1545, loss: 0.08434001356363297 2023-01-23 12:09:10.679972: step: 666/1545, loss: 0.004138268064707518 2023-01-23 12:09:11.539294: step: 668/1545, loss: 0.0840078815817833 2023-01-23 12:09:12.436154: step: 670/1545, loss: 0.03332461789250374 2023-01-23 12:09:13.296307: step: 672/1545, loss: 0.014686273410916328 2023-01-23 12:09:14.157657: step: 674/1545, loss: 0.04644289240241051 2023-01-23 12:09:14.974024: step: 676/1545, loss: 0.13373737037181854 2023-01-23 12:09:15.840410: step: 678/1545, loss: 0.29651087522506714 2023-01-23 12:09:16.697436: step: 680/1545, loss: 0.33703088760375977 2023-01-23 12:09:17.566825: step: 682/1545, loss: 0.039672330021858215 2023-01-23 12:09:18.505531: step: 684/1545, loss: 0.06387735158205032 2023-01-23 12:09:19.406926: step: 686/1545, loss: 0.12133435904979706 2023-01-23 12:09:20.272575: step: 688/1545, loss: 0.02842576429247856 2023-01-23 12:09:21.134041: step: 690/1545, loss: 0.313235878944397 2023-01-23 12:09:22.020745: step: 692/1545, loss: 0.09622088819742203 2023-01-23 12:09:22.892796: step: 694/1545, loss: 0.051896966993808746 2023-01-23 12:09:23.745483: step: 696/1545, loss: 0.09467152506113052 2023-01-23 12:09:24.590605: step: 698/1545, loss: 0.0007793271215632558 2023-01-23 12:09:25.479170: step: 700/1545, loss: 0.2101818174123764 2023-01-23 12:09:26.372095: step: 702/1545, loss: 0.029600713402032852 2023-01-23 12:09:27.234787: step: 704/1545, loss: 0.015217656269669533 2023-01-23 12:09:28.064870: step: 706/1545, loss: 0.15409336984157562 2023-01-23 12:09:28.939682: step: 708/1545, loss: 0.03576314449310303 2023-01-23 12:09:29.803666: step: 710/1545, loss: 0.09897365421056747 2023-01-23 12:09:30.672554: step: 712/1545, loss: 0.049956902861595154 2023-01-23 12:09:31.574833: step: 714/1545, loss: 0.03112996742129326 2023-01-23 12:09:32.458018: step: 716/1545, loss: 0.04545886069536209 2023-01-23 12:09:33.340784: step: 718/1545, loss: 0.04093826562166214 2023-01-23 12:09:34.190196: step: 720/1545, loss: 0.013475406914949417 2023-01-23 12:09:35.064885: step: 722/1545, loss: 0.15924231708049774 2023-01-23 12:09:35.960667: step: 724/1545, loss: 0.2914692163467407 2023-01-23 12:09:36.832529: step: 726/1545, loss: 0.01659236289560795 2023-01-23 12:09:37.725666: step: 728/1545, loss: 0.14199520647525787 2023-01-23 12:09:38.596634: step: 730/1545, loss: 0.023797443136572838 2023-01-23 12:09:39.503508: step: 732/1545, loss: 0.12796650826931 2023-01-23 12:09:40.356999: step: 734/1545, loss: 0.29724428057670593 2023-01-23 12:09:41.212801: step: 736/1545, loss: 0.002523350063711405 2023-01-23 12:09:42.096051: step: 738/1545, loss: 0.08247201144695282 2023-01-23 12:09:42.939351: step: 740/1545, loss: 0.014418850652873516 2023-01-23 12:09:43.824062: step: 742/1545, loss: 0.33956804871559143 2023-01-23 12:09:44.695354: step: 744/1545, loss: 0.2534348964691162 2023-01-23 12:09:45.533833: step: 746/1545, loss: 0.004848554264754057 2023-01-23 12:09:46.429642: step: 748/1545, loss: 0.019129328429698944 2023-01-23 12:09:47.340785: step: 750/1545, loss: 0.446748286485672 2023-01-23 12:09:48.302329: step: 752/1545, loss: 0.01196274720132351 2023-01-23 12:09:49.170436: step: 754/1545, loss: 0.11917579919099808 2023-01-23 12:09:50.053969: step: 756/1545, loss: 0.012387149967253208 2023-01-23 12:09:50.942097: step: 758/1545, loss: 0.017352107912302017 2023-01-23 12:09:51.775670: step: 760/1545, loss: 0.4443565607070923 2023-01-23 12:09:52.650431: step: 762/1545, loss: 0.02000427059829235 2023-01-23 12:09:53.473369: step: 764/1545, loss: 0.2217201590538025 2023-01-23 12:09:54.323799: step: 766/1545, loss: 0.002443137113004923 2023-01-23 12:09:55.204926: step: 768/1545, loss: 0.0916169062256813 2023-01-23 12:09:56.053313: step: 770/1545, loss: 0.3628847301006317 2023-01-23 12:09:56.971631: step: 772/1545, loss: 0.08307090401649475 2023-01-23 12:09:57.850123: step: 774/1545, loss: 0.008164852857589722 2023-01-23 12:09:58.711689: step: 776/1545, loss: 0.056443795561790466 2023-01-23 12:09:59.651215: step: 778/1545, loss: 0.1141311451792717 2023-01-23 12:10:00.531348: step: 780/1545, loss: 0.004060305655002594 2023-01-23 12:10:01.436381: step: 782/1545, loss: 0.32438942790031433 2023-01-23 12:10:02.325248: step: 784/1545, loss: 0.2535085082054138 2023-01-23 12:10:03.253068: step: 786/1545, loss: 0.03792034462094307 2023-01-23 12:10:04.126539: step: 788/1545, loss: 0.567444384098053 2023-01-23 12:10:05.014343: step: 790/1545, loss: 0.08930367976427078 2023-01-23 12:10:05.936354: step: 792/1545, loss: 0.007101660594344139 2023-01-23 12:10:06.812953: step: 794/1545, loss: 0.07692331075668335 2023-01-23 12:10:07.696156: step: 796/1545, loss: 0.2943972647190094 2023-01-23 12:10:08.583174: step: 798/1545, loss: 0.06978215277194977 2023-01-23 12:10:09.444375: step: 800/1545, loss: 0.021640973165631294 2023-01-23 12:10:10.338932: step: 802/1545, loss: 0.11318051815032959 2023-01-23 12:10:11.235137: step: 804/1545, loss: 0.012914636172354221 2023-01-23 12:10:12.148448: step: 806/1545, loss: 0.07126457244157791 2023-01-23 12:10:13.038387: step: 808/1545, loss: 0.12971051037311554 2023-01-23 12:10:13.944827: step: 810/1545, loss: 0.14071139693260193 2023-01-23 12:10:14.824871: step: 812/1545, loss: 0.1495852917432785 2023-01-23 12:10:15.725104: step: 814/1545, loss: 0.15509402751922607 2023-01-23 12:10:16.628389: step: 816/1545, loss: 0.021669631823897362 2023-01-23 12:10:17.505598: step: 818/1545, loss: 0.15167167782783508 2023-01-23 12:10:18.353978: step: 820/1545, loss: 0.03336475044488907 2023-01-23 12:10:19.280823: step: 822/1545, loss: 0.11679348349571228 2023-01-23 12:10:20.169755: step: 824/1545, loss: 0.0870247408747673 2023-01-23 12:10:21.020420: step: 826/1545, loss: 0.08858900517225266 2023-01-23 12:10:21.916972: step: 828/1545, loss: 0.03145502135157585 2023-01-23 12:10:22.856593: step: 830/1545, loss: 0.17214533686637878 2023-01-23 12:10:23.784150: step: 832/1545, loss: 0.004674014635384083 2023-01-23 12:10:24.651972: step: 834/1545, loss: 0.026227429509162903 2023-01-23 12:10:25.526311: step: 836/1545, loss: 0.0065084658563137054 2023-01-23 12:10:26.460509: step: 838/1545, loss: 0.007985012605786324 2023-01-23 12:10:27.379362: step: 840/1545, loss: 0.12872819602489471 2023-01-23 12:10:28.240571: step: 842/1545, loss: 0.08862174302339554 2023-01-23 12:10:29.132173: step: 844/1545, loss: 0.007056232541799545 2023-01-23 12:10:29.992048: step: 846/1545, loss: 0.24735553562641144 2023-01-23 12:10:30.868362: step: 848/1545, loss: 0.15936551988124847 2023-01-23 12:10:31.726031: step: 850/1545, loss: 0.18433509767055511 2023-01-23 12:10:32.596077: step: 852/1545, loss: 0.2533498704433441 2023-01-23 12:10:33.432411: step: 854/1545, loss: 0.08126229047775269 2023-01-23 12:10:34.345812: step: 856/1545, loss: 0.015999050810933113 2023-01-23 12:10:35.210167: step: 858/1545, loss: 0.0233093723654747 2023-01-23 12:10:36.072675: step: 860/1545, loss: 0.0802847295999527 2023-01-23 12:10:36.953752: step: 862/1545, loss: 0.004007937386631966 2023-01-23 12:10:37.817990: step: 864/1545, loss: 0.09714999049901962 2023-01-23 12:10:38.704876: step: 866/1545, loss: 0.2583431303501129 2023-01-23 12:10:39.552625: step: 868/1545, loss: 0.009978911839425564 2023-01-23 12:10:40.412594: step: 870/1545, loss: 0.286448210477829 2023-01-23 12:10:41.280630: step: 872/1545, loss: 0.05704118683934212 2023-01-23 12:10:42.106947: step: 874/1545, loss: 0.17260675132274628 2023-01-23 12:10:42.988293: step: 876/1545, loss: 0.022225307300686836 2023-01-23 12:10:43.839441: step: 878/1545, loss: 0.015586985275149345 2023-01-23 12:10:44.684867: step: 880/1545, loss: 0.32230639457702637 2023-01-23 12:10:45.548540: step: 882/1545, loss: 0.03740845248103142 2023-01-23 12:10:46.427581: step: 884/1545, loss: 0.12406454235315323 2023-01-23 12:10:47.268084: step: 886/1545, loss: 0.11849404871463776 2023-01-23 12:10:48.148482: step: 888/1545, loss: 0.08622069656848907 2023-01-23 12:10:49.032103: step: 890/1545, loss: 0.08542206138372421 2023-01-23 12:10:49.903494: step: 892/1545, loss: 0.026224467903375626 2023-01-23 12:10:50.795478: step: 894/1545, loss: 0.03705257177352905 2023-01-23 12:10:51.652405: step: 896/1545, loss: 0.019318118691444397 2023-01-23 12:10:52.561844: step: 898/1545, loss: 0.02368246391415596 2023-01-23 12:10:53.412417: step: 900/1545, loss: 0.11488433927297592 2023-01-23 12:10:54.308039: step: 902/1545, loss: 0.012263148091733456 2023-01-23 12:10:55.181770: step: 904/1545, loss: 0.3290383517742157 2023-01-23 12:10:56.123196: step: 906/1545, loss: 0.07058369368314743 2023-01-23 12:10:56.990810: step: 908/1545, loss: 0.11686386168003082 2023-01-23 12:10:57.850866: step: 910/1545, loss: 0.03184310719370842 2023-01-23 12:10:58.714019: step: 912/1545, loss: 0.06456403434276581 2023-01-23 12:10:59.573477: step: 914/1545, loss: 0.013427652418613434 2023-01-23 12:11:00.426244: step: 916/1545, loss: 0.07844515889883041 2023-01-23 12:11:01.286887: step: 918/1545, loss: 0.007512139622122049 2023-01-23 12:11:02.259147: step: 920/1545, loss: 0.053682584315538406 2023-01-23 12:11:03.092286: step: 922/1545, loss: 0.020230263471603394 2023-01-23 12:11:03.977870: step: 924/1545, loss: 0.10185283422470093 2023-01-23 12:11:04.849037: step: 926/1545, loss: 0.17790038883686066 2023-01-23 12:11:05.732096: step: 928/1545, loss: 0.24552106857299805 2023-01-23 12:11:06.604188: step: 930/1545, loss: 0.008644688874483109 2023-01-23 12:11:07.491159: step: 932/1545, loss: 0.005135028623044491 2023-01-23 12:11:08.384179: step: 934/1545, loss: 0.4862545132637024 2023-01-23 12:11:09.315294: step: 936/1545, loss: 0.10208746790885925 2023-01-23 12:11:10.181061: step: 938/1545, loss: 0.10616346448659897 2023-01-23 12:11:11.042713: step: 940/1545, loss: 0.4021487534046173 2023-01-23 12:11:11.908522: step: 942/1545, loss: 0.01973010040819645 2023-01-23 12:11:12.816373: step: 944/1545, loss: 0.02168954163789749 2023-01-23 12:11:13.720711: step: 946/1545, loss: 0.023755552247166634 2023-01-23 12:11:14.565127: step: 948/1545, loss: 0.0009136535227298737 2023-01-23 12:11:15.491324: step: 950/1545, loss: 0.013634995557367802 2023-01-23 12:11:16.366614: step: 952/1545, loss: 0.3439124822616577 2023-01-23 12:11:17.262499: step: 954/1545, loss: 0.13110245764255524 2023-01-23 12:11:18.129362: step: 956/1545, loss: 0.11217574030160904 2023-01-23 12:11:19.049427: step: 958/1545, loss: 0.03397934511303902 2023-01-23 12:11:19.971555: step: 960/1545, loss: 0.16352543234825134 2023-01-23 12:11:20.857050: step: 962/1545, loss: 0.45164093375205994 2023-01-23 12:11:21.727881: step: 964/1545, loss: 0.4031376540660858 2023-01-23 12:11:22.616029: step: 966/1545, loss: 0.028896035626530647 2023-01-23 12:11:23.499236: step: 968/1545, loss: 0.0036632029805332422 2023-01-23 12:11:24.390209: step: 970/1545, loss: 0.005492212250828743 2023-01-23 12:11:25.273042: step: 972/1545, loss: 0.08779126405715942 2023-01-23 12:11:26.124028: step: 974/1545, loss: 0.07843721657991409 2023-01-23 12:11:27.027505: step: 976/1545, loss: 0.020931802690029144 2023-01-23 12:11:27.865764: step: 978/1545, loss: 0.5949313044548035 2023-01-23 12:11:28.805016: step: 980/1545, loss: 0.036932572722435 2023-01-23 12:11:29.675358: step: 982/1545, loss: 0.0028045393992215395 2023-01-23 12:11:30.543774: step: 984/1545, loss: 0.09419401735067368 2023-01-23 12:11:31.425154: step: 986/1545, loss: 0.01073438860476017 2023-01-23 12:11:32.303046: step: 988/1545, loss: 0.26501160860061646 2023-01-23 12:11:33.146945: step: 990/1545, loss: 0.02862098067998886 2023-01-23 12:11:34.020863: step: 992/1545, loss: 0.11296961456537247 2023-01-23 12:11:34.868939: step: 994/1545, loss: 0.07739650458097458 2023-01-23 12:11:35.784189: step: 996/1545, loss: 0.09608613699674606 2023-01-23 12:11:36.638597: step: 998/1545, loss: 0.01101007591933012 2023-01-23 12:11:37.531633: step: 1000/1545, loss: 0.10460101068019867 2023-01-23 12:11:38.409577: step: 1002/1545, loss: 0.05898350849747658 2023-01-23 12:11:39.274620: step: 1004/1545, loss: 0.397197425365448 2023-01-23 12:11:40.184932: step: 1006/1545, loss: 0.1427219808101654 2023-01-23 12:11:41.057740: step: 1008/1545, loss: 0.03474383056163788 2023-01-23 12:11:41.946556: step: 1010/1545, loss: 0.04178573191165924 2023-01-23 12:11:42.788272: step: 1012/1545, loss: 0.3099414110183716 2023-01-23 12:11:43.711022: step: 1014/1545, loss: 0.38976502418518066 2023-01-23 12:11:44.602321: step: 1016/1545, loss: 0.2288977950811386 2023-01-23 12:11:45.496445: step: 1018/1545, loss: 0.05756447836756706 2023-01-23 12:11:46.369271: step: 1020/1545, loss: 0.0068626198917627335 2023-01-23 12:11:47.235516: step: 1022/1545, loss: 0.1921079158782959 2023-01-23 12:11:48.105126: step: 1024/1545, loss: 0.023173609748482704 2023-01-23 12:11:49.040709: step: 1026/1545, loss: 0.0680670216679573 2023-01-23 12:11:49.879712: step: 1028/1545, loss: 0.10062995553016663 2023-01-23 12:11:50.750806: step: 1030/1545, loss: 0.06171463429927826 2023-01-23 12:11:51.623240: step: 1032/1545, loss: 0.13087286055088043 2023-01-23 12:11:52.529606: step: 1034/1545, loss: 0.1380634605884552 2023-01-23 12:11:53.424059: step: 1036/1545, loss: 0.19737879931926727 2023-01-23 12:11:54.262321: step: 1038/1545, loss: 0.18363721668720245 2023-01-23 12:11:55.139706: step: 1040/1545, loss: 0.019914424046874046 2023-01-23 12:11:56.079136: step: 1042/1545, loss: 0.09662464261054993 2023-01-23 12:11:56.956336: step: 1044/1545, loss: 0.0017859474755823612 2023-01-23 12:11:57.862136: step: 1046/1545, loss: 0.08101782947778702 2023-01-23 12:11:58.728271: step: 1048/1545, loss: 0.21442911028862 2023-01-23 12:11:59.552865: step: 1050/1545, loss: 0.022842926904559135 2023-01-23 12:12:00.460912: step: 1052/1545, loss: 0.2241596281528473 2023-01-23 12:12:01.355996: step: 1054/1545, loss: 0.09036220610141754 2023-01-23 12:12:02.272377: step: 1056/1545, loss: 0.5034279823303223 2023-01-23 12:12:03.112767: step: 1058/1545, loss: 0.1241535171866417 2023-01-23 12:12:03.965462: step: 1060/1545, loss: 0.10182269662618637 2023-01-23 12:12:04.833679: step: 1062/1545, loss: 0.007602778263390064 2023-01-23 12:12:05.715490: step: 1064/1545, loss: 0.08624890446662903 2023-01-23 12:12:06.609740: step: 1066/1545, loss: 0.4086720645427704 2023-01-23 12:12:07.510631: step: 1068/1545, loss: 0.20960409939289093 2023-01-23 12:12:08.399621: step: 1070/1545, loss: 0.11723565310239792 2023-01-23 12:12:09.279730: step: 1072/1545, loss: 0.00485818088054657 2023-01-23 12:12:10.137983: step: 1074/1545, loss: 0.04855699464678764 2023-01-23 12:12:11.049677: step: 1076/1545, loss: 0.29306405782699585 2023-01-23 12:12:11.978851: step: 1078/1545, loss: 0.04338882118463516 2023-01-23 12:12:12.873949: step: 1080/1545, loss: 0.18420691788196564 2023-01-23 12:12:13.731824: step: 1082/1545, loss: 0.064139224588871 2023-01-23 12:12:14.594564: step: 1084/1545, loss: 0.2506057918071747 2023-01-23 12:12:15.456755: step: 1086/1545, loss: 0.38351306319236755 2023-01-23 12:12:16.298216: step: 1088/1545, loss: 0.03655022382736206 2023-01-23 12:12:17.162203: step: 1090/1545, loss: 0.012526920065283775 2023-01-23 12:12:18.038894: step: 1092/1545, loss: 0.2012990564107895 2023-01-23 12:12:18.883765: step: 1094/1545, loss: 0.01036785263568163 2023-01-23 12:12:19.725238: step: 1096/1545, loss: 0.3149237632751465 2023-01-23 12:12:20.601751: step: 1098/1545, loss: 0.00879608653485775 2023-01-23 12:12:21.533922: step: 1100/1545, loss: 0.08940982073545456 2023-01-23 12:12:22.404370: step: 1102/1545, loss: 0.20264387130737305 2023-01-23 12:12:23.277666: step: 1104/1545, loss: 0.13562700152397156 2023-01-23 12:12:24.166996: step: 1106/1545, loss: 0.06808493286371231 2023-01-23 12:12:25.033466: step: 1108/1545, loss: 0.01893513649702072 2023-01-23 12:12:25.940831: step: 1110/1545, loss: 0.09634009003639221 2023-01-23 12:12:26.839691: step: 1112/1545, loss: 0.05219029635190964 2023-01-23 12:12:27.737695: step: 1114/1545, loss: 0.20536187291145325 2023-01-23 12:12:28.630709: step: 1116/1545, loss: 0.18228493630886078 2023-01-23 12:12:29.510989: step: 1118/1545, loss: 0.04005542770028114 2023-01-23 12:12:30.413738: step: 1120/1545, loss: 0.5002660751342773 2023-01-23 12:12:31.361808: step: 1122/1545, loss: 0.4366292357444763 2023-01-23 12:12:32.276844: step: 1124/1545, loss: 0.3034071624279022 2023-01-23 12:12:33.134980: step: 1126/1545, loss: 0.391507625579834 2023-01-23 12:12:33.993126: step: 1128/1545, loss: 0.0710902214050293 2023-01-23 12:12:34.881755: step: 1130/1545, loss: 0.09029810130596161 2023-01-23 12:12:35.731998: step: 1132/1545, loss: 0.10630572587251663 2023-01-23 12:12:36.623867: step: 1134/1545, loss: 0.02761901170015335 2023-01-23 12:12:37.507577: step: 1136/1545, loss: 0.06574990600347519 2023-01-23 12:12:38.379118: step: 1138/1545, loss: 0.16037186980247498 2023-01-23 12:12:39.353847: step: 1140/1545, loss: 0.27032285928726196 2023-01-23 12:12:40.205907: step: 1142/1545, loss: 0.23912644386291504 2023-01-23 12:12:41.036556: step: 1144/1545, loss: 0.007019035052508116 2023-01-23 12:12:41.883629: step: 1146/1545, loss: 0.5196831226348877 2023-01-23 12:12:42.882394: step: 1148/1545, loss: 0.2178698182106018 2023-01-23 12:12:43.774356: step: 1150/1545, loss: 0.13021543622016907 2023-01-23 12:12:44.673878: step: 1152/1545, loss: 0.20957055687904358 2023-01-23 12:12:45.499838: step: 1154/1545, loss: 0.043557800352573395 2023-01-23 12:12:46.444973: step: 1156/1545, loss: 0.03274587541818619 2023-01-23 12:12:47.382353: step: 1158/1545, loss: 0.12701614201068878 2023-01-23 12:12:48.250370: step: 1160/1545, loss: 0.009775795042514801 2023-01-23 12:12:49.172927: step: 1162/1545, loss: 0.004354339092969894 2023-01-23 12:12:50.026712: step: 1164/1545, loss: 0.32013583183288574 2023-01-23 12:12:50.884816: step: 1166/1545, loss: 0.09930513054132462 2023-01-23 12:12:51.752399: step: 1168/1545, loss: 0.16896578669548035 2023-01-23 12:12:52.577276: step: 1170/1545, loss: 0.3387511372566223 2023-01-23 12:12:53.493855: step: 1172/1545, loss: 0.06738276779651642 2023-01-23 12:12:54.414570: step: 1174/1545, loss: 0.06880997866392136 2023-01-23 12:12:55.307374: step: 1176/1545, loss: 0.04000701755285263 2023-01-23 12:12:56.201271: step: 1178/1545, loss: 0.35877737402915955 2023-01-23 12:12:57.123294: step: 1180/1545, loss: 0.6876859664916992 2023-01-23 12:12:58.056038: step: 1182/1545, loss: 0.025905117392539978 2023-01-23 12:12:58.927922: step: 1184/1545, loss: 0.043757230043411255 2023-01-23 12:12:59.768346: step: 1186/1545, loss: 0.40807464718818665 2023-01-23 12:13:00.646178: step: 1188/1545, loss: 0.01323431171476841 2023-01-23 12:13:01.590339: step: 1190/1545, loss: 0.32892507314682007 2023-01-23 12:13:02.491452: step: 1192/1545, loss: 0.03480851650238037 2023-01-23 12:13:03.357160: step: 1194/1545, loss: 0.11553525924682617 2023-01-23 12:13:04.263321: step: 1196/1545, loss: 0.052657198160886765 2023-01-23 12:13:05.151823: step: 1198/1545, loss: 0.40939298272132874 2023-01-23 12:13:05.993680: step: 1200/1545, loss: 0.031056810170412064 2023-01-23 12:13:06.835411: step: 1202/1545, loss: 0.18559744954109192 2023-01-23 12:13:07.735539: step: 1204/1545, loss: 0.14199480414390564 2023-01-23 12:13:08.569318: step: 1206/1545, loss: 0.054993465542793274 2023-01-23 12:13:09.449651: step: 1208/1545, loss: 0.047795701771974564 2023-01-23 12:13:10.302164: step: 1210/1545, loss: 0.013191401958465576 2023-01-23 12:13:11.221455: step: 1212/1545, loss: 0.08182547241449356 2023-01-23 12:13:12.068468: step: 1214/1545, loss: 0.03631390258669853 2023-01-23 12:13:12.961201: step: 1216/1545, loss: 0.027386397123336792 2023-01-23 12:13:13.844227: step: 1218/1545, loss: 0.02967516891658306 2023-01-23 12:13:14.731583: step: 1220/1545, loss: 0.013840344734489918 2023-01-23 12:13:15.702274: step: 1222/1545, loss: 0.0920950248837471 2023-01-23 12:13:16.581360: step: 1224/1545, loss: 0.1747942715883255 2023-01-23 12:13:17.516732: step: 1226/1545, loss: 0.02521093562245369 2023-01-23 12:13:18.397520: step: 1228/1545, loss: 0.48455655574798584 2023-01-23 12:13:19.285792: step: 1230/1545, loss: 0.011894053779542446 2023-01-23 12:13:20.131745: step: 1232/1545, loss: 0.30511096119880676 2023-01-23 12:13:21.002549: step: 1234/1545, loss: 0.3552021384239197 2023-01-23 12:13:21.878757: step: 1236/1545, loss: 0.15242992341518402 2023-01-23 12:13:22.784063: step: 1238/1545, loss: 0.030611397698521614 2023-01-23 12:13:23.673290: step: 1240/1545, loss: 0.06566935777664185 2023-01-23 12:13:24.536388: step: 1242/1545, loss: 0.1058867797255516 2023-01-23 12:13:25.524177: step: 1244/1545, loss: 0.30507534742355347 2023-01-23 12:13:26.414100: step: 1246/1545, loss: 0.042963553220033646 2023-01-23 12:13:27.342860: step: 1248/1545, loss: 0.08591169863939285 2023-01-23 12:13:28.187375: step: 1250/1545, loss: 0.006729693617671728 2023-01-23 12:13:29.156056: step: 1252/1545, loss: 0.023781336843967438 2023-01-23 12:13:30.032302: step: 1254/1545, loss: 0.04930313676595688 2023-01-23 12:13:30.885044: step: 1256/1545, loss: 0.08253306150436401 2023-01-23 12:13:31.805494: step: 1258/1545, loss: 0.008313908241689205 2023-01-23 12:13:32.710050: step: 1260/1545, loss: 0.008518910966813564 2023-01-23 12:13:33.651978: step: 1262/1545, loss: 0.01837422139942646 2023-01-23 12:13:34.526962: step: 1264/1545, loss: 0.016454214230179787 2023-01-23 12:13:35.390731: step: 1266/1545, loss: 0.11157245188951492 2023-01-23 12:13:36.264097: step: 1268/1545, loss: 0.0743417739868164 2023-01-23 12:13:37.170186: step: 1270/1545, loss: 0.08655519038438797 2023-01-23 12:13:38.023055: step: 1272/1545, loss: 0.0030775414779782295 2023-01-23 12:13:38.883018: step: 1274/1545, loss: 0.4168833792209625 2023-01-23 12:13:39.697910: step: 1276/1545, loss: 0.18217733502388 2023-01-23 12:13:40.647976: step: 1278/1545, loss: 0.31287845969200134 2023-01-23 12:13:41.548992: step: 1280/1545, loss: 0.0415252223610878 2023-01-23 12:13:42.425382: step: 1282/1545, loss: 0.5877150893211365 2023-01-23 12:13:43.328982: step: 1284/1545, loss: 0.12807530164718628 2023-01-23 12:13:44.221788: step: 1286/1545, loss: 0.0012638203334063292 2023-01-23 12:13:45.132226: step: 1288/1545, loss: 0.29574695229530334 2023-01-23 12:13:45.992057: step: 1290/1545, loss: 0.11038776487112045 2023-01-23 12:13:46.896051: step: 1292/1545, loss: 0.01862119324505329 2023-01-23 12:13:47.817698: step: 1294/1545, loss: 0.10632400214672089 2023-01-23 12:13:48.689906: step: 1296/1545, loss: 0.26316818594932556 2023-01-23 12:13:49.659328: step: 1298/1545, loss: 0.014890660531818867 2023-01-23 12:13:50.621350: step: 1300/1545, loss: 0.1797265261411667 2023-01-23 12:13:51.536701: step: 1302/1545, loss: 0.1950724720954895 2023-01-23 12:13:52.431656: step: 1304/1545, loss: 0.09456688165664673 2023-01-23 12:13:53.335928: step: 1306/1545, loss: 0.016315709799528122 2023-01-23 12:13:54.238680: step: 1308/1545, loss: 0.03519183769822121 2023-01-23 12:13:55.104359: step: 1310/1545, loss: 0.5255287885665894 2023-01-23 12:13:55.988814: step: 1312/1545, loss: 0.05927293375134468 2023-01-23 12:13:56.838741: step: 1314/1545, loss: 0.17807361483573914 2023-01-23 12:13:57.728052: step: 1316/1545, loss: 0.04704452306032181 2023-01-23 12:13:58.561066: step: 1318/1545, loss: 0.12682537734508514 2023-01-23 12:13:59.396688: step: 1320/1545, loss: 0.08393201977014542 2023-01-23 12:14:00.279614: step: 1322/1545, loss: 0.004250183701515198 2023-01-23 12:14:01.149609: step: 1324/1545, loss: 0.1992146521806717 2023-01-23 12:14:02.042051: step: 1326/1545, loss: 0.0026809298433363438 2023-01-23 12:14:02.965875: step: 1328/1545, loss: 0.03232792019844055 2023-01-23 12:14:03.821431: step: 1330/1545, loss: 0.30809080600738525 2023-01-23 12:14:04.678863: step: 1332/1545, loss: 0.08891589194536209 2023-01-23 12:14:05.546614: step: 1334/1545, loss: 0.03399338945746422 2023-01-23 12:14:06.434982: step: 1336/1545, loss: 0.09664986282587051 2023-01-23 12:14:07.329997: step: 1338/1545, loss: 0.8298401236534119 2023-01-23 12:14:08.231124: step: 1340/1545, loss: 0.05551101267337799 2023-01-23 12:14:09.073543: step: 1342/1545, loss: 0.03161037713289261 2023-01-23 12:14:09.920803: step: 1344/1545, loss: 0.05371586233377457 2023-01-23 12:14:10.827819: step: 1346/1545, loss: 0.13174648582935333 2023-01-23 12:14:11.719877: step: 1348/1545, loss: 0.03480564430356026 2023-01-23 12:14:12.692457: step: 1350/1545, loss: 0.08095334470272064 2023-01-23 12:14:13.529715: step: 1352/1545, loss: 2.3444457054138184 2023-01-23 12:14:14.363087: step: 1354/1545, loss: 0.027238450944423676 2023-01-23 12:14:15.203484: step: 1356/1545, loss: 0.4047005772590637 2023-01-23 12:14:16.038252: step: 1358/1545, loss: 0.012690150178968906 2023-01-23 12:14:17.048101: step: 1360/1545, loss: 0.9512187838554382 2023-01-23 12:14:17.907148: step: 1362/1545, loss: 0.17372149229049683 2023-01-23 12:14:18.842540: step: 1364/1545, loss: 0.030978891998529434 2023-01-23 12:14:19.739464: step: 1366/1545, loss: 0.031227774918079376 2023-01-23 12:14:20.637381: step: 1368/1545, loss: 0.10026618093252182 2023-01-23 12:14:21.528164: step: 1370/1545, loss: 0.07599315792322159 2023-01-23 12:14:22.379943: step: 1372/1545, loss: 0.16977442800998688 2023-01-23 12:14:23.281100: step: 1374/1545, loss: 0.6007598042488098 2023-01-23 12:14:24.154032: step: 1376/1545, loss: 0.1256023645401001 2023-01-23 12:14:25.086677: step: 1378/1545, loss: 0.8989803791046143 2023-01-23 12:14:25.959026: step: 1380/1545, loss: 0.019294094294309616 2023-01-23 12:14:26.837121: step: 1382/1545, loss: 0.014490380883216858 2023-01-23 12:14:27.686586: step: 1384/1545, loss: 0.010044816881418228 2023-01-23 12:14:28.582630: step: 1386/1545, loss: 0.17880724370479584 2023-01-23 12:14:29.483455: step: 1388/1545, loss: 0.004424048587679863 2023-01-23 12:14:30.359346: step: 1390/1545, loss: 0.021316178143024445 2023-01-23 12:14:31.262386: step: 1392/1545, loss: 0.05891764536499977 2023-01-23 12:14:32.161808: step: 1394/1545, loss: 0.15096111595630646 2023-01-23 12:14:33.032137: step: 1396/1545, loss: 0.11201556026935577 2023-01-23 12:14:33.909954: step: 1398/1545, loss: 0.00988350622355938 2023-01-23 12:14:34.804414: step: 1400/1545, loss: 0.02744263783097267 2023-01-23 12:14:35.695123: step: 1402/1545, loss: 0.13818173110485077 2023-01-23 12:14:36.638462: step: 1404/1545, loss: 0.19137583673000336 2023-01-23 12:14:37.534398: step: 1406/1545, loss: 0.08260588347911835 2023-01-23 12:14:38.429755: step: 1408/1545, loss: 0.0407634936273098 2023-01-23 12:14:39.348889: step: 1410/1545, loss: 0.4416660964488983 2023-01-23 12:14:40.221580: step: 1412/1545, loss: 0.14404238760471344 2023-01-23 12:14:41.097383: step: 1414/1545, loss: 0.019436441361904144 2023-01-23 12:14:41.993800: step: 1416/1545, loss: 0.041853226721286774 2023-01-23 12:14:42.860942: step: 1418/1545, loss: 0.022688500583171844 2023-01-23 12:14:43.749432: step: 1420/1545, loss: 0.05281086638569832 2023-01-23 12:14:44.637924: step: 1422/1545, loss: 0.14726683497428894 2023-01-23 12:14:45.500819: step: 1424/1545, loss: 0.190615713596344 2023-01-23 12:14:46.413887: step: 1426/1545, loss: 0.023805517703294754 2023-01-23 12:14:47.298307: step: 1428/1545, loss: 0.17463542520999908 2023-01-23 12:14:48.201776: step: 1430/1545, loss: 0.2667025923728943 2023-01-23 12:14:49.097023: step: 1432/1545, loss: 0.1311403512954712 2023-01-23 12:14:49.972990: step: 1434/1545, loss: 0.03297314792871475 2023-01-23 12:14:50.912998: step: 1436/1545, loss: 0.19041813910007477 2023-01-23 12:14:51.815664: step: 1438/1545, loss: 0.1589035987854004 2023-01-23 12:14:52.704238: step: 1440/1545, loss: 0.06573360413312912 2023-01-23 12:14:53.573266: step: 1442/1545, loss: 0.025349384173750877 2023-01-23 12:14:54.448310: step: 1444/1545, loss: 0.0756223127245903 2023-01-23 12:14:55.281361: step: 1446/1545, loss: 0.023541312664747238 2023-01-23 12:14:56.138120: step: 1448/1545, loss: 0.029955532401800156 2023-01-23 12:14:57.014774: step: 1450/1545, loss: 0.16752839088439941 2023-01-23 12:14:57.896979: step: 1452/1545, loss: 0.0868828296661377 2023-01-23 12:14:58.747557: step: 1454/1545, loss: 0.0037156559992581606 2023-01-23 12:14:59.628940: step: 1456/1545, loss: 0.03392193093895912 2023-01-23 12:15:00.521368: step: 1458/1545, loss: 0.01013979408890009 2023-01-23 12:15:01.406590: step: 1460/1545, loss: 0.1687815636396408 2023-01-23 12:15:02.289242: step: 1462/1545, loss: 0.08451741933822632 2023-01-23 12:15:03.161680: step: 1464/1545, loss: 0.06765778362751007 2023-01-23 12:15:04.035709: step: 1466/1545, loss: 0.050843946635723114 2023-01-23 12:15:04.938223: step: 1468/1545, loss: 0.08938275277614594 2023-01-23 12:15:05.865092: step: 1470/1545, loss: 0.12396550923585892 2023-01-23 12:15:06.721571: step: 1472/1545, loss: 0.47674134373664856 2023-01-23 12:15:07.582029: step: 1474/1545, loss: 0.07311415672302246 2023-01-23 12:15:08.494313: step: 1476/1545, loss: 0.0635526031255722 2023-01-23 12:15:09.376871: step: 1478/1545, loss: 0.05138610675930977 2023-01-23 12:15:10.235755: step: 1480/1545, loss: 0.10675598680973053 2023-01-23 12:15:11.093479: step: 1482/1545, loss: 0.013306140899658203 2023-01-23 12:15:11.967625: step: 1484/1545, loss: 0.03222665563225746 2023-01-23 12:15:12.830499: step: 1486/1545, loss: 0.030875995755195618 2023-01-23 12:15:13.770702: step: 1488/1545, loss: 0.08105970919132233 2023-01-23 12:15:14.659208: step: 1490/1545, loss: 0.024593807756900787 2023-01-23 12:15:15.548503: step: 1492/1545, loss: 0.4128311276435852 2023-01-23 12:15:16.470737: step: 1494/1545, loss: 0.023441245779395103 2023-01-23 12:15:17.294723: step: 1496/1545, loss: 0.14557041227817535 2023-01-23 12:15:18.206209: step: 1498/1545, loss: 0.012816383503377438 2023-01-23 12:15:19.110155: step: 1500/1545, loss: 0.029567008838057518 2023-01-23 12:15:19.981132: step: 1502/1545, loss: 0.006941303610801697 2023-01-23 12:15:20.825781: step: 1504/1545, loss: 0.0017351160058751702 2023-01-23 12:15:21.672398: step: 1506/1545, loss: 0.05831126123666763 2023-01-23 12:15:22.655036: step: 1508/1545, loss: 0.0391470342874527 2023-01-23 12:15:23.493953: step: 1510/1545, loss: 0.07389732450246811 2023-01-23 12:15:24.365362: step: 1512/1545, loss: 0.005781241692602634 2023-01-23 12:15:25.210587: step: 1514/1545, loss: 0.14152002334594727 2023-01-23 12:15:26.054359: step: 1516/1545, loss: 0.10049796104431152 2023-01-23 12:15:26.916999: step: 1518/1545, loss: 0.05959218367934227 2023-01-23 12:15:27.824864: step: 1520/1545, loss: 0.07480186223983765 2023-01-23 12:15:28.722979: step: 1522/1545, loss: 0.03163113445043564 2023-01-23 12:15:29.595660: step: 1524/1545, loss: 0.024418789893388748 2023-01-23 12:15:30.523722: step: 1526/1545, loss: 0.05925313010811806 2023-01-23 12:15:31.391610: step: 1528/1545, loss: 0.11029239743947983 2023-01-23 12:15:32.286406: step: 1530/1545, loss: 0.05767082795500755 2023-01-23 12:15:33.173733: step: 1532/1545, loss: 0.23966416716575623 2023-01-23 12:15:34.037539: step: 1534/1545, loss: 0.07107240706682205 2023-01-23 12:15:34.973316: step: 1536/1545, loss: 0.1509055346250534 2023-01-23 12:15:35.875990: step: 1538/1545, loss: 0.11484523117542267 2023-01-23 12:15:36.798911: step: 1540/1545, loss: 0.05678108334541321 2023-01-23 12:15:37.681710: step: 1542/1545, loss: 0.12123311311006546 2023-01-23 12:15:38.555713: step: 1544/1545, loss: 0.01044329535216093 2023-01-23 12:15:39.423263: step: 1546/1545, loss: 0.23385216295719147 2023-01-23 12:15:40.276418: step: 1548/1545, loss: 0.06594844907522202 2023-01-23 12:15:41.135555: step: 1550/1545, loss: 0.032131627202034 2023-01-23 12:15:41.987557: step: 1552/1545, loss: 0.13181453943252563 2023-01-23 12:15:42.857250: step: 1554/1545, loss: 0.003355823690071702 2023-01-23 12:15:43.715902: step: 1556/1545, loss: 0.008198253810405731 2023-01-23 12:15:44.609652: step: 1558/1545, loss: 0.1263277232646942 2023-01-23 12:15:45.492142: step: 1560/1545, loss: 0.17896467447280884 2023-01-23 12:15:46.393798: step: 1562/1545, loss: 0.21555857360363007 2023-01-23 12:15:47.318281: step: 1564/1545, loss: 0.2101926952600479 2023-01-23 12:15:48.160762: step: 1566/1545, loss: 0.004260340239852667 2023-01-23 12:15:49.021265: step: 1568/1545, loss: 0.15399208664894104 2023-01-23 12:15:49.897240: step: 1570/1545, loss: 0.015919465571641922 2023-01-23 12:15:50.883612: step: 1572/1545, loss: 0.0159380454570055 2023-01-23 12:15:51.795835: step: 1574/1545, loss: 0.1877448856830597 2023-01-23 12:15:52.642169: step: 1576/1545, loss: 0.022697079926729202 2023-01-23 12:15:53.539512: step: 1578/1545, loss: 0.0017200749134644866 2023-01-23 12:15:54.511293: step: 1580/1545, loss: 0.01686903089284897 2023-01-23 12:15:55.382413: step: 1582/1545, loss: 0.028837062418460846 2023-01-23 12:15:56.238740: step: 1584/1545, loss: 0.20792746543884277 2023-01-23 12:15:57.125607: step: 1586/1545, loss: 0.01515168510377407 2023-01-23 12:15:58.033503: step: 1588/1545, loss: 0.08798401802778244 2023-01-23 12:15:58.955206: step: 1590/1545, loss: 0.17967334389686584 2023-01-23 12:15:59.829366: step: 1592/1545, loss: 0.054347626864910126 2023-01-23 12:16:00.688001: step: 1594/1545, loss: 0.12259221076965332 2023-01-23 12:16:01.553533: step: 1596/1545, loss: 0.06749583780765533 2023-01-23 12:16:02.462278: step: 1598/1545, loss: 0.07923037558794022 2023-01-23 12:16:03.313760: step: 1600/1545, loss: 0.3995496928691864 2023-01-23 12:16:04.213045: step: 1602/1545, loss: 0.015761667862534523 2023-01-23 12:16:05.095247: step: 1604/1545, loss: 0.024493254721164703 2023-01-23 12:16:06.019657: step: 1606/1545, loss: 0.06111157312989235 2023-01-23 12:16:06.946128: step: 1608/1545, loss: 0.145860493183136 2023-01-23 12:16:07.843219: step: 1610/1545, loss: 0.48115384578704834 2023-01-23 12:16:08.730671: step: 1612/1545, loss: 0.017902221530675888 2023-01-23 12:16:09.621248: step: 1614/1545, loss: 0.004906450863927603 2023-01-23 12:16:10.483817: step: 1616/1545, loss: 0.015532659366726875 2023-01-23 12:16:11.391045: step: 1618/1545, loss: 0.4007991552352905 2023-01-23 12:16:12.259174: step: 1620/1545, loss: 0.030728960409760475 2023-01-23 12:16:13.136545: step: 1622/1545, loss: 0.1252119541168213 2023-01-23 12:16:14.009075: step: 1624/1545, loss: 0.02737974375486374 2023-01-23 12:16:14.931799: step: 1626/1545, loss: 0.20154136419296265 2023-01-23 12:16:15.855193: step: 1628/1545, loss: 0.21615749597549438 2023-01-23 12:16:16.798096: step: 1630/1545, loss: 0.5233015418052673 2023-01-23 12:16:17.660776: step: 1632/1545, loss: 0.0358852744102478 2023-01-23 12:16:18.540466: step: 1634/1545, loss: 0.5957342982292175 2023-01-23 12:16:19.427957: step: 1636/1545, loss: 0.17521393299102783 2023-01-23 12:16:20.330812: step: 1638/1545, loss: 0.06333515048027039 2023-01-23 12:16:21.173567: step: 1640/1545, loss: 0.6230067014694214 2023-01-23 12:16:22.043095: step: 1642/1545, loss: 0.006871364079415798 2023-01-23 12:16:22.900867: step: 1644/1545, loss: 0.047390613704919815 2023-01-23 12:16:23.729744: step: 1646/1545, loss: 0.20624327659606934 2023-01-23 12:16:24.589150: step: 1648/1545, loss: 0.010449349880218506 2023-01-23 12:16:25.469688: step: 1650/1545, loss: 0.010379140265285969 2023-01-23 12:16:26.301333: step: 1652/1545, loss: 0.029759854078292847 2023-01-23 12:16:27.176177: step: 1654/1545, loss: 0.024139316752552986 2023-01-23 12:16:28.067178: step: 1656/1545, loss: 0.5461364388465881 2023-01-23 12:16:28.951213: step: 1658/1545, loss: 0.022080570459365845 2023-01-23 12:16:29.824590: step: 1660/1545, loss: 0.07508046925067902 2023-01-23 12:16:30.711815: step: 1662/1545, loss: 0.04360758513212204 2023-01-23 12:16:31.587593: step: 1664/1545, loss: 0.11489207297563553 2023-01-23 12:16:32.482369: step: 1666/1545, loss: 0.28722530603408813 2023-01-23 12:16:33.362476: step: 1668/1545, loss: 0.07628312706947327 2023-01-23 12:16:34.266710: step: 1670/1545, loss: 0.3939321041107178 2023-01-23 12:16:35.122336: step: 1672/1545, loss: 0.06747575104236603 2023-01-23 12:16:36.026631: step: 1674/1545, loss: 0.005760559346526861 2023-01-23 12:16:36.923071: step: 1676/1545, loss: 0.07804717123508453 2023-01-23 12:16:37.803003: step: 1678/1545, loss: 0.03579876199364662 2023-01-23 12:16:38.754040: step: 1680/1545, loss: 0.029748771339654922 2023-01-23 12:16:39.660372: step: 1682/1545, loss: 0.16662922501564026 2023-01-23 12:16:40.517341: step: 1684/1545, loss: 0.2085859477519989 2023-01-23 12:16:41.406718: step: 1686/1545, loss: 0.14255337417125702 2023-01-23 12:16:42.308616: step: 1688/1545, loss: 0.03489811718463898 2023-01-23 12:16:43.200681: step: 1690/1545, loss: 0.013551803305745125 2023-01-23 12:16:44.058127: step: 1692/1545, loss: 0.023112177848815918 2023-01-23 12:16:44.983721: step: 1694/1545, loss: 0.16446806490421295 2023-01-23 12:16:45.902244: step: 1696/1545, loss: 0.20599988102912903 2023-01-23 12:16:46.760909: step: 1698/1545, loss: 0.14062169194221497 2023-01-23 12:16:47.660592: step: 1700/1545, loss: 0.032564226537942886 2023-01-23 12:16:48.570107: step: 1702/1545, loss: 0.19196854531764984 2023-01-23 12:16:49.426334: step: 1704/1545, loss: 0.08238904178142548 2023-01-23 12:16:50.328082: step: 1706/1545, loss: 0.019030654802918434 2023-01-23 12:16:51.229208: step: 1708/1545, loss: 0.030406394973397255 2023-01-23 12:16:52.152670: step: 1710/1545, loss: 0.18538954854011536 2023-01-23 12:16:53.025220: step: 1712/1545, loss: 0.4968840181827545 2023-01-23 12:16:53.901251: step: 1714/1545, loss: 0.2206270843744278 2023-01-23 12:16:54.789229: step: 1716/1545, loss: 0.0019209637539461255 2023-01-23 12:16:55.658770: step: 1718/1545, loss: 0.17770324647426605 2023-01-23 12:16:56.540910: step: 1720/1545, loss: 0.003224578220397234 2023-01-23 12:16:57.442577: step: 1722/1545, loss: 0.23729068040847778 2023-01-23 12:16:58.293912: step: 1724/1545, loss: 0.12294331938028336 2023-01-23 12:16:59.208985: step: 1726/1545, loss: 0.012318629771471024 2023-01-23 12:17:00.087331: step: 1728/1545, loss: 0.0467119999229908 2023-01-23 12:17:00.974489: step: 1730/1545, loss: 0.037035416811704636 2023-01-23 12:17:01.990734: step: 1732/1545, loss: 0.08568999171257019 2023-01-23 12:17:02.855891: step: 1734/1545, loss: 0.032521359622478485 2023-01-23 12:17:03.755072: step: 1736/1545, loss: 0.07339347898960114 2023-01-23 12:17:04.657329: step: 1738/1545, loss: 0.060961879789829254 2023-01-23 12:17:05.502078: step: 1740/1545, loss: 0.027754534035921097 2023-01-23 12:17:06.343173: step: 1742/1545, loss: 0.0350518599152565 2023-01-23 12:17:07.299467: step: 1744/1545, loss: 0.06501208245754242 2023-01-23 12:17:08.177957: step: 1746/1545, loss: 0.043857332319021225 2023-01-23 12:17:09.057424: step: 1748/1545, loss: 0.3978559076786041 2023-01-23 12:17:09.931801: step: 1750/1545, loss: 0.0739620104432106 2023-01-23 12:17:10.865363: step: 1752/1545, loss: 0.2424592673778534 2023-01-23 12:17:11.692046: step: 1754/1545, loss: 0.0038659749552607536 2023-01-23 12:17:12.618767: step: 1756/1545, loss: 0.05845580995082855 2023-01-23 12:17:13.516870: step: 1758/1545, loss: 0.04448126256465912 2023-01-23 12:17:14.389753: step: 1760/1545, loss: 0.000506280513945967 2023-01-23 12:17:15.250927: step: 1762/1545, loss: 0.08439978212118149 2023-01-23 12:17:16.133239: step: 1764/1545, loss: 0.03366709128022194 2023-01-23 12:17:16.984965: step: 1766/1545, loss: 0.1456700563430786 2023-01-23 12:17:17.866914: step: 1768/1545, loss: 0.15820153057575226 2023-01-23 12:17:18.734406: step: 1770/1545, loss: 0.1712293028831482 2023-01-23 12:17:19.638392: step: 1772/1545, loss: 0.0033860388211905956 2023-01-23 12:17:20.541194: step: 1774/1545, loss: 0.07178889214992523 2023-01-23 12:17:21.423695: step: 1776/1545, loss: 0.4334547221660614 2023-01-23 12:17:22.279874: step: 1778/1545, loss: 0.1794453263282776 2023-01-23 12:17:23.211677: step: 1780/1545, loss: 0.2264825701713562 2023-01-23 12:17:24.058205: step: 1782/1545, loss: 0.009024709463119507 2023-01-23 12:17:24.941600: step: 1784/1545, loss: 0.3747802972793579 2023-01-23 12:17:25.904325: step: 1786/1545, loss: 0.032644886523485184 2023-01-23 12:17:26.794802: step: 1788/1545, loss: 0.04863709583878517 2023-01-23 12:17:27.665744: step: 1790/1545, loss: 0.7332435250282288 2023-01-23 12:17:28.577034: step: 1792/1545, loss: 0.022031264379620552 2023-01-23 12:17:29.453930: step: 1794/1545, loss: 0.40952229499816895 2023-01-23 12:17:30.299363: step: 1796/1545, loss: 0.2924502491950989 2023-01-23 12:17:31.174877: step: 1798/1545, loss: 0.0024728926364332438 2023-01-23 12:17:32.051033: step: 1800/1545, loss: 0.35246703028678894 2023-01-23 12:17:32.907939: step: 1802/1545, loss: 0.03735482692718506 2023-01-23 12:17:33.770968: step: 1804/1545, loss: 0.28224971890449524 2023-01-23 12:17:34.631737: step: 1806/1545, loss: 0.013055171817541122 2023-01-23 12:17:35.514471: step: 1808/1545, loss: 0.19431765377521515 2023-01-23 12:17:36.399724: step: 1810/1545, loss: 0.14586971700191498 2023-01-23 12:17:37.270338: step: 1812/1545, loss: 0.03339032456278801 2023-01-23 12:17:38.184907: step: 1814/1545, loss: 1.0950003862380981 2023-01-23 12:17:39.054014: step: 1816/1545, loss: 0.20572875440120697 2023-01-23 12:17:39.931962: step: 1818/1545, loss: 0.002239859662950039 2023-01-23 12:17:40.812943: step: 1820/1545, loss: 0.12818443775177002 2023-01-23 12:17:41.731529: step: 1822/1545, loss: 0.05702807009220123 2023-01-23 12:17:42.624590: step: 1824/1545, loss: 0.5143297910690308 2023-01-23 12:17:43.506021: step: 1826/1545, loss: 0.13560254871845245 2023-01-23 12:17:44.350584: step: 1828/1545, loss: 0.18051747977733612 2023-01-23 12:17:45.210214: step: 1830/1545, loss: 0.10815654695034027 2023-01-23 12:17:46.090725: step: 1832/1545, loss: 0.06011171638965607 2023-01-23 12:17:46.945174: step: 1834/1545, loss: 0.01675930991768837 2023-01-23 12:17:47.828422: step: 1836/1545, loss: 0.14358587563037872 2023-01-23 12:17:48.730262: step: 1838/1545, loss: 0.07625312358140945 2023-01-23 12:17:49.618757: step: 1840/1545, loss: 0.0295155830681324 2023-01-23 12:17:50.546601: step: 1842/1545, loss: 0.1034960076212883 2023-01-23 12:17:51.455903: step: 1844/1545, loss: 0.0565272681415081 2023-01-23 12:17:52.346016: step: 1846/1545, loss: 0.9792730212211609 2023-01-23 12:17:53.202555: step: 1848/1545, loss: 0.0036082768347114325 2023-01-23 12:17:54.067710: step: 1850/1545, loss: 0.15435393154621124 2023-01-23 12:17:54.952721: step: 1852/1545, loss: 0.21773342788219452 2023-01-23 12:17:55.842195: step: 1854/1545, loss: 0.08535611629486084 2023-01-23 12:17:56.826041: step: 1856/1545, loss: 0.13550104200839996 2023-01-23 12:17:57.696942: step: 1858/1545, loss: 0.05371087044477463 2023-01-23 12:17:58.589233: step: 1860/1545, loss: 0.16456352174282074 2023-01-23 12:17:59.542752: step: 1862/1545, loss: 0.12422583252191544 2023-01-23 12:18:00.433251: step: 1864/1545, loss: 0.10085215419530869 2023-01-23 12:18:01.293705: step: 1866/1545, loss: 0.08232957869768143 2023-01-23 12:18:02.197339: step: 1868/1545, loss: 0.01519654132425785 2023-01-23 12:18:03.104418: step: 1870/1545, loss: 0.10371756553649902 2023-01-23 12:18:03.963063: step: 1872/1545, loss: 0.005029682070016861 2023-01-23 12:18:04.823210: step: 1874/1545, loss: 0.009386659599840641 2023-01-23 12:18:05.710767: step: 1876/1545, loss: 0.20346835255622864 2023-01-23 12:18:06.617681: step: 1878/1545, loss: 0.06618962436914444 2023-01-23 12:18:07.470728: step: 1880/1545, loss: 0.05484243854880333 2023-01-23 12:18:08.358481: step: 1882/1545, loss: 0.020861497148871422 2023-01-23 12:18:09.306808: step: 1884/1545, loss: 0.03509209677577019 2023-01-23 12:18:10.155018: step: 1886/1545, loss: 0.17871370911598206 2023-01-23 12:18:11.079911: step: 1888/1545, loss: 0.08579619228839874 2023-01-23 12:18:11.948788: step: 1890/1545, loss: 0.0020653665997087955 2023-01-23 12:18:12.888709: step: 1892/1545, loss: 0.3095385432243347 2023-01-23 12:18:13.789825: step: 1894/1545, loss: 0.4119144082069397 2023-01-23 12:18:14.687470: step: 1896/1545, loss: 0.18239948153495789 2023-01-23 12:18:15.541721: step: 1898/1545, loss: 0.1005888432264328 2023-01-23 12:18:16.388950: step: 1900/1545, loss: 0.29429489374160767 2023-01-23 12:18:17.311352: step: 1902/1545, loss: 0.20549197494983673 2023-01-23 12:18:18.184218: step: 1904/1545, loss: 0.6071079969406128 2023-01-23 12:18:19.035235: step: 1906/1545, loss: 0.02704024314880371 2023-01-23 12:18:19.900795: step: 1908/1545, loss: 0.3074498772621155 2023-01-23 12:18:20.784476: step: 1910/1545, loss: 0.14129644632339478 2023-01-23 12:18:21.645194: step: 1912/1545, loss: 0.24949787557125092 2023-01-23 12:18:22.552830: step: 1914/1545, loss: 0.002527758479118347 2023-01-23 12:18:23.445799: step: 1916/1545, loss: 0.1540481150150299 2023-01-23 12:18:24.305262: step: 1918/1545, loss: 0.14631067216396332 2023-01-23 12:18:25.191580: step: 1920/1545, loss: 0.11980849504470825 2023-01-23 12:18:26.028431: step: 1922/1545, loss: 0.016924705356359482 2023-01-23 12:18:26.893482: step: 1924/1545, loss: 0.3652968108654022 2023-01-23 12:18:27.760843: step: 1926/1545, loss: 0.036476414650678635 2023-01-23 12:18:28.621883: step: 1928/1545, loss: 0.0035951549652963877 2023-01-23 12:18:29.462966: step: 1930/1545, loss: 0.003328512655571103 2023-01-23 12:18:30.446385: step: 1932/1545, loss: 0.005396068096160889 2023-01-23 12:18:31.336367: step: 1934/1545, loss: 0.239145889878273 2023-01-23 12:18:32.213512: step: 1936/1545, loss: 0.03779158741235733 2023-01-23 12:18:33.115591: step: 1938/1545, loss: 5.37743616104126 2023-01-23 12:18:33.986298: step: 1940/1545, loss: 0.023464135825634003 2023-01-23 12:18:34.849967: step: 1942/1545, loss: 0.01731838658452034 2023-01-23 12:18:35.734866: step: 1944/1545, loss: 0.4551568329334259 2023-01-23 12:18:36.628669: step: 1946/1545, loss: 0.04360034316778183 2023-01-23 12:18:37.506999: step: 1948/1545, loss: 0.45172327756881714 2023-01-23 12:18:38.421932: step: 1950/1545, loss: 0.28585243225097656 2023-01-23 12:18:39.276274: step: 1952/1545, loss: 0.012818369083106518 2023-01-23 12:18:40.190053: step: 1954/1545, loss: 0.3381008803844452 2023-01-23 12:18:41.072424: step: 1956/1545, loss: 0.12108670175075531 2023-01-23 12:18:41.953377: step: 1958/1545, loss: 0.07542359083890915 2023-01-23 12:18:42.847148: step: 1960/1545, loss: 0.10905160009860992 2023-01-23 12:18:43.763164: step: 1962/1545, loss: 0.032738957554101944 2023-01-23 12:18:44.618032: step: 1964/1545, loss: 0.002628528978675604 2023-01-23 12:18:45.520091: step: 1966/1545, loss: 0.013168912380933762 2023-01-23 12:18:46.426201: step: 1968/1545, loss: 0.056339383125305176 2023-01-23 12:18:47.282003: step: 1970/1545, loss: 0.013411134481430054 2023-01-23 12:18:48.141569: step: 1972/1545, loss: 0.0010061482898890972 2023-01-23 12:18:49.062156: step: 1974/1545, loss: 0.0024310823064297438 2023-01-23 12:18:49.898857: step: 1976/1545, loss: 0.011619605123996735 2023-01-23 12:18:50.780868: step: 1978/1545, loss: 0.05522081255912781 2023-01-23 12:18:51.656141: step: 1980/1545, loss: 0.01167879905551672 2023-01-23 12:18:52.527685: step: 1982/1545, loss: 0.8219925165176392 2023-01-23 12:18:53.393716: step: 1984/1545, loss: 0.002930473769083619 2023-01-23 12:18:54.307835: step: 1986/1545, loss: 0.10636994987726212 2023-01-23 12:18:55.218106: step: 1988/1545, loss: 0.14787869155406952 2023-01-23 12:18:56.117987: step: 1990/1545, loss: 0.0036124985199421644 2023-01-23 12:18:56.992528: step: 1992/1545, loss: 0.08647474646568298 2023-01-23 12:18:57.845437: step: 1994/1545, loss: 0.4736696779727936 2023-01-23 12:18:58.849120: step: 1996/1545, loss: 0.012918979860842228 2023-01-23 12:18:59.756305: step: 1998/1545, loss: 0.6224790811538696 2023-01-23 12:19:00.612434: step: 2000/1545, loss: 0.022584015503525734 2023-01-23 12:19:01.473815: step: 2002/1545, loss: 0.11306395381689072 2023-01-23 12:19:02.371581: step: 2004/1545, loss: 0.09251780062913895 2023-01-23 12:19:03.262842: step: 2006/1545, loss: 0.176506906747818 2023-01-23 12:19:04.160367: step: 2008/1545, loss: 0.18394021689891815 2023-01-23 12:19:05.050642: step: 2010/1545, loss: 0.02016596682369709 2023-01-23 12:19:05.927683: step: 2012/1545, loss: 0.04971950873732567 2023-01-23 12:19:06.788657: step: 2014/1545, loss: 0.38298338651657104 2023-01-23 12:19:07.707342: step: 2016/1545, loss: 0.002736274618655443 2023-01-23 12:19:08.571738: step: 2018/1545, loss: 0.1722550243139267 2023-01-23 12:19:09.420442: step: 2020/1545, loss: 0.27005311846733093 2023-01-23 12:19:10.306362: step: 2022/1545, loss: 0.42148375511169434 2023-01-23 12:19:11.201804: step: 2024/1545, loss: 0.15986013412475586 2023-01-23 12:19:12.140116: step: 2026/1545, loss: 0.42155003547668457 2023-01-23 12:19:13.015678: step: 2028/1545, loss: 0.3342331051826477 2023-01-23 12:19:13.884454: step: 2030/1545, loss: 0.05285697057843208 2023-01-23 12:19:14.808126: step: 2032/1545, loss: 0.03896354138851166 2023-01-23 12:19:15.692011: step: 2034/1545, loss: 0.05751064792275429 2023-01-23 12:19:16.534692: step: 2036/1545, loss: 0.23734940588474274 2023-01-23 12:19:17.402084: step: 2038/1545, loss: 0.022434551268815994 2023-01-23 12:19:18.238644: step: 2040/1545, loss: 0.25101569294929504 2023-01-23 12:19:19.082606: step: 2042/1545, loss: 0.025171350687742233 2023-01-23 12:19:19.970002: step: 2044/1545, loss: 0.2515406012535095 2023-01-23 12:19:20.970463: step: 2046/1545, loss: 0.10348542034626007 2023-01-23 12:19:21.859911: step: 2048/1545, loss: 0.2091951072216034 2023-01-23 12:19:22.736845: step: 2050/1545, loss: 0.014795505441725254 2023-01-23 12:19:23.614579: step: 2052/1545, loss: 0.08365181088447571 2023-01-23 12:19:24.511769: step: 2054/1545, loss: 0.043646734207868576 2023-01-23 12:19:25.383489: step: 2056/1545, loss: 0.15492889285087585 2023-01-23 12:19:26.266980: step: 2058/1545, loss: 0.07108404487371445 2023-01-23 12:19:27.113841: step: 2060/1545, loss: 0.010235742665827274 2023-01-23 12:19:27.993467: step: 2062/1545, loss: 0.02920268103480339 2023-01-23 12:19:28.910679: step: 2064/1545, loss: 0.17128491401672363 2023-01-23 12:19:29.834466: step: 2066/1545, loss: 0.03730667009949684 2023-01-23 12:19:30.697935: step: 2068/1545, loss: 0.15880045294761658 2023-01-23 12:19:31.562518: step: 2070/1545, loss: 0.010127587243914604 2023-01-23 12:19:32.459460: step: 2072/1545, loss: 0.010437519289553165 2023-01-23 12:19:33.363841: step: 2074/1545, loss: 1.3640514612197876 2023-01-23 12:19:34.251392: step: 2076/1545, loss: 0.045979633927345276 2023-01-23 12:19:35.139665: step: 2078/1545, loss: 0.056057095527648926 2023-01-23 12:19:35.997189: step: 2080/1545, loss: 0.20426034927368164 2023-01-23 12:19:36.844821: step: 2082/1545, loss: 0.14817987382411957 2023-01-23 12:19:37.709813: step: 2084/1545, loss: 0.1429082453250885 2023-01-23 12:19:38.563922: step: 2086/1545, loss: 0.09361531585454941 2023-01-23 12:19:39.481844: step: 2088/1545, loss: 0.30609431862831116 2023-01-23 12:19:40.382110: step: 2090/1545, loss: 0.15887990593910217 2023-01-23 12:19:41.283752: step: 2092/1545, loss: 0.03732534870505333 2023-01-23 12:19:42.148781: step: 2094/1545, loss: 0.023521633818745613 2023-01-23 12:19:43.081871: step: 2096/1545, loss: 0.017717113718390465 2023-01-23 12:19:43.957419: step: 2098/1545, loss: 0.07808371633291245 2023-01-23 12:19:44.847899: step: 2100/1545, loss: 0.04619697853922844 2023-01-23 12:19:45.733793: step: 2102/1545, loss: 0.051469672471284866 2023-01-23 12:19:46.638624: step: 2104/1545, loss: 0.08983245491981506 2023-01-23 12:19:47.591956: step: 2106/1545, loss: 0.0975242331624031 2023-01-23 12:19:48.457819: step: 2108/1545, loss: 0.17239905893802643 2023-01-23 12:19:49.315210: step: 2110/1545, loss: 0.018369946628808975 2023-01-23 12:19:50.172481: step: 2112/1545, loss: 0.2298053503036499 2023-01-23 12:19:51.102077: step: 2114/1545, loss: 0.14009270071983337 2023-01-23 12:19:51.971558: step: 2116/1545, loss: 0.01079204585403204 2023-01-23 12:19:52.888062: step: 2118/1545, loss: 0.1429576426744461 2023-01-23 12:19:53.727072: step: 2120/1545, loss: 0.10848964005708694 2023-01-23 12:19:54.598560: step: 2122/1545, loss: 0.23897956311702728 2023-01-23 12:19:55.460525: step: 2124/1545, loss: 0.17837384343147278 2023-01-23 12:19:56.369183: step: 2126/1545, loss: 0.22962802648544312 2023-01-23 12:19:57.236346: step: 2128/1545, loss: 0.15183886885643005 2023-01-23 12:19:58.076016: step: 2130/1545, loss: 0.25794342160224915 2023-01-23 12:19:58.935829: step: 2132/1545, loss: 0.06760647892951965 2023-01-23 12:19:59.800957: step: 2134/1545, loss: 0.0026504434645175934 2023-01-23 12:20:00.657424: step: 2136/1545, loss: 0.6205361485481262 2023-01-23 12:20:01.533559: step: 2138/1545, loss: 2.0406949520111084 2023-01-23 12:20:02.491681: step: 2140/1545, loss: 0.009487077593803406 2023-01-23 12:20:03.379821: step: 2142/1545, loss: 0.23856106400489807 2023-01-23 12:20:04.279719: step: 2144/1545, loss: 0.6573092341423035 2023-01-23 12:20:05.143135: step: 2146/1545, loss: 0.23999148607254028 2023-01-23 12:20:05.970816: step: 2148/1545, loss: 0.02961491420865059 2023-01-23 12:20:06.897668: step: 2150/1545, loss: 0.191409170627594 2023-01-23 12:20:07.780164: step: 2152/1545, loss: 0.13960111141204834 2023-01-23 12:20:08.700112: step: 2154/1545, loss: 0.008847344666719437 2023-01-23 12:20:09.556973: step: 2156/1545, loss: 0.08045293390750885 2023-01-23 12:20:10.407559: step: 2158/1545, loss: 0.002211644547060132 2023-01-23 12:20:11.262652: step: 2160/1545, loss: 0.0654267892241478 2023-01-23 12:20:12.141332: step: 2162/1545, loss: 0.05541996285319328 2023-01-23 12:20:13.036854: step: 2164/1545, loss: 0.05763062834739685 2023-01-23 12:20:13.905472: step: 2166/1545, loss: 0.005902700126171112 2023-01-23 12:20:14.797230: step: 2168/1545, loss: 0.1380765587091446 2023-01-23 12:20:15.626836: step: 2170/1545, loss: 0.19779497385025024 2023-01-23 12:20:16.477408: step: 2172/1545, loss: 0.08420255035161972 2023-01-23 12:20:17.348469: step: 2174/1545, loss: 0.009625285863876343 2023-01-23 12:20:18.352761: step: 2176/1545, loss: 3.310615301132202 2023-01-23 12:20:19.245023: step: 2178/1545, loss: 0.10041006654500961 2023-01-23 12:20:20.147092: step: 2180/1545, loss: 0.06108802929520607 2023-01-23 12:20:21.019506: step: 2182/1545, loss: 0.2596408724784851 2023-01-23 12:20:21.883817: step: 2184/1545, loss: 0.005807066336274147 2023-01-23 12:20:22.793540: step: 2186/1545, loss: 0.09930536150932312 2023-01-23 12:20:23.681270: step: 2188/1545, loss: 0.007392921019345522 2023-01-23 12:20:24.524992: step: 2190/1545, loss: 0.09554463624954224 2023-01-23 12:20:25.438241: step: 2192/1545, loss: 0.03836866840720177 2023-01-23 12:20:26.299297: step: 2194/1545, loss: 0.08493660390377045 2023-01-23 12:20:27.189203: step: 2196/1545, loss: 0.3751146197319031 2023-01-23 12:20:28.094068: step: 2198/1545, loss: 0.1116686686873436 2023-01-23 12:20:28.944967: step: 2200/1545, loss: 0.21037229895591736 2023-01-23 12:20:29.918655: step: 2202/1545, loss: 0.3715042769908905 2023-01-23 12:20:30.771608: step: 2204/1545, loss: 0.03302343934774399 2023-01-23 12:20:31.707378: step: 2206/1545, loss: 0.17400112748146057 2023-01-23 12:20:32.633375: step: 2208/1545, loss: 0.025880564004182816 2023-01-23 12:20:33.537837: step: 2210/1545, loss: 0.22281454503536224 2023-01-23 12:20:34.416792: step: 2212/1545, loss: 0.5024903416633606 2023-01-23 12:20:35.330890: step: 2214/1545, loss: 0.06428439170122147 2023-01-23 12:20:36.226154: step: 2216/1545, loss: 0.13969938457012177 2023-01-23 12:20:37.121419: step: 2218/1545, loss: 0.0897577628493309 2023-01-23 12:20:38.080785: step: 2220/1545, loss: 0.09314356744289398 2023-01-23 12:20:38.961383: step: 2222/1545, loss: 0.014356899075210094 2023-01-23 12:20:39.834216: step: 2224/1545, loss: 0.040883079171180725 2023-01-23 12:20:40.675010: step: 2226/1545, loss: 0.09487667679786682 2023-01-23 12:20:41.516766: step: 2228/1545, loss: 0.11009284853935242 2023-01-23 12:20:42.395599: step: 2230/1545, loss: 0.06170704960823059 2023-01-23 12:20:43.362744: step: 2232/1545, loss: 0.7722797989845276 2023-01-23 12:20:44.229309: step: 2234/1545, loss: 0.018481582403182983 2023-01-23 12:20:45.095683: step: 2236/1545, loss: 0.1308039277791977 2023-01-23 12:20:45.974080: step: 2238/1545, loss: 0.17842556536197662 2023-01-23 12:20:46.827967: step: 2240/1545, loss: 0.4715053141117096 2023-01-23 12:20:47.690612: step: 2242/1545, loss: 0.002367915352806449 2023-01-23 12:20:48.599702: step: 2244/1545, loss: 0.13655373454093933 2023-01-23 12:20:49.510351: step: 2246/1545, loss: 0.2309197187423706 2023-01-23 12:20:50.385944: step: 2248/1545, loss: 0.0372619666159153 2023-01-23 12:20:51.311903: step: 2250/1545, loss: 0.13370735943317413 2023-01-23 12:20:52.233438: step: 2252/1545, loss: 0.015285417437553406 2023-01-23 12:20:53.087941: step: 2254/1545, loss: 0.11139589548110962 2023-01-23 12:20:53.955385: step: 2256/1545, loss: 0.29349449276924133 2023-01-23 12:20:54.884966: step: 2258/1545, loss: 0.05407137796282768 2023-01-23 12:20:55.745189: step: 2260/1545, loss: 0.013191089034080505 2023-01-23 12:20:56.616723: step: 2262/1545, loss: 0.24234722554683685 2023-01-23 12:20:57.524053: step: 2264/1545, loss: 0.09375933557748795 2023-01-23 12:20:58.389629: step: 2266/1545, loss: 0.10565762221813202 2023-01-23 12:20:59.386710: step: 2268/1545, loss: 0.02781212516129017 2023-01-23 12:21:00.235312: step: 2270/1545, loss: 0.04372626170516014 2023-01-23 12:21:01.133125: step: 2272/1545, loss: 0.0878823921084404 2023-01-23 12:21:02.024746: step: 2274/1545, loss: 0.07481514662504196 2023-01-23 12:21:02.920165: step: 2276/1545, loss: 0.01942942850291729 2023-01-23 12:21:03.805244: step: 2278/1545, loss: 0.030237538740038872 2023-01-23 12:21:04.707308: step: 2280/1545, loss: 0.025013793259859085 2023-01-23 12:21:05.580475: step: 2282/1545, loss: 0.02284855954349041 2023-01-23 12:21:06.432412: step: 2284/1545, loss: 0.08970252424478531 2023-01-23 12:21:07.372580: step: 2286/1545, loss: 0.035033877938985825 2023-01-23 12:21:08.279387: step: 2288/1545, loss: 0.01487062033265829 2023-01-23 12:21:09.131018: step: 2290/1545, loss: 0.03560766950249672 2023-01-23 12:21:09.997236: step: 2292/1545, loss: 0.1791251003742218 2023-01-23 12:21:10.906909: step: 2294/1545, loss: 0.039047855883836746 2023-01-23 12:21:11.779198: step: 2296/1545, loss: 0.15678440034389496 2023-01-23 12:21:12.710036: step: 2298/1545, loss: 0.180843785405159 2023-01-23 12:21:13.635712: step: 2300/1545, loss: 0.07507586479187012 2023-01-23 12:21:14.543426: step: 2302/1545, loss: 0.006633356213569641 2023-01-23 12:21:15.396778: step: 2304/1545, loss: 0.01139310747385025 2023-01-23 12:21:16.322061: step: 2306/1545, loss: 0.02738342434167862 2023-01-23 12:21:17.185574: step: 2308/1545, loss: 0.01529870554804802 2023-01-23 12:21:18.048812: step: 2310/1545, loss: 0.05504971370100975 2023-01-23 12:21:18.978165: step: 2312/1545, loss: 0.012919100001454353 2023-01-23 12:21:19.890635: step: 2314/1545, loss: 0.021568194031715393 2023-01-23 12:21:20.774679: step: 2316/1545, loss: 0.16451871395111084 2023-01-23 12:21:21.655250: step: 2318/1545, loss: 0.19636541604995728 2023-01-23 12:21:22.571021: step: 2320/1545, loss: 0.20166368782520294 2023-01-23 12:21:23.450505: step: 2322/1545, loss: 0.015154529362916946 2023-01-23 12:21:24.320638: step: 2324/1545, loss: 0.10863690078258514 2023-01-23 12:21:25.206050: step: 2326/1545, loss: 0.012379557825624943 2023-01-23 12:21:26.084825: step: 2328/1545, loss: 0.11790899932384491 2023-01-23 12:21:26.948173: step: 2330/1545, loss: 0.0003711419412866235 2023-01-23 12:21:27.787698: step: 2332/1545, loss: 0.13821449875831604 2023-01-23 12:21:28.679395: step: 2334/1545, loss: 0.19824182987213135 2023-01-23 12:21:29.554488: step: 2336/1545, loss: 0.1908729523420334 2023-01-23 12:21:30.396153: step: 2338/1545, loss: 0.004694483708590269 2023-01-23 12:21:31.288370: step: 2340/1545, loss: 0.04463301971554756 2023-01-23 12:21:32.176276: step: 2342/1545, loss: 0.12940971553325653 2023-01-23 12:21:33.041650: step: 2344/1545, loss: 0.030971702188253403 2023-01-23 12:21:33.903305: step: 2346/1545, loss: 0.6370624899864197 2023-01-23 12:21:34.766175: step: 2348/1545, loss: 0.20882248878479004 2023-01-23 12:21:35.614162: step: 2350/1545, loss: 0.12941430509090424 2023-01-23 12:21:36.479052: step: 2352/1545, loss: 0.002583554945886135 2023-01-23 12:21:37.362584: step: 2354/1545, loss: 0.14387443661689758 2023-01-23 12:21:38.319100: step: 2356/1545, loss: 0.012545140460133553 2023-01-23 12:21:39.231013: step: 2358/1545, loss: 0.132147878408432 2023-01-23 12:21:40.083205: step: 2360/1545, loss: 1.4011389017105103 2023-01-23 12:21:41.006916: step: 2362/1545, loss: 0.5276058316230774 2023-01-23 12:21:41.913407: step: 2364/1545, loss: 0.24437877535820007 2023-01-23 12:21:42.791122: step: 2366/1545, loss: 0.028674541041254997 2023-01-23 12:21:43.653784: step: 2368/1545, loss: 0.03652248531579971 2023-01-23 12:21:44.545518: step: 2370/1545, loss: 0.029742509126663208 2023-01-23 12:21:45.433671: step: 2372/1545, loss: 0.11654596030712128 2023-01-23 12:21:46.274865: step: 2374/1545, loss: 0.049910902976989746 2023-01-23 12:21:47.131174: step: 2376/1545, loss: 0.018334615975618362 2023-01-23 12:21:47.966494: step: 2378/1545, loss: 0.10472691059112549 2023-01-23 12:21:48.805682: step: 2380/1545, loss: 0.04952685162425041 2023-01-23 12:21:49.688241: step: 2382/1545, loss: 0.0023785659577697515 2023-01-23 12:21:50.544617: step: 2384/1545, loss: 0.0716724544763565 2023-01-23 12:21:51.385395: step: 2386/1545, loss: 0.06723953038454056 2023-01-23 12:21:52.262469: step: 2388/1545, loss: 0.1557818353176117 2023-01-23 12:21:53.114676: step: 2390/1545, loss: 0.4497824013233185 2023-01-23 12:21:54.000596: step: 2392/1545, loss: 0.17115193605422974 2023-01-23 12:21:54.866164: step: 2394/1545, loss: 0.033216554671525955 2023-01-23 12:21:55.735857: step: 2396/1545, loss: 0.10872917622327805 2023-01-23 12:21:56.619108: step: 2398/1545, loss: 0.01316701527684927 2023-01-23 12:21:57.487458: step: 2400/1545, loss: 0.02295347861945629 2023-01-23 12:21:58.356418: step: 2402/1545, loss: 0.07116030901670456 2023-01-23 12:21:59.245345: step: 2404/1545, loss: 0.05446953698992729 2023-01-23 12:22:00.111100: step: 2406/1545, loss: 0.19462823867797852 2023-01-23 12:22:00.981715: step: 2408/1545, loss: 0.11251568794250488 2023-01-23 12:22:01.926113: step: 2410/1545, loss: 0.11858516186475754 2023-01-23 12:22:02.822026: step: 2412/1545, loss: 0.13444209098815918 2023-01-23 12:22:03.708256: step: 2414/1545, loss: 0.06999938935041428 2023-01-23 12:22:04.594591: step: 2416/1545, loss: 0.05107691138982773 2023-01-23 12:22:05.459901: step: 2418/1545, loss: 0.1440240889787674 2023-01-23 12:22:06.358091: step: 2420/1545, loss: 0.021116500720381737 2023-01-23 12:22:07.295760: step: 2422/1545, loss: 0.01443449966609478 2023-01-23 12:22:08.168022: step: 2424/1545, loss: 0.009021252393722534 2023-01-23 12:22:09.036051: step: 2426/1545, loss: 0.004349390044808388 2023-01-23 12:22:09.882968: step: 2428/1545, loss: 0.02742065116763115 2023-01-23 12:22:10.761639: step: 2430/1545, loss: 0.18271706998348236 2023-01-23 12:22:11.648183: step: 2432/1545, loss: 0.05537637323141098 2023-01-23 12:22:12.541649: step: 2434/1545, loss: 0.06021662428975105 2023-01-23 12:22:13.419587: step: 2436/1545, loss: 0.059544291347265244 2023-01-23 12:22:14.270246: step: 2438/1545, loss: 0.0022416170686483383 2023-01-23 12:22:15.166467: step: 2440/1545, loss: 0.31412285566329956 2023-01-23 12:22:16.066931: step: 2442/1545, loss: 0.11691828072071075 2023-01-23 12:22:16.915085: step: 2444/1545, loss: 0.023505311459302902 2023-01-23 12:22:17.807916: step: 2446/1545, loss: 0.06471498310565948 2023-01-23 12:22:18.682160: step: 2448/1545, loss: 0.16074848175048828 2023-01-23 12:22:19.527377: step: 2450/1545, loss: 0.0030744082760065794 2023-01-23 12:22:20.408132: step: 2452/1545, loss: 0.004127690102905035 2023-01-23 12:22:21.290109: step: 2454/1545, loss: 0.15929725766181946 2023-01-23 12:22:22.269373: step: 2456/1545, loss: 0.05020827054977417 2023-01-23 12:22:23.136040: step: 2458/1545, loss: 0.09464727342128754 2023-01-23 12:22:23.976702: step: 2460/1545, loss: 0.019340315833687782 2023-01-23 12:22:24.868630: step: 2462/1545, loss: 0.23608773946762085 2023-01-23 12:22:25.748906: step: 2464/1545, loss: 0.07389625906944275 2023-01-23 12:22:26.613326: step: 2466/1545, loss: 0.09234181046485901 2023-01-23 12:22:27.504990: step: 2468/1545, loss: 0.01250905729830265 2023-01-23 12:22:28.341896: step: 2470/1545, loss: 0.16308239102363586 2023-01-23 12:22:29.262435: step: 2472/1545, loss: 0.21211306750774384 2023-01-23 12:22:30.183456: step: 2474/1545, loss: 0.022413846105337143 2023-01-23 12:22:31.079014: step: 2476/1545, loss: 1.043595790863037 2023-01-23 12:22:31.938489: step: 2478/1545, loss: 0.017641346901655197 2023-01-23 12:22:32.834795: step: 2480/1545, loss: 0.1705927848815918 2023-01-23 12:22:33.693467: step: 2482/1545, loss: 0.004739928059279919 2023-01-23 12:22:34.570165: step: 2484/1545, loss: 0.07654890418052673 2023-01-23 12:22:35.403900: step: 2486/1545, loss: 0.11086086928844452 2023-01-23 12:22:36.255620: step: 2488/1545, loss: 0.15091213583946228 2023-01-23 12:22:37.143137: step: 2490/1545, loss: 0.2958064377307892 2023-01-23 12:22:37.985516: step: 2492/1545, loss: 0.08154010772705078 2023-01-23 12:22:38.837396: step: 2494/1545, loss: 0.07484211772680283 2023-01-23 12:22:39.714414: step: 2496/1545, loss: 0.08423818647861481 2023-01-23 12:22:40.603635: step: 2498/1545, loss: 0.06360696256160736 2023-01-23 12:22:41.451035: step: 2500/1545, loss: 0.21322157979011536 2023-01-23 12:22:42.311597: step: 2502/1545, loss: 0.10677650570869446 2023-01-23 12:22:43.147236: step: 2504/1545, loss: 0.041019633412361145 2023-01-23 12:22:44.046977: step: 2506/1545, loss: 0.19378022849559784 2023-01-23 12:22:44.988800: step: 2508/1545, loss: 0.05113585293292999 2023-01-23 12:22:45.869456: step: 2510/1545, loss: 0.8976846933364868 2023-01-23 12:22:46.775999: step: 2512/1545, loss: 0.12268951535224915 2023-01-23 12:22:47.733411: step: 2514/1545, loss: 0.04456600174307823 2023-01-23 12:22:48.609566: step: 2516/1545, loss: 0.02439809963107109 2023-01-23 12:22:49.488909: step: 2518/1545, loss: 0.027249310165643692 2023-01-23 12:22:50.379910: step: 2520/1545, loss: 0.170066699385643 2023-01-23 12:22:51.236731: step: 2522/1545, loss: 0.038557618856430054 2023-01-23 12:22:52.101642: step: 2524/1545, loss: 0.059230729937553406 2023-01-23 12:22:52.937217: step: 2526/1545, loss: 0.053661976009607315 2023-01-23 12:22:53.847602: step: 2528/1545, loss: 0.03994378820061684 2023-01-23 12:22:54.687490: step: 2530/1545, loss: 0.33181458711624146 2023-01-23 12:22:55.586113: step: 2532/1545, loss: 0.027733946219086647 2023-01-23 12:22:56.456434: step: 2534/1545, loss: 0.053711898624897 2023-01-23 12:22:57.411312: step: 2536/1545, loss: 0.046893611550331116 2023-01-23 12:22:58.309360: step: 2538/1545, loss: 0.11721289157867432 2023-01-23 12:22:59.157658: step: 2540/1545, loss: 0.3424058258533478 2023-01-23 12:23:00.050971: step: 2542/1545, loss: 0.15203213691711426 2023-01-23 12:23:00.968163: step: 2544/1545, loss: 0.13379822671413422 2023-01-23 12:23:01.822503: step: 2546/1545, loss: 0.011547591537237167 2023-01-23 12:23:02.713482: step: 2548/1545, loss: 0.3176431357860565 2023-01-23 12:23:03.586330: step: 2550/1545, loss: 0.09411939978599548 2023-01-23 12:23:04.478466: step: 2552/1545, loss: 0.05377589166164398 2023-01-23 12:23:05.385461: step: 2554/1545, loss: 0.3497167229652405 2023-01-23 12:23:06.258882: step: 2556/1545, loss: 0.0441010445356369 2023-01-23 12:23:07.114880: step: 2558/1545, loss: 1.3190428018569946 2023-01-23 12:23:07.962178: step: 2560/1545, loss: 0.016216807067394257 2023-01-23 12:23:08.843915: step: 2562/1545, loss: 0.014228381216526031 2023-01-23 12:23:09.708826: step: 2564/1545, loss: 0.04656153544783592 2023-01-23 12:23:10.598458: step: 2566/1545, loss: 0.2582486867904663 2023-01-23 12:23:11.499521: step: 2568/1545, loss: 0.41096416115760803 2023-01-23 12:23:12.367161: step: 2570/1545, loss: 0.023558029904961586 2023-01-23 12:23:13.269346: step: 2572/1545, loss: 0.021039653569459915 2023-01-23 12:23:14.122703: step: 2574/1545, loss: 0.038780514150857925 2023-01-23 12:23:15.034082: step: 2576/1545, loss: 0.02839958481490612 2023-01-23 12:23:15.944204: step: 2578/1545, loss: 0.046883828938007355 2023-01-23 12:23:16.809611: step: 2580/1545, loss: 0.6166428327560425 2023-01-23 12:23:17.672414: step: 2582/1545, loss: 0.02543918788433075 2023-01-23 12:23:18.531129: step: 2584/1545, loss: 0.08769592642784119 2023-01-23 12:23:19.465051: step: 2586/1545, loss: 0.12815795838832855 2023-01-23 12:23:20.323527: step: 2588/1545, loss: 0.4401451051235199 2023-01-23 12:23:21.196882: step: 2590/1545, loss: 0.18448403477668762 2023-01-23 12:23:22.069467: step: 2592/1545, loss: 0.08844371885061264 2023-01-23 12:23:22.919960: step: 2594/1545, loss: 0.057626768946647644 2023-01-23 12:23:23.780671: step: 2596/1545, loss: 0.02827269211411476 2023-01-23 12:23:24.663280: step: 2598/1545, loss: 0.2981395423412323 2023-01-23 12:23:25.530171: step: 2600/1545, loss: 0.051832109689712524 2023-01-23 12:23:26.406769: step: 2602/1545, loss: 0.10922782868146896 2023-01-23 12:23:27.307367: step: 2604/1545, loss: 0.35427260398864746 2023-01-23 12:23:28.247706: step: 2606/1545, loss: 0.10852311551570892 2023-01-23 12:23:29.119377: step: 2608/1545, loss: 0.0018965181661769748 2023-01-23 12:23:29.951657: step: 2610/1545, loss: 0.0032467020209878683 2023-01-23 12:23:30.823041: step: 2612/1545, loss: 0.1211736798286438 2023-01-23 12:23:31.690569: step: 2614/1545, loss: 0.015866994857788086 2023-01-23 12:23:32.555875: step: 2616/1545, loss: 0.03597529977560043 2023-01-23 12:23:33.417334: step: 2618/1545, loss: 0.09613645076751709 2023-01-23 12:23:34.288130: step: 2620/1545, loss: 0.006738053169101477 2023-01-23 12:23:35.174245: step: 2622/1545, loss: 0.37369227409362793 2023-01-23 12:23:36.113100: step: 2624/1545, loss: 0.06672671437263489 2023-01-23 12:23:37.018858: step: 2626/1545, loss: 0.08156164735555649 2023-01-23 12:23:37.910341: step: 2628/1545, loss: 0.0918826162815094 2023-01-23 12:23:38.790115: step: 2630/1545, loss: 0.4940539598464966 2023-01-23 12:23:39.715408: step: 2632/1545, loss: 0.4468419849872589 2023-01-23 12:23:40.613602: step: 2634/1545, loss: 0.14769385755062103 2023-01-23 12:23:41.492625: step: 2636/1545, loss: 0.01992161013185978 2023-01-23 12:23:42.455165: step: 2638/1545, loss: 0.1714525818824768 2023-01-23 12:23:43.313734: step: 2640/1545, loss: 0.27599334716796875 2023-01-23 12:23:44.181439: step: 2642/1545, loss: 0.03540605306625366 2023-01-23 12:23:45.065880: step: 2644/1545, loss: 0.020892590284347534 2023-01-23 12:23:45.926715: step: 2646/1545, loss: 0.05639109015464783 2023-01-23 12:23:46.876633: step: 2648/1545, loss: 0.24335432052612305 2023-01-23 12:23:47.751537: step: 2650/1545, loss: 0.09560185670852661 2023-01-23 12:23:48.610436: step: 2652/1545, loss: 0.011821502819657326 2023-01-23 12:23:49.489045: step: 2654/1545, loss: 0.08464499562978745 2023-01-23 12:23:50.334196: step: 2656/1545, loss: 0.02572694979608059 2023-01-23 12:23:51.196503: step: 2658/1545, loss: 0.256378173828125 2023-01-23 12:23:52.082526: step: 2660/1545, loss: 0.02028195932507515 2023-01-23 12:23:52.950598: step: 2662/1545, loss: 0.05337591469287872 2023-01-23 12:23:53.829301: step: 2664/1545, loss: 0.07444431632757187 2023-01-23 12:23:54.729038: step: 2666/1545, loss: 0.07645654678344727 2023-01-23 12:23:55.629202: step: 2668/1545, loss: 0.008150981739163399 2023-01-23 12:23:56.497883: step: 2670/1545, loss: 0.03937341645359993 2023-01-23 12:23:57.356476: step: 2672/1545, loss: 0.11655022948980331 2023-01-23 12:23:58.254624: step: 2674/1545, loss: 0.08260217308998108 2023-01-23 12:23:59.134782: step: 2676/1545, loss: 0.012888988479971886 2023-01-23 12:24:00.132008: step: 2678/1545, loss: 0.6156141757965088 2023-01-23 12:24:01.044125: step: 2680/1545, loss: 0.11152777075767517 2023-01-23 12:24:01.900149: step: 2682/1545, loss: 0.16709120571613312 2023-01-23 12:24:02.771555: step: 2684/1545, loss: 0.1844727247953415 2023-01-23 12:24:03.630378: step: 2686/1545, loss: 0.13092964887619019 2023-01-23 12:24:04.517858: step: 2688/1545, loss: 0.18886798620224 2023-01-23 12:24:05.447037: step: 2690/1545, loss: 0.006838398054242134 2023-01-23 12:24:06.321097: step: 2692/1545, loss: 0.11323753744363785 2023-01-23 12:24:07.182985: step: 2694/1545, loss: 0.05601583421230316 2023-01-23 12:24:08.060219: step: 2696/1545, loss: 0.4671114683151245 2023-01-23 12:24:08.939876: step: 2698/1545, loss: 0.40829500555992126 2023-01-23 12:24:09.833956: step: 2700/1545, loss: 0.24208363890647888 2023-01-23 12:24:10.730955: step: 2702/1545, loss: 0.2805863618850708 2023-01-23 12:24:11.615337: step: 2704/1545, loss: 0.0167539045214653 2023-01-23 12:24:12.520133: step: 2706/1545, loss: 0.06133219972252846 2023-01-23 12:24:13.399617: step: 2708/1545, loss: 0.048310548067092896 2023-01-23 12:24:14.263116: step: 2710/1545, loss: 0.06024857982993126 2023-01-23 12:24:15.177952: step: 2712/1545, loss: 0.07048337161540985 2023-01-23 12:24:16.096438: step: 2714/1545, loss: 0.08359276503324509 2023-01-23 12:24:16.974083: step: 2716/1545, loss: 0.01950254663825035 2023-01-23 12:24:17.830497: step: 2718/1545, loss: 0.025015302002429962 2023-01-23 12:24:18.739082: step: 2720/1545, loss: 0.41436251997947693 2023-01-23 12:24:19.676483: step: 2722/1545, loss: 0.04715544730424881 2023-01-23 12:24:20.524747: step: 2724/1545, loss: 0.012644169852137566 2023-01-23 12:24:21.402912: step: 2726/1545, loss: 0.14754420518875122 2023-01-23 12:24:22.276863: step: 2728/1545, loss: 0.05711040273308754 2023-01-23 12:24:23.130296: step: 2730/1545, loss: 0.033933356404304504 2023-01-23 12:24:24.022199: step: 2732/1545, loss: 0.01857774145901203 2023-01-23 12:24:24.880555: step: 2734/1545, loss: 0.025359133258461952 2023-01-23 12:24:25.820249: step: 2736/1545, loss: 0.022369682788848877 2023-01-23 12:24:26.675983: step: 2738/1545, loss: 0.018730707466602325 2023-01-23 12:24:27.556082: step: 2740/1545, loss: 0.02617020718753338 2023-01-23 12:24:28.427451: step: 2742/1545, loss: 0.16171026229858398 2023-01-23 12:24:29.314919: step: 2744/1545, loss: 0.050030454993247986 2023-01-23 12:24:30.194474: step: 2746/1545, loss: 0.042478643357753754 2023-01-23 12:24:31.045510: step: 2748/1545, loss: 0.2842980623245239 2023-01-23 12:24:31.954557: step: 2750/1545, loss: 0.128694549202919 2023-01-23 12:24:32.811447: step: 2752/1545, loss: 0.1291172355413437 2023-01-23 12:24:33.668480: step: 2754/1545, loss: 0.003389368997886777 2023-01-23 12:24:34.574991: step: 2756/1545, loss: 0.001424396294169128 2023-01-23 12:24:35.415674: step: 2758/1545, loss: 0.00890674814581871 2023-01-23 12:24:36.235855: step: 2760/1545, loss: 0.0017311907140538096 2023-01-23 12:24:37.122979: step: 2762/1545, loss: 0.19611279666423798 2023-01-23 12:24:38.055049: step: 2764/1545, loss: 0.45376208424568176 2023-01-23 12:24:38.981765: step: 2766/1545, loss: 0.044692423194646835 2023-01-23 12:24:39.859418: step: 2768/1545, loss: 0.16626441478729248 2023-01-23 12:24:40.703980: step: 2770/1545, loss: 0.10765935480594635 2023-01-23 12:24:41.631973: step: 2772/1545, loss: 0.13212093710899353 2023-01-23 12:24:42.511514: step: 2774/1545, loss: 0.10205142199993134 2023-01-23 12:24:43.362033: step: 2776/1545, loss: 0.18564105033874512 2023-01-23 12:24:44.232402: step: 2778/1545, loss: 1.4122998714447021 2023-01-23 12:24:45.072271: step: 2780/1545, loss: 0.12022414803504944 2023-01-23 12:24:45.962804: step: 2782/1545, loss: 0.01649017073214054 2023-01-23 12:24:46.886755: step: 2784/1545, loss: 0.6283696293830872 2023-01-23 12:24:47.761356: step: 2786/1545, loss: 0.5405502319335938 2023-01-23 12:24:48.644971: step: 2788/1545, loss: 0.5073129534721375 2023-01-23 12:24:49.505174: step: 2790/1545, loss: 0.11125385016202927 2023-01-23 12:24:50.351723: step: 2792/1545, loss: 0.056681446731090546 2023-01-23 12:24:51.273964: step: 2794/1545, loss: 0.040661003440618515 2023-01-23 12:24:52.093459: step: 2796/1545, loss: 0.24207153916358948 2023-01-23 12:24:52.977010: step: 2798/1545, loss: 0.12074905633926392 2023-01-23 12:24:53.871850: step: 2800/1545, loss: 0.014939327724277973 2023-01-23 12:24:54.768294: step: 2802/1545, loss: 0.18112418055534363 2023-01-23 12:24:55.631344: step: 2804/1545, loss: 0.18383023142814636 2023-01-23 12:24:56.510270: step: 2806/1545, loss: 0.0234775822609663 2023-01-23 12:24:57.365617: step: 2808/1545, loss: 0.17453618347644806 2023-01-23 12:24:58.212452: step: 2810/1545, loss: 0.0077534266747534275 2023-01-23 12:24:59.090479: step: 2812/1545, loss: 0.019940972328186035 2023-01-23 12:24:59.975565: step: 2814/1545, loss: 0.686890721321106 2023-01-23 12:25:00.855154: step: 2816/1545, loss: 0.3209477365016937 2023-01-23 12:25:01.737740: step: 2818/1545, loss: 0.09812252223491669 2023-01-23 12:25:02.737078: step: 2820/1545, loss: 0.011323935352265835 2023-01-23 12:25:03.598548: step: 2822/1545, loss: 0.01438608206808567 2023-01-23 12:25:04.434707: step: 2824/1545, loss: 0.1077907606959343 2023-01-23 12:25:05.288743: step: 2826/1545, loss: 0.0980946272611618 2023-01-23 12:25:06.128971: step: 2828/1545, loss: 0.05489024519920349 2023-01-23 12:25:07.005225: step: 2830/1545, loss: 0.029639998450875282 2023-01-23 12:25:07.889461: step: 2832/1545, loss: 0.29444000124931335 2023-01-23 12:25:08.716209: step: 2834/1545, loss: 0.00572088360786438 2023-01-23 12:25:09.595970: step: 2836/1545, loss: 0.06755916774272919 2023-01-23 12:25:10.565926: step: 2838/1545, loss: 0.34421834349632263 2023-01-23 12:25:11.407150: step: 2840/1545, loss: 0.13208156824111938 2023-01-23 12:25:12.307638: step: 2842/1545, loss: 0.09390244632959366 2023-01-23 12:25:13.185515: step: 2844/1545, loss: 0.28322911262512207 2023-01-23 12:25:14.048806: step: 2846/1545, loss: 0.019504403695464134 2023-01-23 12:25:14.901135: step: 2848/1545, loss: 0.004483414813876152 2023-01-23 12:25:15.779030: step: 2850/1545, loss: 0.01590579003095627 2023-01-23 12:25:16.687855: step: 2852/1545, loss: 0.021973678842186928 2023-01-23 12:25:17.608441: step: 2854/1545, loss: 2.6450417041778564 2023-01-23 12:25:18.462666: step: 2856/1545, loss: 0.011942246928811073 2023-01-23 12:25:19.385585: step: 2858/1545, loss: 0.09792273491621017 2023-01-23 12:25:20.257347: step: 2860/1545, loss: 0.005585013888776302 2023-01-23 12:25:21.127465: step: 2862/1545, loss: 0.1636960655450821 2023-01-23 12:25:22.032535: step: 2864/1545, loss: 0.18917417526245117 2023-01-23 12:25:22.902860: step: 2866/1545, loss: 0.08514425158500671 2023-01-23 12:25:23.798958: step: 2868/1545, loss: 0.014897690154612064 2023-01-23 12:25:24.675658: step: 2870/1545, loss: 0.17896942794322968 2023-01-23 12:25:25.523045: step: 2872/1545, loss: 0.0015369347529485822 2023-01-23 12:25:26.424636: step: 2874/1545, loss: 0.03277149423956871 2023-01-23 12:25:27.301938: step: 2876/1545, loss: 0.10820838063955307 2023-01-23 12:25:28.163560: step: 2878/1545, loss: 0.24104350805282593 2023-01-23 12:25:29.074584: step: 2880/1545, loss: 0.23642930388450623 2023-01-23 12:25:29.900296: step: 2882/1545, loss: 0.092723548412323 2023-01-23 12:25:30.774665: step: 2884/1545, loss: 0.37139129638671875 2023-01-23 12:25:31.672804: step: 2886/1545, loss: 0.030996173620224 2023-01-23 12:25:32.553815: step: 2888/1545, loss: 0.3192784786224365 2023-01-23 12:25:33.445144: step: 2890/1545, loss: 0.01866789348423481 2023-01-23 12:25:34.392171: step: 2892/1545, loss: 0.030243277549743652 2023-01-23 12:25:35.262101: step: 2894/1545, loss: 0.35398486256599426 2023-01-23 12:25:36.102673: step: 2896/1545, loss: 2.2868688106536865 2023-01-23 12:25:36.930621: step: 2898/1545, loss: 0.016164906322956085 2023-01-23 12:25:37.803202: step: 2900/1545, loss: 0.013885119929909706 2023-01-23 12:25:38.704625: step: 2902/1545, loss: 0.005861680023372173 2023-01-23 12:25:39.582759: step: 2904/1545, loss: 0.0572768896818161 2023-01-23 12:25:40.430456: step: 2906/1545, loss: 0.2823876440525055 2023-01-23 12:25:41.323631: step: 2908/1545, loss: 0.03394157439470291 2023-01-23 12:25:42.194006: step: 2910/1545, loss: 0.18237701058387756 2023-01-23 12:25:43.091925: step: 2912/1545, loss: 0.11035391688346863 2023-01-23 12:25:43.988457: step: 2914/1545, loss: 0.035547275096178055 2023-01-23 12:25:44.852476: step: 2916/1545, loss: 0.02849375084042549 2023-01-23 12:25:45.726362: step: 2918/1545, loss: 0.14682479202747345 2023-01-23 12:25:46.585023: step: 2920/1545, loss: 0.005252111703157425 2023-01-23 12:25:47.489947: step: 2922/1545, loss: 0.07862567156553268 2023-01-23 12:25:48.377265: step: 2924/1545, loss: 0.014556707814335823 2023-01-23 12:25:49.299426: step: 2926/1545, loss: 0.5945305824279785 2023-01-23 12:25:50.208239: step: 2928/1545, loss: 0.04219263046979904 2023-01-23 12:25:51.082517: step: 2930/1545, loss: 0.18199263513088226 2023-01-23 12:25:51.979785: step: 2932/1545, loss: 0.3648737072944641 2023-01-23 12:25:52.847984: step: 2934/1545, loss: 0.04648393392562866 2023-01-23 12:25:53.728402: step: 2936/1545, loss: 0.025294115766882896 2023-01-23 12:25:54.631859: step: 2938/1545, loss: 0.16571363806724548 2023-01-23 12:25:55.527947: step: 2940/1545, loss: 0.06542275100946426 2023-01-23 12:25:56.458937: step: 2942/1545, loss: 0.10453696548938751 2023-01-23 12:25:57.406250: step: 2944/1545, loss: 0.05166986212134361 2023-01-23 12:25:58.286395: step: 2946/1545, loss: 0.07714315503835678 2023-01-23 12:25:59.255782: step: 2948/1545, loss: 0.18874414265155792 2023-01-23 12:26:00.151372: step: 2950/1545, loss: 1.038442850112915 2023-01-23 12:26:01.021536: step: 2952/1545, loss: 0.04370594769716263 2023-01-23 12:26:01.869678: step: 2954/1545, loss: 0.10405660420656204 2023-01-23 12:26:02.744014: step: 2956/1545, loss: 0.01672758348286152 2023-01-23 12:26:03.634273: step: 2958/1545, loss: 0.042897697538137436 2023-01-23 12:26:04.559827: step: 2960/1545, loss: 0.045586686581373215 2023-01-23 12:26:05.475408: step: 2962/1545, loss: 0.0353480689227581 2023-01-23 12:26:06.374667: step: 2964/1545, loss: 0.272102952003479 2023-01-23 12:26:07.302009: step: 2966/1545, loss: 0.13998670876026154 2023-01-23 12:26:08.182276: step: 2968/1545, loss: 0.029660269618034363 2023-01-23 12:26:09.116283: step: 2970/1545, loss: 0.15441282093524933 2023-01-23 12:26:09.973331: step: 2972/1545, loss: 0.49265024065971375 2023-01-23 12:26:10.860581: step: 2974/1545, loss: 0.022273674607276917 2023-01-23 12:26:11.766741: step: 2976/1545, loss: 0.8247397541999817 2023-01-23 12:26:12.650409: step: 2978/1545, loss: 0.24411816895008087 2023-01-23 12:26:13.536265: step: 2980/1545, loss: 0.16959522664546967 2023-01-23 12:26:14.424072: step: 2982/1545, loss: 0.24135686457157135 2023-01-23 12:26:15.359243: step: 2984/1545, loss: 0.03871425986289978 2023-01-23 12:26:16.263987: step: 2986/1545, loss: 0.11735683679580688 2023-01-23 12:26:17.154295: step: 2988/1545, loss: 0.42266905307769775 2023-01-23 12:26:18.043040: step: 2990/1545, loss: 0.1180218905210495 2023-01-23 12:26:18.944830: step: 2992/1545, loss: 0.008241812698543072 2023-01-23 12:26:19.884136: step: 2994/1545, loss: 0.20200732350349426 2023-01-23 12:26:20.746774: step: 2996/1545, loss: 0.07991115748882294 2023-01-23 12:26:21.663265: step: 2998/1545, loss: 0.17719320952892303 2023-01-23 12:26:22.519417: step: 3000/1545, loss: 0.07691030204296112 2023-01-23 12:26:23.421541: step: 3002/1545, loss: 0.10277474671602249 2023-01-23 12:26:24.335855: step: 3004/1545, loss: 0.07009828835725784 2023-01-23 12:26:25.228657: step: 3006/1545, loss: 0.03206804394721985 2023-01-23 12:26:26.118194: step: 3008/1545, loss: 0.330583781003952 2023-01-23 12:26:27.032786: step: 3010/1545, loss: 0.08043520897626877 2023-01-23 12:26:27.872978: step: 3012/1545, loss: 0.008623508736491203 2023-01-23 12:26:28.730610: step: 3014/1545, loss: 0.20055702328681946 2023-01-23 12:26:29.598919: step: 3016/1545, loss: 0.0056185852736234665 2023-01-23 12:26:30.497562: step: 3018/1545, loss: 0.00029260211158543825 2023-01-23 12:26:31.389432: step: 3020/1545, loss: 0.1475057452917099 2023-01-23 12:26:32.234532: step: 3022/1545, loss: 0.24007417261600494 2023-01-23 12:26:33.080489: step: 3024/1545, loss: 0.12087389081716537 2023-01-23 12:26:34.004748: step: 3026/1545, loss: 0.04717066511511803 2023-01-23 12:26:34.923683: step: 3028/1545, loss: 0.027833838015794754 2023-01-23 12:26:35.811974: step: 3030/1545, loss: 0.05944126471877098 2023-01-23 12:26:36.691988: step: 3032/1545, loss: 0.4467974603176117 2023-01-23 12:26:37.600454: step: 3034/1545, loss: 0.2048465758562088 2023-01-23 12:26:38.480728: step: 3036/1545, loss: 0.2647865414619446 2023-01-23 12:26:39.368284: step: 3038/1545, loss: 0.05301670730113983 2023-01-23 12:26:40.224953: step: 3040/1545, loss: 0.18014386296272278 2023-01-23 12:26:41.122049: step: 3042/1545, loss: 0.09759239107370377 2023-01-23 12:26:42.026836: step: 3044/1545, loss: 0.6161607503890991 2023-01-23 12:26:42.916437: step: 3046/1545, loss: 0.014126705937087536 2023-01-23 12:26:43.828794: step: 3048/1545, loss: 0.04084049165248871 2023-01-23 12:26:44.694936: step: 3050/1545, loss: 0.012084425427019596 2023-01-23 12:26:45.581845: step: 3052/1545, loss: 0.18963958323001862 2023-01-23 12:26:46.445927: step: 3054/1545, loss: 0.02133057452738285 2023-01-23 12:26:47.338337: step: 3056/1545, loss: 0.02296522445976734 2023-01-23 12:26:48.302426: step: 3058/1545, loss: 0.012195048853754997 2023-01-23 12:26:49.242841: step: 3060/1545, loss: 0.2233353555202484 2023-01-23 12:26:50.129449: step: 3062/1545, loss: 0.06737319380044937 2023-01-23 12:26:51.004684: step: 3064/1545, loss: 0.21462371945381165 2023-01-23 12:26:51.929078: step: 3066/1545, loss: 0.05360819771885872 2023-01-23 12:26:52.792179: step: 3068/1545, loss: 0.012641018256545067 2023-01-23 12:26:53.620801: step: 3070/1545, loss: 0.0076963938772678375 2023-01-23 12:26:54.488533: step: 3072/1545, loss: 0.11560144275426865 2023-01-23 12:26:55.413636: step: 3074/1545, loss: 0.04792410135269165 2023-01-23 12:26:56.297440: step: 3076/1545, loss: 0.008429447188973427 2023-01-23 12:26:57.151305: step: 3078/1545, loss: 0.012842436321079731 2023-01-23 12:26:58.049636: step: 3080/1545, loss: 0.01566418632864952 2023-01-23 12:26:58.975055: step: 3082/1545, loss: 0.020061476156115532 2023-01-23 12:26:59.864924: step: 3084/1545, loss: 0.17881178855895996 2023-01-23 12:27:00.749596: step: 3086/1545, loss: 0.7292872667312622 2023-01-23 12:27:01.623084: step: 3088/1545, loss: 0.016615955159068108 2023-01-23 12:27:02.556895: step: 3090/1545, loss: 0.4995597302913666 ================================================== Loss: 0.148 -------------------- Dev Chinese: {'event': {'p': 0.6030534351145038, 'r': 0.7363515312916112, 'f1': 0.6630695443645084}, 'argument': {'p': 0.6532830345792509, 'r': 0.6659966265695656, 'f1': 0.6595785716063304}, 'combined': 0.43734646294760277, 'epoch': 15} Test Chinese: {'event': {'p': 0.6430096051227321, 'r': 0.770460358056266, 'f1': 0.7009889470622455}, 'argument': {'p': 0.6948353928350569, 'r': 0.7316987972640924, 'f1': 0.7127907971117018}, 'combined': 0.4996584703429905, 'epoch': 15} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6585116653200844, 'r': 0.6649385809726077, 'f1': 0.6617095180093489}, 'combined': 0.4427293712086574, 'epoch': 15} Test Korean: {'event': {'p': 0.6312169312169312, 'r': 0.7627877237851662, 'f1': 0.6907932831499711}, 'argument': {'p': 0.687670847656362, 'r': 0.7257871599308927, 'f1': 0.7062150680227693}, 'combined': 0.48784862544942903, 'epoch': 15} Dev Russian: {'event': {'p': 0.5728346456692913, 'r': 0.7749667110519307, 'f1': 0.6587436332767402}, 'argument': {'p': 0.6523178704592026, 'r': 0.6681825396978385, 'f1': 0.660154904945285}, 'combined': 0.43487284060911807, 'epoch': 15} Test Russian: {'event': {'p': 0.630293971101146, 'r': 0.8088235294117647, 'f1': 0.7084850182021843}, 'argument': {'p': 0.6983500056232312, 'r': 0.7388909235526697, 'f1': 0.7180486864005926}, 'combined': 0.5087267366545785, 'epoch': 15} Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.657262277951933, 'r': 0.6301026796894564, 'f1': 0.643395985168137}, 'combined': 0.438679080796457, 'epoch': 15} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6113428997329925, 'r': 0.47734993540795306, 'f1': 0.5361006966889319}, 'combined': 0.3385899136982728, 'epoch': 15} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5554601722730378, 'r': 0.5356223089775722, 'f1': 0.545360896413528}, 'combined': 0.3175519143673707, 'epoch': 15} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6192560175054704, 'r': 0.7536617842876165, 'f1': 0.6798798798798799}, 'argument': {'p': 0.6632184815074122, 'r': 0.6433020105912738, 'f1': 0.6531084436795553}, 'combined': 0.44403529023739136, 'epoch': 14} Test for Korean: {'event': {'p': 0.6343915343915344, 'r': 0.7666240409207161, 'f1': 0.694267515923567}, 'argument': {'p': 0.7134384328444346, 'r': 0.7077112894615091, 'f1': 0.7105633211403983}, 'combined': 0.4933210318745441, 'epoch': 14} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6992753623188407, 'r': 0.44063926940639275, 'f1': 0.5406162464985995}, 'combined': 0.34144183989385235, 'epoch': 14} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 16 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 12:32:17.516305: step: 2/1545, loss: 0.03986426070332527 2023-01-23 12:32:18.384193: step: 4/1545, loss: 0.04942755401134491 2023-01-23 12:32:19.367645: step: 6/1545, loss: 0.037790343165397644 2023-01-23 12:32:20.222878: step: 8/1545, loss: 0.004872114397585392 2023-01-23 12:32:21.095316: step: 10/1545, loss: 0.0420159287750721 2023-01-23 12:32:22.054849: step: 12/1545, loss: 0.017349179834127426 2023-01-23 12:32:22.931997: step: 14/1545, loss: 0.034668177366256714 2023-01-23 12:32:23.894819: step: 16/1545, loss: 0.056211017072200775 2023-01-23 12:32:24.767556: step: 18/1545, loss: 0.0022108431439846754 2023-01-23 12:32:25.681684: step: 20/1545, loss: 0.015932820737361908 2023-01-23 12:32:26.603045: step: 22/1545, loss: 1.5732128620147705 2023-01-23 12:32:27.478979: step: 24/1545, loss: 0.004133815411478281 2023-01-23 12:32:28.400493: step: 26/1545, loss: 0.005120824556797743 2023-01-23 12:32:29.318100: step: 28/1545, loss: 0.09023326635360718 2023-01-23 12:32:30.200121: step: 30/1545, loss: 0.010395465418696404 2023-01-23 12:32:31.072888: step: 32/1545, loss: 0.06043633073568344 2023-01-23 12:32:31.928600: step: 34/1545, loss: 0.0788608118891716 2023-01-23 12:32:32.741202: step: 36/1545, loss: 0.10195378959178925 2023-01-23 12:32:33.624352: step: 38/1545, loss: 0.8735794425010681 2023-01-23 12:32:34.516320: step: 40/1545, loss: 0.23655281960964203 2023-01-23 12:32:35.495169: step: 42/1545, loss: 0.26414722204208374 2023-01-23 12:32:36.395580: step: 44/1545, loss: 0.00788105372339487 2023-01-23 12:32:37.291643: step: 46/1545, loss: 0.09233954548835754 2023-01-23 12:32:38.203605: step: 48/1545, loss: 0.02065691538155079 2023-01-23 12:32:39.107426: step: 50/1545, loss: 0.1246802806854248 2023-01-23 12:32:40.012481: step: 52/1545, loss: 0.12670183181762695 2023-01-23 12:32:40.898413: step: 54/1545, loss: 0.023773621767759323 2023-01-23 12:32:41.809709: step: 56/1545, loss: 0.036226462572813034 2023-01-23 12:32:42.687302: step: 58/1545, loss: 0.007476892787963152 2023-01-23 12:32:43.554194: step: 60/1545, loss: 0.003196276258677244 2023-01-23 12:32:44.369692: step: 62/1545, loss: 0.017695944756269455 2023-01-23 12:32:45.256871: step: 64/1545, loss: 0.04698187857866287 2023-01-23 12:32:46.136148: step: 66/1545, loss: 0.0023331372067332268 2023-01-23 12:32:47.010320: step: 68/1545, loss: 0.03294336795806885 2023-01-23 12:32:47.896606: step: 70/1545, loss: 0.01742587797343731 2023-01-23 12:32:48.787643: step: 72/1545, loss: 0.17413339018821716 2023-01-23 12:32:49.672332: step: 74/1545, loss: 0.04909257963299751 2023-01-23 12:32:50.528383: step: 76/1545, loss: 0.004982814192771912 2023-01-23 12:32:51.373470: step: 78/1545, loss: 0.03043205291032791 2023-01-23 12:32:52.262176: step: 80/1545, loss: 0.0332336351275444 2023-01-23 12:32:53.169934: step: 82/1545, loss: 0.02472274750471115 2023-01-23 12:32:54.074506: step: 84/1545, loss: 0.24385829269886017 2023-01-23 12:32:54.963306: step: 86/1545, loss: 0.340573787689209 2023-01-23 12:32:55.852919: step: 88/1545, loss: 0.025422044098377228 2023-01-23 12:32:56.784263: step: 90/1545, loss: 0.2561784088611603 2023-01-23 12:32:57.709610: step: 92/1545, loss: 0.0665188729763031 2023-01-23 12:32:58.630802: step: 94/1545, loss: 0.09061835706233978 2023-01-23 12:32:59.479677: step: 96/1545, loss: 0.019265983253717422 2023-01-23 12:33:00.345601: step: 98/1545, loss: 0.10881917178630829 2023-01-23 12:33:01.185783: step: 100/1545, loss: 0.17520955204963684 2023-01-23 12:33:02.071340: step: 102/1545, loss: 0.19081398844718933 2023-01-23 12:33:02.966005: step: 104/1545, loss: 0.0037375991232693195 2023-01-23 12:33:03.905377: step: 106/1545, loss: 0.23855629563331604 2023-01-23 12:33:04.771652: step: 108/1545, loss: 0.2802058160305023 2023-01-23 12:33:05.639948: step: 110/1545, loss: 0.30739134550094604 2023-01-23 12:33:06.529213: step: 112/1545, loss: 0.10038676857948303 2023-01-23 12:33:07.433039: step: 114/1545, loss: 0.008703329600393772 2023-01-23 12:33:08.407943: step: 116/1545, loss: 0.2224625051021576 2023-01-23 12:33:09.269454: step: 118/1545, loss: 0.16682375967502594 2023-01-23 12:33:10.152385: step: 120/1545, loss: 0.01642213575541973 2023-01-23 12:33:11.014952: step: 122/1545, loss: 0.012061107903718948 2023-01-23 12:33:11.950127: step: 124/1545, loss: 0.0036133811809122562 2023-01-23 12:33:12.762129: step: 126/1545, loss: 0.01014835573732853 2023-01-23 12:33:13.599774: step: 128/1545, loss: 0.09146124124526978 2023-01-23 12:33:14.572112: step: 130/1545, loss: 0.011012526229023933 2023-01-23 12:33:15.442483: step: 132/1545, loss: 0.0562439039349556 2023-01-23 12:33:16.326957: step: 134/1545, loss: 0.015979936346411705 2023-01-23 12:33:17.186313: step: 136/1545, loss: 0.03857762739062309 2023-01-23 12:33:18.033251: step: 138/1545, loss: 0.12027852982282639 2023-01-23 12:33:18.914112: step: 140/1545, loss: 0.06971193850040436 2023-01-23 12:33:19.793050: step: 142/1545, loss: 0.16701510548591614 2023-01-23 12:33:20.683856: step: 144/1545, loss: 0.022236468270421028 2023-01-23 12:33:21.545085: step: 146/1545, loss: 0.004603493493050337 2023-01-23 12:33:22.487711: step: 148/1545, loss: 0.11545617878437042 2023-01-23 12:33:23.396882: step: 150/1545, loss: 0.0017206016927957535 2023-01-23 12:33:24.300406: step: 152/1545, loss: 0.02924695424735546 2023-01-23 12:33:25.202485: step: 154/1545, loss: 0.020108692348003387 2023-01-23 12:33:26.105748: step: 156/1545, loss: 0.007280899677425623 2023-01-23 12:33:27.001039: step: 158/1545, loss: 0.30838847160339355 2023-01-23 12:33:27.857926: step: 160/1545, loss: 0.007845625281333923 2023-01-23 12:33:28.733236: step: 162/1545, loss: 0.2824997305870056 2023-01-23 12:33:29.644146: step: 164/1545, loss: 0.4637555181980133 2023-01-23 12:33:30.522354: step: 166/1545, loss: 0.12696979939937592 2023-01-23 12:33:31.434110: step: 168/1545, loss: 0.1284613311290741 2023-01-23 12:33:32.301521: step: 170/1545, loss: 0.0037322118878364563 2023-01-23 12:33:33.205761: step: 172/1545, loss: 0.0015970616368576884 2023-01-23 12:33:34.099406: step: 174/1545, loss: 0.09994588047266006 2023-01-23 12:33:34.949026: step: 176/1545, loss: 0.0786278173327446 2023-01-23 12:33:35.823132: step: 178/1545, loss: 0.694133460521698 2023-01-23 12:33:36.674100: step: 180/1545, loss: 0.054154958575963974 2023-01-23 12:33:37.527336: step: 182/1545, loss: 0.09499655663967133 2023-01-23 12:33:38.416010: step: 184/1545, loss: 0.040258925408124924 2023-01-23 12:33:39.276848: step: 186/1545, loss: 0.01011321134865284 2023-01-23 12:33:40.125829: step: 188/1545, loss: 0.18138742446899414 2023-01-23 12:33:40.993427: step: 190/1545, loss: 0.002596963429823518 2023-01-23 12:33:41.889331: step: 192/1545, loss: 0.011275106109678745 2023-01-23 12:33:42.750651: step: 194/1545, loss: 0.11970502883195877 2023-01-23 12:33:43.628476: step: 196/1545, loss: 0.057533156126737595 2023-01-23 12:33:44.512966: step: 198/1545, loss: 0.1682155728340149 2023-01-23 12:33:45.369334: step: 200/1545, loss: 0.017616325989365578 2023-01-23 12:33:46.274625: step: 202/1545, loss: 0.09135910868644714 2023-01-23 12:33:47.116527: step: 204/1545, loss: 0.17076463997364044 2023-01-23 12:33:48.040130: step: 206/1545, loss: 0.016894690692424774 2023-01-23 12:33:48.898547: step: 208/1545, loss: 0.003685377072542906 2023-01-23 12:33:49.729270: step: 210/1545, loss: 0.003697315463796258 2023-01-23 12:33:50.635583: step: 212/1545, loss: 0.0017410845030099154 2023-01-23 12:33:51.497586: step: 214/1545, loss: 5.022714614868164 2023-01-23 12:33:52.394848: step: 216/1545, loss: 0.3097570836544037 2023-01-23 12:33:53.272506: step: 218/1545, loss: 0.19856809079647064 2023-01-23 12:33:54.151427: step: 220/1545, loss: 0.05135802552103996 2023-01-23 12:33:55.018384: step: 222/1545, loss: 0.06006113067269325 2023-01-23 12:33:55.883792: step: 224/1545, loss: 0.10573340207338333 2023-01-23 12:33:56.828531: step: 226/1545, loss: 0.30466169118881226 2023-01-23 12:33:57.719549: step: 228/1545, loss: 0.09234979003667831 2023-01-23 12:33:58.607289: step: 230/1545, loss: 0.19852222502231598 2023-01-23 12:33:59.477111: step: 232/1545, loss: 0.0026794089935719967 2023-01-23 12:34:00.388249: step: 234/1545, loss: 0.03755664825439453 2023-01-23 12:34:01.265771: step: 236/1545, loss: 0.16694609820842743 2023-01-23 12:34:02.119895: step: 238/1545, loss: 0.09964274615049362 2023-01-23 12:34:03.064633: step: 240/1545, loss: 0.0009508068906143308 2023-01-23 12:34:03.953445: step: 242/1545, loss: 0.033865757286548615 2023-01-23 12:34:04.875067: step: 244/1545, loss: 0.27498066425323486 2023-01-23 12:34:05.756359: step: 246/1545, loss: 0.021744009107351303 2023-01-23 12:34:06.616295: step: 248/1545, loss: 0.02502838522195816 2023-01-23 12:34:07.597354: step: 250/1545, loss: 0.023511387407779694 2023-01-23 12:34:08.443129: step: 252/1545, loss: 0.032976049929857254 2023-01-23 12:34:09.365642: step: 254/1545, loss: 0.04219479858875275 2023-01-23 12:34:10.241403: step: 256/1545, loss: 0.3519552946090698 2023-01-23 12:34:11.167006: step: 258/1545, loss: 0.004204586148262024 2023-01-23 12:34:12.068711: step: 260/1545, loss: 0.008398161269724369 2023-01-23 12:34:12.972822: step: 262/1545, loss: 0.030301149934530258 2023-01-23 12:34:13.850233: step: 264/1545, loss: 0.02776358649134636 2023-01-23 12:34:14.767671: step: 266/1545, loss: 0.03261386230587959 2023-01-23 12:34:15.612394: step: 268/1545, loss: 0.10763591527938843 2023-01-23 12:34:16.492583: step: 270/1545, loss: 0.002364128828048706 2023-01-23 12:34:17.388414: step: 272/1545, loss: 0.26352447271347046 2023-01-23 12:34:18.273810: step: 274/1545, loss: 0.005833080504089594 2023-01-23 12:34:19.301955: step: 276/1545, loss: 0.04942268505692482 2023-01-23 12:34:20.192202: step: 278/1545, loss: 0.027918925508856773 2023-01-23 12:34:21.140428: step: 280/1545, loss: 0.032626088708639145 2023-01-23 12:34:22.026564: step: 282/1545, loss: 0.00414039334282279 2023-01-23 12:34:22.927722: step: 284/1545, loss: 0.2011454552412033 2023-01-23 12:34:23.832205: step: 286/1545, loss: 0.07564026862382889 2023-01-23 12:34:24.724886: step: 288/1545, loss: 0.0024963412433862686 2023-01-23 12:34:25.617557: step: 290/1545, loss: 0.018117405474185944 2023-01-23 12:34:26.503163: step: 292/1545, loss: 0.030184809118509293 2023-01-23 12:34:27.374520: step: 294/1545, loss: 0.008442005142569542 2023-01-23 12:34:28.299490: step: 296/1545, loss: 0.003935332875698805 2023-01-23 12:34:29.186583: step: 298/1545, loss: 0.006563382688909769 2023-01-23 12:34:30.063399: step: 300/1545, loss: 0.23426945507526398 2023-01-23 12:34:30.947260: step: 302/1545, loss: 0.033243417739868164 2023-01-23 12:34:31.805079: step: 304/1545, loss: 0.002261541085317731 2023-01-23 12:34:32.665294: step: 306/1545, loss: 0.21340277791023254 2023-01-23 12:34:33.570973: step: 308/1545, loss: 0.21690332889556885 2023-01-23 12:34:34.440570: step: 310/1545, loss: 0.12666067481040955 2023-01-23 12:34:35.351032: step: 312/1545, loss: 0.058600880205631256 2023-01-23 12:34:36.202078: step: 314/1545, loss: 0.016185734421014786 2023-01-23 12:34:37.142884: step: 316/1545, loss: 0.055470168590545654 2023-01-23 12:34:38.048429: step: 318/1545, loss: 1.714260220527649 2023-01-23 12:34:38.945748: step: 320/1545, loss: 0.2077668309211731 2023-01-23 12:34:39.846034: step: 322/1545, loss: 0.0008766254759393632 2023-01-23 12:34:40.696809: step: 324/1545, loss: 0.15067189931869507 2023-01-23 12:34:41.591887: step: 326/1545, loss: 0.040088213980197906 2023-01-23 12:34:42.451492: step: 328/1545, loss: 0.15909703075885773 2023-01-23 12:34:43.346534: step: 330/1545, loss: 0.07140015810728073 2023-01-23 12:34:44.193693: step: 332/1545, loss: 0.04135693609714508 2023-01-23 12:34:45.061308: step: 334/1545, loss: 0.013132307678461075 2023-01-23 12:34:45.956294: step: 336/1545, loss: 0.4433523714542389 2023-01-23 12:34:46.825030: step: 338/1545, loss: 0.033328503370285034 2023-01-23 12:34:47.700661: step: 340/1545, loss: 0.01901235803961754 2023-01-23 12:34:48.612089: step: 342/1545, loss: 0.6364791393280029 2023-01-23 12:34:49.505351: step: 344/1545, loss: 0.264358252286911 2023-01-23 12:34:50.482225: step: 346/1545, loss: 0.0071809981018304825 2023-01-23 12:34:51.384876: step: 348/1545, loss: 0.03383854776620865 2023-01-23 12:34:52.233529: step: 350/1545, loss: 1.6077057123184204 2023-01-23 12:34:53.099666: step: 352/1545, loss: 0.18041998147964478 2023-01-23 12:34:53.942364: step: 354/1545, loss: 0.06556558609008789 2023-01-23 12:34:54.801897: step: 356/1545, loss: 0.1772189885377884 2023-01-23 12:34:55.664535: step: 358/1545, loss: 0.016820212826132774 2023-01-23 12:34:56.534718: step: 360/1545, loss: 0.30675122141838074 2023-01-23 12:34:57.469986: step: 362/1545, loss: 0.061392053961753845 2023-01-23 12:34:58.315740: step: 364/1545, loss: 0.31022214889526367 2023-01-23 12:34:59.176149: step: 366/1545, loss: 0.1443084478378296 2023-01-23 12:35:00.044267: step: 368/1545, loss: 0.06563279032707214 2023-01-23 12:35:00.885181: step: 370/1545, loss: 0.0176132433116436 2023-01-23 12:35:01.785835: step: 372/1545, loss: 0.00863413792103529 2023-01-23 12:35:02.613976: step: 374/1545, loss: 0.015464958734810352 2023-01-23 12:35:03.503019: step: 376/1545, loss: 0.048254914581775665 2023-01-23 12:35:04.382206: step: 378/1545, loss: 0.030231330543756485 2023-01-23 12:35:05.238893: step: 380/1545, loss: 0.09449504315853119 2023-01-23 12:35:06.136886: step: 382/1545, loss: 0.03746365010738373 2023-01-23 12:35:06.994090: step: 384/1545, loss: 0.0729108452796936 2023-01-23 12:35:07.862005: step: 386/1545, loss: 0.016783010214567184 2023-01-23 12:35:08.764735: step: 388/1545, loss: 0.03636164590716362 2023-01-23 12:35:09.646405: step: 390/1545, loss: 0.15439079701900482 2023-01-23 12:35:10.478232: step: 392/1545, loss: 0.08905624598264694 2023-01-23 12:35:11.382544: step: 394/1545, loss: 0.07407595217227936 2023-01-23 12:35:12.263043: step: 396/1545, loss: 0.26257672905921936 2023-01-23 12:35:13.126352: step: 398/1545, loss: 0.026964813470840454 2023-01-23 12:35:14.000154: step: 400/1545, loss: 0.14644160866737366 2023-01-23 12:35:14.847601: step: 402/1545, loss: 0.001611556624993682 2023-01-23 12:35:15.704693: step: 404/1545, loss: 0.0020106665324419737 2023-01-23 12:35:16.566161: step: 406/1545, loss: 0.11742982268333435 2023-01-23 12:35:17.418819: step: 408/1545, loss: 0.029679883271455765 2023-01-23 12:35:18.290690: step: 410/1545, loss: 1.1303119659423828 2023-01-23 12:35:19.151910: step: 412/1545, loss: 0.20115217566490173 2023-01-23 12:35:20.045398: step: 414/1545, loss: 0.14175540208816528 2023-01-23 12:35:20.929902: step: 416/1545, loss: 0.055159151554107666 2023-01-23 12:35:21.796230: step: 418/1545, loss: 0.0030533578246831894 2023-01-23 12:35:22.732636: step: 420/1545, loss: 0.14620652794837952 2023-01-23 12:35:23.664687: step: 422/1545, loss: 0.018118469044566154 2023-01-23 12:35:24.498020: step: 424/1545, loss: 0.15668006241321564 2023-01-23 12:35:25.344883: step: 426/1545, loss: 0.02472924441099167 2023-01-23 12:35:26.201434: step: 428/1545, loss: 0.0020436840131878853 2023-01-23 12:35:27.075351: step: 430/1545, loss: 0.022830018773674965 2023-01-23 12:35:27.938502: step: 432/1545, loss: 0.037946056574583054 2023-01-23 12:35:28.784958: step: 434/1545, loss: 0.010700750164687634 2023-01-23 12:35:29.650331: step: 436/1545, loss: 1.0678316354751587 2023-01-23 12:35:30.501110: step: 438/1545, loss: 0.03496811166405678 2023-01-23 12:35:31.360721: step: 440/1545, loss: 0.009112861007452011 2023-01-23 12:35:32.270501: step: 442/1545, loss: 0.17137573659420013 2023-01-23 12:35:33.102003: step: 444/1545, loss: 0.07025996595621109 2023-01-23 12:35:34.001167: step: 446/1545, loss: 0.1389315277338028 2023-01-23 12:35:34.877630: step: 448/1545, loss: 0.03744892030954361 2023-01-23 12:35:35.749019: step: 450/1545, loss: 0.07101075351238251 2023-01-23 12:35:36.636330: step: 452/1545, loss: 0.05653424188494682 2023-01-23 12:35:37.519929: step: 454/1545, loss: 0.06641827523708344 2023-01-23 12:35:38.354017: step: 456/1545, loss: 0.003725634189322591 2023-01-23 12:35:39.230258: step: 458/1545, loss: 0.08222851902246475 2023-01-23 12:35:40.083018: step: 460/1545, loss: 0.10693048685789108 2023-01-23 12:35:40.949903: step: 462/1545, loss: 0.05287328362464905 2023-01-23 12:35:41.784995: step: 464/1545, loss: 0.00856845173984766 2023-01-23 12:35:42.635787: step: 466/1545, loss: 0.1289720982313156 2023-01-23 12:35:43.506118: step: 468/1545, loss: 0.013045248575508595 2023-01-23 12:35:44.374887: step: 470/1545, loss: 0.03789655119180679 2023-01-23 12:35:45.252806: step: 472/1545, loss: 0.003208145499229431 2023-01-23 12:35:46.234406: step: 474/1545, loss: 0.18488828837871552 2023-01-23 12:35:47.099395: step: 476/1545, loss: 0.0465615950524807 2023-01-23 12:35:47.951049: step: 478/1545, loss: 0.0039562201127409935 2023-01-23 12:35:48.777978: step: 480/1545, loss: 0.012055379338562489 2023-01-23 12:35:49.674380: step: 482/1545, loss: 0.022807208821177483 2023-01-23 12:35:50.617854: step: 484/1545, loss: 0.08105108141899109 2023-01-23 12:35:51.475512: step: 486/1545, loss: 0.04240398854017258 2023-01-23 12:35:52.341610: step: 488/1545, loss: 0.47126996517181396 2023-01-23 12:35:53.204517: step: 490/1545, loss: 0.0059632714837789536 2023-01-23 12:35:54.109391: step: 492/1545, loss: 0.4645768404006958 2023-01-23 12:35:54.988282: step: 494/1545, loss: 0.017759336158633232 2023-01-23 12:35:55.825642: step: 496/1545, loss: 0.04213797673583031 2023-01-23 12:35:56.709191: step: 498/1545, loss: 0.6403753161430359 2023-01-23 12:35:57.659761: step: 500/1545, loss: 0.01725451834499836 2023-01-23 12:35:58.518870: step: 502/1545, loss: 0.0650954619050026 2023-01-23 12:35:59.355658: step: 504/1545, loss: 0.2650696635246277 2023-01-23 12:36:00.229002: step: 506/1545, loss: 0.019129863008856773 2023-01-23 12:36:01.096909: step: 508/1545, loss: 0.21193276345729828 2023-01-23 12:36:01.997322: step: 510/1545, loss: 0.2877557575702667 2023-01-23 12:36:02.935661: step: 512/1545, loss: 0.020896580070257187 2023-01-23 12:36:03.828680: step: 514/1545, loss: 0.06419293582439423 2023-01-23 12:36:04.690110: step: 516/1545, loss: 0.09414228796958923 2023-01-23 12:36:05.538610: step: 518/1545, loss: 0.1010851040482521 2023-01-23 12:36:06.369875: step: 520/1545, loss: 0.009154084138572216 2023-01-23 12:36:07.304613: step: 522/1545, loss: 0.022804129868745804 2023-01-23 12:36:08.174101: step: 524/1545, loss: 0.07735983282327652 2023-01-23 12:36:09.066250: step: 526/1545, loss: 0.002950609428808093 2023-01-23 12:36:09.887018: step: 528/1545, loss: 0.15090197324752808 2023-01-23 12:36:10.811457: step: 530/1545, loss: 0.014558304101228714 2023-01-23 12:36:11.701626: step: 532/1545, loss: 0.1072947084903717 2023-01-23 12:36:12.565548: step: 534/1545, loss: 0.0011395749170333147 2023-01-23 12:36:13.422620: step: 536/1545, loss: 0.003702897345647216 2023-01-23 12:36:14.303590: step: 538/1545, loss: 0.03805093094706535 2023-01-23 12:36:15.192474: step: 540/1545, loss: 0.32157090306282043 2023-01-23 12:36:16.039940: step: 542/1545, loss: 0.1687811315059662 2023-01-23 12:36:16.873983: step: 544/1545, loss: 0.14962807297706604 2023-01-23 12:36:17.738473: step: 546/1545, loss: 0.3611273765563965 2023-01-23 12:36:18.627714: step: 548/1545, loss: 0.1738716959953308 2023-01-23 12:36:19.470878: step: 550/1545, loss: 0.009308433160185814 2023-01-23 12:36:20.320338: step: 552/1545, loss: 0.020017938688397408 2023-01-23 12:36:21.245920: step: 554/1545, loss: 0.01694379560649395 2023-01-23 12:36:22.102010: step: 556/1545, loss: 0.059744637459516525 2023-01-23 12:36:22.956483: step: 558/1545, loss: 0.0005011390894651413 2023-01-23 12:36:23.804320: step: 560/1545, loss: 0.06655146926641464 2023-01-23 12:36:24.663008: step: 562/1545, loss: 0.005230501294136047 2023-01-23 12:36:25.523949: step: 564/1545, loss: 0.14381031692028046 2023-01-23 12:36:26.387403: step: 566/1545, loss: 0.020949291065335274 2023-01-23 12:36:27.273697: step: 568/1545, loss: 0.15702441334724426 2023-01-23 12:36:28.135676: step: 570/1545, loss: 0.01569732464849949 2023-01-23 12:36:28.966002: step: 572/1545, loss: 0.06171197071671486 2023-01-23 12:36:29.860462: step: 574/1545, loss: 0.2987525165081024 2023-01-23 12:36:30.727372: step: 576/1545, loss: 0.03133809193968773 2023-01-23 12:36:31.580017: step: 578/1545, loss: 0.13776323199272156 2023-01-23 12:36:32.470793: step: 580/1545, loss: 0.07041068375110626 2023-01-23 12:36:33.319548: step: 582/1545, loss: 0.017850607633590698 2023-01-23 12:36:34.184646: step: 584/1545, loss: 0.3389715552330017 2023-01-23 12:36:35.066244: step: 586/1545, loss: 0.3947989344596863 2023-01-23 12:36:35.954429: step: 588/1545, loss: 0.2152854949235916 2023-01-23 12:36:36.807190: step: 590/1545, loss: 0.14102990925312042 2023-01-23 12:36:37.685787: step: 592/1545, loss: 0.00469894427806139 2023-01-23 12:36:38.554442: step: 594/1545, loss: 0.06592502444982529 2023-01-23 12:36:39.446683: step: 596/1545, loss: 1.2817234992980957 2023-01-23 12:36:40.321820: step: 598/1545, loss: 0.00628444692119956 2023-01-23 12:36:41.180989: step: 600/1545, loss: 0.07295598089694977 2023-01-23 12:36:42.062418: step: 602/1545, loss: 0.09538440406322479 2023-01-23 12:36:42.934010: step: 604/1545, loss: 0.47217857837677 2023-01-23 12:36:43.782063: step: 606/1545, loss: 0.010897258296608925 2023-01-23 12:36:44.613393: step: 608/1545, loss: 0.5971806049346924 2023-01-23 12:36:45.472990: step: 610/1545, loss: 0.12169652432203293 2023-01-23 12:36:46.344508: step: 612/1545, loss: 0.1304265707731247 2023-01-23 12:36:47.217292: step: 614/1545, loss: 0.0026595615781843662 2023-01-23 12:36:48.062585: step: 616/1545, loss: 0.03329627215862274 2023-01-23 12:36:48.915749: step: 618/1545, loss: 0.011961398646235466 2023-01-23 12:36:49.805811: step: 620/1545, loss: 0.08467701077461243 2023-01-23 12:36:50.691664: step: 622/1545, loss: 0.16949592530727386 2023-01-23 12:36:51.575776: step: 624/1545, loss: 0.00795077160000801 2023-01-23 12:36:52.418651: step: 626/1545, loss: 0.18212151527404785 2023-01-23 12:36:53.327524: step: 628/1545, loss: 0.015127413906157017 2023-01-23 12:36:54.217504: step: 630/1545, loss: 0.11628742516040802 2023-01-23 12:36:55.074273: step: 632/1545, loss: 0.023391395807266235 2023-01-23 12:36:55.997207: step: 634/1545, loss: 0.03148050978779793 2023-01-23 12:36:56.871642: step: 636/1545, loss: 0.009980572387576103 2023-01-23 12:36:57.767323: step: 638/1545, loss: 0.18581123650074005 2023-01-23 12:36:58.657012: step: 640/1545, loss: 0.23723064363002777 2023-01-23 12:36:59.521277: step: 642/1545, loss: 0.5509203672409058 2023-01-23 12:37:00.367811: step: 644/1545, loss: 0.06228601187467575 2023-01-23 12:37:01.282335: step: 646/1545, loss: 0.10524818301200867 2023-01-23 12:37:02.152880: step: 648/1545, loss: 0.0212640892714262 2023-01-23 12:37:03.065609: step: 650/1545, loss: 0.30540648102760315 2023-01-23 12:37:04.011113: step: 652/1545, loss: 0.007583345752209425 2023-01-23 12:37:04.915717: step: 654/1545, loss: 0.08504724502563477 2023-01-23 12:37:05.791753: step: 656/1545, loss: 0.03234207630157471 2023-01-23 12:37:06.676443: step: 658/1545, loss: 0.11257842928171158 2023-01-23 12:37:07.551602: step: 660/1545, loss: 0.2819458842277527 2023-01-23 12:37:08.399894: step: 662/1545, loss: 0.25420859456062317 2023-01-23 12:37:09.247076: step: 664/1545, loss: 0.08223234862089157 2023-01-23 12:37:10.120194: step: 666/1545, loss: 0.01472510863095522 2023-01-23 12:37:10.986641: step: 668/1545, loss: 0.00419999472796917 2023-01-23 12:37:11.873074: step: 670/1545, loss: 0.11728742718696594 2023-01-23 12:37:12.722240: step: 672/1545, loss: 1.8019994497299194 2023-01-23 12:37:13.555058: step: 674/1545, loss: 0.02441413141787052 2023-01-23 12:37:14.432802: step: 676/1545, loss: 0.013447828590869904 2023-01-23 12:37:15.324688: step: 678/1545, loss: 0.2744607925415039 2023-01-23 12:37:16.225476: step: 680/1545, loss: 0.04903287813067436 2023-01-23 12:37:17.059637: step: 682/1545, loss: 0.007843776606023312 2023-01-23 12:37:17.900977: step: 684/1545, loss: 0.37621983885765076 2023-01-23 12:37:18.740764: step: 686/1545, loss: 0.18148061633110046 2023-01-23 12:37:19.641283: step: 688/1545, loss: 0.17359322309494019 2023-01-23 12:37:20.515930: step: 690/1545, loss: 0.010155762545764446 2023-01-23 12:37:21.513522: step: 692/1545, loss: 0.014175050891935825 2023-01-23 12:37:22.415945: step: 694/1545, loss: 0.15127688646316528 2023-01-23 12:37:23.271926: step: 696/1545, loss: 0.006998746190220118 2023-01-23 12:37:24.155699: step: 698/1545, loss: 0.07659504562616348 2023-01-23 12:37:25.042963: step: 700/1545, loss: 0.01117740198969841 2023-01-23 12:37:25.921338: step: 702/1545, loss: 0.017039069905877113 2023-01-23 12:37:26.804026: step: 704/1545, loss: 0.2811623513698578 2023-01-23 12:37:27.680098: step: 706/1545, loss: 0.08508973568677902 2023-01-23 12:37:28.571790: step: 708/1545, loss: 0.02880859188735485 2023-01-23 12:37:29.494589: step: 710/1545, loss: 0.100760817527771 2023-01-23 12:37:30.379531: step: 712/1545, loss: 0.3210958242416382 2023-01-23 12:37:31.255824: step: 714/1545, loss: 0.032298244535923004 2023-01-23 12:37:32.085940: step: 716/1545, loss: 0.011605052277445793 2023-01-23 12:37:32.955721: step: 718/1545, loss: 0.008655117824673653 2023-01-23 12:37:33.854432: step: 720/1545, loss: 0.002216271823272109 2023-01-23 12:37:34.690474: step: 722/1545, loss: 0.04803834110498428 2023-01-23 12:37:35.596557: step: 724/1545, loss: 0.033891461789608 2023-01-23 12:37:36.512706: step: 726/1545, loss: 0.26176145672798157 2023-01-23 12:37:37.375180: step: 728/1545, loss: 0.013661274686455727 2023-01-23 12:37:38.241570: step: 730/1545, loss: 0.0501222237944603 2023-01-23 12:37:39.144026: step: 732/1545, loss: 0.15757742524147034 2023-01-23 12:37:40.008097: step: 734/1545, loss: 0.035041678696870804 2023-01-23 12:37:40.924456: step: 736/1545, loss: 0.00480304192751646 2023-01-23 12:37:41.813918: step: 738/1545, loss: 0.161879301071167 2023-01-23 12:37:42.741939: step: 740/1545, loss: 0.08419571071863174 2023-01-23 12:37:43.583838: step: 742/1545, loss: 0.23185604810714722 2023-01-23 12:37:44.454268: step: 744/1545, loss: 0.10929212719202042 2023-01-23 12:37:45.323497: step: 746/1545, loss: 0.08946894854307175 2023-01-23 12:37:46.218148: step: 748/1545, loss: 0.012868001125752926 2023-01-23 12:37:47.080275: step: 750/1545, loss: 0.00030127610079944134 2023-01-23 12:37:47.970921: step: 752/1545, loss: 0.0033634828869253397 2023-01-23 12:37:48.896858: step: 754/1545, loss: 0.04405684396624565 2023-01-23 12:37:49.739277: step: 756/1545, loss: 0.031487300992012024 2023-01-23 12:37:50.597429: step: 758/1545, loss: 0.4538213312625885 2023-01-23 12:37:51.483189: step: 760/1545, loss: 0.6200878024101257 2023-01-23 12:37:52.413705: step: 762/1545, loss: 0.16731716692447662 2023-01-23 12:37:53.330482: step: 764/1545, loss: 0.19250783324241638 2023-01-23 12:37:54.176705: step: 766/1545, loss: 0.4238739609718323 2023-01-23 12:37:55.103413: step: 768/1545, loss: 0.09548487514257431 2023-01-23 12:37:55.977959: step: 770/1545, loss: 0.27722451090812683 2023-01-23 12:37:56.857903: step: 772/1545, loss: 0.05841566622257233 2023-01-23 12:37:57.682164: step: 774/1545, loss: 0.014767960645258427 2023-01-23 12:37:58.550990: step: 776/1545, loss: 0.10719093680381775 2023-01-23 12:37:59.431308: step: 778/1545, loss: 0.06030759960412979 2023-01-23 12:38:00.303165: step: 780/1545, loss: 0.08949260413646698 2023-01-23 12:38:01.168884: step: 782/1545, loss: 0.1110394224524498 2023-01-23 12:38:02.042591: step: 784/1545, loss: 0.050856247544288635 2023-01-23 12:38:02.945919: step: 786/1545, loss: 0.4391377866268158 2023-01-23 12:38:03.791684: step: 788/1545, loss: 0.8744685053825378 2023-01-23 12:38:04.681137: step: 790/1545, loss: 0.005735498387366533 2023-01-23 12:38:05.580679: step: 792/1545, loss: 0.2033572494983673 2023-01-23 12:38:06.451144: step: 794/1545, loss: 0.1486874222755432 2023-01-23 12:38:07.298820: step: 796/1545, loss: 0.003919793758541346 2023-01-23 12:38:08.154942: step: 798/1545, loss: 0.07066132873296738 2023-01-23 12:38:09.095623: step: 800/1545, loss: 0.09213864803314209 2023-01-23 12:38:09.939473: step: 802/1545, loss: 0.023266492411494255 2023-01-23 12:38:10.763525: step: 804/1545, loss: 0.20889893174171448 2023-01-23 12:38:11.615541: step: 806/1545, loss: 0.27794939279556274 2023-01-23 12:38:12.546415: step: 808/1545, loss: 0.15525229275226593 2023-01-23 12:38:13.437211: step: 810/1545, loss: 0.0017841689987108111 2023-01-23 12:38:14.401918: step: 812/1545, loss: 0.18534286320209503 2023-01-23 12:38:15.286785: step: 814/1545, loss: 0.01732470467686653 2023-01-23 12:38:16.162645: step: 816/1545, loss: 0.2570693790912628 2023-01-23 12:38:17.048674: step: 818/1545, loss: 0.006709282286465168 2023-01-23 12:38:17.918700: step: 820/1545, loss: 0.14348353445529938 2023-01-23 12:38:18.806403: step: 822/1545, loss: 0.11982665210962296 2023-01-23 12:38:19.676805: step: 824/1545, loss: 0.04449618607759476 2023-01-23 12:38:20.508722: step: 826/1545, loss: 0.2247457653284073 2023-01-23 12:38:21.372458: step: 828/1545, loss: 0.10341842472553253 2023-01-23 12:38:22.226652: step: 830/1545, loss: 0.01573917455971241 2023-01-23 12:38:23.130676: step: 832/1545, loss: 0.7801722288131714 2023-01-23 12:38:24.037366: step: 834/1545, loss: 0.1483391523361206 2023-01-23 12:38:24.923612: step: 836/1545, loss: 0.5060770511627197 2023-01-23 12:38:25.872051: step: 838/1545, loss: 0.06918428838253021 2023-01-23 12:38:26.736796: step: 840/1545, loss: 0.07826852053403854 2023-01-23 12:38:27.599339: step: 842/1545, loss: 0.004966620821505785 2023-01-23 12:38:28.490794: step: 844/1545, loss: 0.13334816694259644 2023-01-23 12:38:29.330873: step: 846/1545, loss: 0.1601795256137848 2023-01-23 12:38:30.184374: step: 848/1545, loss: 2.546100616455078 2023-01-23 12:38:31.097086: step: 850/1545, loss: 0.02441190741956234 2023-01-23 12:38:31.971913: step: 852/1545, loss: 0.030493708327412605 2023-01-23 12:38:32.839078: step: 854/1545, loss: 0.1316903829574585 2023-01-23 12:38:33.713491: step: 856/1545, loss: 0.1810755431652069 2023-01-23 12:38:34.637912: step: 858/1545, loss: 0.4000822901725769 2023-01-23 12:38:35.511632: step: 860/1545, loss: 0.04119336977601051 2023-01-23 12:38:36.436767: step: 862/1545, loss: 0.20414583384990692 2023-01-23 12:38:37.315859: step: 864/1545, loss: 0.0809711143374443 2023-01-23 12:38:38.184013: step: 866/1545, loss: 0.23986954987049103 2023-01-23 12:38:39.048806: step: 868/1545, loss: 0.012931915931403637 2023-01-23 12:38:39.935695: step: 870/1545, loss: 0.0064504207111895084 2023-01-23 12:38:40.825248: step: 872/1545, loss: 0.04468017816543579 2023-01-23 12:38:41.682051: step: 874/1545, loss: 0.13461916148662567 2023-01-23 12:38:42.537775: step: 876/1545, loss: 0.3245181739330292 2023-01-23 12:38:43.430623: step: 878/1545, loss: 0.07786537706851959 2023-01-23 12:38:44.297080: step: 880/1545, loss: 0.18156172335147858 2023-01-23 12:38:45.189273: step: 882/1545, loss: 0.17741388082504272 2023-01-23 12:38:46.092243: step: 884/1545, loss: 0.1948121041059494 2023-01-23 12:38:46.988291: step: 886/1545, loss: 0.11419674009084702 2023-01-23 12:38:47.923216: step: 888/1545, loss: 0.006227710284292698 2023-01-23 12:38:48.799201: step: 890/1545, loss: 0.4302850365638733 2023-01-23 12:38:49.741012: step: 892/1545, loss: 0.06545684486627579 2023-01-23 12:38:50.618668: step: 894/1545, loss: 0.0017848900752142072 2023-01-23 12:38:51.509402: step: 896/1545, loss: 0.06030391529202461 2023-01-23 12:38:52.390811: step: 898/1545, loss: 0.0077087292447686195 2023-01-23 12:38:53.231788: step: 900/1545, loss: 0.1269983947277069 2023-01-23 12:38:54.081139: step: 902/1545, loss: 0.018391547724604607 2023-01-23 12:38:54.923015: step: 904/1545, loss: 0.027983225882053375 2023-01-23 12:38:55.791016: step: 906/1545, loss: 0.007481638342142105 2023-01-23 12:38:56.660854: step: 908/1545, loss: 0.022573348134756088 2023-01-23 12:38:57.514763: step: 910/1545, loss: 0.1882270723581314 2023-01-23 12:38:58.409557: step: 912/1545, loss: 0.026598747819662094 2023-01-23 12:38:59.278499: step: 914/1545, loss: 0.10301468521356583 2023-01-23 12:39:00.165878: step: 916/1545, loss: 0.03259321302175522 2023-01-23 12:39:01.048789: step: 918/1545, loss: 0.13940727710723877 2023-01-23 12:39:01.954364: step: 920/1545, loss: 0.3107229173183441 2023-01-23 12:39:02.827154: step: 922/1545, loss: 0.028865011408925056 2023-01-23 12:39:03.714461: step: 924/1545, loss: 0.026399120688438416 2023-01-23 12:39:04.604900: step: 926/1545, loss: 0.14352023601531982 2023-01-23 12:39:05.446361: step: 928/1545, loss: 0.06800632178783417 2023-01-23 12:39:06.331971: step: 930/1545, loss: 0.15127475559711456 2023-01-23 12:39:07.229963: step: 932/1545, loss: 0.5006126761436462 2023-01-23 12:39:08.148627: step: 934/1545, loss: 0.008766796439886093 2023-01-23 12:39:09.110020: step: 936/1545, loss: 0.19307386875152588 2023-01-23 12:39:09.976465: step: 938/1545, loss: 0.008195387199521065 2023-01-23 12:39:10.867158: step: 940/1545, loss: 0.1191977709531784 2023-01-23 12:39:11.754693: step: 942/1545, loss: 0.24987176060676575 2023-01-23 12:39:12.698787: step: 944/1545, loss: 0.03202557563781738 2023-01-23 12:39:13.529847: step: 946/1545, loss: 0.24753932654857635 2023-01-23 12:39:14.364824: step: 948/1545, loss: 0.2545788884162903 2023-01-23 12:39:15.253704: step: 950/1545, loss: 0.013679848983883858 2023-01-23 12:39:16.134965: step: 952/1545, loss: 0.004719197284430265 2023-01-23 12:39:17.096924: step: 954/1545, loss: 0.08943861722946167 2023-01-23 12:39:17.963859: step: 956/1545, loss: 0.269938200712204 2023-01-23 12:39:18.822830: step: 958/1545, loss: 0.13652606308460236 2023-01-23 12:39:19.705459: step: 960/1545, loss: 0.035588715225458145 2023-01-23 12:39:20.675332: step: 962/1545, loss: 0.10000397264957428 2023-01-23 12:39:21.560121: step: 964/1545, loss: 0.09672001749277115 2023-01-23 12:39:22.462909: step: 966/1545, loss: 0.10911311209201813 2023-01-23 12:39:23.294496: step: 968/1545, loss: 0.05671807378530502 2023-01-23 12:39:24.235650: step: 970/1545, loss: 0.008802053518593311 2023-01-23 12:39:25.101303: step: 972/1545, loss: 0.0904916450381279 2023-01-23 12:39:25.977111: step: 974/1545, loss: 0.0014212061651051044 2023-01-23 12:39:26.823926: step: 976/1545, loss: 0.07613667100667953 2023-01-23 12:39:27.737880: step: 978/1545, loss: 0.8445188403129578 2023-01-23 12:39:28.607166: step: 980/1545, loss: 0.18729831278324127 2023-01-23 12:39:29.477076: step: 982/1545, loss: 0.2159017026424408 2023-01-23 12:39:30.357535: step: 984/1545, loss: 0.035306889563798904 2023-01-23 12:39:31.187612: step: 986/1545, loss: 0.05612270161509514 2023-01-23 12:39:32.077180: step: 988/1545, loss: 0.11356452852487564 2023-01-23 12:39:33.042970: step: 990/1545, loss: 0.006871460471302271 2023-01-23 12:39:33.928367: step: 992/1545, loss: 0.051128700375556946 2023-01-23 12:39:34.765793: step: 994/1545, loss: 0.10347641259431839 2023-01-23 12:39:35.637545: step: 996/1545, loss: 0.09837354719638824 2023-01-23 12:39:36.503109: step: 998/1545, loss: 0.05083842948079109 2023-01-23 12:39:37.395943: step: 1000/1545, loss: 0.06522062420845032 2023-01-23 12:39:38.277805: step: 1002/1545, loss: 0.13423579931259155 2023-01-23 12:39:39.112542: step: 1004/1545, loss: 0.14740870893001556 2023-01-23 12:39:39.977101: step: 1006/1545, loss: 0.3891189694404602 2023-01-23 12:39:40.853976: step: 1008/1545, loss: 0.08489930629730225 2023-01-23 12:39:41.715005: step: 1010/1545, loss: 0.5587449073791504 2023-01-23 12:39:42.576313: step: 1012/1545, loss: 0.10620059818029404 2023-01-23 12:39:43.438131: step: 1014/1545, loss: 0.3794631063938141 2023-01-23 12:39:44.298786: step: 1016/1545, loss: 0.11025550961494446 2023-01-23 12:39:45.176695: step: 1018/1545, loss: 0.13374342024326324 2023-01-23 12:39:46.036069: step: 1020/1545, loss: 0.03386740759015083 2023-01-23 12:39:46.904828: step: 1022/1545, loss: 0.10655265301465988 2023-01-23 12:39:47.829740: step: 1024/1545, loss: 0.06280270218849182 2023-01-23 12:39:48.693516: step: 1026/1545, loss: 0.01180505845695734 2023-01-23 12:39:49.588403: step: 1028/1545, loss: 0.0678948163986206 2023-01-23 12:39:50.485240: step: 1030/1545, loss: 0.04413120821118355 2023-01-23 12:39:51.390593: step: 1032/1545, loss: 0.03874654322862625 2023-01-23 12:39:52.253192: step: 1034/1545, loss: 0.04391065984964371 2023-01-23 12:39:53.114399: step: 1036/1545, loss: 0.027132157236337662 2023-01-23 12:39:53.987473: step: 1038/1545, loss: 0.15974578261375427 2023-01-23 12:39:54.853155: step: 1040/1545, loss: 0.17321665585041046 2023-01-23 12:39:55.722004: step: 1042/1545, loss: 0.02772669494152069 2023-01-23 12:39:56.639806: step: 1044/1545, loss: 0.07850948721170425 2023-01-23 12:39:57.509466: step: 1046/1545, loss: 0.12461011856794357 2023-01-23 12:39:58.369494: step: 1048/1545, loss: 0.10987680405378342 2023-01-23 12:39:59.241395: step: 1050/1545, loss: 0.06512453407049179 2023-01-23 12:40:00.137355: step: 1052/1545, loss: 0.022269032895565033 2023-01-23 12:40:01.081366: step: 1054/1545, loss: 0.1456109583377838 2023-01-23 12:40:01.941139: step: 1056/1545, loss: 0.10089118033647537 2023-01-23 12:40:02.810465: step: 1058/1545, loss: 0.0015874644741415977 2023-01-23 12:40:03.707961: step: 1060/1545, loss: 0.006525799632072449 2023-01-23 12:40:04.553791: step: 1062/1545, loss: 0.03244395926594734 2023-01-23 12:40:05.445312: step: 1064/1545, loss: 0.04042249172925949 2023-01-23 12:40:06.383440: step: 1066/1545, loss: 0.009640159085392952 2023-01-23 12:40:07.287582: step: 1068/1545, loss: 0.006263077259063721 2023-01-23 12:40:08.195704: step: 1070/1545, loss: 0.384325236082077 2023-01-23 12:40:09.107763: step: 1072/1545, loss: 0.022939538583159447 2023-01-23 12:40:09.986709: step: 1074/1545, loss: 0.00963133666664362 2023-01-23 12:40:10.828199: step: 1076/1545, loss: 0.04905985668301582 2023-01-23 12:40:11.735687: step: 1078/1545, loss: 0.03798659145832062 2023-01-23 12:40:12.588944: step: 1080/1545, loss: 0.366872102022171 2023-01-23 12:40:13.472143: step: 1082/1545, loss: 0.061811190098524094 2023-01-23 12:40:14.419762: step: 1084/1545, loss: 0.09392382204532623 2023-01-23 12:40:15.280463: step: 1086/1545, loss: 0.09654825180768967 2023-01-23 12:40:16.119455: step: 1088/1545, loss: 0.06201130151748657 2023-01-23 12:40:16.980382: step: 1090/1545, loss: 0.4677264988422394 2023-01-23 12:40:17.870759: step: 1092/1545, loss: 0.014001848176121712 2023-01-23 12:40:18.724191: step: 1094/1545, loss: 0.011319517157971859 2023-01-23 12:40:19.624476: step: 1096/1545, loss: 0.05194346606731415 2023-01-23 12:40:20.515089: step: 1098/1545, loss: 0.09808710962533951 2023-01-23 12:40:21.406304: step: 1100/1545, loss: 0.27699753642082214 2023-01-23 12:40:22.272537: step: 1102/1545, loss: 0.1618591994047165 2023-01-23 12:40:23.149305: step: 1104/1545, loss: 0.07250238209962845 2023-01-23 12:40:24.097598: step: 1106/1545, loss: 0.024462562054395676 2023-01-23 12:40:24.968030: step: 1108/1545, loss: 2.4887335300445557 2023-01-23 12:40:25.910705: step: 1110/1545, loss: 0.13896965980529785 2023-01-23 12:40:26.761496: step: 1112/1545, loss: 0.08494433015584946 2023-01-23 12:40:27.609323: step: 1114/1545, loss: 0.08751825988292694 2023-01-23 12:40:28.473409: step: 1116/1545, loss: 0.06438975036144257 2023-01-23 12:40:29.349324: step: 1118/1545, loss: 0.02914152294397354 2023-01-23 12:40:30.216720: step: 1120/1545, loss: 0.0862000361084938 2023-01-23 12:40:31.078076: step: 1122/1545, loss: 1.0393166542053223 2023-01-23 12:40:31.983994: step: 1124/1545, loss: 0.07131342589855194 2023-01-23 12:40:32.812675: step: 1126/1545, loss: 0.004400249104946852 2023-01-23 12:40:33.684115: step: 1128/1545, loss: 0.023078199476003647 2023-01-23 12:40:34.542284: step: 1130/1545, loss: 0.5246734619140625 2023-01-23 12:40:35.402379: step: 1132/1545, loss: 0.3760263919830322 2023-01-23 12:40:36.278441: step: 1134/1545, loss: 0.16618435084819794 2023-01-23 12:40:37.172860: step: 1136/1545, loss: 0.028365761041641235 2023-01-23 12:40:38.046656: step: 1138/1545, loss: 0.10527747124433517 2023-01-23 12:40:38.912855: step: 1140/1545, loss: 1.4246649742126465 2023-01-23 12:40:39.774786: step: 1142/1545, loss: 0.07313095778226852 2023-01-23 12:40:40.615216: step: 1144/1545, loss: 0.005388720892369747 2023-01-23 12:40:41.555247: step: 1146/1545, loss: 0.0017881505191326141 2023-01-23 12:40:42.394344: step: 1148/1545, loss: 0.005845250096172094 2023-01-23 12:40:43.338335: step: 1150/1545, loss: 0.05263781547546387 2023-01-23 12:40:44.223548: step: 1152/1545, loss: 0.007606740575283766 2023-01-23 12:40:45.095142: step: 1154/1545, loss: 0.12018292397260666 2023-01-23 12:40:45.976307: step: 1156/1545, loss: 0.009747936390340328 2023-01-23 12:40:46.855209: step: 1158/1545, loss: 0.007884129881858826 2023-01-23 12:40:47.705238: step: 1160/1545, loss: 0.2086179405450821 2023-01-23 12:40:48.582921: step: 1162/1545, loss: 0.04889504611492157 2023-01-23 12:40:49.497784: step: 1164/1545, loss: 0.04277537763118744 2023-01-23 12:40:50.427696: step: 1166/1545, loss: 0.006393299903720617 2023-01-23 12:40:51.312487: step: 1168/1545, loss: 3.0870912075042725 2023-01-23 12:40:52.205848: step: 1170/1545, loss: 0.0027463887818157673 2023-01-23 12:40:53.078568: step: 1172/1545, loss: 0.12398312985897064 2023-01-23 12:40:53.927841: step: 1174/1545, loss: 0.002052037278190255 2023-01-23 12:40:54.838168: step: 1176/1545, loss: 0.19183628261089325 2023-01-23 12:40:55.705336: step: 1178/1545, loss: 0.006228853948414326 2023-01-23 12:40:56.564899: step: 1180/1545, loss: 0.012124809436500072 2023-01-23 12:40:57.427981: step: 1182/1545, loss: 0.16210222244262695 2023-01-23 12:40:58.315757: step: 1184/1545, loss: 0.06220121681690216 2023-01-23 12:40:59.181021: step: 1186/1545, loss: 0.03518795222043991 2023-01-23 12:41:00.059287: step: 1188/1545, loss: 0.0002744468511082232 2023-01-23 12:41:00.933415: step: 1190/1545, loss: 0.05717578902840614 2023-01-23 12:41:01.825680: step: 1192/1545, loss: 0.06922989338636398 2023-01-23 12:41:02.687235: step: 1194/1545, loss: 0.16093969345092773 2023-01-23 12:41:03.590159: step: 1196/1545, loss: 0.037685174494981766 2023-01-23 12:41:04.464974: step: 1198/1545, loss: 0.015601901337504387 2023-01-23 12:41:05.374509: step: 1200/1545, loss: 0.13043592870235443 2023-01-23 12:41:06.216696: step: 1202/1545, loss: 0.39906346797943115 2023-01-23 12:41:07.124071: step: 1204/1545, loss: 0.08978095650672913 2023-01-23 12:41:07.997765: step: 1206/1545, loss: 0.04405268281698227 2023-01-23 12:41:08.862379: step: 1208/1545, loss: 0.1605474054813385 2023-01-23 12:41:09.706772: step: 1210/1545, loss: 0.4372809827327728 2023-01-23 12:41:10.566668: step: 1212/1545, loss: 0.05238114297389984 2023-01-23 12:41:11.417721: step: 1214/1545, loss: 0.13756203651428223 2023-01-23 12:41:12.258032: step: 1216/1545, loss: 0.009459291584789753 2023-01-23 12:41:13.155365: step: 1218/1545, loss: 0.017731083557009697 2023-01-23 12:41:14.014205: step: 1220/1545, loss: 0.41975149512290955 2023-01-23 12:41:14.897404: step: 1222/1545, loss: 0.02064463123679161 2023-01-23 12:41:15.795752: step: 1224/1545, loss: 0.09839220345020294 2023-01-23 12:41:16.655534: step: 1226/1545, loss: 0.013225181959569454 2023-01-23 12:41:17.589428: step: 1228/1545, loss: 0.011874085292220116 2023-01-23 12:41:18.437247: step: 1230/1545, loss: 0.089267797768116 2023-01-23 12:41:19.276903: step: 1232/1545, loss: 0.11801157891750336 2023-01-23 12:41:20.241913: step: 1234/1545, loss: 0.014493554830551147 2023-01-23 12:41:21.108451: step: 1236/1545, loss: 0.20755426585674286 2023-01-23 12:41:22.025829: step: 1238/1545, loss: 0.009346124716103077 2023-01-23 12:41:22.887807: step: 1240/1545, loss: 0.25254496932029724 2023-01-23 12:41:23.731128: step: 1242/1545, loss: 0.8313225507736206 2023-01-23 12:41:24.581105: step: 1244/1545, loss: 0.09342463314533234 2023-01-23 12:41:25.441249: step: 1246/1545, loss: 0.025319714099168777 2023-01-23 12:41:26.336231: step: 1248/1545, loss: 0.10355545580387115 2023-01-23 12:41:27.215392: step: 1250/1545, loss: 0.14288419485092163 2023-01-23 12:41:28.072459: step: 1252/1545, loss: 0.0319511815905571 2023-01-23 12:41:28.934187: step: 1254/1545, loss: 0.056410957127809525 2023-01-23 12:41:29.783018: step: 1256/1545, loss: 0.49841445684432983 2023-01-23 12:41:30.677080: step: 1258/1545, loss: 0.11753673851490021 2023-01-23 12:41:31.579929: step: 1260/1545, loss: 0.04600676894187927 2023-01-23 12:41:32.468728: step: 1262/1545, loss: 0.11136610805988312 2023-01-23 12:41:33.355045: step: 1264/1545, loss: 0.025973303243517876 2023-01-23 12:41:34.192016: step: 1266/1545, loss: 0.5619221329689026 2023-01-23 12:41:35.023691: step: 1268/1545, loss: 0.3458350896835327 2023-01-23 12:41:35.909231: step: 1270/1545, loss: 0.03321253880858421 2023-01-23 12:41:36.742649: step: 1272/1545, loss: 0.10422532260417938 2023-01-23 12:41:37.566949: step: 1274/1545, loss: 0.03508152812719345 2023-01-23 12:41:38.458386: step: 1276/1545, loss: 0.013710771687328815 2023-01-23 12:41:39.309693: step: 1278/1545, loss: 0.26298215985298157 2023-01-23 12:41:40.208072: step: 1280/1545, loss: 0.11223043501377106 2023-01-23 12:41:41.079232: step: 1282/1545, loss: 0.24630022048950195 2023-01-23 12:41:41.957138: step: 1284/1545, loss: 0.1320902556180954 2023-01-23 12:41:42.821079: step: 1286/1545, loss: 0.10649658739566803 2023-01-23 12:41:43.694278: step: 1288/1545, loss: 0.009067283943295479 2023-01-23 12:41:44.568744: step: 1290/1545, loss: 0.011018069460988045 2023-01-23 12:41:45.470980: step: 1292/1545, loss: 0.08226298540830612 2023-01-23 12:41:46.403750: step: 1294/1545, loss: 0.05646730586886406 2023-01-23 12:41:47.345313: step: 1296/1545, loss: 0.0344189777970314 2023-01-23 12:41:48.242463: step: 1298/1545, loss: 0.05660190433263779 2023-01-23 12:41:49.132351: step: 1300/1545, loss: 0.13122230768203735 2023-01-23 12:41:49.983109: step: 1302/1545, loss: 0.0033262395299971104 2023-01-23 12:41:50.870767: step: 1304/1545, loss: 0.018070900812745094 2023-01-23 12:41:51.761416: step: 1306/1545, loss: 0.24957160651683807 2023-01-23 12:41:52.609083: step: 1308/1545, loss: 0.023194411769509315 2023-01-23 12:41:53.541771: step: 1310/1545, loss: 0.03954591229557991 2023-01-23 12:41:54.397098: step: 1312/1545, loss: 0.08270744979381561 2023-01-23 12:41:55.276925: step: 1314/1545, loss: 0.04755708947777748 2023-01-23 12:41:56.162132: step: 1316/1545, loss: 0.019151786342263222 2023-01-23 12:41:57.044114: step: 1318/1545, loss: 0.019006643444299698 2023-01-23 12:41:58.033160: step: 1320/1545, loss: 0.32857009768486023 2023-01-23 12:41:58.931918: step: 1322/1545, loss: 0.0592515729367733 2023-01-23 12:41:59.801609: step: 1324/1545, loss: 0.017112068831920624 2023-01-23 12:42:00.733962: step: 1326/1545, loss: 0.01889096014201641 2023-01-23 12:42:01.709280: step: 1328/1545, loss: 0.07925581187009811 2023-01-23 12:42:02.629285: step: 1330/1545, loss: 0.0626664087176323 2023-01-23 12:42:03.506175: step: 1332/1545, loss: 0.030766863375902176 2023-01-23 12:42:04.376503: step: 1334/1545, loss: 0.03753787651658058 2023-01-23 12:42:05.298920: step: 1336/1545, loss: 0.003252726048231125 2023-01-23 12:42:06.200835: step: 1338/1545, loss: 0.044583991169929504 2023-01-23 12:42:07.164191: step: 1340/1545, loss: 0.011452099308371544 2023-01-23 12:42:08.040408: step: 1342/1545, loss: 0.03828716278076172 2023-01-23 12:42:08.906881: step: 1344/1545, loss: 0.14418041706085205 2023-01-23 12:42:09.819452: step: 1346/1545, loss: 1.4917972087860107 2023-01-23 12:42:10.709557: step: 1348/1545, loss: 0.20908096432685852 2023-01-23 12:42:11.605866: step: 1350/1545, loss: 0.3812520503997803 2023-01-23 12:42:12.505641: step: 1352/1545, loss: 0.028100665658712387 2023-01-23 12:42:13.378677: step: 1354/1545, loss: 0.20858493447303772 2023-01-23 12:42:14.270574: step: 1356/1545, loss: 0.053014691919088364 2023-01-23 12:42:15.198409: step: 1358/1545, loss: 0.20008447766304016 2023-01-23 12:42:16.052987: step: 1360/1545, loss: 0.11535760015249252 2023-01-23 12:42:16.919256: step: 1362/1545, loss: 0.0010620277607813478 2023-01-23 12:42:17.814061: step: 1364/1545, loss: 0.29611876606941223 2023-01-23 12:42:18.659899: step: 1366/1545, loss: 0.014687059447169304 2023-01-23 12:42:19.674735: step: 1368/1545, loss: 0.11847510188817978 2023-01-23 12:42:20.557342: step: 1370/1545, loss: 0.19992613792419434 2023-01-23 12:42:21.472081: step: 1372/1545, loss: 0.05472136288881302 2023-01-23 12:42:22.471773: step: 1374/1545, loss: 0.3879365622997284 2023-01-23 12:42:23.377592: step: 1376/1545, loss: 0.1050366759300232 2023-01-23 12:42:24.296545: step: 1378/1545, loss: 0.09910307079553604 2023-01-23 12:42:25.167028: step: 1380/1545, loss: 0.27113309502601624 2023-01-23 12:42:26.041050: step: 1382/1545, loss: 0.40643367171287537 2023-01-23 12:42:26.921125: step: 1384/1545, loss: 0.13977274298667908 2023-01-23 12:42:27.834470: step: 1386/1545, loss: 0.01708303391933441 2023-01-23 12:42:28.705316: step: 1388/1545, loss: 0.43411877751350403 2023-01-23 12:42:29.601005: step: 1390/1545, loss: 0.11534345895051956 2023-01-23 12:42:30.514731: step: 1392/1545, loss: 0.15373371541500092 2023-01-23 12:42:31.363664: step: 1394/1545, loss: 0.8759581446647644 2023-01-23 12:42:32.213614: step: 1396/1545, loss: 0.05116379261016846 2023-01-23 12:42:33.119264: step: 1398/1545, loss: 0.14927054941654205 2023-01-23 12:42:34.013886: step: 1400/1545, loss: 0.1649107038974762 2023-01-23 12:42:34.881027: step: 1402/1545, loss: 0.010417800396680832 2023-01-23 12:42:35.792663: step: 1404/1545, loss: 0.081940196454525 2023-01-23 12:42:36.666574: step: 1406/1545, loss: 0.027067143470048904 2023-01-23 12:42:37.561692: step: 1408/1545, loss: 0.008025222457945347 2023-01-23 12:42:38.476516: step: 1410/1545, loss: 0.02507864683866501 2023-01-23 12:42:39.364832: step: 1412/1545, loss: 0.06737403571605682 2023-01-23 12:42:40.259830: step: 1414/1545, loss: 0.04212970286607742 2023-01-23 12:42:41.132073: step: 1416/1545, loss: 0.012296550907194614 2023-01-23 12:42:41.998760: step: 1418/1545, loss: 0.021929912269115448 2023-01-23 12:42:42.876659: step: 1420/1545, loss: 0.006106121931225061 2023-01-23 12:42:43.790444: step: 1422/1545, loss: 0.00588416401296854 2023-01-23 12:42:44.694323: step: 1424/1545, loss: 0.047589775174856186 2023-01-23 12:42:45.600457: step: 1426/1545, loss: 0.003922560252249241 2023-01-23 12:42:46.484222: step: 1428/1545, loss: 0.25865140557289124 2023-01-23 12:42:47.370501: step: 1430/1545, loss: 0.02634279802441597 2023-01-23 12:42:48.392464: step: 1432/1545, loss: 0.021061906591057777 2023-01-23 12:42:49.275630: step: 1434/1545, loss: 0.28907379508018494 2023-01-23 12:42:50.146228: step: 1436/1545, loss: 0.017905181273818016 2023-01-23 12:42:51.032697: step: 1438/1545, loss: 0.21971867978572845 2023-01-23 12:42:51.888975: step: 1440/1545, loss: 0.0616581067442894 2023-01-23 12:42:52.768639: step: 1442/1545, loss: 0.6854440569877625 2023-01-23 12:42:53.670852: step: 1444/1545, loss: 0.02132302150130272 2023-01-23 12:42:54.590616: step: 1446/1545, loss: 0.07646246999502182 2023-01-23 12:42:55.496975: step: 1448/1545, loss: 0.057123713195323944 2023-01-23 12:42:56.367430: step: 1450/1545, loss: 0.008630787953734398 2023-01-23 12:42:57.257855: step: 1452/1545, loss: 0.05716660991311073 2023-01-23 12:42:58.138635: step: 1454/1545, loss: 0.11175152659416199 2023-01-23 12:42:59.051880: step: 1456/1545, loss: 0.028679879382252693 2023-01-23 12:42:59.975595: step: 1458/1545, loss: 0.03423139825463295 2023-01-23 12:43:00.846830: step: 1460/1545, loss: 0.0024063759483397007 2023-01-23 12:43:01.734184: step: 1462/1545, loss: 0.04717366397380829 2023-01-23 12:43:02.591237: step: 1464/1545, loss: 0.12131492048501968 2023-01-23 12:43:03.496910: step: 1466/1545, loss: 0.023951398208737373 2023-01-23 12:43:04.438125: step: 1468/1545, loss: 0.15190058946609497 2023-01-23 12:43:05.329183: step: 1470/1545, loss: 0.046592459082603455 2023-01-23 12:43:06.218294: step: 1472/1545, loss: 0.009941738098859787 2023-01-23 12:43:07.054979: step: 1474/1545, loss: 0.09670012444257736 2023-01-23 12:43:07.977384: step: 1476/1545, loss: 0.08680731058120728 2023-01-23 12:43:08.849187: step: 1478/1545, loss: 0.030300037935376167 2023-01-23 12:43:09.744908: step: 1480/1545, loss: 0.04788234829902649 2023-01-23 12:43:10.589610: step: 1482/1545, loss: 0.04696784168481827 2023-01-23 12:43:11.511797: step: 1484/1545, loss: 0.04227157682180405 2023-01-23 12:43:12.368540: step: 1486/1545, loss: 0.07025480270385742 2023-01-23 12:43:13.242366: step: 1488/1545, loss: 0.1482969969511032 2023-01-23 12:43:14.109211: step: 1490/1545, loss: 0.11840541660785675 2023-01-23 12:43:15.022179: step: 1492/1545, loss: 0.04645518213510513 2023-01-23 12:43:15.901314: step: 1494/1545, loss: 0.009247655980288982 2023-01-23 12:43:16.789401: step: 1496/1545, loss: 0.20825110375881195 2023-01-23 12:43:17.663702: step: 1498/1545, loss: 0.1778140515089035 2023-01-23 12:43:18.566882: step: 1500/1545, loss: 0.2469908893108368 2023-01-23 12:43:19.486439: step: 1502/1545, loss: 0.00772184319794178 2023-01-23 12:43:20.414967: step: 1504/1545, loss: 0.0010692646028473973 2023-01-23 12:43:21.277113: step: 1506/1545, loss: 0.3104225695133209 2023-01-23 12:43:22.182893: step: 1508/1545, loss: 0.10099285840988159 2023-01-23 12:43:23.137718: step: 1510/1545, loss: 0.16407109797000885 2023-01-23 12:43:24.054338: step: 1512/1545, loss: 0.2320793718099594 2023-01-23 12:43:24.933373: step: 1514/1545, loss: 0.17841725051403046 2023-01-23 12:43:25.789830: step: 1516/1545, loss: 0.18494275212287903 2023-01-23 12:43:26.761033: step: 1518/1545, loss: 0.37267813086509705 2023-01-23 12:43:27.625004: step: 1520/1545, loss: 0.04415137693285942 2023-01-23 12:43:28.526441: step: 1522/1545, loss: 0.03325536847114563 2023-01-23 12:43:29.416626: step: 1524/1545, loss: 0.022186147049069405 2023-01-23 12:43:30.341697: step: 1526/1545, loss: 0.024861693382263184 2023-01-23 12:43:31.231300: step: 1528/1545, loss: 0.04186815395951271 2023-01-23 12:43:32.161871: step: 1530/1545, loss: 0.06255657225847244 2023-01-23 12:43:33.019898: step: 1532/1545, loss: 0.01867663487792015 2023-01-23 12:43:33.895535: step: 1534/1545, loss: 0.5248519778251648 2023-01-23 12:43:34.742132: step: 1536/1545, loss: 0.199508398771286 2023-01-23 12:43:35.656474: step: 1538/1545, loss: 0.06970733404159546 2023-01-23 12:43:36.535696: step: 1540/1545, loss: 0.17483286559581757 2023-01-23 12:43:37.467828: step: 1542/1545, loss: 0.002350941766053438 2023-01-23 12:43:38.360157: step: 1544/1545, loss: 0.034245364367961884 2023-01-23 12:43:39.249777: step: 1546/1545, loss: 0.10391932725906372 2023-01-23 12:43:40.158001: step: 1548/1545, loss: 0.039369404315948486 2023-01-23 12:43:41.073348: step: 1550/1545, loss: 0.19834968447685242 2023-01-23 12:43:41.950347: step: 1552/1545, loss: 0.05433891713619232 2023-01-23 12:43:42.844001: step: 1554/1545, loss: 0.3102935254573822 2023-01-23 12:43:43.742382: step: 1556/1545, loss: 0.03433138504624367 2023-01-23 12:43:44.677480: step: 1558/1545, loss: 0.054725635796785355 2023-01-23 12:43:45.581212: step: 1560/1545, loss: 0.4099292457103729 2023-01-23 12:43:46.548790: step: 1562/1545, loss: 0.1419786959886551 2023-01-23 12:43:47.412396: step: 1564/1545, loss: 0.01929374784231186 2023-01-23 12:43:48.289629: step: 1566/1545, loss: 0.09010464698076248 2023-01-23 12:43:49.177868: step: 1568/1545, loss: 0.12213777750730515 2023-01-23 12:43:50.074161: step: 1570/1545, loss: 0.015288906171917915 2023-01-23 12:43:50.965469: step: 1572/1545, loss: 0.08119955658912659 2023-01-23 12:43:51.900884: step: 1574/1545, loss: 0.0742068961262703 2023-01-23 12:43:52.848853: step: 1576/1545, loss: 0.5816917419433594 2023-01-23 12:43:53.765936: step: 1578/1545, loss: 0.16631335020065308 2023-01-23 12:43:54.662791: step: 1580/1545, loss: 0.02934076637029648 2023-01-23 12:43:55.496004: step: 1582/1545, loss: 0.8295627236366272 2023-01-23 12:43:56.407054: step: 1584/1545, loss: 1.6737016439437866 2023-01-23 12:43:57.266402: step: 1586/1545, loss: 0.05986756086349487 2023-01-23 12:43:58.163167: step: 1588/1545, loss: 0.17540517449378967 2023-01-23 12:43:59.060567: step: 1590/1545, loss: 0.028457598760724068 2023-01-23 12:43:59.973203: step: 1592/1545, loss: 0.11711623519659042 2023-01-23 12:44:00.862573: step: 1594/1545, loss: 0.02004789002239704 2023-01-23 12:44:01.747165: step: 1596/1545, loss: 0.04143967479467392 2023-01-23 12:44:02.653638: step: 1598/1545, loss: 0.13063481450080872 2023-01-23 12:44:03.546123: step: 1600/1545, loss: 1.1073969602584839 2023-01-23 12:44:04.448323: step: 1602/1545, loss: 0.4062104821205139 2023-01-23 12:44:05.344578: step: 1604/1545, loss: 0.13560259342193604 2023-01-23 12:44:06.197706: step: 1606/1545, loss: 0.2018575519323349 2023-01-23 12:44:07.050463: step: 1608/1545, loss: 0.017069051042199135 2023-01-23 12:44:07.955592: step: 1610/1545, loss: 0.16952142119407654 2023-01-23 12:44:08.840474: step: 1612/1545, loss: 0.006495578680187464 2023-01-23 12:44:09.727798: step: 1614/1545, loss: 0.0067575727589428425 2023-01-23 12:44:10.613864: step: 1616/1545, loss: 0.018104463815689087 2023-01-23 12:44:11.506972: step: 1618/1545, loss: 0.015846313908696175 2023-01-23 12:44:12.439974: step: 1620/1545, loss: 0.021029487252235413 2023-01-23 12:44:13.327567: step: 1622/1545, loss: 0.006121176294982433 2023-01-23 12:44:14.211279: step: 1624/1545, loss: 0.26890939474105835 2023-01-23 12:44:15.103225: step: 1626/1545, loss: 0.11026766151189804 2023-01-23 12:44:15.996619: step: 1628/1545, loss: 0.021642392501235008 2023-01-23 12:44:16.947416: step: 1630/1545, loss: 0.026771465316414833 2023-01-23 12:44:17.828112: step: 1632/1545, loss: 0.019764505326747894 2023-01-23 12:44:18.701822: step: 1634/1545, loss: 1.131321668624878 2023-01-23 12:44:19.599288: step: 1636/1545, loss: 0.1702037751674652 2023-01-23 12:44:20.467140: step: 1638/1545, loss: 0.10541991889476776 2023-01-23 12:44:21.420210: step: 1640/1545, loss: 0.3371543288230896 2023-01-23 12:44:22.343860: step: 1642/1545, loss: 0.28014934062957764 2023-01-23 12:44:23.225669: step: 1644/1545, loss: 0.05744347348809242 2023-01-23 12:44:24.137589: step: 1646/1545, loss: 0.15002606809139252 2023-01-23 12:44:25.037687: step: 1648/1545, loss: 0.09114006906747818 2023-01-23 12:44:25.927749: step: 1650/1545, loss: 0.04497572407126427 2023-01-23 12:44:26.851876: step: 1652/1545, loss: 0.07759346812963486 2023-01-23 12:44:27.762649: step: 1654/1545, loss: 0.0017634294927120209 2023-01-23 12:44:28.650066: step: 1656/1545, loss: 0.5341769456863403 2023-01-23 12:44:29.569399: step: 1658/1545, loss: 0.009938124567270279 2023-01-23 12:44:30.458346: step: 1660/1545, loss: 0.1466245949268341 2023-01-23 12:44:31.304762: step: 1662/1545, loss: 0.25050970911979675 2023-01-23 12:44:32.232686: step: 1664/1545, loss: 0.012949353083968163 2023-01-23 12:44:33.114806: step: 1666/1545, loss: 0.02851184457540512 2023-01-23 12:44:34.019704: step: 1668/1545, loss: 0.09544702619314194 2023-01-23 12:44:34.921623: step: 1670/1545, loss: 0.088983915746212 2023-01-23 12:44:35.808145: step: 1672/1545, loss: 0.023655569180846214 2023-01-23 12:44:36.694660: step: 1674/1545, loss: 0.0026957932859659195 2023-01-23 12:44:37.568627: step: 1676/1545, loss: 0.022057710215449333 2023-01-23 12:44:38.403818: step: 1678/1545, loss: 0.04295336455106735 2023-01-23 12:44:39.293945: step: 1680/1545, loss: 0.19202721118927002 2023-01-23 12:44:40.197528: step: 1682/1545, loss: 0.06466198712587357 2023-01-23 12:44:41.058487: step: 1684/1545, loss: 0.045566245913505554 2023-01-23 12:44:41.934316: step: 1686/1545, loss: 0.15214918553829193 2023-01-23 12:44:42.835275: step: 1688/1545, loss: 0.8055400252342224 2023-01-23 12:44:43.696024: step: 1690/1545, loss: 0.1781221330165863 2023-01-23 12:44:44.587436: step: 1692/1545, loss: 0.027934523299336433 2023-01-23 12:44:45.497713: step: 1694/1545, loss: 0.04354730620980263 2023-01-23 12:44:46.394556: step: 1696/1545, loss: 0.02586297132074833 2023-01-23 12:44:47.286305: step: 1698/1545, loss: 0.03490258753299713 2023-01-23 12:44:48.161020: step: 1700/1545, loss: 0.03818673640489578 2023-01-23 12:44:49.031132: step: 1702/1545, loss: 0.23872092366218567 2023-01-23 12:44:49.910991: step: 1704/1545, loss: 0.0012858264381065965 2023-01-23 12:44:50.749306: step: 1706/1545, loss: 0.10290568321943283 2023-01-23 12:44:51.615702: step: 1708/1545, loss: 0.6296842098236084 2023-01-23 12:44:52.534441: step: 1710/1545, loss: 0.002349858172237873 2023-01-23 12:44:53.477355: step: 1712/1545, loss: 0.03184225782752037 2023-01-23 12:44:54.332432: step: 1714/1545, loss: 0.19650818407535553 2023-01-23 12:44:55.229525: step: 1716/1545, loss: 0.3730989694595337 2023-01-23 12:44:56.064743: step: 1718/1545, loss: 0.057065449655056 2023-01-23 12:44:56.917538: step: 1720/1545, loss: 0.10459545999765396 2023-01-23 12:44:57.818930: step: 1722/1545, loss: 0.13575132191181183 2023-01-23 12:44:58.685594: step: 1724/1545, loss: 0.005860253237187862 2023-01-23 12:44:59.541689: step: 1726/1545, loss: 0.12580931186676025 2023-01-23 12:45:00.428154: step: 1728/1545, loss: 0.14230112731456757 2023-01-23 12:45:01.308362: step: 1730/1545, loss: 0.02541913092136383 2023-01-23 12:45:02.167975: step: 1732/1545, loss: 0.019935529679059982 2023-01-23 12:45:03.049712: step: 1734/1545, loss: 0.17033173143863678 2023-01-23 12:45:04.001328: step: 1736/1545, loss: 0.23844142258167267 2023-01-23 12:45:04.931306: step: 1738/1545, loss: 0.020721592009067535 2023-01-23 12:45:05.816807: step: 1740/1545, loss: 0.05512206628918648 2023-01-23 12:45:06.717805: step: 1742/1545, loss: 0.00393585255369544 2023-01-23 12:45:07.596430: step: 1744/1545, loss: 0.01883533224463463 2023-01-23 12:45:08.582793: step: 1746/1545, loss: 0.34633857011795044 2023-01-23 12:45:09.464310: step: 1748/1545, loss: 0.022967252880334854 2023-01-23 12:45:10.349344: step: 1750/1545, loss: 0.7831830382347107 2023-01-23 12:45:11.266954: step: 1752/1545, loss: 0.5257190465927124 2023-01-23 12:45:12.130199: step: 1754/1545, loss: 0.28584447503089905 2023-01-23 12:45:13.074741: step: 1756/1545, loss: 0.027310479432344437 2023-01-23 12:45:13.940883: step: 1758/1545, loss: 0.008873827755451202 2023-01-23 12:45:14.784131: step: 1760/1545, loss: 0.12383262813091278 2023-01-23 12:45:15.656783: step: 1762/1545, loss: 0.11167402565479279 2023-01-23 12:45:16.546946: step: 1764/1545, loss: 0.006719344295561314 2023-01-23 12:45:17.446487: step: 1766/1545, loss: 0.049036744982004166 2023-01-23 12:45:18.369893: step: 1768/1545, loss: 0.03109649568796158 2023-01-23 12:45:19.295100: step: 1770/1545, loss: 0.08628138154745102 2023-01-23 12:45:20.231638: step: 1772/1545, loss: 0.13673852384090424 2023-01-23 12:45:21.131157: step: 1774/1545, loss: 0.043691620230674744 2023-01-23 12:45:22.023283: step: 1776/1545, loss: 0.02245449647307396 2023-01-23 12:45:22.917334: step: 1778/1545, loss: 0.03042330965399742 2023-01-23 12:45:23.793357: step: 1780/1545, loss: 0.07201224565505981 2023-01-23 12:45:24.865200: step: 1782/1545, loss: 0.043550755828619 2023-01-23 12:45:25.739649: step: 1784/1545, loss: 0.04766574874520302 2023-01-23 12:45:26.601578: step: 1786/1545, loss: 0.20935370028018951 2023-01-23 12:45:27.496356: step: 1788/1545, loss: 0.37409237027168274 2023-01-23 12:45:28.431277: step: 1790/1545, loss: 0.20953784883022308 2023-01-23 12:45:29.299616: step: 1792/1545, loss: 0.6555649042129517 2023-01-23 12:45:30.161839: step: 1794/1545, loss: 0.0035051731392741203 2023-01-23 12:45:31.065087: step: 1796/1545, loss: 0.2875951826572418 2023-01-23 12:45:31.986975: step: 1798/1545, loss: 0.1590883731842041 2023-01-23 12:45:32.910738: step: 1800/1545, loss: 0.019170086830854416 2023-01-23 12:45:33.782824: step: 1802/1545, loss: 0.23826009035110474 2023-01-23 12:45:34.673256: step: 1804/1545, loss: 0.10372737795114517 2023-01-23 12:45:35.627759: step: 1806/1545, loss: 0.0033205561339855194 2023-01-23 12:45:36.558425: step: 1808/1545, loss: 0.02723032608628273 2023-01-23 12:45:37.411693: step: 1810/1545, loss: 0.010602634400129318 2023-01-23 12:45:38.293454: step: 1812/1545, loss: 0.0650794506072998 2023-01-23 12:45:39.165195: step: 1814/1545, loss: 0.032917313277721405 2023-01-23 12:45:40.090942: step: 1816/1545, loss: 0.030544446781277657 2023-01-23 12:45:40.937749: step: 1818/1545, loss: 0.10897467285394669 2023-01-23 12:45:41.803765: step: 1820/1545, loss: 0.1520479917526245 2023-01-23 12:45:42.703410: step: 1822/1545, loss: 0.1350933015346527 2023-01-23 12:45:43.589394: step: 1824/1545, loss: 0.009365326724946499 2023-01-23 12:45:44.462064: step: 1826/1545, loss: 0.02888641506433487 2023-01-23 12:45:45.338521: step: 1828/1545, loss: 0.04947240650653839 2023-01-23 12:45:46.220997: step: 1830/1545, loss: 0.04987812414765358 2023-01-23 12:45:47.101711: step: 1832/1545, loss: 0.016289539635181427 2023-01-23 12:45:47.980676: step: 1834/1545, loss: 0.1685059666633606 2023-01-23 12:45:48.912776: step: 1836/1545, loss: 0.0019158392678946257 2023-01-23 12:45:49.841146: step: 1838/1545, loss: 0.1492026448249817 2023-01-23 12:45:50.749214: step: 1840/1545, loss: 0.33836108446121216 2023-01-23 12:45:51.664001: step: 1842/1545, loss: 0.049957748502492905 2023-01-23 12:45:52.548101: step: 1844/1545, loss: 0.14274893701076508 2023-01-23 12:45:53.550895: step: 1846/1545, loss: 0.0030529387295246124 2023-01-23 12:45:54.450188: step: 1848/1545, loss: 0.13432945311069489 2023-01-23 12:45:55.335177: step: 1850/1545, loss: 0.06196903809905052 2023-01-23 12:45:56.236825: step: 1852/1545, loss: 0.07195991277694702 2023-01-23 12:45:57.119789: step: 1854/1545, loss: 0.02213863469660282 2023-01-23 12:45:58.027722: step: 1856/1545, loss: 0.09310659766197205 2023-01-23 12:45:58.938830: step: 1858/1545, loss: 0.014172638766467571 2023-01-23 12:45:59.791047: step: 1860/1545, loss: 0.08159051835536957 2023-01-23 12:46:00.693361: step: 1862/1545, loss: 0.022146837785840034 2023-01-23 12:46:01.617213: step: 1864/1545, loss: 0.1141878142952919 2023-01-23 12:46:02.504501: step: 1866/1545, loss: 0.015660360455513 2023-01-23 12:46:03.389531: step: 1868/1545, loss: 0.013360138982534409 2023-01-23 12:46:04.285046: step: 1870/1545, loss: 0.05124193802475929 2023-01-23 12:46:05.157794: step: 1872/1545, loss: 0.002804502611979842 2023-01-23 12:46:06.013005: step: 1874/1545, loss: 0.12604522705078125 2023-01-23 12:46:06.869755: step: 1876/1545, loss: 0.09707891196012497 2023-01-23 12:46:07.798073: step: 1878/1545, loss: 0.010855469852685928 2023-01-23 12:46:08.675761: step: 1880/1545, loss: 0.16624954342842102 2023-01-23 12:46:09.566636: step: 1882/1545, loss: 0.3264685273170471 2023-01-23 12:46:10.454055: step: 1884/1545, loss: 0.12410812079906464 2023-01-23 12:46:11.344277: step: 1886/1545, loss: 0.0586673766374588 2023-01-23 12:46:12.273924: step: 1888/1545, loss: 0.3399287462234497 2023-01-23 12:46:13.181739: step: 1890/1545, loss: 0.11524767428636551 2023-01-23 12:46:14.075406: step: 1892/1545, loss: 0.0006468225037679076 2023-01-23 12:46:14.969211: step: 1894/1545, loss: 0.030795998871326447 2023-01-23 12:46:15.824546: step: 1896/1545, loss: 0.05293748527765274 2023-01-23 12:46:16.682288: step: 1898/1545, loss: 0.31298166513442993 2023-01-23 12:46:17.562494: step: 1900/1545, loss: 0.006237940397113562 2023-01-23 12:46:18.430346: step: 1902/1545, loss: 0.0597788468003273 2023-01-23 12:46:19.323971: step: 1904/1545, loss: 0.4759007394313812 2023-01-23 12:46:20.234809: step: 1906/1545, loss: 0.3451458513736725 2023-01-23 12:46:21.095451: step: 1908/1545, loss: 0.04511742293834686 2023-01-23 12:46:22.017909: step: 1910/1545, loss: 0.1528775990009308 2023-01-23 12:46:22.893117: step: 1912/1545, loss: 0.024045346304774284 2023-01-23 12:46:23.738514: step: 1914/1545, loss: 0.16113637387752533 2023-01-23 12:46:24.610749: step: 1916/1545, loss: 0.16927912831306458 2023-01-23 12:46:25.463469: step: 1918/1545, loss: 0.3029578924179077 2023-01-23 12:46:26.353513: step: 1920/1545, loss: 0.120413638651371 2023-01-23 12:46:27.253854: step: 1922/1545, loss: 0.048453740775585175 2023-01-23 12:46:28.204019: step: 1924/1545, loss: 0.1969812959432602 2023-01-23 12:46:29.110194: step: 1926/1545, loss: 0.06777641922235489 2023-01-23 12:46:29.960803: step: 1928/1545, loss: 0.016431039199233055 2023-01-23 12:46:30.902731: step: 1930/1545, loss: 0.10710078477859497 2023-01-23 12:46:31.849518: step: 1932/1545, loss: 0.010797721333801746 2023-01-23 12:46:32.722566: step: 1934/1545, loss: 0.06424827128648758 2023-01-23 12:46:33.617512: step: 1936/1545, loss: 0.09674010425806046 2023-01-23 12:46:34.541879: step: 1938/1545, loss: 0.05713813006877899 2023-01-23 12:46:35.455868: step: 1940/1545, loss: 0.28892233967781067 2023-01-23 12:46:36.418100: step: 1942/1545, loss: 0.03391651436686516 2023-01-23 12:46:37.305393: step: 1944/1545, loss: 0.06326092034578323 2023-01-23 12:46:38.200271: step: 1946/1545, loss: 0.14272500574588776 2023-01-23 12:46:39.103216: step: 1948/1545, loss: 0.010425852611660957 2023-01-23 12:46:39.986124: step: 1950/1545, loss: 0.1701831817626953 2023-01-23 12:46:40.876018: step: 1952/1545, loss: 0.01892579160630703 2023-01-23 12:46:41.780822: step: 1954/1545, loss: 0.0022753810044378042 2023-01-23 12:46:42.691009: step: 1956/1545, loss: 0.027156179770827293 2023-01-23 12:46:43.584139: step: 1958/1545, loss: 0.04310116171836853 2023-01-23 12:46:44.465066: step: 1960/1545, loss: 0.0028846319764852524 2023-01-23 12:46:45.315841: step: 1962/1545, loss: 0.1333606094121933 2023-01-23 12:46:46.276941: step: 1964/1545, loss: 0.12085150927305222 2023-01-23 12:46:47.142848: step: 1966/1545, loss: 0.06385820358991623 2023-01-23 12:46:48.035219: step: 1968/1545, loss: 0.24207930266857147 2023-01-23 12:46:48.900732: step: 1970/1545, loss: 0.036015696823596954 2023-01-23 12:46:49.807698: step: 1972/1545, loss: 0.2497018724679947 2023-01-23 12:46:50.750871: step: 1974/1545, loss: 0.10461919009685516 2023-01-23 12:46:51.659226: step: 1976/1545, loss: 0.004698909819126129 2023-01-23 12:46:52.535310: step: 1978/1545, loss: 0.39028769731521606 2023-01-23 12:46:53.399864: step: 1980/1545, loss: 0.4272708594799042 2023-01-23 12:46:54.297489: step: 1982/1545, loss: 0.6972476243972778 2023-01-23 12:46:55.145597: step: 1984/1545, loss: 0.09704358130693436 2023-01-23 12:46:56.094562: step: 1986/1545, loss: 0.004342094529420137 2023-01-23 12:46:56.999421: step: 1988/1545, loss: 0.020376872271299362 2023-01-23 12:46:57.909284: step: 1990/1545, loss: 0.11006665974855423 2023-01-23 12:46:58.836148: step: 1992/1545, loss: 0.04225221648812294 2023-01-23 12:46:59.721523: step: 1994/1545, loss: 0.07728581130504608 2023-01-23 12:47:00.650394: step: 1996/1545, loss: 0.042877960950136185 2023-01-23 12:47:01.529201: step: 1998/1545, loss: 0.0042653814889490604 2023-01-23 12:47:02.387633: step: 2000/1545, loss: 0.13822250068187714 2023-01-23 12:47:03.303098: step: 2002/1545, loss: 0.09110388159751892 2023-01-23 12:47:04.228698: step: 2004/1545, loss: 0.13764366507530212 2023-01-23 12:47:05.186701: step: 2006/1545, loss: 0.008291112259030342 2023-01-23 12:47:06.088365: step: 2008/1545, loss: 0.6350017189979553 2023-01-23 12:47:07.038469: step: 2010/1545, loss: 0.013888039626181126 2023-01-23 12:47:07.916799: step: 2012/1545, loss: 0.01696011610329151 2023-01-23 12:47:08.812650: step: 2014/1545, loss: 0.2820778489112854 2023-01-23 12:47:09.681814: step: 2016/1545, loss: 0.022082580253481865 2023-01-23 12:47:10.558414: step: 2018/1545, loss: 0.04349491000175476 2023-01-23 12:47:11.447103: step: 2020/1545, loss: 0.05247175320982933 2023-01-23 12:47:12.343247: step: 2022/1545, loss: 0.0010030223056674004 2023-01-23 12:47:13.213407: step: 2024/1545, loss: 0.030038215219974518 2023-01-23 12:47:14.101440: step: 2026/1545, loss: 0.06641611456871033 2023-01-23 12:47:14.981641: step: 2028/1545, loss: 0.06753179430961609 2023-01-23 12:47:15.828836: step: 2030/1545, loss: 0.43866294622421265 2023-01-23 12:47:16.678405: step: 2032/1545, loss: 0.014661588706076145 2023-01-23 12:47:17.524889: step: 2034/1545, loss: 0.14815936982631683 2023-01-23 12:47:18.371291: step: 2036/1545, loss: 0.04801146313548088 2023-01-23 12:47:19.276941: step: 2038/1545, loss: 0.0761755183339119 2023-01-23 12:47:20.168325: step: 2040/1545, loss: 0.11692313849925995 2023-01-23 12:47:21.013308: step: 2042/1545, loss: 0.09781930595636368 2023-01-23 12:47:21.869672: step: 2044/1545, loss: 0.2886509895324707 2023-01-23 12:47:22.731184: step: 2046/1545, loss: 0.20446190237998962 2023-01-23 12:47:23.623268: step: 2048/1545, loss: 0.0920032411813736 2023-01-23 12:47:24.495122: step: 2050/1545, loss: 0.00677143270149827 2023-01-23 12:47:25.366086: step: 2052/1545, loss: 0.09417053312063217 2023-01-23 12:47:26.242398: step: 2054/1545, loss: 0.09769800305366516 2023-01-23 12:47:27.110362: step: 2056/1545, loss: 0.2672484219074249 2023-01-23 12:47:27.968515: step: 2058/1545, loss: 0.0265967957675457 2023-01-23 12:47:28.859757: step: 2060/1545, loss: 0.07828474044799805 2023-01-23 12:47:29.736694: step: 2062/1545, loss: 0.15434327721595764 2023-01-23 12:47:30.592198: step: 2064/1545, loss: 0.04317198321223259 2023-01-23 12:47:31.477606: step: 2066/1545, loss: 0.6270100474357605 2023-01-23 12:47:32.370073: step: 2068/1545, loss: 2.1714110374450684 2023-01-23 12:47:33.290613: step: 2070/1545, loss: 0.017193904146552086 2023-01-23 12:47:34.140394: step: 2072/1545, loss: 0.01606799103319645 2023-01-23 12:47:35.004469: step: 2074/1545, loss: 0.024292606860399246 2023-01-23 12:47:35.863577: step: 2076/1545, loss: 0.0025902038905769587 2023-01-23 12:47:36.752995: step: 2078/1545, loss: 0.1640719622373581 2023-01-23 12:47:37.620504: step: 2080/1545, loss: 0.2205546796321869 2023-01-23 12:47:38.530922: step: 2082/1545, loss: 0.08388866484165192 2023-01-23 12:47:39.393675: step: 2084/1545, loss: 0.007172604091465473 2023-01-23 12:47:40.315294: step: 2086/1545, loss: 0.03261329233646393 2023-01-23 12:47:41.204589: step: 2088/1545, loss: 0.06849260628223419 2023-01-23 12:47:42.043968: step: 2090/1545, loss: 0.21831825375556946 2023-01-23 12:47:42.910337: step: 2092/1545, loss: 0.1400492787361145 2023-01-23 12:47:43.779860: step: 2094/1545, loss: 0.025809956714510918 2023-01-23 12:47:44.687628: step: 2096/1545, loss: 1.080370545387268 2023-01-23 12:47:45.574174: step: 2098/1545, loss: 0.17755195498466492 2023-01-23 12:47:46.432715: step: 2100/1545, loss: 0.2610126733779907 2023-01-23 12:47:47.286813: step: 2102/1545, loss: 0.009958290494978428 2023-01-23 12:47:48.166700: step: 2104/1545, loss: 0.7413944005966187 2023-01-23 12:47:49.030865: step: 2106/1545, loss: 0.1101362481713295 2023-01-23 12:47:49.960256: step: 2108/1545, loss: 0.027651064097881317 2023-01-23 12:47:50.811177: step: 2110/1545, loss: 0.13650938868522644 2023-01-23 12:47:51.741943: step: 2112/1545, loss: 0.05737479031085968 2023-01-23 12:47:52.654454: step: 2114/1545, loss: 0.009184647351503372 2023-01-23 12:47:53.527222: step: 2116/1545, loss: 0.09729906916618347 2023-01-23 12:47:54.386364: step: 2118/1545, loss: 0.053392864763736725 2023-01-23 12:47:55.241736: step: 2120/1545, loss: 0.054538533091545105 2023-01-23 12:47:56.159010: step: 2122/1545, loss: 0.056056976318359375 2023-01-23 12:47:57.082110: step: 2124/1545, loss: 0.10417468845844269 2023-01-23 12:47:57.950271: step: 2126/1545, loss: 0.12526601552963257 2023-01-23 12:47:58.814531: step: 2128/1545, loss: 0.11823223531246185 2023-01-23 12:47:59.710811: step: 2130/1545, loss: 0.15589208900928497 2023-01-23 12:48:00.694391: step: 2132/1545, loss: 0.25116655230522156 2023-01-23 12:48:01.569653: step: 2134/1545, loss: 0.016834521666169167 2023-01-23 12:48:02.432574: step: 2136/1545, loss: 0.3551669120788574 2023-01-23 12:48:03.380374: step: 2138/1545, loss: 0.04228204861283302 2023-01-23 12:48:04.281455: step: 2140/1545, loss: 0.10898508876562119 2023-01-23 12:48:05.152030: step: 2142/1545, loss: 0.17360913753509521 2023-01-23 12:48:06.042417: step: 2144/1545, loss: 0.009756981395184994 2023-01-23 12:48:06.892953: step: 2146/1545, loss: 0.025219816714525223 2023-01-23 12:48:07.781037: step: 2148/1545, loss: 0.4255172908306122 2023-01-23 12:48:08.670282: step: 2150/1545, loss: 0.014447225257754326 2023-01-23 12:48:09.544373: step: 2152/1545, loss: 0.018300237134099007 2023-01-23 12:48:10.477421: step: 2154/1545, loss: 0.10043767839670181 2023-01-23 12:48:11.350289: step: 2156/1545, loss: 0.006021467968821526 2023-01-23 12:48:12.197580: step: 2158/1545, loss: 0.008274049498140812 2023-01-23 12:48:13.102498: step: 2160/1545, loss: 0.06462282687425613 2023-01-23 12:48:13.978291: step: 2162/1545, loss: 0.14446182548999786 2023-01-23 12:48:14.868310: step: 2164/1545, loss: 0.010895327664911747 2023-01-23 12:48:15.751936: step: 2166/1545, loss: 0.017963634803891182 2023-01-23 12:48:16.648228: step: 2168/1545, loss: 0.3398180305957794 2023-01-23 12:48:17.576023: step: 2170/1545, loss: 0.005341007374227047 2023-01-23 12:48:18.494422: step: 2172/1545, loss: 0.005839938297867775 2023-01-23 12:48:19.365708: step: 2174/1545, loss: 0.1569318324327469 2023-01-23 12:48:20.230423: step: 2176/1545, loss: 0.024133559316396713 2023-01-23 12:48:21.103732: step: 2178/1545, loss: 0.18240538239479065 2023-01-23 12:48:21.998360: step: 2180/1545, loss: 0.036577075719833374 2023-01-23 12:48:22.873199: step: 2182/1545, loss: 0.04691207408905029 2023-01-23 12:48:23.743791: step: 2184/1545, loss: 0.0032896532211452723 2023-01-23 12:48:24.614459: step: 2186/1545, loss: 0.36059463024139404 2023-01-23 12:48:25.473506: step: 2188/1545, loss: 0.026753295212984085 2023-01-23 12:48:26.332313: step: 2190/1545, loss: 0.12562672793865204 2023-01-23 12:48:27.165797: step: 2192/1545, loss: 0.35357287526130676 2023-01-23 12:48:28.073257: step: 2194/1545, loss: 0.02280012145638466 2023-01-23 12:48:28.982942: step: 2196/1545, loss: 0.0895610898733139 2023-01-23 12:48:29.868176: step: 2198/1545, loss: 0.3696115016937256 2023-01-23 12:48:30.772245: step: 2200/1545, loss: 1.0108392238616943 2023-01-23 12:48:31.689463: step: 2202/1545, loss: 0.1400880366563797 2023-01-23 12:48:32.575040: step: 2204/1545, loss: 0.0019302635919302702 2023-01-23 12:48:33.461169: step: 2206/1545, loss: 0.05951342731714249 2023-01-23 12:48:34.340215: step: 2208/1545, loss: 0.08370322734117508 2023-01-23 12:48:35.187654: step: 2210/1545, loss: 0.15194985270500183 2023-01-23 12:48:36.044562: step: 2212/1545, loss: 0.007447885815054178 2023-01-23 12:48:36.918673: step: 2214/1545, loss: 0.23174092173576355 2023-01-23 12:48:37.844719: step: 2216/1545, loss: 0.031768422573804855 2023-01-23 12:48:38.709742: step: 2218/1545, loss: 0.028582461178302765 2023-01-23 12:48:39.560465: step: 2220/1545, loss: 0.09448886662721634 2023-01-23 12:48:40.480388: step: 2222/1545, loss: 0.008072021417319775 2023-01-23 12:48:41.362571: step: 2224/1545, loss: 0.10530343651771545 2023-01-23 12:48:42.211215: step: 2226/1545, loss: 0.018206484615802765 2023-01-23 12:48:43.188009: step: 2228/1545, loss: 0.06463892757892609 2023-01-23 12:48:44.070934: step: 2230/1545, loss: 0.15217983722686768 2023-01-23 12:48:44.959366: step: 2232/1545, loss: 0.11120636761188507 2023-01-23 12:48:45.835238: step: 2234/1545, loss: 0.13680419325828552 2023-01-23 12:48:46.746692: step: 2236/1545, loss: 0.005432341247797012 2023-01-23 12:48:47.628956: step: 2238/1545, loss: 0.11858996003866196 2023-01-23 12:48:48.551373: step: 2240/1545, loss: 0.02548236772418022 2023-01-23 12:48:49.451260: step: 2242/1545, loss: 0.07975631952285767 2023-01-23 12:48:50.323985: step: 2244/1545, loss: 0.08719612658023834 2023-01-23 12:48:51.170837: step: 2246/1545, loss: 0.21232931315898895 2023-01-23 12:48:52.063797: step: 2248/1545, loss: 0.07950392365455627 2023-01-23 12:48:52.963048: step: 2250/1545, loss: 0.0035037535708397627 2023-01-23 12:48:53.869190: step: 2252/1545, loss: 0.10614724457263947 2023-01-23 12:48:54.720648: step: 2254/1545, loss: 0.5622758269309998 2023-01-23 12:48:55.594665: step: 2256/1545, loss: 0.1746455281972885 2023-01-23 12:48:56.455050: step: 2258/1545, loss: 0.004033017437905073 2023-01-23 12:48:57.334413: step: 2260/1545, loss: 0.0046984185464680195 2023-01-23 12:48:58.206863: step: 2262/1545, loss: 0.07954470813274384 2023-01-23 12:48:59.046483: step: 2264/1545, loss: 0.1474020779132843 2023-01-23 12:48:59.944033: step: 2266/1545, loss: 0.1069781705737114 2023-01-23 12:49:00.857204: step: 2268/1545, loss: 0.09604909271001816 2023-01-23 12:49:01.699369: step: 2270/1545, loss: 0.04256274551153183 2023-01-23 12:49:02.601189: step: 2272/1545, loss: 0.010253477841615677 2023-01-23 12:49:03.503158: step: 2274/1545, loss: 0.2907164692878723 2023-01-23 12:49:04.366429: step: 2276/1545, loss: 0.044410839676856995 2023-01-23 12:49:05.305360: step: 2278/1545, loss: 0.0053222100250422955 2023-01-23 12:49:06.214261: step: 2280/1545, loss: 0.0059737153351306915 2023-01-23 12:49:07.094136: step: 2282/1545, loss: 0.09836461395025253 2023-01-23 12:49:07.974390: step: 2284/1545, loss: 0.0639209970831871 2023-01-23 12:49:08.875027: step: 2286/1545, loss: 0.10274859517812729 2023-01-23 12:49:09.735594: step: 2288/1545, loss: 0.005490710027515888 2023-01-23 12:49:10.579587: step: 2290/1545, loss: 0.004408863373100758 2023-01-23 12:49:11.435820: step: 2292/1545, loss: 0.03959708660840988 2023-01-23 12:49:12.296611: step: 2294/1545, loss: 0.19599050283432007 2023-01-23 12:49:13.216514: step: 2296/1545, loss: 0.009665992110967636 2023-01-23 12:49:14.117483: step: 2298/1545, loss: 0.003677577944472432 2023-01-23 12:49:14.969518: step: 2300/1545, loss: 0.20281922817230225 2023-01-23 12:49:15.780509: step: 2302/1545, loss: 0.07258867472410202 2023-01-23 12:49:16.606512: step: 2304/1545, loss: 0.007344033103436232 2023-01-23 12:49:17.471105: step: 2306/1545, loss: 0.03272496536374092 2023-01-23 12:49:18.359237: step: 2308/1545, loss: 0.15394820272922516 2023-01-23 12:49:19.292954: step: 2310/1545, loss: 0.04344826564192772 2023-01-23 12:49:20.188327: step: 2312/1545, loss: 0.09596064686775208 2023-01-23 12:49:21.079787: step: 2314/1545, loss: 0.38423848152160645 2023-01-23 12:49:21.943582: step: 2316/1545, loss: 0.035684097558259964 2023-01-23 12:49:22.833131: step: 2318/1545, loss: 0.007632152177393436 2023-01-23 12:49:23.726193: step: 2320/1545, loss: 0.11781997233629227 2023-01-23 12:49:24.679780: step: 2322/1545, loss: 0.05401849374175072 2023-01-23 12:49:25.599099: step: 2324/1545, loss: 0.33697906136512756 2023-01-23 12:49:26.489950: step: 2326/1545, loss: 0.003345956327393651 2023-01-23 12:49:27.399328: step: 2328/1545, loss: 0.11534429341554642 2023-01-23 12:49:28.304930: step: 2330/1545, loss: 0.004964977037161589 2023-01-23 12:49:29.225231: step: 2332/1545, loss: 0.0003964847419410944 2023-01-23 12:49:30.107317: step: 2334/1545, loss: 0.0006838198169134557 2023-01-23 12:49:30.987688: step: 2336/1545, loss: 0.3316413462162018 2023-01-23 12:49:31.827661: step: 2338/1545, loss: 0.4559914767742157 2023-01-23 12:49:32.729864: step: 2340/1545, loss: 0.46326956152915955 2023-01-23 12:49:33.644696: step: 2342/1545, loss: 0.06955377012491226 2023-01-23 12:49:34.509918: step: 2344/1545, loss: 0.09233148396015167 2023-01-23 12:49:35.408216: step: 2346/1545, loss: 0.3194350600242615 2023-01-23 12:49:36.360491: step: 2348/1545, loss: 0.25656720995903015 2023-01-23 12:49:37.349595: step: 2350/1545, loss: 0.018535319715738297 2023-01-23 12:49:38.226741: step: 2352/1545, loss: 0.04191021993756294 2023-01-23 12:49:39.057547: step: 2354/1545, loss: 0.009967072866857052 2023-01-23 12:49:39.945540: step: 2356/1545, loss: 0.040833599865436554 2023-01-23 12:49:40.821953: step: 2358/1545, loss: 0.01827123947441578 2023-01-23 12:49:41.666168: step: 2360/1545, loss: 0.02843981795012951 2023-01-23 12:49:42.490384: step: 2362/1545, loss: 0.4077668786048889 2023-01-23 12:49:43.394611: step: 2364/1545, loss: 0.07448035478591919 2023-01-23 12:49:44.330834: step: 2366/1545, loss: 0.03650544583797455 2023-01-23 12:49:45.248913: step: 2368/1545, loss: 0.11667752265930176 2023-01-23 12:49:46.122711: step: 2370/1545, loss: 0.32648441195487976 2023-01-23 12:49:46.988655: step: 2372/1545, loss: 0.32129690051078796 2023-01-23 12:49:47.813651: step: 2374/1545, loss: 3.304213047027588 2023-01-23 12:49:48.728138: step: 2376/1545, loss: 0.144616037607193 2023-01-23 12:49:49.616436: step: 2378/1545, loss: 0.09471875429153442 2023-01-23 12:49:50.501214: step: 2380/1545, loss: 0.0567317008972168 2023-01-23 12:49:51.449657: step: 2382/1545, loss: 0.049177687615156174 2023-01-23 12:49:52.298472: step: 2384/1545, loss: 0.032149236649274826 2023-01-23 12:49:53.174491: step: 2386/1545, loss: 0.01157359592616558 2023-01-23 12:49:54.060887: step: 2388/1545, loss: 0.06098778545856476 2023-01-23 12:49:54.963190: step: 2390/1545, loss: 0.1712576001882553 2023-01-23 12:49:55.858485: step: 2392/1545, loss: 0.05538876727223396 2023-01-23 12:49:56.717105: step: 2394/1545, loss: 0.04849311336874962 2023-01-23 12:49:57.561536: step: 2396/1545, loss: 0.026495376601815224 2023-01-23 12:49:58.395975: step: 2398/1545, loss: 0.012158120982348919 2023-01-23 12:49:59.296305: step: 2400/1545, loss: 0.32200101017951965 2023-01-23 12:50:00.165730: step: 2402/1545, loss: 0.08390146493911743 2023-01-23 12:50:01.043027: step: 2404/1545, loss: 0.07886488735675812 2023-01-23 12:50:01.926602: step: 2406/1545, loss: 0.03886851295828819 2023-01-23 12:50:02.826775: step: 2408/1545, loss: 0.13244162499904633 2023-01-23 12:50:03.714310: step: 2410/1545, loss: 0.08501140773296356 2023-01-23 12:50:04.580955: step: 2412/1545, loss: 0.1925257295370102 2023-01-23 12:50:05.455785: step: 2414/1545, loss: 0.05210866779088974 2023-01-23 12:50:06.415425: step: 2416/1545, loss: 0.028300615027546883 2023-01-23 12:50:07.251278: step: 2418/1545, loss: 0.1821552962064743 2023-01-23 12:50:08.142977: step: 2420/1545, loss: 0.07438839226961136 2023-01-23 12:50:09.041454: step: 2422/1545, loss: 0.2145838439464569 2023-01-23 12:50:09.885052: step: 2424/1545, loss: 0.0029034665785729885 2023-01-23 12:50:10.750364: step: 2426/1545, loss: 0.2208436131477356 2023-01-23 12:50:11.638899: step: 2428/1545, loss: 0.01664789952337742 2023-01-23 12:50:12.511358: step: 2430/1545, loss: 0.2670193612575531 2023-01-23 12:50:13.396580: step: 2432/1545, loss: 0.0017125633312389255 2023-01-23 12:50:14.304133: step: 2434/1545, loss: 0.17258889973163605 2023-01-23 12:50:15.169852: step: 2436/1545, loss: 0.07679540663957596 2023-01-23 12:50:16.047802: step: 2438/1545, loss: 0.07858667522668839 2023-01-23 12:50:16.944345: step: 2440/1545, loss: 0.053733307868242264 2023-01-23 12:50:17.962255: step: 2442/1545, loss: 0.017063645645976067 2023-01-23 12:50:18.866226: step: 2444/1545, loss: 0.5132707953453064 2023-01-23 12:50:19.721445: step: 2446/1545, loss: 0.06657762080430984 2023-01-23 12:50:20.551368: step: 2448/1545, loss: 0.037461139261722565 2023-01-23 12:50:21.401621: step: 2450/1545, loss: 0.11638966202735901 2023-01-23 12:50:22.297397: step: 2452/1545, loss: 0.00805942714214325 2023-01-23 12:50:23.209808: step: 2454/1545, loss: 0.5774396061897278 2023-01-23 12:50:24.066851: step: 2456/1545, loss: 0.32442334294319153 2023-01-23 12:50:24.981458: step: 2458/1545, loss: 0.36065900325775146 2023-01-23 12:50:25.849905: step: 2460/1545, loss: 0.16158609092235565 2023-01-23 12:50:26.717753: step: 2462/1545, loss: 0.0047386386431753635 2023-01-23 12:50:27.600750: step: 2464/1545, loss: 0.018135609105229378 2023-01-23 12:50:28.446313: step: 2466/1545, loss: 0.04245138168334961 2023-01-23 12:50:29.289424: step: 2468/1545, loss: 0.359451562166214 2023-01-23 12:50:30.196683: step: 2470/1545, loss: 0.18128371238708496 2023-01-23 12:50:31.092461: step: 2472/1545, loss: 0.026483619585633278 2023-01-23 12:50:31.984394: step: 2474/1545, loss: 0.6129217743873596 2023-01-23 12:50:32.852288: step: 2476/1545, loss: 0.0037740818224847317 2023-01-23 12:50:33.761800: step: 2478/1545, loss: 0.013570399023592472 2023-01-23 12:50:34.630871: step: 2480/1545, loss: 0.11779524385929108 2023-01-23 12:50:35.501559: step: 2482/1545, loss: 0.04223969206213951 2023-01-23 12:50:36.382307: step: 2484/1545, loss: 0.007648508995771408 2023-01-23 12:50:37.276699: step: 2486/1545, loss: 0.1116892471909523 2023-01-23 12:50:38.088709: step: 2488/1545, loss: 1.9051427841186523 2023-01-23 12:50:38.974649: step: 2490/1545, loss: 0.0698714405298233 2023-01-23 12:50:39.892307: step: 2492/1545, loss: 0.6407921314239502 2023-01-23 12:50:40.840774: step: 2494/1545, loss: 0.017621735110878944 2023-01-23 12:50:41.727938: step: 2496/1545, loss: 0.22312936186790466 2023-01-23 12:50:42.596439: step: 2498/1545, loss: 0.006186384242027998 2023-01-23 12:50:43.511168: step: 2500/1545, loss: 0.16146908700466156 2023-01-23 12:50:44.448772: step: 2502/1545, loss: 0.09524906426668167 2023-01-23 12:50:45.365298: step: 2504/1545, loss: 0.3474888205528259 2023-01-23 12:50:46.255829: step: 2506/1545, loss: 0.14651283621788025 2023-01-23 12:50:47.116047: step: 2508/1545, loss: 0.04653714597225189 2023-01-23 12:50:48.101716: step: 2510/1545, loss: 0.020432868972420692 2023-01-23 12:50:48.959503: step: 2512/1545, loss: 0.00868571549654007 2023-01-23 12:50:49.815412: step: 2514/1545, loss: 0.01956188678741455 2023-01-23 12:50:50.686907: step: 2516/1545, loss: 0.0084044449031353 2023-01-23 12:50:51.589670: step: 2518/1545, loss: 0.26138436794281006 2023-01-23 12:50:52.485567: step: 2520/1545, loss: 0.2081751674413681 2023-01-23 12:50:53.349810: step: 2522/1545, loss: 0.030609799548983574 2023-01-23 12:50:54.288648: step: 2524/1545, loss: 0.08822193741798401 2023-01-23 12:50:55.160791: step: 2526/1545, loss: 0.024682506918907166 2023-01-23 12:50:56.082780: step: 2528/1545, loss: 0.03143375366926193 2023-01-23 12:50:57.035777: step: 2530/1545, loss: 0.1713983416557312 2023-01-23 12:50:57.859634: step: 2532/1545, loss: 0.0011267790105193853 2023-01-23 12:50:58.770864: step: 2534/1545, loss: 0.11832358688116074 2023-01-23 12:50:59.724485: step: 2536/1545, loss: 0.2693255841732025 2023-01-23 12:51:00.655074: step: 2538/1545, loss: 0.36427950859069824 2023-01-23 12:51:01.537602: step: 2540/1545, loss: 0.04227737337350845 2023-01-23 12:51:02.369073: step: 2542/1545, loss: 0.011344386264681816 2023-01-23 12:51:03.273300: step: 2544/1545, loss: 0.1524115800857544 2023-01-23 12:51:04.137231: step: 2546/1545, loss: 0.1016380786895752 2023-01-23 12:51:05.006784: step: 2548/1545, loss: 0.3297310471534729 2023-01-23 12:51:05.872143: step: 2550/1545, loss: 0.06214458867907524 2023-01-23 12:51:06.764487: step: 2552/1545, loss: 0.2053457647562027 2023-01-23 12:51:07.657034: step: 2554/1545, loss: 0.05620583891868591 2023-01-23 12:51:08.519738: step: 2556/1545, loss: 0.029534222558140755 2023-01-23 12:51:09.445520: step: 2558/1545, loss: 0.02160310000181198 2023-01-23 12:51:10.339460: step: 2560/1545, loss: 0.06770221889019012 2023-01-23 12:51:11.191034: step: 2562/1545, loss: 0.7260892987251282 2023-01-23 12:51:12.053833: step: 2564/1545, loss: 0.05035799741744995 2023-01-23 12:51:12.913513: step: 2566/1545, loss: 0.8207378387451172 2023-01-23 12:51:13.787538: step: 2568/1545, loss: 0.0170782208442688 2023-01-23 12:51:14.648101: step: 2570/1545, loss: 0.08425791561603546 2023-01-23 12:51:15.493921: step: 2572/1545, loss: 0.028692813590168953 2023-01-23 12:51:16.357823: step: 2574/1545, loss: 0.027103358879685402 2023-01-23 12:51:17.243709: step: 2576/1545, loss: 0.2035970687866211 2023-01-23 12:51:18.150611: step: 2578/1545, loss: 0.13746115565299988 2023-01-23 12:51:19.031957: step: 2580/1545, loss: 0.1115303784608841 2023-01-23 12:51:19.915686: step: 2582/1545, loss: 0.7209429144859314 2023-01-23 12:51:20.776197: step: 2584/1545, loss: 0.13613952696323395 2023-01-23 12:51:21.710983: step: 2586/1545, loss: 0.13302434980869293 2023-01-23 12:51:22.562642: step: 2588/1545, loss: 0.010045906528830528 2023-01-23 12:51:23.417309: step: 2590/1545, loss: 0.10321532934904099 2023-01-23 12:51:24.291984: step: 2592/1545, loss: 0.35525116324424744 2023-01-23 12:51:25.201162: step: 2594/1545, loss: 0.13052517175674438 2023-01-23 12:51:26.068016: step: 2596/1545, loss: 0.002405781764537096 2023-01-23 12:51:26.958727: step: 2598/1545, loss: 0.2291036993265152 2023-01-23 12:51:27.888341: step: 2600/1545, loss: 1.7058817148208618 2023-01-23 12:51:28.724162: step: 2602/1545, loss: 0.19591523706912994 2023-01-23 12:51:29.602063: step: 2604/1545, loss: 0.12001216411590576 2023-01-23 12:51:30.475764: step: 2606/1545, loss: 0.043917782604694366 2023-01-23 12:51:31.372887: step: 2608/1545, loss: 0.07140470296144485 2023-01-23 12:51:32.235242: step: 2610/1545, loss: 0.08181218057870865 2023-01-23 12:51:33.089037: step: 2612/1545, loss: 0.037855204194784164 2023-01-23 12:51:33.947500: step: 2614/1545, loss: 0.1852884590625763 2023-01-23 12:51:34.828488: step: 2616/1545, loss: 0.1586500108242035 2023-01-23 12:51:35.726128: step: 2618/1545, loss: 0.09588320553302765 2023-01-23 12:51:36.624769: step: 2620/1545, loss: 0.08339410275220871 2023-01-23 12:51:37.522035: step: 2622/1545, loss: 0.4246808588504791 2023-01-23 12:51:38.420852: step: 2624/1545, loss: 0.34548240900039673 2023-01-23 12:51:39.256733: step: 2626/1545, loss: 0.06469664722681046 2023-01-23 12:51:40.126320: step: 2628/1545, loss: 0.008676939643919468 2023-01-23 12:51:41.070543: step: 2630/1545, loss: 0.6851906180381775 2023-01-23 12:51:42.014309: step: 2632/1545, loss: 0.05426301062107086 2023-01-23 12:51:42.860328: step: 2634/1545, loss: 0.1117282286286354 2023-01-23 12:51:43.737922: step: 2636/1545, loss: 0.017283393070101738 2023-01-23 12:51:44.598182: step: 2638/1545, loss: 0.3087296485900879 2023-01-23 12:51:45.458924: step: 2640/1545, loss: 0.09052694588899612 2023-01-23 12:51:46.332484: step: 2642/1545, loss: 0.06284819543361664 2023-01-23 12:51:47.249293: step: 2644/1545, loss: 0.08786444365978241 2023-01-23 12:51:48.135764: step: 2646/1545, loss: 0.013913799077272415 2023-01-23 12:51:49.037105: step: 2648/1545, loss: 0.014356016181409359 2023-01-23 12:51:49.886356: step: 2650/1545, loss: 0.01404736377298832 2023-01-23 12:51:50.809229: step: 2652/1545, loss: 0.025706196203827858 2023-01-23 12:51:51.750007: step: 2654/1545, loss: 0.25651815533638 2023-01-23 12:51:52.610643: step: 2656/1545, loss: 0.06759153306484222 2023-01-23 12:51:53.495898: step: 2658/1545, loss: 0.02719893306493759 2023-01-23 12:51:54.409396: step: 2660/1545, loss: 0.16577935218811035 2023-01-23 12:51:55.263032: step: 2662/1545, loss: 0.13748428225517273 2023-01-23 12:51:56.181052: step: 2664/1545, loss: 0.027698591351509094 2023-01-23 12:51:57.073557: step: 2666/1545, loss: 0.031684938818216324 2023-01-23 12:51:58.019526: step: 2668/1545, loss: 0.03172014653682709 2023-01-23 12:51:58.956601: step: 2670/1545, loss: 0.2175230085849762 2023-01-23 12:51:59.836717: step: 2672/1545, loss: 0.0043184999376535416 2023-01-23 12:52:00.730603: step: 2674/1545, loss: 0.19492481648921967 2023-01-23 12:52:01.710484: step: 2676/1545, loss: 0.471770316362381 2023-01-23 12:52:02.623660: step: 2678/1545, loss: 0.07624422013759613 2023-01-23 12:52:03.482177: step: 2680/1545, loss: 0.14105089008808136 2023-01-23 12:52:04.370040: step: 2682/1545, loss: 1.414880394935608 2023-01-23 12:52:05.275455: step: 2684/1545, loss: 0.034172769635915756 2023-01-23 12:52:06.175951: step: 2686/1545, loss: 0.2693406939506531 2023-01-23 12:52:07.135915: step: 2688/1545, loss: 0.08443422615528107 2023-01-23 12:52:08.017684: step: 2690/1545, loss: 0.18403659760951996 2023-01-23 12:52:08.905585: step: 2692/1545, loss: 0.006344335153698921 2023-01-23 12:52:09.784388: step: 2694/1545, loss: 0.31868627667427063 2023-01-23 12:52:10.718743: step: 2696/1545, loss: 0.009514289908111095 2023-01-23 12:52:11.574338: step: 2698/1545, loss: 0.0918319895863533 2023-01-23 12:52:12.444386: step: 2700/1545, loss: 0.05590611696243286 2023-01-23 12:52:13.302390: step: 2702/1545, loss: 0.005407706834375858 2023-01-23 12:52:14.167965: step: 2704/1545, loss: 0.1243140771985054 2023-01-23 12:52:15.150152: step: 2706/1545, loss: 0.02299857698380947 2023-01-23 12:52:16.073211: step: 2708/1545, loss: 0.09433222562074661 2023-01-23 12:52:16.965749: step: 2710/1545, loss: 0.003508128924295306 2023-01-23 12:52:17.861012: step: 2712/1545, loss: 0.023916546255350113 2023-01-23 12:52:18.721502: step: 2714/1545, loss: 0.47929856181144714 2023-01-23 12:52:19.661728: step: 2716/1545, loss: 0.250419557094574 2023-01-23 12:52:20.544798: step: 2718/1545, loss: 0.15745973587036133 2023-01-23 12:52:21.429589: step: 2720/1545, loss: 0.03275791555643082 2023-01-23 12:52:22.354798: step: 2722/1545, loss: 0.02072160691022873 2023-01-23 12:52:23.223720: step: 2724/1545, loss: 0.04668130725622177 2023-01-23 12:52:24.104383: step: 2726/1545, loss: 0.014730596914887428 2023-01-23 12:52:24.972994: step: 2728/1545, loss: 0.013339747674763203 2023-01-23 12:52:25.822014: step: 2730/1545, loss: 0.020624352619051933 2023-01-23 12:52:26.687009: step: 2732/1545, loss: 0.03309357911348343 2023-01-23 12:52:27.545301: step: 2734/1545, loss: 0.3759986460208893 2023-01-23 12:52:28.399544: step: 2736/1545, loss: 0.30642348527908325 2023-01-23 12:52:29.236781: step: 2738/1545, loss: 0.06788775324821472 2023-01-23 12:52:30.135712: step: 2740/1545, loss: 0.02839140221476555 2023-01-23 12:52:31.007711: step: 2742/1545, loss: 0.08509493619203568 2023-01-23 12:52:31.874972: step: 2744/1545, loss: 0.0528046190738678 2023-01-23 12:52:32.772878: step: 2746/1545, loss: 0.018705828115344048 2023-01-23 12:52:33.617697: step: 2748/1545, loss: 0.044036876410245895 2023-01-23 12:52:34.511276: step: 2750/1545, loss: 0.07752782106399536 2023-01-23 12:52:35.364648: step: 2752/1545, loss: 0.0014749584952369332 2023-01-23 12:52:36.234623: step: 2754/1545, loss: 0.07170498371124268 2023-01-23 12:52:37.108247: step: 2756/1545, loss: 0.04339577630162239 2023-01-23 12:52:37.953655: step: 2758/1545, loss: 0.023816298693418503 2023-01-23 12:52:38.810362: step: 2760/1545, loss: 0.06401540338993073 2023-01-23 12:52:39.681835: step: 2762/1545, loss: 0.028772123157978058 2023-01-23 12:52:40.552833: step: 2764/1545, loss: 0.02163560688495636 2023-01-23 12:52:41.413943: step: 2766/1545, loss: 0.3863546550273895 2023-01-23 12:52:42.307692: step: 2768/1545, loss: 0.07802152633666992 2023-01-23 12:52:43.187086: step: 2770/1545, loss: 0.005661733914166689 2023-01-23 12:52:44.028510: step: 2772/1545, loss: 0.00896332785487175 2023-01-23 12:52:44.934365: step: 2774/1545, loss: 0.1825927346944809 2023-01-23 12:52:45.789236: step: 2776/1545, loss: 0.11415261030197144 2023-01-23 12:52:46.636445: step: 2778/1545, loss: 0.02020794339478016 2023-01-23 12:52:47.508522: step: 2780/1545, loss: 0.03569311648607254 2023-01-23 12:52:48.367441: step: 2782/1545, loss: 0.1638379544019699 2023-01-23 12:52:49.282756: step: 2784/1545, loss: 0.012084098532795906 2023-01-23 12:52:50.163434: step: 2786/1545, loss: 0.20088675618171692 2023-01-23 12:52:51.022485: step: 2788/1545, loss: 0.08163831382989883 2023-01-23 12:52:51.869357: step: 2790/1545, loss: 0.023022372275590897 2023-01-23 12:52:52.715021: step: 2792/1545, loss: 0.022859979420900345 2023-01-23 12:52:53.574345: step: 2794/1545, loss: 0.025207672268152237 2023-01-23 12:52:54.451807: step: 2796/1545, loss: 0.02402948960661888 2023-01-23 12:52:55.305349: step: 2798/1545, loss: 0.01304692029953003 2023-01-23 12:52:56.171777: step: 2800/1545, loss: 0.13491752743721008 2023-01-23 12:52:57.049783: step: 2802/1545, loss: 0.021249644458293915 2023-01-23 12:52:57.939395: step: 2804/1545, loss: 0.013642856851220131 2023-01-23 12:52:58.852194: step: 2806/1545, loss: 0.16144144535064697 2023-01-23 12:52:59.815093: step: 2808/1545, loss: 0.027894336730241776 2023-01-23 12:53:00.695914: step: 2810/1545, loss: 0.04741406440734863 2023-01-23 12:53:01.611134: step: 2812/1545, loss: 0.07804274559020996 2023-01-23 12:53:02.484020: step: 2814/1545, loss: 0.03993857279419899 2023-01-23 12:53:03.332575: step: 2816/1545, loss: 0.041839901357889175 2023-01-23 12:53:04.196862: step: 2818/1545, loss: 0.001358463428914547 2023-01-23 12:53:05.045963: step: 2820/1545, loss: 0.01157983299344778 2023-01-23 12:53:05.926343: step: 2822/1545, loss: 0.07033418864011765 2023-01-23 12:53:06.821529: step: 2824/1545, loss: 0.07472598552703857 2023-01-23 12:53:07.686438: step: 2826/1545, loss: 0.0005802782252430916 2023-01-23 12:53:08.572455: step: 2828/1545, loss: 0.29479414224624634 2023-01-23 12:53:09.521270: step: 2830/1545, loss: 0.11290237307548523 2023-01-23 12:53:10.346985: step: 2832/1545, loss: 0.08918669819831848 2023-01-23 12:53:11.206157: step: 2834/1545, loss: 0.04074954614043236 2023-01-23 12:53:12.071239: step: 2836/1545, loss: 0.1597653478384018 2023-01-23 12:53:12.892542: step: 2838/1545, loss: 0.007162762805819511 2023-01-23 12:53:13.761571: step: 2840/1545, loss: 0.11845843493938446 2023-01-23 12:53:14.662168: step: 2842/1545, loss: 0.013367461040616035 2023-01-23 12:53:15.514244: step: 2844/1545, loss: 0.08359571546316147 2023-01-23 12:53:16.372469: step: 2846/1545, loss: 0.018260659649968147 2023-01-23 12:53:17.261227: step: 2848/1545, loss: 0.016728417947888374 2023-01-23 12:53:18.132881: step: 2850/1545, loss: 0.07916822284460068 2023-01-23 12:53:19.010241: step: 2852/1545, loss: 0.020386455580592155 2023-01-23 12:53:19.978636: step: 2854/1545, loss: 0.02857165038585663 2023-01-23 12:53:20.840695: step: 2856/1545, loss: 0.014896026812493801 2023-01-23 12:53:21.715025: step: 2858/1545, loss: 0.07131785154342651 2023-01-23 12:53:22.564314: step: 2860/1545, loss: 0.025598034262657166 2023-01-23 12:53:23.448472: step: 2862/1545, loss: 0.29567021131515503 2023-01-23 12:53:24.315810: step: 2864/1545, loss: 0.05405889451503754 2023-01-23 12:53:25.206275: step: 2866/1545, loss: 0.04013868048787117 2023-01-23 12:53:26.084798: step: 2868/1545, loss: 0.05674468353390694 2023-01-23 12:53:26.951329: step: 2870/1545, loss: 0.16359326243400574 2023-01-23 12:53:27.853223: step: 2872/1545, loss: 0.025739476084709167 2023-01-23 12:53:28.745323: step: 2874/1545, loss: 0.0008735773735679686 2023-01-23 12:53:29.596765: step: 2876/1545, loss: 0.002575110411271453 2023-01-23 12:53:30.461179: step: 2878/1545, loss: 0.0018239569617435336 2023-01-23 12:53:31.375164: step: 2880/1545, loss: 0.17465713620185852 2023-01-23 12:53:32.246995: step: 2882/1545, loss: 0.0011883658589795232 2023-01-23 12:53:33.138515: step: 2884/1545, loss: 0.16458585858345032 2023-01-23 12:53:34.005151: step: 2886/1545, loss: 0.3451635539531708 2023-01-23 12:53:34.875041: step: 2888/1545, loss: 0.025762245059013367 2023-01-23 12:53:35.721120: step: 2890/1545, loss: 0.29379576444625854 2023-01-23 12:53:36.582560: step: 2892/1545, loss: 0.06539643555879593 2023-01-23 12:53:37.468436: step: 2894/1545, loss: 0.02919135056436062 2023-01-23 12:53:38.338057: step: 2896/1545, loss: 0.032610934227705 2023-01-23 12:53:39.251984: step: 2898/1545, loss: 0.19812314212322235 2023-01-23 12:53:40.148972: step: 2900/1545, loss: 0.07102865725755692 2023-01-23 12:53:41.037411: step: 2902/1545, loss: 0.01045277900993824 2023-01-23 12:53:41.897632: step: 2904/1545, loss: 0.18199467658996582 2023-01-23 12:53:42.843711: step: 2906/1545, loss: 0.6028578877449036 2023-01-23 12:53:43.740924: step: 2908/1545, loss: 0.08160106092691422 2023-01-23 12:53:44.624659: step: 2910/1545, loss: 0.008469573222100735 2023-01-23 12:53:45.504475: step: 2912/1545, loss: 0.0024055386893451214 2023-01-23 12:53:46.373067: step: 2914/1545, loss: 0.09130285680294037 2023-01-23 12:53:47.268726: step: 2916/1545, loss: 0.03871398791670799 2023-01-23 12:53:48.142093: step: 2918/1545, loss: 0.028233131393790245 2023-01-23 12:53:49.034138: step: 2920/1545, loss: 0.06251852959394455 2023-01-23 12:53:49.910824: step: 2922/1545, loss: 0.022678155452013016 2023-01-23 12:53:50.837318: step: 2924/1545, loss: 0.12384102493524551 2023-01-23 12:53:51.716249: step: 2926/1545, loss: 0.1988365203142166 2023-01-23 12:53:52.597637: step: 2928/1545, loss: 0.04761679098010063 2023-01-23 12:53:53.479637: step: 2930/1545, loss: 0.05354144424200058 2023-01-23 12:53:54.349565: step: 2932/1545, loss: 0.13077931106090546 2023-01-23 12:53:55.243963: step: 2934/1545, loss: 0.00322746648453176 2023-01-23 12:53:56.144567: step: 2936/1545, loss: 0.005316201131790876 2023-01-23 12:53:57.009233: step: 2938/1545, loss: 0.1636790931224823 2023-01-23 12:53:57.877122: step: 2940/1545, loss: 0.11020449548959732 2023-01-23 12:53:58.764341: step: 2942/1545, loss: 0.15787973999977112 2023-01-23 12:53:59.674929: step: 2944/1545, loss: 0.043639473617076874 2023-01-23 12:54:00.580861: step: 2946/1545, loss: 0.04204842075705528 2023-01-23 12:54:01.441319: step: 2948/1545, loss: 0.16360831260681152 2023-01-23 12:54:02.305008: step: 2950/1545, loss: 0.7472679615020752 2023-01-23 12:54:03.208587: step: 2952/1545, loss: 0.2024490237236023 2023-01-23 12:54:04.095052: step: 2954/1545, loss: 0.11740152537822723 2023-01-23 12:54:04.983566: step: 2956/1545, loss: 0.0537247397005558 2023-01-23 12:54:05.882447: step: 2958/1545, loss: 0.24525433778762817 2023-01-23 12:54:06.736808: step: 2960/1545, loss: 0.23362861573696136 2023-01-23 12:54:07.623002: step: 2962/1545, loss: 0.20859915018081665 2023-01-23 12:54:08.482634: step: 2964/1545, loss: 0.09271513670682907 2023-01-23 12:54:09.386324: step: 2966/1545, loss: 0.4822894036769867 2023-01-23 12:54:10.349629: step: 2968/1545, loss: 0.15242595970630646 2023-01-23 12:54:11.193918: step: 2970/1545, loss: 0.19660016894340515 2023-01-23 12:54:12.098630: step: 2972/1545, loss: 0.038952600210905075 2023-01-23 12:54:13.102956: step: 2974/1545, loss: 0.0032199574634432793 2023-01-23 12:54:14.033542: step: 2976/1545, loss: 0.07953977584838867 2023-01-23 12:54:14.914001: step: 2978/1545, loss: 0.26483088731765747 2023-01-23 12:54:15.773903: step: 2980/1545, loss: 0.011071876622736454 2023-01-23 12:54:16.644941: step: 2982/1545, loss: 0.0711328387260437 2023-01-23 12:54:17.490499: step: 2984/1545, loss: 0.015033463947474957 2023-01-23 12:54:18.384302: step: 2986/1545, loss: 0.03487473353743553 2023-01-23 12:54:19.319297: step: 2988/1545, loss: 0.11028824746608734 2023-01-23 12:54:20.191747: step: 2990/1545, loss: 0.006033255718648434 2023-01-23 12:54:21.065428: step: 2992/1545, loss: 0.044418081641197205 2023-01-23 12:54:21.917399: step: 2994/1545, loss: 0.008784452453255653 2023-01-23 12:54:22.785260: step: 2996/1545, loss: 0.012009837664663792 2023-01-23 12:54:23.659262: step: 2998/1545, loss: 0.003883077297359705 2023-01-23 12:54:24.488173: step: 3000/1545, loss: 0.01289447583258152 2023-01-23 12:54:25.351329: step: 3002/1545, loss: 0.16192318499088287 2023-01-23 12:54:26.207393: step: 3004/1545, loss: 0.08926008641719818 2023-01-23 12:54:27.096044: step: 3006/1545, loss: 0.008953891694545746 2023-01-23 12:54:27.957746: step: 3008/1545, loss: 0.07601393014192581 2023-01-23 12:54:28.875091: step: 3010/1545, loss: 0.21316048502922058 2023-01-23 12:54:29.725887: step: 3012/1545, loss: 0.11037999391555786 2023-01-23 12:54:30.615314: step: 3014/1545, loss: 0.08534824103116989 2023-01-23 12:54:31.465308: step: 3016/1545, loss: 0.1296452134847641 2023-01-23 12:54:32.340288: step: 3018/1545, loss: 0.007505196612328291 2023-01-23 12:54:33.199471: step: 3020/1545, loss: 0.10092610865831375 2023-01-23 12:54:34.105798: step: 3022/1545, loss: 0.27921009063720703 2023-01-23 12:54:35.004754: step: 3024/1545, loss: 0.18814589083194733 2023-01-23 12:54:35.855252: step: 3026/1545, loss: 0.027551745995879173 2023-01-23 12:54:36.743557: step: 3028/1545, loss: 0.04273948073387146 2023-01-23 12:54:37.606176: step: 3030/1545, loss: 0.054619934409856796 2023-01-23 12:54:38.493493: step: 3032/1545, loss: 0.3099008798599243 2023-01-23 12:54:39.391754: step: 3034/1545, loss: 0.9257116913795471 2023-01-23 12:54:40.309493: step: 3036/1545, loss: 0.1618555635213852 2023-01-23 12:54:41.214280: step: 3038/1545, loss: 0.04155513271689415 2023-01-23 12:54:42.068111: step: 3040/1545, loss: 0.2370402067899704 2023-01-23 12:54:42.971870: step: 3042/1545, loss: 0.0938318520784378 2023-01-23 12:54:43.985580: step: 3044/1545, loss: 0.045323945581912994 2023-01-23 12:54:44.842948: step: 3046/1545, loss: 0.04133740812540054 2023-01-23 12:54:45.714103: step: 3048/1545, loss: 0.06135500222444534 2023-01-23 12:54:46.568787: step: 3050/1545, loss: 0.04726449400186539 2023-01-23 12:54:47.414064: step: 3052/1545, loss: 0.03702859953045845 2023-01-23 12:54:48.275232: step: 3054/1545, loss: 0.189840629696846 2023-01-23 12:54:49.139400: step: 3056/1545, loss: 0.1312943398952484 2023-01-23 12:54:50.019342: step: 3058/1545, loss: 0.1021796315908432 2023-01-23 12:54:50.905957: step: 3060/1545, loss: 0.16436955332756042 2023-01-23 12:54:51.820880: step: 3062/1545, loss: 0.0041889711283147335 2023-01-23 12:54:52.749589: step: 3064/1545, loss: 0.06367944180965424 2023-01-23 12:54:53.682830: step: 3066/1545, loss: 0.020853575319051743 2023-01-23 12:54:54.524101: step: 3068/1545, loss: 0.025820016860961914 2023-01-23 12:54:55.421024: step: 3070/1545, loss: 0.02521481364965439 2023-01-23 12:54:56.346007: step: 3072/1545, loss: 0.0535893477499485 2023-01-23 12:54:57.247334: step: 3074/1545, loss: 0.18191559612751007 2023-01-23 12:54:58.131350: step: 3076/1545, loss: 0.6301816701889038 2023-01-23 12:54:59.008760: step: 3078/1545, loss: 0.0032835437450557947 2023-01-23 12:54:59.885168: step: 3080/1545, loss: 0.2332434207201004 2023-01-23 12:55:00.755705: step: 3082/1545, loss: 0.33753281831741333 2023-01-23 12:55:01.674505: step: 3084/1545, loss: 0.20755240321159363 2023-01-23 12:55:02.560378: step: 3086/1545, loss: 0.002376583870500326 2023-01-23 12:55:03.439866: step: 3088/1545, loss: 0.3210669457912445 2023-01-23 12:55:04.320212: step: 3090/1545, loss: 0.05332675948739052 ================================================== Loss: 0.141 -------------------- Dev Chinese: {'event': {'p': 0.5965103598691385, 'r': 0.7283621837549934, 'f1': 0.6558752997601919}, 'argument': {'p': 0.6570539472018659, 'r': 0.6590182340395396, 'f1': 0.6580346247350031}, 'combined': 0.4315886567506555, 'epoch': 16} Test Chinese: {'event': {'p': 0.6387406616862327, 'r': 0.7653452685421995, 'f1': 0.6963350785340314}, 'argument': {'p': 0.6985107908580674, 'r': 0.7323699017126379, 'f1': 0.7150397400734531}, 'combined': 0.49790725355900134, 'epoch': 16} Dev Korean: {'event': {'p': 0.6039387308533917, 'r': 0.7350199733688415, 'f1': 0.6630630630630631}, 'argument': {'p': 0.6579040422602876, 'r': 0.6633453538880043, 'f1': 0.660613493576223}, 'combined': 0.43802840655144154, 'epoch': 16} Test Korean: {'event': {'p': 0.629100529100529, 'r': 0.760230179028133, 'f1': 0.6884771279675738}, 'argument': {'p': 0.6911946012374106, 'r': 0.7268367980162687, 'f1': 0.7085677666008533}, 'combined': 0.4878327009197536, 'epoch': 16} Dev Russian: {'event': {'p': 0.5679133858267716, 'r': 0.7683089214380826, 'f1': 0.653084323712507}, 'argument': {'p': 0.6521642958266336, 'r': 0.6633522465770547, 'f1': 0.6577106966416014}, 'combined': 0.42954054551466214, 'epoch': 16} Test Russian: {'event': {'p': 0.6258096661684106, 'r': 0.80306905370844, 'f1': 0.7034444133295996}, 'argument': {'p': 0.700616930504113, 'r': 0.7410119163886631, 'f1': 0.7202484820502618}, 'combined': 0.5066547709073811, 'epoch': 16} Chinese: {'event': {'p': 0.5769230769230769, 'r': 0.8333333333333334, 'f1': 0.6818181818181818}, 'argument': {'p': 0.6944444444444444, 'r': 0.6198347107438017, 'f1': 0.6550218340611353}, 'combined': 0.44660579595077404, 'epoch': 16} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6699346405228758, 'r': 0.46803652968036524, 'f1': 0.5510752688172041}, 'combined': 0.3383795510281078, 'epoch': 16} Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.6180881691408007, 'r': 0.6070508804061435, 'f1': 0.6125198072566492}, 'combined': 0.3256434418326489, 'epoch': 16} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6192560175054704, 'r': 0.7536617842876165, 'f1': 0.6798798798798799}, 'argument': {'p': 0.6632184815074122, 'r': 0.6433020105912738, 'f1': 0.6531084436795553}, 'combined': 0.44403529023739136, 'epoch': 14} Test for Korean: {'event': {'p': 0.6343915343915344, 'r': 0.7666240409207161, 'f1': 0.694267515923567}, 'argument': {'p': 0.7134384328444346, 'r': 0.7077112894615091, 'f1': 0.7105633211403983}, 'combined': 0.4933210318745441, 'epoch': 14} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6992753623188407, 'r': 0.44063926940639275, 'f1': 0.5406162464985995}, 'combined': 0.34144183989385235, 'epoch': 14} -------------------- Dev for Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6600380148157703, 'r': 0.6373432979739673, 'f1': 0.648492160329197}, 'combined': 0.42792408542379373, 'epoch': 3} Test for Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7083565804213369, 'r': 0.7086213866196253, 'f1': 0.7084889587768632}, 'combined': 0.5007634085558115, 'epoch': 3} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.6156786087148964, 'r': 0.5826958261051699, 'f1': 0.5987333259062295}, 'combined': 0.3486295315403361, 'epoch': 3} ****************************** Epoch: 17 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 13:00:19.428672: step: 2/1545, loss: 0.05600529909133911 2023-01-23 13:00:20.298816: step: 4/1545, loss: 0.13160091638565063 2023-01-23 13:00:21.179766: step: 6/1545, loss: 0.18756712973117828 2023-01-23 13:00:22.118414: step: 8/1545, loss: 0.39586198329925537 2023-01-23 13:00:22.966276: step: 10/1545, loss: 0.007606972940266132 2023-01-23 13:00:23.851828: step: 12/1545, loss: 0.025739887729287148 2023-01-23 13:00:24.748313: step: 14/1545, loss: 0.866529107093811 2023-01-23 13:00:25.624888: step: 16/1545, loss: 0.06767690926790237 2023-01-23 13:00:26.500021: step: 18/1545, loss: 0.14248690009117126 2023-01-23 13:00:27.390549: step: 20/1545, loss: 0.6799736022949219 2023-01-23 13:00:28.313932: step: 22/1545, loss: 0.13422319293022156 2023-01-23 13:00:29.228725: step: 24/1545, loss: 0.05035921931266785 2023-01-23 13:00:30.158230: step: 26/1545, loss: 0.03810985013842583 2023-01-23 13:00:31.021936: step: 28/1545, loss: 0.15870603919029236 2023-01-23 13:00:31.886835: step: 30/1545, loss: 0.030234796926379204 2023-01-23 13:00:32.755658: step: 32/1545, loss: 0.013487358577549458 2023-01-23 13:00:33.657672: step: 34/1545, loss: 0.019558850675821304 2023-01-23 13:00:34.520070: step: 36/1545, loss: 0.011267103254795074 2023-01-23 13:00:35.489492: step: 38/1545, loss: 0.04609043151140213 2023-01-23 13:00:36.387546: step: 40/1545, loss: 0.256918340921402 2023-01-23 13:00:37.265982: step: 42/1545, loss: 0.25364166498184204 2023-01-23 13:00:38.167897: step: 44/1545, loss: 0.034351546317338943 2023-01-23 13:00:39.066644: step: 46/1545, loss: 0.022147754207253456 2023-01-23 13:00:39.924195: step: 48/1545, loss: 0.03169313818216324 2023-01-23 13:00:40.822583: step: 50/1545, loss: 0.020292799919843674 2023-01-23 13:00:41.692631: step: 52/1545, loss: 0.03130798786878586 2023-01-23 13:00:42.557176: step: 54/1545, loss: 0.15709321200847626 2023-01-23 13:00:43.415181: step: 56/1545, loss: 0.0028610462322831154 2023-01-23 13:00:44.287443: step: 58/1545, loss: 0.06174251064658165 2023-01-23 13:00:45.174418: step: 60/1545, loss: 0.0386304035782814 2023-01-23 13:00:45.985703: step: 62/1545, loss: 0.238888218998909 2023-01-23 13:00:46.829395: step: 64/1545, loss: 0.024808313697576523 2023-01-23 13:00:47.708682: step: 66/1545, loss: 0.006140129640698433 2023-01-23 13:00:48.608712: step: 68/1545, loss: 0.00645100511610508 2023-01-23 13:00:49.534742: step: 70/1545, loss: 0.05541711673140526 2023-01-23 13:00:50.476444: step: 72/1545, loss: 0.1727614551782608 2023-01-23 13:00:51.358103: step: 74/1545, loss: 0.04509977996349335 2023-01-23 13:00:52.278111: step: 76/1545, loss: 0.005747975781559944 2023-01-23 13:00:53.138470: step: 78/1545, loss: 0.175000861287117 2023-01-23 13:00:54.037081: step: 80/1545, loss: 0.02224811166524887 2023-01-23 13:00:54.902928: step: 82/1545, loss: 0.017349684610962868 2023-01-23 13:00:55.726464: step: 84/1545, loss: 0.2608664333820343 2023-01-23 13:00:56.589387: step: 86/1545, loss: 0.011912491172552109 2023-01-23 13:00:57.481644: step: 88/1545, loss: 0.0009922918397933245 2023-01-23 13:00:58.360844: step: 90/1545, loss: 0.06568534672260284 2023-01-23 13:00:59.223299: step: 92/1545, loss: 0.0406821109354496 2023-01-23 13:01:00.078032: step: 94/1545, loss: 0.016352655366063118 2023-01-23 13:01:00.937714: step: 96/1545, loss: 0.019863508641719818 2023-01-23 13:01:01.823967: step: 98/1545, loss: 0.0020515916403383017 2023-01-23 13:01:02.684178: step: 100/1545, loss: 0.27577781677246094 2023-01-23 13:01:03.523909: step: 102/1545, loss: 0.06923728436231613 2023-01-23 13:01:04.378615: step: 104/1545, loss: 0.0032023764215409756 2023-01-23 13:01:05.226204: step: 106/1545, loss: 0.10644084215164185 2023-01-23 13:01:06.084959: step: 108/1545, loss: 0.005480388179421425 2023-01-23 13:01:06.959838: step: 110/1545, loss: 0.0016312155639752746 2023-01-23 13:01:07.829821: step: 112/1545, loss: 0.026535959914326668 2023-01-23 13:01:08.713571: step: 114/1545, loss: 0.2423008680343628 2023-01-23 13:01:09.569097: step: 116/1545, loss: 0.42341873049736023 2023-01-23 13:01:10.446635: step: 118/1545, loss: 0.0030998168513178825 2023-01-23 13:01:11.302733: step: 120/1545, loss: 0.16885675489902496 2023-01-23 13:01:12.172498: step: 122/1545, loss: 0.030555978417396545 2023-01-23 13:01:13.030098: step: 124/1545, loss: 0.005953710526227951 2023-01-23 13:01:13.942691: step: 126/1545, loss: 0.048645224422216415 2023-01-23 13:01:14.826611: step: 128/1545, loss: 0.09982945024967194 2023-01-23 13:01:15.710806: step: 130/1545, loss: 0.009819502010941505 2023-01-23 13:01:16.594081: step: 132/1545, loss: 0.002282446948811412 2023-01-23 13:01:17.505479: step: 134/1545, loss: 0.1674818992614746 2023-01-23 13:01:18.403747: step: 136/1545, loss: 0.12360957264900208 2023-01-23 13:01:19.342339: step: 138/1545, loss: 0.11226194351911545 2023-01-23 13:01:20.202438: step: 140/1545, loss: 0.14272117614746094 2023-01-23 13:01:21.077348: step: 142/1545, loss: 0.19516663253307343 2023-01-23 13:01:21.984414: step: 144/1545, loss: 0.08469990640878677 2023-01-23 13:01:22.884656: step: 146/1545, loss: 0.014129837974905968 2023-01-23 13:01:23.745712: step: 148/1545, loss: 1.4439932107925415 2023-01-23 13:01:24.603921: step: 150/1545, loss: 0.003730193944647908 2023-01-23 13:01:25.470413: step: 152/1545, loss: 0.6025477647781372 2023-01-23 13:01:26.367663: step: 154/1545, loss: 0.07336125522851944 2023-01-23 13:01:27.200062: step: 156/1545, loss: 0.05038773640990257 2023-01-23 13:01:28.111173: step: 158/1545, loss: 0.04674476385116577 2023-01-23 13:01:28.985738: step: 160/1545, loss: 0.017772315070033073 2023-01-23 13:01:29.905269: step: 162/1545, loss: 0.24082277715206146 2023-01-23 13:01:30.840848: step: 164/1545, loss: 0.18392986059188843 2023-01-23 13:01:31.721291: step: 166/1545, loss: 0.012895021587610245 2023-01-23 13:01:32.630250: step: 168/1545, loss: 0.07222880423069 2023-01-23 13:01:33.532382: step: 170/1545, loss: 0.025744475424289703 2023-01-23 13:01:34.358108: step: 172/1545, loss: 0.00039693660801276565 2023-01-23 13:01:35.214649: step: 174/1545, loss: 0.5086997747421265 2023-01-23 13:01:36.132964: step: 176/1545, loss: 0.38123902678489685 2023-01-23 13:01:37.007231: step: 178/1545, loss: 0.09995322674512863 2023-01-23 13:01:37.896251: step: 180/1545, loss: 0.023311685770750046 2023-01-23 13:01:38.720817: step: 182/1545, loss: 0.024968987330794334 2023-01-23 13:01:39.584471: step: 184/1545, loss: 0.02224397286772728 2023-01-23 13:01:40.434356: step: 186/1545, loss: 0.15490847826004028 2023-01-23 13:01:41.350043: step: 188/1545, loss: 0.07196217030286789 2023-01-23 13:01:42.331918: step: 190/1545, loss: 0.03560715913772583 2023-01-23 13:01:43.249843: step: 192/1545, loss: 0.047077298164367676 2023-01-23 13:01:44.083098: step: 194/1545, loss: 0.0038948161527514458 2023-01-23 13:01:44.990391: step: 196/1545, loss: 0.055080167949199677 2023-01-23 13:01:45.931191: step: 198/1545, loss: 0.15981215238571167 2023-01-23 13:01:46.788244: step: 200/1545, loss: 0.6070494055747986 2023-01-23 13:01:47.747641: step: 202/1545, loss: 0.07294522225856781 2023-01-23 13:01:48.668326: step: 204/1545, loss: 0.09968576580286026 2023-01-23 13:01:49.528557: step: 206/1545, loss: 0.2986123263835907 2023-01-23 13:01:50.375043: step: 208/1545, loss: 0.36941641569137573 2023-01-23 13:01:51.249258: step: 210/1545, loss: 0.18867969512939453 2023-01-23 13:01:52.145953: step: 212/1545, loss: 0.13055726885795593 2023-01-23 13:01:53.017792: step: 214/1545, loss: 0.03414244204759598 2023-01-23 13:01:53.922372: step: 216/1545, loss: 0.09626956284046173 2023-01-23 13:01:54.794329: step: 218/1545, loss: 0.024952247738838196 2023-01-23 13:01:55.658180: step: 220/1545, loss: 0.013828855939209461 2023-01-23 13:01:56.532283: step: 222/1545, loss: 0.0013391311513260007 2023-01-23 13:01:57.393600: step: 224/1545, loss: 0.3811224400997162 2023-01-23 13:01:58.272204: step: 226/1545, loss: 0.1068039983510971 2023-01-23 13:01:59.125416: step: 228/1545, loss: 0.34059980511665344 2023-01-23 13:02:00.014935: step: 230/1545, loss: 0.2668084502220154 2023-01-23 13:02:00.883977: step: 232/1545, loss: 0.026992272585630417 2023-01-23 13:02:01.766307: step: 234/1545, loss: 0.028157955035567284 2023-01-23 13:02:02.624827: step: 236/1545, loss: 0.0030897674150764942 2023-01-23 13:02:03.540684: step: 238/1545, loss: 0.14135727286338806 2023-01-23 13:02:04.510219: step: 240/1545, loss: 0.047500766813755035 2023-01-23 13:02:05.440525: step: 242/1545, loss: 0.029245933517813683 2023-01-23 13:02:06.310134: step: 244/1545, loss: 0.07457440346479416 2023-01-23 13:02:07.199862: step: 246/1545, loss: 0.2188347429037094 2023-01-23 13:02:08.207812: step: 248/1545, loss: 0.01479902770370245 2023-01-23 13:02:09.050132: step: 250/1545, loss: 0.05360143259167671 2023-01-23 13:02:09.954780: step: 252/1545, loss: 0.011304054409265518 2023-01-23 13:02:10.864508: step: 254/1545, loss: 0.19742821156978607 2023-01-23 13:02:11.772209: step: 256/1545, loss: 0.016714690253138542 2023-01-23 13:02:12.650721: step: 258/1545, loss: 0.06308244913816452 2023-01-23 13:02:13.481598: step: 260/1545, loss: 0.040653325617313385 2023-01-23 13:02:14.334002: step: 262/1545, loss: 0.08418294787406921 2023-01-23 13:02:15.208564: step: 264/1545, loss: 0.026940174400806427 2023-01-23 13:02:16.103647: step: 266/1545, loss: 0.0826430693268776 2023-01-23 13:02:16.957133: step: 268/1545, loss: 0.007093584630638361 2023-01-23 13:02:17.867006: step: 270/1545, loss: 0.2481634020805359 2023-01-23 13:02:18.734300: step: 272/1545, loss: 0.16509965062141418 2023-01-23 13:02:19.650869: step: 274/1545, loss: 0.10601990669965744 2023-01-23 13:02:20.493230: step: 276/1545, loss: 0.06074073538184166 2023-01-23 13:02:21.365065: step: 278/1545, loss: 0.21363037824630737 2023-01-23 13:02:22.222722: step: 280/1545, loss: 0.000637473538517952 2023-01-23 13:02:23.124145: step: 282/1545, loss: 0.09856509417295456 2023-01-23 13:02:24.003109: step: 284/1545, loss: 0.003326410660520196 2023-01-23 13:02:24.909981: step: 286/1545, loss: 0.0047663310542702675 2023-01-23 13:02:25.768012: step: 288/1545, loss: 0.00296764075756073 2023-01-23 13:02:26.624915: step: 290/1545, loss: 0.008415094576776028 2023-01-23 13:02:27.534215: step: 292/1545, loss: 0.023863978683948517 2023-01-23 13:02:28.419264: step: 294/1545, loss: 0.02097567357122898 2023-01-23 13:02:29.309665: step: 296/1545, loss: 0.505524754524231 2023-01-23 13:02:30.185436: step: 298/1545, loss: 0.13800983130931854 2023-01-23 13:02:31.037518: step: 300/1545, loss: 0.20386193692684174 2023-01-23 13:02:31.900252: step: 302/1545, loss: 0.06514190137386322 2023-01-23 13:02:32.792733: step: 304/1545, loss: 0.11243728548288345 2023-01-23 13:02:33.633772: step: 306/1545, loss: 0.1281486302614212 2023-01-23 13:02:34.542991: step: 308/1545, loss: 0.13578492403030396 2023-01-23 13:02:35.385935: step: 310/1545, loss: 0.002555639250203967 2023-01-23 13:02:36.284289: step: 312/1545, loss: 0.5944651365280151 2023-01-23 13:02:37.155225: step: 314/1545, loss: 0.5603681802749634 2023-01-23 13:02:38.060100: step: 316/1545, loss: 0.00472189299762249 2023-01-23 13:02:38.988499: step: 318/1545, loss: 0.2040361911058426 2023-01-23 13:02:39.874823: step: 320/1545, loss: 0.1388179510831833 2023-01-23 13:02:40.769275: step: 322/1545, loss: 0.15261167287826538 2023-01-23 13:02:41.642002: step: 324/1545, loss: 0.2150295525789261 2023-01-23 13:02:42.508666: step: 326/1545, loss: 0.007099972106516361 2023-01-23 13:02:43.438237: step: 328/1545, loss: 0.0005629195366054773 2023-01-23 13:02:44.314155: step: 330/1545, loss: 0.2374383807182312 2023-01-23 13:02:45.213181: step: 332/1545, loss: 0.2750532925128937 2023-01-23 13:02:46.121132: step: 334/1545, loss: 0.0601591058075428 2023-01-23 13:02:47.044266: step: 336/1545, loss: 0.02913145162165165 2023-01-23 13:02:47.889515: step: 338/1545, loss: 0.00024232856230810285 2023-01-23 13:02:48.803325: step: 340/1545, loss: 0.0065821269527077675 2023-01-23 13:02:49.679745: step: 342/1545, loss: 0.05348987504839897 2023-01-23 13:02:50.516994: step: 344/1545, loss: 0.009857607074081898 2023-01-23 13:02:51.393521: step: 346/1545, loss: 0.04340223968029022 2023-01-23 13:02:52.276483: step: 348/1545, loss: 0.06087733805179596 2023-01-23 13:02:53.187546: step: 350/1545, loss: 0.06523499637842178 2023-01-23 13:02:54.053796: step: 352/1545, loss: 0.019139034673571587 2023-01-23 13:02:54.928049: step: 354/1545, loss: 0.02863813005387783 2023-01-23 13:02:55.806582: step: 356/1545, loss: 0.10392945259809494 2023-01-23 13:02:56.689465: step: 358/1545, loss: 0.06287643313407898 2023-01-23 13:02:57.551259: step: 360/1545, loss: 0.2716463804244995 2023-01-23 13:02:58.453747: step: 362/1545, loss: 0.03351462632417679 2023-01-23 13:02:59.321027: step: 364/1545, loss: 0.028726596385240555 2023-01-23 13:03:00.182337: step: 366/1545, loss: 0.0019690620247274637 2023-01-23 13:03:01.031881: step: 368/1545, loss: 0.029401537030935287 2023-01-23 13:03:01.945232: step: 370/1545, loss: 0.16091711819171906 2023-01-23 13:03:02.849777: step: 372/1545, loss: 0.2032746523618698 2023-01-23 13:03:03.736087: step: 374/1545, loss: 0.29034262895584106 2023-01-23 13:03:04.619209: step: 376/1545, loss: 0.041551508009433746 2023-01-23 13:03:05.497521: step: 378/1545, loss: 0.0029266737401485443 2023-01-23 13:03:06.360183: step: 380/1545, loss: 0.032824527472257614 2023-01-23 13:03:07.210111: step: 382/1545, loss: 0.018304472789168358 2023-01-23 13:03:08.087768: step: 384/1545, loss: 0.21451090276241302 2023-01-23 13:03:08.943196: step: 386/1545, loss: 0.000873359851539135 2023-01-23 13:03:09.794653: step: 388/1545, loss: 0.011946670711040497 2023-01-23 13:03:10.650323: step: 390/1545, loss: 0.031734250485897064 2023-01-23 13:03:11.497029: step: 392/1545, loss: 0.05012128874659538 2023-01-23 13:03:12.411111: step: 394/1545, loss: 0.008271279744803905 2023-01-23 13:03:13.330502: step: 396/1545, loss: 0.2144007384777069 2023-01-23 13:03:14.256532: step: 398/1545, loss: 0.05592196434736252 2023-01-23 13:03:15.109991: step: 400/1545, loss: 0.02167537994682789 2023-01-23 13:03:15.995235: step: 402/1545, loss: 0.01563364267349243 2023-01-23 13:03:16.843933: step: 404/1545, loss: 0.004119607154279947 2023-01-23 13:03:17.749140: step: 406/1545, loss: 0.15766170620918274 2023-01-23 13:03:18.640373: step: 408/1545, loss: 0.8597472310066223 2023-01-23 13:03:19.547235: step: 410/1545, loss: 0.003684871830046177 2023-01-23 13:03:20.390872: step: 412/1545, loss: 0.0011793009471148252 2023-01-23 13:03:21.255311: step: 414/1545, loss: 0.005645063705742359 2023-01-23 13:03:22.084865: step: 416/1545, loss: 0.18597328662872314 2023-01-23 13:03:22.971163: step: 418/1545, loss: 0.0021375829819589853 2023-01-23 13:03:23.838224: step: 420/1545, loss: 0.005002455785870552 2023-01-23 13:03:24.707443: step: 422/1545, loss: 0.05934108421206474 2023-01-23 13:03:25.576872: step: 424/1545, loss: 0.09963349252939224 2023-01-23 13:03:26.468801: step: 426/1545, loss: 0.010379735380411148 2023-01-23 13:03:27.404194: step: 428/1545, loss: 0.15097740292549133 2023-01-23 13:03:28.275790: step: 430/1545, loss: 0.06360851973295212 2023-01-23 13:03:29.140168: step: 432/1545, loss: 0.01620456762611866 2023-01-23 13:03:30.043398: step: 434/1545, loss: 0.24459733068943024 2023-01-23 13:03:30.902570: step: 436/1545, loss: 0.0011630499502643943 2023-01-23 13:03:31.802243: step: 438/1545, loss: 0.8247736692428589 2023-01-23 13:03:32.682120: step: 440/1545, loss: 0.021806901320815086 2023-01-23 13:03:33.570860: step: 442/1545, loss: 0.03382876515388489 2023-01-23 13:03:34.437475: step: 444/1545, loss: 0.007684067357331514 2023-01-23 13:03:35.316853: step: 446/1545, loss: 0.05428629368543625 2023-01-23 13:03:36.181594: step: 448/1545, loss: 0.2081553190946579 2023-01-23 13:03:36.999026: step: 450/1545, loss: 0.0758039653301239 2023-01-23 13:03:37.868226: step: 452/1545, loss: 0.04800138249993324 2023-01-23 13:03:38.724199: step: 454/1545, loss: 0.09392198920249939 2023-01-23 13:03:39.565035: step: 456/1545, loss: 0.00590170081704855 2023-01-23 13:03:40.443192: step: 458/1545, loss: 0.0008237900910899043 2023-01-23 13:03:41.277601: step: 460/1545, loss: 0.003638072405010462 2023-01-23 13:03:42.159629: step: 462/1545, loss: 0.0009659274946898222 2023-01-23 13:03:43.028896: step: 464/1545, loss: 0.010757259093225002 2023-01-23 13:03:43.882807: step: 466/1545, loss: 0.00805692095309496 2023-01-23 13:03:44.775973: step: 468/1545, loss: 0.044227130711078644 2023-01-23 13:03:45.650372: step: 470/1545, loss: 0.002124705584719777 2023-01-23 13:03:46.570510: step: 472/1545, loss: 0.016759397462010384 2023-01-23 13:03:47.468749: step: 474/1545, loss: 0.3311019837856293 2023-01-23 13:03:48.447028: step: 476/1545, loss: 0.00019047201203648 2023-01-23 13:03:49.353485: step: 478/1545, loss: 0.043304719030857086 2023-01-23 13:03:50.216933: step: 480/1545, loss: 0.0005955800297670066 2023-01-23 13:03:51.095503: step: 482/1545, loss: 0.004311258438974619 2023-01-23 13:03:51.949355: step: 484/1545, loss: 0.0003844598541036248 2023-01-23 13:03:52.842226: step: 486/1545, loss: 0.040014564990997314 2023-01-23 13:03:53.687531: step: 488/1545, loss: 0.13912807404994965 2023-01-23 13:03:54.554587: step: 490/1545, loss: 0.012197663076221943 2023-01-23 13:03:55.477946: step: 492/1545, loss: 0.002110427711158991 2023-01-23 13:03:56.345497: step: 494/1545, loss: 0.006259284447878599 2023-01-23 13:03:57.209497: step: 496/1545, loss: 0.0002831313177011907 2023-01-23 13:03:58.087554: step: 498/1545, loss: 0.07891327887773514 2023-01-23 13:03:58.946460: step: 500/1545, loss: 0.0006788746104575694 2023-01-23 13:03:59.826788: step: 502/1545, loss: 0.015219264663755894 2023-01-23 13:04:00.692157: step: 504/1545, loss: 0.010411989875137806 2023-01-23 13:04:01.591457: step: 506/1545, loss: 0.0008434964693151414 2023-01-23 13:04:02.466345: step: 508/1545, loss: 0.016743695363402367 2023-01-23 13:04:03.340204: step: 510/1545, loss: 0.41538330912590027 2023-01-23 13:04:04.258001: step: 512/1545, loss: 0.03698255866765976 2023-01-23 13:04:05.145041: step: 514/1545, loss: 0.00031844410113990307 2023-01-23 13:04:06.029838: step: 516/1545, loss: 0.18308866024017334 2023-01-23 13:04:06.880781: step: 518/1545, loss: 0.02661219611763954 2023-01-23 13:04:07.721106: step: 520/1545, loss: 0.29120194911956787 2023-01-23 13:04:08.606101: step: 522/1545, loss: 0.016200030222535133 2023-01-23 13:04:09.511570: step: 524/1545, loss: 0.07398694008588791 2023-01-23 13:04:10.410491: step: 526/1545, loss: 0.0035371489357203245 2023-01-23 13:04:11.252753: step: 528/1545, loss: 0.3784793019294739 2023-01-23 13:04:12.125796: step: 530/1545, loss: 0.0015914884861558676 2023-01-23 13:04:13.001441: step: 532/1545, loss: 0.0009661907679401338 2023-01-23 13:04:13.979699: step: 534/1545, loss: 0.023201236501336098 2023-01-23 13:04:14.871511: step: 536/1545, loss: 0.24693267047405243 2023-01-23 13:04:15.751182: step: 538/1545, loss: 0.05567223206162453 2023-01-23 13:04:16.612093: step: 540/1545, loss: 0.06997379660606384 2023-01-23 13:04:17.480693: step: 542/1545, loss: 0.02384180948138237 2023-01-23 13:04:18.387961: step: 544/1545, loss: 0.053606148809194565 2023-01-23 13:04:19.280397: step: 546/1545, loss: 0.00512323435395956 2023-01-23 13:04:20.144427: step: 548/1545, loss: 0.05879919230937958 2023-01-23 13:04:20.981800: step: 550/1545, loss: 0.07179246842861176 2023-01-23 13:04:21.949323: step: 552/1545, loss: 0.3102774918079376 2023-01-23 13:04:22.844536: step: 554/1545, loss: 0.011933811940252781 2023-01-23 13:04:23.694978: step: 556/1545, loss: 0.09653749316930771 2023-01-23 13:04:24.592187: step: 558/1545, loss: 0.5317774415016174 2023-01-23 13:04:25.477257: step: 560/1545, loss: 0.03186669945716858 2023-01-23 13:04:26.333133: step: 562/1545, loss: 0.07951866090297699 2023-01-23 13:04:27.193671: step: 564/1545, loss: 0.0060710362158715725 2023-01-23 13:04:28.097728: step: 566/1545, loss: 0.10532540082931519 2023-01-23 13:04:29.086871: step: 568/1545, loss: 0.040145549923181534 2023-01-23 13:04:29.959857: step: 570/1545, loss: 0.06666721403598785 2023-01-23 13:04:30.845985: step: 572/1545, loss: 0.06341161578893661 2023-01-23 13:04:31.712858: step: 574/1545, loss: 0.09384126961231232 2023-01-23 13:04:32.569481: step: 576/1545, loss: 0.011138441041111946 2023-01-23 13:04:33.443342: step: 578/1545, loss: 0.18712759017944336 2023-01-23 13:04:34.322322: step: 580/1545, loss: 0.15307223796844482 2023-01-23 13:04:35.209030: step: 582/1545, loss: 0.05314380303025246 2023-01-23 13:04:36.084785: step: 584/1545, loss: 0.5382211208343506 2023-01-23 13:04:36.959530: step: 586/1545, loss: 0.009183967486023903 2023-01-23 13:04:37.825085: step: 588/1545, loss: 0.032545506954193115 2023-01-23 13:04:38.689790: step: 590/1545, loss: 0.01851639524102211 2023-01-23 13:04:39.602590: step: 592/1545, loss: 0.059031981974840164 2023-01-23 13:04:40.552548: step: 594/1545, loss: 0.017013156786561012 2023-01-23 13:04:41.433915: step: 596/1545, loss: 0.04287254065275192 2023-01-23 13:04:42.303288: step: 598/1545, loss: 0.03897968307137489 2023-01-23 13:04:43.196469: step: 600/1545, loss: 0.17158626019954681 2023-01-23 13:04:44.096812: step: 602/1545, loss: 0.007988538593053818 2023-01-23 13:04:44.987499: step: 604/1545, loss: 0.15020804107189178 2023-01-23 13:04:45.851664: step: 606/1545, loss: 0.060609448701143265 2023-01-23 13:04:46.801179: step: 608/1545, loss: 0.1617872565984726 2023-01-23 13:04:47.672088: step: 610/1545, loss: 0.2198324054479599 2023-01-23 13:04:48.545084: step: 612/1545, loss: 0.25533589720726013 2023-01-23 13:04:49.399340: step: 614/1545, loss: 0.11705628782510757 2023-01-23 13:04:50.245012: step: 616/1545, loss: 0.5202316045761108 2023-01-23 13:04:51.135634: step: 618/1545, loss: 0.007779641076922417 2023-01-23 13:04:51.986335: step: 620/1545, loss: 0.03769970312714577 2023-01-23 13:04:52.851151: step: 622/1545, loss: 0.04135952889919281 2023-01-23 13:04:53.772087: step: 624/1545, loss: 0.031942225992679596 2023-01-23 13:04:54.634064: step: 626/1545, loss: 0.19755718111991882 2023-01-23 13:04:55.518350: step: 628/1545, loss: 0.08883573859930038 2023-01-23 13:04:56.401281: step: 630/1545, loss: 0.005186222959309816 2023-01-23 13:04:57.257763: step: 632/1545, loss: 0.0010478722397238016 2023-01-23 13:04:58.121496: step: 634/1545, loss: 0.25500771403312683 2023-01-23 13:04:59.004429: step: 636/1545, loss: 0.03842691704630852 2023-01-23 13:04:59.917247: step: 638/1545, loss: 0.02476520650088787 2023-01-23 13:05:00.760850: step: 640/1545, loss: 0.1595716029405594 2023-01-23 13:05:01.688642: step: 642/1545, loss: 0.011796360835433006 2023-01-23 13:05:02.593308: step: 644/1545, loss: 0.02126772701740265 2023-01-23 13:05:03.425275: step: 646/1545, loss: 0.017468838021159172 2023-01-23 13:05:04.258808: step: 648/1545, loss: 0.007675757631659508 2023-01-23 13:05:05.142770: step: 650/1545, loss: 0.0014970789197832346 2023-01-23 13:05:06.037092: step: 652/1545, loss: 0.020328592509031296 2023-01-23 13:05:06.871728: step: 654/1545, loss: 6.104700088500977 2023-01-23 13:05:07.763733: step: 656/1545, loss: 0.05890849977731705 2023-01-23 13:05:08.636627: step: 658/1545, loss: 0.03842831030488014 2023-01-23 13:05:09.492148: step: 660/1545, loss: 0.048136260360479355 2023-01-23 13:05:10.404582: step: 662/1545, loss: 0.014949620701372623 2023-01-23 13:05:11.266280: step: 664/1545, loss: 0.14164675772190094 2023-01-23 13:05:12.150670: step: 666/1545, loss: 0.0035839173942804337 2023-01-23 13:05:13.084728: step: 668/1545, loss: 0.15898434817790985 2023-01-23 13:05:13.966804: step: 670/1545, loss: 3.567575454711914 2023-01-23 13:05:14.829086: step: 672/1545, loss: 0.0013578101061284542 2023-01-23 13:05:15.699825: step: 674/1545, loss: 0.0012932787649333477 2023-01-23 13:05:16.564819: step: 676/1545, loss: 0.3195172846317291 2023-01-23 13:05:17.440582: step: 678/1545, loss: 0.17178092896938324 2023-01-23 13:05:18.350549: step: 680/1545, loss: 0.040731847286224365 2023-01-23 13:05:19.220332: step: 682/1545, loss: 0.19691428542137146 2023-01-23 13:05:20.059478: step: 684/1545, loss: 0.02195361815392971 2023-01-23 13:05:20.965355: step: 686/1545, loss: 0.017675599083304405 2023-01-23 13:05:21.837917: step: 688/1545, loss: 0.00795273669064045 2023-01-23 13:05:22.708692: step: 690/1545, loss: 0.02872428297996521 2023-01-23 13:05:23.584264: step: 692/1545, loss: 0.2383842021226883 2023-01-23 13:05:24.494869: step: 694/1545, loss: 0.18742485344409943 2023-01-23 13:05:25.366581: step: 696/1545, loss: 0.12965618073940277 2023-01-23 13:05:26.240626: step: 698/1545, loss: 0.1863347291946411 2023-01-23 13:05:27.128292: step: 700/1545, loss: 0.18154510855674744 2023-01-23 13:05:28.023875: step: 702/1545, loss: 0.13310930132865906 2023-01-23 13:05:28.898336: step: 704/1545, loss: 0.11725934594869614 2023-01-23 13:05:29.792345: step: 706/1545, loss: 0.29129230976104736 2023-01-23 13:05:30.649971: step: 708/1545, loss: 0.03877861052751541 2023-01-23 13:05:31.491657: step: 710/1545, loss: 0.0022827479988336563 2023-01-23 13:05:32.383005: step: 712/1545, loss: 0.016525808721780777 2023-01-23 13:05:33.276951: step: 714/1545, loss: 0.04269660636782646 2023-01-23 13:05:34.149185: step: 716/1545, loss: 0.02085358463227749 2023-01-23 13:05:35.080747: step: 718/1545, loss: 0.017608720809221268 2023-01-23 13:05:35.989500: step: 720/1545, loss: 0.06868242472410202 2023-01-23 13:05:36.913579: step: 722/1545, loss: 0.09946905821561813 2023-01-23 13:05:37.857923: step: 724/1545, loss: 0.0281694196164608 2023-01-23 13:05:38.703572: step: 726/1545, loss: 0.20795856416225433 2023-01-23 13:05:39.613895: step: 728/1545, loss: 0.008797341957688332 2023-01-23 13:05:40.477189: step: 730/1545, loss: 0.5729557871818542 2023-01-23 13:05:41.351454: step: 732/1545, loss: 0.00293255178257823 2023-01-23 13:05:42.213421: step: 734/1545, loss: 0.02407277375459671 2023-01-23 13:05:43.126144: step: 736/1545, loss: 0.034506987780332565 2023-01-23 13:05:43.956408: step: 738/1545, loss: 0.0026945415884256363 2023-01-23 13:05:44.864371: step: 740/1545, loss: 0.01829705201089382 2023-01-23 13:05:45.782548: step: 742/1545, loss: 0.10199102014303207 2023-01-23 13:05:46.631100: step: 744/1545, loss: 0.13668914139270782 2023-01-23 13:05:47.512273: step: 746/1545, loss: 0.2187645584344864 2023-01-23 13:05:48.363079: step: 748/1545, loss: 0.01086550671607256 2023-01-23 13:05:49.326266: step: 750/1545, loss: 0.004444057587534189 2023-01-23 13:05:50.208170: step: 752/1545, loss: 0.03961367532610893 2023-01-23 13:05:51.069563: step: 754/1545, loss: 0.2672857344150543 2023-01-23 13:05:52.018877: step: 756/1545, loss: 0.021016258746385574 2023-01-23 13:05:52.872360: step: 758/1545, loss: 0.06627320498228073 2023-01-23 13:05:53.720895: step: 760/1545, loss: 0.04769467934966087 2023-01-23 13:05:54.617956: step: 762/1545, loss: 0.025989755988121033 2023-01-23 13:05:55.513372: step: 764/1545, loss: 1.2562717199325562 2023-01-23 13:05:56.373679: step: 766/1545, loss: 0.0040020328015089035 2023-01-23 13:05:57.284340: step: 768/1545, loss: 0.3544442057609558 2023-01-23 13:05:58.198383: step: 770/1545, loss: 0.020320426672697067 2023-01-23 13:05:59.052460: step: 772/1545, loss: 0.18057839572429657 2023-01-23 13:05:59.899123: step: 774/1545, loss: 0.011312228627502918 2023-01-23 13:06:00.777827: step: 776/1545, loss: 0.025146087631583214 2023-01-23 13:06:01.665660: step: 778/1545, loss: 0.10066857188940048 2023-01-23 13:06:02.550612: step: 780/1545, loss: 0.0031461715698242188 2023-01-23 13:06:03.437493: step: 782/1545, loss: 0.05960961431264877 2023-01-23 13:06:04.368500: step: 784/1545, loss: 0.0005644502234645188 2023-01-23 13:06:05.234446: step: 786/1545, loss: 0.2749848961830139 2023-01-23 13:06:06.089015: step: 788/1545, loss: 0.0006664221291430295 2023-01-23 13:06:06.978067: step: 790/1545, loss: 0.10228795558214188 2023-01-23 13:06:07.846732: step: 792/1545, loss: 0.1012239158153534 2023-01-23 13:06:08.697586: step: 794/1545, loss: 0.1935991495847702 2023-01-23 13:06:09.569879: step: 796/1545, loss: 0.011885641142725945 2023-01-23 13:06:10.442721: step: 798/1545, loss: 0.038856495171785355 2023-01-23 13:06:11.294761: step: 800/1545, loss: 0.0053261928260326385 2023-01-23 13:06:12.171209: step: 802/1545, loss: 0.014249049127101898 2023-01-23 13:06:13.032904: step: 804/1545, loss: 0.07789111137390137 2023-01-23 13:06:13.890283: step: 806/1545, loss: 0.002565621165558696 2023-01-23 13:06:14.809505: step: 808/1545, loss: 0.0032229353673756123 2023-01-23 13:06:15.679044: step: 810/1545, loss: 0.039594266563653946 2023-01-23 13:06:16.529162: step: 812/1545, loss: 0.029291342943906784 2023-01-23 13:06:17.378734: step: 814/1545, loss: 0.019818924367427826 2023-01-23 13:06:18.273948: step: 816/1545, loss: 0.18374289572238922 2023-01-23 13:06:19.124405: step: 818/1545, loss: 0.3937387764453888 2023-01-23 13:06:20.025187: step: 820/1545, loss: 0.024264613166451454 2023-01-23 13:06:20.925358: step: 822/1545, loss: 0.013881062157452106 2023-01-23 13:06:21.796266: step: 824/1545, loss: 0.015167856588959694 2023-01-23 13:06:22.667664: step: 826/1545, loss: 0.17129381000995636 2023-01-23 13:06:23.604524: step: 828/1545, loss: 0.07840064913034439 2023-01-23 13:06:24.531243: step: 830/1545, loss: 0.00788012146949768 2023-01-23 13:06:25.394804: step: 832/1545, loss: 0.027030715718865395 2023-01-23 13:06:26.302711: step: 834/1545, loss: 0.17151543498039246 2023-01-23 13:06:27.182887: step: 836/1545, loss: 0.021787254139780998 2023-01-23 13:06:28.078191: step: 838/1545, loss: 0.11089206486940384 2023-01-23 13:06:28.996205: step: 840/1545, loss: 0.18757706880569458 2023-01-23 13:06:29.842989: step: 842/1545, loss: 0.013705940917134285 2023-01-23 13:06:30.764327: step: 844/1545, loss: 0.009400429204106331 2023-01-23 13:06:31.630814: step: 846/1545, loss: 0.010230515152215958 2023-01-23 13:06:32.589447: step: 848/1545, loss: 1.7677279710769653 2023-01-23 13:06:33.482874: step: 850/1545, loss: 0.007822694256901741 2023-01-23 13:06:34.325931: step: 852/1545, loss: 0.3540712893009186 2023-01-23 13:06:35.201545: step: 854/1545, loss: 0.20899684727191925 2023-01-23 13:06:36.108933: step: 856/1545, loss: 0.005423150025308132 2023-01-23 13:06:37.007733: step: 858/1545, loss: 0.02043721079826355 2023-01-23 13:06:37.881392: step: 860/1545, loss: 0.08448413014411926 2023-01-23 13:06:38.791193: step: 862/1545, loss: 0.051071491092443466 2023-01-23 13:06:39.649776: step: 864/1545, loss: 0.07899343967437744 2023-01-23 13:06:40.535637: step: 866/1545, loss: 0.06450490653514862 2023-01-23 13:06:41.376666: step: 868/1545, loss: 0.0393398217856884 2023-01-23 13:06:42.276268: step: 870/1545, loss: 0.026235409080982208 2023-01-23 13:06:43.133039: step: 872/1545, loss: 0.0011768722906708717 2023-01-23 13:06:43.975907: step: 874/1545, loss: 0.0014314069412648678 2023-01-23 13:06:44.842787: step: 876/1545, loss: 0.6203831434249878 2023-01-23 13:06:45.731587: step: 878/1545, loss: 0.00799794215708971 2023-01-23 13:06:46.599060: step: 880/1545, loss: 0.026298856362700462 2023-01-23 13:06:47.442151: step: 882/1545, loss: 0.12304197996854782 2023-01-23 13:06:48.299688: step: 884/1545, loss: 0.036740742623806 2023-01-23 13:06:49.184935: step: 886/1545, loss: 0.07212378084659576 2023-01-23 13:06:50.052566: step: 888/1545, loss: 0.009764822199940681 2023-01-23 13:06:50.965686: step: 890/1545, loss: 0.024733049795031548 2023-01-23 13:06:51.801597: step: 892/1545, loss: 0.008856236934661865 2023-01-23 13:06:52.667084: step: 894/1545, loss: 0.07496245950460434 2023-01-23 13:06:53.557682: step: 896/1545, loss: 0.011781911365687847 2023-01-23 13:06:54.427792: step: 898/1545, loss: 0.0534963458776474 2023-01-23 13:06:55.286843: step: 900/1545, loss: 0.1550801694393158 2023-01-23 13:06:56.191415: step: 902/1545, loss: 0.047029998153448105 2023-01-23 13:06:57.161484: step: 904/1545, loss: 0.20026685297489166 2023-01-23 13:06:58.051498: step: 906/1545, loss: 0.038306597620248795 2023-01-23 13:06:58.927620: step: 908/1545, loss: 0.05181856453418732 2023-01-23 13:06:59.851996: step: 910/1545, loss: 0.025866413488984108 2023-01-23 13:07:00.689806: step: 912/1545, loss: 0.06411012262105942 2023-01-23 13:07:01.572310: step: 914/1545, loss: 0.1595892757177353 2023-01-23 13:07:02.439875: step: 916/1545, loss: 0.4977847635746002 2023-01-23 13:07:03.269728: step: 918/1545, loss: 0.009481336921453476 2023-01-23 13:07:04.122580: step: 920/1545, loss: 0.022968456149101257 2023-01-23 13:07:05.126492: step: 922/1545, loss: 0.06619071960449219 2023-01-23 13:07:06.053648: step: 924/1545, loss: 0.0018780860118567944 2023-01-23 13:07:06.935509: step: 926/1545, loss: 0.04099848121404648 2023-01-23 13:07:07.779212: step: 928/1545, loss: 0.06402618438005447 2023-01-23 13:07:08.634528: step: 930/1545, loss: 0.00575867248699069 2023-01-23 13:07:09.511636: step: 932/1545, loss: 0.021065665408968925 2023-01-23 13:07:10.453618: step: 934/1545, loss: 0.005926859099417925 2023-01-23 13:07:11.298637: step: 936/1545, loss: 0.0036697322502732277 2023-01-23 13:07:12.176498: step: 938/1545, loss: 0.005394695792347193 2023-01-23 13:07:13.148609: step: 940/1545, loss: 0.24086609482765198 2023-01-23 13:07:14.019367: step: 942/1545, loss: 0.024817004799842834 2023-01-23 13:07:14.896350: step: 944/1545, loss: 0.014054019935429096 2023-01-23 13:07:15.738369: step: 946/1545, loss: 0.0007809754461050034 2023-01-23 13:07:16.611628: step: 948/1545, loss: 0.02173788659274578 2023-01-23 13:07:17.465877: step: 950/1545, loss: 0.021517451852560043 2023-01-23 13:07:18.336798: step: 952/1545, loss: 0.1639011800289154 2023-01-23 13:07:19.264231: step: 954/1545, loss: 0.048093702644109726 2023-01-23 13:07:20.142582: step: 956/1545, loss: 0.039789628237485886 2023-01-23 13:07:21.016959: step: 958/1545, loss: 0.431468665599823 2023-01-23 13:07:21.843587: step: 960/1545, loss: 0.00965199340134859 2023-01-23 13:07:22.718391: step: 962/1545, loss: 0.13370923697948456 2023-01-23 13:07:23.553522: step: 964/1545, loss: 0.5584167242050171 2023-01-23 13:07:24.399431: step: 966/1545, loss: 0.12328696995973587 2023-01-23 13:07:25.244221: step: 968/1545, loss: 0.06544400006532669 2023-01-23 13:07:26.140292: step: 970/1545, loss: 0.4141349792480469 2023-01-23 13:07:27.041388: step: 972/1545, loss: 0.0733504444360733 2023-01-23 13:07:27.938959: step: 974/1545, loss: 0.008785724639892578 2023-01-23 13:07:28.941465: step: 976/1545, loss: 0.030283566564321518 2023-01-23 13:07:29.781529: step: 978/1545, loss: 0.04595573619008064 2023-01-23 13:07:30.643109: step: 980/1545, loss: 0.12847843766212463 2023-01-23 13:07:31.525443: step: 982/1545, loss: 0.00258005503565073 2023-01-23 13:07:32.393575: step: 984/1545, loss: 0.06962419301271439 2023-01-23 13:07:33.286812: step: 986/1545, loss: 0.0402386300265789 2023-01-23 13:07:34.177554: step: 988/1545, loss: 0.011738907545804977 2023-01-23 13:07:35.055014: step: 990/1545, loss: 0.004595313221216202 2023-01-23 13:07:35.990633: step: 992/1545, loss: 0.05242118611931801 2023-01-23 13:07:36.846569: step: 994/1545, loss: 0.18260139226913452 2023-01-23 13:07:37.780869: step: 996/1545, loss: 0.32426413893699646 2023-01-23 13:07:38.668804: step: 998/1545, loss: 0.04450227692723274 2023-01-23 13:07:39.539981: step: 1000/1545, loss: 0.04786035418510437 2023-01-23 13:07:40.433142: step: 1002/1545, loss: 0.047363363206386566 2023-01-23 13:07:41.270121: step: 1004/1545, loss: 0.14344438910484314 2023-01-23 13:07:42.136602: step: 1006/1545, loss: 0.0035983496345579624 2023-01-23 13:07:43.036289: step: 1008/1545, loss: 0.002956488635390997 2023-01-23 13:07:43.894607: step: 1010/1545, loss: 0.17325207591056824 2023-01-23 13:07:44.762495: step: 1012/1545, loss: 0.2859855890274048 2023-01-23 13:07:45.610306: step: 1014/1545, loss: 0.02763945236802101 2023-01-23 13:07:46.521829: step: 1016/1545, loss: 0.4797540605068207 2023-01-23 13:07:47.375033: step: 1018/1545, loss: 0.19973577558994293 2023-01-23 13:07:48.299226: step: 1020/1545, loss: 0.0360695905983448 2023-01-23 13:07:49.178718: step: 1022/1545, loss: 0.006211233790963888 2023-01-23 13:07:50.032315: step: 1024/1545, loss: 0.1643458902835846 2023-01-23 13:07:50.900395: step: 1026/1545, loss: 0.14721347391605377 2023-01-23 13:07:51.749388: step: 1028/1545, loss: 0.06970681995153427 2023-01-23 13:07:52.684791: step: 1030/1545, loss: 0.4125458300113678 2023-01-23 13:07:53.542836: step: 1032/1545, loss: 0.01753436028957367 2023-01-23 13:07:54.441386: step: 1034/1545, loss: 0.2369089424610138 2023-01-23 13:07:55.312410: step: 1036/1545, loss: 0.44565078616142273 2023-01-23 13:07:56.186867: step: 1038/1545, loss: 0.20668545365333557 2023-01-23 13:07:57.128850: step: 1040/1545, loss: 0.03815381973981857 2023-01-23 13:07:58.055178: step: 1042/1545, loss: 0.03651246428489685 2023-01-23 13:07:58.958531: step: 1044/1545, loss: 0.0034383446909487247 2023-01-23 13:07:59.835371: step: 1046/1545, loss: 0.1555180847644806 2023-01-23 13:08:00.714944: step: 1048/1545, loss: 0.15351329743862152 2023-01-23 13:08:01.552411: step: 1050/1545, loss: 0.025459080934524536 2023-01-23 13:08:02.401740: step: 1052/1545, loss: 0.0038858549669384956 2023-01-23 13:08:03.283244: step: 1054/1545, loss: 0.15092766284942627 2023-01-23 13:08:04.157276: step: 1056/1545, loss: 0.10411089658737183 2023-01-23 13:08:05.043129: step: 1058/1545, loss: 0.05614379420876503 2023-01-23 13:08:05.982099: step: 1060/1545, loss: 0.008924786001443863 2023-01-23 13:08:06.857407: step: 1062/1545, loss: 0.07450135797262192 2023-01-23 13:08:07.695755: step: 1064/1545, loss: 0.1837264448404312 2023-01-23 13:08:08.583967: step: 1066/1545, loss: 0.14747416973114014 2023-01-23 13:08:09.453867: step: 1068/1545, loss: 0.3078141510486603 2023-01-23 13:08:10.340796: step: 1070/1545, loss: 0.0030472634825855494 2023-01-23 13:08:11.244695: step: 1072/1545, loss: 0.040007006376981735 2023-01-23 13:08:12.104963: step: 1074/1545, loss: 0.0036421597469598055 2023-01-23 13:08:12.983579: step: 1076/1545, loss: 0.0016886504599824548 2023-01-23 13:08:13.908649: step: 1078/1545, loss: 0.006647337693721056 2023-01-23 13:08:14.774510: step: 1080/1545, loss: 0.09451030939817429 2023-01-23 13:08:15.650510: step: 1082/1545, loss: 0.008357152342796326 2023-01-23 13:08:16.493083: step: 1084/1545, loss: 0.049672938883304596 2023-01-23 13:08:17.366448: step: 1086/1545, loss: 0.1709023416042328 2023-01-23 13:08:18.244522: step: 1088/1545, loss: 0.11201626807451248 2023-01-23 13:08:19.114933: step: 1090/1545, loss: 0.012103801593184471 2023-01-23 13:08:20.004033: step: 1092/1545, loss: 0.15927082300186157 2023-01-23 13:08:20.902829: step: 1094/1545, loss: 0.004722684621810913 2023-01-23 13:08:21.825470: step: 1096/1545, loss: 0.1288529932498932 2023-01-23 13:08:22.745646: step: 1098/1545, loss: 0.31917133927345276 2023-01-23 13:08:23.680831: step: 1100/1545, loss: 0.00926683284342289 2023-01-23 13:08:24.574791: step: 1102/1545, loss: 0.14312420785427094 2023-01-23 13:08:25.431894: step: 1104/1545, loss: 0.05791093409061432 2023-01-23 13:08:26.303293: step: 1106/1545, loss: 0.5601202249526978 2023-01-23 13:08:27.170990: step: 1108/1545, loss: 0.08476884663105011 2023-01-23 13:08:28.016245: step: 1110/1545, loss: 0.2877418100833893 2023-01-23 13:08:28.878667: step: 1112/1545, loss: 0.017615096643567085 2023-01-23 13:08:29.802086: step: 1114/1545, loss: 0.02420734614133835 2023-01-23 13:08:30.707296: step: 1116/1545, loss: 0.0543423593044281 2023-01-23 13:08:31.575315: step: 1118/1545, loss: 0.028827035799622536 2023-01-23 13:08:32.449362: step: 1120/1545, loss: 0.011326028034090996 2023-01-23 13:08:33.392899: step: 1122/1545, loss: 0.054521456360816956 2023-01-23 13:08:34.274539: step: 1124/1545, loss: 0.05776859074831009 2023-01-23 13:08:35.196419: step: 1126/1545, loss: 0.08990152925252914 2023-01-23 13:08:36.060540: step: 1128/1545, loss: 0.21402636170387268 2023-01-23 13:08:36.958165: step: 1130/1545, loss: 0.003927511628717184 2023-01-23 13:08:37.860440: step: 1132/1545, loss: 0.273237019777298 2023-01-23 13:08:38.718867: step: 1134/1545, loss: 0.021859023720026016 2023-01-23 13:08:39.610122: step: 1136/1545, loss: 0.05826658010482788 2023-01-23 13:08:40.476715: step: 1138/1545, loss: 0.007171271834522486 2023-01-23 13:08:41.371463: step: 1140/1545, loss: 0.027244597673416138 2023-01-23 13:08:42.255955: step: 1142/1545, loss: 0.13665741682052612 2023-01-23 13:08:43.216082: step: 1144/1545, loss: 0.029156778007745743 2023-01-23 13:08:44.083470: step: 1146/1545, loss: 0.005310961976647377 2023-01-23 13:08:44.973792: step: 1148/1545, loss: 0.005026026628911495 2023-01-23 13:08:45.850000: step: 1150/1545, loss: 0.24499034881591797 2023-01-23 13:08:46.686604: step: 1152/1545, loss: 0.010480867698788643 2023-01-23 13:08:47.576229: step: 1154/1545, loss: 0.0007534888572990894 2023-01-23 13:08:48.443030: step: 1156/1545, loss: 0.0014841726515442133 2023-01-23 13:08:49.302562: step: 1158/1545, loss: 0.006522407289594412 2023-01-23 13:08:50.152708: step: 1160/1545, loss: 0.10381516814231873 2023-01-23 13:08:51.067201: step: 1162/1545, loss: 0.02546071633696556 2023-01-23 13:08:51.934793: step: 1164/1545, loss: 0.0007854393334127963 2023-01-23 13:08:52.826063: step: 1166/1545, loss: 0.051755622029304504 2023-01-23 13:08:53.713261: step: 1168/1545, loss: 0.0003020945587195456 2023-01-23 13:08:54.565869: step: 1170/1545, loss: 0.0023106823209673166 2023-01-23 13:08:55.536199: step: 1172/1545, loss: 0.09816019237041473 2023-01-23 13:08:56.417408: step: 1174/1545, loss: 0.01678610034286976 2023-01-23 13:08:57.308899: step: 1176/1545, loss: 0.14030678570270538 2023-01-23 13:08:58.202364: step: 1178/1545, loss: 0.020381726324558258 2023-01-23 13:08:59.174236: step: 1180/1545, loss: 0.05517632141709328 2023-01-23 13:09:00.093086: step: 1182/1545, loss: 0.0032785742077976465 2023-01-23 13:09:00.981812: step: 1184/1545, loss: 0.0028768822085112333 2023-01-23 13:09:01.862817: step: 1186/1545, loss: 0.7261391878128052 2023-01-23 13:09:02.734082: step: 1188/1545, loss: 0.14001141488552094 2023-01-23 13:09:03.607979: step: 1190/1545, loss: 0.008588568307459354 2023-01-23 13:09:04.479545: step: 1192/1545, loss: 0.2187015265226364 2023-01-23 13:09:05.385293: step: 1194/1545, loss: 0.0008589307544752955 2023-01-23 13:09:06.286361: step: 1196/1545, loss: 0.8038954734802246 2023-01-23 13:09:07.163593: step: 1198/1545, loss: 0.07563087344169617 2023-01-23 13:09:08.053592: step: 1200/1545, loss: 0.00137260090559721 2023-01-23 13:09:08.915993: step: 1202/1545, loss: 0.021065639331936836 2023-01-23 13:09:09.839339: step: 1204/1545, loss: 0.10251327604055405 2023-01-23 13:09:10.693167: step: 1206/1545, loss: 0.3420215845108032 2023-01-23 13:09:11.518601: step: 1208/1545, loss: 0.03218495845794678 2023-01-23 13:09:12.390140: step: 1210/1545, loss: 0.09092093259096146 2023-01-23 13:09:13.282592: step: 1212/1545, loss: 0.06608667224645615 2023-01-23 13:09:14.162588: step: 1214/1545, loss: 0.010365478694438934 2023-01-23 13:09:15.055330: step: 1216/1545, loss: 0.08090388774871826 2023-01-23 13:09:15.907696: step: 1218/1545, loss: 0.1401548683643341 2023-01-23 13:09:16.788268: step: 1220/1545, loss: 0.15049739181995392 2023-01-23 13:09:17.738830: step: 1222/1545, loss: 0.0014603716554120183 2023-01-23 13:09:18.647951: step: 1224/1545, loss: 0.23233294486999512 2023-01-23 13:09:19.523356: step: 1226/1545, loss: 0.08877502381801605 2023-01-23 13:09:20.411170: step: 1228/1545, loss: 0.09259054809808731 2023-01-23 13:09:21.381059: step: 1230/1545, loss: 0.028283346444368362 2023-01-23 13:09:22.214885: step: 1232/1545, loss: 0.30652138590812683 2023-01-23 13:09:23.117021: step: 1234/1545, loss: 0.013206147588789463 2023-01-23 13:09:23.995505: step: 1236/1545, loss: 0.39104384183883667 2023-01-23 13:09:24.897576: step: 1238/1545, loss: 0.06381361186504364 2023-01-23 13:09:25.757730: step: 1240/1545, loss: 0.03899291157722473 2023-01-23 13:09:26.611402: step: 1242/1545, loss: 0.2238772213459015 2023-01-23 13:09:27.471363: step: 1244/1545, loss: 0.004860507324337959 2023-01-23 13:09:28.352729: step: 1246/1545, loss: 0.08459219336509705 2023-01-23 13:09:29.251338: step: 1248/1545, loss: 0.0018197819590568542 2023-01-23 13:09:30.124870: step: 1250/1545, loss: 0.1275644749403 2023-01-23 13:09:30.980455: step: 1252/1545, loss: 0.2032606601715088 2023-01-23 13:09:31.838937: step: 1254/1545, loss: 0.4782716929912567 2023-01-23 13:09:32.729964: step: 1256/1545, loss: 0.3846624791622162 2023-01-23 13:09:33.571124: step: 1258/1545, loss: 0.004207625985145569 2023-01-23 13:09:34.470576: step: 1260/1545, loss: 0.3768818974494934 2023-01-23 13:09:35.326841: step: 1262/1545, loss: 0.012278062291443348 2023-01-23 13:09:36.216287: step: 1264/1545, loss: 0.08101669698953629 2023-01-23 13:09:37.093153: step: 1266/1545, loss: 0.4408513903617859 2023-01-23 13:09:37.988660: step: 1268/1545, loss: 0.04403993487358093 2023-01-23 13:09:38.910701: step: 1270/1545, loss: 0.030481938272714615 2023-01-23 13:09:39.814894: step: 1272/1545, loss: 0.08346486836671829 2023-01-23 13:09:40.673357: step: 1274/1545, loss: 0.027241846546530724 2023-01-23 13:09:41.557826: step: 1276/1545, loss: 0.0269634909927845 2023-01-23 13:09:42.496052: step: 1278/1545, loss: 0.46071216464042664 2023-01-23 13:09:43.423777: step: 1280/1545, loss: 0.2756492793560028 2023-01-23 13:09:44.277711: step: 1282/1545, loss: 0.241171196103096 2023-01-23 13:09:45.194376: step: 1284/1545, loss: 0.0195601973682642 2023-01-23 13:09:46.115696: step: 1286/1545, loss: 0.10184057056903839 2023-01-23 13:09:47.026862: step: 1288/1545, loss: 0.34181076288223267 2023-01-23 13:09:47.909451: step: 1290/1545, loss: 0.07306207716464996 2023-01-23 13:09:48.735180: step: 1292/1545, loss: 0.03108353354036808 2023-01-23 13:09:49.614300: step: 1294/1545, loss: 0.22571726143360138 2023-01-23 13:09:50.530722: step: 1296/1545, loss: 0.036529865115880966 2023-01-23 13:09:51.397391: step: 1298/1545, loss: 0.06783270090818405 2023-01-23 13:09:52.255230: step: 1300/1545, loss: 0.044623006135225296 2023-01-23 13:09:53.102966: step: 1302/1545, loss: 0.06799346953630447 2023-01-23 13:09:53.950219: step: 1304/1545, loss: 0.016475368291139603 2023-01-23 13:09:54.894687: step: 1306/1545, loss: 1.0301203727722168 2023-01-23 13:09:55.767033: step: 1308/1545, loss: 0.008785915561020374 2023-01-23 13:09:56.630630: step: 1310/1545, loss: 0.0247909277677536 2023-01-23 13:09:57.498498: step: 1312/1545, loss: 0.7550013065338135 2023-01-23 13:09:58.396621: step: 1314/1545, loss: 0.31742578744888306 2023-01-23 13:09:59.272854: step: 1316/1545, loss: 0.19542011618614197 2023-01-23 13:10:00.142074: step: 1318/1545, loss: 0.03508434072136879 2023-01-23 13:10:01.050343: step: 1320/1545, loss: 0.0002881773980334401 2023-01-23 13:10:01.944305: step: 1322/1545, loss: 0.4143025279045105 2023-01-23 13:10:02.817239: step: 1324/1545, loss: 0.01603677123785019 2023-01-23 13:10:03.659144: step: 1326/1545, loss: 0.045581791549921036 2023-01-23 13:10:04.617993: step: 1328/1545, loss: 0.009542351588606834 2023-01-23 13:10:05.509512: step: 1330/1545, loss: 0.01766502484679222 2023-01-23 13:10:06.376681: step: 1332/1545, loss: 0.16149428486824036 2023-01-23 13:10:07.221268: step: 1334/1545, loss: 0.014780922792851925 2023-01-23 13:10:08.105747: step: 1336/1545, loss: 0.013073720037937164 2023-01-23 13:10:08.999868: step: 1338/1545, loss: 0.0023110026959329844 2023-01-23 13:10:09.883961: step: 1340/1545, loss: 0.05409025400876999 2023-01-23 13:10:10.823787: step: 1342/1545, loss: 0.0028735001105815172 2023-01-23 13:10:11.655218: step: 1344/1545, loss: 0.12786827981472015 2023-01-23 13:10:12.508830: step: 1346/1545, loss: 0.17057491838932037 2023-01-23 13:10:13.382474: step: 1348/1545, loss: 0.001253277761861682 2023-01-23 13:10:14.259220: step: 1350/1545, loss: 0.11684352159500122 2023-01-23 13:10:15.146216: step: 1352/1545, loss: 0.007962558418512344 2023-01-23 13:10:16.033721: step: 1354/1545, loss: 0.1296406239271164 2023-01-23 13:10:16.890730: step: 1356/1545, loss: 0.1754501312971115 2023-01-23 13:10:17.746764: step: 1358/1545, loss: 0.0029085357673466206 2023-01-23 13:10:18.603668: step: 1360/1545, loss: 2.3393261432647705 2023-01-23 13:10:19.443422: step: 1362/1545, loss: 0.4732205271720886 2023-01-23 13:10:20.316141: step: 1364/1545, loss: 0.003062554867938161 2023-01-23 13:10:21.191143: step: 1366/1545, loss: 0.011759452521800995 2023-01-23 13:10:22.072099: step: 1368/1545, loss: 0.02039674110710621 2023-01-23 13:10:22.984735: step: 1370/1545, loss: 0.09774304926395416 2023-01-23 13:10:23.879599: step: 1372/1545, loss: 0.06922571361064911 2023-01-23 13:10:24.748161: step: 1374/1545, loss: 0.012789038009941578 2023-01-23 13:10:25.628644: step: 1376/1545, loss: 0.00764982495456934 2023-01-23 13:10:26.497391: step: 1378/1545, loss: 0.05260886251926422 2023-01-23 13:10:27.430932: step: 1380/1545, loss: 0.11314557492733002 2023-01-23 13:10:28.352354: step: 1382/1545, loss: 0.08748579770326614 2023-01-23 13:10:29.283992: step: 1384/1545, loss: 0.12393706291913986 2023-01-23 13:10:30.156111: step: 1386/1545, loss: 0.11272687464952469 2023-01-23 13:10:31.024691: step: 1388/1545, loss: 0.25031042098999023 2023-01-23 13:10:31.866696: step: 1390/1545, loss: 0.10137572139501572 2023-01-23 13:10:32.712336: step: 1392/1545, loss: 0.008936100639402866 2023-01-23 13:10:33.588988: step: 1394/1545, loss: 0.1115957498550415 2023-01-23 13:10:34.494881: step: 1396/1545, loss: 0.01153477281332016 2023-01-23 13:10:35.395732: step: 1398/1545, loss: 0.05044851824641228 2023-01-23 13:10:36.249651: step: 1400/1545, loss: 0.008492509834468365 2023-01-23 13:10:37.105159: step: 1402/1545, loss: 0.005327027756720781 2023-01-23 13:10:37.996885: step: 1404/1545, loss: 0.004729739390313625 2023-01-23 13:10:38.885466: step: 1406/1545, loss: 0.0036684577353298664 2023-01-23 13:10:39.833479: step: 1408/1545, loss: 0.015193828381597996 2023-01-23 13:10:40.690306: step: 1410/1545, loss: 0.0195262860506773 2023-01-23 13:10:41.520772: step: 1412/1545, loss: 0.0050808945670723915 2023-01-23 13:10:42.368232: step: 1414/1545, loss: 0.18078476190567017 2023-01-23 13:10:43.400567: step: 1416/1545, loss: 0.09907902032136917 2023-01-23 13:10:44.269738: step: 1418/1545, loss: 0.060998521745204926 2023-01-23 13:10:45.204279: step: 1420/1545, loss: 0.002931367140263319 2023-01-23 13:10:46.082462: step: 1422/1545, loss: 0.008580286987125874 2023-01-23 13:10:46.920992: step: 1424/1545, loss: 0.002559439977630973 2023-01-23 13:10:47.783764: step: 1426/1545, loss: 0.010618475265800953 2023-01-23 13:10:48.673977: step: 1428/1545, loss: 0.025116749107837677 2023-01-23 13:10:49.569159: step: 1430/1545, loss: 0.0002251500845886767 2023-01-23 13:10:50.428704: step: 1432/1545, loss: 0.739711344242096 2023-01-23 13:10:51.333514: step: 1434/1545, loss: 0.20844300091266632 2023-01-23 13:10:52.207621: step: 1436/1545, loss: 0.7339999079704285 2023-01-23 13:10:53.054259: step: 1438/1545, loss: 1.5052205324172974 2023-01-23 13:10:53.907018: step: 1440/1545, loss: 0.005573701579123735 2023-01-23 13:10:54.916141: step: 1442/1545, loss: 0.06322547793388367 2023-01-23 13:10:55.774887: step: 1444/1545, loss: 0.21933338046073914 2023-01-23 13:10:56.640524: step: 1446/1545, loss: 0.14068946242332458 2023-01-23 13:10:57.509196: step: 1448/1545, loss: 0.010011809878051281 2023-01-23 13:10:58.388492: step: 1450/1545, loss: 0.324622243642807 2023-01-23 13:10:59.297149: step: 1452/1545, loss: 0.005431618541479111 2023-01-23 13:11:00.146589: step: 1454/1545, loss: 0.019686643034219742 2023-01-23 13:11:00.979572: step: 1456/1545, loss: 0.29080918431282043 2023-01-23 13:11:01.875016: step: 1458/1545, loss: 0.12482184916734695 2023-01-23 13:11:02.808672: step: 1460/1545, loss: 0.24368853867053986 2023-01-23 13:11:03.689598: step: 1462/1545, loss: 0.0174405500292778 2023-01-23 13:11:04.604067: step: 1464/1545, loss: 0.03987235948443413 2023-01-23 13:11:05.471093: step: 1466/1545, loss: 0.3094376027584076 2023-01-23 13:11:06.334141: step: 1468/1545, loss: 0.05416828393936157 2023-01-23 13:11:07.228402: step: 1470/1545, loss: 0.3694382905960083 2023-01-23 13:11:08.112174: step: 1472/1545, loss: 0.01458775531500578 2023-01-23 13:11:08.986230: step: 1474/1545, loss: 0.03998719900846481 2023-01-23 13:11:09.861876: step: 1476/1545, loss: 0.16716212034225464 2023-01-23 13:11:10.717109: step: 1478/1545, loss: 0.3051580488681793 2023-01-23 13:11:11.566835: step: 1480/1545, loss: 0.0017469015438109636 2023-01-23 13:11:12.440683: step: 1482/1545, loss: 0.17084956169128418 2023-01-23 13:11:13.333676: step: 1484/1545, loss: 0.11720294505357742 2023-01-23 13:11:14.259780: step: 1486/1545, loss: 0.10051168501377106 2023-01-23 13:11:15.139804: step: 1488/1545, loss: 0.23859864473342896 2023-01-23 13:11:16.049923: step: 1490/1545, loss: 0.0737856924533844 2023-01-23 13:11:16.923939: step: 1492/1545, loss: 0.018159078434109688 2023-01-23 13:11:17.881526: step: 1494/1545, loss: 0.03538314253091812 2023-01-23 13:11:18.719814: step: 1496/1545, loss: 0.02836969867348671 2023-01-23 13:11:19.565306: step: 1498/1545, loss: 0.048324085772037506 2023-01-23 13:11:20.460713: step: 1500/1545, loss: 0.09659964591264725 2023-01-23 13:11:21.341150: step: 1502/1545, loss: 0.012563064694404602 2023-01-23 13:11:22.261438: step: 1504/1545, loss: 0.003383542411029339 2023-01-23 13:11:23.190617: step: 1506/1545, loss: 0.15717336535453796 2023-01-23 13:11:24.114259: step: 1508/1545, loss: 0.0017739032628014684 2023-01-23 13:11:25.006831: step: 1510/1545, loss: 0.19514217972755432 2023-01-23 13:11:25.935814: step: 1512/1545, loss: 0.18674840033054352 2023-01-23 13:11:26.815442: step: 1514/1545, loss: 0.16390036046504974 2023-01-23 13:11:27.690207: step: 1516/1545, loss: 0.13913752138614655 2023-01-23 13:11:28.584966: step: 1518/1545, loss: 0.005959231406450272 2023-01-23 13:11:29.472241: step: 1520/1545, loss: 0.14451941847801208 2023-01-23 13:11:30.353681: step: 1522/1545, loss: 0.09128985553979874 2023-01-23 13:11:31.238589: step: 1524/1545, loss: 0.22637835144996643 2023-01-23 13:11:32.131532: step: 1526/1545, loss: 0.07706230878829956 2023-01-23 13:11:32.981843: step: 1528/1545, loss: 0.015012589283287525 2023-01-23 13:11:33.850327: step: 1530/1545, loss: 0.02583838254213333 2023-01-23 13:11:34.769880: step: 1532/1545, loss: 0.023262759670615196 2023-01-23 13:11:35.650974: step: 1534/1545, loss: 0.015649665147066116 2023-01-23 13:11:36.587395: step: 1536/1545, loss: 0.04979775846004486 2023-01-23 13:11:37.498113: step: 1538/1545, loss: 0.1977996677160263 2023-01-23 13:11:38.338623: step: 1540/1545, loss: 0.008078833110630512 2023-01-23 13:11:39.241772: step: 1542/1545, loss: 0.006499752402305603 2023-01-23 13:11:40.088288: step: 1544/1545, loss: 0.10376230627298355 2023-01-23 13:11:40.921723: step: 1546/1545, loss: 0.008907976560294628 2023-01-23 13:11:41.770363: step: 1548/1545, loss: 0.08830216526985168 2023-01-23 13:11:42.675278: step: 1550/1545, loss: 0.007910970598459244 2023-01-23 13:11:43.568183: step: 1552/1545, loss: 0.0070446208119392395 2023-01-23 13:11:44.487726: step: 1554/1545, loss: 0.1663651168346405 2023-01-23 13:11:45.353126: step: 1556/1545, loss: 0.10514496266841888 2023-01-23 13:11:46.286516: step: 1558/1545, loss: 0.07171735912561417 2023-01-23 13:11:47.178601: step: 1560/1545, loss: 0.8473116755485535 2023-01-23 13:11:48.011397: step: 1562/1545, loss: 0.12224704027175903 2023-01-23 13:11:48.902856: step: 1564/1545, loss: 0.07000192254781723 2023-01-23 13:11:49.771520: step: 1566/1545, loss: 0.0077957697212696075 2023-01-23 13:11:50.638947: step: 1568/1545, loss: 0.035529620945453644 2023-01-23 13:11:51.521446: step: 1570/1545, loss: 0.11033596098423004 2023-01-23 13:11:52.367821: step: 1572/1545, loss: 0.008843391202390194 2023-01-23 13:11:53.226188: step: 1574/1545, loss: 0.028201039880514145 2023-01-23 13:11:54.184958: step: 1576/1545, loss: 0.04921320453286171 2023-01-23 13:11:55.066118: step: 1578/1545, loss: 0.04657413065433502 2023-01-23 13:11:55.932327: step: 1580/1545, loss: 0.052485283464193344 2023-01-23 13:11:56.846869: step: 1582/1545, loss: 0.015775959938764572 2023-01-23 13:11:57.734889: step: 1584/1545, loss: 0.15212062001228333 2023-01-23 13:11:58.620333: step: 1586/1545, loss: 0.2621224522590637 2023-01-23 13:11:59.473565: step: 1588/1545, loss: 0.0008242063922807574 2023-01-23 13:12:00.367380: step: 1590/1545, loss: 0.18786132335662842 2023-01-23 13:12:01.267756: step: 1592/1545, loss: 0.03731011226773262 2023-01-23 13:12:02.178525: step: 1594/1545, loss: 0.27678075432777405 2023-01-23 13:12:03.033586: step: 1596/1545, loss: 0.041976455599069595 2023-01-23 13:12:03.938727: step: 1598/1545, loss: 0.03461577743291855 2023-01-23 13:12:04.776577: step: 1600/1545, loss: 0.016115611419081688 2023-01-23 13:12:05.627580: step: 1602/1545, loss: 0.07760685682296753 2023-01-23 13:12:06.513865: step: 1604/1545, loss: 0.003728131763637066 2023-01-23 13:12:07.406483: step: 1606/1545, loss: 0.05548375844955444 2023-01-23 13:12:08.264945: step: 1608/1545, loss: 0.15279129147529602 2023-01-23 13:12:09.178485: step: 1610/1545, loss: 0.09939572215080261 2023-01-23 13:12:10.045078: step: 1612/1545, loss: 0.11383641511201859 2023-01-23 13:12:10.922454: step: 1614/1545, loss: 0.059343334287405014 2023-01-23 13:12:11.785077: step: 1616/1545, loss: 0.014692082069814205 2023-01-23 13:12:12.674853: step: 1618/1545, loss: 0.32372716069221497 2023-01-23 13:12:13.543290: step: 1620/1545, loss: 0.02161071076989174 2023-01-23 13:12:14.544864: step: 1622/1545, loss: 0.03318018466234207 2023-01-23 13:12:15.399301: step: 1624/1545, loss: 0.03218240290880203 2023-01-23 13:12:16.260931: step: 1626/1545, loss: 0.03744323179125786 2023-01-23 13:12:17.103914: step: 1628/1545, loss: 0.018262915313243866 2023-01-23 13:12:17.945236: step: 1630/1545, loss: 0.008902217261493206 2023-01-23 13:12:18.819994: step: 1632/1545, loss: 0.1594412624835968 2023-01-23 13:12:19.750187: step: 1634/1545, loss: 0.7316502928733826 2023-01-23 13:12:20.662270: step: 1636/1545, loss: 0.07200103253126144 2023-01-23 13:12:21.558596: step: 1638/1545, loss: 0.1319291889667511 2023-01-23 13:12:22.439422: step: 1640/1545, loss: 0.5350074768066406 2023-01-23 13:12:23.323958: step: 1642/1545, loss: 0.1012640967965126 2023-01-23 13:12:24.176280: step: 1644/1545, loss: 0.05833209306001663 2023-01-23 13:12:25.069973: step: 1646/1545, loss: 0.16810789704322815 2023-01-23 13:12:25.952898: step: 1648/1545, loss: 0.011440053582191467 2023-01-23 13:12:26.834710: step: 1650/1545, loss: 0.0034243017435073853 2023-01-23 13:12:27.669802: step: 1652/1545, loss: 0.039795178920030594 2023-01-23 13:12:28.582064: step: 1654/1545, loss: 0.2024025171995163 2023-01-23 13:12:29.450154: step: 1656/1545, loss: 0.5348802208900452 2023-01-23 13:12:30.334884: step: 1658/1545, loss: 0.026620198041200638 2023-01-23 13:12:31.237623: step: 1660/1545, loss: 0.4799284040927887 2023-01-23 13:12:32.137223: step: 1662/1545, loss: 6.8160810470581055 2023-01-23 13:12:33.005349: step: 1664/1545, loss: 0.006541271228343248 2023-01-23 13:12:33.846788: step: 1666/1545, loss: 0.03507464751601219 2023-01-23 13:12:34.712434: step: 1668/1545, loss: 0.015017416328191757 2023-01-23 13:12:35.572527: step: 1670/1545, loss: 0.038959477096796036 2023-01-23 13:12:36.421376: step: 1672/1545, loss: 0.13384099304676056 2023-01-23 13:12:37.265863: step: 1674/1545, loss: 0.09171741455793381 2023-01-23 13:12:38.140282: step: 1676/1545, loss: 0.3007144629955292 2023-01-23 13:12:39.038762: step: 1678/1545, loss: 0.0058222683146595955 2023-01-23 13:12:39.946221: step: 1680/1545, loss: 0.542150616645813 2023-01-23 13:12:40.851793: step: 1682/1545, loss: 0.09651926904916763 2023-01-23 13:12:41.713251: step: 1684/1545, loss: 0.04210178181529045 2023-01-23 13:12:42.564024: step: 1686/1545, loss: 0.3383825421333313 2023-01-23 13:12:43.487427: step: 1688/1545, loss: 0.12405222654342651 2023-01-23 13:12:44.360402: step: 1690/1545, loss: 0.15725865960121155 2023-01-23 13:12:45.207463: step: 1692/1545, loss: 0.15329234302043915 2023-01-23 13:12:46.042715: step: 1694/1545, loss: 0.0033375839702785015 2023-01-23 13:12:46.891540: step: 1696/1545, loss: 0.0033332742750644684 2023-01-23 13:12:47.771486: step: 1698/1545, loss: 0.016834627836942673 2023-01-23 13:12:48.685027: step: 1700/1545, loss: 0.01702667586505413 2023-01-23 13:12:49.579122: step: 1702/1545, loss: 0.006058266386389732 2023-01-23 13:12:50.519627: step: 1704/1545, loss: 0.01551147736608982 2023-01-23 13:12:51.396066: step: 1706/1545, loss: 0.23538821935653687 2023-01-23 13:12:52.373536: step: 1708/1545, loss: 0.023639937862753868 2023-01-23 13:12:53.344412: step: 1710/1545, loss: 0.12862618267536163 2023-01-23 13:12:54.272255: step: 1712/1545, loss: 0.210145965218544 2023-01-23 13:12:55.111594: step: 1714/1545, loss: 0.0761294960975647 2023-01-23 13:12:55.996735: step: 1716/1545, loss: 0.050883904099464417 2023-01-23 13:12:56.884957: step: 1718/1545, loss: 0.011127511039376259 2023-01-23 13:12:57.757728: step: 1720/1545, loss: 0.10283895581960678 2023-01-23 13:12:58.610174: step: 1722/1545, loss: 0.0030054396484047174 2023-01-23 13:12:59.465996: step: 1724/1545, loss: 0.07956590503454208 2023-01-23 13:13:00.325158: step: 1726/1545, loss: 0.01894993707537651 2023-01-23 13:13:01.254459: step: 1728/1545, loss: 0.05055241286754608 2023-01-23 13:13:02.113093: step: 1730/1545, loss: 0.0028667200822383165 2023-01-23 13:13:02.972462: step: 1732/1545, loss: 0.02325962856411934 2023-01-23 13:13:03.836764: step: 1734/1545, loss: 0.0024946718476712704 2023-01-23 13:13:04.752206: step: 1736/1545, loss: 0.0092122508212924 2023-01-23 13:13:05.622828: step: 1738/1545, loss: 0.1874474436044693 2023-01-23 13:13:06.503673: step: 1740/1545, loss: 0.13867928087711334 2023-01-23 13:13:07.379504: step: 1742/1545, loss: 0.10570337623357773 2023-01-23 13:13:08.241632: step: 1744/1545, loss: 0.004215652123093605 2023-01-23 13:13:09.162983: step: 1746/1545, loss: 0.13770636916160583 2023-01-23 13:13:10.053361: step: 1748/1545, loss: 0.25687915086746216 2023-01-23 13:13:10.913530: step: 1750/1545, loss: 0.03227464109659195 2023-01-23 13:13:11.786080: step: 1752/1545, loss: 0.05437946319580078 2023-01-23 13:13:12.661747: step: 1754/1545, loss: 0.02206454984843731 2023-01-23 13:13:13.528970: step: 1756/1545, loss: 0.08009108155965805 2023-01-23 13:13:14.402918: step: 1758/1545, loss: 0.04529329389333725 2023-01-23 13:13:15.244394: step: 1760/1545, loss: 0.010329028591513634 2023-01-23 13:13:16.116769: step: 1762/1545, loss: 0.014425165951251984 2023-01-23 13:13:17.028005: step: 1764/1545, loss: 0.05322442203760147 2023-01-23 13:13:17.894349: step: 1766/1545, loss: 0.0048316847532987595 2023-01-23 13:13:18.742457: step: 1768/1545, loss: 0.030594095587730408 2023-01-23 13:13:19.635182: step: 1770/1545, loss: 0.14942516386508942 2023-01-23 13:13:20.486274: step: 1772/1545, loss: 0.16033515334129333 2023-01-23 13:13:21.463417: step: 1774/1545, loss: 0.1361466348171234 2023-01-23 13:13:22.343442: step: 1776/1545, loss: 0.07484010607004166 2023-01-23 13:13:23.208248: step: 1778/1545, loss: 0.0902465283870697 2023-01-23 13:13:24.085686: step: 1780/1545, loss: 0.007893821224570274 2023-01-23 13:13:24.957221: step: 1782/1545, loss: 0.04155251756310463 2023-01-23 13:13:25.856359: step: 1784/1545, loss: 0.09573141485452652 2023-01-23 13:13:26.775120: step: 1786/1545, loss: 0.2452065497636795 2023-01-23 13:13:27.638742: step: 1788/1545, loss: 0.0022360316943377256 2023-01-23 13:13:28.521495: step: 1790/1545, loss: 0.04129102826118469 2023-01-23 13:13:29.410267: step: 1792/1545, loss: 1.015882968902588 2023-01-23 13:13:30.277636: step: 1794/1545, loss: 0.013483734801411629 2023-01-23 13:13:31.170719: step: 1796/1545, loss: 0.36740976572036743 2023-01-23 13:13:32.079595: step: 1798/1545, loss: 0.07741081714630127 2023-01-23 13:13:33.007754: step: 1800/1545, loss: 0.06371130794286728 2023-01-23 13:13:33.905427: step: 1802/1545, loss: 0.08380411565303802 2023-01-23 13:13:34.792119: step: 1804/1545, loss: 0.09835822880268097 2023-01-23 13:13:35.685213: step: 1806/1545, loss: 0.018920807167887688 2023-01-23 13:13:36.563375: step: 1808/1545, loss: 0.1198260560631752 2023-01-23 13:13:37.434178: step: 1810/1545, loss: 0.11366964131593704 2023-01-23 13:13:38.302974: step: 1812/1545, loss: 0.4852813482284546 2023-01-23 13:13:39.174401: step: 1814/1545, loss: 0.04791221767663956 2023-01-23 13:13:40.031375: step: 1816/1545, loss: 0.10807233303785324 2023-01-23 13:13:40.892567: step: 1818/1545, loss: 0.0534055195748806 2023-01-23 13:13:41.777458: step: 1820/1545, loss: 0.03697967529296875 2023-01-23 13:13:42.648879: step: 1822/1545, loss: 0.004237933084368706 2023-01-23 13:13:43.531947: step: 1824/1545, loss: 0.0032820268534123898 2023-01-23 13:13:44.442086: step: 1826/1545, loss: 0.07862650603055954 2023-01-23 13:13:45.305319: step: 1828/1545, loss: 0.005530095659196377 2023-01-23 13:13:46.161591: step: 1830/1545, loss: 0.8327198028564453 2023-01-23 13:13:47.061088: step: 1832/1545, loss: 0.06326363980770111 2023-01-23 13:13:47.958999: step: 1834/1545, loss: 0.09932269155979156 2023-01-23 13:13:48.834115: step: 1836/1545, loss: 0.006534771993756294 2023-01-23 13:13:49.707184: step: 1838/1545, loss: 0.27221137285232544 2023-01-23 13:13:50.600943: step: 1840/1545, loss: 1.0018057823181152 2023-01-23 13:13:51.544019: step: 1842/1545, loss: 0.1353830248117447 2023-01-23 13:13:52.480812: step: 1844/1545, loss: 0.005393609870225191 2023-01-23 13:13:53.364708: step: 1846/1545, loss: 0.28576740622520447 2023-01-23 13:13:54.237727: step: 1848/1545, loss: 0.9643625617027283 2023-01-23 13:13:55.097951: step: 1850/1545, loss: 0.3039553761482239 2023-01-23 13:13:56.052008: step: 1852/1545, loss: 0.3027800917625427 2023-01-23 13:13:56.950596: step: 1854/1545, loss: 0.17599865794181824 2023-01-23 13:13:57.796238: step: 1856/1545, loss: 0.01263126078993082 2023-01-23 13:13:58.659093: step: 1858/1545, loss: 0.029545968398451805 2023-01-23 13:13:59.596475: step: 1860/1545, loss: 0.0029258800204843283 2023-01-23 13:14:00.509796: step: 1862/1545, loss: 0.16565948724746704 2023-01-23 13:14:01.401538: step: 1864/1545, loss: 0.0029842325020581484 2023-01-23 13:14:02.270045: step: 1866/1545, loss: 0.10113988816738129 2023-01-23 13:14:03.167527: step: 1868/1545, loss: 0.14281046390533447 2023-01-23 13:14:04.077262: step: 1870/1545, loss: 0.006739106960594654 2023-01-23 13:14:04.981818: step: 1872/1545, loss: 0.04191708564758301 2023-01-23 13:14:05.864121: step: 1874/1545, loss: 0.011711865663528442 2023-01-23 13:14:06.734583: step: 1876/1545, loss: 0.14799223840236664 2023-01-23 13:14:07.624975: step: 1878/1545, loss: 0.011387491598725319 2023-01-23 13:14:08.437767: step: 1880/1545, loss: 0.014137757010757923 2023-01-23 13:14:09.318992: step: 1882/1545, loss: 0.029550326988101006 2023-01-23 13:14:10.220713: step: 1884/1545, loss: 0.3487023711204529 2023-01-23 13:14:11.085240: step: 1886/1545, loss: 0.02240641415119171 2023-01-23 13:14:11.955073: step: 1888/1545, loss: 0.04987205192446709 2023-01-23 13:14:12.831533: step: 1890/1545, loss: 0.0018477097619324923 2023-01-23 13:14:13.741710: step: 1892/1545, loss: 0.039997346699237823 2023-01-23 13:14:14.650787: step: 1894/1545, loss: 0.09365455061197281 2023-01-23 13:14:15.513295: step: 1896/1545, loss: 0.15182150900363922 2023-01-23 13:14:16.362396: step: 1898/1545, loss: 0.2062050700187683 2023-01-23 13:14:17.206972: step: 1900/1545, loss: 0.060538798570632935 2023-01-23 13:14:18.067440: step: 1902/1545, loss: 0.005612322129309177 2023-01-23 13:14:18.967501: step: 1904/1545, loss: 0.2271866649389267 2023-01-23 13:14:19.887587: step: 1906/1545, loss: 0.009196720086038113 2023-01-23 13:14:20.848714: step: 1908/1545, loss: 0.0030389169696718454 2023-01-23 13:14:21.707761: step: 1910/1545, loss: 0.002488987520337105 2023-01-23 13:14:22.621972: step: 1912/1545, loss: 0.03637829050421715 2023-01-23 13:14:23.526055: step: 1914/1545, loss: 0.04541170969605446 2023-01-23 13:14:24.416970: step: 1916/1545, loss: 0.07705061137676239 2023-01-23 13:14:25.271432: step: 1918/1545, loss: 0.1440318077802658 2023-01-23 13:14:26.095851: step: 1920/1545, loss: 0.0028316716197878122 2023-01-23 13:14:26.923720: step: 1922/1545, loss: 0.03920067846775055 2023-01-23 13:14:27.813889: step: 1924/1545, loss: 0.12465690821409225 2023-01-23 13:14:28.730813: step: 1926/1545, loss: 0.0808487981557846 2023-01-23 13:14:29.602572: step: 1928/1545, loss: 0.013197317719459534 2023-01-23 13:14:30.502547: step: 1930/1545, loss: 0.03655361756682396 2023-01-23 13:14:31.350186: step: 1932/1545, loss: 0.13201335072517395 2023-01-23 13:14:32.243654: step: 1934/1545, loss: 0.004297004081308842 2023-01-23 13:14:33.148899: step: 1936/1545, loss: 0.011812564916908741 2023-01-23 13:14:34.001540: step: 1938/1545, loss: 0.07756968587636948 2023-01-23 13:14:34.835523: step: 1940/1545, loss: 0.03969142213463783 2023-01-23 13:14:35.720637: step: 1942/1545, loss: 0.4315439760684967 2023-01-23 13:14:36.581523: step: 1944/1545, loss: 0.061275187879800797 2023-01-23 13:14:37.457765: step: 1946/1545, loss: 0.010865596123039722 2023-01-23 13:14:38.303120: step: 1948/1545, loss: 0.05646514147520065 2023-01-23 13:14:39.154421: step: 1950/1545, loss: 0.1537320911884308 2023-01-23 13:14:40.024439: step: 1952/1545, loss: 0.13312751054763794 2023-01-23 13:14:40.902631: step: 1954/1545, loss: 0.32527393102645874 2023-01-23 13:14:41.768042: step: 1956/1545, loss: 0.06853421032428741 2023-01-23 13:14:42.625790: step: 1958/1545, loss: 0.2086264044046402 2023-01-23 13:14:43.493493: step: 1960/1545, loss: 0.030128343030810356 2023-01-23 13:14:44.384126: step: 1962/1545, loss: 0.0769033133983612 2023-01-23 13:14:45.309546: step: 1964/1545, loss: 0.1478116810321808 2023-01-23 13:14:46.216061: step: 1966/1545, loss: 0.018307529389858246 2023-01-23 13:14:47.113731: step: 1968/1545, loss: 0.07666905969381332 2023-01-23 13:14:47.977250: step: 1970/1545, loss: 0.023451315239071846 2023-01-23 13:14:48.862589: step: 1972/1545, loss: 0.07265465706586838 2023-01-23 13:14:49.733853: step: 1974/1545, loss: 0.18658827245235443 2023-01-23 13:14:50.590089: step: 1976/1545, loss: 0.23488663136959076 2023-01-23 13:14:51.498459: step: 1978/1545, loss: 0.01290223840624094 2023-01-23 13:14:52.376711: step: 1980/1545, loss: 0.055813368409872055 2023-01-23 13:14:53.244838: step: 1982/1545, loss: 0.1352507323026657 2023-01-23 13:14:54.168061: step: 1984/1545, loss: 0.0011949579929932952 2023-01-23 13:14:55.057890: step: 1986/1545, loss: 0.010313039645552635 2023-01-23 13:14:55.951147: step: 1988/1545, loss: 0.74042809009552 2023-01-23 13:14:56.824338: step: 1990/1545, loss: 0.11295191198587418 2023-01-23 13:14:57.672259: step: 1992/1545, loss: 0.5271374583244324 2023-01-23 13:14:58.533877: step: 1994/1545, loss: 0.013880515471100807 2023-01-23 13:14:59.486208: step: 1996/1545, loss: 0.01474376767873764 2023-01-23 13:15:00.395286: step: 1998/1545, loss: 0.23203711211681366 2023-01-23 13:15:01.252336: step: 2000/1545, loss: 0.06496059894561768 2023-01-23 13:15:02.116358: step: 2002/1545, loss: 0.00607444578781724 2023-01-23 13:15:02.988198: step: 2004/1545, loss: 0.05075879767537117 2023-01-23 13:15:03.893574: step: 2006/1545, loss: 0.01769399084150791 2023-01-23 13:15:04.758893: step: 2008/1545, loss: 0.2520526051521301 2023-01-23 13:15:05.607910: step: 2010/1545, loss: 0.0006238687783479691 2023-01-23 13:15:06.576621: step: 2012/1545, loss: 0.020623913034796715 2023-01-23 13:15:07.445085: step: 2014/1545, loss: 0.02590879052877426 2023-01-23 13:15:08.316899: step: 2016/1545, loss: 0.07774585485458374 2023-01-23 13:15:09.206718: step: 2018/1545, loss: 0.009943710640072823 2023-01-23 13:15:10.040608: step: 2020/1545, loss: 0.35207539796829224 2023-01-23 13:15:10.908608: step: 2022/1545, loss: 0.12878938019275665 2023-01-23 13:15:11.800682: step: 2024/1545, loss: 0.32027626037597656 2023-01-23 13:15:12.676398: step: 2026/1545, loss: 0.047610606998205185 2023-01-23 13:15:13.546411: step: 2028/1545, loss: 0.03904351964592934 2023-01-23 13:15:14.431438: step: 2030/1545, loss: 0.39820438623428345 2023-01-23 13:15:15.265100: step: 2032/1545, loss: 0.20508360862731934 2023-01-23 13:15:16.102826: step: 2034/1545, loss: 0.8041406273841858 2023-01-23 13:15:16.970753: step: 2036/1545, loss: 0.4908750355243683 2023-01-23 13:15:17.838697: step: 2038/1545, loss: 0.04330812022089958 2023-01-23 13:15:18.726062: step: 2040/1545, loss: 0.05321882292628288 2023-01-23 13:15:19.600124: step: 2042/1545, loss: 0.0016008258098736405 2023-01-23 13:15:20.491971: step: 2044/1545, loss: 0.08555540442466736 2023-01-23 13:15:21.362999: step: 2046/1545, loss: 0.027706798166036606 2023-01-23 13:15:22.249396: step: 2048/1545, loss: 0.18275469541549683 2023-01-23 13:15:23.091681: step: 2050/1545, loss: 0.029928352683782578 2023-01-23 13:15:24.044043: step: 2052/1545, loss: 0.3216903507709503 2023-01-23 13:15:24.879792: step: 2054/1545, loss: 0.2505718171596527 2023-01-23 13:15:25.726261: step: 2056/1545, loss: 0.04163007810711861 2023-01-23 13:15:26.598591: step: 2058/1545, loss: 0.4074135720729828 2023-01-23 13:15:27.531650: step: 2060/1545, loss: 0.17140920460224152 2023-01-23 13:15:28.397073: step: 2062/1545, loss: 0.04036802798509598 2023-01-23 13:15:29.238971: step: 2064/1545, loss: 0.07553791999816895 2023-01-23 13:15:30.152819: step: 2066/1545, loss: 0.006818622350692749 2023-01-23 13:15:31.079941: step: 2068/1545, loss: 0.023172177374362946 2023-01-23 13:15:31.942232: step: 2070/1545, loss: 0.004428900312632322 2023-01-23 13:15:32.800744: step: 2072/1545, loss: 0.03263893723487854 2023-01-23 13:15:33.744458: step: 2074/1545, loss: 0.005710036493837833 2023-01-23 13:15:34.627156: step: 2076/1545, loss: 0.06468108296394348 2023-01-23 13:15:35.539763: step: 2078/1545, loss: 0.005985523574054241 2023-01-23 13:15:36.386999: step: 2080/1545, loss: 0.21665030717849731 2023-01-23 13:15:37.252928: step: 2082/1545, loss: 0.024311944842338562 2023-01-23 13:15:38.124957: step: 2084/1545, loss: 0.037747226655483246 2023-01-23 13:15:39.005153: step: 2086/1545, loss: 0.11930518597364426 2023-01-23 13:15:39.896970: step: 2088/1545, loss: 0.03521410748362541 2023-01-23 13:15:40.776499: step: 2090/1545, loss: 0.01148754172027111 2023-01-23 13:15:41.655993: step: 2092/1545, loss: 0.003872469998896122 2023-01-23 13:15:42.536715: step: 2094/1545, loss: 0.06271108984947205 2023-01-23 13:15:43.437327: step: 2096/1545, loss: 0.0009469365468248725 2023-01-23 13:15:44.258195: step: 2098/1545, loss: 0.10396259278059006 2023-01-23 13:15:45.120453: step: 2100/1545, loss: 0.282122939825058 2023-01-23 13:15:46.013152: step: 2102/1545, loss: 0.008426693268120289 2023-01-23 13:15:46.902360: step: 2104/1545, loss: 0.07691489905118942 2023-01-23 13:15:47.779894: step: 2106/1545, loss: 0.12856577336788177 2023-01-23 13:15:48.641682: step: 2108/1545, loss: 0.06286677718162537 2023-01-23 13:15:49.524861: step: 2110/1545, loss: 0.06330595165491104 2023-01-23 13:15:50.405977: step: 2112/1545, loss: 0.19056282937526703 2023-01-23 13:15:51.296317: step: 2114/1545, loss: 0.028493806719779968 2023-01-23 13:15:52.176322: step: 2116/1545, loss: 0.0037432133685797453 2023-01-23 13:15:53.068742: step: 2118/1545, loss: 0.1265176236629486 2023-01-23 13:15:53.976409: step: 2120/1545, loss: 0.029779987409710884 2023-01-23 13:15:54.875388: step: 2122/1545, loss: 0.0693797692656517 2023-01-23 13:15:55.743750: step: 2124/1545, loss: 0.02105386182665825 2023-01-23 13:15:56.656103: step: 2126/1545, loss: 0.11255737394094467 2023-01-23 13:15:57.505578: step: 2128/1545, loss: 0.22851034998893738 2023-01-23 13:15:58.403579: step: 2130/1545, loss: 0.08418336510658264 2023-01-23 13:15:59.285715: step: 2132/1545, loss: 0.1387588530778885 2023-01-23 13:16:00.147515: step: 2134/1545, loss: 0.11205437779426575 2023-01-23 13:16:01.007790: step: 2136/1545, loss: 0.09805367887020111 2023-01-23 13:16:01.855605: step: 2138/1545, loss: 0.01709066890180111 2023-01-23 13:16:02.730341: step: 2140/1545, loss: 0.025603314861655235 2023-01-23 13:16:03.634657: step: 2142/1545, loss: 0.0031885807402431965 2023-01-23 13:16:04.506485: step: 2144/1545, loss: 0.015618464909493923 2023-01-23 13:16:05.355585: step: 2146/1545, loss: 0.020074112340807915 2023-01-23 13:16:06.222942: step: 2148/1545, loss: 0.1348533034324646 2023-01-23 13:16:07.142962: step: 2150/1545, loss: 2.716026544570923 2023-01-23 13:16:08.041189: step: 2152/1545, loss: 0.5417485237121582 2023-01-23 13:16:08.932461: step: 2154/1545, loss: 0.013738072477281094 2023-01-23 13:16:09.789801: step: 2156/1545, loss: 0.0019841808825731277 2023-01-23 13:16:10.655599: step: 2158/1545, loss: 0.274554967880249 2023-01-23 13:16:11.482686: step: 2160/1545, loss: 0.09987097233533859 2023-01-23 13:16:12.327426: step: 2162/1545, loss: 0.006891623605042696 2023-01-23 13:16:13.171811: step: 2164/1545, loss: 0.03195316344499588 2023-01-23 13:16:14.020503: step: 2166/1545, loss: 0.02754121460020542 2023-01-23 13:16:14.897048: step: 2168/1545, loss: 0.014544250443577766 2023-01-23 13:16:15.783789: step: 2170/1545, loss: 0.011944103054702282 2023-01-23 13:16:16.652090: step: 2172/1545, loss: 0.09566006064414978 2023-01-23 13:16:17.516011: step: 2174/1545, loss: 0.08421172946691513 2023-01-23 13:16:18.351412: step: 2176/1545, loss: 0.020342063158750534 2023-01-23 13:16:19.267253: step: 2178/1545, loss: 0.010204341262578964 2023-01-23 13:16:20.183793: step: 2180/1545, loss: 0.1349181830883026 2023-01-23 13:16:21.011206: step: 2182/1545, loss: 0.024739079177379608 2023-01-23 13:16:21.894407: step: 2184/1545, loss: 0.03182448074221611 2023-01-23 13:16:22.798610: step: 2186/1545, loss: 0.19424019753932953 2023-01-23 13:16:23.657018: step: 2188/1545, loss: 0.02864883467555046 2023-01-23 13:16:24.584326: step: 2190/1545, loss: 0.7743207216262817 2023-01-23 13:16:25.458702: step: 2192/1545, loss: 0.053842104971408844 2023-01-23 13:16:26.404165: step: 2194/1545, loss: 0.19264979660511017 2023-01-23 13:16:27.272156: step: 2196/1545, loss: 0.10665122419595718 2023-01-23 13:16:28.131164: step: 2198/1545, loss: 0.01902276650071144 2023-01-23 13:16:28.979895: step: 2200/1545, loss: 0.02399594523012638 2023-01-23 13:16:29.830567: step: 2202/1545, loss: 0.08815188705921173 2023-01-23 13:16:30.741331: step: 2204/1545, loss: 0.4681447744369507 2023-01-23 13:16:31.595631: step: 2206/1545, loss: 0.0037019243463873863 2023-01-23 13:16:32.452627: step: 2208/1545, loss: 0.1180560290813446 2023-01-23 13:16:33.327247: step: 2210/1545, loss: 0.49029433727264404 2023-01-23 13:16:34.223191: step: 2212/1545, loss: 0.1716385930776596 2023-01-23 13:16:35.114812: step: 2214/1545, loss: 0.18183693289756775 2023-01-23 13:16:35.958585: step: 2216/1545, loss: 0.17445743083953857 2023-01-23 13:16:36.837432: step: 2218/1545, loss: 0.17626357078552246 2023-01-23 13:16:37.735648: step: 2220/1545, loss: 0.03129436820745468 2023-01-23 13:16:38.634673: step: 2222/1545, loss: 0.16860783100128174 2023-01-23 13:16:39.494797: step: 2224/1545, loss: 0.4689171016216278 2023-01-23 13:16:40.417571: step: 2226/1545, loss: 0.3977038562297821 2023-01-23 13:16:41.289810: step: 2228/1545, loss: 0.1097019761800766 2023-01-23 13:16:42.132211: step: 2230/1545, loss: 0.032740745693445206 2023-01-23 13:16:43.005629: step: 2232/1545, loss: 0.025143830105662346 2023-01-23 13:16:43.888450: step: 2234/1545, loss: 0.03944778814911842 2023-01-23 13:16:44.829668: step: 2236/1545, loss: 0.05247470363974571 2023-01-23 13:16:45.676721: step: 2238/1545, loss: 0.14185966551303864 2023-01-23 13:16:46.539322: step: 2240/1545, loss: 0.07151813805103302 2023-01-23 13:16:47.443131: step: 2242/1545, loss: 0.03864353895187378 2023-01-23 13:16:48.370363: step: 2244/1545, loss: 0.196635901927948 2023-01-23 13:16:49.273381: step: 2246/1545, loss: 0.030176382511854172 2023-01-23 13:16:50.127968: step: 2248/1545, loss: 0.047315098345279694 2023-01-23 13:16:50.997503: step: 2250/1545, loss: 0.20797298848628998 2023-01-23 13:16:51.891581: step: 2252/1545, loss: 0.1447155773639679 2023-01-23 13:16:52.776986: step: 2254/1545, loss: 0.0031855732668191195 2023-01-23 13:16:53.725753: step: 2256/1545, loss: 0.021489141508936882 2023-01-23 13:16:54.581191: step: 2258/1545, loss: 0.004638057202100754 2023-01-23 13:16:55.446981: step: 2260/1545, loss: 0.00936183426529169 2023-01-23 13:16:56.300073: step: 2262/1545, loss: 0.0567430779337883 2023-01-23 13:16:57.160260: step: 2264/1545, loss: 0.08284357935190201 2023-01-23 13:16:58.058074: step: 2266/1545, loss: 0.010317557491362095 2023-01-23 13:16:58.916558: step: 2268/1545, loss: 0.0032752875704318285 2023-01-23 13:16:59.781729: step: 2270/1545, loss: 0.005612425040453672 2023-01-23 13:17:00.640415: step: 2272/1545, loss: 0.0071983421221375465 2023-01-23 13:17:01.512095: step: 2274/1545, loss: 0.08274232596158981 2023-01-23 13:17:02.356534: step: 2276/1545, loss: 0.005507649853825569 2023-01-23 13:17:03.230071: step: 2278/1545, loss: 0.006024748086929321 2023-01-23 13:17:04.121140: step: 2280/1545, loss: 0.05114827677607536 2023-01-23 13:17:04.993432: step: 2282/1545, loss: 0.10489538311958313 2023-01-23 13:17:05.829170: step: 2284/1545, loss: 0.10253310203552246 2023-01-23 13:17:06.703344: step: 2286/1545, loss: 0.05750232934951782 2023-01-23 13:17:07.588800: step: 2288/1545, loss: 0.20508913695812225 2023-01-23 13:17:08.461332: step: 2290/1545, loss: 0.003324538469314575 2023-01-23 13:17:09.305345: step: 2292/1545, loss: 0.11933101713657379 2023-01-23 13:17:10.214904: step: 2294/1545, loss: 0.21228714287281036 2023-01-23 13:17:11.098779: step: 2296/1545, loss: 0.4593462646007538 2023-01-23 13:17:11.996336: step: 2298/1545, loss: 0.003895092522725463 2023-01-23 13:17:12.883336: step: 2300/1545, loss: 0.035089850425720215 2023-01-23 13:17:13.766803: step: 2302/1545, loss: 0.0182382483035326 2023-01-23 13:17:14.587817: step: 2304/1545, loss: 0.009063605219125748 2023-01-23 13:17:15.451041: step: 2306/1545, loss: 0.05065328627824783 2023-01-23 13:17:16.329017: step: 2308/1545, loss: 0.20829303562641144 2023-01-23 13:17:17.267378: step: 2310/1545, loss: 2.3596458435058594 2023-01-23 13:17:18.114366: step: 2312/1545, loss: 0.0003518856246955693 2023-01-23 13:17:18.980099: step: 2314/1545, loss: 0.007615651469677687 2023-01-23 13:17:19.847396: step: 2316/1545, loss: 0.312930703163147 2023-01-23 13:17:20.703150: step: 2318/1545, loss: 0.02003755047917366 2023-01-23 13:17:21.559186: step: 2320/1545, loss: 0.0015863400185480714 2023-01-23 13:17:22.457616: step: 2322/1545, loss: 0.35224276781082153 2023-01-23 13:17:23.313315: step: 2324/1545, loss: 0.022610940039157867 2023-01-23 13:17:24.165232: step: 2326/1545, loss: 0.8271859884262085 2023-01-23 13:17:25.067859: step: 2328/1545, loss: 0.004174451343715191 2023-01-23 13:17:26.019032: step: 2330/1545, loss: 0.14997190237045288 2023-01-23 13:17:26.868744: step: 2332/1545, loss: 0.2902618646621704 2023-01-23 13:17:27.742232: step: 2334/1545, loss: 0.04347481206059456 2023-01-23 13:17:28.761854: step: 2336/1545, loss: 0.18914330005645752 2023-01-23 13:17:29.708531: step: 2338/1545, loss: 0.028232993558049202 2023-01-23 13:17:30.599420: step: 2340/1545, loss: 0.1087733805179596 2023-01-23 13:17:31.511072: step: 2342/1545, loss: 0.06161768361926079 2023-01-23 13:17:32.420542: step: 2344/1545, loss: 0.06310324370861053 2023-01-23 13:17:33.297725: step: 2346/1545, loss: 0.09923196583986282 2023-01-23 13:17:34.147547: step: 2348/1545, loss: 0.10850907117128372 2023-01-23 13:17:35.010926: step: 2350/1545, loss: 0.010290984064340591 2023-01-23 13:17:35.902839: step: 2352/1545, loss: 0.003146507777273655 2023-01-23 13:17:36.820695: step: 2354/1545, loss: 0.3492579758167267 2023-01-23 13:17:37.759926: step: 2356/1545, loss: 0.04597271606326103 2023-01-23 13:17:38.624854: step: 2358/1545, loss: 0.5625627040863037 2023-01-23 13:17:39.516416: step: 2360/1545, loss: 0.0048700422048568726 2023-01-23 13:17:40.424930: step: 2362/1545, loss: 0.17290571331977844 2023-01-23 13:17:41.329408: step: 2364/1545, loss: 0.3122197091579437 2023-01-23 13:17:42.189098: step: 2366/1545, loss: 0.07692521065473557 2023-01-23 13:17:43.096876: step: 2368/1545, loss: 0.020464904606342316 2023-01-23 13:17:44.027419: step: 2370/1545, loss: 0.12301486730575562 2023-01-23 13:17:44.918315: step: 2372/1545, loss: 0.005537243559956551 2023-01-23 13:17:45.799945: step: 2374/1545, loss: 0.3159806728363037 2023-01-23 13:17:46.701208: step: 2376/1545, loss: 0.08558699488639832 2023-01-23 13:17:47.601590: step: 2378/1545, loss: 0.45112037658691406 2023-01-23 13:17:48.522493: step: 2380/1545, loss: 0.5736693143844604 2023-01-23 13:17:49.440567: step: 2382/1545, loss: 0.1309373825788498 2023-01-23 13:17:50.286743: step: 2384/1545, loss: 0.060611192137002945 2023-01-23 13:17:51.190376: step: 2386/1545, loss: 0.15108156204223633 2023-01-23 13:17:52.049978: step: 2388/1545, loss: 0.11861395835876465 2023-01-23 13:17:52.918107: step: 2390/1545, loss: 0.018499648198485374 2023-01-23 13:17:53.816582: step: 2392/1545, loss: 0.11417651921510696 2023-01-23 13:17:54.714480: step: 2394/1545, loss: 0.01614346355199814 2023-01-23 13:17:55.574949: step: 2396/1545, loss: 0.34342214465141296 2023-01-23 13:17:56.430151: step: 2398/1545, loss: 0.03070925734937191 2023-01-23 13:17:57.289828: step: 2400/1545, loss: 0.0772017166018486 2023-01-23 13:17:58.213142: step: 2402/1545, loss: 0.19465066492557526 2023-01-23 13:17:59.148221: step: 2404/1545, loss: 0.05832452327013016 2023-01-23 13:18:00.035397: step: 2406/1545, loss: 0.009620292112231255 2023-01-23 13:18:00.913684: step: 2408/1545, loss: 0.2059948742389679 2023-01-23 13:18:01.757793: step: 2410/1545, loss: 0.011442946270108223 2023-01-23 13:18:02.674644: step: 2412/1545, loss: 0.043879929929971695 2023-01-23 13:18:03.569420: step: 2414/1545, loss: 0.33895647525787354 2023-01-23 13:18:04.471268: step: 2416/1545, loss: 0.01813405752182007 2023-01-23 13:18:05.344278: step: 2418/1545, loss: 0.13474464416503906 2023-01-23 13:18:06.237476: step: 2420/1545, loss: 0.03098754957318306 2023-01-23 13:18:07.127041: step: 2422/1545, loss: 0.007630464155226946 2023-01-23 13:18:08.011066: step: 2424/1545, loss: 0.09540962427854538 2023-01-23 13:18:08.881861: step: 2426/1545, loss: 0.029899049550294876 2023-01-23 13:18:09.743511: step: 2428/1545, loss: 0.0304553359746933 2023-01-23 13:18:10.610945: step: 2430/1545, loss: 1.662959337234497 2023-01-23 13:18:11.502574: step: 2432/1545, loss: 0.1449221521615982 2023-01-23 13:18:12.420562: step: 2434/1545, loss: 0.0616765096783638 2023-01-23 13:18:13.290005: step: 2436/1545, loss: 0.059311024844646454 2023-01-23 13:18:14.137946: step: 2438/1545, loss: 0.004892021883279085 2023-01-23 13:18:15.029462: step: 2440/1545, loss: 0.17487414181232452 2023-01-23 13:18:15.928449: step: 2442/1545, loss: 0.028922157362103462 2023-01-23 13:18:16.810350: step: 2444/1545, loss: 0.14877276122570038 2023-01-23 13:18:17.693381: step: 2446/1545, loss: 0.029781512916088104 2023-01-23 13:18:18.549471: step: 2448/1545, loss: 0.046505119651556015 2023-01-23 13:18:19.411842: step: 2450/1545, loss: 0.10636787861585617 2023-01-23 13:18:20.291191: step: 2452/1545, loss: 0.04839715734124184 2023-01-23 13:18:21.161914: step: 2454/1545, loss: 0.0890420451760292 2023-01-23 13:18:22.013624: step: 2456/1545, loss: 0.09224466234445572 2023-01-23 13:18:22.900759: step: 2458/1545, loss: 0.04325311630964279 2023-01-23 13:18:23.775391: step: 2460/1545, loss: 0.009379149414598942 2023-01-23 13:18:24.659893: step: 2462/1545, loss: 0.15906699001789093 2023-01-23 13:18:25.497392: step: 2464/1545, loss: 0.012615736573934555 2023-01-23 13:18:26.370211: step: 2466/1545, loss: 0.018839940428733826 2023-01-23 13:18:27.234986: step: 2468/1545, loss: 0.13820859789848328 2023-01-23 13:18:28.140295: step: 2470/1545, loss: 0.1650010049343109 2023-01-23 13:18:29.018556: step: 2472/1545, loss: 0.2749015688896179 2023-01-23 13:18:29.874249: step: 2474/1545, loss: 0.06711876392364502 2023-01-23 13:18:30.733861: step: 2476/1545, loss: 0.33669137954711914 2023-01-23 13:18:31.605369: step: 2478/1545, loss: 0.06518606841564178 2023-01-23 13:18:32.480688: step: 2480/1545, loss: 0.03936299681663513 2023-01-23 13:18:33.326296: step: 2482/1545, loss: 0.07844318449497223 2023-01-23 13:18:34.197272: step: 2484/1545, loss: 0.03391335532069206 2023-01-23 13:18:35.068595: step: 2486/1545, loss: 0.0031877716537564993 2023-01-23 13:18:35.931063: step: 2488/1545, loss: 0.010607287287712097 2023-01-23 13:18:36.853992: step: 2490/1545, loss: 0.03655703738331795 2023-01-23 13:18:37.747092: step: 2492/1545, loss: 0.003467338625341654 2023-01-23 13:18:38.599085: step: 2494/1545, loss: 0.09175249934196472 2023-01-23 13:18:39.494651: step: 2496/1545, loss: 0.15162883698940277 2023-01-23 13:18:40.390711: step: 2498/1545, loss: 0.08790227770805359 2023-01-23 13:18:41.307825: step: 2500/1545, loss: 0.13586720824241638 2023-01-23 13:18:42.217040: step: 2502/1545, loss: 0.03974897786974907 2023-01-23 13:18:43.101155: step: 2504/1545, loss: 0.438725084066391 2023-01-23 13:18:44.018118: step: 2506/1545, loss: 0.07260920107364655 2023-01-23 13:18:44.873856: step: 2508/1545, loss: 0.0669933333992958 2023-01-23 13:18:45.779548: step: 2510/1545, loss: 0.7371311783790588 2023-01-23 13:18:46.653833: step: 2512/1545, loss: 0.2592056691646576 2023-01-23 13:18:47.498372: step: 2514/1545, loss: 0.2927010655403137 2023-01-23 13:18:48.351001: step: 2516/1545, loss: 0.020636819303035736 2023-01-23 13:18:49.272071: step: 2518/1545, loss: 0.026334330439567566 2023-01-23 13:18:50.242761: step: 2520/1545, loss: 0.15730619430541992 2023-01-23 13:18:51.105747: step: 2522/1545, loss: 0.057800401002168655 2023-01-23 13:18:51.955096: step: 2524/1545, loss: 0.019851550459861755 2023-01-23 13:18:52.831915: step: 2526/1545, loss: 0.009576786309480667 2023-01-23 13:18:53.692887: step: 2528/1545, loss: 0.004023831803351641 2023-01-23 13:18:54.602197: step: 2530/1545, loss: 0.011812531389296055 2023-01-23 13:18:55.470962: step: 2532/1545, loss: 0.006963799707591534 2023-01-23 13:18:56.312007: step: 2534/1545, loss: 0.006765537895262241 2023-01-23 13:18:57.197277: step: 2536/1545, loss: 0.07324612140655518 2023-01-23 13:18:58.078889: step: 2538/1545, loss: 0.27209678292274475 2023-01-23 13:18:58.967983: step: 2540/1545, loss: 0.005719571840018034 2023-01-23 13:18:59.862037: step: 2542/1545, loss: 0.011040925979614258 2023-01-23 13:19:00.733735: step: 2544/1545, loss: 0.06878021359443665 2023-01-23 13:19:01.683670: step: 2546/1545, loss: 0.04949415847659111 2023-01-23 13:19:02.546987: step: 2548/1545, loss: 0.00023311532277148217 2023-01-23 13:19:03.416853: step: 2550/1545, loss: 0.32921186089515686 2023-01-23 13:19:04.287311: step: 2552/1545, loss: 0.04087766632437706 2023-01-23 13:19:05.238858: step: 2554/1545, loss: 0.025512954220175743 2023-01-23 13:19:06.113856: step: 2556/1545, loss: 0.03594738990068436 2023-01-23 13:19:06.955803: step: 2558/1545, loss: 0.047813769429922104 2023-01-23 13:19:07.871327: step: 2560/1545, loss: 0.012952893041074276 2023-01-23 13:19:08.750718: step: 2562/1545, loss: 0.05738424137234688 2023-01-23 13:19:09.636143: step: 2564/1545, loss: 0.007242796942591667 2023-01-23 13:19:10.539736: step: 2566/1545, loss: 0.1281120777130127 2023-01-23 13:19:11.429708: step: 2568/1545, loss: 0.0007532385061495006 2023-01-23 13:19:12.372019: step: 2570/1545, loss: 0.1674918383359909 2023-01-23 13:19:13.274849: step: 2572/1545, loss: 0.06072823330760002 2023-01-23 13:19:14.181890: step: 2574/1545, loss: 0.027615252882242203 2023-01-23 13:19:15.081569: step: 2576/1545, loss: 0.0027578030712902546 2023-01-23 13:19:15.949704: step: 2578/1545, loss: 0.05441365763545036 2023-01-23 13:19:16.845950: step: 2580/1545, loss: 0.02616742067039013 2023-01-23 13:19:17.734274: step: 2582/1545, loss: 0.12355358898639679 2023-01-23 13:19:18.671344: step: 2584/1545, loss: 0.011085622012615204 2023-01-23 13:19:19.547466: step: 2586/1545, loss: 0.003253541188314557 2023-01-23 13:19:20.405972: step: 2588/1545, loss: 0.0018231924623250961 2023-01-23 13:19:21.278045: step: 2590/1545, loss: 0.07744976878166199 2023-01-23 13:19:22.146863: step: 2592/1545, loss: 0.00042036542436107993 2023-01-23 13:19:23.031925: step: 2594/1545, loss: 0.0627896785736084 2023-01-23 13:19:23.919631: step: 2596/1545, loss: 0.13326826691627502 2023-01-23 13:19:24.836361: step: 2598/1545, loss: 0.08064392954111099 2023-01-23 13:19:25.678794: step: 2600/1545, loss: 0.9973689913749695 2023-01-23 13:19:26.557278: step: 2602/1545, loss: 0.548352837562561 2023-01-23 13:19:27.427608: step: 2604/1545, loss: 0.4462718963623047 2023-01-23 13:19:28.273500: step: 2606/1545, loss: 0.07769554853439331 2023-01-23 13:19:29.170722: step: 2608/1545, loss: 0.013596730306744576 2023-01-23 13:19:30.089905: step: 2610/1545, loss: 0.12765109539031982 2023-01-23 13:19:30.918466: step: 2612/1545, loss: 0.017840923741459846 2023-01-23 13:19:31.778614: step: 2614/1545, loss: 0.022251995280385017 2023-01-23 13:19:32.659295: step: 2616/1545, loss: 0.0038292058743536472 2023-01-23 13:19:33.533399: step: 2618/1545, loss: 0.007485450245440006 2023-01-23 13:19:34.413254: step: 2620/1545, loss: 0.028444765135645866 2023-01-23 13:19:35.308611: step: 2622/1545, loss: 0.028507912531495094 2023-01-23 13:19:36.272110: step: 2624/1545, loss: 0.035166092216968536 2023-01-23 13:19:37.172381: step: 2626/1545, loss: 0.07854259014129639 2023-01-23 13:19:38.029413: step: 2628/1545, loss: 0.1647045910358429 2023-01-23 13:19:38.886386: step: 2630/1545, loss: 0.0275689959526062 2023-01-23 13:19:39.755013: step: 2632/1545, loss: 0.14072896540164948 2023-01-23 13:19:40.695467: step: 2634/1545, loss: 0.002440395997837186 2023-01-23 13:19:41.536934: step: 2636/1545, loss: 0.7457275986671448 2023-01-23 13:19:42.391548: step: 2638/1545, loss: 0.0274212546646595 2023-01-23 13:19:43.258695: step: 2640/1545, loss: 0.15440699458122253 2023-01-23 13:19:44.191756: step: 2642/1545, loss: 0.03830985724925995 2023-01-23 13:19:45.063000: step: 2644/1545, loss: 0.0029947152361273766 2023-01-23 13:19:45.942908: step: 2646/1545, loss: 0.0147944251075387 2023-01-23 13:19:46.825093: step: 2648/1545, loss: 0.13603575527668 2023-01-23 13:19:47.685742: step: 2650/1545, loss: 0.12042629718780518 2023-01-23 13:19:48.527525: step: 2652/1545, loss: 0.13120435178279877 2023-01-23 13:19:49.362265: step: 2654/1545, loss: 0.0303790420293808 2023-01-23 13:19:50.221932: step: 2656/1545, loss: 0.003786283079534769 2023-01-23 13:19:51.122946: step: 2658/1545, loss: 0.16655759513378143 2023-01-23 13:19:51.984792: step: 2660/1545, loss: 0.18849962949752808 2023-01-23 13:19:52.879986: step: 2662/1545, loss: 0.0037934419233351946 2023-01-23 13:19:53.804344: step: 2664/1545, loss: 0.12483535706996918 2023-01-23 13:19:54.686355: step: 2666/1545, loss: 0.10692083090543747 2023-01-23 13:19:55.530407: step: 2668/1545, loss: 0.7505874633789062 2023-01-23 13:19:56.454886: step: 2670/1545, loss: 0.08973095566034317 2023-01-23 13:19:57.308730: step: 2672/1545, loss: 0.10850990563631058 2023-01-23 13:19:58.209090: step: 2674/1545, loss: 0.5395265817642212 2023-01-23 13:19:59.121208: step: 2676/1545, loss: 1.1473300457000732 2023-01-23 13:20:00.043586: step: 2678/1545, loss: 0.10747001320123672 2023-01-23 13:20:00.951069: step: 2680/1545, loss: 0.13536235690116882 2023-01-23 13:20:01.913380: step: 2682/1545, loss: 0.030699925497174263 2023-01-23 13:20:02.804255: step: 2684/1545, loss: 0.03722472861409187 2023-01-23 13:20:03.728228: step: 2686/1545, loss: 0.0883784145116806 2023-01-23 13:20:04.642213: step: 2688/1545, loss: 0.1453377604484558 2023-01-23 13:20:05.546494: step: 2690/1545, loss: 0.006049731746315956 2023-01-23 13:20:06.385612: step: 2692/1545, loss: 0.0038570042233914137 2023-01-23 13:20:07.294760: step: 2694/1545, loss: 0.010232614353299141 2023-01-23 13:20:08.137562: step: 2696/1545, loss: 0.08569508045911789 2023-01-23 13:20:09.075229: step: 2698/1545, loss: 0.022764405235648155 2023-01-23 13:20:09.939679: step: 2700/1545, loss: 0.06252583861351013 2023-01-23 13:20:10.893072: step: 2702/1545, loss: 0.02176383137702942 2023-01-23 13:20:11.761410: step: 2704/1545, loss: 0.16340427100658417 2023-01-23 13:20:12.664051: step: 2706/1545, loss: 0.0059564122930169106 2023-01-23 13:20:13.552902: step: 2708/1545, loss: 0.006524108350276947 2023-01-23 13:20:14.460090: step: 2710/1545, loss: 0.008696088567376137 2023-01-23 13:20:15.322510: step: 2712/1545, loss: 0.009378309361636639 2023-01-23 13:20:16.290864: step: 2714/1545, loss: 0.13495223224163055 2023-01-23 13:20:17.122463: step: 2716/1545, loss: 0.032723017036914825 2023-01-23 13:20:18.005671: step: 2718/1545, loss: 0.039128776639699936 2023-01-23 13:20:18.886588: step: 2720/1545, loss: 0.011472650803625584 2023-01-23 13:20:19.806261: step: 2722/1545, loss: 0.0224606990814209 2023-01-23 13:20:20.688490: step: 2724/1545, loss: 0.1394742727279663 2023-01-23 13:20:21.575865: step: 2726/1545, loss: 0.35794857144355774 2023-01-23 13:20:22.465707: step: 2728/1545, loss: 0.02036982774734497 2023-01-23 13:20:23.349648: step: 2730/1545, loss: 0.017875617370009422 2023-01-23 13:20:24.247999: step: 2732/1545, loss: 0.026554904878139496 2023-01-23 13:20:25.153584: step: 2734/1545, loss: 2.3667709827423096 2023-01-23 13:20:26.011177: step: 2736/1545, loss: 0.12144487351179123 2023-01-23 13:20:26.897722: step: 2738/1545, loss: 0.005830642767250538 2023-01-23 13:20:27.808724: step: 2740/1545, loss: 0.037544138729572296 2023-01-23 13:20:28.755406: step: 2742/1545, loss: 0.5305483937263489 2023-01-23 13:20:29.637920: step: 2744/1545, loss: 1.5306345224380493 2023-01-23 13:20:30.492847: step: 2746/1545, loss: 0.16062095761299133 2023-01-23 13:20:31.387707: step: 2748/1545, loss: 0.016388610005378723 2023-01-23 13:20:32.328408: step: 2750/1545, loss: 0.11971153318881989 2023-01-23 13:20:33.217042: step: 2752/1545, loss: 0.47504740953445435 2023-01-23 13:20:34.089322: step: 2754/1545, loss: 1.186254858970642 2023-01-23 13:20:34.958547: step: 2756/1545, loss: 0.024013100191950798 2023-01-23 13:20:35.851001: step: 2758/1545, loss: 3.1721842288970947 2023-01-23 13:20:36.714958: step: 2760/1545, loss: 0.18737226724624634 2023-01-23 13:20:37.617324: step: 2762/1545, loss: 0.26325559616088867 2023-01-23 13:20:38.466502: step: 2764/1545, loss: 0.08895212411880493 2023-01-23 13:20:39.354356: step: 2766/1545, loss: 0.12511864304542542 2023-01-23 13:20:40.261127: step: 2768/1545, loss: 0.27137303352355957 2023-01-23 13:20:41.137232: step: 2770/1545, loss: 0.22109957039356232 2023-01-23 13:20:42.000916: step: 2772/1545, loss: 0.0980173721909523 2023-01-23 13:20:42.894454: step: 2774/1545, loss: 0.1201910525560379 2023-01-23 13:20:43.769499: step: 2776/1545, loss: 0.0056974212639033794 2023-01-23 13:20:44.676681: step: 2778/1545, loss: 0.009089941158890724 2023-01-23 13:20:45.541325: step: 2780/1545, loss: 0.08880652487277985 2023-01-23 13:20:46.483248: step: 2782/1545, loss: 0.007970920763909817 2023-01-23 13:20:47.500862: step: 2784/1545, loss: 0.3132041394710541 2023-01-23 13:20:48.403326: step: 2786/1545, loss: 0.10483308881521225 2023-01-23 13:20:49.343414: step: 2788/1545, loss: 0.011370474472641945 2023-01-23 13:20:50.267318: step: 2790/1545, loss: 0.0197446309030056 2023-01-23 13:20:51.265565: step: 2792/1545, loss: 0.03487437590956688 2023-01-23 13:20:52.183373: step: 2794/1545, loss: 0.07762744277715683 2023-01-23 13:20:53.049633: step: 2796/1545, loss: 0.10373540222644806 2023-01-23 13:20:53.957754: step: 2798/1545, loss: 0.09509578347206116 2023-01-23 13:20:54.882059: step: 2800/1545, loss: 0.06400705873966217 2023-01-23 13:20:55.748424: step: 2802/1545, loss: 0.0030891422647982836 2023-01-23 13:20:56.594369: step: 2804/1545, loss: 0.0075332848355174065 2023-01-23 13:20:57.428896: step: 2806/1545, loss: 0.00731708575040102 2023-01-23 13:20:58.332351: step: 2808/1545, loss: 0.09417422860860825 2023-01-23 13:20:59.238657: step: 2810/1545, loss: 0.07034444808959961 2023-01-23 13:21:00.107474: step: 2812/1545, loss: 0.004968729335814714 2023-01-23 13:21:00.977022: step: 2814/1545, loss: 0.26260319352149963 2023-01-23 13:21:01.834572: step: 2816/1545, loss: 0.14128556847572327 2023-01-23 13:21:02.696934: step: 2818/1545, loss: 0.018786223605275154 2023-01-23 13:21:03.576416: step: 2820/1545, loss: 0.03901764377951622 2023-01-23 13:21:04.404917: step: 2822/1545, loss: 0.17969253659248352 2023-01-23 13:21:05.288361: step: 2824/1545, loss: 0.21783629059791565 2023-01-23 13:21:06.168238: step: 2826/1545, loss: 0.00291493465192616 2023-01-23 13:21:06.994049: step: 2828/1545, loss: 0.10745719820261002 2023-01-23 13:21:07.912184: step: 2830/1545, loss: 0.03031589277088642 2023-01-23 13:21:08.805074: step: 2832/1545, loss: 0.3655407130718231 2023-01-23 13:21:09.711805: step: 2834/1545, loss: 0.0004821081238333136 2023-01-23 13:21:10.600883: step: 2836/1545, loss: 0.004911025054752827 2023-01-23 13:21:11.491516: step: 2838/1545, loss: 0.7201080322265625 2023-01-23 13:21:12.382505: step: 2840/1545, loss: 0.18200130760669708 2023-01-23 13:21:13.254720: step: 2842/1545, loss: 0.2067730575799942 2023-01-23 13:21:14.152849: step: 2844/1545, loss: 0.059100423008203506 2023-01-23 13:21:15.034878: step: 2846/1545, loss: 0.0015703149838373065 2023-01-23 13:21:15.928693: step: 2848/1545, loss: 1.1432347297668457 2023-01-23 13:21:16.825058: step: 2850/1545, loss: 0.19425253570079803 2023-01-23 13:21:17.741977: step: 2852/1545, loss: 0.960628867149353 2023-01-23 13:21:18.584591: step: 2854/1545, loss: 0.01626570336520672 2023-01-23 13:21:19.497836: step: 2856/1545, loss: 0.20589661598205566 2023-01-23 13:21:20.439092: step: 2858/1545, loss: 0.035062216222286224 2023-01-23 13:21:21.329083: step: 2860/1545, loss: 0.07599351555109024 2023-01-23 13:21:22.240564: step: 2862/1545, loss: 0.11572781205177307 2023-01-23 13:21:23.099215: step: 2864/1545, loss: 0.32860296964645386 2023-01-23 13:21:24.000205: step: 2866/1545, loss: 0.46637970209121704 2023-01-23 13:21:24.905286: step: 2868/1545, loss: 0.018250759690999985 2023-01-23 13:21:25.803823: step: 2870/1545, loss: 0.025153756141662598 2023-01-23 13:21:26.722974: step: 2872/1545, loss: 0.006534865591675043 2023-01-23 13:21:27.594319: step: 2874/1545, loss: 0.013045811094343662 2023-01-23 13:21:28.457270: step: 2876/1545, loss: 0.07751626521348953 2023-01-23 13:21:29.320051: step: 2878/1545, loss: 0.036736469715833664 2023-01-23 13:21:30.188440: step: 2880/1545, loss: 0.007799886167049408 2023-01-23 13:21:31.046457: step: 2882/1545, loss: 0.061510030180215836 2023-01-23 13:21:31.930988: step: 2884/1545, loss: 0.32374307513237 2023-01-23 13:21:32.795300: step: 2886/1545, loss: 0.09861051291227341 2023-01-23 13:21:33.670539: step: 2888/1545, loss: 0.0073221102356910706 2023-01-23 13:21:34.546409: step: 2890/1545, loss: 0.1221999004483223 2023-01-23 13:21:35.393486: step: 2892/1545, loss: 0.014888240024447441 2023-01-23 13:21:36.245934: step: 2894/1545, loss: 0.0894884243607521 2023-01-23 13:21:37.085397: step: 2896/1545, loss: 0.09514211863279343 2023-01-23 13:21:37.942864: step: 2898/1545, loss: 0.012261566706001759 2023-01-23 13:21:38.799995: step: 2900/1545, loss: 0.005396244581788778 2023-01-23 13:21:39.680627: step: 2902/1545, loss: 0.23340514302253723 2023-01-23 13:21:40.558310: step: 2904/1545, loss: 0.017180345952510834 2023-01-23 13:21:41.405846: step: 2906/1545, loss: 0.3787632882595062 2023-01-23 13:21:42.254773: step: 2908/1545, loss: 0.01592099294066429 2023-01-23 13:21:43.152651: step: 2910/1545, loss: 0.33836114406585693 2023-01-23 13:21:44.045990: step: 2912/1545, loss: 0.1444568634033203 2023-01-23 13:21:44.923564: step: 2914/1545, loss: 0.07047785818576813 2023-01-23 13:21:45.782069: step: 2916/1545, loss: 0.016308706253767014 2023-01-23 13:21:46.718095: step: 2918/1545, loss: 0.022873196750879288 2023-01-23 13:21:47.628134: step: 2920/1545, loss: 0.07940759509801865 2023-01-23 13:21:48.520092: step: 2922/1545, loss: 0.031056441366672516 2023-01-23 13:21:49.393375: step: 2924/1545, loss: 0.16110311448574066 2023-01-23 13:21:50.292295: step: 2926/1545, loss: 0.008868803270161152 2023-01-23 13:21:51.175993: step: 2928/1545, loss: 0.006894109304994345 2023-01-23 13:21:52.051931: step: 2930/1545, loss: 1.275387167930603 2023-01-23 13:21:52.972708: step: 2932/1545, loss: 0.236646369099617 2023-01-23 13:21:53.874327: step: 2934/1545, loss: 0.0026035872288048267 2023-01-23 13:21:54.742292: step: 2936/1545, loss: 0.25335681438446045 2023-01-23 13:21:55.662962: step: 2938/1545, loss: 0.020891502499580383 2023-01-23 13:21:56.507182: step: 2940/1545, loss: 0.11739678680896759 2023-01-23 13:21:57.417656: step: 2942/1545, loss: 0.33935680985450745 2023-01-23 13:21:58.273541: step: 2944/1545, loss: 0.0056930361315608025 2023-01-23 13:21:59.279872: step: 2946/1545, loss: 0.12284094095230103 2023-01-23 13:22:00.126601: step: 2948/1545, loss: 0.14361122250556946 2023-01-23 13:22:00.985799: step: 2950/1545, loss: 0.034746453166007996 2023-01-23 13:22:01.869475: step: 2952/1545, loss: 0.024874739348888397 2023-01-23 13:22:02.726619: step: 2954/1545, loss: 0.023639369755983353 2023-01-23 13:22:03.600148: step: 2956/1545, loss: 0.36801040172576904 2023-01-23 13:22:04.466760: step: 2958/1545, loss: 0.02551371417939663 2023-01-23 13:22:05.431955: step: 2960/1545, loss: 0.11065778881311417 2023-01-23 13:22:06.293952: step: 2962/1545, loss: 0.27514418959617615 2023-01-23 13:22:07.150107: step: 2964/1545, loss: 0.13912102580070496 2023-01-23 13:22:08.038163: step: 2966/1545, loss: 0.1205812394618988 2023-01-23 13:22:08.896903: step: 2968/1545, loss: 0.2671569585800171 2023-01-23 13:22:09.870625: step: 2970/1545, loss: 0.03999999910593033 2023-01-23 13:22:10.747230: step: 2972/1545, loss: 0.1388060301542282 2023-01-23 13:22:11.661637: step: 2974/1545, loss: 0.0015487412456423044 2023-01-23 13:22:12.541362: step: 2976/1545, loss: 0.03676365688443184 2023-01-23 13:22:13.472875: step: 2978/1545, loss: 0.004329409450292587 2023-01-23 13:22:14.391496: step: 2980/1545, loss: 0.7322356700897217 2023-01-23 13:22:15.308918: step: 2982/1545, loss: 0.03099980391561985 2023-01-23 13:22:16.216893: step: 2984/1545, loss: 0.007667334750294685 2023-01-23 13:22:17.081097: step: 2986/1545, loss: 0.003994218073785305 2023-01-23 13:22:17.934710: step: 2988/1545, loss: 0.000878932187333703 2023-01-23 13:22:18.838466: step: 2990/1545, loss: 0.0058320676907896996 2023-01-23 13:22:19.692346: step: 2992/1545, loss: 0.006453927606344223 2023-01-23 13:22:20.596584: step: 2994/1545, loss: 0.6228402256965637 2023-01-23 13:22:21.506496: step: 2996/1545, loss: 0.004699181765317917 2023-01-23 13:22:22.400867: step: 2998/1545, loss: 0.0922560766339302 2023-01-23 13:22:23.257800: step: 3000/1545, loss: 0.006946356501430273 2023-01-23 13:22:24.141912: step: 3002/1545, loss: 0.013834334909915924 2023-01-23 13:22:25.063433: step: 3004/1545, loss: 0.14049680531024933 2023-01-23 13:22:25.964700: step: 3006/1545, loss: 0.02728274278342724 2023-01-23 13:22:26.833295: step: 3008/1545, loss: 0.0008652624674141407 2023-01-23 13:22:27.741497: step: 3010/1545, loss: 0.027387799695134163 2023-01-23 13:22:28.626698: step: 3012/1545, loss: 0.013757866807281971 2023-01-23 13:22:29.482028: step: 3014/1545, loss: 0.08451197296380997 2023-01-23 13:22:30.364234: step: 3016/1545, loss: 0.0229909997433424 2023-01-23 13:22:31.233677: step: 3018/1545, loss: 0.3467440903186798 2023-01-23 13:22:32.117786: step: 3020/1545, loss: 0.04847472161054611 2023-01-23 13:22:32.971548: step: 3022/1545, loss: 0.001916208304464817 2023-01-23 13:22:33.835345: step: 3024/1545, loss: 0.0006900322041474283 2023-01-23 13:22:34.704705: step: 3026/1545, loss: 0.018766213208436966 2023-01-23 13:22:35.594962: step: 3028/1545, loss: 0.0018543667392805219 2023-01-23 13:22:36.463462: step: 3030/1545, loss: 0.20005595684051514 2023-01-23 13:22:37.333075: step: 3032/1545, loss: 0.023773381486535072 2023-01-23 13:22:38.179292: step: 3034/1545, loss: 0.009727285243570805 2023-01-23 13:22:39.110362: step: 3036/1545, loss: 0.007096061948686838 2023-01-23 13:22:40.010571: step: 3038/1545, loss: 0.3146243393421173 2023-01-23 13:22:40.901951: step: 3040/1545, loss: 0.004696056246757507 2023-01-23 13:22:41.838445: step: 3042/1545, loss: 0.521516740322113 2023-01-23 13:22:42.699767: step: 3044/1545, loss: 0.21357446908950806 2023-01-23 13:22:43.591633: step: 3046/1545, loss: 0.008667690679430962 2023-01-23 13:22:44.454965: step: 3048/1545, loss: 0.050294965505599976 2023-01-23 13:22:45.373738: step: 3050/1545, loss: 0.007972197607159615 2023-01-23 13:22:46.239084: step: 3052/1545, loss: 0.0314641073346138 2023-01-23 13:22:47.125810: step: 3054/1545, loss: 0.1483335644006729 2023-01-23 13:22:47.997411: step: 3056/1545, loss: 0.23929733037948608 2023-01-23 13:22:48.836812: step: 3058/1545, loss: 0.004462647717446089 2023-01-23 13:22:49.699077: step: 3060/1545, loss: 0.0015422526048496366 2023-01-23 13:22:50.620324: step: 3062/1545, loss: 0.2187647819519043 2023-01-23 13:22:51.565450: step: 3064/1545, loss: 0.08356927335262299 2023-01-23 13:22:52.418789: step: 3066/1545, loss: 0.3528784215450287 2023-01-23 13:22:53.294774: step: 3068/1545, loss: 0.06377006322145462 2023-01-23 13:22:54.248849: step: 3070/1545, loss: 0.032530903816223145 2023-01-23 13:22:55.171248: step: 3072/1545, loss: 0.035353660583496094 2023-01-23 13:22:56.154361: step: 3074/1545, loss: 0.02501479536294937 2023-01-23 13:22:57.080933: step: 3076/1545, loss: 0.00812057126313448 2023-01-23 13:22:57.966627: step: 3078/1545, loss: 0.06313697248697281 2023-01-23 13:22:58.916547: step: 3080/1545, loss: 0.0017715736757963896 2023-01-23 13:22:59.831697: step: 3082/1545, loss: 0.09680679440498352 2023-01-23 13:23:00.718617: step: 3084/1545, loss: 0.009383108466863632 2023-01-23 13:23:01.654412: step: 3086/1545, loss: 0.11574792861938477 2023-01-23 13:23:02.531036: step: 3088/1545, loss: 0.02378997579216957 2023-01-23 13:23:03.413376: step: 3090/1545, loss: 0.06388762593269348 ================================================== Loss: 0.135 -------------------- Dev Chinese: {'event': {'p': 0.6052344601962922, 'r': 0.7390146471371505, 'f1': 0.6654676258992807}, 'argument': {'p': 0.6499157257873251, 'r': 0.6533184259223374, 'f1': 0.6516126336875532}, 'combined': 0.4336271123460336, 'epoch': 17} Test Chinese: {'event': {'p': 0.6414087513340448, 'r': 0.768542199488491, 'f1': 0.6992437463641652}, 'argument': {'p': 0.7023112844001405, 'r': 0.7119687352169491, 'f1': 0.7071070367215375}, 'combined': 0.49444017343763125, 'epoch': 17} Dev Korean: {'event': {'p': 0.6105032822757112, 'r': 0.7430093209054593, 'f1': 0.6702702702702702}, 'argument': {'p': 0.6585233819851708, 'r': 0.6550600734397942, 'f1': 0.6567871621456619}, 'combined': 0.44022490868141656, 'epoch': 17} Test Korean: {'event': {'p': 0.6322751322751323, 'r': 0.7640664961636828, 'f1': 0.6919513607411696}, 'argument': {'p': 0.6974316896181407, 'r': 0.7096907105285093, 'f1': 0.7035077990352685}, 'combined': 0.4867931788344793, 'epoch': 17} Dev Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.6713113275613275, 'r': 0.6213790800567659, 'f1': 0.6453808470975851}, 'combined': 0.4693678887982438, 'epoch': 17} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6641681363903587, 'r': 0.49130245705588177, 'f1': 0.5648043994500689}, 'combined': 0.3468097189605686, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} New best korean model... New best russian model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6105032822757112, 'r': 0.7430093209054593, 'f1': 0.6702702702702702}, 'argument': {'p': 0.6585233819851708, 'r': 0.6550600734397942, 'f1': 0.6567871621456619}, 'combined': 0.44022490868141656, 'epoch': 17} Test for Korean: {'event': {'p': 0.6322751322751323, 'r': 0.7640664961636828, 'f1': 0.6919513607411696}, 'argument': {'p': 0.6974316896181407, 'r': 0.7096907105285093, 'f1': 0.7035077990352685}, 'combined': 0.4867931788344793, 'epoch': 17} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6641681363903587, 'r': 0.49130245705588177, 'f1': 0.5648043994500689}, 'combined': 0.3468097189605686, 'epoch': 17} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 18 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 13:28:28.201934: step: 2/1545, loss: 0.14539097249507904 2023-01-23 13:28:29.041417: step: 4/1545, loss: 0.033329740166664124 2023-01-23 13:28:29.942900: step: 6/1545, loss: 0.07417663186788559 2023-01-23 13:28:30.877081: step: 8/1545, loss: 0.08235273510217667 2023-01-23 13:28:31.758554: step: 10/1545, loss: 0.024416405707597733 2023-01-23 13:28:32.626380: step: 12/1545, loss: 0.0021931547671556473 2023-01-23 13:28:33.528238: step: 14/1545, loss: 0.06490126997232437 2023-01-23 13:28:34.370564: step: 16/1545, loss: 0.040945958346128464 2023-01-23 13:28:35.242939: step: 18/1545, loss: 0.01953986845910549 2023-01-23 13:28:36.121519: step: 20/1545, loss: 0.012123698368668556 2023-01-23 13:28:36.997354: step: 22/1545, loss: 0.0964253842830658 2023-01-23 13:28:37.895672: step: 24/1545, loss: 0.00015167202218435705 2023-01-23 13:28:38.723643: step: 26/1545, loss: 9.061732998816296e-05 2023-01-23 13:28:39.578385: step: 28/1545, loss: 0.0005272533744573593 2023-01-23 13:28:40.442472: step: 30/1545, loss: 0.03300132602453232 2023-01-23 13:28:41.302256: step: 32/1545, loss: 0.016006072983145714 2023-01-23 13:28:42.182896: step: 34/1545, loss: 0.005772063042968512 2023-01-23 13:28:43.015168: step: 36/1545, loss: 0.16321057081222534 2023-01-23 13:28:43.918031: step: 38/1545, loss: 0.00016076426254585385 2023-01-23 13:28:44.777913: step: 40/1545, loss: 0.003569299355149269 2023-01-23 13:28:45.659099: step: 42/1545, loss: 0.02083711139857769 2023-01-23 13:28:46.537589: step: 44/1545, loss: 0.01473266538232565 2023-01-23 13:28:47.381337: step: 46/1545, loss: 0.1089228019118309 2023-01-23 13:28:48.270231: step: 48/1545, loss: 0.01997070200741291 2023-01-23 13:28:49.150304: step: 50/1545, loss: 0.00770622119307518 2023-01-23 13:28:50.048295: step: 52/1545, loss: 0.0006603382644243538 2023-01-23 13:28:51.005819: step: 54/1545, loss: 0.016136586666107178 2023-01-23 13:28:51.841785: step: 56/1545, loss: 0.008137769997119904 2023-01-23 13:28:52.685683: step: 58/1545, loss: 0.06078898534178734 2023-01-23 13:28:53.586497: step: 60/1545, loss: 0.11640598624944687 2023-01-23 13:28:54.444220: step: 62/1545, loss: 0.1929606795310974 2023-01-23 13:28:55.289725: step: 64/1545, loss: 0.04545018821954727 2023-01-23 13:28:56.128945: step: 66/1545, loss: 0.006216810084879398 2023-01-23 13:28:57.083562: step: 68/1545, loss: 1.1267033815383911 2023-01-23 13:28:58.019020: step: 70/1545, loss: 0.11865833401679993 2023-01-23 13:28:58.916704: step: 72/1545, loss: 0.08237379044294357 2023-01-23 13:28:59.783611: step: 74/1545, loss: 0.05278883874416351 2023-01-23 13:29:00.693379: step: 76/1545, loss: 1.1490577459335327 2023-01-23 13:29:01.588707: step: 78/1545, loss: 0.015365458093583584 2023-01-23 13:29:02.442361: step: 80/1545, loss: 0.08513491600751877 2023-01-23 13:29:03.309374: step: 82/1545, loss: 0.08523974567651749 2023-01-23 13:29:04.141559: step: 84/1545, loss: 0.001085102092474699 2023-01-23 13:29:05.018344: step: 86/1545, loss: 0.013752025552093983 2023-01-23 13:29:05.915143: step: 88/1545, loss: 0.27748903632164 2023-01-23 13:29:06.793049: step: 90/1545, loss: 0.11464750021696091 2023-01-23 13:29:07.651898: step: 92/1545, loss: 0.01480476651340723 2023-01-23 13:29:08.499505: step: 94/1545, loss: 0.13463465869426727 2023-01-23 13:29:09.386130: step: 96/1545, loss: 0.021911507472395897 2023-01-23 13:29:10.301339: step: 98/1545, loss: 0.2591315805912018 2023-01-23 13:29:11.183631: step: 100/1545, loss: 0.03441368788480759 2023-01-23 13:29:12.074252: step: 102/1545, loss: 0.033713921904563904 2023-01-23 13:29:12.979240: step: 104/1545, loss: 0.003780410159379244 2023-01-23 13:29:13.798469: step: 106/1545, loss: 0.01602562703192234 2023-01-23 13:29:14.661171: step: 108/1545, loss: 0.12331219762563705 2023-01-23 13:29:15.548002: step: 110/1545, loss: 0.00811423733830452 2023-01-23 13:29:16.496730: step: 112/1545, loss: 0.021857257932424545 2023-01-23 13:29:17.379040: step: 114/1545, loss: 0.0011913725174963474 2023-01-23 13:29:18.249027: step: 116/1545, loss: 0.009549678303301334 2023-01-23 13:29:19.143476: step: 118/1545, loss: 0.0036215607542544603 2023-01-23 13:29:19.988883: step: 120/1545, loss: 0.0687936469912529 2023-01-23 13:29:20.825119: step: 122/1545, loss: 0.04508494213223457 2023-01-23 13:29:21.698853: step: 124/1545, loss: 0.08000391721725464 2023-01-23 13:29:22.542783: step: 126/1545, loss: 0.000270407268544659 2023-01-23 13:29:23.426436: step: 128/1545, loss: 0.02091536670923233 2023-01-23 13:29:24.312445: step: 130/1545, loss: 0.08140143752098083 2023-01-23 13:29:25.226022: step: 132/1545, loss: 0.1163116842508316 2023-01-23 13:29:26.097578: step: 134/1545, loss: 0.0005195282283239067 2023-01-23 13:29:27.005056: step: 136/1545, loss: 0.012986349873244762 2023-01-23 13:29:27.894950: step: 138/1545, loss: 0.03650881350040436 2023-01-23 13:29:28.762455: step: 140/1545, loss: 0.006815092638134956 2023-01-23 13:29:29.683277: step: 142/1545, loss: 0.10879146307706833 2023-01-23 13:29:30.538804: step: 144/1545, loss: 0.005144573748111725 2023-01-23 13:29:31.450819: step: 146/1545, loss: 0.10586072504520416 2023-01-23 13:29:32.364461: step: 148/1545, loss: 0.08620305359363556 2023-01-23 13:29:33.234091: step: 150/1545, loss: 0.012045447714626789 2023-01-23 13:29:34.105435: step: 152/1545, loss: 0.001861165277659893 2023-01-23 13:29:34.988960: step: 154/1545, loss: 0.2741411626338959 2023-01-23 13:29:35.879959: step: 156/1545, loss: 0.18506748974323273 2023-01-23 13:29:36.768437: step: 158/1545, loss: 0.0027989065274596214 2023-01-23 13:29:37.695524: step: 160/1545, loss: 0.21784448623657227 2023-01-23 13:29:38.538002: step: 162/1545, loss: 0.027206867933273315 2023-01-23 13:29:39.414264: step: 164/1545, loss: 0.13810063898563385 2023-01-23 13:29:40.325985: step: 166/1545, loss: 0.0030298451893031597 2023-01-23 13:29:41.166890: step: 168/1545, loss: 0.07989692687988281 2023-01-23 13:29:42.034616: step: 170/1545, loss: 0.04258237034082413 2023-01-23 13:29:42.899910: step: 172/1545, loss: 0.0461130291223526 2023-01-23 13:29:43.724669: step: 174/1545, loss: 0.09589303284883499 2023-01-23 13:29:44.587814: step: 176/1545, loss: 0.011278455145657063 2023-01-23 13:29:45.467812: step: 178/1545, loss: 0.07021249830722809 2023-01-23 13:29:46.315422: step: 180/1545, loss: 0.03808940574526787 2023-01-23 13:29:47.235461: step: 182/1545, loss: 0.03170650824904442 2023-01-23 13:29:48.153924: step: 184/1545, loss: 0.03201686590909958 2023-01-23 13:29:49.049777: step: 186/1545, loss: 0.01240226998925209 2023-01-23 13:29:49.917076: step: 188/1545, loss: 0.16707265377044678 2023-01-23 13:29:50.867281: step: 190/1545, loss: 0.015140737406909466 2023-01-23 13:29:51.734818: step: 192/1545, loss: 0.0006659164209850132 2023-01-23 13:29:52.634057: step: 194/1545, loss: 0.0013350746594369411 2023-01-23 13:29:53.566464: step: 196/1545, loss: 0.24679933488368988 2023-01-23 13:29:54.468959: step: 198/1545, loss: 0.09555919468402863 2023-01-23 13:29:55.398459: step: 200/1545, loss: 0.34132128953933716 2023-01-23 13:29:56.289981: step: 202/1545, loss: 0.07664226740598679 2023-01-23 13:29:57.152342: step: 204/1545, loss: 0.007743298076093197 2023-01-23 13:29:58.001323: step: 206/1545, loss: 0.0670677050948143 2023-01-23 13:29:58.876459: step: 208/1545, loss: 0.056297361850738525 2023-01-23 13:29:59.755842: step: 210/1545, loss: 0.16988690197467804 2023-01-23 13:30:00.674502: step: 212/1545, loss: 0.06939107924699783 2023-01-23 13:30:01.523462: step: 214/1545, loss: 0.0077198888175189495 2023-01-23 13:30:02.430533: step: 216/1545, loss: 0.06056738644838333 2023-01-23 13:30:03.276519: step: 218/1545, loss: 0.008746030740439892 2023-01-23 13:30:04.189535: step: 220/1545, loss: 0.15979592502117157 2023-01-23 13:30:05.154377: step: 222/1545, loss: 0.6029623746871948 2023-01-23 13:30:06.022591: step: 224/1545, loss: 0.07044025510549545 2023-01-23 13:30:06.886650: step: 226/1545, loss: 0.14482368528842926 2023-01-23 13:30:07.724130: step: 228/1545, loss: 0.012317568063735962 2023-01-23 13:30:08.655958: step: 230/1545, loss: 0.11279016733169556 2023-01-23 13:30:09.523821: step: 232/1545, loss: 0.24870434403419495 2023-01-23 13:30:10.390499: step: 234/1545, loss: 0.038675419986248016 2023-01-23 13:30:11.266611: step: 236/1545, loss: 0.0139169218018651 2023-01-23 13:30:12.126753: step: 238/1545, loss: 0.01588321104645729 2023-01-23 13:30:13.011076: step: 240/1545, loss: 0.010051647201180458 2023-01-23 13:30:13.943533: step: 242/1545, loss: 0.05360554903745651 2023-01-23 13:30:14.796961: step: 244/1545, loss: 0.0010715750977396965 2023-01-23 13:30:15.720066: step: 246/1545, loss: 0.010730813257396221 2023-01-23 13:30:16.581091: step: 248/1545, loss: 0.010811029002070427 2023-01-23 13:30:17.469324: step: 250/1545, loss: 0.0012392643839120865 2023-01-23 13:30:18.347142: step: 252/1545, loss: 0.037384033203125 2023-01-23 13:30:19.279557: step: 254/1545, loss: 0.05113494023680687 2023-01-23 13:30:20.153181: step: 256/1545, loss: 0.10264138877391815 2023-01-23 13:30:21.047306: step: 258/1545, loss: 0.13387314975261688 2023-01-23 13:30:21.892458: step: 260/1545, loss: 0.021123483777046204 2023-01-23 13:30:22.798743: step: 262/1545, loss: 0.6377899646759033 2023-01-23 13:30:23.630815: step: 264/1545, loss: 0.007986730895936489 2023-01-23 13:30:24.510199: step: 266/1545, loss: 0.023616181686520576 2023-01-23 13:30:25.391550: step: 268/1545, loss: 0.039081871509552 2023-01-23 13:30:26.289709: step: 270/1545, loss: 0.06476890295743942 2023-01-23 13:30:27.174592: step: 272/1545, loss: 0.001876344671472907 2023-01-23 13:30:28.029049: step: 274/1545, loss: 0.10813316702842712 2023-01-23 13:30:28.902789: step: 276/1545, loss: 0.06410642713308334 2023-01-23 13:30:29.784993: step: 278/1545, loss: 0.02526746317744255 2023-01-23 13:30:30.683817: step: 280/1545, loss: 0.04346895217895508 2023-01-23 13:30:31.543035: step: 282/1545, loss: 0.01396963745355606 2023-01-23 13:30:32.409820: step: 284/1545, loss: 0.02060926891863346 2023-01-23 13:30:33.255469: step: 286/1545, loss: 0.01590159721672535 2023-01-23 13:30:34.162884: step: 288/1545, loss: 0.0015835794620215893 2023-01-23 13:30:35.064037: step: 290/1545, loss: 0.053422361612319946 2023-01-23 13:30:35.931337: step: 292/1545, loss: 0.23506532609462738 2023-01-23 13:30:36.781018: step: 294/1545, loss: 0.0902547836303711 2023-01-23 13:30:37.745503: step: 296/1545, loss: 0.16475483775138855 2023-01-23 13:30:38.636592: step: 298/1545, loss: 0.2842738628387451 2023-01-23 13:30:39.499653: step: 300/1545, loss: 0.12139866501092911 2023-01-23 13:30:40.431744: step: 302/1545, loss: 0.3306724429130554 2023-01-23 13:30:41.394236: step: 304/1545, loss: 0.1326090693473816 2023-01-23 13:30:42.268976: step: 306/1545, loss: 0.4170992374420166 2023-01-23 13:30:43.119345: step: 308/1545, loss: 0.17713075876235962 2023-01-23 13:30:44.055377: step: 310/1545, loss: 0.013057956472039223 2023-01-23 13:30:44.920591: step: 312/1545, loss: 0.5265604257583618 2023-01-23 13:30:45.780317: step: 314/1545, loss: 0.40074846148490906 2023-01-23 13:30:46.672545: step: 316/1545, loss: 0.0632052943110466 2023-01-23 13:30:47.581998: step: 318/1545, loss: 0.5869441032409668 2023-01-23 13:30:48.486934: step: 320/1545, loss: 0.008817829191684723 2023-01-23 13:30:49.436762: step: 322/1545, loss: 0.09732800722122192 2023-01-23 13:30:50.287077: step: 324/1545, loss: 0.012118205428123474 2023-01-23 13:30:51.162082: step: 326/1545, loss: 0.185540109872818 2023-01-23 13:30:52.042589: step: 328/1545, loss: 0.011465203016996384 2023-01-23 13:30:52.976755: step: 330/1545, loss: 0.02303791046142578 2023-01-23 13:30:53.838400: step: 332/1545, loss: 0.023528195917606354 2023-01-23 13:30:54.687527: step: 334/1545, loss: 0.005757968872785568 2023-01-23 13:30:55.597422: step: 336/1545, loss: 0.05809035897254944 2023-01-23 13:30:56.514306: step: 338/1545, loss: 0.009430032223463058 2023-01-23 13:30:57.367400: step: 340/1545, loss: 0.156579852104187 2023-01-23 13:30:58.240040: step: 342/1545, loss: 0.06640364229679108 2023-01-23 13:30:59.141683: step: 344/1545, loss: 0.037872254848480225 2023-01-23 13:31:00.023300: step: 346/1545, loss: 0.002625667955726385 2023-01-23 13:31:00.865739: step: 348/1545, loss: 0.3697039783000946 2023-01-23 13:31:01.708764: step: 350/1545, loss: 0.0025095785968005657 2023-01-23 13:31:02.578499: step: 352/1545, loss: 0.019275100901722908 2023-01-23 13:31:03.488016: step: 354/1545, loss: 0.02711770310997963 2023-01-23 13:31:04.352233: step: 356/1545, loss: 0.03992272913455963 2023-01-23 13:31:05.302948: step: 358/1545, loss: 0.11888010799884796 2023-01-23 13:31:06.135507: step: 360/1545, loss: 0.025295855477452278 2023-01-23 13:31:07.013745: step: 362/1545, loss: 0.005975082982331514 2023-01-23 13:31:07.947230: step: 364/1545, loss: 0.004369047936052084 2023-01-23 13:31:08.831912: step: 366/1545, loss: 0.007546490989625454 2023-01-23 13:31:09.851733: step: 368/1545, loss: 0.005626375321298838 2023-01-23 13:31:10.751321: step: 370/1545, loss: 0.03882350027561188 2023-01-23 13:31:11.587400: step: 372/1545, loss: 0.030451040714979172 2023-01-23 13:31:12.433516: step: 374/1545, loss: 0.1022629365324974 2023-01-23 13:31:13.317714: step: 376/1545, loss: 0.24910180270671844 2023-01-23 13:31:14.190772: step: 378/1545, loss: 0.0026732857804745436 2023-01-23 13:31:15.056544: step: 380/1545, loss: 0.03627602010965347 2023-01-23 13:31:15.965431: step: 382/1545, loss: 0.17788903415203094 2023-01-23 13:31:16.838245: step: 384/1545, loss: 0.08578485995531082 2023-01-23 13:31:17.809852: step: 386/1545, loss: 0.1424725502729416 2023-01-23 13:31:18.659627: step: 388/1545, loss: 0.05877730995416641 2023-01-23 13:31:19.511946: step: 390/1545, loss: 0.14518171548843384 2023-01-23 13:31:20.364722: step: 392/1545, loss: 0.06918919831514359 2023-01-23 13:31:21.247473: step: 394/1545, loss: 0.0010169424349442124 2023-01-23 13:31:22.133405: step: 396/1545, loss: 0.0033836879301816225 2023-01-23 13:31:22.988478: step: 398/1545, loss: 0.011723196133971214 2023-01-23 13:31:23.871537: step: 400/1545, loss: 0.03657078742980957 2023-01-23 13:31:24.750098: step: 402/1545, loss: 0.1228690892457962 2023-01-23 13:31:25.641009: step: 404/1545, loss: 0.0005453037447296083 2023-01-23 13:31:26.510453: step: 406/1545, loss: 0.027933837845921516 2023-01-23 13:31:27.352180: step: 408/1545, loss: 0.03603202849626541 2023-01-23 13:31:28.231712: step: 410/1545, loss: 0.20451438426971436 2023-01-23 13:31:29.141095: step: 412/1545, loss: 0.0012338141677901149 2023-01-23 13:31:30.011449: step: 414/1545, loss: 0.045332882553339005 2023-01-23 13:31:30.876511: step: 416/1545, loss: 0.00207999418489635 2023-01-23 13:31:31.760739: step: 418/1545, loss: 0.009617963805794716 2023-01-23 13:31:32.626324: step: 420/1545, loss: 0.014348937198519707 2023-01-23 13:31:33.478690: step: 422/1545, loss: 0.19587387144565582 2023-01-23 13:31:34.389120: step: 424/1545, loss: 0.11389680951833725 2023-01-23 13:31:35.292160: step: 426/1545, loss: 0.01335974782705307 2023-01-23 13:31:36.173979: step: 428/1545, loss: 0.06395541876554489 2023-01-23 13:31:37.126214: step: 430/1545, loss: 0.0021790042519569397 2023-01-23 13:31:38.018695: step: 432/1545, loss: 0.5168487429618835 2023-01-23 13:31:38.895216: step: 434/1545, loss: 0.005980280693620443 2023-01-23 13:31:39.775048: step: 436/1545, loss: 0.3864399194717407 2023-01-23 13:31:40.611683: step: 438/1545, loss: 0.02775070071220398 2023-01-23 13:31:41.470729: step: 440/1545, loss: 0.0012086562346667051 2023-01-23 13:31:42.422736: step: 442/1545, loss: 0.08481542766094208 2023-01-23 13:31:43.280218: step: 444/1545, loss: 0.27651703357696533 2023-01-23 13:31:44.199835: step: 446/1545, loss: 0.06928063929080963 2023-01-23 13:31:45.140917: step: 448/1545, loss: 0.007597945164889097 2023-01-23 13:31:46.012565: step: 450/1545, loss: 0.11214245110750198 2023-01-23 13:31:46.919695: step: 452/1545, loss: 0.3518052399158478 2023-01-23 13:31:47.822511: step: 454/1545, loss: 0.12830403447151184 2023-01-23 13:31:48.712234: step: 456/1545, loss: 0.24359944462776184 2023-01-23 13:31:49.611847: step: 458/1545, loss: 0.03917360305786133 2023-01-23 13:31:50.482753: step: 460/1545, loss: 0.17156508564949036 2023-01-23 13:31:51.356172: step: 462/1545, loss: 0.004565797280520201 2023-01-23 13:31:52.215325: step: 464/1545, loss: 0.020270736888051033 2023-01-23 13:31:53.124914: step: 466/1545, loss: 0.6818276643753052 2023-01-23 13:31:54.012850: step: 468/1545, loss: 0.16282859444618225 2023-01-23 13:31:54.859384: step: 470/1545, loss: 0.7552820444107056 2023-01-23 13:31:55.799326: step: 472/1545, loss: 0.2759443521499634 2023-01-23 13:31:56.678487: step: 474/1545, loss: 0.0015613570576533675 2023-01-23 13:31:57.546681: step: 476/1545, loss: 0.0042638024315238 2023-01-23 13:31:58.486665: step: 478/1545, loss: 0.042722396552562714 2023-01-23 13:31:59.493030: step: 480/1545, loss: 0.28364601731300354 2023-01-23 13:32:00.366169: step: 482/1545, loss: 0.038496583700180054 2023-01-23 13:32:01.260399: step: 484/1545, loss: 0.008650537580251694 2023-01-23 13:32:02.150751: step: 486/1545, loss: 0.053632769733667374 2023-01-23 13:32:03.008494: step: 488/1545, loss: 0.4162987768650055 2023-01-23 13:32:03.914012: step: 490/1545, loss: 0.04928496107459068 2023-01-23 13:32:04.799144: step: 492/1545, loss: 0.009715938940644264 2023-01-23 13:32:05.686887: step: 494/1545, loss: 0.13941018283367157 2023-01-23 13:32:06.587524: step: 496/1545, loss: 0.21461789309978485 2023-01-23 13:32:07.476581: step: 498/1545, loss: 0.14643435180187225 2023-01-23 13:32:08.331182: step: 500/1545, loss: 0.010608186013996601 2023-01-23 13:32:09.179829: step: 502/1545, loss: 0.0016204745043069124 2023-01-23 13:32:10.046108: step: 504/1545, loss: 0.11034994572401047 2023-01-23 13:32:10.919309: step: 506/1545, loss: 0.013610468246042728 2023-01-23 13:32:11.788363: step: 508/1545, loss: 0.16940747201442719 2023-01-23 13:32:12.726043: step: 510/1545, loss: 0.004397656302899122 2023-01-23 13:32:13.596006: step: 512/1545, loss: 0.118874192237854 2023-01-23 13:32:14.538658: step: 514/1545, loss: 0.0019202278926968575 2023-01-23 13:32:15.413436: step: 516/1545, loss: 0.05057918280363083 2023-01-23 13:32:16.257373: step: 518/1545, loss: 0.05640990659594536 2023-01-23 13:32:17.129794: step: 520/1545, loss: 0.02478509210050106 2023-01-23 13:32:18.087247: step: 522/1545, loss: 0.026764458045363426 2023-01-23 13:32:18.978805: step: 524/1545, loss: 0.2276897132396698 2023-01-23 13:32:19.887676: step: 526/1545, loss: 0.004972927737981081 2023-01-23 13:32:20.763381: step: 528/1545, loss: 0.16155387461185455 2023-01-23 13:32:21.627062: step: 530/1545, loss: 0.03485257923603058 2023-01-23 13:32:22.568684: step: 532/1545, loss: 0.39911457896232605 2023-01-23 13:32:23.469258: step: 534/1545, loss: 0.05766568332910538 2023-01-23 13:32:24.391684: step: 536/1545, loss: 0.11089308559894562 2023-01-23 13:32:25.224299: step: 538/1545, loss: 0.0038446078542619944 2023-01-23 13:32:26.098200: step: 540/1545, loss: 0.025557637214660645 2023-01-23 13:32:26.933063: step: 542/1545, loss: 0.04136231914162636 2023-01-23 13:32:27.856773: step: 544/1545, loss: 0.013370855711400509 2023-01-23 13:32:28.732998: step: 546/1545, loss: 0.030880514532327652 2023-01-23 13:32:29.655602: step: 548/1545, loss: 0.04016607254743576 2023-01-23 13:32:30.587984: step: 550/1545, loss: 0.018323563039302826 2023-01-23 13:32:31.438630: step: 552/1545, loss: 0.010704942047595978 2023-01-23 13:32:32.301984: step: 554/1545, loss: 0.021657366305589676 2023-01-23 13:32:33.166386: step: 556/1545, loss: 0.014116239733994007 2023-01-23 13:32:34.082955: step: 558/1545, loss: 0.032454296946525574 2023-01-23 13:32:34.972908: step: 560/1545, loss: 0.12044277042150497 2023-01-23 13:32:35.815627: step: 562/1545, loss: 0.0826340839266777 2023-01-23 13:32:36.687541: step: 564/1545, loss: 0.016957256942987442 2023-01-23 13:32:37.567846: step: 566/1545, loss: 0.014854840002954006 2023-01-23 13:32:38.463988: step: 568/1545, loss: 0.6008307933807373 2023-01-23 13:32:39.301017: step: 570/1545, loss: 0.30246448516845703 2023-01-23 13:32:40.170249: step: 572/1545, loss: 0.01878066547214985 2023-01-23 13:32:41.066944: step: 574/1545, loss: 0.08538687229156494 2023-01-23 13:32:41.969045: step: 576/1545, loss: 0.07276057451963425 2023-01-23 13:32:42.830811: step: 578/1545, loss: 0.1322958618402481 2023-01-23 13:32:43.718390: step: 580/1545, loss: 0.22639100253582 2023-01-23 13:32:44.575178: step: 582/1545, loss: 0.04185709357261658 2023-01-23 13:32:45.463999: step: 584/1545, loss: 0.0066524287685751915 2023-01-23 13:32:46.332848: step: 586/1545, loss: 0.1023571640253067 2023-01-23 13:32:47.221102: step: 588/1545, loss: 0.0489610880613327 2023-01-23 13:32:48.080008: step: 590/1545, loss: 0.4223920404911041 2023-01-23 13:32:48.958247: step: 592/1545, loss: 0.055600304156541824 2023-01-23 13:32:49.848484: step: 594/1545, loss: 0.00976361520588398 2023-01-23 13:32:50.706474: step: 596/1545, loss: 0.143064945936203 2023-01-23 13:32:51.601579: step: 598/1545, loss: 0.0014433100586757064 2023-01-23 13:32:52.513371: step: 600/1545, loss: 0.10607705265283585 2023-01-23 13:32:53.409874: step: 602/1545, loss: 0.2578643262386322 2023-01-23 13:32:54.319242: step: 604/1545, loss: 0.06353182345628738 2023-01-23 13:32:55.186080: step: 606/1545, loss: 0.02147153578698635 2023-01-23 13:32:56.024161: step: 608/1545, loss: 0.03363671526312828 2023-01-23 13:32:56.946603: step: 610/1545, loss: 0.08772891759872437 2023-01-23 13:32:57.846529: step: 612/1545, loss: 0.024465860798954964 2023-01-23 13:32:58.725977: step: 614/1545, loss: 0.029594460502266884 2023-01-23 13:32:59.643220: step: 616/1545, loss: 1.378488540649414 2023-01-23 13:33:00.503543: step: 618/1545, loss: 0.0007462541107088327 2023-01-23 13:33:01.388610: step: 620/1545, loss: 0.07111094892024994 2023-01-23 13:33:02.285946: step: 622/1545, loss: 0.07271706312894821 2023-01-23 13:33:03.160827: step: 624/1545, loss: 0.0033761966042220592 2023-01-23 13:33:04.046080: step: 626/1545, loss: 0.025908170267939568 2023-01-23 13:33:04.948507: step: 628/1545, loss: 0.07306870073080063 2023-01-23 13:33:05.815841: step: 630/1545, loss: 0.19761863350868225 2023-01-23 13:33:06.679743: step: 632/1545, loss: 0.04472893103957176 2023-01-23 13:33:07.561647: step: 634/1545, loss: 0.12451396882534027 2023-01-23 13:33:08.414451: step: 636/1545, loss: 0.03778041899204254 2023-01-23 13:33:09.320587: step: 638/1545, loss: 0.05788541957736015 2023-01-23 13:33:10.188515: step: 640/1545, loss: 0.35458454489707947 2023-01-23 13:33:11.067294: step: 642/1545, loss: 0.23874711990356445 2023-01-23 13:33:12.034856: step: 644/1545, loss: 0.16923946142196655 2023-01-23 13:33:12.908346: step: 646/1545, loss: 0.003467501373961568 2023-01-23 13:33:13.767745: step: 648/1545, loss: 0.023581640794873238 2023-01-23 13:33:14.668825: step: 650/1545, loss: 0.09286274015903473 2023-01-23 13:33:15.599112: step: 652/1545, loss: 0.0181858092546463 2023-01-23 13:33:16.488948: step: 654/1545, loss: 0.0004995533963665366 2023-01-23 13:33:17.389951: step: 656/1545, loss: 0.08257173746824265 2023-01-23 13:33:18.249017: step: 658/1545, loss: 0.10103316605091095 2023-01-23 13:33:19.143517: step: 660/1545, loss: 0.006236751098185778 2023-01-23 13:33:20.104367: step: 662/1545, loss: 0.0049560656771063805 2023-01-23 13:33:21.003731: step: 664/1545, loss: 0.3991028368473053 2023-01-23 13:33:21.891120: step: 666/1545, loss: 0.054007578641176224 2023-01-23 13:33:22.730541: step: 668/1545, loss: 2.2767980098724365 2023-01-23 13:33:23.757556: step: 670/1545, loss: 0.12075145542621613 2023-01-23 13:33:24.643701: step: 672/1545, loss: 0.22948268055915833 2023-01-23 13:33:25.478169: step: 674/1545, loss: 0.004130400717258453 2023-01-23 13:33:26.427376: step: 676/1545, loss: 0.015603326261043549 2023-01-23 13:33:27.311809: step: 678/1545, loss: 0.061833158135414124 2023-01-23 13:33:28.190628: step: 680/1545, loss: 0.028389759361743927 2023-01-23 13:33:29.056626: step: 682/1545, loss: 0.016146967187523842 2023-01-23 13:33:29.970824: step: 684/1545, loss: 0.01195208728313446 2023-01-23 13:33:30.839916: step: 686/1545, loss: 0.004487872589379549 2023-01-23 13:33:31.688293: step: 688/1545, loss: 0.06272981315851212 2023-01-23 13:33:32.663331: step: 690/1545, loss: 0.043792545795440674 2023-01-23 13:33:33.490230: step: 692/1545, loss: 0.04746454954147339 2023-01-23 13:33:34.299060: step: 694/1545, loss: 0.0009232667507603765 2023-01-23 13:33:35.128493: step: 696/1545, loss: 0.0219966359436512 2023-01-23 13:33:36.046395: step: 698/1545, loss: 0.017360758036375046 2023-01-23 13:33:36.913917: step: 700/1545, loss: 0.04191209748387337 2023-01-23 13:33:37.786738: step: 702/1545, loss: 0.00964583270251751 2023-01-23 13:33:38.659874: step: 704/1545, loss: 0.3141312897205353 2023-01-23 13:33:39.519482: step: 706/1545, loss: 0.2546130120754242 2023-01-23 13:33:40.379525: step: 708/1545, loss: 0.024098850786685944 2023-01-23 13:33:41.240258: step: 710/1545, loss: 0.0005597914569079876 2023-01-23 13:33:42.116757: step: 712/1545, loss: 0.1225517988204956 2023-01-23 13:33:42.985602: step: 714/1545, loss: 0.09826625138521194 2023-01-23 13:33:43.910437: step: 716/1545, loss: 0.028411881998181343 2023-01-23 13:33:44.814059: step: 718/1545, loss: 0.10567251592874527 2023-01-23 13:33:45.666139: step: 720/1545, loss: 0.05226650461554527 2023-01-23 13:33:46.556756: step: 722/1545, loss: 0.013771669007837772 2023-01-23 13:33:47.475265: step: 724/1545, loss: 0.06875081360340118 2023-01-23 13:33:48.395718: step: 726/1545, loss: 0.04066329076886177 2023-01-23 13:33:49.258281: step: 728/1545, loss: 0.15989208221435547 2023-01-23 13:33:50.116717: step: 730/1545, loss: 0.044430505484342575 2023-01-23 13:33:51.031129: step: 732/1545, loss: 0.14655084908008575 2023-01-23 13:33:51.892334: step: 734/1545, loss: 0.0001529617002233863 2023-01-23 13:33:52.773877: step: 736/1545, loss: 0.060530323535203934 2023-01-23 13:33:53.631820: step: 738/1545, loss: 0.11778198182582855 2023-01-23 13:33:54.511314: step: 740/1545, loss: 0.09435687214136124 2023-01-23 13:33:55.394042: step: 742/1545, loss: 0.02319423109292984 2023-01-23 13:33:56.229962: step: 744/1545, loss: 0.002177539048716426 2023-01-23 13:33:57.106722: step: 746/1545, loss: 0.07352745532989502 2023-01-23 13:33:57.998250: step: 748/1545, loss: 0.0649832934141159 2023-01-23 13:33:58.920014: step: 750/1545, loss: 0.036973729729652405 2023-01-23 13:33:59.743956: step: 752/1545, loss: 0.045041292905807495 2023-01-23 13:34:00.635790: step: 754/1545, loss: 0.18076759576797485 2023-01-23 13:34:01.472055: step: 756/1545, loss: 0.13218095898628235 2023-01-23 13:34:02.378755: step: 758/1545, loss: 0.04150950163602829 2023-01-23 13:34:03.221453: step: 760/1545, loss: 0.004778746981173754 2023-01-23 13:34:04.085374: step: 762/1545, loss: 0.2202526330947876 2023-01-23 13:34:04.963631: step: 764/1545, loss: 0.24094420671463013 2023-01-23 13:34:05.852766: step: 766/1545, loss: 0.003063873155042529 2023-01-23 13:34:06.708741: step: 768/1545, loss: 0.09860734641551971 2023-01-23 13:34:07.585647: step: 770/1545, loss: 0.0008345773676410317 2023-01-23 13:34:08.465951: step: 772/1545, loss: 0.13676616549491882 2023-01-23 13:34:09.396234: step: 774/1545, loss: 0.013033160008490086 2023-01-23 13:34:10.283440: step: 776/1545, loss: 0.01695617474615574 2023-01-23 13:34:11.156413: step: 778/1545, loss: 0.10649176687002182 2023-01-23 13:34:12.037787: step: 780/1545, loss: 0.04168142378330231 2023-01-23 13:34:12.924349: step: 782/1545, loss: 0.06235310062766075 2023-01-23 13:34:13.805965: step: 784/1545, loss: 0.08404757082462311 2023-01-23 13:34:14.642276: step: 786/1545, loss: 0.1877511888742447 2023-01-23 13:34:15.518388: step: 788/1545, loss: 0.01137229148298502 2023-01-23 13:34:16.409877: step: 790/1545, loss: 0.6103835701942444 2023-01-23 13:34:17.293887: step: 792/1545, loss: 0.05383917689323425 2023-01-23 13:34:18.142392: step: 794/1545, loss: 0.0035147261805832386 2023-01-23 13:34:19.031707: step: 796/1545, loss: 0.05481639876961708 2023-01-23 13:34:19.889859: step: 798/1545, loss: 0.07793334126472473 2023-01-23 13:34:20.751010: step: 800/1545, loss: 0.010887141339480877 2023-01-23 13:34:21.629162: step: 802/1545, loss: 0.1491873860359192 2023-01-23 13:34:22.520259: step: 804/1545, loss: 0.16470307111740112 2023-01-23 13:34:23.381834: step: 806/1545, loss: 0.005566027481108904 2023-01-23 13:34:24.206035: step: 808/1545, loss: 0.007606121711432934 2023-01-23 13:34:25.110487: step: 810/1545, loss: 0.22835172712802887 2023-01-23 13:34:25.997980: step: 812/1545, loss: 0.014003641903400421 2023-01-23 13:34:26.899492: step: 814/1545, loss: 0.15351594984531403 2023-01-23 13:34:27.878635: step: 816/1545, loss: 0.0938093513250351 2023-01-23 13:34:28.760750: step: 818/1545, loss: 0.1722962111234665 2023-01-23 13:34:29.620042: step: 820/1545, loss: 0.07964856922626495 2023-01-23 13:34:30.555778: step: 822/1545, loss: 0.002215684624388814 2023-01-23 13:34:31.481959: step: 824/1545, loss: 0.16636814177036285 2023-01-23 13:34:32.358370: step: 826/1545, loss: 0.009652669541537762 2023-01-23 13:34:33.270182: step: 828/1545, loss: 0.04915320873260498 2023-01-23 13:34:34.185128: step: 830/1545, loss: 0.07160331308841705 2023-01-23 13:34:35.064082: step: 832/1545, loss: 0.007791498210281134 2023-01-23 13:34:35.965322: step: 834/1545, loss: 0.053249720484018326 2023-01-23 13:34:36.803994: step: 836/1545, loss: 0.13094939291477203 2023-01-23 13:34:37.713867: step: 838/1545, loss: 0.11026236414909363 2023-01-23 13:34:38.604345: step: 840/1545, loss: 0.40660274028778076 2023-01-23 13:34:39.476874: step: 842/1545, loss: 0.024964388459920883 2023-01-23 13:34:40.345410: step: 844/1545, loss: 0.15082590281963348 2023-01-23 13:34:41.265102: step: 846/1545, loss: 0.08060356229543686 2023-01-23 13:34:42.144712: step: 848/1545, loss: 0.43800461292266846 2023-01-23 13:34:43.045428: step: 850/1545, loss: 0.03401004523038864 2023-01-23 13:34:43.944410: step: 852/1545, loss: 0.0791609063744545 2023-01-23 13:34:44.832356: step: 854/1545, loss: 0.07803517580032349 2023-01-23 13:34:45.767130: step: 856/1545, loss: 0.3085204064846039 2023-01-23 13:34:46.626658: step: 858/1545, loss: 0.011011619120836258 2023-01-23 13:34:47.468954: step: 860/1545, loss: 0.23087178170681 2023-01-23 13:34:48.326949: step: 862/1545, loss: 0.0037964684888720512 2023-01-23 13:34:49.257691: step: 864/1545, loss: 0.010877992026507854 2023-01-23 13:34:50.141058: step: 866/1545, loss: 0.006028828211128712 2023-01-23 13:34:51.032120: step: 868/1545, loss: 0.05125531926751137 2023-01-23 13:34:51.886194: step: 870/1545, loss: 0.11046119034290314 2023-01-23 13:34:52.731714: step: 872/1545, loss: 0.008779656141996384 2023-01-23 13:34:53.595718: step: 874/1545, loss: 0.007557525299489498 2023-01-23 13:34:54.478823: step: 876/1545, loss: 0.451505571603775 2023-01-23 13:34:55.370565: step: 878/1545, loss: 0.008306602947413921 2023-01-23 13:34:56.269486: step: 880/1545, loss: 0.25402605533599854 2023-01-23 13:34:57.141676: step: 882/1545, loss: 0.06653301417827606 2023-01-23 13:34:57.995379: step: 884/1545, loss: 0.1529860943555832 2023-01-23 13:34:58.873631: step: 886/1545, loss: 0.12245458364486694 2023-01-23 13:34:59.745621: step: 888/1545, loss: 0.11691182851791382 2023-01-23 13:35:00.645131: step: 890/1545, loss: 0.014252163469791412 2023-01-23 13:35:01.548853: step: 892/1545, loss: 0.0015890260692685843 2023-01-23 13:35:02.485273: step: 894/1545, loss: 0.05073659121990204 2023-01-23 13:35:03.351510: step: 896/1545, loss: 0.09725198894739151 2023-01-23 13:35:04.219706: step: 898/1545, loss: 0.011472729966044426 2023-01-23 13:35:05.117201: step: 900/1545, loss: 0.01094607450067997 2023-01-23 13:35:05.979151: step: 902/1545, loss: 0.08717712759971619 2023-01-23 13:35:06.852457: step: 904/1545, loss: 0.09795527160167694 2023-01-23 13:35:07.755526: step: 906/1545, loss: 0.006835300475358963 2023-01-23 13:35:08.599481: step: 908/1545, loss: 0.008981830440461636 2023-01-23 13:35:09.494285: step: 910/1545, loss: 0.04114487022161484 2023-01-23 13:35:10.388666: step: 912/1545, loss: 0.0036411783657968044 2023-01-23 13:35:11.243058: step: 914/1545, loss: 0.09935128688812256 2023-01-23 13:35:12.129045: step: 916/1545, loss: 0.37559884786605835 2023-01-23 13:35:13.012354: step: 918/1545, loss: 0.011021047830581665 2023-01-23 13:35:13.865069: step: 920/1545, loss: 0.01174550037831068 2023-01-23 13:35:14.719096: step: 922/1545, loss: 0.0761827751994133 2023-01-23 13:35:15.613609: step: 924/1545, loss: 0.2861379384994507 2023-01-23 13:35:16.491706: step: 926/1545, loss: 0.049522243440151215 2023-01-23 13:35:17.351050: step: 928/1545, loss: 0.2044454663991928 2023-01-23 13:35:18.237402: step: 930/1545, loss: 0.019302116706967354 2023-01-23 13:35:19.109520: step: 932/1545, loss: 0.0009496053098700941 2023-01-23 13:35:19.985179: step: 934/1545, loss: 0.1015915647149086 2023-01-23 13:35:20.825860: step: 936/1545, loss: 0.0015413311775773764 2023-01-23 13:35:21.671700: step: 938/1545, loss: 0.0975179597735405 2023-01-23 13:35:22.515609: step: 940/1545, loss: 0.034179817885160446 2023-01-23 13:35:23.353985: step: 942/1545, loss: 0.12087167799472809 2023-01-23 13:35:24.174901: step: 944/1545, loss: 0.011418802663683891 2023-01-23 13:35:25.006338: step: 946/1545, loss: 0.0030670103151351213 2023-01-23 13:35:25.833514: step: 948/1545, loss: 0.0345035120844841 2023-01-23 13:35:26.685567: step: 950/1545, loss: 0.194015234708786 2023-01-23 13:35:27.596480: step: 952/1545, loss: 0.31117770075798035 2023-01-23 13:35:28.444945: step: 954/1545, loss: 0.005897709168493748 2023-01-23 13:35:29.323033: step: 956/1545, loss: 0.014896386303007603 2023-01-23 13:35:30.191418: step: 958/1545, loss: 0.07112372666597366 2023-01-23 13:35:31.041292: step: 960/1545, loss: 0.0010376685531809926 2023-01-23 13:35:32.047276: step: 962/1545, loss: 0.056783176958560944 2023-01-23 13:35:32.913502: step: 964/1545, loss: 0.12685389816761017 2023-01-23 13:35:33.788079: step: 966/1545, loss: 0.06822085380554199 2023-01-23 13:35:34.661962: step: 968/1545, loss: 0.012055417522788048 2023-01-23 13:35:35.570983: step: 970/1545, loss: 1.451216459274292 2023-01-23 13:35:36.486748: step: 972/1545, loss: 0.009219817817211151 2023-01-23 13:35:37.326088: step: 974/1545, loss: 0.02459939382970333 2023-01-23 13:35:38.209373: step: 976/1545, loss: 0.15014195442199707 2023-01-23 13:35:39.030772: step: 978/1545, loss: 0.32711440324783325 2023-01-23 13:35:40.010746: step: 980/1545, loss: 0.028482995927333832 2023-01-23 13:35:40.930511: step: 982/1545, loss: 0.09245635569095612 2023-01-23 13:35:41.795314: step: 984/1545, loss: 0.29645130038261414 2023-01-23 13:35:42.641001: step: 986/1545, loss: 0.11330098658800125 2023-01-23 13:35:43.493470: step: 988/1545, loss: 0.02411588467657566 2023-01-23 13:35:44.358535: step: 990/1545, loss: 0.04855458438396454 2023-01-23 13:35:45.240041: step: 992/1545, loss: 0.23202255368232727 2023-01-23 13:35:46.086039: step: 994/1545, loss: 0.5820285081863403 2023-01-23 13:35:46.976060: step: 996/1545, loss: 0.641051709651947 2023-01-23 13:35:47.841603: step: 998/1545, loss: 0.1289985626935959 2023-01-23 13:35:48.714864: step: 1000/1545, loss: 0.14932477474212646 2023-01-23 13:35:49.590060: step: 1002/1545, loss: 0.17273302376270294 2023-01-23 13:35:50.522571: step: 1004/1545, loss: 0.10257735848426819 2023-01-23 13:35:51.430558: step: 1006/1545, loss: 0.005031234584748745 2023-01-23 13:35:52.327245: step: 1008/1545, loss: 0.003978574648499489 2023-01-23 13:35:53.238355: step: 1010/1545, loss: 0.03039631061255932 2023-01-23 13:35:54.103669: step: 1012/1545, loss: 0.02556939609348774 2023-01-23 13:35:54.923811: step: 1014/1545, loss: 0.09215372055768967 2023-01-23 13:35:55.755336: step: 1016/1545, loss: 0.0026256472337991 2023-01-23 13:35:56.598993: step: 1018/1545, loss: 0.12034367769956589 2023-01-23 13:35:57.502771: step: 1020/1545, loss: 0.055051762610673904 2023-01-23 13:35:58.484200: step: 1022/1545, loss: 0.007211857475340366 2023-01-23 13:35:59.368824: step: 1024/1545, loss: 0.04974282905459404 2023-01-23 13:36:00.254070: step: 1026/1545, loss: 0.10115769505500793 2023-01-23 13:36:01.157738: step: 1028/1545, loss: 0.04394792392849922 2023-01-23 13:36:02.043559: step: 1030/1545, loss: 0.005215426441282034 2023-01-23 13:36:02.885779: step: 1032/1545, loss: 0.044612985104322433 2023-01-23 13:36:03.773583: step: 1034/1545, loss: 0.00492931017652154 2023-01-23 13:36:04.649480: step: 1036/1545, loss: 0.445218026638031 2023-01-23 13:36:05.518847: step: 1038/1545, loss: 0.27968406677246094 2023-01-23 13:36:06.378344: step: 1040/1545, loss: 0.32254090905189514 2023-01-23 13:36:07.249696: step: 1042/1545, loss: 0.004282065201550722 2023-01-23 13:36:08.111886: step: 1044/1545, loss: 0.16955512762069702 2023-01-23 13:36:08.969488: step: 1046/1545, loss: 0.08643180131912231 2023-01-23 13:36:09.846408: step: 1048/1545, loss: 0.1466580629348755 2023-01-23 13:36:10.796890: step: 1050/1545, loss: 0.09758303314447403 2023-01-23 13:36:11.701972: step: 1052/1545, loss: 0.08729033917188644 2023-01-23 13:36:12.543791: step: 1054/1545, loss: 0.011192644014954567 2023-01-23 13:36:13.470044: step: 1056/1545, loss: 0.01879950240254402 2023-01-23 13:36:14.341978: step: 1058/1545, loss: 0.23427613079547882 2023-01-23 13:36:15.233600: step: 1060/1545, loss: 0.04472886770963669 2023-01-23 13:36:16.134980: step: 1062/1545, loss: 0.008711716160178185 2023-01-23 13:36:17.068192: step: 1064/1545, loss: 0.05666881799697876 2023-01-23 13:36:17.944905: step: 1066/1545, loss: 0.05755777284502983 2023-01-23 13:36:18.848620: step: 1068/1545, loss: 0.20517565310001373 2023-01-23 13:36:19.791121: step: 1070/1545, loss: 0.3535979092121124 2023-01-23 13:36:20.651063: step: 1072/1545, loss: 0.009621795266866684 2023-01-23 13:36:21.533123: step: 1074/1545, loss: 0.02909720130264759 2023-01-23 13:36:22.381472: step: 1076/1545, loss: 0.02507113851606846 2023-01-23 13:36:23.271889: step: 1078/1545, loss: 0.04649550840258598 2023-01-23 13:36:24.168772: step: 1080/1545, loss: 0.05765122175216675 2023-01-23 13:36:25.067032: step: 1082/1545, loss: 0.44184112548828125 2023-01-23 13:36:25.998361: step: 1084/1545, loss: 0.0002825249976012856 2023-01-23 13:36:26.860683: step: 1086/1545, loss: 0.0416734516620636 2023-01-23 13:36:27.774288: step: 1088/1545, loss: 0.01414327509701252 2023-01-23 13:36:28.660450: step: 1090/1545, loss: 0.007399474736303091 2023-01-23 13:36:29.536758: step: 1092/1545, loss: 0.0011742603965103626 2023-01-23 13:36:30.406459: step: 1094/1545, loss: 0.013504475355148315 2023-01-23 13:36:31.309660: step: 1096/1545, loss: 0.04445686563849449 2023-01-23 13:36:32.249199: step: 1098/1545, loss: 0.20967721939086914 2023-01-23 13:36:33.101263: step: 1100/1545, loss: 0.09455213695764542 2023-01-23 13:36:34.009199: step: 1102/1545, loss: 0.008220571093261242 2023-01-23 13:36:34.855602: step: 1104/1545, loss: 0.003626040415838361 2023-01-23 13:36:35.697164: step: 1106/1545, loss: 0.007273872382938862 2023-01-23 13:36:36.589486: step: 1108/1545, loss: 0.022715553641319275 2023-01-23 13:36:37.535483: step: 1110/1545, loss: 0.15229840576648712 2023-01-23 13:36:38.349998: step: 1112/1545, loss: 0.08256873488426208 2023-01-23 13:36:39.251517: step: 1114/1545, loss: 0.030163060873746872 2023-01-23 13:36:40.115875: step: 1116/1545, loss: 0.8759663701057434 2023-01-23 13:36:41.032072: step: 1118/1545, loss: 0.1706775724887848 2023-01-23 13:36:41.950380: step: 1120/1545, loss: 0.12496501207351685 2023-01-23 13:36:42.839159: step: 1122/1545, loss: 0.2427448332309723 2023-01-23 13:36:43.704089: step: 1124/1545, loss: 0.0020423850510269403 2023-01-23 13:36:44.598595: step: 1126/1545, loss: 0.10477537661790848 2023-01-23 13:36:45.494665: step: 1128/1545, loss: 0.012095010839402676 2023-01-23 13:36:46.367623: step: 1130/1545, loss: 0.2598724961280823 2023-01-23 13:36:47.237816: step: 1132/1545, loss: 0.04193222522735596 2023-01-23 13:36:48.088247: step: 1134/1545, loss: 0.07263153791427612 2023-01-23 13:36:49.031742: step: 1136/1545, loss: 0.09379027783870697 2023-01-23 13:36:49.904394: step: 1138/1545, loss: 0.15801462531089783 2023-01-23 13:36:50.825016: step: 1140/1545, loss: 0.0053822933696210384 2023-01-23 13:36:51.679083: step: 1142/1545, loss: 0.06882543861865997 2023-01-23 13:36:52.579991: step: 1144/1545, loss: 0.0029302004259079695 2023-01-23 13:36:53.452957: step: 1146/1545, loss: 0.13051436841487885 2023-01-23 13:36:54.371963: step: 1148/1545, loss: 0.006523339077830315 2023-01-23 13:36:55.219367: step: 1150/1545, loss: 0.008030789904296398 2023-01-23 13:36:56.099027: step: 1152/1545, loss: 0.18785645067691803 2023-01-23 13:36:56.991717: step: 1154/1545, loss: 0.07643062621355057 2023-01-23 13:36:57.862121: step: 1156/1545, loss: 0.04424227774143219 2023-01-23 13:36:58.749597: step: 1158/1545, loss: 0.046474821865558624 2023-01-23 13:36:59.638546: step: 1160/1545, loss: 0.05074724927544594 2023-01-23 13:37:00.503452: step: 1162/1545, loss: 0.031156232580542564 2023-01-23 13:37:01.438160: step: 1164/1545, loss: 0.19661343097686768 2023-01-23 13:37:02.305097: step: 1166/1545, loss: 0.0026243343017995358 2023-01-23 13:37:03.140909: step: 1168/1545, loss: 0.016222767531871796 2023-01-23 13:37:03.984074: step: 1170/1545, loss: 0.16104908287525177 2023-01-23 13:37:04.855375: step: 1172/1545, loss: 0.018798619508743286 2023-01-23 13:37:05.678158: step: 1174/1545, loss: 0.008147547952830791 2023-01-23 13:37:06.607595: step: 1176/1545, loss: 0.08468766510486603 2023-01-23 13:37:07.539370: step: 1178/1545, loss: 0.10497374087572098 2023-01-23 13:37:08.403023: step: 1180/1545, loss: 0.057906247675418854 2023-01-23 13:37:09.239619: step: 1182/1545, loss: 0.6943939328193665 2023-01-23 13:37:10.080873: step: 1184/1545, loss: 0.2179751694202423 2023-01-23 13:37:10.948257: step: 1186/1545, loss: 0.05922717601060867 2023-01-23 13:37:11.821605: step: 1188/1545, loss: 0.14687497913837433 2023-01-23 13:37:12.715194: step: 1190/1545, loss: 0.003186666639521718 2023-01-23 13:37:13.563635: step: 1192/1545, loss: 0.1278349757194519 2023-01-23 13:37:14.433156: step: 1194/1545, loss: 0.017864245921373367 2023-01-23 13:37:15.287250: step: 1196/1545, loss: 0.003668713616207242 2023-01-23 13:37:16.149691: step: 1198/1545, loss: 0.015404187142848969 2023-01-23 13:37:17.018847: step: 1200/1545, loss: 0.07179789245128632 2023-01-23 13:37:17.872734: step: 1202/1545, loss: 0.00838744081556797 2023-01-23 13:37:18.748660: step: 1204/1545, loss: 0.0007382484618574381 2023-01-23 13:37:19.704970: step: 1206/1545, loss: 0.025557808578014374 2023-01-23 13:37:20.630202: step: 1208/1545, loss: 0.11773528158664703 2023-01-23 13:37:21.466632: step: 1210/1545, loss: 0.015046102926135063 2023-01-23 13:37:22.329350: step: 1212/1545, loss: 0.0013731076614931226 2023-01-23 13:37:23.233380: step: 1214/1545, loss: 0.025716979056596756 2023-01-23 13:37:24.154117: step: 1216/1545, loss: 0.0031964522786438465 2023-01-23 13:37:25.087537: step: 1218/1545, loss: 0.055362578481435776 2023-01-23 13:37:25.956315: step: 1220/1545, loss: 0.0282012727111578 2023-01-23 13:37:26.848511: step: 1222/1545, loss: 0.040664397180080414 2023-01-23 13:37:27.734846: step: 1224/1545, loss: 0.004176918417215347 2023-01-23 13:37:28.650479: step: 1226/1545, loss: 0.1257966011762619 2023-01-23 13:37:29.512886: step: 1228/1545, loss: 0.010723184794187546 2023-01-23 13:37:30.413034: step: 1230/1545, loss: 0.21221458911895752 2023-01-23 13:37:31.317056: step: 1232/1545, loss: 0.01574632152915001 2023-01-23 13:37:32.269443: step: 1234/1545, loss: 0.003450110089033842 2023-01-23 13:37:33.204409: step: 1236/1545, loss: 0.03818468749523163 2023-01-23 13:37:34.078141: step: 1238/1545, loss: 0.5020281672477722 2023-01-23 13:37:34.947742: step: 1240/1545, loss: 0.06222349777817726 2023-01-23 13:37:35.870453: step: 1242/1545, loss: 0.08784285932779312 2023-01-23 13:37:36.750733: step: 1244/1545, loss: 0.05600816011428833 2023-01-23 13:37:37.648694: step: 1246/1545, loss: 0.1591828465461731 2023-01-23 13:37:38.524153: step: 1248/1545, loss: 0.1285124570131302 2023-01-23 13:37:39.463862: step: 1250/1545, loss: 0.037745118141174316 2023-01-23 13:37:40.347770: step: 1252/1545, loss: 0.07502758502960205 2023-01-23 13:37:41.220786: step: 1254/1545, loss: 0.006647502072155476 2023-01-23 13:37:42.136266: step: 1256/1545, loss: 0.34937551617622375 2023-01-23 13:37:43.008904: step: 1258/1545, loss: 0.2572076916694641 2023-01-23 13:37:43.970454: step: 1260/1545, loss: 0.017825257033109665 2023-01-23 13:37:44.835080: step: 1262/1545, loss: 0.03784314915537834 2023-01-23 13:37:45.696115: step: 1264/1545, loss: 0.041695207357406616 2023-01-23 13:37:46.551657: step: 1266/1545, loss: 0.025761226192116737 2023-01-23 13:37:47.454878: step: 1268/1545, loss: 0.08452370017766953 2023-01-23 13:37:48.304631: step: 1270/1545, loss: 0.09019549190998077 2023-01-23 13:37:49.151699: step: 1272/1545, loss: 0.4055038094520569 2023-01-23 13:37:50.030613: step: 1274/1545, loss: 0.4076630771160126 2023-01-23 13:37:50.932855: step: 1276/1545, loss: 0.059989117085933685 2023-01-23 13:37:51.878336: step: 1278/1545, loss: 0.002820283640176058 2023-01-23 13:37:52.841858: step: 1280/1545, loss: 0.06908977031707764 2023-01-23 13:37:53.709113: step: 1282/1545, loss: 0.003951407503336668 2023-01-23 13:37:54.573843: step: 1284/1545, loss: 0.06721561402082443 2023-01-23 13:37:55.458732: step: 1286/1545, loss: 1.311576247215271 2023-01-23 13:37:56.310756: step: 1288/1545, loss: 0.3977808654308319 2023-01-23 13:37:57.208030: step: 1290/1545, loss: 0.03223443031311035 2023-01-23 13:37:58.045944: step: 1292/1545, loss: 0.6285350918769836 2023-01-23 13:37:58.925789: step: 1294/1545, loss: 0.06105716899037361 2023-01-23 13:37:59.810167: step: 1296/1545, loss: 0.5681230425834656 2023-01-23 13:38:00.708055: step: 1298/1545, loss: 0.007989717647433281 2023-01-23 13:38:01.590264: step: 1300/1545, loss: 0.0008915867656469345 2023-01-23 13:38:02.504791: step: 1302/1545, loss: 0.015870029106736183 2023-01-23 13:38:03.376643: step: 1304/1545, loss: 0.008143720217049122 2023-01-23 13:38:04.257075: step: 1306/1545, loss: 0.16254109144210815 2023-01-23 13:38:05.177796: step: 1308/1545, loss: 0.048199232667684555 2023-01-23 13:38:06.102540: step: 1310/1545, loss: 0.04707743600010872 2023-01-23 13:38:07.017584: step: 1312/1545, loss: 0.015453058294951916 2023-01-23 13:38:07.967672: step: 1314/1545, loss: 0.35458630323410034 2023-01-23 13:38:08.847970: step: 1316/1545, loss: 0.1421853005886078 2023-01-23 13:38:09.706242: step: 1318/1545, loss: 0.21920359134674072 2023-01-23 13:38:10.561792: step: 1320/1545, loss: 0.009472684934735298 2023-01-23 13:38:11.422138: step: 1322/1545, loss: 0.07769584655761719 2023-01-23 13:38:12.330973: step: 1324/1545, loss: 0.00404336117208004 2023-01-23 13:38:13.225939: step: 1326/1545, loss: 0.33285513520240784 2023-01-23 13:38:14.137873: step: 1328/1545, loss: 0.18906258046627045 2023-01-23 13:38:14.994893: step: 1330/1545, loss: 0.41249024868011475 2023-01-23 13:38:15.847495: step: 1332/1545, loss: 0.0031490218825638294 2023-01-23 13:38:16.716391: step: 1334/1545, loss: 0.17355166375637054 2023-01-23 13:38:17.586884: step: 1336/1545, loss: 0.07044314593076706 2023-01-23 13:38:18.488713: step: 1338/1545, loss: 0.017288856208324432 2023-01-23 13:38:19.429975: step: 1340/1545, loss: 0.0820651724934578 2023-01-23 13:38:20.372063: step: 1342/1545, loss: 0.044759418815374374 2023-01-23 13:38:21.261193: step: 1344/1545, loss: 0.21723788976669312 2023-01-23 13:38:22.133410: step: 1346/1545, loss: 0.09591160714626312 2023-01-23 13:38:22.997961: step: 1348/1545, loss: 0.008633304387331009 2023-01-23 13:38:23.894240: step: 1350/1545, loss: 0.007416791282594204 2023-01-23 13:38:24.803264: step: 1352/1545, loss: 0.011823270469903946 2023-01-23 13:38:25.671476: step: 1354/1545, loss: 0.033976126462221146 2023-01-23 13:38:26.517008: step: 1356/1545, loss: 0.06183085963129997 2023-01-23 13:38:27.379680: step: 1358/1545, loss: 0.1322348564863205 2023-01-23 13:38:28.229764: step: 1360/1545, loss: 0.022257164120674133 2023-01-23 13:38:29.118043: step: 1362/1545, loss: 0.09027132391929626 2023-01-23 13:38:29.973456: step: 1364/1545, loss: 0.05520627275109291 2023-01-23 13:38:30.845112: step: 1366/1545, loss: 0.04503213241696358 2023-01-23 13:38:31.722254: step: 1368/1545, loss: 0.06678835302591324 2023-01-23 13:38:32.648082: step: 1370/1545, loss: 0.060978103429079056 2023-01-23 13:38:33.557911: step: 1372/1545, loss: 0.03934582322835922 2023-01-23 13:38:34.444408: step: 1374/1545, loss: 0.01591983623802662 2023-01-23 13:38:35.336996: step: 1376/1545, loss: 0.06077781319618225 2023-01-23 13:38:36.240391: step: 1378/1545, loss: 0.13231255114078522 2023-01-23 13:38:37.139335: step: 1380/1545, loss: 0.03340652212500572 2023-01-23 13:38:37.976213: step: 1382/1545, loss: 0.04316963627934456 2023-01-23 13:38:38.841528: step: 1384/1545, loss: 0.022269172593951225 2023-01-23 13:38:39.751368: step: 1386/1545, loss: 0.1577238142490387 2023-01-23 13:38:40.629356: step: 1388/1545, loss: 0.0010076997568830848 2023-01-23 13:38:41.509411: step: 1390/1545, loss: 0.0024308422580361366 2023-01-23 13:38:42.380415: step: 1392/1545, loss: 0.029801029711961746 2023-01-23 13:38:43.262292: step: 1394/1545, loss: 0.2600546181201935 2023-01-23 13:38:44.123288: step: 1396/1545, loss: 0.028976501896977425 2023-01-23 13:38:44.974741: step: 1398/1545, loss: 0.04874417185783386 2023-01-23 13:38:45.830858: step: 1400/1545, loss: 0.021075580269098282 2023-01-23 13:38:46.702038: step: 1402/1545, loss: 0.009975437074899673 2023-01-23 13:38:47.615667: step: 1404/1545, loss: 0.0048428745940327644 2023-01-23 13:38:48.513030: step: 1406/1545, loss: 2.1482789516448975 2023-01-23 13:38:49.417347: step: 1408/1545, loss: 0.016433073207736015 2023-01-23 13:38:50.279374: step: 1410/1545, loss: 0.060855068266391754 2023-01-23 13:38:51.179833: step: 1412/1545, loss: 0.010099063627421856 2023-01-23 13:38:52.073023: step: 1414/1545, loss: 0.028040673583745956 2023-01-23 13:38:52.952105: step: 1416/1545, loss: 0.46759265661239624 2023-01-23 13:38:53.827236: step: 1418/1545, loss: 0.0856970027089119 2023-01-23 13:38:54.782821: step: 1420/1545, loss: 0.027893392369151115 2023-01-23 13:38:55.630123: step: 1422/1545, loss: 0.020566819235682487 2023-01-23 13:38:56.463082: step: 1424/1545, loss: 0.4407390356063843 2023-01-23 13:38:57.335445: step: 1426/1545, loss: 2.6433651447296143 2023-01-23 13:38:58.205710: step: 1428/1545, loss: 0.00402777548879385 2023-01-23 13:38:59.064724: step: 1430/1545, loss: 0.08202703297138214 2023-01-23 13:38:59.942039: step: 1432/1545, loss: 0.01446594949811697 2023-01-23 13:39:00.795096: step: 1434/1545, loss: 0.02347484417259693 2023-01-23 13:39:01.664243: step: 1436/1545, loss: 0.02370145358145237 2023-01-23 13:39:02.490018: step: 1438/1545, loss: 0.00029178650584071875 2023-01-23 13:39:03.361012: step: 1440/1545, loss: 0.07922792434692383 2023-01-23 13:39:04.222232: step: 1442/1545, loss: 0.4272131025791168 2023-01-23 13:39:05.085273: step: 1444/1545, loss: 0.006348130758851767 2023-01-23 13:39:06.020715: step: 1446/1545, loss: 0.05526123195886612 2023-01-23 13:39:06.932742: step: 1448/1545, loss: 0.012162319384515285 2023-01-23 13:39:07.794255: step: 1450/1545, loss: 0.004987612832337618 2023-01-23 13:39:08.643744: step: 1452/1545, loss: 0.09143052250146866 2023-01-23 13:39:09.555988: step: 1454/1545, loss: 0.0004797214351128787 2023-01-23 13:39:10.458108: step: 1456/1545, loss: 0.012662784196436405 2023-01-23 13:39:11.337035: step: 1458/1545, loss: 0.028575271368026733 2023-01-23 13:39:12.174110: step: 1460/1545, loss: 0.1177259236574173 2023-01-23 13:39:13.015130: step: 1462/1545, loss: 0.009024698287248611 2023-01-23 13:39:13.906547: step: 1464/1545, loss: 0.11821752786636353 2023-01-23 13:39:14.743739: step: 1466/1545, loss: 0.8716954588890076 2023-01-23 13:39:15.629343: step: 1468/1545, loss: 0.0033009981270879507 2023-01-23 13:39:16.556452: step: 1470/1545, loss: 0.054305147379636765 2023-01-23 13:39:17.446371: step: 1472/1545, loss: 0.29010289907455444 2023-01-23 13:39:18.351479: step: 1474/1545, loss: 0.0017913688207045197 2023-01-23 13:39:19.229525: step: 1476/1545, loss: 0.003647818462923169 2023-01-23 13:39:20.190283: step: 1478/1545, loss: 0.1048036739230156 2023-01-23 13:39:21.118108: step: 1480/1545, loss: 1.2066843509674072 2023-01-23 13:39:22.009147: step: 1482/1545, loss: 0.012998648919165134 2023-01-23 13:39:22.918295: step: 1484/1545, loss: 0.006441166624426842 2023-01-23 13:39:23.800846: step: 1486/1545, loss: 0.002205753466114402 2023-01-23 13:39:24.684469: step: 1488/1545, loss: 0.018994977697730064 2023-01-23 13:39:25.563520: step: 1490/1545, loss: 0.0012339400127530098 2023-01-23 13:39:26.487800: step: 1492/1545, loss: 0.3450091481208801 2023-01-23 13:39:27.353245: step: 1494/1545, loss: 0.09548795968294144 2023-01-23 13:39:28.216416: step: 1496/1545, loss: 0.008747282437980175 2023-01-23 13:39:29.069086: step: 1498/1545, loss: 1.9273494482040405 2023-01-23 13:39:29.921243: step: 1500/1545, loss: 0.011761858128011227 2023-01-23 13:39:30.782975: step: 1502/1545, loss: 0.021686915308237076 2023-01-23 13:39:31.664379: step: 1504/1545, loss: 0.0018940630834549665 2023-01-23 13:39:32.562326: step: 1506/1545, loss: 0.10366150736808777 2023-01-23 13:39:33.448241: step: 1508/1545, loss: 0.005236128345131874 2023-01-23 13:39:34.320093: step: 1510/1545, loss: 0.017443476244807243 2023-01-23 13:39:35.184363: step: 1512/1545, loss: 0.043319083750247955 2023-01-23 13:39:36.074571: step: 1514/1545, loss: 0.09723460674285889 2023-01-23 13:39:36.909923: step: 1516/1545, loss: 0.128445565700531 2023-01-23 13:39:37.801809: step: 1518/1545, loss: 0.01481477078050375 2023-01-23 13:39:38.686949: step: 1520/1545, loss: 0.01984526589512825 2023-01-23 13:39:39.660844: step: 1522/1545, loss: 0.05143358185887337 2023-01-23 13:39:40.568016: step: 1524/1545, loss: 0.03219150751829147 2023-01-23 13:39:41.526503: step: 1526/1545, loss: 0.14496095478534698 2023-01-23 13:39:42.433217: step: 1528/1545, loss: 0.012719506397843361 2023-01-23 13:39:43.363480: step: 1530/1545, loss: 0.038084667176008224 2023-01-23 13:39:44.235727: step: 1532/1545, loss: 0.0034531436394900084 2023-01-23 13:39:45.127125: step: 1534/1545, loss: 0.228287473320961 2023-01-23 13:39:46.029106: step: 1536/1545, loss: 0.27115094661712646 2023-01-23 13:39:46.960460: step: 1538/1545, loss: 0.16878129541873932 2023-01-23 13:39:47.881147: step: 1540/1545, loss: 0.15375398099422455 2023-01-23 13:39:48.752889: step: 1542/1545, loss: 0.13223345577716827 2023-01-23 13:39:49.611437: step: 1544/1545, loss: 0.05634332075715065 2023-01-23 13:39:50.441441: step: 1546/1545, loss: 0.0073640900664031506 2023-01-23 13:39:51.299060: step: 1548/1545, loss: 0.010785916820168495 2023-01-23 13:39:52.158717: step: 1550/1545, loss: 0.05246506258845329 2023-01-23 13:39:53.042130: step: 1552/1545, loss: 0.017793122678995132 2023-01-23 13:39:53.933793: step: 1554/1545, loss: 0.01149531826376915 2023-01-23 13:39:54.796841: step: 1556/1545, loss: 0.1567385196685791 2023-01-23 13:39:55.643905: step: 1558/1545, loss: 0.2914349436759949 2023-01-23 13:39:56.499077: step: 1560/1545, loss: 0.009186165407299995 2023-01-23 13:39:57.339824: step: 1562/1545, loss: 0.04667635262012482 2023-01-23 13:39:58.225643: step: 1564/1545, loss: 0.07368232309818268 2023-01-23 13:39:59.128724: step: 1566/1545, loss: 0.0009533418924547732 2023-01-23 13:39:59.988810: step: 1568/1545, loss: 0.0071375127881765366 2023-01-23 13:40:00.866849: step: 1570/1545, loss: 0.11229042708873749 2023-01-23 13:40:01.776090: step: 1572/1545, loss: 0.006782720796763897 2023-01-23 13:40:02.653073: step: 1574/1545, loss: 0.002166270511224866 2023-01-23 13:40:03.482068: step: 1576/1545, loss: 0.26494747400283813 2023-01-23 13:40:04.349476: step: 1578/1545, loss: 0.0046777245588600636 2023-01-23 13:40:05.195292: step: 1580/1545, loss: 0.053408440202474594 2023-01-23 13:40:06.044991: step: 1582/1545, loss: 0.02878699079155922 2023-01-23 13:40:06.887027: step: 1584/1545, loss: 0.10449595004320145 2023-01-23 13:40:07.755909: step: 1586/1545, loss: 0.0004595475329551846 2023-01-23 13:40:08.628109: step: 1588/1545, loss: 0.07039389759302139 2023-01-23 13:40:09.507407: step: 1590/1545, loss: 0.005211556330323219 2023-01-23 13:40:10.409453: step: 1592/1545, loss: 0.062331944704055786 2023-01-23 13:40:11.308905: step: 1594/1545, loss: 0.00016591700841672719 2023-01-23 13:40:12.186288: step: 1596/1545, loss: 0.0002552331134211272 2023-01-23 13:40:13.055332: step: 1598/1545, loss: 0.09663044661283493 2023-01-23 13:40:13.899475: step: 1600/1545, loss: 0.012728669680655003 2023-01-23 13:40:14.790916: step: 1602/1545, loss: 0.010665172711014748 2023-01-23 13:40:15.655331: step: 1604/1545, loss: 0.06236628443002701 2023-01-23 13:40:16.557739: step: 1606/1545, loss: 0.024595528841018677 2023-01-23 13:40:17.431776: step: 1608/1545, loss: 0.40151506662368774 2023-01-23 13:40:18.321303: step: 1610/1545, loss: 0.050317224115133286 2023-01-23 13:40:19.183700: step: 1612/1545, loss: 0.009731716476380825 2023-01-23 13:40:20.059817: step: 1614/1545, loss: 0.0008307616226375103 2023-01-23 13:40:20.949220: step: 1616/1545, loss: 0.15709277987480164 2023-01-23 13:40:21.847609: step: 1618/1545, loss: 0.38279494643211365 2023-01-23 13:40:22.688444: step: 1620/1545, loss: 0.011761673726141453 2023-01-23 13:40:23.552865: step: 1622/1545, loss: 0.14675918221473694 2023-01-23 13:40:24.483453: step: 1624/1545, loss: 0.18057666718959808 2023-01-23 13:40:25.356351: step: 1626/1545, loss: 0.3852476179599762 2023-01-23 13:40:26.237397: step: 1628/1545, loss: 0.3716084659099579 2023-01-23 13:40:27.124039: step: 1630/1545, loss: 0.08276443928480148 2023-01-23 13:40:28.062890: step: 1632/1545, loss: 0.042704466730356216 2023-01-23 13:40:28.989475: step: 1634/1545, loss: 0.07786080986261368 2023-01-23 13:40:29.860386: step: 1636/1545, loss: 0.24171359837055206 2023-01-23 13:40:30.722275: step: 1638/1545, loss: 0.20285649597644806 2023-01-23 13:40:31.569703: step: 1640/1545, loss: 0.05695163458585739 2023-01-23 13:40:32.449201: step: 1642/1545, loss: 0.330179363489151 2023-01-23 13:40:33.501576: step: 1644/1545, loss: 0.07158263027667999 2023-01-23 13:40:34.399000: step: 1646/1545, loss: 0.002725672209635377 2023-01-23 13:40:35.281734: step: 1648/1545, loss: 0.157719224691391 2023-01-23 13:40:36.197369: step: 1650/1545, loss: 0.1344614028930664 2023-01-23 13:40:37.052061: step: 1652/1545, loss: 0.39401257038116455 2023-01-23 13:40:37.976620: step: 1654/1545, loss: 0.06637701392173767 2023-01-23 13:40:38.848643: step: 1656/1545, loss: 0.0067442841827869415 2023-01-23 13:40:39.739152: step: 1658/1545, loss: 0.04401908442378044 2023-01-23 13:40:40.620226: step: 1660/1545, loss: 0.20287682116031647 2023-01-23 13:40:41.494214: step: 1662/1545, loss: 0.036231569945812225 2023-01-23 13:40:42.337555: step: 1664/1545, loss: 0.29381152987480164 2023-01-23 13:40:43.212962: step: 1666/1545, loss: 0.0005605906480923295 2023-01-23 13:40:44.090203: step: 1668/1545, loss: 0.012536908499896526 2023-01-23 13:40:44.941778: step: 1670/1545, loss: 0.09666947275400162 2023-01-23 13:40:45.862058: step: 1672/1545, loss: 0.03635646775364876 2023-01-23 13:40:46.741512: step: 1674/1545, loss: 0.004288774915039539 2023-01-23 13:40:47.641481: step: 1676/1545, loss: 0.08267124742269516 2023-01-23 13:40:48.524461: step: 1678/1545, loss: 0.007495211437344551 2023-01-23 13:40:49.390866: step: 1680/1545, loss: 0.1095835492014885 2023-01-23 13:40:50.234062: step: 1682/1545, loss: 0.26761025190353394 2023-01-23 13:40:51.094479: step: 1684/1545, loss: 0.018890058621764183 2023-01-23 13:40:51.969211: step: 1686/1545, loss: 0.01995854265987873 2023-01-23 13:40:52.834712: step: 1688/1545, loss: 0.022508947178721428 2023-01-23 13:40:53.681499: step: 1690/1545, loss: 0.005524098873138428 2023-01-23 13:40:54.644997: step: 1692/1545, loss: 0.057479605078697205 2023-01-23 13:40:55.519073: step: 1694/1545, loss: 0.23823051154613495 2023-01-23 13:40:56.391538: step: 1696/1545, loss: 0.4021720886230469 2023-01-23 13:40:57.274184: step: 1698/1545, loss: 0.06736521422863007 2023-01-23 13:40:58.156468: step: 1700/1545, loss: 0.06894388049840927 2023-01-23 13:40:58.995058: step: 1702/1545, loss: 0.40011706948280334 2023-01-23 13:40:59.896463: step: 1704/1545, loss: 0.10772256553173065 2023-01-23 13:41:00.803490: step: 1706/1545, loss: 0.04236388951539993 2023-01-23 13:41:01.722758: step: 1708/1545, loss: 0.04339734464883804 2023-01-23 13:41:02.566576: step: 1710/1545, loss: 0.026496773585677147 2023-01-23 13:41:03.530833: step: 1712/1545, loss: 0.01932639069855213 2023-01-23 13:41:04.495272: step: 1714/1545, loss: 0.042292363941669464 2023-01-23 13:41:05.407092: step: 1716/1545, loss: 0.04015856608748436 2023-01-23 13:41:06.313497: step: 1718/1545, loss: 0.5622345209121704 2023-01-23 13:41:07.262257: step: 1720/1545, loss: 0.17515255510807037 2023-01-23 13:41:08.134393: step: 1722/1545, loss: 0.005442575551569462 2023-01-23 13:41:09.017139: step: 1724/1545, loss: 0.22569698095321655 2023-01-23 13:41:09.879247: step: 1726/1545, loss: 0.2224237024784088 2023-01-23 13:41:10.757095: step: 1728/1545, loss: 0.04302852600812912 2023-01-23 13:41:11.638907: step: 1730/1545, loss: 0.1401865929365158 2023-01-23 13:41:12.473777: step: 1732/1545, loss: 0.09679612517356873 2023-01-23 13:41:13.316353: step: 1734/1545, loss: 0.0867592990398407 2023-01-23 13:41:14.165965: step: 1736/1545, loss: 0.029059182852506638 2023-01-23 13:41:15.055024: step: 1738/1545, loss: 0.18996484577655792 2023-01-23 13:41:15.941727: step: 1740/1545, loss: 0.010530021972954273 2023-01-23 13:41:16.889459: step: 1742/1545, loss: 0.12895455956459045 2023-01-23 13:41:17.785974: step: 1744/1545, loss: 0.004876517225056887 2023-01-23 13:41:18.686230: step: 1746/1545, loss: 0.09680774062871933 2023-01-23 13:41:19.540481: step: 1748/1545, loss: 0.006018714513629675 2023-01-23 13:41:20.476369: step: 1750/1545, loss: 0.016464587301015854 2023-01-23 13:41:21.329422: step: 1752/1545, loss: 0.01763707585632801 2023-01-23 13:41:22.159181: step: 1754/1545, loss: 0.01426532119512558 2023-01-23 13:41:23.006441: step: 1756/1545, loss: 0.03710734099149704 2023-01-23 13:41:23.922347: step: 1758/1545, loss: 0.04581106826663017 2023-01-23 13:41:24.818265: step: 1760/1545, loss: 0.18494930863380432 2023-01-23 13:41:25.688589: step: 1762/1545, loss: 0.3721454441547394 2023-01-23 13:41:26.529360: step: 1764/1545, loss: 0.004317695274949074 2023-01-23 13:41:27.425253: step: 1766/1545, loss: 0.003971152473241091 2023-01-23 13:41:28.295472: step: 1768/1545, loss: 0.09303046762943268 2023-01-23 13:41:29.211345: step: 1770/1545, loss: 0.28091248869895935 2023-01-23 13:41:30.093844: step: 1772/1545, loss: 0.3714624047279358 2023-01-23 13:41:30.988789: step: 1774/1545, loss: 0.006296433042734861 2023-01-23 13:41:31.918221: step: 1776/1545, loss: 0.021075457334518433 2023-01-23 13:41:32.777359: step: 1778/1545, loss: 0.0001280365395359695 2023-01-23 13:41:33.597350: step: 1780/1545, loss: 0.004666606429964304 2023-01-23 13:41:34.574602: step: 1782/1545, loss: 0.12300333380699158 2023-01-23 13:41:35.431680: step: 1784/1545, loss: 0.0015433698426932096 2023-01-23 13:41:36.294544: step: 1786/1545, loss: 0.0007866728701628745 2023-01-23 13:41:37.134658: step: 1788/1545, loss: 0.0034767736215144396 2023-01-23 13:41:37.967333: step: 1790/1545, loss: 0.5922822952270508 2023-01-23 13:41:38.821310: step: 1792/1545, loss: 0.5076384544372559 2023-01-23 13:41:39.682695: step: 1794/1545, loss: 1.431281328201294 2023-01-23 13:41:40.605052: step: 1796/1545, loss: 0.5367557406425476 2023-01-23 13:41:41.476312: step: 1798/1545, loss: 0.10604672133922577 2023-01-23 13:41:42.322898: step: 1800/1545, loss: 0.10073263943195343 2023-01-23 13:41:43.271405: step: 1802/1545, loss: 0.008700037375092506 2023-01-23 13:41:44.129355: step: 1804/1545, loss: 0.1275138407945633 2023-01-23 13:41:45.006471: step: 1806/1545, loss: 0.005859826225787401 2023-01-23 13:41:45.877808: step: 1808/1545, loss: 0.005622560158371925 2023-01-23 13:41:46.793244: step: 1810/1545, loss: 0.03578512370586395 2023-01-23 13:41:47.654415: step: 1812/1545, loss: 0.0172642320394516 2023-01-23 13:41:48.510471: step: 1814/1545, loss: 1.2967671155929565 2023-01-23 13:41:49.386711: step: 1816/1545, loss: 0.009965376928448677 2023-01-23 13:41:50.345382: step: 1818/1545, loss: 0.2749905288219452 2023-01-23 13:41:51.196956: step: 1820/1545, loss: 0.0012208892730996013 2023-01-23 13:41:52.100282: step: 1822/1545, loss: 0.005108315031975508 2023-01-23 13:41:52.956115: step: 1824/1545, loss: 0.023992009460926056 2023-01-23 13:41:53.808330: step: 1826/1545, loss: 0.02382383495569229 2023-01-23 13:41:54.725014: step: 1828/1545, loss: 0.0009517750586383045 2023-01-23 13:41:55.608708: step: 1830/1545, loss: 0.03893052414059639 2023-01-23 13:41:56.472087: step: 1832/1545, loss: 0.008331318385899067 2023-01-23 13:41:57.318584: step: 1834/1545, loss: 0.1740521937608719 2023-01-23 13:41:58.199768: step: 1836/1545, loss: 0.22971194982528687 2023-01-23 13:41:59.083709: step: 1838/1545, loss: 0.06453844904899597 2023-01-23 13:41:59.996560: step: 1840/1545, loss: 0.0297554824501276 2023-01-23 13:42:00.862974: step: 1842/1545, loss: 0.00636899983510375 2023-01-23 13:42:01.767839: step: 1844/1545, loss: 0.03281479328870773 2023-01-23 13:42:02.639134: step: 1846/1545, loss: 0.01718801073729992 2023-01-23 13:42:03.565252: step: 1848/1545, loss: 0.027350790798664093 2023-01-23 13:42:04.437304: step: 1850/1545, loss: 0.3410366475582123 2023-01-23 13:42:05.307661: step: 1852/1545, loss: 0.011662274599075317 2023-01-23 13:42:06.194290: step: 1854/1545, loss: 0.012285672128200531 2023-01-23 13:42:07.072306: step: 1856/1545, loss: 0.0068468255922198296 2023-01-23 13:42:07.993983: step: 1858/1545, loss: 0.003912740387022495 2023-01-23 13:42:08.902205: step: 1860/1545, loss: 0.004100012592971325 2023-01-23 13:42:09.772093: step: 1862/1545, loss: 0.03164199739694595 2023-01-23 13:42:10.662085: step: 1864/1545, loss: 0.004978488199412823 2023-01-23 13:42:11.544714: step: 1866/1545, loss: 0.013854514807462692 2023-01-23 13:42:12.445618: step: 1868/1545, loss: 0.047637153416872025 2023-01-23 13:42:13.341143: step: 1870/1545, loss: 0.002453007735311985 2023-01-23 13:42:14.197253: step: 1872/1545, loss: 0.34551385045051575 2023-01-23 13:42:15.128012: step: 1874/1545, loss: 0.00956020038574934 2023-01-23 13:42:16.064044: step: 1876/1545, loss: 0.04206402227282524 2023-01-23 13:42:16.922557: step: 1878/1545, loss: 0.025599049404263496 2023-01-23 13:42:17.788677: step: 1880/1545, loss: 0.5441029667854309 2023-01-23 13:42:18.673416: step: 1882/1545, loss: 0.027981873601675034 2023-01-23 13:42:19.528865: step: 1884/1545, loss: 0.018916122615337372 2023-01-23 13:42:20.380093: step: 1886/1545, loss: 0.0006448610802181065 2023-01-23 13:42:21.273158: step: 1888/1545, loss: 0.14599639177322388 2023-01-23 13:42:22.156492: step: 1890/1545, loss: 0.32460057735443115 2023-01-23 13:42:23.048866: step: 1892/1545, loss: 0.044341012835502625 2023-01-23 13:42:23.920781: step: 1894/1545, loss: 0.0019181570969522 2023-01-23 13:42:24.810202: step: 1896/1545, loss: 0.015987863764166832 2023-01-23 13:42:25.742075: step: 1898/1545, loss: 0.21698805689811707 2023-01-23 13:42:26.617146: step: 1900/1545, loss: 0.023215938359498978 2023-01-23 13:42:27.426701: step: 1902/1545, loss: 0.00017046628636308014 2023-01-23 13:42:28.259417: step: 1904/1545, loss: 0.0020722595509141684 2023-01-23 13:42:29.110676: step: 1906/1545, loss: 0.0008803256787359715 2023-01-23 13:42:30.015777: step: 1908/1545, loss: 0.03882297873497009 2023-01-23 13:42:30.888086: step: 1910/1545, loss: 0.09680664539337158 2023-01-23 13:42:31.865944: step: 1912/1545, loss: 0.001705906935967505 2023-01-23 13:42:32.770403: step: 1914/1545, loss: 0.23338870704174042 2023-01-23 13:42:33.625987: step: 1916/1545, loss: 0.03172925114631653 2023-01-23 13:42:34.560151: step: 1918/1545, loss: 0.0039181155152618885 2023-01-23 13:42:35.445139: step: 1920/1545, loss: 0.03463693708181381 2023-01-23 13:42:36.315478: step: 1922/1545, loss: 0.0018527130596339703 2023-01-23 13:42:37.207909: step: 1924/1545, loss: 0.07766202092170715 2023-01-23 13:42:38.096943: step: 1926/1545, loss: 0.035746823996305466 2023-01-23 13:42:38.982358: step: 1928/1545, loss: 0.023423947393894196 2023-01-23 13:42:39.848692: step: 1930/1545, loss: 0.0471302755177021 2023-01-23 13:42:40.705672: step: 1932/1545, loss: 0.005560705903917551 2023-01-23 13:42:41.549437: step: 1934/1545, loss: 0.13036851584911346 2023-01-23 13:42:42.399078: step: 1936/1545, loss: 0.14645346999168396 2023-01-23 13:42:43.265962: step: 1938/1545, loss: 0.03150862827897072 2023-01-23 13:42:44.141509: step: 1940/1545, loss: 0.13041183352470398 2023-01-23 13:42:45.061908: step: 1942/1545, loss: 0.08463330566883087 2023-01-23 13:42:45.945513: step: 1944/1545, loss: 0.7444267272949219 2023-01-23 13:42:46.875920: step: 1946/1545, loss: 0.35097435116767883 2023-01-23 13:42:47.804980: step: 1948/1545, loss: 0.1838851422071457 2023-01-23 13:42:48.704291: step: 1950/1545, loss: 0.010765316896140575 2023-01-23 13:42:49.631434: step: 1952/1545, loss: 0.020046161487698555 2023-01-23 13:42:50.493153: step: 1954/1545, loss: 0.08549130707979202 2023-01-23 13:42:51.381956: step: 1956/1545, loss: 0.02868669107556343 2023-01-23 13:42:52.289844: step: 1958/1545, loss: 0.01036830898374319 2023-01-23 13:42:53.221296: step: 1960/1545, loss: 0.3297775983810425 2023-01-23 13:42:54.109556: step: 1962/1545, loss: 0.9663916826248169 2023-01-23 13:42:54.926766: step: 1964/1545, loss: 0.0294460691511631 2023-01-23 13:42:55.771117: step: 1966/1545, loss: 0.042279455810785294 2023-01-23 13:42:56.673163: step: 1968/1545, loss: 0.004017269238829613 2023-01-23 13:42:57.542093: step: 1970/1545, loss: 0.014274358749389648 2023-01-23 13:42:58.484515: step: 1972/1545, loss: 0.03111100383102894 2023-01-23 13:42:59.308802: step: 1974/1545, loss: 0.007862888276576996 2023-01-23 13:43:00.175038: step: 1976/1545, loss: 0.04306182637810707 2023-01-23 13:43:01.036174: step: 1978/1545, loss: 0.29662665724754333 2023-01-23 13:43:01.922620: step: 1980/1545, loss: 0.019898787140846252 2023-01-23 13:43:02.810976: step: 1982/1545, loss: 0.034781571477651596 2023-01-23 13:43:03.670387: step: 1984/1545, loss: 0.29716813564300537 2023-01-23 13:43:04.548020: step: 1986/1545, loss: 0.016297388821840286 2023-01-23 13:43:05.406960: step: 1988/1545, loss: 0.02349925972521305 2023-01-23 13:43:06.237362: step: 1990/1545, loss: 0.12339695543050766 2023-01-23 13:43:07.163423: step: 1992/1545, loss: 0.06556682288646698 2023-01-23 13:43:08.008089: step: 1994/1545, loss: 0.05298633500933647 2023-01-23 13:43:08.861969: step: 1996/1545, loss: 0.09663720428943634 2023-01-23 13:43:09.755772: step: 1998/1545, loss: 0.007588233333081007 2023-01-23 13:43:10.605149: step: 2000/1545, loss: 0.101793073117733 2023-01-23 13:43:11.512734: step: 2002/1545, loss: 0.041166502982378006 2023-01-23 13:43:12.391634: step: 2004/1545, loss: 0.0034819915890693665 2023-01-23 13:43:13.276686: step: 2006/1545, loss: 0.07108238339424133 2023-01-23 13:43:14.203155: step: 2008/1545, loss: 0.053971223533153534 2023-01-23 13:43:15.058553: step: 2010/1545, loss: 0.016439342871308327 2023-01-23 13:43:15.920754: step: 2012/1545, loss: 0.035312116146087646 2023-01-23 13:43:16.816823: step: 2014/1545, loss: 0.034149330109357834 2023-01-23 13:43:17.663606: step: 2016/1545, loss: 0.053393032401800156 2023-01-23 13:43:18.540085: step: 2018/1545, loss: 0.15361139178276062 2023-01-23 13:43:19.474224: step: 2020/1545, loss: 0.0012486097402870655 2023-01-23 13:43:20.342251: step: 2022/1545, loss: 0.04676424711942673 2023-01-23 13:43:21.215998: step: 2024/1545, loss: 0.025345025584101677 2023-01-23 13:43:22.093601: step: 2026/1545, loss: 0.025063959881663322 2023-01-23 13:43:23.018234: step: 2028/1545, loss: 0.17838263511657715 2023-01-23 13:43:23.905305: step: 2030/1545, loss: 0.02045268937945366 2023-01-23 13:43:24.813350: step: 2032/1545, loss: 0.05237773060798645 2023-01-23 13:43:25.683502: step: 2034/1545, loss: 0.03897827863693237 2023-01-23 13:43:26.555061: step: 2036/1545, loss: 0.6007260084152222 2023-01-23 13:43:27.431062: step: 2038/1545, loss: 0.11557541787624359 2023-01-23 13:43:28.352124: step: 2040/1545, loss: 0.30904051661491394 2023-01-23 13:43:29.229578: step: 2042/1545, loss: 0.011426486074924469 2023-01-23 13:43:30.099260: step: 2044/1545, loss: 0.011835605837404728 2023-01-23 13:43:30.971780: step: 2046/1545, loss: 0.05048536881804466 2023-01-23 13:43:31.822470: step: 2048/1545, loss: 0.042969245463609695 2023-01-23 13:43:32.708486: step: 2050/1545, loss: 0.05504646897315979 2023-01-23 13:43:33.700356: step: 2052/1545, loss: 0.017225801944732666 2023-01-23 13:43:34.566322: step: 2054/1545, loss: 0.03692407160997391 2023-01-23 13:43:35.450432: step: 2056/1545, loss: 0.16985109448432922 2023-01-23 13:43:36.316410: step: 2058/1545, loss: 0.001771486597135663 2023-01-23 13:43:37.194168: step: 2060/1545, loss: 0.012888745404779911 2023-01-23 13:43:38.032485: step: 2062/1545, loss: 0.3836192488670349 2023-01-23 13:43:38.937981: step: 2064/1545, loss: 0.1408078670501709 2023-01-23 13:43:39.876754: step: 2066/1545, loss: 0.012900246307253838 2023-01-23 13:43:40.750375: step: 2068/1545, loss: 0.0013902769424021244 2023-01-23 13:43:41.608764: step: 2070/1545, loss: 0.01142410933971405 2023-01-23 13:43:42.461621: step: 2072/1545, loss: 0.013754162937402725 2023-01-23 13:43:43.366160: step: 2074/1545, loss: 0.3547190725803375 2023-01-23 13:43:44.215517: step: 2076/1545, loss: 0.008927219547331333 2023-01-23 13:43:45.086780: step: 2078/1545, loss: 0.013018381781876087 2023-01-23 13:43:45.972886: step: 2080/1545, loss: 2.4844837188720703 2023-01-23 13:43:46.818560: step: 2082/1545, loss: 0.049457330256700516 2023-01-23 13:43:47.736781: step: 2084/1545, loss: 0.0078005921095609665 2023-01-23 13:43:48.671379: step: 2086/1545, loss: 0.044808387756347656 2023-01-23 13:43:49.636029: step: 2088/1545, loss: 0.04512647166848183 2023-01-23 13:43:50.499560: step: 2090/1545, loss: 0.06270614266395569 2023-01-23 13:43:51.327088: step: 2092/1545, loss: 0.0010300814174115658 2023-01-23 13:43:52.216355: step: 2094/1545, loss: 0.11118075251579285 2023-01-23 13:43:53.115890: step: 2096/1545, loss: 0.15837441384792328 2023-01-23 13:43:54.015053: step: 2098/1545, loss: 0.008162172511219978 2023-01-23 13:43:54.839355: step: 2100/1545, loss: 0.25419291853904724 2023-01-23 13:43:55.794051: step: 2102/1545, loss: 0.1333206743001938 2023-01-23 13:43:56.730689: step: 2104/1545, loss: 0.3218664228916168 2023-01-23 13:43:57.611786: step: 2106/1545, loss: 0.03041442483663559 2023-01-23 13:43:58.545937: step: 2108/1545, loss: 0.6093789339065552 2023-01-23 13:43:59.429621: step: 2110/1545, loss: 0.03837853670120239 2023-01-23 13:44:00.295108: step: 2112/1545, loss: 0.013818424195051193 2023-01-23 13:44:01.219220: step: 2114/1545, loss: 0.015520762652158737 2023-01-23 13:44:02.055868: step: 2116/1545, loss: 0.07442688941955566 2023-01-23 13:44:02.905533: step: 2118/1545, loss: 0.08375895023345947 2023-01-23 13:44:03.794902: step: 2120/1545, loss: 0.016572505235671997 2023-01-23 13:44:04.698882: step: 2122/1545, loss: 0.005542802158743143 2023-01-23 13:44:05.554822: step: 2124/1545, loss: 0.15689925849437714 2023-01-23 13:44:06.468166: step: 2126/1545, loss: 0.10357040166854858 2023-01-23 13:44:07.340216: step: 2128/1545, loss: 0.2065354585647583 2023-01-23 13:44:08.226325: step: 2130/1545, loss: 0.013671522960066795 2023-01-23 13:44:09.143443: step: 2132/1545, loss: 0.009766748175024986 2023-01-23 13:44:10.029930: step: 2134/1545, loss: 0.02567741461098194 2023-01-23 13:44:10.870582: step: 2136/1545, loss: 0.07142460346221924 2023-01-23 13:44:11.756865: step: 2138/1545, loss: 0.049754854291677475 2023-01-23 13:44:12.662890: step: 2140/1545, loss: 0.03999297693371773 2023-01-23 13:44:13.532761: step: 2142/1545, loss: 0.12603728473186493 2023-01-23 13:44:14.387789: step: 2144/1545, loss: 0.0005689080571755767 2023-01-23 13:44:15.287082: step: 2146/1545, loss: 0.10157179832458496 2023-01-23 13:44:16.212249: step: 2148/1545, loss: 0.007400042377412319 2023-01-23 13:44:17.068387: step: 2150/1545, loss: 0.11774490028619766 2023-01-23 13:44:17.959469: step: 2152/1545, loss: 0.018163658678531647 2023-01-23 13:44:18.811146: step: 2154/1545, loss: 0.002338084392249584 2023-01-23 13:44:19.712447: step: 2156/1545, loss: 0.2620995342731476 2023-01-23 13:44:20.609145: step: 2158/1545, loss: 0.027196675539016724 2023-01-23 13:44:21.507192: step: 2160/1545, loss: 0.0006594287697225809 2023-01-23 13:44:22.349847: step: 2162/1545, loss: 0.11802703142166138 2023-01-23 13:44:23.192912: step: 2164/1545, loss: 0.007959785871207714 2023-01-23 13:44:24.052480: step: 2166/1545, loss: 0.036216046661138535 2023-01-23 13:44:24.963310: step: 2168/1545, loss: 0.009568820707499981 2023-01-23 13:44:25.852142: step: 2170/1545, loss: 0.028206825256347656 2023-01-23 13:44:26.702373: step: 2172/1545, loss: 0.08059932291507721 2023-01-23 13:44:27.599153: step: 2174/1545, loss: 0.0033019164111465216 2023-01-23 13:44:28.467199: step: 2176/1545, loss: 0.017199836671352386 2023-01-23 13:44:29.334141: step: 2178/1545, loss: 0.014978011138737202 2023-01-23 13:44:30.184415: step: 2180/1545, loss: 0.04359797015786171 2023-01-23 13:44:31.100095: step: 2182/1545, loss: 0.00018332114268559963 2023-01-23 13:44:31.940105: step: 2184/1545, loss: 0.45032525062561035 2023-01-23 13:44:32.813190: step: 2186/1545, loss: 0.005348581820726395 2023-01-23 13:44:33.648773: step: 2188/1545, loss: 0.33294177055358887 2023-01-23 13:44:34.524498: step: 2190/1545, loss: 0.4359767436981201 2023-01-23 13:44:35.368068: step: 2192/1545, loss: 0.27465689182281494 2023-01-23 13:44:36.230318: step: 2194/1545, loss: 0.03691966086626053 2023-01-23 13:44:37.120495: step: 2196/1545, loss: 0.06406861543655396 2023-01-23 13:44:38.058619: step: 2198/1545, loss: 0.12999652326107025 2023-01-23 13:44:38.933593: step: 2200/1545, loss: 0.006251477636396885 2023-01-23 13:44:39.863704: step: 2202/1545, loss: 0.00849810428917408 2023-01-23 13:44:40.751494: step: 2204/1545, loss: 0.016735808923840523 2023-01-23 13:44:41.598798: step: 2206/1545, loss: 0.0032980868127197027 2023-01-23 13:44:42.509479: step: 2208/1545, loss: 0.27320751547813416 2023-01-23 13:44:43.438617: step: 2210/1545, loss: 0.018884312361478806 2023-01-23 13:44:44.321896: step: 2212/1545, loss: 0.10225042700767517 2023-01-23 13:44:45.142504: step: 2214/1545, loss: 0.24891269207000732 2023-01-23 13:44:46.064236: step: 2216/1545, loss: 0.32768478989601135 2023-01-23 13:44:46.955051: step: 2218/1545, loss: 0.15789665281772614 2023-01-23 13:44:47.849782: step: 2220/1545, loss: 0.09484705328941345 2023-01-23 13:44:48.734245: step: 2222/1545, loss: 0.19681543111801147 2023-01-23 13:44:49.651725: step: 2224/1545, loss: 0.00508279912173748 2023-01-23 13:44:50.543012: step: 2226/1545, loss: 0.0029632155783474445 2023-01-23 13:44:51.414816: step: 2228/1545, loss: 0.027453532442450523 2023-01-23 13:44:52.368304: step: 2230/1545, loss: 0.17593322694301605 2023-01-23 13:44:53.226818: step: 2232/1545, loss: 0.06728652119636536 2023-01-23 13:44:54.129171: step: 2234/1545, loss: 0.041957832872867584 2023-01-23 13:44:55.004728: step: 2236/1545, loss: 0.10347040742635727 2023-01-23 13:44:55.864245: step: 2238/1545, loss: 0.016798336058855057 2023-01-23 13:44:56.744932: step: 2240/1545, loss: 0.0869031473994255 2023-01-23 13:44:57.596915: step: 2242/1545, loss: 0.0327749028801918 2023-01-23 13:44:58.472214: step: 2244/1545, loss: 0.09920006990432739 2023-01-23 13:44:59.442024: step: 2246/1545, loss: 0.0056516737677156925 2023-01-23 13:45:00.309720: step: 2248/1545, loss: 0.06324351578950882 2023-01-23 13:45:01.178090: step: 2250/1545, loss: 0.04067203402519226 2023-01-23 13:45:02.151086: step: 2252/1545, loss: 0.03600963205099106 2023-01-23 13:45:03.032187: step: 2254/1545, loss: 0.014802669174969196 2023-01-23 13:45:03.869502: step: 2256/1545, loss: 0.026670416817069054 2023-01-23 13:45:04.752903: step: 2258/1545, loss: 0.5272388458251953 2023-01-23 13:45:05.594630: step: 2260/1545, loss: 0.0509989857673645 2023-01-23 13:45:06.485035: step: 2262/1545, loss: 0.023874102160334587 2023-01-23 13:45:07.370035: step: 2264/1545, loss: 0.1112552136182785 2023-01-23 13:45:08.240814: step: 2266/1545, loss: 0.09415091574192047 2023-01-23 13:45:09.159544: step: 2268/1545, loss: 0.018269773572683334 2023-01-23 13:45:10.072014: step: 2270/1545, loss: 0.10283433645963669 2023-01-23 13:45:10.943271: step: 2272/1545, loss: 0.0035943114198744297 2023-01-23 13:45:11.786538: step: 2274/1545, loss: 0.004765961319208145 2023-01-23 13:45:12.767878: step: 2276/1545, loss: 0.007592746987938881 2023-01-23 13:45:13.620177: step: 2278/1545, loss: 0.34672534465789795 2023-01-23 13:45:14.467253: step: 2280/1545, loss: 0.01943371631205082 2023-01-23 13:45:15.344082: step: 2282/1545, loss: 0.16799889504909515 2023-01-23 13:45:16.218124: step: 2284/1545, loss: 0.03427920117974281 2023-01-23 13:45:17.063453: step: 2286/1545, loss: 0.03379308059811592 2023-01-23 13:45:17.993861: step: 2288/1545, loss: 0.2815430760383606 2023-01-23 13:45:18.846449: step: 2290/1545, loss: 0.2296915352344513 2023-01-23 13:45:19.737717: step: 2292/1545, loss: 0.07423171401023865 2023-01-23 13:45:20.662408: step: 2294/1545, loss: 0.0015469106147065759 2023-01-23 13:45:21.562978: step: 2296/1545, loss: 0.01747206412255764 2023-01-23 13:45:22.431102: step: 2298/1545, loss: 0.013265511952340603 2023-01-23 13:45:23.271252: step: 2300/1545, loss: 0.0024718770291656256 2023-01-23 13:45:24.152526: step: 2302/1545, loss: 0.08037129789590836 2023-01-23 13:45:25.021641: step: 2304/1545, loss: 0.01503837388008833 2023-01-23 13:45:25.928780: step: 2306/1545, loss: 0.07518334686756134 2023-01-23 13:45:26.841438: step: 2308/1545, loss: 0.05800286680459976 2023-01-23 13:45:27.645833: step: 2310/1545, loss: 0.010358483530580997 2023-01-23 13:45:28.530375: step: 2312/1545, loss: 0.0020420802757143974 2023-01-23 13:45:29.413464: step: 2314/1545, loss: 0.046383313834667206 2023-01-23 13:45:30.267726: step: 2316/1545, loss: 0.030331367626786232 2023-01-23 13:45:31.191920: step: 2318/1545, loss: 0.008132409304380417 2023-01-23 13:45:32.057889: step: 2320/1545, loss: 0.03272414952516556 2023-01-23 13:45:32.899206: step: 2322/1545, loss: 0.10752177983522415 2023-01-23 13:45:33.801205: step: 2324/1545, loss: 0.015808578580617905 2023-01-23 13:45:34.662609: step: 2326/1545, loss: 0.07826986163854599 2023-01-23 13:45:35.560745: step: 2328/1545, loss: 0.15786795318126678 2023-01-23 13:45:36.483818: step: 2330/1545, loss: 0.03220449388027191 2023-01-23 13:45:37.346414: step: 2332/1545, loss: 0.2787659168243408 2023-01-23 13:45:38.230916: step: 2334/1545, loss: 0.15780939161777496 2023-01-23 13:45:39.088722: step: 2336/1545, loss: 0.023333081975579262 2023-01-23 13:45:39.969664: step: 2338/1545, loss: 0.09590251743793488 2023-01-23 13:45:40.846332: step: 2340/1545, loss: 0.05329360067844391 2023-01-23 13:45:41.734861: step: 2342/1545, loss: 0.17417101562023163 2023-01-23 13:45:42.620977: step: 2344/1545, loss: 0.005766158923506737 2023-01-23 13:45:43.480053: step: 2346/1545, loss: 0.0017581938300281763 2023-01-23 13:45:44.386607: step: 2348/1545, loss: 0.15045718848705292 2023-01-23 13:45:45.279183: step: 2350/1545, loss: 0.013391364365816116 2023-01-23 13:45:46.175878: step: 2352/1545, loss: 0.05691881477832794 2023-01-23 13:45:47.015672: step: 2354/1545, loss: 0.007735930848866701 2023-01-23 13:45:47.932809: step: 2356/1545, loss: 0.03847324475646019 2023-01-23 13:45:48.880354: step: 2358/1545, loss: 0.27998656034469604 2023-01-23 13:45:49.781201: step: 2360/1545, loss: 0.007418711204081774 2023-01-23 13:45:50.666453: step: 2362/1545, loss: 0.049309078603982925 2023-01-23 13:45:51.615621: step: 2364/1545, loss: 0.03000272437930107 2023-01-23 13:45:52.478594: step: 2366/1545, loss: 0.13594283163547516 2023-01-23 13:45:53.374434: step: 2368/1545, loss: 0.009468290954828262 2023-01-23 13:45:54.243620: step: 2370/1545, loss: 0.09476244449615479 2023-01-23 13:45:55.162300: step: 2372/1545, loss: 0.051424045115709305 2023-01-23 13:45:56.037128: step: 2374/1545, loss: 0.007201865781098604 2023-01-23 13:45:56.847674: step: 2376/1545, loss: 1.5250672101974487 2023-01-23 13:45:57.678374: step: 2378/1545, loss: 0.0251265037804842 2023-01-23 13:45:58.534023: step: 2380/1545, loss: 0.023376813158392906 2023-01-23 13:45:59.387006: step: 2382/1545, loss: 0.012765630148351192 2023-01-23 13:46:00.236049: step: 2384/1545, loss: 0.0039000725373625755 2023-01-23 13:46:01.123167: step: 2386/1545, loss: 0.5222256779670715 2023-01-23 13:46:02.005528: step: 2388/1545, loss: 0.004992946051061153 2023-01-23 13:46:02.923458: step: 2390/1545, loss: 0.15991128981113434 2023-01-23 13:46:03.822748: step: 2392/1545, loss: 0.003354474902153015 2023-01-23 13:46:04.659451: step: 2394/1545, loss: 0.030418826267123222 2023-01-23 13:46:05.528659: step: 2396/1545, loss: 0.0192592553794384 2023-01-23 13:46:06.414391: step: 2398/1545, loss: 0.8662895560264587 2023-01-23 13:46:07.274814: step: 2400/1545, loss: 0.36847391724586487 2023-01-23 13:46:08.138654: step: 2402/1545, loss: 0.0005380927468650043 2023-01-23 13:46:09.016933: step: 2404/1545, loss: 0.06538938730955124 2023-01-23 13:46:09.865779: step: 2406/1545, loss: 0.08421465009450912 2023-01-23 13:46:10.770575: step: 2408/1545, loss: 0.1068134754896164 2023-01-23 13:46:11.646437: step: 2410/1545, loss: 0.08579778671264648 2023-01-23 13:46:12.498435: step: 2412/1545, loss: 0.0674014613032341 2023-01-23 13:46:13.357914: step: 2414/1545, loss: 0.9761515855789185 2023-01-23 13:46:14.205453: step: 2416/1545, loss: 0.0062265414744615555 2023-01-23 13:46:15.120145: step: 2418/1545, loss: 0.07960625737905502 2023-01-23 13:46:15.984421: step: 2420/1545, loss: 0.2549286484718323 2023-01-23 13:46:16.896364: step: 2422/1545, loss: 0.28766053915023804 2023-01-23 13:46:17.743489: step: 2424/1545, loss: 0.09173360466957092 2023-01-23 13:46:18.657738: step: 2426/1545, loss: 0.44202283024787903 2023-01-23 13:46:19.579247: step: 2428/1545, loss: 0.37288251519203186 2023-01-23 13:46:20.433698: step: 2430/1545, loss: 0.013526936993002892 2023-01-23 13:46:21.374301: step: 2432/1545, loss: 0.19470679759979248 2023-01-23 13:46:22.212476: step: 2434/1545, loss: 0.10132826119661331 2023-01-23 13:46:23.062548: step: 2436/1545, loss: 0.01968850940465927 2023-01-23 13:46:23.865347: step: 2438/1545, loss: 0.014628097414970398 2023-01-23 13:46:24.765624: step: 2440/1545, loss: 0.2103075534105301 2023-01-23 13:46:25.641804: step: 2442/1545, loss: 0.0008243151241913438 2023-01-23 13:46:26.542176: step: 2444/1545, loss: 0.11320583522319794 2023-01-23 13:46:27.415778: step: 2446/1545, loss: 0.04928756505250931 2023-01-23 13:46:28.307533: step: 2448/1545, loss: 0.013172219507396221 2023-01-23 13:46:29.196043: step: 2450/1545, loss: 0.20727287232875824 2023-01-23 13:46:30.104797: step: 2452/1545, loss: 0.00959185790270567 2023-01-23 13:46:30.971060: step: 2454/1545, loss: 0.18119415640830994 2023-01-23 13:46:31.863683: step: 2456/1545, loss: 0.062517911195755 2023-01-23 13:46:32.756397: step: 2458/1545, loss: 0.1623772382736206 2023-01-23 13:46:33.638307: step: 2460/1545, loss: 0.15163099765777588 2023-01-23 13:46:34.504217: step: 2462/1545, loss: 0.1155446469783783 2023-01-23 13:46:35.355927: step: 2464/1545, loss: 0.004263114649802446 2023-01-23 13:46:36.231730: step: 2466/1545, loss: 0.018692079931497574 2023-01-23 13:46:37.113377: step: 2468/1545, loss: 0.09741701930761337 2023-01-23 13:46:38.025813: step: 2470/1545, loss: 0.07093697786331177 2023-01-23 13:46:38.873753: step: 2472/1545, loss: 0.01382878702133894 2023-01-23 13:46:39.769518: step: 2474/1545, loss: 0.0036942705046385527 2023-01-23 13:46:40.624140: step: 2476/1545, loss: 0.0162875484675169 2023-01-23 13:46:41.497347: step: 2478/1545, loss: 0.23460912704467773 2023-01-23 13:46:42.367577: step: 2480/1545, loss: 1.0746709108352661 2023-01-23 13:46:43.259884: step: 2482/1545, loss: 0.002223872346803546 2023-01-23 13:46:44.126219: step: 2484/1545, loss: 0.010822195559740067 2023-01-23 13:46:45.012384: step: 2486/1545, loss: 0.07828790694475174 2023-01-23 13:46:45.956863: step: 2488/1545, loss: 0.7704617977142334 2023-01-23 13:46:46.825637: step: 2490/1545, loss: 0.33044740557670593 2023-01-23 13:46:47.732347: step: 2492/1545, loss: 0.01380449440330267 2023-01-23 13:46:48.639562: step: 2494/1545, loss: 0.1703794151544571 2023-01-23 13:46:49.511095: step: 2496/1545, loss: 0.12495221942663193 2023-01-23 13:46:50.500470: step: 2498/1545, loss: 0.009448138996958733 2023-01-23 13:46:51.428016: step: 2500/1545, loss: 1.1761841773986816 2023-01-23 13:46:52.292831: step: 2502/1545, loss: 0.044696297496557236 2023-01-23 13:46:53.243442: step: 2504/1545, loss: 0.16117914021015167 2023-01-23 13:46:54.148599: step: 2506/1545, loss: 0.053886305540800095 2023-01-23 13:46:55.039695: step: 2508/1545, loss: 0.19038599729537964 2023-01-23 13:46:55.916829: step: 2510/1545, loss: 0.0006482674507424235 2023-01-23 13:46:56.772129: step: 2512/1545, loss: 0.0031615705229341984 2023-01-23 13:46:57.656699: step: 2514/1545, loss: 0.10184020549058914 2023-01-23 13:46:58.535378: step: 2516/1545, loss: 0.1371711939573288 2023-01-23 13:46:59.421349: step: 2518/1545, loss: 0.006836435757577419 2023-01-23 13:47:00.303822: step: 2520/1545, loss: 0.2213049679994583 2023-01-23 13:47:01.149978: step: 2522/1545, loss: 0.12218139320611954 2023-01-23 13:47:02.044841: step: 2524/1545, loss: 0.019666995853185654 2023-01-23 13:47:02.903875: step: 2526/1545, loss: 0.014164194464683533 2023-01-23 13:47:03.852519: step: 2528/1545, loss: 0.04729212820529938 2023-01-23 13:47:04.719160: step: 2530/1545, loss: 0.04666381701827049 2023-01-23 13:47:05.599612: step: 2532/1545, loss: 0.00411170395091176 2023-01-23 13:47:06.480117: step: 2534/1545, loss: 0.15469683706760406 2023-01-23 13:47:07.340621: step: 2536/1545, loss: 0.1841454654932022 2023-01-23 13:47:08.204127: step: 2538/1545, loss: 0.32694894075393677 2023-01-23 13:47:09.046885: step: 2540/1545, loss: 0.08321556448936462 2023-01-23 13:47:09.954853: step: 2542/1545, loss: 0.006703091319650412 2023-01-23 13:47:10.822047: step: 2544/1545, loss: 0.15133801102638245 2023-01-23 13:47:11.700064: step: 2546/1545, loss: 0.1437341868877411 2023-01-23 13:47:12.643847: step: 2548/1545, loss: 0.0027958780992776155 2023-01-23 13:47:13.525862: step: 2550/1545, loss: 0.05275723710656166 2023-01-23 13:47:14.382232: step: 2552/1545, loss: 0.14424332976341248 2023-01-23 13:47:15.247911: step: 2554/1545, loss: 0.2812145948410034 2023-01-23 13:47:16.102716: step: 2556/1545, loss: 0.051405105739831924 2023-01-23 13:47:16.984678: step: 2558/1545, loss: 0.10352115333080292 2023-01-23 13:47:17.892737: step: 2560/1545, loss: 0.059953898191452026 2023-01-23 13:47:18.765988: step: 2562/1545, loss: 0.2977612018585205 2023-01-23 13:47:19.630615: step: 2564/1545, loss: 0.10552520304918289 2023-01-23 13:47:20.468759: step: 2566/1545, loss: 0.02912035956978798 2023-01-23 13:47:21.426903: step: 2568/1545, loss: 0.46886155009269714 2023-01-23 13:47:22.298311: step: 2570/1545, loss: 0.0011160123394802213 2023-01-23 13:47:23.173629: step: 2572/1545, loss: 0.07258332520723343 2023-01-23 13:47:24.110604: step: 2574/1545, loss: 0.07717829942703247 2023-01-23 13:47:25.008865: step: 2576/1545, loss: 0.09625079482793808 2023-01-23 13:47:25.903990: step: 2578/1545, loss: 0.017264770343899727 2023-01-23 13:47:26.760190: step: 2580/1545, loss: 0.0013159334193915129 2023-01-23 13:47:27.597324: step: 2582/1545, loss: 0.09765587002038956 2023-01-23 13:47:28.464467: step: 2584/1545, loss: 0.11289182305335999 2023-01-23 13:47:29.380088: step: 2586/1545, loss: 0.008344870060682297 2023-01-23 13:47:30.290977: step: 2588/1545, loss: 0.07302862405776978 2023-01-23 13:47:31.185910: step: 2590/1545, loss: 0.5533138513565063 2023-01-23 13:47:32.042125: step: 2592/1545, loss: 0.1250770092010498 2023-01-23 13:47:32.921680: step: 2594/1545, loss: 0.10816224664449692 2023-01-23 13:47:33.778574: step: 2596/1545, loss: 0.2352651059627533 2023-01-23 13:47:34.646038: step: 2598/1545, loss: 0.06028171256184578 2023-01-23 13:47:35.522163: step: 2600/1545, loss: 0.10527260601520538 2023-01-23 13:47:36.372960: step: 2602/1545, loss: 0.03915129229426384 2023-01-23 13:47:37.301663: step: 2604/1545, loss: 0.28393062949180603 2023-01-23 13:47:38.191200: step: 2606/1545, loss: 0.23499314486980438 2023-01-23 13:47:39.078433: step: 2608/1545, loss: 0.04642539471387863 2023-01-23 13:47:39.952774: step: 2610/1545, loss: 0.069058358669281 2023-01-23 13:47:40.863075: step: 2612/1545, loss: 0.007115006446838379 2023-01-23 13:47:41.725391: step: 2614/1545, loss: 0.2606674134731293 2023-01-23 13:47:42.611300: step: 2616/1545, loss: 2.230339527130127 2023-01-23 13:47:43.464491: step: 2618/1545, loss: 0.029580529779195786 2023-01-23 13:47:44.379404: step: 2620/1545, loss: 0.02596789225935936 2023-01-23 13:47:45.289726: step: 2622/1545, loss: 0.009135592728853226 2023-01-23 13:47:46.220374: step: 2624/1545, loss: 0.022378504276275635 2023-01-23 13:47:47.110793: step: 2626/1545, loss: 0.006605867296457291 2023-01-23 13:47:47.990829: step: 2628/1545, loss: 0.07805205881595612 2023-01-23 13:47:48.849329: step: 2630/1545, loss: 0.0016307999612763524 2023-01-23 13:47:49.770170: step: 2632/1545, loss: 0.1876009851694107 2023-01-23 13:47:50.658906: step: 2634/1545, loss: 0.026871057227253914 2023-01-23 13:47:51.522760: step: 2636/1545, loss: 0.004656893201172352 2023-01-23 13:47:52.415094: step: 2638/1545, loss: 0.025896038860082626 2023-01-23 13:47:53.431769: step: 2640/1545, loss: 0.26127901673316956 2023-01-23 13:47:54.306482: step: 2642/1545, loss: 0.031581465154886246 2023-01-23 13:47:55.191142: step: 2644/1545, loss: 0.008684775792062283 2023-01-23 13:47:56.124052: step: 2646/1545, loss: 0.006881400942802429 2023-01-23 13:47:56.992459: step: 2648/1545, loss: 0.2976956069469452 2023-01-23 13:47:57.877521: step: 2650/1545, loss: 0.023056354373693466 2023-01-23 13:47:58.702719: step: 2652/1545, loss: 0.13465164601802826 2023-01-23 13:47:59.545567: step: 2654/1545, loss: 0.03367209807038307 2023-01-23 13:48:00.437389: step: 2656/1545, loss: 0.669884979724884 2023-01-23 13:48:01.294078: step: 2658/1545, loss: 0.4175087809562683 2023-01-23 13:48:02.186729: step: 2660/1545, loss: 0.09795313328504562 2023-01-23 13:48:03.088882: step: 2662/1545, loss: 0.008208254352211952 2023-01-23 13:48:03.984022: step: 2664/1545, loss: 0.03061024472117424 2023-01-23 13:48:04.884608: step: 2666/1545, loss: 0.03406519815325737 2023-01-23 13:48:05.728201: step: 2668/1545, loss: 0.17628656327724457 2023-01-23 13:48:06.621769: step: 2670/1545, loss: 0.01251463033258915 2023-01-23 13:48:07.512585: step: 2672/1545, loss: 0.15119069814682007 2023-01-23 13:48:08.365739: step: 2674/1545, loss: 0.005514663644134998 2023-01-23 13:48:09.225906: step: 2676/1545, loss: 0.04960479959845543 2023-01-23 13:48:10.095703: step: 2678/1545, loss: 0.27076029777526855 2023-01-23 13:48:10.978950: step: 2680/1545, loss: 0.24118860065937042 2023-01-23 13:48:11.900220: step: 2682/1545, loss: 0.10104573518037796 2023-01-23 13:48:12.789666: step: 2684/1545, loss: 0.023680521175265312 2023-01-23 13:48:13.739061: step: 2686/1545, loss: 0.19602994620800018 2023-01-23 13:48:14.609888: step: 2688/1545, loss: 0.008943352848291397 2023-01-23 13:48:15.521874: step: 2690/1545, loss: 0.4131009578704834 2023-01-23 13:48:16.455754: step: 2692/1545, loss: 0.018104704096913338 2023-01-23 13:48:17.336808: step: 2694/1545, loss: 0.006299477536231279 2023-01-23 13:48:18.235964: step: 2696/1545, loss: 0.17132094502449036 2023-01-23 13:48:19.140805: step: 2698/1545, loss: 0.00854971818625927 2023-01-23 13:48:20.030829: step: 2700/1545, loss: 0.017316654324531555 2023-01-23 13:48:20.884897: step: 2702/1545, loss: 0.10443129390478134 2023-01-23 13:48:21.792231: step: 2704/1545, loss: 0.11544392257928848 2023-01-23 13:48:22.675003: step: 2706/1545, loss: 0.019476305693387985 2023-01-23 13:48:23.534298: step: 2708/1545, loss: 0.004833874758332968 2023-01-23 13:48:24.419480: step: 2710/1545, loss: 0.1023331880569458 2023-01-23 13:48:25.321368: step: 2712/1545, loss: 0.05055339261889458 2023-01-23 13:48:26.208957: step: 2714/1545, loss: 0.01759170927107334 2023-01-23 13:48:27.098920: step: 2716/1545, loss: 0.002066916786134243 2023-01-23 13:48:27.994443: step: 2718/1545, loss: 0.005006001330912113 2023-01-23 13:48:28.853655: step: 2720/1545, loss: 0.0005871620960533619 2023-01-23 13:48:29.744158: step: 2722/1545, loss: 0.005906286183744669 2023-01-23 13:48:30.599208: step: 2724/1545, loss: 0.022436929866671562 2023-01-23 13:48:31.458926: step: 2726/1545, loss: 0.765175461769104 2023-01-23 13:48:32.360879: step: 2728/1545, loss: 0.2501913607120514 2023-01-23 13:48:33.276964: step: 2730/1545, loss: 0.19793307781219482 2023-01-23 13:48:34.173196: step: 2732/1545, loss: 0.04361874610185623 2023-01-23 13:48:35.024690: step: 2734/1545, loss: 0.001231493428349495 2023-01-23 13:48:35.866226: step: 2736/1545, loss: 0.10550650954246521 2023-01-23 13:48:36.777185: step: 2738/1545, loss: 0.004603537265211344 2023-01-23 13:48:37.704534: step: 2740/1545, loss: 0.005815127864480019 2023-01-23 13:48:38.567053: step: 2742/1545, loss: 0.08481629937887192 2023-01-23 13:48:39.454769: step: 2744/1545, loss: 0.23527617752552032 2023-01-23 13:48:40.315892: step: 2746/1545, loss: 0.07554065436124802 2023-01-23 13:48:41.206819: step: 2748/1545, loss: 0.12204620242118835 2023-01-23 13:48:42.103615: step: 2750/1545, loss: 0.019247371703386307 2023-01-23 13:48:43.018530: step: 2752/1545, loss: 0.17025183141231537 2023-01-23 13:48:43.864929: step: 2754/1545, loss: 0.09264054894447327 2023-01-23 13:48:44.741038: step: 2756/1545, loss: 0.045609913766384125 2023-01-23 13:48:45.629850: step: 2758/1545, loss: 0.0003945374337490648 2023-01-23 13:48:46.515446: step: 2760/1545, loss: 0.03604739159345627 2023-01-23 13:48:47.432723: step: 2762/1545, loss: 0.17967015504837036 2023-01-23 13:48:48.366984: step: 2764/1545, loss: 0.01869496889412403 2023-01-23 13:48:49.256632: step: 2766/1545, loss: 0.16356682777404785 2023-01-23 13:48:50.214606: step: 2768/1545, loss: 0.6639609336853027 2023-01-23 13:48:51.062850: step: 2770/1545, loss: 0.030174048617482185 2023-01-23 13:48:51.951347: step: 2772/1545, loss: 0.24647513031959534 2023-01-23 13:48:52.858002: step: 2774/1545, loss: 0.001667532604187727 2023-01-23 13:48:53.708807: step: 2776/1545, loss: 0.1269504278898239 2023-01-23 13:48:54.746235: step: 2778/1545, loss: 0.05155790597200394 2023-01-23 13:48:55.651270: step: 2780/1545, loss: 0.03190845996141434 2023-01-23 13:48:56.520213: step: 2782/1545, loss: 0.46860453486442566 2023-01-23 13:48:57.426483: step: 2784/1545, loss: 0.050863929092884064 2023-01-23 13:48:58.273387: step: 2786/1545, loss: 0.12667341530323029 2023-01-23 13:48:59.135040: step: 2788/1545, loss: 0.7367875576019287 2023-01-23 13:49:00.034752: step: 2790/1545, loss: 0.10957206040620804 2023-01-23 13:49:00.919415: step: 2792/1545, loss: 0.0049781035631895065 2023-01-23 13:49:01.773698: step: 2794/1545, loss: 0.0040329513140022755 2023-01-23 13:49:02.664275: step: 2796/1545, loss: 0.051924414932727814 2023-01-23 13:49:03.514444: step: 2798/1545, loss: 0.13413971662521362 2023-01-23 13:49:04.373240: step: 2800/1545, loss: 0.04405292123556137 2023-01-23 13:49:05.193951: step: 2802/1545, loss: 0.022828537970781326 2023-01-23 13:49:06.055037: step: 2804/1545, loss: 0.004883948247879744 2023-01-23 13:49:06.927605: step: 2806/1545, loss: 0.17426255345344543 2023-01-23 13:49:07.827529: step: 2808/1545, loss: 0.17230354249477386 2023-01-23 13:49:08.700433: step: 2810/1545, loss: 0.009013356640934944 2023-01-23 13:49:09.576723: step: 2812/1545, loss: 0.07086934894323349 2023-01-23 13:49:10.416527: step: 2814/1545, loss: 0.04896577447652817 2023-01-23 13:49:11.263411: step: 2816/1545, loss: 0.0011036688229069114 2023-01-23 13:49:12.118875: step: 2818/1545, loss: 0.23273403942584991 2023-01-23 13:49:13.015857: step: 2820/1545, loss: 0.013898110948503017 2023-01-23 13:49:13.887031: step: 2822/1545, loss: 0.036471977829933167 2023-01-23 13:49:14.805749: step: 2824/1545, loss: 0.049390021711587906 2023-01-23 13:49:15.669436: step: 2826/1545, loss: 0.08470306545495987 2023-01-23 13:49:16.560518: step: 2828/1545, loss: 0.09960722923278809 2023-01-23 13:49:17.420007: step: 2830/1545, loss: 0.08797460794448853 2023-01-23 13:49:18.253617: step: 2832/1545, loss: 0.39069893956184387 2023-01-23 13:49:19.105223: step: 2834/1545, loss: 0.0045075323432683945 2023-01-23 13:49:19.973112: step: 2836/1545, loss: 0.01657152734696865 2023-01-23 13:49:20.877217: step: 2838/1545, loss: 0.00160092837177217 2023-01-23 13:49:21.726212: step: 2840/1545, loss: 0.16208158433437347 2023-01-23 13:49:22.638390: step: 2842/1545, loss: 0.020063577219843864 2023-01-23 13:49:23.496072: step: 2844/1545, loss: 0.011001360602676868 2023-01-23 13:49:24.351190: step: 2846/1545, loss: 0.1994810253381729 2023-01-23 13:49:25.258111: step: 2848/1545, loss: 0.03973901644349098 2023-01-23 13:49:26.164909: step: 2850/1545, loss: 0.28047975897789 2023-01-23 13:49:27.062734: step: 2852/1545, loss: 0.02524585649371147 2023-01-23 13:49:27.943923: step: 2854/1545, loss: 0.010195726528763771 2023-01-23 13:49:28.849452: step: 2856/1545, loss: 0.0039295414462685585 2023-01-23 13:49:29.699430: step: 2858/1545, loss: 0.057601794600486755 2023-01-23 13:49:30.584804: step: 2860/1545, loss: 0.0058718593791127205 2023-01-23 13:49:31.443114: step: 2862/1545, loss: 0.10635484009981155 2023-01-23 13:49:32.304579: step: 2864/1545, loss: 0.024396024644374847 2023-01-23 13:49:33.183227: step: 2866/1545, loss: 0.1527271866798401 2023-01-23 13:49:34.039207: step: 2868/1545, loss: 0.02946755290031433 2023-01-23 13:49:34.906630: step: 2870/1545, loss: 0.010124982334673405 2023-01-23 13:49:35.777058: step: 2872/1545, loss: 0.0016675645019859076 2023-01-23 13:49:36.631042: step: 2874/1545, loss: 0.03635697439312935 2023-01-23 13:49:37.494414: step: 2876/1545, loss: 0.07042735815048218 2023-01-23 13:49:38.440023: step: 2878/1545, loss: 0.07287762314081192 2023-01-23 13:49:39.334782: step: 2880/1545, loss: 0.01219741627573967 2023-01-23 13:49:40.218950: step: 2882/1545, loss: 0.007226789835840464 2023-01-23 13:49:41.196129: step: 2884/1545, loss: 0.1681535691022873 2023-01-23 13:49:42.109538: step: 2886/1545, loss: 0.2035139501094818 2023-01-23 13:49:43.026444: step: 2888/1545, loss: 0.001639454043470323 2023-01-23 13:49:43.863560: step: 2890/1545, loss: 0.34176501631736755 2023-01-23 13:49:44.855876: step: 2892/1545, loss: 0.11188701540231705 2023-01-23 13:49:45.728741: step: 2894/1545, loss: 0.011968240141868591 2023-01-23 13:49:46.585884: step: 2896/1545, loss: 0.4372135102748871 2023-01-23 13:49:47.531220: step: 2898/1545, loss: 0.003956071566790342 2023-01-23 13:49:48.433083: step: 2900/1545, loss: 0.011271312832832336 2023-01-23 13:49:49.297902: step: 2902/1545, loss: 0.0536259189248085 2023-01-23 13:49:50.215175: step: 2904/1545, loss: 0.11070345342159271 2023-01-23 13:49:51.069445: step: 2906/1545, loss: 0.13317187130451202 2023-01-23 13:49:51.921194: step: 2908/1545, loss: 0.007278492208570242 2023-01-23 13:49:52.759870: step: 2910/1545, loss: 0.006484655197709799 2023-01-23 13:49:53.689664: step: 2912/1545, loss: 0.08552031219005585 2023-01-23 13:49:54.600360: step: 2914/1545, loss: 0.24585993587970734 2023-01-23 13:49:55.442247: step: 2916/1545, loss: 0.02198529615998268 2023-01-23 13:49:56.303012: step: 2918/1545, loss: 0.8406470417976379 2023-01-23 13:49:57.238832: step: 2920/1545, loss: 0.22188246250152588 2023-01-23 13:49:58.113396: step: 2922/1545, loss: 0.16730627417564392 2023-01-23 13:49:58.964802: step: 2924/1545, loss: 0.1780414879322052 2023-01-23 13:49:59.847855: step: 2926/1545, loss: 0.0036722139921039343 2023-01-23 13:50:00.778361: step: 2928/1545, loss: 0.11156827956438065 2023-01-23 13:50:01.666724: step: 2930/1545, loss: 0.004153321962803602 2023-01-23 13:50:02.600155: step: 2932/1545, loss: 0.01481834426522255 2023-01-23 13:50:03.460835: step: 2934/1545, loss: 0.012948071584105492 2023-01-23 13:50:04.367484: step: 2936/1545, loss: 0.07460341602563858 2023-01-23 13:50:05.236743: step: 2938/1545, loss: 0.019788209348917007 2023-01-23 13:50:06.094115: step: 2940/1545, loss: 0.06531084328889847 2023-01-23 13:50:06.934016: step: 2942/1545, loss: 0.02216414548456669 2023-01-23 13:50:07.824400: step: 2944/1545, loss: 0.2008042186498642 2023-01-23 13:50:08.693579: step: 2946/1545, loss: 0.05007623881101608 2023-01-23 13:50:09.596213: step: 2948/1545, loss: 0.05251600593328476 2023-01-23 13:50:10.468494: step: 2950/1545, loss: 0.016612356528639793 2023-01-23 13:50:11.352654: step: 2952/1545, loss: 0.0121486596763134 2023-01-23 13:50:12.245371: step: 2954/1545, loss: 0.05115704983472824 2023-01-23 13:50:13.145983: step: 2956/1545, loss: 0.09327409416437149 2023-01-23 13:50:13.981195: step: 2958/1545, loss: 0.03226678445935249 2023-01-23 13:50:14.862285: step: 2960/1545, loss: 0.022569071501493454 2023-01-23 13:50:15.724887: step: 2962/1545, loss: 0.008005744777619839 2023-01-23 13:50:16.596978: step: 2964/1545, loss: 0.12202910333871841 2023-01-23 13:50:17.549074: step: 2966/1545, loss: 0.04935738444328308 2023-01-23 13:50:18.419934: step: 2968/1545, loss: 0.037484053522348404 2023-01-23 13:50:19.313987: step: 2970/1545, loss: 0.19112469255924225 2023-01-23 13:50:20.164748: step: 2972/1545, loss: 0.027974870055913925 2023-01-23 13:50:21.096075: step: 2974/1545, loss: 0.0354534350335598 2023-01-23 13:50:22.039308: step: 2976/1545, loss: 0.43324539065361023 2023-01-23 13:50:22.967693: step: 2978/1545, loss: 0.08811725676059723 2023-01-23 13:50:23.843738: step: 2980/1545, loss: 0.012761319987475872 2023-01-23 13:50:24.715122: step: 2982/1545, loss: 0.02613939717411995 2023-01-23 13:50:25.604350: step: 2984/1545, loss: 0.08083607256412506 2023-01-23 13:50:26.457168: step: 2986/1545, loss: 0.002858475549146533 2023-01-23 13:50:27.333237: step: 2988/1545, loss: 0.07702469825744629 2023-01-23 13:50:28.266224: step: 2990/1545, loss: 0.010392679832875729 2023-01-23 13:50:29.118583: step: 2992/1545, loss: 0.7196457982063293 2023-01-23 13:50:29.993459: step: 2994/1545, loss: 0.1484035849571228 2023-01-23 13:50:30.843432: step: 2996/1545, loss: 0.6783754825592041 2023-01-23 13:50:31.679536: step: 2998/1545, loss: 0.15482133626937866 2023-01-23 13:50:32.586229: step: 3000/1545, loss: 0.09431583434343338 2023-01-23 13:50:33.454836: step: 3002/1545, loss: 0.0410040020942688 2023-01-23 13:50:34.357297: step: 3004/1545, loss: 0.07124799489974976 2023-01-23 13:50:35.233971: step: 3006/1545, loss: 0.31928929686546326 2023-01-23 13:50:36.061494: step: 3008/1545, loss: 0.0009489444782957435 2023-01-23 13:50:36.936699: step: 3010/1545, loss: 0.02321634255349636 2023-01-23 13:50:37.811354: step: 3012/1545, loss: 0.005742973182350397 2023-01-23 13:50:38.689789: step: 3014/1545, loss: 0.11215813457965851 2023-01-23 13:50:39.583406: step: 3016/1545, loss: 0.008006523363292217 2023-01-23 13:50:40.432411: step: 3018/1545, loss: 0.08729786425828934 2023-01-23 13:50:41.307614: step: 3020/1545, loss: 0.04159848764538765 2023-01-23 13:50:42.193529: step: 3022/1545, loss: 0.04879750311374664 2023-01-23 13:50:43.076634: step: 3024/1545, loss: 0.29302456974983215 2023-01-23 13:50:43.969027: step: 3026/1545, loss: 0.12188927829265594 2023-01-23 13:50:44.874458: step: 3028/1545, loss: 0.05062846466898918 2023-01-23 13:50:45.727967: step: 3030/1545, loss: 0.4390818178653717 2023-01-23 13:50:46.583210: step: 3032/1545, loss: 0.044926967471838 2023-01-23 13:50:47.484585: step: 3034/1545, loss: 0.17044983804225922 2023-01-23 13:50:48.315398: step: 3036/1545, loss: 0.18839843571186066 2023-01-23 13:50:49.249793: step: 3038/1545, loss: 0.05186518654227257 2023-01-23 13:50:50.155533: step: 3040/1545, loss: 0.6043030023574829 2023-01-23 13:50:51.089176: step: 3042/1545, loss: 0.21283645927906036 2023-01-23 13:50:51.923535: step: 3044/1545, loss: 0.1386989951133728 2023-01-23 13:50:52.758468: step: 3046/1545, loss: 0.009003090672194958 2023-01-23 13:50:53.628919: step: 3048/1545, loss: 0.0209360234439373 2023-01-23 13:50:54.577605: step: 3050/1545, loss: 0.011066264472901821 2023-01-23 13:50:55.481581: step: 3052/1545, loss: 0.10864423960447311 2023-01-23 13:50:56.342597: step: 3054/1545, loss: 0.15760377049446106 2023-01-23 13:50:57.213352: step: 3056/1545, loss: 0.033019792288541794 2023-01-23 13:50:58.169705: step: 3058/1545, loss: 0.2823866605758667 2023-01-23 13:50:59.017603: step: 3060/1545, loss: 0.6581215858459473 2023-01-23 13:50:59.888063: step: 3062/1545, loss: 0.03336187079548836 2023-01-23 13:51:00.791941: step: 3064/1545, loss: 0.14420124888420105 2023-01-23 13:51:01.683071: step: 3066/1545, loss: 0.19370326399803162 2023-01-23 13:51:02.561976: step: 3068/1545, loss: 0.2843855917453766 2023-01-23 13:51:03.454047: step: 3070/1545, loss: 0.06241286173462868 2023-01-23 13:51:04.367706: step: 3072/1545, loss: 0.0118519626557827 2023-01-23 13:51:05.241897: step: 3074/1545, loss: 0.34191879630088806 2023-01-23 13:51:06.115102: step: 3076/1545, loss: 0.15288075804710388 2023-01-23 13:51:06.938176: step: 3078/1545, loss: 0.009143110364675522 2023-01-23 13:51:07.829420: step: 3080/1545, loss: 0.046083319932222366 2023-01-23 13:51:08.703847: step: 3082/1545, loss: 0.8003619313240051 2023-01-23 13:51:09.666717: step: 3084/1545, loss: 0.45818403363227844 2023-01-23 13:51:10.488780: step: 3086/1545, loss: 0.026980914175510406 2023-01-23 13:51:11.361154: step: 3088/1545, loss: 0.07866724580526352 2023-01-23 13:51:12.238541: step: 3090/1545, loss: 0.10804931819438934 ================================================== Loss: 0.116 -------------------- Dev Chinese: {'event': {'p': 0.6030534351145038, 'r': 0.7363515312916112, 'f1': 0.6630695443645084}, 'argument': {'p': 0.6464189693864957, 'r': 0.6570715666348125, 'f1': 0.6517017395672173}, 'combined': 0.4321235755163923, 'epoch': 18} Test Chinese: {'event': {'p': 0.6366061899679829, 'r': 0.7627877237851662, 'f1': 0.6940081442699244}, 'argument': {'p': 0.7044881340243597, 'r': 0.708524544265141, 'f1': 0.7065005739425402}, 'combined': 0.49031715224749883, 'epoch': 18} Dev Korean: {'event': {'p': 0.6061269146608315, 'r': 0.7376830892143809, 'f1': 0.6654654654654655}, 'argument': {'p': 0.6571334539663469, 'r': 0.6596057393462053, 'f1': 0.658367275697414}, 'combined': 0.4381206855692101, 'epoch': 18} Test Korean: {'event': {'p': 0.6275132275132275, 'r': 0.7583120204603581, 'f1': 0.6867400115807759}, 'argument': {'p': 0.6972332451712081, 'r': 0.7022972480986748, 'f1': 0.6997560849461563}, 'combined': 0.48055050187964177, 'epoch': 18} Dev Russian: {'event': {'p': 0.5688976377952756, 'r': 0.7696404793608522, 'f1': 0.6542161856253538}, 'argument': {'p': 0.6484735469415961, 'r': 0.6619158148910645, 'f1': 0.6551257340166957}, 'combined': 0.4285938588134127, 'epoch': 18} Test Russian: {'event': {'p': 0.6233183856502242, 'r': 0.7998721227621484, 'f1': 0.7006440772892747}, 'argument': {'p': 0.7072013830251471, 'r': 0.7175274234362219, 'f1': 0.7123269830879572}, 'combined': 0.49908768179391455, 'epoch': 18} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6680632411067193, 'r': 0.6349361382419234, 'f1': 0.6510785824345146}, 'combined': 0.463646869309427, 'epoch': 18} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6462780514504654, 'r': 0.5134811915633833, 'f1': 0.572276747849267}, 'combined': 0.35139800306533936, 'epoch': 18} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5516353328059318, 'r': 0.5713365946918579, 'f1': 0.5613131456621762}, 'combined': 0.3268405658286088, 'epoch': 18} New best korean model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6061269146608315, 'r': 0.7376830892143809, 'f1': 0.6654654654654655}, 'argument': {'p': 0.6571334539663469, 'r': 0.6596057393462053, 'f1': 0.658367275697414}, 'combined': 0.4381206855692101, 'epoch': 18} Test for Korean: {'event': {'p': 0.6275132275132275, 'r': 0.7583120204603581, 'f1': 0.6867400115807759}, 'argument': {'p': 0.6972332451712081, 'r': 0.7022972480986748, 'f1': 0.6997560849461563}, 'combined': 0.48055050187964177, 'epoch': 18} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6462780514504654, 'r': 0.5134811915633833, 'f1': 0.572276747849267}, 'combined': 0.35139800306533936, 'epoch': 18} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 19 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 13:56:29.516809: step: 2/1545, loss: 0.01566721871495247 2023-01-23 13:56:30.346345: step: 4/1545, loss: 0.14707635343074799 2023-01-23 13:56:31.204840: step: 6/1545, loss: 0.008484558202326298 2023-01-23 13:56:32.110549: step: 8/1545, loss: 0.09258925169706345 2023-01-23 13:56:33.028769: step: 10/1545, loss: 0.01608334854245186 2023-01-23 13:56:33.898521: step: 12/1545, loss: 0.00452080462127924 2023-01-23 13:56:34.826936: step: 14/1545, loss: 0.054388627409935 2023-01-23 13:56:35.688310: step: 16/1545, loss: 0.007477256935089827 2023-01-23 13:56:36.535203: step: 18/1545, loss: 0.04324675723910332 2023-01-23 13:56:37.437838: step: 20/1545, loss: 0.20652155578136444 2023-01-23 13:56:38.292469: step: 22/1545, loss: 0.4408113360404968 2023-01-23 13:56:39.162161: step: 24/1545, loss: 0.1081787496805191 2023-01-23 13:56:40.066996: step: 26/1545, loss: 0.07299406826496124 2023-01-23 13:56:40.942275: step: 28/1545, loss: 0.05800870433449745 2023-01-23 13:56:41.804693: step: 30/1545, loss: 0.07881969213485718 2023-01-23 13:56:42.655509: step: 32/1545, loss: 0.21466298401355743 2023-01-23 13:56:43.542176: step: 34/1545, loss: 2.3181402683258057 2023-01-23 13:56:44.431350: step: 36/1545, loss: 0.00393380643799901 2023-01-23 13:56:45.326642: step: 38/1545, loss: 0.008039964362978935 2023-01-23 13:56:46.208710: step: 40/1545, loss: 0.003757868893444538 2023-01-23 13:56:47.095300: step: 42/1545, loss: 0.007856721058487892 2023-01-23 13:56:47.991043: step: 44/1545, loss: 0.4367324709892273 2023-01-23 13:56:48.865595: step: 46/1545, loss: 0.4566805362701416 2023-01-23 13:56:49.841951: step: 48/1545, loss: 0.012614872306585312 2023-01-23 13:56:50.759813: step: 50/1545, loss: 0.09492455422878265 2023-01-23 13:56:51.688098: step: 52/1545, loss: 0.2196267694234848 2023-01-23 13:56:52.561270: step: 54/1545, loss: 0.07168810069561005 2023-01-23 13:56:53.449238: step: 56/1545, loss: 0.15050077438354492 2023-01-23 13:56:54.331100: step: 58/1545, loss: 0.026034317910671234 2023-01-23 13:56:55.205035: step: 60/1545, loss: 0.0508454404771328 2023-01-23 13:56:56.103731: step: 62/1545, loss: 0.008208992891013622 2023-01-23 13:56:56.983569: step: 64/1545, loss: 0.014267796650528908 2023-01-23 13:56:57.854027: step: 66/1545, loss: 0.1940520852804184 2023-01-23 13:56:58.767463: step: 68/1545, loss: 0.1069817841053009 2023-01-23 13:56:59.604214: step: 70/1545, loss: 0.045429520308971405 2023-01-23 13:57:00.490761: step: 72/1545, loss: 0.34226176142692566 2023-01-23 13:57:01.363487: step: 74/1545, loss: 0.17305053770542145 2023-01-23 13:57:02.258491: step: 76/1545, loss: 0.10508249700069427 2023-01-23 13:57:03.123783: step: 78/1545, loss: 0.03790004178881645 2023-01-23 13:57:03.999255: step: 80/1545, loss: 0.10145371407270432 2023-01-23 13:57:04.862568: step: 82/1545, loss: 0.08732939511537552 2023-01-23 13:57:05.768555: step: 84/1545, loss: 0.18615125119686127 2023-01-23 13:57:06.729949: step: 86/1545, loss: 0.19229383766651154 2023-01-23 13:57:07.608065: step: 88/1545, loss: 0.29861101508140564 2023-01-23 13:57:08.525007: step: 90/1545, loss: 0.01923864707350731 2023-01-23 13:57:09.339373: step: 92/1545, loss: 0.17051298916339874 2023-01-23 13:57:10.202039: step: 94/1545, loss: 0.004431316629052162 2023-01-23 13:57:11.084558: step: 96/1545, loss: 0.02964198589324951 2023-01-23 13:57:11.943898: step: 98/1545, loss: 0.018930798396468163 2023-01-23 13:57:12.818698: step: 100/1545, loss: 0.31620877981185913 2023-01-23 13:57:13.706528: step: 102/1545, loss: 0.0366043820977211 2023-01-23 13:57:14.584335: step: 104/1545, loss: 0.008257521316409111 2023-01-23 13:57:15.452815: step: 106/1545, loss: 0.07409431785345078 2023-01-23 13:57:16.368093: step: 108/1545, loss: 0.17319825291633606 2023-01-23 13:57:17.220998: step: 110/1545, loss: 0.03480815514922142 2023-01-23 13:57:18.097454: step: 112/1545, loss: 0.002057313919067383 2023-01-23 13:57:18.980644: step: 114/1545, loss: 0.006874992046505213 2023-01-23 13:57:19.823522: step: 116/1545, loss: 0.10028809309005737 2023-01-23 13:57:20.712124: step: 118/1545, loss: 0.000984431360848248 2023-01-23 13:57:21.573784: step: 120/1545, loss: 0.0017669722437858582 2023-01-23 13:57:22.474952: step: 122/1545, loss: 0.029199030250310898 2023-01-23 13:57:23.353682: step: 124/1545, loss: 0.033691417425870895 2023-01-23 13:57:24.225065: step: 126/1545, loss: 0.0014809730928391218 2023-01-23 13:57:25.138730: step: 128/1545, loss: 0.008327220566570759 2023-01-23 13:57:26.037892: step: 130/1545, loss: 0.00545354513451457 2023-01-23 13:57:26.969103: step: 132/1545, loss: 0.41158196330070496 2023-01-23 13:57:27.804813: step: 134/1545, loss: 0.0002638789592310786 2023-01-23 13:57:28.732071: step: 136/1545, loss: 0.0002594930410850793 2023-01-23 13:57:29.599226: step: 138/1545, loss: 0.02696191892027855 2023-01-23 13:57:30.494820: step: 140/1545, loss: 1.988489031791687 2023-01-23 13:57:31.334952: step: 142/1545, loss: 0.012692024931311607 2023-01-23 13:57:32.205320: step: 144/1545, loss: 0.040674060583114624 2023-01-23 13:57:33.200598: step: 146/1545, loss: 0.11126557737588882 2023-01-23 13:57:34.167177: step: 148/1545, loss: 0.5939692258834839 2023-01-23 13:57:35.020322: step: 150/1545, loss: 0.0012120807077735662 2023-01-23 13:57:35.921139: step: 152/1545, loss: 0.09813214838504791 2023-01-23 13:57:36.829785: step: 154/1545, loss: 0.2204865664243698 2023-01-23 13:57:37.727778: step: 156/1545, loss: 0.25905174016952515 2023-01-23 13:57:38.601917: step: 158/1545, loss: 0.004483805503696203 2023-01-23 13:57:39.535475: step: 160/1545, loss: 0.0012791578192263842 2023-01-23 13:57:40.432516: step: 162/1545, loss: 0.07161246240139008 2023-01-23 13:57:41.299668: step: 164/1545, loss: 0.00993820745497942 2023-01-23 13:57:42.216857: step: 166/1545, loss: 0.21316461265087128 2023-01-23 13:57:43.117911: step: 168/1545, loss: 0.37233027815818787 2023-01-23 13:57:43.992082: step: 170/1545, loss: 0.10713145136833191 2023-01-23 13:57:44.876729: step: 172/1545, loss: 0.00985678005963564 2023-01-23 13:57:45.746090: step: 174/1545, loss: 0.003089393489062786 2023-01-23 13:57:46.607590: step: 176/1545, loss: 0.027540666982531548 2023-01-23 13:57:47.460019: step: 178/1545, loss: 0.011276645585894585 2023-01-23 13:57:48.311963: step: 180/1545, loss: 0.027594009414315224 2023-01-23 13:57:49.174585: step: 182/1545, loss: 0.0012342343106865883 2023-01-23 13:57:50.047769: step: 184/1545, loss: 0.22731953859329224 2023-01-23 13:57:50.914655: step: 186/1545, loss: 0.41428911685943604 2023-01-23 13:57:51.805240: step: 188/1545, loss: 0.0069532329216599464 2023-01-23 13:57:52.691509: step: 190/1545, loss: 0.008573105558753014 2023-01-23 13:57:53.604510: step: 192/1545, loss: 0.051316037774086 2023-01-23 13:57:54.493950: step: 194/1545, loss: 0.07620969414710999 2023-01-23 13:57:55.344960: step: 196/1545, loss: 0.06728359311819077 2023-01-23 13:57:56.228081: step: 198/1545, loss: 0.01618904434144497 2023-01-23 13:57:57.082763: step: 200/1545, loss: 0.22905248403549194 2023-01-23 13:57:57.931230: step: 202/1545, loss: 0.0005912249907851219 2023-01-23 13:57:58.800557: step: 204/1545, loss: 0.1639842391014099 2023-01-23 13:57:59.635958: step: 206/1545, loss: 0.010305331088602543 2023-01-23 13:58:00.543523: step: 208/1545, loss: 1.1185719966888428 2023-01-23 13:58:01.461081: step: 210/1545, loss: 0.012527698650956154 2023-01-23 13:58:02.352172: step: 212/1545, loss: 0.06960401684045792 2023-01-23 13:58:03.202830: step: 214/1545, loss: 0.0018825491424649954 2023-01-23 13:58:04.039242: step: 216/1545, loss: 0.005783977918326855 2023-01-23 13:58:04.906830: step: 218/1545, loss: 0.008587096817791462 2023-01-23 13:58:05.765831: step: 220/1545, loss: 0.20751196146011353 2023-01-23 13:58:06.600637: step: 222/1545, loss: 0.587443470954895 2023-01-23 13:58:07.523872: step: 224/1545, loss: 0.019562261179089546 2023-01-23 13:58:08.385971: step: 226/1545, loss: 0.03370068222284317 2023-01-23 13:58:09.259976: step: 228/1545, loss: 0.1320323348045349 2023-01-23 13:58:10.202110: step: 230/1545, loss: 0.00629466725513339 2023-01-23 13:58:11.063576: step: 232/1545, loss: 0.05093638226389885 2023-01-23 13:58:11.947035: step: 234/1545, loss: 0.030231665819883347 2023-01-23 13:58:12.803875: step: 236/1545, loss: 0.009960430674254894 2023-01-23 13:58:13.665116: step: 238/1545, loss: 0.11388418823480606 2023-01-23 13:58:14.516217: step: 240/1545, loss: 0.0050330013036727905 2023-01-23 13:58:15.413306: step: 242/1545, loss: 0.0016178907826542854 2023-01-23 13:58:16.330896: step: 244/1545, loss: 0.1616629809141159 2023-01-23 13:58:17.205634: step: 246/1545, loss: 0.00011647120845736936 2023-01-23 13:58:18.128393: step: 248/1545, loss: 0.4464639723300934 2023-01-23 13:58:19.020571: step: 250/1545, loss: 0.00017562339780852199 2023-01-23 13:58:19.887813: step: 252/1545, loss: 0.06466388702392578 2023-01-23 13:58:20.766763: step: 254/1545, loss: 0.055758897215127945 2023-01-23 13:58:21.678977: step: 256/1545, loss: 0.000735684297978878 2023-01-23 13:58:22.549607: step: 258/1545, loss: 0.0005578178097493947 2023-01-23 13:58:23.433192: step: 260/1545, loss: 0.24731384217739105 2023-01-23 13:58:24.344858: step: 262/1545, loss: 0.011212432757019997 2023-01-23 13:58:25.236343: step: 264/1545, loss: 0.07377484440803528 2023-01-23 13:58:26.144914: step: 266/1545, loss: 0.7068814635276794 2023-01-23 13:58:27.023629: step: 268/1545, loss: 0.15323945879936218 2023-01-23 13:58:27.909335: step: 270/1545, loss: 0.14975012838840485 2023-01-23 13:58:28.779718: step: 272/1545, loss: 0.0018902166048064828 2023-01-23 13:58:29.632739: step: 274/1545, loss: 8.560472633689642e-05 2023-01-23 13:58:30.529005: step: 276/1545, loss: 0.05678630247712135 2023-01-23 13:58:31.417637: step: 278/1545, loss: 0.16108280420303345 2023-01-23 13:58:32.305516: step: 280/1545, loss: 0.20195883512496948 2023-01-23 13:58:33.198292: step: 282/1545, loss: 0.03099721670150757 2023-01-23 13:58:34.081214: step: 284/1545, loss: 0.09966027736663818 2023-01-23 13:58:34.967858: step: 286/1545, loss: 0.3718307614326477 2023-01-23 13:58:35.847541: step: 288/1545, loss: 0.0015323805855587125 2023-01-23 13:58:36.706071: step: 290/1545, loss: 0.0021247905679047108 2023-01-23 13:58:37.572973: step: 292/1545, loss: 0.03731323778629303 2023-01-23 13:58:38.458698: step: 294/1545, loss: 0.0015341631369665265 2023-01-23 13:58:39.314652: step: 296/1545, loss: 0.0012094974517822266 2023-01-23 13:58:40.194425: step: 298/1545, loss: 0.09198790043592453 2023-01-23 13:58:41.091599: step: 300/1545, loss: 0.0475299246609211 2023-01-23 13:58:41.950184: step: 302/1545, loss: 0.01677122712135315 2023-01-23 13:58:42.833216: step: 304/1545, loss: 0.1312669962644577 2023-01-23 13:58:43.693310: step: 306/1545, loss: 0.008726004511117935 2023-01-23 13:58:44.597591: step: 308/1545, loss: 0.057462774217128754 2023-01-23 13:58:45.467128: step: 310/1545, loss: 0.07813942432403564 2023-01-23 13:58:46.355575: step: 312/1545, loss: 0.04549632593989372 2023-01-23 13:58:47.210088: step: 314/1545, loss: 0.04412133991718292 2023-01-23 13:58:48.062913: step: 316/1545, loss: 0.9275644421577454 2023-01-23 13:58:48.975728: step: 318/1545, loss: 0.10155070573091507 2023-01-23 13:58:49.936668: step: 320/1545, loss: 0.011160709895193577 2023-01-23 13:58:50.814023: step: 322/1545, loss: 0.041872117668390274 2023-01-23 13:58:51.760026: step: 324/1545, loss: 0.20836153626441956 2023-01-23 13:58:52.617478: step: 326/1545, loss: 0.7375857830047607 2023-01-23 13:58:53.474862: step: 328/1545, loss: 0.010380877181887627 2023-01-23 13:58:54.372127: step: 330/1545, loss: 0.14329223334789276 2023-01-23 13:58:55.236678: step: 332/1545, loss: 0.006177669856697321 2023-01-23 13:58:56.117842: step: 334/1545, loss: 0.007425572723150253 2023-01-23 13:58:56.963231: step: 336/1545, loss: 0.26932641863822937 2023-01-23 13:58:57.855905: step: 338/1545, loss: 0.0016829799860715866 2023-01-23 13:58:58.738918: step: 340/1545, loss: 0.008065086789429188 2023-01-23 13:58:59.636626: step: 342/1545, loss: 0.002292344579473138 2023-01-23 13:59:00.551462: step: 344/1545, loss: 0.04623321816325188 2023-01-23 13:59:01.407252: step: 346/1545, loss: 0.032777875661849976 2023-01-23 13:59:02.327883: step: 348/1545, loss: 0.02180277369916439 2023-01-23 13:59:03.219105: step: 350/1545, loss: 0.02560129389166832 2023-01-23 13:59:04.121142: step: 352/1545, loss: 0.007438271772116423 2023-01-23 13:59:05.015691: step: 354/1545, loss: 0.007961350493133068 2023-01-23 13:59:05.877017: step: 356/1545, loss: 0.2846813499927521 2023-01-23 13:59:06.760155: step: 358/1545, loss: 0.038044966757297516 2023-01-23 13:59:07.645218: step: 360/1545, loss: 0.027864597737789154 2023-01-23 13:59:08.579504: step: 362/1545, loss: 0.0032839225605130196 2023-01-23 13:59:09.462968: step: 364/1545, loss: 0.043141547590494156 2023-01-23 13:59:10.350033: step: 366/1545, loss: 0.32240328192710876 2023-01-23 13:59:11.257962: step: 368/1545, loss: 0.22168532013893127 2023-01-23 13:59:12.103466: step: 370/1545, loss: 0.022152423858642578 2023-01-23 13:59:13.031922: step: 372/1545, loss: 0.07013165950775146 2023-01-23 13:59:13.874450: step: 374/1545, loss: 0.0017216294072568417 2023-01-23 13:59:14.768515: step: 376/1545, loss: 0.014463198371231556 2023-01-23 13:59:15.643711: step: 378/1545, loss: 0.01678878627717495 2023-01-23 13:59:16.539554: step: 380/1545, loss: 0.08987759798765182 2023-01-23 13:59:17.406653: step: 382/1545, loss: 0.1544628143310547 2023-01-23 13:59:18.242902: step: 384/1545, loss: 0.28726068139076233 2023-01-23 13:59:19.132818: step: 386/1545, loss: 0.0432276651263237 2023-01-23 13:59:20.029330: step: 388/1545, loss: 0.013626517727971077 2023-01-23 13:59:20.896560: step: 390/1545, loss: 0.1083064079284668 2023-01-23 13:59:21.736144: step: 392/1545, loss: 0.0002322749642189592 2023-01-23 13:59:22.636994: step: 394/1545, loss: 0.04030037671327591 2023-01-23 13:59:23.540228: step: 396/1545, loss: 0.11721650511026382 2023-01-23 13:59:24.438029: step: 398/1545, loss: 0.13509714603424072 2023-01-23 13:59:25.313654: step: 400/1545, loss: 0.05148101970553398 2023-01-23 13:59:26.191534: step: 402/1545, loss: 0.016051575541496277 2023-01-23 13:59:27.078547: step: 404/1545, loss: 0.004009697586297989 2023-01-23 13:59:27.931364: step: 406/1545, loss: 0.38720324635505676 2023-01-23 13:59:28.785706: step: 408/1545, loss: 0.02349187806248665 2023-01-23 13:59:29.732388: step: 410/1545, loss: 0.44739392399787903 2023-01-23 13:59:30.714268: step: 412/1545, loss: 0.07791361957788467 2023-01-23 13:59:31.566798: step: 414/1545, loss: 0.031617891043424606 2023-01-23 13:59:32.428146: step: 416/1545, loss: 0.02989066019654274 2023-01-23 13:59:33.320352: step: 418/1545, loss: 0.009947807528078556 2023-01-23 13:59:34.220518: step: 420/1545, loss: 0.003473445540294051 2023-01-23 13:59:35.092970: step: 422/1545, loss: 0.009671318344771862 2023-01-23 13:59:35.986388: step: 424/1545, loss: 0.022783732041716576 2023-01-23 13:59:36.869321: step: 426/1545, loss: 0.3473903238773346 2023-01-23 13:59:37.713816: step: 428/1545, loss: 0.010830703191459179 2023-01-23 13:59:38.602102: step: 430/1545, loss: 0.003912656102329493 2023-01-23 13:59:39.461464: step: 432/1545, loss: 0.0016761637525632977 2023-01-23 13:59:40.328160: step: 434/1545, loss: 0.0039968350902199745 2023-01-23 13:59:41.217519: step: 436/1545, loss: 0.03264087066054344 2023-01-23 13:59:42.062626: step: 438/1545, loss: 0.008006651885807514 2023-01-23 13:59:42.907328: step: 440/1545, loss: 0.002183883683755994 2023-01-23 13:59:43.729010: step: 442/1545, loss: 0.7314338684082031 2023-01-23 13:59:44.569124: step: 444/1545, loss: 0.01006939448416233 2023-01-23 13:59:45.469677: step: 446/1545, loss: 0.029350366443395615 2023-01-23 13:59:46.385937: step: 448/1545, loss: 0.005434139631688595 2023-01-23 13:59:47.257809: step: 450/1545, loss: 0.1595248430967331 2023-01-23 13:59:48.142073: step: 452/1545, loss: 0.10055862367153168 2023-01-23 13:59:49.031839: step: 454/1545, loss: 0.032170847058296204 2023-01-23 13:59:49.880830: step: 456/1545, loss: 0.23771509528160095 2023-01-23 13:59:50.742926: step: 458/1545, loss: 0.1139163076877594 2023-01-23 13:59:51.650390: step: 460/1545, loss: 0.16209708154201508 2023-01-23 13:59:52.570850: step: 462/1545, loss: 0.05334612727165222 2023-01-23 13:59:53.423827: step: 464/1545, loss: 0.09429832547903061 2023-01-23 13:59:54.384184: step: 466/1545, loss: 0.47013184428215027 2023-01-23 13:59:55.235539: step: 468/1545, loss: 0.1352185308933258 2023-01-23 13:59:56.128304: step: 470/1545, loss: 0.15101294219493866 2023-01-23 13:59:57.012489: step: 472/1545, loss: 0.00920129008591175 2023-01-23 13:59:57.876738: step: 474/1545, loss: 0.004355092532932758 2023-01-23 13:59:58.774358: step: 476/1545, loss: 0.2706651985645294 2023-01-23 13:59:59.646010: step: 478/1545, loss: 0.024395857006311417 2023-01-23 14:00:00.612149: step: 480/1545, loss: 0.027259226888418198 2023-01-23 14:00:01.517304: step: 482/1545, loss: 0.01613062620162964 2023-01-23 14:00:02.383718: step: 484/1545, loss: 0.14690075814723969 2023-01-23 14:00:03.291954: step: 486/1545, loss: 0.17943094670772552 2023-01-23 14:00:04.204182: step: 488/1545, loss: 0.03287285193800926 2023-01-23 14:00:05.033258: step: 490/1545, loss: 0.008086537942290306 2023-01-23 14:00:05.893373: step: 492/1545, loss: 0.01164249423891306 2023-01-23 14:00:06.725513: step: 494/1545, loss: 0.0020207015331834555 2023-01-23 14:00:07.714878: step: 496/1545, loss: 0.42256960272789 2023-01-23 14:00:08.608024: step: 498/1545, loss: 0.11304248869419098 2023-01-23 14:00:09.543737: step: 500/1545, loss: 0.013442793861031532 2023-01-23 14:00:10.395339: step: 502/1545, loss: 0.2839006781578064 2023-01-23 14:00:11.247284: step: 504/1545, loss: 0.023752320557832718 2023-01-23 14:00:12.137518: step: 506/1545, loss: 0.0034117340110242367 2023-01-23 14:00:13.035019: step: 508/1545, loss: 0.08202953636646271 2023-01-23 14:00:13.903522: step: 510/1545, loss: 0.010824217461049557 2023-01-23 14:00:14.805050: step: 512/1545, loss: 0.005002783145755529 2023-01-23 14:00:15.721437: step: 514/1545, loss: 0.1294298768043518 2023-01-23 14:00:16.659332: step: 516/1545, loss: 0.21472041308879852 2023-01-23 14:00:17.528617: step: 518/1545, loss: 0.1867482215166092 2023-01-23 14:00:18.371468: step: 520/1545, loss: 0.002111393492668867 2023-01-23 14:00:19.293013: step: 522/1545, loss: 0.005386929027736187 2023-01-23 14:00:20.203406: step: 524/1545, loss: 0.1194465160369873 2023-01-23 14:00:21.077011: step: 526/1545, loss: 0.002388392575085163 2023-01-23 14:00:21.971806: step: 528/1545, loss: 0.15215164422988892 2023-01-23 14:00:22.849227: step: 530/1545, loss: 0.07559797167778015 2023-01-23 14:00:23.700490: step: 532/1545, loss: 0.0017025992274284363 2023-01-23 14:00:24.573547: step: 534/1545, loss: 0.16487833857536316 2023-01-23 14:00:25.498998: step: 536/1545, loss: 0.02918684296309948 2023-01-23 14:00:26.433909: step: 538/1545, loss: 0.0014331575948745012 2023-01-23 14:00:27.347447: step: 540/1545, loss: 0.14226047694683075 2023-01-23 14:00:28.215262: step: 542/1545, loss: 0.0021145734935998917 2023-01-23 14:00:29.109806: step: 544/1545, loss: 0.005524280481040478 2023-01-23 14:00:29.998963: step: 546/1545, loss: 0.06266939640045166 2023-01-23 14:00:30.943093: step: 548/1545, loss: 0.008232885971665382 2023-01-23 14:00:31.858112: step: 550/1545, loss: 0.10770433396100998 2023-01-23 14:00:32.705401: step: 552/1545, loss: 0.017627058550715446 2023-01-23 14:00:33.575118: step: 554/1545, loss: 0.058012284338474274 2023-01-23 14:00:34.432141: step: 556/1545, loss: 0.0076874028891325 2023-01-23 14:00:35.298255: step: 558/1545, loss: 0.0007656791131012142 2023-01-23 14:00:36.148998: step: 560/1545, loss: 0.014354354701936245 2023-01-23 14:00:37.095883: step: 562/1545, loss: 0.0031262747943401337 2023-01-23 14:00:37.921179: step: 564/1545, loss: 0.021149005740880966 2023-01-23 14:00:38.849059: step: 566/1545, loss: 0.20560643076896667 2023-01-23 14:00:39.738630: step: 568/1545, loss: 0.12934774160385132 2023-01-23 14:00:40.607177: step: 570/1545, loss: 0.12925578653812408 2023-01-23 14:00:41.448402: step: 572/1545, loss: 0.02999955788254738 2023-01-23 14:00:42.332174: step: 574/1545, loss: 0.06232214719057083 2023-01-23 14:00:43.317212: step: 576/1545, loss: 0.002195454202592373 2023-01-23 14:00:44.174507: step: 578/1545, loss: 0.0032138170208781958 2023-01-23 14:00:45.098869: step: 580/1545, loss: 0.37142014503479004 2023-01-23 14:00:45.960287: step: 582/1545, loss: 0.10329193621873856 2023-01-23 14:00:46.867027: step: 584/1545, loss: 0.16822373867034912 2023-01-23 14:00:47.778796: step: 586/1545, loss: 0.0014322116039693356 2023-01-23 14:00:48.655052: step: 588/1545, loss: 0.1441100388765335 2023-01-23 14:00:49.542846: step: 590/1545, loss: 0.015326686203479767 2023-01-23 14:00:50.413530: step: 592/1545, loss: 0.003692952450364828 2023-01-23 14:00:51.312669: step: 594/1545, loss: 0.12030339241027832 2023-01-23 14:00:52.222811: step: 596/1545, loss: 0.09506722539663315 2023-01-23 14:00:53.109408: step: 598/1545, loss: 0.11572584509849548 2023-01-23 14:00:53.967065: step: 600/1545, loss: 0.03964436426758766 2023-01-23 14:00:54.895603: step: 602/1545, loss: 0.002317420206964016 2023-01-23 14:00:55.826562: step: 604/1545, loss: 0.004384230822324753 2023-01-23 14:00:56.681876: step: 606/1545, loss: 0.11794300377368927 2023-01-23 14:00:57.570759: step: 608/1545, loss: 0.023559248074889183 2023-01-23 14:00:58.448931: step: 610/1545, loss: 0.0909675657749176 2023-01-23 14:00:59.413484: step: 612/1545, loss: 0.04442417994141579 2023-01-23 14:01:00.341845: step: 614/1545, loss: 0.013067088089883327 2023-01-23 14:01:01.216402: step: 616/1545, loss: 0.01151957456022501 2023-01-23 14:01:02.082576: step: 618/1545, loss: 0.012793933972716331 2023-01-23 14:01:02.951377: step: 620/1545, loss: 0.01480371318757534 2023-01-23 14:01:03.872414: step: 622/1545, loss: 0.009796717204153538 2023-01-23 14:01:04.715844: step: 624/1545, loss: 0.002138052601367235 2023-01-23 14:01:05.565493: step: 626/1545, loss: 0.008532372303307056 2023-01-23 14:01:06.427285: step: 628/1545, loss: 0.01158132404088974 2023-01-23 14:01:07.353920: step: 630/1545, loss: 0.014670869335532188 2023-01-23 14:01:08.300746: step: 632/1545, loss: 0.12289759516716003 2023-01-23 14:01:09.191764: step: 634/1545, loss: 0.18153086304664612 2023-01-23 14:01:10.077185: step: 636/1545, loss: 0.008453932590782642 2023-01-23 14:01:10.927177: step: 638/1545, loss: 0.007148736622184515 2023-01-23 14:01:11.834530: step: 640/1545, loss: 0.03644540533423424 2023-01-23 14:01:12.697762: step: 642/1545, loss: 0.0005540909478440881 2023-01-23 14:01:13.566847: step: 644/1545, loss: 0.1435561180114746 2023-01-23 14:01:14.417593: step: 646/1545, loss: 0.04750312119722366 2023-01-23 14:01:15.319410: step: 648/1545, loss: 0.6113395094871521 2023-01-23 14:01:16.177091: step: 650/1545, loss: 0.011870529502630234 2023-01-23 14:01:17.050197: step: 652/1545, loss: 0.04776133596897125 2023-01-23 14:01:17.918215: step: 654/1545, loss: 0.0047250366769731045 2023-01-23 14:01:18.788218: step: 656/1545, loss: 0.0467194989323616 2023-01-23 14:01:19.747389: step: 658/1545, loss: 0.05301680415868759 2023-01-23 14:01:20.576880: step: 660/1545, loss: 0.006235212553292513 2023-01-23 14:01:21.457057: step: 662/1545, loss: 0.49659979343414307 2023-01-23 14:01:22.331547: step: 664/1545, loss: 1.1177934408187866 2023-01-23 14:01:23.298862: step: 666/1545, loss: 0.007513861637562513 2023-01-23 14:01:24.193012: step: 668/1545, loss: 0.012384233996272087 2023-01-23 14:01:25.056556: step: 670/1545, loss: 0.0026049790903925896 2023-01-23 14:01:25.956833: step: 672/1545, loss: 0.06858507543802261 2023-01-23 14:01:26.880012: step: 674/1545, loss: 0.023199835792183876 2023-01-23 14:01:27.774532: step: 676/1545, loss: 0.010543569922447205 2023-01-23 14:01:28.634774: step: 678/1545, loss: 0.003564930520951748 2023-01-23 14:01:29.519050: step: 680/1545, loss: 0.044151000678539276 2023-01-23 14:01:30.421114: step: 682/1545, loss: 0.047860223799943924 2023-01-23 14:01:31.289372: step: 684/1545, loss: 0.0011490778997540474 2023-01-23 14:01:32.275162: step: 686/1545, loss: 0.44326791167259216 2023-01-23 14:01:33.133402: step: 688/1545, loss: 0.0010739450808614492 2023-01-23 14:01:34.130523: step: 690/1545, loss: 0.010222877375781536 2023-01-23 14:01:35.026741: step: 692/1545, loss: 0.01078046578913927 2023-01-23 14:01:35.927019: step: 694/1545, loss: 0.010998481884598732 2023-01-23 14:01:36.812547: step: 696/1545, loss: 0.005193687509745359 2023-01-23 14:01:37.718705: step: 698/1545, loss: 0.11948201060295105 2023-01-23 14:01:38.573755: step: 700/1545, loss: 0.0006746931467205286 2023-01-23 14:01:39.426163: step: 702/1545, loss: 0.0006727888248860836 2023-01-23 14:01:40.334293: step: 704/1545, loss: 0.013654755428433418 2023-01-23 14:01:41.296677: step: 706/1545, loss: 0.13135826587677002 2023-01-23 14:01:42.201047: step: 708/1545, loss: 0.15035904943943024 2023-01-23 14:01:43.102909: step: 710/1545, loss: 0.000294651894364506 2023-01-23 14:01:43.954216: step: 712/1545, loss: 0.010066526010632515 2023-01-23 14:01:44.818029: step: 714/1545, loss: 0.3119644522666931 2023-01-23 14:01:45.739813: step: 716/1545, loss: 0.1335570514202118 2023-01-23 14:01:46.586690: step: 718/1545, loss: 0.0009156910236924887 2023-01-23 14:01:47.481983: step: 720/1545, loss: 0.6337462663650513 2023-01-23 14:01:48.315359: step: 722/1545, loss: 0.04761078953742981 2023-01-23 14:01:49.250494: step: 724/1545, loss: 0.000644537853077054 2023-01-23 14:01:50.122781: step: 726/1545, loss: 0.11035877466201782 2023-01-23 14:01:50.993457: step: 728/1545, loss: 0.87180095911026 2023-01-23 14:01:51.894455: step: 730/1545, loss: 0.029917020350694656 2023-01-23 14:01:52.772669: step: 732/1545, loss: 0.362440824508667 2023-01-23 14:01:53.601669: step: 734/1545, loss: 0.19940970838069916 2023-01-23 14:01:54.495265: step: 736/1545, loss: 0.010382983833551407 2023-01-23 14:01:55.352990: step: 738/1545, loss: 0.0053836870938539505 2023-01-23 14:01:56.269646: step: 740/1545, loss: 0.008360234089195728 2023-01-23 14:01:57.144421: step: 742/1545, loss: 0.13477663695812225 2023-01-23 14:01:58.054371: step: 744/1545, loss: 0.007604777812957764 2023-01-23 14:01:58.979124: step: 746/1545, loss: 0.0027510235086083412 2023-01-23 14:01:59.852994: step: 748/1545, loss: 0.00860811397433281 2023-01-23 14:02:00.745769: step: 750/1545, loss: 0.007825502194464207 2023-01-23 14:02:01.610769: step: 752/1545, loss: 0.036158014088869095 2023-01-23 14:02:02.540533: step: 754/1545, loss: 0.048683781176805496 2023-01-23 14:02:03.417452: step: 756/1545, loss: 0.4258991479873657 2023-01-23 14:02:04.299105: step: 758/1545, loss: 0.13359802961349487 2023-01-23 14:02:05.203922: step: 760/1545, loss: 0.020158380270004272 2023-01-23 14:02:06.084973: step: 762/1545, loss: 0.2444191426038742 2023-01-23 14:02:06.962980: step: 764/1545, loss: 0.043295495212078094 2023-01-23 14:02:07.859263: step: 766/1545, loss: 0.011909203603863716 2023-01-23 14:02:08.795301: step: 768/1545, loss: 0.030812304466962814 2023-01-23 14:02:09.740658: step: 770/1545, loss: 0.07779645174741745 2023-01-23 14:02:10.589320: step: 772/1545, loss: 0.053037043660879135 2023-01-23 14:02:11.477751: step: 774/1545, loss: 0.03944802284240723 2023-01-23 14:02:12.380165: step: 776/1545, loss: 0.2633827328681946 2023-01-23 14:02:13.323437: step: 778/1545, loss: 0.001975700259208679 2023-01-23 14:02:14.211148: step: 780/1545, loss: 0.006434508133679628 2023-01-23 14:02:15.070684: step: 782/1545, loss: 0.0021458964329212904 2023-01-23 14:02:15.989733: step: 784/1545, loss: 0.002646747278049588 2023-01-23 14:02:16.828437: step: 786/1545, loss: 0.23803044855594635 2023-01-23 14:02:17.700570: step: 788/1545, loss: 0.00020291071268729866 2023-01-23 14:02:18.680347: step: 790/1545, loss: 0.18949569761753082 2023-01-23 14:02:19.663577: step: 792/1545, loss: 0.032887741923332214 2023-01-23 14:02:20.530937: step: 794/1545, loss: 0.020615091547369957 2023-01-23 14:02:21.448490: step: 796/1545, loss: 0.007603147998452187 2023-01-23 14:02:22.317407: step: 798/1545, loss: 0.09611696749925613 2023-01-23 14:02:23.228432: step: 800/1545, loss: 0.0068604000844061375 2023-01-23 14:02:24.094061: step: 802/1545, loss: 0.11320122331380844 2023-01-23 14:02:24.971504: step: 804/1545, loss: 0.0028855237178504467 2023-01-23 14:02:25.848836: step: 806/1545, loss: 0.23326006531715393 2023-01-23 14:02:26.716534: step: 808/1545, loss: 0.19052202999591827 2023-01-23 14:02:27.575625: step: 810/1545, loss: 0.11873187124729156 2023-01-23 14:02:28.489323: step: 812/1545, loss: 0.11052460223436356 2023-01-23 14:02:29.356969: step: 814/1545, loss: 0.009631833992898464 2023-01-23 14:02:30.256534: step: 816/1545, loss: 0.03282606229186058 2023-01-23 14:02:31.096841: step: 818/1545, loss: 0.014514711685478687 2023-01-23 14:02:31.964427: step: 820/1545, loss: 0.10012304782867432 2023-01-23 14:02:32.836352: step: 822/1545, loss: 0.30597320199012756 2023-01-23 14:02:33.731944: step: 824/1545, loss: 0.004562330897897482 2023-01-23 14:02:34.594586: step: 826/1545, loss: 0.36924609541893005 2023-01-23 14:02:35.527451: step: 828/1545, loss: 0.09701170772314072 2023-01-23 14:02:36.407041: step: 830/1545, loss: 0.02342393435537815 2023-01-23 14:02:37.311285: step: 832/1545, loss: 0.07919523864984512 2023-01-23 14:02:38.160952: step: 834/1545, loss: 0.0028518883045762777 2023-01-23 14:02:39.052748: step: 836/1545, loss: 0.2751714885234833 2023-01-23 14:02:39.995736: step: 838/1545, loss: 0.012547684833407402 2023-01-23 14:02:40.900527: step: 840/1545, loss: 0.1426667422056198 2023-01-23 14:02:41.812193: step: 842/1545, loss: 0.07816141843795776 2023-01-23 14:02:42.723659: step: 844/1545, loss: 0.0006236190674826503 2023-01-23 14:02:43.586278: step: 846/1545, loss: 0.049921076744794846 2023-01-23 14:02:44.493540: step: 848/1545, loss: 0.0061141145415604115 2023-01-23 14:02:45.395250: step: 850/1545, loss: 0.004019514657557011 2023-01-23 14:02:46.252993: step: 852/1545, loss: 0.024274645373225212 2023-01-23 14:02:47.168327: step: 854/1545, loss: 0.039662301540374756 2023-01-23 14:02:48.037510: step: 856/1545, loss: 0.05706603825092316 2023-01-23 14:02:48.897600: step: 858/1545, loss: 0.13565285503864288 2023-01-23 14:02:49.742241: step: 860/1545, loss: 0.002581784501671791 2023-01-23 14:02:50.610700: step: 862/1545, loss: 0.018043527379631996 2023-01-23 14:02:51.481778: step: 864/1545, loss: 0.0018397236708551645 2023-01-23 14:02:52.292803: step: 866/1545, loss: 0.012652872130274773 2023-01-23 14:02:53.223169: step: 868/1545, loss: 0.2106246054172516 2023-01-23 14:02:54.138931: step: 870/1545, loss: 0.0022518252953886986 2023-01-23 14:02:55.012343: step: 872/1545, loss: 0.0324101597070694 2023-01-23 14:02:55.914367: step: 874/1545, loss: 0.04155111685395241 2023-01-23 14:02:56.802401: step: 876/1545, loss: 0.0025272115599364042 2023-01-23 14:02:57.709673: step: 878/1545, loss: 0.00983879528939724 2023-01-23 14:02:58.589763: step: 880/1545, loss: 0.20949886739253998 2023-01-23 14:02:59.462631: step: 882/1545, loss: 0.012242752127349377 2023-01-23 14:03:00.374832: step: 884/1545, loss: 0.007139463443309069 2023-01-23 14:03:01.231849: step: 886/1545, loss: 0.008896456100046635 2023-01-23 14:03:02.101802: step: 888/1545, loss: 0.018245035782456398 2023-01-23 14:03:02.964578: step: 890/1545, loss: 0.008397550322115421 2023-01-23 14:03:03.848805: step: 892/1545, loss: 0.03509488329291344 2023-01-23 14:03:04.719025: step: 894/1545, loss: 0.10298570245504379 2023-01-23 14:03:05.608684: step: 896/1545, loss: 0.006195803172886372 2023-01-23 14:03:06.483777: step: 898/1545, loss: 0.28007808327674866 2023-01-23 14:03:07.345451: step: 900/1545, loss: 0.0010081174550577998 2023-01-23 14:03:08.273203: step: 902/1545, loss: 0.17578551173210144 2023-01-23 14:03:09.190993: step: 904/1545, loss: 0.01571008190512657 2023-01-23 14:03:10.043597: step: 906/1545, loss: 0.04461770877242088 2023-01-23 14:03:10.937498: step: 908/1545, loss: 0.18088805675506592 2023-01-23 14:03:11.797596: step: 910/1545, loss: 0.058649130165576935 2023-01-23 14:03:12.675980: step: 912/1545, loss: 0.0031281004194170237 2023-01-23 14:03:13.544679: step: 914/1545, loss: 0.026933223009109497 2023-01-23 14:03:14.401835: step: 916/1545, loss: 0.15877215564250946 2023-01-23 14:03:15.268130: step: 918/1545, loss: 0.011355817317962646 2023-01-23 14:03:16.135128: step: 920/1545, loss: 0.07698006927967072 2023-01-23 14:03:17.123868: step: 922/1545, loss: 0.020061342045664787 2023-01-23 14:03:18.040192: step: 924/1545, loss: 0.00587936956435442 2023-01-23 14:03:18.969257: step: 926/1545, loss: 0.006376133766025305 2023-01-23 14:03:19.869902: step: 928/1545, loss: 0.0006991586997173727 2023-01-23 14:03:20.725874: step: 930/1545, loss: 0.006457654293626547 2023-01-23 14:03:21.645313: step: 932/1545, loss: 0.01277039386332035 2023-01-23 14:03:22.491217: step: 934/1545, loss: 0.14922036230564117 2023-01-23 14:03:23.353695: step: 936/1545, loss: 0.009521418251097202 2023-01-23 14:03:24.215399: step: 938/1545, loss: 0.1695723682641983 2023-01-23 14:03:25.095050: step: 940/1545, loss: 0.04223084822297096 2023-01-23 14:03:25.958320: step: 942/1545, loss: 0.003655347041785717 2023-01-23 14:03:26.839072: step: 944/1545, loss: 0.004000082612037659 2023-01-23 14:03:27.784282: step: 946/1545, loss: 0.00012032761151203886 2023-01-23 14:03:28.644939: step: 948/1545, loss: 0.12796437740325928 2023-01-23 14:03:29.526050: step: 950/1545, loss: 0.013938210904598236 2023-01-23 14:03:30.448906: step: 952/1545, loss: 0.1493281126022339 2023-01-23 14:03:31.348613: step: 954/1545, loss: 0.0025353459641337395 2023-01-23 14:03:32.278977: step: 956/1545, loss: 0.09396114945411682 2023-01-23 14:03:33.190404: step: 958/1545, loss: 0.4541873037815094 2023-01-23 14:03:34.047313: step: 960/1545, loss: 0.20551945269107819 2023-01-23 14:03:34.915267: step: 962/1545, loss: 0.00257879844866693 2023-01-23 14:03:35.766097: step: 964/1545, loss: 0.007984432391822338 2023-01-23 14:03:36.628383: step: 966/1545, loss: 0.03743031993508339 2023-01-23 14:03:37.528374: step: 968/1545, loss: 0.02492578886449337 2023-01-23 14:03:38.415025: step: 970/1545, loss: 0.022681791335344315 2023-01-23 14:03:39.305355: step: 972/1545, loss: 0.003963057417422533 2023-01-23 14:03:40.210676: step: 974/1545, loss: 8.057014201767743e-05 2023-01-23 14:03:41.056532: step: 976/1545, loss: 0.0020985722076147795 2023-01-23 14:03:41.947696: step: 978/1545, loss: 0.011019802652299404 2023-01-23 14:03:42.828030: step: 980/1545, loss: 0.13319621980190277 2023-01-23 14:03:43.729155: step: 982/1545, loss: 0.07106897979974747 2023-01-23 14:03:44.593944: step: 984/1545, loss: 0.14678287506103516 2023-01-23 14:03:45.480381: step: 986/1545, loss: 0.045778997242450714 2023-01-23 14:03:46.337742: step: 988/1545, loss: 0.02893085777759552 2023-01-23 14:03:47.191240: step: 990/1545, loss: 0.008527793921530247 2023-01-23 14:03:48.066907: step: 992/1545, loss: 0.0068533397279679775 2023-01-23 14:03:48.964023: step: 994/1545, loss: 0.019596047699451447 2023-01-23 14:03:49.841516: step: 996/1545, loss: 0.009439256973564625 2023-01-23 14:03:50.728445: step: 998/1545, loss: 0.013951864093542099 2023-01-23 14:03:51.566639: step: 1000/1545, loss: 0.0007412884733639657 2023-01-23 14:03:52.456804: step: 1002/1545, loss: 0.16203562915325165 2023-01-23 14:03:53.399947: step: 1004/1545, loss: 0.0008362196967937052 2023-01-23 14:03:54.320683: step: 1006/1545, loss: 0.011474492028355598 2023-01-23 14:03:55.212499: step: 1008/1545, loss: 0.013387778773903847 2023-01-23 14:03:56.078802: step: 1010/1545, loss: 0.09651871025562286 2023-01-23 14:03:56.945670: step: 1012/1545, loss: 0.1462893784046173 2023-01-23 14:03:57.816985: step: 1014/1545, loss: 0.013925403356552124 2023-01-23 14:03:58.747120: step: 1016/1545, loss: 0.03100544959306717 2023-01-23 14:03:59.623296: step: 1018/1545, loss: 0.03895900025963783 2023-01-23 14:04:00.504178: step: 1020/1545, loss: 0.00438309833407402 2023-01-23 14:04:01.405860: step: 1022/1545, loss: 0.4163797199726105 2023-01-23 14:04:02.258005: step: 1024/1545, loss: 0.006029993761330843 2023-01-23 14:04:03.114743: step: 1026/1545, loss: 0.1937524974346161 2023-01-23 14:04:04.008844: step: 1028/1545, loss: 0.010375072248280048 2023-01-23 14:04:04.895057: step: 1030/1545, loss: 0.026578018441796303 2023-01-23 14:04:05.774332: step: 1032/1545, loss: 0.03473303094506264 2023-01-23 14:04:06.671986: step: 1034/1545, loss: 0.0715315043926239 2023-01-23 14:04:07.569087: step: 1036/1545, loss: 0.0016198726370930672 2023-01-23 14:04:08.521912: step: 1038/1545, loss: 0.05814824625849724 2023-01-23 14:04:09.493012: step: 1040/1545, loss: 0.07607360184192657 2023-01-23 14:04:10.340826: step: 1042/1545, loss: 0.29953819513320923 2023-01-23 14:04:11.225375: step: 1044/1545, loss: 0.02225692756474018 2023-01-23 14:04:12.099880: step: 1046/1545, loss: 0.01013815589249134 2023-01-23 14:04:12.981111: step: 1048/1545, loss: 0.20470060408115387 2023-01-23 14:04:13.893166: step: 1050/1545, loss: 0.004020769149065018 2023-01-23 14:04:14.793234: step: 1052/1545, loss: 0.07621821016073227 2023-01-23 14:04:15.721994: step: 1054/1545, loss: 0.17782196402549744 2023-01-23 14:04:16.592104: step: 1056/1545, loss: 0.04251088947057724 2023-01-23 14:04:17.455861: step: 1058/1545, loss: 0.007005107589066029 2023-01-23 14:04:18.371783: step: 1060/1545, loss: 0.024637877941131592 2023-01-23 14:04:19.339312: step: 1062/1545, loss: 0.19229300320148468 2023-01-23 14:04:20.193248: step: 1064/1545, loss: 0.028189921751618385 2023-01-23 14:04:21.129375: step: 1066/1545, loss: 0.002861626911908388 2023-01-23 14:04:22.017141: step: 1068/1545, loss: 0.028963344171643257 2023-01-23 14:04:22.896816: step: 1070/1545, loss: 0.09717977792024612 2023-01-23 14:04:23.792612: step: 1072/1545, loss: 0.12467555701732635 2023-01-23 14:04:24.642147: step: 1074/1545, loss: 0.00620818417519331 2023-01-23 14:04:25.537178: step: 1076/1545, loss: 0.005860941018909216 2023-01-23 14:04:26.417085: step: 1078/1545, loss: 0.0006888617645017803 2023-01-23 14:04:27.329891: step: 1080/1545, loss: 0.017323467880487442 2023-01-23 14:04:28.195813: step: 1082/1545, loss: 0.0006558657623827457 2023-01-23 14:04:29.048504: step: 1084/1545, loss: 0.02975519746541977 2023-01-23 14:04:29.910612: step: 1086/1545, loss: 0.023973437026143074 2023-01-23 14:04:30.841605: step: 1088/1545, loss: 0.019399844110012054 2023-01-23 14:04:31.670226: step: 1090/1545, loss: 0.037083111703395844 2023-01-23 14:04:32.572390: step: 1092/1545, loss: 0.047919392585754395 2023-01-23 14:04:33.407290: step: 1094/1545, loss: 0.0010736612603068352 2023-01-23 14:04:34.284695: step: 1096/1545, loss: 0.0031031982507556677 2023-01-23 14:04:35.276867: step: 1098/1545, loss: 0.11547641456127167 2023-01-23 14:04:36.147742: step: 1100/1545, loss: 0.12760406732559204 2023-01-23 14:04:37.020107: step: 1102/1545, loss: 0.031699199229478836 2023-01-23 14:04:37.964885: step: 1104/1545, loss: 0.031715065240859985 2023-01-23 14:04:38.822411: step: 1106/1545, loss: 0.07069142162799835 2023-01-23 14:04:39.708507: step: 1108/1545, loss: 0.032022133469581604 2023-01-23 14:04:40.554991: step: 1110/1545, loss: 0.0755939781665802 2023-01-23 14:04:41.423185: step: 1112/1545, loss: 0.1465374082326889 2023-01-23 14:04:42.292696: step: 1114/1545, loss: 0.041082173585891724 2023-01-23 14:04:43.164390: step: 1116/1545, loss: 0.04552645981311798 2023-01-23 14:04:44.054521: step: 1118/1545, loss: 0.08137340098619461 2023-01-23 14:04:44.946183: step: 1120/1545, loss: 0.07669683545827866 2023-01-23 14:04:45.803100: step: 1122/1545, loss: 0.010944750159978867 2023-01-23 14:04:46.644540: step: 1124/1545, loss: 0.022821662947535515 2023-01-23 14:04:47.495722: step: 1126/1545, loss: 0.029375489801168442 2023-01-23 14:04:48.366627: step: 1128/1545, loss: 0.0093885138630867 2023-01-23 14:04:49.276397: step: 1130/1545, loss: 0.010526116006076336 2023-01-23 14:04:50.188197: step: 1132/1545, loss: 0.1001034528017044 2023-01-23 14:04:51.118107: step: 1134/1545, loss: 0.05035559833049774 2023-01-23 14:04:51.979942: step: 1136/1545, loss: 0.23857681453227997 2023-01-23 14:04:52.832601: step: 1138/1545, loss: 0.00038112959009595215 2023-01-23 14:04:53.688166: step: 1140/1545, loss: 0.02258031815290451 2023-01-23 14:04:54.656581: step: 1142/1545, loss: 1.109519124031067 2023-01-23 14:04:55.540501: step: 1144/1545, loss: 0.0031226924620568752 2023-01-23 14:04:56.418873: step: 1146/1545, loss: 0.014142109081149101 2023-01-23 14:04:57.280170: step: 1148/1545, loss: 0.03448988124728203 2023-01-23 14:04:58.161998: step: 1150/1545, loss: 0.025799520313739777 2023-01-23 14:04:59.097560: step: 1152/1545, loss: 0.0062249330803751945 2023-01-23 14:04:59.982443: step: 1154/1545, loss: 1.343838095664978 2023-01-23 14:05:00.845628: step: 1156/1545, loss: 0.3185056149959564 2023-01-23 14:05:01.732795: step: 1158/1545, loss: 0.21474213898181915 2023-01-23 14:05:02.693603: step: 1160/1545, loss: 0.45459115505218506 2023-01-23 14:05:03.595998: step: 1162/1545, loss: 0.06762874871492386 2023-01-23 14:05:04.443760: step: 1164/1545, loss: 0.1853076070547104 2023-01-23 14:05:05.351238: step: 1166/1545, loss: 0.035556502640247345 2023-01-23 14:05:06.199524: step: 1168/1545, loss: 0.002048086142167449 2023-01-23 14:05:07.087077: step: 1170/1545, loss: 0.007124498952180147 2023-01-23 14:05:07.975443: step: 1172/1545, loss: 0.03895965963602066 2023-01-23 14:05:08.816057: step: 1174/1545, loss: 0.000797316140960902 2023-01-23 14:05:09.656324: step: 1176/1545, loss: 0.0615088976919651 2023-01-23 14:05:10.543896: step: 1178/1545, loss: 0.03275974839925766 2023-01-23 14:05:11.447447: step: 1180/1545, loss: 0.054032787680625916 2023-01-23 14:05:12.337173: step: 1182/1545, loss: 0.017605502158403397 2023-01-23 14:05:13.208835: step: 1184/1545, loss: 0.0006213430897332728 2023-01-23 14:05:14.102197: step: 1186/1545, loss: 0.007724257186055183 2023-01-23 14:05:14.966733: step: 1188/1545, loss: 0.28639116883277893 2023-01-23 14:05:15.835160: step: 1190/1545, loss: 0.002062280895188451 2023-01-23 14:05:16.770173: step: 1192/1545, loss: 0.2215130627155304 2023-01-23 14:05:17.706099: step: 1194/1545, loss: 0.0022989711724221706 2023-01-23 14:05:18.582401: step: 1196/1545, loss: 0.07068899273872375 2023-01-23 14:05:19.453160: step: 1198/1545, loss: 0.058465566486120224 2023-01-23 14:05:20.328724: step: 1200/1545, loss: 0.054187849164009094 2023-01-23 14:05:21.173525: step: 1202/1545, loss: 0.06442353129386902 2023-01-23 14:05:22.062350: step: 1204/1545, loss: 0.03606770560145378 2023-01-23 14:05:22.916407: step: 1206/1545, loss: 0.010303355753421783 2023-01-23 14:05:23.820732: step: 1208/1545, loss: 0.005176665727049112 2023-01-23 14:05:24.671174: step: 1210/1545, loss: 0.06650570034980774 2023-01-23 14:05:25.526245: step: 1212/1545, loss: 0.0974518209695816 2023-01-23 14:05:26.363263: step: 1214/1545, loss: 0.09947141259908676 2023-01-23 14:05:27.286346: step: 1216/1545, loss: 0.15575003623962402 2023-01-23 14:05:28.183646: step: 1218/1545, loss: 0.016802262514829636 2023-01-23 14:05:29.029890: step: 1220/1545, loss: 0.056020066142082214 2023-01-23 14:05:29.866122: step: 1222/1545, loss: 0.0015819002874195576 2023-01-23 14:05:30.711763: step: 1224/1545, loss: 0.028131995350122452 2023-01-23 14:05:31.597021: step: 1226/1545, loss: 1.1463003158569336 2023-01-23 14:05:32.454620: step: 1228/1545, loss: 0.31116488575935364 2023-01-23 14:05:33.322489: step: 1230/1545, loss: 0.007597445975989103 2023-01-23 14:05:34.160013: step: 1232/1545, loss: 0.0023350557312369347 2023-01-23 14:05:34.986929: step: 1234/1545, loss: 0.002816151361912489 2023-01-23 14:05:35.924011: step: 1236/1545, loss: 0.024144204333424568 2023-01-23 14:05:36.778728: step: 1238/1545, loss: 0.010072034783661366 2023-01-23 14:05:37.665257: step: 1240/1545, loss: 0.03134610503911972 2023-01-23 14:05:38.530264: step: 1242/1545, loss: 0.04529600962996483 2023-01-23 14:05:39.430957: step: 1244/1545, loss: 0.11706054210662842 2023-01-23 14:05:40.305667: step: 1246/1545, loss: 0.019075993448495865 2023-01-23 14:05:41.199159: step: 1248/1545, loss: 0.007985696196556091 2023-01-23 14:05:42.096610: step: 1250/1545, loss: 0.08920242637395859 2023-01-23 14:05:42.943420: step: 1252/1545, loss: 0.004960120655596256 2023-01-23 14:05:43.864035: step: 1254/1545, loss: 0.006464651320129633 2023-01-23 14:05:44.738135: step: 1256/1545, loss: 0.02029488980770111 2023-01-23 14:05:45.599179: step: 1258/1545, loss: 0.026191025972366333 2023-01-23 14:05:46.475790: step: 1260/1545, loss: 0.48576176166534424 2023-01-23 14:05:47.306349: step: 1262/1545, loss: 0.0051143052987754345 2023-01-23 14:05:48.134747: step: 1264/1545, loss: 0.01503806747496128 2023-01-23 14:05:49.017613: step: 1266/1545, loss: 0.00846314150840044 2023-01-23 14:05:49.865929: step: 1268/1545, loss: 0.016513999551534653 2023-01-23 14:05:50.765810: step: 1270/1545, loss: 0.13428984582424164 2023-01-23 14:05:51.607131: step: 1272/1545, loss: 0.0392538383603096 2023-01-23 14:05:52.483416: step: 1274/1545, loss: 0.00932136457413435 2023-01-23 14:05:53.368946: step: 1276/1545, loss: 0.030080143362283707 2023-01-23 14:05:54.235719: step: 1278/1545, loss: 0.0986022800207138 2023-01-23 14:05:55.093621: step: 1280/1545, loss: 0.44131794571876526 2023-01-23 14:05:55.927311: step: 1282/1545, loss: 0.1707412302494049 2023-01-23 14:05:56.822474: step: 1284/1545, loss: 0.07946783304214478 2023-01-23 14:05:57.708764: step: 1286/1545, loss: 0.002536798594519496 2023-01-23 14:05:58.551610: step: 1288/1545, loss: 0.03788751736283302 2023-01-23 14:05:59.416398: step: 1290/1545, loss: 0.3337702751159668 2023-01-23 14:06:00.299375: step: 1292/1545, loss: 0.0017498964443802834 2023-01-23 14:06:01.166961: step: 1294/1545, loss: 0.03930314630270004 2023-01-23 14:06:02.013207: step: 1296/1545, loss: 0.06000364199280739 2023-01-23 14:06:02.917395: step: 1298/1545, loss: 0.014815589413046837 2023-01-23 14:06:03.823186: step: 1300/1545, loss: 0.08553966879844666 2023-01-23 14:06:04.772740: step: 1302/1545, loss: 0.4506095051765442 2023-01-23 14:06:05.616625: step: 1304/1545, loss: 0.017108190804719925 2023-01-23 14:06:06.516813: step: 1306/1545, loss: 0.27090319991111755 2023-01-23 14:06:07.514362: step: 1308/1545, loss: 0.12398281693458557 2023-01-23 14:06:08.384347: step: 1310/1545, loss: 0.07562560588121414 2023-01-23 14:06:09.231710: step: 1312/1545, loss: 0.13239668309688568 2023-01-23 14:06:10.109931: step: 1314/1545, loss: 0.5718898177146912 2023-01-23 14:06:10.973877: step: 1316/1545, loss: 0.14879965782165527 2023-01-23 14:06:11.868022: step: 1318/1545, loss: 0.004626851063221693 2023-01-23 14:06:12.710432: step: 1320/1545, loss: 0.08114364743232727 2023-01-23 14:06:13.619061: step: 1322/1545, loss: 0.05577145144343376 2023-01-23 14:06:14.499731: step: 1324/1545, loss: 0.18702226877212524 2023-01-23 14:06:15.405421: step: 1326/1545, loss: 0.2238629013299942 2023-01-23 14:06:16.318562: step: 1328/1545, loss: 0.09978663176298141 2023-01-23 14:06:17.228421: step: 1330/1545, loss: 0.1021837666630745 2023-01-23 14:06:18.070245: step: 1332/1545, loss: 0.0003729464951902628 2023-01-23 14:06:18.971850: step: 1334/1545, loss: 0.0855771005153656 2023-01-23 14:06:19.825204: step: 1336/1545, loss: 0.01702822744846344 2023-01-23 14:06:20.751713: step: 1338/1545, loss: 0.009482955560088158 2023-01-23 14:06:21.602109: step: 1340/1545, loss: 0.0038995605427771807 2023-01-23 14:06:22.481140: step: 1342/1545, loss: 0.002305690199136734 2023-01-23 14:06:23.314697: step: 1344/1545, loss: 0.01944671757519245 2023-01-23 14:06:24.221331: step: 1346/1545, loss: 0.06675311923027039 2023-01-23 14:06:25.145279: step: 1348/1545, loss: 0.19082428514957428 2023-01-23 14:06:25.997362: step: 1350/1545, loss: 0.004519806709140539 2023-01-23 14:06:26.852069: step: 1352/1545, loss: 0.18489880859851837 2023-01-23 14:06:27.706758: step: 1354/1545, loss: 0.7488040924072266 2023-01-23 14:06:28.607324: step: 1356/1545, loss: 0.006807281170040369 2023-01-23 14:06:29.446849: step: 1358/1545, loss: 0.028236091136932373 2023-01-23 14:06:30.352577: step: 1360/1545, loss: 0.003255655290558934 2023-01-23 14:06:31.231322: step: 1362/1545, loss: 0.03810974955558777 2023-01-23 14:06:32.163560: step: 1364/1545, loss: 0.02360830269753933 2023-01-23 14:06:33.046345: step: 1366/1545, loss: 0.1979455202817917 2023-01-23 14:06:33.940691: step: 1368/1545, loss: 0.10390937328338623 2023-01-23 14:06:34.827006: step: 1370/1545, loss: 0.01931634172797203 2023-01-23 14:06:35.682465: step: 1372/1545, loss: 0.02399369701743126 2023-01-23 14:06:36.589660: step: 1374/1545, loss: 0.004192340187728405 2023-01-23 14:06:37.469770: step: 1376/1545, loss: 0.0748845636844635 2023-01-23 14:06:38.350637: step: 1378/1545, loss: 0.017708031460642815 2023-01-23 14:06:39.208065: step: 1380/1545, loss: 0.0720297321677208 2023-01-23 14:06:40.218506: step: 1382/1545, loss: 0.3619639575481415 2023-01-23 14:06:41.101239: step: 1384/1545, loss: 0.005235400516539812 2023-01-23 14:06:42.006344: step: 1386/1545, loss: 0.1415846049785614 2023-01-23 14:06:42.878528: step: 1388/1545, loss: 0.013904369436204433 2023-01-23 14:06:43.740837: step: 1390/1545, loss: 0.15660123527050018 2023-01-23 14:06:44.663109: step: 1392/1545, loss: 0.004373573698103428 2023-01-23 14:06:45.524549: step: 1394/1545, loss: 0.06338036060333252 2023-01-23 14:06:46.459299: step: 1396/1545, loss: 0.07915806025266647 2023-01-23 14:06:47.339401: step: 1398/1545, loss: 0.09564537554979324 2023-01-23 14:06:48.213195: step: 1400/1545, loss: 0.03149107098579407 2023-01-23 14:06:49.142818: step: 1402/1545, loss: 0.014497858472168446 2023-01-23 14:06:50.018513: step: 1404/1545, loss: 0.5431711077690125 2023-01-23 14:06:50.906743: step: 1406/1545, loss: 0.004042429383844137 2023-01-23 14:06:51.890612: step: 1408/1545, loss: 0.025690928101539612 2023-01-23 14:06:52.740822: step: 1410/1545, loss: 0.003260065568611026 2023-01-23 14:06:53.623836: step: 1412/1545, loss: 0.10249561071395874 2023-01-23 14:06:54.539462: step: 1414/1545, loss: 0.24195149540901184 2023-01-23 14:06:55.405292: step: 1416/1545, loss: 0.04024660587310791 2023-01-23 14:06:56.258380: step: 1418/1545, loss: 0.11444833874702454 2023-01-23 14:06:57.104268: step: 1420/1545, loss: 0.0006853441009297967 2023-01-23 14:06:58.010190: step: 1422/1545, loss: 0.004371392074972391 2023-01-23 14:06:58.894457: step: 1424/1545, loss: 0.004194905050098896 2023-01-23 14:06:59.795402: step: 1426/1545, loss: 0.015229237265884876 2023-01-23 14:07:00.618179: step: 1428/1545, loss: 0.2133423089981079 2023-01-23 14:07:01.545081: step: 1430/1545, loss: 0.43742018938064575 2023-01-23 14:07:02.456038: step: 1432/1545, loss: 0.014767699874937534 2023-01-23 14:07:03.319446: step: 1434/1545, loss: 0.09054785221815109 2023-01-23 14:07:04.207585: step: 1436/1545, loss: 0.07645399123430252 2023-01-23 14:07:05.098110: step: 1438/1545, loss: 0.07159334421157837 2023-01-23 14:07:06.002404: step: 1440/1545, loss: 0.0005889680469408631 2023-01-23 14:07:06.859350: step: 1442/1545, loss: 0.7527891993522644 2023-01-23 14:07:07.736730: step: 1444/1545, loss: 0.05022396519780159 2023-01-23 14:07:08.602934: step: 1446/1545, loss: 0.03816887363791466 2023-01-23 14:07:09.437533: step: 1448/1545, loss: 0.002333474112674594 2023-01-23 14:07:10.274932: step: 1450/1545, loss: 0.060400716960430145 2023-01-23 14:07:11.124007: step: 1452/1545, loss: 0.2010515332221985 2023-01-23 14:07:11.961099: step: 1454/1545, loss: 0.0033418776001781225 2023-01-23 14:07:12.807602: step: 1456/1545, loss: 0.05937173590064049 2023-01-23 14:07:13.649253: step: 1458/1545, loss: 0.028235703706741333 2023-01-23 14:07:14.517177: step: 1460/1545, loss: 0.11205711960792542 2023-01-23 14:07:15.392718: step: 1462/1545, loss: 0.06812438368797302 2023-01-23 14:07:16.280695: step: 1464/1545, loss: 0.19529564678668976 2023-01-23 14:07:17.101599: step: 1466/1545, loss: 0.11376338452100754 2023-01-23 14:07:17.963045: step: 1468/1545, loss: 0.08167225122451782 2023-01-23 14:07:18.831903: step: 1470/1545, loss: 0.24683283269405365 2023-01-23 14:07:19.773108: step: 1472/1545, loss: 0.005256311502307653 2023-01-23 14:07:20.651895: step: 1474/1545, loss: 0.02973710373044014 2023-01-23 14:07:21.551038: step: 1476/1545, loss: 0.0026039762888103724 2023-01-23 14:07:22.443135: step: 1478/1545, loss: 0.3785405457019806 2023-01-23 14:07:23.316222: step: 1480/1545, loss: 0.004129467066377401 2023-01-23 14:07:24.203564: step: 1482/1545, loss: 0.23859985172748566 2023-01-23 14:07:25.122836: step: 1484/1545, loss: 0.8043980002403259 2023-01-23 14:07:26.005403: step: 1486/1545, loss: 0.026861360296607018 2023-01-23 14:07:26.965694: step: 1488/1545, loss: 0.0994054526090622 2023-01-23 14:07:27.813517: step: 1490/1545, loss: 0.02494918741285801 2023-01-23 14:07:28.686446: step: 1492/1545, loss: 0.03191232308745384 2023-01-23 14:07:29.528506: step: 1494/1545, loss: 0.177669957280159 2023-01-23 14:07:30.460285: step: 1496/1545, loss: 0.18382593989372253 2023-01-23 14:07:31.428542: step: 1498/1545, loss: 0.007008867803961039 2023-01-23 14:07:32.320980: step: 1500/1545, loss: 0.017155414447188377 2023-01-23 14:07:33.199933: step: 1502/1545, loss: 0.08678115159273148 2023-01-23 14:07:34.046078: step: 1504/1545, loss: 0.0068778772838413715 2023-01-23 14:07:34.903060: step: 1506/1545, loss: 0.12415528297424316 2023-01-23 14:07:35.779265: step: 1508/1545, loss: 0.04614484682679176 2023-01-23 14:07:36.644126: step: 1510/1545, loss: 0.0004662804421968758 2023-01-23 14:07:37.535187: step: 1512/1545, loss: 0.009550635702908039 2023-01-23 14:07:38.381340: step: 1514/1545, loss: 0.08647598326206207 2023-01-23 14:07:39.258115: step: 1516/1545, loss: 0.08697566390037537 2023-01-23 14:07:40.129177: step: 1518/1545, loss: 0.13063322007656097 2023-01-23 14:07:41.029398: step: 1520/1545, loss: 0.08257361501455307 2023-01-23 14:07:41.854872: step: 1522/1545, loss: 0.012006711214780807 2023-01-23 14:07:42.737906: step: 1524/1545, loss: 0.19085286557674408 2023-01-23 14:07:43.635955: step: 1526/1545, loss: 0.010130658745765686 2023-01-23 14:07:44.502776: step: 1528/1545, loss: 0.011629829183220863 2023-01-23 14:07:45.343421: step: 1530/1545, loss: 0.004250805824995041 2023-01-23 14:07:46.203814: step: 1532/1545, loss: 0.057671770453453064 2023-01-23 14:07:47.047941: step: 1534/1545, loss: 0.15630535781383514 2023-01-23 14:07:47.923924: step: 1536/1545, loss: 0.06063143163919449 2023-01-23 14:07:48.809029: step: 1538/1545, loss: 0.0030447018798440695 2023-01-23 14:07:49.715631: step: 1540/1545, loss: 0.660994291305542 2023-01-23 14:07:50.616898: step: 1542/1545, loss: 0.17019064724445343 2023-01-23 14:07:51.507334: step: 1544/1545, loss: 0.005505642853677273 2023-01-23 14:07:52.360689: step: 1546/1545, loss: 0.002409673761576414 2023-01-23 14:07:53.289226: step: 1548/1545, loss: 0.004690956324338913 2023-01-23 14:07:54.173180: step: 1550/1545, loss: 0.028850458562374115 2023-01-23 14:07:55.108322: step: 1552/1545, loss: 0.011692559346556664 2023-01-23 14:07:56.000217: step: 1554/1545, loss: 0.857629656791687 2023-01-23 14:07:56.849954: step: 1556/1545, loss: 0.012880872003734112 2023-01-23 14:07:57.724165: step: 1558/1545, loss: 0.00313525996170938 2023-01-23 14:07:58.569743: step: 1560/1545, loss: 0.0032638004049658775 2023-01-23 14:07:59.539938: step: 1562/1545, loss: 0.005214589647948742 2023-01-23 14:08:00.451169: step: 1564/1545, loss: 0.055438488721847534 2023-01-23 14:08:01.360368: step: 1566/1545, loss: 0.18394461274147034 2023-01-23 14:08:02.257734: step: 1568/1545, loss: 0.4757300615310669 2023-01-23 14:08:03.126057: step: 1570/1545, loss: 0.5051376223564148 2023-01-23 14:08:03.988502: step: 1572/1545, loss: 0.03805326670408249 2023-01-23 14:08:04.837474: step: 1574/1545, loss: 0.1753726303577423 2023-01-23 14:08:05.711797: step: 1576/1545, loss: 0.06791477650403976 2023-01-23 14:08:06.578085: step: 1578/1545, loss: 0.021358421072363853 2023-01-23 14:08:07.479349: step: 1580/1545, loss: 0.07281846553087234 2023-01-23 14:08:08.377478: step: 1582/1545, loss: 0.018677448853850365 2023-01-23 14:08:09.285212: step: 1584/1545, loss: 0.3018820285797119 2023-01-23 14:08:10.149918: step: 1586/1545, loss: 0.1217915415763855 2023-01-23 14:08:11.078561: step: 1588/1545, loss: 0.02362385019659996 2023-01-23 14:08:11.959668: step: 1590/1545, loss: 0.001989358337596059 2023-01-23 14:08:12.848177: step: 1592/1545, loss: 0.04718008637428284 2023-01-23 14:08:13.754814: step: 1594/1545, loss: 0.048939771950244904 2023-01-23 14:08:14.623502: step: 1596/1545, loss: 0.017211541533470154 2023-01-23 14:08:15.515356: step: 1598/1545, loss: 0.006833619903773069 2023-01-23 14:08:16.385431: step: 1600/1545, loss: 0.42975717782974243 2023-01-23 14:08:17.238756: step: 1602/1545, loss: 0.06501345336437225 2023-01-23 14:08:18.116024: step: 1604/1545, loss: 0.050573885440826416 2023-01-23 14:08:18.990229: step: 1606/1545, loss: 0.13085877895355225 2023-01-23 14:08:19.832669: step: 1608/1545, loss: 0.1484231948852539 2023-01-23 14:08:20.708522: step: 1610/1545, loss: 0.29670414328575134 2023-01-23 14:08:21.657915: step: 1612/1545, loss: 0.03142329677939415 2023-01-23 14:08:22.540509: step: 1614/1545, loss: 0.03133896365761757 2023-01-23 14:08:23.439467: step: 1616/1545, loss: 0.2645881772041321 2023-01-23 14:08:24.302082: step: 1618/1545, loss: 0.00024896347895264626 2023-01-23 14:08:25.123662: step: 1620/1545, loss: 0.1414748877286911 2023-01-23 14:08:25.972558: step: 1622/1545, loss: 0.39315223693847656 2023-01-23 14:08:26.838997: step: 1624/1545, loss: 0.6585338711738586 2023-01-23 14:08:27.718214: step: 1626/1545, loss: 0.2604157328605652 2023-01-23 14:08:28.557664: step: 1628/1545, loss: 0.10831966996192932 2023-01-23 14:08:29.434795: step: 1630/1545, loss: 0.0025327967014163733 2023-01-23 14:08:30.323654: step: 1632/1545, loss: 0.060899995267391205 2023-01-23 14:08:31.199962: step: 1634/1545, loss: 0.08550623804330826 2023-01-23 14:08:32.056623: step: 1636/1545, loss: 0.10648997128009796 2023-01-23 14:08:32.923428: step: 1638/1545, loss: 0.02291145734488964 2023-01-23 14:08:33.801523: step: 1640/1545, loss: 0.043400902301073074 2023-01-23 14:08:34.696903: step: 1642/1545, loss: 0.002333839191123843 2023-01-23 14:08:35.564764: step: 1644/1545, loss: 0.11123578995466232 2023-01-23 14:08:36.495131: step: 1646/1545, loss: 0.07141971588134766 2023-01-23 14:08:37.364439: step: 1648/1545, loss: 0.18172016739845276 2023-01-23 14:08:38.198354: step: 1650/1545, loss: 0.16650106012821198 2023-01-23 14:08:39.066412: step: 1652/1545, loss: 0.6686283349990845 2023-01-23 14:08:39.890702: step: 1654/1545, loss: 0.2730395793914795 2023-01-23 14:08:40.789642: step: 1656/1545, loss: 0.06624411046504974 2023-01-23 14:08:41.646173: step: 1658/1545, loss: 0.7647492289543152 2023-01-23 14:08:42.493902: step: 1660/1545, loss: 0.03807062283158302 2023-01-23 14:08:43.403240: step: 1662/1545, loss: 0.14733989536762238 2023-01-23 14:08:44.301314: step: 1664/1545, loss: 0.0012717897770926356 2023-01-23 14:08:45.145751: step: 1666/1545, loss: 0.1108238697052002 2023-01-23 14:08:46.039408: step: 1668/1545, loss: 0.01097570825368166 2023-01-23 14:08:46.870457: step: 1670/1545, loss: 0.003737080842256546 2023-01-23 14:08:47.745066: step: 1672/1545, loss: 0.024034567177295685 2023-01-23 14:08:48.651074: step: 1674/1545, loss: 0.018332667648792267 2023-01-23 14:08:49.518706: step: 1676/1545, loss: 0.10986119508743286 2023-01-23 14:08:50.382354: step: 1678/1545, loss: 0.0217062309384346 2023-01-23 14:08:51.261332: step: 1680/1545, loss: 0.1169259324669838 2023-01-23 14:08:52.099300: step: 1682/1545, loss: 0.20496131479740143 2023-01-23 14:08:53.018345: step: 1684/1545, loss: 0.025419263169169426 2023-01-23 14:08:53.862730: step: 1686/1545, loss: 0.08917878568172455 2023-01-23 14:08:54.714895: step: 1688/1545, loss: 0.37924253940582275 2023-01-23 14:08:55.597334: step: 1690/1545, loss: 0.16024531424045563 2023-01-23 14:08:56.488021: step: 1692/1545, loss: 0.03416639193892479 2023-01-23 14:08:57.321286: step: 1694/1545, loss: 0.09005672484636307 2023-01-23 14:08:58.213705: step: 1696/1545, loss: 0.030263569205999374 2023-01-23 14:08:59.072892: step: 1698/1545, loss: 0.05974588915705681 2023-01-23 14:08:59.980835: step: 1700/1545, loss: 0.01785573922097683 2023-01-23 14:09:00.853925: step: 1702/1545, loss: 0.007817266508936882 2023-01-23 14:09:01.754796: step: 1704/1545, loss: 0.000876705045811832 2023-01-23 14:09:02.632960: step: 1706/1545, loss: 0.1665317267179489 2023-01-23 14:09:03.604461: step: 1708/1545, loss: 0.04468408599495888 2023-01-23 14:09:04.503962: step: 1710/1545, loss: 0.20908227562904358 2023-01-23 14:09:05.348015: step: 1712/1545, loss: 0.006693572737276554 2023-01-23 14:09:06.237052: step: 1714/1545, loss: 0.38543766736984253 2023-01-23 14:09:07.106626: step: 1716/1545, loss: 0.14425954222679138 2023-01-23 14:09:07.977063: step: 1718/1545, loss: 0.0755070298910141 2023-01-23 14:09:08.852985: step: 1720/1545, loss: 0.0377933569252491 2023-01-23 14:09:09.727065: step: 1722/1545, loss: 0.1408999115228653 2023-01-23 14:09:10.579561: step: 1724/1545, loss: 0.021888883784413338 2023-01-23 14:09:11.443207: step: 1726/1545, loss: 0.006380051374435425 2023-01-23 14:09:12.328688: step: 1728/1545, loss: 0.00670902244746685 2023-01-23 14:09:13.181145: step: 1730/1545, loss: 0.03724704310297966 2023-01-23 14:09:14.061406: step: 1732/1545, loss: 0.10299764573574066 2023-01-23 14:09:14.915160: step: 1734/1545, loss: 0.009282601997256279 2023-01-23 14:09:15.760115: step: 1736/1545, loss: 0.13815295696258545 2023-01-23 14:09:16.640518: step: 1738/1545, loss: 0.12209165841341019 2023-01-23 14:09:17.513550: step: 1740/1545, loss: 0.10313299298286438 2023-01-23 14:09:18.389725: step: 1742/1545, loss: 0.1844598650932312 2023-01-23 14:09:19.338212: step: 1744/1545, loss: 0.006773760542273521 2023-01-23 14:09:20.193540: step: 1746/1545, loss: 0.06455429643392563 2023-01-23 14:09:21.119206: step: 1748/1545, loss: 0.01964814029633999 2023-01-23 14:09:22.049125: step: 1750/1545, loss: 0.04456990212202072 2023-01-23 14:09:22.942950: step: 1752/1545, loss: 0.0245766993612051 2023-01-23 14:09:23.829660: step: 1754/1545, loss: 0.027567623183131218 2023-01-23 14:09:24.723925: step: 1756/1545, loss: 0.25865504145622253 2023-01-23 14:09:25.608982: step: 1758/1545, loss: 0.010863079689443111 2023-01-23 14:09:26.453960: step: 1760/1545, loss: 0.005842375103384256 2023-01-23 14:09:27.309204: step: 1762/1545, loss: 0.014597633853554726 2023-01-23 14:09:28.186052: step: 1764/1545, loss: 0.15077245235443115 2023-01-23 14:09:29.081042: step: 1766/1545, loss: 0.27808377146720886 2023-01-23 14:09:29.959509: step: 1768/1545, loss: 0.6326113939285278 2023-01-23 14:09:30.827396: step: 1770/1545, loss: 0.030697043985128403 2023-01-23 14:09:31.771275: step: 1772/1545, loss: 0.06483826041221619 2023-01-23 14:09:32.653516: step: 1774/1545, loss: 0.062080804258584976 2023-01-23 14:09:33.521548: step: 1776/1545, loss: 0.0030749456491321325 2023-01-23 14:09:34.394012: step: 1778/1545, loss: 0.10908591002225876 2023-01-23 14:09:35.247210: step: 1780/1545, loss: 0.029222045093774796 2023-01-23 14:09:36.094309: step: 1782/1545, loss: 0.25649189949035645 2023-01-23 14:09:36.964623: step: 1784/1545, loss: 0.0009669028222560883 2023-01-23 14:09:37.828351: step: 1786/1545, loss: 0.37566205859184265 2023-01-23 14:09:38.683603: step: 1788/1545, loss: 0.07494515180587769 2023-01-23 14:09:39.589643: step: 1790/1545, loss: 0.024890752509236336 2023-01-23 14:09:40.508571: step: 1792/1545, loss: 0.0436047799885273 2023-01-23 14:09:41.383724: step: 1794/1545, loss: 0.001610590610653162 2023-01-23 14:09:42.243939: step: 1796/1545, loss: 0.005350060760974884 2023-01-23 14:09:43.118574: step: 1798/1545, loss: 0.030842909589409828 2023-01-23 14:09:43.993707: step: 1800/1545, loss: 0.031459394842386246 2023-01-23 14:09:44.863295: step: 1802/1545, loss: 0.0024940422736108303 2023-01-23 14:09:45.759570: step: 1804/1545, loss: 0.062032897025346756 2023-01-23 14:09:46.669676: step: 1806/1545, loss: 0.09718175232410431 2023-01-23 14:09:47.580938: step: 1808/1545, loss: 0.009045579470694065 2023-01-23 14:09:48.493312: step: 1810/1545, loss: 0.2082424908876419 2023-01-23 14:09:49.370188: step: 1812/1545, loss: 0.003965198993682861 2023-01-23 14:09:50.292892: step: 1814/1545, loss: 0.0017007252899929881 2023-01-23 14:09:51.161468: step: 1816/1545, loss: 0.08602574467658997 2023-01-23 14:09:52.036342: step: 1818/1545, loss: 0.03517332673072815 2023-01-23 14:09:52.936179: step: 1820/1545, loss: 0.28457510471343994 2023-01-23 14:09:53.861466: step: 1822/1545, loss: 0.009809834882616997 2023-01-23 14:09:54.793377: step: 1824/1545, loss: 0.0014046886935830116 2023-01-23 14:09:55.678911: step: 1826/1545, loss: 0.22817544639110565 2023-01-23 14:09:56.555262: step: 1828/1545, loss: 0.0806356742978096 2023-01-23 14:09:57.444144: step: 1830/1545, loss: 0.04100525751709938 2023-01-23 14:09:58.387365: step: 1832/1545, loss: 0.31159672141075134 2023-01-23 14:09:59.380650: step: 1834/1545, loss: 0.0003180374624207616 2023-01-23 14:10:00.289174: step: 1836/1545, loss: 0.525916576385498 2023-01-23 14:10:01.159334: step: 1838/1545, loss: 0.005549724213778973 2023-01-23 14:10:02.058005: step: 1840/1545, loss: 0.39155349135398865 2023-01-23 14:10:03.018398: step: 1842/1545, loss: 0.18380196392536163 2023-01-23 14:10:03.876747: step: 1844/1545, loss: 0.02049141190946102 2023-01-23 14:10:04.786777: step: 1846/1545, loss: 0.02817019447684288 2023-01-23 14:10:05.704536: step: 1848/1545, loss: 0.17704851925373077 2023-01-23 14:10:06.556917: step: 1850/1545, loss: 0.004618242383003235 2023-01-23 14:10:07.448450: step: 1852/1545, loss: 0.07187563925981522 2023-01-23 14:10:08.335968: step: 1854/1545, loss: 0.2915845215320587 2023-01-23 14:10:09.216575: step: 1856/1545, loss: 0.003071708371862769 2023-01-23 14:10:10.116061: step: 1858/1545, loss: 0.38338884711265564 2023-01-23 14:10:10.977790: step: 1860/1545, loss: 0.015382393263280392 2023-01-23 14:10:11.843501: step: 1862/1545, loss: 0.005803859792649746 2023-01-23 14:10:12.712976: step: 1864/1545, loss: 0.06931642442941666 2023-01-23 14:10:13.558379: step: 1866/1545, loss: 0.019083186984062195 2023-01-23 14:10:14.432932: step: 1868/1545, loss: 0.004501522984355688 2023-01-23 14:10:15.299104: step: 1870/1545, loss: 0.1949351727962494 2023-01-23 14:10:16.184665: step: 1872/1545, loss: 0.008540342561900616 2023-01-23 14:10:17.045485: step: 1874/1545, loss: 0.001526437234133482 2023-01-23 14:10:17.925669: step: 1876/1545, loss: 0.020716683939099312 2023-01-23 14:10:18.796739: step: 1878/1545, loss: 0.001639683498069644 2023-01-23 14:10:19.661831: step: 1880/1545, loss: 0.055540356785058975 2023-01-23 14:10:20.582799: step: 1882/1545, loss: 0.48000073432922363 2023-01-23 14:10:21.478804: step: 1884/1545, loss: 0.00642109801992774 2023-01-23 14:10:22.336156: step: 1886/1545, loss: 0.009060465730726719 2023-01-23 14:10:23.247413: step: 1888/1545, loss: 0.014686232432723045 2023-01-23 14:10:24.139254: step: 1890/1545, loss: 0.016566606238484383 2023-01-23 14:10:25.010361: step: 1892/1545, loss: 0.28947827219963074 2023-01-23 14:10:25.903353: step: 1894/1545, loss: 0.04694519564509392 2023-01-23 14:10:26.744115: step: 1896/1545, loss: 0.25929519534111023 2023-01-23 14:10:27.637561: step: 1898/1545, loss: 0.008399656973779202 2023-01-23 14:10:28.503657: step: 1900/1545, loss: 0.04084805026650429 2023-01-23 14:10:29.364718: step: 1902/1545, loss: 0.0040055434219539165 2023-01-23 14:10:30.237378: step: 1904/1545, loss: 0.06476125121116638 2023-01-23 14:10:31.160109: step: 1906/1545, loss: 0.019185218960046768 2023-01-23 14:10:32.022335: step: 1908/1545, loss: 0.011781795881688595 2023-01-23 14:10:32.937316: step: 1910/1545, loss: 0.008417770266532898 2023-01-23 14:10:33.804329: step: 1912/1545, loss: 0.005756258498877287 2023-01-23 14:10:34.638389: step: 1914/1545, loss: 0.01733403466641903 2023-01-23 14:10:35.533079: step: 1916/1545, loss: 0.008861154317855835 2023-01-23 14:10:36.433233: step: 1918/1545, loss: 0.002419040771201253 2023-01-23 14:10:37.297194: step: 1920/1545, loss: 0.004351729527115822 2023-01-23 14:10:38.188900: step: 1922/1545, loss: 0.05271616578102112 2023-01-23 14:10:39.168214: step: 1924/1545, loss: 0.07559356838464737 2023-01-23 14:10:40.094000: step: 1926/1545, loss: 0.036235954612493515 2023-01-23 14:10:40.992931: step: 1928/1545, loss: 0.09046214073896408 2023-01-23 14:10:41.873714: step: 1930/1545, loss: 0.057120613753795624 2023-01-23 14:10:42.804159: step: 1932/1545, loss: 0.310879111289978 2023-01-23 14:10:43.673943: step: 1934/1545, loss: 0.001687929150648415 2023-01-23 14:10:44.601708: step: 1936/1545, loss: 0.06268364936113358 2023-01-23 14:10:45.479746: step: 1938/1545, loss: 0.016449468210339546 2023-01-23 14:10:46.376960: step: 1940/1545, loss: 0.02484615333378315 2023-01-23 14:10:47.293563: step: 1942/1545, loss: 0.19991885125637054 2023-01-23 14:10:48.168190: step: 1944/1545, loss: 0.005457381717860699 2023-01-23 14:10:49.035828: step: 1946/1545, loss: 0.3003406226634979 2023-01-23 14:10:49.926037: step: 1948/1545, loss: 1.2145949602127075 2023-01-23 14:10:50.788043: step: 1950/1545, loss: 0.11945317685604095 2023-01-23 14:10:51.674826: step: 1952/1545, loss: 0.0881071537733078 2023-01-23 14:10:52.609170: step: 1954/1545, loss: 0.0009263121173717082 2023-01-23 14:10:53.479614: step: 1956/1545, loss: 0.12705707550048828 2023-01-23 14:10:54.326810: step: 1958/1545, loss: 0.009497666731476784 2023-01-23 14:10:55.247867: step: 1960/1545, loss: 0.03359244763851166 2023-01-23 14:10:56.109690: step: 1962/1545, loss: 0.021270595490932465 2023-01-23 14:10:56.952123: step: 1964/1545, loss: 0.09750192612409592 2023-01-23 14:10:57.833527: step: 1966/1545, loss: 0.003267493098974228 2023-01-23 14:10:58.676699: step: 1968/1545, loss: 0.0031372327357530594 2023-01-23 14:10:59.593672: step: 1970/1545, loss: 0.4786577522754669 2023-01-23 14:11:00.482890: step: 1972/1545, loss: 0.1462596356868744 2023-01-23 14:11:01.357414: step: 1974/1545, loss: 0.2280641794204712 2023-01-23 14:11:02.231521: step: 1976/1545, loss: 0.06855272501707077 2023-01-23 14:11:03.135491: step: 1978/1545, loss: 0.0010463547660037875 2023-01-23 14:11:04.051486: step: 1980/1545, loss: 0.015831299126148224 2023-01-23 14:11:04.924662: step: 1982/1545, loss: 0.0036084074527025223 2023-01-23 14:11:05.780092: step: 1984/1545, loss: 0.0036681797355413437 2023-01-23 14:11:06.638740: step: 1986/1545, loss: 0.2649088203907013 2023-01-23 14:11:07.498201: step: 1988/1545, loss: 0.0703016147017479 2023-01-23 14:11:08.367065: step: 1990/1545, loss: 0.01959412917494774 2023-01-23 14:11:09.219281: step: 1992/1545, loss: 0.5314414501190186 2023-01-23 14:11:10.049338: step: 1994/1545, loss: 0.007771722506731749 2023-01-23 14:11:10.952979: step: 1996/1545, loss: 0.007262745872139931 2023-01-23 14:11:11.796766: step: 1998/1545, loss: 0.04562148079276085 2023-01-23 14:11:12.678348: step: 2000/1545, loss: 0.05185163766145706 2023-01-23 14:11:13.547053: step: 2002/1545, loss: 0.29004502296447754 2023-01-23 14:11:14.440386: step: 2004/1545, loss: 0.019983092322945595 2023-01-23 14:11:15.310174: step: 2006/1545, loss: 0.005928087048232555 2023-01-23 14:11:16.197052: step: 2008/1545, loss: 0.30929145216941833 2023-01-23 14:11:17.050210: step: 2010/1545, loss: 0.012848038226366043 2023-01-23 14:11:17.882683: step: 2012/1545, loss: 0.08391445875167847 2023-01-23 14:11:18.778204: step: 2014/1545, loss: 0.018044427037239075 2023-01-23 14:11:19.637084: step: 2016/1545, loss: 0.0021846096497029066 2023-01-23 14:11:20.490074: step: 2018/1545, loss: 0.07325255870819092 2023-01-23 14:11:21.365661: step: 2020/1545, loss: 0.5472164750099182 2023-01-23 14:11:22.255430: step: 2022/1545, loss: 0.0467255599796772 2023-01-23 14:11:23.162964: step: 2024/1545, loss: 0.3034782409667969 2023-01-23 14:11:24.043567: step: 2026/1545, loss: 0.05060908570885658 2023-01-23 14:11:24.940415: step: 2028/1545, loss: 0.005868456792086363 2023-01-23 14:11:25.814499: step: 2030/1545, loss: 0.025534169748425484 2023-01-23 14:11:26.689006: step: 2032/1545, loss: 0.013966338708996773 2023-01-23 14:11:27.537813: step: 2034/1545, loss: 0.0028889672830700874 2023-01-23 14:11:28.475072: step: 2036/1545, loss: 0.010582088492810726 2023-01-23 14:11:29.373215: step: 2038/1545, loss: 0.003667386481538415 2023-01-23 14:11:30.242099: step: 2040/1545, loss: 0.09453598409891129 2023-01-23 14:11:31.128797: step: 2042/1545, loss: 0.14701439440250397 2023-01-23 14:11:32.035079: step: 2044/1545, loss: 0.007350290659815073 2023-01-23 14:11:32.947897: step: 2046/1545, loss: 0.03339288383722305 2023-01-23 14:11:33.851758: step: 2048/1545, loss: 0.004750758409500122 2023-01-23 14:11:34.774857: step: 2050/1545, loss: 0.09781187027692795 2023-01-23 14:11:35.650292: step: 2052/1545, loss: 0.1203511506319046 2023-01-23 14:11:36.493655: step: 2054/1545, loss: 0.17764942348003387 2023-01-23 14:11:37.454640: step: 2056/1545, loss: 0.045186419039964676 2023-01-23 14:11:38.439140: step: 2058/1545, loss: 0.12045664340257645 2023-01-23 14:11:39.311237: step: 2060/1545, loss: 0.10435418039560318 2023-01-23 14:11:40.199207: step: 2062/1545, loss: 0.009596583433449268 2023-01-23 14:11:41.090266: step: 2064/1545, loss: 0.14029207825660706 2023-01-23 14:11:41.974371: step: 2066/1545, loss: 0.04127931594848633 2023-01-23 14:11:42.853909: step: 2068/1545, loss: 0.0938376784324646 2023-01-23 14:11:43.744903: step: 2070/1545, loss: 0.6720927357673645 2023-01-23 14:11:44.619617: step: 2072/1545, loss: 0.05423732474446297 2023-01-23 14:11:45.491808: step: 2074/1545, loss: 0.12107086181640625 2023-01-23 14:11:46.343195: step: 2076/1545, loss: 0.0053345090709626675 2023-01-23 14:11:47.281179: step: 2078/1545, loss: 0.0237980205565691 2023-01-23 14:11:48.165723: step: 2080/1545, loss: 0.03595202416181564 2023-01-23 14:11:49.030946: step: 2082/1545, loss: 0.03615100309252739 2023-01-23 14:11:49.941938: step: 2084/1545, loss: 0.01459568738937378 2023-01-23 14:11:50.804283: step: 2086/1545, loss: 0.1959754377603531 2023-01-23 14:11:51.685856: step: 2088/1545, loss: 0.012851964682340622 2023-01-23 14:11:52.623590: step: 2090/1545, loss: 0.02234381064772606 2023-01-23 14:11:53.511430: step: 2092/1545, loss: 0.09052671492099762 2023-01-23 14:11:54.407457: step: 2094/1545, loss: 0.058973655104637146 2023-01-23 14:11:55.266030: step: 2096/1545, loss: 0.003750826930627227 2023-01-23 14:11:56.120575: step: 2098/1545, loss: 1.1976664066314697 2023-01-23 14:11:56.989409: step: 2100/1545, loss: 0.005697373300790787 2023-01-23 14:11:57.868692: step: 2102/1545, loss: 0.07257222384214401 2023-01-23 14:11:58.729996: step: 2104/1545, loss: 0.06880201399326324 2023-01-23 14:11:59.628207: step: 2106/1545, loss: 0.004412262234836817 2023-01-23 14:12:00.558235: step: 2108/1545, loss: 0.001675603212788701 2023-01-23 14:12:01.474990: step: 2110/1545, loss: 0.0006183783989399672 2023-01-23 14:12:02.352782: step: 2112/1545, loss: 0.04919755458831787 2023-01-23 14:12:03.225741: step: 2114/1545, loss: 0.22333835065364838 2023-01-23 14:12:04.143906: step: 2116/1545, loss: 0.01121242344379425 2023-01-23 14:12:05.055710: step: 2118/1545, loss: 0.2599019706249237 2023-01-23 14:12:05.922845: step: 2120/1545, loss: 0.05570284277200699 2023-01-23 14:12:06.758283: step: 2122/1545, loss: 0.08688542991876602 2023-01-23 14:12:07.650733: step: 2124/1545, loss: 0.1525404304265976 2023-01-23 14:12:08.543666: step: 2126/1545, loss: 0.016066834330558777 2023-01-23 14:12:09.398781: step: 2128/1545, loss: 0.02747681364417076 2023-01-23 14:12:10.311754: step: 2130/1545, loss: 0.01707080937922001 2023-01-23 14:12:11.175559: step: 2132/1545, loss: 0.006872727535665035 2023-01-23 14:12:12.023774: step: 2134/1545, loss: 0.001314726541750133 2023-01-23 14:12:12.904286: step: 2136/1545, loss: 0.004620907362550497 2023-01-23 14:12:13.820020: step: 2138/1545, loss: 0.3107103705406189 2023-01-23 14:12:14.665877: step: 2140/1545, loss: 0.013917384669184685 2023-01-23 14:12:15.504084: step: 2142/1545, loss: 0.01809365302324295 2023-01-23 14:12:16.363270: step: 2144/1545, loss: 0.00027879292611032724 2023-01-23 14:12:17.237006: step: 2146/1545, loss: 0.022811751812696457 2023-01-23 14:12:18.145202: step: 2148/1545, loss: 0.09721492975950241 2023-01-23 14:12:18.989501: step: 2150/1545, loss: 0.0012125883949920535 2023-01-23 14:12:19.839136: step: 2152/1545, loss: 0.03958785533905029 2023-01-23 14:12:20.756786: step: 2154/1545, loss: 0.003545705694705248 2023-01-23 14:12:21.627274: step: 2156/1545, loss: 0.007155576720833778 2023-01-23 14:12:22.467645: step: 2158/1545, loss: 0.04475262016057968 2023-01-23 14:12:23.345643: step: 2160/1545, loss: 0.018267259001731873 2023-01-23 14:12:24.204077: step: 2162/1545, loss: 0.004801594652235508 2023-01-23 14:12:25.106523: step: 2164/1545, loss: 0.5053296089172363 2023-01-23 14:12:25.996856: step: 2166/1545, loss: 0.0739288479089737 2023-01-23 14:12:26.887831: step: 2168/1545, loss: 0.013709665276110172 2023-01-23 14:12:27.729939: step: 2170/1545, loss: 0.009862329810857773 2023-01-23 14:12:28.665371: step: 2172/1545, loss: 0.05993787944316864 2023-01-23 14:12:29.529037: step: 2174/1545, loss: 0.03129826858639717 2023-01-23 14:12:30.403184: step: 2176/1545, loss: 0.015027502551674843 2023-01-23 14:12:31.319326: step: 2178/1545, loss: 0.0010405255015939474 2023-01-23 14:12:32.244086: step: 2180/1545, loss: 0.0022750592324882746 2023-01-23 14:12:33.127858: step: 2182/1545, loss: 0.37037375569343567 2023-01-23 14:12:34.004894: step: 2184/1545, loss: 0.25937914848327637 2023-01-23 14:12:34.883084: step: 2186/1545, loss: 0.12301894277334213 2023-01-23 14:12:35.776625: step: 2188/1545, loss: 0.02155061811208725 2023-01-23 14:12:36.637323: step: 2190/1545, loss: 0.005596455652266741 2023-01-23 14:12:37.483952: step: 2192/1545, loss: 0.012748954817652702 2023-01-23 14:12:38.418688: step: 2194/1545, loss: 0.11198627948760986 2023-01-23 14:12:39.277712: step: 2196/1545, loss: 0.010916855186223984 2023-01-23 14:12:40.167631: step: 2198/1545, loss: 0.3675439953804016 2023-01-23 14:12:41.085740: step: 2200/1545, loss: 0.1061885729432106 2023-01-23 14:12:41.946499: step: 2202/1545, loss: 0.6429182291030884 2023-01-23 14:12:42.814039: step: 2204/1545, loss: 0.6485862731933594 2023-01-23 14:12:43.652886: step: 2206/1545, loss: 0.04184241592884064 2023-01-23 14:12:44.559775: step: 2208/1545, loss: 0.0031325749587267637 2023-01-23 14:12:45.475145: step: 2210/1545, loss: 0.060423314571380615 2023-01-23 14:12:46.347750: step: 2212/1545, loss: 0.10436401516199112 2023-01-23 14:12:47.231001: step: 2214/1545, loss: 0.026928454637527466 2023-01-23 14:12:48.107614: step: 2216/1545, loss: 0.07729092240333557 2023-01-23 14:12:49.058712: step: 2218/1545, loss: 0.05621658265590668 2023-01-23 14:12:49.940603: step: 2220/1545, loss: 0.004341465421020985 2023-01-23 14:12:50.807630: step: 2222/1545, loss: 0.004053911659866571 2023-01-23 14:12:51.758219: step: 2224/1545, loss: 0.05540701374411583 2023-01-23 14:12:52.668683: step: 2226/1545, loss: 0.051669891923666 2023-01-23 14:12:53.508856: step: 2228/1545, loss: 0.012745114974677563 2023-01-23 14:12:54.398019: step: 2230/1545, loss: 0.2708429992198944 2023-01-23 14:12:55.314433: step: 2232/1545, loss: 0.02109628915786743 2023-01-23 14:12:56.192872: step: 2234/1545, loss: 1.0546640157699585 2023-01-23 14:12:57.062198: step: 2236/1545, loss: 0.013394132256507874 2023-01-23 14:12:57.963133: step: 2238/1545, loss: 0.021168746054172516 2023-01-23 14:12:58.805621: step: 2240/1545, loss: 0.8912703394889832 2023-01-23 14:12:59.665280: step: 2242/1545, loss: 0.004327028524130583 2023-01-23 14:13:00.582957: step: 2244/1545, loss: 0.012785750441253185 2023-01-23 14:13:01.482535: step: 2246/1545, loss: 0.006680638529360294 2023-01-23 14:13:02.364259: step: 2248/1545, loss: 0.16069161891937256 2023-01-23 14:13:03.233005: step: 2250/1545, loss: 0.035279739648103714 2023-01-23 14:13:04.119001: step: 2252/1545, loss: 0.03442732244729996 2023-01-23 14:13:05.075393: step: 2254/1545, loss: 0.028684303164482117 2023-01-23 14:13:05.973426: step: 2256/1545, loss: 0.030982721596956253 2023-01-23 14:13:06.863351: step: 2258/1545, loss: 0.0014546080492436886 2023-01-23 14:13:07.720036: step: 2260/1545, loss: 0.0957644060254097 2023-01-23 14:13:08.569113: step: 2262/1545, loss: 0.08154002577066422 2023-01-23 14:13:09.481808: step: 2264/1545, loss: 0.009547524154186249 2023-01-23 14:13:10.377326: step: 2266/1545, loss: 0.1588156819343567 2023-01-23 14:13:11.235117: step: 2268/1545, loss: 0.007512162439525127 2023-01-23 14:13:12.118444: step: 2270/1545, loss: 0.09341292828321457 2023-01-23 14:13:13.034672: step: 2272/1545, loss: 0.007117802742868662 2023-01-23 14:13:13.935304: step: 2274/1545, loss: 0.004337131977081299 2023-01-23 14:13:14.765238: step: 2276/1545, loss: 0.0010285454336553812 2023-01-23 14:13:15.643867: step: 2278/1545, loss: 0.37827828526496887 2023-01-23 14:13:16.542911: step: 2280/1545, loss: 0.008540268056094646 2023-01-23 14:13:17.411801: step: 2282/1545, loss: 0.01771930418908596 2023-01-23 14:13:18.264247: step: 2284/1545, loss: 0.0022654030472040176 2023-01-23 14:13:19.145469: step: 2286/1545, loss: 0.016110040247440338 2023-01-23 14:13:20.053768: step: 2288/1545, loss: 0.02803873084485531 2023-01-23 14:13:20.907900: step: 2290/1545, loss: 0.04070363938808441 2023-01-23 14:13:21.874335: step: 2292/1545, loss: 0.08303114026784897 2023-01-23 14:13:22.785247: step: 2294/1545, loss: 0.523420512676239 2023-01-23 14:13:23.637411: step: 2296/1545, loss: 0.05494191497564316 2023-01-23 14:13:24.495726: step: 2298/1545, loss: 0.025961436331272125 2023-01-23 14:13:25.394291: step: 2300/1545, loss: 0.029942449182271957 2023-01-23 14:13:26.301544: step: 2302/1545, loss: 0.10433641821146011 2023-01-23 14:13:27.155356: step: 2304/1545, loss: 0.0376058928668499 2023-01-23 14:13:28.071036: step: 2306/1545, loss: 0.08816983550786972 2023-01-23 14:13:28.950096: step: 2308/1545, loss: 0.03792667016386986 2023-01-23 14:13:29.839154: step: 2310/1545, loss: 1.410685658454895 2023-01-23 14:13:30.686148: step: 2312/1545, loss: 0.00010710311471484601 2023-01-23 14:13:31.589647: step: 2314/1545, loss: 0.02200664021074772 2023-01-23 14:13:32.457730: step: 2316/1545, loss: 0.14853021502494812 2023-01-23 14:13:33.333303: step: 2318/1545, loss: 0.1043798103928566 2023-01-23 14:13:34.257033: step: 2320/1545, loss: 0.015812411904335022 2023-01-23 14:13:35.165100: step: 2322/1545, loss: 0.06738761812448502 2023-01-23 14:13:36.081967: step: 2324/1545, loss: 0.19477178156375885 2023-01-23 14:13:36.940037: step: 2326/1545, loss: 1.9246530532836914 2023-01-23 14:13:37.807187: step: 2328/1545, loss: 0.024944694712758064 2023-01-23 14:13:38.662966: step: 2330/1545, loss: 0.2670001983642578 2023-01-23 14:13:39.535752: step: 2332/1545, loss: 0.04712758958339691 2023-01-23 14:13:40.516767: step: 2334/1545, loss: 0.2609868049621582 2023-01-23 14:13:41.395227: step: 2336/1545, loss: 0.30900320410728455 2023-01-23 14:13:42.254843: step: 2338/1545, loss: 0.024813227355480194 2023-01-23 14:13:43.153311: step: 2340/1545, loss: 0.002843475202098489 2023-01-23 14:13:44.017258: step: 2342/1545, loss: 0.07766786962747574 2023-01-23 14:13:44.896252: step: 2344/1545, loss: 0.28829488158226013 2023-01-23 14:13:45.792645: step: 2346/1545, loss: 0.006814825348556042 2023-01-23 14:13:46.708190: step: 2348/1545, loss: 0.012460749596357346 2023-01-23 14:13:47.619274: step: 2350/1545, loss: 0.09555503726005554 2023-01-23 14:13:48.477862: step: 2352/1545, loss: 0.008771185763180256 2023-01-23 14:13:49.354181: step: 2354/1545, loss: 0.006749889347702265 2023-01-23 14:13:50.194017: step: 2356/1545, loss: 0.3644161820411682 2023-01-23 14:13:51.040731: step: 2358/1545, loss: 0.05824219435453415 2023-01-23 14:13:51.963824: step: 2360/1545, loss: 0.21101364493370056 2023-01-23 14:13:52.825260: step: 2362/1545, loss: 0.003929128870368004 2023-01-23 14:13:53.708625: step: 2364/1545, loss: 0.0993623211979866 2023-01-23 14:13:54.552418: step: 2366/1545, loss: 0.06378455460071564 2023-01-23 14:13:55.401655: step: 2368/1545, loss: 0.4312153458595276 2023-01-23 14:13:56.313969: step: 2370/1545, loss: 0.00905854906886816 2023-01-23 14:13:57.276107: step: 2372/1545, loss: 0.08089569211006165 2023-01-23 14:13:58.157938: step: 2374/1545, loss: 0.08474381268024445 2023-01-23 14:13:59.043630: step: 2376/1545, loss: 0.014601089060306549 2023-01-23 14:13:59.887232: step: 2378/1545, loss: 0.004458907060325146 2023-01-23 14:14:00.798515: step: 2380/1545, loss: 0.033280227333307266 2023-01-23 14:14:01.678884: step: 2382/1545, loss: 0.0034769526682794094 2023-01-23 14:14:02.627219: step: 2384/1545, loss: 0.14827167987823486 2023-01-23 14:14:03.536484: step: 2386/1545, loss: 0.05253307521343231 2023-01-23 14:14:04.435490: step: 2388/1545, loss: 0.0751737430691719 2023-01-23 14:14:05.252182: step: 2390/1545, loss: 0.019971761852502823 2023-01-23 14:14:06.113127: step: 2392/1545, loss: 0.0020457140635699034 2023-01-23 14:14:07.131859: step: 2394/1545, loss: 0.3101891875267029 2023-01-23 14:14:08.046637: step: 2396/1545, loss: 0.10276518017053604 2023-01-23 14:14:08.931847: step: 2398/1545, loss: 0.004301940090954304 2023-01-23 14:14:09.786724: step: 2400/1545, loss: 0.0889846459031105 2023-01-23 14:14:10.674326: step: 2402/1545, loss: 0.08724238723516464 2023-01-23 14:14:11.560934: step: 2404/1545, loss: 0.11953290551900864 2023-01-23 14:14:12.430157: step: 2406/1545, loss: 0.07466824352741241 2023-01-23 14:14:13.320953: step: 2408/1545, loss: 0.20337307453155518 2023-01-23 14:14:14.230526: step: 2410/1545, loss: 0.009338900446891785 2023-01-23 14:14:15.089721: step: 2412/1545, loss: 0.008940940722823143 2023-01-23 14:14:15.982831: step: 2414/1545, loss: 0.019202755764126778 2023-01-23 14:14:16.869809: step: 2416/1545, loss: 0.08461953699588776 2023-01-23 14:14:17.782426: step: 2418/1545, loss: 0.011016806587576866 2023-01-23 14:14:18.679604: step: 2420/1545, loss: 0.008676230907440186 2023-01-23 14:14:19.579340: step: 2422/1545, loss: 0.10638459026813507 2023-01-23 14:14:20.445812: step: 2424/1545, loss: 0.020517604425549507 2023-01-23 14:14:21.341771: step: 2426/1545, loss: 0.005683818366378546 2023-01-23 14:14:22.242240: step: 2428/1545, loss: 0.18083655834197998 2023-01-23 14:14:23.093868: step: 2430/1545, loss: 1.0402843952178955 2023-01-23 14:14:23.950980: step: 2432/1545, loss: 0.16420842707157135 2023-01-23 14:14:24.865207: step: 2434/1545, loss: 0.0385318249464035 2023-01-23 14:14:25.744604: step: 2436/1545, loss: 0.021534038707613945 2023-01-23 14:14:26.643936: step: 2438/1545, loss: 0.039698291569948196 2023-01-23 14:14:27.504406: step: 2440/1545, loss: 0.12394332885742188 2023-01-23 14:14:28.466919: step: 2442/1545, loss: 0.23934733867645264 2023-01-23 14:14:29.320987: step: 2444/1545, loss: 0.16847990453243256 2023-01-23 14:14:30.205870: step: 2446/1545, loss: 0.1063491627573967 2023-01-23 14:14:31.109760: step: 2448/1545, loss: 0.19996117055416107 2023-01-23 14:14:31.963163: step: 2450/1545, loss: 0.08438659459352493 2023-01-23 14:14:32.838576: step: 2452/1545, loss: 0.028221258893609047 2023-01-23 14:14:33.674832: step: 2454/1545, loss: 0.1766897737979889 2023-01-23 14:14:34.526796: step: 2456/1545, loss: 0.012937449850142002 2023-01-23 14:14:35.401692: step: 2458/1545, loss: 0.11013007909059525 2023-01-23 14:14:36.306589: step: 2460/1545, loss: 0.009052416309714317 2023-01-23 14:14:37.158910: step: 2462/1545, loss: 0.20049186050891876 2023-01-23 14:14:38.028562: step: 2464/1545, loss: 0.0006324468995444477 2023-01-23 14:14:38.891759: step: 2466/1545, loss: 0.0020717200823128223 2023-01-23 14:14:39.738997: step: 2468/1545, loss: 0.034789077937603 2023-01-23 14:14:40.590799: step: 2470/1545, loss: 0.2542110085487366 2023-01-23 14:14:41.404928: step: 2472/1545, loss: 0.04203162342309952 2023-01-23 14:14:42.269430: step: 2474/1545, loss: 0.19499266147613525 2023-01-23 14:14:43.176086: step: 2476/1545, loss: 0.0052012428641319275 2023-01-23 14:14:44.075107: step: 2478/1545, loss: 0.26786765456199646 2023-01-23 14:14:44.944404: step: 2480/1545, loss: 0.06866542994976044 2023-01-23 14:14:45.788608: step: 2482/1545, loss: 0.05844705179333687 2023-01-23 14:14:46.680840: step: 2484/1545, loss: 0.006941488012671471 2023-01-23 14:14:47.527806: step: 2486/1545, loss: 0.012096931226551533 2023-01-23 14:14:48.412262: step: 2488/1545, loss: 0.020495306700468063 2023-01-23 14:14:49.276922: step: 2490/1545, loss: 0.07531522214412689 2023-01-23 14:14:50.170953: step: 2492/1545, loss: 0.029716096818447113 2023-01-23 14:14:51.037932: step: 2494/1545, loss: 0.18422840535640717 2023-01-23 14:14:51.946396: step: 2496/1545, loss: 0.032092902809381485 2023-01-23 14:14:52.902355: step: 2498/1545, loss: 0.043829333037137985 2023-01-23 14:14:53.786544: step: 2500/1545, loss: 0.02213786542415619 2023-01-23 14:14:54.713519: step: 2502/1545, loss: 0.14505422115325928 2023-01-23 14:14:55.610957: step: 2504/1545, loss: 0.08537083119153976 2023-01-23 14:14:56.492657: step: 2506/1545, loss: 0.157369002699852 2023-01-23 14:14:57.368186: step: 2508/1545, loss: 0.0379287414252758 2023-01-23 14:14:58.301145: step: 2510/1545, loss: 0.014682695269584656 2023-01-23 14:14:59.222423: step: 2512/1545, loss: 0.39839985966682434 2023-01-23 14:15:00.079723: step: 2514/1545, loss: 0.008041081950068474 2023-01-23 14:15:01.005300: step: 2516/1545, loss: 0.29773029685020447 2023-01-23 14:15:01.928794: step: 2518/1545, loss: 0.03519199788570404 2023-01-23 14:15:02.797541: step: 2520/1545, loss: 0.19940896332263947 2023-01-23 14:15:03.676932: step: 2522/1545, loss: 0.34755739569664 2023-01-23 14:15:04.534360: step: 2524/1545, loss: 0.27353838086128235 2023-01-23 14:15:05.412111: step: 2526/1545, loss: 0.27575284242630005 2023-01-23 14:15:06.268890: step: 2528/1545, loss: 0.04329061135649681 2023-01-23 14:15:07.144136: step: 2530/1545, loss: 0.07371559739112854 2023-01-23 14:15:08.035786: step: 2532/1545, loss: 0.048135705292224884 2023-01-23 14:15:08.930878: step: 2534/1545, loss: 0.1567915380001068 2023-01-23 14:15:09.790879: step: 2536/1545, loss: 0.040082719177007675 2023-01-23 14:15:10.676607: step: 2538/1545, loss: 0.1760331243276596 2023-01-23 14:15:11.665758: step: 2540/1545, loss: 0.041290685534477234 2023-01-23 14:15:12.558140: step: 2542/1545, loss: 0.12166060507297516 2023-01-23 14:15:13.427764: step: 2544/1545, loss: 0.011532461270689964 2023-01-23 14:15:14.427015: step: 2546/1545, loss: 0.32434532046318054 2023-01-23 14:15:15.317500: step: 2548/1545, loss: 0.13973037898540497 2023-01-23 14:15:16.231407: step: 2550/1545, loss: 0.10959209501743317 2023-01-23 14:15:17.125337: step: 2552/1545, loss: 0.6921380162239075 2023-01-23 14:15:18.039659: step: 2554/1545, loss: 0.02746523730456829 2023-01-23 14:15:18.892244: step: 2556/1545, loss: 0.0016590559389442205 2023-01-23 14:15:19.767633: step: 2558/1545, loss: 0.22904184460639954 2023-01-23 14:15:20.646327: step: 2560/1545, loss: 0.014175975695252419 2023-01-23 14:15:21.528884: step: 2562/1545, loss: 0.03987313061952591 2023-01-23 14:15:22.369044: step: 2564/1545, loss: 0.0934816524386406 2023-01-23 14:15:23.216413: step: 2566/1545, loss: 0.0006413750234059989 2023-01-23 14:15:24.068876: step: 2568/1545, loss: 0.016024567186832428 2023-01-23 14:15:24.956835: step: 2570/1545, loss: 0.2363869547843933 2023-01-23 14:15:25.838496: step: 2572/1545, loss: 0.5719231367111206 2023-01-23 14:15:26.705273: step: 2574/1545, loss: 0.0833999291062355 2023-01-23 14:15:27.586352: step: 2576/1545, loss: 0.02922840043902397 2023-01-23 14:15:28.534736: step: 2578/1545, loss: 0.004577190615236759 2023-01-23 14:15:29.400456: step: 2580/1545, loss: 0.027054067701101303 2023-01-23 14:15:30.276348: step: 2582/1545, loss: 0.015469837933778763 2023-01-23 14:15:31.141685: step: 2584/1545, loss: 0.00681003462523222 2023-01-23 14:15:32.025241: step: 2586/1545, loss: 0.04314739257097244 2023-01-23 14:15:32.898956: step: 2588/1545, loss: 0.001487700967118144 2023-01-23 14:15:33.757581: step: 2590/1545, loss: 0.004945761989802122 2023-01-23 14:15:34.617298: step: 2592/1545, loss: 0.01987013965845108 2023-01-23 14:15:35.499235: step: 2594/1545, loss: 0.3216322660446167 2023-01-23 14:15:36.382741: step: 2596/1545, loss: 0.08318942040205002 2023-01-23 14:15:37.275248: step: 2598/1545, loss: 0.11177241057157516 2023-01-23 14:15:38.143025: step: 2600/1545, loss: 1.183009147644043 2023-01-23 14:15:39.012289: step: 2602/1545, loss: 0.06976282596588135 2023-01-23 14:15:39.915460: step: 2604/1545, loss: 0.1790754646062851 2023-01-23 14:15:40.780401: step: 2606/1545, loss: 0.0832040011882782 2023-01-23 14:15:41.704199: step: 2608/1545, loss: 0.0014777653850615025 2023-01-23 14:15:42.571482: step: 2610/1545, loss: 0.025586219504475594 2023-01-23 14:15:43.516180: step: 2612/1545, loss: 0.31995174288749695 2023-01-23 14:15:44.365038: step: 2614/1545, loss: 0.016172071918845177 2023-01-23 14:15:45.271348: step: 2616/1545, loss: 0.0027530353982001543 2023-01-23 14:15:46.169379: step: 2618/1545, loss: 0.0015215632738545537 2023-01-23 14:15:47.038324: step: 2620/1545, loss: 0.0005422041867859662 2023-01-23 14:15:47.990269: step: 2622/1545, loss: 0.49835437536239624 2023-01-23 14:15:48.901524: step: 2624/1545, loss: 0.0027637085877358913 2023-01-23 14:15:49.769871: step: 2626/1545, loss: 0.025558391585946083 2023-01-23 14:15:50.633259: step: 2628/1545, loss: 0.0008532664505764842 2023-01-23 14:15:51.477621: step: 2630/1545, loss: 0.11533049494028091 2023-01-23 14:15:52.359010: step: 2632/1545, loss: 0.012226354330778122 2023-01-23 14:15:53.206820: step: 2634/1545, loss: 0.003006688319146633 2023-01-23 14:15:54.069532: step: 2636/1545, loss: 0.013122334145009518 2023-01-23 14:15:54.964848: step: 2638/1545, loss: 0.17725321650505066 2023-01-23 14:15:55.859266: step: 2640/1545, loss: 0.10464470088481903 2023-01-23 14:15:56.781862: step: 2642/1545, loss: 0.6548736095428467 2023-01-23 14:15:57.738163: step: 2644/1545, loss: 0.009074191562831402 2023-01-23 14:15:58.658914: step: 2646/1545, loss: 0.0013609989546239376 2023-01-23 14:15:59.537588: step: 2648/1545, loss: 0.031498983502388 2023-01-23 14:16:00.422732: step: 2650/1545, loss: 0.1062508076429367 2023-01-23 14:16:01.302161: step: 2652/1545, loss: 0.019397826865315437 2023-01-23 14:16:02.192045: step: 2654/1545, loss: 0.1555432826280594 2023-01-23 14:16:03.044741: step: 2656/1545, loss: 0.3313862681388855 2023-01-23 14:16:03.965915: step: 2658/1545, loss: 1.4607561826705933 2023-01-23 14:16:04.793745: step: 2660/1545, loss: 0.0004768733633682132 2023-01-23 14:16:05.672426: step: 2662/1545, loss: 0.004806152544915676 2023-01-23 14:16:06.500306: step: 2664/1545, loss: 0.08323092758655548 2023-01-23 14:16:07.381581: step: 2666/1545, loss: 0.012545912526547909 2023-01-23 14:16:08.277759: step: 2668/1545, loss: 0.017267556861042976 2023-01-23 14:16:09.116036: step: 2670/1545, loss: 1.0922006368637085 2023-01-23 14:16:09.988287: step: 2672/1545, loss: 0.21331731975078583 2023-01-23 14:16:10.836823: step: 2674/1545, loss: 0.1929028332233429 2023-01-23 14:16:11.761647: step: 2676/1545, loss: 0.0058763287961483 2023-01-23 14:16:12.632660: step: 2678/1545, loss: 0.1996965855360031 2023-01-23 14:16:13.511891: step: 2680/1545, loss: 0.5059987902641296 2023-01-23 14:16:14.403120: step: 2682/1545, loss: 0.13162025809288025 2023-01-23 14:16:15.339155: step: 2684/1545, loss: 0.21233725547790527 2023-01-23 14:16:16.224994: step: 2686/1545, loss: 0.050551071763038635 2023-01-23 14:16:17.139194: step: 2688/1545, loss: 0.033680509775877 2023-01-23 14:16:18.050396: step: 2690/1545, loss: 0.009160103276371956 2023-01-23 14:16:18.905854: step: 2692/1545, loss: 0.04496318846940994 2023-01-23 14:16:19.816977: step: 2694/1545, loss: 0.05748017877340317 2023-01-23 14:16:20.712996: step: 2696/1545, loss: 0.01644379459321499 2023-01-23 14:16:21.636771: step: 2698/1545, loss: 0.16642101109027863 2023-01-23 14:16:22.530267: step: 2700/1545, loss: 0.10223081707954407 2023-01-23 14:16:23.481313: step: 2702/1545, loss: 0.04414070397615433 2023-01-23 14:16:24.362598: step: 2704/1545, loss: 0.0070115430280566216 2023-01-23 14:16:25.212360: step: 2706/1545, loss: 0.2825142443180084 2023-01-23 14:16:26.071670: step: 2708/1545, loss: 0.06349175423383713 2023-01-23 14:16:26.946120: step: 2710/1545, loss: 0.0008099419064819813 2023-01-23 14:16:27.863669: step: 2712/1545, loss: 0.020396914333105087 2023-01-23 14:16:28.733983: step: 2714/1545, loss: 0.023540841415524483 2023-01-23 14:16:29.647296: step: 2716/1545, loss: 0.034330807626247406 2023-01-23 14:16:30.538627: step: 2718/1545, loss: 0.8689678907394409 2023-01-23 14:16:31.448584: step: 2720/1545, loss: 0.03957503288984299 2023-01-23 14:16:32.307913: step: 2722/1545, loss: 0.038750965148210526 2023-01-23 14:16:33.196139: step: 2724/1545, loss: 0.08163527399301529 2023-01-23 14:16:34.032931: step: 2726/1545, loss: 0.0021094621624797583 2023-01-23 14:16:34.928883: step: 2728/1545, loss: 0.22867123782634735 2023-01-23 14:16:35.794957: step: 2730/1545, loss: 0.048894770443439484 2023-01-23 14:16:36.690099: step: 2732/1545, loss: 0.08166274428367615 2023-01-23 14:16:37.549862: step: 2734/1545, loss: 0.025958307087421417 2023-01-23 14:16:38.425654: step: 2736/1545, loss: 0.04743781313300133 2023-01-23 14:16:39.271491: step: 2738/1545, loss: 0.10120510309934616 2023-01-23 14:16:40.109996: step: 2740/1545, loss: 0.022080756723880768 2023-01-23 14:16:41.034154: step: 2742/1545, loss: 0.009860430844128132 2023-01-23 14:16:41.906579: step: 2744/1545, loss: 0.07704771310091019 2023-01-23 14:16:42.813355: step: 2746/1545, loss: 0.03018074296414852 2023-01-23 14:16:43.640744: step: 2748/1545, loss: 0.23240628838539124 2023-01-23 14:16:44.493924: step: 2750/1545, loss: 0.13655221462249756 2023-01-23 14:16:45.385329: step: 2752/1545, loss: 0.2017209678888321 2023-01-23 14:16:46.244609: step: 2754/1545, loss: 0.3408326506614685 2023-01-23 14:16:47.147482: step: 2756/1545, loss: 0.017303410917520523 2023-01-23 14:16:48.012251: step: 2758/1545, loss: 0.18758191168308258 2023-01-23 14:16:48.884841: step: 2760/1545, loss: 0.11265585571527481 2023-01-23 14:16:49.730811: step: 2762/1545, loss: 0.33915573358535767 2023-01-23 14:16:50.604687: step: 2764/1545, loss: 0.0449318066239357 2023-01-23 14:16:51.462372: step: 2766/1545, loss: 0.01335970126092434 2023-01-23 14:16:52.399971: step: 2768/1545, loss: 0.02813040092587471 2023-01-23 14:16:53.285324: step: 2770/1545, loss: 0.002146682236343622 2023-01-23 14:16:54.183446: step: 2772/1545, loss: 0.09308730065822601 2023-01-23 14:16:55.040961: step: 2774/1545, loss: 0.001296054688282311 2023-01-23 14:16:55.926099: step: 2776/1545, loss: 0.039139486849308014 2023-01-23 14:16:56.846844: step: 2778/1545, loss: 0.713071882724762 2023-01-23 14:16:57.809540: step: 2780/1545, loss: 0.0025570238940417767 2023-01-23 14:16:58.666267: step: 2782/1545, loss: 0.0024075722321867943 2023-01-23 14:16:59.515570: step: 2784/1545, loss: 0.30669358372688293 2023-01-23 14:17:00.399854: step: 2786/1545, loss: 0.0035376406740397215 2023-01-23 14:17:01.275182: step: 2788/1545, loss: 0.0003675058833323419 2023-01-23 14:17:02.125310: step: 2790/1545, loss: 0.0023134800139814615 2023-01-23 14:17:03.039646: step: 2792/1545, loss: 0.1681351214647293 2023-01-23 14:17:03.974261: step: 2794/1545, loss: 0.0002923408756032586 2023-01-23 14:17:04.828281: step: 2796/1545, loss: 0.5661096572875977 2023-01-23 14:17:05.712705: step: 2798/1545, loss: 0.27054405212402344 2023-01-23 14:17:06.552736: step: 2800/1545, loss: 0.005822866223752499 2023-01-23 14:17:07.418265: step: 2802/1545, loss: 0.0015068445354700089 2023-01-23 14:17:08.348159: step: 2804/1545, loss: 0.12093271315097809 2023-01-23 14:17:09.221061: step: 2806/1545, loss: 0.0032370612025260925 2023-01-23 14:17:10.087622: step: 2808/1545, loss: 0.4968094229698181 2023-01-23 14:17:10.948771: step: 2810/1545, loss: 0.21824130415916443 2023-01-23 14:17:11.840341: step: 2812/1545, loss: 1.448933720588684 2023-01-23 14:17:12.737382: step: 2814/1545, loss: 1.123842477798462 2023-01-23 14:17:13.613178: step: 2816/1545, loss: 0.006453861948102713 2023-01-23 14:17:14.475763: step: 2818/1545, loss: 0.029155120253562927 2023-01-23 14:17:15.342068: step: 2820/1545, loss: 0.02971334382891655 2023-01-23 14:17:16.252109: step: 2822/1545, loss: 0.009555581957101822 2023-01-23 14:17:17.130322: step: 2824/1545, loss: 0.1004195585846901 2023-01-23 14:17:18.031523: step: 2826/1545, loss: 0.0027503659948706627 2023-01-23 14:17:18.967699: step: 2828/1545, loss: 0.05576507747173309 2023-01-23 14:17:19.798101: step: 2830/1545, loss: 0.08608727902173996 2023-01-23 14:17:20.703163: step: 2832/1545, loss: 0.10350140184164047 2023-01-23 14:17:21.584838: step: 2834/1545, loss: 0.15501989424228668 2023-01-23 14:17:22.479452: step: 2836/1545, loss: 0.15558470785617828 2023-01-23 14:17:23.391226: step: 2838/1545, loss: 0.2542386054992676 2023-01-23 14:17:24.245202: step: 2840/1545, loss: 0.0006911182426847517 2023-01-23 14:17:25.162089: step: 2842/1545, loss: 0.03369400277733803 2023-01-23 14:17:26.024873: step: 2844/1545, loss: 0.0143045075237751 2023-01-23 14:17:26.886094: step: 2846/1545, loss: 0.0942729115486145 2023-01-23 14:17:27.760859: step: 2848/1545, loss: 0.3778941035270691 2023-01-23 14:17:28.688953: step: 2850/1545, loss: 0.45437824726104736 2023-01-23 14:17:29.560736: step: 2852/1545, loss: 0.028172770515084267 2023-01-23 14:17:30.437193: step: 2854/1545, loss: 0.0034963032230734825 2023-01-23 14:17:31.320069: step: 2856/1545, loss: 0.046044278889894485 2023-01-23 14:17:32.203324: step: 2858/1545, loss: 0.025701239705085754 2023-01-23 14:17:33.214326: step: 2860/1545, loss: 0.06102488189935684 2023-01-23 14:17:34.098033: step: 2862/1545, loss: 0.006508417893201113 2023-01-23 14:17:34.973169: step: 2864/1545, loss: 0.0455826073884964 2023-01-23 14:17:35.834235: step: 2866/1545, loss: 0.2561194598674774 2023-01-23 14:17:36.779352: step: 2868/1545, loss: 0.019601227715611458 2023-01-23 14:17:37.691729: step: 2870/1545, loss: 0.03656219691038132 2023-01-23 14:17:38.601428: step: 2872/1545, loss: 0.018490944057703018 2023-01-23 14:17:39.445589: step: 2874/1545, loss: 0.03214779123663902 2023-01-23 14:17:40.301135: step: 2876/1545, loss: 0.1578218638896942 2023-01-23 14:17:41.204446: step: 2878/1545, loss: 0.32958248257637024 2023-01-23 14:17:42.120861: step: 2880/1545, loss: 0.08357302099466324 2023-01-23 14:17:42.983954: step: 2882/1545, loss: 0.030057508498430252 2023-01-23 14:17:43.817054: step: 2884/1545, loss: 0.023079270496964455 2023-01-23 14:17:44.692257: step: 2886/1545, loss: 0.013937268406152725 2023-01-23 14:17:45.530750: step: 2888/1545, loss: 0.01245253998786211 2023-01-23 14:17:46.388530: step: 2890/1545, loss: 0.19441360235214233 2023-01-23 14:17:47.314957: step: 2892/1545, loss: 0.003363731550052762 2023-01-23 14:17:48.181595: step: 2894/1545, loss: 0.16139031946659088 2023-01-23 14:17:49.110533: step: 2896/1545, loss: 0.20971696078777313 2023-01-23 14:17:49.956496: step: 2898/1545, loss: 0.3243788182735443 2023-01-23 14:17:50.812654: step: 2900/1545, loss: 0.007854156196117401 2023-01-23 14:17:51.692912: step: 2902/1545, loss: 0.21485520899295807 2023-01-23 14:17:52.596574: step: 2904/1545, loss: 0.030740942806005478 2023-01-23 14:17:53.496687: step: 2906/1545, loss: 0.009151047095656395 2023-01-23 14:17:54.357978: step: 2908/1545, loss: 0.014943389222025871 2023-01-23 14:17:55.201175: step: 2910/1545, loss: 0.009051735512912273 2023-01-23 14:17:56.100820: step: 2912/1545, loss: 0.06795132160186768 2023-01-23 14:17:56.943789: step: 2914/1545, loss: 0.036151446402072906 2023-01-23 14:17:57.820803: step: 2916/1545, loss: 0.7383586168289185 2023-01-23 14:17:58.728393: step: 2918/1545, loss: 0.1614329069852829 2023-01-23 14:17:59.615139: step: 2920/1545, loss: 0.04656725749373436 2023-01-23 14:18:00.491732: step: 2922/1545, loss: 0.02663584239780903 2023-01-23 14:18:01.366645: step: 2924/1545, loss: 0.3419486880302429 2023-01-23 14:18:02.265034: step: 2926/1545, loss: 0.01234557293355465 2023-01-23 14:18:03.144067: step: 2928/1545, loss: 0.015359582379460335 2023-01-23 14:18:04.063965: step: 2930/1545, loss: 0.17108261585235596 2023-01-23 14:18:04.914678: step: 2932/1545, loss: 0.013076599687337875 2023-01-23 14:18:05.795358: step: 2934/1545, loss: 0.026069452986121178 2023-01-23 14:18:06.658828: step: 2936/1545, loss: 0.0038647400215268135 2023-01-23 14:18:07.495657: step: 2938/1545, loss: 0.13724835216999054 2023-01-23 14:18:08.417450: step: 2940/1545, loss: 0.010280495509505272 2023-01-23 14:18:09.267039: step: 2942/1545, loss: 0.031530819833278656 2023-01-23 14:18:10.180860: step: 2944/1545, loss: 0.0035450514405965805 2023-01-23 14:18:11.087367: step: 2946/1545, loss: 0.0329354964196682 2023-01-23 14:18:11.938225: step: 2948/1545, loss: 0.00045905139995738864 2023-01-23 14:18:12.838687: step: 2950/1545, loss: 0.2506313920021057 2023-01-23 14:18:13.714219: step: 2952/1545, loss: 0.0031688266899436712 2023-01-23 14:18:14.632354: step: 2954/1545, loss: 1.5830137729644775 2023-01-23 14:18:15.495307: step: 2956/1545, loss: 0.0539107583463192 2023-01-23 14:18:16.383188: step: 2958/1545, loss: 0.08128244429826736 2023-01-23 14:18:17.220001: step: 2960/1545, loss: 0.03594309464097023 2023-01-23 14:18:18.092783: step: 2962/1545, loss: 0.14204417169094086 2023-01-23 14:18:18.976992: step: 2964/1545, loss: 0.03488101437687874 2023-01-23 14:18:19.823585: step: 2966/1545, loss: 0.0007681367569603026 2023-01-23 14:18:20.681226: step: 2968/1545, loss: 0.04223494231700897 2023-01-23 14:18:21.528876: step: 2970/1545, loss: 0.035806600004434586 2023-01-23 14:18:22.380592: step: 2972/1545, loss: 0.19267693161964417 2023-01-23 14:18:23.265008: step: 2974/1545, loss: 0.3907777965068817 2023-01-23 14:18:24.124102: step: 2976/1545, loss: 0.06559596955776215 2023-01-23 14:18:24.995637: step: 2978/1545, loss: 0.03679809346795082 2023-01-23 14:18:25.851750: step: 2980/1545, loss: 0.15921036899089813 2023-01-23 14:18:26.729808: step: 2982/1545, loss: 0.010062298737466335 2023-01-23 14:18:27.678610: step: 2984/1545, loss: 0.003958901856094599 2023-01-23 14:18:28.557743: step: 2986/1545, loss: 0.18681484460830688 2023-01-23 14:18:29.458112: step: 2988/1545, loss: 0.03004680760204792 2023-01-23 14:18:30.336783: step: 2990/1545, loss: 0.11254808306694031 2023-01-23 14:18:31.222826: step: 2992/1545, loss: 0.0018354319036006927 2023-01-23 14:18:32.136932: step: 2994/1545, loss: 0.001118820975534618 2023-01-23 14:18:33.052393: step: 2996/1545, loss: 0.01757567748427391 2023-01-23 14:18:33.915325: step: 2998/1545, loss: 0.019463667646050453 2023-01-23 14:18:34.840269: step: 3000/1545, loss: 0.2515121400356293 2023-01-23 14:18:35.676856: step: 3002/1545, loss: 0.03030363656580448 2023-01-23 14:18:36.500212: step: 3004/1545, loss: 0.0054578701965510845 2023-01-23 14:18:37.350660: step: 3006/1545, loss: 0.006539256777614355 2023-01-23 14:18:38.235931: step: 3008/1545, loss: 0.07493174821138382 2023-01-23 14:18:39.125755: step: 3010/1545, loss: 0.08114367723464966 2023-01-23 14:18:40.010534: step: 3012/1545, loss: 0.15902075171470642 2023-01-23 14:18:40.852657: step: 3014/1545, loss: 0.012243254110217094 2023-01-23 14:18:41.734933: step: 3016/1545, loss: 0.15245158970355988 2023-01-23 14:18:42.613120: step: 3018/1545, loss: 0.1716037541627884 2023-01-23 14:18:43.575660: step: 3020/1545, loss: 0.01239106711000204 2023-01-23 14:18:44.506751: step: 3022/1545, loss: 0.00276792305521667 2023-01-23 14:18:45.389620: step: 3024/1545, loss: 0.3123539984226227 2023-01-23 14:18:46.273254: step: 3026/1545, loss: 0.0008656748104840517 2023-01-23 14:18:47.187451: step: 3028/1545, loss: 0.023862306028604507 2023-01-23 14:18:48.082041: step: 3030/1545, loss: 0.3979364037513733 2023-01-23 14:18:48.955835: step: 3032/1545, loss: 0.014111943542957306 2023-01-23 14:18:49.814615: step: 3034/1545, loss: 0.018086912110447884 2023-01-23 14:18:50.655494: step: 3036/1545, loss: 0.002550367498770356 2023-01-23 14:18:51.590129: step: 3038/1545, loss: 0.06745023280382156 2023-01-23 14:18:52.464753: step: 3040/1545, loss: 0.023229509592056274 2023-01-23 14:18:53.324672: step: 3042/1545, loss: 0.02762746997177601 2023-01-23 14:18:54.189852: step: 3044/1545, loss: 0.07230588048696518 2023-01-23 14:18:55.094618: step: 3046/1545, loss: 0.043312471359968185 2023-01-23 14:18:55.965346: step: 3048/1545, loss: 0.0416468009352684 2023-01-23 14:18:56.892367: step: 3050/1545, loss: 0.032623596489429474 2023-01-23 14:18:57.766435: step: 3052/1545, loss: 0.04539293050765991 2023-01-23 14:18:58.637169: step: 3054/1545, loss: 0.10594236850738525 2023-01-23 14:18:59.542735: step: 3056/1545, loss: 0.7454984784126282 2023-01-23 14:19:00.393429: step: 3058/1545, loss: 0.045157529413700104 2023-01-23 14:19:01.275906: step: 3060/1545, loss: 0.009379805997014046 2023-01-23 14:19:02.143798: step: 3062/1545, loss: 0.09323455393314362 2023-01-23 14:19:02.987409: step: 3064/1545, loss: 0.0012828498147428036 2023-01-23 14:19:03.845584: step: 3066/1545, loss: 0.05539406090974808 2023-01-23 14:19:04.725013: step: 3068/1545, loss: 0.010029592551290989 2023-01-23 14:19:05.575223: step: 3070/1545, loss: 0.00016445570508949459 2023-01-23 14:19:06.435114: step: 3072/1545, loss: 0.3836720287799835 2023-01-23 14:19:07.280444: step: 3074/1545, loss: 0.004156029783189297 2023-01-23 14:19:08.173364: step: 3076/1545, loss: 0.007496356498450041 2023-01-23 14:19:09.085745: step: 3078/1545, loss: 0.015112309716641903 2023-01-23 14:19:09.944449: step: 3080/1545, loss: 0.0024913297966122627 2023-01-23 14:19:10.818886: step: 3082/1545, loss: 0.02313508279621601 2023-01-23 14:19:11.687214: step: 3084/1545, loss: 0.0047578816302120686 2023-01-23 14:19:12.582694: step: 3086/1545, loss: 0.0004985903506167233 2023-01-23 14:19:13.406009: step: 3088/1545, loss: 0.04511675983667374 2023-01-23 14:19:14.291112: step: 3090/1545, loss: 0.0002939922851510346 ================================================== Loss: 0.109 -------------------- Dev Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6669509987520128, 'r': 0.6669509987520128, 'f1': 0.6669509987520128}, 'combined': 0.44063549198124585, 'epoch': 19} Test Chinese: {'event': {'p': 0.6392742796157951, 'r': 0.7659846547314578, 'f1': 0.6969168121000582}, 'argument': {'p': 0.7165364993103626, 'r': 0.7044984672486382, 'f1': 0.7104664943104287}, 'combined': 0.4951360443187281, 'epoch': 19} Dev Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.665609309737802, 'r': 0.6721299736613826, 'f1': 0.6688537495677951}, 'combined': 0.44590249971186335, 'epoch': 19} Test Korean: {'event': {'p': 0.6312169312169312, 'r': 0.7627877237851662, 'f1': 0.6907932831499711}, 'argument': {'p': 0.7096480242524722, 'r': 0.7004141808446711, 'f1': 0.7050008684696171}, 'combined': 0.48700986455370776, 'epoch': 19} Dev Russian: {'event': {'p': 0.5679133858267716, 'r': 0.7683089214380826, 'f1': 0.653084323712507}, 'argument': {'p': 0.6637001701988704, 'r': 0.6722640433627267, 'f1': 0.667954658469376}, 'combined': 0.436230716397091, 'epoch': 19} Test Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7186624970441664, 'r': 0.7122050279580339, 'f1': 0.7154191913034632}, 'combined': 0.5056617302856178, 'epoch': 19} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6338609307359306, 'r': 0.5867142499373904, 'f1': 0.6093770321238132}, 'combined': 0.43395031075483664, 'epoch': 19} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6713836477987422, 'r': 0.48744292237442927, 'f1': 0.5648148148148148}, 'combined': 0.346816114359974, 'epoch': 19} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5577002310554942, 'r': 0.5577002310554942, 'f1': 0.5577002310554942}, 'combined': 0.3106178502081233, 'epoch': 19} New best korean model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.665609309737802, 'r': 0.6721299736613826, 'f1': 0.6688537495677951}, 'combined': 0.44590249971186335, 'epoch': 19} Test for Korean: {'event': {'p': 0.6312169312169312, 'r': 0.7627877237851662, 'f1': 0.6907932831499711}, 'argument': {'p': 0.7096480242524722, 'r': 0.7004141808446711, 'f1': 0.7050008684696171}, 'combined': 0.48700986455370776, 'epoch': 19} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6713836477987422, 'r': 0.48744292237442927, 'f1': 0.5648148148148148}, 'combined': 0.346816114359974, 'epoch': 19} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 20 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 14:24:38.427749: step: 2/1545, loss: 0.017370853573083878 2023-01-23 14:24:39.344539: step: 4/1545, loss: 0.1179002970457077 2023-01-23 14:24:40.199487: step: 6/1545, loss: 0.003270543646067381 2023-01-23 14:24:41.078001: step: 8/1545, loss: 0.0008517117821611464 2023-01-23 14:24:41.939561: step: 10/1545, loss: 0.0062208534218370914 2023-01-23 14:24:42.841493: step: 12/1545, loss: 0.09256323426961899 2023-01-23 14:24:43.712932: step: 14/1545, loss: 0.07797065377235413 2023-01-23 14:24:44.575035: step: 16/1545, loss: 0.16949935257434845 2023-01-23 14:24:45.439905: step: 18/1545, loss: 0.005733522120863199 2023-01-23 14:24:46.335717: step: 20/1545, loss: 0.14509917795658112 2023-01-23 14:24:47.209783: step: 22/1545, loss: 0.04008275642991066 2023-01-23 14:24:48.096411: step: 24/1545, loss: 0.03162651136517525 2023-01-23 14:24:48.987852: step: 26/1545, loss: 0.08056478947401047 2023-01-23 14:24:49.854452: step: 28/1545, loss: 0.000462445430457592 2023-01-23 14:24:50.751034: step: 30/1545, loss: 0.06709815561771393 2023-01-23 14:24:51.612756: step: 32/1545, loss: 0.09145193547010422 2023-01-23 14:24:52.491155: step: 34/1545, loss: 0.042343828827142715 2023-01-23 14:24:53.365677: step: 36/1545, loss: 0.052426524460315704 2023-01-23 14:24:54.222983: step: 38/1545, loss: 0.20481239259243011 2023-01-23 14:24:55.086086: step: 40/1545, loss: 0.03960951790213585 2023-01-23 14:24:56.037370: step: 42/1545, loss: 0.004007053095847368 2023-01-23 14:24:56.884050: step: 44/1545, loss: 0.18004262447357178 2023-01-23 14:24:57.727475: step: 46/1545, loss: 0.004588601645082235 2023-01-23 14:24:58.707482: step: 48/1545, loss: 0.018326394259929657 2023-01-23 14:24:59.630795: step: 50/1545, loss: 0.008614282123744488 2023-01-23 14:25:00.542370: step: 52/1545, loss: 0.563597559928894 2023-01-23 14:25:01.429603: step: 54/1545, loss: 0.05562837794423103 2023-01-23 14:25:02.299822: step: 56/1545, loss: 0.0017778521869331598 2023-01-23 14:25:03.163773: step: 58/1545, loss: 0.030446697026491165 2023-01-23 14:25:04.009623: step: 60/1545, loss: 0.22476249933242798 2023-01-23 14:25:04.907120: step: 62/1545, loss: 0.012980164960026741 2023-01-23 14:25:05.823796: step: 64/1545, loss: 0.05410686507821083 2023-01-23 14:25:06.671240: step: 66/1545, loss: 0.026543157175183296 2023-01-23 14:25:07.574784: step: 68/1545, loss: 0.34515127539634705 2023-01-23 14:25:08.471633: step: 70/1545, loss: 0.004763323348015547 2023-01-23 14:25:09.388980: step: 72/1545, loss: 0.26134833693504333 2023-01-23 14:25:10.257575: step: 74/1545, loss: 0.05490832403302193 2023-01-23 14:25:11.187761: step: 76/1545, loss: 0.029883887618780136 2023-01-23 14:25:12.088176: step: 78/1545, loss: 0.04865892976522446 2023-01-23 14:25:12.942230: step: 80/1545, loss: 0.06505817174911499 2023-01-23 14:25:13.833696: step: 82/1545, loss: 0.025135934352874756 2023-01-23 14:25:14.706719: step: 84/1545, loss: 0.12462221831083298 2023-01-23 14:25:15.548818: step: 86/1545, loss: 0.004648716654628515 2023-01-23 14:25:16.467938: step: 88/1545, loss: 0.010911673307418823 2023-01-23 14:25:17.396112: step: 90/1545, loss: 0.08437386155128479 2023-01-23 14:25:18.269061: step: 92/1545, loss: 0.00035794079303741455 2023-01-23 14:25:19.142969: step: 94/1545, loss: 0.0017970167100429535 2023-01-23 14:25:20.058707: step: 96/1545, loss: 0.04856140539050102 2023-01-23 14:25:20.979284: step: 98/1545, loss: 0.2617053985595703 2023-01-23 14:25:21.866903: step: 100/1545, loss: 0.1536989063024521 2023-01-23 14:25:22.723833: step: 102/1545, loss: 0.011547891423106194 2023-01-23 14:25:23.579327: step: 104/1545, loss: 0.0038288533687591553 2023-01-23 14:25:24.504480: step: 106/1545, loss: 0.06791722029447556 2023-01-23 14:25:25.438474: step: 108/1545, loss: 0.039644863456487656 2023-01-23 14:25:26.330595: step: 110/1545, loss: 0.0026192902587354183 2023-01-23 14:25:27.190615: step: 112/1545, loss: 0.02028360404074192 2023-01-23 14:25:28.068095: step: 114/1545, loss: 0.2490539252758026 2023-01-23 14:25:28.958838: step: 116/1545, loss: 0.002597122685983777 2023-01-23 14:25:29.814468: step: 118/1545, loss: 0.01709870621562004 2023-01-23 14:25:30.682706: step: 120/1545, loss: 0.001087524346075952 2023-01-23 14:25:31.524102: step: 122/1545, loss: 0.003781060455366969 2023-01-23 14:25:32.344632: step: 124/1545, loss: 0.002101341262459755 2023-01-23 14:25:33.216958: step: 126/1545, loss: 0.0013181451940909028 2023-01-23 14:25:34.141096: step: 128/1545, loss: 0.0023423684760928154 2023-01-23 14:25:35.017954: step: 130/1545, loss: 0.004786988720297813 2023-01-23 14:25:35.853281: step: 132/1545, loss: 0.011652492918074131 2023-01-23 14:25:36.712460: step: 134/1545, loss: 0.07961833477020264 2023-01-23 14:25:37.669294: step: 136/1545, loss: 0.03860824555158615 2023-01-23 14:25:38.505048: step: 138/1545, loss: 0.020949753001332283 2023-01-23 14:25:39.375583: step: 140/1545, loss: 0.03835117444396019 2023-01-23 14:25:40.208960: step: 142/1545, loss: 0.001312626525759697 2023-01-23 14:25:41.049326: step: 144/1545, loss: 0.011326281353831291 2023-01-23 14:25:41.892080: step: 146/1545, loss: 0.0262684915214777 2023-01-23 14:25:42.834835: step: 148/1545, loss: 0.08637998253107071 2023-01-23 14:25:43.774491: step: 150/1545, loss: 0.02257513254880905 2023-01-23 14:25:44.641034: step: 152/1545, loss: 0.003131493693217635 2023-01-23 14:25:45.565817: step: 154/1545, loss: 0.014886683784425259 2023-01-23 14:25:46.394974: step: 156/1545, loss: 0.1530413031578064 2023-01-23 14:25:47.292517: step: 158/1545, loss: 0.37357577681541443 2023-01-23 14:25:48.164641: step: 160/1545, loss: 0.006003405898809433 2023-01-23 14:25:49.055322: step: 162/1545, loss: 0.001564519596286118 2023-01-23 14:25:49.917690: step: 164/1545, loss: 0.04395533353090286 2023-01-23 14:25:50.830433: step: 166/1545, loss: 0.002747925231233239 2023-01-23 14:25:51.742072: step: 168/1545, loss: 0.0187691580504179 2023-01-23 14:25:52.622163: step: 170/1545, loss: 0.00015498987340833992 2023-01-23 14:25:53.507180: step: 172/1545, loss: 0.001783412997610867 2023-01-23 14:25:54.411111: step: 174/1545, loss: 0.025507809594273567 2023-01-23 14:25:55.337685: step: 176/1545, loss: 0.18225184082984924 2023-01-23 14:25:56.217699: step: 178/1545, loss: 0.004896179772913456 2023-01-23 14:25:57.076034: step: 180/1545, loss: 0.00023650762159377337 2023-01-23 14:25:57.949516: step: 182/1545, loss: 0.008996943943202496 2023-01-23 14:25:58.853837: step: 184/1545, loss: 0.24149931967258453 2023-01-23 14:25:59.787245: step: 186/1545, loss: 0.0006771218031644821 2023-01-23 14:26:00.651532: step: 188/1545, loss: 0.0008177604759112 2023-01-23 14:26:01.585787: step: 190/1545, loss: 0.0022711160127073526 2023-01-23 14:26:02.474276: step: 192/1545, loss: 0.02154611051082611 2023-01-23 14:26:03.380536: step: 194/1545, loss: 0.028476351872086525 2023-01-23 14:26:04.294713: step: 196/1545, loss: 0.0006335739744827151 2023-01-23 14:26:05.183583: step: 198/1545, loss: 0.22177651524543762 2023-01-23 14:26:06.078636: step: 200/1545, loss: 0.00028097908943891525 2023-01-23 14:26:06.988022: step: 202/1545, loss: 0.04520334675908089 2023-01-23 14:26:07.852157: step: 204/1545, loss: 0.028883835300803185 2023-01-23 14:26:08.745200: step: 206/1545, loss: 0.21854570508003235 2023-01-23 14:26:09.613596: step: 208/1545, loss: 0.0005047593731433153 2023-01-23 14:26:10.521748: step: 210/1545, loss: 0.0007396112778224051 2023-01-23 14:26:11.439504: step: 212/1545, loss: 0.022981073707342148 2023-01-23 14:26:12.340072: step: 214/1545, loss: 0.0028143778908997774 2023-01-23 14:26:13.229869: step: 216/1545, loss: 0.003909614402800798 2023-01-23 14:26:14.105247: step: 218/1545, loss: 0.006537346169352531 2023-01-23 14:26:15.007556: step: 220/1545, loss: 0.01381749752908945 2023-01-23 14:26:15.893059: step: 222/1545, loss: 0.001228656736202538 2023-01-23 14:26:16.826602: step: 224/1545, loss: 0.07754022628068924 2023-01-23 14:26:17.729013: step: 226/1545, loss: 0.013328827917575836 2023-01-23 14:26:18.594302: step: 228/1545, loss: 0.0009382156422361732 2023-01-23 14:26:19.546712: step: 230/1545, loss: 0.3402279317378998 2023-01-23 14:26:20.405034: step: 232/1545, loss: 0.011378495953977108 2023-01-23 14:26:21.261805: step: 234/1545, loss: 0.022103097289800644 2023-01-23 14:26:22.143328: step: 236/1545, loss: 0.004601079970598221 2023-01-23 14:26:23.102475: step: 238/1545, loss: 0.03334769234061241 2023-01-23 14:26:23.987197: step: 240/1545, loss: 0.199740931391716 2023-01-23 14:26:24.887920: step: 242/1545, loss: 0.08566125482320786 2023-01-23 14:26:25.797693: step: 244/1545, loss: 0.03820393607020378 2023-01-23 14:26:26.746274: step: 246/1545, loss: 0.002347234170883894 2023-01-23 14:26:27.650330: step: 248/1545, loss: 0.17298182845115662 2023-01-23 14:26:28.537748: step: 250/1545, loss: 0.055765774101018906 2023-01-23 14:26:29.399795: step: 252/1545, loss: 0.050638433545827866 2023-01-23 14:26:30.287209: step: 254/1545, loss: 0.0008927858434617519 2023-01-23 14:26:31.168622: step: 256/1545, loss: 0.013715919107198715 2023-01-23 14:26:32.030730: step: 258/1545, loss: 0.033861562609672546 2023-01-23 14:26:32.902228: step: 260/1545, loss: 0.004632720723748207 2023-01-23 14:26:33.797821: step: 262/1545, loss: 0.18484216928482056 2023-01-23 14:26:34.699569: step: 264/1545, loss: 0.003986027091741562 2023-01-23 14:26:35.602070: step: 266/1545, loss: 0.17823873460292816 2023-01-23 14:26:36.447655: step: 268/1545, loss: 0.016597412526607513 2023-01-23 14:26:37.312109: step: 270/1545, loss: 0.0037667679134756327 2023-01-23 14:26:38.156201: step: 272/1545, loss: 0.00024267016851808876 2023-01-23 14:26:39.030689: step: 274/1545, loss: 0.003367156721651554 2023-01-23 14:26:39.916895: step: 276/1545, loss: 0.296669065952301 2023-01-23 14:26:40.811285: step: 278/1545, loss: 0.03598003461956978 2023-01-23 14:26:41.658533: step: 280/1545, loss: 0.007238152902573347 2023-01-23 14:26:42.563246: step: 282/1545, loss: 0.04284459352493286 2023-01-23 14:26:43.439148: step: 284/1545, loss: 0.013673556968569756 2023-01-23 14:26:44.298021: step: 286/1545, loss: 0.014448563568294048 2023-01-23 14:26:45.213480: step: 288/1545, loss: 0.013196460902690887 2023-01-23 14:26:46.111308: step: 290/1545, loss: 0.013183149509131908 2023-01-23 14:26:46.972675: step: 292/1545, loss: 0.029719941318035126 2023-01-23 14:26:47.932463: step: 294/1545, loss: 0.10646370053291321 2023-01-23 14:26:48.830783: step: 296/1545, loss: 0.03265739232301712 2023-01-23 14:26:49.740492: step: 298/1545, loss: 0.16814066469669342 2023-01-23 14:26:50.641837: step: 300/1545, loss: 0.1360631287097931 2023-01-23 14:26:51.508206: step: 302/1545, loss: 0.10430634021759033 2023-01-23 14:26:52.493088: step: 304/1545, loss: 1.4236793518066406 2023-01-23 14:26:53.401369: step: 306/1545, loss: 0.013608580455183983 2023-01-23 14:26:54.288101: step: 308/1545, loss: 0.0316363200545311 2023-01-23 14:26:55.209942: step: 310/1545, loss: 0.14353469014167786 2023-01-23 14:26:56.108000: step: 312/1545, loss: 0.02720034122467041 2023-01-23 14:26:56.960129: step: 314/1545, loss: 0.00563958752900362 2023-01-23 14:26:57.833992: step: 316/1545, loss: 0.03745070472359657 2023-01-23 14:26:58.706564: step: 318/1545, loss: 0.0034540449269115925 2023-01-23 14:26:59.538162: step: 320/1545, loss: 0.0007318446878343821 2023-01-23 14:27:00.388092: step: 322/1545, loss: 0.0152159184217453 2023-01-23 14:27:01.260166: step: 324/1545, loss: 0.11256054788827896 2023-01-23 14:27:02.187785: step: 326/1545, loss: 0.11130335927009583 2023-01-23 14:27:03.123038: step: 328/1545, loss: 0.1009908989071846 2023-01-23 14:27:04.053188: step: 330/1545, loss: 0.028223181143403053 2023-01-23 14:27:04.948168: step: 332/1545, loss: 0.00774375069886446 2023-01-23 14:27:05.931615: step: 334/1545, loss: 0.0005021282704547048 2023-01-23 14:27:06.871674: step: 336/1545, loss: 0.05084579065442085 2023-01-23 14:27:07.825783: step: 338/1545, loss: 0.023692045360803604 2023-01-23 14:27:08.696794: step: 340/1545, loss: 0.009728423319756985 2023-01-23 14:27:09.561718: step: 342/1545, loss: 0.0018676117761060596 2023-01-23 14:27:10.450795: step: 344/1545, loss: 0.03028111904859543 2023-01-23 14:27:11.367395: step: 346/1545, loss: 0.03194503113627434 2023-01-23 14:27:12.277102: step: 348/1545, loss: 0.38381001353263855 2023-01-23 14:27:13.145038: step: 350/1545, loss: 0.03711320459842682 2023-01-23 14:27:14.017970: step: 352/1545, loss: 0.14840921759605408 2023-01-23 14:27:14.887410: step: 354/1545, loss: 0.0003429537464398891 2023-01-23 14:27:15.763469: step: 356/1545, loss: 0.0036365706473588943 2023-01-23 14:27:16.679395: step: 358/1545, loss: 0.15062497556209564 2023-01-23 14:27:17.644404: step: 360/1545, loss: 0.30071374773979187 2023-01-23 14:27:18.579991: step: 362/1545, loss: 0.0005960236303508282 2023-01-23 14:27:19.496440: step: 364/1545, loss: 0.0009287282009609044 2023-01-23 14:27:20.446556: step: 366/1545, loss: 0.12658175826072693 2023-01-23 14:27:21.362004: step: 368/1545, loss: 0.005730900913476944 2023-01-23 14:27:22.300480: step: 370/1545, loss: 0.00019021179468836635 2023-01-23 14:27:23.186921: step: 372/1545, loss: 0.10340379178524017 2023-01-23 14:27:24.114449: step: 374/1545, loss: 0.0038914948236197233 2023-01-23 14:27:24.976209: step: 376/1545, loss: 0.0030547697097063065 2023-01-23 14:27:25.873994: step: 378/1545, loss: 0.005157897714525461 2023-01-23 14:27:26.738452: step: 380/1545, loss: 0.012412969022989273 2023-01-23 14:27:27.630107: step: 382/1545, loss: 0.04747779294848442 2023-01-23 14:27:28.475625: step: 384/1545, loss: 0.34913331270217896 2023-01-23 14:27:29.371427: step: 386/1545, loss: 0.018172703683376312 2023-01-23 14:27:30.271053: step: 388/1545, loss: 0.008594545535743237 2023-01-23 14:27:31.204550: step: 390/1545, loss: 0.00038551288889721036 2023-01-23 14:27:32.094367: step: 392/1545, loss: 0.0005187644856050611 2023-01-23 14:27:32.977958: step: 394/1545, loss: 0.01134397927671671 2023-01-23 14:27:33.849390: step: 396/1545, loss: 0.004312619566917419 2023-01-23 14:27:34.705926: step: 398/1545, loss: 0.026553170755505562 2023-01-23 14:27:35.618586: step: 400/1545, loss: 0.22498087584972382 2023-01-23 14:27:36.498365: step: 402/1545, loss: 0.0071071903221309185 2023-01-23 14:27:37.407005: step: 404/1545, loss: 0.008368170820176601 2023-01-23 14:27:38.331432: step: 406/1545, loss: 0.13628330826759338 2023-01-23 14:27:39.208330: step: 408/1545, loss: 0.1212233155965805 2023-01-23 14:27:40.103293: step: 410/1545, loss: 0.08200788497924805 2023-01-23 14:27:40.963288: step: 412/1545, loss: 0.025826286524534225 2023-01-23 14:27:41.857015: step: 414/1545, loss: 0.09438930451869965 2023-01-23 14:27:42.749406: step: 416/1545, loss: 0.007844989188015461 2023-01-23 14:27:43.616926: step: 418/1545, loss: 0.008673736825585365 2023-01-23 14:27:44.571260: step: 420/1545, loss: 0.18260438740253448 2023-01-23 14:27:45.470589: step: 422/1545, loss: 0.07121126353740692 2023-01-23 14:27:46.317107: step: 424/1545, loss: 0.002817922504618764 2023-01-23 14:27:47.208436: step: 426/1545, loss: 0.29878363013267517 2023-01-23 14:27:48.107566: step: 428/1545, loss: 0.01467030867934227 2023-01-23 14:27:49.003476: step: 430/1545, loss: 0.014220168814063072 2023-01-23 14:27:49.922803: step: 432/1545, loss: 0.0046962047927081585 2023-01-23 14:27:50.767994: step: 434/1545, loss: 0.004989197943359613 2023-01-23 14:27:51.612310: step: 436/1545, loss: 0.09051989763975143 2023-01-23 14:27:52.495150: step: 438/1545, loss: 0.006354428827762604 2023-01-23 14:27:53.381923: step: 440/1545, loss: 0.01814359799027443 2023-01-23 14:27:54.267826: step: 442/1545, loss: 0.5661057829856873 2023-01-23 14:27:55.162608: step: 444/1545, loss: 0.0032998444512486458 2023-01-23 14:27:56.128939: step: 446/1545, loss: 0.12824437022209167 2023-01-23 14:27:57.081645: step: 448/1545, loss: 0.01150711253285408 2023-01-23 14:27:58.022262: step: 450/1545, loss: 0.002833410631865263 2023-01-23 14:27:58.940210: step: 452/1545, loss: 0.07055015861988068 2023-01-23 14:27:59.809190: step: 454/1545, loss: 0.008691158145666122 2023-01-23 14:28:00.806850: step: 456/1545, loss: 0.08300821483135223 2023-01-23 14:28:01.662616: step: 458/1545, loss: 0.09320848435163498 2023-01-23 14:28:02.531062: step: 460/1545, loss: 0.11350135505199432 2023-01-23 14:28:03.492869: step: 462/1545, loss: 0.03154878318309784 2023-01-23 14:28:04.454046: step: 464/1545, loss: 0.10514163970947266 2023-01-23 14:28:05.322759: step: 466/1545, loss: 0.16351890563964844 2023-01-23 14:28:06.185251: step: 468/1545, loss: 0.053488463163375854 2023-01-23 14:28:07.031946: step: 470/1545, loss: 0.007184124086052179 2023-01-23 14:28:07.976523: step: 472/1545, loss: 0.044643301516771317 2023-01-23 14:28:08.851003: step: 474/1545, loss: 0.03655882179737091 2023-01-23 14:28:09.743530: step: 476/1545, loss: 0.030445508658885956 2023-01-23 14:28:10.636986: step: 478/1545, loss: 0.0044963001273572445 2023-01-23 14:28:11.543142: step: 480/1545, loss: 0.05725134536623955 2023-01-23 14:28:12.394105: step: 482/1545, loss: 0.008376125246286392 2023-01-23 14:28:13.319026: step: 484/1545, loss: 0.00900667067617178 2023-01-23 14:28:14.178026: step: 486/1545, loss: 0.07060234993696213 2023-01-23 14:28:15.079816: step: 488/1545, loss: 0.11304383724927902 2023-01-23 14:28:15.931015: step: 490/1545, loss: 0.11434069275856018 2023-01-23 14:28:16.783285: step: 492/1545, loss: 0.10631609708070755 2023-01-23 14:28:17.727509: step: 494/1545, loss: 0.01308831200003624 2023-01-23 14:28:18.585088: step: 496/1545, loss: 0.0053350841626524925 2023-01-23 14:28:19.464490: step: 498/1545, loss: 0.001999619649723172 2023-01-23 14:28:20.449394: step: 500/1545, loss: 0.009532385505735874 2023-01-23 14:28:21.329988: step: 502/1545, loss: 0.007168970536440611 2023-01-23 14:28:22.265146: step: 504/1545, loss: 0.07947155088186264 2023-01-23 14:28:23.133083: step: 506/1545, loss: 0.0007337982533499599 2023-01-23 14:28:23.960431: step: 508/1545, loss: 0.0017149175982922316 2023-01-23 14:28:24.908602: step: 510/1545, loss: 0.005024034529924393 2023-01-23 14:28:25.833280: step: 512/1545, loss: 0.020154841244220734 2023-01-23 14:28:26.746956: step: 514/1545, loss: 0.0017715254798531532 2023-01-23 14:28:27.586911: step: 516/1545, loss: 0.0015460953582078218 2023-01-23 14:28:28.448904: step: 518/1545, loss: 0.00206561665982008 2023-01-23 14:28:29.296457: step: 520/1545, loss: 0.004173710942268372 2023-01-23 14:28:30.191294: step: 522/1545, loss: 0.3084467053413391 2023-01-23 14:28:31.084333: step: 524/1545, loss: 0.0072523015551269054 2023-01-23 14:28:31.927745: step: 526/1545, loss: 0.0017803400987759233 2023-01-23 14:28:32.846155: step: 528/1545, loss: 0.4880519211292267 2023-01-23 14:28:33.715591: step: 530/1545, loss: 0.008580324240028858 2023-01-23 14:28:34.616023: step: 532/1545, loss: 0.012679768726229668 2023-01-23 14:28:35.523691: step: 534/1545, loss: 0.2284950613975525 2023-01-23 14:28:36.418888: step: 536/1545, loss: 0.08129234611988068 2023-01-23 14:28:37.307241: step: 538/1545, loss: 0.3020452558994293 2023-01-23 14:28:38.180977: step: 540/1545, loss: 0.5769849419593811 2023-01-23 14:28:39.103372: step: 542/1545, loss: 0.0031907809898257256 2023-01-23 14:28:39.995664: step: 544/1545, loss: 0.007543026003986597 2023-01-23 14:28:40.963644: step: 546/1545, loss: 0.007704860996454954 2023-01-23 14:28:41.806567: step: 548/1545, loss: 0.014382581226527691 2023-01-23 14:28:42.691133: step: 550/1545, loss: 0.024235785007476807 2023-01-23 14:28:43.566640: step: 552/1545, loss: 0.04284084588289261 2023-01-23 14:28:44.440654: step: 554/1545, loss: 0.15505769848823547 2023-01-23 14:28:45.307306: step: 556/1545, loss: 0.10153868049383163 2023-01-23 14:28:46.228860: step: 558/1545, loss: 0.04818655550479889 2023-01-23 14:28:47.107401: step: 560/1545, loss: 0.066403329372406 2023-01-23 14:28:47.994521: step: 562/1545, loss: 0.005083476193249226 2023-01-23 14:28:48.951240: step: 564/1545, loss: 0.050006117671728134 2023-01-23 14:28:49.853270: step: 566/1545, loss: 0.24836111068725586 2023-01-23 14:28:50.714346: step: 568/1545, loss: 0.09376976639032364 2023-01-23 14:28:51.578271: step: 570/1545, loss: 0.00955099705606699 2023-01-23 14:28:52.444325: step: 572/1545, loss: 0.004544694442301989 2023-01-23 14:28:53.299516: step: 574/1545, loss: 0.03388804569840431 2023-01-23 14:28:54.299341: step: 576/1545, loss: 0.008884457871317863 2023-01-23 14:28:55.222273: step: 578/1545, loss: 0.24138911068439484 2023-01-23 14:28:56.122631: step: 580/1545, loss: 0.0003546180378179997 2023-01-23 14:28:56.951584: step: 582/1545, loss: 0.11021386086940765 2023-01-23 14:28:57.859963: step: 584/1545, loss: 0.05108264461159706 2023-01-23 14:28:58.713887: step: 586/1545, loss: 0.08785971999168396 2023-01-23 14:28:59.637008: step: 588/1545, loss: 0.14588439464569092 2023-01-23 14:29:00.533590: step: 590/1545, loss: 0.003762101521715522 2023-01-23 14:29:01.470821: step: 592/1545, loss: 0.2915596067905426 2023-01-23 14:29:02.430309: step: 594/1545, loss: 0.10588307678699493 2023-01-23 14:29:03.301562: step: 596/1545, loss: 0.02101976051926613 2023-01-23 14:29:04.200751: step: 598/1545, loss: 0.018129166215658188 2023-01-23 14:29:05.116614: step: 600/1545, loss: 0.07835288345813751 2023-01-23 14:29:05.983516: step: 602/1545, loss: 0.0018859270494431257 2023-01-23 14:29:06.843095: step: 604/1545, loss: 0.06191365420818329 2023-01-23 14:29:07.669573: step: 606/1545, loss: 0.05198979005217552 2023-01-23 14:29:08.577991: step: 608/1545, loss: 0.07633335888385773 2023-01-23 14:29:09.458451: step: 610/1545, loss: 0.09966131299734116 2023-01-23 14:29:10.313810: step: 612/1545, loss: 0.0015228040283545852 2023-01-23 14:29:11.222021: step: 614/1545, loss: 0.15160399675369263 2023-01-23 14:29:12.175856: step: 616/1545, loss: 1.82802152633667 2023-01-23 14:29:13.057273: step: 618/1545, loss: 0.9411966800689697 2023-01-23 14:29:13.981347: step: 620/1545, loss: 0.038537491112947464 2023-01-23 14:29:14.880208: step: 622/1545, loss: 1.5474636554718018 2023-01-23 14:29:15.812717: step: 624/1545, loss: 0.027280647307634354 2023-01-23 14:29:16.675773: step: 626/1545, loss: 0.015004299581050873 2023-01-23 14:29:17.585988: step: 628/1545, loss: 0.2084926813840866 2023-01-23 14:29:18.452311: step: 630/1545, loss: 0.0029063792899250984 2023-01-23 14:29:19.355508: step: 632/1545, loss: 0.0522816963493824 2023-01-23 14:29:20.229631: step: 634/1545, loss: 2.261354684829712 2023-01-23 14:29:21.129283: step: 636/1545, loss: 0.04164355248212814 2023-01-23 14:29:22.028370: step: 638/1545, loss: 0.008650003001093864 2023-01-23 14:29:22.935269: step: 640/1545, loss: 0.012254884466528893 2023-01-23 14:29:23.793465: step: 642/1545, loss: 0.0057882871478796005 2023-01-23 14:29:24.717256: step: 644/1545, loss: 0.03142143040895462 2023-01-23 14:29:25.662843: step: 646/1545, loss: 0.10138441622257233 2023-01-23 14:29:26.510597: step: 648/1545, loss: 0.12889668345451355 2023-01-23 14:29:27.403735: step: 650/1545, loss: 0.2836450934410095 2023-01-23 14:29:28.294279: step: 652/1545, loss: 0.003978140652179718 2023-01-23 14:29:29.163354: step: 654/1545, loss: 0.09665148705244064 2023-01-23 14:29:30.040320: step: 656/1545, loss: 0.41735297441482544 2023-01-23 14:29:30.924424: step: 658/1545, loss: 0.25986364483833313 2023-01-23 14:29:31.878630: step: 660/1545, loss: 0.26115792989730835 2023-01-23 14:29:32.797104: step: 662/1545, loss: 0.3303458094596863 2023-01-23 14:29:33.680015: step: 664/1545, loss: 0.3372563123703003 2023-01-23 14:29:34.708566: step: 666/1545, loss: 0.005948627833276987 2023-01-23 14:29:35.576183: step: 668/1545, loss: 0.0041406890377402306 2023-01-23 14:29:36.473973: step: 670/1545, loss: 0.1612326204776764 2023-01-23 14:29:37.319813: step: 672/1545, loss: 0.15855719149112701 2023-01-23 14:29:38.209604: step: 674/1545, loss: 1.742189884185791 2023-01-23 14:29:39.124233: step: 676/1545, loss: 0.019472267478704453 2023-01-23 14:29:39.971683: step: 678/1545, loss: 0.008002973161637783 2023-01-23 14:29:40.823700: step: 680/1545, loss: 0.03393256291747093 2023-01-23 14:29:41.736073: step: 682/1545, loss: 0.039761733263731 2023-01-23 14:29:42.587453: step: 684/1545, loss: 0.03942209854722023 2023-01-23 14:29:43.449325: step: 686/1545, loss: 0.2006009817123413 2023-01-23 14:29:44.311084: step: 688/1545, loss: 0.038707613945007324 2023-01-23 14:29:45.184117: step: 690/1545, loss: 0.02147470787167549 2023-01-23 14:29:46.079044: step: 692/1545, loss: 0.004194269422441721 2023-01-23 14:29:46.945024: step: 694/1545, loss: 0.20195679366588593 2023-01-23 14:29:47.868976: step: 696/1545, loss: 0.009307794272899628 2023-01-23 14:29:48.766160: step: 698/1545, loss: 0.1347692757844925 2023-01-23 14:29:49.706669: step: 700/1545, loss: 0.10586696863174438 2023-01-23 14:29:50.570004: step: 702/1545, loss: 0.03123459964990616 2023-01-23 14:29:51.481437: step: 704/1545, loss: 0.05966046452522278 2023-01-23 14:29:52.361914: step: 706/1545, loss: 0.0037764781154692173 2023-01-23 14:29:53.272774: step: 708/1545, loss: 0.001917517278343439 2023-01-23 14:29:54.170557: step: 710/1545, loss: 0.19786645472049713 2023-01-23 14:29:55.046582: step: 712/1545, loss: 0.009562091901898384 2023-01-23 14:29:55.926717: step: 714/1545, loss: 0.2311127930879593 2023-01-23 14:29:56.824533: step: 716/1545, loss: 0.0036371806636452675 2023-01-23 14:29:57.695882: step: 718/1545, loss: 0.006426892708986998 2023-01-23 14:29:58.631748: step: 720/1545, loss: 0.004131670575588942 2023-01-23 14:29:59.537391: step: 722/1545, loss: 0.028970645740628242 2023-01-23 14:30:00.468586: step: 724/1545, loss: 0.016825387254357338 2023-01-23 14:30:01.333788: step: 726/1545, loss: 0.07684308290481567 2023-01-23 14:30:02.182515: step: 728/1545, loss: 0.04098360985517502 2023-01-23 14:30:03.127992: step: 730/1545, loss: 0.0038433156441897154 2023-01-23 14:30:03.980341: step: 732/1545, loss: 0.07984083145856857 2023-01-23 14:30:04.898099: step: 734/1545, loss: 0.05479623004794121 2023-01-23 14:30:05.845537: step: 736/1545, loss: 0.1297653466463089 2023-01-23 14:30:06.743989: step: 738/1545, loss: 0.03508441150188446 2023-01-23 14:30:07.668753: step: 740/1545, loss: 0.017721574753522873 2023-01-23 14:30:08.560956: step: 742/1545, loss: 0.020803701132535934 2023-01-23 14:30:09.469895: step: 744/1545, loss: 0.031399160623550415 2023-01-23 14:30:10.341824: step: 746/1545, loss: 0.006444317288696766 2023-01-23 14:30:11.254961: step: 748/1545, loss: 0.0033363320399075747 2023-01-23 14:30:12.131153: step: 750/1545, loss: 0.00384526327252388 2023-01-23 14:30:13.062155: step: 752/1545, loss: 0.482185035943985 2023-01-23 14:30:13.936187: step: 754/1545, loss: 0.0037918733432888985 2023-01-23 14:30:14.802571: step: 756/1545, loss: 0.020701613277196884 2023-01-23 14:30:15.643793: step: 758/1545, loss: 0.01281085703521967 2023-01-23 14:30:16.599657: step: 760/1545, loss: 0.07751792669296265 2023-01-23 14:30:17.470362: step: 762/1545, loss: 0.0014701607869938016 2023-01-23 14:30:18.408870: step: 764/1545, loss: 0.05588816851377487 2023-01-23 14:30:19.312849: step: 766/1545, loss: 0.004771874751895666 2023-01-23 14:30:20.218207: step: 768/1545, loss: 0.061438243836164474 2023-01-23 14:30:21.182015: step: 770/1545, loss: 0.13741378486156464 2023-01-23 14:30:22.078841: step: 772/1545, loss: 0.013983742333948612 2023-01-23 14:30:22.939213: step: 774/1545, loss: 0.2184087187051773 2023-01-23 14:30:23.802908: step: 776/1545, loss: 0.04859308525919914 2023-01-23 14:30:24.692320: step: 778/1545, loss: 0.042622677981853485 2023-01-23 14:30:25.584491: step: 780/1545, loss: 0.023441307246685028 2023-01-23 14:30:26.476186: step: 782/1545, loss: 0.005848313681781292 2023-01-23 14:30:27.336452: step: 784/1545, loss: 0.060795582830905914 2023-01-23 14:30:28.195928: step: 786/1545, loss: 0.08793184906244278 2023-01-23 14:30:29.050538: step: 788/1545, loss: 0.023582464084029198 2023-01-23 14:30:29.958540: step: 790/1545, loss: 0.021804288029670715 2023-01-23 14:30:30.914026: step: 792/1545, loss: 0.11804661154747009 2023-01-23 14:30:31.841670: step: 794/1545, loss: 0.06186399981379509 2023-01-23 14:30:32.759374: step: 796/1545, loss: 0.2789483964443207 2023-01-23 14:30:33.631007: step: 798/1545, loss: 0.01321664173156023 2023-01-23 14:30:34.537518: step: 800/1545, loss: 0.00442187674343586 2023-01-23 14:30:35.426412: step: 802/1545, loss: 0.05829976871609688 2023-01-23 14:30:36.321612: step: 804/1545, loss: 0.02010944113135338 2023-01-23 14:30:37.226545: step: 806/1545, loss: 0.0006857168045826256 2023-01-23 14:30:38.079639: step: 808/1545, loss: 0.03288710489869118 2023-01-23 14:30:38.988041: step: 810/1545, loss: 0.06978777050971985 2023-01-23 14:30:39.856091: step: 812/1545, loss: 0.26220691204071045 2023-01-23 14:30:40.704473: step: 814/1545, loss: 0.008230402134358883 2023-01-23 14:30:41.578193: step: 816/1545, loss: 0.05321340262889862 2023-01-23 14:30:42.411803: step: 818/1545, loss: 0.0393209382891655 2023-01-23 14:30:43.293343: step: 820/1545, loss: 0.3216710686683655 2023-01-23 14:30:44.180532: step: 822/1545, loss: 0.00999047327786684 2023-01-23 14:30:45.024382: step: 824/1545, loss: 0.01850101351737976 2023-01-23 14:30:45.870272: step: 826/1545, loss: 0.04093610867857933 2023-01-23 14:30:46.790844: step: 828/1545, loss: 0.0671888217329979 2023-01-23 14:30:47.694949: step: 830/1545, loss: 0.0031882559414952993 2023-01-23 14:30:48.584599: step: 832/1545, loss: 0.004945310764014721 2023-01-23 14:30:49.503131: step: 834/1545, loss: 0.0006131609552539885 2023-01-23 14:30:50.455645: step: 836/1545, loss: 0.41591373085975647 2023-01-23 14:30:51.410063: step: 838/1545, loss: 0.00013137752830516547 2023-01-23 14:30:52.291616: step: 840/1545, loss: 0.00040674477349966764 2023-01-23 14:30:53.175241: step: 842/1545, loss: 0.00824824720621109 2023-01-23 14:30:54.081282: step: 844/1545, loss: 0.12690669298171997 2023-01-23 14:30:54.973536: step: 846/1545, loss: 0.13081304728984833 2023-01-23 14:30:55.845563: step: 848/1545, loss: 0.006624627858400345 2023-01-23 14:30:56.723099: step: 850/1545, loss: 0.029699744656682014 2023-01-23 14:30:57.641981: step: 852/1545, loss: 0.23334366083145142 2023-01-23 14:30:58.542858: step: 854/1545, loss: 0.0016540163196623325 2023-01-23 14:30:59.393524: step: 856/1545, loss: 0.1112690344452858 2023-01-23 14:31:00.283585: step: 858/1545, loss: 0.11242173612117767 2023-01-23 14:31:01.156060: step: 860/1545, loss: 0.00935145653784275 2023-01-23 14:31:02.033649: step: 862/1545, loss: 0.04410265013575554 2023-01-23 14:31:02.929511: step: 864/1545, loss: 0.0037891960237175226 2023-01-23 14:31:03.801809: step: 866/1545, loss: 0.1457843780517578 2023-01-23 14:31:04.682006: step: 868/1545, loss: 0.018746264278888702 2023-01-23 14:31:05.557494: step: 870/1545, loss: 0.0005409711739048362 2023-01-23 14:31:06.390258: step: 872/1545, loss: 0.1675095409154892 2023-01-23 14:31:07.233493: step: 874/1545, loss: 0.002311271382495761 2023-01-23 14:31:08.083929: step: 876/1545, loss: 0.0005161091685295105 2023-01-23 14:31:08.978413: step: 878/1545, loss: 0.0023628275375813246 2023-01-23 14:31:09.855582: step: 880/1545, loss: 0.0027686385437846184 2023-01-23 14:31:10.780013: step: 882/1545, loss: 0.019841602072119713 2023-01-23 14:31:11.685809: step: 884/1545, loss: 0.006847204174846411 2023-01-23 14:31:12.533856: step: 886/1545, loss: 0.17842687666416168 2023-01-23 14:31:13.420035: step: 888/1545, loss: 0.044622018933296204 2023-01-23 14:31:14.310907: step: 890/1545, loss: 0.0026851454749703407 2023-01-23 14:31:15.203586: step: 892/1545, loss: 0.3971409201622009 2023-01-23 14:31:16.133845: step: 894/1545, loss: 0.00023832180886529386 2023-01-23 14:31:17.083604: step: 896/1545, loss: 4.640177940018475e-05 2023-01-23 14:31:18.072224: step: 898/1545, loss: 0.041534483432769775 2023-01-23 14:31:18.982791: step: 900/1545, loss: 0.0343652069568634 2023-01-23 14:31:19.933348: step: 902/1545, loss: 0.002462551696226001 2023-01-23 14:31:20.864863: step: 904/1545, loss: 0.29151055216789246 2023-01-23 14:31:21.788333: step: 906/1545, loss: 0.03947491943836212 2023-01-23 14:31:22.661603: step: 908/1545, loss: 0.06395447254180908 2023-01-23 14:31:23.557281: step: 910/1545, loss: 0.15313278138637543 2023-01-23 14:31:24.421578: step: 912/1545, loss: 0.005714702885597944 2023-01-23 14:31:25.304188: step: 914/1545, loss: 0.13359792530536652 2023-01-23 14:31:26.190750: step: 916/1545, loss: 0.036198779940605164 2023-01-23 14:31:27.083656: step: 918/1545, loss: 0.011982208117842674 2023-01-23 14:31:27.957005: step: 920/1545, loss: 0.0564146526157856 2023-01-23 14:31:28.784635: step: 922/1545, loss: 0.0006890023360028863 2023-01-23 14:31:29.645382: step: 924/1545, loss: 0.01272701658308506 2023-01-23 14:31:30.547341: step: 926/1545, loss: 0.0007014720467850566 2023-01-23 14:31:31.410402: step: 928/1545, loss: 0.004139509983360767 2023-01-23 14:31:32.295278: step: 930/1545, loss: 0.015043924562633038 2023-01-23 14:31:33.139236: step: 932/1545, loss: 0.08216861635446548 2023-01-23 14:31:34.039139: step: 934/1545, loss: 0.14049260318279266 2023-01-23 14:31:34.955651: step: 936/1545, loss: 0.05668500438332558 2023-01-23 14:31:35.862249: step: 938/1545, loss: 0.029779570177197456 2023-01-23 14:31:36.738358: step: 940/1545, loss: 0.04021336883306503 2023-01-23 14:31:37.654371: step: 942/1545, loss: 0.11745961755514145 2023-01-23 14:31:38.553732: step: 944/1545, loss: 0.12577608227729797 2023-01-23 14:31:39.417395: step: 946/1545, loss: 0.03969469666481018 2023-01-23 14:31:40.312347: step: 948/1545, loss: 0.00018994006677530706 2023-01-23 14:31:41.219028: step: 950/1545, loss: 0.028568003326654434 2023-01-23 14:31:42.130696: step: 952/1545, loss: 0.0013303171144798398 2023-01-23 14:31:43.020934: step: 954/1545, loss: 0.283538818359375 2023-01-23 14:31:43.892797: step: 956/1545, loss: 0.016564063727855682 2023-01-23 14:31:44.797095: step: 958/1545, loss: 0.007773380260914564 2023-01-23 14:31:45.893977: step: 960/1545, loss: 0.14844344556331635 2023-01-23 14:31:46.765170: step: 962/1545, loss: 0.0026810872368514538 2023-01-23 14:31:47.690180: step: 964/1545, loss: 0.21628107130527496 2023-01-23 14:31:48.567282: step: 966/1545, loss: 0.10292962938547134 2023-01-23 14:31:49.435094: step: 968/1545, loss: 0.0027434369549155235 2023-01-23 14:31:50.288316: step: 970/1545, loss: 0.12402698397636414 2023-01-23 14:31:51.155473: step: 972/1545, loss: 0.03328837454319 2023-01-23 14:31:52.014968: step: 974/1545, loss: 0.00664703780785203 2023-01-23 14:31:52.892546: step: 976/1545, loss: 0.199750155210495 2023-01-23 14:31:53.766480: step: 978/1545, loss: 0.3216165602207184 2023-01-23 14:31:54.676131: step: 980/1545, loss: 0.679512083530426 2023-01-23 14:31:55.561199: step: 982/1545, loss: 0.051601655781269073 2023-01-23 14:31:56.501956: step: 984/1545, loss: 0.12443225085735321 2023-01-23 14:31:57.395921: step: 986/1545, loss: 0.002581255743280053 2023-01-23 14:31:58.226186: step: 988/1545, loss: 0.003715338185429573 2023-01-23 14:31:59.159023: step: 990/1545, loss: 0.003991447389125824 2023-01-23 14:32:00.037502: step: 992/1545, loss: 0.10274101793766022 2023-01-23 14:32:01.019544: step: 994/1545, loss: 0.7650678753852844 2023-01-23 14:32:01.893800: step: 996/1545, loss: 0.07018420100212097 2023-01-23 14:32:02.793160: step: 998/1545, loss: 0.002279632491990924 2023-01-23 14:32:03.667538: step: 1000/1545, loss: 0.00045671017142012715 2023-01-23 14:32:04.541670: step: 1002/1545, loss: 0.3442630171775818 2023-01-23 14:32:05.430735: step: 1004/1545, loss: 0.022820191457867622 2023-01-23 14:32:06.403888: step: 1006/1545, loss: 0.00062422058545053 2023-01-23 14:32:07.312247: step: 1008/1545, loss: 0.01517594326287508 2023-01-23 14:32:08.247629: step: 1010/1545, loss: 0.3661755323410034 2023-01-23 14:32:09.075076: step: 1012/1545, loss: 0.11371767520904541 2023-01-23 14:32:09.937010: step: 1014/1545, loss: 0.27175047993659973 2023-01-23 14:32:10.827778: step: 1016/1545, loss: 0.07752919942140579 2023-01-23 14:32:11.692855: step: 1018/1545, loss: 0.0037181302905082703 2023-01-23 14:32:12.636062: step: 1020/1545, loss: 0.10836037993431091 2023-01-23 14:32:13.487753: step: 1022/1545, loss: 0.005877142772078514 2023-01-23 14:32:14.327388: step: 1024/1545, loss: 0.011698976159095764 2023-01-23 14:32:15.228964: step: 1026/1545, loss: 0.05570110306143761 2023-01-23 14:32:16.108209: step: 1028/1545, loss: 0.009707250632345676 2023-01-23 14:32:16.991882: step: 1030/1545, loss: 0.025640815496444702 2023-01-23 14:32:17.856796: step: 1032/1545, loss: 0.36263489723205566 2023-01-23 14:32:18.749106: step: 1034/1545, loss: 0.015724413096904755 2023-01-23 14:32:19.612484: step: 1036/1545, loss: 0.007336239330470562 2023-01-23 14:32:20.476514: step: 1038/1545, loss: 0.008369161747395992 2023-01-23 14:32:21.429829: step: 1040/1545, loss: 0.13686344027519226 2023-01-23 14:32:22.337849: step: 1042/1545, loss: 0.012133341282606125 2023-01-23 14:32:23.207830: step: 1044/1545, loss: 0.024394385516643524 2023-01-23 14:32:24.100728: step: 1046/1545, loss: 0.015354696661233902 2023-01-23 14:32:24.961513: step: 1048/1545, loss: 0.004556217696517706 2023-01-23 14:32:25.866528: step: 1050/1545, loss: 0.44162094593048096 2023-01-23 14:32:26.772492: step: 1052/1545, loss: 0.06757405400276184 2023-01-23 14:32:27.659245: step: 1054/1545, loss: 0.07173778861761093 2023-01-23 14:32:28.536093: step: 1056/1545, loss: 0.0015521289315074682 2023-01-23 14:32:29.542993: step: 1058/1545, loss: 0.0029427579138427973 2023-01-23 14:32:30.399378: step: 1060/1545, loss: 0.016496622934937477 2023-01-23 14:32:31.274517: step: 1062/1545, loss: 0.3180699348449707 2023-01-23 14:32:32.226999: step: 1064/1545, loss: 0.30549290776252747 2023-01-23 14:32:33.170546: step: 1066/1545, loss: 0.03276963159441948 2023-01-23 14:32:34.053710: step: 1068/1545, loss: 0.0506424605846405 2023-01-23 14:32:34.955845: step: 1070/1545, loss: 0.04738561809062958 2023-01-23 14:32:35.877164: step: 1072/1545, loss: 0.0681256428360939 2023-01-23 14:32:36.755966: step: 1074/1545, loss: 0.005488470196723938 2023-01-23 14:32:37.649718: step: 1076/1545, loss: 0.21657995879650116 2023-01-23 14:32:38.514029: step: 1078/1545, loss: 0.021915270015597343 2023-01-23 14:32:39.466818: step: 1080/1545, loss: 0.00858873501420021 2023-01-23 14:32:40.373856: step: 1082/1545, loss: 2.5183229446411133 2023-01-23 14:32:41.261641: step: 1084/1545, loss: 0.0009013903327286243 2023-01-23 14:32:42.158099: step: 1086/1545, loss: 0.27846285700798035 2023-01-23 14:32:43.039840: step: 1088/1545, loss: 0.06033831462264061 2023-01-23 14:32:43.935934: step: 1090/1545, loss: 0.0006637892220169306 2023-01-23 14:32:44.920899: step: 1092/1545, loss: 0.009861242026090622 2023-01-23 14:32:45.798604: step: 1094/1545, loss: 0.0803610235452652 2023-01-23 14:32:46.722711: step: 1096/1545, loss: 0.04579642787575722 2023-01-23 14:32:47.623647: step: 1098/1545, loss: 0.02166016586124897 2023-01-23 14:32:48.483574: step: 1100/1545, loss: 0.027164671570062637 2023-01-23 14:32:49.409834: step: 1102/1545, loss: 0.01300373300909996 2023-01-23 14:32:50.285369: step: 1104/1545, loss: 0.06521275639533997 2023-01-23 14:32:51.154909: step: 1106/1545, loss: 0.18142510950565338 2023-01-23 14:32:52.053954: step: 1108/1545, loss: 0.19080933928489685 2023-01-23 14:32:52.898624: step: 1110/1545, loss: 0.005208679474890232 2023-01-23 14:32:53.773008: step: 1112/1545, loss: 0.0015941776800900698 2023-01-23 14:32:54.664870: step: 1114/1545, loss: 0.03467920422554016 2023-01-23 14:32:55.546537: step: 1116/1545, loss: 0.004451475106179714 2023-01-23 14:32:56.464438: step: 1118/1545, loss: 0.0019001993350684643 2023-01-23 14:32:57.424237: step: 1120/1545, loss: 0.14420652389526367 2023-01-23 14:32:58.256667: step: 1122/1545, loss: 0.0018996179569512606 2023-01-23 14:32:59.136781: step: 1124/1545, loss: 0.13926967978477478 2023-01-23 14:32:59.984249: step: 1126/1545, loss: 0.20603469014167786 2023-01-23 14:33:00.838750: step: 1128/1545, loss: 0.0008584875613451004 2023-01-23 14:33:01.756316: step: 1130/1545, loss: 0.04848809540271759 2023-01-23 14:33:02.632895: step: 1132/1545, loss: 0.02401234395802021 2023-01-23 14:33:03.523604: step: 1134/1545, loss: 0.039370544254779816 2023-01-23 14:33:04.377422: step: 1136/1545, loss: 0.00038700414006598294 2023-01-23 14:33:05.259574: step: 1138/1545, loss: 0.07238511741161346 2023-01-23 14:33:06.118768: step: 1140/1545, loss: 0.13433997333049774 2023-01-23 14:33:07.020068: step: 1142/1545, loss: 0.06922371685504913 2023-01-23 14:33:07.887330: step: 1144/1545, loss: 0.09952676296234131 2023-01-23 14:33:08.786371: step: 1146/1545, loss: 0.001945912721566856 2023-01-23 14:33:09.675232: step: 1148/1545, loss: 0.018396545201539993 2023-01-23 14:33:10.580276: step: 1150/1545, loss: 0.11990980058908463 2023-01-23 14:33:11.479401: step: 1152/1545, loss: 0.19434033334255219 2023-01-23 14:33:12.323407: step: 1154/1545, loss: 0.01252228207886219 2023-01-23 14:33:13.180070: step: 1156/1545, loss: 0.0014643211616203189 2023-01-23 14:33:14.059142: step: 1158/1545, loss: 0.16839122772216797 2023-01-23 14:33:14.921803: step: 1160/1545, loss: 0.0010781955206766725 2023-01-23 14:33:15.817308: step: 1162/1545, loss: 0.021152250468730927 2023-01-23 14:33:16.737081: step: 1164/1545, loss: 0.09465230256319046 2023-01-23 14:33:17.606955: step: 1166/1545, loss: 0.027683094143867493 2023-01-23 14:33:18.470467: step: 1168/1545, loss: 0.020159434527158737 2023-01-23 14:33:19.334451: step: 1170/1545, loss: 0.18535733222961426 2023-01-23 14:33:20.168881: step: 1172/1545, loss: 0.005749559961259365 2023-01-23 14:33:21.010867: step: 1174/1545, loss: 0.006557737477123737 2023-01-23 14:33:21.871566: step: 1176/1545, loss: 0.21362020075321198 2023-01-23 14:33:22.790209: step: 1178/1545, loss: 0.36201414465904236 2023-01-23 14:33:23.627013: step: 1180/1545, loss: 0.005049820989370346 2023-01-23 14:33:24.547098: step: 1182/1545, loss: 0.025151126086711884 2023-01-23 14:33:25.460823: step: 1184/1545, loss: 0.010870187543332577 2023-01-23 14:33:26.320376: step: 1186/1545, loss: 0.004105130676180124 2023-01-23 14:33:27.217520: step: 1188/1545, loss: 0.7019758820533752 2023-01-23 14:33:28.063209: step: 1190/1545, loss: 0.06625717878341675 2023-01-23 14:33:28.929419: step: 1192/1545, loss: 0.01717158779501915 2023-01-23 14:33:29.794018: step: 1194/1545, loss: 0.09617452323436737 2023-01-23 14:33:30.669741: step: 1196/1545, loss: 0.025234434753656387 2023-01-23 14:33:31.554782: step: 1198/1545, loss: 0.015288382768630981 2023-01-23 14:33:32.460150: step: 1200/1545, loss: 0.004498648457229137 2023-01-23 14:33:33.388339: step: 1202/1545, loss: 0.17691291868686676 2023-01-23 14:33:34.261084: step: 1204/1545, loss: 0.27903255820274353 2023-01-23 14:33:35.102517: step: 1206/1545, loss: 0.337468683719635 2023-01-23 14:33:35.970072: step: 1208/1545, loss: 0.22321996092796326 2023-01-23 14:33:36.827702: step: 1210/1545, loss: 0.0017532599158585072 2023-01-23 14:33:37.679531: step: 1212/1545, loss: 0.0023852381855249405 2023-01-23 14:33:38.573789: step: 1214/1545, loss: 0.0017868061549961567 2023-01-23 14:33:39.555565: step: 1216/1545, loss: 0.053620558232069016 2023-01-23 14:33:40.440611: step: 1218/1545, loss: 0.00477111479267478 2023-01-23 14:33:41.325379: step: 1220/1545, loss: 0.24425354599952698 2023-01-23 14:33:42.189192: step: 1222/1545, loss: 0.04100006818771362 2023-01-23 14:33:43.024240: step: 1224/1545, loss: 0.05038176476955414 2023-01-23 14:33:43.885498: step: 1226/1545, loss: 0.04411587491631508 2023-01-23 14:33:44.780051: step: 1228/1545, loss: 0.24390389025211334 2023-01-23 14:33:45.687423: step: 1230/1545, loss: 0.3629838824272156 2023-01-23 14:33:46.601776: step: 1232/1545, loss: 0.3331289291381836 2023-01-23 14:33:47.441480: step: 1234/1545, loss: 0.001239665667526424 2023-01-23 14:33:48.271397: step: 1236/1545, loss: 0.03335448354482651 2023-01-23 14:33:49.135136: step: 1238/1545, loss: 0.04904297739267349 2023-01-23 14:33:49.990258: step: 1240/1545, loss: 0.037170108407735825 2023-01-23 14:33:50.901928: step: 1242/1545, loss: 0.05007687583565712 2023-01-23 14:33:51.756238: step: 1244/1545, loss: 0.09718621522188187 2023-01-23 14:33:52.695439: step: 1246/1545, loss: 0.4015806019306183 2023-01-23 14:33:53.597749: step: 1248/1545, loss: 0.04347249120473862 2023-01-23 14:33:54.519906: step: 1250/1545, loss: 0.44906067848205566 2023-01-23 14:33:55.416806: step: 1252/1545, loss: 0.017824307084083557 2023-01-23 14:33:56.318859: step: 1254/1545, loss: 0.1229628175497055 2023-01-23 14:33:57.201272: step: 1256/1545, loss: 0.08503057062625885 2023-01-23 14:33:58.054364: step: 1258/1545, loss: 0.04326265677809715 2023-01-23 14:33:58.920769: step: 1260/1545, loss: 0.48020854592323303 2023-01-23 14:33:59.807171: step: 1262/1545, loss: 0.04398326575756073 2023-01-23 14:34:00.671750: step: 1264/1545, loss: 0.21901211142539978 2023-01-23 14:34:01.548733: step: 1266/1545, loss: 0.0032168771140277386 2023-01-23 14:34:02.396671: step: 1268/1545, loss: 0.007017452269792557 2023-01-23 14:34:03.276675: step: 1270/1545, loss: 0.003609888721257448 2023-01-23 14:34:04.145766: step: 1272/1545, loss: 0.005816706456243992 2023-01-23 14:34:04.987985: step: 1274/1545, loss: 0.07325118780136108 2023-01-23 14:34:05.849917: step: 1276/1545, loss: 0.0053668394684791565 2023-01-23 14:34:06.726486: step: 1278/1545, loss: 0.33291739225387573 2023-01-23 14:34:07.577966: step: 1280/1545, loss: 0.014771753922104836 2023-01-23 14:34:08.496822: step: 1282/1545, loss: 0.020126016810536385 2023-01-23 14:34:09.366470: step: 1284/1545, loss: 0.006985337473452091 2023-01-23 14:34:10.217820: step: 1286/1545, loss: 0.022883320227265358 2023-01-23 14:34:11.077307: step: 1288/1545, loss: 0.040777020156383514 2023-01-23 14:34:11.938703: step: 1290/1545, loss: 0.0007893636357039213 2023-01-23 14:34:12.772020: step: 1292/1545, loss: 0.011678501963615417 2023-01-23 14:34:13.640410: step: 1294/1545, loss: 0.1200750321149826 2023-01-23 14:34:14.566334: step: 1296/1545, loss: 0.6738390922546387 2023-01-23 14:34:15.454673: step: 1298/1545, loss: 0.035892464220523834 2023-01-23 14:34:16.313416: step: 1300/1545, loss: 0.13886766135692596 2023-01-23 14:34:17.217463: step: 1302/1545, loss: 0.14471879601478577 2023-01-23 14:34:18.109781: step: 1304/1545, loss: 0.09482152760028839 2023-01-23 14:34:18.985886: step: 1306/1545, loss: 0.022283846512436867 2023-01-23 14:34:19.836509: step: 1308/1545, loss: 0.022443439811468124 2023-01-23 14:34:20.703021: step: 1310/1545, loss: 0.05926094576716423 2023-01-23 14:34:21.551187: step: 1312/1545, loss: 0.14394190907478333 2023-01-23 14:34:22.420720: step: 1314/1545, loss: 0.0003102557675447315 2023-01-23 14:34:23.235503: step: 1316/1545, loss: 0.20881661772727966 2023-01-23 14:34:24.155047: step: 1318/1545, loss: 0.05865029990673065 2023-01-23 14:34:25.045121: step: 1320/1545, loss: 0.595710039138794 2023-01-23 14:34:25.966157: step: 1322/1545, loss: 0.01926366612315178 2023-01-23 14:34:26.809577: step: 1324/1545, loss: 0.00023852131562307477 2023-01-23 14:34:27.696846: step: 1326/1545, loss: 0.039139799773693085 2023-01-23 14:34:28.559587: step: 1328/1545, loss: 0.00151063222438097 2023-01-23 14:34:29.465568: step: 1330/1545, loss: 8.601216541137546e-05 2023-01-23 14:34:30.325844: step: 1332/1545, loss: 0.008714573457837105 2023-01-23 14:34:31.177548: step: 1334/1545, loss: 0.01835688017308712 2023-01-23 14:34:32.067323: step: 1336/1545, loss: 0.017789999023079872 2023-01-23 14:34:32.917420: step: 1338/1545, loss: 0.0012453380040824413 2023-01-23 14:34:33.796726: step: 1340/1545, loss: 0.008320506662130356 2023-01-23 14:34:34.670671: step: 1342/1545, loss: 0.01152658462524414 2023-01-23 14:34:35.607348: step: 1344/1545, loss: 0.0024674951564520597 2023-01-23 14:34:36.523796: step: 1346/1545, loss: 0.07505832612514496 2023-01-23 14:34:37.417022: step: 1348/1545, loss: 0.006812294479459524 2023-01-23 14:34:38.300107: step: 1350/1545, loss: 0.08674026280641556 2023-01-23 14:34:39.176113: step: 1352/1545, loss: 0.002429334679618478 2023-01-23 14:34:40.108470: step: 1354/1545, loss: 0.5385693907737732 2023-01-23 14:34:40.964292: step: 1356/1545, loss: 0.0004352618707343936 2023-01-23 14:34:41.848131: step: 1358/1545, loss: 0.09683266282081604 2023-01-23 14:34:42.741129: step: 1360/1545, loss: 0.0017565558664500713 2023-01-23 14:34:43.663687: step: 1362/1545, loss: 0.02816695161163807 2023-01-23 14:34:44.519510: step: 1364/1545, loss: 0.0008813904132694006 2023-01-23 14:34:45.373940: step: 1366/1545, loss: 7.158903463277966e-05 2023-01-23 14:34:46.292184: step: 1368/1545, loss: 0.03382605314254761 2023-01-23 14:34:47.160440: step: 1370/1545, loss: 0.07290773838758469 2023-01-23 14:34:48.052804: step: 1372/1545, loss: 0.39222002029418945 2023-01-23 14:34:48.948617: step: 1374/1545, loss: 0.4867189824581146 2023-01-23 14:34:49.814751: step: 1376/1545, loss: 0.059649508446455 2023-01-23 14:34:50.658311: step: 1378/1545, loss: 0.032448090612888336 2023-01-23 14:34:51.522583: step: 1380/1545, loss: 0.006901105400174856 2023-01-23 14:34:52.338134: step: 1382/1545, loss: 0.12457416206598282 2023-01-23 14:34:53.184323: step: 1384/1545, loss: 0.0007243127329275012 2023-01-23 14:34:54.045896: step: 1386/1545, loss: 0.005817721132189035 2023-01-23 14:34:54.924770: step: 1388/1545, loss: 0.16108496487140656 2023-01-23 14:34:55.790504: step: 1390/1545, loss: 0.005117938853800297 2023-01-23 14:34:56.672905: step: 1392/1545, loss: 0.011408473365008831 2023-01-23 14:34:57.575793: step: 1394/1545, loss: 0.002422983292490244 2023-01-23 14:34:58.450120: step: 1396/1545, loss: 0.007803681772202253 2023-01-23 14:34:59.310141: step: 1398/1545, loss: 0.12098663300275803 2023-01-23 14:35:00.187000: step: 1400/1545, loss: 0.20253781974315643 2023-01-23 14:35:01.020443: step: 1402/1545, loss: 0.1767445206642151 2023-01-23 14:35:01.869640: step: 1404/1545, loss: 0.00025162758538499475 2023-01-23 14:35:02.795409: step: 1406/1545, loss: 0.06452687829732895 2023-01-23 14:35:03.708167: step: 1408/1545, loss: 0.08799946308135986 2023-01-23 14:35:04.596857: step: 1410/1545, loss: 0.05608677864074707 2023-01-23 14:35:05.479507: step: 1412/1545, loss: 0.3194849193096161 2023-01-23 14:35:06.354988: step: 1414/1545, loss: 0.14237459003925323 2023-01-23 14:35:07.174511: step: 1416/1545, loss: 0.030741991475224495 2023-01-23 14:35:08.055390: step: 1418/1545, loss: 0.03811720758676529 2023-01-23 14:35:08.909591: step: 1420/1545, loss: 0.010573305189609528 2023-01-23 14:35:09.781895: step: 1422/1545, loss: 0.01645219698548317 2023-01-23 14:35:10.653396: step: 1424/1545, loss: 0.03387812152504921 2023-01-23 14:35:11.524346: step: 1426/1545, loss: 0.0192861407995224 2023-01-23 14:35:12.414421: step: 1428/1545, loss: 0.0022008251398801804 2023-01-23 14:35:13.293654: step: 1430/1545, loss: 0.01763310097157955 2023-01-23 14:35:14.134478: step: 1432/1545, loss: 0.02183130383491516 2023-01-23 14:35:14.984035: step: 1434/1545, loss: 0.0026962824631482363 2023-01-23 14:35:15.816124: step: 1436/1545, loss: 0.18553505837917328 2023-01-23 14:35:16.701533: step: 1438/1545, loss: 0.36270320415496826 2023-01-23 14:35:17.556108: step: 1440/1545, loss: 0.03793584555387497 2023-01-23 14:35:18.408353: step: 1442/1545, loss: 0.003269025357440114 2023-01-23 14:35:19.306923: step: 1444/1545, loss: 0.04921673610806465 2023-01-23 14:35:20.182140: step: 1446/1545, loss: 0.23555172979831696 2023-01-23 14:35:21.084935: step: 1448/1545, loss: 0.006516578607261181 2023-01-23 14:35:21.949507: step: 1450/1545, loss: 0.010707532986998558 2023-01-23 14:35:22.823859: step: 1452/1545, loss: 0.005462975241243839 2023-01-23 14:35:23.684400: step: 1454/1545, loss: 0.008311523124575615 2023-01-23 14:35:24.569512: step: 1456/1545, loss: 0.043190669268369675 2023-01-23 14:35:25.496909: step: 1458/1545, loss: 0.01076272688806057 2023-01-23 14:35:26.429418: step: 1460/1545, loss: 0.07051829248666763 2023-01-23 14:35:27.276806: step: 1462/1545, loss: 0.000985447084531188 2023-01-23 14:35:28.258055: step: 1464/1545, loss: 0.07475040853023529 2023-01-23 14:35:29.116843: step: 1466/1545, loss: 0.17175666987895966 2023-01-23 14:35:29.994308: step: 1468/1545, loss: 0.00563395768404007 2023-01-23 14:35:30.844095: step: 1470/1545, loss: 0.09232956171035767 2023-01-23 14:35:31.700431: step: 1472/1545, loss: 0.036307442933321 2023-01-23 14:35:32.556320: step: 1474/1545, loss: 0.006429297383874655 2023-01-23 14:35:33.428122: step: 1476/1545, loss: 0.2289379984140396 2023-01-23 14:35:34.313208: step: 1478/1545, loss: 0.03917597606778145 2023-01-23 14:35:35.144422: step: 1480/1545, loss: 0.057326704263687134 2023-01-23 14:35:36.014797: step: 1482/1545, loss: 0.0002631699026096612 2023-01-23 14:35:36.893347: step: 1484/1545, loss: 0.14801958203315735 2023-01-23 14:35:37.757814: step: 1486/1545, loss: 0.05479473993182182 2023-01-23 14:35:38.645058: step: 1488/1545, loss: 0.16278010606765747 2023-01-23 14:35:39.507279: step: 1490/1545, loss: 0.1599009782075882 2023-01-23 14:35:40.376781: step: 1492/1545, loss: 0.012461931444704533 2023-01-23 14:35:41.260210: step: 1494/1545, loss: 0.18039891123771667 2023-01-23 14:35:42.127970: step: 1496/1545, loss: 0.1208978146314621 2023-01-23 14:35:43.001362: step: 1498/1545, loss: 0.01667647436261177 2023-01-23 14:35:43.882426: step: 1500/1545, loss: 0.0012793715577572584 2023-01-23 14:35:44.753843: step: 1502/1545, loss: 0.001130986725911498 2023-01-23 14:35:45.713602: step: 1504/1545, loss: 0.0010031471028923988 2023-01-23 14:35:46.600739: step: 1506/1545, loss: 0.23419815301895142 2023-01-23 14:35:47.519523: step: 1508/1545, loss: 0.012679285369813442 2023-01-23 14:35:48.392153: step: 1510/1545, loss: 0.4833226799964905 2023-01-23 14:35:49.342777: step: 1512/1545, loss: 0.023329846560955048 2023-01-23 14:35:50.238210: step: 1514/1545, loss: 0.6614150404930115 2023-01-23 14:35:51.135993: step: 1516/1545, loss: 0.02483072504401207 2023-01-23 14:35:52.016985: step: 1518/1545, loss: 0.4276503324508667 2023-01-23 14:35:52.866674: step: 1520/1545, loss: 0.012820354662835598 2023-01-23 14:35:53.722752: step: 1522/1545, loss: 0.023765377700328827 2023-01-23 14:35:54.632330: step: 1524/1545, loss: 0.06650156527757645 2023-01-23 14:35:55.520791: step: 1526/1545, loss: 0.04080641269683838 2023-01-23 14:35:56.474792: step: 1528/1545, loss: 0.366651713848114 2023-01-23 14:35:57.358876: step: 1530/1545, loss: 0.02583664283156395 2023-01-23 14:35:58.209636: step: 1532/1545, loss: 0.002426963299512863 2023-01-23 14:35:59.117469: step: 1534/1545, loss: 0.31479254364967346 2023-01-23 14:36:00.031116: step: 1536/1545, loss: 0.004725469276309013 2023-01-23 14:36:00.897068: step: 1538/1545, loss: 0.00017842790111899376 2023-01-23 14:36:01.794793: step: 1540/1545, loss: 0.194468155503273 2023-01-23 14:36:02.659647: step: 1542/1545, loss: 0.23667731881141663 2023-01-23 14:36:03.537775: step: 1544/1545, loss: 0.0030125733464956284 2023-01-23 14:36:04.484102: step: 1546/1545, loss: 0.0180843323469162 2023-01-23 14:36:05.465180: step: 1548/1545, loss: 0.005465859081596136 2023-01-23 14:36:06.352995: step: 1550/1545, loss: 0.0018419342814013362 2023-01-23 14:36:07.204412: step: 1552/1545, loss: 0.0009836031822487712 2023-01-23 14:36:08.088898: step: 1554/1545, loss: 1.2922556400299072 2023-01-23 14:36:08.950953: step: 1556/1545, loss: 0.0038203902076929808 2023-01-23 14:36:09.863772: step: 1558/1545, loss: 0.1787680834531784 2023-01-23 14:36:10.755107: step: 1560/1545, loss: 0.02385079860687256 2023-01-23 14:36:11.660628: step: 1562/1545, loss: 0.06419522315263748 2023-01-23 14:36:12.538065: step: 1564/1545, loss: 0.09802348911762238 2023-01-23 14:36:13.428935: step: 1566/1545, loss: 0.01923554018139839 2023-01-23 14:36:14.343745: step: 1568/1545, loss: 0.5888134241104126 2023-01-23 14:36:15.212813: step: 1570/1545, loss: 0.009289399720728397 2023-01-23 14:36:16.073043: step: 1572/1545, loss: 0.02187742479145527 2023-01-23 14:36:17.021091: step: 1574/1545, loss: 0.006617304868996143 2023-01-23 14:36:17.925830: step: 1576/1545, loss: 0.0005125587922520936 2023-01-23 14:36:18.847987: step: 1578/1545, loss: 0.011529725044965744 2023-01-23 14:36:19.739807: step: 1580/1545, loss: 0.06636247783899307 2023-01-23 14:36:20.661034: step: 1582/1545, loss: 0.0401754267513752 2023-01-23 14:36:21.571285: step: 1584/1545, loss: 0.0004478502960409969 2023-01-23 14:36:22.482405: step: 1586/1545, loss: 0.03512187674641609 2023-01-23 14:36:23.376073: step: 1588/1545, loss: 0.0026664629112929106 2023-01-23 14:36:24.248987: step: 1590/1545, loss: 0.09105274081230164 2023-01-23 14:36:25.108610: step: 1592/1545, loss: 0.0002008775481954217 2023-01-23 14:36:25.991686: step: 1594/1545, loss: 0.0025435551069676876 2023-01-23 14:36:26.885443: step: 1596/1545, loss: 0.0009903986938297749 2023-01-23 14:36:27.773305: step: 1598/1545, loss: 0.02296285517513752 2023-01-23 14:36:28.638979: step: 1600/1545, loss: 0.0004804641648661345 2023-01-23 14:36:29.538428: step: 1602/1545, loss: 0.0029460142832249403 2023-01-23 14:36:30.433712: step: 1604/1545, loss: 0.007297155447304249 2023-01-23 14:36:31.290060: step: 1606/1545, loss: 0.0035660178400576115 2023-01-23 14:36:32.180734: step: 1608/1545, loss: 0.33752039074897766 2023-01-23 14:36:33.021214: step: 1610/1545, loss: 0.011886312626302242 2023-01-23 14:36:33.893581: step: 1612/1545, loss: 0.0034657567739486694 2023-01-23 14:36:34.764472: step: 1614/1545, loss: 0.000978429103270173 2023-01-23 14:36:35.647118: step: 1616/1545, loss: 0.30364421010017395 2023-01-23 14:36:36.568619: step: 1618/1545, loss: 0.011606601998209953 2023-01-23 14:36:37.525530: step: 1620/1545, loss: 1.795006513595581 2023-01-23 14:36:38.395783: step: 1622/1545, loss: 0.009222038090229034 2023-01-23 14:36:39.292174: step: 1624/1545, loss: 0.09301450103521347 2023-01-23 14:36:40.170644: step: 1626/1545, loss: 0.4960741102695465 2023-01-23 14:36:41.052447: step: 1628/1545, loss: 0.014891767874360085 2023-01-23 14:36:41.931332: step: 1630/1545, loss: 0.17877721786499023 2023-01-23 14:36:42.774722: step: 1632/1545, loss: 0.05576667934656143 2023-01-23 14:36:43.675833: step: 1634/1545, loss: 0.0031045523937791586 2023-01-23 14:36:44.565763: step: 1636/1545, loss: 0.0005947432364337146 2023-01-23 14:36:45.442242: step: 1638/1545, loss: 0.0002128644846379757 2023-01-23 14:36:46.338442: step: 1640/1545, loss: 0.011975417844951153 2023-01-23 14:36:47.261727: step: 1642/1545, loss: 0.05704966187477112 2023-01-23 14:36:48.148785: step: 1644/1545, loss: 0.40192264318466187 2023-01-23 14:36:49.042883: step: 1646/1545, loss: 0.013291711919009686 2023-01-23 14:36:49.962453: step: 1648/1545, loss: 0.024074671790003777 2023-01-23 14:36:50.857490: step: 1650/1545, loss: 0.0027421850245445967 2023-01-23 14:36:51.754181: step: 1652/1545, loss: 0.05627761036157608 2023-01-23 14:36:52.687536: step: 1654/1545, loss: 0.017182622104883194 2023-01-23 14:36:53.554307: step: 1656/1545, loss: 0.16254138946533203 2023-01-23 14:36:54.492054: step: 1658/1545, loss: 0.008736347779631615 2023-01-23 14:36:55.388800: step: 1660/1545, loss: 0.7542219161987305 2023-01-23 14:36:56.256620: step: 1662/1545, loss: 0.014388053677976131 2023-01-23 14:36:57.151175: step: 1664/1545, loss: 0.15003889799118042 2023-01-23 14:36:58.020395: step: 1666/1545, loss: 0.12050507962703705 2023-01-23 14:36:58.969802: step: 1668/1545, loss: 0.015257611870765686 2023-01-23 14:36:59.896580: step: 1670/1545, loss: 0.04414099082350731 2023-01-23 14:37:00.755894: step: 1672/1545, loss: 0.3386557102203369 2023-01-23 14:37:01.647050: step: 1674/1545, loss: 0.10447637736797333 2023-01-23 14:37:02.529527: step: 1676/1545, loss: 0.13785520195960999 2023-01-23 14:37:03.403653: step: 1678/1545, loss: 0.0667409673333168 2023-01-23 14:37:04.312586: step: 1680/1545, loss: 0.019926801323890686 2023-01-23 14:37:05.205646: step: 1682/1545, loss: 0.010338676162064075 2023-01-23 14:37:06.075835: step: 1684/1545, loss: 0.00018339364032726735 2023-01-23 14:37:06.932145: step: 1686/1545, loss: 0.020548803731799126 2023-01-23 14:37:07.777859: step: 1688/1545, loss: 0.0007571034948341548 2023-01-23 14:37:08.642687: step: 1690/1545, loss: 0.04147081449627876 2023-01-23 14:37:09.549830: step: 1692/1545, loss: 0.5138582587242126 2023-01-23 14:37:10.433855: step: 1694/1545, loss: 0.021216562017798424 2023-01-23 14:37:11.284662: step: 1696/1545, loss: 0.0009719140361994505 2023-01-23 14:37:12.184134: step: 1698/1545, loss: 0.06871461123228073 2023-01-23 14:37:13.039222: step: 1700/1545, loss: 0.07003827393054962 2023-01-23 14:37:13.943469: step: 1702/1545, loss: 0.1087183877825737 2023-01-23 14:37:14.877469: step: 1704/1545, loss: 0.007643198594450951 2023-01-23 14:37:15.765781: step: 1706/1545, loss: 0.009181997738778591 2023-01-23 14:37:16.668236: step: 1708/1545, loss: 0.04828427731990814 2023-01-23 14:37:17.565193: step: 1710/1545, loss: 0.11435995250940323 2023-01-23 14:37:18.415660: step: 1712/1545, loss: 0.013776971958577633 2023-01-23 14:37:19.382062: step: 1714/1545, loss: 0.00676083704456687 2023-01-23 14:37:20.279588: step: 1716/1545, loss: 0.019291361793875694 2023-01-23 14:37:21.159925: step: 1718/1545, loss: 0.03522969037294388 2023-01-23 14:37:22.019309: step: 1720/1545, loss: 0.060262467712163925 2023-01-23 14:37:22.891435: step: 1722/1545, loss: 0.06833912432193756 2023-01-23 14:37:23.787126: step: 1724/1545, loss: 0.0036982649471610785 2023-01-23 14:37:24.701182: step: 1726/1545, loss: 0.0480414517223835 2023-01-23 14:37:25.568150: step: 1728/1545, loss: 0.0076974197290837765 2023-01-23 14:37:26.460398: step: 1730/1545, loss: 0.004656976088881493 2023-01-23 14:37:27.413007: step: 1732/1545, loss: 0.02929205447435379 2023-01-23 14:37:28.277465: step: 1734/1545, loss: 0.027867907658219337 2023-01-23 14:37:29.170214: step: 1736/1545, loss: 0.13086742162704468 2023-01-23 14:37:30.082096: step: 1738/1545, loss: 0.07367642968893051 2023-01-23 14:37:30.957902: step: 1740/1545, loss: 0.012695233337581158 2023-01-23 14:37:31.809980: step: 1742/1545, loss: 0.01732645183801651 2023-01-23 14:37:32.662382: step: 1744/1545, loss: 0.10156772285699844 2023-01-23 14:37:33.564197: step: 1746/1545, loss: 0.012331148609519005 2023-01-23 14:37:34.424626: step: 1748/1545, loss: 0.08382649719715118 2023-01-23 14:37:35.376094: step: 1750/1545, loss: 0.023428454995155334 2023-01-23 14:37:36.264965: step: 1752/1545, loss: 0.09695728123188019 2023-01-23 14:37:37.174954: step: 1754/1545, loss: 0.2660183608531952 2023-01-23 14:37:38.068814: step: 1756/1545, loss: 0.011791152879595757 2023-01-23 14:37:38.960855: step: 1758/1545, loss: 0.04925566166639328 2023-01-23 14:37:39.907865: step: 1760/1545, loss: 0.00814817938953638 2023-01-23 14:37:40.873279: step: 1762/1545, loss: 0.0001292887463932857 2023-01-23 14:37:41.826661: step: 1764/1545, loss: 0.06599283218383789 2023-01-23 14:37:42.696936: step: 1766/1545, loss: 0.009718282148241997 2023-01-23 14:37:43.582265: step: 1768/1545, loss: 1.7810641527175903 2023-01-23 14:37:44.512620: step: 1770/1545, loss: 0.6384729146957397 2023-01-23 14:37:45.401480: step: 1772/1545, loss: 0.0032759136520326138 2023-01-23 14:37:46.279841: step: 1774/1545, loss: 0.018278978765010834 2023-01-23 14:37:47.161464: step: 1776/1545, loss: 0.049728717654943466 2023-01-23 14:37:48.057658: step: 1778/1545, loss: 0.784081757068634 2023-01-23 14:37:48.982499: step: 1780/1545, loss: 0.08529216051101685 2023-01-23 14:37:49.905283: step: 1782/1545, loss: 0.010119643993675709 2023-01-23 14:37:50.768403: step: 1784/1545, loss: 0.0019496571039780974 2023-01-23 14:37:51.673203: step: 1786/1545, loss: 0.045084841549396515 2023-01-23 14:37:52.533207: step: 1788/1545, loss: 0.0014526599552482367 2023-01-23 14:37:53.367361: step: 1790/1545, loss: 0.019384151324629784 2023-01-23 14:37:54.247884: step: 1792/1545, loss: 0.000651362759526819 2023-01-23 14:37:55.104276: step: 1794/1545, loss: 0.046457383781671524 2023-01-23 14:37:55.969230: step: 1796/1545, loss: 0.5537703633308411 2023-01-23 14:37:56.839227: step: 1798/1545, loss: 0.03261303901672363 2023-01-23 14:37:57.753786: step: 1800/1545, loss: 0.006776696071028709 2023-01-23 14:37:58.584746: step: 1802/1545, loss: 0.11059047281742096 2023-01-23 14:37:59.507158: step: 1804/1545, loss: 0.03471478447318077 2023-01-23 14:38:00.398034: step: 1806/1545, loss: 0.0531734935939312 2023-01-23 14:38:01.420164: step: 1808/1545, loss: 0.0051568420603871346 2023-01-23 14:38:02.292253: step: 1810/1545, loss: 0.0747295618057251 2023-01-23 14:38:03.172499: step: 1812/1545, loss: 0.002669004024937749 2023-01-23 14:38:04.007030: step: 1814/1545, loss: 2.4658049369463697e-05 2023-01-23 14:38:04.906712: step: 1816/1545, loss: 0.08671595901250839 2023-01-23 14:38:05.800648: step: 1818/1545, loss: 0.009156166575849056 2023-01-23 14:38:06.650301: step: 1820/1545, loss: 0.7959109544754028 2023-01-23 14:38:07.534658: step: 1822/1545, loss: 0.0008494556532241404 2023-01-23 14:38:08.387719: step: 1824/1545, loss: 0.00032298016594722867 2023-01-23 14:38:09.320861: step: 1826/1545, loss: 0.003678200300782919 2023-01-23 14:38:10.203308: step: 1828/1545, loss: 0.00018400420958641917 2023-01-23 14:38:11.163092: step: 1830/1545, loss: 0.05006451532244682 2023-01-23 14:38:12.029965: step: 1832/1545, loss: 0.12134934961795807 2023-01-23 14:38:12.903378: step: 1834/1545, loss: 0.23121140897274017 2023-01-23 14:38:13.806682: step: 1836/1545, loss: 0.08465076237916946 2023-01-23 14:38:14.707459: step: 1838/1545, loss: 0.21883624792099 2023-01-23 14:38:15.596210: step: 1840/1545, loss: 0.0009929330553859472 2023-01-23 14:38:16.488772: step: 1842/1545, loss: 0.0027688532136380672 2023-01-23 14:38:17.349962: step: 1844/1545, loss: 0.2602999806404114 2023-01-23 14:38:18.225623: step: 1846/1545, loss: 0.08613951504230499 2023-01-23 14:38:19.083115: step: 1848/1545, loss: 0.054456375539302826 2023-01-23 14:38:19.965563: step: 1850/1545, loss: 0.0639585331082344 2023-01-23 14:38:20.822107: step: 1852/1545, loss: 0.12376734614372253 2023-01-23 14:38:21.696753: step: 1854/1545, loss: 0.07858347147703171 2023-01-23 14:38:22.657300: step: 1856/1545, loss: 0.23927950859069824 2023-01-23 14:38:23.558230: step: 1858/1545, loss: 0.0332847535610199 2023-01-23 14:38:24.402379: step: 1860/1545, loss: 0.1626860648393631 2023-01-23 14:38:25.283597: step: 1862/1545, loss: 0.16335414350032806 2023-01-23 14:38:26.169177: step: 1864/1545, loss: 0.039312079548835754 2023-01-23 14:38:27.024596: step: 1866/1545, loss: 0.1884078085422516 2023-01-23 14:38:27.921229: step: 1868/1545, loss: 0.015727877616882324 2023-01-23 14:38:28.912173: step: 1870/1545, loss: 0.031428076326847076 2023-01-23 14:38:29.813280: step: 1872/1545, loss: 0.04934258386492729 2023-01-23 14:38:30.664712: step: 1874/1545, loss: 0.015129737555980682 2023-01-23 14:38:31.556036: step: 1876/1545, loss: 0.055697157979011536 2023-01-23 14:38:32.456699: step: 1878/1545, loss: 0.007830584421753883 2023-01-23 14:38:33.305916: step: 1880/1545, loss: 0.003100066911429167 2023-01-23 14:38:34.240124: step: 1882/1545, loss: 0.036135293543338776 2023-01-23 14:38:35.154554: step: 1884/1545, loss: 0.002223000396043062 2023-01-23 14:38:36.065908: step: 1886/1545, loss: 0.09594801813364029 2023-01-23 14:38:36.919907: step: 1888/1545, loss: 0.021424386650323868 2023-01-23 14:38:37.808665: step: 1890/1545, loss: 0.15426401793956757 2023-01-23 14:38:38.696732: step: 1892/1545, loss: 0.008043878711760044 2023-01-23 14:38:39.617461: step: 1894/1545, loss: 0.17233233153820038 2023-01-23 14:38:40.470755: step: 1896/1545, loss: 0.0040808385238051414 2023-01-23 14:38:41.317148: step: 1898/1545, loss: 0.07408001273870468 2023-01-23 14:38:42.162509: step: 1900/1545, loss: 0.0775710716843605 2023-01-23 14:38:43.030975: step: 1902/1545, loss: 0.1119220107793808 2023-01-23 14:38:43.898652: step: 1904/1545, loss: 0.1091916561126709 2023-01-23 14:38:44.783370: step: 1906/1545, loss: 0.007265882566571236 2023-01-23 14:38:45.708556: step: 1908/1545, loss: 0.1868586242198944 2023-01-23 14:38:46.602710: step: 1910/1545, loss: 0.010329876095056534 2023-01-23 14:38:47.455134: step: 1912/1545, loss: 0.07280375063419342 2023-01-23 14:38:48.316452: step: 1914/1545, loss: 0.013959960080683231 2023-01-23 14:38:49.271840: step: 1916/1545, loss: 0.019032225012779236 2023-01-23 14:38:50.235817: step: 1918/1545, loss: 0.08602134883403778 2023-01-23 14:38:51.135268: step: 1920/1545, loss: 0.6717368364334106 2023-01-23 14:38:52.172424: step: 1922/1545, loss: 0.051830679178237915 2023-01-23 14:38:53.133472: step: 1924/1545, loss: 0.3202926516532898 2023-01-23 14:38:54.009175: step: 1926/1545, loss: 0.12050192058086395 2023-01-23 14:38:54.880342: step: 1928/1545, loss: 0.13010826706886292 2023-01-23 14:38:55.792915: step: 1930/1545, loss: 0.0003206375986337662 2023-01-23 14:38:56.656595: step: 1932/1545, loss: 0.0018406606977805495 2023-01-23 14:38:57.532727: step: 1934/1545, loss: 0.8533974289894104 2023-01-23 14:38:58.380308: step: 1936/1545, loss: 0.020471498370170593 2023-01-23 14:38:59.234290: step: 1938/1545, loss: 0.024586979299783707 2023-01-23 14:39:00.097925: step: 1940/1545, loss: 0.011209361255168915 2023-01-23 14:39:00.961821: step: 1942/1545, loss: 0.02389949932694435 2023-01-23 14:39:01.881679: step: 1944/1545, loss: 0.08256664872169495 2023-01-23 14:39:02.716210: step: 1946/1545, loss: 0.030052851885557175 2023-01-23 14:39:03.601798: step: 1948/1545, loss: 0.03208974748849869 2023-01-23 14:39:04.509092: step: 1950/1545, loss: 0.152483731508255 2023-01-23 14:39:05.369853: step: 1952/1545, loss: 0.0006684939726255834 2023-01-23 14:39:06.271128: step: 1954/1545, loss: 0.0009178596665151417 2023-01-23 14:39:07.131750: step: 1956/1545, loss: 0.09956240653991699 2023-01-23 14:39:08.089705: step: 1958/1545, loss: 0.024782150983810425 2023-01-23 14:39:09.008107: step: 1960/1545, loss: 0.002018982544541359 2023-01-23 14:39:09.899560: step: 1962/1545, loss: 0.024419767782092094 2023-01-23 14:39:10.803613: step: 1964/1545, loss: 0.26014190912246704 2023-01-23 14:39:11.702192: step: 1966/1545, loss: 0.08778167515993118 2023-01-23 14:39:12.568377: step: 1968/1545, loss: 0.05255360156297684 2023-01-23 14:39:13.459808: step: 1970/1545, loss: 0.19299332797527313 2023-01-23 14:39:14.371481: step: 1972/1545, loss: 0.12328783422708511 2023-01-23 14:39:15.223328: step: 1974/1545, loss: 0.006238696165382862 2023-01-23 14:39:16.090812: step: 1976/1545, loss: 0.3114914298057556 2023-01-23 14:39:16.948877: step: 1978/1545, loss: 0.02402844838798046 2023-01-23 14:39:17.837681: step: 1980/1545, loss: 0.0881783589720726 2023-01-23 14:39:18.690802: step: 1982/1545, loss: 0.02083127573132515 2023-01-23 14:39:19.582135: step: 1984/1545, loss: 0.0003232901799492538 2023-01-23 14:39:20.424977: step: 1986/1545, loss: 0.014617670327425003 2023-01-23 14:39:21.287207: step: 1988/1545, loss: 0.057345982640981674 2023-01-23 14:39:22.215234: step: 1990/1545, loss: 0.035880181938409805 2023-01-23 14:39:23.125380: step: 1992/1545, loss: 0.048342060297727585 2023-01-23 14:39:24.007956: step: 1994/1545, loss: 0.037437088787555695 2023-01-23 14:39:24.904213: step: 1996/1545, loss: 0.16106127202510834 2023-01-23 14:39:25.766892: step: 1998/1545, loss: 0.11507933586835861 2023-01-23 14:39:26.613549: step: 2000/1545, loss: 0.03257615864276886 2023-01-23 14:39:27.481679: step: 2002/1545, loss: 0.020061923190951347 2023-01-23 14:39:28.357249: step: 2004/1545, loss: 0.0026460986118763685 2023-01-23 14:39:29.259396: step: 2006/1545, loss: 0.0004667926114052534 2023-01-23 14:39:30.125791: step: 2008/1545, loss: 0.005452670156955719 2023-01-23 14:39:31.010074: step: 2010/1545, loss: 0.007329462096095085 2023-01-23 14:39:31.886597: step: 2012/1545, loss: 0.2744261622428894 2023-01-23 14:39:32.753117: step: 2014/1545, loss: 0.03785635158419609 2023-01-23 14:39:33.627744: step: 2016/1545, loss: 0.11376147717237473 2023-01-23 14:39:34.543009: step: 2018/1545, loss: 0.16321499645709991 2023-01-23 14:39:35.426637: step: 2020/1545, loss: 0.03493524715304375 2023-01-23 14:39:36.288792: step: 2022/1545, loss: 0.19597795605659485 2023-01-23 14:39:37.216310: step: 2024/1545, loss: 0.21463163197040558 2023-01-23 14:39:38.068519: step: 2026/1545, loss: 0.02348273992538452 2023-01-23 14:39:38.934113: step: 2028/1545, loss: 0.08598965406417847 2023-01-23 14:39:39.829653: step: 2030/1545, loss: 0.08132000267505646 2023-01-23 14:39:40.701910: step: 2032/1545, loss: 0.18750347197055817 2023-01-23 14:39:41.595766: step: 2034/1545, loss: 0.10404396057128906 2023-01-23 14:39:42.502580: step: 2036/1545, loss: 0.03281861171126366 2023-01-23 14:39:43.418565: step: 2038/1545, loss: 0.0023907560389488935 2023-01-23 14:39:44.313900: step: 2040/1545, loss: 0.41719934344291687 2023-01-23 14:39:45.213525: step: 2042/1545, loss: 0.10382431000471115 2023-01-23 14:39:46.128392: step: 2044/1545, loss: 0.06624503433704376 2023-01-23 14:39:46.974741: step: 2046/1545, loss: 0.08556064963340759 2023-01-23 14:39:47.977269: step: 2048/1545, loss: 0.2285308539867401 2023-01-23 14:39:48.884015: step: 2050/1545, loss: 0.13875125348567963 2023-01-23 14:39:49.748463: step: 2052/1545, loss: 0.16416418552398682 2023-01-23 14:39:50.608466: step: 2054/1545, loss: 0.05540437623858452 2023-01-23 14:39:51.533174: step: 2056/1545, loss: 0.3289199471473694 2023-01-23 14:39:52.431362: step: 2058/1545, loss: 0.001639609457924962 2023-01-23 14:39:53.319228: step: 2060/1545, loss: 0.013693828135728836 2023-01-23 14:39:54.187394: step: 2062/1545, loss: 0.05480741336941719 2023-01-23 14:39:55.073663: step: 2064/1545, loss: 0.0019137713825330138 2023-01-23 14:39:55.996072: step: 2066/1545, loss: 0.04048041254281998 2023-01-23 14:39:56.841696: step: 2068/1545, loss: 0.05167973041534424 2023-01-23 14:39:57.684116: step: 2070/1545, loss: 0.004882043693214655 2023-01-23 14:39:58.575848: step: 2072/1545, loss: 0.037380002439022064 2023-01-23 14:39:59.445227: step: 2074/1545, loss: 0.11593108624219894 2023-01-23 14:40:00.394080: step: 2076/1545, loss: 0.06425882875919342 2023-01-23 14:40:01.283982: step: 2078/1545, loss: 0.09668057411909103 2023-01-23 14:40:02.222547: step: 2080/1545, loss: 0.030008496716618538 2023-01-23 14:40:03.079448: step: 2082/1545, loss: 0.05618538334965706 2023-01-23 14:40:04.022288: step: 2084/1545, loss: 0.0019411171087995172 2023-01-23 14:40:04.908380: step: 2086/1545, loss: 0.004871889483183622 2023-01-23 14:40:05.764281: step: 2088/1545, loss: 0.0007374791894108057 2023-01-23 14:40:06.664214: step: 2090/1545, loss: 0.01311815157532692 2023-01-23 14:40:07.553019: step: 2092/1545, loss: 0.016845237463712692 2023-01-23 14:40:08.428457: step: 2094/1545, loss: 0.005567869171500206 2023-01-23 14:40:09.377152: step: 2096/1545, loss: 0.20391298830509186 2023-01-23 14:40:10.283908: step: 2098/1545, loss: 0.022021634504199028 2023-01-23 14:40:11.203507: step: 2100/1545, loss: 0.04188090190291405 2023-01-23 14:40:12.100041: step: 2102/1545, loss: 0.1093468964099884 2023-01-23 14:40:12.977566: step: 2104/1545, loss: 0.4635384976863861 2023-01-23 14:40:13.852637: step: 2106/1545, loss: 0.013844887726008892 2023-01-23 14:40:14.739846: step: 2108/1545, loss: 0.01122058741748333 2023-01-23 14:40:15.602090: step: 2110/1545, loss: 0.014849857427179813 2023-01-23 14:40:16.480665: step: 2112/1545, loss: 0.4369580149650574 2023-01-23 14:40:17.345141: step: 2114/1545, loss: 0.13905037939548492 2023-01-23 14:40:18.240688: step: 2116/1545, loss: 0.01926443725824356 2023-01-23 14:40:19.153920: step: 2118/1545, loss: 0.08057631552219391 2023-01-23 14:40:20.127486: step: 2120/1545, loss: 0.004117351491004229 2023-01-23 14:40:21.057359: step: 2122/1545, loss: 0.598136842250824 2023-01-23 14:40:21.908253: step: 2124/1545, loss: 0.17368781566619873 2023-01-23 14:40:22.808360: step: 2126/1545, loss: 0.4918478727340698 2023-01-23 14:40:23.630792: step: 2128/1545, loss: 0.003787510097026825 2023-01-23 14:40:24.505844: step: 2130/1545, loss: 0.015276160091161728 2023-01-23 14:40:25.341580: step: 2132/1545, loss: 0.0010795702692121267 2023-01-23 14:40:26.249417: step: 2134/1545, loss: 0.2573518455028534 2023-01-23 14:40:27.184691: step: 2136/1545, loss: 0.0007480172789655626 2023-01-23 14:40:28.082325: step: 2138/1545, loss: 0.01147205475717783 2023-01-23 14:40:29.029292: step: 2140/1545, loss: 0.053776662796735764 2023-01-23 14:40:29.929363: step: 2142/1545, loss: 0.06586793065071106 2023-01-23 14:40:30.785217: step: 2144/1545, loss: 0.3214718997478485 2023-01-23 14:40:31.740715: step: 2146/1545, loss: 0.006095591001212597 2023-01-23 14:40:32.595808: step: 2148/1545, loss: 0.041211336851119995 2023-01-23 14:40:33.448238: step: 2150/1545, loss: 0.4878970980644226 2023-01-23 14:40:34.341880: step: 2152/1545, loss: 0.21121712028980255 2023-01-23 14:40:35.201794: step: 2154/1545, loss: 0.0035697869025170803 2023-01-23 14:40:36.101879: step: 2156/1545, loss: 0.14470313489437103 2023-01-23 14:40:37.023138: step: 2158/1545, loss: 0.02770516648888588 2023-01-23 14:40:37.948773: step: 2160/1545, loss: 0.008951041847467422 2023-01-23 14:40:38.828680: step: 2162/1545, loss: 0.10350832343101501 2023-01-23 14:40:39.719008: step: 2164/1545, loss: 0.020281923934817314 2023-01-23 14:40:40.613949: step: 2166/1545, loss: 0.002193727996200323 2023-01-23 14:40:41.458301: step: 2168/1545, loss: 0.24663536250591278 2023-01-23 14:40:42.344444: step: 2170/1545, loss: 0.004333991091698408 2023-01-23 14:40:43.255340: step: 2172/1545, loss: 0.2653822600841522 2023-01-23 14:40:44.134733: step: 2174/1545, loss: 0.44279390573501587 2023-01-23 14:40:45.021710: step: 2176/1545, loss: 0.025689776986837387 2023-01-23 14:40:45.899219: step: 2178/1545, loss: 0.001886909012682736 2023-01-23 14:40:46.789341: step: 2180/1545, loss: 0.0026975551154464483 2023-01-23 14:40:47.713883: step: 2182/1545, loss: 0.031237542629241943 2023-01-23 14:40:48.602568: step: 2184/1545, loss: 0.04979509860277176 2023-01-23 14:40:49.457111: step: 2186/1545, loss: 0.0014199198922142386 2023-01-23 14:40:50.302218: step: 2188/1545, loss: 0.20753934979438782 2023-01-23 14:40:51.188985: step: 2190/1545, loss: 0.013499835506081581 2023-01-23 14:40:52.101163: step: 2192/1545, loss: 0.14190055429935455 2023-01-23 14:40:52.973074: step: 2194/1545, loss: 0.005662014242261648 2023-01-23 14:40:53.830285: step: 2196/1545, loss: 0.1560671329498291 2023-01-23 14:40:54.797756: step: 2198/1545, loss: 0.08971400558948517 2023-01-23 14:40:55.717320: step: 2200/1545, loss: 0.016688086092472076 2023-01-23 14:40:56.593188: step: 2202/1545, loss: 0.10515779256820679 2023-01-23 14:40:57.445076: step: 2204/1545, loss: 0.0015531664248555899 2023-01-23 14:40:58.276505: step: 2206/1545, loss: 0.000544958864338696 2023-01-23 14:40:59.175235: step: 2208/1545, loss: 0.002157923998311162 2023-01-23 14:41:00.036689: step: 2210/1545, loss: 0.0989345982670784 2023-01-23 14:41:00.938733: step: 2212/1545, loss: 0.005791713483631611 2023-01-23 14:41:01.806710: step: 2214/1545, loss: 0.015831084921956062 2023-01-23 14:41:02.645007: step: 2216/1545, loss: 0.0005171739612706006 2023-01-23 14:41:03.520735: step: 2218/1545, loss: 0.016572076827287674 2023-01-23 14:41:04.382065: step: 2220/1545, loss: 0.027443233877420425 2023-01-23 14:41:05.203138: step: 2222/1545, loss: 0.0009634022135287523 2023-01-23 14:41:06.077315: step: 2224/1545, loss: 0.01506546325981617 2023-01-23 14:41:07.031480: step: 2226/1545, loss: 0.08205332607030869 2023-01-23 14:41:07.911741: step: 2228/1545, loss: 0.5379413366317749 2023-01-23 14:41:08.829076: step: 2230/1545, loss: 0.1280350387096405 2023-01-23 14:41:09.717892: step: 2232/1545, loss: 0.14484436810016632 2023-01-23 14:41:10.576893: step: 2234/1545, loss: 0.03178626671433449 2023-01-23 14:41:11.439447: step: 2236/1545, loss: 0.011417211964726448 2023-01-23 14:41:12.325756: step: 2238/1545, loss: 0.029714474454522133 2023-01-23 14:41:13.190527: step: 2240/1545, loss: 0.004596383776515722 2023-01-23 14:41:14.105456: step: 2242/1545, loss: 0.049450650811195374 2023-01-23 14:41:14.941995: step: 2244/1545, loss: 0.1481124609708786 2023-01-23 14:41:15.872854: step: 2246/1545, loss: 0.00110735057387501 2023-01-23 14:41:16.729354: step: 2248/1545, loss: 0.025540456175804138 2023-01-23 14:41:17.646978: step: 2250/1545, loss: 0.015210158191621304 2023-01-23 14:41:18.530188: step: 2252/1545, loss: 0.02481052279472351 2023-01-23 14:41:19.432361: step: 2254/1545, loss: 0.011205809190869331 2023-01-23 14:41:20.300707: step: 2256/1545, loss: 0.08157867193222046 2023-01-23 14:41:21.218496: step: 2258/1545, loss: 0.04052410274744034 2023-01-23 14:41:22.091729: step: 2260/1545, loss: 0.047372061759233475 2023-01-23 14:41:22.966855: step: 2262/1545, loss: 0.004655221477150917 2023-01-23 14:41:23.813670: step: 2264/1545, loss: 0.007872537709772587 2023-01-23 14:41:24.723206: step: 2266/1545, loss: 0.12868651747703552 2023-01-23 14:41:25.649011: step: 2268/1545, loss: 0.01589595153927803 2023-01-23 14:41:26.535662: step: 2270/1545, loss: 0.01932879351079464 2023-01-23 14:41:27.449985: step: 2272/1545, loss: 0.007272646296769381 2023-01-23 14:41:28.322804: step: 2274/1545, loss: 0.006655814126133919 2023-01-23 14:41:29.223123: step: 2276/1545, loss: 0.15837842226028442 2023-01-23 14:41:30.191959: step: 2278/1545, loss: 0.25182849168777466 2023-01-23 14:41:31.051609: step: 2280/1545, loss: 0.24268272519111633 2023-01-23 14:41:31.947504: step: 2282/1545, loss: 0.11866600811481476 2023-01-23 14:41:32.807301: step: 2284/1545, loss: 0.03477887064218521 2023-01-23 14:41:33.701109: step: 2286/1545, loss: 0.13182899355888367 2023-01-23 14:41:34.574537: step: 2288/1545, loss: 0.06927158683538437 2023-01-23 14:41:35.578169: step: 2290/1545, loss: 0.01707163266837597 2023-01-23 14:41:36.498494: step: 2292/1545, loss: 0.3436014652252197 2023-01-23 14:41:37.363088: step: 2294/1545, loss: 0.028726808726787567 2023-01-23 14:41:38.265952: step: 2296/1545, loss: 0.025470653548836708 2023-01-23 14:41:39.129682: step: 2298/1545, loss: 0.006494556088000536 2023-01-23 14:41:40.001273: step: 2300/1545, loss: 0.2383914589881897 2023-01-23 14:41:40.896173: step: 2302/1545, loss: 2.1973583698272705 2023-01-23 14:41:41.752901: step: 2304/1545, loss: 0.2032047063112259 2023-01-23 14:41:42.648666: step: 2306/1545, loss: 0.08469387143850327 2023-01-23 14:41:43.516945: step: 2308/1545, loss: 0.001673698308877647 2023-01-23 14:41:44.376897: step: 2310/1545, loss: 0.013276584446430206 2023-01-23 14:41:45.244204: step: 2312/1545, loss: 0.3968539237976074 2023-01-23 14:41:46.126457: step: 2314/1545, loss: 0.010924807749688625 2023-01-23 14:41:46.992545: step: 2316/1545, loss: 0.08966853469610214 2023-01-23 14:41:47.878349: step: 2318/1545, loss: 0.16459538042545319 2023-01-23 14:41:48.765656: step: 2320/1545, loss: 0.014125491492450237 2023-01-23 14:41:49.704123: step: 2322/1545, loss: 0.023226020857691765 2023-01-23 14:41:50.562833: step: 2324/1545, loss: 0.010799655690789223 2023-01-23 14:41:51.406119: step: 2326/1545, loss: 0.08012089133262634 2023-01-23 14:41:52.274990: step: 2328/1545, loss: 0.01230438519269228 2023-01-23 14:41:53.128790: step: 2330/1545, loss: 0.09036939591169357 2023-01-23 14:41:53.977895: step: 2332/1545, loss: 0.010399503633379936 2023-01-23 14:41:54.862078: step: 2334/1545, loss: 0.04553263634443283 2023-01-23 14:41:55.753373: step: 2336/1545, loss: 1.275596022605896 2023-01-23 14:41:56.564790: step: 2338/1545, loss: 0.020363667979836464 2023-01-23 14:41:57.420359: step: 2340/1545, loss: 0.05028083175420761 2023-01-23 14:41:58.314623: step: 2342/1545, loss: 0.04043174162507057 2023-01-23 14:41:59.211142: step: 2344/1545, loss: 0.04173025116324425 2023-01-23 14:42:00.121032: step: 2346/1545, loss: 0.018542956560850143 2023-01-23 14:42:01.058353: step: 2348/1545, loss: 0.5954902768135071 2023-01-23 14:42:01.945854: step: 2350/1545, loss: 0.15257366001605988 2023-01-23 14:42:02.806499: step: 2352/1545, loss: 0.06462990492582321 2023-01-23 14:42:03.644103: step: 2354/1545, loss: 0.15035013854503632 2023-01-23 14:42:04.519103: step: 2356/1545, loss: 0.00056844501523301 2023-01-23 14:42:05.387558: step: 2358/1545, loss: 0.025876443833112717 2023-01-23 14:42:06.256733: step: 2360/1545, loss: 0.009303588420152664 2023-01-23 14:42:07.118857: step: 2362/1545, loss: 0.008348899893462658 2023-01-23 14:42:07.995254: step: 2364/1545, loss: 0.11556290835142136 2023-01-23 14:42:08.891907: step: 2366/1545, loss: 0.01514323242008686 2023-01-23 14:42:09.754163: step: 2368/1545, loss: 0.02515236660838127 2023-01-23 14:42:10.603501: step: 2370/1545, loss: 0.0055928356014192104 2023-01-23 14:42:11.456170: step: 2372/1545, loss: 0.32788461446762085 2023-01-23 14:42:12.332576: step: 2374/1545, loss: 0.09696194529533386 2023-01-23 14:42:13.258601: step: 2376/1545, loss: 0.014259153977036476 2023-01-23 14:42:14.177820: step: 2378/1545, loss: 0.0011273471172899008 2023-01-23 14:42:15.046694: step: 2380/1545, loss: 0.19809946417808533 2023-01-23 14:42:15.932863: step: 2382/1545, loss: 0.06597635895013809 2023-01-23 14:42:16.887635: step: 2384/1545, loss: 0.0787215307354927 2023-01-23 14:42:17.799991: step: 2386/1545, loss: 0.0013930286513641477 2023-01-23 14:42:18.697508: step: 2388/1545, loss: 0.0014124235603958368 2023-01-23 14:42:19.567740: step: 2390/1545, loss: 0.0069526308216154575 2023-01-23 14:42:20.435394: step: 2392/1545, loss: 0.2145290970802307 2023-01-23 14:42:21.298513: step: 2394/1545, loss: 0.0805620551109314 2023-01-23 14:42:22.202666: step: 2396/1545, loss: 0.12870976328849792 2023-01-23 14:42:23.077534: step: 2398/1545, loss: 0.0028759955894201994 2023-01-23 14:42:24.010309: step: 2400/1545, loss: 0.19298967719078064 2023-01-23 14:42:24.952865: step: 2402/1545, loss: 0.03782065585255623 2023-01-23 14:42:25.833457: step: 2404/1545, loss: 0.1107221469283104 2023-01-23 14:42:26.716955: step: 2406/1545, loss: 0.003155434038490057 2023-01-23 14:42:27.595291: step: 2408/1545, loss: 0.053300634026527405 2023-01-23 14:42:28.504893: step: 2410/1545, loss: 0.10245714336633682 2023-01-23 14:42:29.406083: step: 2412/1545, loss: 0.1273641139268875 2023-01-23 14:42:30.260415: step: 2414/1545, loss: 0.0021087978966534138 2023-01-23 14:42:31.166660: step: 2416/1545, loss: 0.060617413371801376 2023-01-23 14:42:32.065735: step: 2418/1545, loss: 0.011219126172363758 2023-01-23 14:42:32.930679: step: 2420/1545, loss: 0.5749011635780334 2023-01-23 14:42:33.902961: step: 2422/1545, loss: 0.12870299816131592 2023-01-23 14:42:34.762163: step: 2424/1545, loss: 0.10083121806383133 2023-01-23 14:42:35.585153: step: 2426/1545, loss: 0.09733618050813675 2023-01-23 14:42:36.424508: step: 2428/1545, loss: 0.16824288666248322 2023-01-23 14:42:37.309968: step: 2430/1545, loss: 0.01243760995566845 2023-01-23 14:42:38.193481: step: 2432/1545, loss: 0.09633622318506241 2023-01-23 14:42:39.074647: step: 2434/1545, loss: 0.10246232897043228 2023-01-23 14:42:39.973433: step: 2436/1545, loss: 0.12020327150821686 2023-01-23 14:42:40.798068: step: 2438/1545, loss: 0.009556285105645657 2023-01-23 14:42:41.633931: step: 2440/1545, loss: 0.05244716629385948 2023-01-23 14:42:42.465607: step: 2442/1545, loss: 0.002289379248395562 2023-01-23 14:42:43.332670: step: 2444/1545, loss: 0.005301443859934807 2023-01-23 14:42:44.260190: step: 2446/1545, loss: 0.10655202716588974 2023-01-23 14:42:45.153961: step: 2448/1545, loss: 0.014615969732403755 2023-01-23 14:42:46.009442: step: 2450/1545, loss: 0.14919699728488922 2023-01-23 14:42:46.857984: step: 2452/1545, loss: 0.08399081230163574 2023-01-23 14:42:47.712915: step: 2454/1545, loss: 0.009775638580322266 2023-01-23 14:42:48.645440: step: 2456/1545, loss: 0.10798011720180511 2023-01-23 14:42:49.567909: step: 2458/1545, loss: 0.014811292290687561 2023-01-23 14:42:50.423570: step: 2460/1545, loss: 0.19648447632789612 2023-01-23 14:42:51.270698: step: 2462/1545, loss: 0.05347878485918045 2023-01-23 14:42:52.180236: step: 2464/1545, loss: 0.23197336494922638 2023-01-23 14:42:53.074809: step: 2466/1545, loss: 0.08887141942977905 2023-01-23 14:42:54.004105: step: 2468/1545, loss: 0.04090063273906708 2023-01-23 14:42:54.956208: step: 2470/1545, loss: 0.15922535955905914 2023-01-23 14:42:55.826128: step: 2472/1545, loss: 0.008571842685341835 2023-01-23 14:42:56.731681: step: 2474/1545, loss: 0.2327008992433548 2023-01-23 14:42:57.641715: step: 2476/1545, loss: 0.032934997230768204 2023-01-23 14:42:58.509386: step: 2478/1545, loss: 0.010994099080562592 2023-01-23 14:42:59.382728: step: 2480/1545, loss: 0.06867815554141998 2023-01-23 14:43:00.239872: step: 2482/1545, loss: 0.11104673147201538 2023-01-23 14:43:01.086433: step: 2484/1545, loss: 0.12014254182577133 2023-01-23 14:43:01.938303: step: 2486/1545, loss: 0.05196651816368103 2023-01-23 14:43:02.787013: step: 2488/1545, loss: 0.04233657568693161 2023-01-23 14:43:03.629465: step: 2490/1545, loss: 0.0013358175056055188 2023-01-23 14:43:04.578428: step: 2492/1545, loss: 0.10691075026988983 2023-01-23 14:43:05.425600: step: 2494/1545, loss: 0.02319648116827011 2023-01-23 14:43:06.283323: step: 2496/1545, loss: 0.17926077544689178 2023-01-23 14:43:07.161717: step: 2498/1545, loss: 0.13725599646568298 2023-01-23 14:43:08.120381: step: 2500/1545, loss: 0.161615788936615 2023-01-23 14:43:08.984499: step: 2502/1545, loss: 0.07805843651294708 2023-01-23 14:43:09.833104: step: 2504/1545, loss: 0.010603050701320171 2023-01-23 14:43:10.692366: step: 2506/1545, loss: 0.09141869843006134 2023-01-23 14:43:11.542562: step: 2508/1545, loss: 0.005361317656934261 2023-01-23 14:43:12.459168: step: 2510/1545, loss: 0.09343381226062775 2023-01-23 14:43:13.355183: step: 2512/1545, loss: 0.013779236935079098 2023-01-23 14:43:14.195471: step: 2514/1545, loss: 0.2133164405822754 2023-01-23 14:43:15.120871: step: 2516/1545, loss: 0.009248120710253716 2023-01-23 14:43:15.995726: step: 2518/1545, loss: 0.04508965089917183 2023-01-23 14:43:16.823431: step: 2520/1545, loss: 0.016963815316557884 2023-01-23 14:43:17.673862: step: 2522/1545, loss: 0.02818581461906433 2023-01-23 14:43:18.604467: step: 2524/1545, loss: 0.10426254570484161 2023-01-23 14:43:19.543553: step: 2526/1545, loss: 0.07360266149044037 2023-01-23 14:43:20.447888: step: 2528/1545, loss: 0.6502127051353455 2023-01-23 14:43:21.300711: step: 2530/1545, loss: 0.048748213797807693 2023-01-23 14:43:22.227747: step: 2532/1545, loss: 0.11983158439397812 2023-01-23 14:43:23.127401: step: 2534/1545, loss: 0.02020290680229664 2023-01-23 14:43:23.975233: step: 2536/1545, loss: 0.0026515289209783077 2023-01-23 14:43:24.846733: step: 2538/1545, loss: 0.1805926114320755 2023-01-23 14:43:25.716089: step: 2540/1545, loss: 0.11591541767120361 2023-01-23 14:43:26.582234: step: 2542/1545, loss: 0.033326830714941025 2023-01-23 14:43:27.476383: step: 2544/1545, loss: 0.014532286673784256 2023-01-23 14:43:28.346036: step: 2546/1545, loss: 0.01943078450858593 2023-01-23 14:43:29.225992: step: 2548/1545, loss: 0.28201034665107727 2023-01-23 14:43:30.117254: step: 2550/1545, loss: 0.25939950346946716 2023-01-23 14:43:30.990324: step: 2552/1545, loss: 0.03550949692726135 2023-01-23 14:43:31.950687: step: 2554/1545, loss: 0.03459268808364868 2023-01-23 14:43:32.872719: step: 2556/1545, loss: 0.12553422152996063 2023-01-23 14:43:33.760404: step: 2558/1545, loss: 0.06095029413700104 2023-01-23 14:43:34.667298: step: 2560/1545, loss: 0.05486726760864258 2023-01-23 14:43:35.557620: step: 2562/1545, loss: 0.012077920138835907 2023-01-23 14:43:36.476352: step: 2564/1545, loss: 0.02675660327076912 2023-01-23 14:43:37.341286: step: 2566/1545, loss: 0.9543637037277222 2023-01-23 14:43:38.248245: step: 2568/1545, loss: 0.08146554976701736 2023-01-23 14:43:39.165670: step: 2570/1545, loss: 0.020080693066120148 2023-01-23 14:43:40.052983: step: 2572/1545, loss: 0.0006190179847180843 2023-01-23 14:43:40.949439: step: 2574/1545, loss: 0.01199290994554758 2023-01-23 14:43:41.774631: step: 2576/1545, loss: 0.025633087381720543 2023-01-23 14:43:42.675461: step: 2578/1545, loss: 0.0047684321179986 2023-01-23 14:43:43.598565: step: 2580/1545, loss: 0.009756463579833508 2023-01-23 14:43:44.471523: step: 2582/1545, loss: 0.024767793715000153 2023-01-23 14:43:45.340518: step: 2584/1545, loss: 0.11087902635335922 2023-01-23 14:43:46.261232: step: 2586/1545, loss: 0.02417724020779133 2023-01-23 14:43:47.181507: step: 2588/1545, loss: 0.055736154317855835 2023-01-23 14:43:48.075895: step: 2590/1545, loss: 0.032442621886730194 2023-01-23 14:43:49.031523: step: 2592/1545, loss: 0.04545603320002556 2023-01-23 14:43:49.881987: step: 2594/1545, loss: 0.08401273190975189 2023-01-23 14:43:50.770600: step: 2596/1545, loss: 0.0008427877328358591 2023-01-23 14:43:51.624091: step: 2598/1545, loss: 0.08036962151527405 2023-01-23 14:43:52.475137: step: 2600/1545, loss: 0.008178076706826687 2023-01-23 14:43:53.440906: step: 2602/1545, loss: 0.12658146023750305 2023-01-23 14:43:54.329753: step: 2604/1545, loss: 0.00835318025201559 2023-01-23 14:43:55.176691: step: 2606/1545, loss: 0.01857231743633747 2023-01-23 14:43:56.142202: step: 2608/1545, loss: 0.0016063186340034008 2023-01-23 14:43:57.008563: step: 2610/1545, loss: 0.13919083774089813 2023-01-23 14:43:57.913604: step: 2612/1545, loss: 0.1707989126443863 2023-01-23 14:43:58.803804: step: 2614/1545, loss: 0.001397784799337387 2023-01-23 14:43:59.675311: step: 2616/1545, loss: 0.04509984329342842 2023-01-23 14:44:00.563999: step: 2618/1545, loss: 0.0018190373666584492 2023-01-23 14:44:01.434816: step: 2620/1545, loss: 0.047054871916770935 2023-01-23 14:44:02.339642: step: 2622/1545, loss: 0.06720340996980667 2023-01-23 14:44:03.260716: step: 2624/1545, loss: 0.23909041285514832 2023-01-23 14:44:04.237636: step: 2626/1545, loss: 0.04373913258314133 2023-01-23 14:44:05.094065: step: 2628/1545, loss: 0.007275492884218693 2023-01-23 14:44:05.991146: step: 2630/1545, loss: 0.1276637613773346 2023-01-23 14:44:06.838167: step: 2632/1545, loss: 0.02512563392519951 2023-01-23 14:44:07.720506: step: 2634/1545, loss: 0.2208896279335022 2023-01-23 14:44:08.618703: step: 2636/1545, loss: 0.0052283466793596745 2023-01-23 14:44:09.540652: step: 2638/1545, loss: 0.01809481903910637 2023-01-23 14:44:10.440977: step: 2640/1545, loss: 0.17977160215377808 2023-01-23 14:44:11.316968: step: 2642/1545, loss: 0.017253246158361435 2023-01-23 14:44:12.169664: step: 2644/1545, loss: 0.12675966322422028 2023-01-23 14:44:13.049236: step: 2646/1545, loss: 0.21852421760559082 2023-01-23 14:44:13.931899: step: 2648/1545, loss: 0.30717378854751587 2023-01-23 14:44:14.884460: step: 2650/1545, loss: 0.018731577321887016 2023-01-23 14:44:15.748943: step: 2652/1545, loss: 0.003995433449745178 2023-01-23 14:44:16.656329: step: 2654/1545, loss: 0.0003465306363068521 2023-01-23 14:44:17.540857: step: 2656/1545, loss: 0.05817442014813423 2023-01-23 14:44:18.424051: step: 2658/1545, loss: 0.16367487609386444 2023-01-23 14:44:19.322314: step: 2660/1545, loss: 0.0009405920282006264 2023-01-23 14:44:20.229005: step: 2662/1545, loss: 0.125468447804451 2023-01-23 14:44:21.181345: step: 2664/1545, loss: 0.008452314883470535 2023-01-23 14:44:22.063966: step: 2666/1545, loss: 0.2673032283782959 2023-01-23 14:44:22.962644: step: 2668/1545, loss: 0.10206237435340881 2023-01-23 14:44:23.853037: step: 2670/1545, loss: 0.26609140634536743 2023-01-23 14:44:24.704638: step: 2672/1545, loss: 0.026907796040177345 2023-01-23 14:44:25.610142: step: 2674/1545, loss: 0.006539401598274708 2023-01-23 14:44:26.517368: step: 2676/1545, loss: 0.5575260519981384 2023-01-23 14:44:27.402419: step: 2678/1545, loss: 0.18271096050739288 2023-01-23 14:44:28.262341: step: 2680/1545, loss: 0.01612969860434532 2023-01-23 14:44:29.148800: step: 2682/1545, loss: 0.023301029577851295 2023-01-23 14:44:29.971219: step: 2684/1545, loss: 0.01963278278708458 2023-01-23 14:44:30.839573: step: 2686/1545, loss: 0.49378660321235657 2023-01-23 14:44:31.721374: step: 2688/1545, loss: 0.06400588154792786 2023-01-23 14:44:32.617911: step: 2690/1545, loss: 0.144275963306427 2023-01-23 14:44:33.471375: step: 2692/1545, loss: 0.014985760673880577 2023-01-23 14:44:34.332935: step: 2694/1545, loss: 0.04709203168749809 2023-01-23 14:44:35.210996: step: 2696/1545, loss: 0.010510506108403206 2023-01-23 14:44:36.107188: step: 2698/1545, loss: 0.34341543912887573 2023-01-23 14:44:36.974497: step: 2700/1545, loss: 0.017831293866038322 2023-01-23 14:44:37.858140: step: 2702/1545, loss: 0.008495436049997807 2023-01-23 14:44:38.771520: step: 2704/1545, loss: 0.09838171303272247 2023-01-23 14:44:39.638590: step: 2706/1545, loss: 0.14001993834972382 2023-01-23 14:44:40.481206: step: 2708/1545, loss: 0.07102596759796143 2023-01-23 14:44:41.430615: step: 2710/1545, loss: 0.20387400686740875 2023-01-23 14:44:42.315669: step: 2712/1545, loss: 0.11646255850791931 2023-01-23 14:44:43.197509: step: 2714/1545, loss: 0.010708490386605263 2023-01-23 14:44:44.048106: step: 2716/1545, loss: 0.016586080193519592 2023-01-23 14:44:44.957932: step: 2718/1545, loss: 0.030103392899036407 2023-01-23 14:44:45.820045: step: 2720/1545, loss: 0.2906411588191986 2023-01-23 14:44:46.749127: step: 2722/1545, loss: 0.2088840901851654 2023-01-23 14:44:47.597242: step: 2724/1545, loss: 0.12255419045686722 2023-01-23 14:44:48.457733: step: 2726/1545, loss: 0.014591014944016933 2023-01-23 14:44:49.364075: step: 2728/1545, loss: 0.20100824534893036 2023-01-23 14:44:50.225984: step: 2730/1545, loss: 0.0014674494741484523 2023-01-23 14:44:51.107023: step: 2732/1545, loss: 0.02004680596292019 2023-01-23 14:44:52.040458: step: 2734/1545, loss: 0.004287246614694595 2023-01-23 14:44:52.972464: step: 2736/1545, loss: 0.008142976090312004 2023-01-23 14:44:53.831269: step: 2738/1545, loss: 0.0005385722615756094 2023-01-23 14:44:54.743968: step: 2740/1545, loss: 0.09428136795759201 2023-01-23 14:44:55.627417: step: 2742/1545, loss: 0.03948814421892166 2023-01-23 14:44:56.508744: step: 2744/1545, loss: 0.4040282964706421 2023-01-23 14:44:57.397700: step: 2746/1545, loss: 0.21679909527301788 2023-01-23 14:44:58.280654: step: 2748/1545, loss: 0.08257405459880829 2023-01-23 14:44:59.159881: step: 2750/1545, loss: 0.05021921172738075 2023-01-23 14:45:00.034108: step: 2752/1545, loss: 0.011967610567808151 2023-01-23 14:45:00.915312: step: 2754/1545, loss: 0.01510712318122387 2023-01-23 14:45:01.752661: step: 2756/1545, loss: 0.12003935873508453 2023-01-23 14:45:02.649217: step: 2758/1545, loss: 0.000627937144599855 2023-01-23 14:45:03.561534: step: 2760/1545, loss: 0.320502370595932 2023-01-23 14:45:04.430404: step: 2762/1545, loss: 0.012002289295196533 2023-01-23 14:45:05.318529: step: 2764/1545, loss: 0.15219974517822266 2023-01-23 14:45:06.240031: step: 2766/1545, loss: 0.02259693294763565 2023-01-23 14:45:07.100010: step: 2768/1545, loss: 0.0041678790003061295 2023-01-23 14:45:07.947968: step: 2770/1545, loss: 0.09528093785047531 2023-01-23 14:45:08.857815: step: 2772/1545, loss: 0.019990338012576103 2023-01-23 14:45:09.781615: step: 2774/1545, loss: 0.002482557436451316 2023-01-23 14:45:10.674309: step: 2776/1545, loss: 0.033407680690288544 2023-01-23 14:45:11.596833: step: 2778/1545, loss: 0.0736980140209198 2023-01-23 14:45:12.472279: step: 2780/1545, loss: 0.013406728394329548 2023-01-23 14:45:13.330234: step: 2782/1545, loss: 0.037554994225502014 2023-01-23 14:45:14.214860: step: 2784/1545, loss: 0.012582230381667614 2023-01-23 14:45:15.127865: step: 2786/1545, loss: 0.16096772253513336 2023-01-23 14:45:16.011044: step: 2788/1545, loss: 0.0011036824434995651 2023-01-23 14:45:16.892165: step: 2790/1545, loss: 0.02840348333120346 2023-01-23 14:45:17.803869: step: 2792/1545, loss: 0.07080774009227753 2023-01-23 14:45:18.727288: step: 2794/1545, loss: 0.043985843658447266 2023-01-23 14:45:19.677516: step: 2796/1545, loss: 0.012913967482745647 2023-01-23 14:45:20.570072: step: 2798/1545, loss: 0.07107841968536377 2023-01-23 14:45:21.503476: step: 2800/1545, loss: 0.13919572532176971 2023-01-23 14:45:22.377897: step: 2802/1545, loss: 0.056828148663043976 2023-01-23 14:45:23.288688: step: 2804/1545, loss: 0.000781784881837666 2023-01-23 14:45:24.158580: step: 2806/1545, loss: 0.006497077643871307 2023-01-23 14:45:25.031774: step: 2808/1545, loss: 0.0020851597655564547 2023-01-23 14:45:25.928356: step: 2810/1545, loss: 0.08064789324998856 2023-01-23 14:45:26.769587: step: 2812/1545, loss: 0.12207832932472229 2023-01-23 14:45:27.654737: step: 2814/1545, loss: 0.11516647040843964 2023-01-23 14:45:28.563723: step: 2816/1545, loss: 0.7404306530952454 2023-01-23 14:45:29.464022: step: 2818/1545, loss: 0.04959449544548988 2023-01-23 14:45:30.400410: step: 2820/1545, loss: 0.19014550745487213 2023-01-23 14:45:31.346020: step: 2822/1545, loss: 0.07923470437526703 2023-01-23 14:45:32.246245: step: 2824/1545, loss: 0.24931545555591583 2023-01-23 14:45:33.141235: step: 2826/1545, loss: 0.017384489998221397 2023-01-23 14:45:34.056959: step: 2828/1545, loss: 0.2493407428264618 2023-01-23 14:45:34.925942: step: 2830/1545, loss: 0.07717470824718475 2023-01-23 14:45:35.807297: step: 2832/1545, loss: 0.06184893101453781 2023-01-23 14:45:36.694708: step: 2834/1545, loss: 0.3423140347003937 2023-01-23 14:45:37.594111: step: 2836/1545, loss: 0.014869735576212406 2023-01-23 14:45:38.573956: step: 2838/1545, loss: 0.04906666278839111 2023-01-23 14:45:39.425007: step: 2840/1545, loss: 0.2247815579175949 2023-01-23 14:45:40.301791: step: 2842/1545, loss: 0.07080620527267456 2023-01-23 14:45:41.197395: step: 2844/1545, loss: 0.008515916764736176 2023-01-23 14:45:42.105643: step: 2846/1545, loss: 0.008738352917134762 2023-01-23 14:45:42.963145: step: 2848/1545, loss: 0.0059843482449650764 2023-01-23 14:45:43.793775: step: 2850/1545, loss: 0.0163161288946867 2023-01-23 14:45:44.673767: step: 2852/1545, loss: 0.018923016265034676 2023-01-23 14:45:45.523996: step: 2854/1545, loss: 0.0787544995546341 2023-01-23 14:45:46.374875: step: 2856/1545, loss: 0.11503524333238602 2023-01-23 14:45:47.224334: step: 2858/1545, loss: 0.02217349037528038 2023-01-23 14:45:48.077036: step: 2860/1545, loss: 0.13642358779907227 2023-01-23 14:45:48.976191: step: 2862/1545, loss: 0.05467817932367325 2023-01-23 14:45:49.838499: step: 2864/1545, loss: 0.10790935903787613 2023-01-23 14:45:50.692679: step: 2866/1545, loss: 0.039518412202596664 2023-01-23 14:45:51.554612: step: 2868/1545, loss: 0.013486489653587341 2023-01-23 14:45:52.450739: step: 2870/1545, loss: 0.0015555869322270155 2023-01-23 14:45:53.380447: step: 2872/1545, loss: 0.019648991525173187 2023-01-23 14:45:54.247616: step: 2874/1545, loss: 0.11956055462360382 2023-01-23 14:45:55.170916: step: 2876/1545, loss: 0.010175000876188278 2023-01-23 14:45:56.014483: step: 2878/1545, loss: 0.20168420672416687 2023-01-23 14:45:56.954258: step: 2880/1545, loss: 0.024852601811289787 2023-01-23 14:45:57.792535: step: 2882/1545, loss: 0.017389200627803802 2023-01-23 14:45:58.649619: step: 2884/1545, loss: 0.00161131436470896 2023-01-23 14:45:59.618120: step: 2886/1545, loss: 0.3075144588947296 2023-01-23 14:46:00.532589: step: 2888/1545, loss: 8.643257024232298e-05 2023-01-23 14:46:01.396344: step: 2890/1545, loss: 0.34838569164276123 2023-01-23 14:46:02.262712: step: 2892/1545, loss: 0.07354461401700974 2023-01-23 14:46:03.136342: step: 2894/1545, loss: 0.007080636918544769 2023-01-23 14:46:04.106886: step: 2896/1545, loss: 0.019161876291036606 2023-01-23 14:46:04.978563: step: 2898/1545, loss: 0.04515599459409714 2023-01-23 14:46:05.832395: step: 2900/1545, loss: 0.015063419006764889 2023-01-23 14:46:06.761094: step: 2902/1545, loss: 0.002361958846449852 2023-01-23 14:46:07.607669: step: 2904/1545, loss: 0.0025339354760944843 2023-01-23 14:46:08.497606: step: 2906/1545, loss: 0.051247868686914444 2023-01-23 14:46:09.345632: step: 2908/1545, loss: 0.13289174437522888 2023-01-23 14:46:10.275803: step: 2910/1545, loss: 0.4968729615211487 2023-01-23 14:46:11.147615: step: 2912/1545, loss: 0.051387153565883636 2023-01-23 14:46:12.087782: step: 2914/1545, loss: 0.1361885368824005 2023-01-23 14:46:12.970118: step: 2916/1545, loss: 0.06842251121997833 2023-01-23 14:46:13.839101: step: 2918/1545, loss: 0.0004596052167471498 2023-01-23 14:46:14.707267: step: 2920/1545, loss: 0.014305760152637959 2023-01-23 14:46:15.555541: step: 2922/1545, loss: 0.05164784938097 2023-01-23 14:46:16.456284: step: 2924/1545, loss: 0.0022663618437945843 2023-01-23 14:46:17.340929: step: 2926/1545, loss: 0.11916462332010269 2023-01-23 14:46:18.169136: step: 2928/1545, loss: 0.007008714601397514 2023-01-23 14:46:19.072702: step: 2930/1545, loss: 0.014098375104367733 2023-01-23 14:46:19.988628: step: 2932/1545, loss: 0.07531064748764038 2023-01-23 14:46:20.841242: step: 2934/1545, loss: 0.0002807191922329366 2023-01-23 14:46:21.746179: step: 2936/1545, loss: 0.02279948815703392 2023-01-23 14:46:22.682919: step: 2938/1545, loss: 0.03408820927143097 2023-01-23 14:46:23.562691: step: 2940/1545, loss: 0.05926471948623657 2023-01-23 14:46:24.440715: step: 2942/1545, loss: 0.32273879647254944 2023-01-23 14:46:25.336412: step: 2944/1545, loss: 0.009813639335334301 2023-01-23 14:46:26.166623: step: 2946/1545, loss: 0.00386816100217402 2023-01-23 14:46:27.015855: step: 2948/1545, loss: 0.07417711615562439 2023-01-23 14:46:27.879345: step: 2950/1545, loss: 0.017576320096850395 2023-01-23 14:46:28.776927: step: 2952/1545, loss: 0.0007531469454988837 2023-01-23 14:46:29.697588: step: 2954/1545, loss: 0.012270083650946617 2023-01-23 14:46:30.583373: step: 2956/1545, loss: 0.019128592684864998 2023-01-23 14:46:31.500486: step: 2958/1545, loss: 0.3500586748123169 2023-01-23 14:46:32.404719: step: 2960/1545, loss: 0.00412548566237092 2023-01-23 14:46:33.272630: step: 2962/1545, loss: 0.19045409560203552 2023-01-23 14:46:34.119198: step: 2964/1545, loss: 0.000878368504345417 2023-01-23 14:46:35.048959: step: 2966/1545, loss: 0.010647565126419067 2023-01-23 14:46:35.945517: step: 2968/1545, loss: 0.005625964142382145 2023-01-23 14:46:36.790627: step: 2970/1545, loss: 0.12700818479061127 2023-01-23 14:46:37.652124: step: 2972/1545, loss: 0.05900897458195686 2023-01-23 14:46:38.533749: step: 2974/1545, loss: 0.0043504005298018456 2023-01-23 14:46:39.506624: step: 2976/1545, loss: 0.005659129470586777 2023-01-23 14:46:40.386042: step: 2978/1545, loss: 0.42487475275993347 2023-01-23 14:46:41.232994: step: 2980/1545, loss: 0.0018534925766289234 2023-01-23 14:46:42.121205: step: 2982/1545, loss: 0.003433812875300646 2023-01-23 14:46:43.020515: step: 2984/1545, loss: 0.05949854478240013 2023-01-23 14:46:43.931801: step: 2986/1545, loss: 0.0458533801138401 2023-01-23 14:46:44.803238: step: 2988/1545, loss: 0.002078485442325473 2023-01-23 14:46:45.701555: step: 2990/1545, loss: 0.004307553172111511 2023-01-23 14:46:46.548839: step: 2992/1545, loss: 0.06057199463248253 2023-01-23 14:46:47.398328: step: 2994/1545, loss: 0.0214096587151289 2023-01-23 14:46:48.294709: step: 2996/1545, loss: 0.0028905849903821945 2023-01-23 14:46:49.226540: step: 2998/1545, loss: 0.3856358528137207 2023-01-23 14:46:50.184334: step: 3000/1545, loss: 0.04463690519332886 2023-01-23 14:46:51.063900: step: 3002/1545, loss: 0.2832963466644287 2023-01-23 14:46:51.973828: step: 3004/1545, loss: 0.04824987053871155 2023-01-23 14:46:52.861722: step: 3006/1545, loss: 0.013011150062084198 2023-01-23 14:46:53.744411: step: 3008/1545, loss: 0.0020379051566123962 2023-01-23 14:46:54.640149: step: 3010/1545, loss: 0.030679304152727127 2023-01-23 14:46:55.517641: step: 3012/1545, loss: 0.3561737835407257 2023-01-23 14:46:56.444969: step: 3014/1545, loss: 0.005893230438232422 2023-01-23 14:46:57.289732: step: 3016/1545, loss: 0.041247352957725525 2023-01-23 14:46:58.137644: step: 3018/1545, loss: 0.00475173769518733 2023-01-23 14:46:59.015009: step: 3020/1545, loss: 0.1232825517654419 2023-01-23 14:46:59.911429: step: 3022/1545, loss: 0.008742764592170715 2023-01-23 14:47:00.806021: step: 3024/1545, loss: 0.08262743800878525 2023-01-23 14:47:01.699732: step: 3026/1545, loss: 0.12194013595581055 2023-01-23 14:47:02.603113: step: 3028/1545, loss: 0.20239625871181488 2023-01-23 14:47:03.483529: step: 3030/1545, loss: 0.023789212107658386 2023-01-23 14:47:04.347065: step: 3032/1545, loss: 0.17996542155742645 2023-01-23 14:47:05.258032: step: 3034/1545, loss: 0.1504231095314026 2023-01-23 14:47:06.142718: step: 3036/1545, loss: 0.002753034234046936 2023-01-23 14:47:07.023862: step: 3038/1545, loss: 0.1223793625831604 2023-01-23 14:47:07.938486: step: 3040/1545, loss: 0.12336526811122894 2023-01-23 14:47:08.818222: step: 3042/1545, loss: 0.030282748863101006 2023-01-23 14:47:09.713854: step: 3044/1545, loss: 0.08220762759447098 2023-01-23 14:47:10.560308: step: 3046/1545, loss: 0.03954986482858658 2023-01-23 14:47:11.462051: step: 3048/1545, loss: 0.005520950071513653 2023-01-23 14:47:12.329336: step: 3050/1545, loss: 0.0056642452254891396 2023-01-23 14:47:13.213813: step: 3052/1545, loss: 0.16783717274665833 2023-01-23 14:47:14.191455: step: 3054/1545, loss: 0.020639579743146896 2023-01-23 14:47:15.068133: step: 3056/1545, loss: 0.1001044511795044 2023-01-23 14:47:15.919277: step: 3058/1545, loss: 0.002344417152926326 2023-01-23 14:47:16.805931: step: 3060/1545, loss: 0.03986622393131256 2023-01-23 14:47:17.775220: step: 3062/1545, loss: 0.08516745269298553 2023-01-23 14:47:18.654013: step: 3064/1545, loss: 0.04897426813840866 2023-01-23 14:47:19.506723: step: 3066/1545, loss: 0.01071308832615614 2023-01-23 14:47:20.389186: step: 3068/1545, loss: 0.15182910859584808 2023-01-23 14:47:21.291473: step: 3070/1545, loss: 0.0004245795716997236 2023-01-23 14:47:22.145893: step: 3072/1545, loss: 0.0032694563269615173 2023-01-23 14:47:23.012933: step: 3074/1545, loss: 0.21393132209777832 2023-01-23 14:47:23.944108: step: 3076/1545, loss: 0.2332373708486557 2023-01-23 14:47:24.839161: step: 3078/1545, loss: 0.24594378471374512 2023-01-23 14:47:25.730269: step: 3080/1545, loss: 0.0771055668592453 2023-01-23 14:47:26.626182: step: 3082/1545, loss: 0.03409075364470482 2023-01-23 14:47:27.524634: step: 3084/1545, loss: 0.2519146800041199 2023-01-23 14:47:28.375914: step: 3086/1545, loss: 0.13041196763515472 2023-01-23 14:47:29.234861: step: 3088/1545, loss: 0.07097309827804565 2023-01-23 14:47:30.134544: step: 3090/1545, loss: 0.05127254128456116 ================================================== Loss: 0.095 -------------------- Dev Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6717678270879244, 'r': 0.6642255236400809, 'f1': 0.6679753854596523}, 'combined': 0.4413122750458854, 'epoch': 20} Test Chinese: {'event': {'p': 0.6414087513340448, 'r': 0.768542199488491, 'f1': 0.6992437463641652}, 'argument': {'p': 0.7142472009963787, 'r': 0.7035990202475795, 'f1': 0.7088831261188785}, 'combined': 0.4956820928417056, 'epoch': 20} Dev Korean: {'event': {'p': 0.6050328227571116, 'r': 0.7363515312916112, 'f1': 0.6642642642642642}, 'argument': {'p': 0.6764248869158849, 'r': 0.6647361022434091, 'f1': 0.6705295582311311}, 'combined': 0.44540882366584444, 'epoch': 20} Test Korean: {'event': {'p': 0.6333333333333333, 'r': 0.7653452685421995, 'f1': 0.6931094383323683}, 'argument': {'p': 0.7105687610691339, 'r': 0.7005109782996015, 'f1': 0.7055040251493577}, 'combined': 0.48899149861249636, 'epoch': 20} Dev Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6774217798792312, 'r': 0.6686933675400573, 'f1': 0.6730292755428386}, 'combined': 0.44259197406948414, 'epoch': 20} Test Russian: {'event': {'p': 0.6283009466865969, 'r': 0.8062659846547314, 'f1': 0.7062447493699243}, 'argument': {'p': 0.7173603528297395, 'r': 0.7103748213040566, 'f1': 0.7138504978855218}, 'combined': 0.5041531659667561, 'epoch': 20} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.657937869258624, 'r': 0.5763753234827614, 'f1': 0.6144617986027677}, 'combined': 0.4282612535716261, 'epoch': 20} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.7246031746031747, 'r': 0.4592555331991952, 'f1': 0.5621921182266011}, 'combined': 0.3452056866303691, 'epoch': 20} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.6398969860548809, 'r': 0.5713365946918579, 'f1': 0.6036764019385669}, 'combined': 0.3362248314594549, 'epoch': 20} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.665609309737802, 'r': 0.6721299736613826, 'f1': 0.6688537495677951}, 'combined': 0.44590249971186335, 'epoch': 19} Test for Korean: {'event': {'p': 0.6312169312169312, 'r': 0.7627877237851662, 'f1': 0.6907932831499711}, 'argument': {'p': 0.7096480242524722, 'r': 0.7004141808446711, 'f1': 0.7050008684696171}, 'combined': 0.48700986455370776, 'epoch': 19} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6713836477987422, 'r': 0.48744292237442927, 'f1': 0.5648148148148148}, 'combined': 0.346816114359974, 'epoch': 19} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 21 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 14:52:45.107308: step: 2/1545, loss: 0.003270023735240102 2023-01-23 14:52:46.034079: step: 4/1545, loss: 0.07364150881767273 2023-01-23 14:52:46.944652: step: 6/1545, loss: 0.19674409925937653 2023-01-23 14:52:47.890394: step: 8/1545, loss: 0.029025115072727203 2023-01-23 14:52:48.745526: step: 10/1545, loss: 0.06314601749181747 2023-01-23 14:52:49.612099: step: 12/1545, loss: 0.001132915960624814 2023-01-23 14:52:50.458703: step: 14/1545, loss: 0.03699689358472824 2023-01-23 14:52:51.365181: step: 16/1545, loss: 0.02959708496928215 2023-01-23 14:52:52.267575: step: 18/1545, loss: 0.005682586692273617 2023-01-23 14:52:53.188183: step: 20/1545, loss: 0.0339474231004715 2023-01-23 14:52:54.063865: step: 22/1545, loss: 0.0005634506233036518 2023-01-23 14:52:54.954441: step: 24/1545, loss: 0.010832728818058968 2023-01-23 14:52:55.898697: step: 26/1545, loss: 0.001377591979689896 2023-01-23 14:52:56.804107: step: 28/1545, loss: 0.1476602405309677 2023-01-23 14:52:57.688269: step: 30/1545, loss: 0.0016838273731991649 2023-01-23 14:52:58.563033: step: 32/1545, loss: 0.03125499561429024 2023-01-23 14:52:59.418131: step: 34/1545, loss: 0.0002685737272258848 2023-01-23 14:53:00.348999: step: 36/1545, loss: 0.010015489533543587 2023-01-23 14:53:01.253545: step: 38/1545, loss: 0.0009443331509828568 2023-01-23 14:53:02.279091: step: 40/1545, loss: 0.03944011777639389 2023-01-23 14:53:03.171253: step: 42/1545, loss: 0.0035830989945679903 2023-01-23 14:53:04.041306: step: 44/1545, loss: 0.16352210938930511 2023-01-23 14:53:04.899362: step: 46/1545, loss: 0.006639852188527584 2023-01-23 14:53:05.782309: step: 48/1545, loss: 0.00964402686804533 2023-01-23 14:53:06.673021: step: 50/1545, loss: 0.018643870949745178 2023-01-23 14:53:07.627294: step: 52/1545, loss: 0.09818604588508606 2023-01-23 14:53:08.521935: step: 54/1545, loss: 0.0046870824880898 2023-01-23 14:53:09.403993: step: 56/1545, loss: 0.08008045703172684 2023-01-23 14:53:10.264506: step: 58/1545, loss: 0.14184542000293732 2023-01-23 14:53:11.216555: step: 60/1545, loss: 0.009709381498396397 2023-01-23 14:53:12.058086: step: 62/1545, loss: 0.4309540092945099 2023-01-23 14:53:12.868917: step: 64/1545, loss: 0.0005005260463804007 2023-01-23 14:53:13.817494: step: 66/1545, loss: 0.16233114898204803 2023-01-23 14:53:14.799377: step: 68/1545, loss: 0.11427546292543411 2023-01-23 14:53:15.695492: step: 70/1545, loss: 0.004885630216449499 2023-01-23 14:53:16.579565: step: 72/1545, loss: 0.12414099276065826 2023-01-23 14:53:17.485147: step: 74/1545, loss: 0.0021948665380477905 2023-01-23 14:53:18.368925: step: 76/1545, loss: 0.03852659836411476 2023-01-23 14:53:19.231046: step: 78/1545, loss: 0.05606004223227501 2023-01-23 14:53:20.107155: step: 80/1545, loss: 0.07358238846063614 2023-01-23 14:53:20.985316: step: 82/1545, loss: 0.009554626420140266 2023-01-23 14:53:21.845564: step: 84/1545, loss: 0.0022974861785769463 2023-01-23 14:53:22.730466: step: 86/1545, loss: 0.07055795937776566 2023-01-23 14:53:23.608744: step: 88/1545, loss: 0.013766634277999401 2023-01-23 14:53:24.496806: step: 90/1545, loss: 0.1970650851726532 2023-01-23 14:53:25.382426: step: 92/1545, loss: 0.19274358451366425 2023-01-23 14:53:26.249927: step: 94/1545, loss: 0.006305925082415342 2023-01-23 14:53:27.136971: step: 96/1545, loss: 0.01563594862818718 2023-01-23 14:53:27.993129: step: 98/1545, loss: 0.0003826770407613367 2023-01-23 14:53:28.861790: step: 100/1545, loss: 0.010796749964356422 2023-01-23 14:53:29.738038: step: 102/1545, loss: 0.018959440290927887 2023-01-23 14:53:30.621662: step: 104/1545, loss: 0.011819703504443169 2023-01-23 14:53:31.486358: step: 106/1545, loss: 0.10846946388483047 2023-01-23 14:53:32.353789: step: 108/1545, loss: 0.07117055356502533 2023-01-23 14:53:33.221637: step: 110/1545, loss: 0.040999386459589005 2023-01-23 14:53:34.096081: step: 112/1545, loss: 0.17205549776554108 2023-01-23 14:53:34.982952: step: 114/1545, loss: 0.004448389168828726 2023-01-23 14:53:35.848038: step: 116/1545, loss: 0.0013591337483376265 2023-01-23 14:53:36.807273: step: 118/1545, loss: 0.010159553028643131 2023-01-23 14:53:37.747699: step: 120/1545, loss: 0.04821529984474182 2023-01-23 14:53:38.632657: step: 122/1545, loss: 0.019901635125279427 2023-01-23 14:53:39.588516: step: 124/1545, loss: 0.07602404057979584 2023-01-23 14:53:40.491028: step: 126/1545, loss: 0.0035240885335952044 2023-01-23 14:53:41.401762: step: 128/1545, loss: 0.4615227282047272 2023-01-23 14:53:42.330977: step: 130/1545, loss: 0.034518126398324966 2023-01-23 14:53:43.211611: step: 132/1545, loss: 0.17128726840019226 2023-01-23 14:53:44.081178: step: 134/1545, loss: 0.004368586931377649 2023-01-23 14:53:44.934804: step: 136/1545, loss: 0.0006643709493800998 2023-01-23 14:53:45.805118: step: 138/1545, loss: 0.007984568364918232 2023-01-23 14:53:46.664169: step: 140/1545, loss: 0.0022180923260748386 2023-01-23 14:53:47.555931: step: 142/1545, loss: 0.01861342042684555 2023-01-23 14:53:48.430584: step: 144/1545, loss: 0.08386939764022827 2023-01-23 14:53:49.297051: step: 146/1545, loss: 0.031048214063048363 2023-01-23 14:53:50.166533: step: 148/1545, loss: 0.14336910843849182 2023-01-23 14:53:51.052222: step: 150/1545, loss: 0.025477729737758636 2023-01-23 14:53:51.975446: step: 152/1545, loss: 0.026033364236354828 2023-01-23 14:53:52.876333: step: 154/1545, loss: 0.013649322092533112 2023-01-23 14:53:53.763145: step: 156/1545, loss: 0.031163042411208153 2023-01-23 14:53:54.667905: step: 158/1545, loss: 0.06811497360467911 2023-01-23 14:53:55.560673: step: 160/1545, loss: 0.0012184808729216456 2023-01-23 14:53:56.430858: step: 162/1545, loss: 0.2933127284049988 2023-01-23 14:53:57.294601: step: 164/1545, loss: 0.17756511270999908 2023-01-23 14:53:58.266204: step: 166/1545, loss: 0.13914676010608673 2023-01-23 14:53:59.111346: step: 168/1545, loss: 0.000896553392522037 2023-01-23 14:53:59.995677: step: 170/1545, loss: 0.08891645818948746 2023-01-23 14:54:00.957302: step: 172/1545, loss: 0.004161084070801735 2023-01-23 14:54:01.829194: step: 174/1545, loss: 0.20219625532627106 2023-01-23 14:54:02.709314: step: 176/1545, loss: 0.03465694561600685 2023-01-23 14:54:03.592759: step: 178/1545, loss: 0.0071726273745298386 2023-01-23 14:54:04.470131: step: 180/1545, loss: 0.004773502238094807 2023-01-23 14:54:05.346517: step: 182/1545, loss: 0.02644362859427929 2023-01-23 14:54:06.220067: step: 184/1545, loss: 0.02953200787305832 2023-01-23 14:54:07.121602: step: 186/1545, loss: 0.0001573388435645029 2023-01-23 14:54:08.014439: step: 188/1545, loss: 0.00893794372677803 2023-01-23 14:54:08.934694: step: 190/1545, loss: 0.005139046814292669 2023-01-23 14:54:09.863506: step: 192/1545, loss: 0.004016558174043894 2023-01-23 14:54:10.722876: step: 194/1545, loss: 0.0018010311760008335 2023-01-23 14:54:11.581061: step: 196/1545, loss: 0.00693289702758193 2023-01-23 14:54:12.469086: step: 198/1545, loss: 0.044842787086963654 2023-01-23 14:54:13.349271: step: 200/1545, loss: 0.01478760689496994 2023-01-23 14:54:14.233984: step: 202/1545, loss: 0.012311665341258049 2023-01-23 14:54:15.203043: step: 204/1545, loss: 0.15400995314121246 2023-01-23 14:54:16.096923: step: 206/1545, loss: 0.022073401138186455 2023-01-23 14:54:16.995643: step: 208/1545, loss: 0.3389805257320404 2023-01-23 14:54:17.879709: step: 210/1545, loss: 0.2944008409976959 2023-01-23 14:54:18.732193: step: 212/1545, loss: 0.0027746837586164474 2023-01-23 14:54:19.617134: step: 214/1545, loss: 0.041522152721881866 2023-01-23 14:54:20.490246: step: 216/1545, loss: 0.013486146926879883 2023-01-23 14:54:21.358172: step: 218/1545, loss: 0.0673956573009491 2023-01-23 14:54:22.275086: step: 220/1545, loss: 0.0908462405204773 2023-01-23 14:54:23.198161: step: 222/1545, loss: 0.2192276269197464 2023-01-23 14:54:24.079843: step: 224/1545, loss: 0.00624789809808135 2023-01-23 14:54:24.947895: step: 226/1545, loss: 0.0011296693701297045 2023-01-23 14:54:25.812308: step: 228/1545, loss: 0.10547319799661636 2023-01-23 14:54:26.649785: step: 230/1545, loss: 0.00018565496429800987 2023-01-23 14:54:27.506895: step: 232/1545, loss: 0.004400129429996014 2023-01-23 14:54:28.424509: step: 234/1545, loss: 0.0018382809357717633 2023-01-23 14:54:29.320267: step: 236/1545, loss: 0.23841145634651184 2023-01-23 14:54:30.182784: step: 238/1545, loss: 0.06562285870313644 2023-01-23 14:54:31.044450: step: 240/1545, loss: 0.003927828744053841 2023-01-23 14:54:31.931330: step: 242/1545, loss: 0.11871910095214844 2023-01-23 14:54:32.851601: step: 244/1545, loss: 0.004251477774232626 2023-01-23 14:54:33.715409: step: 246/1545, loss: 0.012519512325525284 2023-01-23 14:54:34.574220: step: 248/1545, loss: 0.22013625502586365 2023-01-23 14:54:35.474897: step: 250/1545, loss: 1.0399656295776367 2023-01-23 14:54:36.329278: step: 252/1545, loss: 0.010236939415335655 2023-01-23 14:54:37.178569: step: 254/1545, loss: 0.01835460402071476 2023-01-23 14:54:38.099843: step: 256/1545, loss: 0.011335567571222782 2023-01-23 14:54:38.962381: step: 258/1545, loss: 0.006882426328957081 2023-01-23 14:54:39.794097: step: 260/1545, loss: 0.005077142734080553 2023-01-23 14:54:40.716314: step: 262/1545, loss: 0.0036140528973191977 2023-01-23 14:54:41.590298: step: 264/1545, loss: 0.4770382046699524 2023-01-23 14:54:42.464445: step: 266/1545, loss: 0.004578742664307356 2023-01-23 14:54:43.311166: step: 268/1545, loss: 0.6509221792221069 2023-01-23 14:54:44.178255: step: 270/1545, loss: 0.0618026964366436 2023-01-23 14:54:45.067408: step: 272/1545, loss: 0.06656884402036667 2023-01-23 14:54:45.939768: step: 274/1545, loss: 0.16287726163864136 2023-01-23 14:54:46.790204: step: 276/1545, loss: 0.39191386103630066 2023-01-23 14:54:47.651365: step: 278/1545, loss: 0.00611236784607172 2023-01-23 14:54:48.589002: step: 280/1545, loss: 0.031971804797649384 2023-01-23 14:54:49.423405: step: 282/1545, loss: 0.0007578405202366412 2023-01-23 14:54:50.317401: step: 284/1545, loss: 0.10333758592605591 2023-01-23 14:54:51.242884: step: 286/1545, loss: 0.13622131943702698 2023-01-23 14:54:52.114822: step: 288/1545, loss: 0.02645527943968773 2023-01-23 14:54:53.001448: step: 290/1545, loss: 0.13134455680847168 2023-01-23 14:54:53.884894: step: 292/1545, loss: 0.2800593078136444 2023-01-23 14:54:54.817040: step: 294/1545, loss: 0.01932157576084137 2023-01-23 14:54:55.665626: step: 296/1545, loss: 0.03989459574222565 2023-01-23 14:54:56.545171: step: 298/1545, loss: 0.004985945764929056 2023-01-23 14:54:57.421393: step: 300/1545, loss: 0.06529039889574051 2023-01-23 14:54:58.260452: step: 302/1545, loss: 0.06300322711467743 2023-01-23 14:54:59.159606: step: 304/1545, loss: 0.03693361207842827 2023-01-23 14:55:00.096998: step: 306/1545, loss: 0.015513930469751358 2023-01-23 14:55:00.977479: step: 308/1545, loss: 0.09543854743242264 2023-01-23 14:55:01.831585: step: 310/1545, loss: 0.9984779357910156 2023-01-23 14:55:02.701151: step: 312/1545, loss: 0.010669856332242489 2023-01-23 14:55:03.568291: step: 314/1545, loss: 0.04273022711277008 2023-01-23 14:55:04.427936: step: 316/1545, loss: 1.6126419305801392 2023-01-23 14:55:05.305967: step: 318/1545, loss: 0.001180134480819106 2023-01-23 14:55:06.155940: step: 320/1545, loss: 2.8581035137176514 2023-01-23 14:55:07.044012: step: 322/1545, loss: 0.005765491630882025 2023-01-23 14:55:07.902053: step: 324/1545, loss: 0.22707071900367737 2023-01-23 14:55:08.766191: step: 326/1545, loss: 0.0062146373093128204 2023-01-23 14:55:09.666806: step: 328/1545, loss: 0.0027452909853309393 2023-01-23 14:55:10.540053: step: 330/1545, loss: 0.003426105948165059 2023-01-23 14:55:11.379018: step: 332/1545, loss: 0.14875443279743195 2023-01-23 14:55:12.265135: step: 334/1545, loss: 0.004557757172733545 2023-01-23 14:55:13.114084: step: 336/1545, loss: 0.0012474411632865667 2023-01-23 14:55:13.968937: step: 338/1545, loss: 0.0024915351532399654 2023-01-23 14:55:14.823524: step: 340/1545, loss: 0.028300996869802475 2023-01-23 14:55:15.674832: step: 342/1545, loss: 0.18070048093795776 2023-01-23 14:55:16.523594: step: 344/1545, loss: 0.01734107919037342 2023-01-23 14:55:17.434072: step: 346/1545, loss: 0.02352030761539936 2023-01-23 14:55:18.295044: step: 348/1545, loss: 0.013143343850970268 2023-01-23 14:55:19.150929: step: 350/1545, loss: 0.001393914339132607 2023-01-23 14:55:20.032114: step: 352/1545, loss: 0.17766264081001282 2023-01-23 14:55:20.894732: step: 354/1545, loss: 0.0418248176574707 2023-01-23 14:55:21.794631: step: 356/1545, loss: 0.08906355500221252 2023-01-23 14:55:22.642308: step: 358/1545, loss: 0.012706841342151165 2023-01-23 14:55:23.492574: step: 360/1545, loss: 0.0015274981269612908 2023-01-23 14:55:24.453212: step: 362/1545, loss: 0.01807899959385395 2023-01-23 14:55:25.317688: step: 364/1545, loss: 0.004847261589020491 2023-01-23 14:55:26.143840: step: 366/1545, loss: 0.0002177720016334206 2023-01-23 14:55:27.014608: step: 368/1545, loss: 0.00298322644084692 2023-01-23 14:55:27.910488: step: 370/1545, loss: 0.007249266840517521 2023-01-23 14:55:28.780916: step: 372/1545, loss: 0.04863981530070305 2023-01-23 14:55:29.683631: step: 374/1545, loss: 0.05908576399087906 2023-01-23 14:55:30.540175: step: 376/1545, loss: 0.0009606926469132304 2023-01-23 14:55:31.394412: step: 378/1545, loss: 0.008386723697185516 2023-01-23 14:55:32.258011: step: 380/1545, loss: 0.8071128129959106 2023-01-23 14:55:33.143910: step: 382/1545, loss: 0.062392883002758026 2023-01-23 14:55:34.051999: step: 384/1545, loss: 0.0008467273437418044 2023-01-23 14:55:34.919176: step: 386/1545, loss: 0.14843326807022095 2023-01-23 14:55:35.765142: step: 388/1545, loss: 0.028913354501128197 2023-01-23 14:55:36.613421: step: 390/1545, loss: 0.00033286536927334964 2023-01-23 14:55:37.465849: step: 392/1545, loss: 0.009075396694242954 2023-01-23 14:55:38.352457: step: 394/1545, loss: 0.00067616265732795 2023-01-23 14:55:39.324272: step: 396/1545, loss: 0.02188444696366787 2023-01-23 14:55:40.212402: step: 398/1545, loss: 0.031009208410978317 2023-01-23 14:55:41.114708: step: 400/1545, loss: 0.08762931823730469 2023-01-23 14:55:42.025561: step: 402/1545, loss: 0.008487323299050331 2023-01-23 14:55:42.838841: step: 404/1545, loss: 0.13116401433944702 2023-01-23 14:55:43.672775: step: 406/1545, loss: 0.0007366669597104192 2023-01-23 14:55:44.541120: step: 408/1545, loss: 0.32444506883621216 2023-01-23 14:55:45.447356: step: 410/1545, loss: 0.023562530055642128 2023-01-23 14:55:46.322910: step: 412/1545, loss: 0.07033558934926987 2023-01-23 14:55:47.201945: step: 414/1545, loss: 0.0021825293079018593 2023-01-23 14:55:48.195257: step: 416/1545, loss: 0.14091402292251587 2023-01-23 14:55:49.058659: step: 418/1545, loss: 0.016904961317777634 2023-01-23 14:55:49.973793: step: 420/1545, loss: 0.060464948415756226 2023-01-23 14:55:50.887954: step: 422/1545, loss: 0.00018309889128431678 2023-01-23 14:55:51.731830: step: 424/1545, loss: 0.18284529447555542 2023-01-23 14:55:52.630631: step: 426/1545, loss: 0.006071812938898802 2023-01-23 14:55:53.481199: step: 428/1545, loss: 0.015360663644969463 2023-01-23 14:55:54.375992: step: 430/1545, loss: 0.008505611680448055 2023-01-23 14:55:55.261690: step: 432/1545, loss: 0.05685865506529808 2023-01-23 14:55:56.174323: step: 434/1545, loss: 0.0608842633664608 2023-01-23 14:55:57.028257: step: 436/1545, loss: 0.05981094390153885 2023-01-23 14:55:57.973513: step: 438/1545, loss: 0.05241728201508522 2023-01-23 14:55:58.874965: step: 440/1545, loss: 0.18557846546173096 2023-01-23 14:55:59.768902: step: 442/1545, loss: 0.03872339054942131 2023-01-23 14:56:00.642335: step: 444/1545, loss: 0.628271758556366 2023-01-23 14:56:01.559955: step: 446/1545, loss: 0.03205427899956703 2023-01-23 14:56:02.445434: step: 448/1545, loss: 0.013101300224661827 2023-01-23 14:56:03.335536: step: 450/1545, loss: 0.060911811888217926 2023-01-23 14:56:04.241878: step: 452/1545, loss: 0.08729790896177292 2023-01-23 14:56:05.120614: step: 454/1545, loss: 0.10752230882644653 2023-01-23 14:56:06.002544: step: 456/1545, loss: 0.02824818715453148 2023-01-23 14:56:06.872819: step: 458/1545, loss: 0.03422841429710388 2023-01-23 14:56:07.793194: step: 460/1545, loss: 0.0006105514476075768 2023-01-23 14:56:08.649803: step: 462/1545, loss: 0.004168020095676184 2023-01-23 14:56:09.543878: step: 464/1545, loss: 0.018415188416838646 2023-01-23 14:56:10.440729: step: 466/1545, loss: 0.0042580789886415005 2023-01-23 14:56:11.366317: step: 468/1545, loss: 0.03581693768501282 2023-01-23 14:56:12.276456: step: 470/1545, loss: 0.1945153921842575 2023-01-23 14:56:13.154334: step: 472/1545, loss: 0.01672372594475746 2023-01-23 14:56:14.028278: step: 474/1545, loss: 0.003978893626481295 2023-01-23 14:56:14.928697: step: 476/1545, loss: 0.15867172181606293 2023-01-23 14:56:15.809408: step: 478/1545, loss: 0.5931485891342163 2023-01-23 14:56:16.693754: step: 480/1545, loss: 0.002231398830190301 2023-01-23 14:56:17.584496: step: 482/1545, loss: 0.024022182449698448 2023-01-23 14:56:18.504031: step: 484/1545, loss: 0.08712368458509445 2023-01-23 14:56:19.399769: step: 486/1545, loss: 0.0758804902434349 2023-01-23 14:56:20.260912: step: 488/1545, loss: 0.043457213789224625 2023-01-23 14:56:21.185212: step: 490/1545, loss: 0.010465091094374657 2023-01-23 14:56:22.103373: step: 492/1545, loss: 0.06001371145248413 2023-01-23 14:56:22.973335: step: 494/1545, loss: 0.001844835001975298 2023-01-23 14:56:23.868072: step: 496/1545, loss: 0.03921625763177872 2023-01-23 14:56:24.774812: step: 498/1545, loss: 0.06544509530067444 2023-01-23 14:56:25.652633: step: 500/1545, loss: 0.0781184732913971 2023-01-23 14:56:26.569116: step: 502/1545, loss: 0.5992614030838013 2023-01-23 14:56:27.486475: step: 504/1545, loss: 0.001203056424856186 2023-01-23 14:56:28.354522: step: 506/1545, loss: 0.042950212955474854 2023-01-23 14:56:29.252159: step: 508/1545, loss: 0.07383763790130615 2023-01-23 14:56:30.158473: step: 510/1545, loss: 0.00042056903475895524 2023-01-23 14:56:31.052983: step: 512/1545, loss: 0.09605240076780319 2023-01-23 14:56:31.977213: step: 514/1545, loss: 0.23386169970035553 2023-01-23 14:56:32.850101: step: 516/1545, loss: 0.14393556118011475 2023-01-23 14:56:33.752837: step: 518/1545, loss: 0.13603757321834564 2023-01-23 14:56:34.653837: step: 520/1545, loss: 0.0045551033690571785 2023-01-23 14:56:35.585337: step: 522/1545, loss: 0.36456239223480225 2023-01-23 14:56:36.453591: step: 524/1545, loss: 0.0008209216757677495 2023-01-23 14:56:37.325558: step: 526/1545, loss: 6.657781341345981e-05 2023-01-23 14:56:38.211059: step: 528/1545, loss: 0.0016898205503821373 2023-01-23 14:56:39.080125: step: 530/1545, loss: 0.01427699625492096 2023-01-23 14:56:39.988930: step: 532/1545, loss: 0.0024389002937823534 2023-01-23 14:56:40.929049: step: 534/1545, loss: 0.01564524509012699 2023-01-23 14:56:41.792408: step: 536/1545, loss: 0.1145521029829979 2023-01-23 14:56:42.698670: step: 538/1545, loss: 0.023921143263578415 2023-01-23 14:56:43.561885: step: 540/1545, loss: 0.008221311494708061 2023-01-23 14:56:44.420861: step: 542/1545, loss: 0.00012027475167997181 2023-01-23 14:56:45.292402: step: 544/1545, loss: 0.03944137692451477 2023-01-23 14:56:46.192930: step: 546/1545, loss: 0.10679911822080612 2023-01-23 14:56:47.069655: step: 548/1545, loss: 0.006745653692632914 2023-01-23 14:56:47.986918: step: 550/1545, loss: 0.05233583226799965 2023-01-23 14:56:48.851491: step: 552/1545, loss: 0.0006435678224079311 2023-01-23 14:56:49.833936: step: 554/1545, loss: 0.0017989904154092073 2023-01-23 14:56:50.692062: step: 556/1545, loss: 0.026029158383607864 2023-01-23 14:56:51.577493: step: 558/1545, loss: 0.016264325007796288 2023-01-23 14:56:52.489182: step: 560/1545, loss: 0.03065347857773304 2023-01-23 14:56:53.405662: step: 562/1545, loss: 0.3330570459365845 2023-01-23 14:56:54.293259: step: 564/1545, loss: 0.036526549607515335 2023-01-23 14:56:55.218709: step: 566/1545, loss: 0.17135021090507507 2023-01-23 14:56:56.093503: step: 568/1545, loss: 0.06111885607242584 2023-01-23 14:56:56.949846: step: 570/1545, loss: 0.41837793588638306 2023-01-23 14:56:57.864389: step: 572/1545, loss: 0.09156075865030289 2023-01-23 14:56:58.717627: step: 574/1545, loss: 0.03648073226213455 2023-01-23 14:56:59.591527: step: 576/1545, loss: 0.15906429290771484 2023-01-23 14:57:00.476762: step: 578/1545, loss: 0.2595019042491913 2023-01-23 14:57:01.351857: step: 580/1545, loss: 0.0024409655015915632 2023-01-23 14:57:02.262240: step: 582/1545, loss: 0.0009599424665793777 2023-01-23 14:57:03.155834: step: 584/1545, loss: 0.1049872487783432 2023-01-23 14:57:04.073367: step: 586/1545, loss: 0.0299896951764822 2023-01-23 14:57:04.951559: step: 588/1545, loss: 0.007150628603994846 2023-01-23 14:57:05.854148: step: 590/1545, loss: 0.2573474049568176 2023-01-23 14:57:06.702365: step: 592/1545, loss: 0.31181609630584717 2023-01-23 14:57:07.572468: step: 594/1545, loss: 0.0054214028641581535 2023-01-23 14:57:08.431926: step: 596/1545, loss: 0.0002562023582868278 2023-01-23 14:57:09.310211: step: 598/1545, loss: 0.03774740919470787 2023-01-23 14:57:10.180893: step: 600/1545, loss: 0.0011903513222932816 2023-01-23 14:57:11.016594: step: 602/1545, loss: 0.00048016212531365454 2023-01-23 14:57:11.854350: step: 604/1545, loss: 0.0009430276695638895 2023-01-23 14:57:12.764780: step: 606/1545, loss: 0.15490689873695374 2023-01-23 14:57:13.628472: step: 608/1545, loss: 0.006144898012280464 2023-01-23 14:57:14.489481: step: 610/1545, loss: 0.4310641586780548 2023-01-23 14:57:15.414461: step: 612/1545, loss: 0.13999399542808533 2023-01-23 14:57:16.321286: step: 614/1545, loss: 0.13523460924625397 2023-01-23 14:57:17.272405: step: 616/1545, loss: 0.016527634114027023 2023-01-23 14:57:18.234031: step: 618/1545, loss: 0.05724141746759415 2023-01-23 14:57:19.099682: step: 620/1545, loss: 0.20508284866809845 2023-01-23 14:57:19.994748: step: 622/1545, loss: 0.2095910906791687 2023-01-23 14:57:20.888316: step: 624/1545, loss: 0.06850741803646088 2023-01-23 14:57:21.753685: step: 626/1545, loss: 0.18666644394397736 2023-01-23 14:57:22.661502: step: 628/1545, loss: 0.00851746927946806 2023-01-23 14:57:23.548507: step: 630/1545, loss: 0.02050699293613434 2023-01-23 14:57:24.437594: step: 632/1545, loss: 0.2299003005027771 2023-01-23 14:57:25.288461: step: 634/1545, loss: 0.007664832286536694 2023-01-23 14:57:26.116452: step: 636/1545, loss: 0.2589382231235504 2023-01-23 14:57:26.979827: step: 638/1545, loss: 0.08433865755796432 2023-01-23 14:57:27.857807: step: 640/1545, loss: 0.004185053054243326 2023-01-23 14:57:28.710922: step: 642/1545, loss: 0.00044794235145673156 2023-01-23 14:57:29.561589: step: 644/1545, loss: 0.32720714807510376 2023-01-23 14:57:30.445482: step: 646/1545, loss: 0.006663275882601738 2023-01-23 14:57:31.328072: step: 648/1545, loss: 0.0006496827118098736 2023-01-23 14:57:32.191964: step: 650/1545, loss: 0.11840692162513733 2023-01-23 14:57:33.040610: step: 652/1545, loss: 0.003343085991218686 2023-01-23 14:57:33.910905: step: 654/1545, loss: 0.13912051916122437 2023-01-23 14:57:34.778018: step: 656/1545, loss: 0.19329938292503357 2023-01-23 14:57:35.689605: step: 658/1545, loss: 0.0006720045348629355 2023-01-23 14:57:36.542631: step: 660/1545, loss: 0.001250330125913024 2023-01-23 14:57:37.451666: step: 662/1545, loss: 0.008401080034673214 2023-01-23 14:57:38.422522: step: 664/1545, loss: 0.04050733521580696 2023-01-23 14:57:39.298310: step: 666/1545, loss: 0.04858149588108063 2023-01-23 14:57:40.163585: step: 668/1545, loss: 0.04220851883292198 2023-01-23 14:57:41.042565: step: 670/1545, loss: 0.0029033562168478966 2023-01-23 14:57:41.912731: step: 672/1545, loss: 0.008285691030323505 2023-01-23 14:57:42.784976: step: 674/1545, loss: 0.07026275247335434 2023-01-23 14:57:43.633148: step: 676/1545, loss: 0.24258722364902496 2023-01-23 14:57:44.496461: step: 678/1545, loss: 0.004900493659079075 2023-01-23 14:57:45.370564: step: 680/1545, loss: 0.191389262676239 2023-01-23 14:57:46.240594: step: 682/1545, loss: 0.011837068945169449 2023-01-23 14:57:47.139977: step: 684/1545, loss: 0.4042576551437378 2023-01-23 14:57:48.068132: step: 686/1545, loss: 0.07383430004119873 2023-01-23 14:57:48.962783: step: 688/1545, loss: 0.01357958186417818 2023-01-23 14:57:49.837986: step: 690/1545, loss: 0.043269719928503036 2023-01-23 14:57:50.665843: step: 692/1545, loss: 0.12506447732448578 2023-01-23 14:57:51.575347: step: 694/1545, loss: 0.0014880034141242504 2023-01-23 14:57:52.435556: step: 696/1545, loss: 0.10423437505960464 2023-01-23 14:57:53.279410: step: 698/1545, loss: 0.01788933202624321 2023-01-23 14:57:54.114398: step: 700/1545, loss: 2.582098960876465 2023-01-23 14:57:54.988144: step: 702/1545, loss: 0.1869758814573288 2023-01-23 14:57:55.867946: step: 704/1545, loss: 0.004885864444077015 2023-01-23 14:57:56.733451: step: 706/1545, loss: 0.002239617984741926 2023-01-23 14:57:57.635561: step: 708/1545, loss: 0.019412729889154434 2023-01-23 14:57:58.555792: step: 710/1545, loss: 0.011325967498123646 2023-01-23 14:57:59.438570: step: 712/1545, loss: 0.14292867481708527 2023-01-23 14:58:00.343800: step: 714/1545, loss: 0.19294948875904083 2023-01-23 14:58:01.220241: step: 716/1545, loss: 0.009565048851072788 2023-01-23 14:58:02.098014: step: 718/1545, loss: 0.0919029489159584 2023-01-23 14:58:02.973377: step: 720/1545, loss: 1.0546486377716064 2023-01-23 14:58:03.853390: step: 722/1545, loss: 0.0038041218649595976 2023-01-23 14:58:04.782917: step: 724/1545, loss: 0.17257119715213776 2023-01-23 14:58:05.663462: step: 726/1545, loss: 0.007746885530650616 2023-01-23 14:58:06.513376: step: 728/1545, loss: 0.0377667061984539 2023-01-23 14:58:07.349522: step: 730/1545, loss: 0.005095663946121931 2023-01-23 14:58:08.273318: step: 732/1545, loss: 0.005916927941143513 2023-01-23 14:58:09.140152: step: 734/1545, loss: 0.00606749951839447 2023-01-23 14:58:10.036521: step: 736/1545, loss: 0.16338969767093658 2023-01-23 14:58:10.926152: step: 738/1545, loss: 0.34232425689697266 2023-01-23 14:58:11.836661: step: 740/1545, loss: 0.04845836013555527 2023-01-23 14:58:12.697591: step: 742/1545, loss: 0.04039720073342323 2023-01-23 14:58:13.561740: step: 744/1545, loss: 0.00504915788769722 2023-01-23 14:58:14.469236: step: 746/1545, loss: 0.12530040740966797 2023-01-23 14:58:15.352222: step: 748/1545, loss: 0.04069581255316734 2023-01-23 14:58:16.232434: step: 750/1545, loss: 0.00046795583330094814 2023-01-23 14:58:17.096532: step: 752/1545, loss: 0.12210635095834732 2023-01-23 14:58:18.037966: step: 754/1545, loss: 0.006394617259502411 2023-01-23 14:58:18.939418: step: 756/1545, loss: 0.007220009807497263 2023-01-23 14:58:19.848753: step: 758/1545, loss: 0.0008315876475535333 2023-01-23 14:58:20.687153: step: 760/1545, loss: 0.0005491159972734749 2023-01-23 14:58:21.577449: step: 762/1545, loss: 0.00633166404440999 2023-01-23 14:58:22.526834: step: 764/1545, loss: 0.0018950540106743574 2023-01-23 14:58:23.411459: step: 766/1545, loss: 0.11470154672861099 2023-01-23 14:58:24.285763: step: 768/1545, loss: 0.022752435877919197 2023-01-23 14:58:25.148060: step: 770/1545, loss: 0.0063944594003260136 2023-01-23 14:58:26.035776: step: 772/1545, loss: 0.08593420684337616 2023-01-23 14:58:26.938838: step: 774/1545, loss: 0.0011259109014645219 2023-01-23 14:58:27.784993: step: 776/1545, loss: 0.0083276042714715 2023-01-23 14:58:28.674049: step: 778/1545, loss: 0.0021026269532740116 2023-01-23 14:58:29.586650: step: 780/1545, loss: 0.05400049686431885 2023-01-23 14:58:30.462125: step: 782/1545, loss: 0.02568136900663376 2023-01-23 14:58:31.402668: step: 784/1545, loss: 0.03142658993601799 2023-01-23 14:58:32.245986: step: 786/1545, loss: 0.3741368055343628 2023-01-23 14:58:33.168739: step: 788/1545, loss: 0.03882985562086105 2023-01-23 14:58:34.048809: step: 790/1545, loss: 0.025269336998462677 2023-01-23 14:58:34.915303: step: 792/1545, loss: 0.002255489584058523 2023-01-23 14:58:35.756186: step: 794/1545, loss: 0.006199497729539871 2023-01-23 14:58:36.597240: step: 796/1545, loss: 0.003138653701171279 2023-01-23 14:58:37.500575: step: 798/1545, loss: 0.017563411965966225 2023-01-23 14:58:38.416211: step: 800/1545, loss: 0.09212395548820496 2023-01-23 14:58:39.316416: step: 802/1545, loss: 0.01579974591732025 2023-01-23 14:58:40.193150: step: 804/1545, loss: 0.02688468247652054 2023-01-23 14:58:41.104845: step: 806/1545, loss: 0.12589982151985168 2023-01-23 14:58:41.971835: step: 808/1545, loss: 0.01608094573020935 2023-01-23 14:58:42.840300: step: 810/1545, loss: 0.15282535552978516 2023-01-23 14:58:43.704267: step: 812/1545, loss: 0.0019509373232722282 2023-01-23 14:58:44.562060: step: 814/1545, loss: 0.14583411812782288 2023-01-23 14:58:45.439824: step: 816/1545, loss: 0.0357854999601841 2023-01-23 14:58:46.354806: step: 818/1545, loss: 0.01990029402077198 2023-01-23 14:58:47.206332: step: 820/1545, loss: 0.18799535930156708 2023-01-23 14:58:48.129312: step: 822/1545, loss: 0.06895293295383453 2023-01-23 14:58:49.029701: step: 824/1545, loss: 0.15276911854743958 2023-01-23 14:58:49.883610: step: 826/1545, loss: 0.007056593894958496 2023-01-23 14:58:50.745693: step: 828/1545, loss: 0.004724366124719381 2023-01-23 14:58:51.605778: step: 830/1545, loss: 0.019955195486545563 2023-01-23 14:58:52.483009: step: 832/1545, loss: 0.0047269295901060104 2023-01-23 14:58:53.374245: step: 834/1545, loss: 0.00012175636948086321 2023-01-23 14:58:54.252879: step: 836/1545, loss: 0.06645216792821884 2023-01-23 14:58:55.133813: step: 838/1545, loss: 0.08422544598579407 2023-01-23 14:58:55.995560: step: 840/1545, loss: 0.0001604160643182695 2023-01-23 14:58:56.875353: step: 842/1545, loss: 0.061262600123882294 2023-01-23 14:58:57.798524: step: 844/1545, loss: 0.00811947975307703 2023-01-23 14:58:58.675350: step: 846/1545, loss: 0.0013071548892185092 2023-01-23 14:58:59.590329: step: 848/1545, loss: 0.00017700048920232803 2023-01-23 14:59:00.467758: step: 850/1545, loss: 0.0012796880910173059 2023-01-23 14:59:01.305473: step: 852/1545, loss: 0.0010154529009014368 2023-01-23 14:59:02.164593: step: 854/1545, loss: 0.012411779724061489 2023-01-23 14:59:03.030735: step: 856/1545, loss: 0.1363818347454071 2023-01-23 14:59:04.015668: step: 858/1545, loss: 0.49653980135917664 2023-01-23 14:59:04.897236: step: 860/1545, loss: 0.02968868985772133 2023-01-23 14:59:05.755391: step: 862/1545, loss: 0.08550338447093964 2023-01-23 14:59:06.649963: step: 864/1545, loss: 0.030040612444281578 2023-01-23 14:59:07.502582: step: 866/1545, loss: 0.003962507471442223 2023-01-23 14:59:08.355910: step: 868/1545, loss: 0.17765507102012634 2023-01-23 14:59:09.203907: step: 870/1545, loss: 0.0011907470179721713 2023-01-23 14:59:10.094422: step: 872/1545, loss: 0.005832569673657417 2023-01-23 14:59:10.973043: step: 874/1545, loss: 0.0012433630181476474 2023-01-23 14:59:11.839902: step: 876/1545, loss: 0.0007325636688619852 2023-01-23 14:59:12.720122: step: 878/1545, loss: 0.2936362624168396 2023-01-23 14:59:13.715467: step: 880/1545, loss: 0.103599414229393 2023-01-23 14:59:14.541514: step: 882/1545, loss: 0.00224169809371233 2023-01-23 14:59:15.390866: step: 884/1545, loss: 0.18174536526203156 2023-01-23 14:59:16.308057: step: 886/1545, loss: 0.10975217819213867 2023-01-23 14:59:17.206984: step: 888/1545, loss: 0.0026369744446128607 2023-01-23 14:59:18.046184: step: 890/1545, loss: 0.0069211493246257305 2023-01-23 14:59:18.939821: step: 892/1545, loss: 0.004694686736911535 2023-01-23 14:59:19.919073: step: 894/1545, loss: 0.04771869257092476 2023-01-23 14:59:20.783772: step: 896/1545, loss: 0.02269771508872509 2023-01-23 14:59:21.619007: step: 898/1545, loss: 0.017800411209464073 2023-01-23 14:59:22.534995: step: 900/1545, loss: 0.09207825362682343 2023-01-23 14:59:23.391533: step: 902/1545, loss: 0.00021365724387578666 2023-01-23 14:59:24.320754: step: 904/1545, loss: 0.003256291151046753 2023-01-23 14:59:25.219021: step: 906/1545, loss: 0.07102388143539429 2023-01-23 14:59:26.126990: step: 908/1545, loss: 0.005945083685219288 2023-01-23 14:59:27.007636: step: 910/1545, loss: 0.025746172294020653 2023-01-23 14:59:27.899426: step: 912/1545, loss: 0.1827223151922226 2023-01-23 14:59:28.773893: step: 914/1545, loss: 0.012352808378636837 2023-01-23 14:59:29.680924: step: 916/1545, loss: 0.13654913008213043 2023-01-23 14:59:30.605889: step: 918/1545, loss: 0.009074305184185505 2023-01-23 14:59:31.588162: step: 920/1545, loss: 0.08722759038209915 2023-01-23 14:59:32.497232: step: 922/1545, loss: 0.002099669072777033 2023-01-23 14:59:33.451964: step: 924/1545, loss: 0.03497728705406189 2023-01-23 14:59:34.336576: step: 926/1545, loss: 0.004093308933079243 2023-01-23 14:59:35.214536: step: 928/1545, loss: 0.0763888731598854 2023-01-23 14:59:36.105613: step: 930/1545, loss: 0.11959550529718399 2023-01-23 14:59:37.026711: step: 932/1545, loss: 0.14950112998485565 2023-01-23 14:59:37.916057: step: 934/1545, loss: 0.002221910748630762 2023-01-23 14:59:38.763235: step: 936/1545, loss: 0.09806566685438156 2023-01-23 14:59:39.635881: step: 938/1545, loss: 0.1653064787387848 2023-01-23 14:59:40.551299: step: 940/1545, loss: 0.028493912890553474 2023-01-23 14:59:41.431721: step: 942/1545, loss: 0.004279710352420807 2023-01-23 14:59:42.348758: step: 944/1545, loss: 0.03986098989844322 2023-01-23 14:59:43.232765: step: 946/1545, loss: 0.15667343139648438 2023-01-23 14:59:44.112202: step: 948/1545, loss: 0.033477723598480225 2023-01-23 14:59:44.968513: step: 950/1545, loss: 0.0006115009891800582 2023-01-23 14:59:45.835381: step: 952/1545, loss: 0.0207202211022377 2023-01-23 14:59:46.734367: step: 954/1545, loss: 0.20302219688892365 2023-01-23 14:59:47.578893: step: 956/1545, loss: 0.0003378025721758604 2023-01-23 14:59:48.501882: step: 958/1545, loss: 0.01583300717175007 2023-01-23 14:59:49.379473: step: 960/1545, loss: 0.22454321384429932 2023-01-23 14:59:50.241105: step: 962/1545, loss: 0.0979803204536438 2023-01-23 14:59:51.116706: step: 964/1545, loss: 0.013529838994145393 2023-01-23 14:59:52.002912: step: 966/1545, loss: 0.042341697961091995 2023-01-23 14:59:52.858922: step: 968/1545, loss: 0.01373273879289627 2023-01-23 14:59:53.724274: step: 970/1545, loss: 2.4136879444122314 2023-01-23 14:59:54.606975: step: 972/1545, loss: 0.0009093637927435338 2023-01-23 14:59:55.491066: step: 974/1545, loss: 0.0862785279750824 2023-01-23 14:59:56.361373: step: 976/1545, loss: 0.0005296308663673699 2023-01-23 14:59:57.264379: step: 978/1545, loss: 0.002551730489358306 2023-01-23 14:59:58.135892: step: 980/1545, loss: 0.006257652770727873 2023-01-23 14:59:59.022900: step: 982/1545, loss: 0.012630898505449295 2023-01-23 14:59:59.905190: step: 984/1545, loss: 0.45727890729904175 2023-01-23 15:00:00.788656: step: 986/1545, loss: 0.0010791827226057649 2023-01-23 15:00:01.713717: step: 988/1545, loss: 0.003409745404496789 2023-01-23 15:00:02.583576: step: 990/1545, loss: 0.005429781042039394 2023-01-23 15:00:03.595738: step: 992/1545, loss: 0.04584786668419838 2023-01-23 15:00:04.494233: step: 994/1545, loss: 0.045745011419057846 2023-01-23 15:00:05.393854: step: 996/1545, loss: 0.1577279269695282 2023-01-23 15:00:06.260441: step: 998/1545, loss: 0.0953867956995964 2023-01-23 15:00:07.112302: step: 1000/1545, loss: 0.0032245665788650513 2023-01-23 15:00:08.057396: step: 1002/1545, loss: 0.03921842947602272 2023-01-23 15:00:08.905932: step: 1004/1545, loss: 0.003714733524248004 2023-01-23 15:00:09.785758: step: 1006/1545, loss: 0.1900419443845749 2023-01-23 15:00:10.683816: step: 1008/1545, loss: 0.45288386940956116 2023-01-23 15:00:11.518675: step: 1010/1545, loss: 0.004324084147810936 2023-01-23 15:00:12.422059: step: 1012/1545, loss: 0.0005482995184138417 2023-01-23 15:00:13.308038: step: 1014/1545, loss: 0.13255815207958221 2023-01-23 15:00:14.190535: step: 1016/1545, loss: 0.008641249500215054 2023-01-23 15:00:15.078698: step: 1018/1545, loss: 0.027743976563215256 2023-01-23 15:00:15.977221: step: 1020/1545, loss: 0.08693475276231766 2023-01-23 15:00:16.843903: step: 1022/1545, loss: 0.01711970940232277 2023-01-23 15:00:17.715159: step: 1024/1545, loss: 0.03286878392100334 2023-01-23 15:00:18.595787: step: 1026/1545, loss: 0.012859964743256569 2023-01-23 15:00:19.468861: step: 1028/1545, loss: 0.010661406442523003 2023-01-23 15:00:20.338557: step: 1030/1545, loss: 0.006343160290271044 2023-01-23 15:00:21.216863: step: 1032/1545, loss: 0.0073922364972531796 2023-01-23 15:00:22.117565: step: 1034/1545, loss: 0.040108442306518555 2023-01-23 15:00:22.997570: step: 1036/1545, loss: 0.0035460249055176973 2023-01-23 15:00:23.894878: step: 1038/1545, loss: 0.0050819190219044685 2023-01-23 15:00:24.760705: step: 1040/1545, loss: 0.12769638001918793 2023-01-23 15:00:25.692639: step: 1042/1545, loss: 0.027049552649259567 2023-01-23 15:00:26.591405: step: 1044/1545, loss: 0.06694331020116806 2023-01-23 15:00:27.470183: step: 1046/1545, loss: 0.17359484732151031 2023-01-23 15:00:28.396353: step: 1048/1545, loss: 0.025354988873004913 2023-01-23 15:00:29.270116: step: 1050/1545, loss: 0.00937742181122303 2023-01-23 15:00:30.150540: step: 1052/1545, loss: 0.019315732643008232 2023-01-23 15:00:31.092286: step: 1054/1545, loss: 0.010004434734582901 2023-01-23 15:00:32.007205: step: 1056/1545, loss: 0.018432749435305595 2023-01-23 15:00:32.879108: step: 1058/1545, loss: 0.002354029566049576 2023-01-23 15:00:33.774794: step: 1060/1545, loss: 0.000297161634080112 2023-01-23 15:00:34.664513: step: 1062/1545, loss: 0.006408835761249065 2023-01-23 15:00:35.513319: step: 1064/1545, loss: 0.0018628097604960203 2023-01-23 15:00:36.419722: step: 1066/1545, loss: 0.0006541747716255486 2023-01-23 15:00:37.265383: step: 1068/1545, loss: 0.33203446865081787 2023-01-23 15:00:38.180013: step: 1070/1545, loss: 0.5817300081253052 2023-01-23 15:00:39.046313: step: 1072/1545, loss: 0.15518999099731445 2023-01-23 15:00:39.960720: step: 1074/1545, loss: 0.0008566882461309433 2023-01-23 15:00:40.871570: step: 1076/1545, loss: 0.3081909418106079 2023-01-23 15:00:41.727485: step: 1078/1545, loss: 0.09133739769458771 2023-01-23 15:00:42.637529: step: 1080/1545, loss: 0.024403713643550873 2023-01-23 15:00:43.526952: step: 1082/1545, loss: 0.1932663768529892 2023-01-23 15:00:44.405206: step: 1084/1545, loss: 0.0006163483485579491 2023-01-23 15:00:45.285370: step: 1086/1545, loss: 0.0005543853621929884 2023-01-23 15:00:46.152437: step: 1088/1545, loss: 0.010618087835609913 2023-01-23 15:00:47.127288: step: 1090/1545, loss: 0.016108693554997444 2023-01-23 15:00:48.016767: step: 1092/1545, loss: 0.00018578357412479818 2023-01-23 15:00:48.889217: step: 1094/1545, loss: 0.00576814915984869 2023-01-23 15:00:49.782657: step: 1096/1545, loss: 0.07203663140535355 2023-01-23 15:00:50.625555: step: 1098/1545, loss: 0.14509083330631256 2023-01-23 15:00:51.562852: step: 1100/1545, loss: 0.011206361465156078 2023-01-23 15:00:52.403614: step: 1102/1545, loss: 0.003964317962527275 2023-01-23 15:00:53.287768: step: 1104/1545, loss: 0.0005280823679640889 2023-01-23 15:00:54.201776: step: 1106/1545, loss: 0.6417808532714844 2023-01-23 15:00:55.106982: step: 1108/1545, loss: 0.15185846388339996 2023-01-23 15:00:56.019421: step: 1110/1545, loss: 0.05280375853180885 2023-01-23 15:00:56.952961: step: 1112/1545, loss: 0.064995177090168 2023-01-23 15:00:57.838606: step: 1114/1545, loss: 0.014495317824184895 2023-01-23 15:00:58.726939: step: 1116/1545, loss: 0.011306154541671276 2023-01-23 15:00:59.608711: step: 1118/1545, loss: 0.006882629357278347 2023-01-23 15:01:00.474017: step: 1120/1545, loss: 0.21029792726039886 2023-01-23 15:01:01.377512: step: 1122/1545, loss: 0.03706042841076851 2023-01-23 15:01:02.249281: step: 1124/1545, loss: 1.7085317373275757 2023-01-23 15:01:03.093077: step: 1126/1545, loss: 0.002307355869561434 2023-01-23 15:01:03.940750: step: 1128/1545, loss: 0.00724331708624959 2023-01-23 15:01:04.852322: step: 1130/1545, loss: 0.12704122066497803 2023-01-23 15:01:05.729388: step: 1132/1545, loss: 0.004889652132987976 2023-01-23 15:01:06.648500: step: 1134/1545, loss: 0.023818476125597954 2023-01-23 15:01:07.530824: step: 1136/1545, loss: 0.21223223209381104 2023-01-23 15:01:08.389939: step: 1138/1545, loss: 0.02565961703658104 2023-01-23 15:01:09.273157: step: 1140/1545, loss: 0.17222756147384644 2023-01-23 15:01:10.173208: step: 1142/1545, loss: 0.07646604627370834 2023-01-23 15:01:11.026266: step: 1144/1545, loss: 0.0892123356461525 2023-01-23 15:01:11.945335: step: 1146/1545, loss: 0.015211655758321285 2023-01-23 15:01:12.792850: step: 1148/1545, loss: 0.004150359891355038 2023-01-23 15:01:13.649897: step: 1150/1545, loss: 0.02895081415772438 2023-01-23 15:01:14.513670: step: 1152/1545, loss: 0.0004990497836843133 2023-01-23 15:01:15.397287: step: 1154/1545, loss: 0.14854000508785248 2023-01-23 15:01:16.247422: step: 1156/1545, loss: 0.020536324009299278 2023-01-23 15:01:17.186879: step: 1158/1545, loss: 0.005050167441368103 2023-01-23 15:01:18.046494: step: 1160/1545, loss: 0.6427631378173828 2023-01-23 15:01:18.894363: step: 1162/1545, loss: 0.17867445945739746 2023-01-23 15:01:19.812229: step: 1164/1545, loss: 0.0012537757866084576 2023-01-23 15:01:20.715085: step: 1166/1545, loss: 0.061713624745607376 2023-01-23 15:01:21.564455: step: 1168/1545, loss: 0.011372925713658333 2023-01-23 15:01:22.380804: step: 1170/1545, loss: 0.0037932966370135546 2023-01-23 15:01:23.265653: step: 1172/1545, loss: 0.040645163506269455 2023-01-23 15:01:24.155966: step: 1174/1545, loss: 0.06807168573141098 2023-01-23 15:01:25.017784: step: 1176/1545, loss: 0.013825778849422932 2023-01-23 15:01:25.949820: step: 1178/1545, loss: 0.07224375009536743 2023-01-23 15:01:26.803375: step: 1180/1545, loss: 0.001921889721415937 2023-01-23 15:01:27.708922: step: 1182/1545, loss: 0.2867554724216461 2023-01-23 15:01:28.586112: step: 1184/1545, loss: 0.010319259017705917 2023-01-23 15:01:29.451123: step: 1186/1545, loss: 0.06827344745397568 2023-01-23 15:01:30.298033: step: 1188/1545, loss: 0.01463155448436737 2023-01-23 15:01:31.209723: step: 1190/1545, loss: 0.06149527430534363 2023-01-23 15:01:32.090879: step: 1192/1545, loss: 0.024415642023086548 2023-01-23 15:01:32.968666: step: 1194/1545, loss: 0.06612098217010498 2023-01-23 15:01:33.932178: step: 1196/1545, loss: 0.0006679632351733744 2023-01-23 15:01:34.767426: step: 1198/1545, loss: 0.009588435292243958 2023-01-23 15:01:35.699581: step: 1200/1545, loss: 0.1710963100194931 2023-01-23 15:01:36.533110: step: 1202/1545, loss: 0.100283183157444 2023-01-23 15:01:37.411394: step: 1204/1545, loss: 0.0010021829511970282 2023-01-23 15:01:38.275860: step: 1206/1545, loss: 0.026681240648031235 2023-01-23 15:01:39.143181: step: 1208/1545, loss: 0.010539996437728405 2023-01-23 15:01:40.002611: step: 1210/1545, loss: 0.002350045368075371 2023-01-23 15:01:40.856797: step: 1212/1545, loss: 0.0008783054072409868 2023-01-23 15:01:41.757585: step: 1214/1545, loss: 0.00021334984921850264 2023-01-23 15:01:42.631226: step: 1216/1545, loss: 0.0019148550927639008 2023-01-23 15:01:43.534191: step: 1218/1545, loss: 0.028960363939404488 2023-01-23 15:01:44.403678: step: 1220/1545, loss: 0.2319459468126297 2023-01-23 15:01:45.269993: step: 1222/1545, loss: 0.002752870786935091 2023-01-23 15:01:46.149046: step: 1224/1545, loss: 0.002706338418647647 2023-01-23 15:01:46.993651: step: 1226/1545, loss: 0.039178334176540375 2023-01-23 15:01:47.942118: step: 1228/1545, loss: 0.18976764380931854 2023-01-23 15:01:48.800381: step: 1230/1545, loss: 0.012954475358128548 2023-01-23 15:01:49.649639: step: 1232/1545, loss: 0.0012929566437378526 2023-01-23 15:01:50.536239: step: 1234/1545, loss: 0.05951213091611862 2023-01-23 15:01:51.407867: step: 1236/1545, loss: 0.05948522686958313 2023-01-23 15:01:52.293812: step: 1238/1545, loss: 0.7118918299674988 2023-01-23 15:01:53.299521: step: 1240/1545, loss: 1.2181662321090698 2023-01-23 15:01:54.174572: step: 1242/1545, loss: 0.0035488379653543234 2023-01-23 15:01:55.096110: step: 1244/1545, loss: 0.030862383544445038 2023-01-23 15:01:55.933032: step: 1246/1545, loss: 0.018706247210502625 2023-01-23 15:01:56.826576: step: 1248/1545, loss: 0.05791131779551506 2023-01-23 15:01:57.729497: step: 1250/1545, loss: 0.0013068479020148516 2023-01-23 15:01:58.630505: step: 1252/1545, loss: 0.023350035771727562 2023-01-23 15:01:59.514800: step: 1254/1545, loss: 0.00018816224473994225 2023-01-23 15:02:00.381710: step: 1256/1545, loss: 0.00022355717374011874 2023-01-23 15:02:01.271144: step: 1258/1545, loss: 0.30495569109916687 2023-01-23 15:02:02.142886: step: 1260/1545, loss: 0.00019131568842567503 2023-01-23 15:02:03.061165: step: 1262/1545, loss: 0.1478811353445053 2023-01-23 15:02:03.911878: step: 1264/1545, loss: 0.3071165084838867 2023-01-23 15:02:04.827797: step: 1266/1545, loss: 0.02183748595416546 2023-01-23 15:02:05.673191: step: 1268/1545, loss: 0.01372713502496481 2023-01-23 15:02:06.594392: step: 1270/1545, loss: 0.1762307733297348 2023-01-23 15:02:07.469561: step: 1272/1545, loss: 0.003981403540819883 2023-01-23 15:02:08.326095: step: 1274/1545, loss: 0.011714310385286808 2023-01-23 15:02:09.180841: step: 1276/1545, loss: 0.011707169003784657 2023-01-23 15:02:10.164797: step: 1278/1545, loss: 0.09576958417892456 2023-01-23 15:02:11.003785: step: 1280/1545, loss: 0.025186728686094284 2023-01-23 15:02:11.880528: step: 1282/1545, loss: 0.0002957644173875451 2023-01-23 15:02:12.801001: step: 1284/1545, loss: 0.015139088965952396 2023-01-23 15:02:13.708684: step: 1286/1545, loss: 0.12054601311683655 2023-01-23 15:02:14.645750: step: 1288/1545, loss: 0.14505493640899658 2023-01-23 15:02:15.524420: step: 1290/1545, loss: 0.6251211762428284 2023-01-23 15:02:16.424836: step: 1292/1545, loss: 1.3574750423431396 2023-01-23 15:02:17.334061: step: 1294/1545, loss: 0.1560838371515274 2023-01-23 15:02:18.201367: step: 1296/1545, loss: 0.007507591973990202 2023-01-23 15:02:19.080098: step: 1298/1545, loss: 0.06114190071821213 2023-01-23 15:02:19.983528: step: 1300/1545, loss: 0.018375400453805923 2023-01-23 15:02:20.831582: step: 1302/1545, loss: 0.007831425406038761 2023-01-23 15:02:21.699927: step: 1304/1545, loss: 0.008679096587002277 2023-01-23 15:02:22.583135: step: 1306/1545, loss: 0.008374212309718132 2023-01-23 15:02:23.482113: step: 1308/1545, loss: 0.048589251935482025 2023-01-23 15:02:24.396629: step: 1310/1545, loss: 0.061721719801425934 2023-01-23 15:02:25.280136: step: 1312/1545, loss: 0.16187171638011932 2023-01-23 15:02:26.200659: step: 1314/1545, loss: 0.008702166378498077 2023-01-23 15:02:27.101090: step: 1316/1545, loss: 0.12979015707969666 2023-01-23 15:02:28.113713: step: 1318/1545, loss: 0.06565451622009277 2023-01-23 15:02:28.989168: step: 1320/1545, loss: 0.0018583090277388692 2023-01-23 15:02:29.883838: step: 1322/1545, loss: 0.002229395555332303 2023-01-23 15:02:30.817989: step: 1324/1545, loss: 0.16957902908325195 2023-01-23 15:02:31.685222: step: 1326/1545, loss: 0.0032655587419867516 2023-01-23 15:02:32.612302: step: 1328/1545, loss: 0.001552531961351633 2023-01-23 15:02:33.611513: step: 1330/1545, loss: 0.0017622399609535933 2023-01-23 15:02:34.529451: step: 1332/1545, loss: 0.13045132160186768 2023-01-23 15:02:35.397659: step: 1334/1545, loss: 0.007668672129511833 2023-01-23 15:02:36.290658: step: 1336/1545, loss: 0.01171038392931223 2023-01-23 15:02:37.179406: step: 1338/1545, loss: 0.002454179571941495 2023-01-23 15:02:38.059240: step: 1340/1545, loss: 0.03245122358202934 2023-01-23 15:02:38.930973: step: 1342/1545, loss: 0.010842571966350079 2023-01-23 15:02:39.841782: step: 1344/1545, loss: 0.01673290878534317 2023-01-23 15:02:40.683419: step: 1346/1545, loss: 0.0005628366488963366 2023-01-23 15:02:41.594731: step: 1348/1545, loss: 0.02593262493610382 2023-01-23 15:02:42.477330: step: 1350/1545, loss: 0.018313398584723473 2023-01-23 15:02:43.403549: step: 1352/1545, loss: 0.009914646856486797 2023-01-23 15:02:44.256421: step: 1354/1545, loss: 0.003267725231125951 2023-01-23 15:02:45.139146: step: 1356/1545, loss: 0.1012595146894455 2023-01-23 15:02:46.023904: step: 1358/1545, loss: 0.04068287834525108 2023-01-23 15:02:46.885063: step: 1360/1545, loss: 0.23453794419765472 2023-01-23 15:02:47.806399: step: 1362/1545, loss: 0.0027638229075819254 2023-01-23 15:02:48.707263: step: 1364/1545, loss: 0.2288401871919632 2023-01-23 15:02:49.575040: step: 1366/1545, loss: 0.20846892893314362 2023-01-23 15:02:50.464040: step: 1368/1545, loss: 0.12824256718158722 2023-01-23 15:02:51.366490: step: 1370/1545, loss: 0.0011930791661143303 2023-01-23 15:02:52.255643: step: 1372/1545, loss: 0.11800259351730347 2023-01-23 15:02:53.164713: step: 1374/1545, loss: 0.919257640838623 2023-01-23 15:02:54.025271: step: 1376/1545, loss: 0.08953333646059036 2023-01-23 15:02:54.904750: step: 1378/1545, loss: 0.006223312579095364 2023-01-23 15:02:55.762558: step: 1380/1545, loss: 0.018063385039567947 2023-01-23 15:02:56.683007: step: 1382/1545, loss: 0.0013311144430190325 2023-01-23 15:02:57.551882: step: 1384/1545, loss: 0.0011384445242583752 2023-01-23 15:02:58.475274: step: 1386/1545, loss: 0.3487931191921234 2023-01-23 15:02:59.341880: step: 1388/1545, loss: 0.18823464214801788 2023-01-23 15:03:00.265664: step: 1390/1545, loss: 0.01324248407036066 2023-01-23 15:03:01.167732: step: 1392/1545, loss: 0.0038878205232322216 2023-01-23 15:03:02.047732: step: 1394/1545, loss: 0.04241097718477249 2023-01-23 15:03:02.929858: step: 1396/1545, loss: 0.32793357968330383 2023-01-23 15:03:03.837665: step: 1398/1545, loss: 0.01675453968346119 2023-01-23 15:03:04.762288: step: 1400/1545, loss: 0.03713158145546913 2023-01-23 15:03:05.676687: step: 1402/1545, loss: 0.14416782557964325 2023-01-23 15:03:06.585495: step: 1404/1545, loss: 0.057666171342134476 2023-01-23 15:03:07.455341: step: 1406/1545, loss: 0.131125807762146 2023-01-23 15:03:08.367765: step: 1408/1545, loss: 0.00044471389264799654 2023-01-23 15:03:09.324383: step: 1410/1545, loss: 0.09834755212068558 2023-01-23 15:03:10.171027: step: 1412/1545, loss: 0.0529666393995285 2023-01-23 15:03:11.023678: step: 1414/1545, loss: 0.001104930299334228 2023-01-23 15:03:11.891826: step: 1416/1545, loss: 0.00438027735799551 2023-01-23 15:03:12.809110: step: 1418/1545, loss: 0.1356116682291031 2023-01-23 15:03:13.727442: step: 1420/1545, loss: 0.6368343830108643 2023-01-23 15:03:14.578996: step: 1422/1545, loss: 0.05841772258281708 2023-01-23 15:03:15.443205: step: 1424/1545, loss: 0.10376095771789551 2023-01-23 15:03:16.343800: step: 1426/1545, loss: 0.29771333932876587 2023-01-23 15:03:17.186609: step: 1428/1545, loss: 0.049011025577783585 2023-01-23 15:03:18.219670: step: 1430/1545, loss: 0.0654670000076294 2023-01-23 15:03:19.086240: step: 1432/1545, loss: 0.04342041537165642 2023-01-23 15:03:19.993269: step: 1434/1545, loss: 0.04421617090702057 2023-01-23 15:03:20.910293: step: 1436/1545, loss: 0.005258715711534023 2023-01-23 15:03:21.777233: step: 1438/1545, loss: 0.002244028728455305 2023-01-23 15:03:22.708978: step: 1440/1545, loss: 0.0016394344856962562 2023-01-23 15:03:23.577565: step: 1442/1545, loss: 0.061372414231300354 2023-01-23 15:03:24.470345: step: 1444/1545, loss: 0.035361796617507935 2023-01-23 15:03:25.410135: step: 1446/1545, loss: 0.002920155180618167 2023-01-23 15:03:26.259354: step: 1448/1545, loss: 0.005434214137494564 2023-01-23 15:03:27.158848: step: 1450/1545, loss: 0.012644326314330101 2023-01-23 15:03:28.143967: step: 1452/1545, loss: 0.02357354573905468 2023-01-23 15:03:29.048850: step: 1454/1545, loss: 0.050552044063806534 2023-01-23 15:03:29.996657: step: 1456/1545, loss: 0.016945507377386093 2023-01-23 15:03:30.878462: step: 1458/1545, loss: 0.05021646246314049 2023-01-23 15:03:31.755221: step: 1460/1545, loss: 0.007764240261167288 2023-01-23 15:03:32.675987: step: 1462/1545, loss: 0.4232047498226166 2023-01-23 15:03:33.543405: step: 1464/1545, loss: 0.33817747235298157 2023-01-23 15:03:34.469214: step: 1466/1545, loss: 0.011611846275627613 2023-01-23 15:03:35.315511: step: 1468/1545, loss: 0.0746239423751831 2023-01-23 15:03:36.169318: step: 1470/1545, loss: 0.0001448118855478242 2023-01-23 15:03:37.088439: step: 1472/1545, loss: 0.03206434100866318 2023-01-23 15:03:38.021776: step: 1474/1545, loss: 0.0008059811079874635 2023-01-23 15:03:38.902747: step: 1476/1545, loss: 0.0010294709354639053 2023-01-23 15:03:39.801377: step: 1478/1545, loss: 0.027362365275621414 2023-01-23 15:03:40.681081: step: 1480/1545, loss: 0.012339535169303417 2023-01-23 15:03:41.536408: step: 1482/1545, loss: 0.01722075417637825 2023-01-23 15:03:42.534342: step: 1484/1545, loss: 0.3282823860645294 2023-01-23 15:03:43.455834: step: 1486/1545, loss: 0.00211265217512846 2023-01-23 15:03:44.335090: step: 1488/1545, loss: 0.0029747760854661465 2023-01-23 15:03:45.205582: step: 1490/1545, loss: 0.02454310841858387 2023-01-23 15:03:46.121437: step: 1492/1545, loss: 0.02138695865869522 2023-01-23 15:03:47.003575: step: 1494/1545, loss: 0.004225442185997963 2023-01-23 15:03:47.848850: step: 1496/1545, loss: 0.0002648400259204209 2023-01-23 15:03:48.704747: step: 1498/1545, loss: 0.026178602129220963 2023-01-23 15:03:49.620671: step: 1500/1545, loss: 0.05892360955476761 2023-01-23 15:03:50.522889: step: 1502/1545, loss: 0.057450130581855774 2023-01-23 15:03:51.379046: step: 1504/1545, loss: 0.0011926630977541208 2023-01-23 15:03:52.301225: step: 1506/1545, loss: 0.004240793641656637 2023-01-23 15:03:53.151274: step: 1508/1545, loss: 0.9363183975219727 2023-01-23 15:03:54.002220: step: 1510/1545, loss: 0.09941986203193665 2023-01-23 15:03:54.862264: step: 1512/1545, loss: 0.02754814922809601 2023-01-23 15:03:55.710987: step: 1514/1545, loss: 0.056442566215991974 2023-01-23 15:03:56.564879: step: 1516/1545, loss: 0.15751831233501434 2023-01-23 15:03:57.497055: step: 1518/1545, loss: 0.0005034900386817753 2023-01-23 15:03:58.333515: step: 1520/1545, loss: 0.03956502676010132 2023-01-23 15:03:59.189881: step: 1522/1545, loss: 0.0031357486732304096 2023-01-23 15:04:00.086325: step: 1524/1545, loss: 0.03718223795294762 2023-01-23 15:04:00.922123: step: 1526/1545, loss: 0.13062907755374908 2023-01-23 15:04:01.819095: step: 1528/1545, loss: 0.2778306007385254 2023-01-23 15:04:02.652173: step: 1530/1545, loss: 0.2156990021467209 2023-01-23 15:04:03.552784: step: 1532/1545, loss: 0.09936477243900299 2023-01-23 15:04:04.419328: step: 1534/1545, loss: 0.014486727304756641 2023-01-23 15:04:05.310718: step: 1536/1545, loss: 0.24570772051811218 2023-01-23 15:04:06.159863: step: 1538/1545, loss: 0.0234268456697464 2023-01-23 15:04:07.010476: step: 1540/1545, loss: 0.09591691941022873 2023-01-23 15:04:07.923607: step: 1542/1545, loss: 0.0027896896935999393 2023-01-23 15:04:08.813727: step: 1544/1545, loss: 0.015206342563033104 2023-01-23 15:04:09.668306: step: 1546/1545, loss: 0.01708124577999115 2023-01-23 15:04:10.538188: step: 1548/1545, loss: 0.3218909800052643 2023-01-23 15:04:11.418182: step: 1550/1545, loss: 0.017831793054938316 2023-01-23 15:04:12.278472: step: 1552/1545, loss: 0.1487167626619339 2023-01-23 15:04:13.180043: step: 1554/1545, loss: 0.7842485904693604 2023-01-23 15:04:14.072173: step: 1556/1545, loss: 0.2617702782154083 2023-01-23 15:04:14.935784: step: 1558/1545, loss: 0.10776402056217194 2023-01-23 15:04:15.798317: step: 1560/1545, loss: 0.004181592259556055 2023-01-23 15:04:16.712697: step: 1562/1545, loss: 0.0025512140709906816 2023-01-23 15:04:17.605792: step: 1564/1545, loss: 0.09783325344324112 2023-01-23 15:04:18.457692: step: 1566/1545, loss: 0.025843871757388115 2023-01-23 15:04:19.357306: step: 1568/1545, loss: 0.0024531115777790546 2023-01-23 15:04:20.249274: step: 1570/1545, loss: 0.01570259965956211 2023-01-23 15:04:21.105742: step: 1572/1545, loss: 0.012688967399299145 2023-01-23 15:04:22.018904: step: 1574/1545, loss: 0.4674450755119324 2023-01-23 15:04:22.982311: step: 1576/1545, loss: 0.008361154235899448 2023-01-23 15:04:23.856559: step: 1578/1545, loss: 0.022844962775707245 2023-01-23 15:04:24.768234: step: 1580/1545, loss: 0.0007649128092452884 2023-01-23 15:04:25.643801: step: 1582/1545, loss: 0.12362883239984512 2023-01-23 15:04:26.544328: step: 1584/1545, loss: 0.007595065515488386 2023-01-23 15:04:27.434626: step: 1586/1545, loss: 0.7613673806190491 2023-01-23 15:04:28.345657: step: 1588/1545, loss: 0.0006572596612386405 2023-01-23 15:04:29.233814: step: 1590/1545, loss: 0.055207204073667526 2023-01-23 15:04:30.154428: step: 1592/1545, loss: 0.0022555217146873474 2023-01-23 15:04:31.068345: step: 1594/1545, loss: 0.001419311505742371 2023-01-23 15:04:31.946791: step: 1596/1545, loss: 0.045354168862104416 2023-01-23 15:04:32.804270: step: 1598/1545, loss: 0.21021141111850739 2023-01-23 15:04:33.639720: step: 1600/1545, loss: 0.44345328211784363 2023-01-23 15:04:34.534275: step: 1602/1545, loss: 0.041768595576286316 2023-01-23 15:04:35.476514: step: 1604/1545, loss: 0.007122301030904055 2023-01-23 15:04:36.336863: step: 1606/1545, loss: 0.0041622137650847435 2023-01-23 15:04:37.177969: step: 1608/1545, loss: 0.13905248045921326 2023-01-23 15:04:38.074475: step: 1610/1545, loss: 0.06072613224387169 2023-01-23 15:04:38.967539: step: 1612/1545, loss: 0.2742983102798462 2023-01-23 15:04:39.842772: step: 1614/1545, loss: 0.004681973718106747 2023-01-23 15:04:40.733078: step: 1616/1545, loss: 0.004250059835612774 2023-01-23 15:04:41.592695: step: 1618/1545, loss: 0.0006065763300284743 2023-01-23 15:04:42.460422: step: 1620/1545, loss: 0.07677055150270462 2023-01-23 15:04:43.291214: step: 1622/1545, loss: 0.001095866085961461 2023-01-23 15:04:44.202563: step: 1624/1545, loss: 0.0032458712812513113 2023-01-23 15:04:45.079379: step: 1626/1545, loss: 0.00047246660687960684 2023-01-23 15:04:45.955684: step: 1628/1545, loss: 0.07918989658355713 2023-01-23 15:04:46.828507: step: 1630/1545, loss: 0.2994571626186371 2023-01-23 15:04:47.758311: step: 1632/1545, loss: 0.0012536742724478245 2023-01-23 15:04:48.631538: step: 1634/1545, loss: 0.007821274921298027 2023-01-23 15:04:49.523914: step: 1636/1545, loss: 0.001996641280129552 2023-01-23 15:04:50.449650: step: 1638/1545, loss: 0.027975015342235565 2023-01-23 15:04:51.313070: step: 1640/1545, loss: 0.09006819874048233 2023-01-23 15:04:52.184001: step: 1642/1545, loss: 0.02346923016011715 2023-01-23 15:04:53.058797: step: 1644/1545, loss: 0.002183980541303754 2023-01-23 15:04:53.923705: step: 1646/1545, loss: 0.001736034289933741 2023-01-23 15:04:54.811490: step: 1648/1545, loss: 0.0411122590303421 2023-01-23 15:04:55.703681: step: 1650/1545, loss: 0.00019931039423681796 2023-01-23 15:04:56.624369: step: 1652/1545, loss: 0.03555294871330261 2023-01-23 15:04:57.522769: step: 1654/1545, loss: 0.012783368118107319 2023-01-23 15:04:58.391425: step: 1656/1545, loss: 0.029170993715524673 2023-01-23 15:04:59.270730: step: 1658/1545, loss: 0.06985419243574142 2023-01-23 15:05:00.151798: step: 1660/1545, loss: 0.0016121880616992712 2023-01-23 15:05:01.026032: step: 1662/1545, loss: 0.026217181235551834 2023-01-23 15:05:01.944430: step: 1664/1545, loss: 0.15612809360027313 2023-01-23 15:05:02.837528: step: 1666/1545, loss: 0.24008238315582275 2023-01-23 15:05:03.730402: step: 1668/1545, loss: 0.0007079003262333572 2023-01-23 15:05:04.611349: step: 1670/1545, loss: 0.09091786295175552 2023-01-23 15:05:05.529226: step: 1672/1545, loss: 0.08175532519817352 2023-01-23 15:05:06.477482: step: 1674/1545, loss: 0.026593169197440147 2023-01-23 15:05:07.353680: step: 1676/1545, loss: 0.05910908430814743 2023-01-23 15:05:08.259807: step: 1678/1545, loss: 0.2724437117576599 2023-01-23 15:05:09.145883: step: 1680/1545, loss: 0.004382085520774126 2023-01-23 15:05:10.125005: step: 1682/1545, loss: 0.023805204778909683 2023-01-23 15:05:10.971427: step: 1684/1545, loss: 0.00032964430283755064 2023-01-23 15:05:11.850189: step: 1686/1545, loss: 0.3459922671318054 2023-01-23 15:05:12.722149: step: 1688/1545, loss: 0.04696018993854523 2023-01-23 15:05:13.651223: step: 1690/1545, loss: 0.0033527405466884375 2023-01-23 15:05:14.517539: step: 1692/1545, loss: 0.07511726766824722 2023-01-23 15:05:15.397025: step: 1694/1545, loss: 0.0620880052447319 2023-01-23 15:05:16.304132: step: 1696/1545, loss: 0.11763640493154526 2023-01-23 15:05:17.193977: step: 1698/1545, loss: 1.0888142585754395 2023-01-23 15:05:18.067278: step: 1700/1545, loss: 0.12252076715230942 2023-01-23 15:05:19.028423: step: 1702/1545, loss: 0.022648580372333527 2023-01-23 15:05:19.894993: step: 1704/1545, loss: 0.021165525540709496 2023-01-23 15:05:20.744169: step: 1706/1545, loss: 0.0025436005089432 2023-01-23 15:05:21.687250: step: 1708/1545, loss: 0.0620025098323822 2023-01-23 15:05:22.620364: step: 1710/1545, loss: 0.04481944814324379 2023-01-23 15:05:23.502988: step: 1712/1545, loss: 0.004068370908498764 2023-01-23 15:05:24.544431: step: 1714/1545, loss: 0.0017816368490457535 2023-01-23 15:05:25.408209: step: 1716/1545, loss: 0.05175957828760147 2023-01-23 15:05:26.266251: step: 1718/1545, loss: 0.009418496862053871 2023-01-23 15:05:27.144845: step: 1720/1545, loss: 0.19568389654159546 2023-01-23 15:05:28.083071: step: 1722/1545, loss: 0.13685865700244904 2023-01-23 15:05:28.966311: step: 1724/1545, loss: 0.04472773149609566 2023-01-23 15:05:29.872630: step: 1726/1545, loss: 0.0238100104033947 2023-01-23 15:05:30.740421: step: 1728/1545, loss: 0.0014485233696177602 2023-01-23 15:05:31.569875: step: 1730/1545, loss: 0.23784109950065613 2023-01-23 15:05:32.450762: step: 1732/1545, loss: 0.3674061894416809 2023-01-23 15:05:33.379586: step: 1734/1545, loss: 0.09330474585294724 2023-01-23 15:05:34.293389: step: 1736/1545, loss: 0.0014725448563694954 2023-01-23 15:05:35.172213: step: 1738/1545, loss: 0.0006957883597351611 2023-01-23 15:05:36.062968: step: 1740/1545, loss: 0.03867443650960922 2023-01-23 15:05:36.940567: step: 1742/1545, loss: 0.00025332265067845583 2023-01-23 15:05:37.811591: step: 1744/1545, loss: 0.015178070403635502 2023-01-23 15:05:38.719132: step: 1746/1545, loss: 0.02344992756843567 2023-01-23 15:05:39.729338: step: 1748/1545, loss: 0.0003917057765647769 2023-01-23 15:05:40.577347: step: 1750/1545, loss: 0.0026546132285147905 2023-01-23 15:05:41.438212: step: 1752/1545, loss: 0.41043269634246826 2023-01-23 15:05:42.362750: step: 1754/1545, loss: 0.019499581307172775 2023-01-23 15:05:43.236762: step: 1756/1545, loss: 0.13514961302280426 2023-01-23 15:05:44.076749: step: 1758/1545, loss: 0.017116736620664597 2023-01-23 15:05:44.955620: step: 1760/1545, loss: 0.18331323564052582 2023-01-23 15:05:45.815027: step: 1762/1545, loss: 0.020960550755262375 2023-01-23 15:05:46.630410: step: 1764/1545, loss: 0.00016426517686340958 2023-01-23 15:05:47.572225: step: 1766/1545, loss: 0.0036226194351911545 2023-01-23 15:05:48.450775: step: 1768/1545, loss: 0.05743718147277832 2023-01-23 15:05:49.362769: step: 1770/1545, loss: 0.2371162325143814 2023-01-23 15:05:50.214782: step: 1772/1545, loss: 0.3422989845275879 2023-01-23 15:05:51.067602: step: 1774/1545, loss: 0.06628112494945526 2023-01-23 15:05:51.960761: step: 1776/1545, loss: 0.007782705593854189 2023-01-23 15:05:52.833027: step: 1778/1545, loss: 0.004618571139872074 2023-01-23 15:05:53.679157: step: 1780/1545, loss: 0.01864447072148323 2023-01-23 15:05:54.496035: step: 1782/1545, loss: 0.0008082082495093346 2023-01-23 15:05:55.324597: step: 1784/1545, loss: 0.015785472467541695 2023-01-23 15:05:56.198408: step: 1786/1545, loss: 0.12294419854879379 2023-01-23 15:05:57.092520: step: 1788/1545, loss: 0.006237357389181852 2023-01-23 15:05:58.014106: step: 1790/1545, loss: 0.12133423238992691 2023-01-23 15:05:58.848355: step: 1792/1545, loss: 2.6446105039212853e-05 2023-01-23 15:05:59.784198: step: 1794/1545, loss: 0.28632408380508423 2023-01-23 15:06:00.666181: step: 1796/1545, loss: 0.010896030813455582 2023-01-23 15:06:01.575026: step: 1798/1545, loss: 0.13107849657535553 2023-01-23 15:06:02.517577: step: 1800/1545, loss: 0.521120011806488 2023-01-23 15:06:03.408492: step: 1802/1545, loss: 0.016341939568519592 2023-01-23 15:06:04.270635: step: 1804/1545, loss: 0.05134300887584686 2023-01-23 15:06:05.163065: step: 1806/1545, loss: 0.005534521769732237 2023-01-23 15:06:06.043205: step: 1808/1545, loss: 0.0004395097494125366 2023-01-23 15:06:06.925191: step: 1810/1545, loss: 0.0001671771751716733 2023-01-23 15:06:07.801718: step: 1812/1545, loss: 0.11796759068965912 2023-01-23 15:06:08.680015: step: 1814/1545, loss: 0.14153483510017395 2023-01-23 15:06:09.559686: step: 1816/1545, loss: 0.002057890174910426 2023-01-23 15:06:10.411747: step: 1818/1545, loss: 0.01649303361773491 2023-01-23 15:06:11.270162: step: 1820/1545, loss: 0.0015803665155544877 2023-01-23 15:06:12.175422: step: 1822/1545, loss: 0.0013806070201098919 2023-01-23 15:06:13.088792: step: 1824/1545, loss: 0.02507285214960575 2023-01-23 15:06:13.942791: step: 1826/1545, loss: 0.15335921943187714 2023-01-23 15:06:14.853392: step: 1828/1545, loss: 0.0002729996922425926 2023-01-23 15:06:15.698762: step: 1830/1545, loss: 0.17760324478149414 2023-01-23 15:06:16.532774: step: 1832/1545, loss: 0.005806938745081425 2023-01-23 15:06:17.421916: step: 1834/1545, loss: 0.008242322131991386 2023-01-23 15:06:18.281971: step: 1836/1545, loss: 0.02362997643649578 2023-01-23 15:06:19.179397: step: 1838/1545, loss: 0.03630770370364189 2023-01-23 15:06:20.046807: step: 1840/1545, loss: 0.018537526950240135 2023-01-23 15:06:20.946125: step: 1842/1545, loss: 0.052146587520837784 2023-01-23 15:06:21.843720: step: 1844/1545, loss: 0.02234679087996483 2023-01-23 15:06:22.706243: step: 1846/1545, loss: 0.17498241364955902 2023-01-23 15:06:23.589993: step: 1848/1545, loss: 0.36954882740974426 2023-01-23 15:06:24.416875: step: 1850/1545, loss: 0.4059879779815674 2023-01-23 15:06:25.287641: step: 1852/1545, loss: 0.20635345578193665 2023-01-23 15:06:26.177730: step: 1854/1545, loss: 1.3632572889328003 2023-01-23 15:06:27.034778: step: 1856/1545, loss: 0.022547664120793343 2023-01-23 15:06:27.949873: step: 1858/1545, loss: 0.13308826088905334 2023-01-23 15:06:28.840604: step: 1860/1545, loss: 0.1490291953086853 2023-01-23 15:06:29.704660: step: 1862/1545, loss: 0.10069629549980164 2023-01-23 15:06:30.628880: step: 1864/1545, loss: 0.007846162654459476 2023-01-23 15:06:31.495895: step: 1866/1545, loss: 0.017188455909490585 2023-01-23 15:06:32.354941: step: 1868/1545, loss: 0.0007060192292556167 2023-01-23 15:06:33.264251: step: 1870/1545, loss: 0.027400663122534752 2023-01-23 15:06:34.202570: step: 1872/1545, loss: 0.12566690146923065 2023-01-23 15:06:35.139545: step: 1874/1545, loss: 0.032254476100206375 2023-01-23 15:06:35.987518: step: 1876/1545, loss: 0.05860252305865288 2023-01-23 15:06:36.828440: step: 1878/1545, loss: 0.003115070518106222 2023-01-23 15:06:37.707238: step: 1880/1545, loss: 0.11395604908466339 2023-01-23 15:06:38.629826: step: 1882/1545, loss: 0.02528098039329052 2023-01-23 15:06:39.543194: step: 1884/1545, loss: 0.13303141295909882 2023-01-23 15:06:40.423519: step: 1886/1545, loss: 0.17414827644824982 2023-01-23 15:06:41.329772: step: 1888/1545, loss: 0.09823434054851532 2023-01-23 15:06:42.207538: step: 1890/1545, loss: 0.2588160037994385 2023-01-23 15:06:43.103192: step: 1892/1545, loss: 0.07249647378921509 2023-01-23 15:06:44.064071: step: 1894/1545, loss: 0.017560793086886406 2023-01-23 15:06:44.924138: step: 1896/1545, loss: 0.12761175632476807 2023-01-23 15:06:45.799651: step: 1898/1545, loss: 0.28761959075927734 2023-01-23 15:06:46.762762: step: 1900/1545, loss: 0.026202350854873657 2023-01-23 15:06:47.678970: step: 1902/1545, loss: 0.00246614683419466 2023-01-23 15:06:48.591011: step: 1904/1545, loss: 0.0288227591663599 2023-01-23 15:06:49.462405: step: 1906/1545, loss: 0.003965407609939575 2023-01-23 15:06:50.343318: step: 1908/1545, loss: 0.22288626432418823 2023-01-23 15:06:51.231143: step: 1910/1545, loss: 0.28949007391929626 2023-01-23 15:06:52.159093: step: 1912/1545, loss: 0.01183826383203268 2023-01-23 15:06:53.032458: step: 1914/1545, loss: 0.09234239906072617 2023-01-23 15:06:53.899441: step: 1916/1545, loss: 0.07479715347290039 2023-01-23 15:06:54.787847: step: 1918/1545, loss: 0.001998622203245759 2023-01-23 15:06:55.711204: step: 1920/1545, loss: 0.000973351183347404 2023-01-23 15:06:56.550307: step: 1922/1545, loss: 0.018355593085289 2023-01-23 15:06:57.464992: step: 1924/1545, loss: 0.22233107686042786 2023-01-23 15:06:58.372607: step: 1926/1545, loss: 0.14719967544078827 2023-01-23 15:06:59.190938: step: 1928/1545, loss: 0.0683215782046318 2023-01-23 15:07:00.137089: step: 1930/1545, loss: 0.045137688517570496 2023-01-23 15:07:00.995147: step: 1932/1545, loss: 0.008044791407883167 2023-01-23 15:07:01.886200: step: 1934/1545, loss: 0.04168661683797836 2023-01-23 15:07:02.760187: step: 1936/1545, loss: 0.011622229591012001 2023-01-23 15:07:03.731460: step: 1938/1545, loss: 0.02975328639149666 2023-01-23 15:07:04.600875: step: 1940/1545, loss: 0.03218447417020798 2023-01-23 15:07:05.473073: step: 1942/1545, loss: 0.1912248134613037 2023-01-23 15:07:06.377949: step: 1944/1545, loss: 0.17600440979003906 2023-01-23 15:07:07.227246: step: 1946/1545, loss: 0.034524932503700256 2023-01-23 15:07:08.109658: step: 1948/1545, loss: 0.015932299196720123 2023-01-23 15:07:09.006497: step: 1950/1545, loss: 0.007900627329945564 2023-01-23 15:07:09.927822: step: 1952/1545, loss: 0.014963960275053978 2023-01-23 15:07:10.812409: step: 1954/1545, loss: 0.6682942509651184 2023-01-23 15:07:11.650834: step: 1956/1545, loss: 0.07089199870824814 2023-01-23 15:07:12.562929: step: 1958/1545, loss: 0.14434432983398438 2023-01-23 15:07:13.436952: step: 1960/1545, loss: 0.17299959063529968 2023-01-23 15:07:14.341878: step: 1962/1545, loss: 0.11376143246889114 2023-01-23 15:07:15.249451: step: 1964/1545, loss: 0.040249988436698914 2023-01-23 15:07:16.120819: step: 1966/1545, loss: 0.1478009968996048 2023-01-23 15:07:17.004652: step: 1968/1545, loss: 0.008738147094845772 2023-01-23 15:07:17.924538: step: 1970/1545, loss: 0.0018979846499860287 2023-01-23 15:07:18.841512: step: 1972/1545, loss: 0.10560230910778046 2023-01-23 15:07:19.772913: step: 1974/1545, loss: 0.00434557581320405 2023-01-23 15:07:20.614937: step: 1976/1545, loss: 0.10656081885099411 2023-01-23 15:07:21.502663: step: 1978/1545, loss: 0.004133804701268673 2023-01-23 15:07:22.369084: step: 1980/1545, loss: 0.003218497149646282 2023-01-23 15:07:23.309919: step: 1982/1545, loss: 0.1399305760860443 2023-01-23 15:07:24.206512: step: 1984/1545, loss: 0.0614033006131649 2023-01-23 15:07:25.102935: step: 1986/1545, loss: 0.07766851037740707 2023-01-23 15:07:25.967361: step: 1988/1545, loss: 0.33023709058761597 2023-01-23 15:07:26.847664: step: 1990/1545, loss: 0.05069345235824585 2023-01-23 15:07:27.764139: step: 1992/1545, loss: 0.25734376907348633 2023-01-23 15:07:28.654484: step: 1994/1545, loss: 0.007986854761838913 2023-01-23 15:07:29.472848: step: 1996/1545, loss: 0.00042475521331653 2023-01-23 15:07:30.331941: step: 1998/1545, loss: 0.0002933120122179389 2023-01-23 15:07:31.218186: step: 2000/1545, loss: 0.014836248010396957 2023-01-23 15:07:32.087170: step: 2002/1545, loss: 0.08825583010911942 2023-01-23 15:07:33.046866: step: 2004/1545, loss: 0.0008478188537992537 2023-01-23 15:07:33.912284: step: 2006/1545, loss: 0.1801590472459793 2023-01-23 15:07:34.786199: step: 2008/1545, loss: 0.12254686653614044 2023-01-23 15:07:35.654481: step: 2010/1545, loss: 0.014806211926043034 2023-01-23 15:07:36.544230: step: 2012/1545, loss: 0.10539580136537552 2023-01-23 15:07:37.397230: step: 2014/1545, loss: 0.12088101357221603 2023-01-23 15:07:38.312124: step: 2016/1545, loss: 1.365051507949829 2023-01-23 15:07:39.181566: step: 2018/1545, loss: 0.004163033328950405 2023-01-23 15:07:40.099965: step: 2020/1545, loss: 0.13274163007736206 2023-01-23 15:07:40.965858: step: 2022/1545, loss: 0.007791402284055948 2023-01-23 15:07:41.829120: step: 2024/1545, loss: 0.1676073521375656 2023-01-23 15:07:42.702263: step: 2026/1545, loss: 0.0038547709118574858 2023-01-23 15:07:43.600494: step: 2028/1545, loss: 0.030983399599790573 2023-01-23 15:07:44.491065: step: 2030/1545, loss: 0.12592485547065735 2023-01-23 15:07:45.348639: step: 2032/1545, loss: 0.018502820283174515 2023-01-23 15:07:46.257622: step: 2034/1545, loss: 0.0858113169670105 2023-01-23 15:07:47.135027: step: 2036/1545, loss: 0.05213608965277672 2023-01-23 15:07:47.991987: step: 2038/1545, loss: 0.0755353644490242 2023-01-23 15:07:48.849406: step: 2040/1545, loss: 0.011495782062411308 2023-01-23 15:07:49.694804: step: 2042/1545, loss: 0.06815650314092636 2023-01-23 15:07:50.551843: step: 2044/1545, loss: 0.002075828379020095 2023-01-23 15:07:51.406780: step: 2046/1545, loss: 0.010589167475700378 2023-01-23 15:07:52.314769: step: 2048/1545, loss: 0.6343505382537842 2023-01-23 15:07:53.210136: step: 2050/1545, loss: 0.2525375783443451 2023-01-23 15:07:54.078353: step: 2052/1545, loss: 0.05755143612623215 2023-01-23 15:07:54.949522: step: 2054/1545, loss: 0.005463919602334499 2023-01-23 15:07:55.853770: step: 2056/1545, loss: 0.05916199833154678 2023-01-23 15:07:56.744130: step: 2058/1545, loss: 0.004630571696907282 2023-01-23 15:07:57.605331: step: 2060/1545, loss: 0.10854225605726242 2023-01-23 15:07:58.515722: step: 2062/1545, loss: 0.13904035091400146 2023-01-23 15:07:59.373081: step: 2064/1545, loss: 0.15810219943523407 2023-01-23 15:08:00.274185: step: 2066/1545, loss: 0.02819562330842018 2023-01-23 15:08:01.154110: step: 2068/1545, loss: 0.2802305519580841 2023-01-23 15:08:01.997495: step: 2070/1545, loss: 0.00556638790294528 2023-01-23 15:08:02.914867: step: 2072/1545, loss: 0.12658999860286713 2023-01-23 15:08:03.760530: step: 2074/1545, loss: 0.002032249001786113 2023-01-23 15:08:04.673372: step: 2076/1545, loss: 0.0023531897459179163 2023-01-23 15:08:05.515074: step: 2078/1545, loss: 0.02114986628293991 2023-01-23 15:08:06.430881: step: 2080/1545, loss: 0.025672877207398415 2023-01-23 15:08:07.342286: step: 2082/1545, loss: 0.1778394728899002 2023-01-23 15:08:08.234488: step: 2084/1545, loss: 0.0027808635495603085 2023-01-23 15:08:09.106528: step: 2086/1545, loss: 0.03468447923660278 2023-01-23 15:08:10.048270: step: 2088/1545, loss: 0.017003269866108894 2023-01-23 15:08:10.942702: step: 2090/1545, loss: 0.004326654132455587 2023-01-23 15:08:11.882491: step: 2092/1545, loss: 0.012038047425448895 2023-01-23 15:08:12.761023: step: 2094/1545, loss: 0.019016703590750694 2023-01-23 15:08:13.635726: step: 2096/1545, loss: 0.006893112789839506 2023-01-23 15:08:14.513677: step: 2098/1545, loss: 0.06581203639507294 2023-01-23 15:08:15.407004: step: 2100/1545, loss: 0.02949303202331066 2023-01-23 15:08:16.287570: step: 2102/1545, loss: 0.0019919159822165966 2023-01-23 15:08:17.197628: step: 2104/1545, loss: 0.048064179718494415 2023-01-23 15:08:18.043046: step: 2106/1545, loss: 0.35164567828178406 2023-01-23 15:08:19.066236: step: 2108/1545, loss: 0.015293541364371777 2023-01-23 15:08:19.952064: step: 2110/1545, loss: 0.14670538902282715 2023-01-23 15:08:20.828173: step: 2112/1545, loss: 0.007845933549106121 2023-01-23 15:08:21.747845: step: 2114/1545, loss: 0.006394503638148308 2023-01-23 15:08:22.654488: step: 2116/1545, loss: 0.007075818721204996 2023-01-23 15:08:23.578745: step: 2118/1545, loss: 0.0387929230928421 2023-01-23 15:08:24.460036: step: 2120/1545, loss: 0.01027290802448988 2023-01-23 15:08:25.337237: step: 2122/1545, loss: 2.454881191253662 2023-01-23 15:08:26.219522: step: 2124/1545, loss: 0.09891132265329361 2023-01-23 15:08:27.120851: step: 2126/1545, loss: 0.001192016527056694 2023-01-23 15:08:28.026820: step: 2128/1545, loss: 0.15436598658561707 2023-01-23 15:08:28.933197: step: 2130/1545, loss: 0.09486812353134155 2023-01-23 15:08:29.808081: step: 2132/1545, loss: 0.001962769078090787 2023-01-23 15:08:30.780191: step: 2134/1545, loss: 0.1149725392460823 2023-01-23 15:08:31.632991: step: 2136/1545, loss: 0.04405665397644043 2023-01-23 15:08:32.655701: step: 2138/1545, loss: 0.22519071400165558 2023-01-23 15:08:33.568230: step: 2140/1545, loss: 0.19103217124938965 2023-01-23 15:08:34.472500: step: 2142/1545, loss: 0.19550248980522156 2023-01-23 15:08:35.387012: step: 2144/1545, loss: 0.022298583760857582 2023-01-23 15:08:36.269876: step: 2146/1545, loss: 0.0049979775212705135 2023-01-23 15:08:37.167079: step: 2148/1545, loss: 0.0015031425282359123 2023-01-23 15:08:38.042677: step: 2150/1545, loss: 0.142044797539711 2023-01-23 15:08:38.965051: step: 2152/1545, loss: 0.009665541350841522 2023-01-23 15:08:39.889643: step: 2154/1545, loss: 0.0007692989893257618 2023-01-23 15:08:40.752122: step: 2156/1545, loss: 0.0002739627962000668 2023-01-23 15:08:41.646487: step: 2158/1545, loss: 0.7225065231323242 2023-01-23 15:08:42.509059: step: 2160/1545, loss: 0.056009288877248764 2023-01-23 15:08:43.379196: step: 2162/1545, loss: 0.4234848916530609 2023-01-23 15:08:44.305071: step: 2164/1545, loss: 0.9383386969566345 2023-01-23 15:08:45.179470: step: 2166/1545, loss: 0.000144647725392133 2023-01-23 15:08:46.073715: step: 2168/1545, loss: 0.018573705106973648 2023-01-23 15:08:46.941680: step: 2170/1545, loss: 0.0012878874549642205 2023-01-23 15:08:47.806332: step: 2172/1545, loss: 0.015685182064771652 2023-01-23 15:08:48.695855: step: 2174/1545, loss: 0.0005512640927918255 2023-01-23 15:08:49.578574: step: 2176/1545, loss: 0.07976692169904709 2023-01-23 15:08:50.443173: step: 2178/1545, loss: 0.22527340054512024 2023-01-23 15:08:51.404689: step: 2180/1545, loss: 0.002833610400557518 2023-01-23 15:08:52.320234: step: 2182/1545, loss: 0.0022284407168626785 2023-01-23 15:08:53.215117: step: 2184/1545, loss: 0.014565245248377323 2023-01-23 15:08:54.135789: step: 2186/1545, loss: 0.010467740707099438 2023-01-23 15:08:55.030823: step: 2188/1545, loss: 0.08655664324760437 2023-01-23 15:08:55.934651: step: 2190/1545, loss: 0.009334043599665165 2023-01-23 15:08:56.865853: step: 2192/1545, loss: 0.00432001706212759 2023-01-23 15:08:57.780671: step: 2194/1545, loss: 0.17778092622756958 2023-01-23 15:08:58.687187: step: 2196/1545, loss: 0.02697034738957882 2023-01-23 15:08:59.576929: step: 2198/1545, loss: 0.06044429913163185 2023-01-23 15:09:00.501541: step: 2200/1545, loss: 0.03891288861632347 2023-01-23 15:09:01.389409: step: 2202/1545, loss: 0.04782587289810181 2023-01-23 15:09:02.295686: step: 2204/1545, loss: 0.2272564023733139 2023-01-23 15:09:03.161594: step: 2206/1545, loss: 0.07050683349370956 2023-01-23 15:09:04.087451: step: 2208/1545, loss: 0.11568183451890945 2023-01-23 15:09:04.926094: step: 2210/1545, loss: 0.011055603623390198 2023-01-23 15:09:05.848890: step: 2212/1545, loss: 0.018222644925117493 2023-01-23 15:09:06.708507: step: 2214/1545, loss: 0.05196818336844444 2023-01-23 15:09:07.607909: step: 2216/1545, loss: 0.02439964935183525 2023-01-23 15:09:08.513300: step: 2218/1545, loss: 0.0353400744497776 2023-01-23 15:09:09.412147: step: 2220/1545, loss: 0.00795840285718441 2023-01-23 15:09:10.367074: step: 2222/1545, loss: 0.3763071894645691 2023-01-23 15:09:11.290461: step: 2224/1545, loss: 0.16245809197425842 2023-01-23 15:09:12.167017: step: 2226/1545, loss: 0.6373791098594666 2023-01-23 15:09:13.094799: step: 2228/1545, loss: 0.2797781229019165 2023-01-23 15:09:13.960180: step: 2230/1545, loss: 0.013537321239709854 2023-01-23 15:09:14.811603: step: 2232/1545, loss: 0.0202488973736763 2023-01-23 15:09:15.700429: step: 2234/1545, loss: 0.0013747417833656073 2023-01-23 15:09:16.622469: step: 2236/1545, loss: 0.0011161199072375894 2023-01-23 15:09:17.507372: step: 2238/1545, loss: 0.057792067527770996 2023-01-23 15:09:18.391457: step: 2240/1545, loss: 0.006073132622987032 2023-01-23 15:09:19.267865: step: 2242/1545, loss: 0.0037460578605532646 2023-01-23 15:09:20.152665: step: 2244/1545, loss: 0.053501877933740616 2023-01-23 15:09:21.016510: step: 2246/1545, loss: 0.01113276369869709 2023-01-23 15:09:21.912209: step: 2248/1545, loss: 0.0017896591452881694 2023-01-23 15:09:22.790400: step: 2250/1545, loss: 0.12364789843559265 2023-01-23 15:09:23.657739: step: 2252/1545, loss: 0.024563610553741455 2023-01-23 15:09:24.506623: step: 2254/1545, loss: 0.006459343247115612 2023-01-23 15:09:25.378097: step: 2256/1545, loss: 0.05497553199529648 2023-01-23 15:09:26.270903: step: 2258/1545, loss: 0.015034325420856476 2023-01-23 15:09:27.158368: step: 2260/1545, loss: 0.0008429710869677365 2023-01-23 15:09:28.091172: step: 2262/1545, loss: 0.06655948609113693 2023-01-23 15:09:29.007265: step: 2264/1545, loss: 0.014697384089231491 2023-01-23 15:09:29.891570: step: 2266/1545, loss: 0.00035619857953861356 2023-01-23 15:09:30.807274: step: 2268/1545, loss: 0.01745300181210041 2023-01-23 15:09:31.693924: step: 2270/1545, loss: 0.0046178861521184444 2023-01-23 15:09:32.604162: step: 2272/1545, loss: 0.16582655906677246 2023-01-23 15:09:33.464373: step: 2274/1545, loss: 0.00709461560472846 2023-01-23 15:09:34.345234: step: 2276/1545, loss: 0.17485244572162628 2023-01-23 15:09:35.257625: step: 2278/1545, loss: 0.23096933960914612 2023-01-23 15:09:36.123054: step: 2280/1545, loss: 0.005345352925360203 2023-01-23 15:09:36.996660: step: 2282/1545, loss: 0.0040756408125162125 2023-01-23 15:09:37.877331: step: 2284/1545, loss: 0.025455297902226448 2023-01-23 15:09:38.775195: step: 2286/1545, loss: 0.004983846098184586 2023-01-23 15:09:39.685989: step: 2288/1545, loss: 0.3492851257324219 2023-01-23 15:09:40.693269: step: 2290/1545, loss: 0.002112968359142542 2023-01-23 15:09:41.583651: step: 2292/1545, loss: 0.5847131609916687 2023-01-23 15:09:42.438438: step: 2294/1545, loss: 0.1518242508172989 2023-01-23 15:09:43.353955: step: 2296/1545, loss: 0.03470458835363388 2023-01-23 15:09:44.233800: step: 2298/1545, loss: 0.1467462182044983 2023-01-23 15:09:45.169999: step: 2300/1545, loss: 0.038699593394994736 2023-01-23 15:09:46.069184: step: 2302/1545, loss: 0.013771634548902512 2023-01-23 15:09:47.015036: step: 2304/1545, loss: 0.28199517726898193 2023-01-23 15:09:47.906275: step: 2306/1545, loss: 0.00022685909061692655 2023-01-23 15:09:48.814278: step: 2308/1545, loss: 0.10774428397417068 2023-01-23 15:09:49.733124: step: 2310/1545, loss: 0.0011620009317994118 2023-01-23 15:09:50.582586: step: 2312/1545, loss: 0.0008356662001460791 2023-01-23 15:09:51.439069: step: 2314/1545, loss: 0.07553841918706894 2023-01-23 15:09:52.329270: step: 2316/1545, loss: 0.1251075565814972 2023-01-23 15:09:53.240607: step: 2318/1545, loss: 0.0006115768337622285 2023-01-23 15:09:54.139479: step: 2320/1545, loss: 0.007516765967011452 2023-01-23 15:09:55.056178: step: 2322/1545, loss: 0.08050746470689774 2023-01-23 15:09:56.016605: step: 2324/1545, loss: 0.00012410152703523636 2023-01-23 15:09:56.915312: step: 2326/1545, loss: 0.025386732071638107 2023-01-23 15:09:57.810391: step: 2328/1545, loss: 0.08837252855300903 2023-01-23 15:09:58.643355: step: 2330/1545, loss: 0.00032884872052818537 2023-01-23 15:09:59.559372: step: 2332/1545, loss: 0.1838448941707611 2023-01-23 15:10:00.486114: step: 2334/1545, loss: 0.020544636994600296 2023-01-23 15:10:01.347222: step: 2336/1545, loss: 0.05155418813228607 2023-01-23 15:10:02.249351: step: 2338/1545, loss: 0.3342132866382599 2023-01-23 15:10:03.159695: step: 2340/1545, loss: 0.007751932833343744 2023-01-23 15:10:04.021517: step: 2342/1545, loss: 0.18190963566303253 2023-01-23 15:10:04.890891: step: 2344/1545, loss: 0.04817771911621094 2023-01-23 15:10:05.811289: step: 2346/1545, loss: 0.08804779499769211 2023-01-23 15:10:06.723289: step: 2348/1545, loss: 0.0012018585111945868 2023-01-23 15:10:07.590856: step: 2350/1545, loss: 0.0165159422904253 2023-01-23 15:10:08.459040: step: 2352/1545, loss: 0.0011431744787842035 2023-01-23 15:10:09.325632: step: 2354/1545, loss: 0.0017998499097302556 2023-01-23 15:10:10.272075: step: 2356/1545, loss: 0.0021938756108283997 2023-01-23 15:10:11.126531: step: 2358/1545, loss: 0.0007401712937280536 2023-01-23 15:10:12.015196: step: 2360/1545, loss: 0.0036968982312828302 2023-01-23 15:10:12.886836: step: 2362/1545, loss: 0.0014651058008894324 2023-01-23 15:10:13.754860: step: 2364/1545, loss: 0.014009055681526661 2023-01-23 15:10:14.680945: step: 2366/1545, loss: 0.0331093855202198 2023-01-23 15:10:15.551687: step: 2368/1545, loss: 0.003902704920619726 2023-01-23 15:10:16.527289: step: 2370/1545, loss: 0.2062610238790512 2023-01-23 15:10:17.407040: step: 2372/1545, loss: 0.005011226981878281 2023-01-23 15:10:18.338453: step: 2374/1545, loss: 0.008348549716174603 2023-01-23 15:10:19.238637: step: 2376/1545, loss: 0.007470007054507732 2023-01-23 15:10:20.141805: step: 2378/1545, loss: 0.03709906339645386 2023-01-23 15:10:20.999564: step: 2380/1545, loss: 0.07547954469919205 2023-01-23 15:10:21.937395: step: 2382/1545, loss: 0.11122722923755646 2023-01-23 15:10:22.789180: step: 2384/1545, loss: 0.019340086728334427 2023-01-23 15:10:23.672794: step: 2386/1545, loss: 0.023575471714138985 2023-01-23 15:10:24.547178: step: 2388/1545, loss: 0.4556201100349426 2023-01-23 15:10:25.484747: step: 2390/1545, loss: 0.00011547747999429703 2023-01-23 15:10:26.387190: step: 2392/1545, loss: 0.09683709591627121 2023-01-23 15:10:27.237703: step: 2394/1545, loss: 0.04824754223227501 2023-01-23 15:10:28.101968: step: 2396/1545, loss: 0.027106301859021187 2023-01-23 15:10:28.960171: step: 2398/1545, loss: 0.1756068766117096 2023-01-23 15:10:29.907921: step: 2400/1545, loss: 0.13820672035217285 2023-01-23 15:10:30.789807: step: 2402/1545, loss: 0.21764223277568817 2023-01-23 15:10:31.732377: step: 2404/1545, loss: 0.023750340566039085 2023-01-23 15:10:32.603856: step: 2406/1545, loss: 0.08906349539756775 2023-01-23 15:10:33.475170: step: 2408/1545, loss: 0.000882631866261363 2023-01-23 15:10:34.347767: step: 2410/1545, loss: 0.13803452253341675 2023-01-23 15:10:35.296576: step: 2412/1545, loss: 0.0021933987736701965 2023-01-23 15:10:36.223584: step: 2414/1545, loss: 0.00039313951856456697 2023-01-23 15:10:37.121268: step: 2416/1545, loss: 0.13003599643707275 2023-01-23 15:10:37.978435: step: 2418/1545, loss: 0.0690193921327591 2023-01-23 15:10:38.870312: step: 2420/1545, loss: 0.023668503388762474 2023-01-23 15:10:39.758445: step: 2422/1545, loss: 0.0037670833989977837 2023-01-23 15:10:40.639368: step: 2424/1545, loss: 0.0037525168154388666 2023-01-23 15:10:41.493568: step: 2426/1545, loss: 0.0018355079228058457 2023-01-23 15:10:42.357712: step: 2428/1545, loss: 0.03952696546912193 2023-01-23 15:10:43.232332: step: 2430/1545, loss: 0.042084403336048126 2023-01-23 15:10:44.091332: step: 2432/1545, loss: 0.0023797089233994484 2023-01-23 15:10:44.945142: step: 2434/1545, loss: 0.018940692767500877 2023-01-23 15:10:45.858208: step: 2436/1545, loss: 0.026005549356341362 2023-01-23 15:10:46.771044: step: 2438/1545, loss: 0.10605441778898239 2023-01-23 15:10:47.666824: step: 2440/1545, loss: 0.019588353112339973 2023-01-23 15:10:48.537372: step: 2442/1545, loss: 0.30902206897735596 2023-01-23 15:10:49.403810: step: 2444/1545, loss: 0.05091541260480881 2023-01-23 15:10:50.244537: step: 2446/1545, loss: 0.027948644012212753 2023-01-23 15:10:51.136423: step: 2448/1545, loss: 0.01169216725975275 2023-01-23 15:10:51.991811: step: 2450/1545, loss: 1.5031241178512573 2023-01-23 15:10:52.858531: step: 2452/1545, loss: 0.002727522049099207 2023-01-23 15:10:53.756368: step: 2454/1545, loss: 0.05288726091384888 2023-01-23 15:10:54.669109: step: 2456/1545, loss: 0.06074140965938568 2023-01-23 15:10:55.556460: step: 2458/1545, loss: 0.019677598029375076 2023-01-23 15:10:56.425362: step: 2460/1545, loss: 0.020301278680562973 2023-01-23 15:10:57.302313: step: 2462/1545, loss: 0.10065225511789322 2023-01-23 15:10:58.162685: step: 2464/1545, loss: 0.12912006676197052 2023-01-23 15:10:59.054856: step: 2466/1545, loss: 0.9940172433853149 2023-01-23 15:10:59.974412: step: 2468/1545, loss: 0.0024285349063575268 2023-01-23 15:11:00.856434: step: 2470/1545, loss: 0.25479134917259216 2023-01-23 15:11:01.704560: step: 2472/1545, loss: 0.12895333766937256 2023-01-23 15:11:02.607582: step: 2474/1545, loss: 0.5003690719604492 2023-01-23 15:11:03.531396: step: 2476/1545, loss: 0.009994219057261944 2023-01-23 15:11:04.426030: step: 2478/1545, loss: 5.323411464691162 2023-01-23 15:11:05.341629: step: 2480/1545, loss: 0.27228593826293945 2023-01-23 15:11:06.218372: step: 2482/1545, loss: 0.04680243507027626 2023-01-23 15:11:07.077492: step: 2484/1545, loss: 0.08471914380788803 2023-01-23 15:11:07.943320: step: 2486/1545, loss: 0.006478148512542248 2023-01-23 15:11:08.832035: step: 2488/1545, loss: 0.08679766207933426 2023-01-23 15:11:09.729454: step: 2490/1545, loss: 1.2310268878936768 2023-01-23 15:11:10.703256: step: 2492/1545, loss: 0.0007122912793420255 2023-01-23 15:11:11.566110: step: 2494/1545, loss: 0.005503623280674219 2023-01-23 15:11:12.489713: step: 2496/1545, loss: 0.21901729702949524 2023-01-23 15:11:13.450910: step: 2498/1545, loss: 0.14638292789459229 2023-01-23 15:11:14.300072: step: 2500/1545, loss: 0.15807099640369415 2023-01-23 15:11:15.161024: step: 2502/1545, loss: 0.10656554996967316 2023-01-23 15:11:16.072866: step: 2504/1545, loss: 0.03650272637605667 2023-01-23 15:11:16.936083: step: 2506/1545, loss: 0.04905661568045616 2023-01-23 15:11:17.832156: step: 2508/1545, loss: 0.13848957419395447 2023-01-23 15:11:18.703499: step: 2510/1545, loss: 0.00797860324382782 2023-01-23 15:11:19.599994: step: 2512/1545, loss: 0.09641936421394348 2023-01-23 15:11:20.521234: step: 2514/1545, loss: 0.043075449764728546 2023-01-23 15:11:21.425415: step: 2516/1545, loss: 0.00704692117869854 2023-01-23 15:11:22.287382: step: 2518/1545, loss: 0.07984147220849991 2023-01-23 15:11:23.233874: step: 2520/1545, loss: 0.10692869126796722 2023-01-23 15:11:24.136601: step: 2522/1545, loss: 0.0349557064473629 2023-01-23 15:11:25.035085: step: 2524/1545, loss: 0.146382674574852 2023-01-23 15:11:25.965647: step: 2526/1545, loss: 0.001934075728058815 2023-01-23 15:11:26.839207: step: 2528/1545, loss: 0.317695289850235 2023-01-23 15:11:27.682869: step: 2530/1545, loss: 0.004167393781244755 2023-01-23 15:11:28.561795: step: 2532/1545, loss: 0.004194183275103569 2023-01-23 15:11:29.424075: step: 2534/1545, loss: 0.010902322828769684 2023-01-23 15:11:30.302421: step: 2536/1545, loss: 0.13155750930309296 2023-01-23 15:11:31.188946: step: 2538/1545, loss: 0.3018624484539032 2023-01-23 15:11:32.084958: step: 2540/1545, loss: 0.0010505394311621785 2023-01-23 15:11:32.979952: step: 2542/1545, loss: 0.029267150908708572 2023-01-23 15:11:33.864356: step: 2544/1545, loss: 0.0004723646561615169 2023-01-23 15:11:34.743429: step: 2546/1545, loss: 0.4158129096031189 2023-01-23 15:11:35.597366: step: 2548/1545, loss: 0.058925651013851166 2023-01-23 15:11:36.474857: step: 2550/1545, loss: 0.009968506172299385 2023-01-23 15:11:37.349886: step: 2552/1545, loss: 0.009254999458789825 2023-01-23 15:11:38.257629: step: 2554/1545, loss: 0.8749536275863647 2023-01-23 15:11:39.168539: step: 2556/1545, loss: 0.010401677340269089 2023-01-23 15:11:40.053422: step: 2558/1545, loss: 0.0010849889367818832 2023-01-23 15:11:40.997152: step: 2560/1545, loss: 0.003314585192129016 2023-01-23 15:11:41.851205: step: 2562/1545, loss: 0.0007295210380107164 2023-01-23 15:11:42.788230: step: 2564/1545, loss: 0.5736050605773926 2023-01-23 15:11:43.682179: step: 2566/1545, loss: 0.1254415214061737 2023-01-23 15:11:44.586440: step: 2568/1545, loss: 0.06836920231580734 2023-01-23 15:11:45.490651: step: 2570/1545, loss: 0.005842163227498531 2023-01-23 15:11:46.368161: step: 2572/1545, loss: 0.004276394844055176 2023-01-23 15:11:47.260219: step: 2574/1545, loss: 0.06598901748657227 2023-01-23 15:11:48.167795: step: 2576/1545, loss: 0.001317485235631466 2023-01-23 15:11:49.028310: step: 2578/1545, loss: 0.0013625352876260877 2023-01-23 15:11:49.974027: step: 2580/1545, loss: 0.002604370703920722 2023-01-23 15:11:50.911269: step: 2582/1545, loss: 0.046132009476423264 2023-01-23 15:11:51.802723: step: 2584/1545, loss: 0.00543245067819953 2023-01-23 15:11:52.662629: step: 2586/1545, loss: 0.0022066624369472265 2023-01-23 15:11:53.518612: step: 2588/1545, loss: 0.0011600337456911802 2023-01-23 15:11:54.402854: step: 2590/1545, loss: 0.14887621998786926 2023-01-23 15:11:55.285577: step: 2592/1545, loss: 0.01432659849524498 2023-01-23 15:11:56.165627: step: 2594/1545, loss: 0.04656657576560974 2023-01-23 15:11:57.094218: step: 2596/1545, loss: 0.03171684592962265 2023-01-23 15:11:57.964478: step: 2598/1545, loss: 0.359147310256958 2023-01-23 15:11:58.827208: step: 2600/1545, loss: 0.0703916847705841 2023-01-23 15:11:59.697425: step: 2602/1545, loss: 0.3754730224609375 2023-01-23 15:12:00.615725: step: 2604/1545, loss: 0.2714766561985016 2023-01-23 15:12:01.512765: step: 2606/1545, loss: 0.09919431805610657 2023-01-23 15:12:02.381575: step: 2608/1545, loss: 0.20757907629013062 2023-01-23 15:12:03.258783: step: 2610/1545, loss: 0.007254120893776417 2023-01-23 15:12:04.171454: step: 2612/1545, loss: 0.24894601106643677 2023-01-23 15:12:05.042804: step: 2614/1545, loss: 0.037086520344018936 2023-01-23 15:12:05.935268: step: 2616/1545, loss: 0.14148451387882233 2023-01-23 15:12:06.834462: step: 2618/1545, loss: 0.45264309644699097 2023-01-23 15:12:07.712573: step: 2620/1545, loss: 0.0022755558602511883 2023-01-23 15:12:08.571869: step: 2622/1545, loss: 0.14958423376083374 2023-01-23 15:12:09.458554: step: 2624/1545, loss: 0.0611242949962616 2023-01-23 15:12:10.327015: step: 2626/1545, loss: 0.03093237802386284 2023-01-23 15:12:11.185428: step: 2628/1545, loss: 0.07351332902908325 2023-01-23 15:12:12.071748: step: 2630/1545, loss: 0.0659870058298111 2023-01-23 15:12:12.922608: step: 2632/1545, loss: 0.14565454423427582 2023-01-23 15:12:13.811205: step: 2634/1545, loss: 0.017063405364751816 2023-01-23 15:12:14.692336: step: 2636/1545, loss: 0.036937166005373 2023-01-23 15:12:15.558036: step: 2638/1545, loss: 0.3360200524330139 2023-01-23 15:12:16.414903: step: 2640/1545, loss: 0.1169295385479927 2023-01-23 15:12:17.280890: step: 2642/1545, loss: 0.04033231735229492 2023-01-23 15:12:18.185419: step: 2644/1545, loss: 0.0032384220976382494 2023-01-23 15:12:19.057663: step: 2646/1545, loss: 0.05297480523586273 2023-01-23 15:12:19.909305: step: 2648/1545, loss: 0.0015407066093757749 2023-01-23 15:12:20.808156: step: 2650/1545, loss: 0.06502998620271683 2023-01-23 15:12:21.711901: step: 2652/1545, loss: 0.038199327886104584 2023-01-23 15:12:22.581570: step: 2654/1545, loss: 0.12643519043922424 2023-01-23 15:12:23.444186: step: 2656/1545, loss: 0.07971465587615967 2023-01-23 15:12:24.393260: step: 2658/1545, loss: 0.2219759076833725 2023-01-23 15:12:25.343940: step: 2660/1545, loss: 0.4205770492553711 2023-01-23 15:12:26.230703: step: 2662/1545, loss: 0.03210057318210602 2023-01-23 15:12:27.065813: step: 2664/1545, loss: 0.0054885754361748695 2023-01-23 15:12:27.964945: step: 2666/1545, loss: 0.28108593821525574 2023-01-23 15:12:28.820950: step: 2668/1545, loss: 0.5609256625175476 2023-01-23 15:12:29.732226: step: 2670/1545, loss: 0.3759196102619171 2023-01-23 15:12:30.618241: step: 2672/1545, loss: 0.009749417193233967 2023-01-23 15:12:31.486698: step: 2674/1545, loss: 0.10734418034553528 2023-01-23 15:12:32.361181: step: 2676/1545, loss: 0.012883459217846394 2023-01-23 15:12:33.227143: step: 2678/1545, loss: 0.0098087377846241 2023-01-23 15:12:34.154684: step: 2680/1545, loss: 0.005914629902690649 2023-01-23 15:12:35.013414: step: 2682/1545, loss: 0.09129206091165543 2023-01-23 15:12:35.934313: step: 2684/1545, loss: 0.1244896650314331 2023-01-23 15:12:36.767331: step: 2686/1545, loss: 0.0018957852153107524 2023-01-23 15:12:37.641559: step: 2688/1545, loss: 0.15861760079860687 2023-01-23 15:12:38.537373: step: 2690/1545, loss: 0.020176619291305542 2023-01-23 15:12:39.438516: step: 2692/1545, loss: 0.055824413895606995 2023-01-23 15:12:40.329639: step: 2694/1545, loss: 0.17302554845809937 2023-01-23 15:12:41.228578: step: 2696/1545, loss: 0.040598250925540924 2023-01-23 15:12:42.142951: step: 2698/1545, loss: 0.08587539941072464 2023-01-23 15:12:43.016711: step: 2700/1545, loss: 0.005880253855139017 2023-01-23 15:12:43.880173: step: 2702/1545, loss: 0.10870767384767532 2023-01-23 15:12:44.754808: step: 2704/1545, loss: 0.046073876321315765 2023-01-23 15:12:45.653243: step: 2706/1545, loss: 0.03764019161462784 2023-01-23 15:12:46.518751: step: 2708/1545, loss: 0.04915290325880051 2023-01-23 15:12:47.386328: step: 2710/1545, loss: 0.07777652144432068 2023-01-23 15:12:48.251282: step: 2712/1545, loss: 0.06681156903505325 2023-01-23 15:12:49.102784: step: 2714/1545, loss: 9.772319754119962e-05 2023-01-23 15:12:49.984434: step: 2716/1545, loss: 0.13838671147823334 2023-01-23 15:12:50.873610: step: 2718/1545, loss: 0.028474541381001472 2023-01-23 15:12:51.740585: step: 2720/1545, loss: 0.01621447131037712 2023-01-23 15:12:52.627467: step: 2722/1545, loss: 0.050213392823934555 2023-01-23 15:12:53.539767: step: 2724/1545, loss: 0.047543540596961975 2023-01-23 15:12:54.404815: step: 2726/1545, loss: 0.04929203912615776 2023-01-23 15:12:55.263441: step: 2728/1545, loss: 0.17311584949493408 2023-01-23 15:12:56.175941: step: 2730/1545, loss: 0.03707990050315857 2023-01-23 15:12:57.050128: step: 2732/1545, loss: 0.009108004160225391 2023-01-23 15:12:57.949032: step: 2734/1545, loss: 0.0005628199432976544 2023-01-23 15:12:58.893532: step: 2736/1545, loss: 0.003229104448109865 2023-01-23 15:12:59.775834: step: 2738/1545, loss: 0.011822992004454136 2023-01-23 15:13:00.623483: step: 2740/1545, loss: 0.025824738666415215 2023-01-23 15:13:01.467409: step: 2742/1545, loss: 0.2552461624145508 2023-01-23 15:13:02.338641: step: 2744/1545, loss: 0.2735077738761902 2023-01-23 15:13:03.301013: step: 2746/1545, loss: 0.034204378724098206 2023-01-23 15:13:04.228628: step: 2748/1545, loss: 0.007859931327402592 2023-01-23 15:13:05.101649: step: 2750/1545, loss: 0.21213310956954956 2023-01-23 15:13:06.010401: step: 2752/1545, loss: 0.33296504616737366 2023-01-23 15:13:06.885177: step: 2754/1545, loss: 0.040130291134119034 2023-01-23 15:13:07.773032: step: 2756/1545, loss: 0.006163490936160088 2023-01-23 15:13:08.667369: step: 2758/1545, loss: 0.04425111040472984 2023-01-23 15:13:09.510389: step: 2760/1545, loss: 0.0631701648235321 2023-01-23 15:13:10.350934: step: 2762/1545, loss: 0.0006647243862971663 2023-01-23 15:13:11.208501: step: 2764/1545, loss: 0.07175019383430481 2023-01-23 15:13:12.088859: step: 2766/1545, loss: 0.016797244548797607 2023-01-23 15:13:12.958855: step: 2768/1545, loss: 0.009078692644834518 2023-01-23 15:13:13.888173: step: 2770/1545, loss: 0.043111540377140045 2023-01-23 15:13:14.740283: step: 2772/1545, loss: 0.09094814956188202 2023-01-23 15:13:15.562742: step: 2774/1545, loss: 0.11440595984458923 2023-01-23 15:13:16.424829: step: 2776/1545, loss: 0.0682566687464714 2023-01-23 15:13:17.333803: step: 2778/1545, loss: 0.03797174245119095 2023-01-23 15:13:18.243077: step: 2780/1545, loss: 0.016885118559002876 2023-01-23 15:13:19.123776: step: 2782/1545, loss: 0.0022717395331710577 2023-01-23 15:13:20.002395: step: 2784/1545, loss: 0.0030738015193492174 2023-01-23 15:13:20.874193: step: 2786/1545, loss: 0.14221026003360748 2023-01-23 15:13:21.748985: step: 2788/1545, loss: 0.0016353842802345753 2023-01-23 15:13:22.587249: step: 2790/1545, loss: 0.0023135498631745577 2023-01-23 15:13:23.475899: step: 2792/1545, loss: 0.0034087379463016987 2023-01-23 15:13:24.379915: step: 2794/1545, loss: 0.0005165239563211799 2023-01-23 15:13:25.262158: step: 2796/1545, loss: 0.013375204056501389 2023-01-23 15:13:26.135656: step: 2798/1545, loss: 0.11522981524467468 2023-01-23 15:13:26.971102: step: 2800/1545, loss: 0.15719079971313477 2023-01-23 15:13:27.874933: step: 2802/1545, loss: 0.006458308082073927 2023-01-23 15:13:28.770498: step: 2804/1545, loss: 0.032074104994535446 2023-01-23 15:13:29.628736: step: 2806/1545, loss: 0.01203660573810339 2023-01-23 15:13:30.547884: step: 2808/1545, loss: 0.11766010522842407 2023-01-23 15:13:31.421988: step: 2810/1545, loss: 0.05579255148768425 2023-01-23 15:13:32.271378: step: 2812/1545, loss: 0.010207445360720158 2023-01-23 15:13:33.156224: step: 2814/1545, loss: 0.005138696637004614 2023-01-23 15:13:34.052538: step: 2816/1545, loss: 0.28489020466804504 2023-01-23 15:13:34.912040: step: 2818/1545, loss: 0.02861316129565239 2023-01-23 15:13:35.803897: step: 2820/1545, loss: 0.008073809556663036 2023-01-23 15:13:36.695851: step: 2822/1545, loss: 0.00043747990275733173 2023-01-23 15:13:37.561029: step: 2824/1545, loss: 0.001748046837747097 2023-01-23 15:13:38.436051: step: 2826/1545, loss: 0.1139778196811676 2023-01-23 15:13:39.335208: step: 2828/1545, loss: 0.02446359023451805 2023-01-23 15:13:40.252521: step: 2830/1545, loss: 0.04619434475898743 2023-01-23 15:13:41.082526: step: 2832/1545, loss: 0.0022962670773267746 2023-01-23 15:13:41.933149: step: 2834/1545, loss: 0.00925366673618555 2023-01-23 15:13:42.810897: step: 2836/1545, loss: 0.24886496365070343 2023-01-23 15:13:43.689810: step: 2838/1545, loss: 9.59872777457349e-05 2023-01-23 15:13:44.648702: step: 2840/1545, loss: 0.17957237362861633 2023-01-23 15:13:45.532227: step: 2842/1545, loss: 0.002181936986744404 2023-01-23 15:13:46.383293: step: 2844/1545, loss: 0.18797479569911957 2023-01-23 15:13:47.246085: step: 2846/1545, loss: 0.005467379931360483 2023-01-23 15:13:48.116833: step: 2848/1545, loss: 0.011919372715055943 2023-01-23 15:13:49.034815: step: 2850/1545, loss: 0.06652464717626572 2023-01-23 15:13:49.918262: step: 2852/1545, loss: 0.020473450422286987 2023-01-23 15:13:50.846006: step: 2854/1545, loss: 0.06503305584192276 2023-01-23 15:13:51.706586: step: 2856/1545, loss: 0.0007830627146176994 2023-01-23 15:13:52.604725: step: 2858/1545, loss: 0.0005547149921767414 2023-01-23 15:13:53.484267: step: 2860/1545, loss: 0.02945052832365036 2023-01-23 15:13:54.381229: step: 2862/1545, loss: 0.019574161618947983 2023-01-23 15:13:55.235718: step: 2864/1545, loss: 0.23517096042633057 2023-01-23 15:13:56.101740: step: 2866/1545, loss: 0.0005308053805492818 2023-01-23 15:13:56.981528: step: 2868/1545, loss: 0.0008101097191683948 2023-01-23 15:13:57.909617: step: 2870/1545, loss: 0.00023908246657811105 2023-01-23 15:13:58.797753: step: 2872/1545, loss: 0.13754795491695404 2023-01-23 15:13:59.655757: step: 2874/1545, loss: 0.6639178395271301 2023-01-23 15:14:00.520472: step: 2876/1545, loss: 0.0007990939193405211 2023-01-23 15:14:01.394388: step: 2878/1545, loss: 0.10367743670940399 2023-01-23 15:14:02.261488: step: 2880/1545, loss: 0.15210449695587158 2023-01-23 15:14:03.142277: step: 2882/1545, loss: 0.013850018382072449 2023-01-23 15:14:04.015515: step: 2884/1545, loss: 0.11568871885538101 2023-01-23 15:14:04.900483: step: 2886/1545, loss: 0.06071589142084122 2023-01-23 15:14:05.794126: step: 2888/1545, loss: 0.009850879199802876 2023-01-23 15:14:06.692205: step: 2890/1545, loss: 0.036528509110212326 2023-01-23 15:14:07.590119: step: 2892/1545, loss: 0.001233179704286158 2023-01-23 15:14:08.475351: step: 2894/1545, loss: 0.03245006501674652 2023-01-23 15:14:09.374569: step: 2896/1545, loss: 0.00726949330419302 2023-01-23 15:14:10.270039: step: 2898/1545, loss: 0.0071244072169065475 2023-01-23 15:14:11.112280: step: 2900/1545, loss: 0.017329750582575798 2023-01-23 15:14:11.981103: step: 2902/1545, loss: 0.7711365818977356 2023-01-23 15:14:12.847634: step: 2904/1545, loss: 0.07791135460138321 2023-01-23 15:14:13.793505: step: 2906/1545, loss: 0.3451654016971588 2023-01-23 15:14:14.698809: step: 2908/1545, loss: 0.24279266595840454 2023-01-23 15:14:15.617605: step: 2910/1545, loss: 0.09923732280731201 2023-01-23 15:14:16.540700: step: 2912/1545, loss: 0.22334273159503937 2023-01-23 15:14:17.400866: step: 2914/1545, loss: 0.5733891129493713 2023-01-23 15:14:18.259549: step: 2916/1545, loss: 0.01775972917675972 2023-01-23 15:14:19.122407: step: 2918/1545, loss: 0.00114960758946836 2023-01-23 15:14:19.969853: step: 2920/1545, loss: 0.055617086589336395 2023-01-23 15:14:20.875678: step: 2922/1545, loss: 0.0007539289654232562 2023-01-23 15:14:21.721950: step: 2924/1545, loss: 0.12902015447616577 2023-01-23 15:14:22.613312: step: 2926/1545, loss: 0.002480532741174102 2023-01-23 15:14:23.500545: step: 2928/1545, loss: 0.18044474720954895 2023-01-23 15:14:24.351351: step: 2930/1545, loss: 0.11384857445955276 2023-01-23 15:14:25.213507: step: 2932/1545, loss: 0.3709774911403656 2023-01-23 15:14:26.040759: step: 2934/1545, loss: 0.10716182738542557 2023-01-23 15:14:26.939593: step: 2936/1545, loss: 0.025612816214561462 2023-01-23 15:14:27.799976: step: 2938/1545, loss: 0.0007337032584473491 2023-01-23 15:14:28.683513: step: 2940/1545, loss: 0.09609105437994003 2023-01-23 15:14:29.572274: step: 2942/1545, loss: 0.1021105945110321 2023-01-23 15:14:30.485679: step: 2944/1545, loss: 0.01442644465714693 2023-01-23 15:14:31.368283: step: 2946/1545, loss: 0.032503049820661545 2023-01-23 15:14:32.293479: step: 2948/1545, loss: 0.02846403233706951 2023-01-23 15:14:33.163360: step: 2950/1545, loss: 0.0444309301674366 2023-01-23 15:14:34.047947: step: 2952/1545, loss: 0.005660250782966614 2023-01-23 15:14:34.952056: step: 2954/1545, loss: 0.08195208758115768 2023-01-23 15:14:35.858235: step: 2956/1545, loss: 0.057091835886240005 2023-01-23 15:14:36.723202: step: 2958/1545, loss: 0.10692233592271805 2023-01-23 15:14:37.657168: step: 2960/1545, loss: 0.2949546277523041 2023-01-23 15:14:38.528169: step: 2962/1545, loss: 2.0298383235931396 2023-01-23 15:14:39.382520: step: 2964/1545, loss: 0.027752229943871498 2023-01-23 15:14:40.260110: step: 2966/1545, loss: 0.1661408394575119 2023-01-23 15:14:41.098872: step: 2968/1545, loss: 0.003676370019093156 2023-01-23 15:14:42.004072: step: 2970/1545, loss: 0.09664304554462433 2023-01-23 15:14:42.856216: step: 2972/1545, loss: 0.061126772314310074 2023-01-23 15:14:43.722618: step: 2974/1545, loss: 0.12724162638187408 2023-01-23 15:14:44.598812: step: 2976/1545, loss: 0.7763124704360962 2023-01-23 15:14:45.472542: step: 2978/1545, loss: 0.18714284896850586 2023-01-23 15:14:46.359729: step: 2980/1545, loss: 0.06247793510556221 2023-01-23 15:14:47.237265: step: 2982/1545, loss: 0.21269693970680237 2023-01-23 15:14:48.042186: step: 2984/1545, loss: 0.08144569396972656 2023-01-23 15:14:48.945013: step: 2986/1545, loss: 0.08175959438085556 2023-01-23 15:14:49.845365: step: 2988/1545, loss: 0.012633749283850193 2023-01-23 15:14:50.722302: step: 2990/1545, loss: 0.3105424642562866 2023-01-23 15:14:51.605745: step: 2992/1545, loss: 0.00833258219063282 2023-01-23 15:14:52.467490: step: 2994/1545, loss: 0.047866322100162506 2023-01-23 15:14:53.338183: step: 2996/1545, loss: 0.017116190865635872 2023-01-23 15:14:54.209076: step: 2998/1545, loss: 0.007831730879843235 2023-01-23 15:14:55.142576: step: 3000/1545, loss: 0.044908709824085236 2023-01-23 15:14:56.015025: step: 3002/1545, loss: 0.007697475142776966 2023-01-23 15:14:56.859580: step: 3004/1545, loss: 0.004250210709869862 2023-01-23 15:14:57.777204: step: 3006/1545, loss: 0.18162767589092255 2023-01-23 15:14:58.662784: step: 3008/1545, loss: 0.2547486424446106 2023-01-23 15:14:59.539983: step: 3010/1545, loss: 0.13432082533836365 2023-01-23 15:15:00.400092: step: 3012/1545, loss: 9.102167129516602 2023-01-23 15:15:01.278865: step: 3014/1545, loss: 0.47692999243736267 2023-01-23 15:15:02.153759: step: 3016/1545, loss: 0.05339985340833664 2023-01-23 15:15:03.052999: step: 3018/1545, loss: 0.10660616308450699 2023-01-23 15:15:03.922223: step: 3020/1545, loss: 0.014075912535190582 2023-01-23 15:15:04.796139: step: 3022/1545, loss: 0.20329883694648743 2023-01-23 15:15:05.620554: step: 3024/1545, loss: 0.0010616478975862265 2023-01-23 15:15:06.487955: step: 3026/1545, loss: 0.9835612773895264 2023-01-23 15:15:07.346006: step: 3028/1545, loss: 0.04849400743842125 2023-01-23 15:15:08.213333: step: 3030/1545, loss: 0.04110913351178169 2023-01-23 15:15:09.138024: step: 3032/1545, loss: 0.001935556996613741 2023-01-23 15:15:10.008942: step: 3034/1545, loss: 0.01535413134843111 2023-01-23 15:15:10.885149: step: 3036/1545, loss: 0.025506647303700447 2023-01-23 15:15:11.785782: step: 3038/1545, loss: 0.0493423268198967 2023-01-23 15:15:12.675239: step: 3040/1545, loss: 0.004516486544162035 2023-01-23 15:15:13.527599: step: 3042/1545, loss: 0.06276322156190872 2023-01-23 15:15:14.355348: step: 3044/1545, loss: 0.0003678979119285941 2023-01-23 15:15:15.232976: step: 3046/1545, loss: 0.015108766034245491 2023-01-23 15:15:16.100051: step: 3048/1545, loss: 0.00486653670668602 2023-01-23 15:15:16.998970: step: 3050/1545, loss: 0.027698004618287086 2023-01-23 15:15:17.905974: step: 3052/1545, loss: 0.0539233535528183 2023-01-23 15:15:18.838883: step: 3054/1545, loss: 0.019874604418873787 2023-01-23 15:15:19.723977: step: 3056/1545, loss: 0.0036088034976273775 2023-01-23 15:15:20.619948: step: 3058/1545, loss: 0.6306633353233337 2023-01-23 15:15:21.521887: step: 3060/1545, loss: 0.12370522320270538 2023-01-23 15:15:22.481661: step: 3062/1545, loss: 0.007969006896018982 2023-01-23 15:15:23.340456: step: 3064/1545, loss: 0.0013932338915765285 2023-01-23 15:15:24.284081: step: 3066/1545, loss: 0.07992830872535706 2023-01-23 15:15:25.166544: step: 3068/1545, loss: 0.051831264048814774 2023-01-23 15:15:26.043381: step: 3070/1545, loss: 0.15876220166683197 2023-01-23 15:15:26.917484: step: 3072/1545, loss: 0.005347584839910269 2023-01-23 15:15:27.789611: step: 3074/1545, loss: 0.022930504754185677 2023-01-23 15:15:28.672650: step: 3076/1545, loss: 0.26214075088500977 2023-01-23 15:15:29.525296: step: 3078/1545, loss: 0.1383112519979477 2023-01-23 15:15:30.398819: step: 3080/1545, loss: 0.04770740494132042 2023-01-23 15:15:31.277126: step: 3082/1545, loss: 0.08292365074157715 2023-01-23 15:15:32.160671: step: 3084/1545, loss: 0.07371142506599426 2023-01-23 15:15:33.006143: step: 3086/1545, loss: 0.08550452440977097 2023-01-23 15:15:33.871305: step: 3088/1545, loss: 0.0008882317342795432 2023-01-23 15:15:34.700874: step: 3090/1545, loss: 0.0005659238086082041 ================================================== Loss: 0.108 -------------------- Dev Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6752094979248321, 'r': 0.6468648713252889, 'f1': 0.6607333371729981}, 'combined': 0.436527660410458, 'epoch': 21} Test Chinese: {'event': {'p': 0.6419423692636073, 'r': 0.7691815856777494, 'f1': 0.6998254799301921}, 'argument': {'p': 0.7117491540587041, 'r': 0.703334118293708, 'f1': 0.7075166154483417}, 'combined': 0.49513815496472086, 'epoch': 21} Dev Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Dev Russian: {'event': {'p': 0.5738188976377953, 'r': 0.7762982689747004, 'f1': 0.6598754951895868}, 'argument': {'p': 0.6755193864987635, 'r': 0.6532760852969431, 'f1': 0.6642115656185077}, 'combined': 0.4382969357731635, 'epoch': 21} Test Russian: {'event': {'p': 0.6307922272047832, 'r': 0.809462915601023, 'f1': 0.7090450854102492}, 'argument': {'p': 0.7168265240567604, 'r': 0.7149493128078276, 'f1': 0.7158866878199376}, 'combined': 0.5075959377093481, 'epoch': 21} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6905940594059405, 'r': 0.5764462809917356, 'f1': 0.6283783783783784}, 'combined': 0.4379606879606881, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.6180519634839396, 'r': 0.5849420368687286, 'f1': 0.6010413589843816}, 'combined': 0.3195409756625826, 'epoch': 21} New best korean model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 22 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 15:20:56.820070: step: 2/1545, loss: 0.09232566505670547 2023-01-23 15:20:57.678628: step: 4/1545, loss: 0.022531891241669655 2023-01-23 15:20:58.564029: step: 6/1545, loss: 0.004763555712997913 2023-01-23 15:20:59.552432: step: 8/1545, loss: 0.0011269374517723918 2023-01-23 15:21:00.452770: step: 10/1545, loss: 0.00023577189131174237 2023-01-23 15:21:01.306997: step: 12/1545, loss: 0.006538247689604759 2023-01-23 15:21:02.211676: step: 14/1545, loss: 0.1234399750828743 2023-01-23 15:21:03.078795: step: 16/1545, loss: 0.0039044178556650877 2023-01-23 15:21:03.954881: step: 18/1545, loss: 0.0005231430986896157 2023-01-23 15:21:04.856834: step: 20/1545, loss: 0.17644335329532623 2023-01-23 15:21:05.700509: step: 22/1545, loss: 0.0007428106619045138 2023-01-23 15:21:06.588253: step: 24/1545, loss: 0.014985878951847553 2023-01-23 15:21:07.426520: step: 26/1545, loss: 0.22382114827632904 2023-01-23 15:21:08.284361: step: 28/1545, loss: 0.0022601361852139235 2023-01-23 15:21:09.156662: step: 30/1545, loss: 0.05468360334634781 2023-01-23 15:21:10.032449: step: 32/1545, loss: 0.04430758208036423 2023-01-23 15:21:10.906667: step: 34/1545, loss: 0.000953943352214992 2023-01-23 15:21:11.826549: step: 36/1545, loss: 0.012125770561397076 2023-01-23 15:21:12.689725: step: 38/1545, loss: 0.01852652058005333 2023-01-23 15:21:13.603012: step: 40/1545, loss: 0.055534470826387405 2023-01-23 15:21:14.540549: step: 42/1545, loss: 1.483591079711914 2023-01-23 15:21:15.389620: step: 44/1545, loss: 0.007321206387132406 2023-01-23 15:21:16.250261: step: 46/1545, loss: 0.0060988860204815865 2023-01-23 15:21:17.119369: step: 48/1545, loss: 0.007542099803686142 2023-01-23 15:21:18.012565: step: 50/1545, loss: 0.00828738696873188 2023-01-23 15:21:18.904421: step: 52/1545, loss: 0.0019117548363283277 2023-01-23 15:21:19.749784: step: 54/1545, loss: 0.07673737406730652 2023-01-23 15:21:20.667158: step: 56/1545, loss: 0.1636819988489151 2023-01-23 15:21:21.516233: step: 58/1545, loss: 0.004707323387265205 2023-01-23 15:21:22.408193: step: 60/1545, loss: 0.04870734363794327 2023-01-23 15:21:23.265957: step: 62/1545, loss: 0.0030490155331790447 2023-01-23 15:21:24.145078: step: 64/1545, loss: 0.005405389703810215 2023-01-23 15:21:25.012954: step: 66/1545, loss: 0.0032606448512524366 2023-01-23 15:21:25.870468: step: 68/1545, loss: 0.012353213503956795 2023-01-23 15:21:26.769138: step: 70/1545, loss: 0.004317210987210274 2023-01-23 15:21:27.646198: step: 72/1545, loss: 0.0002724801597651094 2023-01-23 15:21:28.531814: step: 74/1545, loss: 0.24110516905784607 2023-01-23 15:21:29.416869: step: 76/1545, loss: 0.00541880214586854 2023-01-23 15:21:30.272983: step: 78/1545, loss: 0.008382458239793777 2023-01-23 15:21:31.113740: step: 80/1545, loss: 0.11681757867336273 2023-01-23 15:21:31.976846: step: 82/1545, loss: 0.025851650163531303 2023-01-23 15:21:32.883792: step: 84/1545, loss: 0.036868978291749954 2023-01-23 15:21:33.740270: step: 86/1545, loss: 0.025546256452798843 2023-01-23 15:21:34.617645: step: 88/1545, loss: 0.47129979729652405 2023-01-23 15:21:35.523149: step: 90/1545, loss: 0.10411648452281952 2023-01-23 15:21:36.401976: step: 92/1545, loss: 0.25711604952812195 2023-01-23 15:21:37.269966: step: 94/1545, loss: 0.002654802519828081 2023-01-23 15:21:38.151330: step: 96/1545, loss: 0.028167417272925377 2023-01-23 15:21:39.010001: step: 98/1545, loss: 0.018291708081960678 2023-01-23 15:21:39.888465: step: 100/1545, loss: 0.00033079684362746775 2023-01-23 15:21:40.757395: step: 102/1545, loss: 0.0013584960252046585 2023-01-23 15:21:41.653366: step: 104/1545, loss: 0.0022940330673009157 2023-01-23 15:21:42.567543: step: 106/1545, loss: 0.00045130279613658786 2023-01-23 15:21:43.449999: step: 108/1545, loss: 0.05156085640192032 2023-01-23 15:21:44.308710: step: 110/1545, loss: 0.0008485703729093075 2023-01-23 15:21:45.165505: step: 112/1545, loss: 0.0005785019602626562 2023-01-23 15:21:46.028424: step: 114/1545, loss: 0.01150551624596119 2023-01-23 15:21:46.870395: step: 116/1545, loss: 0.08107419312000275 2023-01-23 15:21:47.742107: step: 118/1545, loss: 0.4723512530326843 2023-01-23 15:21:48.745825: step: 120/1545, loss: 0.030012134462594986 2023-01-23 15:21:49.682135: step: 122/1545, loss: 0.03648286312818527 2023-01-23 15:21:50.542571: step: 124/1545, loss: 0.038712453097105026 2023-01-23 15:21:51.514650: step: 126/1545, loss: 0.020692626014351845 2023-01-23 15:21:52.399292: step: 128/1545, loss: 0.03228515759110451 2023-01-23 15:21:53.313471: step: 130/1545, loss: 0.20018920302391052 2023-01-23 15:21:54.179139: step: 132/1545, loss: 0.1922421157360077 2023-01-23 15:21:55.104607: step: 134/1545, loss: 0.1059962809085846 2023-01-23 15:21:56.044232: step: 136/1545, loss: 0.0005394984618760645 2023-01-23 15:21:57.008636: step: 138/1545, loss: 0.03531412407755852 2023-01-23 15:21:57.898417: step: 140/1545, loss: 0.1474304348230362 2023-01-23 15:21:58.828407: step: 142/1545, loss: 0.017455987632274628 2023-01-23 15:21:59.680877: step: 144/1545, loss: 0.06780198961496353 2023-01-23 15:22:00.571235: step: 146/1545, loss: 0.0010914778104051948 2023-01-23 15:22:01.440500: step: 148/1545, loss: 0.008111891336739063 2023-01-23 15:22:02.349610: step: 150/1545, loss: 0.00832340307533741 2023-01-23 15:22:03.222627: step: 152/1545, loss: 0.13404183089733124 2023-01-23 15:22:04.066331: step: 154/1545, loss: 0.1981598436832428 2023-01-23 15:22:04.936513: step: 156/1545, loss: 0.23133155703544617 2023-01-23 15:22:05.813252: step: 158/1545, loss: 0.003725311253219843 2023-01-23 15:22:06.714174: step: 160/1545, loss: 0.00720070768147707 2023-01-23 15:22:07.602797: step: 162/1545, loss: 0.0018639216432347894 2023-01-23 15:22:08.431259: step: 164/1545, loss: 0.005773134995251894 2023-01-23 15:22:09.318876: step: 166/1545, loss: 0.0013225509319454432 2023-01-23 15:22:10.231511: step: 168/1545, loss: 0.06617218255996704 2023-01-23 15:22:11.161682: step: 170/1545, loss: 0.5753408074378967 2023-01-23 15:22:12.048789: step: 172/1545, loss: 0.007884103804826736 2023-01-23 15:22:12.925316: step: 174/1545, loss: 0.1454053670167923 2023-01-23 15:22:13.811944: step: 176/1545, loss: 0.42309466004371643 2023-01-23 15:22:14.690860: step: 178/1545, loss: 0.007276119198650122 2023-01-23 15:22:15.588883: step: 180/1545, loss: 0.017733454704284668 2023-01-23 15:22:16.473897: step: 182/1545, loss: 0.012597906403243542 2023-01-23 15:22:17.362192: step: 184/1545, loss: 0.41192826628685 2023-01-23 15:22:18.244978: step: 186/1545, loss: 0.0015551322139799595 2023-01-23 15:22:19.105757: step: 188/1545, loss: 0.31870296597480774 2023-01-23 15:22:19.995733: step: 190/1545, loss: 0.10940230637788773 2023-01-23 15:22:20.862775: step: 192/1545, loss: 0.0005495993536897004 2023-01-23 15:22:21.736665: step: 194/1545, loss: 0.008061259984970093 2023-01-23 15:22:22.650111: step: 196/1545, loss: 0.012234962545335293 2023-01-23 15:22:23.567476: step: 198/1545, loss: 0.00832321960479021 2023-01-23 15:22:24.465062: step: 200/1545, loss: 0.09039268642663956 2023-01-23 15:22:25.417950: step: 202/1545, loss: 0.047220151871442795 2023-01-23 15:22:26.417405: step: 204/1545, loss: 0.0019856628496199846 2023-01-23 15:22:27.312438: step: 206/1545, loss: 0.00017207636847160757 2023-01-23 15:22:28.161937: step: 208/1545, loss: 0.0146741708740592 2023-01-23 15:22:29.048381: step: 210/1545, loss: 0.004380497150123119 2023-01-23 15:22:29.926862: step: 212/1545, loss: 0.019938059151172638 2023-01-23 15:22:30.814184: step: 214/1545, loss: 0.4966529309749603 2023-01-23 15:22:31.792755: step: 216/1545, loss: 0.003874594811350107 2023-01-23 15:22:32.675812: step: 218/1545, loss: 0.0004013621364720166 2023-01-23 15:22:33.652767: step: 220/1545, loss: 0.031147079542279243 2023-01-23 15:22:34.550534: step: 222/1545, loss: 0.12032902240753174 2023-01-23 15:22:35.437861: step: 224/1545, loss: 0.001684596878476441 2023-01-23 15:22:36.319064: step: 226/1545, loss: 0.03437306731939316 2023-01-23 15:22:37.233406: step: 228/1545, loss: 0.05944987013936043 2023-01-23 15:22:38.098556: step: 230/1545, loss: 0.00637689046561718 2023-01-23 15:22:38.936366: step: 232/1545, loss: 0.001073880004696548 2023-01-23 15:22:39.821751: step: 234/1545, loss: 0.626213550567627 2023-01-23 15:22:40.670117: step: 236/1545, loss: 0.000259869615547359 2023-01-23 15:22:41.605201: step: 238/1545, loss: 0.02726856805384159 2023-01-23 15:22:42.531180: step: 240/1545, loss: 0.012367187067866325 2023-01-23 15:22:43.416891: step: 242/1545, loss: 0.013938667252659798 2023-01-23 15:22:44.346864: step: 244/1545, loss: 1.3351565599441528 2023-01-23 15:22:45.250322: step: 246/1545, loss: 0.04587823897600174 2023-01-23 15:22:46.076583: step: 248/1545, loss: 0.10265598446130753 2023-01-23 15:22:46.963508: step: 250/1545, loss: 0.001685630064457655 2023-01-23 15:22:47.802082: step: 252/1545, loss: 0.33070242404937744 2023-01-23 15:22:48.654617: step: 254/1545, loss: 0.304029256105423 2023-01-23 15:22:49.621421: step: 256/1545, loss: 0.0026582370046526194 2023-01-23 15:22:50.528657: step: 258/1545, loss: 0.09610661119222641 2023-01-23 15:22:51.377723: step: 260/1545, loss: 0.0016119731590151787 2023-01-23 15:22:52.255668: step: 262/1545, loss: 0.25911134481430054 2023-01-23 15:22:53.174445: step: 264/1545, loss: 0.4623451232910156 2023-01-23 15:22:54.094780: step: 266/1545, loss: 0.01669888012111187 2023-01-23 15:22:54.993813: step: 268/1545, loss: 0.005273872055113316 2023-01-23 15:22:55.840508: step: 270/1545, loss: 0.003340307157486677 2023-01-23 15:22:56.758837: step: 272/1545, loss: 0.047839682549238205 2023-01-23 15:22:57.637815: step: 274/1545, loss: 0.01288793794810772 2023-01-23 15:22:58.487303: step: 276/1545, loss: 0.0006274202605709434 2023-01-23 15:22:59.361955: step: 278/1545, loss: 0.009598508477210999 2023-01-23 15:23:00.234531: step: 280/1545, loss: 0.0023454332258552313 2023-01-23 15:23:01.155978: step: 282/1545, loss: 0.3582892119884491 2023-01-23 15:23:02.013076: step: 284/1545, loss: 0.01808392070233822 2023-01-23 15:23:02.897504: step: 286/1545, loss: 0.5951316356658936 2023-01-23 15:23:03.752883: step: 288/1545, loss: 0.02543770894408226 2023-01-23 15:23:04.745457: step: 290/1545, loss: 0.016034122556447983 2023-01-23 15:23:05.650475: step: 292/1545, loss: 0.27401891350746155 2023-01-23 15:23:06.533835: step: 294/1545, loss: 0.31355878710746765 2023-01-23 15:23:07.474355: step: 296/1545, loss: 0.00027713057352229953 2023-01-23 15:23:08.382144: step: 298/1545, loss: 0.004077351652085781 2023-01-23 15:23:09.250154: step: 300/1545, loss: 0.1333065629005432 2023-01-23 15:23:10.179700: step: 302/1545, loss: 0.011681707575917244 2023-01-23 15:23:11.032468: step: 304/1545, loss: 0.007944812998175621 2023-01-23 15:23:11.882749: step: 306/1545, loss: 0.00010849820682778955 2023-01-23 15:23:12.742218: step: 308/1545, loss: 0.004664361011236906 2023-01-23 15:23:13.603257: step: 310/1545, loss: 0.009898609481751919 2023-01-23 15:23:14.475764: step: 312/1545, loss: 0.10154473036527634 2023-01-23 15:23:15.372490: step: 314/1545, loss: 0.11857099831104279 2023-01-23 15:23:16.231433: step: 316/1545, loss: 0.15709079802036285 2023-01-23 15:23:17.076306: step: 318/1545, loss: 0.03385881334543228 2023-01-23 15:23:17.924537: step: 320/1545, loss: 0.0009209824493154883 2023-01-23 15:23:18.862045: step: 322/1545, loss: 0.008200544863939285 2023-01-23 15:23:19.744005: step: 324/1545, loss: 0.07188384979963303 2023-01-23 15:23:20.633695: step: 326/1545, loss: 0.0014181920560076833 2023-01-23 15:23:21.517770: step: 328/1545, loss: 0.0011964351870119572 2023-01-23 15:23:22.412054: step: 330/1545, loss: 0.0007456359453499317 2023-01-23 15:23:23.263012: step: 332/1545, loss: 0.00011687896039802581 2023-01-23 15:23:24.182159: step: 334/1545, loss: 0.2015170454978943 2023-01-23 15:23:25.049160: step: 336/1545, loss: 0.009213052690029144 2023-01-23 15:23:25.941879: step: 338/1545, loss: 0.002851489232853055 2023-01-23 15:23:26.812412: step: 340/1545, loss: 0.17163270711898804 2023-01-23 15:23:27.706504: step: 342/1545, loss: 0.005946493241935968 2023-01-23 15:23:28.596214: step: 344/1545, loss: 0.007309326436370611 2023-01-23 15:23:29.469436: step: 346/1545, loss: 0.009645509533584118 2023-01-23 15:23:30.349500: step: 348/1545, loss: 0.0003123597416561097 2023-01-23 15:23:31.270017: step: 350/1545, loss: 0.04916428029537201 2023-01-23 15:23:32.146930: step: 352/1545, loss: 0.5479440093040466 2023-01-23 15:23:33.000890: step: 354/1545, loss: 0.05842477083206177 2023-01-23 15:23:33.857045: step: 356/1545, loss: 0.18177013099193573 2023-01-23 15:23:34.794398: step: 358/1545, loss: 0.1049380749464035 2023-01-23 15:23:35.728349: step: 360/1545, loss: 0.1638074666261673 2023-01-23 15:23:36.591541: step: 362/1545, loss: 0.0005812791641801596 2023-01-23 15:23:37.431530: step: 364/1545, loss: 0.002223407616838813 2023-01-23 15:23:38.276147: step: 366/1545, loss: 0.01271500252187252 2023-01-23 15:23:39.176486: step: 368/1545, loss: 0.4966958463191986 2023-01-23 15:23:40.050596: step: 370/1545, loss: 0.04830441251397133 2023-01-23 15:23:40.905753: step: 372/1545, loss: 0.07074573636054993 2023-01-23 15:23:41.779180: step: 374/1545, loss: 0.022645464166998863 2023-01-23 15:23:42.659075: step: 376/1545, loss: 0.005963361356407404 2023-01-23 15:23:43.564195: step: 378/1545, loss: 0.00253305840305984 2023-01-23 15:23:44.447644: step: 380/1545, loss: 0.09118247032165527 2023-01-23 15:23:45.297128: step: 382/1545, loss: 0.004735639318823814 2023-01-23 15:23:46.175612: step: 384/1545, loss: 0.09652277827262878 2023-01-23 15:23:47.059028: step: 386/1545, loss: 0.019447186961770058 2023-01-23 15:23:47.902394: step: 388/1545, loss: 0.09102456271648407 2023-01-23 15:23:48.815006: step: 390/1545, loss: 0.028240840882062912 2023-01-23 15:23:49.731029: step: 392/1545, loss: 0.01797867938876152 2023-01-23 15:23:50.590124: step: 394/1545, loss: 0.0002980446442961693 2023-01-23 15:23:51.431765: step: 396/1545, loss: 0.08912315964698792 2023-01-23 15:23:52.300189: step: 398/1545, loss: 0.0005423097172752023 2023-01-23 15:23:53.167271: step: 400/1545, loss: 0.02816365472972393 2023-01-23 15:23:54.054284: step: 402/1545, loss: 0.10309839993715286 2023-01-23 15:23:54.945935: step: 404/1545, loss: 0.014959851279854774 2023-01-23 15:23:55.805283: step: 406/1545, loss: 0.005082927644252777 2023-01-23 15:23:56.681510: step: 408/1545, loss: 0.0003624694363679737 2023-01-23 15:23:57.567227: step: 410/1545, loss: 0.01439732313156128 2023-01-23 15:23:58.441193: step: 412/1545, loss: 0.19441458582878113 2023-01-23 15:23:59.276765: step: 414/1545, loss: 0.000968962674960494 2023-01-23 15:24:00.115545: step: 416/1545, loss: 0.13854441046714783 2023-01-23 15:24:01.031278: step: 418/1545, loss: 0.21458014845848083 2023-01-23 15:24:01.931115: step: 420/1545, loss: 0.007194013800472021 2023-01-23 15:24:02.793865: step: 422/1545, loss: 0.011823375709354877 2023-01-23 15:24:03.656992: step: 424/1545, loss: 0.0019196438370272517 2023-01-23 15:24:04.587026: step: 426/1545, loss: 0.05351319909095764 2023-01-23 15:24:05.432129: step: 428/1545, loss: 0.03149334713816643 2023-01-23 15:24:06.336373: step: 430/1545, loss: 0.029910176992416382 2023-01-23 15:24:07.210448: step: 432/1545, loss: 0.004575551021844149 2023-01-23 15:24:08.097024: step: 434/1545, loss: 0.19331680238246918 2023-01-23 15:24:08.995200: step: 436/1545, loss: 0.023368939757347107 2023-01-23 15:24:09.871280: step: 438/1545, loss: 0.005614809226244688 2023-01-23 15:24:10.803797: step: 440/1545, loss: 0.010508444160223007 2023-01-23 15:24:11.683829: step: 442/1545, loss: 0.12722034752368927 2023-01-23 15:24:12.620827: step: 444/1545, loss: 0.19997447729110718 2023-01-23 15:24:13.518149: step: 446/1545, loss: 0.04089535400271416 2023-01-23 15:24:14.392827: step: 448/1545, loss: 0.003201638115569949 2023-01-23 15:24:15.339635: step: 450/1545, loss: 0.012372731231153011 2023-01-23 15:24:16.226929: step: 452/1545, loss: 0.1526845246553421 2023-01-23 15:24:17.094645: step: 454/1545, loss: 0.00832473672926426 2023-01-23 15:24:17.990772: step: 456/1545, loss: 0.09354302287101746 2023-01-23 15:24:18.831755: step: 458/1545, loss: 0.011384587734937668 2023-01-23 15:24:19.735887: step: 460/1545, loss: 0.006502086296677589 2023-01-23 15:24:20.629438: step: 462/1545, loss: 0.008563203737139702 2023-01-23 15:24:21.503253: step: 464/1545, loss: 0.0034125889651477337 2023-01-23 15:24:22.367901: step: 466/1545, loss: 0.006941859144717455 2023-01-23 15:24:23.226232: step: 468/1545, loss: 0.03042829968035221 2023-01-23 15:24:24.132675: step: 470/1545, loss: 0.05544710531830788 2023-01-23 15:24:24.986069: step: 472/1545, loss: 0.08259201794862747 2023-01-23 15:24:25.810703: step: 474/1545, loss: 0.30010920763015747 2023-01-23 15:24:26.760588: step: 476/1545, loss: 0.28895339369773865 2023-01-23 15:24:27.665823: step: 478/1545, loss: 1.3354620933532715 2023-01-23 15:24:28.582278: step: 480/1545, loss: 0.1579185277223587 2023-01-23 15:24:29.460377: step: 482/1545, loss: 0.01518202479928732 2023-01-23 15:24:30.382010: step: 484/1545, loss: 0.10789704322814941 2023-01-23 15:24:31.253088: step: 486/1545, loss: 0.2015663981437683 2023-01-23 15:24:32.138197: step: 488/1545, loss: 0.1241651251912117 2023-01-23 15:24:33.140580: step: 490/1545, loss: 0.07134240865707397 2023-01-23 15:24:34.036184: step: 492/1545, loss: 0.09699150174856186 2023-01-23 15:24:34.935155: step: 494/1545, loss: 0.020184064283967018 2023-01-23 15:24:35.809091: step: 496/1545, loss: 0.0022483791690319777 2023-01-23 15:24:36.773256: step: 498/1545, loss: 0.2821812927722931 2023-01-23 15:24:37.694632: step: 500/1545, loss: 0.12761446833610535 2023-01-23 15:24:38.610313: step: 502/1545, loss: 0.03982317075133324 2023-01-23 15:24:39.465523: step: 504/1545, loss: 0.0864720270037651 2023-01-23 15:24:40.365022: step: 506/1545, loss: 0.17601065337657928 2023-01-23 15:24:41.224742: step: 508/1545, loss: 0.37226149439811707 2023-01-23 15:24:42.138975: step: 510/1545, loss: 0.0883561223745346 2023-01-23 15:24:42.987959: step: 512/1545, loss: 0.23856675624847412 2023-01-23 15:24:43.876108: step: 514/1545, loss: 0.08095617592334747 2023-01-23 15:24:44.751631: step: 516/1545, loss: 0.0032097026705741882 2023-01-23 15:24:45.651550: step: 518/1545, loss: 0.0013869223184883595 2023-01-23 15:24:46.566744: step: 520/1545, loss: 0.04639020934700966 2023-01-23 15:24:47.462925: step: 522/1545, loss: 0.12067723274230957 2023-01-23 15:24:48.352510: step: 524/1545, loss: 0.173246830701828 2023-01-23 15:24:49.284977: step: 526/1545, loss: 0.04050809517502785 2023-01-23 15:24:50.254455: step: 528/1545, loss: 0.03136977180838585 2023-01-23 15:24:51.112601: step: 530/1545, loss: 0.25648224353790283 2023-01-23 15:24:51.959035: step: 532/1545, loss: 0.1701303869485855 2023-01-23 15:24:52.830164: step: 534/1545, loss: 0.4100149869918823 2023-01-23 15:24:53.707845: step: 536/1545, loss: 0.0020024206023663282 2023-01-23 15:24:54.579076: step: 538/1545, loss: 0.04296937584877014 2023-01-23 15:24:55.467369: step: 540/1545, loss: 0.010930719785392284 2023-01-23 15:24:56.327963: step: 542/1545, loss: 0.04383077472448349 2023-01-23 15:24:57.204438: step: 544/1545, loss: 0.021716993302106857 2023-01-23 15:24:58.102576: step: 546/1545, loss: 0.14354491233825684 2023-01-23 15:24:58.968748: step: 548/1545, loss: 0.0045598940923810005 2023-01-23 15:24:59.835983: step: 550/1545, loss: 0.0036283954977989197 2023-01-23 15:25:00.725025: step: 552/1545, loss: 0.12258616834878922 2023-01-23 15:25:01.615103: step: 554/1545, loss: 0.015497938729822636 2023-01-23 15:25:02.504891: step: 556/1545, loss: 0.17576664686203003 2023-01-23 15:25:03.385047: step: 558/1545, loss: 0.196164071559906 2023-01-23 15:25:04.275621: step: 560/1545, loss: 0.014952722936868668 2023-01-23 15:25:05.129258: step: 562/1545, loss: 1.7665143013000488 2023-01-23 15:25:05.994899: step: 564/1545, loss: 0.15796323120594025 2023-01-23 15:25:06.871389: step: 566/1545, loss: 0.005882645957171917 2023-01-23 15:25:07.732459: step: 568/1545, loss: 0.03328433632850647 2023-01-23 15:25:08.587001: step: 570/1545, loss: 0.029141487553715706 2023-01-23 15:25:09.449665: step: 572/1545, loss: 0.0018584304489195347 2023-01-23 15:25:10.341062: step: 574/1545, loss: 0.0776299238204956 2023-01-23 15:25:11.207557: step: 576/1545, loss: 1.1035821437835693 2023-01-23 15:25:12.089947: step: 578/1545, loss: 0.006844751536846161 2023-01-23 15:25:13.015662: step: 580/1545, loss: 0.01793752983212471 2023-01-23 15:25:13.913885: step: 582/1545, loss: 0.0007732117082923651 2023-01-23 15:25:14.780639: step: 584/1545, loss: 0.0021347198635339737 2023-01-23 15:25:15.673921: step: 586/1545, loss: 0.029224544763565063 2023-01-23 15:25:16.554069: step: 588/1545, loss: 0.0034575527533888817 2023-01-23 15:25:17.440309: step: 590/1545, loss: 0.001093184924684465 2023-01-23 15:25:18.276455: step: 592/1545, loss: 0.0057007186114788055 2023-01-23 15:25:19.151582: step: 594/1545, loss: 0.0013534494210034609 2023-01-23 15:25:20.011862: step: 596/1545, loss: 0.00010475922317709774 2023-01-23 15:25:20.862775: step: 598/1545, loss: 0.18320126831531525 2023-01-23 15:25:21.735243: step: 600/1545, loss: 0.08885079622268677 2023-01-23 15:25:22.574422: step: 602/1545, loss: 0.000552046753000468 2023-01-23 15:25:23.454526: step: 604/1545, loss: 0.0035994600038975477 2023-01-23 15:25:24.324918: step: 606/1545, loss: 0.1923850178718567 2023-01-23 15:25:25.246885: step: 608/1545, loss: 0.11199034750461578 2023-01-23 15:25:26.132048: step: 610/1545, loss: 0.0026537629310041666 2023-01-23 15:25:27.036506: step: 612/1545, loss: 0.9340335726737976 2023-01-23 15:25:27.911047: step: 614/1545, loss: 0.00270571350120008 2023-01-23 15:25:28.801489: step: 616/1545, loss: 0.016639161854982376 2023-01-23 15:25:29.693672: step: 618/1545, loss: 0.1283261477947235 2023-01-23 15:25:30.572603: step: 620/1545, loss: 0.13520604372024536 2023-01-23 15:25:31.484234: step: 622/1545, loss: 3.4070431865984574e-05 2023-01-23 15:25:32.362626: step: 624/1545, loss: 0.2211231291294098 2023-01-23 15:25:33.247255: step: 626/1545, loss: 0.010788431391119957 2023-01-23 15:25:34.120102: step: 628/1545, loss: 0.2886601388454437 2023-01-23 15:25:34.989348: step: 630/1545, loss: 0.011477787047624588 2023-01-23 15:25:35.872991: step: 632/1545, loss: 0.09800203889608383 2023-01-23 15:25:36.750338: step: 634/1545, loss: 0.04719221964478493 2023-01-23 15:25:37.640727: step: 636/1545, loss: 0.006889143958687782 2023-01-23 15:25:38.555210: step: 638/1545, loss: 0.03238602727651596 2023-01-23 15:25:39.454059: step: 640/1545, loss: 0.0090797059237957 2023-01-23 15:25:40.313248: step: 642/1545, loss: 0.09579430520534515 2023-01-23 15:25:41.221949: step: 644/1545, loss: 0.0006934182601980865 2023-01-23 15:25:42.117053: step: 646/1545, loss: 0.00209820712916553 2023-01-23 15:25:43.027660: step: 648/1545, loss: 0.03731342777609825 2023-01-23 15:25:43.941289: step: 650/1545, loss: 0.017168717458844185 2023-01-23 15:25:44.792446: step: 652/1545, loss: 0.006249705795198679 2023-01-23 15:25:45.706266: step: 654/1545, loss: 0.0010966083500534296 2023-01-23 15:25:46.582801: step: 656/1545, loss: 0.0015210736310109496 2023-01-23 15:25:47.473211: step: 658/1545, loss: 0.0017705324571579695 2023-01-23 15:25:48.367722: step: 660/1545, loss: 0.08429543673992157 2023-01-23 15:25:49.270362: step: 662/1545, loss: 0.007351225707679987 2023-01-23 15:25:50.153583: step: 664/1545, loss: 0.030152833089232445 2023-01-23 15:25:51.087895: step: 666/1545, loss: 0.073756642639637 2023-01-23 15:25:51.956092: step: 668/1545, loss: 0.00917108915746212 2023-01-23 15:25:52.887031: step: 670/1545, loss: 0.33130985498428345 2023-01-23 15:25:53.800374: step: 672/1545, loss: 2.8116155590396374e-05 2023-01-23 15:25:54.690679: step: 674/1545, loss: 0.0002759361523203552 2023-01-23 15:25:55.534286: step: 676/1545, loss: 0.3501795530319214 2023-01-23 15:25:56.487282: step: 678/1545, loss: 0.0007808580994606018 2023-01-23 15:25:57.382507: step: 680/1545, loss: 0.12513406574726105 2023-01-23 15:25:58.260372: step: 682/1545, loss: 0.0010240307310596108 2023-01-23 15:25:59.121327: step: 684/1545, loss: 0.11875200271606445 2023-01-23 15:26:00.017128: step: 686/1545, loss: 0.0020737459417432547 2023-01-23 15:26:00.865768: step: 688/1545, loss: 0.23482799530029297 2023-01-23 15:26:01.714817: step: 690/1545, loss: 0.055798862129449844 2023-01-23 15:26:02.568215: step: 692/1545, loss: 0.0006043952307663858 2023-01-23 15:26:03.428130: step: 694/1545, loss: 0.0029671008232980967 2023-01-23 15:26:04.288520: step: 696/1545, loss: 0.005448806565254927 2023-01-23 15:26:05.129344: step: 698/1545, loss: 0.0017414677422493696 2023-01-23 15:26:05.941931: step: 700/1545, loss: 0.005186376627534628 2023-01-23 15:26:06.807965: step: 702/1545, loss: 0.0022500117775052786 2023-01-23 15:26:07.687111: step: 704/1545, loss: 0.013351339846849442 2023-01-23 15:26:08.566153: step: 706/1545, loss: 0.04641108587384224 2023-01-23 15:26:09.388177: step: 708/1545, loss: 0.0007854304276406765 2023-01-23 15:26:10.231673: step: 710/1545, loss: 0.020970406010746956 2023-01-23 15:26:11.095961: step: 712/1545, loss: 0.00557535607367754 2023-01-23 15:26:11.994526: step: 714/1545, loss: 0.001554443035274744 2023-01-23 15:26:12.895335: step: 716/1545, loss: 0.0010210189502686262 2023-01-23 15:26:13.774115: step: 718/1545, loss: 0.00035664180177263916 2023-01-23 15:26:14.674572: step: 720/1545, loss: 0.12395710498094559 2023-01-23 15:26:15.524957: step: 722/1545, loss: 0.0009581355843693018 2023-01-23 15:26:16.458467: step: 724/1545, loss: 0.006938958540558815 2023-01-23 15:26:17.333654: step: 726/1545, loss: 0.027942080050706863 2023-01-23 15:26:18.238889: step: 728/1545, loss: 0.1882767230272293 2023-01-23 15:26:19.098033: step: 730/1545, loss: 0.0011764161754399538 2023-01-23 15:26:19.993482: step: 732/1545, loss: 0.040461696684360504 2023-01-23 15:26:20.930213: step: 734/1545, loss: 0.06409472972154617 2023-01-23 15:26:21.808382: step: 736/1545, loss: 0.011502968147397041 2023-01-23 15:26:22.691528: step: 738/1545, loss: 0.4193485975265503 2023-01-23 15:26:23.606140: step: 740/1545, loss: 0.44129666686058044 2023-01-23 15:26:24.493014: step: 742/1545, loss: 0.1349720060825348 2023-01-23 15:26:25.393843: step: 744/1545, loss: 0.0017804510425776243 2023-01-23 15:26:26.260811: step: 746/1545, loss: 0.006132757291197777 2023-01-23 15:26:27.130962: step: 748/1545, loss: 8.808826532913372e-05 2023-01-23 15:26:27.983275: step: 750/1545, loss: 0.00013885166845284402 2023-01-23 15:26:28.817495: step: 752/1545, loss: 0.0007042447687126696 2023-01-23 15:26:29.721433: step: 754/1545, loss: 0.02099928818643093 2023-01-23 15:26:30.614336: step: 756/1545, loss: 0.007541881408542395 2023-01-23 15:26:31.499188: step: 758/1545, loss: 0.12567226588726044 2023-01-23 15:26:32.381686: step: 760/1545, loss: 0.00046306956210173666 2023-01-23 15:26:33.290547: step: 762/1545, loss: 0.0015784804709255695 2023-01-23 15:26:34.178240: step: 764/1545, loss: 0.003040393814444542 2023-01-23 15:26:35.042653: step: 766/1545, loss: 0.006074259988963604 2023-01-23 15:26:35.893802: step: 768/1545, loss: 0.0034643406979739666 2023-01-23 15:26:36.772991: step: 770/1545, loss: 0.0027916589751839638 2023-01-23 15:26:37.652411: step: 772/1545, loss: 0.0009683349053375423 2023-01-23 15:26:38.540882: step: 774/1545, loss: 0.07630569487810135 2023-01-23 15:26:39.431171: step: 776/1545, loss: 0.3433018624782562 2023-01-23 15:26:40.291494: step: 778/1545, loss: 0.20072200894355774 2023-01-23 15:26:41.187248: step: 780/1545, loss: 0.0007771690143272281 2023-01-23 15:26:42.150628: step: 782/1545, loss: 0.0875830128788948 2023-01-23 15:26:43.025120: step: 784/1545, loss: 0.0014910311438143253 2023-01-23 15:26:43.904585: step: 786/1545, loss: 0.04114357754588127 2023-01-23 15:26:44.771624: step: 788/1545, loss: 0.00037400348810479045 2023-01-23 15:26:45.660269: step: 790/1545, loss: 0.2690616548061371 2023-01-23 15:26:46.596437: step: 792/1545, loss: 0.04556237533688545 2023-01-23 15:26:47.508935: step: 794/1545, loss: 0.0019032445270568132 2023-01-23 15:26:48.400957: step: 796/1545, loss: 0.0005518937832675874 2023-01-23 15:26:49.294318: step: 798/1545, loss: 0.0008790360880084336 2023-01-23 15:26:50.200680: step: 800/1545, loss: 0.00022299375268630683 2023-01-23 15:26:51.106321: step: 802/1545, loss: 0.002619640901684761 2023-01-23 15:26:51.981251: step: 804/1545, loss: 0.0022008386440575123 2023-01-23 15:26:52.897393: step: 806/1545, loss: 0.051217325031757355 2023-01-23 15:26:53.749456: step: 808/1545, loss: 0.0044846744276583195 2023-01-23 15:26:54.615709: step: 810/1545, loss: 0.006506668869405985 2023-01-23 15:26:55.483125: step: 812/1545, loss: 0.025192081928253174 2023-01-23 15:26:56.368107: step: 814/1545, loss: 0.24033349752426147 2023-01-23 15:26:57.292325: step: 816/1545, loss: 0.003420452121645212 2023-01-23 15:26:58.181144: step: 818/1545, loss: 0.0687495768070221 2023-01-23 15:26:59.098609: step: 820/1545, loss: 0.07883806526660919 2023-01-23 15:27:00.128305: step: 822/1545, loss: 0.003504903521388769 2023-01-23 15:27:01.027254: step: 824/1545, loss: 0.00010183800623053685 2023-01-23 15:27:01.913231: step: 826/1545, loss: 0.14801831543445587 2023-01-23 15:27:02.790723: step: 828/1545, loss: 0.0009127111989073455 2023-01-23 15:27:03.680756: step: 830/1545, loss: 0.6616293787956238 2023-01-23 15:27:04.552117: step: 832/1545, loss: 0.18135255575180054 2023-01-23 15:27:05.422272: step: 834/1545, loss: 0.1774192452430725 2023-01-23 15:27:06.303471: step: 836/1545, loss: 0.00831296481192112 2023-01-23 15:27:07.154582: step: 838/1545, loss: 0.45965564250946045 2023-01-23 15:27:08.027314: step: 840/1545, loss: 0.056827712804079056 2023-01-23 15:27:08.907701: step: 842/1545, loss: 0.0033137358259409666 2023-01-23 15:27:09.755483: step: 844/1545, loss: 0.05894840136170387 2023-01-23 15:27:10.652711: step: 846/1545, loss: 0.16397331655025482 2023-01-23 15:27:11.553197: step: 848/1545, loss: 0.010262271389365196 2023-01-23 15:27:12.415634: step: 850/1545, loss: 0.16906945407390594 2023-01-23 15:27:13.293212: step: 852/1545, loss: 0.0013192055048421025 2023-01-23 15:27:14.160535: step: 854/1545, loss: 0.01954672858119011 2023-01-23 15:27:15.051508: step: 856/1545, loss: 0.008936170488595963 2023-01-23 15:27:15.909731: step: 858/1545, loss: 0.0702638253569603 2023-01-23 15:27:16.831766: step: 860/1545, loss: 0.051737964153289795 2023-01-23 15:27:17.837425: step: 862/1545, loss: 0.008131155744194984 2023-01-23 15:27:18.709596: step: 864/1545, loss: 0.2351662814617157 2023-01-23 15:27:19.625151: step: 866/1545, loss: 0.11741931736469269 2023-01-23 15:27:20.485616: step: 868/1545, loss: 0.0027336101047694683 2023-01-23 15:27:21.371943: step: 870/1545, loss: 0.46887776255607605 2023-01-23 15:27:22.257419: step: 872/1545, loss: 0.005232646595686674 2023-01-23 15:27:23.102151: step: 874/1545, loss: 0.008343366906046867 2023-01-23 15:27:23.950119: step: 876/1545, loss: 0.001745738903991878 2023-01-23 15:27:24.889979: step: 878/1545, loss: 0.00014500366523861885 2023-01-23 15:27:25.781425: step: 880/1545, loss: 0.26390668749809265 2023-01-23 15:27:26.658139: step: 882/1545, loss: 0.004124142695218325 2023-01-23 15:27:27.560198: step: 884/1545, loss: 0.0298038050532341 2023-01-23 15:27:28.466670: step: 886/1545, loss: 0.017648210749030113 2023-01-23 15:27:29.345824: step: 888/1545, loss: 0.1901327669620514 2023-01-23 15:27:30.280364: step: 890/1545, loss: 0.038977958261966705 2023-01-23 15:27:31.150653: step: 892/1545, loss: 0.0032354569993913174 2023-01-23 15:27:32.058125: step: 894/1545, loss: 0.0008432084578089416 2023-01-23 15:27:32.904792: step: 896/1545, loss: 0.11431475728750229 2023-01-23 15:27:33.816598: step: 898/1545, loss: 0.026043489575386047 2023-01-23 15:27:34.737397: step: 900/1545, loss: 0.004732304252684116 2023-01-23 15:27:35.635396: step: 902/1545, loss: 0.40337997674942017 2023-01-23 15:27:36.536823: step: 904/1545, loss: 0.0022490746341645718 2023-01-23 15:27:37.452013: step: 906/1545, loss: 0.286171019077301 2023-01-23 15:27:38.297255: step: 908/1545, loss: 0.07585812360048294 2023-01-23 15:27:39.174961: step: 910/1545, loss: 0.0018487238558009267 2023-01-23 15:27:40.079690: step: 912/1545, loss: 0.038141269236803055 2023-01-23 15:27:41.028240: step: 914/1545, loss: 0.04883702099323273 2023-01-23 15:27:41.941725: step: 916/1545, loss: 0.13995519280433655 2023-01-23 15:27:42.820686: step: 918/1545, loss: 0.05042189359664917 2023-01-23 15:27:43.687666: step: 920/1545, loss: 0.02132483199238777 2023-01-23 15:27:44.705584: step: 922/1545, loss: 0.0769004374742508 2023-01-23 15:27:45.577565: step: 924/1545, loss: 0.0013178896624594927 2023-01-23 15:27:46.448538: step: 926/1545, loss: 0.08272188901901245 2023-01-23 15:27:47.342409: step: 928/1545, loss: 0.032001376152038574 2023-01-23 15:27:48.222195: step: 930/1545, loss: 0.0005148133495822549 2023-01-23 15:27:49.067247: step: 932/1545, loss: 0.0003399553243070841 2023-01-23 15:27:49.958885: step: 934/1545, loss: 0.046557795256376266 2023-01-23 15:27:50.840603: step: 936/1545, loss: 0.0784057080745697 2023-01-23 15:27:51.753325: step: 938/1545, loss: 0.10272382199764252 2023-01-23 15:27:52.671862: step: 940/1545, loss: 0.1474117636680603 2023-01-23 15:27:53.511323: step: 942/1545, loss: 0.007308377884328365 2023-01-23 15:27:54.411581: step: 944/1545, loss: 2.9138283729553223 2023-01-23 15:27:55.287707: step: 946/1545, loss: 0.004727830179035664 2023-01-23 15:27:56.169380: step: 948/1545, loss: 0.0016999202780425549 2023-01-23 15:27:57.047866: step: 950/1545, loss: 0.005108112469315529 2023-01-23 15:27:57.935880: step: 952/1545, loss: 0.0040351166389882565 2023-01-23 15:27:58.770633: step: 954/1545, loss: 0.0010892683640122414 2023-01-23 15:27:59.644872: step: 956/1545, loss: 0.1345471441745758 2023-01-23 15:28:00.530692: step: 958/1545, loss: 0.0011588960187509656 2023-01-23 15:28:01.418413: step: 960/1545, loss: 0.009838735684752464 2023-01-23 15:28:02.306981: step: 962/1545, loss: 0.09806360304355621 2023-01-23 15:28:03.276208: step: 964/1545, loss: 0.004180133808404207 2023-01-23 15:28:04.165694: step: 966/1545, loss: 0.0665970891714096 2023-01-23 15:28:05.088346: step: 968/1545, loss: 0.1486606001853943 2023-01-23 15:28:05.937264: step: 970/1545, loss: 0.014790852554142475 2023-01-23 15:28:06.817287: step: 972/1545, loss: 0.0003530437534209341 2023-01-23 15:28:07.721376: step: 974/1545, loss: 0.006010384764522314 2023-01-23 15:28:08.597246: step: 976/1545, loss: 0.010939077474176884 2023-01-23 15:28:09.524678: step: 978/1545, loss: 0.024059677496552467 2023-01-23 15:28:10.446426: step: 980/1545, loss: 0.01282594632357359 2023-01-23 15:28:11.399313: step: 982/1545, loss: 0.28560778498649597 2023-01-23 15:28:12.251157: step: 984/1545, loss: 0.0024883337318897247 2023-01-23 15:28:13.134068: step: 986/1545, loss: 1.3846893310546875 2023-01-23 15:28:14.007648: step: 988/1545, loss: 0.06228409335017204 2023-01-23 15:28:14.908973: step: 990/1545, loss: 0.07085004448890686 2023-01-23 15:28:15.809392: step: 992/1545, loss: 0.0014711953699588776 2023-01-23 15:28:16.699693: step: 994/1545, loss: 0.0022897894959896803 2023-01-23 15:28:17.597584: step: 996/1545, loss: 0.09166830778121948 2023-01-23 15:28:18.492019: step: 998/1545, loss: 0.009533360600471497 2023-01-23 15:28:19.370093: step: 1000/1545, loss: 0.010391817428171635 2023-01-23 15:28:20.319476: step: 1002/1545, loss: 0.07280514389276505 2023-01-23 15:28:21.272306: step: 1004/1545, loss: 0.04210858419537544 2023-01-23 15:28:22.263576: step: 1006/1545, loss: 0.07414770871400833 2023-01-23 15:28:23.141403: step: 1008/1545, loss: 0.21061834692955017 2023-01-23 15:28:24.024444: step: 1010/1545, loss: 0.13336113095283508 2023-01-23 15:28:24.882271: step: 1012/1545, loss: 0.4200517535209656 2023-01-23 15:28:25.792601: step: 1014/1545, loss: 0.00017278196173720062 2023-01-23 15:28:26.671440: step: 1016/1545, loss: 0.09853386878967285 2023-01-23 15:28:27.599113: step: 1018/1545, loss: 0.003942066337913275 2023-01-23 15:28:28.420529: step: 1020/1545, loss: 0.0006768762832507491 2023-01-23 15:28:29.335073: step: 1022/1545, loss: 0.0329725444316864 2023-01-23 15:28:30.173462: step: 1024/1545, loss: 0.23596864938735962 2023-01-23 15:28:31.056865: step: 1026/1545, loss: 0.03555943816900253 2023-01-23 15:28:31.935848: step: 1028/1545, loss: 0.0013553437311202288 2023-01-23 15:28:32.937636: step: 1030/1545, loss: 0.0024944620672613382 2023-01-23 15:28:33.813213: step: 1032/1545, loss: 0.03976084664463997 2023-01-23 15:28:34.667695: step: 1034/1545, loss: 0.0002582788001745939 2023-01-23 15:28:35.496259: step: 1036/1545, loss: 0.0031978008337318897 2023-01-23 15:28:36.371327: step: 1038/1545, loss: 0.014219158329069614 2023-01-23 15:28:37.237287: step: 1040/1545, loss: 0.003096369793638587 2023-01-23 15:28:38.137075: step: 1042/1545, loss: 0.0006497604190371931 2023-01-23 15:28:38.981385: step: 1044/1545, loss: 0.03813411295413971 2023-01-23 15:28:39.827676: step: 1046/1545, loss: 0.14107002317905426 2023-01-23 15:28:40.694262: step: 1048/1545, loss: 0.23901619017124176 2023-01-23 15:28:41.603453: step: 1050/1545, loss: 0.009886227548122406 2023-01-23 15:28:42.506289: step: 1052/1545, loss: 0.0015844641020521522 2023-01-23 15:28:43.353017: step: 1054/1545, loss: 0.006005322560667992 2023-01-23 15:28:44.288470: step: 1056/1545, loss: 0.42698734998703003 2023-01-23 15:28:45.190195: step: 1058/1545, loss: 0.0011116480454802513 2023-01-23 15:28:46.121480: step: 1060/1545, loss: 0.002562376204878092 2023-01-23 15:28:47.049692: step: 1062/1545, loss: 0.2251734435558319 2023-01-23 15:28:47.915984: step: 1064/1545, loss: 0.00044051645090803504 2023-01-23 15:28:48.821886: step: 1066/1545, loss: 0.04758094251155853 2023-01-23 15:28:49.714950: step: 1068/1545, loss: 0.042198892682790756 2023-01-23 15:28:50.582911: step: 1070/1545, loss: 0.003043738193809986 2023-01-23 15:28:51.501298: step: 1072/1545, loss: 0.029623616486787796 2023-01-23 15:28:52.403355: step: 1074/1545, loss: 0.0008929369505494833 2023-01-23 15:28:53.313775: step: 1076/1545, loss: 0.01616419106721878 2023-01-23 15:28:54.201068: step: 1078/1545, loss: 0.027775827795267105 2023-01-23 15:28:55.136419: step: 1080/1545, loss: 0.004963169805705547 2023-01-23 15:28:56.053715: step: 1082/1545, loss: 0.05491235479712486 2023-01-23 15:28:56.985406: step: 1084/1545, loss: 0.0159924179315567 2023-01-23 15:28:57.850835: step: 1086/1545, loss: 0.0007654231158085167 2023-01-23 15:28:58.748296: step: 1088/1545, loss: 0.06258386373519897 2023-01-23 15:28:59.648874: step: 1090/1545, loss: 0.15672552585601807 2023-01-23 15:29:00.567701: step: 1092/1545, loss: 0.025966525077819824 2023-01-23 15:29:01.421838: step: 1094/1545, loss: 0.020298343151807785 2023-01-23 15:29:02.282579: step: 1096/1545, loss: 0.012246155180037022 2023-01-23 15:29:03.193652: step: 1098/1545, loss: 0.007226587273180485 2023-01-23 15:29:04.061593: step: 1100/1545, loss: 0.05879625305533409 2023-01-23 15:29:05.017347: step: 1102/1545, loss: 0.0002949994523078203 2023-01-23 15:29:05.906379: step: 1104/1545, loss: 0.15707522630691528 2023-01-23 15:29:06.776357: step: 1106/1545, loss: 0.018156293779611588 2023-01-23 15:29:07.714650: step: 1108/1545, loss: 0.021664470434188843 2023-01-23 15:29:08.601169: step: 1110/1545, loss: 0.001715711085125804 2023-01-23 15:29:09.440687: step: 1112/1545, loss: 0.0009719464578665793 2023-01-23 15:29:10.341425: step: 1114/1545, loss: 0.0026049811858683825 2023-01-23 15:29:11.190269: step: 1116/1545, loss: 0.01115807518362999 2023-01-23 15:29:12.022986: step: 1118/1545, loss: 0.012473500333726406 2023-01-23 15:29:12.895023: step: 1120/1545, loss: 0.013469628989696503 2023-01-23 15:29:13.752289: step: 1122/1545, loss: 0.01689908094704151 2023-01-23 15:29:14.620535: step: 1124/1545, loss: 0.060305818915367126 2023-01-23 15:29:15.545713: step: 1126/1545, loss: 0.0018051511142402887 2023-01-23 15:29:16.449844: step: 1128/1545, loss: 0.04119976982474327 2023-01-23 15:29:17.329087: step: 1130/1545, loss: 0.6218311190605164 2023-01-23 15:29:18.226771: step: 1132/1545, loss: 0.08658339083194733 2023-01-23 15:29:19.192082: step: 1134/1545, loss: 0.00295269931666553 2023-01-23 15:29:20.137880: step: 1136/1545, loss: 0.03759356215596199 2023-01-23 15:29:21.013335: step: 1138/1545, loss: 0.000543531437870115 2023-01-23 15:29:21.924267: step: 1140/1545, loss: 0.28468161821365356 2023-01-23 15:29:22.824275: step: 1142/1545, loss: 0.06533738970756531 2023-01-23 15:29:23.685247: step: 1144/1545, loss: 0.07738051563501358 2023-01-23 15:29:24.621570: step: 1146/1545, loss: 0.011103217490017414 2023-01-23 15:29:25.551240: step: 1148/1545, loss: 0.0012229988351464272 2023-01-23 15:29:26.402233: step: 1150/1545, loss: 0.005060996860265732 2023-01-23 15:29:27.249638: step: 1152/1545, loss: 0.06499166786670685 2023-01-23 15:29:28.093161: step: 1154/1545, loss: 0.09027758240699768 2023-01-23 15:29:28.996977: step: 1156/1545, loss: 0.007839033380150795 2023-01-23 15:29:29.981826: step: 1158/1545, loss: 0.017124975100159645 2023-01-23 15:29:30.904986: step: 1160/1545, loss: 0.12870386242866516 2023-01-23 15:29:31.808212: step: 1162/1545, loss: 0.15731552243232727 2023-01-23 15:29:32.680098: step: 1164/1545, loss: 0.0012654451420530677 2023-01-23 15:29:33.587676: step: 1166/1545, loss: 0.003972477745264769 2023-01-23 15:29:34.484112: step: 1168/1545, loss: 0.0002578762941993773 2023-01-23 15:29:35.416793: step: 1170/1545, loss: 0.03383815288543701 2023-01-23 15:29:36.302395: step: 1172/1545, loss: 0.16147097945213318 2023-01-23 15:29:37.197758: step: 1174/1545, loss: 0.04462742060422897 2023-01-23 15:29:38.069696: step: 1176/1545, loss: 0.07082480937242508 2023-01-23 15:29:38.938776: step: 1178/1545, loss: 0.060615070164203644 2023-01-23 15:29:39.806114: step: 1180/1545, loss: 0.12658299505710602 2023-01-23 15:29:40.679316: step: 1182/1545, loss: 0.18124596774578094 2023-01-23 15:29:41.522487: step: 1184/1545, loss: 0.17502497136592865 2023-01-23 15:29:42.429511: step: 1186/1545, loss: 0.03868698328733444 2023-01-23 15:29:43.335026: step: 1188/1545, loss: 0.0008568085613660514 2023-01-23 15:29:44.200271: step: 1190/1545, loss: 0.009525452740490437 2023-01-23 15:29:45.207301: step: 1192/1545, loss: 0.0022975315805524588 2023-01-23 15:29:46.093196: step: 1194/1545, loss: 0.007849152199923992 2023-01-23 15:29:46.956656: step: 1196/1545, loss: 0.21910923719406128 2023-01-23 15:29:47.871360: step: 1198/1545, loss: 0.1342698186635971 2023-01-23 15:29:48.749764: step: 1200/1545, loss: 0.01829075999557972 2023-01-23 15:29:49.665883: step: 1202/1545, loss: 0.010906653478741646 2023-01-23 15:29:50.549388: step: 1204/1545, loss: 0.0036666227970272303 2023-01-23 15:29:51.456967: step: 1206/1545, loss: 0.007027578540146351 2023-01-23 15:29:52.345376: step: 1208/1545, loss: 0.002913687378168106 2023-01-23 15:29:53.255861: step: 1210/1545, loss: 0.04720066115260124 2023-01-23 15:29:54.150008: step: 1212/1545, loss: 0.026023153215646744 2023-01-23 15:29:55.012660: step: 1214/1545, loss: 0.12603196501731873 2023-01-23 15:29:55.903583: step: 1216/1545, loss: 0.04352881386876106 2023-01-23 15:29:56.778806: step: 1218/1545, loss: 0.0024020057171583176 2023-01-23 15:29:57.648060: step: 1220/1545, loss: 0.03614111989736557 2023-01-23 15:29:58.509473: step: 1222/1545, loss: 0.0057810102589428425 2023-01-23 15:29:59.418107: step: 1224/1545, loss: 0.0002348234411329031 2023-01-23 15:30:00.417492: step: 1226/1545, loss: 0.12534397840499878 2023-01-23 15:30:01.409315: step: 1228/1545, loss: 0.10831533372402191 2023-01-23 15:30:02.327588: step: 1230/1545, loss: 0.13540680706501007 2023-01-23 15:30:03.185119: step: 1232/1545, loss: 0.2776469588279724 2023-01-23 15:30:04.075908: step: 1234/1545, loss: 0.00028026234940625727 2023-01-23 15:30:04.924334: step: 1236/1545, loss: 0.0006794518558308482 2023-01-23 15:30:05.791106: step: 1238/1545, loss: 0.00121156161185354 2023-01-23 15:30:06.709198: step: 1240/1545, loss: 1.2010780572891235 2023-01-23 15:30:07.608874: step: 1242/1545, loss: 0.4799567461013794 2023-01-23 15:30:08.457709: step: 1244/1545, loss: 0.048096414655447006 2023-01-23 15:30:09.340160: step: 1246/1545, loss: 0.020413003861904144 2023-01-23 15:30:10.174765: step: 1248/1545, loss: 0.19148629903793335 2023-01-23 15:30:11.051820: step: 1250/1545, loss: 0.00762200728058815 2023-01-23 15:30:11.959829: step: 1252/1545, loss: 0.028345292434096336 2023-01-23 15:30:12.881294: step: 1254/1545, loss: 0.031243696808815002 2023-01-23 15:30:13.721244: step: 1256/1545, loss: 0.7166901230812073 2023-01-23 15:30:14.651598: step: 1258/1545, loss: 2.5432395935058594 2023-01-23 15:30:15.532394: step: 1260/1545, loss: 0.003421623492613435 2023-01-23 15:30:16.406584: step: 1262/1545, loss: 0.0671345591545105 2023-01-23 15:30:17.299530: step: 1264/1545, loss: 0.2573145925998688 2023-01-23 15:30:18.169866: step: 1266/1545, loss: 0.0023409787099808455 2023-01-23 15:30:19.033266: step: 1268/1545, loss: 0.0006552777485921979 2023-01-23 15:30:19.908901: step: 1270/1545, loss: 0.010177615098655224 2023-01-23 15:30:20.758028: step: 1272/1545, loss: 0.00045557291014119983 2023-01-23 15:30:21.610688: step: 1274/1545, loss: 0.03421968221664429 2023-01-23 15:30:22.456250: step: 1276/1545, loss: 0.00489289965480566 2023-01-23 15:30:23.433582: step: 1278/1545, loss: 0.4373582601547241 2023-01-23 15:30:24.328880: step: 1280/1545, loss: 0.2055915892124176 2023-01-23 15:30:25.243033: step: 1282/1545, loss: 0.07976216822862625 2023-01-23 15:30:26.117293: step: 1284/1545, loss: 0.00667537422850728 2023-01-23 15:30:27.029715: step: 1286/1545, loss: 0.006002232898026705 2023-01-23 15:30:27.904619: step: 1288/1545, loss: 0.07419319450855255 2023-01-23 15:30:28.787067: step: 1290/1545, loss: 0.002444870537146926 2023-01-23 15:30:29.662299: step: 1292/1545, loss: 0.002994661685079336 2023-01-23 15:30:30.551934: step: 1294/1545, loss: 0.11921767890453339 2023-01-23 15:30:31.418903: step: 1296/1545, loss: 0.12784381210803986 2023-01-23 15:30:32.315295: step: 1298/1545, loss: 0.014194187708199024 2023-01-23 15:30:33.193075: step: 1300/1545, loss: 0.008855750784277916 2023-01-23 15:30:34.063228: step: 1302/1545, loss: 0.09597478806972504 2023-01-23 15:30:34.941777: step: 1304/1545, loss: 0.21444915235042572 2023-01-23 15:30:35.813145: step: 1306/1545, loss: 0.01622951589524746 2023-01-23 15:30:36.666379: step: 1308/1545, loss: 0.4053189158439636 2023-01-23 15:30:37.608660: step: 1310/1545, loss: 0.13521674275398254 2023-01-23 15:30:38.479252: step: 1312/1545, loss: 0.00028873159317299724 2023-01-23 15:30:39.363705: step: 1314/1545, loss: 0.33720871806144714 2023-01-23 15:30:40.266448: step: 1316/1545, loss: 0.00639181025326252 2023-01-23 15:30:41.122629: step: 1318/1545, loss: 0.022348538041114807 2023-01-23 15:30:42.020958: step: 1320/1545, loss: 0.01748930849134922 2023-01-23 15:30:42.933024: step: 1322/1545, loss: 0.005397382657974958 2023-01-23 15:30:43.827473: step: 1324/1545, loss: 0.004909350536763668 2023-01-23 15:30:44.695857: step: 1326/1545, loss: 0.0012060742592439055 2023-01-23 15:30:45.645416: step: 1328/1545, loss: 1.3218533992767334 2023-01-23 15:30:46.561069: step: 1330/1545, loss: 0.08328459411859512 2023-01-23 15:30:47.449464: step: 1332/1545, loss: 0.0024964387994259596 2023-01-23 15:30:48.334231: step: 1334/1545, loss: 0.06847944855690002 2023-01-23 15:30:49.162280: step: 1336/1545, loss: 0.1598200500011444 2023-01-23 15:30:50.078043: step: 1338/1545, loss: 0.07105787843465805 2023-01-23 15:30:50.956338: step: 1340/1545, loss: 3.2526302337646484 2023-01-23 15:30:51.787344: step: 1342/1545, loss: 0.06941741704940796 2023-01-23 15:30:52.687799: step: 1344/1545, loss: 0.0011719989124685526 2023-01-23 15:30:53.555234: step: 1346/1545, loss: 0.0005240432219579816 2023-01-23 15:30:54.435016: step: 1348/1545, loss: 0.004082309547811747 2023-01-23 15:30:55.345916: step: 1350/1545, loss: 0.1672566831111908 2023-01-23 15:30:56.293968: step: 1352/1545, loss: 0.0018899913411587477 2023-01-23 15:30:57.206703: step: 1354/1545, loss: 0.08772933483123779 2023-01-23 15:30:58.104031: step: 1356/1545, loss: 0.003470193361863494 2023-01-23 15:30:58.979980: step: 1358/1545, loss: 0.0006456412374973297 2023-01-23 15:30:59.854129: step: 1360/1545, loss: 0.004616857506334782 2023-01-23 15:31:00.748985: step: 1362/1545, loss: 0.0005066341836936772 2023-01-23 15:31:01.614808: step: 1364/1545, loss: 0.09316744655370712 2023-01-23 15:31:02.541434: step: 1366/1545, loss: 0.06123538687825203 2023-01-23 15:31:03.399837: step: 1368/1545, loss: 0.011231524869799614 2023-01-23 15:31:04.337071: step: 1370/1545, loss: 0.0018956088460981846 2023-01-23 15:31:05.179073: step: 1372/1545, loss: 0.006345104891806841 2023-01-23 15:31:06.052958: step: 1374/1545, loss: 0.2562059462070465 2023-01-23 15:31:06.935391: step: 1376/1545, loss: 0.0027864344883710146 2023-01-23 15:31:07.790606: step: 1378/1545, loss: 0.001261596567928791 2023-01-23 15:31:08.683162: step: 1380/1545, loss: 0.019350294023752213 2023-01-23 15:31:09.539317: step: 1382/1545, loss: 0.02434040606021881 2023-01-23 15:31:10.442841: step: 1384/1545, loss: 0.20587708055973053 2023-01-23 15:31:11.312618: step: 1386/1545, loss: 0.0016525634564459324 2023-01-23 15:31:12.208907: step: 1388/1545, loss: 0.0005627713399007916 2023-01-23 15:31:13.070381: step: 1390/1545, loss: 0.045123711228370667 2023-01-23 15:31:13.960703: step: 1392/1545, loss: 0.004845510236918926 2023-01-23 15:31:14.876222: step: 1394/1545, loss: 0.08649364113807678 2023-01-23 15:31:15.822132: step: 1396/1545, loss: 0.11873306334018707 2023-01-23 15:31:16.781963: step: 1398/1545, loss: 0.0017832403536885977 2023-01-23 15:31:17.641077: step: 1400/1545, loss: 0.1910630762577057 2023-01-23 15:31:18.501433: step: 1402/1545, loss: 0.017177797853946686 2023-01-23 15:31:19.422015: step: 1404/1545, loss: 0.07679512351751328 2023-01-23 15:31:20.303248: step: 1406/1545, loss: 0.007935358211398125 2023-01-23 15:31:21.187337: step: 1408/1545, loss: 0.04791295900940895 2023-01-23 15:31:22.080644: step: 1410/1545, loss: 0.005377674475312233 2023-01-23 15:31:22.966944: step: 1412/1545, loss: 9.264823165722191e-05 2023-01-23 15:31:23.827385: step: 1414/1545, loss: 0.0180971659719944 2023-01-23 15:31:24.731887: step: 1416/1545, loss: 0.0006649838178418577 2023-01-23 15:31:25.607975: step: 1418/1545, loss: 0.1617615669965744 2023-01-23 15:31:26.483507: step: 1420/1545, loss: 0.0029309066012501717 2023-01-23 15:31:27.428836: step: 1422/1545, loss: 0.10723795741796494 2023-01-23 15:31:28.257807: step: 1424/1545, loss: 0.09220614284276962 2023-01-23 15:31:29.158099: step: 1426/1545, loss: 0.28033632040023804 2023-01-23 15:31:30.038203: step: 1428/1545, loss: 0.006498811766505241 2023-01-23 15:31:30.908845: step: 1430/1545, loss: 0.020397190004587173 2023-01-23 15:31:31.740359: step: 1432/1545, loss: 0.06601059436798096 2023-01-23 15:31:32.631034: step: 1434/1545, loss: 0.016602065414190292 2023-01-23 15:31:33.508402: step: 1436/1545, loss: 0.017670411616563797 2023-01-23 15:31:34.405440: step: 1438/1545, loss: 0.005342329852283001 2023-01-23 15:31:35.328503: step: 1440/1545, loss: 0.08219971507787704 2023-01-23 15:31:36.178965: step: 1442/1545, loss: 0.0038549150340259075 2023-01-23 15:31:37.044640: step: 1444/1545, loss: 0.0682198703289032 2023-01-23 15:31:37.937902: step: 1446/1545, loss: 0.146104633808136 2023-01-23 15:31:38.811702: step: 1448/1545, loss: 0.004644643981009722 2023-01-23 15:31:39.700027: step: 1450/1545, loss: 0.011822596192359924 2023-01-23 15:31:40.568624: step: 1452/1545, loss: 0.005240781232714653 2023-01-23 15:31:41.532019: step: 1454/1545, loss: 0.08498028665781021 2023-01-23 15:31:42.421678: step: 1456/1545, loss: 0.004100765101611614 2023-01-23 15:31:43.363089: step: 1458/1545, loss: 0.04535696655511856 2023-01-23 15:31:44.240970: step: 1460/1545, loss: 0.00701218843460083 2023-01-23 15:31:45.219106: step: 1462/1545, loss: 0.0019045999506488442 2023-01-23 15:31:46.131733: step: 1464/1545, loss: 0.037974048405885696 2023-01-23 15:31:46.993652: step: 1466/1545, loss: 0.0019403621554374695 2023-01-23 15:31:47.870396: step: 1468/1545, loss: 0.09061291068792343 2023-01-23 15:31:48.750138: step: 1470/1545, loss: 0.003367577213793993 2023-01-23 15:31:49.727279: step: 1472/1545, loss: 0.006291002966463566 2023-01-23 15:31:50.632827: step: 1474/1545, loss: 0.05336463451385498 2023-01-23 15:31:51.569203: step: 1476/1545, loss: 0.03748023137450218 2023-01-23 15:31:52.459762: step: 1478/1545, loss: 0.013863840140402317 2023-01-23 15:31:53.323458: step: 1480/1545, loss: 0.032331474125385284 2023-01-23 15:31:54.203611: step: 1482/1545, loss: 0.0728275403380394 2023-01-23 15:31:55.086441: step: 1484/1545, loss: 0.4823111891746521 2023-01-23 15:31:55.963527: step: 1486/1545, loss: 0.1842392534017563 2023-01-23 15:31:56.840987: step: 1488/1545, loss: 0.008174998685717583 2023-01-23 15:31:57.736422: step: 1490/1545, loss: 0.10628733038902283 2023-01-23 15:31:58.606823: step: 1492/1545, loss: 0.7069097757339478 2023-01-23 15:31:59.476791: step: 1494/1545, loss: 0.08047013729810715 2023-01-23 15:32:00.396528: step: 1496/1545, loss: 0.08158203959465027 2023-01-23 15:32:01.240439: step: 1498/1545, loss: 0.00033758601057343185 2023-01-23 15:32:02.117542: step: 1500/1545, loss: 0.024506842717528343 2023-01-23 15:32:02.962180: step: 1502/1545, loss: 0.12413066625595093 2023-01-23 15:32:03.794528: step: 1504/1545, loss: 0.02037443034350872 2023-01-23 15:32:04.742456: step: 1506/1545, loss: 0.001418845378793776 2023-01-23 15:32:05.687715: step: 1508/1545, loss: 0.03543622046709061 2023-01-23 15:32:06.600704: step: 1510/1545, loss: 0.0013140974333509803 2023-01-23 15:32:07.463843: step: 1512/1545, loss: 0.0006991794216446579 2023-01-23 15:32:08.303950: step: 1514/1545, loss: 0.08587801456451416 2023-01-23 15:32:09.257564: step: 1516/1545, loss: 0.3216300308704376 2023-01-23 15:32:10.158801: step: 1518/1545, loss: 0.013952599838376045 2023-01-23 15:32:11.014130: step: 1520/1545, loss: 0.1046542227268219 2023-01-23 15:32:11.897103: step: 1522/1545, loss: 0.006039610598236322 2023-01-23 15:32:12.792184: step: 1524/1545, loss: 0.005334756337106228 2023-01-23 15:32:13.629491: step: 1526/1545, loss: 0.0014247108483687043 2023-01-23 15:32:14.508659: step: 1528/1545, loss: 0.0016594884218648076 2023-01-23 15:32:15.435901: step: 1530/1545, loss: 0.037602126598358154 2023-01-23 15:32:16.302301: step: 1532/1545, loss: 0.03109842911362648 2023-01-23 15:32:17.171537: step: 1534/1545, loss: 0.09887737035751343 2023-01-23 15:32:18.067860: step: 1536/1545, loss: 0.0015039339195936918 2023-01-23 15:32:19.003503: step: 1538/1545, loss: 0.00722101517021656 2023-01-23 15:32:19.858796: step: 1540/1545, loss: 0.560848593711853 2023-01-23 15:32:20.742904: step: 1542/1545, loss: 0.006480313837528229 2023-01-23 15:32:21.611436: step: 1544/1545, loss: 0.015307766385376453 2023-01-23 15:32:22.477328: step: 1546/1545, loss: 0.0007042527431622148 2023-01-23 15:32:23.341233: step: 1548/1545, loss: 0.0012769894674420357 2023-01-23 15:32:24.275032: step: 1550/1545, loss: 0.0012136430013924837 2023-01-23 15:32:25.129835: step: 1552/1545, loss: 0.04323526471853256 2023-01-23 15:32:26.099249: step: 1554/1545, loss: 0.0017982322024181485 2023-01-23 15:32:27.006929: step: 1556/1545, loss: 0.27304551005363464 2023-01-23 15:32:27.866216: step: 1558/1545, loss: 0.002821898553520441 2023-01-23 15:32:28.765953: step: 1560/1545, loss: 0.7061704993247986 2023-01-23 15:32:29.650980: step: 1562/1545, loss: 1.9127733707427979 2023-01-23 15:32:30.567357: step: 1564/1545, loss: 0.000420540280174464 2023-01-23 15:32:31.500305: step: 1566/1545, loss: 0.000739342300221324 2023-01-23 15:32:32.426335: step: 1568/1545, loss: 0.14842486381530762 2023-01-23 15:32:33.315776: step: 1570/1545, loss: 0.0027008422184735537 2023-01-23 15:32:34.178312: step: 1572/1545, loss: 0.02060280740261078 2023-01-23 15:32:35.084352: step: 1574/1545, loss: 0.05719337984919548 2023-01-23 15:32:36.027418: step: 1576/1545, loss: 0.056712739169597626 2023-01-23 15:32:36.928578: step: 1578/1545, loss: 0.2623252272605896 2023-01-23 15:32:37.816204: step: 1580/1545, loss: 0.015794219449162483 2023-01-23 15:32:38.719017: step: 1582/1545, loss: 0.006808341946452856 2023-01-23 15:32:39.602894: step: 1584/1545, loss: 0.6913177967071533 2023-01-23 15:32:40.562175: step: 1586/1545, loss: 0.14843973517417908 2023-01-23 15:32:41.438128: step: 1588/1545, loss: 0.006963897496461868 2023-01-23 15:32:42.352502: step: 1590/1545, loss: 0.5233550071716309 2023-01-23 15:32:43.232532: step: 1592/1545, loss: 0.016097117215394974 2023-01-23 15:32:44.135356: step: 1594/1545, loss: 0.05506300926208496 2023-01-23 15:32:44.999571: step: 1596/1545, loss: 0.00882353913038969 2023-01-23 15:32:45.904769: step: 1598/1545, loss: 0.10431589186191559 2023-01-23 15:32:46.871379: step: 1600/1545, loss: 0.0018011736683547497 2023-01-23 15:32:47.766042: step: 1602/1545, loss: 0.2196221947669983 2023-01-23 15:32:48.649612: step: 1604/1545, loss: 0.11891829967498779 2023-01-23 15:32:49.571507: step: 1606/1545, loss: 0.02344280295073986 2023-01-23 15:32:50.442984: step: 1608/1545, loss: 0.0025009100791066885 2023-01-23 15:32:51.430883: step: 1610/1545, loss: 0.01042263675481081 2023-01-23 15:32:52.308310: step: 1612/1545, loss: 0.09851371496915817 2023-01-23 15:32:53.181342: step: 1614/1545, loss: 0.003694448620080948 2023-01-23 15:32:54.077641: step: 1616/1545, loss: 1.2686532735824585 2023-01-23 15:32:54.923763: step: 1618/1545, loss: 0.018662603572010994 2023-01-23 15:32:55.787686: step: 1620/1545, loss: 0.03430540859699249 2023-01-23 15:32:56.692361: step: 1622/1545, loss: 0.003447576193138957 2023-01-23 15:32:57.556725: step: 1624/1545, loss: 0.06679940223693848 2023-01-23 15:32:58.455351: step: 1626/1545, loss: 0.052486177533864975 2023-01-23 15:32:59.304137: step: 1628/1545, loss: 0.0042124283500015736 2023-01-23 15:33:00.220723: step: 1630/1545, loss: 0.03871447965502739 2023-01-23 15:33:01.107065: step: 1632/1545, loss: 0.00443509966135025 2023-01-23 15:33:02.058069: step: 1634/1545, loss: 0.012441787868738174 2023-01-23 15:33:02.923912: step: 1636/1545, loss: 0.012637860141694546 2023-01-23 15:33:03.795206: step: 1638/1545, loss: 0.09486428648233414 2023-01-23 15:33:04.766742: step: 1640/1545, loss: 0.21717627346515656 2023-01-23 15:33:05.631086: step: 1642/1545, loss: 0.15121310949325562 2023-01-23 15:33:06.505038: step: 1644/1545, loss: 0.24811020493507385 2023-01-23 15:33:07.410947: step: 1646/1545, loss: 0.06899317353963852 2023-01-23 15:33:08.330747: step: 1648/1545, loss: 0.028382113203406334 2023-01-23 15:33:09.242697: step: 1650/1545, loss: 0.025998694822192192 2023-01-23 15:33:10.104382: step: 1652/1545, loss: 0.002647217595949769 2023-01-23 15:33:10.948209: step: 1654/1545, loss: 0.08422037959098816 2023-01-23 15:33:11.814117: step: 1656/1545, loss: 0.011319204233586788 2023-01-23 15:33:12.679386: step: 1658/1545, loss: 0.0004846329102292657 2023-01-23 15:33:13.583421: step: 1660/1545, loss: 2.4967996068880893e-05 2023-01-23 15:33:14.455174: step: 1662/1545, loss: 0.05163402110338211 2023-01-23 15:33:15.371668: step: 1664/1545, loss: 0.2247212529182434 2023-01-23 15:33:16.280515: step: 1666/1545, loss: 0.00023924445849843323 2023-01-23 15:33:17.173847: step: 1668/1545, loss: 0.0031479671597480774 2023-01-23 15:33:18.077034: step: 1670/1545, loss: 0.00036987182102166116 2023-01-23 15:33:18.979222: step: 1672/1545, loss: 0.019676223397254944 2023-01-23 15:33:19.826389: step: 1674/1545, loss: 0.5708024501800537 2023-01-23 15:33:20.687797: step: 1676/1545, loss: 0.003378247609362006 2023-01-23 15:33:21.540172: step: 1678/1545, loss: 0.009671268053352833 2023-01-23 15:33:22.446958: step: 1680/1545, loss: 0.0012256210902705789 2023-01-23 15:33:23.324044: step: 1682/1545, loss: 0.057998090982437134 2023-01-23 15:33:24.190249: step: 1684/1545, loss: 0.2710862457752228 2023-01-23 15:33:25.100355: step: 1686/1545, loss: 0.02544124238193035 2023-01-23 15:33:25.986149: step: 1688/1545, loss: 0.009583215229213238 2023-01-23 15:33:26.908644: step: 1690/1545, loss: 0.014073806814849377 2023-01-23 15:33:27.793392: step: 1692/1545, loss: 0.01949230395257473 2023-01-23 15:33:28.673760: step: 1694/1545, loss: 0.010315239429473877 2023-01-23 15:33:29.591873: step: 1696/1545, loss: 0.11668935418128967 2023-01-23 15:33:30.473572: step: 1698/1545, loss: 0.09987805038690567 2023-01-23 15:33:31.366514: step: 1700/1545, loss: 0.13508108258247375 2023-01-23 15:33:32.207570: step: 1702/1545, loss: 0.00013575147022493184 2023-01-23 15:33:33.093480: step: 1704/1545, loss: 0.000742207164876163 2023-01-23 15:33:33.956884: step: 1706/1545, loss: 0.008694387972354889 2023-01-23 15:33:34.817895: step: 1708/1545, loss: 0.0006154327420517802 2023-01-23 15:33:35.720685: step: 1710/1545, loss: 0.01571773923933506 2023-01-23 15:33:36.705661: step: 1712/1545, loss: 0.009572078473865986 2023-01-23 15:33:37.578821: step: 1714/1545, loss: 0.07633236795663834 2023-01-23 15:33:38.499115: step: 1716/1545, loss: 7.66335433581844e-05 2023-01-23 15:33:39.436668: step: 1718/1545, loss: 0.0058793965727090836 2023-01-23 15:33:40.338198: step: 1720/1545, loss: 0.0009665911202318966 2023-01-23 15:33:41.250164: step: 1722/1545, loss: 0.014657648280262947 2023-01-23 15:33:42.171619: step: 1724/1545, loss: 0.08953557163476944 2023-01-23 15:33:43.071774: step: 1726/1545, loss: 0.07470294833183289 2023-01-23 15:33:43.946925: step: 1728/1545, loss: 0.24715957045555115 2023-01-23 15:33:44.834664: step: 1730/1545, loss: 7.003665086813271e-05 2023-01-23 15:33:45.727268: step: 1732/1545, loss: 0.0116055216640234 2023-01-23 15:33:46.561855: step: 1734/1545, loss: 0.2995629906654358 2023-01-23 15:33:47.433017: step: 1736/1545, loss: 0.19246149063110352 2023-01-23 15:33:48.272195: step: 1738/1545, loss: 0.19815486669540405 2023-01-23 15:33:49.168117: step: 1740/1545, loss: 1.6342729330062866 2023-01-23 15:33:50.061471: step: 1742/1545, loss: 0.008406803011894226 2023-01-23 15:33:50.936125: step: 1744/1545, loss: 0.04303872957825661 2023-01-23 15:33:51.830028: step: 1746/1545, loss: 0.0004069714341312647 2023-01-23 15:33:52.696836: step: 1748/1545, loss: 0.0004594186320900917 2023-01-23 15:33:53.591173: step: 1750/1545, loss: 0.011269869282841682 2023-01-23 15:33:54.450143: step: 1752/1545, loss: 1.393526554107666 2023-01-23 15:33:55.389873: step: 1754/1545, loss: 0.04356827959418297 2023-01-23 15:33:56.241956: step: 1756/1545, loss: 0.027281630784273148 2023-01-23 15:33:57.091366: step: 1758/1545, loss: 0.01920454576611519 2023-01-23 15:33:58.004502: step: 1760/1545, loss: 0.23766717314720154 2023-01-23 15:33:58.893230: step: 1762/1545, loss: 0.057881616055965424 2023-01-23 15:33:59.765968: step: 1764/1545, loss: 0.0005947669269517064 2023-01-23 15:34:00.645545: step: 1766/1545, loss: 0.22376896440982819 2023-01-23 15:34:01.501718: step: 1768/1545, loss: 0.0809096246957779 2023-01-23 15:34:02.460963: step: 1770/1545, loss: 0.03869353234767914 2023-01-23 15:34:03.349717: step: 1772/1545, loss: 0.3739761412143707 2023-01-23 15:34:04.304729: step: 1774/1545, loss: 0.08756321668624878 2023-01-23 15:34:05.271155: step: 1776/1545, loss: 0.001921408111229539 2023-01-23 15:34:06.190224: step: 1778/1545, loss: 1.639448881149292 2023-01-23 15:34:07.104621: step: 1780/1545, loss: 0.13604597747325897 2023-01-23 15:34:07.990204: step: 1782/1545, loss: 0.0007474491721950471 2023-01-23 15:34:08.897800: step: 1784/1545, loss: 0.008095498196780682 2023-01-23 15:34:09.782818: step: 1786/1545, loss: 0.0015255319885909557 2023-01-23 15:34:10.651488: step: 1788/1545, loss: 0.0045768399722874165 2023-01-23 15:34:11.535436: step: 1790/1545, loss: 0.8714954853057861 2023-01-23 15:34:12.421234: step: 1792/1545, loss: 0.014718960970640182 2023-01-23 15:34:13.329343: step: 1794/1545, loss: 8.082269778242335e-05 2023-01-23 15:34:14.259904: step: 1796/1545, loss: 0.028769541531801224 2023-01-23 15:34:15.204204: step: 1798/1545, loss: 0.13606590032577515 2023-01-23 15:34:16.070259: step: 1800/1545, loss: 8.854765474097803e-05 2023-01-23 15:34:17.033588: step: 1802/1545, loss: 0.07187309861183167 2023-01-23 15:34:17.977261: step: 1804/1545, loss: 0.0961732491850853 2023-01-23 15:34:18.866938: step: 1806/1545, loss: 0.025714952498674393 2023-01-23 15:34:19.832549: step: 1808/1545, loss: 0.10158740729093552 2023-01-23 15:34:20.702560: step: 1810/1545, loss: 0.00040027109207585454 2023-01-23 15:34:21.604479: step: 1812/1545, loss: 0.003986354451626539 2023-01-23 15:34:22.467889: step: 1814/1545, loss: 0.0028190258890390396 2023-01-23 15:34:23.338569: step: 1816/1545, loss: 0.052828386425971985 2023-01-23 15:34:24.222778: step: 1818/1545, loss: 0.08457469195127487 2023-01-23 15:34:25.139680: step: 1820/1545, loss: 0.0002680803881958127 2023-01-23 15:34:26.009450: step: 1822/1545, loss: 0.20340101420879364 2023-01-23 15:34:26.906527: step: 1824/1545, loss: 0.12110311537981033 2023-01-23 15:34:27.805161: step: 1826/1545, loss: 0.002009080955758691 2023-01-23 15:34:28.670900: step: 1828/1545, loss: 0.029309332370758057 2023-01-23 15:34:29.599605: step: 1830/1545, loss: 0.0041901720687747 2023-01-23 15:34:30.556909: step: 1832/1545, loss: 0.020427703857421875 2023-01-23 15:34:31.432609: step: 1834/1545, loss: 0.054679106920957565 2023-01-23 15:34:32.294998: step: 1836/1545, loss: 0.01734570972621441 2023-01-23 15:34:33.150073: step: 1838/1545, loss: 0.0007709120982326567 2023-01-23 15:34:34.047310: step: 1840/1545, loss: 0.016556335613131523 2023-01-23 15:34:34.931936: step: 1842/1545, loss: 0.0027462763246148825 2023-01-23 15:34:35.796335: step: 1844/1545, loss: 4.530142905423418e-05 2023-01-23 15:34:36.667593: step: 1846/1545, loss: 0.0489155538380146 2023-01-23 15:34:37.553126: step: 1848/1545, loss: 0.3398335874080658 2023-01-23 15:34:38.393870: step: 1850/1545, loss: 0.0334099717438221 2023-01-23 15:34:39.249113: step: 1852/1545, loss: 0.016850363463163376 2023-01-23 15:34:40.163139: step: 1854/1545, loss: 0.0020901397801935673 2023-01-23 15:34:41.047070: step: 1856/1545, loss: 0.005432265345007181 2023-01-23 15:34:41.928915: step: 1858/1545, loss: 0.0014097518287599087 2023-01-23 15:34:42.870131: step: 1860/1545, loss: 0.011796638369560242 2023-01-23 15:34:43.785869: step: 1862/1545, loss: 0.018268311396241188 2023-01-23 15:34:44.692473: step: 1864/1545, loss: 0.06463480740785599 2023-01-23 15:34:45.548489: step: 1866/1545, loss: 0.0002774281310848892 2023-01-23 15:34:46.423183: step: 1868/1545, loss: 0.002235245192423463 2023-01-23 15:34:47.334418: step: 1870/1545, loss: 0.0026313234120607376 2023-01-23 15:34:48.292556: step: 1872/1545, loss: 0.07200969755649567 2023-01-23 15:34:49.141046: step: 1874/1545, loss: 0.09693281352519989 2023-01-23 15:34:50.074891: step: 1876/1545, loss: 0.0007236870587803423 2023-01-23 15:34:51.004362: step: 1878/1545, loss: 0.0008282478083856404 2023-01-23 15:34:51.879971: step: 1880/1545, loss: 0.23690475523471832 2023-01-23 15:34:52.740854: step: 1882/1545, loss: 0.0004463589866645634 2023-01-23 15:34:53.635083: step: 1884/1545, loss: 0.18280871212482452 2023-01-23 15:34:54.504654: step: 1886/1545, loss: 0.0014561412390321493 2023-01-23 15:34:55.350112: step: 1888/1545, loss: 0.11791607737541199 2023-01-23 15:34:56.237518: step: 1890/1545, loss: 0.13687308132648468 2023-01-23 15:34:57.118082: step: 1892/1545, loss: 0.5907936692237854 2023-01-23 15:34:57.996367: step: 1894/1545, loss: 0.002399395452812314 2023-01-23 15:34:58.879244: step: 1896/1545, loss: 0.25116485357284546 2023-01-23 15:34:59.741389: step: 1898/1545, loss: 0.0017831422155722976 2023-01-23 15:35:00.672826: step: 1900/1545, loss: 0.0017163188895210624 2023-01-23 15:35:01.562187: step: 1902/1545, loss: 0.010561925359070301 2023-01-23 15:35:02.500232: step: 1904/1545, loss: 0.05826596915721893 2023-01-23 15:35:03.360569: step: 1906/1545, loss: 0.22202283143997192 2023-01-23 15:35:04.249089: step: 1908/1545, loss: 0.03774542734026909 2023-01-23 15:35:05.127141: step: 1910/1545, loss: 0.29973065853118896 2023-01-23 15:35:06.027465: step: 1912/1545, loss: 0.0020998409017920494 2023-01-23 15:35:06.926653: step: 1914/1545, loss: 0.05130372196435928 2023-01-23 15:35:07.794856: step: 1916/1545, loss: 0.14781592786312103 2023-01-23 15:35:08.664867: step: 1918/1545, loss: 0.0021219621412456036 2023-01-23 15:35:09.508141: step: 1920/1545, loss: 0.09396606683731079 2023-01-23 15:35:10.419613: step: 1922/1545, loss: 0.014801092445850372 2023-01-23 15:35:11.309316: step: 1924/1545, loss: 0.016963111236691475 2023-01-23 15:35:12.224200: step: 1926/1545, loss: 0.12303762137889862 2023-01-23 15:35:13.102247: step: 1928/1545, loss: 0.03337147459387779 2023-01-23 15:35:14.020747: step: 1930/1545, loss: 0.022923218086361885 2023-01-23 15:35:14.867556: step: 1932/1545, loss: 0.0015320958336815238 2023-01-23 15:35:15.757305: step: 1934/1545, loss: 0.004890819080173969 2023-01-23 15:35:16.629976: step: 1936/1545, loss: 0.0014903913252055645 2023-01-23 15:35:17.503059: step: 1938/1545, loss: 0.003630036488175392 2023-01-23 15:35:18.412481: step: 1940/1545, loss: 0.00801494624465704 2023-01-23 15:35:19.334746: step: 1942/1545, loss: 0.005342237185686827 2023-01-23 15:35:20.195270: step: 1944/1545, loss: 0.007681448943912983 2023-01-23 15:35:21.085609: step: 1946/1545, loss: 0.07545332610607147 2023-01-23 15:35:21.979297: step: 1948/1545, loss: 0.12552587687969208 2023-01-23 15:35:22.854647: step: 1950/1545, loss: 0.05711033195257187 2023-01-23 15:35:23.729898: step: 1952/1545, loss: 0.03695104271173477 2023-01-23 15:35:24.668521: step: 1954/1545, loss: 0.2390899360179901 2023-01-23 15:35:25.610343: step: 1956/1545, loss: 0.0020207189954817295 2023-01-23 15:35:26.488451: step: 1958/1545, loss: 0.33184459805488586 2023-01-23 15:35:27.416681: step: 1960/1545, loss: 0.12204674631357193 2023-01-23 15:35:28.292656: step: 1962/1545, loss: 0.9383265376091003 2023-01-23 15:35:29.159110: step: 1964/1545, loss: 0.3390626907348633 2023-01-23 15:35:30.053692: step: 1966/1545, loss: 0.2750544846057892 2023-01-23 15:35:30.964219: step: 1968/1545, loss: 0.12554290890693665 2023-01-23 15:35:31.860949: step: 1970/1545, loss: 0.43339911103248596 2023-01-23 15:35:32.787594: step: 1972/1545, loss: 0.03128756210207939 2023-01-23 15:35:33.674466: step: 1974/1545, loss: 0.009996941313147545 2023-01-23 15:35:34.555557: step: 1976/1545, loss: 0.04819350689649582 2023-01-23 15:35:35.417590: step: 1978/1545, loss: 0.08519437909126282 2023-01-23 15:35:36.271767: step: 1980/1545, loss: 0.030416904017329216 2023-01-23 15:35:37.175362: step: 1982/1545, loss: 0.05418183282017708 2023-01-23 15:35:38.037683: step: 1984/1545, loss: 0.029092883691191673 2023-01-23 15:35:38.961856: step: 1986/1545, loss: 1.2257689237594604 2023-01-23 15:35:39.843763: step: 1988/1545, loss: 0.01522764191031456 2023-01-23 15:35:40.774800: step: 1990/1545, loss: 0.06622490286827087 2023-01-23 15:35:41.722726: step: 1992/1545, loss: 0.06230641528964043 2023-01-23 15:35:42.561748: step: 1994/1545, loss: 0.04019749164581299 2023-01-23 15:35:43.482309: step: 1996/1545, loss: 0.002396354917436838 2023-01-23 15:35:44.410438: step: 1998/1545, loss: 0.01274168025702238 2023-01-23 15:35:45.359564: step: 2000/1545, loss: 0.018745725974440575 2023-01-23 15:35:46.214509: step: 2002/1545, loss: 0.1830047070980072 2023-01-23 15:35:47.188298: step: 2004/1545, loss: 0.3248232901096344 2023-01-23 15:35:48.058486: step: 2006/1545, loss: 0.00040729218744672835 2023-01-23 15:35:48.966789: step: 2008/1545, loss: 0.0442928783595562 2023-01-23 15:35:49.812785: step: 2010/1545, loss: 0.049112021923065186 2023-01-23 15:35:50.756255: step: 2012/1545, loss: 0.6577742695808411 2023-01-23 15:35:51.658918: step: 2014/1545, loss: 0.14569519460201263 2023-01-23 15:35:52.558344: step: 2016/1545, loss: 0.04393734782934189 2023-01-23 15:35:53.462589: step: 2018/1545, loss: 2.0033118724823 2023-01-23 15:35:54.343627: step: 2020/1545, loss: 0.05361885577440262 2023-01-23 15:35:55.206864: step: 2022/1545, loss: 0.020182128995656967 2023-01-23 15:35:56.086152: step: 2024/1545, loss: 0.013872656039893627 2023-01-23 15:35:56.941391: step: 2026/1545, loss: 0.08589078485965729 2023-01-23 15:35:57.833783: step: 2028/1545, loss: 0.016598019748926163 2023-01-23 15:35:58.711808: step: 2030/1545, loss: 0.14253222942352295 2023-01-23 15:35:59.594276: step: 2032/1545, loss: 0.04741470888257027 2023-01-23 15:36:00.481998: step: 2034/1545, loss: 0.013783570379018784 2023-01-23 15:36:01.374739: step: 2036/1545, loss: 0.04289600998163223 2023-01-23 15:36:02.280304: step: 2038/1545, loss: 0.077133409678936 2023-01-23 15:36:03.167838: step: 2040/1545, loss: 0.16783852875232697 2023-01-23 15:36:04.089865: step: 2042/1545, loss: 0.008593179285526276 2023-01-23 15:36:04.961895: step: 2044/1545, loss: 0.17966404557228088 2023-01-23 15:36:05.891129: step: 2046/1545, loss: 0.2903461754322052 2023-01-23 15:36:06.798438: step: 2048/1545, loss: 0.09795036911964417 2023-01-23 15:36:07.687382: step: 2050/1545, loss: 0.10564545542001724 2023-01-23 15:36:08.567091: step: 2052/1545, loss: 0.014881010167300701 2023-01-23 15:36:09.475164: step: 2054/1545, loss: 0.07299565523862839 2023-01-23 15:36:10.345003: step: 2056/1545, loss: 0.13055863976478577 2023-01-23 15:36:11.217002: step: 2058/1545, loss: 0.0036102684680372477 2023-01-23 15:36:12.117887: step: 2060/1545, loss: 0.002647095127031207 2023-01-23 15:36:12.976424: step: 2062/1545, loss: 0.11818216741085052 2023-01-23 15:36:13.872903: step: 2064/1545, loss: 0.010464007966220379 2023-01-23 15:36:14.749079: step: 2066/1545, loss: 0.002721986034885049 2023-01-23 15:36:15.619265: step: 2068/1545, loss: 0.07968373596668243 2023-01-23 15:36:16.461910: step: 2070/1545, loss: 0.0010215836809948087 2023-01-23 15:36:17.354566: step: 2072/1545, loss: 0.02076292224228382 2023-01-23 15:36:18.198462: step: 2074/1545, loss: 0.038848720490932465 2023-01-23 15:36:19.087367: step: 2076/1545, loss: 0.2295750081539154 2023-01-23 15:36:19.933834: step: 2078/1545, loss: 0.03481661155819893 2023-01-23 15:36:20.793528: step: 2080/1545, loss: 0.05247360095381737 2023-01-23 15:36:21.686167: step: 2082/1545, loss: 0.03691601753234863 2023-01-23 15:36:22.572632: step: 2084/1545, loss: 0.07984510064125061 2023-01-23 15:36:23.515156: step: 2086/1545, loss: 0.006057587452232838 2023-01-23 15:36:24.382941: step: 2088/1545, loss: 0.04813067242503166 2023-01-23 15:36:25.295498: step: 2090/1545, loss: 0.001093425089493394 2023-01-23 15:36:26.146615: step: 2092/1545, loss: 0.008783623576164246 2023-01-23 15:36:26.988503: step: 2094/1545, loss: 0.01623348705470562 2023-01-23 15:36:27.927483: step: 2096/1545, loss: 0.07435338199138641 2023-01-23 15:36:28.788182: step: 2098/1545, loss: 0.01596500724554062 2023-01-23 15:36:29.656392: step: 2100/1545, loss: 0.035878874361515045 2023-01-23 15:36:30.633878: step: 2102/1545, loss: 0.01062481664121151 2023-01-23 15:36:31.485148: step: 2104/1545, loss: 0.3802725672721863 2023-01-23 15:36:32.403129: step: 2106/1545, loss: 0.17794451117515564 2023-01-23 15:36:33.296893: step: 2108/1545, loss: 0.069764144718647 2023-01-23 15:36:34.140583: step: 2110/1545, loss: 0.2840381860733032 2023-01-23 15:36:35.055863: step: 2112/1545, loss: 0.05429913103580475 2023-01-23 15:36:35.942524: step: 2114/1545, loss: 0.15986843407154083 2023-01-23 15:36:36.815805: step: 2116/1545, loss: 0.008955326862633228 2023-01-23 15:36:37.740139: step: 2118/1545, loss: 0.33312684297561646 2023-01-23 15:36:38.634525: step: 2120/1545, loss: 0.05213063955307007 2023-01-23 15:36:39.508255: step: 2122/1545, loss: 0.051280427724123 2023-01-23 15:36:40.382949: step: 2124/1545, loss: 0.017260126769542694 2023-01-23 15:36:41.266026: step: 2126/1545, loss: 0.0953696221113205 2023-01-23 15:36:42.148342: step: 2128/1545, loss: 0.021094946190714836 2023-01-23 15:36:43.029413: step: 2130/1545, loss: 0.03956247493624687 2023-01-23 15:36:43.996058: step: 2132/1545, loss: 0.04976760223507881 2023-01-23 15:36:44.883635: step: 2134/1545, loss: 0.0030405493453145027 2023-01-23 15:36:45.799494: step: 2136/1545, loss: 0.25149333477020264 2023-01-23 15:36:46.673014: step: 2138/1545, loss: 0.005632356740534306 2023-01-23 15:36:47.516045: step: 2140/1545, loss: 0.005352403037250042 2023-01-23 15:36:48.422761: step: 2142/1545, loss: 0.06483182311058044 2023-01-23 15:36:49.288846: step: 2144/1545, loss: 0.052263293415308 2023-01-23 15:36:50.198390: step: 2146/1545, loss: 0.0013414522400125861 2023-01-23 15:36:51.110522: step: 2148/1545, loss: 0.016932860016822815 2023-01-23 15:36:51.966218: step: 2150/1545, loss: 0.0006957411533221602 2023-01-23 15:36:52.883029: step: 2152/1545, loss: 0.09989138692617416 2023-01-23 15:36:53.806925: step: 2154/1545, loss: 0.1006929948925972 2023-01-23 15:36:54.717689: step: 2156/1545, loss: 0.0052522397600114346 2023-01-23 15:36:55.615625: step: 2158/1545, loss: 0.01573580503463745 2023-01-23 15:36:56.478816: step: 2160/1545, loss: 0.07573004812002182 2023-01-23 15:36:57.355026: step: 2162/1545, loss: 0.07228583842515945 2023-01-23 15:36:58.243001: step: 2164/1545, loss: 0.002767454367130995 2023-01-23 15:36:59.115819: step: 2166/1545, loss: 0.2868695855140686 2023-01-23 15:36:59.992951: step: 2168/1545, loss: 0.032103702425956726 2023-01-23 15:37:00.860538: step: 2170/1545, loss: 0.01057208701968193 2023-01-23 15:37:01.756453: step: 2172/1545, loss: 0.017750298604369164 2023-01-23 15:37:02.657004: step: 2174/1545, loss: 0.0010984456166625023 2023-01-23 15:37:03.553923: step: 2176/1545, loss: 0.018670804798603058 2023-01-23 15:37:04.484893: step: 2178/1545, loss: 0.026671281084418297 2023-01-23 15:37:05.342338: step: 2180/1545, loss: 0.004405996296554804 2023-01-23 15:37:06.271692: step: 2182/1545, loss: 0.0004390220856294036 2023-01-23 15:37:07.139834: step: 2184/1545, loss: 0.0017414108151569963 2023-01-23 15:37:08.040281: step: 2186/1545, loss: 0.12107698619365692 2023-01-23 15:37:08.894719: step: 2188/1545, loss: 0.11292670667171478 2023-01-23 15:37:09.741391: step: 2190/1545, loss: 0.0005602863384410739 2023-01-23 15:37:10.583613: step: 2192/1545, loss: 0.05179998651146889 2023-01-23 15:37:11.523166: step: 2194/1545, loss: 0.0898272693157196 2023-01-23 15:37:12.401042: step: 2196/1545, loss: 0.003030282212421298 2023-01-23 15:37:13.317826: step: 2198/1545, loss: 0.6892052292823792 2023-01-23 15:37:14.268003: step: 2200/1545, loss: 0.32105889916419983 2023-01-23 15:37:15.156061: step: 2202/1545, loss: 0.08822339028120041 2023-01-23 15:37:16.069987: step: 2204/1545, loss: 0.020782047882676125 2023-01-23 15:37:16.944705: step: 2206/1545, loss: 0.010394787415862083 2023-01-23 15:37:17.817345: step: 2208/1545, loss: 0.0034502174239605665 2023-01-23 15:37:18.668166: step: 2210/1545, loss: 0.006997454445809126 2023-01-23 15:37:19.542522: step: 2212/1545, loss: 0.1494894176721573 2023-01-23 15:37:20.498671: step: 2214/1545, loss: 0.18052668869495392 2023-01-23 15:37:21.397744: step: 2216/1545, loss: 0.038196317851543427 2023-01-23 15:37:22.333648: step: 2218/1545, loss: 0.0041534556075930595 2023-01-23 15:37:23.221920: step: 2220/1545, loss: 0.005271369591355324 2023-01-23 15:37:24.051372: step: 2222/1545, loss: 0.3984907269477844 2023-01-23 15:37:24.946827: step: 2224/1545, loss: 0.034119315445423126 2023-01-23 15:37:25.866100: step: 2226/1545, loss: 0.001980537548661232 2023-01-23 15:37:26.767364: step: 2228/1545, loss: 0.01850169524550438 2023-01-23 15:37:27.613700: step: 2230/1545, loss: 0.008661539293825626 2023-01-23 15:37:28.560290: step: 2232/1545, loss: 0.003765951842069626 2023-01-23 15:37:29.450616: step: 2234/1545, loss: 0.012435234151780605 2023-01-23 15:37:30.316058: step: 2236/1545, loss: 0.038160938769578934 2023-01-23 15:37:31.207911: step: 2238/1545, loss: 0.06314883381128311 2023-01-23 15:37:32.098415: step: 2240/1545, loss: 0.26238223910331726 2023-01-23 15:37:32.911591: step: 2242/1545, loss: 0.005755304824560881 2023-01-23 15:37:33.868297: step: 2244/1545, loss: 0.025825710967183113 2023-01-23 15:37:34.810434: step: 2246/1545, loss: 0.1213383898139 2023-01-23 15:37:35.683239: step: 2248/1545, loss: 0.0008021580288186669 2023-01-23 15:37:36.565409: step: 2250/1545, loss: 0.011911907233297825 2023-01-23 15:37:37.534791: step: 2252/1545, loss: 0.7813310623168945 2023-01-23 15:37:38.394501: step: 2254/1545, loss: 0.01920882798731327 2023-01-23 15:37:39.303923: step: 2256/1545, loss: 0.10142134130001068 2023-01-23 15:37:40.158356: step: 2258/1545, loss: 0.05117620900273323 2023-01-23 15:37:41.135235: step: 2260/1545, loss: 0.0007767166243866086 2023-01-23 15:37:42.025889: step: 2262/1545, loss: 0.12245012074708939 2023-01-23 15:37:42.903113: step: 2264/1545, loss: 0.0007602095720358193 2023-01-23 15:37:43.782190: step: 2266/1545, loss: 0.0013842378975823522 2023-01-23 15:37:44.717241: step: 2268/1545, loss: 1.0848528146743774 2023-01-23 15:37:45.608103: step: 2270/1545, loss: 0.010259827598929405 2023-01-23 15:37:46.470990: step: 2272/1545, loss: 0.0018980565946549177 2023-01-23 15:37:47.340166: step: 2274/1545, loss: 0.0011206150520592928 2023-01-23 15:37:48.297155: step: 2276/1545, loss: 0.014071250334382057 2023-01-23 15:37:49.273450: step: 2278/1545, loss: 0.1170673668384552 2023-01-23 15:37:50.182158: step: 2280/1545, loss: 0.015552449971437454 2023-01-23 15:37:51.074329: step: 2282/1545, loss: 0.00010078022751258686 2023-01-23 15:37:51.968194: step: 2284/1545, loss: 0.0011143317678943276 2023-01-23 15:37:52.830056: step: 2286/1545, loss: 0.09391223639249802 2023-01-23 15:37:53.735140: step: 2288/1545, loss: 0.005478584673255682 2023-01-23 15:37:54.599041: step: 2290/1545, loss: 0.026244886219501495 2023-01-23 15:37:55.515899: step: 2292/1545, loss: 0.00782626774162054 2023-01-23 15:37:56.407465: step: 2294/1545, loss: 0.002719296608120203 2023-01-23 15:37:57.352389: step: 2296/1545, loss: 0.13230596482753754 2023-01-23 15:37:58.204613: step: 2298/1545, loss: 0.0010648701572790742 2023-01-23 15:37:59.101570: step: 2300/1545, loss: 0.0232098288834095 2023-01-23 15:38:00.065800: step: 2302/1545, loss: 6.82486715959385e-05 2023-01-23 15:38:00.929194: step: 2304/1545, loss: 0.09293696284294128 2023-01-23 15:38:01.858475: step: 2306/1545, loss: 0.28789639472961426 2023-01-23 15:38:02.739776: step: 2308/1545, loss: 0.01970677636563778 2023-01-23 15:38:03.597210: step: 2310/1545, loss: 0.00029053425532765687 2023-01-23 15:38:04.482077: step: 2312/1545, loss: 0.3017157316207886 2023-01-23 15:38:05.381041: step: 2314/1545, loss: 0.026583168655633926 2023-01-23 15:38:06.286395: step: 2316/1545, loss: 0.4873886704444885 2023-01-23 15:38:07.244572: step: 2318/1545, loss: 0.0011792379664257169 2023-01-23 15:38:08.108437: step: 2320/1545, loss: 0.0005011354223825037 2023-01-23 15:38:09.006566: step: 2322/1545, loss: 0.0005280781188048422 2023-01-23 15:38:09.881897: step: 2324/1545, loss: 0.07940219342708588 2023-01-23 15:38:10.746590: step: 2326/1545, loss: 0.3893829584121704 2023-01-23 15:38:11.624998: step: 2328/1545, loss: 0.00017463511903770268 2023-01-23 15:38:12.489837: step: 2330/1545, loss: 0.12396685779094696 2023-01-23 15:38:13.365070: step: 2332/1545, loss: 0.001983990892767906 2023-01-23 15:38:14.217504: step: 2334/1545, loss: 0.003844449296593666 2023-01-23 15:38:15.092747: step: 2336/1545, loss: 0.11475395411252975 2023-01-23 15:38:15.952485: step: 2338/1545, loss: 0.12909060716629028 2023-01-23 15:38:16.868245: step: 2340/1545, loss: 0.1837640404701233 2023-01-23 15:38:17.826054: step: 2342/1545, loss: 0.8699238300323486 2023-01-23 15:38:18.720082: step: 2344/1545, loss: 0.0502547025680542 2023-01-23 15:38:19.682146: step: 2346/1545, loss: 0.000995179987512529 2023-01-23 15:38:20.585080: step: 2348/1545, loss: 0.0009776639053598046 2023-01-23 15:38:21.469952: step: 2350/1545, loss: 0.012921780347824097 2023-01-23 15:38:22.379539: step: 2352/1545, loss: 0.0019466490484774113 2023-01-23 15:38:23.258045: step: 2354/1545, loss: 0.003246514592319727 2023-01-23 15:38:24.119518: step: 2356/1545, loss: 0.5715919137001038 2023-01-23 15:38:25.036757: step: 2358/1545, loss: 0.2846696674823761 2023-01-23 15:38:25.906441: step: 2360/1545, loss: 0.009164413437247276 2023-01-23 15:38:26.770954: step: 2362/1545, loss: 0.0007408101810142398 2023-01-23 15:38:27.696009: step: 2364/1545, loss: 0.009223277680575848 2023-01-23 15:38:28.568104: step: 2366/1545, loss: 0.013103310018777847 2023-01-23 15:38:29.532793: step: 2368/1545, loss: 0.006865677423775196 2023-01-23 15:38:30.485814: step: 2370/1545, loss: 0.030411697924137115 2023-01-23 15:38:31.380263: step: 2372/1545, loss: 0.03069303371012211 2023-01-23 15:38:32.212836: step: 2374/1545, loss: 0.4758675992488861 2023-01-23 15:38:33.106803: step: 2376/1545, loss: 0.029774902388453484 2023-01-23 15:38:33.972095: step: 2378/1545, loss: 0.12580138444900513 2023-01-23 15:38:34.839945: step: 2380/1545, loss: 0.0016533134039491415 2023-01-23 15:38:35.765947: step: 2382/1545, loss: 0.11887475103139877 2023-01-23 15:38:36.778336: step: 2384/1545, loss: 0.016106411814689636 2023-01-23 15:38:37.693706: step: 2386/1545, loss: 0.04889513552188873 2023-01-23 15:38:38.544308: step: 2388/1545, loss: 0.004518143367022276 2023-01-23 15:38:39.428920: step: 2390/1545, loss: 0.21500054001808167 2023-01-23 15:38:40.289285: step: 2392/1545, loss: 0.008669744245707989 2023-01-23 15:38:41.153090: step: 2394/1545, loss: 0.46513620018959045 2023-01-23 15:38:42.085185: step: 2396/1545, loss: 0.11447544395923615 2023-01-23 15:38:43.017417: step: 2398/1545, loss: 0.0749838799238205 2023-01-23 15:38:43.902330: step: 2400/1545, loss: 0.11614418774843216 2023-01-23 15:38:44.820539: step: 2402/1545, loss: 0.015133274719119072 2023-01-23 15:38:45.700275: step: 2404/1545, loss: 0.012391900643706322 2023-01-23 15:38:46.593054: step: 2406/1545, loss: 0.030087100341916084 2023-01-23 15:38:47.533035: step: 2408/1545, loss: 0.049334585666656494 2023-01-23 15:38:48.419901: step: 2410/1545, loss: 0.0008117269026115537 2023-01-23 15:38:49.378979: step: 2412/1545, loss: 0.03162292763590813 2023-01-23 15:38:50.247213: step: 2414/1545, loss: 0.0010311694350093603 2023-01-23 15:38:51.123855: step: 2416/1545, loss: 0.0002989705535583198 2023-01-23 15:38:52.031293: step: 2418/1545, loss: 0.006710299290716648 2023-01-23 15:38:52.940898: step: 2420/1545, loss: 0.107656329870224 2023-01-23 15:38:53.802605: step: 2422/1545, loss: 0.02065865509212017 2023-01-23 15:38:54.718008: step: 2424/1545, loss: 0.06970905512571335 2023-01-23 15:38:55.644780: step: 2426/1545, loss: 0.025057747960090637 2023-01-23 15:38:56.550871: step: 2428/1545, loss: 0.007287619635462761 2023-01-23 15:38:57.449605: step: 2430/1545, loss: 0.189358651638031 2023-01-23 15:38:58.316431: step: 2432/1545, loss: 0.01815696991980076 2023-01-23 15:38:59.198184: step: 2434/1545, loss: 0.009055724367499352 2023-01-23 15:39:00.056385: step: 2436/1545, loss: 0.0021829118486493826 2023-01-23 15:39:00.960542: step: 2438/1545, loss: 0.001043494325131178 2023-01-23 15:39:01.859727: step: 2440/1545, loss: 0.0015112092951312661 2023-01-23 15:39:02.717061: step: 2442/1545, loss: 0.0014822212979197502 2023-01-23 15:39:03.581141: step: 2444/1545, loss: 0.006049914285540581 2023-01-23 15:39:04.464999: step: 2446/1545, loss: 0.017110880464315414 2023-01-23 15:39:05.345359: step: 2448/1545, loss: 0.09920976310968399 2023-01-23 15:39:06.284593: step: 2450/1545, loss: 0.08082167059183121 2023-01-23 15:39:07.198588: step: 2452/1545, loss: 0.6624600887298584 2023-01-23 15:39:08.035102: step: 2454/1545, loss: 0.0003254749171901494 2023-01-23 15:39:08.965077: step: 2456/1545, loss: 0.004605339374393225 2023-01-23 15:39:09.868228: step: 2458/1545, loss: 0.011013253591954708 2023-01-23 15:39:10.746262: step: 2460/1545, loss: 0.6617501378059387 2023-01-23 15:39:11.700104: step: 2462/1545, loss: 0.011044086888432503 2023-01-23 15:39:12.569129: step: 2464/1545, loss: 0.006694603245705366 2023-01-23 15:39:13.435789: step: 2466/1545, loss: 0.0011203165631741285 2023-01-23 15:39:14.368885: step: 2468/1545, loss: 0.04859817028045654 2023-01-23 15:39:15.240964: step: 2470/1545, loss: 0.02139406092464924 2023-01-23 15:39:16.146901: step: 2472/1545, loss: 0.005269146058708429 2023-01-23 15:39:17.102098: step: 2474/1545, loss: 0.08459078520536423 2023-01-23 15:39:17.994709: step: 2476/1545, loss: 0.07500018924474716 2023-01-23 15:39:18.876922: step: 2478/1545, loss: 0.04262277111411095 2023-01-23 15:39:19.771473: step: 2480/1545, loss: 0.01715013012290001 2023-01-23 15:39:20.683083: step: 2482/1545, loss: 0.0035757082514464855 2023-01-23 15:39:21.602724: step: 2484/1545, loss: 0.018918121233582497 2023-01-23 15:39:22.527577: step: 2486/1545, loss: 0.0305460374802351 2023-01-23 15:39:23.434108: step: 2488/1545, loss: 0.002886876929551363 2023-01-23 15:39:24.311582: step: 2490/1545, loss: 0.000635859149042517 2023-01-23 15:39:25.201311: step: 2492/1545, loss: 0.1259145885705948 2023-01-23 15:39:26.040438: step: 2494/1545, loss: 0.02774808183312416 2023-01-23 15:39:26.970053: step: 2496/1545, loss: 0.06133916601538658 2023-01-23 15:39:27.881059: step: 2498/1545, loss: 0.010225829668343067 2023-01-23 15:39:28.758533: step: 2500/1545, loss: 0.005295031704008579 2023-01-23 15:39:29.661103: step: 2502/1545, loss: 0.056081026792526245 2023-01-23 15:39:30.582664: step: 2504/1545, loss: 0.04754921793937683 2023-01-23 15:39:31.424545: step: 2506/1545, loss: 0.0006210001301951706 2023-01-23 15:39:32.379122: step: 2508/1545, loss: 0.008840368129312992 2023-01-23 15:39:33.246104: step: 2510/1545, loss: 0.13907143473625183 2023-01-23 15:39:34.111430: step: 2512/1545, loss: 0.047717493027448654 2023-01-23 15:39:35.112137: step: 2514/1545, loss: 0.13011179864406586 2023-01-23 15:39:36.034836: step: 2516/1545, loss: 0.002955880481749773 2023-01-23 15:39:36.984861: step: 2518/1545, loss: 0.2960830330848694 2023-01-23 15:39:37.837970: step: 2520/1545, loss: 0.00010962550004478544 2023-01-23 15:39:38.728219: step: 2522/1545, loss: 0.051266565918922424 2023-01-23 15:39:39.629781: step: 2524/1545, loss: 0.00036588398506864905 2023-01-23 15:39:40.536004: step: 2526/1545, loss: 0.0031640734523534775 2023-01-23 15:39:41.425096: step: 2528/1545, loss: 0.019687943160533905 2023-01-23 15:39:42.274476: step: 2530/1545, loss: 0.017407746985554695 2023-01-23 15:39:43.194808: step: 2532/1545, loss: 0.0006087480578571558 2023-01-23 15:39:44.094143: step: 2534/1545, loss: 0.011424936354160309 2023-01-23 15:39:44.941491: step: 2536/1545, loss: 0.00024964468320831656 2023-01-23 15:39:45.816155: step: 2538/1545, loss: 0.0011232636170461774 2023-01-23 15:39:46.696392: step: 2540/1545, loss: 0.013909404166042805 2023-01-23 15:39:47.575684: step: 2542/1545, loss: 0.06616067886352539 2023-01-23 15:39:48.499424: step: 2544/1545, loss: 0.003614918328821659 2023-01-23 15:39:49.351299: step: 2546/1545, loss: 0.022492073476314545 2023-01-23 15:39:50.239045: step: 2548/1545, loss: 0.3169645369052887 2023-01-23 15:39:51.154897: step: 2550/1545, loss: 0.013627884909510612 2023-01-23 15:39:52.002028: step: 2552/1545, loss: 0.0013753093080595136 2023-01-23 15:39:52.982495: step: 2554/1545, loss: 0.292453408241272 2023-01-23 15:39:53.872761: step: 2556/1545, loss: 0.005072190426290035 2023-01-23 15:39:54.726109: step: 2558/1545, loss: 0.027258699759840965 2023-01-23 15:39:55.628577: step: 2560/1545, loss: 0.07643420994281769 2023-01-23 15:39:56.466157: step: 2562/1545, loss: 0.0005977434339001775 2023-01-23 15:39:57.337507: step: 2564/1545, loss: 0.00752691924571991 2023-01-23 15:39:58.226347: step: 2566/1545, loss: 0.00040418264688923955 2023-01-23 15:39:59.074594: step: 2568/1545, loss: 0.028901729732751846 2023-01-23 15:39:59.951569: step: 2570/1545, loss: 0.07907487452030182 2023-01-23 15:40:00.861268: step: 2572/1545, loss: 0.011228811927139759 2023-01-23 15:40:01.711606: step: 2574/1545, loss: 0.0050137764774262905 2023-01-23 15:40:02.644092: step: 2576/1545, loss: 0.005374593194574118 2023-01-23 15:40:03.531712: step: 2578/1545, loss: 0.011920575983822346 2023-01-23 15:40:04.430098: step: 2580/1545, loss: 0.06143476814031601 2023-01-23 15:40:05.277404: step: 2582/1545, loss: 0.0018523761536926031 2023-01-23 15:40:06.217652: step: 2584/1545, loss: 0.0016225988510996103 2023-01-23 15:40:07.092321: step: 2586/1545, loss: 0.007040095515549183 2023-01-23 15:40:07.967016: step: 2588/1545, loss: 0.6844498515129089 2023-01-23 15:40:08.859073: step: 2590/1545, loss: 0.07401303201913834 2023-01-23 15:40:09.742464: step: 2592/1545, loss: 0.0714573860168457 2023-01-23 15:40:10.641906: step: 2594/1545, loss: 0.0010294286767020822 2023-01-23 15:40:11.595697: step: 2596/1545, loss: 0.0021629626862704754 2023-01-23 15:40:12.480313: step: 2598/1545, loss: 0.013321603648364544 2023-01-23 15:40:13.360907: step: 2600/1545, loss: 0.0328557975590229 2023-01-23 15:40:14.256555: step: 2602/1545, loss: 0.066234290599823 2023-01-23 15:40:15.151144: step: 2604/1545, loss: 0.0005406456766650081 2023-01-23 15:40:16.043873: step: 2606/1545, loss: 0.0018821083940565586 2023-01-23 15:40:16.905759: step: 2608/1545, loss: 0.09460935741662979 2023-01-23 15:40:17.788621: step: 2610/1545, loss: 0.04072488471865654 2023-01-23 15:40:18.677394: step: 2612/1545, loss: 0.02911069430410862 2023-01-23 15:40:19.574661: step: 2614/1545, loss: 0.000401977333240211 2023-01-23 15:40:20.514901: step: 2616/1545, loss: 0.0008722377242520452 2023-01-23 15:40:21.410462: step: 2618/1545, loss: 0.07398698478937149 2023-01-23 15:40:22.345266: step: 2620/1545, loss: 0.015834908932447433 2023-01-23 15:40:23.251025: step: 2622/1545, loss: 0.0022546022664755583 2023-01-23 15:40:24.112368: step: 2624/1545, loss: 0.015670420601963997 2023-01-23 15:40:24.992969: step: 2626/1545, loss: 0.1419619768857956 2023-01-23 15:40:25.944469: step: 2628/1545, loss: 0.1661611795425415 2023-01-23 15:40:26.806905: step: 2630/1545, loss: 0.03697796165943146 2023-01-23 15:40:27.718563: step: 2632/1545, loss: 0.05161968991160393 2023-01-23 15:40:28.607194: step: 2634/1545, loss: 0.0009136328590102494 2023-01-23 15:40:29.463232: step: 2636/1545, loss: 0.1657576560974121 2023-01-23 15:40:30.379393: step: 2638/1545, loss: 1.6584798097610474 2023-01-23 15:40:31.260040: step: 2640/1545, loss: 0.015692370012402534 2023-01-23 15:40:32.136432: step: 2642/1545, loss: 0.001073207939043641 2023-01-23 15:40:33.035679: step: 2644/1545, loss: 0.2795667350292206 2023-01-23 15:40:33.927353: step: 2646/1545, loss: 0.05776982381939888 2023-01-23 15:40:34.819559: step: 2648/1545, loss: 0.030253462493419647 2023-01-23 15:40:35.683143: step: 2650/1545, loss: 0.03391680121421814 2023-01-23 15:40:36.567499: step: 2652/1545, loss: 0.07892535626888275 2023-01-23 15:40:37.409721: step: 2654/1545, loss: 0.008524486795067787 2023-01-23 15:40:38.383136: step: 2656/1545, loss: 0.010840482078492641 2023-01-23 15:40:39.214329: step: 2658/1545, loss: 0.010224067606031895 2023-01-23 15:40:40.054931: step: 2660/1545, loss: 0.0031233159825205803 2023-01-23 15:40:41.007778: step: 2662/1545, loss: 0.110598623752594 2023-01-23 15:40:41.860137: step: 2664/1545, loss: 0.14296749234199524 2023-01-23 15:40:42.679345: step: 2666/1545, loss: 0.0014957113889977336 2023-01-23 15:40:43.542890: step: 2668/1545, loss: 0.2659752368927002 2023-01-23 15:40:44.475574: step: 2670/1545, loss: 0.11743433028459549 2023-01-23 15:40:45.333990: step: 2672/1545, loss: 0.017440125346183777 2023-01-23 15:40:46.304944: step: 2674/1545, loss: 0.0011742404894903302 2023-01-23 15:40:47.206974: step: 2676/1545, loss: 0.02973603457212448 2023-01-23 15:40:48.100094: step: 2678/1545, loss: 0.004025781527161598 2023-01-23 15:40:48.978849: step: 2680/1545, loss: 0.05878017097711563 2023-01-23 15:40:49.946030: step: 2682/1545, loss: 0.0019733505323529243 2023-01-23 15:40:50.832989: step: 2684/1545, loss: 0.03831389546394348 2023-01-23 15:40:51.721427: step: 2686/1545, loss: 0.20391929149627686 2023-01-23 15:40:52.579315: step: 2688/1545, loss: 0.01524649653583765 2023-01-23 15:40:53.455591: step: 2690/1545, loss: 0.02690288797020912 2023-01-23 15:40:54.324396: step: 2692/1545, loss: 0.064254030585289 2023-01-23 15:40:55.221936: step: 2694/1545, loss: 0.004556688014417887 2023-01-23 15:40:56.125291: step: 2696/1545, loss: 0.041874147951602936 2023-01-23 15:40:56.998316: step: 2698/1545, loss: 0.007473260164260864 2023-01-23 15:40:57.839750: step: 2700/1545, loss: 0.0029907419811934233 2023-01-23 15:40:58.738549: step: 2702/1545, loss: 0.0037159654311835766 2023-01-23 15:40:59.597849: step: 2704/1545, loss: 0.017722390592098236 2023-01-23 15:41:00.482708: step: 2706/1545, loss: 0.01971364952623844 2023-01-23 15:41:01.379032: step: 2708/1545, loss: 0.03285406902432442 2023-01-23 15:41:02.226067: step: 2710/1545, loss: 0.0006024589529260993 2023-01-23 15:41:03.106864: step: 2712/1545, loss: 0.02358538657426834 2023-01-23 15:41:03.957862: step: 2714/1545, loss: 0.004452089313417673 2023-01-23 15:41:04.775568: step: 2716/1545, loss: 0.17646121978759766 2023-01-23 15:41:05.671108: step: 2718/1545, loss: 0.01772739179432392 2023-01-23 15:41:06.518014: step: 2720/1545, loss: 0.0031299637630581856 2023-01-23 15:41:07.389056: step: 2722/1545, loss: 0.0006813157815486193 2023-01-23 15:41:08.275056: step: 2724/1545, loss: 0.026055242866277695 2023-01-23 15:41:09.119155: step: 2726/1545, loss: 0.003889607498422265 2023-01-23 15:41:10.002426: step: 2728/1545, loss: 0.016045812517404556 2023-01-23 15:41:10.885925: step: 2730/1545, loss: 0.056144703179597855 2023-01-23 15:41:11.741432: step: 2732/1545, loss: 0.0026372424326837063 2023-01-23 15:41:12.632465: step: 2734/1545, loss: 0.0008439173689112067 2023-01-23 15:41:13.571379: step: 2736/1545, loss: 0.0674377903342247 2023-01-23 15:41:14.412502: step: 2738/1545, loss: 0.2438899576663971 2023-01-23 15:41:15.287887: step: 2740/1545, loss: 0.012847842648625374 2023-01-23 15:41:16.186652: step: 2742/1545, loss: 0.0001050877763191238 2023-01-23 15:41:17.138367: step: 2744/1545, loss: 0.011518738232553005 2023-01-23 15:41:18.055633: step: 2746/1545, loss: 0.3617396652698517 2023-01-23 15:41:18.916771: step: 2748/1545, loss: 0.02461697906255722 2023-01-23 15:41:19.825584: step: 2750/1545, loss: 0.0007951430743560195 2023-01-23 15:41:20.683549: step: 2752/1545, loss: 0.25914525985717773 2023-01-23 15:41:21.507398: step: 2754/1545, loss: 0.05628928542137146 2023-01-23 15:41:22.405512: step: 2756/1545, loss: 0.3777044415473938 2023-01-23 15:41:23.286243: step: 2758/1545, loss: 0.31511417031288147 2023-01-23 15:41:24.142816: step: 2760/1545, loss: 0.0027226663660258055 2023-01-23 15:41:25.077141: step: 2762/1545, loss: 0.0007939235074445605 2023-01-23 15:41:25.989734: step: 2764/1545, loss: 0.12053327262401581 2023-01-23 15:41:26.874478: step: 2766/1545, loss: 0.0022772224619984627 2023-01-23 15:41:27.747836: step: 2768/1545, loss: 0.24238958954811096 2023-01-23 15:41:28.620655: step: 2770/1545, loss: 0.0455671027302742 2023-01-23 15:41:29.545452: step: 2772/1545, loss: 0.042815130203962326 2023-01-23 15:41:30.407529: step: 2774/1545, loss: 0.09816824644804001 2023-01-23 15:41:31.279438: step: 2776/1545, loss: 0.03059220500290394 2023-01-23 15:41:32.128910: step: 2778/1545, loss: 0.008134639821946621 2023-01-23 15:41:33.025493: step: 2780/1545, loss: 0.05814727395772934 2023-01-23 15:41:33.901799: step: 2782/1545, loss: 0.001251137349754572 2023-01-23 15:41:34.805805: step: 2784/1545, loss: 0.08498897403478622 2023-01-23 15:41:35.670706: step: 2786/1545, loss: 0.35541877150535583 2023-01-23 15:41:36.547233: step: 2788/1545, loss: 0.0013275983510538936 2023-01-23 15:41:37.422139: step: 2790/1545, loss: 0.26374080777168274 2023-01-23 15:41:38.336479: step: 2792/1545, loss: 0.4613550901412964 2023-01-23 15:41:39.256314: step: 2794/1545, loss: 0.2474430650472641 2023-01-23 15:41:40.154348: step: 2796/1545, loss: 0.07059919089078903 2023-01-23 15:41:41.050746: step: 2798/1545, loss: 0.0022293440997600555 2023-01-23 15:41:41.912498: step: 2800/1545, loss: 0.01766541600227356 2023-01-23 15:41:42.772369: step: 2802/1545, loss: 0.0026428636629134417 2023-01-23 15:41:43.629288: step: 2804/1545, loss: 0.1480870246887207 2023-01-23 15:41:44.510646: step: 2806/1545, loss: 0.02013247273862362 2023-01-23 15:41:45.411104: step: 2808/1545, loss: 0.19266483187675476 2023-01-23 15:41:46.320304: step: 2810/1545, loss: 0.08932310342788696 2023-01-23 15:41:47.202763: step: 2812/1545, loss: 0.000432107801316306 2023-01-23 15:41:48.104937: step: 2814/1545, loss: 0.02102341502904892 2023-01-23 15:41:49.035384: step: 2816/1545, loss: 0.7070551514625549 2023-01-23 15:41:49.889767: step: 2818/1545, loss: 0.05303288251161575 2023-01-23 15:41:50.809465: step: 2820/1545, loss: 0.7031835317611694 2023-01-23 15:41:51.718864: step: 2822/1545, loss: 0.06590745598077774 2023-01-23 15:41:52.611222: step: 2824/1545, loss: 0.526762843132019 2023-01-23 15:41:53.466577: step: 2826/1545, loss: 0.02350245602428913 2023-01-23 15:41:54.336994: step: 2828/1545, loss: 0.0021891319192945957 2023-01-23 15:41:55.203619: step: 2830/1545, loss: 0.14146210253238678 2023-01-23 15:41:56.089379: step: 2832/1545, loss: 1.0355061292648315 2023-01-23 15:41:56.951360: step: 2834/1545, loss: 0.3249453008174896 2023-01-23 15:41:57.861780: step: 2836/1545, loss: 0.04496322199702263 2023-01-23 15:41:58.776690: step: 2838/1545, loss: 0.014702271670103073 2023-01-23 15:41:59.654914: step: 2840/1545, loss: 0.00566176138818264 2023-01-23 15:42:00.564988: step: 2842/1545, loss: 0.05971655622124672 2023-01-23 15:42:01.427544: step: 2844/1545, loss: 0.07200320065021515 2023-01-23 15:42:02.260864: step: 2846/1545, loss: 0.05181393027305603 2023-01-23 15:42:03.115897: step: 2848/1545, loss: 0.0023197210393846035 2023-01-23 15:42:03.988040: step: 2850/1545, loss: 0.03378680720925331 2023-01-23 15:42:04.883382: step: 2852/1545, loss: 0.03655042499303818 2023-01-23 15:42:05.803459: step: 2854/1545, loss: 0.014631316997110844 2023-01-23 15:42:06.823729: step: 2856/1545, loss: 0.019400138407945633 2023-01-23 15:42:07.670952: step: 2858/1545, loss: 0.019540419802069664 2023-01-23 15:42:08.551471: step: 2860/1545, loss: 0.0067700473591685295 2023-01-23 15:42:09.425428: step: 2862/1545, loss: 0.0039769443683326244 2023-01-23 15:42:10.279882: step: 2864/1545, loss: 0.010925698094069958 2023-01-23 15:42:11.164648: step: 2866/1545, loss: 0.015698255971074104 2023-01-23 15:42:12.063432: step: 2868/1545, loss: 0.2255653589963913 2023-01-23 15:42:12.944153: step: 2870/1545, loss: 0.031411319971084595 2023-01-23 15:42:13.809919: step: 2872/1545, loss: 0.00132514419965446 2023-01-23 15:42:14.674919: step: 2874/1545, loss: 0.012295926921069622 2023-01-23 15:42:15.616627: step: 2876/1545, loss: 0.36788210272789 2023-01-23 15:42:16.518905: step: 2878/1545, loss: 0.0033383285626769066 2023-01-23 15:42:17.401414: step: 2880/1545, loss: 0.008422400802373886 2023-01-23 15:42:18.299662: step: 2882/1545, loss: 0.02474316582083702 2023-01-23 15:42:19.230168: step: 2884/1545, loss: 0.005238340701907873 2023-01-23 15:42:20.151134: step: 2886/1545, loss: 0.03911324590444565 2023-01-23 15:42:21.027563: step: 2888/1545, loss: 0.08411624282598495 2023-01-23 15:42:21.879182: step: 2890/1545, loss: 0.26851385831832886 2023-01-23 15:42:22.783537: step: 2892/1545, loss: 0.03928680345416069 2023-01-23 15:42:23.670742: step: 2894/1545, loss: 0.01965802162885666 2023-01-23 15:42:24.530664: step: 2896/1545, loss: 0.00029553240165114403 2023-01-23 15:42:25.434997: step: 2898/1545, loss: 0.010449239984154701 2023-01-23 15:42:26.346699: step: 2900/1545, loss: 0.09272800385951996 2023-01-23 15:42:27.276269: step: 2902/1545, loss: 0.0698210597038269 2023-01-23 15:42:28.112096: step: 2904/1545, loss: 0.0005082603311166167 2023-01-23 15:42:29.104614: step: 2906/1545, loss: 0.0016954188467934728 2023-01-23 15:42:30.003612: step: 2908/1545, loss: 0.012760275974869728 2023-01-23 15:42:30.861167: step: 2910/1545, loss: 0.0011275728465989232 2023-01-23 15:42:31.794291: step: 2912/1545, loss: 0.0003750656032934785 2023-01-23 15:42:32.689789: step: 2914/1545, loss: 0.0019211439648643136 2023-01-23 15:42:33.599390: step: 2916/1545, loss: 0.13216866552829742 2023-01-23 15:42:34.430818: step: 2918/1545, loss: 0.0021061229053884745 2023-01-23 15:42:35.330970: step: 2920/1545, loss: 0.4359261095523834 2023-01-23 15:42:36.215625: step: 2922/1545, loss: 0.01399309653788805 2023-01-23 15:42:37.071837: step: 2924/1545, loss: 0.2861643433570862 2023-01-23 15:42:37.970214: step: 2926/1545, loss: 0.046213652938604355 2023-01-23 15:42:38.854094: step: 2928/1545, loss: 0.0015074304537847638 2023-01-23 15:42:39.768637: step: 2930/1545, loss: 0.005000709090381861 2023-01-23 15:42:40.661966: step: 2932/1545, loss: 0.03569699078798294 2023-01-23 15:42:41.541975: step: 2934/1545, loss: 0.026285044848918915 2023-01-23 15:42:42.429196: step: 2936/1545, loss: 0.2635856866836548 2023-01-23 15:42:43.281194: step: 2938/1545, loss: 0.09626089036464691 2023-01-23 15:42:44.153953: step: 2940/1545, loss: 0.03883038088679314 2023-01-23 15:42:44.998420: step: 2942/1545, loss: 0.10171906650066376 2023-01-23 15:42:45.866437: step: 2944/1545, loss: 0.0013951307628303766 2023-01-23 15:42:46.728352: step: 2946/1545, loss: 0.009794546291232109 2023-01-23 15:42:47.577813: step: 2948/1545, loss: 0.000509631063323468 2023-01-23 15:42:48.449996: step: 2950/1545, loss: 0.02392551861703396 2023-01-23 15:42:49.366696: step: 2952/1545, loss: 0.0006183790392242372 2023-01-23 15:42:50.244543: step: 2954/1545, loss: 0.12306976318359375 2023-01-23 15:42:51.103933: step: 2956/1545, loss: 0.11522282660007477 2023-01-23 15:42:51.949101: step: 2958/1545, loss: 0.011317386291921139 2023-01-23 15:42:52.848545: step: 2960/1545, loss: 0.05478649213910103 2023-01-23 15:42:53.735967: step: 2962/1545, loss: 0.02052232250571251 2023-01-23 15:42:54.577772: step: 2964/1545, loss: 0.012339992448687553 2023-01-23 15:42:55.467998: step: 2966/1545, loss: 0.43407145142555237 2023-01-23 15:42:56.364548: step: 2968/1545, loss: 0.14503398537635803 2023-01-23 15:42:57.254707: step: 2970/1545, loss: 0.007176724262535572 2023-01-23 15:42:58.172845: step: 2972/1545, loss: 0.1130456030368805 2023-01-23 15:42:59.116734: step: 2974/1545, loss: 0.0015084585174918175 2023-01-23 15:42:59.957644: step: 2976/1545, loss: 0.04702669754624367 2023-01-23 15:43:00.844497: step: 2978/1545, loss: 0.035751279443502426 2023-01-23 15:43:01.757115: step: 2980/1545, loss: 0.001540908357128501 2023-01-23 15:43:02.617078: step: 2982/1545, loss: 0.0006125455838628113 2023-01-23 15:43:03.462473: step: 2984/1545, loss: 0.02215196192264557 2023-01-23 15:43:04.325330: step: 2986/1545, loss: 0.1424078643321991 2023-01-23 15:43:05.205733: step: 2988/1545, loss: 0.020911136642098427 2023-01-23 15:43:06.140847: step: 2990/1545, loss: 0.0011619806755334139 2023-01-23 15:43:07.016668: step: 2992/1545, loss: 0.003009185427799821 2023-01-23 15:43:07.962625: step: 2994/1545, loss: 0.013833275996148586 2023-01-23 15:43:08.870424: step: 2996/1545, loss: 0.0010570232989266515 2023-01-23 15:43:09.722625: step: 2998/1545, loss: 0.005030564032495022 2023-01-23 15:43:10.637622: step: 3000/1545, loss: 0.0035611854400485754 2023-01-23 15:43:11.491229: step: 3002/1545, loss: 0.0020680190064013004 2023-01-23 15:43:12.336312: step: 3004/1545, loss: 0.12989088892936707 2023-01-23 15:43:13.260361: step: 3006/1545, loss: 0.04912882298231125 2023-01-23 15:43:14.134602: step: 3008/1545, loss: 0.00025911687407642603 2023-01-23 15:43:14.975985: step: 3010/1545, loss: 0.001618041074834764 2023-01-23 15:43:15.827968: step: 3012/1545, loss: 0.0010520578362047672 2023-01-23 15:43:16.683429: step: 3014/1545, loss: 0.032957643270492554 2023-01-23 15:43:17.543920: step: 3016/1545, loss: 0.0016214050119742751 2023-01-23 15:43:18.416695: step: 3018/1545, loss: 0.1606525331735611 2023-01-23 15:43:19.321882: step: 3020/1545, loss: 0.006161199416965246 2023-01-23 15:43:20.227972: step: 3022/1545, loss: 0.15233513712882996 2023-01-23 15:43:21.122827: step: 3024/1545, loss: 0.0009883305756375194 2023-01-23 15:43:22.094822: step: 3026/1545, loss: 0.0514538511633873 2023-01-23 15:43:22.966453: step: 3028/1545, loss: 0.46171197295188904 2023-01-23 15:43:23.822946: step: 3030/1545, loss: 0.01520974189043045 2023-01-23 15:43:24.678656: step: 3032/1545, loss: 0.01455656811594963 2023-01-23 15:43:25.573058: step: 3034/1545, loss: 0.023932717740535736 2023-01-23 15:43:26.523322: step: 3036/1545, loss: 0.15320153534412384 2023-01-23 15:43:27.428472: step: 3038/1545, loss: 0.005673371255397797 2023-01-23 15:43:28.283625: step: 3040/1545, loss: 0.012056545354425907 2023-01-23 15:43:29.176541: step: 3042/1545, loss: 0.0013918675249442458 2023-01-23 15:43:30.040712: step: 3044/1545, loss: 0.0023874854668974876 2023-01-23 15:43:31.032771: step: 3046/1545, loss: 0.11277108639478683 2023-01-23 15:43:31.906244: step: 3048/1545, loss: 0.0756787657737732 2023-01-23 15:43:32.761475: step: 3050/1545, loss: 0.0021201702766120434 2023-01-23 15:43:33.651853: step: 3052/1545, loss: 0.0013893296709284186 2023-01-23 15:43:34.549200: step: 3054/1545, loss: 0.22938960790634155 2023-01-23 15:43:35.485898: step: 3056/1545, loss: 0.12064606696367264 2023-01-23 15:43:36.348780: step: 3058/1545, loss: 0.016372429206967354 2023-01-23 15:43:37.202134: step: 3060/1545, loss: 0.002650750568136573 2023-01-23 15:43:38.064275: step: 3062/1545, loss: 0.6048235297203064 2023-01-23 15:43:38.936422: step: 3064/1545, loss: 0.00022992781305219978 2023-01-23 15:43:39.810846: step: 3066/1545, loss: 0.0010469797998666763 2023-01-23 15:43:40.655642: step: 3068/1545, loss: 0.15120413899421692 2023-01-23 15:43:41.528177: step: 3070/1545, loss: 0.027397772297263145 2023-01-23 15:43:42.485004: step: 3072/1545, loss: 0.13087564706802368 2023-01-23 15:43:43.324037: step: 3074/1545, loss: 0.001264501130208373 2023-01-23 15:43:44.244350: step: 3076/1545, loss: 0.0002249518147436902 2023-01-23 15:43:45.108765: step: 3078/1545, loss: 0.05063381418585777 2023-01-23 15:43:46.060887: step: 3080/1545, loss: 0.0002372749149799347 2023-01-23 15:43:47.025992: step: 3082/1545, loss: 0.00013033588766120374 2023-01-23 15:43:47.879051: step: 3084/1545, loss: 0.017293771728873253 2023-01-23 15:43:48.731330: step: 3086/1545, loss: 0.5873327255249023 2023-01-23 15:43:49.617373: step: 3088/1545, loss: 0.10846447944641113 2023-01-23 15:43:50.449524: step: 3090/1545, loss: 0.013213792815804482 ================================================== Loss: 0.096 -------------------- Dev Chinese: {'event': {'p': 0.5954198473282443, 'r': 0.7270306258322237, 'f1': 0.6546762589928057}, 'argument': {'p': 0.6449224411644022, 'r': 0.6642170542134495, 'f1': 0.6544275618890065}, 'combined': 0.42843818799927763, 'epoch': 22} Test Chinese: {'event': {'p': 0.6419423692636073, 'r': 0.7691815856777494, 'f1': 0.6998254799301921}, 'argument': {'p': 0.6899783438979525, 'r': 0.720527003398778, 'f1': 0.7049218629218812}, 'combined': 0.49332228103259057, 'epoch': 22} Dev Korean: {'event': {'p': 0.6050328227571116, 'r': 0.7363515312916112, 'f1': 0.6642642642642642}, 'argument': {'p': 0.6495165582802774, 'r': 0.6661207409731568, 'f1': 0.6577138719334065}, 'combined': 0.43689582123624476, 'epoch': 22} Test Korean: {'event': {'p': 0.6328042328042328, 'r': 0.7647058823529411, 'f1': 0.6925303995367689}, 'argument': {'p': 0.6861019053788218, 'r': 0.7136298763626874, 'f1': 0.699595200015416}, 'combined': 0.48449094338068177, 'epoch': 22} Dev Russian: {'event': {'p': 0.5708661417322834, 'r': 0.7723035952063915, 'f1': 0.656479909451047}, 'argument': {'p': 0.6477106149487214, 'r': 0.6722661675898389, 'f1': 0.6597599875679852}, 'combined': 0.43311917689805474, 'epoch': 22} Test Russian: {'event': {'p': 0.6243148978574987, 'r': 0.801150895140665, 'f1': 0.7017642117054047}, 'argument': {'p': 0.6955400831529507, 'r': 0.7317498477815125, 'f1': 0.7131856519717606}, 'combined': 0.5004881668555677, 'epoch': 22} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6623009758602978, 'r': 0.6458802905083896, 'f1': 0.6539875744896664}, 'combined': 0.4657184242577927, 'epoch': 22} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.654040404040404, 'r': 0.4927701674277017, 'f1': 0.5620659722222222}, 'combined': 0.34512822855750486, 'epoch': 22} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5379664923375895, 'r': 0.5667861258556747, 'f1': 0.5520004008333528}, 'combined': 0.3074432612236395, 'epoch': 22} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 23 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 15:49:09.188215: step: 2/1545, loss: 0.013383417390286922 2023-01-23 15:49:10.064711: step: 4/1545, loss: 0.012584253214299679 2023-01-23 15:49:10.948657: step: 6/1545, loss: 0.3123447895050049 2023-01-23 15:49:11.873400: step: 8/1545, loss: 0.0004430711851455271 2023-01-23 15:49:12.780704: step: 10/1545, loss: 0.0022883666679263115 2023-01-23 15:49:13.696950: step: 12/1545, loss: 0.053996335715055466 2023-01-23 15:49:14.571718: step: 14/1545, loss: 0.03756199777126312 2023-01-23 15:49:15.494388: step: 16/1545, loss: 1.2472931146621704 2023-01-23 15:49:16.384506: step: 18/1545, loss: 0.2365679144859314 2023-01-23 15:49:17.318155: step: 20/1545, loss: 0.025943471118807793 2023-01-23 15:49:18.204237: step: 22/1545, loss: 0.06381417065858841 2023-01-23 15:49:19.057894: step: 24/1545, loss: 0.001789617002941668 2023-01-23 15:49:19.937288: step: 26/1545, loss: 0.010022704489529133 2023-01-23 15:49:20.839531: step: 28/1545, loss: 0.008192317560315132 2023-01-23 15:49:21.683853: step: 30/1545, loss: 0.08288554102182388 2023-01-23 15:49:22.552394: step: 32/1545, loss: 0.013650549575686455 2023-01-23 15:49:23.419192: step: 34/1545, loss: 0.023160390555858612 2023-01-23 15:49:24.401111: step: 36/1545, loss: 0.08567409962415695 2023-01-23 15:49:25.268834: step: 38/1545, loss: 0.0010787163628265262 2023-01-23 15:49:26.130057: step: 40/1545, loss: 0.003505359636619687 2023-01-23 15:49:27.030903: step: 42/1545, loss: 0.004451517481356859 2023-01-23 15:49:27.938935: step: 44/1545, loss: 0.4547547698020935 2023-01-23 15:49:28.841170: step: 46/1545, loss: 0.03310937434434891 2023-01-23 15:49:29.717672: step: 48/1545, loss: 0.0017204824835062027 2023-01-23 15:49:30.591622: step: 50/1545, loss: 0.01096679549664259 2023-01-23 15:49:31.564234: step: 52/1545, loss: 0.03605922311544418 2023-01-23 15:49:32.406836: step: 54/1545, loss: 0.0070594120770692825 2023-01-23 15:49:33.332546: step: 56/1545, loss: 0.0009757582447491586 2023-01-23 15:49:34.257361: step: 58/1545, loss: 0.0002712541026994586 2023-01-23 15:49:35.141581: step: 60/1545, loss: 0.005061511415988207 2023-01-23 15:49:36.029413: step: 62/1545, loss: 0.02893436700105667 2023-01-23 15:49:36.890915: step: 64/1545, loss: 0.11761602014303207 2023-01-23 15:49:37.729307: step: 66/1545, loss: 0.0015392600325867534 2023-01-23 15:49:38.571443: step: 68/1545, loss: 0.057718101888895035 2023-01-23 15:49:39.454462: step: 70/1545, loss: 0.0417475700378418 2023-01-23 15:49:40.330466: step: 72/1545, loss: 0.0015848346520215273 2023-01-23 15:49:41.200379: step: 74/1545, loss: 0.05212332680821419 2023-01-23 15:49:42.086208: step: 76/1545, loss: 0.19181659817695618 2023-01-23 15:49:42.991943: step: 78/1545, loss: 0.0990324541926384 2023-01-23 15:49:43.841697: step: 80/1545, loss: 0.009183335117995739 2023-01-23 15:49:44.716015: step: 82/1545, loss: 0.0058103217743337154 2023-01-23 15:49:45.616398: step: 84/1545, loss: 0.03189540654420853 2023-01-23 15:49:46.536959: step: 86/1545, loss: 0.11925968527793884 2023-01-23 15:49:47.460055: step: 88/1545, loss: 0.0038948492147028446 2023-01-23 15:49:48.348331: step: 90/1545, loss: 0.012152155861258507 2023-01-23 15:49:49.226639: step: 92/1545, loss: 0.24596451222896576 2023-01-23 15:49:50.096690: step: 94/1545, loss: 0.0004812825645785779 2023-01-23 15:49:50.996746: step: 96/1545, loss: 0.016580000519752502 2023-01-23 15:49:51.872275: step: 98/1545, loss: 0.019793806597590446 2023-01-23 15:49:52.765789: step: 100/1545, loss: 0.002831726800650358 2023-01-23 15:49:53.671750: step: 102/1545, loss: 0.0015970622189342976 2023-01-23 15:49:54.560878: step: 104/1545, loss: 0.41067615151405334 2023-01-23 15:49:55.410141: step: 106/1545, loss: 0.0032683806493878365 2023-01-23 15:49:56.288138: step: 108/1545, loss: 0.052978143095970154 2023-01-23 15:49:57.146261: step: 110/1545, loss: 3.617292881011963 2023-01-23 15:49:58.020204: step: 112/1545, loss: 0.11615416407585144 2023-01-23 15:49:58.893375: step: 114/1545, loss: 0.14725883305072784 2023-01-23 15:49:59.730471: step: 116/1545, loss: 0.0006216614856384695 2023-01-23 15:50:00.632090: step: 118/1545, loss: 0.03241262957453728 2023-01-23 15:50:01.503370: step: 120/1545, loss: 0.18465818464756012 2023-01-23 15:50:02.368518: step: 122/1545, loss: 0.04703526198863983 2023-01-23 15:50:03.250501: step: 124/1545, loss: 0.004472039639949799 2023-01-23 15:50:04.196986: step: 126/1545, loss: 0.07930929213762283 2023-01-23 15:50:05.060907: step: 128/1545, loss: 0.0010189892491325736 2023-01-23 15:50:05.912689: step: 130/1545, loss: 0.09457104653120041 2023-01-23 15:50:06.771112: step: 132/1545, loss: 0.0033743218518793583 2023-01-23 15:50:07.625420: step: 134/1545, loss: 0.0012867527548223734 2023-01-23 15:50:08.496145: step: 136/1545, loss: 0.10677780210971832 2023-01-23 15:50:09.358909: step: 138/1545, loss: 0.012817785143852234 2023-01-23 15:50:10.255745: step: 140/1545, loss: 0.044684093445539474 2023-01-23 15:50:11.153717: step: 142/1545, loss: 0.000527525378856808 2023-01-23 15:50:12.038517: step: 144/1545, loss: 0.028165996074676514 2023-01-23 15:50:12.903517: step: 146/1545, loss: 0.05115709453821182 2023-01-23 15:50:13.787374: step: 148/1545, loss: 0.045425791293382645 2023-01-23 15:50:14.654087: step: 150/1545, loss: 0.011918107978999615 2023-01-23 15:50:15.555842: step: 152/1545, loss: 0.001520477351732552 2023-01-23 15:50:16.425384: step: 154/1545, loss: 0.0009299691300839186 2023-01-23 15:50:17.258235: step: 156/1545, loss: 0.002905698725953698 2023-01-23 15:50:18.142541: step: 158/1545, loss: 1.842703104019165 2023-01-23 15:50:18.978895: step: 160/1545, loss: 0.0003632720035966486 2023-01-23 15:50:19.866334: step: 162/1545, loss: 0.0013876947341486812 2023-01-23 15:50:20.812930: step: 164/1545, loss: 0.06645737588405609 2023-01-23 15:50:21.667174: step: 166/1545, loss: 0.21150267124176025 2023-01-23 15:50:22.584815: step: 168/1545, loss: 0.004667398985475302 2023-01-23 15:50:23.431339: step: 170/1545, loss: 0.0031085284426808357 2023-01-23 15:50:24.285790: step: 172/1545, loss: 0.002551816636696458 2023-01-23 15:50:25.247853: step: 174/1545, loss: 0.09983047097921371 2023-01-23 15:50:26.083792: step: 176/1545, loss: 0.0002248092059744522 2023-01-23 15:50:26.932004: step: 178/1545, loss: 0.002684757113456726 2023-01-23 15:50:27.824345: step: 180/1545, loss: 0.0617622509598732 2023-01-23 15:50:28.693808: step: 182/1545, loss: 0.011904768645763397 2023-01-23 15:50:29.565533: step: 184/1545, loss: 0.02014176733791828 2023-01-23 15:50:30.473027: step: 186/1545, loss: 0.01777368225157261 2023-01-23 15:50:31.388885: step: 188/1545, loss: 0.004166808910667896 2023-01-23 15:50:32.264479: step: 190/1545, loss: 0.00034344434970989823 2023-01-23 15:50:33.215236: step: 192/1545, loss: 0.0036989885848015547 2023-01-23 15:50:34.120216: step: 194/1545, loss: 0.4407590925693512 2023-01-23 15:50:34.964637: step: 196/1545, loss: 4.870740667684004e-05 2023-01-23 15:50:35.887639: step: 198/1545, loss: 0.0010644475696608424 2023-01-23 15:50:36.732428: step: 200/1545, loss: 0.03940778970718384 2023-01-23 15:50:37.638264: step: 202/1545, loss: 0.6153290867805481 2023-01-23 15:50:38.512323: step: 204/1545, loss: 0.03585818409919739 2023-01-23 15:50:39.357614: step: 206/1545, loss: 0.04642109200358391 2023-01-23 15:50:40.205155: step: 208/1545, loss: 0.07281613349914551 2023-01-23 15:50:41.063373: step: 210/1545, loss: 0.1676000952720642 2023-01-23 15:50:41.933233: step: 212/1545, loss: 0.35757261514663696 2023-01-23 15:50:42.765776: step: 214/1545, loss: 0.08030344545841217 2023-01-23 15:50:43.617319: step: 216/1545, loss: 0.0002941433631349355 2023-01-23 15:50:44.498145: step: 218/1545, loss: 0.003834527451545 2023-01-23 15:50:45.342916: step: 220/1545, loss: 0.13488075137138367 2023-01-23 15:50:46.177829: step: 222/1545, loss: 0.000524357776157558 2023-01-23 15:50:47.019705: step: 224/1545, loss: 0.8444154262542725 2023-01-23 15:50:47.909247: step: 226/1545, loss: 0.01254921592772007 2023-01-23 15:50:48.807179: step: 228/1545, loss: 0.001650166348554194 2023-01-23 15:50:49.718629: step: 230/1545, loss: 0.000601763604208827 2023-01-23 15:50:50.584359: step: 232/1545, loss: 0.004431834444403648 2023-01-23 15:50:51.439376: step: 234/1545, loss: 0.42303571105003357 2023-01-23 15:50:52.340456: step: 236/1545, loss: 0.030999181792140007 2023-01-23 15:50:53.188600: step: 238/1545, loss: 0.03491326794028282 2023-01-23 15:50:54.036451: step: 240/1545, loss: 0.000354186340700835 2023-01-23 15:50:54.912997: step: 242/1545, loss: 0.014228887856006622 2023-01-23 15:50:55.800738: step: 244/1545, loss: 0.009288402274250984 2023-01-23 15:50:56.693928: step: 246/1545, loss: 0.9598101377487183 2023-01-23 15:50:57.568147: step: 248/1545, loss: 0.010556834749877453 2023-01-23 15:50:58.464131: step: 250/1545, loss: 0.00033480703132227063 2023-01-23 15:50:59.330866: step: 252/1545, loss: 0.0657283216714859 2023-01-23 15:51:00.183616: step: 254/1545, loss: 0.000580900174099952 2023-01-23 15:51:01.093723: step: 256/1545, loss: 0.018679846078157425 2023-01-23 15:51:01.986708: step: 258/1545, loss: 0.11452343314886093 2023-01-23 15:51:02.865940: step: 260/1545, loss: 0.7815804481506348 2023-01-23 15:51:03.719171: step: 262/1545, loss: 0.06438923627138138 2023-01-23 15:51:04.640017: step: 264/1545, loss: 0.4012943208217621 2023-01-23 15:51:05.540491: step: 266/1545, loss: 0.11033671349287033 2023-01-23 15:51:06.399653: step: 268/1545, loss: 0.04752027243375778 2023-01-23 15:51:07.329335: step: 270/1545, loss: 0.0011991767678409815 2023-01-23 15:51:08.189103: step: 272/1545, loss: 0.002725455677136779 2023-01-23 15:51:09.060703: step: 274/1545, loss: 0.0003715840575750917 2023-01-23 15:51:09.955281: step: 276/1545, loss: 0.40666529536247253 2023-01-23 15:51:10.854378: step: 278/1545, loss: 0.2890731990337372 2023-01-23 15:51:11.727573: step: 280/1545, loss: 0.028544927015900612 2023-01-23 15:51:12.585969: step: 282/1545, loss: 0.0035901693627238274 2023-01-23 15:51:13.394059: step: 284/1545, loss: 0.01392416562885046 2023-01-23 15:51:14.257609: step: 286/1545, loss: 0.3501981496810913 2023-01-23 15:51:15.135699: step: 288/1545, loss: 0.0712648332118988 2023-01-23 15:51:15.993329: step: 290/1545, loss: 0.23071283102035522 2023-01-23 15:51:16.865229: step: 292/1545, loss: 0.002265638206154108 2023-01-23 15:51:17.759745: step: 294/1545, loss: 0.007553736679255962 2023-01-23 15:51:18.669275: step: 296/1545, loss: 0.02849438041448593 2023-01-23 15:51:19.577863: step: 298/1545, loss: 0.004259713925421238 2023-01-23 15:51:20.422057: step: 300/1545, loss: 0.05897960066795349 2023-01-23 15:51:21.274389: step: 302/1545, loss: 0.002559569664299488 2023-01-23 15:51:22.162203: step: 304/1545, loss: 0.033818092197179794 2023-01-23 15:51:23.093012: step: 306/1545, loss: 0.002999751828610897 2023-01-23 15:51:23.959262: step: 308/1545, loss: 0.004015134647488594 2023-01-23 15:51:24.839464: step: 310/1545, loss: 0.1884050965309143 2023-01-23 15:51:25.725882: step: 312/1545, loss: 0.01884189248085022 2023-01-23 15:51:26.622772: step: 314/1545, loss: 0.3809385597705841 2023-01-23 15:51:27.503239: step: 316/1545, loss: 0.2500355541706085 2023-01-23 15:51:28.370881: step: 318/1545, loss: 0.01748531498014927 2023-01-23 15:51:29.240491: step: 320/1545, loss: 0.06321097910404205 2023-01-23 15:51:30.137813: step: 322/1545, loss: 0.0016173372277989984 2023-01-23 15:51:30.989304: step: 324/1545, loss: 0.0009623972000554204 2023-01-23 15:51:31.855767: step: 326/1545, loss: 0.026995869353413582 2023-01-23 15:51:32.719951: step: 328/1545, loss: 0.006287942640483379 2023-01-23 15:51:33.599826: step: 330/1545, loss: 0.07731690257787704 2023-01-23 15:51:34.480304: step: 332/1545, loss: 1.2509230375289917 2023-01-23 15:51:35.372979: step: 334/1545, loss: 0.00045793980825692415 2023-01-23 15:51:36.208700: step: 336/1545, loss: 0.05322376266121864 2023-01-23 15:51:37.074061: step: 338/1545, loss: 0.0009175121085718274 2023-01-23 15:51:37.975790: step: 340/1545, loss: 0.010928013361990452 2023-01-23 15:51:38.837703: step: 342/1545, loss: 0.2043064683675766 2023-01-23 15:51:39.690172: step: 344/1545, loss: 0.0015855644596740603 2023-01-23 15:51:40.553614: step: 346/1545, loss: 0.004388623870909214 2023-01-23 15:51:41.446661: step: 348/1545, loss: 0.2365311086177826 2023-01-23 15:51:42.286504: step: 350/1545, loss: 0.04625343531370163 2023-01-23 15:51:43.130905: step: 352/1545, loss: 0.0009111028630286455 2023-01-23 15:51:44.011787: step: 354/1545, loss: 0.0006987928645685315 2023-01-23 15:51:44.854820: step: 356/1545, loss: 0.0011298886965960264 2023-01-23 15:51:45.721662: step: 358/1545, loss: 0.15346001088619232 2023-01-23 15:51:46.645844: step: 360/1545, loss: 0.13417215645313263 2023-01-23 15:51:47.591357: step: 362/1545, loss: 0.00043011343223042786 2023-01-23 15:51:48.446317: step: 364/1545, loss: 0.01584397256374359 2023-01-23 15:51:49.366635: step: 366/1545, loss: 0.32489803433418274 2023-01-23 15:51:50.292224: step: 368/1545, loss: 0.0007690979982726276 2023-01-23 15:51:51.145528: step: 370/1545, loss: 0.15237630903720856 2023-01-23 15:51:52.026274: step: 372/1545, loss: 0.07354623824357986 2023-01-23 15:51:52.913986: step: 374/1545, loss: 0.026913486421108246 2023-01-23 15:51:53.754250: step: 376/1545, loss: 0.03832950443029404 2023-01-23 15:51:54.717909: step: 378/1545, loss: 0.0004403265775181353 2023-01-23 15:51:55.591935: step: 380/1545, loss: 0.01941441372036934 2023-01-23 15:51:56.487670: step: 382/1545, loss: 0.10322992503643036 2023-01-23 15:51:57.407348: step: 384/1545, loss: 0.03502636030316353 2023-01-23 15:51:58.254999: step: 386/1545, loss: 0.002786564640700817 2023-01-23 15:51:59.175927: step: 388/1545, loss: 0.046822600066661835 2023-01-23 15:52:00.055561: step: 390/1545, loss: 0.014314506202936172 2023-01-23 15:52:00.964362: step: 392/1545, loss: 0.022807858884334564 2023-01-23 15:52:01.857642: step: 394/1545, loss: 0.1795007884502411 2023-01-23 15:52:02.772037: step: 396/1545, loss: 0.15224476158618927 2023-01-23 15:52:03.634868: step: 398/1545, loss: 0.0002870183379855007 2023-01-23 15:52:04.529104: step: 400/1545, loss: 0.008689513429999352 2023-01-23 15:52:05.449033: step: 402/1545, loss: 0.02149631269276142 2023-01-23 15:52:06.353023: step: 404/1545, loss: 0.10435432940721512 2023-01-23 15:52:07.213786: step: 406/1545, loss: 0.25098922848701477 2023-01-23 15:52:08.103929: step: 408/1545, loss: 0.003026367397978902 2023-01-23 15:52:08.978703: step: 410/1545, loss: 0.23316389322280884 2023-01-23 15:52:09.870945: step: 412/1545, loss: 0.009641662240028381 2023-01-23 15:52:10.813842: step: 414/1545, loss: 0.0007858311291784048 2023-01-23 15:52:11.683359: step: 416/1545, loss: 0.04679730534553528 2023-01-23 15:52:12.513335: step: 418/1545, loss: 0.012811767868697643 2023-01-23 15:52:13.404799: step: 420/1545, loss: 0.03792768716812134 2023-01-23 15:52:14.314121: step: 422/1545, loss: 0.00018245840328745544 2023-01-23 15:52:15.176233: step: 424/1545, loss: 0.1518610119819641 2023-01-23 15:52:16.071299: step: 426/1545, loss: 0.003738907165825367 2023-01-23 15:52:17.019630: step: 428/1545, loss: 0.0027359093073755503 2023-01-23 15:52:17.978462: step: 430/1545, loss: 0.0002606578345876187 2023-01-23 15:52:18.871802: step: 432/1545, loss: 0.00020460737869143486 2023-01-23 15:52:19.744256: step: 434/1545, loss: 0.00025903937057591975 2023-01-23 15:52:20.628853: step: 436/1545, loss: 0.10943357646465302 2023-01-23 15:52:21.556312: step: 438/1545, loss: 0.004668636247515678 2023-01-23 15:52:22.502641: step: 440/1545, loss: 0.034407392144203186 2023-01-23 15:52:23.413892: step: 442/1545, loss: 0.016093233600258827 2023-01-23 15:52:24.250652: step: 444/1545, loss: 0.0002645038766786456 2023-01-23 15:52:25.119490: step: 446/1545, loss: 0.00029015893233008683 2023-01-23 15:52:26.003452: step: 448/1545, loss: 0.0021053478121757507 2023-01-23 15:52:26.891193: step: 450/1545, loss: 0.018461033701896667 2023-01-23 15:52:27.790372: step: 452/1545, loss: 0.3640879690647125 2023-01-23 15:52:28.693210: step: 454/1545, loss: 0.01234764140099287 2023-01-23 15:52:29.594937: step: 456/1545, loss: 0.20983348786830902 2023-01-23 15:52:30.506245: step: 458/1545, loss: 0.03411389887332916 2023-01-23 15:52:31.425769: step: 460/1545, loss: 0.0009865370811894536 2023-01-23 15:52:32.316033: step: 462/1545, loss: 0.030835598707199097 2023-01-23 15:52:33.199471: step: 464/1545, loss: 0.023938169702887535 2023-01-23 15:52:34.175344: step: 466/1545, loss: 0.003795789321884513 2023-01-23 15:52:35.043476: step: 468/1545, loss: 0.016423339024186134 2023-01-23 15:52:35.940289: step: 470/1545, loss: 0.07709140330553055 2023-01-23 15:52:36.800880: step: 472/1545, loss: 0.002672200556844473 2023-01-23 15:52:37.733160: step: 474/1545, loss: 0.06537715345621109 2023-01-23 15:52:38.617373: step: 476/1545, loss: 0.157713383436203 2023-01-23 15:52:39.473884: step: 478/1545, loss: 0.004430723842233419 2023-01-23 15:52:40.326852: step: 480/1545, loss: 0.3950478434562683 2023-01-23 15:52:41.252682: step: 482/1545, loss: 0.4510308504104614 2023-01-23 15:52:42.112094: step: 484/1545, loss: 0.08772613108158112 2023-01-23 15:52:42.963584: step: 486/1545, loss: 0.10978911817073822 2023-01-23 15:52:43.815123: step: 488/1545, loss: 0.019947145134210587 2023-01-23 15:52:44.663123: step: 490/1545, loss: 0.012929800897836685 2023-01-23 15:52:45.601828: step: 492/1545, loss: 0.004925906658172607 2023-01-23 15:52:46.467048: step: 494/1545, loss: 0.0053749955259263515 2023-01-23 15:52:47.403337: step: 496/1545, loss: 0.17839226126670837 2023-01-23 15:52:48.259183: step: 498/1545, loss: 0.00010219250543741509 2023-01-23 15:52:49.118742: step: 500/1545, loss: 0.0018676120089367032 2023-01-23 15:52:50.023767: step: 502/1545, loss: 0.00428591575473547 2023-01-23 15:52:50.900021: step: 504/1545, loss: 0.07823124527931213 2023-01-23 15:52:51.785336: step: 506/1545, loss: 0.04074555262923241 2023-01-23 15:52:52.637639: step: 508/1545, loss: 0.005288862157613039 2023-01-23 15:52:53.469795: step: 510/1545, loss: 0.0029066414572298527 2023-01-23 15:52:54.378981: step: 512/1545, loss: 0.029376907274127007 2023-01-23 15:52:55.254329: step: 514/1545, loss: 0.02512229233980179 2023-01-23 15:52:56.121247: step: 516/1545, loss: 0.004704593680799007 2023-01-23 15:52:56.982533: step: 518/1545, loss: 0.012833497487008572 2023-01-23 15:52:57.829501: step: 520/1545, loss: 0.008488878607749939 2023-01-23 15:52:58.705512: step: 522/1545, loss: 0.10899054259061813 2023-01-23 15:52:59.606629: step: 524/1545, loss: 0.28084880113601685 2023-01-23 15:53:00.477152: step: 526/1545, loss: 0.0036300213541835546 2023-01-23 15:53:01.402806: step: 528/1545, loss: 0.0009993340354412794 2023-01-23 15:53:02.284574: step: 530/1545, loss: 0.7339797019958496 2023-01-23 15:53:03.151752: step: 532/1545, loss: 0.0026656908448785543 2023-01-23 15:53:04.008056: step: 534/1545, loss: 0.0008502681157551706 2023-01-23 15:53:04.906746: step: 536/1545, loss: 0.30466604232788086 2023-01-23 15:53:05.751823: step: 538/1545, loss: 0.007198308128863573 2023-01-23 15:53:06.632983: step: 540/1545, loss: 0.0015636401949450374 2023-01-23 15:53:07.520794: step: 542/1545, loss: 0.00394436763599515 2023-01-23 15:53:08.434660: step: 544/1545, loss: 0.00230618380010128 2023-01-23 15:53:09.312793: step: 546/1545, loss: 0.0257624052464962 2023-01-23 15:53:10.195951: step: 548/1545, loss: 0.008661978878080845 2023-01-23 15:53:11.105324: step: 550/1545, loss: 0.10588399320840836 2023-01-23 15:53:11.956469: step: 552/1545, loss: 3.0111453533172607 2023-01-23 15:53:12.909642: step: 554/1545, loss: 0.00119863694999367 2023-01-23 15:53:13.808149: step: 556/1545, loss: 0.011032582260668278 2023-01-23 15:53:14.719182: step: 558/1545, loss: 0.00017087682499550283 2023-01-23 15:53:15.594884: step: 560/1545, loss: 0.008365752175450325 2023-01-23 15:53:16.468520: step: 562/1545, loss: 0.10840694606304169 2023-01-23 15:53:17.384294: step: 564/1545, loss: 0.06161250174045563 2023-01-23 15:53:18.280884: step: 566/1545, loss: 0.17818401753902435 2023-01-23 15:53:19.144762: step: 568/1545, loss: 0.289855420589447 2023-01-23 15:53:20.024911: step: 570/1545, loss: 0.09123300015926361 2023-01-23 15:53:20.946723: step: 572/1545, loss: 0.004514820873737335 2023-01-23 15:53:21.815822: step: 574/1545, loss: 0.0016406584763899446 2023-01-23 15:53:22.668154: step: 576/1545, loss: 0.014508968219161034 2023-01-23 15:53:23.552497: step: 578/1545, loss: 0.006620064843446016 2023-01-23 15:53:24.444453: step: 580/1545, loss: 0.22790972888469696 2023-01-23 15:53:25.323885: step: 582/1545, loss: 0.008780800737440586 2023-01-23 15:53:26.217324: step: 584/1545, loss: 0.17138269543647766 2023-01-23 15:53:27.115678: step: 586/1545, loss: 1.6077988147735596 2023-01-23 15:53:28.030397: step: 588/1545, loss: 0.07628103345632553 2023-01-23 15:53:28.919225: step: 590/1545, loss: 0.004369964823126793 2023-01-23 15:53:29.876104: step: 592/1545, loss: 0.257449209690094 2023-01-23 15:53:30.832913: step: 594/1545, loss: 0.0016453686403110623 2023-01-23 15:53:31.740094: step: 596/1545, loss: 0.16590052843093872 2023-01-23 15:53:32.601789: step: 598/1545, loss: 0.0013876283774152398 2023-01-23 15:53:33.479770: step: 600/1545, loss: 0.0013955588219687343 2023-01-23 15:53:34.344536: step: 602/1545, loss: 0.3444233536720276 2023-01-23 15:53:35.205289: step: 604/1545, loss: 0.01652415655553341 2023-01-23 15:53:36.067546: step: 606/1545, loss: 0.0024495634716004133 2023-01-23 15:53:36.936147: step: 608/1545, loss: 0.03389612212777138 2023-01-23 15:53:37.821837: step: 610/1545, loss: 0.0011978251859545708 2023-01-23 15:53:38.707310: step: 612/1545, loss: 0.05431532487273216 2023-01-23 15:53:39.610107: step: 614/1545, loss: 0.0015795568469911814 2023-01-23 15:53:40.491350: step: 616/1545, loss: 0.003715807804837823 2023-01-23 15:53:41.332447: step: 618/1545, loss: 0.008962878957390785 2023-01-23 15:53:42.200616: step: 620/1545, loss: 0.0020373896695673466 2023-01-23 15:53:43.137360: step: 622/1545, loss: 0.017161358147859573 2023-01-23 15:53:44.045873: step: 624/1545, loss: 0.019871611148118973 2023-01-23 15:53:44.929121: step: 626/1545, loss: 0.05084504559636116 2023-01-23 15:53:45.772308: step: 628/1545, loss: 0.13615070283412933 2023-01-23 15:53:46.623992: step: 630/1545, loss: 0.01767822541296482 2023-01-23 15:53:47.471631: step: 632/1545, loss: 0.00032442068913951516 2023-01-23 15:53:48.370290: step: 634/1545, loss: 0.010652746073901653 2023-01-23 15:53:49.293508: step: 636/1545, loss: 0.821524441242218 2023-01-23 15:53:50.144121: step: 638/1545, loss: 0.0009683519601821899 2023-01-23 15:53:51.033213: step: 640/1545, loss: 0.0009096570429392159 2023-01-23 15:53:51.938850: step: 642/1545, loss: 0.38733893632888794 2023-01-23 15:53:52.853096: step: 644/1545, loss: 0.03565848991274834 2023-01-23 15:53:53.750470: step: 646/1545, loss: 0.4533543884754181 2023-01-23 15:53:54.649820: step: 648/1545, loss: 0.2098187804222107 2023-01-23 15:53:55.547453: step: 650/1545, loss: 0.004899073392152786 2023-01-23 15:53:56.489736: step: 652/1545, loss: 0.002812081715092063 2023-01-23 15:53:57.377397: step: 654/1545, loss: 0.18800105154514313 2023-01-23 15:53:58.208443: step: 656/1545, loss: 0.007625150494277477 2023-01-23 15:53:59.032735: step: 658/1545, loss: 0.0025430340319871902 2023-01-23 15:53:59.929317: step: 660/1545, loss: 0.0017375475727021694 2023-01-23 15:54:00.829142: step: 662/1545, loss: 0.1059100553393364 2023-01-23 15:54:01.710472: step: 664/1545, loss: 0.04749194160103798 2023-01-23 15:54:02.602230: step: 666/1545, loss: 0.0008830197039060295 2023-01-23 15:54:03.573791: step: 668/1545, loss: 0.19572927057743073 2023-01-23 15:54:04.500775: step: 670/1545, loss: 0.00021251953148748726 2023-01-23 15:54:05.406669: step: 672/1545, loss: 0.005148142576217651 2023-01-23 15:54:06.258711: step: 674/1545, loss: 0.0013340909499675035 2023-01-23 15:54:07.152268: step: 676/1545, loss: 0.49944862723350525 2023-01-23 15:54:08.054657: step: 678/1545, loss: 0.009633274748921394 2023-01-23 15:54:08.931086: step: 680/1545, loss: 0.0011785513488575816 2023-01-23 15:54:09.828986: step: 682/1545, loss: 0.07502433657646179 2023-01-23 15:54:10.676385: step: 684/1545, loss: 0.11843421310186386 2023-01-23 15:54:11.537399: step: 686/1545, loss: 0.21838216483592987 2023-01-23 15:54:12.436291: step: 688/1545, loss: 0.10837200284004211 2023-01-23 15:54:13.327836: step: 690/1545, loss: 0.08055854588747025 2023-01-23 15:54:14.182309: step: 692/1545, loss: 0.00199641240760684 2023-01-23 15:54:15.017673: step: 694/1545, loss: 0.0019428840605542064 2023-01-23 15:54:15.880457: step: 696/1545, loss: 0.005361087154597044 2023-01-23 15:54:16.764043: step: 698/1545, loss: 0.05333500728011131 2023-01-23 15:54:17.719713: step: 700/1545, loss: 0.002604604931548238 2023-01-23 15:54:18.583053: step: 702/1545, loss: 0.015679454430937767 2023-01-23 15:54:19.466380: step: 704/1545, loss: 0.00956888496875763 2023-01-23 15:54:20.346546: step: 706/1545, loss: 0.2164386510848999 2023-01-23 15:54:21.257344: step: 708/1545, loss: 0.004572686739265919 2023-01-23 15:54:22.164868: step: 710/1545, loss: 0.02356283739209175 2023-01-23 15:54:23.047793: step: 712/1545, loss: 0.27980485558509827 2023-01-23 15:54:23.921730: step: 714/1545, loss: 0.0010229898616671562 2023-01-23 15:54:24.789456: step: 716/1545, loss: 0.0012420878047123551 2023-01-23 15:54:25.665146: step: 718/1545, loss: 0.02628418803215027 2023-01-23 15:54:26.572852: step: 720/1545, loss: 0.0027532100211828947 2023-01-23 15:54:27.431504: step: 722/1545, loss: 0.0005151756922714412 2023-01-23 15:54:28.320839: step: 724/1545, loss: 0.00825790036469698 2023-01-23 15:54:29.219412: step: 726/1545, loss: 0.028052423149347305 2023-01-23 15:54:30.232547: step: 728/1545, loss: 0.07945606857538223 2023-01-23 15:54:31.138682: step: 730/1545, loss: 0.01721121370792389 2023-01-23 15:54:32.037107: step: 732/1545, loss: 0.07475704699754715 2023-01-23 15:54:32.934767: step: 734/1545, loss: 1.2383798360824585 2023-01-23 15:54:33.805067: step: 736/1545, loss: 0.1388903111219406 2023-01-23 15:54:34.670486: step: 738/1545, loss: 0.0024152996484190226 2023-01-23 15:54:35.603125: step: 740/1545, loss: 0.0017148798797279596 2023-01-23 15:54:36.473365: step: 742/1545, loss: 0.10038512945175171 2023-01-23 15:54:37.362237: step: 744/1545, loss: 0.005762256216257811 2023-01-23 15:54:38.254475: step: 746/1545, loss: 0.012598603032529354 2023-01-23 15:54:39.107950: step: 748/1545, loss: 0.19003047049045563 2023-01-23 15:54:39.966461: step: 750/1545, loss: 0.008185598999261856 2023-01-23 15:54:40.819941: step: 752/1545, loss: 0.04174146056175232 2023-01-23 15:54:41.675456: step: 754/1545, loss: 0.03889864683151245 2023-01-23 15:54:42.593988: step: 756/1545, loss: 0.02886979468166828 2023-01-23 15:54:43.461531: step: 758/1545, loss: 0.010931518860161304 2023-01-23 15:54:44.348021: step: 760/1545, loss: 0.008000580593943596 2023-01-23 15:54:45.232493: step: 762/1545, loss: 0.00035953757469542325 2023-01-23 15:54:46.163967: step: 764/1545, loss: 0.0010098000057041645 2023-01-23 15:54:47.113481: step: 766/1545, loss: 0.0069854226894676685 2023-01-23 15:54:47.989463: step: 768/1545, loss: 0.02530038356781006 2023-01-23 15:54:48.829610: step: 770/1545, loss: 0.00022644601995125413 2023-01-23 15:54:49.780791: step: 772/1545, loss: 0.09584985673427582 2023-01-23 15:54:50.657123: step: 774/1545, loss: 0.005351247265934944 2023-01-23 15:54:51.594344: step: 776/1545, loss: 0.4759034812450409 2023-01-23 15:54:52.517511: step: 778/1545, loss: 0.0008132384391501546 2023-01-23 15:54:53.432684: step: 780/1545, loss: 0.0008087064488790929 2023-01-23 15:54:54.298700: step: 782/1545, loss: 0.18499359488487244 2023-01-23 15:54:55.192706: step: 784/1545, loss: 0.0005437348154373467 2023-01-23 15:54:56.052612: step: 786/1545, loss: 0.006145763210952282 2023-01-23 15:54:56.973454: step: 788/1545, loss: 0.5500553846359253 2023-01-23 15:54:57.858772: step: 790/1545, loss: 0.01477994117885828 2023-01-23 15:54:58.755904: step: 792/1545, loss: 0.09286987036466599 2023-01-23 15:54:59.713016: step: 794/1545, loss: 0.0675702691078186 2023-01-23 15:55:00.571688: step: 796/1545, loss: 0.0002163592289434746 2023-01-23 15:55:01.439383: step: 798/1545, loss: 0.21413274109363556 2023-01-23 15:55:02.327004: step: 800/1545, loss: 0.034611817449331284 2023-01-23 15:55:03.191587: step: 802/1545, loss: 0.004141300916671753 2023-01-23 15:55:04.043676: step: 804/1545, loss: 0.0016693145735189319 2023-01-23 15:55:04.921700: step: 806/1545, loss: 0.18428292870521545 2023-01-23 15:55:05.834172: step: 808/1545, loss: 0.0008715476142242551 2023-01-23 15:55:06.754570: step: 810/1545, loss: 0.0010080444626510143 2023-01-23 15:55:07.681371: step: 812/1545, loss: 0.015891078859567642 2023-01-23 15:55:08.547334: step: 814/1545, loss: 0.11355346441268921 2023-01-23 15:55:09.423019: step: 816/1545, loss: 0.39568182826042175 2023-01-23 15:55:10.331859: step: 818/1545, loss: 0.008956706151366234 2023-01-23 15:55:11.229672: step: 820/1545, loss: 0.008858688175678253 2023-01-23 15:55:12.117724: step: 822/1545, loss: 0.020265815779566765 2023-01-23 15:55:13.060448: step: 824/1545, loss: 0.020017562434077263 2023-01-23 15:55:13.930945: step: 826/1545, loss: 0.02014680579304695 2023-01-23 15:55:14.776945: step: 828/1545, loss: 0.6219263672828674 2023-01-23 15:55:15.644139: step: 830/1545, loss: 0.14755426347255707 2023-01-23 15:55:16.535400: step: 832/1545, loss: 0.0027749063447117805 2023-01-23 15:55:17.534816: step: 834/1545, loss: 0.022261474281549454 2023-01-23 15:55:18.431889: step: 836/1545, loss: 0.010986328125 2023-01-23 15:55:19.307902: step: 838/1545, loss: 0.0145363574847579 2023-01-23 15:55:20.210873: step: 840/1545, loss: 0.011120901443064213 2023-01-23 15:55:21.076369: step: 842/1545, loss: 0.009879257529973984 2023-01-23 15:55:21.990591: step: 844/1545, loss: 0.04280328378081322 2023-01-23 15:55:22.850500: step: 846/1545, loss: 0.012921378016471863 2023-01-23 15:55:23.757798: step: 848/1545, loss: 0.1243327185511589 2023-01-23 15:55:24.694541: step: 850/1545, loss: 0.19478018581867218 2023-01-23 15:55:25.567160: step: 852/1545, loss: 0.0007281071739271283 2023-01-23 15:55:26.412844: step: 854/1545, loss: 0.05121998488903046 2023-01-23 15:55:27.276505: step: 856/1545, loss: 0.011332329362630844 2023-01-23 15:55:28.155191: step: 858/1545, loss: 0.009898400865495205 2023-01-23 15:55:29.065835: step: 860/1545, loss: 0.04318104684352875 2023-01-23 15:55:29.950830: step: 862/1545, loss: 0.01375069934874773 2023-01-23 15:55:30.827993: step: 864/1545, loss: 0.0025298355612903833 2023-01-23 15:55:31.743240: step: 866/1545, loss: 0.02715928852558136 2023-01-23 15:55:32.683598: step: 868/1545, loss: 0.009108632802963257 2023-01-23 15:55:33.546895: step: 870/1545, loss: 0.11333218216896057 2023-01-23 15:55:34.455645: step: 872/1545, loss: 0.0005643371841870248 2023-01-23 15:55:35.327888: step: 874/1545, loss: 0.06880649924278259 2023-01-23 15:55:36.220498: step: 876/1545, loss: 0.029793132096529007 2023-01-23 15:55:37.096732: step: 878/1545, loss: 0.012210747227072716 2023-01-23 15:55:38.112665: step: 880/1545, loss: 0.0022793151438236237 2023-01-23 15:55:38.954051: step: 882/1545, loss: 0.15691207349300385 2023-01-23 15:55:39.850735: step: 884/1545, loss: 0.006126466207206249 2023-01-23 15:55:40.746054: step: 886/1545, loss: 0.09346604347229004 2023-01-23 15:55:41.760430: step: 888/1545, loss: 0.00046213925816118717 2023-01-23 15:55:42.659438: step: 890/1545, loss: 0.023132361471652985 2023-01-23 15:55:43.508510: step: 892/1545, loss: 0.018499940633773804 2023-01-23 15:55:44.404609: step: 894/1545, loss: 0.004175958689302206 2023-01-23 15:55:45.346378: step: 896/1545, loss: 0.024899287149310112 2023-01-23 15:55:46.224173: step: 898/1545, loss: 0.001874573528766632 2023-01-23 15:55:47.110585: step: 900/1545, loss: 0.010573252104222775 2023-01-23 15:55:48.009103: step: 902/1545, loss: 0.0023035970516502857 2023-01-23 15:55:48.949241: step: 904/1545, loss: 0.0037880700547248125 2023-01-23 15:55:49.856943: step: 906/1545, loss: 0.0014876620844006538 2023-01-23 15:55:50.726251: step: 908/1545, loss: 0.10201504081487656 2023-01-23 15:55:51.581321: step: 910/1545, loss: 0.0008844805415719748 2023-01-23 15:55:52.493936: step: 912/1545, loss: 0.0946078822016716 2023-01-23 15:55:53.360924: step: 914/1545, loss: 0.003641958814114332 2023-01-23 15:55:54.276930: step: 916/1545, loss: 0.0024942888412624598 2023-01-23 15:55:55.196406: step: 918/1545, loss: 0.0002784044190775603 2023-01-23 15:55:56.087511: step: 920/1545, loss: 0.002019341103732586 2023-01-23 15:55:56.968433: step: 922/1545, loss: 0.09583238512277603 2023-01-23 15:55:57.832465: step: 924/1545, loss: 0.017044592648744583 2023-01-23 15:55:58.732620: step: 926/1545, loss: 0.0011434608604758978 2023-01-23 15:55:59.636067: step: 928/1545, loss: 0.0033337713684886694 2023-01-23 15:56:00.519472: step: 930/1545, loss: 0.00827088113874197 2023-01-23 15:56:01.453380: step: 932/1545, loss: 0.0008574494277127087 2023-01-23 15:56:02.320297: step: 934/1545, loss: 0.040754422545433044 2023-01-23 15:56:03.263305: step: 936/1545, loss: 0.01026194542646408 2023-01-23 15:56:04.143657: step: 938/1545, loss: 0.08368203788995743 2023-01-23 15:56:05.050587: step: 940/1545, loss: 0.0029206504113972187 2023-01-23 15:56:05.968510: step: 942/1545, loss: 0.056608255952596664 2023-01-23 15:56:06.877382: step: 944/1545, loss: 0.006090292241424322 2023-01-23 15:56:07.747822: step: 946/1545, loss: 0.002257576212286949 2023-01-23 15:56:08.618393: step: 948/1545, loss: 0.05003887414932251 2023-01-23 15:56:09.482770: step: 950/1545, loss: 0.061928775161504745 2023-01-23 15:56:10.386594: step: 952/1545, loss: 2.7165024280548096 2023-01-23 15:56:11.324053: step: 954/1545, loss: 0.08333656191825867 2023-01-23 15:56:12.186316: step: 956/1545, loss: 0.0005382851813919842 2023-01-23 15:56:13.141033: step: 958/1545, loss: 0.01785854995250702 2023-01-23 15:56:14.045365: step: 960/1545, loss: 0.014413032680749893 2023-01-23 15:56:14.944058: step: 962/1545, loss: 0.006372444797307253 2023-01-23 15:56:15.880245: step: 964/1545, loss: 0.0897039994597435 2023-01-23 15:56:16.743589: step: 966/1545, loss: 0.21663615107536316 2023-01-23 15:56:17.596504: step: 968/1545, loss: 0.002476719208061695 2023-01-23 15:56:18.487783: step: 970/1545, loss: 0.004925449378788471 2023-01-23 15:56:19.357884: step: 972/1545, loss: 0.009360609576106071 2023-01-23 15:56:20.187048: step: 974/1545, loss: 0.08984668552875519 2023-01-23 15:56:21.054461: step: 976/1545, loss: 0.0016088245902210474 2023-01-23 15:56:22.003433: step: 978/1545, loss: 0.0031881220638751984 2023-01-23 15:56:22.876919: step: 980/1545, loss: 0.07530014961957932 2023-01-23 15:56:23.786486: step: 982/1545, loss: 0.024037716910243034 2023-01-23 15:56:24.662798: step: 984/1545, loss: 0.0008201536256819963 2023-01-23 15:56:25.565294: step: 986/1545, loss: 0.030211998149752617 2023-01-23 15:56:26.489445: step: 988/1545, loss: 0.19470901787281036 2023-01-23 15:56:27.424802: step: 990/1545, loss: 0.21840567886829376 2023-01-23 15:56:28.306708: step: 992/1545, loss: 0.2576466202735901 2023-01-23 15:56:29.236781: step: 994/1545, loss: 0.0036156068090349436 2023-01-23 15:56:30.102499: step: 996/1545, loss: 0.000892331765498966 2023-01-23 15:56:31.012187: step: 998/1545, loss: 0.04638051614165306 2023-01-23 15:56:31.892923: step: 1000/1545, loss: 9.700855298433453e-05 2023-01-23 15:56:32.765082: step: 1002/1545, loss: 0.004144435748457909 2023-01-23 15:56:33.786760: step: 1004/1545, loss: 0.08464740216732025 2023-01-23 15:56:34.637033: step: 1006/1545, loss: 0.009538156911730766 2023-01-23 15:56:35.509188: step: 1008/1545, loss: 0.007841596379876137 2023-01-23 15:56:36.406110: step: 1010/1545, loss: 0.009696068242192268 2023-01-23 15:56:37.267859: step: 1012/1545, loss: 0.0003120929468423128 2023-01-23 15:56:38.207632: step: 1014/1545, loss: 0.0009130497346632183 2023-01-23 15:56:39.093760: step: 1016/1545, loss: 0.1976296603679657 2023-01-23 15:56:40.102241: step: 1018/1545, loss: 0.0030279725324362516 2023-01-23 15:56:41.004897: step: 1020/1545, loss: 0.006544073577970266 2023-01-23 15:56:41.864999: step: 1022/1545, loss: 0.003988297190517187 2023-01-23 15:56:42.727204: step: 1024/1545, loss: 0.004098116420209408 2023-01-23 15:56:43.619785: step: 1026/1545, loss: 0.00498059019446373 2023-01-23 15:56:44.568060: step: 1028/1545, loss: 0.0008448371663689613 2023-01-23 15:56:45.494478: step: 1030/1545, loss: 1.7294812202453613 2023-01-23 15:56:46.403945: step: 1032/1545, loss: 0.0014722233172506094 2023-01-23 15:56:47.296208: step: 1034/1545, loss: 0.0003358338144607842 2023-01-23 15:56:48.170465: step: 1036/1545, loss: 0.002393072936683893 2023-01-23 15:56:49.082775: step: 1038/1545, loss: 0.176488995552063 2023-01-23 15:56:49.934754: step: 1040/1545, loss: 0.015101822093129158 2023-01-23 15:56:50.810852: step: 1042/1545, loss: 0.03621934726834297 2023-01-23 15:56:51.707030: step: 1044/1545, loss: 0.00046030638623051345 2023-01-23 15:56:52.610170: step: 1046/1545, loss: 0.0015117685543373227 2023-01-23 15:56:53.479697: step: 1048/1545, loss: 0.015877598896622658 2023-01-23 15:56:54.335792: step: 1050/1545, loss: 0.10775409638881683 2023-01-23 15:56:55.177136: step: 1052/1545, loss: 0.16344353556632996 2023-01-23 15:56:56.090148: step: 1054/1545, loss: 0.000568428891710937 2023-01-23 15:56:56.952954: step: 1056/1545, loss: 0.07699607312679291 2023-01-23 15:56:57.841479: step: 1058/1545, loss: 0.0658743605017662 2023-01-23 15:56:58.713482: step: 1060/1545, loss: 0.0004379475431051105 2023-01-23 15:56:59.570124: step: 1062/1545, loss: 0.0040254537016153336 2023-01-23 15:57:00.443061: step: 1064/1545, loss: 0.036538831889629364 2023-01-23 15:57:01.306340: step: 1066/1545, loss: 0.0006186258397065103 2023-01-23 15:57:02.249477: step: 1068/1545, loss: 0.11328417807817459 2023-01-23 15:57:03.156117: step: 1070/1545, loss: 0.09227238595485687 2023-01-23 15:57:04.067284: step: 1072/1545, loss: 0.0002644245105329901 2023-01-23 15:57:04.946303: step: 1074/1545, loss: 0.0017326632514595985 2023-01-23 15:57:05.844628: step: 1076/1545, loss: 0.1176774725317955 2023-01-23 15:57:06.711002: step: 1078/1545, loss: 0.025468643754720688 2023-01-23 15:57:07.620068: step: 1080/1545, loss: 0.007870673201978207 2023-01-23 15:57:08.498724: step: 1082/1545, loss: 0.014242943376302719 2023-01-23 15:57:09.392155: step: 1084/1545, loss: 0.050398748368024826 2023-01-23 15:57:10.230775: step: 1086/1545, loss: 0.021248023957014084 2023-01-23 15:57:11.094457: step: 1088/1545, loss: 0.0019465002696961164 2023-01-23 15:57:11.947510: step: 1090/1545, loss: 0.04367914795875549 2023-01-23 15:57:12.878884: step: 1092/1545, loss: 0.10273807495832443 2023-01-23 15:57:13.823571: step: 1094/1545, loss: 0.009053354151546955 2023-01-23 15:57:14.668164: step: 1096/1545, loss: 0.3617682158946991 2023-01-23 15:57:15.559567: step: 1098/1545, loss: 0.038554221391677856 2023-01-23 15:57:16.447393: step: 1100/1545, loss: 0.0002155053662136197 2023-01-23 15:57:17.448263: step: 1102/1545, loss: 0.7821998000144958 2023-01-23 15:57:18.319189: step: 1104/1545, loss: 0.0030609804671257734 2023-01-23 15:57:19.185624: step: 1106/1545, loss: 0.017767833545804024 2023-01-23 15:57:20.115975: step: 1108/1545, loss: 0.15738549828529358 2023-01-23 15:57:20.988348: step: 1110/1545, loss: 0.12432675808668137 2023-01-23 15:57:21.902574: step: 1112/1545, loss: 0.0010222544660791755 2023-01-23 15:57:22.805802: step: 1114/1545, loss: 0.014407019130885601 2023-01-23 15:57:23.687752: step: 1116/1545, loss: 0.02016366459429264 2023-01-23 15:57:24.581501: step: 1118/1545, loss: 0.0026878942735493183 2023-01-23 15:57:25.441961: step: 1120/1545, loss: 0.02255779691040516 2023-01-23 15:57:26.291322: step: 1122/1545, loss: 0.02846299484372139 2023-01-23 15:57:27.180611: step: 1124/1545, loss: 0.0020732011180371046 2023-01-23 15:57:28.029824: step: 1126/1545, loss: 0.039006009697914124 2023-01-23 15:57:28.948665: step: 1128/1545, loss: 0.14628319442272186 2023-01-23 15:57:29.830261: step: 1130/1545, loss: 0.0024812528863549232 2023-01-23 15:57:30.744960: step: 1132/1545, loss: 0.00503929890692234 2023-01-23 15:57:31.633493: step: 1134/1545, loss: 0.36905983090400696 2023-01-23 15:57:32.502678: step: 1136/1545, loss: 0.09187702089548111 2023-01-23 15:57:33.409566: step: 1138/1545, loss: 0.007973451167345047 2023-01-23 15:57:34.260725: step: 1140/1545, loss: 0.043080028146505356 2023-01-23 15:57:35.150593: step: 1142/1545, loss: 0.02939845621585846 2023-01-23 15:57:36.019994: step: 1144/1545, loss: 0.006208518985658884 2023-01-23 15:57:36.947287: step: 1146/1545, loss: 0.01912635564804077 2023-01-23 15:57:37.819448: step: 1148/1545, loss: 0.011376731097698212 2023-01-23 15:57:38.704463: step: 1150/1545, loss: 0.0041418178007006645 2023-01-23 15:57:39.651102: step: 1152/1545, loss: 0.0023585560265928507 2023-01-23 15:57:40.541568: step: 1154/1545, loss: 0.009397709742188454 2023-01-23 15:57:41.401736: step: 1156/1545, loss: 0.00023395268362946808 2023-01-23 15:57:42.297391: step: 1158/1545, loss: 0.002027795882895589 2023-01-23 15:57:43.158131: step: 1160/1545, loss: 0.08925891667604446 2023-01-23 15:57:44.050659: step: 1162/1545, loss: 0.02210453525185585 2023-01-23 15:57:44.986194: step: 1164/1545, loss: 0.10083284974098206 2023-01-23 15:57:45.867607: step: 1166/1545, loss: 0.03370395675301552 2023-01-23 15:57:46.694455: step: 1168/1545, loss: 0.022293666377663612 2023-01-23 15:57:47.584643: step: 1170/1545, loss: 0.03987829387187958 2023-01-23 15:57:48.437644: step: 1172/1545, loss: 0.001430465024895966 2023-01-23 15:57:49.317620: step: 1174/1545, loss: 0.01984233781695366 2023-01-23 15:57:50.173282: step: 1176/1545, loss: 0.07212550193071365 2023-01-23 15:57:51.116991: step: 1178/1545, loss: 0.2998179495334625 2023-01-23 15:57:52.016432: step: 1180/1545, loss: 0.740015983581543 2023-01-23 15:57:52.894438: step: 1182/1545, loss: 0.16910775005817413 2023-01-23 15:57:53.749749: step: 1184/1545, loss: 0.004312716890126467 2023-01-23 15:57:54.653682: step: 1186/1545, loss: 0.3591698408126831 2023-01-23 15:57:55.527915: step: 1188/1545, loss: 0.020644372329115868 2023-01-23 15:57:56.392264: step: 1190/1545, loss: 0.0012026610784232616 2023-01-23 15:57:57.245004: step: 1192/1545, loss: 0.05809734761714935 2023-01-23 15:57:58.155976: step: 1194/1545, loss: 0.16787147521972656 2023-01-23 15:57:59.027862: step: 1196/1545, loss: 0.001633419655263424 2023-01-23 15:57:59.934008: step: 1198/1545, loss: 0.030435975641012192 2023-01-23 15:58:00.795440: step: 1200/1545, loss: 0.05734943598508835 2023-01-23 15:58:01.649206: step: 1202/1545, loss: 0.005436351522803307 2023-01-23 15:58:02.496049: step: 1204/1545, loss: 0.17994266748428345 2023-01-23 15:58:03.421959: step: 1206/1545, loss: 0.05737830325961113 2023-01-23 15:58:04.332530: step: 1208/1545, loss: 0.2507205605506897 2023-01-23 15:58:05.208515: step: 1210/1545, loss: 0.11895517259836197 2023-01-23 15:58:06.079171: step: 1212/1545, loss: 0.14253436028957367 2023-01-23 15:58:06.962636: step: 1214/1545, loss: 0.021615829318761826 2023-01-23 15:58:07.967155: step: 1216/1545, loss: 0.0003473017713986337 2023-01-23 15:58:08.804917: step: 1218/1545, loss: 0.0006703702383674681 2023-01-23 15:58:09.665015: step: 1220/1545, loss: 0.04011412709951401 2023-01-23 15:58:10.557603: step: 1222/1545, loss: 0.0022288854233920574 2023-01-23 15:58:11.436429: step: 1224/1545, loss: 0.007959464564919472 2023-01-23 15:58:12.342457: step: 1226/1545, loss: 0.0006068006041459739 2023-01-23 15:58:13.182733: step: 1228/1545, loss: 0.012402267195284367 2023-01-23 15:58:14.037136: step: 1230/1545, loss: 0.0044694687239825726 2023-01-23 15:58:14.881817: step: 1232/1545, loss: 0.02033914253115654 2023-01-23 15:58:15.785038: step: 1234/1545, loss: 0.6621841192245483 2023-01-23 15:58:16.697058: step: 1236/1545, loss: 0.026901211589574814 2023-01-23 15:58:17.574499: step: 1238/1545, loss: 0.0006185907404869795 2023-01-23 15:58:18.481534: step: 1240/1545, loss: 0.0003506986249703914 2023-01-23 15:58:19.364328: step: 1242/1545, loss: 0.00019945006351917982 2023-01-23 15:58:20.228447: step: 1244/1545, loss: 0.16507375240325928 2023-01-23 15:58:21.096027: step: 1246/1545, loss: 0.016130220144987106 2023-01-23 15:58:21.976856: step: 1248/1545, loss: 0.546142578125 2023-01-23 15:58:22.920178: step: 1250/1545, loss: 0.040098417550325394 2023-01-23 15:58:23.855921: step: 1252/1545, loss: 0.09638772159814835 2023-01-23 15:58:24.734532: step: 1254/1545, loss: 0.02917376160621643 2023-01-23 15:58:25.627087: step: 1256/1545, loss: 0.5938018560409546 2023-01-23 15:58:26.491135: step: 1258/1545, loss: 0.26818832755088806 2023-01-23 15:58:27.391865: step: 1260/1545, loss: 0.07142534852027893 2023-01-23 15:58:28.300542: step: 1262/1545, loss: 0.024746209383010864 2023-01-23 15:58:29.231250: step: 1264/1545, loss: 0.027062784880399704 2023-01-23 15:58:30.096580: step: 1266/1545, loss: 0.14684954285621643 2023-01-23 15:58:30.952857: step: 1268/1545, loss: 0.0004679025732912123 2023-01-23 15:58:31.916341: step: 1270/1545, loss: 0.015605135820806026 2023-01-23 15:58:32.793980: step: 1272/1545, loss: 0.009324360638856888 2023-01-23 15:58:33.703406: step: 1274/1545, loss: 0.04261317104101181 2023-01-23 15:58:34.622558: step: 1276/1545, loss: 0.14993910491466522 2023-01-23 15:58:35.505236: step: 1278/1545, loss: 0.0019819834269583225 2023-01-23 15:58:36.391703: step: 1280/1545, loss: 0.08547112345695496 2023-01-23 15:58:37.248935: step: 1282/1545, loss: 0.002893373603001237 2023-01-23 15:58:38.148444: step: 1284/1545, loss: 0.26897963881492615 2023-01-23 15:58:39.011169: step: 1286/1545, loss: 0.05412674695253372 2023-01-23 15:58:39.881861: step: 1288/1545, loss: 0.04200965166091919 2023-01-23 15:58:40.797222: step: 1290/1545, loss: 0.056307319551706314 2023-01-23 15:58:41.663379: step: 1292/1545, loss: 0.006414362229406834 2023-01-23 15:58:42.573107: step: 1294/1545, loss: 0.0017237623687833548 2023-01-23 15:58:43.446452: step: 1296/1545, loss: 0.006618088111281395 2023-01-23 15:58:44.322501: step: 1298/1545, loss: 0.016166459769010544 2023-01-23 15:58:45.250733: step: 1300/1545, loss: 0.013304282911121845 2023-01-23 15:58:46.125406: step: 1302/1545, loss: 0.003912460524588823 2023-01-23 15:58:46.979148: step: 1304/1545, loss: 0.04124876856803894 2023-01-23 15:58:47.924533: step: 1306/1545, loss: 0.002230484504252672 2023-01-23 15:58:48.816271: step: 1308/1545, loss: 0.08991628140211105 2023-01-23 15:58:49.713303: step: 1310/1545, loss: 0.2296011596918106 2023-01-23 15:58:50.574288: step: 1312/1545, loss: 0.0031835248228162527 2023-01-23 15:58:51.484457: step: 1314/1545, loss: 0.01765977032482624 2023-01-23 15:58:52.411571: step: 1316/1545, loss: 0.03512318432331085 2023-01-23 15:58:53.271578: step: 1318/1545, loss: 0.004820039961487055 2023-01-23 15:58:54.153413: step: 1320/1545, loss: 0.021978581324219704 2023-01-23 15:58:55.096939: step: 1322/1545, loss: 0.04560457915067673 2023-01-23 15:58:55.958653: step: 1324/1545, loss: 0.0009196446044370532 2023-01-23 15:58:56.851564: step: 1326/1545, loss: 0.002989401575177908 2023-01-23 15:58:57.789045: step: 1328/1545, loss: 0.0014874069020152092 2023-01-23 15:58:58.669028: step: 1330/1545, loss: 0.001419220701791346 2023-01-23 15:58:59.502505: step: 1332/1545, loss: 0.010812569409608841 2023-01-23 15:59:00.379185: step: 1334/1545, loss: 0.001388931181281805 2023-01-23 15:59:01.280229: step: 1336/1545, loss: 0.0023696059361100197 2023-01-23 15:59:02.179773: step: 1338/1545, loss: 0.0017932987539097667 2023-01-23 15:59:03.148761: step: 1340/1545, loss: 0.18476761877536774 2023-01-23 15:59:04.019333: step: 1342/1545, loss: 0.0025857826694846153 2023-01-23 15:59:04.877420: step: 1344/1545, loss: 0.00014955850201658905 2023-01-23 15:59:05.793047: step: 1346/1545, loss: 0.0027419847901910543 2023-01-23 15:59:06.656834: step: 1348/1545, loss: 0.17034360766410828 2023-01-23 15:59:07.498926: step: 1350/1545, loss: 0.15656457841396332 2023-01-23 15:59:08.345419: step: 1352/1545, loss: 0.14696276187896729 2023-01-23 15:59:09.206003: step: 1354/1545, loss: 0.002302302047610283 2023-01-23 15:59:10.108188: step: 1356/1545, loss: 0.0019090261776000261 2023-01-23 15:59:10.987094: step: 1358/1545, loss: 0.01621243543922901 2023-01-23 15:59:11.894765: step: 1360/1545, loss: 0.12438937276601791 2023-01-23 15:59:12.847589: step: 1362/1545, loss: 0.022841647267341614 2023-01-23 15:59:13.694913: step: 1364/1545, loss: 0.03457600250840187 2023-01-23 15:59:14.595854: step: 1366/1545, loss: 0.03328453749418259 2023-01-23 15:59:15.451906: step: 1368/1545, loss: 0.0010319568682461977 2023-01-23 15:59:16.394026: step: 1370/1545, loss: 0.0013378679286688566 2023-01-23 15:59:17.304767: step: 1372/1545, loss: 0.032684076577425 2023-01-23 15:59:18.164280: step: 1374/1545, loss: 0.00956811010837555 2023-01-23 15:59:19.057722: step: 1376/1545, loss: 0.013628133572638035 2023-01-23 15:59:19.992292: step: 1378/1545, loss: 0.12751363217830658 2023-01-23 15:59:20.847723: step: 1380/1545, loss: 0.017272183671593666 2023-01-23 15:59:21.723968: step: 1382/1545, loss: 5.31653240614105e-05 2023-01-23 15:59:22.610203: step: 1384/1545, loss: 0.0065676989033818245 2023-01-23 15:59:23.567776: step: 1386/1545, loss: 5.355626126402058e-05 2023-01-23 15:59:24.459303: step: 1388/1545, loss: 0.010044030845165253 2023-01-23 15:59:25.392353: step: 1390/1545, loss: 0.1180235892534256 2023-01-23 15:59:26.299686: step: 1392/1545, loss: 0.013579046353697777 2023-01-23 15:59:27.167328: step: 1394/1545, loss: 0.032345522195100784 2023-01-23 15:59:28.028242: step: 1396/1545, loss: 4.433852882357314e-05 2023-01-23 15:59:28.969060: step: 1398/1545, loss: 0.035077791661024094 2023-01-23 15:59:29.835957: step: 1400/1545, loss: 0.002893310273066163 2023-01-23 15:59:30.662155: step: 1402/1545, loss: 0.065516896545887 2023-01-23 15:59:31.655022: step: 1404/1545, loss: 0.21365059912204742 2023-01-23 15:59:32.526891: step: 1406/1545, loss: 0.01003706082701683 2023-01-23 15:59:33.391772: step: 1408/1545, loss: 0.0014107769820839167 2023-01-23 15:59:34.310303: step: 1410/1545, loss: 0.17620891332626343 2023-01-23 15:59:35.203359: step: 1412/1545, loss: 0.00425389688462019 2023-01-23 15:59:36.098323: step: 1414/1545, loss: 0.0551147386431694 2023-01-23 15:59:36.953211: step: 1416/1545, loss: 0.05808392912149429 2023-01-23 15:59:37.833180: step: 1418/1545, loss: 0.30707332491874695 2023-01-23 15:59:38.732006: step: 1420/1545, loss: 0.002059082966297865 2023-01-23 15:59:39.590430: step: 1422/1545, loss: 0.14190784096717834 2023-01-23 15:59:40.455584: step: 1424/1545, loss: 0.05718909949064255 2023-01-23 15:59:41.314496: step: 1426/1545, loss: 0.025135060772299767 2023-01-23 15:59:42.154292: step: 1428/1545, loss: 0.00017470991588197649 2023-01-23 15:59:43.035058: step: 1430/1545, loss: 0.08552143722772598 2023-01-23 15:59:43.882625: step: 1432/1545, loss: 0.001759069156832993 2023-01-23 15:59:44.800724: step: 1434/1545, loss: 0.005541125778108835 2023-01-23 15:59:45.685944: step: 1436/1545, loss: 0.11328902840614319 2023-01-23 15:59:46.533274: step: 1438/1545, loss: 0.0034920470789074898 2023-01-23 15:59:47.396760: step: 1440/1545, loss: 1.9364441633224487 2023-01-23 15:59:48.312504: step: 1442/1545, loss: 0.0027980764862149954 2023-01-23 15:59:49.231749: step: 1444/1545, loss: 0.08291751891374588 2023-01-23 15:59:50.146363: step: 1446/1545, loss: 0.00632866658270359 2023-01-23 15:59:51.030833: step: 1448/1545, loss: 0.02252570353448391 2023-01-23 15:59:51.922815: step: 1450/1545, loss: 0.384255588054657 2023-01-23 15:59:52.817375: step: 1452/1545, loss: 0.12137534469366074 2023-01-23 15:59:53.751920: step: 1454/1545, loss: 0.11313541978597641 2023-01-23 15:59:54.617710: step: 1456/1545, loss: 0.007451550103724003 2023-01-23 15:59:55.503631: step: 1458/1545, loss: 0.002316865138709545 2023-01-23 15:59:56.383204: step: 1460/1545, loss: 0.02159886062145233 2023-01-23 15:59:57.238132: step: 1462/1545, loss: 0.0010825508506968617 2023-01-23 15:59:58.123606: step: 1464/1545, loss: 0.004690183792263269 2023-01-23 15:59:59.052050: step: 1466/1545, loss: 0.0015248989220708609 2023-01-23 15:59:59.926254: step: 1468/1545, loss: 0.006407799199223518 2023-01-23 16:00:00.836208: step: 1470/1545, loss: 0.28595539927482605 2023-01-23 16:00:01.768383: step: 1472/1545, loss: 0.030024277046322823 2023-01-23 16:00:02.679608: step: 1474/1545, loss: 0.10069195926189423 2023-01-23 16:00:03.541123: step: 1476/1545, loss: 0.05568774417042732 2023-01-23 16:00:04.397216: step: 1478/1545, loss: 0.003857656382024288 2023-01-23 16:00:05.305953: step: 1480/1545, loss: 0.0032706402707844973 2023-01-23 16:00:06.131544: step: 1482/1545, loss: 0.00019762584997806698 2023-01-23 16:00:07.037196: step: 1484/1545, loss: 0.019189296290278435 2023-01-23 16:00:07.909958: step: 1486/1545, loss: 0.04298658296465874 2023-01-23 16:00:08.769159: step: 1488/1545, loss: 0.013381445780396461 2023-01-23 16:00:09.640701: step: 1490/1545, loss: 0.040225010365247726 2023-01-23 16:00:10.506385: step: 1492/1545, loss: 0.0027115242555737495 2023-01-23 16:00:11.388266: step: 1494/1545, loss: 0.1443454921245575 2023-01-23 16:00:12.308240: step: 1496/1545, loss: 0.016834259033203125 2023-01-23 16:00:13.163388: step: 1498/1545, loss: 0.012759118340909481 2023-01-23 16:00:14.052595: step: 1500/1545, loss: 0.18433710932731628 2023-01-23 16:00:14.911048: step: 1502/1545, loss: 0.009069308638572693 2023-01-23 16:00:15.779367: step: 1504/1545, loss: 0.003936092834919691 2023-01-23 16:00:16.668900: step: 1506/1545, loss: 0.03635820001363754 2023-01-23 16:00:17.554207: step: 1508/1545, loss: 0.0009866285836324096 2023-01-23 16:00:18.445504: step: 1510/1545, loss: 0.009765634313225746 2023-01-23 16:00:19.394060: step: 1512/1545, loss: 0.032687798142433167 2023-01-23 16:00:20.263489: step: 1514/1545, loss: 0.01693766750395298 2023-01-23 16:00:21.110927: step: 1516/1545, loss: 0.004289472941309214 2023-01-23 16:00:22.002018: step: 1518/1545, loss: 0.061215728521347046 2023-01-23 16:00:22.878645: step: 1520/1545, loss: 0.008313102647662163 2023-01-23 16:00:23.751330: step: 1522/1545, loss: 0.017313655465841293 2023-01-23 16:00:24.627894: step: 1524/1545, loss: 0.037237972021102905 2023-01-23 16:00:25.534958: step: 1526/1545, loss: 0.0007836237200535834 2023-01-23 16:00:26.421541: step: 1528/1545, loss: 0.05946645140647888 2023-01-23 16:00:27.302971: step: 1530/1545, loss: 0.0022330901119858027 2023-01-23 16:00:28.164879: step: 1532/1545, loss: 0.001310159219428897 2023-01-23 16:00:29.056441: step: 1534/1545, loss: 0.23955078423023224 2023-01-23 16:00:29.930454: step: 1536/1545, loss: 0.0024343407712876797 2023-01-23 16:00:30.792499: step: 1538/1545, loss: 0.031238406896591187 2023-01-23 16:00:31.657208: step: 1540/1545, loss: 0.06400411576032639 2023-01-23 16:00:32.564733: step: 1542/1545, loss: 0.05695988982915878 2023-01-23 16:00:33.436748: step: 1544/1545, loss: 0.005190402269363403 2023-01-23 16:00:34.376109: step: 1546/1545, loss: 0.16861356794834137 2023-01-23 16:00:35.223864: step: 1548/1545, loss: 0.03386668860912323 2023-01-23 16:00:36.091563: step: 1550/1545, loss: 0.18950054049491882 2023-01-23 16:00:36.957922: step: 1552/1545, loss: 0.11942816525697708 2023-01-23 16:00:37.822194: step: 1554/1545, loss: 0.14025123417377472 2023-01-23 16:00:38.736584: step: 1556/1545, loss: 0.0008048248128034174 2023-01-23 16:00:39.581669: step: 1558/1545, loss: 0.00042036775266751647 2023-01-23 16:00:40.444688: step: 1560/1545, loss: 0.0005883200792595744 2023-01-23 16:00:41.293017: step: 1562/1545, loss: 0.13820044696331024 2023-01-23 16:00:42.122157: step: 1564/1545, loss: 4.911954601993784e-05 2023-01-23 16:00:43.024689: step: 1566/1545, loss: 0.03897145390510559 2023-01-23 16:00:43.982273: step: 1568/1545, loss: 0.3972695767879486 2023-01-23 16:00:44.875334: step: 1570/1545, loss: 0.020047122612595558 2023-01-23 16:00:45.771795: step: 1572/1545, loss: 0.08411284536123276 2023-01-23 16:00:46.698675: step: 1574/1545, loss: 0.006021265406161547 2023-01-23 16:00:47.547161: step: 1576/1545, loss: 0.2208101451396942 2023-01-23 16:00:48.433353: step: 1578/1545, loss: 0.0015257832128554583 2023-01-23 16:00:49.352910: step: 1580/1545, loss: 0.0017754397122189403 2023-01-23 16:00:50.186785: step: 1582/1545, loss: 0.0012714628828689456 2023-01-23 16:00:51.046016: step: 1584/1545, loss: 0.031919822096824646 2023-01-23 16:00:51.898371: step: 1586/1545, loss: 0.00012354293721728027 2023-01-23 16:00:52.765508: step: 1588/1545, loss: 8.744492515688762e-05 2023-01-23 16:00:53.656491: step: 1590/1545, loss: 0.050601571798324585 2023-01-23 16:00:54.505170: step: 1592/1545, loss: 0.004324560519307852 2023-01-23 16:00:55.422368: step: 1594/1545, loss: 0.02153041586279869 2023-01-23 16:00:56.279822: step: 1596/1545, loss: 0.0018276325426995754 2023-01-23 16:00:57.136785: step: 1598/1545, loss: 0.07689153403043747 2023-01-23 16:00:58.029243: step: 1600/1545, loss: 0.0029382568318396807 2023-01-23 16:00:58.867029: step: 1602/1545, loss: 0.0003440735163167119 2023-01-23 16:00:59.771341: step: 1604/1545, loss: 0.024180760607123375 2023-01-23 16:01:00.699575: step: 1606/1545, loss: 0.0020981894340366125 2023-01-23 16:01:01.624143: step: 1608/1545, loss: 0.008253579027950764 2023-01-23 16:01:02.523657: step: 1610/1545, loss: 0.0034656929783523083 2023-01-23 16:01:03.427220: step: 1612/1545, loss: 0.0005537514225579798 2023-01-23 16:01:04.308018: step: 1614/1545, loss: 0.008414874784648418 2023-01-23 16:01:05.155590: step: 1616/1545, loss: 3.374011066625826e-05 2023-01-23 16:01:06.111270: step: 1618/1545, loss: 0.031411293894052505 2023-01-23 16:01:07.003661: step: 1620/1545, loss: 0.008792025037109852 2023-01-23 16:01:07.864764: step: 1622/1545, loss: 0.0037424929905682802 2023-01-23 16:01:08.761175: step: 1624/1545, loss: 0.0010421473998576403 2023-01-23 16:01:09.651926: step: 1626/1545, loss: 0.0004698902484960854 2023-01-23 16:01:10.526202: step: 1628/1545, loss: 0.1973034292459488 2023-01-23 16:01:11.439058: step: 1630/1545, loss: 0.0022136324550956488 2023-01-23 16:01:12.306932: step: 1632/1545, loss: 0.0037709230091422796 2023-01-23 16:01:13.157615: step: 1634/1545, loss: 0.0005606295308098197 2023-01-23 16:01:14.010622: step: 1636/1545, loss: 0.0014681192114949226 2023-01-23 16:01:14.941465: step: 1638/1545, loss: 0.12250570207834244 2023-01-23 16:01:15.802348: step: 1640/1545, loss: 0.20597070455551147 2023-01-23 16:01:16.651291: step: 1642/1545, loss: 0.00011505431029945612 2023-01-23 16:01:17.534433: step: 1644/1545, loss: 0.0001365840289508924 2023-01-23 16:01:18.405909: step: 1646/1545, loss: 0.000720365671440959 2023-01-23 16:01:19.300457: step: 1648/1545, loss: 0.4485938549041748 2023-01-23 16:01:20.198484: step: 1650/1545, loss: 0.0023778178729116917 2023-01-23 16:01:21.081380: step: 1652/1545, loss: 0.6127554178237915 2023-01-23 16:01:21.974007: step: 1654/1545, loss: 0.006376180332154036 2023-01-23 16:01:22.870393: step: 1656/1545, loss: 0.0009169795084744692 2023-01-23 16:01:23.735940: step: 1658/1545, loss: 0.015369787812232971 2023-01-23 16:01:24.641850: step: 1660/1545, loss: 0.02227347530424595 2023-01-23 16:01:25.497367: step: 1662/1545, loss: 0.0002373772585997358 2023-01-23 16:01:26.390907: step: 1664/1545, loss: 0.0005902100820094347 2023-01-23 16:01:27.279800: step: 1666/1545, loss: 0.01274826005101204 2023-01-23 16:01:28.134116: step: 1668/1545, loss: 0.002375017385929823 2023-01-23 16:01:29.064419: step: 1670/1545, loss: 0.01890343241393566 2023-01-23 16:01:29.934187: step: 1672/1545, loss: 0.05954661965370178 2023-01-23 16:01:30.788686: step: 1674/1545, loss: 0.0016524281818419695 2023-01-23 16:01:31.651506: step: 1676/1545, loss: 0.00012989845708943903 2023-01-23 16:01:32.524285: step: 1678/1545, loss: 0.10153587907552719 2023-01-23 16:01:33.430356: step: 1680/1545, loss: 0.17395317554473877 2023-01-23 16:01:34.305963: step: 1682/1545, loss: 0.15184427797794342 2023-01-23 16:01:35.189201: step: 1684/1545, loss: 0.003939222078770399 2023-01-23 16:01:36.136053: step: 1686/1545, loss: 0.007207589689642191 2023-01-23 16:01:37.046753: step: 1688/1545, loss: 0.00016389184747822583 2023-01-23 16:01:37.951390: step: 1690/1545, loss: 0.000647442415356636 2023-01-23 16:01:38.903205: step: 1692/1545, loss: 0.0982055738568306 2023-01-23 16:01:39.768393: step: 1694/1545, loss: 0.0010055924067273736 2023-01-23 16:01:40.616864: step: 1696/1545, loss: 0.0007314566755667329 2023-01-23 16:01:41.524711: step: 1698/1545, loss: 0.0003986559750046581 2023-01-23 16:01:42.492056: step: 1700/1545, loss: 0.005243685562163591 2023-01-23 16:01:43.525381: step: 1702/1545, loss: 0.06742335855960846 2023-01-23 16:01:44.453584: step: 1704/1545, loss: 0.0039169639348983765 2023-01-23 16:01:45.326943: step: 1706/1545, loss: 0.15754707157611847 2023-01-23 16:01:46.213991: step: 1708/1545, loss: 0.01618283800780773 2023-01-23 16:01:47.063945: step: 1710/1545, loss: 0.09375506639480591 2023-01-23 16:01:47.995161: step: 1712/1545, loss: 0.06517772376537323 2023-01-23 16:01:48.880785: step: 1714/1545, loss: 0.09527913480997086 2023-01-23 16:01:49.758063: step: 1716/1545, loss: 0.0186023972928524 2023-01-23 16:01:50.676935: step: 1718/1545, loss: 0.022900620475411415 2023-01-23 16:01:51.545139: step: 1720/1545, loss: 0.09945410490036011 2023-01-23 16:01:52.481069: step: 1722/1545, loss: 0.00201999070122838 2023-01-23 16:01:53.368953: step: 1724/1545, loss: 0.22989009320735931 2023-01-23 16:01:54.279157: step: 1726/1545, loss: 0.0008839653455652297 2023-01-23 16:01:55.170983: step: 1728/1545, loss: 0.0006802367279306054 2023-01-23 16:01:56.191057: step: 1730/1545, loss: 0.33822381496429443 2023-01-23 16:01:57.089952: step: 1732/1545, loss: 0.03789076581597328 2023-01-23 16:01:57.943915: step: 1734/1545, loss: 0.0011846065754070878 2023-01-23 16:01:58.823724: step: 1736/1545, loss: 0.9363164901733398 2023-01-23 16:01:59.688330: step: 1738/1545, loss: 0.0037389846984297037 2023-01-23 16:02:00.520923: step: 1740/1545, loss: 0.061587024480104446 2023-01-23 16:02:01.436993: step: 1742/1545, loss: 0.21436014771461487 2023-01-23 16:02:02.342789: step: 1744/1545, loss: 0.003768690163269639 2023-01-23 16:02:03.225747: step: 1746/1545, loss: 0.02983243763446808 2023-01-23 16:02:04.046902: step: 1748/1545, loss: 0.0011419409420341253 2023-01-23 16:02:04.906707: step: 1750/1545, loss: 0.0050810519605875015 2023-01-23 16:02:05.748690: step: 1752/1545, loss: 0.0008396171615459025 2023-01-23 16:02:06.596545: step: 1754/1545, loss: 0.5855972766876221 2023-01-23 16:02:07.532234: step: 1756/1545, loss: 0.008489361964166164 2023-01-23 16:02:08.375785: step: 1758/1545, loss: 0.7380619645118713 2023-01-23 16:02:09.273255: step: 1760/1545, loss: 0.01334548369050026 2023-01-23 16:02:10.144933: step: 1762/1545, loss: 0.0754227340221405 2023-01-23 16:02:11.045803: step: 1764/1545, loss: 0.001103854738175869 2023-01-23 16:02:11.901577: step: 1766/1545, loss: 0.01916797272861004 2023-01-23 16:02:12.795835: step: 1768/1545, loss: 0.0015757987275719643 2023-01-23 16:02:13.674142: step: 1770/1545, loss: 0.18144682049751282 2023-01-23 16:02:14.534040: step: 1772/1545, loss: 0.3112540543079376 2023-01-23 16:02:15.372550: step: 1774/1545, loss: 0.0001586794969625771 2023-01-23 16:02:16.233192: step: 1776/1545, loss: 0.005424256902188063 2023-01-23 16:02:17.087623: step: 1778/1545, loss: 0.00029942483524791896 2023-01-23 16:02:17.948829: step: 1780/1545, loss: 0.00019896832236554474 2023-01-23 16:02:18.808385: step: 1782/1545, loss: 0.053043533116579056 2023-01-23 16:02:19.728066: step: 1784/1545, loss: 0.0279807448387146 2023-01-23 16:02:20.591916: step: 1786/1545, loss: 0.008310492150485516 2023-01-23 16:02:21.464822: step: 1788/1545, loss: 0.061151616275310516 2023-01-23 16:02:22.299301: step: 1790/1545, loss: 0.0003419361310079694 2023-01-23 16:02:23.134911: step: 1792/1545, loss: 0.012356930412352085 2023-01-23 16:02:23.996612: step: 1794/1545, loss: 0.03640757128596306 2023-01-23 16:02:24.900608: step: 1796/1545, loss: 0.10060391575098038 2023-01-23 16:02:25.787236: step: 1798/1545, loss: 3.415074388612993e-05 2023-01-23 16:02:26.669507: step: 1800/1545, loss: 0.0056303818710148335 2023-01-23 16:02:27.596992: step: 1802/1545, loss: 0.044708386063575745 2023-01-23 16:02:28.537017: step: 1804/1545, loss: 0.0005375906475819647 2023-01-23 16:02:29.444793: step: 1806/1545, loss: 0.0016544051468372345 2023-01-23 16:02:30.296253: step: 1808/1545, loss: 0.0007794303819537163 2023-01-23 16:02:31.202747: step: 1810/1545, loss: 0.019050156697630882 2023-01-23 16:02:32.082488: step: 1812/1545, loss: 0.00011050709872506559 2023-01-23 16:02:32.918272: step: 1814/1545, loss: 0.12797687947750092 2023-01-23 16:02:33.775725: step: 1816/1545, loss: 0.0024276820477098227 2023-01-23 16:02:34.649846: step: 1818/1545, loss: 0.3243057131767273 2023-01-23 16:02:35.533537: step: 1820/1545, loss: 0.03747578710317612 2023-01-23 16:02:36.400137: step: 1822/1545, loss: 0.14700192213058472 2023-01-23 16:02:37.291671: step: 1824/1545, loss: 0.00158869253937155 2023-01-23 16:02:38.113399: step: 1826/1545, loss: 0.030071575194597244 2023-01-23 16:02:38.976510: step: 1828/1545, loss: 0.24922595918178558 2023-01-23 16:02:39.871923: step: 1830/1545, loss: 0.006166718900203705 2023-01-23 16:02:40.761428: step: 1832/1545, loss: 0.005390829406678677 2023-01-23 16:02:41.626878: step: 1834/1545, loss: 0.008172043599188328 2023-01-23 16:02:42.520338: step: 1836/1545, loss: 0.005348815582692623 2023-01-23 16:02:43.376016: step: 1838/1545, loss: 0.0008703741477802396 2023-01-23 16:02:44.282401: step: 1840/1545, loss: 0.020516782999038696 2023-01-23 16:02:45.158479: step: 1842/1545, loss: 0.11273078620433807 2023-01-23 16:02:46.078073: step: 1844/1545, loss: 0.14292362332344055 2023-01-23 16:02:46.958524: step: 1846/1545, loss: 0.0004994434420950711 2023-01-23 16:02:47.832269: step: 1848/1545, loss: 0.014586291275918484 2023-01-23 16:02:48.722583: step: 1850/1545, loss: 0.10437159240245819 2023-01-23 16:02:49.643835: step: 1852/1545, loss: 0.011394052766263485 2023-01-23 16:02:50.602864: step: 1854/1545, loss: 0.01287627499550581 2023-01-23 16:02:51.558174: step: 1856/1545, loss: 0.21590733528137207 2023-01-23 16:02:52.449305: step: 1858/1545, loss: 0.00931590050458908 2023-01-23 16:02:53.354040: step: 1860/1545, loss: 0.0656275600194931 2023-01-23 16:02:54.259003: step: 1862/1545, loss: 0.0001495864416938275 2023-01-23 16:02:55.168066: step: 1864/1545, loss: 0.17828764021396637 2023-01-23 16:02:56.021648: step: 1866/1545, loss: 0.006573292426764965 2023-01-23 16:02:56.870214: step: 1868/1545, loss: 0.01385523658245802 2023-01-23 16:02:57.752041: step: 1870/1545, loss: 0.16715365648269653 2023-01-23 16:02:58.641327: step: 1872/1545, loss: 0.0005649160593748093 2023-01-23 16:02:59.531068: step: 1874/1545, loss: 0.04240160435438156 2023-01-23 16:03:00.415813: step: 1876/1545, loss: 0.0017189385835081339 2023-01-23 16:03:01.389323: step: 1878/1545, loss: 0.010462047532200813 2023-01-23 16:03:02.250974: step: 1880/1545, loss: 0.41759568452835083 2023-01-23 16:03:03.154262: step: 1882/1545, loss: 3.994224971393123e-05 2023-01-23 16:03:04.034993: step: 1884/1545, loss: 0.0029235375113785267 2023-01-23 16:03:04.970852: step: 1886/1545, loss: 0.2758445143699646 2023-01-23 16:03:05.858150: step: 1888/1545, loss: 0.0021873493678867817 2023-01-23 16:03:06.718596: step: 1890/1545, loss: 0.2235703319311142 2023-01-23 16:03:07.609423: step: 1892/1545, loss: 0.0026669062208384275 2023-01-23 16:03:08.530716: step: 1894/1545, loss: 0.09043670445680618 2023-01-23 16:03:09.471824: step: 1896/1545, loss: 0.0012920773588120937 2023-01-23 16:03:10.355769: step: 1898/1545, loss: 3.494436896289699e-05 2023-01-23 16:03:11.240656: step: 1900/1545, loss: 0.08794742822647095 2023-01-23 16:03:12.163822: step: 1902/1545, loss: 0.011823279783129692 2023-01-23 16:03:13.099657: step: 1904/1545, loss: 0.00027177631272934377 2023-01-23 16:03:13.959039: step: 1906/1545, loss: 0.00022127220290713012 2023-01-23 16:03:14.835060: step: 1908/1545, loss: 0.13435329496860504 2023-01-23 16:03:15.718996: step: 1910/1545, loss: 0.0036892027128487825 2023-01-23 16:03:16.626983: step: 1912/1545, loss: 0.07607872784137726 2023-01-23 16:03:17.514847: step: 1914/1545, loss: 0.004863643553107977 2023-01-23 16:03:18.480705: step: 1916/1545, loss: 0.04177265614271164 2023-01-23 16:03:19.390525: step: 1918/1545, loss: 0.054120831191539764 2023-01-23 16:03:20.265960: step: 1920/1545, loss: 0.1809866577386856 2023-01-23 16:03:21.152599: step: 1922/1545, loss: 0.018504712730646133 2023-01-23 16:03:22.009607: step: 1924/1545, loss: 0.12035718560218811 2023-01-23 16:03:22.874935: step: 1926/1545, loss: 0.006339785642921925 2023-01-23 16:03:23.834617: step: 1928/1545, loss: 0.0003860459546558559 2023-01-23 16:03:24.697241: step: 1930/1545, loss: 0.12439918518066406 2023-01-23 16:03:25.598288: step: 1932/1545, loss: 0.0004678783589042723 2023-01-23 16:03:26.476429: step: 1934/1545, loss: 0.00028110435232520103 2023-01-23 16:03:27.355448: step: 1936/1545, loss: 0.08577632904052734 2023-01-23 16:03:28.225563: step: 1938/1545, loss: 0.09949346631765366 2023-01-23 16:03:29.074003: step: 1940/1545, loss: 0.0005024083657190204 2023-01-23 16:03:29.983053: step: 1942/1545, loss: 0.0004932035226374865 2023-01-23 16:03:30.909819: step: 1944/1545, loss: 0.015803683549165726 2023-01-23 16:03:31.796138: step: 1946/1545, loss: 0.08048616349697113 2023-01-23 16:03:32.696837: step: 1948/1545, loss: 0.00434919586405158 2023-01-23 16:03:33.607631: step: 1950/1545, loss: 0.14771094918251038 2023-01-23 16:03:34.500235: step: 1952/1545, loss: 0.025995267555117607 2023-01-23 16:03:35.387833: step: 1954/1545, loss: 0.0004850222612731159 2023-01-23 16:03:36.276660: step: 1956/1545, loss: 0.008349715732038021 2023-01-23 16:03:37.133991: step: 1958/1545, loss: 0.003109733574092388 2023-01-23 16:03:37.979832: step: 1960/1545, loss: 0.0026869189459830523 2023-01-23 16:03:38.837284: step: 1962/1545, loss: 0.0015883018495514989 2023-01-23 16:03:39.744043: step: 1964/1545, loss: 0.0775417760014534 2023-01-23 16:03:40.668828: step: 1966/1545, loss: 0.022658273577690125 2023-01-23 16:03:41.568336: step: 1968/1545, loss: 0.002917367033660412 2023-01-23 16:03:42.442596: step: 1970/1545, loss: 0.0006251016166061163 2023-01-23 16:03:43.334336: step: 1972/1545, loss: 0.12241377681493759 2023-01-23 16:03:44.250217: step: 1974/1545, loss: 0.1863744705915451 2023-01-23 16:03:45.086665: step: 1976/1545, loss: 0.052747201174497604 2023-01-23 16:03:45.981610: step: 1978/1545, loss: 0.21034227311611176 2023-01-23 16:03:46.897218: step: 1980/1545, loss: 0.005251566879451275 2023-01-23 16:03:47.784636: step: 1982/1545, loss: 0.0010962003143504262 2023-01-23 16:03:48.648769: step: 1984/1545, loss: 0.008662538602948189 2023-01-23 16:03:49.559697: step: 1986/1545, loss: 0.2631889283657074 2023-01-23 16:03:50.471355: step: 1988/1545, loss: 0.3457958996295929 2023-01-23 16:03:51.366933: step: 1990/1545, loss: 0.028481828048825264 2023-01-23 16:03:52.217379: step: 1992/1545, loss: 0.0034575138706713915 2023-01-23 16:03:53.097131: step: 1994/1545, loss: 0.002153531415387988 2023-01-23 16:03:53.977233: step: 1996/1545, loss: 0.002077370649203658 2023-01-23 16:03:54.878309: step: 1998/1545, loss: 0.000982598983682692 2023-01-23 16:03:55.794726: step: 2000/1545, loss: 0.027580494061112404 2023-01-23 16:03:56.654852: step: 2002/1545, loss: 0.06826604902744293 2023-01-23 16:03:57.510417: step: 2004/1545, loss: 0.025516869500279427 2023-01-23 16:03:58.390244: step: 2006/1545, loss: 0.02960030548274517 2023-01-23 16:03:59.286711: step: 2008/1545, loss: 0.005764452740550041 2023-01-23 16:04:00.157327: step: 2010/1545, loss: 0.0006833639345131814 2023-01-23 16:04:01.045884: step: 2012/1545, loss: 0.005064246244728565 2023-01-23 16:04:02.033270: step: 2014/1545, loss: 0.01058945432305336 2023-01-23 16:04:02.941156: step: 2016/1545, loss: 0.19446799159049988 2023-01-23 16:04:03.885925: step: 2018/1545, loss: 0.00126458250451833 2023-01-23 16:04:04.782908: step: 2020/1545, loss: 0.006082640029489994 2023-01-23 16:04:05.651677: step: 2022/1545, loss: 0.23182860016822815 2023-01-23 16:04:06.500681: step: 2024/1545, loss: 0.011259090155363083 2023-01-23 16:04:07.370737: step: 2026/1545, loss: 0.10987231135368347 2023-01-23 16:04:08.221030: step: 2028/1545, loss: 0.0059774345718324184 2023-01-23 16:04:09.122351: step: 2030/1545, loss: 0.003187650116160512 2023-01-23 16:04:10.011680: step: 2032/1545, loss: 0.002963838865980506 2023-01-23 16:04:10.918329: step: 2034/1545, loss: 0.00744156539440155 2023-01-23 16:04:11.775866: step: 2036/1545, loss: 0.09656646847724915 2023-01-23 16:04:12.644947: step: 2038/1545, loss: 0.0009860454592853785 2023-01-23 16:04:13.553221: step: 2040/1545, loss: 0.0018720590742304921 2023-01-23 16:04:14.443677: step: 2042/1545, loss: 0.025474676862359047 2023-01-23 16:04:15.314921: step: 2044/1545, loss: 0.0006058405851945281 2023-01-23 16:04:16.214614: step: 2046/1545, loss: 0.1389656960964203 2023-01-23 16:04:17.092676: step: 2048/1545, loss: 0.008041218854486942 2023-01-23 16:04:17.959689: step: 2050/1545, loss: 0.038693636655807495 2023-01-23 16:04:18.836403: step: 2052/1545, loss: 0.5269708633422852 2023-01-23 16:04:19.733537: step: 2054/1545, loss: 0.01725848764181137 2023-01-23 16:04:20.724184: step: 2056/1545, loss: 0.021548397839069366 2023-01-23 16:04:21.604556: step: 2058/1545, loss: 0.054543644189834595 2023-01-23 16:04:22.472368: step: 2060/1545, loss: 0.43513384461402893 2023-01-23 16:04:23.371816: step: 2062/1545, loss: 0.004371807910501957 2023-01-23 16:04:24.243297: step: 2064/1545, loss: 0.028142264112830162 2023-01-23 16:04:25.136180: step: 2066/1545, loss: 0.019310832023620605 2023-01-23 16:04:26.025012: step: 2068/1545, loss: 0.006133677437901497 2023-01-23 16:04:26.909076: step: 2070/1545, loss: 0.0049100350588560104 2023-01-23 16:04:27.791531: step: 2072/1545, loss: 0.011531669646501541 2023-01-23 16:04:28.675665: step: 2074/1545, loss: 0.007572791073471308 2023-01-23 16:04:29.566755: step: 2076/1545, loss: 0.001751679927110672 2023-01-23 16:04:30.468186: step: 2078/1545, loss: 0.041807278990745544 2023-01-23 16:04:31.353703: step: 2080/1545, loss: 0.005201392807066441 2023-01-23 16:04:32.213430: step: 2082/1545, loss: 0.13992831110954285 2023-01-23 16:04:33.090775: step: 2084/1545, loss: 0.0014703810447826982 2023-01-23 16:04:33.964803: step: 2086/1545, loss: 0.011505534872412682 2023-01-23 16:04:34.815612: step: 2088/1545, loss: 0.0018193364376202226 2023-01-23 16:04:35.677033: step: 2090/1545, loss: 0.02006547339260578 2023-01-23 16:04:36.599461: step: 2092/1545, loss: 0.013870593160390854 2023-01-23 16:04:37.450150: step: 2094/1545, loss: 0.0032357992604374886 2023-01-23 16:04:38.345632: step: 2096/1545, loss: 0.021478109061717987 2023-01-23 16:04:39.209121: step: 2098/1545, loss: 0.24543730914592743 2023-01-23 16:04:40.068600: step: 2100/1545, loss: 0.24540312588214874 2023-01-23 16:04:40.914230: step: 2102/1545, loss: 0.0012568130623549223 2023-01-23 16:04:41.760548: step: 2104/1545, loss: 0.005476848687976599 2023-01-23 16:04:42.616493: step: 2106/1545, loss: 0.0018673879094421864 2023-01-23 16:04:43.483625: step: 2108/1545, loss: 0.06665608286857605 2023-01-23 16:04:44.369734: step: 2110/1545, loss: 0.025967836380004883 2023-01-23 16:04:45.267506: step: 2112/1545, loss: 0.0029588898178189993 2023-01-23 16:04:46.202923: step: 2114/1545, loss: 0.10908756405115128 2023-01-23 16:04:47.136560: step: 2116/1545, loss: 0.007441112771630287 2023-01-23 16:04:48.045020: step: 2118/1545, loss: 0.019200840964913368 2023-01-23 16:04:49.044617: step: 2120/1545, loss: 0.09064804017543793 2023-01-23 16:04:49.989693: step: 2122/1545, loss: 0.003317679511383176 2023-01-23 16:04:50.839969: step: 2124/1545, loss: 0.0013251281343400478 2023-01-23 16:04:51.739275: step: 2126/1545, loss: 0.0751645565032959 2023-01-23 16:04:52.637083: step: 2128/1545, loss: 0.003323590150102973 2023-01-23 16:04:53.509500: step: 2130/1545, loss: 0.004911335185170174 2023-01-23 16:04:54.478295: step: 2132/1545, loss: 0.0009421504219062626 2023-01-23 16:04:55.351654: step: 2134/1545, loss: 0.0005103634903207421 2023-01-23 16:04:56.237629: step: 2136/1545, loss: 0.16228654980659485 2023-01-23 16:04:57.131732: step: 2138/1545, loss: 0.17922630906105042 2023-01-23 16:04:58.002380: step: 2140/1545, loss: 0.0625576451420784 2023-01-23 16:04:58.870101: step: 2142/1545, loss: 0.002548962365835905 2023-01-23 16:04:59.765252: step: 2144/1545, loss: 0.10460525751113892 2023-01-23 16:05:00.658079: step: 2146/1545, loss: 0.12224026024341583 2023-01-23 16:05:01.582234: step: 2148/1545, loss: 0.22978612780570984 2023-01-23 16:05:02.476342: step: 2150/1545, loss: 0.039801936596632004 2023-01-23 16:05:03.374555: step: 2152/1545, loss: 0.2248024195432663 2023-01-23 16:05:04.292329: step: 2154/1545, loss: 0.0018659117631614208 2023-01-23 16:05:05.211402: step: 2156/1545, loss: 0.08231142908334732 2023-01-23 16:05:06.143248: step: 2158/1545, loss: 0.0041546691209077835 2023-01-23 16:05:06.999669: step: 2160/1545, loss: 0.017435884103178978 2023-01-23 16:05:07.871337: step: 2162/1545, loss: 0.03628338500857353 2023-01-23 16:05:08.796470: step: 2164/1545, loss: 0.007232523523271084 2023-01-23 16:05:09.683868: step: 2166/1545, loss: 0.4071175158023834 2023-01-23 16:05:10.554471: step: 2168/1545, loss: 0.009325004182755947 2023-01-23 16:05:11.419250: step: 2170/1545, loss: 0.0015941003803163767 2023-01-23 16:05:12.361412: step: 2172/1545, loss: 0.014615354128181934 2023-01-23 16:05:13.205324: step: 2174/1545, loss: 0.06232792139053345 2023-01-23 16:05:14.073103: step: 2176/1545, loss: 0.0019415686838328838 2023-01-23 16:05:14.911097: step: 2178/1545, loss: 0.0013617665972560644 2023-01-23 16:05:15.788531: step: 2180/1545, loss: 0.024608733132481575 2023-01-23 16:05:16.728169: step: 2182/1545, loss: 0.042635269463062286 2023-01-23 16:05:17.604724: step: 2184/1545, loss: 0.09692980349063873 2023-01-23 16:05:18.449678: step: 2186/1545, loss: 0.0027737487107515335 2023-01-23 16:05:19.324977: step: 2188/1545, loss: 0.2763460576534271 2023-01-23 16:05:20.184915: step: 2190/1545, loss: 0.01450931653380394 2023-01-23 16:05:21.093968: step: 2192/1545, loss: 0.0025683781132102013 2023-01-23 16:05:21.968153: step: 2194/1545, loss: 0.07891476899385452 2023-01-23 16:05:22.828874: step: 2196/1545, loss: 0.0044914716854691505 2023-01-23 16:05:23.681807: step: 2198/1545, loss: 0.0007312290836125612 2023-01-23 16:05:24.580521: step: 2200/1545, loss: 0.010554216802120209 2023-01-23 16:05:25.442408: step: 2202/1545, loss: 0.037519000470638275 2023-01-23 16:05:26.399900: step: 2204/1545, loss: 0.021212410181760788 2023-01-23 16:05:27.243297: step: 2206/1545, loss: 0.0012798764510080218 2023-01-23 16:05:28.117816: step: 2208/1545, loss: 0.04175158217549324 2023-01-23 16:05:29.006479: step: 2210/1545, loss: 0.06645560264587402 2023-01-23 16:05:29.922107: step: 2212/1545, loss: 0.1290162205696106 2023-01-23 16:05:30.815533: step: 2214/1545, loss: 0.003290710039436817 2023-01-23 16:05:31.675849: step: 2216/1545, loss: 0.3161814510822296 2023-01-23 16:05:32.636910: step: 2218/1545, loss: 0.19151701033115387 2023-01-23 16:05:33.518237: step: 2220/1545, loss: 0.019300881773233414 2023-01-23 16:05:34.360828: step: 2222/1545, loss: 0.00034746003802865744 2023-01-23 16:05:35.269327: step: 2224/1545, loss: 0.038784876465797424 2023-01-23 16:05:36.125851: step: 2226/1545, loss: 0.18297907710075378 2023-01-23 16:05:36.984081: step: 2228/1545, loss: 0.0012622365029528737 2023-01-23 16:05:37.821631: step: 2230/1545, loss: 0.1643899828195572 2023-01-23 16:05:38.711460: step: 2232/1545, loss: 0.4491075575351715 2023-01-23 16:05:39.567100: step: 2234/1545, loss: 0.0004758900322485715 2023-01-23 16:05:40.432909: step: 2236/1545, loss: 0.15297582745552063 2023-01-23 16:05:41.276718: step: 2238/1545, loss: 0.0002362671948503703 2023-01-23 16:05:42.142833: step: 2240/1545, loss: 0.01888873055577278 2023-01-23 16:05:43.029016: step: 2242/1545, loss: 0.34860360622406006 2023-01-23 16:05:43.930150: step: 2244/1545, loss: 0.09639085084199905 2023-01-23 16:05:44.849688: step: 2246/1545, loss: 0.45344987511634827 2023-01-23 16:05:45.729486: step: 2248/1545, loss: 0.14258643984794617 2023-01-23 16:05:46.603915: step: 2250/1545, loss: 0.08614449203014374 2023-01-23 16:05:47.479667: step: 2252/1545, loss: 0.002727233339101076 2023-01-23 16:05:48.351493: step: 2254/1545, loss: 0.001620930852368474 2023-01-23 16:05:49.248366: step: 2256/1545, loss: 0.0021783390548080206 2023-01-23 16:05:50.138350: step: 2258/1545, loss: 0.00598552543669939 2023-01-23 16:05:51.130823: step: 2260/1545, loss: 0.0010121953673660755 2023-01-23 16:05:52.042660: step: 2262/1545, loss: 0.030300220474600792 2023-01-23 16:05:52.994731: step: 2264/1545, loss: 0.15825574100017548 2023-01-23 16:05:53.906633: step: 2266/1545, loss: 0.04339836537837982 2023-01-23 16:05:54.783778: step: 2268/1545, loss: 0.002627287758514285 2023-01-23 16:05:55.655661: step: 2270/1545, loss: 0.03637637570500374 2023-01-23 16:05:56.499927: step: 2272/1545, loss: 0.006135334726423025 2023-01-23 16:05:57.371916: step: 2274/1545, loss: 0.3973134458065033 2023-01-23 16:05:58.253950: step: 2276/1545, loss: 0.007238699588924646 2023-01-23 16:05:59.123457: step: 2278/1545, loss: 0.004552220925688744 2023-01-23 16:06:00.028031: step: 2280/1545, loss: 0.0389004647731781 2023-01-23 16:06:00.902681: step: 2282/1545, loss: 0.006408206652849913 2023-01-23 16:06:01.791114: step: 2284/1545, loss: 0.12304537743330002 2023-01-23 16:06:02.693694: step: 2286/1545, loss: 0.4633282423019409 2023-01-23 16:06:03.623802: step: 2288/1545, loss: 0.0005567441112361848 2023-01-23 16:06:04.546799: step: 2290/1545, loss: 0.0016743389423936605 2023-01-23 16:06:05.463295: step: 2292/1545, loss: 0.05242130532860756 2023-01-23 16:06:06.360486: step: 2294/1545, loss: 0.033608995378017426 2023-01-23 16:06:07.241158: step: 2296/1545, loss: 0.002524658804759383 2023-01-23 16:06:08.113133: step: 2298/1545, loss: 0.0849747434258461 2023-01-23 16:06:09.006744: step: 2300/1545, loss: 0.0021361366380006075 2023-01-23 16:06:09.924280: step: 2302/1545, loss: 0.001394448452629149 2023-01-23 16:06:10.845050: step: 2304/1545, loss: 0.08648629486560822 2023-01-23 16:06:11.729211: step: 2306/1545, loss: 0.014376833103597164 2023-01-23 16:06:12.635894: step: 2308/1545, loss: 0.09927623718976974 2023-01-23 16:06:13.497871: step: 2310/1545, loss: 0.04374108836054802 2023-01-23 16:06:14.363335: step: 2312/1545, loss: 0.0025155842304229736 2023-01-23 16:06:15.242060: step: 2314/1545, loss: 0.008165668696165085 2023-01-23 16:06:16.127700: step: 2316/1545, loss: 0.019606683403253555 2023-01-23 16:06:16.991387: step: 2318/1545, loss: 0.0695369616150856 2023-01-23 16:06:17.933407: step: 2320/1545, loss: 0.03431050851941109 2023-01-23 16:06:18.852183: step: 2322/1545, loss: 0.03060252219438553 2023-01-23 16:06:19.767826: step: 2324/1545, loss: 0.0009278403013013303 2023-01-23 16:06:20.713770: step: 2326/1545, loss: 0.12100400775671005 2023-01-23 16:06:21.603788: step: 2328/1545, loss: 0.0027560472954064608 2023-01-23 16:06:22.478825: step: 2330/1545, loss: 0.039865780621767044 2023-01-23 16:06:23.351865: step: 2332/1545, loss: 0.00044454738963395357 2023-01-23 16:06:24.221747: step: 2334/1545, loss: 0.018270989879965782 2023-01-23 16:06:25.126472: step: 2336/1545, loss: 0.002738909563049674 2023-01-23 16:06:25.993573: step: 2338/1545, loss: 0.004965427331626415 2023-01-23 16:06:26.850419: step: 2340/1545, loss: 0.0042527811601758 2023-01-23 16:06:27.764920: step: 2342/1545, loss: 0.010495249181985855 2023-01-23 16:06:28.619901: step: 2344/1545, loss: 0.08638694882392883 2023-01-23 16:06:29.502494: step: 2346/1545, loss: 0.053538646548986435 2023-01-23 16:06:30.333690: step: 2348/1545, loss: 0.02109667658805847 2023-01-23 16:06:31.192766: step: 2350/1545, loss: 1.037331223487854 2023-01-23 16:06:32.092593: step: 2352/1545, loss: 0.18728584051132202 2023-01-23 16:06:32.958540: step: 2354/1545, loss: 0.0005065350560471416 2023-01-23 16:06:33.884988: step: 2356/1545, loss: 0.0465557761490345 2023-01-23 16:06:34.774818: step: 2358/1545, loss: 0.06440785527229309 2023-01-23 16:06:35.641041: step: 2360/1545, loss: 0.008300097659230232 2023-01-23 16:06:36.522321: step: 2362/1545, loss: 0.008912794291973114 2023-01-23 16:06:37.445528: step: 2364/1545, loss: 0.13568131625652313 2023-01-23 16:06:38.413752: step: 2366/1545, loss: 0.17476069927215576 2023-01-23 16:06:39.291958: step: 2368/1545, loss: 0.0022232604678720236 2023-01-23 16:06:40.149830: step: 2370/1545, loss: 0.04183977469801903 2023-01-23 16:06:41.048316: step: 2372/1545, loss: 0.01402062363922596 2023-01-23 16:06:41.919963: step: 2374/1545, loss: 0.06322621554136276 2023-01-23 16:06:42.815209: step: 2376/1545, loss: 0.008938240818679333 2023-01-23 16:06:43.739065: step: 2378/1545, loss: 0.028766164556145668 2023-01-23 16:06:44.657971: step: 2380/1545, loss: 0.023390576243400574 2023-01-23 16:06:45.625966: step: 2382/1545, loss: 0.003125021932646632 2023-01-23 16:06:46.508798: step: 2384/1545, loss: 0.26999858021736145 2023-01-23 16:06:47.377087: step: 2386/1545, loss: 0.0624367780983448 2023-01-23 16:06:48.226149: step: 2388/1545, loss: 0.0023341220803558826 2023-01-23 16:06:49.087978: step: 2390/1545, loss: 0.15951530635356903 2023-01-23 16:06:50.007852: step: 2392/1545, loss: 0.0005065416917204857 2023-01-23 16:06:50.881345: step: 2394/1545, loss: 0.0008641823078505695 2023-01-23 16:06:51.755687: step: 2396/1545, loss: 0.264758825302124 2023-01-23 16:06:52.673361: step: 2398/1545, loss: 0.1844044178724289 2023-01-23 16:06:53.537360: step: 2400/1545, loss: 0.1413297951221466 2023-01-23 16:06:54.414124: step: 2402/1545, loss: 0.0015158822061493993 2023-01-23 16:06:55.262560: step: 2404/1545, loss: 0.0211062990128994 2023-01-23 16:06:56.099533: step: 2406/1545, loss: 0.0016563425306230783 2023-01-23 16:06:56.992459: step: 2408/1545, loss: 0.0005707325763069093 2023-01-23 16:06:57.875602: step: 2410/1545, loss: 0.0027083298191428185 2023-01-23 16:06:58.743250: step: 2412/1545, loss: 0.026936911046504974 2023-01-23 16:06:59.570446: step: 2414/1545, loss: 0.0007417299784719944 2023-01-23 16:07:00.489631: step: 2416/1545, loss: 0.23278526961803436 2023-01-23 16:07:01.369483: step: 2418/1545, loss: 0.10622261464595795 2023-01-23 16:07:02.240408: step: 2420/1545, loss: 0.034554850310087204 2023-01-23 16:07:03.155695: step: 2422/1545, loss: 0.0004760444280691445 2023-01-23 16:07:04.040668: step: 2424/1545, loss: 0.02535463310778141 2023-01-23 16:07:04.915412: step: 2426/1545, loss: 0.0673917829990387 2023-01-23 16:07:05.808030: step: 2428/1545, loss: 0.14983710646629333 2023-01-23 16:07:06.703405: step: 2430/1545, loss: 0.0028087622486054897 2023-01-23 16:07:07.619721: step: 2432/1545, loss: 0.0019111355068162084 2023-01-23 16:07:08.472060: step: 2434/1545, loss: 0.01419721357524395 2023-01-23 16:07:09.355271: step: 2436/1545, loss: 0.027753150090575218 2023-01-23 16:07:10.226340: step: 2438/1545, loss: 1.358338713645935 2023-01-23 16:07:11.176574: step: 2440/1545, loss: 0.027313189581036568 2023-01-23 16:07:12.054667: step: 2442/1545, loss: 0.07720505446195602 2023-01-23 16:07:12.980135: step: 2444/1545, loss: 0.0017728472594171762 2023-01-23 16:07:13.910712: step: 2446/1545, loss: 0.010815279558300972 2023-01-23 16:07:14.787466: step: 2448/1545, loss: 0.008402607403695583 2023-01-23 16:07:15.669684: step: 2450/1545, loss: 0.04453376680612564 2023-01-23 16:07:16.535361: step: 2452/1545, loss: 0.18567031621932983 2023-01-23 16:07:17.390760: step: 2454/1545, loss: 0.0076079824939370155 2023-01-23 16:07:18.269255: step: 2456/1545, loss: 0.009025911800563335 2023-01-23 16:07:19.239846: step: 2458/1545, loss: 0.2759157419204712 2023-01-23 16:07:20.125697: step: 2460/1545, loss: 0.0037078303284943104 2023-01-23 16:07:20.986923: step: 2462/1545, loss: 0.46127229928970337 2023-01-23 16:07:21.841643: step: 2464/1545, loss: 0.0019393796101212502 2023-01-23 16:07:22.757873: step: 2466/1545, loss: 0.1684757024049759 2023-01-23 16:07:23.631771: step: 2468/1545, loss: 0.0031246463768184185 2023-01-23 16:07:24.538924: step: 2470/1545, loss: 0.035177357494831085 2023-01-23 16:07:25.435710: step: 2472/1545, loss: 0.12614579498767853 2023-01-23 16:07:26.404847: step: 2474/1545, loss: 0.001080530695617199 2023-01-23 16:07:27.364683: step: 2476/1545, loss: 0.0012965126661583781 2023-01-23 16:07:28.224312: step: 2478/1545, loss: 0.005384168121963739 2023-01-23 16:07:29.097554: step: 2480/1545, loss: 0.005388232413679361 2023-01-23 16:07:29.990071: step: 2482/1545, loss: 0.21816115081310272 2023-01-23 16:07:30.874135: step: 2484/1545, loss: 0.13137118518352509 2023-01-23 16:07:31.702640: step: 2486/1545, loss: 0.06992576271295547 2023-01-23 16:07:32.608947: step: 2488/1545, loss: 0.09537122398614883 2023-01-23 16:07:33.511699: step: 2490/1545, loss: 0.013557110913097858 2023-01-23 16:07:34.420833: step: 2492/1545, loss: 0.007149570155888796 2023-01-23 16:07:35.278941: step: 2494/1545, loss: 0.11009343713521957 2023-01-23 16:07:36.149081: step: 2496/1545, loss: 0.12403981387615204 2023-01-23 16:07:37.044774: step: 2498/1545, loss: 0.03133426234126091 2023-01-23 16:07:37.930903: step: 2500/1545, loss: 0.017554474994540215 2023-01-23 16:07:38.805873: step: 2502/1545, loss: 0.005326678976416588 2023-01-23 16:07:39.706739: step: 2504/1545, loss: 0.012777050025761127 2023-01-23 16:07:40.575577: step: 2506/1545, loss: 0.32105910778045654 2023-01-23 16:07:41.488092: step: 2508/1545, loss: 0.017151081934571266 2023-01-23 16:07:42.368546: step: 2510/1545, loss: 0.12818144261837006 2023-01-23 16:07:43.232907: step: 2512/1545, loss: 0.03029436618089676 2023-01-23 16:07:44.079377: step: 2514/1545, loss: 0.037590544670820236 2023-01-23 16:07:44.951037: step: 2516/1545, loss: 0.23108135163784027 2023-01-23 16:07:45.830759: step: 2518/1545, loss: 0.016013268381357193 2023-01-23 16:07:46.699938: step: 2520/1545, loss: 0.003003370948135853 2023-01-23 16:07:47.554283: step: 2522/1545, loss: 0.02832723595201969 2023-01-23 16:07:48.479312: step: 2524/1545, loss: 0.007661248557269573 2023-01-23 16:07:49.374977: step: 2526/1545, loss: 0.2543875277042389 2023-01-23 16:07:50.255699: step: 2528/1545, loss: 0.000614855089224875 2023-01-23 16:07:51.111257: step: 2530/1545, loss: 0.03786219656467438 2023-01-23 16:07:51.982704: step: 2532/1545, loss: 0.04337800294160843 2023-01-23 16:07:52.977195: step: 2534/1545, loss: 0.028541384264826775 2023-01-23 16:07:53.867607: step: 2536/1545, loss: 0.014837363734841347 2023-01-23 16:07:54.716524: step: 2538/1545, loss: 0.0004005228402093053 2023-01-23 16:07:55.550026: step: 2540/1545, loss: 0.0006064763874746859 2023-01-23 16:07:56.429435: step: 2542/1545, loss: 0.00999918207526207 2023-01-23 16:07:57.279266: step: 2544/1545, loss: 0.002082821214571595 2023-01-23 16:07:58.118857: step: 2546/1545, loss: 0.0005754125886596739 2023-01-23 16:07:59.002236: step: 2548/1545, loss: 0.0060706655494868755 2023-01-23 16:07:59.880770: step: 2550/1545, loss: 0.023987218737602234 2023-01-23 16:08:00.729197: step: 2552/1545, loss: 0.00032951708999462426 2023-01-23 16:08:01.621069: step: 2554/1545, loss: 0.018175093457102776 2023-01-23 16:08:02.510231: step: 2556/1545, loss: 0.09565682709217072 2023-01-23 16:08:03.392794: step: 2558/1545, loss: 0.458047091960907 2023-01-23 16:08:04.267523: step: 2560/1545, loss: 0.07955309748649597 2023-01-23 16:08:05.136456: step: 2562/1545, loss: 0.011856273747980595 2023-01-23 16:08:06.063134: step: 2564/1545, loss: 0.012606879696249962 2023-01-23 16:08:06.921020: step: 2566/1545, loss: 0.0012425172608345747 2023-01-23 16:08:07.784661: step: 2568/1545, loss: 0.2332202047109604 2023-01-23 16:08:08.718390: step: 2570/1545, loss: 0.10683382302522659 2023-01-23 16:08:09.602482: step: 2572/1545, loss: 0.08360438048839569 2023-01-23 16:08:10.486698: step: 2574/1545, loss: 0.26003870368003845 2023-01-23 16:08:11.432147: step: 2576/1545, loss: 0.004736598115414381 2023-01-23 16:08:12.324156: step: 2578/1545, loss: 0.0009447225020267069 2023-01-23 16:08:13.214570: step: 2580/1545, loss: 0.0035336450673639774 2023-01-23 16:08:14.072312: step: 2582/1545, loss: 0.0031205075792968273 2023-01-23 16:08:15.003671: step: 2584/1545, loss: 0.00154847651720047 2023-01-23 16:08:15.848561: step: 2586/1545, loss: 0.005142154172062874 2023-01-23 16:08:16.706202: step: 2588/1545, loss: 0.967717170715332 2023-01-23 16:08:17.547592: step: 2590/1545, loss: 0.0008308693068102002 2023-01-23 16:08:18.402329: step: 2592/1545, loss: 0.14108571410179138 2023-01-23 16:08:19.310281: step: 2594/1545, loss: 0.00019303441513329744 2023-01-23 16:08:20.149711: step: 2596/1545, loss: 0.054386161267757416 2023-01-23 16:08:21.048047: step: 2598/1545, loss: 0.0114826038479805 2023-01-23 16:08:21.923948: step: 2600/1545, loss: 0.3798847794532776 2023-01-23 16:08:22.797693: step: 2602/1545, loss: 0.008031144738197327 2023-01-23 16:08:23.687004: step: 2604/1545, loss: 0.0014094093348830938 2023-01-23 16:08:24.574995: step: 2606/1545, loss: 0.037925828248262405 2023-01-23 16:08:25.471034: step: 2608/1545, loss: 0.0036860532127320766 2023-01-23 16:08:26.385263: step: 2610/1545, loss: 0.03779776021838188 2023-01-23 16:08:27.296513: step: 2612/1545, loss: 0.006349426694214344 2023-01-23 16:08:28.223730: step: 2614/1545, loss: 0.011933036148548126 2023-01-23 16:08:29.088769: step: 2616/1545, loss: 0.0037059481255710125 2023-01-23 16:08:29.996506: step: 2618/1545, loss: 0.12530860304832458 2023-01-23 16:08:30.835128: step: 2620/1545, loss: 0.0003416856052353978 2023-01-23 16:08:31.678349: step: 2622/1545, loss: 0.002768530510365963 2023-01-23 16:08:32.542743: step: 2624/1545, loss: 0.48117151856422424 2023-01-23 16:08:33.446055: step: 2626/1545, loss: 0.3866640329360962 2023-01-23 16:08:34.378562: step: 2628/1545, loss: 0.003923777490854263 2023-01-23 16:08:35.282693: step: 2630/1545, loss: 0.011271906085312366 2023-01-23 16:08:36.257813: step: 2632/1545, loss: 0.008462848141789436 2023-01-23 16:08:37.144311: step: 2634/1545, loss: 0.020815057680010796 2023-01-23 16:08:38.117936: step: 2636/1545, loss: 0.04489096999168396 2023-01-23 16:08:39.010928: step: 2638/1545, loss: 0.0031228892039507627 2023-01-23 16:08:39.875904: step: 2640/1545, loss: 0.010581126436591148 2023-01-23 16:08:40.771141: step: 2642/1545, loss: 0.11409361660480499 2023-01-23 16:08:41.609059: step: 2644/1545, loss: 0.07959602773189545 2023-01-23 16:08:42.562086: step: 2646/1545, loss: 0.02346830628812313 2023-01-23 16:08:43.476292: step: 2648/1545, loss: 0.021193386986851692 2023-01-23 16:08:44.336016: step: 2650/1545, loss: 0.27418842911720276 2023-01-23 16:08:45.206285: step: 2652/1545, loss: 0.21164003014564514 2023-01-23 16:08:46.056079: step: 2654/1545, loss: 0.014564624056220055 2023-01-23 16:08:46.938622: step: 2656/1545, loss: 0.0817146897315979 2023-01-23 16:08:47.828554: step: 2658/1545, loss: 0.1772497594356537 2023-01-23 16:08:48.682011: step: 2660/1545, loss: 0.016773391515016556 2023-01-23 16:08:49.563685: step: 2662/1545, loss: 0.0028526177629828453 2023-01-23 16:08:50.455273: step: 2664/1545, loss: 0.08510028570890427 2023-01-23 16:08:51.313714: step: 2666/1545, loss: 0.13502416014671326 2023-01-23 16:08:52.176504: step: 2668/1545, loss: 0.024639276787638664 2023-01-23 16:08:53.085704: step: 2670/1545, loss: 0.0005141660221852362 2023-01-23 16:08:53.967120: step: 2672/1545, loss: 0.037012021988630295 2023-01-23 16:08:54.861863: step: 2674/1545, loss: 0.11193061619997025 2023-01-23 16:08:55.751246: step: 2676/1545, loss: 0.6519877314567566 2023-01-23 16:08:56.653724: step: 2678/1545, loss: 0.009559210389852524 2023-01-23 16:08:57.558901: step: 2680/1545, loss: 0.0074506583623588085 2023-01-23 16:08:58.430679: step: 2682/1545, loss: 0.0008403887622989714 2023-01-23 16:08:59.326673: step: 2684/1545, loss: 0.17391517758369446 2023-01-23 16:09:00.234420: step: 2686/1545, loss: 0.01291845552623272 2023-01-23 16:09:01.125214: step: 2688/1545, loss: 0.08520659059286118 2023-01-23 16:09:02.031138: step: 2690/1545, loss: 0.12215816229581833 2023-01-23 16:09:02.957112: step: 2692/1545, loss: 0.002923873020336032 2023-01-23 16:09:03.831083: step: 2694/1545, loss: 0.0019855548162013292 2023-01-23 16:09:04.737911: step: 2696/1545, loss: 0.040673915296792984 2023-01-23 16:09:05.666843: step: 2698/1545, loss: 0.009424724616110325 2023-01-23 16:09:06.570473: step: 2700/1545, loss: 0.0006752576446160674 2023-01-23 16:09:07.466929: step: 2702/1545, loss: 0.16682171821594238 2023-01-23 16:09:08.382709: step: 2704/1545, loss: 0.05713433027267456 2023-01-23 16:09:09.311502: step: 2706/1545, loss: 0.006279158405959606 2023-01-23 16:09:10.258576: step: 2708/1545, loss: 0.0042556109838187695 2023-01-23 16:09:11.211872: step: 2710/1545, loss: 0.05857991799712181 2023-01-23 16:09:12.131163: step: 2712/1545, loss: 0.018371563404798508 2023-01-23 16:09:13.130275: step: 2714/1545, loss: 0.3058435320854187 2023-01-23 16:09:14.053280: step: 2716/1545, loss: 0.00905857514590025 2023-01-23 16:09:14.997615: step: 2718/1545, loss: 0.0030155314598232508 2023-01-23 16:09:15.877818: step: 2720/1545, loss: 0.002497738692909479 2023-01-23 16:09:16.756178: step: 2722/1545, loss: 0.002881063846871257 2023-01-23 16:09:17.655585: step: 2724/1545, loss: 0.0697597861289978 2023-01-23 16:09:18.540071: step: 2726/1545, loss: 0.02031133882701397 2023-01-23 16:09:19.451376: step: 2728/1545, loss: 0.003201331477612257 2023-01-23 16:09:20.351482: step: 2730/1545, loss: 0.21942196786403656 2023-01-23 16:09:21.204702: step: 2732/1545, loss: 0.01792382448911667 2023-01-23 16:09:22.116613: step: 2734/1545, loss: 0.0042418669909238815 2023-01-23 16:09:23.017096: step: 2736/1545, loss: 0.0034103323705494404 2023-01-23 16:09:23.913902: step: 2738/1545, loss: 0.01795906014740467 2023-01-23 16:09:24.767184: step: 2740/1545, loss: 0.24487800896167755 2023-01-23 16:09:25.652470: step: 2742/1545, loss: 0.0003997003077529371 2023-01-23 16:09:26.517084: step: 2744/1545, loss: 0.03575529903173447 2023-01-23 16:09:27.418337: step: 2746/1545, loss: 0.009027594700455666 2023-01-23 16:09:28.248556: step: 2748/1545, loss: 0.15683193504810333 2023-01-23 16:09:29.095922: step: 2750/1545, loss: 0.025227122008800507 2023-01-23 16:09:30.041323: step: 2752/1545, loss: 0.007272203452885151 2023-01-23 16:09:30.923901: step: 2754/1545, loss: 0.016171520575881004 2023-01-23 16:09:31.776601: step: 2756/1545, loss: 0.056795816868543625 2023-01-23 16:09:32.628541: step: 2758/1545, loss: 0.03966115415096283 2023-01-23 16:09:33.489704: step: 2760/1545, loss: 0.007655612658709288 2023-01-23 16:09:34.374468: step: 2762/1545, loss: 0.0001895738678285852 2023-01-23 16:09:35.245961: step: 2764/1545, loss: 0.9059744477272034 2023-01-23 16:09:36.111105: step: 2766/1545, loss: 0.12135861068964005 2023-01-23 16:09:36.986428: step: 2768/1545, loss: 0.0056787580251693726 2023-01-23 16:09:37.876568: step: 2770/1545, loss: 0.004201238509267569 2023-01-23 16:09:38.764881: step: 2772/1545, loss: 0.0005570361390709877 2023-01-23 16:09:39.651402: step: 2774/1545, loss: 0.008935539051890373 2023-01-23 16:09:40.575334: step: 2776/1545, loss: 0.002519628033041954 2023-01-23 16:09:41.437222: step: 2778/1545, loss: 0.25538524985313416 2023-01-23 16:09:42.270048: step: 2780/1545, loss: 0.037121761590242386 2023-01-23 16:09:43.148238: step: 2782/1545, loss: 0.00314680696465075 2023-01-23 16:09:44.026095: step: 2784/1545, loss: 0.022395510226488113 2023-01-23 16:09:44.902587: step: 2786/1545, loss: 0.059776078909635544 2023-01-23 16:09:45.813279: step: 2788/1545, loss: 0.0005086738965474069 2023-01-23 16:09:46.709527: step: 2790/1545, loss: 0.3429080843925476 2023-01-23 16:09:47.586488: step: 2792/1545, loss: 0.017020251601934433 2023-01-23 16:09:48.498076: step: 2794/1545, loss: 0.11419030278921127 2023-01-23 16:09:49.369491: step: 2796/1545, loss: 0.0006660402868874371 2023-01-23 16:09:50.302984: step: 2798/1545, loss: 0.17480365931987762 2023-01-23 16:09:51.156514: step: 2800/1545, loss: 0.025097347795963287 2023-01-23 16:09:52.080766: step: 2802/1545, loss: 0.05108293145895004 2023-01-23 16:09:52.942309: step: 2804/1545, loss: 0.009222612716257572 2023-01-23 16:09:53.853289: step: 2806/1545, loss: 0.06358051300048828 2023-01-23 16:09:54.749278: step: 2808/1545, loss: 0.0007346438942477107 2023-01-23 16:09:55.624779: step: 2810/1545, loss: 0.41952207684516907 2023-01-23 16:09:56.517221: step: 2812/1545, loss: 0.025847984477877617 2023-01-23 16:09:57.399061: step: 2814/1545, loss: 0.042765695601701736 2023-01-23 16:09:58.306537: step: 2816/1545, loss: 0.0019232368795201182 2023-01-23 16:09:59.222662: step: 2818/1545, loss: 0.01189314853399992 2023-01-23 16:10:00.090072: step: 2820/1545, loss: 0.022351618856191635 2023-01-23 16:10:00.961063: step: 2822/1545, loss: 0.00359181291423738 2023-01-23 16:10:01.817180: step: 2824/1545, loss: 0.04200916737318039 2023-01-23 16:10:02.742905: step: 2826/1545, loss: 0.08910627663135529 2023-01-23 16:10:03.624282: step: 2828/1545, loss: 0.0037483510095626116 2023-01-23 16:10:04.483614: step: 2830/1545, loss: 0.35658830404281616 2023-01-23 16:10:05.358530: step: 2832/1545, loss: 0.003188301110640168 2023-01-23 16:10:06.224862: step: 2834/1545, loss: 0.14609108865261078 2023-01-23 16:10:07.081950: step: 2836/1545, loss: 0.20259755849838257 2023-01-23 16:10:07.928847: step: 2838/1545, loss: 0.0023920501116663218 2023-01-23 16:10:08.760711: step: 2840/1545, loss: 0.17664586007595062 2023-01-23 16:10:09.714548: step: 2842/1545, loss: 0.05436859652400017 2023-01-23 16:10:10.571669: step: 2844/1545, loss: 0.003155893413349986 2023-01-23 16:10:11.428709: step: 2846/1545, loss: 0.0008364272071048617 2023-01-23 16:10:12.362983: step: 2848/1545, loss: 0.012342965230345726 2023-01-23 16:10:13.285016: step: 2850/1545, loss: 0.5422767996788025 2023-01-23 16:10:14.208750: step: 2852/1545, loss: 0.0008441559039056301 2023-01-23 16:10:15.073462: step: 2854/1545, loss: 0.19941426813602448 2023-01-23 16:10:15.997977: step: 2856/1545, loss: 0.009582717902958393 2023-01-23 16:10:16.885807: step: 2858/1545, loss: 0.005452642682939768 2023-01-23 16:10:17.782115: step: 2860/1545, loss: 0.003537591313943267 2023-01-23 16:10:18.653082: step: 2862/1545, loss: 0.00012738908117171377 2023-01-23 16:10:19.578573: step: 2864/1545, loss: 0.1706419140100479 2023-01-23 16:10:20.439176: step: 2866/1545, loss: 0.020589549094438553 2023-01-23 16:10:21.315250: step: 2868/1545, loss: 0.17099973559379578 2023-01-23 16:10:22.200517: step: 2870/1545, loss: 0.08588793128728867 2023-01-23 16:10:23.071610: step: 2872/1545, loss: 0.015981007367372513 2023-01-23 16:10:24.017762: step: 2874/1545, loss: 0.007086894474923611 2023-01-23 16:10:24.893070: step: 2876/1545, loss: 0.07241205871105194 2023-01-23 16:10:25.786255: step: 2878/1545, loss: 0.0033585545606911182 2023-01-23 16:10:26.703343: step: 2880/1545, loss: 0.003705499228090048 2023-01-23 16:10:27.590858: step: 2882/1545, loss: 0.4960390031337738 2023-01-23 16:10:28.477048: step: 2884/1545, loss: 0.008188392966985703 2023-01-23 16:10:29.341983: step: 2886/1545, loss: 0.0077471486292779446 2023-01-23 16:10:30.253524: step: 2888/1545, loss: 0.12686242163181305 2023-01-23 16:10:31.097819: step: 2890/1545, loss: 0.02282947488129139 2023-01-23 16:10:31.979491: step: 2892/1545, loss: 0.00348185864277184 2023-01-23 16:10:32.826206: step: 2894/1545, loss: 0.011542950756847858 2023-01-23 16:10:33.746813: step: 2896/1545, loss: 0.3176940679550171 2023-01-23 16:10:34.645658: step: 2898/1545, loss: 0.011990166269242764 2023-01-23 16:10:35.536099: step: 2900/1545, loss: 0.004107687622308731 2023-01-23 16:10:36.379427: step: 2902/1545, loss: 0.0005655675195157528 2023-01-23 16:10:37.275844: step: 2904/1545, loss: 0.00531311659142375 2023-01-23 16:10:38.126223: step: 2906/1545, loss: 1.3444732427597046 2023-01-23 16:10:38.974856: step: 2908/1545, loss: 0.004730076063424349 2023-01-23 16:10:39.902288: step: 2910/1545, loss: 0.04023377224802971 2023-01-23 16:10:40.815734: step: 2912/1545, loss: 0.004850679077208042 2023-01-23 16:10:41.703207: step: 2914/1545, loss: 0.05017769709229469 2023-01-23 16:10:42.582648: step: 2916/1545, loss: 0.0029942584224045277 2023-01-23 16:10:43.437879: step: 2918/1545, loss: 0.4737069010734558 2023-01-23 16:10:44.317412: step: 2920/1545, loss: 0.06565774977207184 2023-01-23 16:10:45.212583: step: 2922/1545, loss: 0.000231441663345322 2023-01-23 16:10:46.100094: step: 2924/1545, loss: 0.010672848671674728 2023-01-23 16:10:46.996995: step: 2926/1545, loss: 0.04717908427119255 2023-01-23 16:10:47.896363: step: 2928/1545, loss: 0.00370663870126009 2023-01-23 16:10:48.798220: step: 2930/1545, loss: 0.006025705952197313 2023-01-23 16:10:49.728820: step: 2932/1545, loss: 1.3272770643234253 2023-01-23 16:10:50.611086: step: 2934/1545, loss: 0.11897165328264236 2023-01-23 16:10:51.511589: step: 2936/1545, loss: 0.0018588179955258965 2023-01-23 16:10:52.429567: step: 2938/1545, loss: 0.004994021728634834 2023-01-23 16:10:53.307722: step: 2940/1545, loss: 0.007049785926938057 2023-01-23 16:10:54.197908: step: 2942/1545, loss: 0.1277131736278534 2023-01-23 16:10:55.095431: step: 2944/1545, loss: 0.1557311713695526 2023-01-23 16:10:55.963011: step: 2946/1545, loss: 0.04121730476617813 2023-01-23 16:10:56.876587: step: 2948/1545, loss: 0.018375853076577187 2023-01-23 16:10:57.702601: step: 2950/1545, loss: 0.0038192318752408028 2023-01-23 16:10:58.605178: step: 2952/1545, loss: 0.0015387173043563962 2023-01-23 16:10:59.489961: step: 2954/1545, loss: 0.00043253315379843116 2023-01-23 16:11:00.362354: step: 2956/1545, loss: 0.11578765511512756 2023-01-23 16:11:01.267352: step: 2958/1545, loss: 0.002621628576889634 2023-01-23 16:11:02.174758: step: 2960/1545, loss: 0.07187671959400177 2023-01-23 16:11:03.186005: step: 2962/1545, loss: 0.0016858852468430996 2023-01-23 16:11:04.056228: step: 2964/1545, loss: 0.0017097282689064741 2023-01-23 16:11:04.970721: step: 2966/1545, loss: 0.00395676726475358 2023-01-23 16:11:05.842795: step: 2968/1545, loss: 0.025130294263362885 2023-01-23 16:11:06.728842: step: 2970/1545, loss: 0.23946502804756165 2023-01-23 16:11:07.693680: step: 2972/1545, loss: 0.05597580224275589 2023-01-23 16:11:08.553523: step: 2974/1545, loss: 0.0005305380327627063 2023-01-23 16:11:09.443787: step: 2976/1545, loss: 0.3021281063556671 2023-01-23 16:11:10.376921: step: 2978/1545, loss: 0.04419468343257904 2023-01-23 16:11:11.287759: step: 2980/1545, loss: 0.07463443279266357 2023-01-23 16:11:12.177001: step: 2982/1545, loss: 0.0062963045202195644 2023-01-23 16:11:13.048446: step: 2984/1545, loss: 0.0006734943599440157 2023-01-23 16:11:13.919078: step: 2986/1545, loss: 0.00931332167237997 2023-01-23 16:11:14.818293: step: 2988/1545, loss: 0.0005679430905729532 2023-01-23 16:11:15.688181: step: 2990/1545, loss: 0.03986707702279091 2023-01-23 16:11:16.537833: step: 2992/1545, loss: 0.035296935588121414 2023-01-23 16:11:17.383570: step: 2994/1545, loss: 0.003060628892853856 2023-01-23 16:11:18.214777: step: 2996/1545, loss: 0.0004027632821816951 2023-01-23 16:11:19.091673: step: 2998/1545, loss: 0.033797796815633774 2023-01-23 16:11:19.964066: step: 3000/1545, loss: 0.008373895660042763 2023-01-23 16:11:20.829437: step: 3002/1545, loss: 0.09732609987258911 2023-01-23 16:11:21.770835: step: 3004/1545, loss: 0.08082585036754608 2023-01-23 16:11:22.661051: step: 3006/1545, loss: 0.01456636842340231 2023-01-23 16:11:23.552069: step: 3008/1545, loss: 0.0009600709308870137 2023-01-23 16:11:24.493927: step: 3010/1545, loss: 0.0004848774697165936 2023-01-23 16:11:25.365960: step: 3012/1545, loss: 0.0009665380930528045 2023-01-23 16:11:26.242297: step: 3014/1545, loss: 0.05788373202085495 2023-01-23 16:11:27.081617: step: 3016/1545, loss: 0.09880304336547852 2023-01-23 16:11:27.953618: step: 3018/1545, loss: 0.4654127359390259 2023-01-23 16:11:28.835698: step: 3020/1545, loss: 0.001426003989763558 2023-01-23 16:11:29.746822: step: 3022/1545, loss: 0.001724948757328093 2023-01-23 16:11:30.628272: step: 3024/1545, loss: 0.019405148923397064 2023-01-23 16:11:31.513065: step: 3026/1545, loss: 0.10288725793361664 2023-01-23 16:11:32.363133: step: 3028/1545, loss: 0.1683354675769806 2023-01-23 16:11:33.251252: step: 3030/1545, loss: 0.02423073910176754 2023-01-23 16:11:34.127238: step: 3032/1545, loss: 0.0009536194265820086 2023-01-23 16:11:35.018424: step: 3034/1545, loss: 0.01459070760756731 2023-01-23 16:11:35.870558: step: 3036/1545, loss: 0.1766088902950287 2023-01-23 16:11:36.772526: step: 3038/1545, loss: 0.00212712399661541 2023-01-23 16:11:37.674066: step: 3040/1545, loss: 0.009592763148248196 2023-01-23 16:11:38.538125: step: 3042/1545, loss: 0.0015130887040868402 2023-01-23 16:11:39.394485: step: 3044/1545, loss: 0.010608049109578133 2023-01-23 16:11:40.246194: step: 3046/1545, loss: 0.0011717552551999688 2023-01-23 16:11:41.111124: step: 3048/1545, loss: 0.3233560621738434 2023-01-23 16:11:42.007291: step: 3050/1545, loss: 0.001712382072582841 2023-01-23 16:11:42.870726: step: 3052/1545, loss: 0.8609694242477417 2023-01-23 16:11:43.738370: step: 3054/1545, loss: 0.1353464275598526 2023-01-23 16:11:44.622210: step: 3056/1545, loss: 0.0002368948480580002 2023-01-23 16:11:45.449824: step: 3058/1545, loss: 0.002401800826191902 2023-01-23 16:11:46.358658: step: 3060/1545, loss: 0.09978893399238586 2023-01-23 16:11:47.230608: step: 3062/1545, loss: 0.008676127530634403 2023-01-23 16:11:48.071331: step: 3064/1545, loss: 0.01768106408417225 2023-01-23 16:11:49.005787: step: 3066/1545, loss: 0.09934259206056595 2023-01-23 16:11:49.985584: step: 3068/1545, loss: 0.07198278605937958 2023-01-23 16:11:50.878435: step: 3070/1545, loss: 0.18061959743499756 2023-01-23 16:11:51.817005: step: 3072/1545, loss: 0.18753990530967712 2023-01-23 16:11:52.721063: step: 3074/1545, loss: 0.0017089288448914886 2023-01-23 16:11:53.628472: step: 3076/1545, loss: 0.3543034791946411 2023-01-23 16:11:54.551404: step: 3078/1545, loss: 0.011405983939766884 2023-01-23 16:11:55.443727: step: 3080/1545, loss: 0.0006432776572182775 2023-01-23 16:11:56.283311: step: 3082/1545, loss: 0.0008766304235905409 2023-01-23 16:11:57.150744: step: 3084/1545, loss: 0.12337684631347656 2023-01-23 16:11:58.016128: step: 3086/1545, loss: 0.11288657784461975 2023-01-23 16:11:58.870629: step: 3088/1545, loss: 0.05891648307442665 2023-01-23 16:11:59.774676: step: 3090/1545, loss: 0.043314337730407715 ================================================== Loss: 0.083 -------------------- Dev Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6723718371838484, 'r': 0.6638097988077244, 'f1': 0.6680633859090178}, 'combined': 0.4405693791965945, 'epoch': 23} Test Chinese: {'event': {'p': 0.6376734258271078, 'r': 0.7640664961636828, 'f1': 0.6951716114019779}, 'argument': {'p': 0.7092168493286913, 'r': 0.7021788195261929, 'f1': 0.7056802865970946}, 'combined': 0.4905689019683118, 'epoch': 23} Dev Korean: {'event': {'p': 0.6050328227571116, 'r': 0.7363515312916112, 'f1': 0.6642642642642642}, 'argument': {'p': 0.6705292368440877, 'r': 0.6604460904253796, 'f1': 0.6654494698982992}, 'combined': 0.44203430252703835, 'epoch': 23} Test Korean: {'event': {'p': 0.6301587301587301, 'r': 0.7615089514066496, 'f1': 0.6896352055587724}, 'argument': {'p': 0.7054837411912293, 'r': 0.6984720526319892, 'f1': 0.7019603878929249}, 'combined': 0.48409659639865293, 'epoch': 23} Dev Russian: {'event': {'p': 0.5669291338582677, 'r': 0.7669773635153129, 'f1': 0.6519524617996605}, 'argument': {'p': 0.6732697025728679, 'r': 0.6650884409976435, 'f1': 0.669154066131394}, 'combined': 0.43625664073761516, 'epoch': 23} Test Russian: {'event': {'p': 0.6273044344793224, 'r': 0.8049872122762148, 'f1': 0.7051246149537944}, 'argument': {'p': 0.7137762458468431, 'r': 0.7113720593900237, 'f1': 0.7125721247198288}, 'combined': 0.5024521450698765, 'epoch': 23} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6691588785046728, 'r': 0.5917355371900826, 'f1': 0.6280701754385964}, 'combined': 0.43774587985114305, 'epoch': 23} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6718020541549953, 'r': 0.469341161121983, 'f1': 0.552611367127496}, 'combined': 0.3393227692888134, 'epoch': 23} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5526021400184079, 'r': 0.5427342446609363, 'f1': 0.5476237423605844}, 'combined': 0.305005628656528, 'epoch': 23} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 24 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 16:17:19.140070: step: 2/1545, loss: 0.06070634350180626 2023-01-23 16:17:20.048979: step: 4/1545, loss: 1.4722877740859985 2023-01-23 16:17:20.935536: step: 6/1545, loss: 0.0006176177994348109 2023-01-23 16:17:21.798441: step: 8/1545, loss: 0.04971786215901375 2023-01-23 16:17:22.683295: step: 10/1545, loss: 0.007611423265188932 2023-01-23 16:17:23.555023: step: 12/1545, loss: 0.005283595062792301 2023-01-23 16:17:24.430182: step: 14/1545, loss: 0.0013963024830445647 2023-01-23 16:17:25.309564: step: 16/1545, loss: 0.007681415416300297 2023-01-23 16:17:26.182998: step: 18/1545, loss: 0.0038698986172676086 2023-01-23 16:17:27.091237: step: 20/1545, loss: 0.048194341361522675 2023-01-23 16:17:27.971162: step: 22/1545, loss: 0.0014880287926644087 2023-01-23 16:17:28.835866: step: 24/1545, loss: 0.0032486827112734318 2023-01-23 16:17:29.695208: step: 26/1545, loss: 0.010608802549540997 2023-01-23 16:17:30.633886: step: 28/1545, loss: 0.0005019936361350119 2023-01-23 16:17:31.558429: step: 30/1545, loss: 0.21293699741363525 2023-01-23 16:17:32.482441: step: 32/1545, loss: 0.002760112751275301 2023-01-23 16:17:33.390252: step: 34/1545, loss: 0.017394745722413063 2023-01-23 16:17:34.249530: step: 36/1545, loss: 0.00561972800642252 2023-01-23 16:17:35.142974: step: 38/1545, loss: 0.01434758398681879 2023-01-23 16:17:36.037855: step: 40/1545, loss: 0.08297634869813919 2023-01-23 16:17:36.942997: step: 42/1545, loss: 0.061383455991744995 2023-01-23 16:17:37.843124: step: 44/1545, loss: 0.006411070004105568 2023-01-23 16:17:38.771245: step: 46/1545, loss: 0.006929009221494198 2023-01-23 16:17:39.647830: step: 48/1545, loss: 8.380010604858398 2023-01-23 16:17:40.531028: step: 50/1545, loss: 0.001835548784583807 2023-01-23 16:17:41.426181: step: 52/1545, loss: 0.1026550680398941 2023-01-23 16:17:42.362947: step: 54/1545, loss: 0.2788531482219696 2023-01-23 16:17:43.239371: step: 56/1545, loss: 0.23827596008777618 2023-01-23 16:17:44.082904: step: 58/1545, loss: 0.00012434212840162218 2023-01-23 16:17:44.985980: step: 60/1545, loss: 0.33150196075439453 2023-01-23 16:17:45.863516: step: 62/1545, loss: 0.0033475072123110294 2023-01-23 16:17:46.727048: step: 64/1545, loss: 0.606256902217865 2023-01-23 16:17:47.646205: step: 66/1545, loss: 0.08215852081775665 2023-01-23 16:17:48.492079: step: 68/1545, loss: 0.0002841632813215256 2023-01-23 16:17:49.333589: step: 70/1545, loss: 0.0016855765134096146 2023-01-23 16:17:50.197758: step: 72/1545, loss: 0.0030622724443674088 2023-01-23 16:17:51.050898: step: 74/1545, loss: 0.04221632331609726 2023-01-23 16:17:51.944543: step: 76/1545, loss: 0.002787685953080654 2023-01-23 16:17:52.841353: step: 78/1545, loss: 0.0005668596713803709 2023-01-23 16:17:53.710345: step: 80/1545, loss: 0.018597614020109177 2023-01-23 16:17:54.559879: step: 82/1545, loss: 0.008398342877626419 2023-01-23 16:17:55.444128: step: 84/1545, loss: 0.0013893702998757362 2023-01-23 16:17:56.297758: step: 86/1545, loss: 0.0023521152324974537 2023-01-23 16:17:57.225522: step: 88/1545, loss: 0.004119242541491985 2023-01-23 16:17:58.098235: step: 90/1545, loss: 0.004693674389272928 2023-01-23 16:17:58.999921: step: 92/1545, loss: 0.0240822471678257 2023-01-23 16:17:59.870146: step: 94/1545, loss: 0.07639805972576141 2023-01-23 16:18:00.749584: step: 96/1545, loss: 0.034563370048999786 2023-01-23 16:18:01.654450: step: 98/1545, loss: 0.023107457906007767 2023-01-23 16:18:02.560688: step: 100/1545, loss: 0.016609687358140945 2023-01-23 16:18:03.476374: step: 102/1545, loss: 0.03180525824427605 2023-01-23 16:18:04.327066: step: 104/1545, loss: 0.24869172275066376 2023-01-23 16:18:05.257976: step: 106/1545, loss: 0.047453757375478745 2023-01-23 16:18:06.120380: step: 108/1545, loss: 0.006330172531306744 2023-01-23 16:18:06.976455: step: 110/1545, loss: 0.0033494499512016773 2023-01-23 16:18:07.861354: step: 112/1545, loss: 0.028871001675724983 2023-01-23 16:18:08.782750: step: 114/1545, loss: 0.2661469280719757 2023-01-23 16:18:09.669740: step: 116/1545, loss: 0.1429576873779297 2023-01-23 16:18:10.522210: step: 118/1545, loss: 0.022023580968379974 2023-01-23 16:18:11.460775: step: 120/1545, loss: 0.003483104519546032 2023-01-23 16:18:12.363361: step: 122/1545, loss: 0.02767915651202202 2023-01-23 16:18:13.254812: step: 124/1545, loss: 0.0007883179932832718 2023-01-23 16:18:14.135427: step: 126/1545, loss: 0.0018730030860751867 2023-01-23 16:18:15.051341: step: 128/1545, loss: 0.34182336926460266 2023-01-23 16:18:15.923428: step: 130/1545, loss: 0.1447935849428177 2023-01-23 16:18:16.872447: step: 132/1545, loss: 0.14196105301380157 2023-01-23 16:18:17.765427: step: 134/1545, loss: 0.029019208624958992 2023-01-23 16:18:18.664192: step: 136/1545, loss: 0.16571085155010223 2023-01-23 16:18:19.548434: step: 138/1545, loss: 0.00191709422506392 2023-01-23 16:18:20.393061: step: 140/1545, loss: 0.007747429423034191 2023-01-23 16:18:21.279019: step: 142/1545, loss: 0.264710009098053 2023-01-23 16:18:22.146946: step: 144/1545, loss: 0.005411025136709213 2023-01-23 16:18:23.042424: step: 146/1545, loss: 0.054804880172014236 2023-01-23 16:18:23.926331: step: 148/1545, loss: 0.023137303069233894 2023-01-23 16:18:24.805954: step: 150/1545, loss: 0.16907942295074463 2023-01-23 16:18:25.651789: step: 152/1545, loss: 0.0005281365592963994 2023-01-23 16:18:26.501096: step: 154/1545, loss: 0.026453781872987747 2023-01-23 16:18:27.406080: step: 156/1545, loss: 0.0004276395193301141 2023-01-23 16:18:28.350670: step: 158/1545, loss: 0.06192374601960182 2023-01-23 16:18:29.242932: step: 160/1545, loss: 0.008585557341575623 2023-01-23 16:18:30.130766: step: 162/1545, loss: 0.002937093609943986 2023-01-23 16:18:31.038591: step: 164/1545, loss: 0.11265742778778076 2023-01-23 16:18:31.908815: step: 166/1545, loss: 0.04570501670241356 2023-01-23 16:18:32.759978: step: 168/1545, loss: 0.14433914422988892 2023-01-23 16:18:33.642403: step: 170/1545, loss: 0.04075909033417702 2023-01-23 16:18:34.604325: step: 172/1545, loss: 0.004970800131559372 2023-01-23 16:18:35.462487: step: 174/1545, loss: 0.01712307706475258 2023-01-23 16:18:36.330920: step: 176/1545, loss: 0.0005645584315061569 2023-01-23 16:18:37.256198: step: 178/1545, loss: 0.07970640063285828 2023-01-23 16:18:38.152808: step: 180/1545, loss: 0.00029281098977662623 2023-01-23 16:18:39.034643: step: 182/1545, loss: 0.003694913350045681 2023-01-23 16:18:39.903212: step: 184/1545, loss: 0.03479636460542679 2023-01-23 16:18:40.824750: step: 186/1545, loss: 0.00462325057014823 2023-01-23 16:18:41.728033: step: 188/1545, loss: 0.11471772193908691 2023-01-23 16:18:42.633695: step: 190/1545, loss: 0.04642034322023392 2023-01-23 16:18:43.585014: step: 192/1545, loss: 0.00650203600525856 2023-01-23 16:18:44.446712: step: 194/1545, loss: 0.0013355023693293333 2023-01-23 16:18:45.335985: step: 196/1545, loss: 0.006170832086354494 2023-01-23 16:18:46.207691: step: 198/1545, loss: 0.014977464452385902 2023-01-23 16:18:47.104380: step: 200/1545, loss: 0.013059566728770733 2023-01-23 16:18:47.984163: step: 202/1545, loss: 0.0015792108606547117 2023-01-23 16:18:48.835856: step: 204/1545, loss: 0.12086553871631622 2023-01-23 16:18:49.754186: step: 206/1545, loss: 0.03692406788468361 2023-01-23 16:18:50.642739: step: 208/1545, loss: 0.15984880924224854 2023-01-23 16:18:51.544878: step: 210/1545, loss: 0.02263421192765236 2023-01-23 16:18:52.415666: step: 212/1545, loss: 0.0023569900076836348 2023-01-23 16:18:53.294468: step: 214/1545, loss: 0.06150525435805321 2023-01-23 16:18:54.192691: step: 216/1545, loss: 0.013947025872766972 2023-01-23 16:18:55.145065: step: 218/1545, loss: 0.03436433896422386 2023-01-23 16:18:56.034211: step: 220/1545, loss: 0.027898767963051796 2023-01-23 16:18:56.913116: step: 222/1545, loss: 0.000387789768865332 2023-01-23 16:18:57.838694: step: 224/1545, loss: 0.007900108583271503 2023-01-23 16:18:58.695254: step: 226/1545, loss: 0.0036641766782850027 2023-01-23 16:18:59.585801: step: 228/1545, loss: 0.00043889586231671274 2023-01-23 16:19:00.554587: step: 230/1545, loss: 0.06671372801065445 2023-01-23 16:19:01.439066: step: 232/1545, loss: 0.005871221423149109 2023-01-23 16:19:02.329668: step: 234/1545, loss: 0.27012234926223755 2023-01-23 16:19:03.198527: step: 236/1545, loss: 9.642616350902244e-05 2023-01-23 16:19:04.072307: step: 238/1545, loss: 0.008741442114114761 2023-01-23 16:19:04.969081: step: 240/1545, loss: 0.0011542325373739004 2023-01-23 16:19:05.864782: step: 242/1545, loss: 0.0018774125492200255 2023-01-23 16:19:06.730647: step: 244/1545, loss: 0.007535865064710379 2023-01-23 16:19:07.614945: step: 246/1545, loss: 0.6510974168777466 2023-01-23 16:19:08.579519: step: 248/1545, loss: 0.0007244014414027333 2023-01-23 16:19:09.444423: step: 250/1545, loss: 0.00881496723741293 2023-01-23 16:19:10.421326: step: 252/1545, loss: 0.0013575711054727435 2023-01-23 16:19:11.274976: step: 254/1545, loss: 0.0003401563153602183 2023-01-23 16:19:12.158190: step: 256/1545, loss: 0.05604284629225731 2023-01-23 16:19:13.032685: step: 258/1545, loss: 0.20393869280815125 2023-01-23 16:19:13.920569: step: 260/1545, loss: 0.00025267968885600567 2023-01-23 16:19:14.810649: step: 262/1545, loss: 0.0006391283823177218 2023-01-23 16:19:15.677976: step: 264/1545, loss: 0.00024328657309524715 2023-01-23 16:19:16.590301: step: 266/1545, loss: 0.00020557016250677407 2023-01-23 16:19:17.463857: step: 268/1545, loss: 0.0002427033323328942 2023-01-23 16:19:18.346144: step: 270/1545, loss: 0.005228820256888866 2023-01-23 16:19:19.244696: step: 272/1545, loss: 0.007285651750862598 2023-01-23 16:19:20.116326: step: 274/1545, loss: 0.0007499352213926613 2023-01-23 16:19:21.011466: step: 276/1545, loss: 0.02160649001598358 2023-01-23 16:19:21.936384: step: 278/1545, loss: 0.0006944849737919867 2023-01-23 16:19:22.797762: step: 280/1545, loss: 0.012993698939681053 2023-01-23 16:19:23.689235: step: 282/1545, loss: 0.0025468601379543543 2023-01-23 16:19:24.592943: step: 284/1545, loss: 0.11023920029401779 2023-01-23 16:19:25.490083: step: 286/1545, loss: 0.0017685922794044018 2023-01-23 16:19:26.389793: step: 288/1545, loss: 0.0013369608204811811 2023-01-23 16:19:27.219229: step: 290/1545, loss: 0.0446484237909317 2023-01-23 16:19:28.127705: step: 292/1545, loss: 0.00705250957980752 2023-01-23 16:19:28.979131: step: 294/1545, loss: 0.08184057474136353 2023-01-23 16:19:29.905628: step: 296/1545, loss: 0.18736833333969116 2023-01-23 16:19:30.786664: step: 298/1545, loss: 0.2954590618610382 2023-01-23 16:19:31.663863: step: 300/1545, loss: 0.00012129732931498438 2023-01-23 16:19:32.528447: step: 302/1545, loss: 0.21449194848537445 2023-01-23 16:19:33.442889: step: 304/1545, loss: 0.00041853912989608943 2023-01-23 16:19:34.332481: step: 306/1545, loss: 0.0008562305592931807 2023-01-23 16:19:35.298505: step: 308/1545, loss: 0.00014534685760736465 2023-01-23 16:19:36.274273: step: 310/1545, loss: 0.00021200228366069496 2023-01-23 16:19:37.195484: step: 312/1545, loss: 0.13804122805595398 2023-01-23 16:19:38.059468: step: 314/1545, loss: 0.048730913549661636 2023-01-23 16:19:38.895061: step: 316/1545, loss: 0.0005691678379662335 2023-01-23 16:19:39.788750: step: 318/1545, loss: 0.02545282617211342 2023-01-23 16:19:40.685456: step: 320/1545, loss: 0.0006761548575013876 2023-01-23 16:19:41.620830: step: 322/1545, loss: 0.026510991156101227 2023-01-23 16:19:42.463671: step: 324/1545, loss: 0.03115582838654518 2023-01-23 16:19:43.343317: step: 326/1545, loss: 0.05620155110955238 2023-01-23 16:19:44.199458: step: 328/1545, loss: 0.11416161805391312 2023-01-23 16:19:45.061458: step: 330/1545, loss: 0.019843915477395058 2023-01-23 16:19:45.947156: step: 332/1545, loss: 0.35089030861854553 2023-01-23 16:19:46.784868: step: 334/1545, loss: 0.15830457210540771 2023-01-23 16:19:47.726295: step: 336/1545, loss: 0.07831224799156189 2023-01-23 16:19:48.599613: step: 338/1545, loss: 0.02953982539474964 2023-01-23 16:19:49.477720: step: 340/1545, loss: 0.10285896807909012 2023-01-23 16:19:50.349339: step: 342/1545, loss: 0.004575035069137812 2023-01-23 16:19:51.292805: step: 344/1545, loss: 0.08178332448005676 2023-01-23 16:19:52.226769: step: 346/1545, loss: 0.0020530172623693943 2023-01-23 16:19:53.117201: step: 348/1545, loss: 0.3588270843029022 2023-01-23 16:19:53.989122: step: 350/1545, loss: 0.00832503754645586 2023-01-23 16:19:54.865831: step: 352/1545, loss: 0.0040697152726352215 2023-01-23 16:19:55.780013: step: 354/1545, loss: 0.022511737421154976 2023-01-23 16:19:56.678073: step: 356/1545, loss: 0.07631438225507736 2023-01-23 16:19:57.557084: step: 358/1545, loss: 0.004372616298496723 2023-01-23 16:19:58.406906: step: 360/1545, loss: 0.0005499020335264504 2023-01-23 16:19:59.302035: step: 362/1545, loss: 0.32085850834846497 2023-01-23 16:20:00.218690: step: 364/1545, loss: 0.10049225389957428 2023-01-23 16:20:01.126351: step: 366/1545, loss: 0.27300864458084106 2023-01-23 16:20:01.977358: step: 368/1545, loss: 0.0006059120059944689 2023-01-23 16:20:02.844473: step: 370/1545, loss: 0.2066900134086609 2023-01-23 16:20:03.730165: step: 372/1545, loss: 0.006578355096280575 2023-01-23 16:20:04.604533: step: 374/1545, loss: 0.16787029802799225 2023-01-23 16:20:05.536235: step: 376/1545, loss: 0.05012822151184082 2023-01-23 16:20:06.422172: step: 378/1545, loss: 0.0011510776821523905 2023-01-23 16:20:07.365129: step: 380/1545, loss: 0.008081922307610512 2023-01-23 16:20:08.231947: step: 382/1545, loss: 0.036043472588062286 2023-01-23 16:20:09.070235: step: 384/1545, loss: 0.14734825491905212 2023-01-23 16:20:09.924938: step: 386/1545, loss: 0.02605651132762432 2023-01-23 16:20:10.814495: step: 388/1545, loss: 0.0001319437869824469 2023-01-23 16:20:11.665337: step: 390/1545, loss: 0.010861432179808617 2023-01-23 16:20:12.501328: step: 392/1545, loss: 0.017643967643380165 2023-01-23 16:20:13.527175: step: 394/1545, loss: 0.016130972653627396 2023-01-23 16:20:14.429200: step: 396/1545, loss: 0.20360277593135834 2023-01-23 16:20:15.305803: step: 398/1545, loss: 0.0007213570061139762 2023-01-23 16:20:16.232980: step: 400/1545, loss: 0.0029587054159492254 2023-01-23 16:20:17.111862: step: 402/1545, loss: 0.00043313667993061244 2023-01-23 16:20:17.987868: step: 404/1545, loss: 0.036613207310438156 2023-01-23 16:20:18.882068: step: 406/1545, loss: 0.0012379438849166036 2023-01-23 16:20:19.812347: step: 408/1545, loss: 0.10173173248767853 2023-01-23 16:20:20.685978: step: 410/1545, loss: 0.20242327451705933 2023-01-23 16:20:21.523501: step: 412/1545, loss: 0.061115898191928864 2023-01-23 16:20:22.373226: step: 414/1545, loss: 0.02932908572256565 2023-01-23 16:20:23.249697: step: 416/1545, loss: 0.006521934177726507 2023-01-23 16:20:24.174448: step: 418/1545, loss: 0.019840387627482414 2023-01-23 16:20:25.075044: step: 420/1545, loss: 0.02703624591231346 2023-01-23 16:20:25.920108: step: 422/1545, loss: 0.02182907424867153 2023-01-23 16:20:26.828796: step: 424/1545, loss: 0.012724857777357101 2023-01-23 16:20:27.687220: step: 426/1545, loss: 0.1446727067232132 2023-01-23 16:20:28.576869: step: 428/1545, loss: 0.004793030209839344 2023-01-23 16:20:29.459631: step: 430/1545, loss: 0.011030226945877075 2023-01-23 16:20:30.334604: step: 432/1545, loss: 0.006384679116308689 2023-01-23 16:20:31.216418: step: 434/1545, loss: 0.00432561757043004 2023-01-23 16:20:32.085205: step: 436/1545, loss: 0.008473796769976616 2023-01-23 16:20:32.958582: step: 438/1545, loss: 0.006670081056654453 2023-01-23 16:20:33.792750: step: 440/1545, loss: 0.14654938876628876 2023-01-23 16:20:34.643443: step: 442/1545, loss: 0.3660026788711548 2023-01-23 16:20:35.527093: step: 444/1545, loss: 0.002394333016127348 2023-01-23 16:20:36.381494: step: 446/1545, loss: 0.3243646025657654 2023-01-23 16:20:37.253169: step: 448/1545, loss: 0.007259376812726259 2023-01-23 16:20:38.151905: step: 450/1545, loss: 0.0009031223598867655 2023-01-23 16:20:39.011521: step: 452/1545, loss: 0.027095837518572807 2023-01-23 16:20:39.933747: step: 454/1545, loss: 0.0011363569647073746 2023-01-23 16:20:40.833320: step: 456/1545, loss: 0.002374432748183608 2023-01-23 16:20:41.728853: step: 458/1545, loss: 0.001785541302524507 2023-01-23 16:20:42.583462: step: 460/1545, loss: 0.08641340583562851 2023-01-23 16:20:43.469958: step: 462/1545, loss: 0.01917213574051857 2023-01-23 16:20:44.350756: step: 464/1545, loss: 0.029667846858501434 2023-01-23 16:20:45.236946: step: 466/1545, loss: 0.24436886608600616 2023-01-23 16:20:46.097871: step: 468/1545, loss: 0.002724018879234791 2023-01-23 16:20:46.894000: step: 470/1545, loss: 0.0010261617135256529 2023-01-23 16:20:47.780974: step: 472/1545, loss: 0.2638440728187561 2023-01-23 16:20:48.682054: step: 474/1545, loss: 0.10825084894895554 2023-01-23 16:20:49.529423: step: 476/1545, loss: 0.01355237327516079 2023-01-23 16:20:50.389044: step: 478/1545, loss: 0.002712355926632881 2023-01-23 16:20:51.242952: step: 480/1545, loss: 0.0069680651649832726 2023-01-23 16:20:52.149427: step: 482/1545, loss: 0.012713761068880558 2023-01-23 16:20:52.999673: step: 484/1545, loss: 0.01980849914252758 2023-01-23 16:20:53.896973: step: 486/1545, loss: 0.0004918886115774512 2023-01-23 16:20:54.775024: step: 488/1545, loss: 0.037626609206199646 2023-01-23 16:20:55.614268: step: 490/1545, loss: 0.02015194296836853 2023-01-23 16:20:56.558550: step: 492/1545, loss: 0.006783461198210716 2023-01-23 16:20:57.428725: step: 494/1545, loss: 0.01570890098810196 2023-01-23 16:20:58.297703: step: 496/1545, loss: 0.001508583314716816 2023-01-23 16:20:59.218919: step: 498/1545, loss: 0.01935209520161152 2023-01-23 16:21:00.106306: step: 500/1545, loss: 0.006985929328948259 2023-01-23 16:21:01.037117: step: 502/1545, loss: 0.0018599454779177904 2023-01-23 16:21:01.921894: step: 504/1545, loss: 0.0003501122409943491 2023-01-23 16:21:02.814419: step: 506/1545, loss: 0.028787173330783844 2023-01-23 16:21:03.715958: step: 508/1545, loss: 0.008905821479856968 2023-01-23 16:21:04.600467: step: 510/1545, loss: 0.2843724191188812 2023-01-23 16:21:05.494593: step: 512/1545, loss: 0.0016984809190034866 2023-01-23 16:21:06.364550: step: 514/1545, loss: 0.16072317957878113 2023-01-23 16:21:07.252525: step: 516/1545, loss: 0.08759105205535889 2023-01-23 16:21:08.121677: step: 518/1545, loss: 0.00014843550161458552 2023-01-23 16:21:08.983283: step: 520/1545, loss: 0.08713437616825104 2023-01-23 16:21:09.865940: step: 522/1545, loss: 0.0014227261999621987 2023-01-23 16:21:10.802422: step: 524/1545, loss: 0.012943334877490997 2023-01-23 16:21:11.657407: step: 526/1545, loss: 2.0320936528150924e-05 2023-01-23 16:21:12.531529: step: 528/1545, loss: 0.00011781220382545143 2023-01-23 16:21:13.412971: step: 530/1545, loss: 0.0014855049084872007 2023-01-23 16:21:14.278248: step: 532/1545, loss: 0.014651093631982803 2023-01-23 16:21:15.184034: step: 534/1545, loss: 0.0566350594162941 2023-01-23 16:21:15.990307: step: 536/1545, loss: 0.0007738307467661798 2023-01-23 16:21:16.841430: step: 538/1545, loss: 0.0021320651285350323 2023-01-23 16:21:17.699594: step: 540/1545, loss: 0.050447363406419754 2023-01-23 16:21:18.561051: step: 542/1545, loss: 0.0014505564467981458 2023-01-23 16:21:19.491226: step: 544/1545, loss: 0.02412237972021103 2023-01-23 16:21:20.333601: step: 546/1545, loss: 0.0006779509712941945 2023-01-23 16:21:21.273184: step: 548/1545, loss: 0.01116169523447752 2023-01-23 16:21:22.165470: step: 550/1545, loss: 0.03491368144750595 2023-01-23 16:21:23.065072: step: 552/1545, loss: 0.015984825789928436 2023-01-23 16:21:23.929705: step: 554/1545, loss: 0.007837481796741486 2023-01-23 16:21:24.777867: step: 556/1545, loss: 0.6690804362297058 2023-01-23 16:21:25.667702: step: 558/1545, loss: 0.029261348769068718 2023-01-23 16:21:26.568005: step: 560/1545, loss: 0.3182608485221863 2023-01-23 16:21:27.456367: step: 562/1545, loss: 0.0030025651212781668 2023-01-23 16:21:28.321013: step: 564/1545, loss: 0.0013892082497477531 2023-01-23 16:21:29.330516: step: 566/1545, loss: 0.0017641490558162332 2023-01-23 16:21:30.215484: step: 568/1545, loss: 0.005917024333029985 2023-01-23 16:21:31.083459: step: 570/1545, loss: 0.13221262395381927 2023-01-23 16:21:31.956344: step: 572/1545, loss: 0.0015763911651447415 2023-01-23 16:21:32.862664: step: 574/1545, loss: 0.00011197565618203953 2023-01-23 16:21:33.778331: step: 576/1545, loss: 0.003911332227289677 2023-01-23 16:21:34.668038: step: 578/1545, loss: 0.2221628576517105 2023-01-23 16:21:35.550634: step: 580/1545, loss: 0.26814955472946167 2023-01-23 16:21:36.426443: step: 582/1545, loss: 0.007752855308353901 2023-01-23 16:21:37.296647: step: 584/1545, loss: 0.2129485160112381 2023-01-23 16:21:38.126157: step: 586/1545, loss: 0.0001313069515163079 2023-01-23 16:21:39.020669: step: 588/1545, loss: 0.056545596569776535 2023-01-23 16:21:39.907345: step: 590/1545, loss: 0.07947912812232971 2023-01-23 16:21:40.829909: step: 592/1545, loss: 0.0026593958027660847 2023-01-23 16:21:41.695413: step: 594/1545, loss: 0.14829498529434204 2023-01-23 16:21:42.590362: step: 596/1545, loss: 0.11326033622026443 2023-01-23 16:21:43.445978: step: 598/1545, loss: 0.0030537559650838375 2023-01-23 16:21:44.277413: step: 600/1545, loss: 0.02500573918223381 2023-01-23 16:21:45.178841: step: 602/1545, loss: 0.035986896604299545 2023-01-23 16:21:46.078851: step: 604/1545, loss: 0.317040354013443 2023-01-23 16:21:47.053820: step: 606/1545, loss: 0.00023645037435926497 2023-01-23 16:21:47.936074: step: 608/1545, loss: 0.00794812012463808 2023-01-23 16:21:48.817703: step: 610/1545, loss: 0.001431246055290103 2023-01-23 16:21:49.758680: step: 612/1545, loss: 0.0009602622012607753 2023-01-23 16:21:50.622851: step: 614/1545, loss: 0.005084413103759289 2023-01-23 16:21:51.495873: step: 616/1545, loss: 0.0006171840941533446 2023-01-23 16:21:52.393408: step: 618/1545, loss: 0.03701568767428398 2023-01-23 16:21:53.250877: step: 620/1545, loss: 0.17588713765144348 2023-01-23 16:21:54.228446: step: 622/1545, loss: 0.10961926728487015 2023-01-23 16:21:55.106592: step: 624/1545, loss: 0.08381005376577377 2023-01-23 16:21:55.974456: step: 626/1545, loss: 0.004742438904941082 2023-01-23 16:21:56.870884: step: 628/1545, loss: 0.14594265818595886 2023-01-23 16:21:57.733734: step: 630/1545, loss: 0.03558843582868576 2023-01-23 16:21:58.657187: step: 632/1545, loss: 0.002607142087072134 2023-01-23 16:21:59.516545: step: 634/1545, loss: 0.00183353410102427 2023-01-23 16:22:00.423108: step: 636/1545, loss: 0.044965021312236786 2023-01-23 16:22:01.290209: step: 638/1545, loss: 0.0005222991458140314 2023-01-23 16:22:02.161135: step: 640/1545, loss: 0.2952720820903778 2023-01-23 16:22:03.017509: step: 642/1545, loss: 0.07381889969110489 2023-01-23 16:22:03.933816: step: 644/1545, loss: 0.06305914372205734 2023-01-23 16:22:04.830561: step: 646/1545, loss: 0.25011834502220154 2023-01-23 16:22:05.692320: step: 648/1545, loss: 0.0010175961069762707 2023-01-23 16:22:06.553650: step: 650/1545, loss: 0.02681497298181057 2023-01-23 16:22:07.424159: step: 652/1545, loss: 0.005751045420765877 2023-01-23 16:22:08.326279: step: 654/1545, loss: 0.039495524019002914 2023-01-23 16:22:09.196746: step: 656/1545, loss: 0.11847251653671265 2023-01-23 16:22:10.137193: step: 658/1545, loss: 0.03274691104888916 2023-01-23 16:22:11.035365: step: 660/1545, loss: 0.5675384402275085 2023-01-23 16:22:11.927129: step: 662/1545, loss: 0.27105557918548584 2023-01-23 16:22:12.773623: step: 664/1545, loss: 0.004764281213283539 2023-01-23 16:22:13.636757: step: 666/1545, loss: 0.41029176115989685 2023-01-23 16:22:14.642739: step: 668/1545, loss: 0.07891646027565002 2023-01-23 16:22:15.551683: step: 670/1545, loss: 0.09400425106287003 2023-01-23 16:22:16.419040: step: 672/1545, loss: 0.052107714116573334 2023-01-23 16:22:17.283400: step: 674/1545, loss: 0.001988880569115281 2023-01-23 16:22:18.170759: step: 676/1545, loss: 0.1161259189248085 2023-01-23 16:22:19.056226: step: 678/1545, loss: 0.11596813797950745 2023-01-23 16:22:19.958499: step: 680/1545, loss: 0.02550858072936535 2023-01-23 16:22:20.797536: step: 682/1545, loss: 0.08938047289848328 2023-01-23 16:22:21.709091: step: 684/1545, loss: 0.08340183645486832 2023-01-23 16:22:22.605100: step: 686/1545, loss: 0.049409057945013046 2023-01-23 16:22:23.511305: step: 688/1545, loss: 0.3180783689022064 2023-01-23 16:22:24.423095: step: 690/1545, loss: 0.0021371692419052124 2023-01-23 16:22:25.271233: step: 692/1545, loss: 0.03327138349413872 2023-01-23 16:22:26.159674: step: 694/1545, loss: 0.00535995326936245 2023-01-23 16:22:27.086029: step: 696/1545, loss: 0.08860891312360764 2023-01-23 16:22:27.992041: step: 698/1545, loss: 0.09834827482700348 2023-01-23 16:22:28.888949: step: 700/1545, loss: 0.07185360789299011 2023-01-23 16:22:29.794047: step: 702/1545, loss: 0.011307284235954285 2023-01-23 16:22:30.728980: step: 704/1545, loss: 0.0523403026163578 2023-01-23 16:22:31.548760: step: 706/1545, loss: 0.012533286586403847 2023-01-23 16:22:32.431403: step: 708/1545, loss: 0.028544273227453232 2023-01-23 16:22:33.347024: step: 710/1545, loss: 0.05462275817990303 2023-01-23 16:22:34.230768: step: 712/1545, loss: 0.09951487183570862 2023-01-23 16:22:35.100951: step: 714/1545, loss: 0.04626632109284401 2023-01-23 16:22:35.971796: step: 716/1545, loss: 0.0003368171164765954 2023-01-23 16:22:36.844109: step: 718/1545, loss: 0.003167115617543459 2023-01-23 16:22:37.729092: step: 720/1545, loss: 0.10337711125612259 2023-01-23 16:22:38.611367: step: 722/1545, loss: 0.005694372113794088 2023-01-23 16:22:39.483706: step: 724/1545, loss: 0.12242448329925537 2023-01-23 16:22:40.451839: step: 726/1545, loss: 0.0008798816124908626 2023-01-23 16:22:41.389863: step: 728/1545, loss: 0.012155418284237385 2023-01-23 16:22:42.266484: step: 730/1545, loss: 0.27779054641723633 2023-01-23 16:22:43.135462: step: 732/1545, loss: 0.0027020350098609924 2023-01-23 16:22:43.998221: step: 734/1545, loss: 0.002446712227538228 2023-01-23 16:22:44.920527: step: 736/1545, loss: 0.07724781334400177 2023-01-23 16:22:45.831534: step: 738/1545, loss: 0.0014772310387343168 2023-01-23 16:22:46.721375: step: 740/1545, loss: 0.007904120720922947 2023-01-23 16:22:47.646337: step: 742/1545, loss: 0.0020215034019201994 2023-01-23 16:22:48.473580: step: 744/1545, loss: 0.018344677984714508 2023-01-23 16:22:49.310709: step: 746/1545, loss: 0.03716056048870087 2023-01-23 16:22:50.208463: step: 748/1545, loss: 0.017284095287322998 2023-01-23 16:22:51.079750: step: 750/1545, loss: 0.03327978774905205 2023-01-23 16:22:51.943782: step: 752/1545, loss: 0.006500025279819965 2023-01-23 16:22:52.841620: step: 754/1545, loss: 0.2551373839378357 2023-01-23 16:22:53.711426: step: 756/1545, loss: 0.07776607573032379 2023-01-23 16:22:54.581396: step: 758/1545, loss: 0.0019985600374639034 2023-01-23 16:22:55.448881: step: 760/1545, loss: 0.017080018296837807 2023-01-23 16:22:56.335590: step: 762/1545, loss: 0.00039675264270044863 2023-01-23 16:22:57.212607: step: 764/1545, loss: 0.0021918537095189095 2023-01-23 16:22:58.108668: step: 766/1545, loss: 0.17712728679180145 2023-01-23 16:22:59.007090: step: 768/1545, loss: 0.3574714958667755 2023-01-23 16:22:59.850129: step: 770/1545, loss: 0.0016281931893900037 2023-01-23 16:23:00.731389: step: 772/1545, loss: 0.08768826723098755 2023-01-23 16:23:01.597525: step: 774/1545, loss: 0.0007597459480166435 2023-01-23 16:23:02.459842: step: 776/1545, loss: 8.179549695341848e-06 2023-01-23 16:23:03.303277: step: 778/1545, loss: 0.005379968322813511 2023-01-23 16:23:04.191002: step: 780/1545, loss: 0.0022797146812081337 2023-01-23 16:23:05.121525: step: 782/1545, loss: 0.0013319363351911306 2023-01-23 16:23:05.984965: step: 784/1545, loss: 0.017179183661937714 2023-01-23 16:23:06.859954: step: 786/1545, loss: 0.03263147175312042 2023-01-23 16:23:07.717242: step: 788/1545, loss: 0.0007612130721099675 2023-01-23 16:23:08.594240: step: 790/1545, loss: 0.012499862350523472 2023-01-23 16:23:09.477311: step: 792/1545, loss: 0.0001199903927044943 2023-01-23 16:23:10.312343: step: 794/1545, loss: 0.02425588294863701 2023-01-23 16:23:11.230635: step: 796/1545, loss: 0.015188658609986305 2023-01-23 16:23:12.076875: step: 798/1545, loss: 0.3188672661781311 2023-01-23 16:23:12.946252: step: 800/1545, loss: 0.24845652282238007 2023-01-23 16:23:13.792093: step: 802/1545, loss: 0.0038597919046878815 2023-01-23 16:23:14.668894: step: 804/1545, loss: 0.0710877999663353 2023-01-23 16:23:15.546502: step: 806/1545, loss: 0.0002715094306040555 2023-01-23 16:23:16.454761: step: 808/1545, loss: 0.7280932068824768 2023-01-23 16:23:17.364577: step: 810/1545, loss: 0.016009964048862457 2023-01-23 16:23:18.252966: step: 812/1545, loss: 0.0060951923951506615 2023-01-23 16:23:19.240861: step: 814/1545, loss: 0.10546497255563736 2023-01-23 16:23:20.105575: step: 816/1545, loss: 0.48859432339668274 2023-01-23 16:23:20.990660: step: 818/1545, loss: 0.02018779329955578 2023-01-23 16:23:21.875194: step: 820/1545, loss: 0.0055712005123496056 2023-01-23 16:23:22.755478: step: 822/1545, loss: 0.00766339898109436 2023-01-23 16:23:23.650237: step: 824/1545, loss: 0.0008347530965693295 2023-01-23 16:23:24.521671: step: 826/1545, loss: 0.00023189884086605161 2023-01-23 16:23:25.369473: step: 828/1545, loss: 0.0007646773592568934 2023-01-23 16:23:26.234149: step: 830/1545, loss: 0.0706152468919754 2023-01-23 16:23:27.129281: step: 832/1545, loss: 0.0044578914530575275 2023-01-23 16:23:27.980345: step: 834/1545, loss: 0.00011459607048891485 2023-01-23 16:23:28.831171: step: 836/1545, loss: 0.2312309294939041 2023-01-23 16:23:29.733608: step: 838/1545, loss: 0.0002576579572632909 2023-01-23 16:23:30.608337: step: 840/1545, loss: 0.004320504609495401 2023-01-23 16:23:31.469874: step: 842/1545, loss: 0.001879091840237379 2023-01-23 16:23:32.316174: step: 844/1545, loss: 9.57305746851489e-05 2023-01-23 16:23:33.152295: step: 846/1545, loss: 1.8847768306732178 2023-01-23 16:23:34.045628: step: 848/1545, loss: 0.002258028369396925 2023-01-23 16:23:34.903147: step: 850/1545, loss: 0.031022652983665466 2023-01-23 16:23:35.788414: step: 852/1545, loss: 0.0945851057767868 2023-01-23 16:23:36.692534: step: 854/1545, loss: 0.00040923786582425237 2023-01-23 16:23:37.558411: step: 856/1545, loss: 0.004795662127435207 2023-01-23 16:23:38.435476: step: 858/1545, loss: 0.18820740282535553 2023-01-23 16:23:39.321723: step: 860/1545, loss: 0.3908534049987793 2023-01-23 16:23:40.253487: step: 862/1545, loss: 0.4004739820957184 2023-01-23 16:23:41.153016: step: 864/1545, loss: 0.01445918157696724 2023-01-23 16:23:42.004619: step: 866/1545, loss: 0.0630272701382637 2023-01-23 16:23:42.899743: step: 868/1545, loss: 0.02294641174376011 2023-01-23 16:23:43.767853: step: 870/1545, loss: 0.21335090696811676 2023-01-23 16:23:44.684446: step: 872/1545, loss: 0.032565053552389145 2023-01-23 16:23:45.561546: step: 874/1545, loss: 0.0012895510299131274 2023-01-23 16:23:46.443067: step: 876/1545, loss: 0.10376594960689545 2023-01-23 16:23:47.344617: step: 878/1545, loss: 0.007111756596714258 2023-01-23 16:23:48.210504: step: 880/1545, loss: 0.0014468866866081953 2023-01-23 16:23:49.092650: step: 882/1545, loss: 0.053175102919340134 2023-01-23 16:23:49.964060: step: 884/1545, loss: 0.002644554479047656 2023-01-23 16:23:50.823861: step: 886/1545, loss: 0.00010204999125562608 2023-01-23 16:23:51.817892: step: 888/1545, loss: 0.0006806682795286179 2023-01-23 16:23:52.678766: step: 890/1545, loss: 0.03385872766375542 2023-01-23 16:23:53.555972: step: 892/1545, loss: 0.0006584686925634742 2023-01-23 16:23:54.395991: step: 894/1545, loss: 0.004930238705128431 2023-01-23 16:23:55.310128: step: 896/1545, loss: 0.14752936363220215 2023-01-23 16:23:56.185875: step: 898/1545, loss: 0.014482860453426838 2023-01-23 16:23:57.034723: step: 900/1545, loss: 0.27195802330970764 2023-01-23 16:23:57.887824: step: 902/1545, loss: 0.005459887441247702 2023-01-23 16:23:58.792809: step: 904/1545, loss: 0.010244945995509624 2023-01-23 16:23:59.657492: step: 906/1545, loss: 0.34187740087509155 2023-01-23 16:24:00.553732: step: 908/1545, loss: 0.11757045239210129 2023-01-23 16:24:01.424494: step: 910/1545, loss: 0.005256394390016794 2023-01-23 16:24:02.295475: step: 912/1545, loss: 0.001910498016513884 2023-01-23 16:24:03.191601: step: 914/1545, loss: 0.05574868619441986 2023-01-23 16:24:04.068751: step: 916/1545, loss: 0.023898372426629066 2023-01-23 16:24:05.020475: step: 918/1545, loss: 0.010076974518597126 2023-01-23 16:24:05.906684: step: 920/1545, loss: 0.0012232856824994087 2023-01-23 16:24:06.773840: step: 922/1545, loss: 0.0026096603833138943 2023-01-23 16:24:07.675202: step: 924/1545, loss: 0.0065089864656329155 2023-01-23 16:24:08.519739: step: 926/1545, loss: 0.0606725811958313 2023-01-23 16:24:09.363847: step: 928/1545, loss: 0.002248742850497365 2023-01-23 16:24:10.211366: step: 930/1545, loss: 0.13689516484737396 2023-01-23 16:24:11.095996: step: 932/1545, loss: 0.0017417214112356305 2023-01-23 16:24:11.980579: step: 934/1545, loss: 0.01178329810500145 2023-01-23 16:24:12.885058: step: 936/1545, loss: 0.05504278838634491 2023-01-23 16:24:13.720487: step: 938/1545, loss: 0.0007538119098171592 2023-01-23 16:24:14.581126: step: 940/1545, loss: 0.04747158661484718 2023-01-23 16:24:15.465770: step: 942/1545, loss: 0.05770011246204376 2023-01-23 16:24:16.378965: step: 944/1545, loss: 0.01605665124952793 2023-01-23 16:24:17.291329: step: 946/1545, loss: 0.18198220431804657 2023-01-23 16:24:18.123432: step: 948/1545, loss: 0.001863860059529543 2023-01-23 16:24:19.030914: step: 950/1545, loss: 0.023318717256188393 2023-01-23 16:24:19.929588: step: 952/1545, loss: 0.0008675054414197803 2023-01-23 16:24:20.804747: step: 954/1545, loss: 0.1682337075471878 2023-01-23 16:24:21.691266: step: 956/1545, loss: 0.29833555221557617 2023-01-23 16:24:22.583916: step: 958/1545, loss: 0.004965304397046566 2023-01-23 16:24:23.435245: step: 960/1545, loss: 0.02013467438519001 2023-01-23 16:24:24.332986: step: 962/1545, loss: 0.027951782569289207 2023-01-23 16:24:25.204228: step: 964/1545, loss: 0.0008291825070045888 2023-01-23 16:24:26.101059: step: 966/1545, loss: 0.0029380801133811474 2023-01-23 16:24:26.982490: step: 968/1545, loss: 1.464938759803772 2023-01-23 16:24:27.866966: step: 970/1545, loss: 0.0005885405698791146 2023-01-23 16:24:28.740534: step: 972/1545, loss: 0.0012922249734401703 2023-01-23 16:24:29.625582: step: 974/1545, loss: 0.006145316641777754 2023-01-23 16:24:30.500666: step: 976/1545, loss: 0.0019322314765304327 2023-01-23 16:24:31.475098: step: 978/1545, loss: 0.047418732196092606 2023-01-23 16:24:32.396084: step: 980/1545, loss: 0.0112879928201437 2023-01-23 16:24:33.306793: step: 982/1545, loss: 0.0012516423594206572 2023-01-23 16:24:34.196616: step: 984/1545, loss: 0.012319565750658512 2023-01-23 16:24:35.062265: step: 986/1545, loss: 0.0018376798834651709 2023-01-23 16:24:35.978606: step: 988/1545, loss: 0.03908972069621086 2023-01-23 16:24:36.857176: step: 990/1545, loss: 0.001155732898041606 2023-01-23 16:24:37.766562: step: 992/1545, loss: 0.0044143847189843655 2023-01-23 16:24:38.651993: step: 994/1545, loss: 0.01159056555479765 2023-01-23 16:24:39.563679: step: 996/1545, loss: 0.0012907878262922168 2023-01-23 16:24:40.415064: step: 998/1545, loss: 0.0009889734210446477 2023-01-23 16:24:41.284480: step: 1000/1545, loss: 0.00032456283224746585 2023-01-23 16:24:42.143258: step: 1002/1545, loss: 0.027121251448988914 2023-01-23 16:24:43.082418: step: 1004/1545, loss: 0.021997306495904922 2023-01-23 16:24:44.003834: step: 1006/1545, loss: 0.4945901930332184 2023-01-23 16:24:44.895228: step: 1008/1545, loss: 0.002158750779926777 2023-01-23 16:24:45.788145: step: 1010/1545, loss: 0.10544785112142563 2023-01-23 16:24:46.664299: step: 1012/1545, loss: 0.04082735627889633 2023-01-23 16:24:47.524207: step: 1014/1545, loss: 0.0010214330395683646 2023-01-23 16:24:48.399655: step: 1016/1545, loss: 0.08741206675767899 2023-01-23 16:24:49.282129: step: 1018/1545, loss: 0.0008355123572982848 2023-01-23 16:24:50.209444: step: 1020/1545, loss: 0.0007432708516716957 2023-01-23 16:24:51.160686: step: 1022/1545, loss: 0.06314018368721008 2023-01-23 16:24:52.002826: step: 1024/1545, loss: 0.010737361386418343 2023-01-23 16:24:52.884637: step: 1026/1545, loss: 0.0015807405579835176 2023-01-23 16:24:53.814614: step: 1028/1545, loss: 0.15022583305835724 2023-01-23 16:24:54.655197: step: 1030/1545, loss: 0.2347726672887802 2023-01-23 16:24:55.486659: step: 1032/1545, loss: 0.0017894507618620992 2023-01-23 16:24:56.406609: step: 1034/1545, loss: 3.3583528420422226e-05 2023-01-23 16:24:57.240062: step: 1036/1545, loss: 5.501979831024073e-05 2023-01-23 16:24:58.103737: step: 1038/1545, loss: 0.02025373838841915 2023-01-23 16:24:58.978243: step: 1040/1545, loss: 0.07179374247789383 2023-01-23 16:24:59.910231: step: 1042/1545, loss: 0.04638369008898735 2023-01-23 16:25:00.827938: step: 1044/1545, loss: 0.00024659314658492804 2023-01-23 16:25:01.713702: step: 1046/1545, loss: 0.03225391358137131 2023-01-23 16:25:02.566081: step: 1048/1545, loss: 0.0007459248299710453 2023-01-23 16:25:03.488192: step: 1050/1545, loss: 0.0012810317566618323 2023-01-23 16:25:04.355257: step: 1052/1545, loss: 0.004581408109515905 2023-01-23 16:25:05.211756: step: 1054/1545, loss: 0.006706024054437876 2023-01-23 16:25:06.095501: step: 1056/1545, loss: 0.07563742250204086 2023-01-23 16:25:06.977982: step: 1058/1545, loss: 0.0003142570494674146 2023-01-23 16:25:07.861945: step: 1060/1545, loss: 0.02483377605676651 2023-01-23 16:25:08.734663: step: 1062/1545, loss: 0.09558998048305511 2023-01-23 16:25:09.678067: step: 1064/1545, loss: 0.005363183096051216 2023-01-23 16:25:10.688177: step: 1066/1545, loss: 0.004147122148424387 2023-01-23 16:25:11.555799: step: 1068/1545, loss: 0.0050295377150177956 2023-01-23 16:25:12.432055: step: 1070/1545, loss: 0.0033764203544706106 2023-01-23 16:25:13.321695: step: 1072/1545, loss: 0.18470704555511475 2023-01-23 16:25:14.189332: step: 1074/1545, loss: 0.031068256124854088 2023-01-23 16:25:15.021254: step: 1076/1545, loss: 0.003980688285082579 2023-01-23 16:25:15.903512: step: 1078/1545, loss: 0.15127140283584595 2023-01-23 16:25:16.815644: step: 1080/1545, loss: 0.03745286539196968 2023-01-23 16:25:17.693140: step: 1082/1545, loss: 0.0007000326295383275 2023-01-23 16:25:18.532222: step: 1084/1545, loss: 0.020313207060098648 2023-01-23 16:25:19.433927: step: 1086/1545, loss: 0.17247362434864044 2023-01-23 16:25:20.311742: step: 1088/1545, loss: 0.02548718824982643 2023-01-23 16:25:21.164926: step: 1090/1545, loss: 0.003362425370141864 2023-01-23 16:25:22.021530: step: 1092/1545, loss: 0.0010435257572680712 2023-01-23 16:25:22.883647: step: 1094/1545, loss: 0.03806522116065025 2023-01-23 16:25:23.736462: step: 1096/1545, loss: 0.0017090474721044302 2023-01-23 16:25:24.610621: step: 1098/1545, loss: 0.0007104318356141448 2023-01-23 16:25:25.507086: step: 1100/1545, loss: 0.0627535805106163 2023-01-23 16:25:26.361797: step: 1102/1545, loss: 0.0003221151710022241 2023-01-23 16:25:27.240207: step: 1104/1545, loss: 0.0291849784553051 2023-01-23 16:25:28.067417: step: 1106/1545, loss: 0.00016522445366717875 2023-01-23 16:25:28.959984: step: 1108/1545, loss: 0.17749474942684174 2023-01-23 16:25:29.825221: step: 1110/1545, loss: 0.00012336717918515205 2023-01-23 16:25:30.801406: step: 1112/1545, loss: 0.00011318465112708509 2023-01-23 16:25:31.668278: step: 1114/1545, loss: 0.13269318640232086 2023-01-23 16:25:32.575025: step: 1116/1545, loss: 0.0004835161380469799 2023-01-23 16:25:33.472546: step: 1118/1545, loss: 3.346068842802197e-05 2023-01-23 16:25:34.322317: step: 1120/1545, loss: 0.004355370998382568 2023-01-23 16:25:35.192822: step: 1122/1545, loss: 0.0001508259738329798 2023-01-23 16:25:36.088577: step: 1124/1545, loss: 0.0653037279844284 2023-01-23 16:25:36.965380: step: 1126/1545, loss: 0.2118915319442749 2023-01-23 16:25:37.839485: step: 1128/1545, loss: 0.0005413871258497238 2023-01-23 16:25:38.759344: step: 1130/1545, loss: 0.5198420882225037 2023-01-23 16:25:39.621146: step: 1132/1545, loss: 0.037195850163698196 2023-01-23 16:25:40.570677: step: 1134/1545, loss: 0.020060570910573006 2023-01-23 16:25:41.463234: step: 1136/1545, loss: 0.0036679424811154604 2023-01-23 16:25:42.318994: step: 1138/1545, loss: 0.001947917859070003 2023-01-23 16:25:43.187109: step: 1140/1545, loss: 0.0646812841296196 2023-01-23 16:25:44.035242: step: 1142/1545, loss: 0.0007838922902010381 2023-01-23 16:25:44.913732: step: 1144/1545, loss: 0.008654984645545483 2023-01-23 16:25:45.797536: step: 1146/1545, loss: 0.00022065042867325246 2023-01-23 16:25:46.707872: step: 1148/1545, loss: 0.0026442918460816145 2023-01-23 16:25:47.678290: step: 1150/1545, loss: 1.9471166133880615 2023-01-23 16:25:48.633131: step: 1152/1545, loss: 0.0039987280033528805 2023-01-23 16:25:49.469345: step: 1154/1545, loss: 0.028040366247296333 2023-01-23 16:25:50.365982: step: 1156/1545, loss: 0.023985857143998146 2023-01-23 16:25:51.236102: step: 1158/1545, loss: 0.13483460247516632 2023-01-23 16:25:52.087935: step: 1160/1545, loss: 0.056116506457328796 2023-01-23 16:25:52.959292: step: 1162/1545, loss: 0.06321060657501221 2023-01-23 16:25:53.849299: step: 1164/1545, loss: 0.5668256282806396 2023-01-23 16:25:54.717832: step: 1166/1545, loss: 0.0007555466145277023 2023-01-23 16:25:55.651342: step: 1168/1545, loss: 0.046314042061567307 2023-01-23 16:25:56.524620: step: 1170/1545, loss: 0.16560319066047668 2023-01-23 16:25:57.364284: step: 1172/1545, loss: 0.007606488652527332 2023-01-23 16:25:58.247763: step: 1174/1545, loss: 0.00674311863258481 2023-01-23 16:25:59.127402: step: 1176/1545, loss: 0.03392000496387482 2023-01-23 16:25:59.995531: step: 1178/1545, loss: 0.14183329045772552 2023-01-23 16:26:00.855368: step: 1180/1545, loss: 0.008820414543151855 2023-01-23 16:26:01.737916: step: 1182/1545, loss: 0.01527461875230074 2023-01-23 16:26:02.629292: step: 1184/1545, loss: 0.30772048234939575 2023-01-23 16:26:03.597132: step: 1186/1545, loss: 0.002295300830155611 2023-01-23 16:26:04.483760: step: 1188/1545, loss: 0.0004453345900401473 2023-01-23 16:26:05.362344: step: 1190/1545, loss: 0.0003076265275012702 2023-01-23 16:26:06.232046: step: 1192/1545, loss: 0.16530808806419373 2023-01-23 16:26:07.085755: step: 1194/1545, loss: 0.023522205650806427 2023-01-23 16:26:07.963907: step: 1196/1545, loss: 0.05939941480755806 2023-01-23 16:26:08.811862: step: 1198/1545, loss: 0.00023808071273379028 2023-01-23 16:26:09.655341: step: 1200/1545, loss: 0.028950810432434082 2023-01-23 16:26:10.571198: step: 1202/1545, loss: 0.21502238512039185 2023-01-23 16:26:11.467037: step: 1204/1545, loss: 0.02065499685704708 2023-01-23 16:26:12.367906: step: 1206/1545, loss: 0.0024031330831348896 2023-01-23 16:26:13.276462: step: 1208/1545, loss: 0.00650001922622323 2023-01-23 16:26:14.170380: step: 1210/1545, loss: 0.0007297483389265835 2023-01-23 16:26:15.063358: step: 1212/1545, loss: 0.01641390286386013 2023-01-23 16:26:15.954025: step: 1214/1545, loss: 2.6626956462860107 2023-01-23 16:26:16.814302: step: 1216/1545, loss: 0.0130929509177804 2023-01-23 16:26:17.759941: step: 1218/1545, loss: 0.30077436566352844 2023-01-23 16:26:18.636660: step: 1220/1545, loss: 0.008121173828840256 2023-01-23 16:26:19.514569: step: 1222/1545, loss: 0.024911243468523026 2023-01-23 16:26:20.410967: step: 1224/1545, loss: 0.017950134351849556 2023-01-23 16:26:21.326199: step: 1226/1545, loss: 0.0022353220265358686 2023-01-23 16:26:22.227777: step: 1228/1545, loss: 0.4483543336391449 2023-01-23 16:26:23.089531: step: 1230/1545, loss: 0.010488289408385754 2023-01-23 16:26:23.953329: step: 1232/1545, loss: 0.00010560164082562551 2023-01-23 16:26:24.816391: step: 1234/1545, loss: 0.0025550408754497766 2023-01-23 16:26:25.709491: step: 1236/1545, loss: 0.0012797042727470398 2023-01-23 16:26:26.625215: step: 1238/1545, loss: 0.0024892722722142935 2023-01-23 16:26:27.490300: step: 1240/1545, loss: 0.007631886284798384 2023-01-23 16:26:28.405617: step: 1242/1545, loss: 0.0012906906194984913 2023-01-23 16:26:29.261238: step: 1244/1545, loss: 2.174929141998291 2023-01-23 16:26:30.148170: step: 1246/1545, loss: 0.0003890030784532428 2023-01-23 16:26:31.035187: step: 1248/1545, loss: 0.020277122035622597 2023-01-23 16:26:31.916651: step: 1250/1545, loss: 0.14783672988414764 2023-01-23 16:26:32.786741: step: 1252/1545, loss: 0.010259311646223068 2023-01-23 16:26:33.674697: step: 1254/1545, loss: 0.027370069175958633 2023-01-23 16:26:34.584447: step: 1256/1545, loss: 0.0004718084819614887 2023-01-23 16:26:35.454776: step: 1258/1545, loss: 0.0003627897531259805 2023-01-23 16:26:36.338719: step: 1260/1545, loss: 0.001431277603842318 2023-01-23 16:26:37.206931: step: 1262/1545, loss: 0.007774749770760536 2023-01-23 16:26:38.116670: step: 1264/1545, loss: 0.00012830882042180747 2023-01-23 16:26:39.009699: step: 1266/1545, loss: 0.012354008853435516 2023-01-23 16:26:39.913607: step: 1268/1545, loss: 0.06299339979887009 2023-01-23 16:26:40.814407: step: 1270/1545, loss: 0.02638150379061699 2023-01-23 16:26:41.682841: step: 1272/1545, loss: 0.34262189269065857 2023-01-23 16:26:42.552305: step: 1274/1545, loss: 0.002455209381878376 2023-01-23 16:26:43.482621: step: 1276/1545, loss: 0.0013288211775943637 2023-01-23 16:26:44.353368: step: 1278/1545, loss: 0.00010814551205839962 2023-01-23 16:26:45.312225: step: 1280/1545, loss: 9.369762847200036e-05 2023-01-23 16:26:46.195235: step: 1282/1545, loss: 0.0021482654847204685 2023-01-23 16:26:47.111955: step: 1284/1545, loss: 0.0004427215608302504 2023-01-23 16:26:48.026226: step: 1286/1545, loss: 0.007788913790136576 2023-01-23 16:26:48.950837: step: 1288/1545, loss: 0.0020802454091608524 2023-01-23 16:26:49.823482: step: 1290/1545, loss: 0.0023411824367940426 2023-01-23 16:26:50.709068: step: 1292/1545, loss: 0.12483545392751694 2023-01-23 16:26:51.574979: step: 1294/1545, loss: 0.13072435557842255 2023-01-23 16:26:52.437995: step: 1296/1545, loss: 0.46109214425086975 2023-01-23 16:26:53.339016: step: 1298/1545, loss: 0.004936687182635069 2023-01-23 16:26:54.228674: step: 1300/1545, loss: 0.00024367938749492168 2023-01-23 16:26:55.104845: step: 1302/1545, loss: 0.011576654389500618 2023-01-23 16:26:55.988753: step: 1304/1545, loss: 0.2895493507385254 2023-01-23 16:26:56.981163: step: 1306/1545, loss: 0.2775740623474121 2023-01-23 16:26:57.880185: step: 1308/1545, loss: 0.003863516729325056 2023-01-23 16:26:58.728597: step: 1310/1545, loss: 0.2115059345960617 2023-01-23 16:26:59.574276: step: 1312/1545, loss: 0.07983095943927765 2023-01-23 16:27:00.518861: step: 1314/1545, loss: 0.0033725262619554996 2023-01-23 16:27:01.437528: step: 1316/1545, loss: 0.15939566493034363 2023-01-23 16:27:02.333645: step: 1318/1545, loss: 0.014848369173705578 2023-01-23 16:27:03.217600: step: 1320/1545, loss: 0.002605996560305357 2023-01-23 16:27:04.064319: step: 1322/1545, loss: 0.004621264524757862 2023-01-23 16:27:04.941961: step: 1324/1545, loss: 0.12386224418878555 2023-01-23 16:27:05.793871: step: 1326/1545, loss: 0.05537637323141098 2023-01-23 16:27:06.695557: step: 1328/1545, loss: 0.07511422038078308 2023-01-23 16:27:07.570488: step: 1330/1545, loss: 0.09885894507169724 2023-01-23 16:27:08.476292: step: 1332/1545, loss: 0.005449100397527218 2023-01-23 16:27:09.347087: step: 1334/1545, loss: 0.0019037544261664152 2023-01-23 16:27:10.209189: step: 1336/1545, loss: 0.0034920857287943363 2023-01-23 16:27:11.080394: step: 1338/1545, loss: 0.0003382026043254882 2023-01-23 16:27:11.947635: step: 1340/1545, loss: 0.0011493206257000566 2023-01-23 16:27:12.802538: step: 1342/1545, loss: 0.0005601096781902015 2023-01-23 16:27:13.656797: step: 1344/1545, loss: 0.0013900627382099628 2023-01-23 16:27:14.503537: step: 1346/1545, loss: 0.0015735799679532647 2023-01-23 16:27:15.417587: step: 1348/1545, loss: 0.001857905532233417 2023-01-23 16:27:16.281142: step: 1350/1545, loss: 0.11642718315124512 2023-01-23 16:27:17.106761: step: 1352/1545, loss: 0.024710604920983315 2023-01-23 16:27:18.012959: step: 1354/1545, loss: 0.08675318211317062 2023-01-23 16:27:18.960051: step: 1356/1545, loss: 0.0011872292961925268 2023-01-23 16:27:19.809410: step: 1358/1545, loss: 0.06878075003623962 2023-01-23 16:27:20.680504: step: 1360/1545, loss: 0.10746224224567413 2023-01-23 16:27:21.542756: step: 1362/1545, loss: 0.001100849243812263 2023-01-23 16:27:22.450489: step: 1364/1545, loss: 0.009598405100405216 2023-01-23 16:27:23.342162: step: 1366/1545, loss: 0.242245614528656 2023-01-23 16:27:24.182876: step: 1368/1545, loss: 0.09763241559267044 2023-01-23 16:27:25.016854: step: 1370/1545, loss: 0.0030747088603675365 2023-01-23 16:27:25.911120: step: 1372/1545, loss: 5.379999856813811e-05 2023-01-23 16:27:26.807605: step: 1374/1545, loss: 0.0008949817274697125 2023-01-23 16:27:27.664424: step: 1376/1545, loss: 0.0006923668552190065 2023-01-23 16:27:28.585511: step: 1378/1545, loss: 0.0462706983089447 2023-01-23 16:27:29.510542: step: 1380/1545, loss: 0.38460707664489746 2023-01-23 16:27:30.380239: step: 1382/1545, loss: 0.0005963252624496818 2023-01-23 16:27:31.350778: step: 1384/1545, loss: 0.1017666831612587 2023-01-23 16:27:32.239040: step: 1386/1545, loss: 0.004067194648087025 2023-01-23 16:27:33.140658: step: 1388/1545, loss: 0.0541243739426136 2023-01-23 16:27:34.025530: step: 1390/1545, loss: 0.0028610294684767723 2023-01-23 16:27:34.936498: step: 1392/1545, loss: 0.0893017053604126 2023-01-23 16:27:35.804728: step: 1394/1545, loss: 0.012691878713667393 2023-01-23 16:27:36.682635: step: 1396/1545, loss: 0.04601133614778519 2023-01-23 16:27:37.571601: step: 1398/1545, loss: 0.07264436036348343 2023-01-23 16:27:38.479633: step: 1400/1545, loss: 0.00383135792799294 2023-01-23 16:27:39.349376: step: 1402/1545, loss: 0.07371000200510025 2023-01-23 16:27:40.231914: step: 1404/1545, loss: 0.0018770690076053143 2023-01-23 16:27:41.162448: step: 1406/1545, loss: 0.10789617151021957 2023-01-23 16:27:42.066455: step: 1408/1545, loss: 0.21024255454540253 2023-01-23 16:27:42.943244: step: 1410/1545, loss: 0.025537872686982155 2023-01-23 16:27:43.811146: step: 1412/1545, loss: 0.027061857283115387 2023-01-23 16:27:44.685745: step: 1414/1545, loss: 0.0005357067566365004 2023-01-23 16:27:45.517276: step: 1416/1545, loss: 0.017815565690398216 2023-01-23 16:27:46.403962: step: 1418/1545, loss: 0.1834164559841156 2023-01-23 16:27:47.296200: step: 1420/1545, loss: 0.002214340725913644 2023-01-23 16:27:48.174864: step: 1422/1545, loss: 0.00025580759393051267 2023-01-23 16:27:49.063673: step: 1424/1545, loss: 0.06706942617893219 2023-01-23 16:27:50.000258: step: 1426/1545, loss: 0.12371911853551865 2023-01-23 16:27:50.939084: step: 1428/1545, loss: 0.0007000009063631296 2023-01-23 16:27:51.812146: step: 1430/1545, loss: 0.0005222383188083768 2023-01-23 16:27:52.711050: step: 1432/1545, loss: 0.0005644498160108924 2023-01-23 16:27:53.584902: step: 1434/1545, loss: 0.002492492785677314 2023-01-23 16:27:54.493294: step: 1436/1545, loss: 0.029894059523940086 2023-01-23 16:27:55.379706: step: 1438/1545, loss: 0.057756468653678894 2023-01-23 16:27:56.266805: step: 1440/1545, loss: 0.010912297293543816 2023-01-23 16:27:57.244259: step: 1442/1545, loss: 0.00024860355188138783 2023-01-23 16:27:58.083753: step: 1444/1545, loss: 0.015178212895989418 2023-01-23 16:27:58.966608: step: 1446/1545, loss: 0.010174786671996117 2023-01-23 16:27:59.891105: step: 1448/1545, loss: 0.04925323277711868 2023-01-23 16:28:00.750890: step: 1450/1545, loss: 0.00029879785142838955 2023-01-23 16:28:01.624592: step: 1452/1545, loss: 1.897721767425537 2023-01-23 16:28:02.472646: step: 1454/1545, loss: 8.612591045675799e-05 2023-01-23 16:28:03.297602: step: 1456/1545, loss: 9.435006359126419e-05 2023-01-23 16:28:04.201518: step: 1458/1545, loss: 0.0011258840095251799 2023-01-23 16:28:05.064775: step: 1460/1545, loss: 0.39670315384864807 2023-01-23 16:28:05.967614: step: 1462/1545, loss: 0.0005937371752224863 2023-01-23 16:28:06.903502: step: 1464/1545, loss: 9.332554327556863e-06 2023-01-23 16:28:07.750274: step: 1466/1545, loss: 0.031187742948532104 2023-01-23 16:28:08.638129: step: 1468/1545, loss: 0.0009404445299878716 2023-01-23 16:28:09.468568: step: 1470/1545, loss: 5.7616100093582645e-05 2023-01-23 16:28:10.347381: step: 1472/1545, loss: 0.0017557027749717236 2023-01-23 16:28:11.252393: step: 1474/1545, loss: 0.1595376580953598 2023-01-23 16:28:12.174460: step: 1476/1545, loss: 0.09549331665039062 2023-01-23 16:28:13.047879: step: 1478/1545, loss: 0.0002937988319899887 2023-01-23 16:28:13.925382: step: 1480/1545, loss: 0.19346758723258972 2023-01-23 16:28:14.780985: step: 1482/1545, loss: 0.001905194018036127 2023-01-23 16:28:15.667196: step: 1484/1545, loss: 0.0011708495439961553 2023-01-23 16:28:16.521517: step: 1486/1545, loss: 0.019754143431782722 2023-01-23 16:28:17.389652: step: 1488/1545, loss: 0.01190407108515501 2023-01-23 16:28:18.264360: step: 1490/1545, loss: 0.03392469137907028 2023-01-23 16:28:19.111650: step: 1492/1545, loss: 0.001291363500058651 2023-01-23 16:28:19.953511: step: 1494/1545, loss: 0.263357549905777 2023-01-23 16:28:20.812092: step: 1496/1545, loss: 0.00012789804895874113 2023-01-23 16:28:21.679274: step: 1498/1545, loss: 0.01909535564482212 2023-01-23 16:28:22.576145: step: 1500/1545, loss: 0.008995460346341133 2023-01-23 16:28:23.434950: step: 1502/1545, loss: 0.16527803242206573 2023-01-23 16:28:24.283140: step: 1504/1545, loss: 0.0006377924000844359 2023-01-23 16:28:25.140679: step: 1506/1545, loss: 0.0044366358779370785 2023-01-23 16:28:25.974619: step: 1508/1545, loss: 0.025836331769824028 2023-01-23 16:28:26.850892: step: 1510/1545, loss: 0.022810522466897964 2023-01-23 16:28:27.727424: step: 1512/1545, loss: 5.54031903448049e-05 2023-01-23 16:28:28.615941: step: 1514/1545, loss: 0.0029180762358009815 2023-01-23 16:28:29.493992: step: 1516/1545, loss: 0.0010701479623094201 2023-01-23 16:28:30.352824: step: 1518/1545, loss: 0.00026110929320566356 2023-01-23 16:28:31.195091: step: 1520/1545, loss: 0.025418125092983246 2023-01-23 16:28:32.032572: step: 1522/1545, loss: 0.005887183360755444 2023-01-23 16:28:32.938125: step: 1524/1545, loss: 0.0004066525143571198 2023-01-23 16:28:33.828910: step: 1526/1545, loss: 0.003728533862158656 2023-01-23 16:28:34.704878: step: 1528/1545, loss: 0.07265861332416534 2023-01-23 16:28:35.577937: step: 1530/1545, loss: 0.028130941092967987 2023-01-23 16:28:36.429898: step: 1532/1545, loss: 0.4599316418170929 2023-01-23 16:28:37.281916: step: 1534/1545, loss: 0.0009203850058838725 2023-01-23 16:28:38.261447: step: 1536/1545, loss: 0.11363720893859863 2023-01-23 16:28:39.089092: step: 1538/1545, loss: 0.004736988339573145 2023-01-23 16:28:39.969688: step: 1540/1545, loss: 0.006548205856233835 2023-01-23 16:28:40.834314: step: 1542/1545, loss: 0.00013095820031594485 2023-01-23 16:28:41.711235: step: 1544/1545, loss: 0.02349490486085415 2023-01-23 16:28:42.585548: step: 1546/1545, loss: 0.21750658750534058 2023-01-23 16:28:43.489997: step: 1548/1545, loss: 0.023666301742196083 2023-01-23 16:28:44.347701: step: 1550/1545, loss: 0.0007596187642775476 2023-01-23 16:28:45.214730: step: 1552/1545, loss: 0.0015260488726198673 2023-01-23 16:28:46.124930: step: 1554/1545, loss: 0.015601475723087788 2023-01-23 16:28:47.035350: step: 1556/1545, loss: 8.748803520575166e-05 2023-01-23 16:28:47.957824: step: 1558/1545, loss: 0.04783514142036438 2023-01-23 16:28:48.808649: step: 1560/1545, loss: 0.2327815592288971 2023-01-23 16:28:49.697179: step: 1562/1545, loss: 0.11902911961078644 2023-01-23 16:28:50.572184: step: 1564/1545, loss: 0.0008346404647454619 2023-01-23 16:28:51.497170: step: 1566/1545, loss: 0.022246813401579857 2023-01-23 16:28:52.411914: step: 1568/1545, loss: 0.025493798777461052 2023-01-23 16:28:53.325830: step: 1570/1545, loss: 0.07244456559419632 2023-01-23 16:28:54.169178: step: 1572/1545, loss: -7.405385531455977e-06 2023-01-23 16:28:55.020156: step: 1574/1545, loss: 0.04386070743203163 2023-01-23 16:28:55.837624: step: 1576/1545, loss: 0.0016835312126204371 2023-01-23 16:28:56.710693: step: 1578/1545, loss: 0.005677294917404652 2023-01-23 16:28:57.596955: step: 1580/1545, loss: 0.21984733641147614 2023-01-23 16:28:58.462020: step: 1582/1545, loss: 2.9297249056980945e-05 2023-01-23 16:28:59.352677: step: 1584/1545, loss: 0.00011323465150780976 2023-01-23 16:29:00.266271: step: 1586/1545, loss: 0.0005713673308491707 2023-01-23 16:29:01.148180: step: 1588/1545, loss: 0.0019806502386927605 2023-01-23 16:29:02.043938: step: 1590/1545, loss: 0.26465463638305664 2023-01-23 16:29:02.909029: step: 1592/1545, loss: 0.12336985021829605 2023-01-23 16:29:03.806423: step: 1594/1545, loss: 0.32707899808883667 2023-01-23 16:29:04.654978: step: 1596/1545, loss: 0.09827333688735962 2023-01-23 16:29:05.504176: step: 1598/1545, loss: 0.0273238904774189 2023-01-23 16:29:06.364483: step: 1600/1545, loss: 0.3951124846935272 2023-01-23 16:29:07.221129: step: 1602/1545, loss: 0.002279565902426839 2023-01-23 16:29:08.085711: step: 1604/1545, loss: 0.0008716121083125472 2023-01-23 16:29:08.958990: step: 1606/1545, loss: 0.006354022771120071 2023-01-23 16:29:09.840259: step: 1608/1545, loss: 0.016457704827189445 2023-01-23 16:29:10.697857: step: 1610/1545, loss: 0.08012872189283371 2023-01-23 16:29:11.549340: step: 1612/1545, loss: 0.009562842547893524 2023-01-23 16:29:12.436124: step: 1614/1545, loss: 0.112125463783741 2023-01-23 16:29:13.292703: step: 1616/1545, loss: 0.003280362579971552 2023-01-23 16:29:14.182666: step: 1618/1545, loss: 0.030100736767053604 2023-01-23 16:29:15.030806: step: 1620/1545, loss: 0.07183244824409485 2023-01-23 16:29:15.893029: step: 1622/1545, loss: 0.032346807420253754 2023-01-23 16:29:16.777943: step: 1624/1545, loss: 0.00033729360438883305 2023-01-23 16:29:17.671561: step: 1626/1545, loss: 0.0008431432070210576 2023-01-23 16:29:18.525653: step: 1628/1545, loss: 0.0034392334055155516 2023-01-23 16:29:19.397214: step: 1630/1545, loss: 0.12823152542114258 2023-01-23 16:29:20.282309: step: 1632/1545, loss: 0.020756563171744347 2023-01-23 16:29:21.171266: step: 1634/1545, loss: 0.11456665396690369 2023-01-23 16:29:22.058732: step: 1636/1545, loss: 0.02309592254459858 2023-01-23 16:29:22.955395: step: 1638/1545, loss: 0.030628623440861702 2023-01-23 16:29:23.894509: step: 1640/1545, loss: 0.0012618136825039983 2023-01-23 16:29:24.759015: step: 1642/1545, loss: 0.0016441554762423038 2023-01-23 16:29:25.627858: step: 1644/1545, loss: 0.08969323337078094 2023-01-23 16:29:26.525152: step: 1646/1545, loss: 0.00033918418921530247 2023-01-23 16:29:27.379843: step: 1648/1545, loss: 0.009595740586519241 2023-01-23 16:29:28.254574: step: 1650/1545, loss: 0.011630520224571228 2023-01-23 16:29:29.156372: step: 1652/1545, loss: 0.0002142314478987828 2023-01-23 16:29:29.991027: step: 1654/1545, loss: 0.013841310515999794 2023-01-23 16:29:30.845339: step: 1656/1545, loss: 0.029574286192655563 2023-01-23 16:29:31.752125: step: 1658/1545, loss: 0.0033800967503339052 2023-01-23 16:29:32.660887: step: 1660/1545, loss: 0.016109300777316093 2023-01-23 16:29:33.522763: step: 1662/1545, loss: 0.003907877951860428 2023-01-23 16:29:34.423512: step: 1664/1545, loss: 0.3449101150035858 2023-01-23 16:29:35.343498: step: 1666/1545, loss: 0.08579494059085846 2023-01-23 16:29:36.279588: step: 1668/1545, loss: 0.0005378990317694843 2023-01-23 16:29:37.153441: step: 1670/1545, loss: 0.09664467722177505 2023-01-23 16:29:38.019673: step: 1672/1545, loss: 0.003458733204752207 2023-01-23 16:29:38.881694: step: 1674/1545, loss: 0.0563637837767601 2023-01-23 16:29:39.797823: step: 1676/1545, loss: 0.3797478675842285 2023-01-23 16:29:40.692479: step: 1678/1545, loss: 0.04989843815565109 2023-01-23 16:29:41.599228: step: 1680/1545, loss: 0.07357440888881683 2023-01-23 16:29:42.498949: step: 1682/1545, loss: 0.0007196353981271386 2023-01-23 16:29:43.358763: step: 1684/1545, loss: 0.0007908556726761162 2023-01-23 16:29:44.258632: step: 1686/1545, loss: 0.018878504633903503 2023-01-23 16:29:45.099221: step: 1688/1545, loss: 0.0006799900438636541 2023-01-23 16:29:46.005099: step: 1690/1545, loss: 0.03816857188940048 2023-01-23 16:29:46.934792: step: 1692/1545, loss: 9.076159039977938e-05 2023-01-23 16:29:47.777603: step: 1694/1545, loss: 0.0008967680623754859 2023-01-23 16:29:48.615014: step: 1696/1545, loss: 0.04612558335065842 2023-01-23 16:29:49.499994: step: 1698/1545, loss: 0.0003102348418906331 2023-01-23 16:29:50.368508: step: 1700/1545, loss: 0.0496395081281662 2023-01-23 16:29:51.219607: step: 1702/1545, loss: 0.0008604805916547775 2023-01-23 16:29:52.072137: step: 1704/1545, loss: 0.037049032747745514 2023-01-23 16:29:52.994511: step: 1706/1545, loss: 0.08112546801567078 2023-01-23 16:29:53.830783: step: 1708/1545, loss: 0.04703846201300621 2023-01-23 16:29:54.707482: step: 1710/1545, loss: 0.44245338439941406 2023-01-23 16:29:55.670795: step: 1712/1545, loss: 0.09462704509496689 2023-01-23 16:29:56.531463: step: 1714/1545, loss: 0.018058935180306435 2023-01-23 16:29:57.426015: step: 1716/1545, loss: 0.06236892193555832 2023-01-23 16:29:58.282711: step: 1718/1545, loss: 0.0029624069575220346 2023-01-23 16:29:59.190281: step: 1720/1545, loss: 0.16191740334033966 2023-01-23 16:30:00.115092: step: 1722/1545, loss: 0.037447620183229446 2023-01-23 16:30:01.031769: step: 1724/1545, loss: 0.03794633597135544 2023-01-23 16:30:01.952680: step: 1726/1545, loss: 0.05908096954226494 2023-01-23 16:30:02.813346: step: 1728/1545, loss: 0.011169162578880787 2023-01-23 16:30:03.713315: step: 1730/1545, loss: 0.010832761414349079 2023-01-23 16:30:04.566624: step: 1732/1545, loss: 0.19141928851604462 2023-01-23 16:30:05.399304: step: 1734/1545, loss: 0.07239297777414322 2023-01-23 16:30:06.274134: step: 1736/1545, loss: 0.01894439198076725 2023-01-23 16:30:07.151469: step: 1738/1545, loss: 0.06128441542387009 2023-01-23 16:30:07.995048: step: 1740/1545, loss: 0.08324090391397476 2023-01-23 16:30:08.879965: step: 1742/1545, loss: 0.007283140439540148 2023-01-23 16:30:09.747167: step: 1744/1545, loss: 0.04891999810934067 2023-01-23 16:30:10.606988: step: 1746/1545, loss: 0.12623950839042664 2023-01-23 16:30:11.460492: step: 1748/1545, loss: 0.005961687304079533 2023-01-23 16:30:12.361498: step: 1750/1545, loss: 0.16778752207756042 2023-01-23 16:30:13.275277: step: 1752/1545, loss: 0.0010752277448773384 2023-01-23 16:30:14.137950: step: 1754/1545, loss: 0.0003217399644199759 2023-01-23 16:30:15.016241: step: 1756/1545, loss: 0.07493439316749573 2023-01-23 16:30:15.888094: step: 1758/1545, loss: 0.005947294179350138 2023-01-23 16:30:16.755765: step: 1760/1545, loss: 0.1467694342136383 2023-01-23 16:30:17.655732: step: 1762/1545, loss: 0.007732962723821402 2023-01-23 16:30:18.501124: step: 1764/1545, loss: 0.011773193255066872 2023-01-23 16:30:19.361916: step: 1766/1545, loss: 0.00166815344709903 2023-01-23 16:30:20.230426: step: 1768/1545, loss: 0.4401128888130188 2023-01-23 16:30:21.090237: step: 1770/1545, loss: 0.13476897776126862 2023-01-23 16:30:21.938802: step: 1772/1545, loss: 0.043200213462114334 2023-01-23 16:30:22.822031: step: 1774/1545, loss: 0.0017735965084284544 2023-01-23 16:30:23.696617: step: 1776/1545, loss: 0.024079855531454086 2023-01-23 16:30:24.566163: step: 1778/1545, loss: 0.21493366360664368 2023-01-23 16:30:25.426912: step: 1780/1545, loss: 0.03755607828497887 2023-01-23 16:30:26.279587: step: 1782/1545, loss: 0.043900009244680405 2023-01-23 16:30:27.146860: step: 1784/1545, loss: 0.000756140099838376 2023-01-23 16:30:27.974815: step: 1786/1545, loss: 0.24614308774471283 2023-01-23 16:30:28.846822: step: 1788/1545, loss: 0.051365502178668976 2023-01-23 16:30:29.706966: step: 1790/1545, loss: 0.02695363201200962 2023-01-23 16:30:30.562371: step: 1792/1545, loss: 0.013954303227365017 2023-01-23 16:30:31.384404: step: 1794/1545, loss: 0.003001380478963256 2023-01-23 16:30:32.232201: step: 1796/1545, loss: 0.006933140568435192 2023-01-23 16:30:33.102864: step: 1798/1545, loss: 0.0013242231216281652 2023-01-23 16:30:33.954623: step: 1800/1545, loss: 0.058562517166137695 2023-01-23 16:30:34.793032: step: 1802/1545, loss: 0.17982928454875946 2023-01-23 16:30:35.683713: step: 1804/1545, loss: 0.00040137808537110686 2023-01-23 16:30:36.570955: step: 1806/1545, loss: 0.2388751059770584 2023-01-23 16:30:37.450037: step: 1808/1545, loss: 0.00027075308025814593 2023-01-23 16:30:38.345939: step: 1810/1545, loss: 0.08688129484653473 2023-01-23 16:30:39.271136: step: 1812/1545, loss: 0.0011721118353307247 2023-01-23 16:30:40.112949: step: 1814/1545, loss: 0.2071344256401062 2023-01-23 16:30:40.998990: step: 1816/1545, loss: 0.0032142181880772114 2023-01-23 16:30:41.904114: step: 1818/1545, loss: 0.0041280873119831085 2023-01-23 16:30:42.734431: step: 1820/1545, loss: 0.09601804614067078 2023-01-23 16:30:43.571070: step: 1822/1545, loss: 0.00540417805314064 2023-01-23 16:30:44.454036: step: 1824/1545, loss: 0.01017073541879654 2023-01-23 16:30:45.301088: step: 1826/1545, loss: 0.4148392081260681 2023-01-23 16:30:46.126735: step: 1828/1545, loss: 0.035674549639225006 2023-01-23 16:30:47.015448: step: 1830/1545, loss: 0.046170756220817566 2023-01-23 16:30:47.944470: step: 1832/1545, loss: 0.0032225141767412424 2023-01-23 16:30:48.795413: step: 1834/1545, loss: 0.016292445361614227 2023-01-23 16:30:49.697146: step: 1836/1545, loss: 0.016251159831881523 2023-01-23 16:30:50.566226: step: 1838/1545, loss: 0.046799227595329285 2023-01-23 16:30:51.440822: step: 1840/1545, loss: 0.005919392220675945 2023-01-23 16:30:52.350424: step: 1842/1545, loss: 0.0014566804748028517 2023-01-23 16:30:53.204010: step: 1844/1545, loss: 0.029661456122994423 2023-01-23 16:30:54.216748: step: 1846/1545, loss: 0.0635070651769638 2023-01-23 16:30:55.075366: step: 1848/1545, loss: 0.06228725239634514 2023-01-23 16:30:55.905653: step: 1850/1545, loss: 0.24610352516174316 2023-01-23 16:30:56.763310: step: 1852/1545, loss: 0.07086022943258286 2023-01-23 16:30:57.649103: step: 1854/1545, loss: 0.0026977460365742445 2023-01-23 16:30:58.530766: step: 1856/1545, loss: 0.0027684431988745928 2023-01-23 16:30:59.374411: step: 1858/1545, loss: 0.0028865148779004812 2023-01-23 16:31:00.244080: step: 1860/1545, loss: 0.07760357111692429 2023-01-23 16:31:01.149147: step: 1862/1545, loss: 0.012547360733151436 2023-01-23 16:31:01.999004: step: 1864/1545, loss: 0.26730895042419434 2023-01-23 16:31:02.899823: step: 1866/1545, loss: 0.05896298959851265 2023-01-23 16:31:03.760489: step: 1868/1545, loss: 0.20677535235881805 2023-01-23 16:31:04.694079: step: 1870/1545, loss: 0.05590595304965973 2023-01-23 16:31:05.613102: step: 1872/1545, loss: 0.0015881754225119948 2023-01-23 16:31:06.552324: step: 1874/1545, loss: 0.0002320305211469531 2023-01-23 16:31:07.413672: step: 1876/1545, loss: 0.07855325192213058 2023-01-23 16:31:08.302419: step: 1878/1545, loss: 0.0357719287276268 2023-01-23 16:31:09.220971: step: 1880/1545, loss: 0.027570385485887527 2023-01-23 16:31:10.061953: step: 1882/1545, loss: 0.015181416645646095 2023-01-23 16:31:10.938252: step: 1884/1545, loss: 0.01600898802280426 2023-01-23 16:31:11.830422: step: 1886/1545, loss: 0.0361875519156456 2023-01-23 16:31:12.752509: step: 1888/1545, loss: 0.002053471514955163 2023-01-23 16:31:13.653198: step: 1890/1545, loss: 0.06316538900136948 2023-01-23 16:31:14.535816: step: 1892/1545, loss: 0.0059414696879684925 2023-01-23 16:31:15.431685: step: 1894/1545, loss: 0.11695583164691925 2023-01-23 16:31:16.362607: step: 1896/1545, loss: 0.00024061596195679158 2023-01-23 16:31:17.274236: step: 1898/1545, loss: 0.6335055828094482 2023-01-23 16:31:18.159457: step: 1900/1545, loss: 0.05143939331173897 2023-01-23 16:31:19.127327: step: 1902/1545, loss: 0.014025432989001274 2023-01-23 16:31:20.010724: step: 1904/1545, loss: 0.11490190029144287 2023-01-23 16:31:20.845763: step: 1906/1545, loss: 0.045844994485378265 2023-01-23 16:31:21.661980: step: 1908/1545, loss: 0.08523520082235336 2023-01-23 16:31:22.534217: step: 1910/1545, loss: 1.342788577079773 2023-01-23 16:31:23.390615: step: 1912/1545, loss: 0.0035149306058883667 2023-01-23 16:31:24.249136: step: 1914/1545, loss: 0.05311310291290283 2023-01-23 16:31:25.067924: step: 1916/1545, loss: 0.006841030903160572 2023-01-23 16:31:25.952394: step: 1918/1545, loss: 0.2006625384092331 2023-01-23 16:31:26.774766: step: 1920/1545, loss: 0.0008010558085516095 2023-01-23 16:31:27.718208: step: 1922/1545, loss: 0.10745646804571152 2023-01-23 16:31:28.587064: step: 1924/1545, loss: 0.009734869003295898 2023-01-23 16:31:29.471362: step: 1926/1545, loss: 0.0002946506720036268 2023-01-23 16:31:30.328749: step: 1928/1545, loss: 0.06879688054323196 2023-01-23 16:31:31.192527: step: 1930/1545, loss: 0.9932481646537781 2023-01-23 16:31:32.036560: step: 1932/1545, loss: 0.17314563691616058 2023-01-23 16:31:32.961002: step: 1934/1545, loss: 0.06618830561637878 2023-01-23 16:31:33.854455: step: 1936/1545, loss: 0.07136163860559464 2023-01-23 16:31:34.702801: step: 1938/1545, loss: 0.034459903836250305 2023-01-23 16:31:35.582673: step: 1940/1545, loss: 0.15890417993068695 2023-01-23 16:31:36.450927: step: 1942/1545, loss: 0.1284853219985962 2023-01-23 16:31:37.319375: step: 1944/1545, loss: 0.186730295419693 2023-01-23 16:31:38.217127: step: 1946/1545, loss: 0.19273003935813904 2023-01-23 16:31:39.062883: step: 1948/1545, loss: 0.0009432000806555152 2023-01-23 16:31:39.937567: step: 1950/1545, loss: 0.04359223321080208 2023-01-23 16:31:40.807800: step: 1952/1545, loss: 0.01591634750366211 2023-01-23 16:31:41.724776: step: 1954/1545, loss: 0.010288042947649956 2023-01-23 16:31:42.662991: step: 1956/1545, loss: 0.0010298762936145067 2023-01-23 16:31:43.551919: step: 1958/1545, loss: 0.003563990816473961 2023-01-23 16:31:44.453392: step: 1960/1545, loss: 0.0025124468374997377 2023-01-23 16:31:45.332740: step: 1962/1545, loss: 0.04247434437274933 2023-01-23 16:31:46.188293: step: 1964/1545, loss: 0.31503957509994507 2023-01-23 16:31:47.038921: step: 1966/1545, loss: 0.5003658533096313 2023-01-23 16:31:47.971159: step: 1968/1545, loss: 0.040884166955947876 2023-01-23 16:31:48.850984: step: 1970/1545, loss: 0.031130658462643623 2023-01-23 16:31:49.717980: step: 1972/1545, loss: 0.015584555454552174 2023-01-23 16:31:50.552126: step: 1974/1545, loss: 0.12057606130838394 2023-01-23 16:31:51.448501: step: 1976/1545, loss: 0.00028980011120438576 2023-01-23 16:31:52.361161: step: 1978/1545, loss: 0.07761532068252563 2023-01-23 16:31:53.238802: step: 1980/1545, loss: 0.15586000680923462 2023-01-23 16:31:54.094636: step: 1982/1545, loss: 0.13106673955917358 2023-01-23 16:31:54.963603: step: 1984/1545, loss: 0.013518454506993294 2023-01-23 16:31:55.837437: step: 1986/1545, loss: 0.0028855365235358477 2023-01-23 16:31:56.754461: step: 1988/1545, loss: 0.05369384586811066 2023-01-23 16:31:57.768108: step: 1990/1545, loss: 0.019894566386938095 2023-01-23 16:31:58.659104: step: 1992/1545, loss: 0.005808471702039242 2023-01-23 16:31:59.567290: step: 1994/1545, loss: 0.0010650366311892867 2023-01-23 16:32:00.485707: step: 1996/1545, loss: 0.021625502035021782 2023-01-23 16:32:01.365555: step: 1998/1545, loss: 0.004558357875794172 2023-01-23 16:32:02.235466: step: 2000/1545, loss: 0.010177710093557835 2023-01-23 16:32:03.133653: step: 2002/1545, loss: 0.05982852354645729 2023-01-23 16:32:03.969059: step: 2004/1545, loss: 0.005607739556580782 2023-01-23 16:32:04.823454: step: 2006/1545, loss: 0.013836333528161049 2023-01-23 16:32:05.721808: step: 2008/1545, loss: 0.13410885632038116 2023-01-23 16:32:06.579936: step: 2010/1545, loss: 0.01440219022333622 2023-01-23 16:32:07.431854: step: 2012/1545, loss: 0.00040628237184137106 2023-01-23 16:32:08.301524: step: 2014/1545, loss: 0.25978678464889526 2023-01-23 16:32:09.191617: step: 2016/1545, loss: 0.021324725821614265 2023-01-23 16:32:10.064708: step: 2018/1545, loss: 0.06561228632926941 2023-01-23 16:32:10.914477: step: 2020/1545, loss: 0.0005916201625950634 2023-01-23 16:32:11.772574: step: 2022/1545, loss: 0.01232803426682949 2023-01-23 16:32:12.603633: step: 2024/1545, loss: 0.08454336225986481 2023-01-23 16:32:13.489750: step: 2026/1545, loss: 0.02879513055086136 2023-01-23 16:32:14.363204: step: 2028/1545, loss: 0.005951350554823875 2023-01-23 16:32:15.251721: step: 2030/1545, loss: 0.009009141474962234 2023-01-23 16:32:16.130741: step: 2032/1545, loss: 0.0003045967314392328 2023-01-23 16:32:16.995212: step: 2034/1545, loss: 0.006600090768188238 2023-01-23 16:32:17.865069: step: 2036/1545, loss: 0.10834839195013046 2023-01-23 16:32:18.703375: step: 2038/1545, loss: 0.009275847114622593 2023-01-23 16:32:19.623448: step: 2040/1545, loss: 0.06840953230857849 2023-01-23 16:32:20.500562: step: 2042/1545, loss: 0.043721526861190796 2023-01-23 16:32:21.370077: step: 2044/1545, loss: 0.0034724536817520857 2023-01-23 16:32:22.247108: step: 2046/1545, loss: 0.0027966713532805443 2023-01-23 16:32:23.158139: step: 2048/1545, loss: 0.004074077121913433 2023-01-23 16:32:24.058541: step: 2050/1545, loss: 0.013971682637929916 2023-01-23 16:32:24.944404: step: 2052/1545, loss: 0.06254179030656815 2023-01-23 16:32:25.849235: step: 2054/1545, loss: 0.021456144750118256 2023-01-23 16:32:26.695670: step: 2056/1545, loss: 0.0001957975619006902 2023-01-23 16:32:27.534097: step: 2058/1545, loss: 0.002596440492197871 2023-01-23 16:32:28.416414: step: 2060/1545, loss: 0.0280921533703804 2023-01-23 16:32:29.289972: step: 2062/1545, loss: 5.828746361657977e-05 2023-01-23 16:32:30.154954: step: 2064/1545, loss: 0.032200220972299576 2023-01-23 16:32:31.036445: step: 2066/1545, loss: 0.0009683453827165067 2023-01-23 16:32:31.880789: step: 2068/1545, loss: 0.00040448506479151547 2023-01-23 16:32:32.804436: step: 2070/1545, loss: 0.030643435195088387 2023-01-23 16:32:33.687326: step: 2072/1545, loss: 0.05300545319914818 2023-01-23 16:32:34.648579: step: 2074/1545, loss: 0.004817414563149214 2023-01-23 16:32:35.505506: step: 2076/1545, loss: 0.015308098867535591 2023-01-23 16:32:36.420925: step: 2078/1545, loss: 0.08358589559793472 2023-01-23 16:32:37.335455: step: 2080/1545, loss: 0.5693215727806091 2023-01-23 16:32:38.201513: step: 2082/1545, loss: 0.001678106957115233 2023-01-23 16:32:39.106891: step: 2084/1545, loss: 0.12207220494747162 2023-01-23 16:32:39.982211: step: 2086/1545, loss: 1.9995883703231812 2023-01-23 16:32:40.939696: step: 2088/1545, loss: 0.15871335566043854 2023-01-23 16:32:41.853638: step: 2090/1545, loss: 0.10142873972654343 2023-01-23 16:32:42.691535: step: 2092/1545, loss: 0.11277385801076889 2023-01-23 16:32:43.561597: step: 2094/1545, loss: 0.03062734380364418 2023-01-23 16:32:44.452395: step: 2096/1545, loss: 0.048272065818309784 2023-01-23 16:32:45.337875: step: 2098/1545, loss: 0.21303915977478027 2023-01-23 16:32:46.261092: step: 2100/1545, loss: 0.0001406277879141271 2023-01-23 16:32:47.185605: step: 2102/1545, loss: 0.015479727648198605 2023-01-23 16:32:48.090751: step: 2104/1545, loss: 0.312298983335495 2023-01-23 16:32:49.052175: step: 2106/1545, loss: 0.053548574447631836 2023-01-23 16:32:49.977231: step: 2108/1545, loss: 0.06291752308607101 2023-01-23 16:32:50.837615: step: 2110/1545, loss: 0.03987371176481247 2023-01-23 16:32:51.712619: step: 2112/1545, loss: 0.09860868752002716 2023-01-23 16:32:52.576001: step: 2114/1545, loss: 0.0013911088462918997 2023-01-23 16:32:53.426525: step: 2116/1545, loss: 2.8116115572629496e-05 2023-01-23 16:32:54.296296: step: 2118/1545, loss: 0.11775989085435867 2023-01-23 16:32:55.201066: step: 2120/1545, loss: 0.30824610590934753 2023-01-23 16:32:56.088779: step: 2122/1545, loss: 0.22838811576366425 2023-01-23 16:32:56.996923: step: 2124/1545, loss: 0.024822572246193886 2023-01-23 16:32:57.953889: step: 2126/1545, loss: 0.0006708225701004267 2023-01-23 16:32:58.841388: step: 2128/1545, loss: 0.06546320766210556 2023-01-23 16:32:59.757369: step: 2130/1545, loss: 0.07074826955795288 2023-01-23 16:33:00.632953: step: 2132/1545, loss: 0.00031512597342953086 2023-01-23 16:33:01.509373: step: 2134/1545, loss: 0.14293409883975983 2023-01-23 16:33:02.425167: step: 2136/1545, loss: 0.07815869152545929 2023-01-23 16:33:03.292374: step: 2138/1545, loss: 0.1415221393108368 2023-01-23 16:33:04.161952: step: 2140/1545, loss: 0.2302103042602539 2023-01-23 16:33:05.001904: step: 2142/1545, loss: 0.16325511038303375 2023-01-23 16:33:05.899310: step: 2144/1545, loss: 0.003314402885735035 2023-01-23 16:33:06.790718: step: 2146/1545, loss: 0.0005952339852228761 2023-01-23 16:33:07.667908: step: 2148/1545, loss: 0.06491674482822418 2023-01-23 16:33:08.559664: step: 2150/1545, loss: 0.13493043184280396 2023-01-23 16:33:09.434686: step: 2152/1545, loss: 0.0004917163751088083 2023-01-23 16:33:10.282356: step: 2154/1545, loss: 0.015001220628619194 2023-01-23 16:33:11.132870: step: 2156/1545, loss: 0.0012867883779108524 2023-01-23 16:33:12.012785: step: 2158/1545, loss: 0.007512575481086969 2023-01-23 16:33:12.868566: step: 2160/1545, loss: 0.20933955907821655 2023-01-23 16:33:13.758365: step: 2162/1545, loss: 0.23242317140102386 2023-01-23 16:33:14.657279: step: 2164/1545, loss: 0.04385216534137726 2023-01-23 16:33:15.536183: step: 2166/1545, loss: 0.021913429722189903 2023-01-23 16:33:16.409372: step: 2168/1545, loss: 0.0010099918581545353 2023-01-23 16:33:17.271408: step: 2170/1545, loss: 0.004821943584829569 2023-01-23 16:33:18.177058: step: 2172/1545, loss: 0.48939645290374756 2023-01-23 16:33:19.030895: step: 2174/1545, loss: 0.5012385249137878 2023-01-23 16:33:19.933815: step: 2176/1545, loss: 0.07789761573076248 2023-01-23 16:33:20.842512: step: 2178/1545, loss: 0.029778199270367622 2023-01-23 16:33:21.704246: step: 2180/1545, loss: 0.008799456059932709 2023-01-23 16:33:22.632339: step: 2182/1545, loss: 0.09768345952033997 2023-01-23 16:33:23.539745: step: 2184/1545, loss: 0.0540422648191452 2023-01-23 16:33:24.414968: step: 2186/1545, loss: 0.014534588903188705 2023-01-23 16:33:25.264543: step: 2188/1545, loss: 0.0648735836148262 2023-01-23 16:33:26.192900: step: 2190/1545, loss: 0.004837897140532732 2023-01-23 16:33:27.065969: step: 2192/1545, loss: 0.0007066599209792912 2023-01-23 16:33:27.943253: step: 2194/1545, loss: 0.0026493954937905073 2023-01-23 16:33:28.890524: step: 2196/1545, loss: 0.030794449150562286 2023-01-23 16:33:29.792403: step: 2198/1545, loss: 0.0012919611763209105 2023-01-23 16:33:30.680621: step: 2200/1545, loss: 0.0010620169341564178 2023-01-23 16:33:31.570496: step: 2202/1545, loss: 0.0014832069864496589 2023-01-23 16:33:32.395395: step: 2204/1545, loss: 0.2779094874858856 2023-01-23 16:33:33.244463: step: 2206/1545, loss: 0.1445976346731186 2023-01-23 16:33:34.081405: step: 2208/1545, loss: 0.0016721831634640694 2023-01-23 16:33:34.952906: step: 2210/1545, loss: 0.0004870512639172375 2023-01-23 16:33:35.828942: step: 2212/1545, loss: 0.17414580285549164 2023-01-23 16:33:36.742491: step: 2214/1545, loss: 0.04152275249361992 2023-01-23 16:33:37.641028: step: 2216/1545, loss: 0.07950115203857422 2023-01-23 16:33:38.560483: step: 2218/1545, loss: 0.0007543818210251629 2023-01-23 16:33:39.497200: step: 2220/1545, loss: 0.07735057175159454 2023-01-23 16:33:40.331968: step: 2222/1545, loss: 0.005107632838189602 2023-01-23 16:33:41.182363: step: 2224/1545, loss: 0.0018324191914871335 2023-01-23 16:33:42.062524: step: 2226/1545, loss: 0.09548430889844894 2023-01-23 16:33:42.896038: step: 2228/1545, loss: 0.0035538687370717525 2023-01-23 16:33:43.784729: step: 2230/1545, loss: 0.07483934611082077 2023-01-23 16:33:44.639894: step: 2232/1545, loss: 0.002095598727464676 2023-01-23 16:33:45.541973: step: 2234/1545, loss: 0.07394354045391083 2023-01-23 16:33:46.388910: step: 2236/1545, loss: 0.010901746340095997 2023-01-23 16:33:47.283013: step: 2238/1545, loss: 0.05092345550656319 2023-01-23 16:33:48.157660: step: 2240/1545, loss: 0.0057236202992498875 2023-01-23 16:33:49.023112: step: 2242/1545, loss: 0.005579904653131962 2023-01-23 16:33:49.894161: step: 2244/1545, loss: 0.10279867053031921 2023-01-23 16:33:50.758318: step: 2246/1545, loss: 0.1065409928560257 2023-01-23 16:33:51.647703: step: 2248/1545, loss: 0.08867296576499939 2023-01-23 16:33:52.500714: step: 2250/1545, loss: 0.00011371588334441185 2023-01-23 16:33:53.390847: step: 2252/1545, loss: 0.003984589129686356 2023-01-23 16:33:54.237874: step: 2254/1545, loss: 0.008183235302567482 2023-01-23 16:33:55.115236: step: 2256/1545, loss: 0.0015000710263848305 2023-01-23 16:33:55.994066: step: 2258/1545, loss: 0.020901469513773918 2023-01-23 16:33:56.871252: step: 2260/1545, loss: 0.009315500035881996 2023-01-23 16:33:57.746408: step: 2262/1545, loss: 0.00024009571643546224 2023-01-23 16:33:58.591330: step: 2264/1545, loss: 0.03520187735557556 2023-01-23 16:33:59.490381: step: 2266/1545, loss: 0.003810740541666746 2023-01-23 16:34:00.364964: step: 2268/1545, loss: 0.10784301161766052 2023-01-23 16:34:01.210338: step: 2270/1545, loss: 0.004425408784300089 2023-01-23 16:34:02.149871: step: 2272/1545, loss: 0.2252717912197113 2023-01-23 16:34:03.048342: step: 2274/1545, loss: 0.005798778496682644 2023-01-23 16:34:03.975046: step: 2276/1545, loss: 0.13138335943222046 2023-01-23 16:34:04.865009: step: 2278/1545, loss: 0.0001435408485122025 2023-01-23 16:34:05.764976: step: 2280/1545, loss: 0.0037462464533746243 2023-01-23 16:34:06.643869: step: 2282/1545, loss: 0.003826938569545746 2023-01-23 16:34:07.544001: step: 2284/1545, loss: 0.4126252830028534 2023-01-23 16:34:08.451820: step: 2286/1545, loss: 0.005943189840763807 2023-01-23 16:34:09.382342: step: 2288/1545, loss: 0.00023274868726730347 2023-01-23 16:34:10.262489: step: 2290/1545, loss: 0.004763432778418064 2023-01-23 16:34:11.103483: step: 2292/1545, loss: 0.024892473593354225 2023-01-23 16:34:11.996189: step: 2294/1545, loss: 0.08865343779325485 2023-01-23 16:34:12.885272: step: 2296/1545, loss: 0.0004493265296332538 2023-01-23 16:34:13.740162: step: 2298/1545, loss: 0.013032364659011364 2023-01-23 16:34:14.622349: step: 2300/1545, loss: 0.008180538192391396 2023-01-23 16:34:15.501709: step: 2302/1545, loss: 0.0016211022157222033 2023-01-23 16:34:16.339176: step: 2304/1545, loss: 0.00258920481428504 2023-01-23 16:34:17.196573: step: 2306/1545, loss: 0.003088823752477765 2023-01-23 16:34:18.124933: step: 2308/1545, loss: 0.013689744286239147 2023-01-23 16:34:19.017910: step: 2310/1545, loss: 0.1140175610780716 2023-01-23 16:34:19.874180: step: 2312/1545, loss: 0.027654865756630898 2023-01-23 16:34:20.758237: step: 2314/1545, loss: 0.1564522534608841 2023-01-23 16:34:21.606341: step: 2316/1545, loss: 0.03330758586525917 2023-01-23 16:34:22.536065: step: 2318/1545, loss: 0.21160165965557098 2023-01-23 16:34:23.415087: step: 2320/1545, loss: 0.018965309485793114 2023-01-23 16:34:24.295683: step: 2322/1545, loss: 0.10212406516075134 2023-01-23 16:34:25.154504: step: 2324/1545, loss: 0.0014938025269657373 2023-01-23 16:34:26.073684: step: 2326/1545, loss: 0.0002650057431310415 2023-01-23 16:34:26.984447: step: 2328/1545, loss: 0.00018907427147496492 2023-01-23 16:34:27.950139: step: 2330/1545, loss: 0.02808256819844246 2023-01-23 16:34:28.796674: step: 2332/1545, loss: 0.08670113980770111 2023-01-23 16:34:29.699286: step: 2334/1545, loss: 0.010618233121931553 2023-01-23 16:34:30.647259: step: 2336/1545, loss: 0.004267760086804628 2023-01-23 16:34:31.514586: step: 2338/1545, loss: 0.3449133038520813 2023-01-23 16:34:32.387895: step: 2340/1545, loss: 0.11838515102863312 2023-01-23 16:34:33.249694: step: 2342/1545, loss: 0.00229661981575191 2023-01-23 16:34:34.112472: step: 2344/1545, loss: 0.0011009708978235722 2023-01-23 16:34:34.975053: step: 2346/1545, loss: 0.012952011078596115 2023-01-23 16:34:35.830952: step: 2348/1545, loss: 0.000806666910648346 2023-01-23 16:34:36.714291: step: 2350/1545, loss: 0.000721832737326622 2023-01-23 16:34:37.601669: step: 2352/1545, loss: 0.007686017081141472 2023-01-23 16:34:38.464128: step: 2354/1545, loss: 0.00022870107204653323 2023-01-23 16:34:39.371324: step: 2356/1545, loss: 0.012353548780083656 2023-01-23 16:34:40.186838: step: 2358/1545, loss: 0.0018691474106162786 2023-01-23 16:34:41.023145: step: 2360/1545, loss: 0.013273158110678196 2023-01-23 16:34:42.014986: step: 2362/1545, loss: 0.0961182564496994 2023-01-23 16:34:42.894103: step: 2364/1545, loss: 1.3387553691864014 2023-01-23 16:34:43.835301: step: 2366/1545, loss: 0.0400911420583725 2023-01-23 16:34:44.753851: step: 2368/1545, loss: 0.004784013610333204 2023-01-23 16:34:45.634856: step: 2370/1545, loss: 0.037518687546253204 2023-01-23 16:34:46.482251: step: 2372/1545, loss: 0.0184730626642704 2023-01-23 16:34:47.400939: step: 2374/1545, loss: 0.2308465987443924 2023-01-23 16:34:48.273460: step: 2376/1545, loss: 0.41091617941856384 2023-01-23 16:34:49.134641: step: 2378/1545, loss: 0.0004969600704498589 2023-01-23 16:34:50.022011: step: 2380/1545, loss: 0.006010938435792923 2023-01-23 16:34:50.869879: step: 2382/1545, loss: 0.0148985106498003 2023-01-23 16:34:51.793085: step: 2384/1545, loss: 0.033168595284223557 2023-01-23 16:34:52.654514: step: 2386/1545, loss: 0.08773106336593628 2023-01-23 16:34:53.537994: step: 2388/1545, loss: 0.15633076429367065 2023-01-23 16:34:54.420869: step: 2390/1545, loss: 0.01980934850871563 2023-01-23 16:34:55.287167: step: 2392/1545, loss: 0.019289420917630196 2023-01-23 16:34:56.155383: step: 2394/1545, loss: 0.23545926809310913 2023-01-23 16:34:57.054523: step: 2396/1545, loss: 0.069552943110466 2023-01-23 16:34:57.974502: step: 2398/1545, loss: 0.009852113202214241 2023-01-23 16:34:58.870345: step: 2400/1545, loss: 0.27192285656929016 2023-01-23 16:34:59.757198: step: 2402/1545, loss: 0.006059544160962105 2023-01-23 16:35:00.653650: step: 2404/1545, loss: 0.12474320083856583 2023-01-23 16:35:01.512928: step: 2406/1545, loss: 0.0008062551496550441 2023-01-23 16:35:02.362043: step: 2408/1545, loss: 0.017670005559921265 2023-01-23 16:35:03.351146: step: 2410/1545, loss: 0.03874098137021065 2023-01-23 16:35:04.224030: step: 2412/1545, loss: 0.019382694736123085 2023-01-23 16:35:05.064117: step: 2414/1545, loss: 0.00934889167547226 2023-01-23 16:35:05.886077: step: 2416/1545, loss: 0.007978426292538643 2023-01-23 16:35:06.773391: step: 2418/1545, loss: 0.0031269285827875137 2023-01-23 16:35:07.662585: step: 2420/1545, loss: 0.02127474546432495 2023-01-23 16:35:08.565084: step: 2422/1545, loss: 0.019551094621419907 2023-01-23 16:35:09.392404: step: 2424/1545, loss: 0.0006344970897771418 2023-01-23 16:35:10.249485: step: 2426/1545, loss: 0.014156553894281387 2023-01-23 16:35:11.100993: step: 2428/1545, loss: 0.002919655293226242 2023-01-23 16:35:12.006167: step: 2430/1545, loss: 0.0065628658048808575 2023-01-23 16:35:12.881904: step: 2432/1545, loss: 0.11278662085533142 2023-01-23 16:35:13.756579: step: 2434/1545, loss: 0.01335984282195568 2023-01-23 16:35:14.609504: step: 2436/1545, loss: 0.04692929983139038 2023-01-23 16:35:15.461409: step: 2438/1545, loss: 0.0013265046291053295 2023-01-23 16:35:16.355485: step: 2440/1545, loss: 0.014019286260008812 2023-01-23 16:35:17.213872: step: 2442/1545, loss: 0.002830970799550414 2023-01-23 16:35:18.119896: step: 2444/1545, loss: 0.031554002314805984 2023-01-23 16:35:19.031701: step: 2446/1545, loss: 0.0035693440586328506 2023-01-23 16:35:19.918571: step: 2448/1545, loss: 0.02805965393781662 2023-01-23 16:35:20.821926: step: 2450/1545, loss: 0.015298563055694103 2023-01-23 16:35:21.703414: step: 2452/1545, loss: 0.17431549727916718 2023-01-23 16:35:22.555125: step: 2454/1545, loss: 0.10341125726699829 2023-01-23 16:35:23.439097: step: 2456/1545, loss: 0.230977863073349 2023-01-23 16:35:24.360174: step: 2458/1545, loss: 0.11048030853271484 2023-01-23 16:35:25.230002: step: 2460/1545, loss: 0.015046828426420689 2023-01-23 16:35:26.095212: step: 2462/1545, loss: 0.026122968643903732 2023-01-23 16:35:27.026425: step: 2464/1545, loss: 0.021587729454040527 2023-01-23 16:35:27.945364: step: 2466/1545, loss: 0.311484694480896 2023-01-23 16:35:28.834729: step: 2468/1545, loss: 0.007208275608718395 2023-01-23 16:35:29.719626: step: 2470/1545, loss: 0.010713738389313221 2023-01-23 16:35:30.597981: step: 2472/1545, loss: 0.10365824401378632 2023-01-23 16:35:31.585651: step: 2474/1545, loss: 0.3804302513599396 2023-01-23 16:35:32.441885: step: 2476/1545, loss: 0.002357733901590109 2023-01-23 16:35:33.351512: step: 2478/1545, loss: 0.0048690796829760075 2023-01-23 16:35:34.244958: step: 2480/1545, loss: 0.0024114814586937428 2023-01-23 16:35:35.152093: step: 2482/1545, loss: 0.0943128913640976 2023-01-23 16:35:36.004644: step: 2484/1545, loss: 0.1010085865855217 2023-01-23 16:35:36.893951: step: 2486/1545, loss: 0.8122329711914062 2023-01-23 16:35:37.803595: step: 2488/1545, loss: 0.014723883010447025 2023-01-23 16:35:38.690828: step: 2490/1545, loss: 0.151265949010849 2023-01-23 16:35:39.604395: step: 2492/1545, loss: 0.09914501011371613 2023-01-23 16:35:40.543296: step: 2494/1545, loss: 0.08110282570123672 2023-01-23 16:35:41.473264: step: 2496/1545, loss: 0.002883625915274024 2023-01-23 16:35:42.359794: step: 2498/1545, loss: 0.12710174918174744 2023-01-23 16:35:43.303065: step: 2500/1545, loss: 0.00715608848258853 2023-01-23 16:35:44.161495: step: 2502/1545, loss: 0.05802614241838455 2023-01-23 16:35:45.015589: step: 2504/1545, loss: 0.01081071887165308 2023-01-23 16:35:45.881796: step: 2506/1545, loss: 0.013753833249211311 2023-01-23 16:35:46.714357: step: 2508/1545, loss: 0.138975128531456 2023-01-23 16:35:47.577889: step: 2510/1545, loss: 0.006542776245623827 2023-01-23 16:35:48.464334: step: 2512/1545, loss: 0.009608262218534946 2023-01-23 16:35:49.306775: step: 2514/1545, loss: 0.09631204605102539 2023-01-23 16:35:50.200976: step: 2516/1545, loss: 0.243724524974823 2023-01-23 16:35:51.053986: step: 2518/1545, loss: 0.21176739037036896 2023-01-23 16:35:51.931571: step: 2520/1545, loss: 0.08073675632476807 2023-01-23 16:35:52.843630: step: 2522/1545, loss: 0.0663774162530899 2023-01-23 16:35:53.724986: step: 2524/1545, loss: 0.0034813147503882647 2023-01-23 16:35:54.629602: step: 2526/1545, loss: 0.1541699767112732 2023-01-23 16:35:55.519654: step: 2528/1545, loss: 0.11684421449899673 2023-01-23 16:35:56.434888: step: 2530/1545, loss: 0.05005338042974472 2023-01-23 16:35:57.288097: step: 2532/1545, loss: 0.02267218753695488 2023-01-23 16:35:58.175126: step: 2534/1545, loss: 0.8445757627487183 2023-01-23 16:35:59.039577: step: 2536/1545, loss: 0.0033377204090356827 2023-01-23 16:35:59.901765: step: 2538/1545, loss: 0.12071043998003006 2023-01-23 16:36:00.837274: step: 2540/1545, loss: 0.012395139783620834 2023-01-23 16:36:01.685268: step: 2542/1545, loss: 0.0024518861901015043 2023-01-23 16:36:02.569850: step: 2544/1545, loss: 0.07949266582727432 2023-01-23 16:36:03.446767: step: 2546/1545, loss: 0.00018673365411814302 2023-01-23 16:36:04.317113: step: 2548/1545, loss: 0.0017516474472358823 2023-01-23 16:36:05.246302: step: 2550/1545, loss: 0.03308488056063652 2023-01-23 16:36:06.114200: step: 2552/1545, loss: 0.0006964228232391179 2023-01-23 16:36:07.055063: step: 2554/1545, loss: 0.0025400931481271982 2023-01-23 16:36:08.019649: step: 2556/1545, loss: 0.011136384680867195 2023-01-23 16:36:08.899447: step: 2558/1545, loss: 0.16915938258171082 2023-01-23 16:36:09.772693: step: 2560/1545, loss: 0.28652718663215637 2023-01-23 16:36:10.651243: step: 2562/1545, loss: 0.28916284441947937 2023-01-23 16:36:11.543484: step: 2564/1545, loss: 0.2039843648672104 2023-01-23 16:36:12.427209: step: 2566/1545, loss: 0.0021086009219288826 2023-01-23 16:36:13.329526: step: 2568/1545, loss: 0.0036868592724204063 2023-01-23 16:36:14.244320: step: 2570/1545, loss: 0.11902756989002228 2023-01-23 16:36:15.107008: step: 2572/1545, loss: 0.012261766009032726 2023-01-23 16:36:15.995891: step: 2574/1545, loss: 0.007503285072743893 2023-01-23 16:36:16.909131: step: 2576/1545, loss: 0.0054590352810919285 2023-01-23 16:36:17.811072: step: 2578/1545, loss: 0.07754495739936829 2023-01-23 16:36:18.664363: step: 2580/1545, loss: 0.0007056217291392386 2023-01-23 16:36:19.506672: step: 2582/1545, loss: 0.00823292788118124 2023-01-23 16:36:20.385310: step: 2584/1545, loss: 0.05572296679019928 2023-01-23 16:36:21.252160: step: 2586/1545, loss: 0.0029020369984209538 2023-01-23 16:36:22.115256: step: 2588/1545, loss: 0.18589213490486145 2023-01-23 16:36:22.980801: step: 2590/1545, loss: 0.00037753768265247345 2023-01-23 16:36:23.847754: step: 2592/1545, loss: 0.011852321214973927 2023-01-23 16:36:24.750951: step: 2594/1545, loss: 1.5736595392227173 2023-01-23 16:36:25.642656: step: 2596/1545, loss: 0.009171850979328156 2023-01-23 16:36:26.525905: step: 2598/1545, loss: 0.0027619448956102133 2023-01-23 16:36:27.421801: step: 2600/1545, loss: 0.003388425800949335 2023-01-23 16:36:28.297228: step: 2602/1545, loss: 0.0164059828966856 2023-01-23 16:36:29.137332: step: 2604/1545, loss: 0.0031827022321522236 2023-01-23 16:36:29.995638: step: 2606/1545, loss: 0.15779341757297516 2023-01-23 16:36:30.882062: step: 2608/1545, loss: 0.008403735235333443 2023-01-23 16:36:31.773879: step: 2610/1545, loss: 0.22030001878738403 2023-01-23 16:36:32.691761: step: 2612/1545, loss: 0.0030098920688033104 2023-01-23 16:36:33.545618: step: 2614/1545, loss: 0.01382536068558693 2023-01-23 16:36:34.376783: step: 2616/1545, loss: 0.01415107399225235 2023-01-23 16:36:35.303726: step: 2618/1545, loss: 0.0034149412531405687 2023-01-23 16:36:36.163026: step: 2620/1545, loss: 1.1033546924591064 2023-01-23 16:36:37.027136: step: 2622/1545, loss: 0.16938617825508118 2023-01-23 16:36:37.925703: step: 2624/1545, loss: 0.005862072110176086 2023-01-23 16:36:38.803632: step: 2626/1545, loss: 0.003142663510516286 2023-01-23 16:36:39.704013: step: 2628/1545, loss: 0.017005478963255882 2023-01-23 16:36:40.578838: step: 2630/1545, loss: 0.004358605016022921 2023-01-23 16:36:41.538617: step: 2632/1545, loss: 0.004033560864627361 2023-01-23 16:36:42.368690: step: 2634/1545, loss: 0.30849775671958923 2023-01-23 16:36:43.240827: step: 2636/1545, loss: 0.0024757306091487408 2023-01-23 16:36:44.080750: step: 2638/1545, loss: 0.00792225357145071 2023-01-23 16:36:44.939471: step: 2640/1545, loss: 0.1938828080892563 2023-01-23 16:36:45.837151: step: 2642/1545, loss: 0.0013792664976790547 2023-01-23 16:36:46.703872: step: 2644/1545, loss: 0.00011425239790696651 2023-01-23 16:36:47.553125: step: 2646/1545, loss: 0.0004029946867376566 2023-01-23 16:36:48.418378: step: 2648/1545, loss: 0.00020106772717554122 2023-01-23 16:36:49.294539: step: 2650/1545, loss: 0.6571094989776611 2023-01-23 16:36:50.130423: step: 2652/1545, loss: 0.04177357256412506 2023-01-23 16:36:51.031090: step: 2654/1545, loss: 0.0002700410841498524 2023-01-23 16:36:51.931270: step: 2656/1545, loss: 0.0181089099496603 2023-01-23 16:36:52.845372: step: 2658/1545, loss: 0.779451847076416 2023-01-23 16:36:53.734599: step: 2660/1545, loss: 0.010094085708260536 2023-01-23 16:36:54.642908: step: 2662/1545, loss: 0.014194780960679054 2023-01-23 16:36:55.530185: step: 2664/1545, loss: 0.015175617299973965 2023-01-23 16:36:56.360904: step: 2666/1545, loss: 0.032954923808574677 2023-01-23 16:36:57.361904: step: 2668/1545, loss: 0.046367306262254715 2023-01-23 16:36:58.228999: step: 2670/1545, loss: 0.004343654029071331 2023-01-23 16:36:59.103966: step: 2672/1545, loss: 0.30354219675064087 2023-01-23 16:36:59.953569: step: 2674/1545, loss: 0.000981590012088418 2023-01-23 16:37:00.829610: step: 2676/1545, loss: 0.1415695697069168 2023-01-23 16:37:01.715260: step: 2678/1545, loss: 0.13824507594108582 2023-01-23 16:37:02.581364: step: 2680/1545, loss: 0.031893834471702576 2023-01-23 16:37:03.419051: step: 2682/1545, loss: 0.5961582660675049 2023-01-23 16:37:04.303282: step: 2684/1545, loss: 0.2992778420448303 2023-01-23 16:37:05.202691: step: 2686/1545, loss: 0.03480863571166992 2023-01-23 16:37:06.083741: step: 2688/1545, loss: 0.0003326104488223791 2023-01-23 16:37:06.930210: step: 2690/1545, loss: 0.4055735766887665 2023-01-23 16:37:07.814323: step: 2692/1545, loss: 0.1995345652103424 2023-01-23 16:37:08.688059: step: 2694/1545, loss: 0.1272173970937729 2023-01-23 16:37:09.598098: step: 2696/1545, loss: 0.014024950563907623 2023-01-23 16:37:10.460348: step: 2698/1545, loss: 0.06290949136018753 2023-01-23 16:37:11.334113: step: 2700/1545, loss: 0.2419895976781845 2023-01-23 16:37:12.191828: step: 2702/1545, loss: 0.04169411584734917 2023-01-23 16:37:13.099943: step: 2704/1545, loss: 0.07386305928230286 2023-01-23 16:37:13.940011: step: 2706/1545, loss: 0.12108872085809708 2023-01-23 16:37:14.906724: step: 2708/1545, loss: 0.05602741613984108 2023-01-23 16:37:15.779515: step: 2710/1545, loss: 0.008488591760396957 2023-01-23 16:37:16.739510: step: 2712/1545, loss: 0.09960426390171051 2023-01-23 16:37:17.594086: step: 2714/1545, loss: 0.11713701486587524 2023-01-23 16:37:18.464557: step: 2716/1545, loss: 0.004573732614517212 2023-01-23 16:37:19.357269: step: 2718/1545, loss: 0.001713769044727087 2023-01-23 16:37:20.223863: step: 2720/1545, loss: 0.1112479418516159 2023-01-23 16:37:21.140435: step: 2722/1545, loss: 0.9910270571708679 2023-01-23 16:37:22.019015: step: 2724/1545, loss: 0.007614501286298037 2023-01-23 16:37:22.928232: step: 2726/1545, loss: 0.0006555093568749726 2023-01-23 16:37:23.851503: step: 2728/1545, loss: 0.03377349302172661 2023-01-23 16:37:24.688320: step: 2730/1545, loss: 0.014193778857588768 2023-01-23 16:37:25.577213: step: 2732/1545, loss: 0.017952555790543556 2023-01-23 16:37:26.463005: step: 2734/1545, loss: 0.12937374413013458 2023-01-23 16:37:27.333746: step: 2736/1545, loss: 0.19753944873809814 2023-01-23 16:37:28.287682: step: 2738/1545, loss: 0.11212626844644547 2023-01-23 16:37:29.141373: step: 2740/1545, loss: 0.3334752023220062 2023-01-23 16:37:30.028894: step: 2742/1545, loss: 0.04127463325858116 2023-01-23 16:37:30.856783: step: 2744/1545, loss: 0.000686637416947633 2023-01-23 16:37:31.749463: step: 2746/1545, loss: 0.4907594621181488 2023-01-23 16:37:32.605858: step: 2748/1545, loss: 0.008216261863708496 2023-01-23 16:37:33.471916: step: 2750/1545, loss: 0.0016826546052470803 2023-01-23 16:37:34.379790: step: 2752/1545, loss: 0.07563826441764832 2023-01-23 16:37:35.209978: step: 2754/1545, loss: 0.05141837149858475 2023-01-23 16:37:36.078339: step: 2756/1545, loss: 0.3104201853275299 2023-01-23 16:37:36.978169: step: 2758/1545, loss: 0.007360242772847414 2023-01-23 16:37:37.878804: step: 2760/1545, loss: 0.024230437353253365 2023-01-23 16:37:38.714519: step: 2762/1545, loss: 0.09642429649829865 2023-01-23 16:37:39.617584: step: 2764/1545, loss: 0.13908980786800385 2023-01-23 16:37:40.453107: step: 2766/1545, loss: 0.007632268592715263 2023-01-23 16:37:41.357574: step: 2768/1545, loss: 0.19319812953472137 2023-01-23 16:37:42.388663: step: 2770/1545, loss: 0.06722202897071838 2023-01-23 16:37:43.278078: step: 2772/1545, loss: 0.13046368956565857 2023-01-23 16:37:44.122883: step: 2774/1545, loss: 0.08281245082616806 2023-01-23 16:37:45.028065: step: 2776/1545, loss: 0.005784216802567244 2023-01-23 16:37:45.881477: step: 2778/1545, loss: 0.025863120332360268 2023-01-23 16:37:46.719131: step: 2780/1545, loss: 0.19836069643497467 2023-01-23 16:37:47.589603: step: 2782/1545, loss: 0.00018884996825363487 2023-01-23 16:37:48.511726: step: 2784/1545, loss: 0.0001519538345746696 2023-01-23 16:37:49.432354: step: 2786/1545, loss: 0.008027208037674427 2023-01-23 16:37:50.276712: step: 2788/1545, loss: 0.0025254078209400177 2023-01-23 16:37:51.123407: step: 2790/1545, loss: 0.051346320658922195 2023-01-23 16:37:51.971822: step: 2792/1545, loss: 0.19038379192352295 2023-01-23 16:37:52.837506: step: 2794/1545, loss: 0.005134037230163813 2023-01-23 16:37:53.706356: step: 2796/1545, loss: 0.041030190885066986 2023-01-23 16:37:54.560377: step: 2798/1545, loss: 0.012256080284714699 2023-01-23 16:37:55.443981: step: 2800/1545, loss: 0.01873908005654812 2023-01-23 16:37:56.308763: step: 2802/1545, loss: 0.10552741587162018 2023-01-23 16:37:57.195627: step: 2804/1545, loss: 0.15804246068000793 2023-01-23 16:37:58.082877: step: 2806/1545, loss: 0.04719513654708862 2023-01-23 16:37:58.977071: step: 2808/1545, loss: 0.0644037276506424 2023-01-23 16:37:59.878904: step: 2810/1545, loss: 0.0037838604766875505 2023-01-23 16:38:00.716657: step: 2812/1545, loss: 0.01187439076602459 2023-01-23 16:38:01.588840: step: 2814/1545, loss: 0.007225820794701576 2023-01-23 16:38:02.470187: step: 2816/1545, loss: 0.02250586822628975 2023-01-23 16:38:03.341301: step: 2818/1545, loss: 0.0005099305417388678 2023-01-23 16:38:04.195684: step: 2820/1545, loss: 0.00024995554122142494 2023-01-23 16:38:05.101710: step: 2822/1545, loss: 0.003246710868552327 2023-01-23 16:38:05.997580: step: 2824/1545, loss: 0.15526235103607178 2023-01-23 16:38:06.853738: step: 2826/1545, loss: 0.00627791415899992 2023-01-23 16:38:07.751030: step: 2828/1545, loss: 0.0007671560160815716 2023-01-23 16:38:08.659846: step: 2830/1545, loss: 0.054846372455358505 2023-01-23 16:38:09.512433: step: 2832/1545, loss: 0.04583979770541191 2023-01-23 16:38:10.365958: step: 2834/1545, loss: 0.0005338898627087474 2023-01-23 16:38:11.210869: step: 2836/1545, loss: 0.003874225541949272 2023-01-23 16:38:12.087360: step: 2838/1545, loss: 0.02443085052073002 2023-01-23 16:38:13.010320: step: 2840/1545, loss: 0.023012109100818634 2023-01-23 16:38:13.922239: step: 2842/1545, loss: 1.6895225048065186 2023-01-23 16:38:14.744955: step: 2844/1545, loss: 0.0010066496906802058 2023-01-23 16:38:15.630242: step: 2846/1545, loss: 0.00457490049302578 2023-01-23 16:38:16.546666: step: 2848/1545, loss: 0.05620308220386505 2023-01-23 16:38:17.461206: step: 2850/1545, loss: 0.024417642503976822 2023-01-23 16:38:18.342618: step: 2852/1545, loss: 0.005438277963548899 2023-01-23 16:38:19.277889: step: 2854/1545, loss: 0.1520845741033554 2023-01-23 16:38:20.133998: step: 2856/1545, loss: 0.09552409499883652 2023-01-23 16:38:21.019589: step: 2858/1545, loss: 0.01144860964268446 2023-01-23 16:38:21.869632: step: 2860/1545, loss: 0.006422712001949549 2023-01-23 16:38:22.733309: step: 2862/1545, loss: 0.0029410969000309706 2023-01-23 16:38:23.618365: step: 2864/1545, loss: 0.03783624991774559 2023-01-23 16:38:24.458174: step: 2866/1545, loss: 0.00043982904753647745 2023-01-23 16:38:25.320897: step: 2868/1545, loss: 0.019627153873443604 2023-01-23 16:38:26.203891: step: 2870/1545, loss: 0.2020215541124344 2023-01-23 16:38:27.072062: step: 2872/1545, loss: 0.04701341688632965 2023-01-23 16:38:27.946500: step: 2874/1545, loss: 0.003212875919416547 2023-01-23 16:38:28.835641: step: 2876/1545, loss: 0.0017342069186270237 2023-01-23 16:38:29.762600: step: 2878/1545, loss: 0.0005141739966347814 2023-01-23 16:38:30.642844: step: 2880/1545, loss: 0.0002416549250483513 2023-01-23 16:38:31.468297: step: 2882/1545, loss: 0.022323884069919586 2023-01-23 16:38:32.355403: step: 2884/1545, loss: 0.0002520690322853625 2023-01-23 16:38:33.201640: step: 2886/1545, loss: 0.013506853953003883 2023-01-23 16:38:34.064075: step: 2888/1545, loss: 0.05611491948366165 2023-01-23 16:38:34.939108: step: 2890/1545, loss: 0.0019081021891906857 2023-01-23 16:38:35.794761: step: 2892/1545, loss: 0.0004395738651510328 2023-01-23 16:38:36.675020: step: 2894/1545, loss: 0.0996299535036087 2023-01-23 16:38:37.644932: step: 2896/1545, loss: 0.0009959402959793806 2023-01-23 16:38:38.565459: step: 2898/1545, loss: 0.058635979890823364 2023-01-23 16:38:39.410900: step: 2900/1545, loss: 0.003144580405205488 2023-01-23 16:38:40.264079: step: 2902/1545, loss: 0.03796225041151047 2023-01-23 16:38:41.129776: step: 2904/1545, loss: 0.04668720066547394 2023-01-23 16:38:41.972311: step: 2906/1545, loss: 0.06668999791145325 2023-01-23 16:38:42.830950: step: 2908/1545, loss: 0.2580302655696869 2023-01-23 16:38:43.756042: step: 2910/1545, loss: 0.0012717117788270116 2023-01-23 16:38:44.632401: step: 2912/1545, loss: 0.014978191815316677 2023-01-23 16:38:45.539184: step: 2914/1545, loss: 0.0002537436375860125 2023-01-23 16:38:46.408230: step: 2916/1545, loss: 0.003120326204225421 2023-01-23 16:38:47.252801: step: 2918/1545, loss: 0.024841036647558212 2023-01-23 16:38:48.179395: step: 2920/1545, loss: 0.37681013345718384 2023-01-23 16:38:49.066180: step: 2922/1545, loss: 0.09296832978725433 2023-01-23 16:38:49.953497: step: 2924/1545, loss: 0.04936020448803902 2023-01-23 16:38:50.842353: step: 2926/1545, loss: 0.007474453654140234 2023-01-23 16:38:51.685849: step: 2928/1545, loss: 0.00894913449883461 2023-01-23 16:38:52.555810: step: 2930/1545, loss: 0.0032862848602235317 2023-01-23 16:38:53.467939: step: 2932/1545, loss: 0.017016194760799408 2023-01-23 16:38:54.316872: step: 2934/1545, loss: 0.0004372264666017145 2023-01-23 16:38:55.215760: step: 2936/1545, loss: 0.41577282547950745 2023-01-23 16:38:56.108599: step: 2938/1545, loss: 0.0001141265092883259 2023-01-23 16:38:56.977495: step: 2940/1545, loss: 0.12578314542770386 2023-01-23 16:38:57.889914: step: 2942/1545, loss: 0.021059300750494003 2023-01-23 16:38:58.740973: step: 2944/1545, loss: 0.04168184846639633 2023-01-23 16:38:59.605425: step: 2946/1545, loss: 0.4357381761074066 2023-01-23 16:39:00.544375: step: 2948/1545, loss: 0.2575896382331848 2023-01-23 16:39:01.481712: step: 2950/1545, loss: 0.1708110272884369 2023-01-23 16:39:02.350302: step: 2952/1545, loss: 0.1861308068037033 2023-01-23 16:39:03.247901: step: 2954/1545, loss: 0.13436450064182281 2023-01-23 16:39:04.114030: step: 2956/1545, loss: 0.007386655546724796 2023-01-23 16:39:04.984141: step: 2958/1545, loss: 0.008624183014035225 2023-01-23 16:39:05.948400: step: 2960/1545, loss: 0.27959007024765015 2023-01-23 16:39:06.812168: step: 2962/1545, loss: 0.0005675412248820066 2023-01-23 16:39:07.655870: step: 2964/1545, loss: 0.3632243871688843 2023-01-23 16:39:08.539619: step: 2966/1545, loss: 0.05330752581357956 2023-01-23 16:39:09.426771: step: 2968/1545, loss: 0.02184324525296688 2023-01-23 16:39:10.261958: step: 2970/1545, loss: 0.09681065380573273 2023-01-23 16:39:11.118653: step: 2972/1545, loss: 0.17974062263965607 2023-01-23 16:39:12.002772: step: 2974/1545, loss: 0.728522777557373 2023-01-23 16:39:12.903271: step: 2976/1545, loss: 0.1886323243379593 2023-01-23 16:39:13.872765: step: 2978/1545, loss: 0.0038306284695863724 2023-01-23 16:39:14.754092: step: 2980/1545, loss: 0.1763043999671936 2023-01-23 16:39:15.607376: step: 2982/1545, loss: 0.011447050608694553 2023-01-23 16:39:16.481690: step: 2984/1545, loss: 0.048947982490062714 2023-01-23 16:39:17.323666: step: 2986/1545, loss: 0.019754085689783096 2023-01-23 16:39:18.289213: step: 2988/1545, loss: 0.38061633706092834 2023-01-23 16:39:19.203484: step: 2990/1545, loss: 0.005077298730611801 2023-01-23 16:39:20.070159: step: 2992/1545, loss: 0.004550740588456392 2023-01-23 16:39:20.949277: step: 2994/1545, loss: 0.02685166895389557 2023-01-23 16:39:21.942492: step: 2996/1545, loss: 0.07163701951503754 2023-01-23 16:39:22.834683: step: 2998/1545, loss: 0.07709604501724243 2023-01-23 16:39:23.719971: step: 3000/1545, loss: 0.0004463868390303105 2023-01-23 16:39:24.586658: step: 3002/1545, loss: 0.010403601452708244 2023-01-23 16:39:25.413503: step: 3004/1545, loss: 0.0035357840824872255 2023-01-23 16:39:26.344536: step: 3006/1545, loss: 0.0030972573440521955 2023-01-23 16:39:27.245181: step: 3008/1545, loss: 0.00031658835359849036 2023-01-23 16:39:28.144994: step: 3010/1545, loss: 0.039769839495420456 2023-01-23 16:39:29.032683: step: 3012/1545, loss: 0.1227569729089737 2023-01-23 16:39:29.878441: step: 3014/1545, loss: 0.01992928609251976 2023-01-23 16:39:30.777653: step: 3016/1545, loss: 0.016555320471525192 2023-01-23 16:39:31.609335: step: 3018/1545, loss: 0.0165602657943964 2023-01-23 16:39:32.478502: step: 3020/1545, loss: 0.014716683886945248 2023-01-23 16:39:33.394299: step: 3022/1545, loss: 0.19291046261787415 2023-01-23 16:39:34.271626: step: 3024/1545, loss: 0.0025823337491601706 2023-01-23 16:39:35.179671: step: 3026/1545, loss: 0.0004317452840041369 2023-01-23 16:39:36.052667: step: 3028/1545, loss: 0.0017462449613958597 2023-01-23 16:39:36.946982: step: 3030/1545, loss: 0.009892596863210201 2023-01-23 16:39:37.861703: step: 3032/1545, loss: 0.0002322949148947373 2023-01-23 16:39:38.759341: step: 3034/1545, loss: 0.0011428218567743897 2023-01-23 16:39:39.621857: step: 3036/1545, loss: 0.011620174162089825 2023-01-23 16:39:40.561492: step: 3038/1545, loss: 0.08130055665969849 2023-01-23 16:39:41.492970: step: 3040/1545, loss: 0.004232930019497871 2023-01-23 16:39:42.404127: step: 3042/1545, loss: 0.007002224680036306 2023-01-23 16:39:43.307618: step: 3044/1545, loss: 0.1474655419588089 2023-01-23 16:39:44.188374: step: 3046/1545, loss: 0.29776936769485474 2023-01-23 16:39:45.048002: step: 3048/1545, loss: 0.03090004436671734 2023-01-23 16:39:45.920198: step: 3050/1545, loss: 0.05718177556991577 2023-01-23 16:39:46.772028: step: 3052/1545, loss: 0.0008646835922263563 2023-01-23 16:39:47.631092: step: 3054/1545, loss: 0.07911883294582367 2023-01-23 16:39:48.496366: step: 3056/1545, loss: 0.005114646162837744 2023-01-23 16:39:49.383096: step: 3058/1545, loss: 0.015768658369779587 2023-01-23 16:39:50.255617: step: 3060/1545, loss: 0.055536989122629166 2023-01-23 16:39:51.153773: step: 3062/1545, loss: 0.00026274798437952995 2023-01-23 16:39:52.043128: step: 3064/1545, loss: 0.03606932982802391 2023-01-23 16:39:52.922975: step: 3066/1545, loss: 0.017116721719503403 2023-01-23 16:39:53.792668: step: 3068/1545, loss: 0.21030844748020172 2023-01-23 16:39:54.642240: step: 3070/1545, loss: 0.04555223509669304 2023-01-23 16:39:55.532099: step: 3072/1545, loss: 0.017310289666056633 2023-01-23 16:39:56.376225: step: 3074/1545, loss: 0.21836312115192413 2023-01-23 16:39:57.246560: step: 3076/1545, loss: 0.289931058883667 2023-01-23 16:39:58.115148: step: 3078/1545, loss: 1.477992057800293 2023-01-23 16:39:59.036510: step: 3080/1545, loss: 0.11335583031177521 2023-01-23 16:39:59.949022: step: 3082/1545, loss: 0.0015318511286750436 2023-01-23 16:40:00.828587: step: 3084/1545, loss: 0.0008712914423085749 2023-01-23 16:40:01.718972: step: 3086/1545, loss: 0.03214949369430542 2023-01-23 16:40:02.632639: step: 3088/1545, loss: 0.07784973829984665 2023-01-23 16:40:03.555918: step: 3090/1545, loss: 0.0007412445265799761 ================================================== Loss: 0.086 -------------------- Dev Chinese: {'event': {'p': 0.6030534351145038, 'r': 0.7363515312916112, 'f1': 0.6630695443645084}, 'argument': {'p': 0.6570935553400805, 'r': 0.6634874297558149, 'f1': 0.6602750138947997}, 'combined': 0.43780825261849426, 'epoch': 24} Test Chinese: {'event': {'p': 0.6371398078975453, 'r': 0.7634271099744245, 'f1': 0.694589877835951}, 'argument': {'p': 0.7025436650262697, 'r': 0.7167337619189498, 'f1': 0.7095677763725049}, 'combined': 0.4928585951069056, 'epoch': 24} Dev Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.6614245020593517, 'r': 0.6644038917082676, 'f1': 0.6629108492549906}, 'combined': 0.44194056616999366, 'epoch': 24} Test Korean: {'event': {'p': 0.6301587301587301, 'r': 0.7615089514066496, 'f1': 0.6896352055587724}, 'argument': {'p': 0.6986998567150585, 'r': 0.7120338234462619, 'f1': 0.7053038251150118}, 'combined': 0.48640234841457963, 'epoch': 24} Dev Russian: {'event': {'p': 0.5728346456692913, 'r': 0.7749667110519307, 'f1': 0.6587436332767402}, 'argument': {'p': 0.6546270102563835, 'r': 0.669611319504026, 'f1': 0.6620343880244897}, 'combined': 0.43611093812139556, 'epoch': 24} Test Russian: {'event': {'p': 0.6263079222720478, 'r': 0.8037084398976982, 'f1': 0.7040044805376645}, 'argument': {'p': 0.7047270861568067, 'r': 0.727409170516644, 'f1': 0.7158885096208002}, 'combined': 0.5039887183384743, 'epoch': 24} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6790024135156878, 'r': 0.6341096919609316, 'f1': 0.6557886557886557}, 'combined': 0.4570648207011844, 'epoch': 24} Korean: {'event': {'p': 0.6666666666666666, 'r': 0.5396825396825397, 'f1': 0.5964912280701754}, 'argument': {'p': 0.613232074438971, 'r': 0.4939925044091711, 'f1': 0.5471916971916972}, 'combined': 0.32639504744767905, 'epoch': 24} Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.575557373912637, 'r': 0.575557373912637, 'f1': 0.575557373912637}, 'combined': 0.30599252790292086, 'epoch': 24} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 25 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 16:45:21.097340: step: 2/1545, loss: 0.0007386198849417269 2023-01-23 16:45:21.983872: step: 4/1545, loss: 0.006372077856212854 2023-01-23 16:45:22.856924: step: 6/1545, loss: 0.10809977352619171 2023-01-23 16:45:23.722420: step: 8/1545, loss: 0.06674730777740479 2023-01-23 16:45:24.638499: step: 10/1545, loss: 0.0004942889208905399 2023-01-23 16:45:25.498265: step: 12/1545, loss: 0.0008639309089630842 2023-01-23 16:45:26.396325: step: 14/1545, loss: 0.0014895333442837 2023-01-23 16:45:27.269077: step: 16/1545, loss: 0.0013995087938383222 2023-01-23 16:45:28.139725: step: 18/1545, loss: 0.02467469871044159 2023-01-23 16:45:29.013669: step: 20/1545, loss: 0.044137779623270035 2023-01-23 16:45:29.895045: step: 22/1545, loss: 0.0032535961363464594 2023-01-23 16:45:30.796984: step: 24/1545, loss: 9.456666157348081e-05 2023-01-23 16:45:31.709951: step: 26/1545, loss: 0.06476858258247375 2023-01-23 16:45:32.575592: step: 28/1545, loss: 0.11127427220344543 2023-01-23 16:45:33.433132: step: 30/1545, loss: 0.0412101112306118 2023-01-23 16:45:34.308744: step: 32/1545, loss: 0.00046605418901890516 2023-01-23 16:45:35.184672: step: 34/1545, loss: 0.053265444934368134 2023-01-23 16:45:36.108634: step: 36/1545, loss: 0.001431536627933383 2023-01-23 16:45:37.033170: step: 38/1545, loss: 0.001000717980787158 2023-01-23 16:45:37.936149: step: 40/1545, loss: 0.0003592852153815329 2023-01-23 16:45:38.816143: step: 42/1545, loss: 0.30000239610671997 2023-01-23 16:45:39.664940: step: 44/1545, loss: 0.004229304846376181 2023-01-23 16:45:40.524088: step: 46/1545, loss: 0.0006753045599907637 2023-01-23 16:45:41.400140: step: 48/1545, loss: 0.006285474169999361 2023-01-23 16:45:42.258607: step: 50/1545, loss: 6.276088242884725e-05 2023-01-23 16:45:43.133986: step: 52/1545, loss: 0.062053654342889786 2023-01-23 16:45:44.023517: step: 54/1545, loss: 0.00015700733638368547 2023-01-23 16:45:44.880355: step: 56/1545, loss: 6.285085692070425e-05 2023-01-23 16:45:45.794451: step: 58/1545, loss: 0.0006871548248454928 2023-01-23 16:45:46.670705: step: 60/1545, loss: 0.0008355856407433748 2023-01-23 16:45:47.550872: step: 62/1545, loss: 0.002320594619959593 2023-01-23 16:45:48.407759: step: 64/1545, loss: 0.06099627539515495 2023-01-23 16:45:49.427234: step: 66/1545, loss: 0.11361231654882431 2023-01-23 16:45:50.298694: step: 68/1545, loss: 0.34010326862335205 2023-01-23 16:45:51.160988: step: 70/1545, loss: 1.4664051377621945e-05 2023-01-23 16:45:52.054590: step: 72/1545, loss: 0.10367663949728012 2023-01-23 16:45:53.039381: step: 74/1545, loss: 0.008370011113584042 2023-01-23 16:45:53.931956: step: 76/1545, loss: 0.0003011677763424814 2023-01-23 16:45:54.864335: step: 78/1545, loss: 0.11654640734195709 2023-01-23 16:45:55.740257: step: 80/1545, loss: 6.71397356200032e-05 2023-01-23 16:45:56.616885: step: 82/1545, loss: 0.0009942124597728252 2023-01-23 16:45:57.507215: step: 84/1545, loss: 0.008062390610575676 2023-01-23 16:45:58.374722: step: 86/1545, loss: 7.896732859080657e-05 2023-01-23 16:45:59.296158: step: 88/1545, loss: 0.13936525583267212 2023-01-23 16:46:00.149993: step: 90/1545, loss: 0.0001812964619603008 2023-01-23 16:46:01.033507: step: 92/1545, loss: 0.0023689481895416975 2023-01-23 16:46:01.896174: step: 94/1545, loss: 0.001110401819460094 2023-01-23 16:46:02.763607: step: 96/1545, loss: 0.1125963032245636 2023-01-23 16:46:03.639965: step: 98/1545, loss: 0.09574542939662933 2023-01-23 16:46:04.513865: step: 100/1545, loss: 0.014625109732151031 2023-01-23 16:46:05.391843: step: 102/1545, loss: 0.1443658322095871 2023-01-23 16:46:06.239391: step: 104/1545, loss: 0.009360901080071926 2023-01-23 16:46:07.112343: step: 106/1545, loss: 0.0007400080212391913 2023-01-23 16:46:07.992364: step: 108/1545, loss: 0.0025647918228060007 2023-01-23 16:46:08.966308: step: 110/1545, loss: 0.00011236318096052855 2023-01-23 16:46:09.862859: step: 112/1545, loss: 1.0365166664123535 2023-01-23 16:46:10.784871: step: 114/1545, loss: 3.323239434394054e-05 2023-01-23 16:46:11.668096: step: 116/1545, loss: 0.0488571971654892 2023-01-23 16:46:12.576480: step: 118/1545, loss: 0.09501510113477707 2023-01-23 16:46:13.496469: step: 120/1545, loss: 0.22083792090415955 2023-01-23 16:46:14.391935: step: 122/1545, loss: 0.05814076215028763 2023-01-23 16:46:15.248758: step: 124/1545, loss: 0.02755359560251236 2023-01-23 16:46:16.102189: step: 126/1545, loss: 0.004399294499307871 2023-01-23 16:46:16.997266: step: 128/1545, loss: 0.040728867053985596 2023-01-23 16:46:17.880958: step: 130/1545, loss: 0.01365443505346775 2023-01-23 16:46:18.812793: step: 132/1545, loss: 0.000328290305333212 2023-01-23 16:46:19.687217: step: 134/1545, loss: 0.003241217928007245 2023-01-23 16:46:20.660205: step: 136/1545, loss: 0.0007476328173652291 2023-01-23 16:46:21.539557: step: 138/1545, loss: 0.033421456813812256 2023-01-23 16:46:22.422581: step: 140/1545, loss: 0.02250024490058422 2023-01-23 16:46:23.358794: step: 142/1545, loss: 0.006970682181417942 2023-01-23 16:46:24.365049: step: 144/1545, loss: 0.005336031783372164 2023-01-23 16:46:25.225887: step: 146/1545, loss: 0.03698040172457695 2023-01-23 16:46:26.080812: step: 148/1545, loss: 0.03416617214679718 2023-01-23 16:46:26.946363: step: 150/1545, loss: 6.634581222897395e-05 2023-01-23 16:46:27.802909: step: 152/1545, loss: 0.014774182811379433 2023-01-23 16:46:28.722004: step: 154/1545, loss: 0.14207467436790466 2023-01-23 16:46:29.617448: step: 156/1545, loss: 0.0004443319921847433 2023-01-23 16:46:30.463496: step: 158/1545, loss: 0.011752033606171608 2023-01-23 16:46:31.329418: step: 160/1545, loss: 0.12738730013370514 2023-01-23 16:46:32.190781: step: 162/1545, loss: 0.0034483219496905804 2023-01-23 16:46:33.108297: step: 164/1545, loss: 0.5334531664848328 2023-01-23 16:46:33.980699: step: 166/1545, loss: 0.43974268436431885 2023-01-23 16:46:34.843152: step: 168/1545, loss: 0.0007737783598713577 2023-01-23 16:46:35.798249: step: 170/1545, loss: 0.778647780418396 2023-01-23 16:46:36.655042: step: 172/1545, loss: 0.000875759229529649 2023-01-23 16:46:37.562646: step: 174/1545, loss: 0.06765298545360565 2023-01-23 16:46:38.435841: step: 176/1545, loss: 0.009033381007611752 2023-01-23 16:46:39.372145: step: 178/1545, loss: 0.0003941949689760804 2023-01-23 16:46:40.223757: step: 180/1545, loss: 0.0007264044834300876 2023-01-23 16:46:41.180491: step: 182/1545, loss: 0.002467055106535554 2023-01-23 16:46:42.036821: step: 184/1545, loss: 0.03582238405942917 2023-01-23 16:46:42.959951: step: 186/1545, loss: 0.07963584363460541 2023-01-23 16:46:43.849600: step: 188/1545, loss: 0.005194544326514006 2023-01-23 16:46:44.756904: step: 190/1545, loss: 0.0010803175391629338 2023-01-23 16:46:45.623387: step: 192/1545, loss: 0.0008997159311547875 2023-01-23 16:46:46.574945: step: 194/1545, loss: 0.008631598204374313 2023-01-23 16:46:47.449687: step: 196/1545, loss: 0.0016653817147016525 2023-01-23 16:46:48.328393: step: 198/1545, loss: 0.3633860647678375 2023-01-23 16:46:49.237935: step: 200/1545, loss: 0.003982719033956528 2023-01-23 16:46:50.139578: step: 202/1545, loss: 0.000639071105979383 2023-01-23 16:46:51.029522: step: 204/1545, loss: 0.002033745404332876 2023-01-23 16:46:51.926151: step: 206/1545, loss: 0.0007102901581674814 2023-01-23 16:46:52.840618: step: 208/1545, loss: 0.006983180996030569 2023-01-23 16:46:53.721130: step: 210/1545, loss: 0.00023885886184871197 2023-01-23 16:46:54.629738: step: 212/1545, loss: 0.00028824873152188957 2023-01-23 16:46:55.519503: step: 214/1545, loss: 0.0030479945708066225 2023-01-23 16:46:56.437148: step: 216/1545, loss: 0.0008777388138696551 2023-01-23 16:46:57.328008: step: 218/1545, loss: 0.0003285213024355471 2023-01-23 16:46:58.209231: step: 220/1545, loss: 0.0035118774976581335 2023-01-23 16:46:59.069942: step: 222/1545, loss: 0.0006574818398803473 2023-01-23 16:46:59.944989: step: 224/1545, loss: 0.09134849905967712 2023-01-23 16:47:00.826864: step: 226/1545, loss: 0.26965993642807007 2023-01-23 16:47:01.659122: step: 228/1545, loss: 0.0001044433010974899 2023-01-23 16:47:02.512406: step: 230/1545, loss: 0.007739543449133635 2023-01-23 16:47:03.423901: step: 232/1545, loss: 0.15337210893630981 2023-01-23 16:47:04.328489: step: 234/1545, loss: 0.0006641083746217191 2023-01-23 16:47:05.189298: step: 236/1545, loss: 0.004822263494133949 2023-01-23 16:47:06.024493: step: 238/1545, loss: 0.0643792524933815 2023-01-23 16:47:06.866393: step: 240/1545, loss: 0.0018911309307441115 2023-01-23 16:47:07.758443: step: 242/1545, loss: 7.848511449992657e-05 2023-01-23 16:47:08.615592: step: 244/1545, loss: 0.8131903409957886 2023-01-23 16:47:09.531537: step: 246/1545, loss: 0.011805851943790913 2023-01-23 16:47:10.440101: step: 248/1545, loss: 0.000638500670902431 2023-01-23 16:47:11.353349: step: 250/1545, loss: 0.0008348198607563972 2023-01-23 16:47:12.207836: step: 252/1545, loss: 0.03940031677484512 2023-01-23 16:47:13.105957: step: 254/1545, loss: 0.13833844661712646 2023-01-23 16:47:13.980117: step: 256/1545, loss: 0.0009903146419674158 2023-01-23 16:47:14.851078: step: 258/1545, loss: 0.08486786484718323 2023-01-23 16:47:15.697101: step: 260/1545, loss: 0.003603848395869136 2023-01-23 16:47:16.588084: step: 262/1545, loss: 0.0003407352196518332 2023-01-23 16:47:17.419003: step: 264/1545, loss: 0.00013100448995828629 2023-01-23 16:47:18.288985: step: 266/1545, loss: 0.3095746636390686 2023-01-23 16:47:19.247991: step: 268/1545, loss: 0.0031820640433579683 2023-01-23 16:47:20.205640: step: 270/1545, loss: 0.06712250411510468 2023-01-23 16:47:21.091137: step: 272/1545, loss: 0.0031742809806019068 2023-01-23 16:47:21.996849: step: 274/1545, loss: 0.009648812934756279 2023-01-23 16:47:22.861822: step: 276/1545, loss: 0.002973309950903058 2023-01-23 16:47:23.845498: step: 278/1545, loss: 0.0024137133732438087 2023-01-23 16:47:24.749484: step: 280/1545, loss: 5.6565782870166004e-05 2023-01-23 16:47:25.646973: step: 282/1545, loss: 0.00031620479421690106 2023-01-23 16:47:26.520517: step: 284/1545, loss: 3.805445521720685e-05 2023-01-23 16:47:27.375190: step: 286/1545, loss: 0.0006302488618530333 2023-01-23 16:47:28.260691: step: 288/1545, loss: 0.06173498556017876 2023-01-23 16:47:29.149290: step: 290/1545, loss: 0.12178122252225876 2023-01-23 16:47:30.005086: step: 292/1545, loss: 0.30186885595321655 2023-01-23 16:47:30.845655: step: 294/1545, loss: 0.05547652393579483 2023-01-23 16:47:31.714189: step: 296/1545, loss: 0.0003182341461069882 2023-01-23 16:47:32.591446: step: 298/1545, loss: 0.10383772104978561 2023-01-23 16:47:33.447645: step: 300/1545, loss: 0.003988934215158224 2023-01-23 16:47:34.318743: step: 302/1545, loss: 0.0006518342415802181 2023-01-23 16:47:35.195086: step: 304/1545, loss: 0.003809358924627304 2023-01-23 16:47:36.070821: step: 306/1545, loss: 0.000910813978407532 2023-01-23 16:47:37.017962: step: 308/1545, loss: 0.006274794694036245 2023-01-23 16:47:37.903897: step: 310/1545, loss: 0.16633079946041107 2023-01-23 16:47:38.814448: step: 312/1545, loss: 0.002003681380301714 2023-01-23 16:47:39.747282: step: 314/1545, loss: 0.0032683871686458588 2023-01-23 16:47:40.630072: step: 316/1545, loss: 0.0042127748019993305 2023-01-23 16:47:41.533573: step: 318/1545, loss: 0.0192948617041111 2023-01-23 16:47:42.382513: step: 320/1545, loss: 0.000232160251471214 2023-01-23 16:47:43.270491: step: 322/1545, loss: 0.0015304089756682515 2023-01-23 16:47:44.131077: step: 324/1545, loss: 0.0040230778977274895 2023-01-23 16:47:45.003937: step: 326/1545, loss: 0.001271459273993969 2023-01-23 16:47:45.985733: step: 328/1545, loss: 0.0008867932483553886 2023-01-23 16:47:46.833667: step: 330/1545, loss: 0.00040962197817862034 2023-01-23 16:47:47.728641: step: 332/1545, loss: 0.004234283231198788 2023-01-23 16:47:48.650098: step: 334/1545, loss: 0.14967995882034302 2023-01-23 16:47:49.524488: step: 336/1545, loss: 0.1803237497806549 2023-01-23 16:47:50.380820: step: 338/1545, loss: 0.006705817766487598 2023-01-23 16:47:51.333690: step: 340/1545, loss: 0.007876030169427395 2023-01-23 16:47:52.190110: step: 342/1545, loss: 0.00029872325831092894 2023-01-23 16:47:53.097511: step: 344/1545, loss: 0.03614208847284317 2023-01-23 16:47:54.015091: step: 346/1545, loss: 0.00024534895783290267 2023-01-23 16:47:54.946697: step: 348/1545, loss: 0.2565883994102478 2023-01-23 16:47:55.788014: step: 350/1545, loss: 0.0017303228378295898 2023-01-23 16:47:56.727943: step: 352/1545, loss: 0.04196992516517639 2023-01-23 16:47:57.600596: step: 354/1545, loss: 0.001986769726499915 2023-01-23 16:47:58.485479: step: 356/1545, loss: 0.0004710191860795021 2023-01-23 16:47:59.363588: step: 358/1545, loss: 0.038620222359895706 2023-01-23 16:48:00.237984: step: 360/1545, loss: 0.011874728836119175 2023-01-23 16:48:01.106531: step: 362/1545, loss: 0.00027649596449919045 2023-01-23 16:48:01.965414: step: 364/1545, loss: 0.0015922931488603354 2023-01-23 16:48:02.890672: step: 366/1545, loss: 0.003601151518523693 2023-01-23 16:48:03.775539: step: 368/1545, loss: 0.003939681686460972 2023-01-23 16:48:04.646093: step: 370/1545, loss: 0.009776167571544647 2023-01-23 16:48:05.528817: step: 372/1545, loss: 0.14707112312316895 2023-01-23 16:48:06.379619: step: 374/1545, loss: 0.001984942937269807 2023-01-23 16:48:07.279453: step: 376/1545, loss: 0.0005799356149509549 2023-01-23 16:48:08.134559: step: 378/1545, loss: 0.001582745579071343 2023-01-23 16:48:09.012281: step: 380/1545, loss: 0.00015316061035264283 2023-01-23 16:48:09.881242: step: 382/1545, loss: 0.001119052292779088 2023-01-23 16:48:10.778713: step: 384/1545, loss: 0.004122378304600716 2023-01-23 16:48:11.643775: step: 386/1545, loss: 0.000887450878508389 2023-01-23 16:48:12.590789: step: 388/1545, loss: 0.024365702643990517 2023-01-23 16:48:13.450874: step: 390/1545, loss: 0.000781854207161814 2023-01-23 16:48:14.305215: step: 392/1545, loss: 0.05470891296863556 2023-01-23 16:48:15.172691: step: 394/1545, loss: 0.15395444631576538 2023-01-23 16:48:15.995498: step: 396/1545, loss: 0.001807686872780323 2023-01-23 16:48:16.833006: step: 398/1545, loss: 0.3671905994415283 2023-01-23 16:48:17.669252: step: 400/1545, loss: 0.004622152540832758 2023-01-23 16:48:18.523402: step: 402/1545, loss: 0.0021971610840409994 2023-01-23 16:48:19.417353: step: 404/1545, loss: 9.48723481997149e-06 2023-01-23 16:48:20.308721: step: 406/1545, loss: 0.006687719840556383 2023-01-23 16:48:21.180432: step: 408/1545, loss: 0.0019521419890224934 2023-01-23 16:48:22.031350: step: 410/1545, loss: 0.009256855584681034 2023-01-23 16:48:22.911980: step: 412/1545, loss: 0.0016311771469190717 2023-01-23 16:48:23.808640: step: 414/1545, loss: 0.38387787342071533 2023-01-23 16:48:24.666921: step: 416/1545, loss: 0.020850645378232002 2023-01-23 16:48:25.582061: step: 418/1545, loss: 0.001610431238077581 2023-01-23 16:48:26.470240: step: 420/1545, loss: 0.015926681458950043 2023-01-23 16:48:27.340715: step: 422/1545, loss: 0.0013550999574363232 2023-01-23 16:48:28.160159: step: 424/1545, loss: 0.1716974824666977 2023-01-23 16:48:29.054921: step: 426/1545, loss: 0.008833217434585094 2023-01-23 16:48:29.946276: step: 428/1545, loss: 0.009195043705403805 2023-01-23 16:48:30.825840: step: 430/1545, loss: 0.002872828394174576 2023-01-23 16:48:31.694602: step: 432/1545, loss: 0.15064026415348053 2023-01-23 16:48:32.529920: step: 434/1545, loss: 0.002723069628700614 2023-01-23 16:48:33.401181: step: 436/1545, loss: 0.0003513990086503327 2023-01-23 16:48:34.262571: step: 438/1545, loss: 0.17309898138046265 2023-01-23 16:48:35.103596: step: 440/1545, loss: 0.009211261756718159 2023-01-23 16:48:36.025704: step: 442/1545, loss: 0.002371768234297633 2023-01-23 16:48:36.917761: step: 444/1545, loss: 0.07428717613220215 2023-01-23 16:48:37.801190: step: 446/1545, loss: 5.634765329887159e-05 2023-01-23 16:48:38.641889: step: 448/1545, loss: 1.34119727590587e-06 2023-01-23 16:48:39.480557: step: 450/1545, loss: 0.0007668374455533922 2023-01-23 16:48:40.386752: step: 452/1545, loss: 0.007486564107239246 2023-01-23 16:48:41.258084: step: 454/1545, loss: 0.04181262478232384 2023-01-23 16:48:42.118267: step: 456/1545, loss: 0.11104987561702728 2023-01-23 16:48:42.988780: step: 458/1545, loss: 0.025101328268647194 2023-01-23 16:48:43.894583: step: 460/1545, loss: 0.057402946054935455 2023-01-23 16:48:44.824225: step: 462/1545, loss: 0.574342668056488 2023-01-23 16:48:45.710488: step: 464/1545, loss: 0.004191075451672077 2023-01-23 16:48:46.569051: step: 466/1545, loss: 3.6324003303889185e-05 2023-01-23 16:48:47.440406: step: 468/1545, loss: 0.0024713589809834957 2023-01-23 16:48:48.302896: step: 470/1545, loss: 0.3577765226364136 2023-01-23 16:48:49.283983: step: 472/1545, loss: 0.0008881819085218012 2023-01-23 16:48:50.253965: step: 474/1545, loss: 0.00040013188845478 2023-01-23 16:48:51.107673: step: 476/1545, loss: 0.0662497878074646 2023-01-23 16:48:51.985142: step: 478/1545, loss: 0.1435452699661255 2023-01-23 16:48:52.879986: step: 480/1545, loss: 0.10373729467391968 2023-01-23 16:48:53.752506: step: 482/1545, loss: 0.0013503851369023323 2023-01-23 16:48:54.648183: step: 484/1545, loss: 0.22361880540847778 2023-01-23 16:48:55.519576: step: 486/1545, loss: 0.0010562303941696882 2023-01-23 16:48:56.371988: step: 488/1545, loss: 0.2747974395751953 2023-01-23 16:48:57.288841: step: 490/1545, loss: 0.1479044258594513 2023-01-23 16:48:58.182519: step: 492/1545, loss: 0.029988864436745644 2023-01-23 16:48:59.051212: step: 494/1545, loss: 0.0005699631292372942 2023-01-23 16:48:59.917824: step: 496/1545, loss: 0.013287324458360672 2023-01-23 16:49:00.826111: step: 498/1545, loss: 0.024202121421694756 2023-01-23 16:49:01.687643: step: 500/1545, loss: 0.0022293864749372005 2023-01-23 16:49:02.560952: step: 502/1545, loss: 0.00038251574733294547 2023-01-23 16:49:03.464431: step: 504/1545, loss: 0.019564323127269745 2023-01-23 16:49:04.376993: step: 506/1545, loss: 0.8863418698310852 2023-01-23 16:49:05.282677: step: 508/1545, loss: 0.01912662200629711 2023-01-23 16:49:06.177658: step: 510/1545, loss: 0.005709177814424038 2023-01-23 16:49:07.075375: step: 512/1545, loss: 0.14182686805725098 2023-01-23 16:49:07.956695: step: 514/1545, loss: 0.002460807329043746 2023-01-23 16:49:08.866623: step: 516/1545, loss: 0.0046996488235890865 2023-01-23 16:49:09.761540: step: 518/1545, loss: 0.11759201437234879 2023-01-23 16:49:10.665406: step: 520/1545, loss: 0.0001793539267964661 2023-01-23 16:49:11.520106: step: 522/1545, loss: 0.31143680214881897 2023-01-23 16:49:12.416370: step: 524/1545, loss: 0.00011651773093035445 2023-01-23 16:49:13.284527: step: 526/1545, loss: 0.05629338324069977 2023-01-23 16:49:14.148790: step: 528/1545, loss: 0.23573113977909088 2023-01-23 16:49:15.084542: step: 530/1545, loss: 0.055742643773555756 2023-01-23 16:49:15.962289: step: 532/1545, loss: 0.0002393644826952368 2023-01-23 16:49:16.842363: step: 534/1545, loss: 0.002205345081165433 2023-01-23 16:49:17.708243: step: 536/1545, loss: 0.005136954598128796 2023-01-23 16:49:18.601378: step: 538/1545, loss: 0.03172873333096504 2023-01-23 16:49:19.492213: step: 540/1545, loss: 0.0007662981515750289 2023-01-23 16:49:20.423210: step: 542/1545, loss: 0.00020329201652202755 2023-01-23 16:49:21.438724: step: 544/1545, loss: 0.041791003197431564 2023-01-23 16:49:22.355183: step: 546/1545, loss: 0.009783229790627956 2023-01-23 16:49:23.272807: step: 548/1545, loss: 0.007467035204172134 2023-01-23 16:49:24.114939: step: 550/1545, loss: 0.011464814655482769 2023-01-23 16:49:24.964140: step: 552/1545, loss: 0.0013818250736221671 2023-01-23 16:49:25.860090: step: 554/1545, loss: 0.017587415874004364 2023-01-23 16:49:26.700319: step: 556/1545, loss: 0.000904289772734046 2023-01-23 16:49:27.599428: step: 558/1545, loss: 0.006846846081316471 2023-01-23 16:49:28.459364: step: 560/1545, loss: 0.009539746679365635 2023-01-23 16:49:29.358390: step: 562/1545, loss: 0.0855865329504013 2023-01-23 16:49:30.291157: step: 564/1545, loss: 0.1550212949514389 2023-01-23 16:49:31.188871: step: 566/1545, loss: 0.05942763388156891 2023-01-23 16:49:32.051241: step: 568/1545, loss: 0.12539249658584595 2023-01-23 16:49:32.932859: step: 570/1545, loss: 0.22588670253753662 2023-01-23 16:49:33.804334: step: 572/1545, loss: 0.002296079881489277 2023-01-23 16:49:34.707786: step: 574/1545, loss: 0.3186168968677521 2023-01-23 16:49:35.571965: step: 576/1545, loss: 0.3138444721698761 2023-01-23 16:49:36.435112: step: 578/1545, loss: 0.34297308325767517 2023-01-23 16:49:37.353677: step: 580/1545, loss: 0.0013446719385683537 2023-01-23 16:49:38.264430: step: 582/1545, loss: 9.076105197891593e-05 2023-01-23 16:49:39.165403: step: 584/1545, loss: 0.0034270340111106634 2023-01-23 16:49:40.097781: step: 586/1545, loss: 0.00615058746188879 2023-01-23 16:49:41.053533: step: 588/1545, loss: 0.022516345605254173 2023-01-23 16:49:41.945190: step: 590/1545, loss: 0.0057494002394378185 2023-01-23 16:49:42.854648: step: 592/1545, loss: 0.0012281776871532202 2023-01-23 16:49:43.767736: step: 594/1545, loss: 0.009790293872356415 2023-01-23 16:49:44.658946: step: 596/1545, loss: 0.0014197609852999449 2023-01-23 16:49:45.559795: step: 598/1545, loss: 0.0023605620954185724 2023-01-23 16:49:46.430883: step: 600/1545, loss: 0.1444627195596695 2023-01-23 16:49:47.307186: step: 602/1545, loss: 0.05151823163032532 2023-01-23 16:49:48.164014: step: 604/1545, loss: 0.0010675627272576094 2023-01-23 16:49:49.097538: step: 606/1545, loss: 0.009693623520433903 2023-01-23 16:49:49.999462: step: 608/1545, loss: 0.1006467342376709 2023-01-23 16:49:50.914919: step: 610/1545, loss: 0.0016858532326295972 2023-01-23 16:49:51.760333: step: 612/1545, loss: 1.479960322380066 2023-01-23 16:49:52.669127: step: 614/1545, loss: 0.062021128833293915 2023-01-23 16:49:53.542609: step: 616/1545, loss: 0.018778324127197266 2023-01-23 16:49:54.439942: step: 618/1545, loss: 0.014050411991775036 2023-01-23 16:49:55.257767: step: 620/1545, loss: 0.009242204017937183 2023-01-23 16:49:56.118580: step: 622/1545, loss: 0.02562924101948738 2023-01-23 16:49:56.983506: step: 624/1545, loss: 0.022904591634869576 2023-01-23 16:49:57.853629: step: 626/1545, loss: 0.08522283285856247 2023-01-23 16:49:58.730624: step: 628/1545, loss: 0.09991735219955444 2023-01-23 16:49:59.599895: step: 630/1545, loss: 0.007570946589112282 2023-01-23 16:50:00.511429: step: 632/1545, loss: 0.24721059203147888 2023-01-23 16:50:01.419819: step: 634/1545, loss: 0.0026191328652203083 2023-01-23 16:50:02.279146: step: 636/1545, loss: 0.01995997503399849 2023-01-23 16:50:03.173575: step: 638/1545, loss: 0.018186446279287338 2023-01-23 16:50:04.053243: step: 640/1545, loss: 0.00035626746830530465 2023-01-23 16:50:04.926903: step: 642/1545, loss: 0.0008877386571839452 2023-01-23 16:50:05.811112: step: 644/1545, loss: 0.0005497634992934763 2023-01-23 16:50:06.659887: step: 646/1545, loss: 0.02898939698934555 2023-01-23 16:50:07.521377: step: 648/1545, loss: 0.003371593775227666 2023-01-23 16:50:08.442845: step: 650/1545, loss: 0.0004856068408116698 2023-01-23 16:50:09.321371: step: 652/1545, loss: 0.6617421507835388 2023-01-23 16:50:10.205964: step: 654/1545, loss: 0.007494583260267973 2023-01-23 16:50:11.098367: step: 656/1545, loss: 0.01921861059963703 2023-01-23 16:50:11.984364: step: 658/1545, loss: 0.09229496121406555 2023-01-23 16:50:12.872657: step: 660/1545, loss: 0.18665483593940735 2023-01-23 16:50:13.710129: step: 662/1545, loss: 0.35675233602523804 2023-01-23 16:50:14.558053: step: 664/1545, loss: 0.005475076846778393 2023-01-23 16:50:15.442680: step: 666/1545, loss: 0.0003032827517017722 2023-01-23 16:50:16.316990: step: 668/1545, loss: 0.001394728315062821 2023-01-23 16:50:17.205926: step: 670/1545, loss: 0.16458161175251007 2023-01-23 16:50:18.093605: step: 672/1545, loss: 0.023173248395323753 2023-01-23 16:50:19.032187: step: 674/1545, loss: 0.03932817652821541 2023-01-23 16:50:19.892751: step: 676/1545, loss: 0.10234653204679489 2023-01-23 16:50:20.734773: step: 678/1545, loss: 0.00020651840895880014 2023-01-23 16:50:21.656910: step: 680/1545, loss: 0.0005566825857385993 2023-01-23 16:50:22.572672: step: 682/1545, loss: 0.06585544347763062 2023-01-23 16:50:23.523621: step: 684/1545, loss: 0.2038109004497528 2023-01-23 16:50:24.525256: step: 686/1545, loss: 0.008834000676870346 2023-01-23 16:50:25.403767: step: 688/1545, loss: 0.0012819247785955667 2023-01-23 16:50:26.334442: step: 690/1545, loss: 0.0762602761387825 2023-01-23 16:50:27.192569: step: 692/1545, loss: 0.017992665991187096 2023-01-23 16:50:28.022300: step: 694/1545, loss: 0.019752873107790947 2023-01-23 16:50:28.895009: step: 696/1545, loss: 0.02645239420235157 2023-01-23 16:50:29.776515: step: 698/1545, loss: 0.027202047407627106 2023-01-23 16:50:30.630915: step: 700/1545, loss: 0.00023530870385002345 2023-01-23 16:50:31.549448: step: 702/1545, loss: 0.00670166639611125 2023-01-23 16:50:32.429017: step: 704/1545, loss: 0.009905312210321426 2023-01-23 16:50:33.261435: step: 706/1545, loss: 0.0005335147143341601 2023-01-23 16:50:34.149602: step: 708/1545, loss: 0.033218830823898315 2023-01-23 16:50:35.005451: step: 710/1545, loss: 0.02124815434217453 2023-01-23 16:50:36.027364: step: 712/1545, loss: 0.02463965304195881 2023-01-23 16:50:36.905961: step: 714/1545, loss: 0.016412314027547836 2023-01-23 16:50:37.759931: step: 716/1545, loss: 0.001681018969975412 2023-01-23 16:50:38.641782: step: 718/1545, loss: 0.034657564014196396 2023-01-23 16:50:39.522436: step: 720/1545, loss: 0.1519942730665207 2023-01-23 16:50:40.414896: step: 722/1545, loss: 0.028254568576812744 2023-01-23 16:50:41.334041: step: 724/1545, loss: 0.000498351117130369 2023-01-23 16:50:42.226283: step: 726/1545, loss: 0.10936857759952545 2023-01-23 16:50:43.084895: step: 728/1545, loss: 0.001109608798287809 2023-01-23 16:50:44.016608: step: 730/1545, loss: 0.21229475736618042 2023-01-23 16:50:44.915446: step: 732/1545, loss: 0.008722134865820408 2023-01-23 16:50:45.783191: step: 734/1545, loss: 0.13356415927410126 2023-01-23 16:50:46.670752: step: 736/1545, loss: 0.011700380593538284 2023-01-23 16:50:47.544982: step: 738/1545, loss: 0.0016230772016569972 2023-01-23 16:50:48.466663: step: 740/1545, loss: 0.23079970479011536 2023-01-23 16:50:49.374958: step: 742/1545, loss: 3.5518224239349365 2023-01-23 16:50:50.305109: step: 744/1545, loss: 0.0006260806694626808 2023-01-23 16:50:51.193548: step: 746/1545, loss: 0.01036769151687622 2023-01-23 16:50:52.097114: step: 748/1545, loss: 0.10556633025407791 2023-01-23 16:50:52.993903: step: 750/1545, loss: 6.450361979659647e-05 2023-01-23 16:50:53.850318: step: 752/1545, loss: 0.001930904109030962 2023-01-23 16:50:54.738513: step: 754/1545, loss: 0.08506203442811966 2023-01-23 16:50:55.629148: step: 756/1545, loss: 0.008585168048739433 2023-01-23 16:50:56.547346: step: 758/1545, loss: 0.2413291484117508 2023-01-23 16:50:57.423170: step: 760/1545, loss: 0.005648654419928789 2023-01-23 16:50:58.344812: step: 762/1545, loss: 0.005231523420661688 2023-01-23 16:50:59.252972: step: 764/1545, loss: 0.05574904382228851 2023-01-23 16:51:00.133748: step: 766/1545, loss: 0.004402443766593933 2023-01-23 16:51:01.006868: step: 768/1545, loss: 0.0026142504066228867 2023-01-23 16:51:01.854943: step: 770/1545, loss: 0.004976827651262283 2023-01-23 16:51:02.772687: step: 772/1545, loss: 0.006182595156133175 2023-01-23 16:51:03.634575: step: 774/1545, loss: 0.002480203751474619 2023-01-23 16:51:04.533266: step: 776/1545, loss: 0.0017359255580231547 2023-01-23 16:51:05.423366: step: 778/1545, loss: 0.015683820471167564 2023-01-23 16:51:06.272549: step: 780/1545, loss: 0.0007036958704702556 2023-01-23 16:51:07.191090: step: 782/1545, loss: 0.0017780689522624016 2023-01-23 16:51:08.053411: step: 784/1545, loss: 0.0235605426132679 2023-01-23 16:51:08.943026: step: 786/1545, loss: 0.0007978426874615252 2023-01-23 16:51:09.854275: step: 788/1545, loss: 0.1869155913591385 2023-01-23 16:51:10.749302: step: 790/1545, loss: 0.2800879180431366 2023-01-23 16:51:11.583756: step: 792/1545, loss: 0.009135219268500805 2023-01-23 16:51:12.430116: step: 794/1545, loss: 0.07792137563228607 2023-01-23 16:51:13.319430: step: 796/1545, loss: 0.07106603682041168 2023-01-23 16:51:14.314017: step: 798/1545, loss: 0.3585750162601471 2023-01-23 16:51:15.195891: step: 800/1545, loss: 0.0019904649816453457 2023-01-23 16:51:16.042478: step: 802/1545, loss: 0.00042943484731949866 2023-01-23 16:51:16.948897: step: 804/1545, loss: 0.0191794466227293 2023-01-23 16:51:17.810077: step: 806/1545, loss: 0.024236569181084633 2023-01-23 16:51:18.788393: step: 808/1545, loss: 0.00023972129565663636 2023-01-23 16:51:19.674299: step: 810/1545, loss: 0.13889384269714355 2023-01-23 16:51:20.554502: step: 812/1545, loss: 0.024932028725743294 2023-01-23 16:51:21.435441: step: 814/1545, loss: 0.026519929990172386 2023-01-23 16:51:22.348733: step: 816/1545, loss: 0.07111918181180954 2023-01-23 16:51:23.198938: step: 818/1545, loss: 0.012024693191051483 2023-01-23 16:51:24.072385: step: 820/1545, loss: 0.1100754663348198 2023-01-23 16:51:24.962103: step: 822/1545, loss: 0.0004261283320374787 2023-01-23 16:51:25.831096: step: 824/1545, loss: 0.0011515739606693387 2023-01-23 16:51:26.698375: step: 826/1545, loss: 0.0003752185439225286 2023-01-23 16:51:27.521868: step: 828/1545, loss: 0.07305256277322769 2023-01-23 16:51:28.367939: step: 830/1545, loss: 0.004886433947831392 2023-01-23 16:51:29.242482: step: 832/1545, loss: 8.125277963699773e-05 2023-01-23 16:51:30.125812: step: 834/1545, loss: 0.1411224901676178 2023-01-23 16:51:31.009987: step: 836/1545, loss: 0.00283940602093935 2023-01-23 16:51:32.001051: step: 838/1545, loss: 0.01638501137495041 2023-01-23 16:51:32.890865: step: 840/1545, loss: 0.06234685331583023 2023-01-23 16:51:33.859450: step: 842/1545, loss: 0.0034712639171630144 2023-01-23 16:51:34.710423: step: 844/1545, loss: 0.10787104815244675 2023-01-23 16:51:35.582909: step: 846/1545, loss: 0.015585682354867458 2023-01-23 16:51:36.479814: step: 848/1545, loss: 0.028497440740466118 2023-01-23 16:51:37.349518: step: 850/1545, loss: 0.16543130576610565 2023-01-23 16:51:38.235670: step: 852/1545, loss: 0.24027588963508606 2023-01-23 16:51:39.149823: step: 854/1545, loss: 0.011073993518948555 2023-01-23 16:51:40.000168: step: 856/1545, loss: 0.006794262211769819 2023-01-23 16:51:40.896562: step: 858/1545, loss: 0.031455546617507935 2023-01-23 16:51:41.854235: step: 860/1545, loss: 0.4745381772518158 2023-01-23 16:51:42.731644: step: 862/1545, loss: 0.03683310002088547 2023-01-23 16:51:43.630771: step: 864/1545, loss: 0.026754222810268402 2023-01-23 16:51:44.551191: step: 866/1545, loss: 0.9956225156784058 2023-01-23 16:51:45.440768: step: 868/1545, loss: 0.0018952676327899098 2023-01-23 16:51:46.310118: step: 870/1545, loss: 0.013314425945281982 2023-01-23 16:51:47.165759: step: 872/1545, loss: 0.005409467965364456 2023-01-23 16:51:48.044018: step: 874/1545, loss: 0.0012147885281592607 2023-01-23 16:51:48.935820: step: 876/1545, loss: 0.01206441130489111 2023-01-23 16:51:49.825944: step: 878/1545, loss: 0.0425645187497139 2023-01-23 16:51:50.687547: step: 880/1545, loss: 0.30297502875328064 2023-01-23 16:51:51.673041: step: 882/1545, loss: 0.0012891392689198256 2023-01-23 16:51:52.601219: step: 884/1545, loss: 0.001158676459454 2023-01-23 16:51:53.483862: step: 886/1545, loss: 0.0014800200005993247 2023-01-23 16:51:54.367317: step: 888/1545, loss: 0.05940240994095802 2023-01-23 16:51:55.234690: step: 890/1545, loss: 0.008363213390111923 2023-01-23 16:51:56.095638: step: 892/1545, loss: 0.009053101763129234 2023-01-23 16:51:56.958629: step: 894/1545, loss: 0.01603151485323906 2023-01-23 16:51:57.868345: step: 896/1545, loss: 0.01289148535579443 2023-01-23 16:51:58.807370: step: 898/1545, loss: 0.14686860144138336 2023-01-23 16:51:59.712983: step: 900/1545, loss: 0.001052376814186573 2023-01-23 16:52:00.587927: step: 902/1545, loss: 0.28038132190704346 2023-01-23 16:52:01.444555: step: 904/1545, loss: 0.006684858817607164 2023-01-23 16:52:02.346102: step: 906/1545, loss: 0.2025563269853592 2023-01-23 16:52:03.174150: step: 908/1545, loss: 0.023298561573028564 2023-01-23 16:52:04.047475: step: 910/1545, loss: 0.0009922358440235257 2023-01-23 16:52:04.996783: step: 912/1545, loss: 0.02316390536725521 2023-01-23 16:52:05.929184: step: 914/1545, loss: 0.0007698409026488662 2023-01-23 16:52:06.904103: step: 916/1545, loss: 0.1337183117866516 2023-01-23 16:52:07.822477: step: 918/1545, loss: 0.0733901709318161 2023-01-23 16:52:08.693634: step: 920/1545, loss: 0.01168637815862894 2023-01-23 16:52:09.556637: step: 922/1545, loss: 0.08771657198667526 2023-01-23 16:52:10.414365: step: 924/1545, loss: 0.013168906792998314 2023-01-23 16:52:11.279901: step: 926/1545, loss: 0.05799146741628647 2023-01-23 16:52:12.211817: step: 928/1545, loss: 0.2930048406124115 2023-01-23 16:52:13.201859: step: 930/1545, loss: 0.0017906245775520802 2023-01-23 16:52:14.085225: step: 932/1545, loss: 0.0007457584142684937 2023-01-23 16:52:14.932325: step: 934/1545, loss: 0.003873111680150032 2023-01-23 16:52:15.768965: step: 936/1545, loss: 0.0021335261408239603 2023-01-23 16:52:16.608185: step: 938/1545, loss: 0.054153211414813995 2023-01-23 16:52:17.477789: step: 940/1545, loss: 0.016526032239198685 2023-01-23 16:52:18.422127: step: 942/1545, loss: 0.0041065514087677 2023-01-23 16:52:19.321274: step: 944/1545, loss: 0.16571590304374695 2023-01-23 16:52:20.151774: step: 946/1545, loss: 0.7117176651954651 2023-01-23 16:52:21.019910: step: 948/1545, loss: 0.00025255861692130566 2023-01-23 16:52:21.897401: step: 950/1545, loss: 0.0004210630140732974 2023-01-23 16:52:22.791050: step: 952/1545, loss: 0.11747987568378448 2023-01-23 16:52:23.696952: step: 954/1545, loss: 0.15339168906211853 2023-01-23 16:52:24.593048: step: 956/1545, loss: 9.132843115366995e-05 2023-01-23 16:52:25.469504: step: 958/1545, loss: 0.012224123813211918 2023-01-23 16:52:26.320941: step: 960/1545, loss: 0.13582350313663483 2023-01-23 16:52:27.184280: step: 962/1545, loss: 0.06253448873758316 2023-01-23 16:52:28.041753: step: 964/1545, loss: 0.0027798227965831757 2023-01-23 16:52:28.912994: step: 966/1545, loss: 0.0023592922370880842 2023-01-23 16:52:29.768086: step: 968/1545, loss: 0.0010180710814893246 2023-01-23 16:52:30.645454: step: 970/1545, loss: 0.04830584675073624 2023-01-23 16:52:31.502824: step: 972/1545, loss: 0.29992130398750305 2023-01-23 16:52:32.372411: step: 974/1545, loss: 0.10995187610387802 2023-01-23 16:52:33.249311: step: 976/1545, loss: 0.0020940685644745827 2023-01-23 16:52:34.110725: step: 978/1545, loss: 0.029639113694429398 2023-01-23 16:52:34.963302: step: 980/1545, loss: 0.002076751785352826 2023-01-23 16:52:35.807437: step: 982/1545, loss: 0.0126597685739398 2023-01-23 16:52:36.752772: step: 984/1545, loss: 0.006786219775676727 2023-01-23 16:52:37.628555: step: 986/1545, loss: 0.02524549886584282 2023-01-23 16:52:38.521463: step: 988/1545, loss: 0.0010941565269604325 2023-01-23 16:52:39.375313: step: 990/1545, loss: 0.10572530329227448 2023-01-23 16:52:40.252335: step: 992/1545, loss: 0.006726776249706745 2023-01-23 16:52:41.153279: step: 994/1545, loss: 0.1727784276008606 2023-01-23 16:52:42.000188: step: 996/1545, loss: 0.0049140797927975655 2023-01-23 16:52:42.900340: step: 998/1545, loss: 0.1570344865322113 2023-01-23 16:52:43.785978: step: 1000/1545, loss: 0.004888505209237337 2023-01-23 16:52:44.647078: step: 1002/1545, loss: 0.013477004133164883 2023-01-23 16:52:45.529768: step: 1004/1545, loss: 0.00024629966355860233 2023-01-23 16:52:46.393237: step: 1006/1545, loss: 0.06012517586350441 2023-01-23 16:52:47.306813: step: 1008/1545, loss: 0.009670814499258995 2023-01-23 16:52:48.187941: step: 1010/1545, loss: 0.010468167252838612 2023-01-23 16:52:49.084523: step: 1012/1545, loss: 0.0002876606013160199 2023-01-23 16:52:50.054458: step: 1014/1545, loss: 0.008311955258250237 2023-01-23 16:52:50.915263: step: 1016/1545, loss: 0.0006660927319899201 2023-01-23 16:52:51.810028: step: 1018/1545, loss: 0.001355222426354885 2023-01-23 16:52:52.705479: step: 1020/1545, loss: 0.00019334979879204184 2023-01-23 16:52:53.599488: step: 1022/1545, loss: 0.002190041821449995 2023-01-23 16:52:54.466649: step: 1024/1545, loss: 0.06111404672265053 2023-01-23 16:52:55.357930: step: 1026/1545, loss: 0.03229531645774841 2023-01-23 16:52:56.315298: step: 1028/1545, loss: 0.0888914093375206 2023-01-23 16:52:57.165442: step: 1030/1545, loss: 0.03185345605015755 2023-01-23 16:52:58.036035: step: 1032/1545, loss: 0.011946352198719978 2023-01-23 16:52:58.919971: step: 1034/1545, loss: 0.11967435479164124 2023-01-23 16:52:59.809715: step: 1036/1545, loss: 0.0005259497556835413 2023-01-23 16:53:00.724736: step: 1038/1545, loss: 0.0065008169040083885 2023-01-23 16:53:01.598536: step: 1040/1545, loss: 0.007933806627988815 2023-01-23 16:53:02.516527: step: 1042/1545, loss: 0.011415446177124977 2023-01-23 16:53:03.418070: step: 1044/1545, loss: 0.00013786923955194652 2023-01-23 16:53:04.269005: step: 1046/1545, loss: 0.004406989552080631 2023-01-23 16:53:05.133777: step: 1048/1545, loss: 0.004756554961204529 2023-01-23 16:53:06.055261: step: 1050/1545, loss: 0.01695309579372406 2023-01-23 16:53:06.928460: step: 1052/1545, loss: 0.2986695170402527 2023-01-23 16:53:07.762387: step: 1054/1545, loss: 0.02724410593509674 2023-01-23 16:53:08.634390: step: 1056/1545, loss: 0.020452627912163734 2023-01-23 16:53:09.487717: step: 1058/1545, loss: 0.002824929542839527 2023-01-23 16:53:10.393013: step: 1060/1545, loss: 0.03690963611006737 2023-01-23 16:53:11.317573: step: 1062/1545, loss: 0.0009032823145389557 2023-01-23 16:53:12.173707: step: 1064/1545, loss: 0.13225534558296204 2023-01-23 16:53:13.038744: step: 1066/1545, loss: 0.0031688299495726824 2023-01-23 16:53:13.960785: step: 1068/1545, loss: 0.000835270038805902 2023-01-23 16:53:14.814013: step: 1070/1545, loss: 0.0016016950830817223 2023-01-23 16:53:15.685719: step: 1072/1545, loss: 0.0010693375952541828 2023-01-23 16:53:16.555095: step: 1074/1545, loss: 0.0003469134389888495 2023-01-23 16:53:17.413334: step: 1076/1545, loss: 0.002560436027124524 2023-01-23 16:53:18.246027: step: 1078/1545, loss: 0.0013498213374987245 2023-01-23 16:53:19.166592: step: 1080/1545, loss: 0.0006462272140197456 2023-01-23 16:53:20.037431: step: 1082/1545, loss: 0.0002845017006620765 2023-01-23 16:53:20.890079: step: 1084/1545, loss: 0.00032650004141032696 2023-01-23 16:53:21.732569: step: 1086/1545, loss: -3.2675550755811855e-05 2023-01-23 16:53:22.664114: step: 1088/1545, loss: 0.19303253293037415 2023-01-23 16:53:23.639444: step: 1090/1545, loss: 0.48590683937072754 2023-01-23 16:53:24.535603: step: 1092/1545, loss: 0.010511917062103748 2023-01-23 16:53:25.465360: step: 1094/1545, loss: 0.6572563052177429 2023-01-23 16:53:26.345799: step: 1096/1545, loss: 0.08982106298208237 2023-01-23 16:53:27.210066: step: 1098/1545, loss: 0.08124490082263947 2023-01-23 16:53:28.097584: step: 1100/1545, loss: 0.00034202708047814667 2023-01-23 16:53:28.998369: step: 1102/1545, loss: 0.009531303308904171 2023-01-23 16:53:29.873661: step: 1104/1545, loss: 0.1574069708585739 2023-01-23 16:53:30.771254: step: 1106/1545, loss: 0.0007961906958371401 2023-01-23 16:53:31.662940: step: 1108/1545, loss: 0.012763183563947678 2023-01-23 16:53:32.564798: step: 1110/1545, loss: 0.2463698834180832 2023-01-23 16:53:33.491441: step: 1112/1545, loss: 0.3102610111236572 2023-01-23 16:53:34.394563: step: 1114/1545, loss: 0.12319613993167877 2023-01-23 16:53:35.285802: step: 1116/1545, loss: 0.00252168788574636 2023-01-23 16:53:36.113982: step: 1118/1545, loss: 0.018028374761343002 2023-01-23 16:53:36.970768: step: 1120/1545, loss: 0.09071197360754013 2023-01-23 16:53:37.865902: step: 1122/1545, loss: 0.0027038510888814926 2023-01-23 16:53:38.725117: step: 1124/1545, loss: 0.03172468766570091 2023-01-23 16:53:39.620846: step: 1126/1545, loss: 0.1018529161810875 2023-01-23 16:53:40.492914: step: 1128/1545, loss: 0.003450933378189802 2023-01-23 16:53:41.381467: step: 1130/1545, loss: 0.0027906966861337423 2023-01-23 16:53:42.262478: step: 1132/1545, loss: 0.0016807874199002981 2023-01-23 16:53:43.141207: step: 1134/1545, loss: 0.000870133750140667 2023-01-23 16:53:44.006460: step: 1136/1545, loss: 0.013158092275261879 2023-01-23 16:53:44.901174: step: 1138/1545, loss: 0.16174811124801636 2023-01-23 16:53:45.790430: step: 1140/1545, loss: 0.04800865054130554 2023-01-23 16:53:46.660296: step: 1142/1545, loss: 0.08411800861358643 2023-01-23 16:53:47.562355: step: 1144/1545, loss: 0.09882104396820068 2023-01-23 16:53:48.438960: step: 1146/1545, loss: 0.002295863348990679 2023-01-23 16:53:49.321309: step: 1148/1545, loss: 0.00103342579677701 2023-01-23 16:53:50.197127: step: 1150/1545, loss: 0.11568133533000946 2023-01-23 16:53:51.048464: step: 1152/1545, loss: 0.004946933593600988 2023-01-23 16:53:51.935225: step: 1154/1545, loss: 0.0009425384923815727 2023-01-23 16:53:52.829504: step: 1156/1545, loss: 0.15642626583576202 2023-01-23 16:53:53.656759: step: 1158/1545, loss: 0.0012187784304842353 2023-01-23 16:53:54.530129: step: 1160/1545, loss: 0.03635110706090927 2023-01-23 16:53:55.462283: step: 1162/1545, loss: 0.16620078682899475 2023-01-23 16:53:56.350707: step: 1164/1545, loss: 0.01289835199713707 2023-01-23 16:53:57.229740: step: 1166/1545, loss: 0.3534630537033081 2023-01-23 16:53:58.103095: step: 1168/1545, loss: 0.047324493527412415 2023-01-23 16:53:58.969959: step: 1170/1545, loss: 0.0062724328599870205 2023-01-23 16:53:59.818452: step: 1172/1545, loss: 0.008568545803427696 2023-01-23 16:54:00.719071: step: 1174/1545, loss: 0.08088117837905884 2023-01-23 16:54:01.583425: step: 1176/1545, loss: 0.019288312643766403 2023-01-23 16:54:02.425554: step: 1178/1545, loss: 0.019789116457104683 2023-01-23 16:54:03.283884: step: 1180/1545, loss: 0.6029114127159119 2023-01-23 16:54:04.168922: step: 1182/1545, loss: 0.0037567364051938057 2023-01-23 16:54:05.063620: step: 1184/1545, loss: 0.0031194158364087343 2023-01-23 16:54:05.927995: step: 1186/1545, loss: 0.01785755716264248 2023-01-23 16:54:06.824222: step: 1188/1545, loss: 0.007758498657494783 2023-01-23 16:54:07.729390: step: 1190/1545, loss: 0.0037388510536402464 2023-01-23 16:54:08.599732: step: 1192/1545, loss: 0.04589271545410156 2023-01-23 16:54:09.506763: step: 1194/1545, loss: 0.01671997271478176 2023-01-23 16:54:10.347496: step: 1196/1545, loss: 0.06370405107736588 2023-01-23 16:54:11.195735: step: 1198/1545, loss: 0.0007461145287379622 2023-01-23 16:54:12.057202: step: 1200/1545, loss: 0.000808403710834682 2023-01-23 16:54:12.915705: step: 1202/1545, loss: 0.012598716653883457 2023-01-23 16:54:13.863781: step: 1204/1545, loss: 0.2660679519176483 2023-01-23 16:54:14.736578: step: 1206/1545, loss: 0.0015511030796915293 2023-01-23 16:54:15.572646: step: 1208/1545, loss: 0.05221834406256676 2023-01-23 16:54:16.468266: step: 1210/1545, loss: 0.1257277876138687 2023-01-23 16:54:17.391619: step: 1212/1545, loss: 0.09063348919153214 2023-01-23 16:54:18.248616: step: 1214/1545, loss: 0.0007708006305620074 2023-01-23 16:54:19.166222: step: 1216/1545, loss: 0.0005927179008722305 2023-01-23 16:54:20.122404: step: 1218/1545, loss: 0.07483720034360886 2023-01-23 16:54:20.997132: step: 1220/1545, loss: 0.0029265224002301693 2023-01-23 16:54:21.891986: step: 1222/1545, loss: 0.015282372012734413 2023-01-23 16:54:22.886213: step: 1224/1545, loss: 1.2141544818878174 2023-01-23 16:54:23.728021: step: 1226/1545, loss: 0.011785642243921757 2023-01-23 16:54:24.608265: step: 1228/1545, loss: 0.0005531308124773204 2023-01-23 16:54:25.493377: step: 1230/1545, loss: 0.0016032099956646562 2023-01-23 16:54:26.371648: step: 1232/1545, loss: 0.03340230882167816 2023-01-23 16:54:27.284011: step: 1234/1545, loss: 0.0048039075918495655 2023-01-23 16:54:28.138925: step: 1236/1545, loss: 0.004493962042033672 2023-01-23 16:54:29.063080: step: 1238/1545, loss: 0.12299921363592148 2023-01-23 16:54:29.916249: step: 1240/1545, loss: 0.000897047168109566 2023-01-23 16:54:30.804162: step: 1242/1545, loss: 0.00018953278777189553 2023-01-23 16:54:31.650524: step: 1244/1545, loss: 0.00048497566604055464 2023-01-23 16:54:32.552109: step: 1246/1545, loss: 0.002544309012591839 2023-01-23 16:54:33.435650: step: 1248/1545, loss: 0.0002133701927959919 2023-01-23 16:54:34.326347: step: 1250/1545, loss: 0.3268183767795563 2023-01-23 16:54:35.198508: step: 1252/1545, loss: 0.0003318490635138005 2023-01-23 16:54:36.068909: step: 1254/1545, loss: 0.00039657694287598133 2023-01-23 16:54:36.944531: step: 1256/1545, loss: 0.2627891004085541 2023-01-23 16:54:37.819318: step: 1258/1545, loss: 0.6369547843933105 2023-01-23 16:54:38.759120: step: 1260/1545, loss: 0.18846362829208374 2023-01-23 16:54:39.597602: step: 1262/1545, loss: 0.00030603999039158225 2023-01-23 16:54:40.502441: step: 1264/1545, loss: 0.2505432665348053 2023-01-23 16:54:41.386639: step: 1266/1545, loss: 0.00024403139832429588 2023-01-23 16:54:42.220765: step: 1268/1545, loss: 0.3753055930137634 2023-01-23 16:54:43.106891: step: 1270/1545, loss: 0.0006302644032984972 2023-01-23 16:54:43.961302: step: 1272/1545, loss: 0.00039975123945623636 2023-01-23 16:54:44.864508: step: 1274/1545, loss: 0.06468923389911652 2023-01-23 16:54:45.778686: step: 1276/1545, loss: 0.04349134862422943 2023-01-23 16:54:46.606164: step: 1278/1545, loss: 0.0006758708623237908 2023-01-23 16:54:47.463179: step: 1280/1545, loss: 0.002664337633177638 2023-01-23 16:54:48.320211: step: 1282/1545, loss: 0.0018245147075504065 2023-01-23 16:54:49.212492: step: 1284/1545, loss: 0.051344554871320724 2023-01-23 16:54:50.092931: step: 1286/1545, loss: 0.021548863500356674 2023-01-23 16:54:50.960104: step: 1288/1545, loss: 0.06195224076509476 2023-01-23 16:54:51.836367: step: 1290/1545, loss: 0.008578641340136528 2023-01-23 16:54:52.848629: step: 1292/1545, loss: 0.009350547567009926 2023-01-23 16:54:53.723653: step: 1294/1545, loss: 0.00034734251676127315 2023-01-23 16:54:54.661295: step: 1296/1545, loss: 0.00010468516848050058 2023-01-23 16:54:55.550375: step: 1298/1545, loss: 0.022813713178038597 2023-01-23 16:54:56.440224: step: 1300/1545, loss: 0.0074889082461595535 2023-01-23 16:54:57.280652: step: 1302/1545, loss: 0.08271420747041702 2023-01-23 16:54:58.183548: step: 1304/1545, loss: 0.1445847451686859 2023-01-23 16:54:59.047165: step: 1306/1545, loss: 1.004470705986023 2023-01-23 16:54:59.937849: step: 1308/1545, loss: 0.002489677630364895 2023-01-23 16:55:00.842879: step: 1310/1545, loss: 0.05389741063117981 2023-01-23 16:55:01.692270: step: 1312/1545, loss: 0.00026326251099817455 2023-01-23 16:55:02.611806: step: 1314/1545, loss: 0.01994742825627327 2023-01-23 16:55:03.546844: step: 1316/1545, loss: 0.3174935579299927 2023-01-23 16:55:04.436388: step: 1318/1545, loss: 0.0011512271594256163 2023-01-23 16:55:05.296320: step: 1320/1545, loss: 0.2757735252380371 2023-01-23 16:55:06.146730: step: 1322/1545, loss: 0.0005451096221804619 2023-01-23 16:55:07.014898: step: 1324/1545, loss: 0.031975388526916504 2023-01-23 16:55:07.889697: step: 1326/1545, loss: 0.27548959851264954 2023-01-23 16:55:08.793979: step: 1328/1545, loss: 0.13054676353931427 2023-01-23 16:55:09.708486: step: 1330/1545, loss: 0.0005663931369781494 2023-01-23 16:55:10.597319: step: 1332/1545, loss: 0.0011174484388902783 2023-01-23 16:55:11.483464: step: 1334/1545, loss: 9.183632937492803e-05 2023-01-23 16:55:12.357444: step: 1336/1545, loss: 0.005872608628123999 2023-01-23 16:55:13.266094: step: 1338/1545, loss: 0.058196038007736206 2023-01-23 16:55:14.150070: step: 1340/1545, loss: 0.04624952748417854 2023-01-23 16:55:15.018934: step: 1342/1545, loss: 0.021390490233898163 2023-01-23 16:55:15.891578: step: 1344/1545, loss: 0.004425838589668274 2023-01-23 16:55:16.768964: step: 1346/1545, loss: 0.005020772572606802 2023-01-23 16:55:17.679218: step: 1348/1545, loss: 0.001027802936732769 2023-01-23 16:55:18.581832: step: 1350/1545, loss: 0.00018303659453522414 2023-01-23 16:55:19.461344: step: 1352/1545, loss: 2.7601872716331854e-05 2023-01-23 16:55:20.344168: step: 1354/1545, loss: 0.19977203011512756 2023-01-23 16:55:21.215709: step: 1356/1545, loss: 0.014108885079622269 2023-01-23 16:55:22.125586: step: 1358/1545, loss: 0.05855351686477661 2023-01-23 16:55:23.000126: step: 1360/1545, loss: 0.05775335803627968 2023-01-23 16:55:23.881825: step: 1362/1545, loss: 0.019740156829357147 2023-01-23 16:55:24.719588: step: 1364/1545, loss: 0.054154254496097565 2023-01-23 16:55:25.588132: step: 1366/1545, loss: 0.0008307655225507915 2023-01-23 16:55:26.477221: step: 1368/1545, loss: 0.002374581526964903 2023-01-23 16:55:27.366294: step: 1370/1545, loss: 0.03739842027425766 2023-01-23 16:55:28.234962: step: 1372/1545, loss: 0.030567064881324768 2023-01-23 16:55:29.114015: step: 1374/1545, loss: 0.006842011120170355 2023-01-23 16:55:29.972375: step: 1376/1545, loss: 0.0016009588725864887 2023-01-23 16:55:30.831176: step: 1378/1545, loss: 0.00032245481270365417 2023-01-23 16:55:31.732800: step: 1380/1545, loss: 0.20880424976348877 2023-01-23 16:55:32.552674: step: 1382/1545, loss: 0.004539968445897102 2023-01-23 16:55:33.463804: step: 1384/1545, loss: 0.0006441468722186983 2023-01-23 16:55:34.400214: step: 1386/1545, loss: 0.02202058769762516 2023-01-23 16:55:35.254963: step: 1388/1545, loss: 0.4143422544002533 2023-01-23 16:55:36.168929: step: 1390/1545, loss: 0.0014302653726190329 2023-01-23 16:55:37.040057: step: 1392/1545, loss: 0.00047417631139978766 2023-01-23 16:55:37.905764: step: 1394/1545, loss: 1.216884732246399 2023-01-23 16:55:38.810626: step: 1396/1545, loss: 0.0011350256390869617 2023-01-23 16:55:39.732647: step: 1398/1545, loss: 1.2185722589492798 2023-01-23 16:55:40.591404: step: 1400/1545, loss: 0.0011342017678543925 2023-01-23 16:55:41.467041: step: 1402/1545, loss: 0.006635486613959074 2023-01-23 16:55:42.344866: step: 1404/1545, loss: 0.03378631919622421 2023-01-23 16:55:43.223201: step: 1406/1545, loss: 0.003102206392213702 2023-01-23 16:55:44.103048: step: 1408/1545, loss: 0.10677343606948853 2023-01-23 16:55:44.981057: step: 1410/1545, loss: 0.0016628920566290617 2023-01-23 16:55:45.839516: step: 1412/1545, loss: 0.05842186510562897 2023-01-23 16:55:46.732167: step: 1414/1545, loss: 0.11453646421432495 2023-01-23 16:55:47.603477: step: 1416/1545, loss: 0.0007610932225361466 2023-01-23 16:55:48.488639: step: 1418/1545, loss: 0.20990361273288727 2023-01-23 16:55:49.342453: step: 1420/1545, loss: 0.005586850922554731 2023-01-23 16:55:50.287509: step: 1422/1545, loss: 0.05301464721560478 2023-01-23 16:55:51.252897: step: 1424/1545, loss: 0.08610432595014572 2023-01-23 16:55:52.154848: step: 1426/1545, loss: 0.0010808877414092422 2023-01-23 16:55:53.027528: step: 1428/1545, loss: 0.0001798108423827216 2023-01-23 16:55:53.902294: step: 1430/1545, loss: 0.02288205921649933 2023-01-23 16:55:54.799001: step: 1432/1545, loss: 0.0023515496868640184 2023-01-23 16:55:55.640578: step: 1434/1545, loss: 0.0012648619012907147 2023-01-23 16:55:56.523619: step: 1436/1545, loss: 0.06433335691690445 2023-01-23 16:55:57.434803: step: 1438/1545, loss: 0.0303790345788002 2023-01-23 16:55:58.289927: step: 1440/1545, loss: 0.0014748090179637074 2023-01-23 16:55:59.157206: step: 1442/1545, loss: 0.11374789476394653 2023-01-23 16:56:00.095260: step: 1444/1545, loss: 0.6916183829307556 2023-01-23 16:56:00.951935: step: 1446/1545, loss: 0.13267329335212708 2023-01-23 16:56:01.817880: step: 1448/1545, loss: 0.027875389903783798 2023-01-23 16:56:02.738119: step: 1450/1545, loss: 0.04002150893211365 2023-01-23 16:56:03.687175: step: 1452/1545, loss: 0.07289377599954605 2023-01-23 16:56:04.548770: step: 1454/1545, loss: 0.02075183019042015 2023-01-23 16:56:05.430666: step: 1456/1545, loss: 0.19010348618030548 2023-01-23 16:56:06.381910: step: 1458/1545, loss: 0.013454214669764042 2023-01-23 16:56:07.218045: step: 1460/1545, loss: 0.13148431479930878 2023-01-23 16:56:08.142365: step: 1462/1545, loss: 0.00342625193297863 2023-01-23 16:56:09.003255: step: 1464/1545, loss: 0.012643891386687756 2023-01-23 16:56:09.924175: step: 1466/1545, loss: 0.044565413147211075 2023-01-23 16:56:10.778176: step: 1468/1545, loss: 0.04192941263318062 2023-01-23 16:56:11.655480: step: 1470/1545, loss: 0.13302010297775269 2023-01-23 16:56:12.544235: step: 1472/1545, loss: 0.005054599139839411 2023-01-23 16:56:13.360186: step: 1474/1545, loss: 0.012457221746444702 2023-01-23 16:56:14.202539: step: 1476/1545, loss: 0.009106717072427273 2023-01-23 16:56:15.233518: step: 1478/1545, loss: 0.09411206096410751 2023-01-23 16:56:16.139153: step: 1480/1545, loss: 0.2385832816362381 2023-01-23 16:56:17.077336: step: 1482/1545, loss: 0.07949089258909225 2023-01-23 16:56:17.964929: step: 1484/1545, loss: 0.0013316686963662505 2023-01-23 16:56:18.842618: step: 1486/1545, loss: 0.0022179579827934504 2023-01-23 16:56:19.732060: step: 1488/1545, loss: 0.0013194511411711574 2023-01-23 16:56:20.596227: step: 1490/1545, loss: 0.005629562772810459 2023-01-23 16:56:21.448178: step: 1492/1545, loss: 0.21854926645755768 2023-01-23 16:56:22.317662: step: 1494/1545, loss: 0.1159515455365181 2023-01-23 16:56:23.189018: step: 1496/1545, loss: 0.0347086638212204 2023-01-23 16:56:24.126383: step: 1498/1545, loss: 0.046359024941921234 2023-01-23 16:56:25.006356: step: 1500/1545, loss: 0.006100099068135023 2023-01-23 16:56:25.865000: step: 1502/1545, loss: 0.08267109096050262 2023-01-23 16:56:26.748171: step: 1504/1545, loss: 0.007025495637208223 2023-01-23 16:56:27.608069: step: 1506/1545, loss: 0.016160741448402405 2023-01-23 16:56:28.544584: step: 1508/1545, loss: 0.05739522725343704 2023-01-23 16:56:29.387832: step: 1510/1545, loss: 0.004441514611244202 2023-01-23 16:56:30.230068: step: 1512/1545, loss: 0.0006815955857746303 2023-01-23 16:56:31.123182: step: 1514/1545, loss: 0.09236542135477066 2023-01-23 16:56:32.022622: step: 1516/1545, loss: 0.0008556211832910776 2023-01-23 16:56:32.886708: step: 1518/1545, loss: 0.17208121716976166 2023-01-23 16:56:33.800148: step: 1520/1545, loss: 0.0033182937186211348 2023-01-23 16:56:34.726082: step: 1522/1545, loss: 0.06332867592573166 2023-01-23 16:56:35.551456: step: 1524/1545, loss: 0.11163821816444397 2023-01-23 16:56:36.465169: step: 1526/1545, loss: 0.22409790754318237 2023-01-23 16:56:37.333268: step: 1528/1545, loss: 0.024415064603090286 2023-01-23 16:56:38.262928: step: 1530/1545, loss: 0.0014564201701432467 2023-01-23 16:56:39.164438: step: 1532/1545, loss: 0.036037884652614594 2023-01-23 16:56:40.056783: step: 1534/1545, loss: 0.0158701129257679 2023-01-23 16:56:40.900448: step: 1536/1545, loss: 0.05579955130815506 2023-01-23 16:56:41.780915: step: 1538/1545, loss: 0.025434913113713264 2023-01-23 16:56:42.676991: step: 1540/1545, loss: 0.00515587767586112 2023-01-23 16:56:43.559470: step: 1542/1545, loss: 0.07640475779771805 2023-01-23 16:56:44.478910: step: 1544/1545, loss: 0.03203745558857918 2023-01-23 16:56:45.361079: step: 1546/1545, loss: 0.048877932131290436 2023-01-23 16:56:46.271671: step: 1548/1545, loss: 0.004179352894425392 2023-01-23 16:56:47.150930: step: 1550/1545, loss: 0.0008167413179762661 2023-01-23 16:56:48.045775: step: 1552/1545, loss: 0.004634063225239515 2023-01-23 16:56:48.961063: step: 1554/1545, loss: 0.00444799056276679 2023-01-23 16:56:49.902322: step: 1556/1545, loss: 0.01911976933479309 2023-01-23 16:56:50.753474: step: 1558/1545, loss: 0.011996433138847351 2023-01-23 16:56:51.611974: step: 1560/1545, loss: 0.0035249392967671156 2023-01-23 16:56:52.501780: step: 1562/1545, loss: 0.0008015991188585758 2023-01-23 16:56:53.433242: step: 1564/1545, loss: 0.00023445217811968178 2023-01-23 16:56:54.295459: step: 1566/1545, loss: 0.007980002090334892 2023-01-23 16:56:55.200281: step: 1568/1545, loss: 0.0038311989046633244 2023-01-23 16:56:56.093913: step: 1570/1545, loss: 0.5196508169174194 2023-01-23 16:56:57.031626: step: 1572/1545, loss: 0.0620117150247097 2023-01-23 16:56:57.906420: step: 1574/1545, loss: 0.0003379260888323188 2023-01-23 16:56:58.813752: step: 1576/1545, loss: 0.062205810099840164 2023-01-23 16:56:59.686352: step: 1578/1545, loss: 0.015982650220394135 2023-01-23 16:57:00.584121: step: 1580/1545, loss: 0.01719321496784687 2023-01-23 16:57:01.495055: step: 1582/1545, loss: 0.0010964212706312537 2023-01-23 16:57:02.362282: step: 1584/1545, loss: 0.5154817700386047 2023-01-23 16:57:03.233620: step: 1586/1545, loss: 0.013768416829407215 2023-01-23 16:57:04.170408: step: 1588/1545, loss: 0.0004891693242825568 2023-01-23 16:57:05.122971: step: 1590/1545, loss: 0.000276854814728722 2023-01-23 16:57:06.009724: step: 1592/1545, loss: 0.0006560384063050151 2023-01-23 16:57:06.885425: step: 1594/1545, loss: 0.03841950744390488 2023-01-23 16:57:07.770188: step: 1596/1545, loss: 0.0013734176754951477 2023-01-23 16:57:08.674905: step: 1598/1545, loss: 0.0019069588743150234 2023-01-23 16:57:09.517747: step: 1600/1545, loss: 0.008254104293882847 2023-01-23 16:57:10.419494: step: 1602/1545, loss: 0.0020476647187024355 2023-01-23 16:57:11.317052: step: 1604/1545, loss: 0.02528953365981579 2023-01-23 16:57:12.226260: step: 1606/1545, loss: 0.1628706157207489 2023-01-23 16:57:13.074184: step: 1608/1545, loss: 0.16441527009010315 2023-01-23 16:57:13.922136: step: 1610/1545, loss: 0.0009240453946404159 2023-01-23 16:57:14.794544: step: 1612/1545, loss: 0.02177722193300724 2023-01-23 16:57:15.715933: step: 1614/1545, loss: 0.0008026789873838425 2023-01-23 16:57:16.613270: step: 1616/1545, loss: 0.0013245707377791405 2023-01-23 16:57:17.491161: step: 1618/1545, loss: 0.00041211742791347206 2023-01-23 16:57:18.325655: step: 1620/1545, loss: 0.0014544781297445297 2023-01-23 16:57:19.197905: step: 1622/1545, loss: 0.0176335908472538 2023-01-23 16:57:20.185608: step: 1624/1545, loss: 0.006494300905615091 2023-01-23 16:57:21.109951: step: 1626/1545, loss: 0.14651072025299072 2023-01-23 16:57:21.960285: step: 1628/1545, loss: 0.006037976127117872 2023-01-23 16:57:22.824204: step: 1630/1545, loss: 0.0008259595488198102 2023-01-23 16:57:23.684067: step: 1632/1545, loss: 0.0003054541884921491 2023-01-23 16:57:24.604523: step: 1634/1545, loss: 0.16003644466400146 2023-01-23 16:57:25.461478: step: 1636/1545, loss: 0.0004494079912547022 2023-01-23 16:57:26.307390: step: 1638/1545, loss: 0.0007499080384150147 2023-01-23 16:57:27.154308: step: 1640/1545, loss: 0.0033409572206437588 2023-01-23 16:57:28.035106: step: 1642/1545, loss: 0.01837688311934471 2023-01-23 16:57:28.952226: step: 1644/1545, loss: 0.12593966722488403 2023-01-23 16:57:29.803824: step: 1646/1545, loss: 0.0198554415255785 2023-01-23 16:57:30.715664: step: 1648/1545, loss: 0.026001542806625366 2023-01-23 16:57:31.588911: step: 1650/1545, loss: 0.0009271484450437129 2023-01-23 16:57:32.473603: step: 1652/1545, loss: 0.10065066069364548 2023-01-23 16:57:33.336210: step: 1654/1545, loss: 0.0010659784311428666 2023-01-23 16:57:34.231024: step: 1656/1545, loss: 0.20193490386009216 2023-01-23 16:57:35.101176: step: 1658/1545, loss: 0.0392877496778965 2023-01-23 16:57:35.965060: step: 1660/1545, loss: 0.1786024123430252 2023-01-23 16:57:36.799711: step: 1662/1545, loss: 0.004510463215410709 2023-01-23 16:57:37.708683: step: 1664/1545, loss: 7.144162178039551 2023-01-23 16:57:38.540577: step: 1666/1545, loss: 0.08031251281499863 2023-01-23 16:57:39.445312: step: 1668/1545, loss: 0.27760639786720276 2023-01-23 16:57:40.387950: step: 1670/1545, loss: 0.013095197267830372 2023-01-23 16:57:41.264225: step: 1672/1545, loss: 1.4687350988388062 2023-01-23 16:57:42.148381: step: 1674/1545, loss: 0.15019768476486206 2023-01-23 16:57:43.033181: step: 1676/1545, loss: 0.01234862394630909 2023-01-23 16:57:43.884099: step: 1678/1545, loss: 0.005182511173188686 2023-01-23 16:57:44.766913: step: 1680/1545, loss: 0.030695809051394463 2023-01-23 16:57:45.668618: step: 1682/1545, loss: 0.11858850717544556 2023-01-23 16:57:46.558144: step: 1684/1545, loss: 0.00752456858754158 2023-01-23 16:57:47.412188: step: 1686/1545, loss: 0.07343760877847672 2023-01-23 16:57:48.278476: step: 1688/1545, loss: 0.18059517443180084 2023-01-23 16:57:49.181631: step: 1690/1545, loss: 0.22797174751758575 2023-01-23 16:57:50.075025: step: 1692/1545, loss: 0.053865160793066025 2023-01-23 16:57:50.967910: step: 1694/1545, loss: 0.0052036684937775135 2023-01-23 16:57:51.914728: step: 1696/1545, loss: 0.05337781086564064 2023-01-23 16:57:52.835916: step: 1698/1545, loss: 0.005344931501895189 2023-01-23 16:57:53.738594: step: 1700/1545, loss: 0.00617609079927206 2023-01-23 16:57:54.611057: step: 1702/1545, loss: 0.003543988335877657 2023-01-23 16:57:55.523203: step: 1704/1545, loss: 0.00256736041046679 2023-01-23 16:57:56.376248: step: 1706/1545, loss: 0.0025758477859199047 2023-01-23 16:57:57.249326: step: 1708/1545, loss: 0.01622776687145233 2023-01-23 16:57:58.189332: step: 1710/1545, loss: 0.008395894430577755 2023-01-23 16:57:59.096719: step: 1712/1545, loss: 0.3001910448074341 2023-01-23 16:58:00.022507: step: 1714/1545, loss: 0.0009711708989925683 2023-01-23 16:58:00.926907: step: 1716/1545, loss: 0.02128170058131218 2023-01-23 16:58:01.793989: step: 1718/1545, loss: 0.10317399352788925 2023-01-23 16:58:02.683955: step: 1720/1545, loss: 0.012268045917153358 2023-01-23 16:58:03.549486: step: 1722/1545, loss: 0.0010237148962914944 2023-01-23 16:58:04.391857: step: 1724/1545, loss: 0.0009163614013232291 2023-01-23 16:58:05.257995: step: 1726/1545, loss: 0.0990358293056488 2023-01-23 16:58:06.152327: step: 1728/1545, loss: 0.0020324706565588713 2023-01-23 16:58:07.044701: step: 1730/1545, loss: 0.0004678485565818846 2023-01-23 16:58:07.899450: step: 1732/1545, loss: 0.00399762624874711 2023-01-23 16:58:08.792709: step: 1734/1545, loss: 0.14795494079589844 2023-01-23 16:58:09.702908: step: 1736/1545, loss: 0.0457087904214859 2023-01-23 16:58:10.544669: step: 1738/1545, loss: 0.16588512063026428 2023-01-23 16:58:11.433803: step: 1740/1545, loss: 0.15365004539489746 2023-01-23 16:58:12.315014: step: 1742/1545, loss: 0.005219563841819763 2023-01-23 16:58:13.154354: step: 1744/1545, loss: 0.00250291358679533 2023-01-23 16:58:14.041285: step: 1746/1545, loss: 0.002736024558544159 2023-01-23 16:58:14.924842: step: 1748/1545, loss: 0.07722184807062149 2023-01-23 16:58:15.931740: step: 1750/1545, loss: 0.09789921343326569 2023-01-23 16:58:16.785841: step: 1752/1545, loss: 0.019141819328069687 2023-01-23 16:58:17.663895: step: 1754/1545, loss: 0.0004001488850917667 2023-01-23 16:58:18.517537: step: 1756/1545, loss: 0.029241301119327545 2023-01-23 16:58:19.422089: step: 1758/1545, loss: 0.018704179674386978 2023-01-23 16:58:20.334701: step: 1760/1545, loss: 0.007298835553228855 2023-01-23 16:58:21.198502: step: 1762/1545, loss: 0.007225080393254757 2023-01-23 16:58:22.048686: step: 1764/1545, loss: 0.10908500105142593 2023-01-23 16:58:22.893257: step: 1766/1545, loss: 0.000574365898501128 2023-01-23 16:58:23.789823: step: 1768/1545, loss: 0.0029014558531343937 2023-01-23 16:58:24.648114: step: 1770/1545, loss: 0.0002841460518538952 2023-01-23 16:58:25.511575: step: 1772/1545, loss: 0.05724409967660904 2023-01-23 16:58:26.407680: step: 1774/1545, loss: 0.004068250302225351 2023-01-23 16:58:27.344511: step: 1776/1545, loss: 0.019852766767144203 2023-01-23 16:58:28.245240: step: 1778/1545, loss: 0.01142776571214199 2023-01-23 16:58:29.148206: step: 1780/1545, loss: 0.02251075580716133 2023-01-23 16:58:30.036573: step: 1782/1545, loss: 0.0005179428262636065 2023-01-23 16:58:31.028865: step: 1784/1545, loss: 0.030908873304724693 2023-01-23 16:58:31.903882: step: 1786/1545, loss: 0.0005665444768965244 2023-01-23 16:58:32.817258: step: 1788/1545, loss: 0.006485781166702509 2023-01-23 16:58:33.750347: step: 1790/1545, loss: 0.00484075304120779 2023-01-23 16:58:34.644888: step: 1792/1545, loss: 0.0005325518432073295 2023-01-23 16:58:35.514011: step: 1794/1545, loss: 0.007066769525408745 2023-01-23 16:58:36.413910: step: 1796/1545, loss: 0.050008662045001984 2023-01-23 16:58:37.383396: step: 1798/1545, loss: 0.0005598486168310046 2023-01-23 16:58:38.324223: step: 1800/1545, loss: 0.006429560482501984 2023-01-23 16:58:39.189685: step: 1802/1545, loss: 0.02038257010281086 2023-01-23 16:58:40.102585: step: 1804/1545, loss: 0.0004602147964760661 2023-01-23 16:58:40.958600: step: 1806/1545, loss: 0.037041034549474716 2023-01-23 16:58:41.776507: step: 1808/1545, loss: 0.0003011433582287282 2023-01-23 16:58:42.726083: step: 1810/1545, loss: 0.013653060421347618 2023-01-23 16:58:43.637611: step: 1812/1545, loss: 0.19865451753139496 2023-01-23 16:58:44.522612: step: 1814/1545, loss: 0.2717893719673157 2023-01-23 16:58:45.406795: step: 1816/1545, loss: 7.833658310119063e-05 2023-01-23 16:58:46.331492: step: 1818/1545, loss: 0.0014631613157689571 2023-01-23 16:58:47.190963: step: 1820/1545, loss: 0.00048314747982658446 2023-01-23 16:58:48.109023: step: 1822/1545, loss: 0.004024281166493893 2023-01-23 16:58:48.977019: step: 1824/1545, loss: 0.007452636491507292 2023-01-23 16:58:49.850354: step: 1826/1545, loss: 0.07213807106018066 2023-01-23 16:58:50.728140: step: 1828/1545, loss: 2.465237776050344e-05 2023-01-23 16:58:51.666894: step: 1830/1545, loss: 0.03580882400274277 2023-01-23 16:58:52.547061: step: 1832/1545, loss: 0.1491573303937912 2023-01-23 16:58:53.398374: step: 1834/1545, loss: 0.002895515179261565 2023-01-23 16:58:54.292268: step: 1836/1545, loss: 0.0007240029517561197 2023-01-23 16:58:55.181745: step: 1838/1545, loss: 0.008250589482486248 2023-01-23 16:58:56.076888: step: 1840/1545, loss: 0.013715751469135284 2023-01-23 16:58:56.980592: step: 1842/1545, loss: 0.00041428447002545 2023-01-23 16:58:57.861321: step: 1844/1545, loss: 0.0715385153889656 2023-01-23 16:58:58.772267: step: 1846/1545, loss: 0.0029329475946724415 2023-01-23 16:58:59.640966: step: 1848/1545, loss: 0.047105852514505386 2023-01-23 16:59:00.516702: step: 1850/1545, loss: 0.0018144134664908051 2023-01-23 16:59:01.464520: step: 1852/1545, loss: 0.035808015614748 2023-01-23 16:59:02.341088: step: 1854/1545, loss: 0.0009267569985240698 2023-01-23 16:59:03.218939: step: 1856/1545, loss: 0.2540895342826843 2023-01-23 16:59:04.111374: step: 1858/1545, loss: 0.0005532563664019108 2023-01-23 16:59:04.998198: step: 1860/1545, loss: 0.0011100727133452892 2023-01-23 16:59:05.871976: step: 1862/1545, loss: 0.00771382637321949 2023-01-23 16:59:06.761469: step: 1864/1545, loss: 0.07575105130672455 2023-01-23 16:59:07.694197: step: 1866/1545, loss: 0.005375673063099384 2023-01-23 16:59:08.623518: step: 1868/1545, loss: 0.004248784855008125 2023-01-23 16:59:09.517863: step: 1870/1545, loss: 9.905369370244443e-05 2023-01-23 16:59:10.401453: step: 1872/1545, loss: 0.007245347369462252 2023-01-23 16:59:11.263987: step: 1874/1545, loss: 0.9159233570098877 2023-01-23 16:59:12.150014: step: 1876/1545, loss: 0.004330688156187534 2023-01-23 16:59:12.995732: step: 1878/1545, loss: 0.0038391940761357546 2023-01-23 16:59:13.964178: step: 1880/1545, loss: 0.24259307980537415 2023-01-23 16:59:14.852463: step: 1882/1545, loss: 0.0036133427638560534 2023-01-23 16:59:15.725324: step: 1884/1545, loss: 0.0018395216902717948 2023-01-23 16:59:16.571824: step: 1886/1545, loss: 0.17761962115764618 2023-01-23 16:59:17.426135: step: 1888/1545, loss: 0.0012028294149786234 2023-01-23 16:59:18.349340: step: 1890/1545, loss: 0.014346743933856487 2023-01-23 16:59:19.254604: step: 1892/1545, loss: 0.0004514124011620879 2023-01-23 16:59:20.128842: step: 1894/1545, loss: 0.1730722188949585 2023-01-23 16:59:21.014752: step: 1896/1545, loss: 0.003554421244189143 2023-01-23 16:59:21.939556: step: 1898/1545, loss: 0.017026860266923904 2023-01-23 16:59:22.889522: step: 1900/1545, loss: 0.05527731403708458 2023-01-23 16:59:23.732922: step: 1902/1545, loss: 0.2067081332206726 2023-01-23 16:59:24.647042: step: 1904/1545, loss: 0.000638311670627445 2023-01-23 16:59:25.573834: step: 1906/1545, loss: 0.012065600603818893 2023-01-23 16:59:26.519207: step: 1908/1545, loss: 0.08908208459615707 2023-01-23 16:59:27.478120: step: 1910/1545, loss: 0.44337454438209534 2023-01-23 16:59:28.375372: step: 1912/1545, loss: 0.0983302891254425 2023-01-23 16:59:29.254624: step: 1914/1545, loss: 0.0003016215923707932 2023-01-23 16:59:30.145784: step: 1916/1545, loss: 0.0001146524227806367 2023-01-23 16:59:31.038659: step: 1918/1545, loss: 0.38120076060295105 2023-01-23 16:59:32.002071: step: 1920/1545, loss: 1.3761849403381348 2023-01-23 16:59:32.879888: step: 1922/1545, loss: 0.00893277209252119 2023-01-23 16:59:33.759288: step: 1924/1545, loss: 0.028944246470928192 2023-01-23 16:59:34.620060: step: 1926/1545, loss: 0.022008854895830154 2023-01-23 16:59:35.470346: step: 1928/1545, loss: 0.09532195329666138 2023-01-23 16:59:36.370130: step: 1930/1545, loss: 0.09413383156061172 2023-01-23 16:59:37.253254: step: 1932/1545, loss: 0.037328410893678665 2023-01-23 16:59:38.171972: step: 1934/1545, loss: 0.0003385311283636838 2023-01-23 16:59:39.118430: step: 1936/1545, loss: 0.23166266083717346 2023-01-23 16:59:39.984078: step: 1938/1545, loss: 0.820629894733429 2023-01-23 16:59:40.929222: step: 1940/1545, loss: 0.17031526565551758 2023-01-23 16:59:41.784347: step: 1942/1545, loss: 0.5934343934059143 2023-01-23 16:59:42.652147: step: 1944/1545, loss: 0.5376695394515991 2023-01-23 16:59:43.518986: step: 1946/1545, loss: 0.023723168298602104 2023-01-23 16:59:44.424003: step: 1948/1545, loss: 0.3881077170372009 2023-01-23 16:59:45.332039: step: 1950/1545, loss: 0.046244412660598755 2023-01-23 16:59:46.225417: step: 1952/1545, loss: 0.6270943284034729 2023-01-23 16:59:47.145920: step: 1954/1545, loss: 0.01662408374249935 2023-01-23 16:59:48.051313: step: 1956/1545, loss: 0.0009054936817847192 2023-01-23 16:59:48.980133: step: 1958/1545, loss: 0.22034424543380737 2023-01-23 16:59:49.887912: step: 1960/1545, loss: 0.008244948461651802 2023-01-23 16:59:50.790592: step: 1962/1545, loss: 0.0652376040816307 2023-01-23 16:59:51.686586: step: 1964/1545, loss: 0.027713997289538383 2023-01-23 16:59:52.557083: step: 1966/1545, loss: 0.00039427558658644557 2023-01-23 16:59:53.432682: step: 1968/1545, loss: 0.011610276997089386 2023-01-23 16:59:54.292871: step: 1970/1545, loss: 0.0014006660785526037 2023-01-23 16:59:55.164261: step: 1972/1545, loss: 0.010477855801582336 2023-01-23 16:59:56.062798: step: 1974/1545, loss: 0.1143888384103775 2023-01-23 16:59:56.967003: step: 1976/1545, loss: 0.0017664339393377304 2023-01-23 16:59:57.851813: step: 1978/1545, loss: 0.000359760713763535 2023-01-23 16:59:58.760309: step: 1980/1545, loss: 0.004066909663379192 2023-01-23 16:59:59.687215: step: 1982/1545, loss: 0.007790593896061182 2023-01-23 17:00:00.578203: step: 1984/1545, loss: 0.0053796907886862755 2023-01-23 17:00:01.467969: step: 1986/1545, loss: 0.020128775388002396 2023-01-23 17:00:02.314358: step: 1988/1545, loss: 0.29782408475875854 2023-01-23 17:00:03.177615: step: 1990/1545, loss: 0.0014175826217979193 2023-01-23 17:00:04.127376: step: 1992/1545, loss: 0.0503632090985775 2023-01-23 17:00:04.986249: step: 1994/1545, loss: 0.10722663998603821 2023-01-23 17:00:05.905168: step: 1996/1545, loss: 0.04613776132464409 2023-01-23 17:00:06.764408: step: 1998/1545, loss: 0.04648963361978531 2023-01-23 17:00:07.639474: step: 2000/1545, loss: 0.01600598730146885 2023-01-23 17:00:08.486725: step: 2002/1545, loss: 0.2088792324066162 2023-01-23 17:00:09.417848: step: 2004/1545, loss: 0.0014166064793244004 2023-01-23 17:00:10.338460: step: 2006/1545, loss: 0.0021125669591128826 2023-01-23 17:00:11.198642: step: 2008/1545, loss: 0.8168063163757324 2023-01-23 17:00:12.080582: step: 2010/1545, loss: 0.0032902040984481573 2023-01-23 17:00:12.944432: step: 2012/1545, loss: 0.000610706047154963 2023-01-23 17:00:13.832623: step: 2014/1545, loss: 0.07871176302433014 2023-01-23 17:00:14.719163: step: 2016/1545, loss: 0.2841169536113739 2023-01-23 17:00:15.590256: step: 2018/1545, loss: 0.0979609489440918 2023-01-23 17:00:16.473495: step: 2020/1545, loss: 0.015901517122983932 2023-01-23 17:00:17.348721: step: 2022/1545, loss: 0.02328803762793541 2023-01-23 17:00:18.230002: step: 2024/1545, loss: 0.0041913534514606 2023-01-23 17:00:19.099531: step: 2026/1545, loss: 0.010891850106418133 2023-01-23 17:00:19.989841: step: 2028/1545, loss: 0.004864828661084175 2023-01-23 17:00:20.843207: step: 2030/1545, loss: 0.015232413075864315 2023-01-23 17:00:21.727300: step: 2032/1545, loss: 0.004002308938652277 2023-01-23 17:00:22.701759: step: 2034/1545, loss: 0.0037941362243145704 2023-01-23 17:00:23.583636: step: 2036/1545, loss: 0.0004836346488445997 2023-01-23 17:00:24.467602: step: 2038/1545, loss: 0.010769127868115902 2023-01-23 17:00:25.305775: step: 2040/1545, loss: 0.07567810267210007 2023-01-23 17:00:26.220916: step: 2042/1545, loss: 0.013750841841101646 2023-01-23 17:00:27.106819: step: 2044/1545, loss: 0.0020786302629858255 2023-01-23 17:00:28.039424: step: 2046/1545, loss: 0.03203340619802475 2023-01-23 17:00:28.908868: step: 2048/1545, loss: 0.0169224850833416 2023-01-23 17:00:29.835310: step: 2050/1545, loss: 0.01645619422197342 2023-01-23 17:00:30.707523: step: 2052/1545, loss: 0.004412434995174408 2023-01-23 17:00:31.556931: step: 2054/1545, loss: 0.006830480881035328 2023-01-23 17:00:32.436506: step: 2056/1545, loss: 0.0071108657866716385 2023-01-23 17:00:33.293571: step: 2058/1545, loss: 0.25876614451408386 2023-01-23 17:00:34.238064: step: 2060/1545, loss: 0.2569997012615204 2023-01-23 17:00:35.109165: step: 2062/1545, loss: 0.317097932100296 2023-01-23 17:00:35.969088: step: 2064/1545, loss: 0.008028900250792503 2023-01-23 17:00:36.904175: step: 2066/1545, loss: 0.046895433217287064 2023-01-23 17:00:37.806026: step: 2068/1545, loss: 0.019713617861270905 2023-01-23 17:00:38.655482: step: 2070/1545, loss: 0.15993542969226837 2023-01-23 17:00:39.547476: step: 2072/1545, loss: 0.022002246230840683 2023-01-23 17:00:40.426999: step: 2074/1545, loss: 0.08417046815156937 2023-01-23 17:00:41.336141: step: 2076/1545, loss: 0.003589948173612356 2023-01-23 17:00:42.254591: step: 2078/1545, loss: 0.00017325649969279766 2023-01-23 17:00:43.095683: step: 2080/1545, loss: 0.0020678166765719652 2023-01-23 17:00:43.956743: step: 2082/1545, loss: 0.0029166643507778645 2023-01-23 17:00:44.831876: step: 2084/1545, loss: 0.0025013405829668045 2023-01-23 17:00:45.740618: step: 2086/1545, loss: 0.00806458666920662 2023-01-23 17:00:46.571570: step: 2088/1545, loss: 0.4603411853313446 2023-01-23 17:00:47.440688: step: 2090/1545, loss: 0.002958446741104126 2023-01-23 17:00:48.284042: step: 2092/1545, loss: 0.00017251737881451845 2023-01-23 17:00:49.228454: step: 2094/1545, loss: 0.0053381784819066525 2023-01-23 17:00:50.127404: step: 2096/1545, loss: 0.0009761379915289581 2023-01-23 17:00:51.059842: step: 2098/1545, loss: 0.031144194304943085 2023-01-23 17:00:52.011713: step: 2100/1545, loss: 0.007371086161583662 2023-01-23 17:00:52.934929: step: 2102/1545, loss: 0.038344331085681915 2023-01-23 17:00:53.792327: step: 2104/1545, loss: 0.101873978972435 2023-01-23 17:00:54.700956: step: 2106/1545, loss: 0.0005438871448859572 2023-01-23 17:00:55.572956: step: 2108/1545, loss: 0.0076070260256528854 2023-01-23 17:00:56.456770: step: 2110/1545, loss: 0.0022115048486739397 2023-01-23 17:00:57.293870: step: 2112/1545, loss: 0.5990335941314697 2023-01-23 17:00:58.196374: step: 2114/1545, loss: 0.0002092374925268814 2023-01-23 17:00:59.036209: step: 2116/1545, loss: 0.01440940611064434 2023-01-23 17:00:59.914807: step: 2118/1545, loss: 0.00047140580136328936 2023-01-23 17:01:00.778149: step: 2120/1545, loss: 0.09829007834196091 2023-01-23 17:01:01.662006: step: 2122/1545, loss: 0.006723665166646242 2023-01-23 17:01:02.614509: step: 2124/1545, loss: 0.03531394898891449 2023-01-23 17:01:03.474740: step: 2126/1545, loss: 0.001178742735646665 2023-01-23 17:01:04.326678: step: 2128/1545, loss: 0.009024480357766151 2023-01-23 17:01:05.206373: step: 2130/1545, loss: 0.06203358992934227 2023-01-23 17:01:06.122651: step: 2132/1545, loss: 0.000249078671913594 2023-01-23 17:01:07.035446: step: 2134/1545, loss: 0.009672745130956173 2023-01-23 17:01:07.910338: step: 2136/1545, loss: 0.021748065948486328 2023-01-23 17:01:08.768762: step: 2138/1545, loss: 0.005517007317394018 2023-01-23 17:01:09.644862: step: 2140/1545, loss: 0.016802126541733742 2023-01-23 17:01:10.517791: step: 2142/1545, loss: 0.06081914156675339 2023-01-23 17:01:11.364185: step: 2144/1545, loss: 0.0025757697876542807 2023-01-23 17:01:12.222443: step: 2146/1545, loss: 0.0012065040646120906 2023-01-23 17:01:13.115561: step: 2148/1545, loss: 0.09558272361755371 2023-01-23 17:01:14.033743: step: 2150/1545, loss: 0.00030696485191583633 2023-01-23 17:01:14.927258: step: 2152/1545, loss: 0.07344737648963928 2023-01-23 17:01:15.814048: step: 2154/1545, loss: 0.25656306743621826 2023-01-23 17:01:16.705500: step: 2156/1545, loss: 0.21709102392196655 2023-01-23 17:01:17.625443: step: 2158/1545, loss: 0.0014137604739516973 2023-01-23 17:01:18.526617: step: 2160/1545, loss: 0.0030041225254535675 2023-01-23 17:01:19.445555: step: 2162/1545, loss: 0.05856984108686447 2023-01-23 17:01:20.358036: step: 2164/1545, loss: 0.00015577225713059306 2023-01-23 17:01:21.232149: step: 2166/1545, loss: 0.021356038749217987 2023-01-23 17:01:22.187059: step: 2168/1545, loss: 0.026779193431138992 2023-01-23 17:01:23.048780: step: 2170/1545, loss: 0.0023716569412499666 2023-01-23 17:01:23.981660: step: 2172/1545, loss: 0.0034059397876262665 2023-01-23 17:01:24.839792: step: 2174/1545, loss: 0.021207543089985847 2023-01-23 17:01:25.715446: step: 2176/1545, loss: 0.0016030768165364861 2023-01-23 17:01:26.627148: step: 2178/1545, loss: 0.004860653541982174 2023-01-23 17:01:27.519833: step: 2180/1545, loss: 0.012027427554130554 2023-01-23 17:01:28.488593: step: 2182/1545, loss: 0.04542883485555649 2023-01-23 17:01:29.386455: step: 2184/1545, loss: 0.13067275285720825 2023-01-23 17:01:30.271305: step: 2186/1545, loss: 0.007878859527409077 2023-01-23 17:01:31.181333: step: 2188/1545, loss: 0.01662497967481613 2023-01-23 17:01:32.098233: step: 2190/1545, loss: 0.13034354150295258 2023-01-23 17:01:33.005881: step: 2192/1545, loss: 0.0043162084184587 2023-01-23 17:01:33.898322: step: 2194/1545, loss: 0.0059794215485453606 2023-01-23 17:01:34.754725: step: 2196/1545, loss: 0.009710042737424374 2023-01-23 17:01:35.626888: step: 2198/1545, loss: 0.11391006410121918 2023-01-23 17:01:36.496737: step: 2200/1545, loss: 0.014210349880158901 2023-01-23 17:01:37.358601: step: 2202/1545, loss: 0.0024577993899583817 2023-01-23 17:01:38.223264: step: 2204/1545, loss: 0.0018941618036478758 2023-01-23 17:01:39.094169: step: 2206/1545, loss: 0.00047992897452786565 2023-01-23 17:01:39.958072: step: 2208/1545, loss: 0.010027660988271236 2023-01-23 17:01:40.849037: step: 2210/1545, loss: 0.0001845213701017201 2023-01-23 17:01:41.770009: step: 2212/1545, loss: 0.1310199648141861 2023-01-23 17:01:42.651297: step: 2214/1545, loss: 0.059868838638067245 2023-01-23 17:01:43.542320: step: 2216/1545, loss: 0.0950329378247261 2023-01-23 17:01:44.445776: step: 2218/1545, loss: 0.0008231024257838726 2023-01-23 17:01:45.292051: step: 2220/1545, loss: 0.28640955686569214 2023-01-23 17:01:46.208388: step: 2222/1545, loss: 0.0912637934088707 2023-01-23 17:01:47.182872: step: 2224/1545, loss: 0.00029445067048072815 2023-01-23 17:01:48.040722: step: 2226/1545, loss: 0.027954142540693283 2023-01-23 17:01:48.950717: step: 2228/1545, loss: 0.05059828609228134 2023-01-23 17:01:49.823876: step: 2230/1545, loss: 0.5786237120628357 2023-01-23 17:01:50.832549: step: 2232/1545, loss: 0.005186404101550579 2023-01-23 17:01:51.707858: step: 2234/1545, loss: 0.0006387232569977641 2023-01-23 17:01:52.593528: step: 2236/1545, loss: 0.31025323271751404 2023-01-23 17:01:53.461939: step: 2238/1545, loss: 0.0017410991713404655 2023-01-23 17:01:54.375509: step: 2240/1545, loss: 0.010407977737486362 2023-01-23 17:01:55.217820: step: 2242/1545, loss: 0.00030275675817392766 2023-01-23 17:01:56.140812: step: 2244/1545, loss: 0.11001419275999069 2023-01-23 17:01:57.016672: step: 2246/1545, loss: 0.002244188915938139 2023-01-23 17:01:57.864610: step: 2248/1545, loss: 0.0022023457568138838 2023-01-23 17:01:58.808689: step: 2250/1545, loss: 0.012461069040000439 2023-01-23 17:01:59.670557: step: 2252/1545, loss: 0.000313810131046921 2023-01-23 17:02:00.578701: step: 2254/1545, loss: 0.182062566280365 2023-01-23 17:02:01.451195: step: 2256/1545, loss: 0.04061659425497055 2023-01-23 17:02:02.299475: step: 2258/1545, loss: 0.0797361508011818 2023-01-23 17:02:03.210847: step: 2260/1545, loss: 0.3271147906780243 2023-01-23 17:02:04.109566: step: 2262/1545, loss: 0.0016873354325070977 2023-01-23 17:02:04.982275: step: 2264/1545, loss: 0.31042397022247314 2023-01-23 17:02:05.818633: step: 2266/1545, loss: 0.001379617489874363 2023-01-23 17:02:06.705720: step: 2268/1545, loss: 1.9245819203206338e-05 2023-01-23 17:02:07.613561: step: 2270/1545, loss: 0.001780961756594479 2023-01-23 17:02:08.478795: step: 2272/1545, loss: 0.005805047228932381 2023-01-23 17:02:09.427539: step: 2274/1545, loss: 0.25064998865127563 2023-01-23 17:02:10.294047: step: 2276/1545, loss: 0.022142771631479263 2023-01-23 17:02:11.178981: step: 2278/1545, loss: 0.004948512185364962 2023-01-23 17:02:12.100854: step: 2280/1545, loss: 0.0007460721535608172 2023-01-23 17:02:13.025456: step: 2282/1545, loss: 0.030819060280919075 2023-01-23 17:02:13.878942: step: 2284/1545, loss: 0.07287674397230148 2023-01-23 17:02:14.731886: step: 2286/1545, loss: 7.665127486689016e-05 2023-01-23 17:02:15.601900: step: 2288/1545, loss: 0.024447619915008545 2023-01-23 17:02:16.489096: step: 2290/1545, loss: 0.07818478345870972 2023-01-23 17:02:17.359430: step: 2292/1545, loss: 0.0030730876605957747 2023-01-23 17:02:18.225110: step: 2294/1545, loss: 0.7160732746124268 2023-01-23 17:02:19.141433: step: 2296/1545, loss: 0.21978065371513367 2023-01-23 17:02:20.003076: step: 2298/1545, loss: 0.08507701754570007 2023-01-23 17:02:20.838607: step: 2300/1545, loss: 0.01221027784049511 2023-01-23 17:02:21.717364: step: 2302/1545, loss: 0.11086542159318924 2023-01-23 17:02:22.580500: step: 2304/1545, loss: 0.00013259165280032903 2023-01-23 17:02:23.467532: step: 2306/1545, loss: 0.12321280688047409 2023-01-23 17:02:24.383404: step: 2308/1545, loss: 0.021388443186879158 2023-01-23 17:02:25.290703: step: 2310/1545, loss: 0.05031253397464752 2023-01-23 17:02:26.123919: step: 2312/1545, loss: 0.06190250441431999 2023-01-23 17:02:27.025837: step: 2314/1545, loss: 0.04294959828257561 2023-01-23 17:02:27.904922: step: 2316/1545, loss: 0.003021314274519682 2023-01-23 17:02:28.788978: step: 2318/1545, loss: 0.002490161918103695 2023-01-23 17:02:29.664385: step: 2320/1545, loss: 0.06933841109275818 2023-01-23 17:02:30.535368: step: 2322/1545, loss: 0.01220661774277687 2023-01-23 17:02:31.551808: step: 2324/1545, loss: 0.0003630408027675003 2023-01-23 17:02:32.418753: step: 2326/1545, loss: 0.04743119329214096 2023-01-23 17:02:33.286431: step: 2328/1545, loss: 0.00463793333619833 2023-01-23 17:02:34.147102: step: 2330/1545, loss: 0.007776459213346243 2023-01-23 17:02:35.061582: step: 2332/1545, loss: 0.0012088618241250515 2023-01-23 17:02:35.926763: step: 2334/1545, loss: 0.001313576241955161 2023-01-23 17:02:36.804184: step: 2336/1545, loss: 0.017766565084457397 2023-01-23 17:02:37.695104: step: 2338/1545, loss: 0.0005552142392843962 2023-01-23 17:02:38.568270: step: 2340/1545, loss: 0.07395083457231522 2023-01-23 17:02:39.417598: step: 2342/1545, loss: 0.003643073607236147 2023-01-23 17:02:40.312066: step: 2344/1545, loss: 0.007067550905048847 2023-01-23 17:02:41.210872: step: 2346/1545, loss: 0.01171802543103695 2023-01-23 17:02:42.061474: step: 2348/1545, loss: 0.002477537142112851 2023-01-23 17:02:42.972936: step: 2350/1545, loss: 0.2485668808221817 2023-01-23 17:02:43.835047: step: 2352/1545, loss: 0.0009139363537542522 2023-01-23 17:02:44.694960: step: 2354/1545, loss: 0.0003264811239205301 2023-01-23 17:02:45.550221: step: 2356/1545, loss: 0.006849583238363266 2023-01-23 17:02:46.454488: step: 2358/1545, loss: 0.0017045263666659594 2023-01-23 17:02:47.358692: step: 2360/1545, loss: 0.0043566105887293816 2023-01-23 17:02:48.280910: step: 2362/1545, loss: 0.001386359566822648 2023-01-23 17:02:49.155420: step: 2364/1545, loss: 0.00046156992902979255 2023-01-23 17:02:50.075046: step: 2366/1545, loss: 0.012683148495852947 2023-01-23 17:02:50.912871: step: 2368/1545, loss: 0.0006900114822201431 2023-01-23 17:02:51.810478: step: 2370/1545, loss: 0.005003553349524736 2023-01-23 17:02:52.736747: step: 2372/1545, loss: 0.000843830406665802 2023-01-23 17:02:53.624033: step: 2374/1545, loss: 0.28506726026535034 2023-01-23 17:02:54.509089: step: 2376/1545, loss: 0.0597747266292572 2023-01-23 17:02:55.463840: step: 2378/1545, loss: 0.3760216534137726 2023-01-23 17:02:56.322123: step: 2380/1545, loss: 0.0018881907453760505 2023-01-23 17:02:57.214735: step: 2382/1545, loss: 0.013640875928103924 2023-01-23 17:02:58.037101: step: 2384/1545, loss: 0.0009037098498083651 2023-01-23 17:02:58.917951: step: 2386/1545, loss: 0.11805009096860886 2023-01-23 17:02:59.822402: step: 2388/1545, loss: 0.0017089633038267493 2023-01-23 17:03:00.727791: step: 2390/1545, loss: 0.00329231726936996 2023-01-23 17:03:01.588649: step: 2392/1545, loss: 0.34294211864471436 2023-01-23 17:03:02.441195: step: 2394/1545, loss: 0.002628496615216136 2023-01-23 17:03:03.302919: step: 2396/1545, loss: 0.017150452360510826 2023-01-23 17:03:04.172927: step: 2398/1545, loss: 0.0014407063135877252 2023-01-23 17:03:05.064652: step: 2400/1545, loss: 0.0006034937687218189 2023-01-23 17:03:05.928795: step: 2402/1545, loss: 0.004683207254856825 2023-01-23 17:03:06.823625: step: 2404/1545, loss: 0.004809404723346233 2023-01-23 17:03:07.734684: step: 2406/1545, loss: 0.04222201555967331 2023-01-23 17:03:08.613724: step: 2408/1545, loss: 0.008235441520810127 2023-01-23 17:03:09.462829: step: 2410/1545, loss: 0.001635607099160552 2023-01-23 17:03:10.376407: step: 2412/1545, loss: 0.005274759605526924 2023-01-23 17:03:11.289954: step: 2414/1545, loss: 0.002894158475100994 2023-01-23 17:03:12.117046: step: 2416/1545, loss: 0.0014449829468503594 2023-01-23 17:03:12.975238: step: 2418/1545, loss: 0.024375181645154953 2023-01-23 17:03:13.831167: step: 2420/1545, loss: 0.0003072184626944363 2023-01-23 17:03:14.784786: step: 2422/1545, loss: 0.006352743599563837 2023-01-23 17:03:15.756712: step: 2424/1545, loss: 0.0007098696660250425 2023-01-23 17:03:16.642192: step: 2426/1545, loss: 0.15032809972763062 2023-01-23 17:03:17.561458: step: 2428/1545, loss: 0.002594677032902837 2023-01-23 17:03:18.421581: step: 2430/1545, loss: 0.0030794560443609953 2023-01-23 17:03:19.301196: step: 2432/1545, loss: 0.928818941116333 2023-01-23 17:03:20.239350: step: 2434/1545, loss: 0.267690509557724 2023-01-23 17:03:21.113873: step: 2436/1545, loss: 0.0007775379344820976 2023-01-23 17:03:22.014361: step: 2438/1545, loss: 0.001268316525965929 2023-01-23 17:03:22.881838: step: 2440/1545, loss: 1.350868821144104 2023-01-23 17:03:23.787720: step: 2442/1545, loss: 0.0015625212108716369 2023-01-23 17:03:24.659100: step: 2444/1545, loss: 0.21623678505420685 2023-01-23 17:03:25.557400: step: 2446/1545, loss: 0.03497502580285072 2023-01-23 17:03:26.400780: step: 2448/1545, loss: 0.0004075960605405271 2023-01-23 17:03:27.326679: step: 2450/1545, loss: 0.11969709396362305 2023-01-23 17:03:28.210647: step: 2452/1545, loss: 8.606007759226486e-05 2023-01-23 17:03:29.085697: step: 2454/1545, loss: 0.0062401327304542065 2023-01-23 17:03:29.979470: step: 2456/1545, loss: 0.0009161313064396381 2023-01-23 17:03:30.881290: step: 2458/1545, loss: 0.007519618608057499 2023-01-23 17:03:31.734535: step: 2460/1545, loss: 0.09482605755329132 2023-01-23 17:03:32.623515: step: 2462/1545, loss: 0.004741876386106014 2023-01-23 17:03:33.505522: step: 2464/1545, loss: 0.2537284791469574 2023-01-23 17:03:34.352667: step: 2466/1545, loss: 0.00031870586099103093 2023-01-23 17:03:35.237751: step: 2468/1545, loss: 0.004353849217295647 2023-01-23 17:03:36.130447: step: 2470/1545, loss: 0.008811240084469318 2023-01-23 17:03:37.016918: step: 2472/1545, loss: 0.0002089888439513743 2023-01-23 17:03:37.878581: step: 2474/1545, loss: 0.0018944267649203539 2023-01-23 17:03:38.771848: step: 2476/1545, loss: 0.014270540326833725 2023-01-23 17:03:39.626718: step: 2478/1545, loss: 0.005202850792557001 2023-01-23 17:03:40.482074: step: 2480/1545, loss: 0.029062187299132347 2023-01-23 17:03:41.352056: step: 2482/1545, loss: 0.0014532975619658828 2023-01-23 17:03:42.285166: step: 2484/1545, loss: 0.02535191737115383 2023-01-23 17:03:43.178102: step: 2486/1545, loss: 0.0019764427561312914 2023-01-23 17:03:44.027992: step: 2488/1545, loss: 0.2442312389612198 2023-01-23 17:03:44.920580: step: 2490/1545, loss: 0.013501280918717384 2023-01-23 17:03:45.809115: step: 2492/1545, loss: 0.0023624543100595474 2023-01-23 17:03:46.670610: step: 2494/1545, loss: 0.003929405473172665 2023-01-23 17:03:47.565923: step: 2496/1545, loss: 0.09086291491985321 2023-01-23 17:03:48.418744: step: 2498/1545, loss: 0.0024766228161752224 2023-01-23 17:03:49.296689: step: 2500/1545, loss: 0.00015300083032343537 2023-01-23 17:03:50.186441: step: 2502/1545, loss: 0.00670623267069459 2023-01-23 17:03:51.051532: step: 2504/1545, loss: 0.05491901561617851 2023-01-23 17:03:51.994861: step: 2506/1545, loss: 0.007508934009820223 2023-01-23 17:03:52.900113: step: 2508/1545, loss: 0.0003990050754509866 2023-01-23 17:03:53.866333: step: 2510/1545, loss: 0.0007238405523821712 2023-01-23 17:03:54.772950: step: 2512/1545, loss: 0.017873793840408325 2023-01-23 17:03:55.628957: step: 2514/1545, loss: 0.0006709122681058943 2023-01-23 17:03:56.540620: step: 2516/1545, loss: 0.021900923922657967 2023-01-23 17:03:57.390570: step: 2518/1545, loss: 0.005635447800159454 2023-01-23 17:03:58.295087: step: 2520/1545, loss: 0.011146016418933868 2023-01-23 17:03:59.152033: step: 2522/1545, loss: 0.0017069975147023797 2023-01-23 17:04:00.013437: step: 2524/1545, loss: 0.014891041442751884 2023-01-23 17:04:00.906452: step: 2526/1545, loss: 0.005567926913499832 2023-01-23 17:04:01.802404: step: 2528/1545, loss: 0.20024922490119934 2023-01-23 17:04:02.741476: step: 2530/1545, loss: 0.18630340695381165 2023-01-23 17:04:03.618199: step: 2532/1545, loss: 0.0004228658217471093 2023-01-23 17:04:04.491814: step: 2534/1545, loss: 9.593635331839323e-05 2023-01-23 17:04:05.338854: step: 2536/1545, loss: 0.07491884380578995 2023-01-23 17:04:06.194486: step: 2538/1545, loss: 0.0010656305821612477 2023-01-23 17:04:07.081678: step: 2540/1545, loss: 0.00430163461714983 2023-01-23 17:04:08.002176: step: 2542/1545, loss: 0.006435606628656387 2023-01-23 17:04:08.916475: step: 2544/1545, loss: 0.23720534145832062 2023-01-23 17:04:09.836476: step: 2546/1545, loss: 0.16631783545017242 2023-01-23 17:04:10.712713: step: 2548/1545, loss: 0.0006750808097422123 2023-01-23 17:04:11.577695: step: 2550/1545, loss: 0.28222954273223877 2023-01-23 17:04:12.468466: step: 2552/1545, loss: 0.0010513493325561285 2023-01-23 17:04:13.325249: step: 2554/1545, loss: 0.12047438323497772 2023-01-23 17:04:14.176154: step: 2556/1545, loss: 2.336695671081543 2023-01-23 17:04:15.068198: step: 2558/1545, loss: 0.037239089608192444 2023-01-23 17:04:15.919454: step: 2560/1545, loss: 0.0007056221948005259 2023-01-23 17:04:16.800943: step: 2562/1545, loss: 0.02165040746331215 2023-01-23 17:04:17.648068: step: 2564/1545, loss: 0.0061956183053553104 2023-01-23 17:04:18.526814: step: 2566/1545, loss: 0.6665879487991333 2023-01-23 17:04:19.416447: step: 2568/1545, loss: 0.07011136412620544 2023-01-23 17:04:20.343683: step: 2570/1545, loss: 0.0024580280296504498 2023-01-23 17:04:21.232319: step: 2572/1545, loss: 0.012481197714805603 2023-01-23 17:04:22.097465: step: 2574/1545, loss: 0.003769806120544672 2023-01-23 17:04:22.964736: step: 2576/1545, loss: 0.02856108918786049 2023-01-23 17:04:23.824628: step: 2578/1545, loss: 0.0009091662941500545 2023-01-23 17:04:24.756170: step: 2580/1545, loss: 0.2761232256889343 2023-01-23 17:04:25.642482: step: 2582/1545, loss: 0.0007271343492902815 2023-01-23 17:04:26.530228: step: 2584/1545, loss: 0.00046756514348089695 2023-01-23 17:04:27.426090: step: 2586/1545, loss: 0.02443947084248066 2023-01-23 17:04:28.268511: step: 2588/1545, loss: 0.0004853833233937621 2023-01-23 17:04:29.181107: step: 2590/1545, loss: 0.0005676020518876612 2023-01-23 17:04:30.011344: step: 2592/1545, loss: 0.00018370094767306 2023-01-23 17:04:30.881991: step: 2594/1545, loss: 0.031156180426478386 2023-01-23 17:04:31.739808: step: 2596/1545, loss: 0.1276967078447342 2023-01-23 17:04:32.613403: step: 2598/1545, loss: 0.19541478157043457 2023-01-23 17:04:33.455463: step: 2600/1545, loss: 0.0062307072803378105 2023-01-23 17:04:34.315734: step: 2602/1545, loss: 0.6052535176277161 2023-01-23 17:04:35.231207: step: 2604/1545, loss: 0.003053346648812294 2023-01-23 17:04:36.085393: step: 2606/1545, loss: 0.031730107963085175 2023-01-23 17:04:36.976626: step: 2608/1545, loss: 0.0006629298441112041 2023-01-23 17:04:37.884774: step: 2610/1545, loss: 0.008937490172684193 2023-01-23 17:04:38.819835: step: 2612/1545, loss: 0.5535309910774231 2023-01-23 17:04:39.705264: step: 2614/1545, loss: 0.10373915731906891 2023-01-23 17:04:40.594084: step: 2616/1545, loss: 0.00031923706410452724 2023-01-23 17:04:41.474948: step: 2618/1545, loss: 0.32771289348602295 2023-01-23 17:04:42.323358: step: 2620/1545, loss: 0.00037709978641942143 2023-01-23 17:04:43.223415: step: 2622/1545, loss: 0.0007340942975133657 2023-01-23 17:04:44.100203: step: 2624/1545, loss: 0.08242126554250717 2023-01-23 17:04:44.999257: step: 2626/1545, loss: 0.010648059658706188 2023-01-23 17:04:45.844499: step: 2628/1545, loss: 0.013826634734869003 2023-01-23 17:04:46.706299: step: 2630/1545, loss: 0.12683799862861633 2023-01-23 17:04:47.566105: step: 2632/1545, loss: 0.05476062744855881 2023-01-23 17:04:48.422827: step: 2634/1545, loss: 0.03747772052884102 2023-01-23 17:04:49.412569: step: 2636/1545, loss: 0.19688160717487335 2023-01-23 17:04:50.292432: step: 2638/1545, loss: 0.011353733949363232 2023-01-23 17:04:51.186337: step: 2640/1545, loss: 0.5879229307174683 2023-01-23 17:04:52.073303: step: 2642/1545, loss: 0.030185913667082787 2023-01-23 17:04:52.937975: step: 2644/1545, loss: 0.053574088960886 2023-01-23 17:04:53.814661: step: 2646/1545, loss: 0.001056584296748042 2023-01-23 17:04:54.711871: step: 2648/1545, loss: 0.06583482772111893 2023-01-23 17:04:55.572239: step: 2650/1545, loss: 0.2898472845554352 2023-01-23 17:04:56.577073: step: 2652/1545, loss: 0.00233640824444592 2023-01-23 17:04:57.464520: step: 2654/1545, loss: 0.12119629234075546 2023-01-23 17:04:58.304708: step: 2656/1545, loss: 0.0007150323363021016 2023-01-23 17:04:59.163718: step: 2658/1545, loss: 0.06035720184445381 2023-01-23 17:05:00.068853: step: 2660/1545, loss: 0.022410357370972633 2023-01-23 17:05:00.923624: step: 2662/1545, loss: 0.03477770462632179 2023-01-23 17:05:01.816531: step: 2664/1545, loss: 0.05276855081319809 2023-01-23 17:05:02.710671: step: 2666/1545, loss: 0.08298385143280029 2023-01-23 17:05:03.613951: step: 2668/1545, loss: 0.01843992993235588 2023-01-23 17:05:04.491309: step: 2670/1545, loss: 0.037193309515714645 2023-01-23 17:05:05.404169: step: 2672/1545, loss: 0.09715054929256439 2023-01-23 17:05:06.269458: step: 2674/1545, loss: 0.0917588621377945 2023-01-23 17:05:07.128147: step: 2676/1545, loss: 0.001048069796524942 2023-01-23 17:05:07.988058: step: 2678/1545, loss: 0.014435473829507828 2023-01-23 17:05:08.883733: step: 2680/1545, loss: 0.10551674664020538 2023-01-23 17:05:09.762377: step: 2682/1545, loss: 0.11780072748661041 2023-01-23 17:05:10.601829: step: 2684/1545, loss: 0.0022729961201548576 2023-01-23 17:05:11.467227: step: 2686/1545, loss: 0.08640719950199127 2023-01-23 17:05:12.338005: step: 2688/1545, loss: 0.07129308581352234 2023-01-23 17:05:13.217007: step: 2690/1545, loss: 0.012707059271633625 2023-01-23 17:05:14.064312: step: 2692/1545, loss: 0.0023503857664763927 2023-01-23 17:05:14.916453: step: 2694/1545, loss: 0.531915009021759 2023-01-23 17:05:15.796357: step: 2696/1545, loss: 0.0021776126231998205 2023-01-23 17:05:16.665990: step: 2698/1545, loss: 0.038557566702365875 2023-01-23 17:05:17.581297: step: 2700/1545, loss: 0.1878502070903778 2023-01-23 17:05:18.431010: step: 2702/1545, loss: 0.13159047067165375 2023-01-23 17:05:19.319819: step: 2704/1545, loss: 0.03767601028084755 2023-01-23 17:05:20.219063: step: 2706/1545, loss: 0.018781214952468872 2023-01-23 17:05:21.159639: step: 2708/1545, loss: 0.03896370530128479 2023-01-23 17:05:22.030616: step: 2710/1545, loss: 0.00605427473783493 2023-01-23 17:05:22.890535: step: 2712/1545, loss: 0.005467778537422419 2023-01-23 17:05:23.728875: step: 2714/1545, loss: 3.4427690505981445 2023-01-23 17:05:24.634076: step: 2716/1545, loss: 0.0027261145878583193 2023-01-23 17:05:25.464575: step: 2718/1545, loss: 0.0017402449157088995 2023-01-23 17:05:26.389608: step: 2720/1545, loss: 0.012334764003753662 2023-01-23 17:05:27.288775: step: 2722/1545, loss: 0.03661825880408287 2023-01-23 17:05:28.121936: step: 2724/1545, loss: 0.005465940106660128 2023-01-23 17:05:29.005838: step: 2726/1545, loss: 0.0008881631074473262 2023-01-23 17:05:29.889870: step: 2728/1545, loss: 0.006880661007016897 2023-01-23 17:05:30.769622: step: 2730/1545, loss: 0.06163211911916733 2023-01-23 17:05:31.612655: step: 2732/1545, loss: 0.00313556962646544 2023-01-23 17:05:32.563626: step: 2734/1545, loss: 0.1720682680606842 2023-01-23 17:05:33.504211: step: 2736/1545, loss: 0.0007621808908879757 2023-01-23 17:05:34.344473: step: 2738/1545, loss: 0.0010216475930064917 2023-01-23 17:05:35.232187: step: 2740/1545, loss: 0.0008162676822394133 2023-01-23 17:05:36.071703: step: 2742/1545, loss: 0.003802885999903083 2023-01-23 17:05:36.935787: step: 2744/1545, loss: 0.011121952906250954 2023-01-23 17:05:37.820950: step: 2746/1545, loss: 0.008746952749788761 2023-01-23 17:05:38.681700: step: 2748/1545, loss: 0.037493105977773666 2023-01-23 17:05:39.545085: step: 2750/1545, loss: 0.09700603783130646 2023-01-23 17:05:40.428140: step: 2752/1545, loss: 0.0008719611796550453 2023-01-23 17:05:41.344515: step: 2754/1545, loss: 0.1039358377456665 2023-01-23 17:05:42.206555: step: 2756/1545, loss: 0.21636398136615753 2023-01-23 17:05:43.079227: step: 2758/1545, loss: 0.01019491907209158 2023-01-23 17:05:43.938263: step: 2760/1545, loss: 0.0022798730060458183 2023-01-23 17:05:44.866488: step: 2762/1545, loss: 0.0001705912291072309 2023-01-23 17:05:45.737452: step: 2764/1545, loss: 0.27642008662223816 2023-01-23 17:05:46.612996: step: 2766/1545, loss: 0.25704705715179443 2023-01-23 17:05:47.482398: step: 2768/1545, loss: 0.052354905754327774 2023-01-23 17:05:48.380500: step: 2770/1545, loss: 0.17536628246307373 2023-01-23 17:05:49.271939: step: 2772/1545, loss: 0.0012017154367640615 2023-01-23 17:05:50.217506: step: 2774/1545, loss: 0.20446975529193878 2023-01-23 17:05:51.107948: step: 2776/1545, loss: 9.808065078686923e-05 2023-01-23 17:05:51.994535: step: 2778/1545, loss: 0.0001787291548680514 2023-01-23 17:05:52.914209: step: 2780/1545, loss: 0.03705626726150513 2023-01-23 17:05:53.806158: step: 2782/1545, loss: 0.17112022638320923 2023-01-23 17:05:54.740111: step: 2784/1545, loss: 0.0028515360318124294 2023-01-23 17:05:55.593177: step: 2786/1545, loss: 0.0008893187041394413 2023-01-23 17:05:56.450600: step: 2788/1545, loss: 7.988748257048428e-05 2023-01-23 17:05:57.281446: step: 2790/1545, loss: 0.20426401495933533 2023-01-23 17:05:58.105371: step: 2792/1545, loss: 0.0036497435066848993 2023-01-23 17:05:58.978215: step: 2794/1545, loss: 0.2358587086200714 2023-01-23 17:05:59.825464: step: 2796/1545, loss: 0.05756046622991562 2023-01-23 17:06:00.668949: step: 2798/1545, loss: 0.2013300061225891 2023-01-23 17:06:01.553156: step: 2800/1545, loss: 0.005644675809890032 2023-01-23 17:06:02.423058: step: 2802/1545, loss: 0.0011545908637344837 2023-01-23 17:06:03.288044: step: 2804/1545, loss: 0.15124477446079254 2023-01-23 17:06:04.158514: step: 2806/1545, loss: 0.15581311285495758 2023-01-23 17:06:04.997666: step: 2808/1545, loss: 0.005222840700298548 2023-01-23 17:06:05.940467: step: 2810/1545, loss: 0.009196446277201176 2023-01-23 17:06:06.837121: step: 2812/1545, loss: 0.05319008603692055 2023-01-23 17:06:07.678458: step: 2814/1545, loss: 0.003555363742634654 2023-01-23 17:06:08.558488: step: 2816/1545, loss: 0.002515333006158471 2023-01-23 17:06:09.414019: step: 2818/1545, loss: 2.182807683944702 2023-01-23 17:06:10.308096: step: 2820/1545, loss: 0.0056770965456962585 2023-01-23 17:06:11.184427: step: 2822/1545, loss: 0.00092232262250036 2023-01-23 17:06:12.063286: step: 2824/1545, loss: 0.030225038528442383 2023-01-23 17:06:13.078616: step: 2826/1545, loss: 0.004371169023215771 2023-01-23 17:06:13.969255: step: 2828/1545, loss: 0.1458696722984314 2023-01-23 17:06:14.837814: step: 2830/1545, loss: 0.057793255895376205 2023-01-23 17:06:15.695384: step: 2832/1545, loss: 0.18983811140060425 2023-01-23 17:06:16.575701: step: 2834/1545, loss: 0.001176114077679813 2023-01-23 17:06:17.463307: step: 2836/1545, loss: 0.12993650138378143 2023-01-23 17:06:18.332386: step: 2838/1545, loss: 0.0032768885139375925 2023-01-23 17:06:19.218810: step: 2840/1545, loss: 0.0020584790036082268 2023-01-23 17:06:20.102353: step: 2842/1545, loss: 4.29056453704834 2023-01-23 17:06:21.002663: step: 2844/1545, loss: 0.01042101625353098 2023-01-23 17:06:21.852926: step: 2846/1545, loss: 0.04488850757479668 2023-01-23 17:06:22.735720: step: 2848/1545, loss: 0.043944451957941055 2023-01-23 17:06:23.621796: step: 2850/1545, loss: 0.009975641965866089 2023-01-23 17:06:24.504700: step: 2852/1545, loss: 0.07371867448091507 2023-01-23 17:06:25.393546: step: 2854/1545, loss: 0.030359402298927307 2023-01-23 17:06:26.236250: step: 2856/1545, loss: 0.0006736968061886728 2023-01-23 17:06:27.087086: step: 2858/1545, loss: 0.0037070740945637226 2023-01-23 17:06:27.939845: step: 2860/1545, loss: 0.0018508482025936246 2023-01-23 17:06:28.806264: step: 2862/1545, loss: 0.11284928023815155 2023-01-23 17:06:29.692372: step: 2864/1545, loss: 0.029827050864696503 2023-01-23 17:06:30.588915: step: 2866/1545, loss: 0.001352106686681509 2023-01-23 17:06:31.519792: step: 2868/1545, loss: 0.035838015377521515 2023-01-23 17:06:32.448333: step: 2870/1545, loss: 0.15926355123519897 2023-01-23 17:06:33.348287: step: 2872/1545, loss: 0.22442813217639923 2023-01-23 17:06:34.174293: step: 2874/1545, loss: 0.5606259107589722 2023-01-23 17:06:35.028058: step: 2876/1545, loss: 0.013270262628793716 2023-01-23 17:06:35.890195: step: 2878/1545, loss: 0.0007832733099348843 2023-01-23 17:06:36.798780: step: 2880/1545, loss: 0.1272372156381607 2023-01-23 17:06:37.632648: step: 2882/1545, loss: 0.2490612268447876 2023-01-23 17:06:38.507257: step: 2884/1545, loss: 0.0034872463438659906 2023-01-23 17:06:39.352172: step: 2886/1545, loss: 0.19825664162635803 2023-01-23 17:06:40.235641: step: 2888/1545, loss: 0.02630580961704254 2023-01-23 17:06:41.119223: step: 2890/1545, loss: 0.08521994948387146 2023-01-23 17:06:41.992204: step: 2892/1545, loss: 0.005275911185890436 2023-01-23 17:06:42.898800: step: 2894/1545, loss: 0.002516559325158596 2023-01-23 17:06:43.780903: step: 2896/1545, loss: 0.00043271624599583447 2023-01-23 17:06:44.666507: step: 2898/1545, loss: 0.012649011798202991 2023-01-23 17:06:45.538990: step: 2900/1545, loss: 0.02069585584104061 2023-01-23 17:06:46.433675: step: 2902/1545, loss: 0.17602820694446564 2023-01-23 17:06:47.305672: step: 2904/1545, loss: 0.00397774251177907 2023-01-23 17:06:48.155742: step: 2906/1545, loss: 0.20058926939964294 2023-01-23 17:06:49.021630: step: 2908/1545, loss: 0.07618844509124756 2023-01-23 17:06:49.884663: step: 2910/1545, loss: 0.002955922856926918 2023-01-23 17:06:50.766612: step: 2912/1545, loss: 0.009422129020094872 2023-01-23 17:06:51.625842: step: 2914/1545, loss: 0.028663016855716705 2023-01-23 17:06:52.496220: step: 2916/1545, loss: 0.012791342101991177 2023-01-23 17:06:53.385755: step: 2918/1545, loss: 0.0011354117887094617 2023-01-23 17:06:54.238045: step: 2920/1545, loss: 0.006779007613658905 2023-01-23 17:06:55.121640: step: 2922/1545, loss: 0.03334178775548935 2023-01-23 17:06:56.027442: step: 2924/1545, loss: 0.2237737476825714 2023-01-23 17:06:56.858465: step: 2926/1545, loss: 0.009475485421717167 2023-01-23 17:06:57.765361: step: 2928/1545, loss: 0.46703818440437317 2023-01-23 17:06:58.621309: step: 2930/1545, loss: 0.024137921631336212 2023-01-23 17:06:59.480740: step: 2932/1545, loss: 0.00437540328130126 2023-01-23 17:07:00.412365: step: 2934/1545, loss: 0.01014519389718771 2023-01-23 17:07:01.328222: step: 2936/1545, loss: 0.1042337641119957 2023-01-23 17:07:02.239693: step: 2938/1545, loss: 0.0011245253263041377 2023-01-23 17:07:03.143974: step: 2940/1545, loss: 0.03512507677078247 2023-01-23 17:07:04.040854: step: 2942/1545, loss: 0.006983020342886448 2023-01-23 17:07:04.893911: step: 2944/1545, loss: 0.006451433524489403 2023-01-23 17:07:05.765013: step: 2946/1545, loss: 0.08260713517665863 2023-01-23 17:07:06.657593: step: 2948/1545, loss: 0.07600060105323792 2023-01-23 17:07:07.558604: step: 2950/1545, loss: 0.007577972020953894 2023-01-23 17:07:08.414938: step: 2952/1545, loss: 0.00209318520501256 2023-01-23 17:07:09.274120: step: 2954/1545, loss: 0.005722937639802694 2023-01-23 17:07:10.161913: step: 2956/1545, loss: 0.003009854117408395 2023-01-23 17:07:11.059810: step: 2958/1545, loss: 0.0011326742824167013 2023-01-23 17:07:11.953330: step: 2960/1545, loss: 0.005179037339985371 2023-01-23 17:07:12.824484: step: 2962/1545, loss: 0.0008676449651829898 2023-01-23 17:07:13.745398: step: 2964/1545, loss: 0.00014953126083128154 2023-01-23 17:07:14.608292: step: 2966/1545, loss: 0.0001064849566319026 2023-01-23 17:07:15.581204: step: 2968/1545, loss: 0.07923974841833115 2023-01-23 17:07:16.506190: step: 2970/1545, loss: 0.13949421048164368 2023-01-23 17:07:17.350981: step: 2972/1545, loss: 0.028821555897593498 2023-01-23 17:07:18.257023: step: 2974/1545, loss: 0.020822476595640182 2023-01-23 17:07:19.136918: step: 2976/1545, loss: 0.20419834554195404 2023-01-23 17:07:20.031117: step: 2978/1545, loss: 0.01532051432877779 2023-01-23 17:07:20.905460: step: 2980/1545, loss: 0.00020815702737309039 2023-01-23 17:07:21.779346: step: 2982/1545, loss: 0.0031141650397330523 2023-01-23 17:07:22.654639: step: 2984/1545, loss: 0.016321957111358643 2023-01-23 17:07:23.562920: step: 2986/1545, loss: 0.007220769301056862 2023-01-23 17:07:24.439432: step: 2988/1545, loss: 0.03766818344593048 2023-01-23 17:07:25.360878: step: 2990/1545, loss: 0.2003462165594101 2023-01-23 17:07:26.216038: step: 2992/1545, loss: 0.0006818295805715024 2023-01-23 17:07:27.131723: step: 2994/1545, loss: 0.012642351910471916 2023-01-23 17:07:28.031651: step: 2996/1545, loss: 0.043520811945199966 2023-01-23 17:07:28.952650: step: 2998/1545, loss: 0.37971633672714233 2023-01-23 17:07:29.838033: step: 3000/1545, loss: 0.00031851703533902764 2023-01-23 17:07:30.712506: step: 3002/1545, loss: 0.2296178638935089 2023-01-23 17:07:31.617224: step: 3004/1545, loss: 0.00038922426756471395 2023-01-23 17:07:32.458520: step: 3006/1545, loss: 0.0018533047987148166 2023-01-23 17:07:33.400841: step: 3008/1545, loss: 0.0003081333125010133 2023-01-23 17:07:34.268319: step: 3010/1545, loss: 0.10918942838907242 2023-01-23 17:07:35.168292: step: 3012/1545, loss: 0.001550345215946436 2023-01-23 17:07:36.068985: step: 3014/1545, loss: 0.009414881467819214 2023-01-23 17:07:36.907925: step: 3016/1545, loss: 0.028761014342308044 2023-01-23 17:07:37.766087: step: 3018/1545, loss: 0.05157073214650154 2023-01-23 17:07:38.650362: step: 3020/1545, loss: 0.0626983791589737 2023-01-23 17:07:39.511398: step: 3022/1545, loss: 0.00018065943731926382 2023-01-23 17:07:40.442480: step: 3024/1545, loss: 0.19966113567352295 2023-01-23 17:07:41.441661: step: 3026/1545, loss: 0.2816619277000427 2023-01-23 17:07:42.310425: step: 3028/1545, loss: 0.012102559208869934 2023-01-23 17:07:43.205132: step: 3030/1545, loss: 0.028523489832878113 2023-01-23 17:07:44.060782: step: 3032/1545, loss: 0.003243698738515377 2023-01-23 17:07:44.941807: step: 3034/1545, loss: 0.02083040587604046 2023-01-23 17:07:45.858568: step: 3036/1545, loss: 0.0005506340530700982 2023-01-23 17:07:46.806387: step: 3038/1545, loss: 0.13987833261489868 2023-01-23 17:07:47.680217: step: 3040/1545, loss: 0.002049518283456564 2023-01-23 17:07:48.528691: step: 3042/1545, loss: 0.01877768151462078 2023-01-23 17:07:49.453236: step: 3044/1545, loss: 0.00021866525639779866 2023-01-23 17:07:50.345928: step: 3046/1545, loss: 0.0011069029569625854 2023-01-23 17:07:51.208710: step: 3048/1545, loss: 0.011275999248027802 2023-01-23 17:07:52.122432: step: 3050/1545, loss: 0.0003513604460749775 2023-01-23 17:07:53.002936: step: 3052/1545, loss: 4.221019480610266e-05 2023-01-23 17:07:53.930917: step: 3054/1545, loss: 0.12093333899974823 2023-01-23 17:07:54.757900: step: 3056/1545, loss: 0.0007383796037174761 2023-01-23 17:07:55.656045: step: 3058/1545, loss: 0.012660887092351913 2023-01-23 17:07:56.512651: step: 3060/1545, loss: 0.006420668214559555 2023-01-23 17:07:57.390582: step: 3062/1545, loss: 0.0008858689107000828 2023-01-23 17:07:58.252721: step: 3064/1545, loss: 0.00026015841285698116 2023-01-23 17:07:59.193340: step: 3066/1545, loss: 0.16066056489944458 2023-01-23 17:08:00.102606: step: 3068/1545, loss: 0.02566358633339405 2023-01-23 17:08:01.001270: step: 3070/1545, loss: 0.1359969973564148 2023-01-23 17:08:01.882235: step: 3072/1545, loss: 0.014838190749287605 2023-01-23 17:08:02.743440: step: 3074/1545, loss: 0.00019633042393252254 2023-01-23 17:08:03.675322: step: 3076/1545, loss: 0.002367079257965088 2023-01-23 17:08:04.528018: step: 3078/1545, loss: 0.00033726569381542504 2023-01-23 17:08:05.409488: step: 3080/1545, loss: 0.0003925904748030007 2023-01-23 17:08:06.406321: step: 3082/1545, loss: 0.0012057244312018156 2023-01-23 17:08:07.304352: step: 3084/1545, loss: 0.09537463635206223 2023-01-23 17:08:08.186786: step: 3086/1545, loss: 0.0039098528213799 2023-01-23 17:08:09.071764: step: 3088/1545, loss: 0.0001794318377505988 2023-01-23 17:08:09.977918: step: 3090/1545, loss: 0.43655842542648315 ================================================== Loss: 0.083 -------------------- Dev Chinese: {'event': {'p': 0.5965103598691385, 'r': 0.7283621837549934, 'f1': 0.6558752997601919}, 'argument': {'p': 0.6594986522834787, 'r': 0.6659111298299898, 'f1': 0.6626893789227364}, 'combined': 0.4346415950488451, 'epoch': 25} Test Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.6950880457507395, 'r': 0.7263696587936789, 'f1': 0.710384649517727}, 'combined': 0.4959055144975407, 'epoch': 25} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6600102330990629, 'r': 0.6704157998371112, 'f1': 0.6651723243076589}, 'combined': 0.4450462277950343, 'epoch': 25} Test Korean: {'event': {'p': 0.6317460317460317, 'r': 0.7634271099744245, 'f1': 0.6913723219455704}, 'argument': {'p': 0.6909323864014446, 'r': 0.7210303199321151, 'f1': 0.705660563673278}, 'combined': 0.48787418241221425, 'epoch': 25} Dev Russian: {'event': {'p': 0.5688976377952756, 'r': 0.7696404793608522, 'f1': 0.6542161856253538}, 'argument': {'p': 0.6565281496607026, 'r': 0.6748433126340699, 'f1': 0.6655597538359292}, 'combined': 0.43541996346029105, 'epoch': 25} Test Russian: {'event': {'p': 0.6283009466865969, 'r': 0.8062659846547314, 'f1': 0.7062447493699243}, 'argument': {'p': 0.6987320765508586, 'r': 0.7368827434081604, 'f1': 0.7173004935833348}, 'combined': 0.5065897073136852, 'epoch': 25} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7073496873496874, 'r': 0.6138158443943568, 'f1': 0.6572718333780282}, 'combined': 0.4580985505362016, 'epoch': 25} Korean: {'event': {'p': 0.6666666666666666, 'r': 0.5396825396825397, 'f1': 0.5964912280701754}, 'argument': {'p': 0.6894444444444444, 'r': 0.4722222222222222, 'f1': 0.5605239385727191}, 'combined': 0.33434761248197276, 'epoch': 25} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.563729326629349, 'r': 0.5335295412742054, 'f1': 0.5482138405753303}, 'combined': 0.3053342909533485, 'epoch': 25} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6584459487309184, 'r': 0.6574580328288466, 'f1': 0.6579516199405799}, 'combined': 0.4346898592173376, 'epoch': 7} Test for Chinese: {'event': {'p': 0.6424759871931697, 'r': 0.7698209718670077, 'f1': 0.7004072134962187}, 'argument': {'p': 0.7021344597431646, 'r': 0.7123297633236919, 'f1': 0.7071953682162753}, 'combined': 0.4953247372497937, 'epoch': 7} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7120517097581317, 'r': 0.641435011269722, 'f1': 0.674901185770751}, 'combined': 0.4703856749311296, 'epoch': 7} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 26 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 17:13:26.170104: step: 2/1545, loss: 0.0022872495464980602 2023-01-23 17:13:27.050707: step: 4/1545, loss: 0.014083916321396828 2023-01-23 17:13:27.925467: step: 6/1545, loss: 0.09139791876077652 2023-01-23 17:13:28.815443: step: 8/1545, loss: 0.029316207394003868 2023-01-23 17:13:29.666508: step: 10/1545, loss: 0.021955763921141624 2023-01-23 17:13:30.569498: step: 12/1545, loss: 0.008510010316967964 2023-01-23 17:13:31.428888: step: 14/1545, loss: 0.00022705394076183438 2023-01-23 17:13:32.269775: step: 16/1545, loss: 0.008607596158981323 2023-01-23 17:13:33.178654: step: 18/1545, loss: 0.00010121819650521502 2023-01-23 17:13:34.074070: step: 20/1545, loss: 0.002638103673234582 2023-01-23 17:13:35.032787: step: 22/1545, loss: 0.006191117689013481 2023-01-23 17:13:35.885008: step: 24/1545, loss: 0.0021131259854882956 2023-01-23 17:13:36.812498: step: 26/1545, loss: 0.0004226047021802515 2023-01-23 17:13:37.694265: step: 28/1545, loss: 0.6814876198768616 2023-01-23 17:13:38.565417: step: 30/1545, loss: 0.0005951322964392602 2023-01-23 17:13:39.487123: step: 32/1545, loss: 0.02539062313735485 2023-01-23 17:13:40.351274: step: 34/1545, loss: 0.002317846519872546 2023-01-23 17:13:41.191382: step: 36/1545, loss: 0.00022163093672133982 2023-01-23 17:13:42.092371: step: 38/1545, loss: 0.05755406245589256 2023-01-23 17:13:42.966621: step: 40/1545, loss: 0.10794524103403091 2023-01-23 17:13:43.835597: step: 42/1545, loss: 0.0010666633024811745 2023-01-23 17:13:44.715172: step: 44/1545, loss: 0.0023511783219873905 2023-01-23 17:13:45.652467: step: 46/1545, loss: 0.0014011365128681064 2023-01-23 17:13:46.522392: step: 48/1545, loss: 0.10483935475349426 2023-01-23 17:13:47.445105: step: 50/1545, loss: 0.004093805328011513 2023-01-23 17:13:48.354358: step: 52/1545, loss: 0.0005718434113077819 2023-01-23 17:13:49.241219: step: 54/1545, loss: 0.001057034358382225 2023-01-23 17:13:50.150066: step: 56/1545, loss: 0.14135906100273132 2023-01-23 17:13:51.012547: step: 58/1545, loss: 0.017658140510320663 2023-01-23 17:13:51.885944: step: 60/1545, loss: 0.004798456095159054 2023-01-23 17:13:52.759431: step: 62/1545, loss: 0.49072250723838806 2023-01-23 17:13:53.653996: step: 64/1545, loss: 0.05293165147304535 2023-01-23 17:13:54.565514: step: 66/1545, loss: 0.010514900088310242 2023-01-23 17:13:55.457480: step: 68/1545, loss: 0.0008494592038914561 2023-01-23 17:13:56.352133: step: 70/1545, loss: 0.295330673456192 2023-01-23 17:13:57.195941: step: 72/1545, loss: 0.0008125989115796983 2023-01-23 17:13:58.075064: step: 74/1545, loss: 0.0005908083403483033 2023-01-23 17:13:58.889430: step: 76/1545, loss: 0.0010587413562461734 2023-01-23 17:13:59.749557: step: 78/1545, loss: 0.0012318934313952923 2023-01-23 17:14:00.604058: step: 80/1545, loss: 0.023522891104221344 2023-01-23 17:14:01.439997: step: 82/1545, loss: 0.005111929029226303 2023-01-23 17:14:02.339000: step: 84/1545, loss: 0.0032471867743879557 2023-01-23 17:14:03.175841: step: 86/1545, loss: 5.609147410723381e-05 2023-01-23 17:14:04.056493: step: 88/1545, loss: 0.20491328835487366 2023-01-23 17:14:04.915035: step: 90/1545, loss: 0.00017676073184702545 2023-01-23 17:14:05.748692: step: 92/1545, loss: 0.005606082733720541 2023-01-23 17:14:06.677665: step: 94/1545, loss: 0.00422813231125474 2023-01-23 17:14:07.565872: step: 96/1545, loss: 0.08398115634918213 2023-01-23 17:14:08.478659: step: 98/1545, loss: 0.0020599395502358675 2023-01-23 17:14:09.318087: step: 100/1545, loss: 0.0011308409739285707 2023-01-23 17:14:10.197599: step: 102/1545, loss: 0.0035157050006091595 2023-01-23 17:14:11.061444: step: 104/1545, loss: 0.0006816826062276959 2023-01-23 17:14:11.964852: step: 106/1545, loss: 0.0002715682494454086 2023-01-23 17:14:12.877791: step: 108/1545, loss: 0.08246976882219315 2023-01-23 17:14:13.744004: step: 110/1545, loss: 0.00012349241296760738 2023-01-23 17:14:14.652225: step: 112/1545, loss: 0.13164269924163818 2023-01-23 17:14:15.511368: step: 114/1545, loss: 0.0010830992832779884 2023-01-23 17:14:16.366803: step: 116/1545, loss: 0.012960261665284634 2023-01-23 17:14:17.212880: step: 118/1545, loss: 0.005835395306348801 2023-01-23 17:14:18.060860: step: 120/1545, loss: 0.010632149875164032 2023-01-23 17:14:18.902513: step: 122/1545, loss: 8.002238610060886e-05 2023-01-23 17:14:19.771087: step: 124/1545, loss: 9.673559543443844e-05 2023-01-23 17:14:20.639387: step: 126/1545, loss: 0.127672016620636 2023-01-23 17:14:21.541613: step: 128/1545, loss: 0.000305099441902712 2023-01-23 17:14:22.404088: step: 130/1545, loss: 0.00042327542905695736 2023-01-23 17:14:23.328156: step: 132/1545, loss: 0.07077360898256302 2023-01-23 17:14:24.236829: step: 134/1545, loss: 0.18136189877986908 2023-01-23 17:14:25.135273: step: 136/1545, loss: 0.00018227855616714805 2023-01-23 17:14:26.008614: step: 138/1545, loss: 0.000580423919018358 2023-01-23 17:14:26.878352: step: 140/1545, loss: 0.2843835949897766 2023-01-23 17:14:27.798306: step: 142/1545, loss: 3.275465496699326e-05 2023-01-23 17:14:28.694200: step: 144/1545, loss: 0.013763485476374626 2023-01-23 17:14:29.532884: step: 146/1545, loss: 0.060584764927625656 2023-01-23 17:14:30.355751: step: 148/1545, loss: 0.01801414042711258 2023-01-23 17:14:31.237210: step: 150/1545, loss: 0.03394199162721634 2023-01-23 17:14:32.114064: step: 152/1545, loss: 9.776352089829743e-05 2023-01-23 17:14:33.000131: step: 154/1545, loss: 0.0006782738491892815 2023-01-23 17:14:33.870978: step: 156/1545, loss: 8.428497676504776e-05 2023-01-23 17:14:34.721353: step: 158/1545, loss: 0.08763600885868073 2023-01-23 17:14:35.615960: step: 160/1545, loss: 5.659833550453186e-05 2023-01-23 17:14:36.500382: step: 162/1545, loss: 0.1673782914876938 2023-01-23 17:14:37.370253: step: 164/1545, loss: 0.00021425144223030657 2023-01-23 17:14:38.265802: step: 166/1545, loss: 0.06339693069458008 2023-01-23 17:14:39.125799: step: 168/1545, loss: 0.0644637942314148 2023-01-23 17:14:40.198208: step: 170/1545, loss: 0.006158434320241213 2023-01-23 17:14:41.089021: step: 172/1545, loss: -3.382447175681591e-05 2023-01-23 17:14:41.955760: step: 174/1545, loss: 0.00014519230171572417 2023-01-23 17:14:42.802781: step: 176/1545, loss: 0.008102985098958015 2023-01-23 17:14:43.705581: step: 178/1545, loss: 0.0019377238349989057 2023-01-23 17:14:44.543842: step: 180/1545, loss: 0.06003795936703682 2023-01-23 17:14:45.428036: step: 182/1545, loss: 0.029219571501016617 2023-01-23 17:14:46.358756: step: 184/1545, loss: 0.007354696746915579 2023-01-23 17:14:47.224587: step: 186/1545, loss: 0.5080105662345886 2023-01-23 17:14:48.147645: step: 188/1545, loss: 0.04874303564429283 2023-01-23 17:14:49.057792: step: 190/1545, loss: 0.0031287313904613256 2023-01-23 17:14:49.905950: step: 192/1545, loss: 0.00028146529803052545 2023-01-23 17:14:50.771079: step: 194/1545, loss: 0.2338671088218689 2023-01-23 17:14:51.621815: step: 196/1545, loss: 0.0008210740052163601 2023-01-23 17:14:52.484618: step: 198/1545, loss: 5.080901610199362e-05 2023-01-23 17:14:53.422164: step: 200/1545, loss: 0.3344758450984955 2023-01-23 17:14:54.305746: step: 202/1545, loss: 9.751368634169921e-05 2023-01-23 17:14:55.229023: step: 204/1545, loss: 0.0002870704629458487 2023-01-23 17:14:56.159142: step: 206/1545, loss: 0.0004942968371324241 2023-01-23 17:14:57.035492: step: 208/1545, loss: 0.001004706835374236 2023-01-23 17:14:57.902256: step: 210/1545, loss: 0.00539357727393508 2023-01-23 17:14:58.751332: step: 212/1545, loss: 7.25240824976936e-05 2023-01-23 17:14:59.589000: step: 214/1545, loss: 0.0009796537924557924 2023-01-23 17:15:00.512824: step: 216/1545, loss: 8.839413567329757e-06 2023-01-23 17:15:01.364878: step: 218/1545, loss: 0.002310746582224965 2023-01-23 17:15:02.237134: step: 220/1545, loss: 0.00015735987108200788 2023-01-23 17:15:03.122191: step: 222/1545, loss: 0.8104054927825928 2023-01-23 17:15:04.011785: step: 224/1545, loss: 0.17654262483119965 2023-01-23 17:15:04.852759: step: 226/1545, loss: 0.00014823710080236197 2023-01-23 17:15:05.723507: step: 228/1545, loss: 0.0009262820240110159 2023-01-23 17:15:06.576670: step: 230/1545, loss: 0.04492409899830818 2023-01-23 17:15:07.461247: step: 232/1545, loss: 0.0002969055494759232 2023-01-23 17:15:08.324699: step: 234/1545, loss: 0.00029186555184423923 2023-01-23 17:15:09.202299: step: 236/1545, loss: 0.003750826697796583 2023-01-23 17:15:10.084068: step: 238/1545, loss: 0.004593474790453911 2023-01-23 17:15:11.016527: step: 240/1545, loss: 0.00037709265598095953 2023-01-23 17:15:12.044836: step: 242/1545, loss: 0.2888733446598053 2023-01-23 17:15:12.947415: step: 244/1545, loss: 0.0006505839410237968 2023-01-23 17:15:13.825895: step: 246/1545, loss: 0.017298003658652306 2023-01-23 17:15:14.720979: step: 248/1545, loss: 0.5082384347915649 2023-01-23 17:15:15.589537: step: 250/1545, loss: 0.2084619551897049 2023-01-23 17:15:16.468669: step: 252/1545, loss: 0.7315871715545654 2023-01-23 17:15:17.344326: step: 254/1545, loss: 0.2828965187072754 2023-01-23 17:15:18.258021: step: 256/1545, loss: 0.0014463975094258785 2023-01-23 17:15:19.132878: step: 258/1545, loss: 0.2766192555427551 2023-01-23 17:15:19.986736: step: 260/1545, loss: 0.0015558302402496338 2023-01-23 17:15:20.930379: step: 262/1545, loss: 0.044045597314834595 2023-01-23 17:15:21.806706: step: 264/1545, loss: 7.423442730214447e-05 2023-01-23 17:15:22.668609: step: 266/1545, loss: 0.003166921203956008 2023-01-23 17:15:23.542838: step: 268/1545, loss: 0.579931378364563 2023-01-23 17:15:24.445147: step: 270/1545, loss: 0.06727531552314758 2023-01-23 17:15:25.323851: step: 272/1545, loss: 0.0036085941828787327 2023-01-23 17:15:26.207275: step: 274/1545, loss: 0.005102088209241629 2023-01-23 17:15:27.046204: step: 276/1545, loss: 0.023411717265844345 2023-01-23 17:15:27.926907: step: 278/1545, loss: 0.025538722053170204 2023-01-23 17:15:28.812545: step: 280/1545, loss: 0.1453012377023697 2023-01-23 17:15:29.692268: step: 282/1545, loss: 0.0067212642170488834 2023-01-23 17:15:30.602148: step: 284/1545, loss: 0.07933123409748077 2023-01-23 17:15:31.451938: step: 286/1545, loss: 0.09550989419221878 2023-01-23 17:15:32.324259: step: 288/1545, loss: 0.16653281450271606 2023-01-23 17:15:33.214098: step: 290/1545, loss: 0.0004833158745896071 2023-01-23 17:15:34.080429: step: 292/1545, loss: 0.004477210808545351 2023-01-23 17:15:34.941627: step: 294/1545, loss: 0.0005613575340248644 2023-01-23 17:15:35.895799: step: 296/1545, loss: 0.0003286254941485822 2023-01-23 17:15:36.776533: step: 298/1545, loss: 0.0007547432323917747 2023-01-23 17:15:37.639249: step: 300/1545, loss: 0.0022407725919038057 2023-01-23 17:15:38.505652: step: 302/1545, loss: 0.0013839306775480509 2023-01-23 17:15:39.343656: step: 304/1545, loss: 0.0012478214921429753 2023-01-23 17:15:40.212452: step: 306/1545, loss: 0.006210748106241226 2023-01-23 17:15:41.132275: step: 308/1545, loss: 0.0013831008691340685 2023-01-23 17:15:42.043721: step: 310/1545, loss: 0.10987985879182816 2023-01-23 17:15:43.028735: step: 312/1545, loss: 0.0022529535926878452 2023-01-23 17:15:43.882164: step: 314/1545, loss: 0.1834237426519394 2023-01-23 17:15:44.732000: step: 316/1545, loss: 0.1683383584022522 2023-01-23 17:15:45.646797: step: 318/1545, loss: 0.0010786894708871841 2023-01-23 17:15:46.628328: step: 320/1545, loss: 0.0008170981891453266 2023-01-23 17:15:47.493863: step: 322/1545, loss: 0.10195273905992508 2023-01-23 17:15:48.459588: step: 324/1545, loss: 0.010934915393590927 2023-01-23 17:15:49.317429: step: 326/1545, loss: 0.0004086332337465137 2023-01-23 17:15:50.251906: step: 328/1545, loss: 0.08938582986593246 2023-01-23 17:15:51.115516: step: 330/1545, loss: 0.0004180421819910407 2023-01-23 17:15:51.953099: step: 332/1545, loss: 0.006503236945718527 2023-01-23 17:15:52.773965: step: 334/1545, loss: 0.059077341109514236 2023-01-23 17:15:53.646148: step: 336/1545, loss: 0.05684749782085419 2023-01-23 17:15:54.509938: step: 338/1545, loss: 0.007310619577765465 2023-01-23 17:15:55.398277: step: 340/1545, loss: 0.03872622549533844 2023-01-23 17:15:56.261359: step: 342/1545, loss: 0.27508917450904846 2023-01-23 17:15:57.129734: step: 344/1545, loss: 0.0029176475945860147 2023-01-23 17:15:58.011240: step: 346/1545, loss: 0.0023041123058646917 2023-01-23 17:15:58.947329: step: 348/1545, loss: 0.0011825673282146454 2023-01-23 17:15:59.802119: step: 350/1545, loss: 0.0039338055066764355 2023-01-23 17:16:00.648806: step: 352/1545, loss: 0.0012757460353896022 2023-01-23 17:16:01.510756: step: 354/1545, loss: 9.158491593552753e-05 2023-01-23 17:16:02.369134: step: 356/1545, loss: 0.0793185830116272 2023-01-23 17:16:03.196530: step: 358/1545, loss: 0.10504660755395889 2023-01-23 17:16:04.067486: step: 360/1545, loss: 0.0027319511864334345 2023-01-23 17:16:04.977997: step: 362/1545, loss: 0.006326127331703901 2023-01-23 17:16:05.854593: step: 364/1545, loss: 0.0007259933627210557 2023-01-23 17:16:06.733351: step: 366/1545, loss: 0.06846106052398682 2023-01-23 17:16:07.588531: step: 368/1545, loss: 5.4511689086211845e-05 2023-01-23 17:16:08.455246: step: 370/1545, loss: 0.00032378683681599796 2023-01-23 17:16:09.314846: step: 372/1545, loss: 0.006877655163407326 2023-01-23 17:16:10.197518: step: 374/1545, loss: 0.0005412864265963435 2023-01-23 17:16:11.075038: step: 376/1545, loss: 0.008565218187868595 2023-01-23 17:16:11.950725: step: 378/1545, loss: 0.0006198728224262595 2023-01-23 17:16:12.820924: step: 380/1545, loss: 0.00040804612217471004 2023-01-23 17:16:13.690030: step: 382/1545, loss: 0.13669943809509277 2023-01-23 17:16:14.586887: step: 384/1545, loss: 0.005546290427446365 2023-01-23 17:16:15.467562: step: 386/1545, loss: 0.09294077754020691 2023-01-23 17:16:16.397094: step: 388/1545, loss: 0.09058292210102081 2023-01-23 17:16:17.255134: step: 390/1545, loss: 0.002873653080314398 2023-01-23 17:16:18.132105: step: 392/1545, loss: 0.005869863089174032 2023-01-23 17:16:19.032722: step: 394/1545, loss: 0.3322458267211914 2023-01-23 17:16:19.884258: step: 396/1545, loss: 8.200477896025404e-05 2023-01-23 17:16:20.845400: step: 398/1545, loss: 0.0004910789430141449 2023-01-23 17:16:21.700317: step: 400/1545, loss: 0.019594259560108185 2023-01-23 17:16:22.619175: step: 402/1545, loss: 0.018909677863121033 2023-01-23 17:16:23.510760: step: 404/1545, loss: 0.44242849946022034 2023-01-23 17:16:24.404942: step: 406/1545, loss: 0.06361226737499237 2023-01-23 17:16:25.334077: step: 408/1545, loss: 0.16104325652122498 2023-01-23 17:16:26.206288: step: 410/1545, loss: 0.010492277331650257 2023-01-23 17:16:27.085592: step: 412/1545, loss: 0.0006850540521554649 2023-01-23 17:16:27.953603: step: 414/1545, loss: 0.6323390603065491 2023-01-23 17:16:28.822487: step: 416/1545, loss: 0.020862439647316933 2023-01-23 17:16:29.749860: step: 418/1545, loss: 0.04387952759861946 2023-01-23 17:16:30.667279: step: 420/1545, loss: 0.02420937828719616 2023-01-23 17:16:31.566502: step: 422/1545, loss: 0.005759742576628923 2023-01-23 17:16:32.529038: step: 424/1545, loss: 0.00019040847837459296 2023-01-23 17:16:33.404748: step: 426/1545, loss: 0.0003613541484810412 2023-01-23 17:16:34.255922: step: 428/1545, loss: 0.44412121176719666 2023-01-23 17:16:35.132322: step: 430/1545, loss: 0.0005531294154934585 2023-01-23 17:16:35.983605: step: 432/1545, loss: 0.0024580613244324923 2023-01-23 17:16:36.853140: step: 434/1545, loss: 0.03425349295139313 2023-01-23 17:16:37.720500: step: 436/1545, loss: 0.003169901203364134 2023-01-23 17:16:38.606796: step: 438/1545, loss: 0.5546122789382935 2023-01-23 17:16:39.461729: step: 440/1545, loss: 0.0003463135799393058 2023-01-23 17:16:40.299205: step: 442/1545, loss: 0.0006702507380396128 2023-01-23 17:16:41.203908: step: 444/1545, loss: 0.14373016357421875 2023-01-23 17:16:42.091439: step: 446/1545, loss: 3.020058647962287e-05 2023-01-23 17:16:42.986863: step: 448/1545, loss: 0.024016477167606354 2023-01-23 17:16:43.854140: step: 450/1545, loss: 3.4955144656123593e-05 2023-01-23 17:16:44.743201: step: 452/1545, loss: 0.020202910527586937 2023-01-23 17:16:45.651787: step: 454/1545, loss: 0.002046603476628661 2023-01-23 17:16:46.545437: step: 456/1545, loss: 0.24193459749221802 2023-01-23 17:16:47.459751: step: 458/1545, loss: 0.013500268571078777 2023-01-23 17:16:48.383400: step: 460/1545, loss: 0.024992838501930237 2023-01-23 17:16:49.298112: step: 462/1545, loss: 0.00043017877032980323 2023-01-23 17:16:50.207121: step: 464/1545, loss: 0.08088399469852448 2023-01-23 17:16:51.040157: step: 466/1545, loss: 0.016070540994405746 2023-01-23 17:16:51.936819: step: 468/1545, loss: 0.007110889069736004 2023-01-23 17:16:52.872673: step: 470/1545, loss: 0.4824635684490204 2023-01-23 17:16:53.746211: step: 472/1545, loss: 0.29785051941871643 2023-01-23 17:16:54.664514: step: 474/1545, loss: 0.057891812175512314 2023-01-23 17:16:55.517299: step: 476/1545, loss: 0.09811288863420486 2023-01-23 17:16:56.416804: step: 478/1545, loss: 0.002440151060000062 2023-01-23 17:16:57.336616: step: 480/1545, loss: 0.0016836505383253098 2023-01-23 17:16:58.177306: step: 482/1545, loss: 0.0019906628876924515 2023-01-23 17:16:59.091457: step: 484/1545, loss: 0.0360076017677784 2023-01-23 17:17:00.004857: step: 486/1545, loss: 0.010140454396605492 2023-01-23 17:17:00.914510: step: 488/1545, loss: 0.001988256350159645 2023-01-23 17:17:01.777156: step: 490/1545, loss: 0.0026953257620334625 2023-01-23 17:17:02.659220: step: 492/1545, loss: 0.021881669759750366 2023-01-23 17:17:03.558691: step: 494/1545, loss: 0.005724161397665739 2023-01-23 17:17:04.431436: step: 496/1545, loss: 0.004453870467841625 2023-01-23 17:17:05.292860: step: 498/1545, loss: 2.708561805775389e-05 2023-01-23 17:17:06.194389: step: 500/1545, loss: 0.5649099946022034 2023-01-23 17:17:07.096110: step: 502/1545, loss: 0.035138681530952454 2023-01-23 17:17:08.014955: step: 504/1545, loss: 0.12999102473258972 2023-01-23 17:17:08.906606: step: 506/1545, loss: 0.019193220883607864 2023-01-23 17:17:09.773333: step: 508/1545, loss: 0.04090377315878868 2023-01-23 17:17:10.641575: step: 510/1545, loss: 0.002049703849479556 2023-01-23 17:17:11.543637: step: 512/1545, loss: 0.0007085776887834072 2023-01-23 17:17:12.454236: step: 514/1545, loss: 0.3173307776451111 2023-01-23 17:17:13.337290: step: 516/1545, loss: 0.002681208774447441 2023-01-23 17:17:14.197471: step: 518/1545, loss: 0.0717666745185852 2023-01-23 17:17:15.114384: step: 520/1545, loss: 0.22835008800029755 2023-01-23 17:17:16.025807: step: 522/1545, loss: 0.04814857617020607 2023-01-23 17:17:16.912081: step: 524/1545, loss: 0.2607913315296173 2023-01-23 17:17:17.761837: step: 526/1545, loss: 0.04943588003516197 2023-01-23 17:17:18.619773: step: 528/1545, loss: 0.0001981954846996814 2023-01-23 17:17:19.478271: step: 530/1545, loss: 0.18374764919281006 2023-01-23 17:17:20.335674: step: 532/1545, loss: 0.01654994487762451 2023-01-23 17:17:21.237871: step: 534/1545, loss: 0.0024337598588317633 2023-01-23 17:17:22.105801: step: 536/1545, loss: 0.0009927175706252456 2023-01-23 17:17:22.970324: step: 538/1545, loss: 0.0011503692949190736 2023-01-23 17:17:23.835528: step: 540/1545, loss: 0.008861829526722431 2023-01-23 17:17:24.747503: step: 542/1545, loss: 0.0020655894186347723 2023-01-23 17:17:25.608896: step: 544/1545, loss: 0.0006485950434580445 2023-01-23 17:17:26.540763: step: 546/1545, loss: 0.006072924006730318 2023-01-23 17:17:27.412459: step: 548/1545, loss: 0.004811221733689308 2023-01-23 17:17:28.259767: step: 550/1545, loss: 0.00021410184854175895 2023-01-23 17:17:29.131656: step: 552/1545, loss: 0.0018717491766437888 2023-01-23 17:17:30.020146: step: 554/1545, loss: 0.6204755902290344 2023-01-23 17:17:30.884489: step: 556/1545, loss: 0.08216967433691025 2023-01-23 17:17:31.786343: step: 558/1545, loss: 0.0006288400618359447 2023-01-23 17:17:32.654745: step: 560/1545, loss: 0.005421989597380161 2023-01-23 17:17:33.532335: step: 562/1545, loss: 0.0022709660697728395 2023-01-23 17:17:34.409467: step: 564/1545, loss: 0.31836315989494324 2023-01-23 17:17:35.290062: step: 566/1545, loss: 0.010436278767883778 2023-01-23 17:17:36.206545: step: 568/1545, loss: 0.1803101748228073 2023-01-23 17:17:37.081363: step: 570/1545, loss: 0.7374002933502197 2023-01-23 17:17:37.949848: step: 572/1545, loss: 0.003867223160341382 2023-01-23 17:17:38.824710: step: 574/1545, loss: 0.0004682395956479013 2023-01-23 17:17:39.680662: step: 576/1545, loss: 0.0014473956543952227 2023-01-23 17:17:40.564724: step: 578/1545, loss: 0.0004494254826568067 2023-01-23 17:17:41.467825: step: 580/1545, loss: 0.0033598821610212326 2023-01-23 17:17:42.371731: step: 582/1545, loss: 0.016120074316859245 2023-01-23 17:17:43.295261: step: 584/1545, loss: 0.005996547639369965 2023-01-23 17:17:44.209916: step: 586/1545, loss: 0.033470045775175095 2023-01-23 17:17:45.119428: step: 588/1545, loss: 0.1952669769525528 2023-01-23 17:17:46.012395: step: 590/1545, loss: 2.6621302822604775e-05 2023-01-23 17:17:46.931417: step: 592/1545, loss: 0.004489073064178228 2023-01-23 17:17:47.775400: step: 594/1545, loss: 0.1900206059217453 2023-01-23 17:17:48.641921: step: 596/1545, loss: 0.00023539035464636981 2023-01-23 17:17:49.505736: step: 598/1545, loss: 0.0001534386829007417 2023-01-23 17:17:50.359440: step: 600/1545, loss: 0.04763191565871239 2023-01-23 17:17:51.248991: step: 602/1545, loss: 0.0019943781662732363 2023-01-23 17:17:52.110913: step: 604/1545, loss: 0.016540249809622765 2023-01-23 17:17:52.993033: step: 606/1545, loss: 0.055106017738580704 2023-01-23 17:17:53.877136: step: 608/1545, loss: 0.006496493238955736 2023-01-23 17:17:54.773966: step: 610/1545, loss: 0.00039515792741440237 2023-01-23 17:17:55.639680: step: 612/1545, loss: 0.025996264070272446 2023-01-23 17:17:56.554852: step: 614/1545, loss: 0.060180146247148514 2023-01-23 17:17:57.462523: step: 616/1545, loss: 0.000640197831671685 2023-01-23 17:17:58.340531: step: 618/1545, loss: 0.18255256116390228 2023-01-23 17:17:59.181843: step: 620/1545, loss: 0.03737131133675575 2023-01-23 17:18:00.091084: step: 622/1545, loss: 0.00018826079030986875 2023-01-23 17:18:01.040489: step: 624/1545, loss: 0.030916595831513405 2023-01-23 17:18:01.911851: step: 626/1545, loss: 0.041359711438417435 2023-01-23 17:18:02.796381: step: 628/1545, loss: 0.057095788419246674 2023-01-23 17:18:03.660898: step: 630/1545, loss: 0.002142900601029396 2023-01-23 17:18:04.546620: step: 632/1545, loss: 0.021975912153720856 2023-01-23 17:18:05.415433: step: 634/1545, loss: 0.003047745209187269 2023-01-23 17:18:06.314738: step: 636/1545, loss: 0.0005051200860179961 2023-01-23 17:18:07.165172: step: 638/1545, loss: 0.07627436518669128 2023-01-23 17:18:08.060452: step: 640/1545, loss: 0.0012455843389034271 2023-01-23 17:18:08.939853: step: 642/1545, loss: 0.0005184717592783272 2023-01-23 17:18:09.846576: step: 644/1545, loss: 0.00011956735397689044 2023-01-23 17:18:10.722980: step: 646/1545, loss: 0.0015556163853034377 2023-01-23 17:18:11.572521: step: 648/1545, loss: 0.0014053265331313014 2023-01-23 17:18:12.465633: step: 650/1545, loss: 0.07717978954315186 2023-01-23 17:18:13.353311: step: 652/1545, loss: 0.013215725310146809 2023-01-23 17:18:14.359451: step: 654/1545, loss: 0.0006408179760910571 2023-01-23 17:18:15.258895: step: 656/1545, loss: 0.0016871257685124874 2023-01-23 17:18:16.132639: step: 658/1545, loss: 0.03443063795566559 2023-01-23 17:18:17.008821: step: 660/1545, loss: 0.01888332888484001 2023-01-23 17:18:17.875791: step: 662/1545, loss: 0.6905002593994141 2023-01-23 17:18:18.776428: step: 664/1545, loss: 0.00010707903129514307 2023-01-23 17:18:19.660655: step: 666/1545, loss: 7.330928201554343e-05 2023-01-23 17:18:20.551437: step: 668/1545, loss: 0.44961562752723694 2023-01-23 17:18:21.399058: step: 670/1545, loss: 0.04703281819820404 2023-01-23 17:18:22.247336: step: 672/1545, loss: 0.0017560271080583334 2023-01-23 17:18:23.133726: step: 674/1545, loss: 0.031278736889362335 2023-01-23 17:18:23.994580: step: 676/1545, loss: 0.02629314363002777 2023-01-23 17:18:24.875580: step: 678/1545, loss: 0.00022346961486618966 2023-01-23 17:18:25.790862: step: 680/1545, loss: 0.8796797394752502 2023-01-23 17:18:26.652659: step: 682/1545, loss: 0.017879197373986244 2023-01-23 17:18:27.534877: step: 684/1545, loss: 0.5009264349937439 2023-01-23 17:18:28.395686: step: 686/1545, loss: 0.1770845204591751 2023-01-23 17:18:29.267440: step: 688/1545, loss: 0.044902727007865906 2023-01-23 17:18:30.134790: step: 690/1545, loss: 0.002100195037201047 2023-01-23 17:18:31.007085: step: 692/1545, loss: 0.002607506001368165 2023-01-23 17:18:31.893988: step: 694/1545, loss: 0.0010641941335052252 2023-01-23 17:18:32.825512: step: 696/1545, loss: 0.012057341635227203 2023-01-23 17:18:33.717676: step: 698/1545, loss: 0.12225192040205002 2023-01-23 17:18:34.591735: step: 700/1545, loss: 0.10718847066164017 2023-01-23 17:18:35.463641: step: 702/1545, loss: 0.09680306166410446 2023-01-23 17:18:36.346676: step: 704/1545, loss: 0.008539971895515919 2023-01-23 17:18:37.230621: step: 706/1545, loss: 0.0014602737501263618 2023-01-23 17:18:38.112690: step: 708/1545, loss: 0.218997985124588 2023-01-23 17:18:39.052866: step: 710/1545, loss: 0.08945930004119873 2023-01-23 17:18:39.945365: step: 712/1545, loss: 0.0015330552123486996 2023-01-23 17:18:40.832984: step: 714/1545, loss: 0.018078427761793137 2023-01-23 17:18:41.733563: step: 716/1545, loss: 0.0015993486158549786 2023-01-23 17:18:42.604695: step: 718/1545, loss: 0.5109965205192566 2023-01-23 17:18:43.464504: step: 720/1545, loss: 4.7358986194012687e-05 2023-01-23 17:18:44.437676: step: 722/1545, loss: 0.0015224645612761378 2023-01-23 17:18:45.314111: step: 724/1545, loss: 0.150368332862854 2023-01-23 17:18:46.184291: step: 726/1545, loss: 0.012042485177516937 2023-01-23 17:18:47.075277: step: 728/1545, loss: 0.016030363738536835 2023-01-23 17:18:47.962734: step: 730/1545, loss: 0.007097363471984863 2023-01-23 17:18:48.854934: step: 732/1545, loss: 0.021526288241147995 2023-01-23 17:18:49.703000: step: 734/1545, loss: 0.03181367740035057 2023-01-23 17:18:50.536573: step: 736/1545, loss: 0.09333435446023941 2023-01-23 17:18:51.426482: step: 738/1545, loss: 0.0015066983178257942 2023-01-23 17:18:52.318002: step: 740/1545, loss: 0.008295835927128792 2023-01-23 17:18:53.217210: step: 742/1545, loss: 0.001005695667117834 2023-01-23 17:18:54.067222: step: 744/1545, loss: 0.02616257406771183 2023-01-23 17:18:54.962804: step: 746/1545, loss: 0.01656017079949379 2023-01-23 17:18:55.861072: step: 748/1545, loss: 0.03892546147108078 2023-01-23 17:18:56.761955: step: 750/1545, loss: 0.0014749234542250633 2023-01-23 17:18:57.638133: step: 752/1545, loss: 0.0012116532307118177 2023-01-23 17:18:58.481076: step: 754/1545, loss: 0.28110837936401367 2023-01-23 17:18:59.360257: step: 756/1545, loss: 0.0032054386101663113 2023-01-23 17:19:00.195065: step: 758/1545, loss: 0.001802343176677823 2023-01-23 17:19:01.042834: step: 760/1545, loss: 0.0018220169004052877 2023-01-23 17:19:01.920639: step: 762/1545, loss: 0.07515563070774078 2023-01-23 17:19:02.766631: step: 764/1545, loss: 0.1373390555381775 2023-01-23 17:19:03.629094: step: 766/1545, loss: 0.0017767214449122548 2023-01-23 17:19:04.479703: step: 768/1545, loss: 0.0026374906301498413 2023-01-23 17:19:05.347987: step: 770/1545, loss: 0.00031150769791565835 2023-01-23 17:19:06.323364: step: 772/1545, loss: 0.06595179438591003 2023-01-23 17:19:07.182766: step: 774/1545, loss: 0.000703581958077848 2023-01-23 17:19:08.040753: step: 776/1545, loss: 0.0003817332617472857 2023-01-23 17:19:08.889919: step: 778/1545, loss: 0.0008386628469452262 2023-01-23 17:19:09.760570: step: 780/1545, loss: 0.0034993961453437805 2023-01-23 17:19:10.640871: step: 782/1545, loss: 0.13714486360549927 2023-01-23 17:19:11.501200: step: 784/1545, loss: 0.013886822387576103 2023-01-23 17:19:12.365485: step: 786/1545, loss: 0.004763368051499128 2023-01-23 17:19:13.235941: step: 788/1545, loss: 0.010091179050505161 2023-01-23 17:19:14.096786: step: 790/1545, loss: 0.003795517608523369 2023-01-23 17:19:14.920124: step: 792/1545, loss: 0.00035716494312509894 2023-01-23 17:19:15.788265: step: 794/1545, loss: 0.00017353372822981328 2023-01-23 17:19:16.675035: step: 796/1545, loss: 0.08834243565797806 2023-01-23 17:19:17.534679: step: 798/1545, loss: 0.007428381592035294 2023-01-23 17:19:18.444727: step: 800/1545, loss: 0.05513596907258034 2023-01-23 17:19:19.295752: step: 802/1545, loss: 0.000101281184470281 2023-01-23 17:19:20.179955: step: 804/1545, loss: 0.0014522143173962831 2023-01-23 17:19:21.040452: step: 806/1545, loss: 0.001217429293319583 2023-01-23 17:19:21.942932: step: 808/1545, loss: 0.13342036306858063 2023-01-23 17:19:22.845152: step: 810/1545, loss: 1.3090156244288664e-05 2023-01-23 17:19:23.685181: step: 812/1545, loss: 0.001979613909497857 2023-01-23 17:19:24.563641: step: 814/1545, loss: 0.0007475040038116276 2023-01-23 17:19:25.431232: step: 816/1545, loss: 0.002150325570255518 2023-01-23 17:19:26.302456: step: 818/1545, loss: 0.3285204768180847 2023-01-23 17:19:27.154009: step: 820/1545, loss: 0.0008277420420199633 2023-01-23 17:19:28.060307: step: 822/1545, loss: 0.21549059450626373 2023-01-23 17:19:28.937287: step: 824/1545, loss: 0.033703625202178955 2023-01-23 17:19:29.767238: step: 826/1545, loss: 0.0004812226688954979 2023-01-23 17:19:30.622448: step: 828/1545, loss: 0.00042490806663408875 2023-01-23 17:19:31.522673: step: 830/1545, loss: 0.0004917162004858255 2023-01-23 17:19:32.355696: step: 832/1545, loss: 0.00496446480974555 2023-01-23 17:19:33.315896: step: 834/1545, loss: 6.743201083736494e-05 2023-01-23 17:19:34.172464: step: 836/1545, loss: 0.0010710679925978184 2023-01-23 17:19:35.077747: step: 838/1545, loss: 0.011367326602339745 2023-01-23 17:19:35.931395: step: 840/1545, loss: 0.00010249181650578976 2023-01-23 17:19:36.843042: step: 842/1545, loss: 0.5523291826248169 2023-01-23 17:19:37.712116: step: 844/1545, loss: 0.030824068933725357 2023-01-23 17:19:38.613264: step: 846/1545, loss: 0.07908890396356583 2023-01-23 17:19:39.514570: step: 848/1545, loss: 0.0033883145079016685 2023-01-23 17:19:40.344584: step: 850/1545, loss: 0.05669933184981346 2023-01-23 17:19:41.254395: step: 852/1545, loss: 0.05656568706035614 2023-01-23 17:19:42.094141: step: 854/1545, loss: 0.00015076340059749782 2023-01-23 17:19:42.971628: step: 856/1545, loss: 0.015095068141818047 2023-01-23 17:19:43.853937: step: 858/1545, loss: -2.7719244826585054e-05 2023-01-23 17:19:44.742365: step: 860/1545, loss: 0.0005479322280734777 2023-01-23 17:19:45.584917: step: 862/1545, loss: 0.002046804642304778 2023-01-23 17:19:46.449461: step: 864/1545, loss: 4.7595396608812734e-05 2023-01-23 17:19:47.336322: step: 866/1545, loss: 0.035832133144140244 2023-01-23 17:19:48.231670: step: 868/1545, loss: 0.0033428024034947157 2023-01-23 17:19:49.096696: step: 870/1545, loss: 0.02321040816605091 2023-01-23 17:19:49.926144: step: 872/1545, loss: 2.191911517002154e-05 2023-01-23 17:19:50.808537: step: 874/1545, loss: 0.013570642098784447 2023-01-23 17:19:51.637467: step: 876/1545, loss: 0.00020660567679442465 2023-01-23 17:19:52.487017: step: 878/1545, loss: 0.33543941378593445 2023-01-23 17:19:53.377293: step: 880/1545, loss: 0.00032027644920162857 2023-01-23 17:19:54.326303: step: 882/1545, loss: 0.09717798233032227 2023-01-23 17:19:55.219809: step: 884/1545, loss: 0.27680981159210205 2023-01-23 17:19:56.080979: step: 886/1545, loss: 0.00021096561977174133 2023-01-23 17:19:56.961003: step: 888/1545, loss: 0.1264510601758957 2023-01-23 17:19:57.825233: step: 890/1545, loss: 0.0008483077399432659 2023-01-23 17:19:58.689773: step: 892/1545, loss: 0.01338894758373499 2023-01-23 17:19:59.543729: step: 894/1545, loss: 0.0006570367841050029 2023-01-23 17:20:00.463241: step: 896/1545, loss: 0.002234030980616808 2023-01-23 17:20:01.304824: step: 898/1545, loss: 0.04395436495542526 2023-01-23 17:20:02.220946: step: 900/1545, loss: 0.011245165951550007 2023-01-23 17:20:03.095601: step: 902/1545, loss: 0.0017060937825590372 2023-01-23 17:20:03.959457: step: 904/1545, loss: 0.09839604794979095 2023-01-23 17:20:04.850765: step: 906/1545, loss: 0.03616396710276604 2023-01-23 17:20:05.718215: step: 908/1545, loss: 0.05558984726667404 2023-01-23 17:20:06.593723: step: 910/1545, loss: 0.08680123835802078 2023-01-23 17:20:07.487885: step: 912/1545, loss: 0.20239832997322083 2023-01-23 17:20:08.440540: step: 914/1545, loss: 0.0633634403347969 2023-01-23 17:20:09.306513: step: 916/1545, loss: 0.005317166447639465 2023-01-23 17:20:10.197504: step: 918/1545, loss: 0.076150082051754 2023-01-23 17:20:11.068595: step: 920/1545, loss: 0.008267656899988651 2023-01-23 17:20:11.963199: step: 922/1545, loss: 0.00017046957509592175 2023-01-23 17:20:12.901418: step: 924/1545, loss: 0.001141343149356544 2023-01-23 17:20:13.775989: step: 926/1545, loss: 0.38439854979515076 2023-01-23 17:20:14.670214: step: 928/1545, loss: 0.054653894156217575 2023-01-23 17:20:15.579793: step: 930/1545, loss: 0.016253501176834106 2023-01-23 17:20:16.461053: step: 932/1545, loss: 0.10976570099592209 2023-01-23 17:20:17.349946: step: 934/1545, loss: 0.0004913884913548827 2023-01-23 17:20:18.280412: step: 936/1545, loss: 0.0015746343415230513 2023-01-23 17:20:19.162931: step: 938/1545, loss: 6.648596900049597e-05 2023-01-23 17:20:20.098825: step: 940/1545, loss: 0.06526127457618713 2023-01-23 17:20:20.954584: step: 942/1545, loss: 0.0005532867508009076 2023-01-23 17:20:21.800304: step: 944/1545, loss: 0.000911173177883029 2023-01-23 17:20:22.714063: step: 946/1545, loss: 0.3039649426937103 2023-01-23 17:20:23.634623: step: 948/1545, loss: 0.0015460260910913348 2023-01-23 17:20:24.521591: step: 950/1545, loss: 0.4583429992198944 2023-01-23 17:20:25.383646: step: 952/1545, loss: 0.011273909360170364 2023-01-23 17:20:26.257686: step: 954/1545, loss: 0.2627919316291809 2023-01-23 17:20:27.147475: step: 956/1545, loss: 0.013444583863019943 2023-01-23 17:20:28.069153: step: 958/1545, loss: 0.055965740233659744 2023-01-23 17:20:28.989481: step: 960/1545, loss: 0.002588048577308655 2023-01-23 17:20:29.870462: step: 962/1545, loss: 0.18744267523288727 2023-01-23 17:20:30.752885: step: 964/1545, loss: 0.09357009828090668 2023-01-23 17:20:31.655869: step: 966/1545, loss: 0.09704151004552841 2023-01-23 17:20:32.465426: step: 968/1545, loss: 0.0006970608374103904 2023-01-23 17:20:33.328589: step: 970/1545, loss: 0.016240287572145462 2023-01-23 17:20:34.187623: step: 972/1545, loss: 0.46753281354904175 2023-01-23 17:20:35.077464: step: 974/1545, loss: 0.000752772786654532 2023-01-23 17:20:35.950776: step: 976/1545, loss: 0.029033534228801727 2023-01-23 17:20:36.798780: step: 978/1545, loss: 0.057438481599092484 2023-01-23 17:20:37.675233: step: 980/1545, loss: 0.046064797788858414 2023-01-23 17:20:38.529211: step: 982/1545, loss: 0.320058673620224 2023-01-23 17:20:39.417541: step: 984/1545, loss: 0.10301800072193146 2023-01-23 17:20:40.353448: step: 986/1545, loss: 0.00530373677611351 2023-01-23 17:20:41.213382: step: 988/1545, loss: 0.11483856290578842 2023-01-23 17:20:42.094199: step: 990/1545, loss: 0.1593465358018875 2023-01-23 17:20:42.948031: step: 992/1545, loss: 0.00540672754868865 2023-01-23 17:20:43.815344: step: 994/1545, loss: 0.003469003364443779 2023-01-23 17:20:44.664326: step: 996/1545, loss: 0.2537764608860016 2023-01-23 17:20:45.539267: step: 998/1545, loss: 0.0037933578714728355 2023-01-23 17:20:46.398005: step: 1000/1545, loss: 0.001493910443969071 2023-01-23 17:20:47.270062: step: 1002/1545, loss: 0.028473012149333954 2023-01-23 17:20:48.131847: step: 1004/1545, loss: 0.011013579554855824 2023-01-23 17:20:49.058275: step: 1006/1545, loss: 0.09085097908973694 2023-01-23 17:20:49.918595: step: 1008/1545, loss: 0.0008804070530459285 2023-01-23 17:20:50.781805: step: 1010/1545, loss: 0.0007005963125266135 2023-01-23 17:20:51.681947: step: 1012/1545, loss: 0.0009978209855034947 2023-01-23 17:20:52.516698: step: 1014/1545, loss: 0.0014396208571270108 2023-01-23 17:20:53.341822: step: 1016/1545, loss: 8.578931010561064e-05 2023-01-23 17:20:54.205516: step: 1018/1545, loss: 9.723074617795646e-05 2023-01-23 17:20:55.049890: step: 1020/1545, loss: 0.0019813403487205505 2023-01-23 17:20:55.884572: step: 1022/1545, loss: 0.1642734855413437 2023-01-23 17:20:56.743455: step: 1024/1545, loss: 0.0027666701935231686 2023-01-23 17:20:57.619371: step: 1026/1545, loss: 0.00863619428128004 2023-01-23 17:20:58.527457: step: 1028/1545, loss: 0.0017028901493176818 2023-01-23 17:20:59.427359: step: 1030/1545, loss: 0.08478911221027374 2023-01-23 17:21:00.338373: step: 1032/1545, loss: 0.0010403323685750365 2023-01-23 17:21:01.293650: step: 1034/1545, loss: 0.023702573031187057 2023-01-23 17:21:02.205263: step: 1036/1545, loss: 0.29027360677719116 2023-01-23 17:21:03.129148: step: 1038/1545, loss: 0.1048818975687027 2023-01-23 17:21:03.989259: step: 1040/1545, loss: 0.07217678427696228 2023-01-23 17:21:04.830081: step: 1042/1545, loss: 0.0008424255065619946 2023-01-23 17:21:05.677547: step: 1044/1545, loss: 0.5979477167129517 2023-01-23 17:21:06.554484: step: 1046/1545, loss: 0.0001455366291338578 2023-01-23 17:21:07.393428: step: 1048/1545, loss: 0.00010091118747368455 2023-01-23 17:21:08.269999: step: 1050/1545, loss: 0.001724367612041533 2023-01-23 17:21:09.171762: step: 1052/1545, loss: 0.0018533533439040184 2023-01-23 17:21:10.040229: step: 1054/1545, loss: 7.995963824214414e-05 2023-01-23 17:21:10.909626: step: 1056/1545, loss: 0.006218756549060345 2023-01-23 17:21:11.836535: step: 1058/1545, loss: 0.08602404594421387 2023-01-23 17:21:12.730727: step: 1060/1545, loss: 0.25810468196868896 2023-01-23 17:21:13.582707: step: 1062/1545, loss: 0.04295730963349342 2023-01-23 17:21:14.476069: step: 1064/1545, loss: 0.0009670252911746502 2023-01-23 17:21:15.393211: step: 1066/1545, loss: -1.995078127947636e-05 2023-01-23 17:21:16.286857: step: 1068/1545, loss: 0.12803317606449127 2023-01-23 17:21:17.161049: step: 1070/1545, loss: 0.005401037633419037 2023-01-23 17:21:18.018367: step: 1072/1545, loss: 0.40374836325645447 2023-01-23 17:21:18.867698: step: 1074/1545, loss: -2.4807093723211437e-05 2023-01-23 17:21:19.733283: step: 1076/1545, loss: 0.03252670541405678 2023-01-23 17:21:20.602210: step: 1078/1545, loss: 0.010750215500593185 2023-01-23 17:21:21.463374: step: 1080/1545, loss: -1.4358252883539535e-05 2023-01-23 17:21:22.402842: step: 1082/1545, loss: 0.009713415056467056 2023-01-23 17:21:23.242518: step: 1084/1545, loss: 0.07147777825593948 2023-01-23 17:21:24.120515: step: 1086/1545, loss: 0.028811868280172348 2023-01-23 17:21:25.013860: step: 1088/1545, loss: 0.07876508682966232 2023-01-23 17:21:25.911787: step: 1090/1545, loss: 0.02243509702384472 2023-01-23 17:21:26.756249: step: 1092/1545, loss: 0.0001317878341069445 2023-01-23 17:21:27.697458: step: 1094/1545, loss: 0.06942582130432129 2023-01-23 17:21:28.561224: step: 1096/1545, loss: 0.18582603335380554 2023-01-23 17:21:29.426579: step: 1098/1545, loss: 0.00019266772142145783 2023-01-23 17:21:30.312945: step: 1100/1545, loss: 0.026357432827353477 2023-01-23 17:21:31.204613: step: 1102/1545, loss: 8.019954839255661e-05 2023-01-23 17:21:32.087538: step: 1104/1545, loss: 0.002629390684887767 2023-01-23 17:21:33.003962: step: 1106/1545, loss: 0.02605079859495163 2023-01-23 17:21:33.850836: step: 1108/1545, loss: 0.018295016139745712 2023-01-23 17:21:34.727595: step: 1110/1545, loss: 0.0002291325363330543 2023-01-23 17:21:35.636781: step: 1112/1545, loss: 0.00020033528562635183 2023-01-23 17:21:36.612059: step: 1114/1545, loss: 0.0021599663887172937 2023-01-23 17:21:37.500683: step: 1116/1545, loss: 0.03405199944972992 2023-01-23 17:21:38.352330: step: 1118/1545, loss: 0.02628399431705475 2023-01-23 17:21:39.224192: step: 1120/1545, loss: 0.0010792287066578865 2023-01-23 17:21:40.122643: step: 1122/1545, loss: 0.0016601901734247804 2023-01-23 17:21:41.024760: step: 1124/1545, loss: 3.097380977123976e-05 2023-01-23 17:21:41.997379: step: 1126/1545, loss: 0.00016262559802271426 2023-01-23 17:21:42.884411: step: 1128/1545, loss: 0.04921557009220123 2023-01-23 17:21:43.768140: step: 1130/1545, loss: 0.00020983218564651906 2023-01-23 17:21:44.628709: step: 1132/1545, loss: 0.11244165152311325 2023-01-23 17:21:45.524087: step: 1134/1545, loss: 0.011463688686490059 2023-01-23 17:21:46.360456: step: 1136/1545, loss: 0.004701888654381037 2023-01-23 17:21:47.254561: step: 1138/1545, loss: 0.0005807233974337578 2023-01-23 17:21:48.097921: step: 1140/1545, loss: 0.11112769693136215 2023-01-23 17:21:49.006440: step: 1142/1545, loss: 0.00011593626550165936 2023-01-23 17:21:49.977592: step: 1144/1545, loss: 0.004780278075486422 2023-01-23 17:21:50.832373: step: 1146/1545, loss: 0.0008739527547731996 2023-01-23 17:21:51.742009: step: 1148/1545, loss: 0.22117945551872253 2023-01-23 17:21:52.653635: step: 1150/1545, loss: 0.02409529685974121 2023-01-23 17:21:53.537256: step: 1152/1545, loss: 0.00043233949691057205 2023-01-23 17:21:54.408441: step: 1154/1545, loss: 0.0003125829389318824 2023-01-23 17:21:55.250459: step: 1156/1545, loss: 0.009221621789038181 2023-01-23 17:21:56.106322: step: 1158/1545, loss: 0.0020735992584377527 2023-01-23 17:21:56.951302: step: 1160/1545, loss: 0.0004407280357554555 2023-01-23 17:21:57.841743: step: 1162/1545, loss: -9.080667950911447e-08 2023-01-23 17:21:58.703515: step: 1164/1545, loss: 0.043773673474788666 2023-01-23 17:21:59.543786: step: 1166/1545, loss: 0.030973752960562706 2023-01-23 17:22:00.424037: step: 1168/1545, loss: 0.010301065631210804 2023-01-23 17:22:01.306349: step: 1170/1545, loss: 0.007967141456902027 2023-01-23 17:22:02.253369: step: 1172/1545, loss: 0.009247716516256332 2023-01-23 17:22:03.140589: step: 1174/1545, loss: 0.0013556047342717648 2023-01-23 17:22:04.013586: step: 1176/1545, loss: 0.2125953882932663 2023-01-23 17:22:04.888308: step: 1178/1545, loss: 0.1790020614862442 2023-01-23 17:22:05.741976: step: 1180/1545, loss: 0.0003728661104105413 2023-01-23 17:22:06.637034: step: 1182/1545, loss: 0.0004296217521186918 2023-01-23 17:22:07.578566: step: 1184/1545, loss: 0.20359539985656738 2023-01-23 17:22:08.496654: step: 1186/1545, loss: 0.001032380387187004 2023-01-23 17:22:09.370530: step: 1188/1545, loss: 0.05170741304755211 2023-01-23 17:22:10.218373: step: 1190/1545, loss: 0.4854516088962555 2023-01-23 17:22:11.147965: step: 1192/1545, loss: 0.00010634206410031766 2023-01-23 17:22:12.027522: step: 1194/1545, loss: 0.008441080339252949 2023-01-23 17:22:13.005132: step: 1196/1545, loss: 0.0038072490133345127 2023-01-23 17:22:13.990380: step: 1198/1545, loss: 0.00010078967170557007 2023-01-23 17:22:14.867087: step: 1200/1545, loss: 0.0002427035360597074 2023-01-23 17:22:15.686873: step: 1202/1545, loss: 0.11833080649375916 2023-01-23 17:22:16.578373: step: 1204/1545, loss: 0.000882017717231065 2023-01-23 17:22:17.495468: step: 1206/1545, loss: 0.007364183664321899 2023-01-23 17:22:18.351398: step: 1208/1545, loss: 5.135560786584392e-05 2023-01-23 17:22:19.236005: step: 1210/1545, loss: 0.2340182065963745 2023-01-23 17:22:20.106917: step: 1212/1545, loss: 0.0012912389356642962 2023-01-23 17:22:20.947412: step: 1214/1545, loss: 0.0006362416315823793 2023-01-23 17:22:21.780707: step: 1216/1545, loss: 0.43721163272857666 2023-01-23 17:22:22.622688: step: 1218/1545, loss: 0.024505946785211563 2023-01-23 17:22:23.500187: step: 1220/1545, loss: 0.027284953743219376 2023-01-23 17:22:24.385226: step: 1222/1545, loss: 0.2182660549879074 2023-01-23 17:22:25.262195: step: 1224/1545, loss: 0.02719356119632721 2023-01-23 17:22:26.134557: step: 1226/1545, loss: 0.0013994107721373439 2023-01-23 17:22:27.053649: step: 1228/1545, loss: 0.011416946537792683 2023-01-23 17:22:27.972266: step: 1230/1545, loss: 0.0023790213745087385 2023-01-23 17:22:28.823201: step: 1232/1545, loss: 0.043694134801626205 2023-01-23 17:22:29.702031: step: 1234/1545, loss: 0.04075058177113533 2023-01-23 17:22:30.613310: step: 1236/1545, loss: 1.1898458003997803 2023-01-23 17:22:31.507223: step: 1238/1545, loss: 0.010572829283773899 2023-01-23 17:22:32.403119: step: 1240/1545, loss: 0.005231705028563738 2023-01-23 17:22:33.251499: step: 1242/1545, loss: 0.0021608455572277308 2023-01-23 17:22:34.094472: step: 1244/1545, loss: 0.06445851922035217 2023-01-23 17:22:34.963685: step: 1246/1545, loss: 0.015621931292116642 2023-01-23 17:22:35.944875: step: 1248/1545, loss: 0.0009282514802180231 2023-01-23 17:22:36.841881: step: 1250/1545, loss: 0.006257212720811367 2023-01-23 17:22:37.724497: step: 1252/1545, loss: 0.0018400527769699693 2023-01-23 17:22:38.576719: step: 1254/1545, loss: 0.08780965209007263 2023-01-23 17:22:39.467708: step: 1256/1545, loss: 0.006891678553074598 2023-01-23 17:22:40.330180: step: 1258/1545, loss: 0.0029946418944746256 2023-01-23 17:22:41.235411: step: 1260/1545, loss: 0.05343399941921234 2023-01-23 17:22:42.085840: step: 1262/1545, loss: 0.0622771754860878 2023-01-23 17:22:42.971893: step: 1264/1545, loss: 0.0018595934379845858 2023-01-23 17:22:43.821144: step: 1266/1545, loss: 0.0007460000924766064 2023-01-23 17:22:44.660285: step: 1268/1545, loss: 0.012649882584810257 2023-01-23 17:22:45.582322: step: 1270/1545, loss: 0.25995662808418274 2023-01-23 17:22:46.432663: step: 1272/1545, loss: 0.005427828989923 2023-01-23 17:22:47.292634: step: 1274/1545, loss: 0.0055039371363818645 2023-01-23 17:22:48.166045: step: 1276/1545, loss: 0.0038458891212940216 2023-01-23 17:22:49.041085: step: 1278/1545, loss: 0.056960441172122955 2023-01-23 17:22:49.893452: step: 1280/1545, loss: 0.030615536496043205 2023-01-23 17:22:50.751566: step: 1282/1545, loss: 0.0009348790626972914 2023-01-23 17:22:51.624894: step: 1284/1545, loss: 0.001963830552995205 2023-01-23 17:22:52.520050: step: 1286/1545, loss: 0.03896388038992882 2023-01-23 17:22:53.494869: step: 1288/1545, loss: 0.06899552047252655 2023-01-23 17:22:54.347996: step: 1290/1545, loss: 0.001965336501598358 2023-01-23 17:22:55.228429: step: 1292/1545, loss: 0.003518646350130439 2023-01-23 17:22:56.123047: step: 1294/1545, loss: 0.06903543323278427 2023-01-23 17:22:56.959556: step: 1296/1545, loss: 0.0037092736456543207 2023-01-23 17:22:57.817124: step: 1298/1545, loss: 0.0022970589343458414 2023-01-23 17:22:58.724443: step: 1300/1545, loss: 0.026080401614308357 2023-01-23 17:22:59.587946: step: 1302/1545, loss: 0.14452902972698212 2023-01-23 17:23:00.485517: step: 1304/1545, loss: 0.042169809341430664 2023-01-23 17:23:01.350757: step: 1306/1545, loss: 0.017026176676154137 2023-01-23 17:23:02.185820: step: 1308/1545, loss: 0.007101311814039946 2023-01-23 17:23:03.070110: step: 1310/1545, loss: 0.04272577539086342 2023-01-23 17:23:03.952824: step: 1312/1545, loss: 0.008592390455305576 2023-01-23 17:23:04.787850: step: 1314/1545, loss: 0.0012913711834698915 2023-01-23 17:23:05.628940: step: 1316/1545, loss: 0.11385504901409149 2023-01-23 17:23:06.489294: step: 1318/1545, loss: 0.021543506532907486 2023-01-23 17:23:07.364723: step: 1320/1545, loss: 0.04425433650612831 2023-01-23 17:23:08.244831: step: 1322/1545, loss: 0.0012098265578970313 2023-01-23 17:23:09.148992: step: 1324/1545, loss: 0.0007547086570411921 2023-01-23 17:23:09.998035: step: 1326/1545, loss: 0.005412723869085312 2023-01-23 17:23:10.898459: step: 1328/1545, loss: 0.24097248911857605 2023-01-23 17:23:11.768682: step: 1330/1545, loss: 0.013191147707402706 2023-01-23 17:23:12.670687: step: 1332/1545, loss: 0.025633467361330986 2023-01-23 17:23:13.529322: step: 1334/1545, loss: 0.15244771540164948 2023-01-23 17:23:14.409889: step: 1336/1545, loss: 0.006357768550515175 2023-01-23 17:23:15.297099: step: 1338/1545, loss: 0.026680750772356987 2023-01-23 17:23:16.133231: step: 1340/1545, loss: 0.003668217919766903 2023-01-23 17:23:17.043670: step: 1342/1545, loss: 0.0912899374961853 2023-01-23 17:23:17.925543: step: 1344/1545, loss: 0.0020533427596092224 2023-01-23 17:23:18.944360: step: 1346/1545, loss: 0.05349074676632881 2023-01-23 17:23:19.842930: step: 1348/1545, loss: 0.0036829609889537096 2023-01-23 17:23:20.759794: step: 1350/1545, loss: 0.04386571794748306 2023-01-23 17:23:21.619139: step: 1352/1545, loss: 0.008407884277403355 2023-01-23 17:23:22.512429: step: 1354/1545, loss: 0.01593145728111267 2023-01-23 17:23:23.387147: step: 1356/1545, loss: 0.11831439286470413 2023-01-23 17:23:24.283492: step: 1358/1545, loss: 0.03813052549958229 2023-01-23 17:23:25.140868: step: 1360/1545, loss: 0.00042430165922269225 2023-01-23 17:23:25.990380: step: 1362/1545, loss: 0.12766875326633453 2023-01-23 17:23:26.865582: step: 1364/1545, loss: 0.00043296528747305274 2023-01-23 17:23:27.698268: step: 1366/1545, loss: 0.24745848774909973 2023-01-23 17:23:28.541971: step: 1368/1545, loss: 0.01377253420650959 2023-01-23 17:23:29.413990: step: 1370/1545, loss: 0.023075241595506668 2023-01-23 17:23:30.274077: step: 1372/1545, loss: 0.09296606481075287 2023-01-23 17:23:31.165718: step: 1374/1545, loss: 6.820516136940569e-05 2023-01-23 17:23:32.053441: step: 1376/1545, loss: 0.002433817833662033 2023-01-23 17:23:32.920253: step: 1378/1545, loss: 0.011507676914334297 2023-01-23 17:23:33.770219: step: 1380/1545, loss: 0.028307922184467316 2023-01-23 17:23:34.602481: step: 1382/1545, loss: 0.00045524793677031994 2023-01-23 17:23:35.475090: step: 1384/1545, loss: 0.8734363913536072 2023-01-23 17:23:36.353052: step: 1386/1545, loss: 0.09941479563713074 2023-01-23 17:23:37.222780: step: 1388/1545, loss: 0.002208918100222945 2023-01-23 17:23:38.040861: step: 1390/1545, loss: 0.0006301740650087595 2023-01-23 17:23:38.906698: step: 1392/1545, loss: 0.7676935195922852 2023-01-23 17:23:39.751948: step: 1394/1545, loss: 9.994719221140258e-06 2023-01-23 17:23:40.588967: step: 1396/1545, loss: 0.0014893946936354041 2023-01-23 17:23:41.457756: step: 1398/1545, loss: 0.006472505629062653 2023-01-23 17:23:42.360133: step: 1400/1545, loss: 0.045740410685539246 2023-01-23 17:23:43.265018: step: 1402/1545, loss: 0.007346509490162134 2023-01-23 17:23:44.097964: step: 1404/1545, loss: 0.008175112307071686 2023-01-23 17:23:45.014247: step: 1406/1545, loss: 0.4808381497859955 2023-01-23 17:23:45.900649: step: 1408/1545, loss: 0.35000720620155334 2023-01-23 17:23:46.724225: step: 1410/1545, loss: 0.3028624653816223 2023-01-23 17:23:47.593904: step: 1412/1545, loss: 0.2672160565853119 2023-01-23 17:23:48.446452: step: 1414/1545, loss: 0.11575599014759064 2023-01-23 17:23:49.357418: step: 1416/1545, loss: 0.022402383387088776 2023-01-23 17:23:50.221542: step: 1418/1545, loss: 0.0828637182712555 2023-01-23 17:23:51.085602: step: 1420/1545, loss: 0.15286608040332794 2023-01-23 17:23:52.067783: step: 1422/1545, loss: 0.11767511069774628 2023-01-23 17:23:52.934614: step: 1424/1545, loss: 0.1309763640165329 2023-01-23 17:23:53.815571: step: 1426/1545, loss: 0.020822159945964813 2023-01-23 17:23:54.698831: step: 1428/1545, loss: 0.22251906991004944 2023-01-23 17:23:55.631677: step: 1430/1545, loss: 0.011979709379374981 2023-01-23 17:23:56.491888: step: 1432/1545, loss: 0.0020681109745055437 2023-01-23 17:23:57.383583: step: 1434/1545, loss: 0.1850489377975464 2023-01-23 17:23:58.327359: step: 1436/1545, loss: 0.006837420631200075 2023-01-23 17:23:59.198450: step: 1438/1545, loss: 0.4401850402355194 2023-01-23 17:24:00.032755: step: 1440/1545, loss: 0.0037495684809982777 2023-01-23 17:24:00.948102: step: 1442/1545, loss: 0.0013979378854855895 2023-01-23 17:24:01.816066: step: 1444/1545, loss: 0.0012389913899824023 2023-01-23 17:24:02.730824: step: 1446/1545, loss: 0.006250687874853611 2023-01-23 17:24:03.598730: step: 1448/1545, loss: 0.002086164429783821 2023-01-23 17:24:04.477125: step: 1450/1545, loss: 0.010241425596177578 2023-01-23 17:24:05.368151: step: 1452/1545, loss: 0.006021997891366482 2023-01-23 17:24:06.269769: step: 1454/1545, loss: 0.0591878816485405 2023-01-23 17:24:07.148887: step: 1456/1545, loss: 0.0028060078620910645 2023-01-23 17:24:07.995828: step: 1458/1545, loss: 0.020157817751169205 2023-01-23 17:24:08.876329: step: 1460/1545, loss: 0.00021638326870743185 2023-01-23 17:24:09.746683: step: 1462/1545, loss: 0.028925424441695213 2023-01-23 17:24:10.584744: step: 1464/1545, loss: 0.026465628296136856 2023-01-23 17:24:11.474593: step: 1466/1545, loss: 0.0022776033729314804 2023-01-23 17:24:12.363860: step: 1468/1545, loss: 0.0006653415039181709 2023-01-23 17:24:13.221087: step: 1470/1545, loss: 0.019093425944447517 2023-01-23 17:24:14.114835: step: 1472/1545, loss: 0.00012550251267384738 2023-01-23 17:24:14.960053: step: 1474/1545, loss: 0.002752851229161024 2023-01-23 17:24:15.820335: step: 1476/1545, loss: 0.042840376496315 2023-01-23 17:24:16.705994: step: 1478/1545, loss: 0.6102507710456848 2023-01-23 17:24:17.588287: step: 1480/1545, loss: 0.01299841795116663 2023-01-23 17:24:18.443184: step: 1482/1545, loss: 0.012611394748091698 2023-01-23 17:24:19.313268: step: 1484/1545, loss: 0.019750619307160378 2023-01-23 17:24:20.149822: step: 1486/1545, loss: 0.0025787095073610544 2023-01-23 17:24:21.063815: step: 1488/1545, loss: 0.0025123287923634052 2023-01-23 17:24:21.965970: step: 1490/1545, loss: 0.005575205665081739 2023-01-23 17:24:22.941333: step: 1492/1545, loss: 0.34606415033340454 2023-01-23 17:24:23.788786: step: 1494/1545, loss: 0.00029819077462889254 2023-01-23 17:24:24.663236: step: 1496/1545, loss: 0.0067510767839848995 2023-01-23 17:24:25.523716: step: 1498/1545, loss: 0.0006431941292248666 2023-01-23 17:24:26.387680: step: 1500/1545, loss: 0.004028297029435635 2023-01-23 17:24:27.221323: step: 1502/1545, loss: 0.0021776780486106873 2023-01-23 17:24:28.103030: step: 1504/1545, loss: 0.018091104924678802 2023-01-23 17:24:28.991269: step: 1506/1545, loss: 0.02731899917125702 2023-01-23 17:24:29.856961: step: 1508/1545, loss: 0.22929686307907104 2023-01-23 17:24:30.758149: step: 1510/1545, loss: 0.0055990214459598064 2023-01-23 17:24:31.633813: step: 1512/1545, loss: 0.041834697127342224 2023-01-23 17:24:32.535956: step: 1514/1545, loss: 0.4127390682697296 2023-01-23 17:24:33.415123: step: 1516/1545, loss: 0.0015452209627255797 2023-01-23 17:24:34.261986: step: 1518/1545, loss: 0.005506254732608795 2023-01-23 17:24:35.139920: step: 1520/1545, loss: 4.488486592890695e-05 2023-01-23 17:24:35.996910: step: 1522/1545, loss: 0.002149063628166914 2023-01-23 17:24:36.867290: step: 1524/1545, loss: 0.007084188051521778 2023-01-23 17:24:37.738479: step: 1526/1545, loss: 0.1182859018445015 2023-01-23 17:24:38.604317: step: 1528/1545, loss: 0.0008104967419058084 2023-01-23 17:24:39.514705: step: 1530/1545, loss: 0.06004786491394043 2023-01-23 17:24:40.396315: step: 1532/1545, loss: 0.07375846058130264 2023-01-23 17:24:41.296264: step: 1534/1545, loss: 1.0130006074905396 2023-01-23 17:24:42.249446: step: 1536/1545, loss: 0.12984508275985718 2023-01-23 17:24:43.191770: step: 1538/1545, loss: 0.011805201880633831 2023-01-23 17:24:44.047325: step: 1540/1545, loss: 0.11277714371681213 2023-01-23 17:24:44.939927: step: 1542/1545, loss: 0.04900866746902466 2023-01-23 17:24:45.818848: step: 1544/1545, loss: 0.0026585753075778484 2023-01-23 17:24:46.698496: step: 1546/1545, loss: 5.49211363249924e-05 2023-01-23 17:24:47.536028: step: 1548/1545, loss: 0.03154538944363594 2023-01-23 17:24:48.408924: step: 1550/1545, loss: 0.2900700569152832 2023-01-23 17:24:49.286698: step: 1552/1545, loss: 0.023293614387512207 2023-01-23 17:24:50.128361: step: 1554/1545, loss: 0.0013312584487721324 2023-01-23 17:24:50.967593: step: 1556/1545, loss: 0.05493428558111191 2023-01-23 17:24:51.941766: step: 1558/1545, loss: 0.009358215145766735 2023-01-23 17:24:52.811459: step: 1560/1545, loss: 8.843610703479499e-05 2023-01-23 17:24:53.654302: step: 1562/1545, loss: 0.050985127687454224 2023-01-23 17:24:54.562670: step: 1564/1545, loss: 0.0021847011521458626 2023-01-23 17:24:55.517589: step: 1566/1545, loss: 0.02542293258011341 2023-01-23 17:24:56.400429: step: 1568/1545, loss: 0.0025330660864710808 2023-01-23 17:24:57.289952: step: 1570/1545, loss: 0.160993292927742 2023-01-23 17:24:58.186774: step: 1572/1545, loss: 0.004015911370515823 2023-01-23 17:24:59.124609: step: 1574/1545, loss: 0.1121654361486435 2023-01-23 17:24:59.989301: step: 1576/1545, loss: 0.07197347283363342 2023-01-23 17:25:00.827581: step: 1578/1545, loss: 0.04537438601255417 2023-01-23 17:25:01.740663: step: 1580/1545, loss: 0.010684707202017307 2023-01-23 17:25:02.616669: step: 1582/1545, loss: 0.0029187644831836224 2023-01-23 17:25:03.537449: step: 1584/1545, loss: 0.0005531451315619051 2023-01-23 17:25:04.429362: step: 1586/1545, loss: 0.000825720198918134 2023-01-23 17:25:05.356069: step: 1588/1545, loss: 0.14646722376346588 2023-01-23 17:25:06.192706: step: 1590/1545, loss: 0.00025549533893354237 2023-01-23 17:25:07.064802: step: 1592/1545, loss: 0.03060177154839039 2023-01-23 17:25:07.924372: step: 1594/1545, loss: 0.006990963593125343 2023-01-23 17:25:08.916375: step: 1596/1545, loss: 0.03067146986722946 2023-01-23 17:25:09.788721: step: 1598/1545, loss: 0.00028785463655367494 2023-01-23 17:25:10.655761: step: 1600/1545, loss: 0.0033410387113690376 2023-01-23 17:25:11.555041: step: 1602/1545, loss: 0.0045405966229736805 2023-01-23 17:25:12.442850: step: 1604/1545, loss: 0.06629601120948792 2023-01-23 17:25:13.281614: step: 1606/1545, loss: 0.0016538465861231089 2023-01-23 17:25:14.175005: step: 1608/1545, loss: 0.09096916764974594 2023-01-23 17:25:15.039631: step: 1610/1545, loss: 0.0015397376846522093 2023-01-23 17:25:15.904864: step: 1612/1545, loss: 0.024889525026082993 2023-01-23 17:25:16.796279: step: 1614/1545, loss: 0.001565276295877993 2023-01-23 17:25:17.735192: step: 1616/1545, loss: 0.00748864421620965 2023-01-23 17:25:18.651999: step: 1618/1545, loss: 0.07854783535003662 2023-01-23 17:25:19.510645: step: 1620/1545, loss: 0.0008625524351373315 2023-01-23 17:25:20.377634: step: 1622/1545, loss: 0.38219311833381653 2023-01-23 17:25:21.272008: step: 1624/1545, loss: 0.0003339216054882854 2023-01-23 17:25:22.140837: step: 1626/1545, loss: 0.006220491137355566 2023-01-23 17:25:23.011077: step: 1628/1545, loss: 0.001195811084471643 2023-01-23 17:25:23.863805: step: 1630/1545, loss: 0.07019852101802826 2023-01-23 17:25:24.756213: step: 1632/1545, loss: 0.006165242288261652 2023-01-23 17:25:25.673265: step: 1634/1545, loss: 6.672204472124577e-05 2023-01-23 17:25:26.575936: step: 1636/1545, loss: 0.35394859313964844 2023-01-23 17:25:27.493456: step: 1638/1545, loss: 0.007892606779932976 2023-01-23 17:25:28.350879: step: 1640/1545, loss: 0.24542595446109772 2023-01-23 17:25:29.255707: step: 1642/1545, loss: 0.05531232804059982 2023-01-23 17:25:30.176375: step: 1644/1545, loss: 0.0006503964541479945 2023-01-23 17:25:31.025918: step: 1646/1545, loss: 0.28244683146476746 2023-01-23 17:25:31.898846: step: 1648/1545, loss: 0.002499775495380163 2023-01-23 17:25:32.800266: step: 1650/1545, loss: 0.00019445418729446828 2023-01-23 17:25:33.681247: step: 1652/1545, loss: 0.0010755200637504458 2023-01-23 17:25:34.587073: step: 1654/1545, loss: 0.015479694120585918 2023-01-23 17:25:35.435159: step: 1656/1545, loss: 9.402469004271552e-05 2023-01-23 17:25:36.292567: step: 1658/1545, loss: 0.0007061250507831573 2023-01-23 17:25:37.207094: step: 1660/1545, loss: 0.00031631276942789555 2023-01-23 17:25:38.116799: step: 1662/1545, loss: 0.024951554834842682 2023-01-23 17:25:38.970255: step: 1664/1545, loss: 0.0065211341716349125 2023-01-23 17:25:39.855870: step: 1666/1545, loss: 0.14256048202514648 2023-01-23 17:25:40.707069: step: 1668/1545, loss: 0.4412437379360199 2023-01-23 17:25:41.589424: step: 1670/1545, loss: 0.008508868515491486 2023-01-23 17:25:42.446670: step: 1672/1545, loss: 0.00013483408838510513 2023-01-23 17:25:43.309686: step: 1674/1545, loss: 0.0002755843161139637 2023-01-23 17:25:44.169642: step: 1676/1545, loss: 0.09319336712360382 2023-01-23 17:25:45.026192: step: 1678/1545, loss: 0.001348113059066236 2023-01-23 17:25:45.920305: step: 1680/1545, loss: 0.014053795486688614 2023-01-23 17:25:46.775351: step: 1682/1545, loss: 0.00027796081849373877 2023-01-23 17:25:47.658459: step: 1684/1545, loss: 0.00017830979777500033 2023-01-23 17:25:48.561632: step: 1686/1545, loss: 0.06459353864192963 2023-01-23 17:25:49.473453: step: 1688/1545, loss: 0.00014026557619217783 2023-01-23 17:25:50.342813: step: 1690/1545, loss: 0.017889773473143578 2023-01-23 17:25:51.203183: step: 1692/1545, loss: 0.010683136060833931 2023-01-23 17:25:52.044653: step: 1694/1545, loss: 0.00023068615701049566 2023-01-23 17:25:52.958695: step: 1696/1545, loss: 0.004970606416463852 2023-01-23 17:25:53.826560: step: 1698/1545, loss: 0.0002777055196929723 2023-01-23 17:25:54.657041: step: 1700/1545, loss: 0.0007943809032440186 2023-01-23 17:25:55.498155: step: 1702/1545, loss: 0.2739543318748474 2023-01-23 17:25:56.384230: step: 1704/1545, loss: 0.0024446684401482344 2023-01-23 17:25:57.240107: step: 1706/1545, loss: 0.0003478399885352701 2023-01-23 17:25:58.060202: step: 1708/1545, loss: 0.00086242362158373 2023-01-23 17:25:58.922824: step: 1710/1545, loss: 0.086650550365448 2023-01-23 17:25:59.816719: step: 1712/1545, loss: 0.002153501147404313 2023-01-23 17:26:00.761133: step: 1714/1545, loss: 0.15204519033432007 2023-01-23 17:26:01.644070: step: 1716/1545, loss: 0.5134490728378296 2023-01-23 17:26:02.499784: step: 1718/1545, loss: 5.2129900723230094e-05 2023-01-23 17:26:03.403996: step: 1720/1545, loss: 0.0010835707653313875 2023-01-23 17:26:04.300521: step: 1722/1545, loss: 0.1713053435087204 2023-01-23 17:26:05.156389: step: 1724/1545, loss: 0.00136442924849689 2023-01-23 17:26:06.069522: step: 1726/1545, loss: 0.07351024448871613 2023-01-23 17:26:06.930132: step: 1728/1545, loss: 0.0002844514965545386 2023-01-23 17:26:07.862121: step: 1730/1545, loss: 0.0010564374970272183 2023-01-23 17:26:08.780761: step: 1732/1545, loss: 0.004855223000049591 2023-01-23 17:26:09.622688: step: 1734/1545, loss: 0.00026470472221262753 2023-01-23 17:26:10.495281: step: 1736/1545, loss: 0.016063660383224487 2023-01-23 17:26:11.405455: step: 1738/1545, loss: 0.00805011298507452 2023-01-23 17:26:12.318415: step: 1740/1545, loss: 0.0001867831451818347 2023-01-23 17:26:13.179470: step: 1742/1545, loss: 0.02057948336005211 2023-01-23 17:26:14.076714: step: 1744/1545, loss: 0.011924969963729382 2023-01-23 17:26:14.980740: step: 1746/1545, loss: 0.004773580003529787 2023-01-23 17:26:15.897014: step: 1748/1545, loss: 0.022502850741147995 2023-01-23 17:26:16.788306: step: 1750/1545, loss: 0.16970835626125336 2023-01-23 17:26:17.645881: step: 1752/1545, loss: 0.14178262650966644 2023-01-23 17:26:18.515843: step: 1754/1545, loss: 0.003997578751295805 2023-01-23 17:26:19.384611: step: 1756/1545, loss: 0.014601217582821846 2023-01-23 17:26:20.272694: step: 1758/1545, loss: 0.09359386563301086 2023-01-23 17:26:21.110286: step: 1760/1545, loss: 0.002999805612489581 2023-01-23 17:26:21.976810: step: 1762/1545, loss: 0.0030778509099036455 2023-01-23 17:26:22.879221: step: 1764/1545, loss: 0.43726062774658203 2023-01-23 17:26:23.757376: step: 1766/1545, loss: 0.0004861106863245368 2023-01-23 17:26:24.665346: step: 1768/1545, loss: 0.08201946318149567 2023-01-23 17:26:25.567807: step: 1770/1545, loss: 0.31711143255233765 2023-01-23 17:26:26.471757: step: 1772/1545, loss: 0.09309752285480499 2023-01-23 17:26:27.348045: step: 1774/1545, loss: 0.04498731717467308 2023-01-23 17:26:28.174523: step: 1776/1545, loss: 0.18405979871749878 2023-01-23 17:26:29.071359: step: 1778/1545, loss: 0.0013062860816717148 2023-01-23 17:26:29.967169: step: 1780/1545, loss: 0.0009971673134714365 2023-01-23 17:26:30.881910: step: 1782/1545, loss: 0.034538384526968 2023-01-23 17:26:31.735482: step: 1784/1545, loss: 0.049676619470119476 2023-01-23 17:26:32.633463: step: 1786/1545, loss: 0.03770098090171814 2023-01-23 17:26:33.535248: step: 1788/1545, loss: 0.06241625174880028 2023-01-23 17:26:34.383971: step: 1790/1545, loss: 0.002561449771746993 2023-01-23 17:26:35.261872: step: 1792/1545, loss: 0.015136339701712132 2023-01-23 17:26:36.117278: step: 1794/1545, loss: 0.15550778806209564 2023-01-23 17:26:36.960244: step: 1796/1545, loss: 0.0802106037735939 2023-01-23 17:26:37.831849: step: 1798/1545, loss: 0.352237731218338 2023-01-23 17:26:38.807194: step: 1800/1545, loss: 0.11494816094636917 2023-01-23 17:26:39.697883: step: 1802/1545, loss: 0.00026852349401451647 2023-01-23 17:26:40.559656: step: 1804/1545, loss: 0.10146202892065048 2023-01-23 17:26:41.551095: step: 1806/1545, loss: 0.018339574337005615 2023-01-23 17:26:42.407888: step: 1808/1545, loss: 0.0005954357911832631 2023-01-23 17:26:43.293042: step: 1810/1545, loss: 0.0006184615194797516 2023-01-23 17:26:44.171416: step: 1812/1545, loss: 0.05031059309840202 2023-01-23 17:26:45.031018: step: 1814/1545, loss: 0.9425404667854309 2023-01-23 17:26:45.879661: step: 1816/1545, loss: 0.0006620652857236564 2023-01-23 17:26:46.757651: step: 1818/1545, loss: 0.0018464253516867757 2023-01-23 17:26:47.618329: step: 1820/1545, loss: 0.009152804501354694 2023-01-23 17:26:48.493895: step: 1822/1545, loss: 0.0035546510480344296 2023-01-23 17:26:49.335645: step: 1824/1545, loss: 0.0007562814280390739 2023-01-23 17:26:50.203052: step: 1826/1545, loss: 0.013177440501749516 2023-01-23 17:26:51.083364: step: 1828/1545, loss: 0.00031204038532450795 2023-01-23 17:26:51.949855: step: 1830/1545, loss: 0.10132035613059998 2023-01-23 17:26:52.845242: step: 1832/1545, loss: 0.00041527021676301956 2023-01-23 17:26:53.721557: step: 1834/1545, loss: 0.0026016789488494396 2023-01-23 17:26:54.567800: step: 1836/1545, loss: 0.057364895939826965 2023-01-23 17:26:55.458578: step: 1838/1545, loss: 0.0944763794541359 2023-01-23 17:26:56.390354: step: 1840/1545, loss: 0.011043032631278038 2023-01-23 17:26:57.257812: step: 1842/1545, loss: 0.29149091243743896 2023-01-23 17:26:58.093809: step: 1844/1545, loss: 0.00041987045551650226 2023-01-23 17:26:58.940952: step: 1846/1545, loss: 0.11943744868040085 2023-01-23 17:26:59.794905: step: 1848/1545, loss: 0.0005361916846595705 2023-01-23 17:27:00.738284: step: 1850/1545, loss: 0.0536169596016407 2023-01-23 17:27:01.591303: step: 1852/1545, loss: 0.0031441038008779287 2023-01-23 17:27:02.466706: step: 1854/1545, loss: 0.061389099806547165 2023-01-23 17:27:03.363879: step: 1856/1545, loss: 0.0036740342620760202 2023-01-23 17:27:04.230412: step: 1858/1545, loss: -3.4352319744357374e-06 2023-01-23 17:27:05.101861: step: 1860/1545, loss: 0.0018430349882692099 2023-01-23 17:27:06.063879: step: 1862/1545, loss: 0.13717380166053772 2023-01-23 17:27:06.967439: step: 1864/1545, loss: 0.0970333144068718 2023-01-23 17:27:07.836806: step: 1866/1545, loss: 1.6408170461654663 2023-01-23 17:27:08.760298: step: 1868/1545, loss: 0.011288280598819256 2023-01-23 17:27:09.605392: step: 1870/1545, loss: 0.3318363428115845 2023-01-23 17:27:10.488821: step: 1872/1545, loss: 0.03746671602129936 2023-01-23 17:27:11.342367: step: 1874/1545, loss: 0.0004270524950698018 2023-01-23 17:27:12.232594: step: 1876/1545, loss: 0.12508167326450348 2023-01-23 17:27:13.192980: step: 1878/1545, loss: 0.0002515685046091676 2023-01-23 17:27:14.040654: step: 1880/1545, loss: 0.01583428867161274 2023-01-23 17:27:14.920378: step: 1882/1545, loss: 0.01797350123524666 2023-01-23 17:27:15.824171: step: 1884/1545, loss: 0.21626880764961243 2023-01-23 17:27:16.768278: step: 1886/1545, loss: 0.10226047039031982 2023-01-23 17:27:17.614748: step: 1888/1545, loss: 0.19243015348911285 2023-01-23 17:27:18.509048: step: 1890/1545, loss: 0.49477142095565796 2023-01-23 17:27:19.370591: step: 1892/1545, loss: 0.00605181185528636 2023-01-23 17:27:20.250011: step: 1894/1545, loss: 0.0019977649208158255 2023-01-23 17:27:21.141242: step: 1896/1545, loss: 0.0018797427183017135 2023-01-23 17:27:22.049011: step: 1898/1545, loss: 0.01347686629742384 2023-01-23 17:27:22.942816: step: 1900/1545, loss: 0.029146356508135796 2023-01-23 17:27:23.775020: step: 1902/1545, loss: 4.5894034883531276e-07 2023-01-23 17:27:24.629019: step: 1904/1545, loss: 0.0006733608315698802 2023-01-23 17:27:25.520257: step: 1906/1545, loss: 0.0007720266003161669 2023-01-23 17:27:26.383799: step: 1908/1545, loss: 0.0019817983265966177 2023-01-23 17:27:27.218162: step: 1910/1545, loss: 0.011200585402548313 2023-01-23 17:27:28.067327: step: 1912/1545, loss: 0.001508161542005837 2023-01-23 17:27:28.937730: step: 1914/1545, loss: 0.20188592374324799 2023-01-23 17:27:29.819780: step: 1916/1545, loss: 0.030772466212511063 2023-01-23 17:27:30.787267: step: 1918/1545, loss: 7.270118658198044e-05 2023-01-23 17:27:31.638758: step: 1920/1545, loss: 0.014882273972034454 2023-01-23 17:27:32.484527: step: 1922/1545, loss: -3.1212595786200836e-05 2023-01-23 17:27:33.334412: step: 1924/1545, loss: 0.00028728292090818286 2023-01-23 17:27:34.243166: step: 1926/1545, loss: 0.0009606077219359577 2023-01-23 17:27:35.105225: step: 1928/1545, loss: 0.0003061852476093918 2023-01-23 17:27:36.024672: step: 1930/1545, loss: 0.0003576099989004433 2023-01-23 17:27:36.923418: step: 1932/1545, loss: 0.0007066332036629319 2023-01-23 17:27:37.813668: step: 1934/1545, loss: 0.031868524849414825 2023-01-23 17:27:38.688025: step: 1936/1545, loss: 0.028390198945999146 2023-01-23 17:27:39.530695: step: 1938/1545, loss: 0.043459147214889526 2023-01-23 17:27:40.345770: step: 1940/1545, loss: 0.09663162380456924 2023-01-23 17:27:41.232612: step: 1942/1545, loss: 0.00017802935326471925 2023-01-23 17:27:42.170160: step: 1944/1545, loss: 0.027377411723136902 2023-01-23 17:27:43.011873: step: 1946/1545, loss: 0.00012695119949057698 2023-01-23 17:27:43.888260: step: 1948/1545, loss: 0.07743912935256958 2023-01-23 17:27:44.798619: step: 1950/1545, loss: 0.004524208605289459 2023-01-23 17:27:45.650704: step: 1952/1545, loss: 0.8101047277450562 2023-01-23 17:27:46.546296: step: 1954/1545, loss: 0.04650011658668518 2023-01-23 17:27:47.458779: step: 1956/1545, loss: 0.07230962067842484 2023-01-23 17:27:48.314098: step: 1958/1545, loss: 0.00042854875209741294 2023-01-23 17:27:49.260631: step: 1960/1545, loss: 0.005016283132135868 2023-01-23 17:27:50.191415: step: 1962/1545, loss: 0.0634615421295166 2023-01-23 17:27:51.111232: step: 1964/1545, loss: 0.009769709780812263 2023-01-23 17:27:52.005279: step: 1966/1545, loss: 0.001080694841220975 2023-01-23 17:27:52.890630: step: 1968/1545, loss: 0.01175918709486723 2023-01-23 17:27:53.769581: step: 1970/1545, loss: 0.3697536587715149 2023-01-23 17:27:54.627974: step: 1972/1545, loss: 0.0021047296468168497 2023-01-23 17:27:55.480023: step: 1974/1545, loss: 0.001310607185587287 2023-01-23 17:27:56.405734: step: 1976/1545, loss: 0.20217527449131012 2023-01-23 17:27:57.341944: step: 1978/1545, loss: 0.00031554375891573727 2023-01-23 17:27:58.193366: step: 1980/1545, loss: 0.583858847618103 2023-01-23 17:27:59.037268: step: 1982/1545, loss: 0.1347699612379074 2023-01-23 17:27:59.908834: step: 1984/1545, loss: 0.060929518193006516 2023-01-23 17:28:00.766532: step: 1986/1545, loss: 0.18542362749576569 2023-01-23 17:28:01.660673: step: 1988/1545, loss: 0.33322861790657043 2023-01-23 17:28:02.545714: step: 1990/1545, loss: 0.0006081127212382853 2023-01-23 17:28:03.417697: step: 1992/1545, loss: 0.020681137219071388 2023-01-23 17:28:04.287040: step: 1994/1545, loss: 1.0797114372253418 2023-01-23 17:28:05.142571: step: 1996/1545, loss: 0.008901258930563927 2023-01-23 17:28:06.018720: step: 1998/1545, loss: 0.0023807757534086704 2023-01-23 17:28:06.893834: step: 2000/1545, loss: 0.31939470767974854 2023-01-23 17:28:07.792492: step: 2002/1545, loss: 0.005371610634028912 2023-01-23 17:28:08.684926: step: 2004/1545, loss: 0.05125938355922699 2023-01-23 17:28:09.589698: step: 2006/1545, loss: 0.023871004581451416 2023-01-23 17:28:10.458023: step: 2008/1545, loss: 3.1635708808898926 2023-01-23 17:28:11.326432: step: 2010/1545, loss: 0.00035297730937600136 2023-01-23 17:28:12.168735: step: 2012/1545, loss: 0.0005173488752916455 2023-01-23 17:28:13.067052: step: 2014/1545, loss: 0.005763696506619453 2023-01-23 17:28:13.905964: step: 2016/1545, loss: 0.004599917680025101 2023-01-23 17:28:14.752976: step: 2018/1545, loss: 0.05979429557919502 2023-01-23 17:28:15.741585: step: 2020/1545, loss: 0.10346481204032898 2023-01-23 17:28:16.626902: step: 2022/1545, loss: 0.16378693282604218 2023-01-23 17:28:17.503758: step: 2024/1545, loss: 0.19631722569465637 2023-01-23 17:28:18.333257: step: 2026/1545, loss: 0.002674270188435912 2023-01-23 17:28:19.335214: step: 2028/1545, loss: 0.04040881246328354 2023-01-23 17:28:20.213651: step: 2030/1545, loss: 0.0093821557238698 2023-01-23 17:28:21.109433: step: 2032/1545, loss: 0.0019133383175358176 2023-01-23 17:28:22.020432: step: 2034/1545, loss: 0.000189473110367544 2023-01-23 17:28:22.887055: step: 2036/1545, loss: 0.0014990874333307147 2023-01-23 17:28:23.761479: step: 2038/1545, loss: 0.0013157339999452233 2023-01-23 17:28:24.604255: step: 2040/1545, loss: 0.29576584696769714 2023-01-23 17:28:25.472284: step: 2042/1545, loss: 0.0028961908537894487 2023-01-23 17:28:26.363302: step: 2044/1545, loss: 0.1026981994509697 2023-01-23 17:28:27.211370: step: 2046/1545, loss: 0.020160328596830368 2023-01-23 17:28:28.062234: step: 2048/1545, loss: 0.008994020521640778 2023-01-23 17:28:28.912843: step: 2050/1545, loss: 0.00019798878929577768 2023-01-23 17:28:29.801060: step: 2052/1545, loss: 0.0005550811183638871 2023-01-23 17:28:30.643364: step: 2054/1545, loss: 0.006474951282143593 2023-01-23 17:28:31.486914: step: 2056/1545, loss: 0.0006510687526315451 2023-01-23 17:28:32.376819: step: 2058/1545, loss: 0.03401675820350647 2023-01-23 17:28:33.257667: step: 2060/1545, loss: 0.03651777654886246 2023-01-23 17:28:34.109162: step: 2062/1545, loss: 0.023538216948509216 2023-01-23 17:28:34.986497: step: 2064/1545, loss: 0.0007616164512000978 2023-01-23 17:28:35.890237: step: 2066/1545, loss: 0.14655838906764984 2023-01-23 17:28:36.705618: step: 2068/1545, loss: 0.0006437724223360419 2023-01-23 17:28:37.588539: step: 2070/1545, loss: 0.00015029279165901244 2023-01-23 17:28:38.436401: step: 2072/1545, loss: 0.15810956060886383 2023-01-23 17:28:39.350379: step: 2074/1545, loss: 0.0064152623526751995 2023-01-23 17:28:40.262192: step: 2076/1545, loss: 0.008262534625828266 2023-01-23 17:28:41.123462: step: 2078/1545, loss: 0.003382888389751315 2023-01-23 17:28:41.952000: step: 2080/1545, loss: 0.5963402986526489 2023-01-23 17:28:42.817159: step: 2082/1545, loss: 0.0025759537238627672 2023-01-23 17:28:43.715043: step: 2084/1545, loss: 0.0001280383439734578 2023-01-23 17:28:44.559635: step: 2086/1545, loss: 0.014838352799415588 2023-01-23 17:28:45.453298: step: 2088/1545, loss: 0.030113430693745613 2023-01-23 17:28:46.329076: step: 2090/1545, loss: 0.09820278733968735 2023-01-23 17:28:47.231101: step: 2092/1545, loss: 0.006658212281763554 2023-01-23 17:28:48.112586: step: 2094/1545, loss: 0.006712830159813166 2023-01-23 17:28:49.099312: step: 2096/1545, loss: 0.0032136545050889254 2023-01-23 17:28:49.948917: step: 2098/1545, loss: 0.049547940492630005 2023-01-23 17:28:50.828588: step: 2100/1545, loss: 0.0003599606279749423 2023-01-23 17:28:51.675592: step: 2102/1545, loss: 0.025902921333909035 2023-01-23 17:28:52.566748: step: 2104/1545, loss: 0.00043742451816797256 2023-01-23 17:28:53.417344: step: 2106/1545, loss: 0.00516241742298007 2023-01-23 17:28:54.318153: step: 2108/1545, loss: 0.08490456640720367 2023-01-23 17:28:55.186556: step: 2110/1545, loss: 0.005110913421958685 2023-01-23 17:28:56.108728: step: 2112/1545, loss: 0.0003330967447254807 2023-01-23 17:28:57.008828: step: 2114/1545, loss: 0.03910231590270996 2023-01-23 17:28:57.876464: step: 2116/1545, loss: 0.0026362775824964046 2023-01-23 17:28:58.731912: step: 2118/1545, loss: 0.03550552949309349 2023-01-23 17:28:59.592816: step: 2120/1545, loss: 0.018694834783673286 2023-01-23 17:29:00.488003: step: 2122/1545, loss: 0.20350432395935059 2023-01-23 17:29:01.377790: step: 2124/1545, loss: 0.14616085588932037 2023-01-23 17:29:02.250181: step: 2126/1545, loss: 0.0266814474016428 2023-01-23 17:29:03.090920: step: 2128/1545, loss: 6.325619324343279e-05 2023-01-23 17:29:04.001952: step: 2130/1545, loss: 0.0006361226551234722 2023-01-23 17:29:04.886290: step: 2132/1545, loss: 0.0029278090223670006 2023-01-23 17:29:05.731348: step: 2134/1545, loss: 0.03167147934436798 2023-01-23 17:29:06.567011: step: 2136/1545, loss: 0.00035469530848786235 2023-01-23 17:29:07.452628: step: 2138/1545, loss: 0.7418002486228943 2023-01-23 17:29:08.306035: step: 2140/1545, loss: 0.0001467145193601027 2023-01-23 17:29:09.203810: step: 2142/1545, loss: 0.5416448712348938 2023-01-23 17:29:10.058363: step: 2144/1545, loss: 0.038844358175992966 2023-01-23 17:29:10.912579: step: 2146/1545, loss: 0.002537455875426531 2023-01-23 17:29:11.750277: step: 2148/1545, loss: 0.045754462480545044 2023-01-23 17:29:12.631726: step: 2150/1545, loss: 0.00015312270261347294 2023-01-23 17:29:13.512527: step: 2152/1545, loss: 0.008924705907702446 2023-01-23 17:29:14.378310: step: 2154/1545, loss: 0.004350125323981047 2023-01-23 17:29:15.325222: step: 2156/1545, loss: 0.02326495759189129 2023-01-23 17:29:16.184620: step: 2158/1545, loss: 0.0136727849021554 2023-01-23 17:29:17.054446: step: 2160/1545, loss: 0.23882019519805908 2023-01-23 17:29:17.891116: step: 2162/1545, loss: 0.1021193191409111 2023-01-23 17:29:18.764621: step: 2164/1545, loss: 0.0985243171453476 2023-01-23 17:29:19.722413: step: 2166/1545, loss: 0.016948170959949493 2023-01-23 17:29:20.639274: step: 2168/1545, loss: 0.991208016872406 2023-01-23 17:29:21.538479: step: 2170/1545, loss: 0.013225561939179897 2023-01-23 17:29:22.409353: step: 2172/1545, loss: 0.012157905846834183 2023-01-23 17:29:23.290487: step: 2174/1545, loss: 4.47278653155081e-05 2023-01-23 17:29:24.176423: step: 2176/1545, loss: 0.01884501799941063 2023-01-23 17:29:25.020962: step: 2178/1545, loss: 0.05744989961385727 2023-01-23 17:29:25.983679: step: 2180/1545, loss: 0.021487537771463394 2023-01-23 17:29:26.856137: step: 2182/1545, loss: 0.001080137793906033 2023-01-23 17:29:27.725815: step: 2184/1545, loss: 0.00010295445099473 2023-01-23 17:29:28.644889: step: 2186/1545, loss: 0.11592776328325272 2023-01-23 17:29:29.552264: step: 2188/1545, loss: 0.0022198541555553675 2023-01-23 17:29:30.432928: step: 2190/1545, loss: 7.779331644997001e-05 2023-01-23 17:29:31.253130: step: 2192/1545, loss: 0.0003370951453689486 2023-01-23 17:29:32.179650: step: 2194/1545, loss: 0.0016154395416378975 2023-01-23 17:29:33.103493: step: 2196/1545, loss: 0.009249668568372726 2023-01-23 17:29:33.972866: step: 2198/1545, loss: 0.0056442320346832275 2023-01-23 17:29:34.864912: step: 2200/1545, loss: 0.032428380101919174 2023-01-23 17:29:35.756225: step: 2202/1545, loss: 0.5182797908782959 2023-01-23 17:29:36.643270: step: 2204/1545, loss: 0.9546213150024414 2023-01-23 17:29:37.519823: step: 2206/1545, loss: 0.001509238500148058 2023-01-23 17:29:38.436452: step: 2208/1545, loss: 0.397046834230423 2023-01-23 17:29:39.340612: step: 2210/1545, loss: 0.0030201433692127466 2023-01-23 17:29:40.228060: step: 2212/1545, loss: 0.0010540453949943185 2023-01-23 17:29:41.104723: step: 2214/1545, loss: 0.0005596226546913385 2023-01-23 17:29:42.007591: step: 2216/1545, loss: 0.21085608005523682 2023-01-23 17:29:42.887436: step: 2218/1545, loss: 0.049733616411685944 2023-01-23 17:29:43.785752: step: 2220/1545, loss: 0.27271217107772827 2023-01-23 17:29:44.652909: step: 2222/1545, loss: 0.0005631288513541222 2023-01-23 17:29:45.554073: step: 2224/1545, loss: 0.01894919015467167 2023-01-23 17:29:46.399091: step: 2226/1545, loss: 0.0032536094076931477 2023-01-23 17:29:47.282390: step: 2228/1545, loss: 0.3394084870815277 2023-01-23 17:29:48.184626: step: 2230/1545, loss: 0.0005963052390143275 2023-01-23 17:29:49.030996: step: 2232/1545, loss: 0.001779319834895432 2023-01-23 17:29:49.915412: step: 2234/1545, loss: 0.11805974692106247 2023-01-23 17:29:50.784979: step: 2236/1545, loss: 6.68915017740801e-05 2023-01-23 17:29:51.633068: step: 2238/1545, loss: 0.07945244014263153 2023-01-23 17:29:52.505249: step: 2240/1545, loss: 0.00467493012547493 2023-01-23 17:29:53.362779: step: 2242/1545, loss: 0.0006772361812181771 2023-01-23 17:29:54.225497: step: 2244/1545, loss: 0.014936806634068489 2023-01-23 17:29:55.077530: step: 2246/1545, loss: 0.005315790418535471 2023-01-23 17:29:56.053489: step: 2248/1545, loss: 0.1002589538693428 2023-01-23 17:29:56.939771: step: 2250/1545, loss: 0.0003998147149104625 2023-01-23 17:29:57.820297: step: 2252/1545, loss: 0.006413817871361971 2023-01-23 17:29:58.695223: step: 2254/1545, loss: 0.0015545672504231334 2023-01-23 17:29:59.549517: step: 2256/1545, loss: 0.40182819962501526 2023-01-23 17:30:00.485193: step: 2258/1545, loss: 0.08874467760324478 2023-01-23 17:30:01.385534: step: 2260/1545, loss: 0.0010724873282015324 2023-01-23 17:30:02.293999: step: 2262/1545, loss: 0.011959077790379524 2023-01-23 17:30:03.228752: step: 2264/1545, loss: 0.005228268448263407 2023-01-23 17:30:04.155201: step: 2266/1545, loss: 0.03526069596409798 2023-01-23 17:30:05.044032: step: 2268/1545, loss: 0.0024380460381507874 2023-01-23 17:30:05.940861: step: 2270/1545, loss: 0.15224497020244598 2023-01-23 17:30:06.815032: step: 2272/1545, loss: 3.008775472640991 2023-01-23 17:30:07.708517: step: 2274/1545, loss: 0.0006131255649961531 2023-01-23 17:30:08.581605: step: 2276/1545, loss: 0.04257575049996376 2023-01-23 17:30:09.481171: step: 2278/1545, loss: 0.006679750047624111 2023-01-23 17:30:10.343939: step: 2280/1545, loss: 0.01683587208390236 2023-01-23 17:30:11.294926: step: 2282/1545, loss: 0.0009595360606908798 2023-01-23 17:30:12.134032: step: 2284/1545, loss: 0.010152614675462246 2023-01-23 17:30:13.008660: step: 2286/1545, loss: 0.0281244907528162 2023-01-23 17:30:13.872879: step: 2288/1545, loss: 0.0003544265928212553 2023-01-23 17:30:14.774110: step: 2290/1545, loss: 0.006517512258142233 2023-01-23 17:30:15.655273: step: 2292/1545, loss: 0.00886264443397522 2023-01-23 17:30:16.644633: step: 2294/1545, loss: 0.024586506187915802 2023-01-23 17:30:17.532027: step: 2296/1545, loss: 0.004567233845591545 2023-01-23 17:30:18.402390: step: 2298/1545, loss: 0.02187340520322323 2023-01-23 17:30:19.282543: step: 2300/1545, loss: 0.003027647500857711 2023-01-23 17:30:20.140238: step: 2302/1545, loss: 0.0023521175608038902 2023-01-23 17:30:20.988977: step: 2304/1545, loss: 0.3842201232910156 2023-01-23 17:30:21.903913: step: 2306/1545, loss: 0.3471183776855469 2023-01-23 17:30:22.780297: step: 2308/1545, loss: 0.4971817433834076 2023-01-23 17:30:23.628018: step: 2310/1545, loss: 0.0004224661679472774 2023-01-23 17:30:24.501105: step: 2312/1545, loss: 0.03791715204715729 2023-01-23 17:30:25.393568: step: 2314/1545, loss: 0.00740923173725605 2023-01-23 17:30:26.290268: step: 2316/1545, loss: 0.39218035340309143 2023-01-23 17:30:27.185002: step: 2318/1545, loss: 0.0013912573922425508 2023-01-23 17:30:28.071069: step: 2320/1545, loss: 0.06712368130683899 2023-01-23 17:30:28.968284: step: 2322/1545, loss: 0.6097875833511353 2023-01-23 17:30:29.809538: step: 2324/1545, loss: 0.005060927011072636 2023-01-23 17:30:30.690697: step: 2326/1545, loss: 0.0408206582069397 2023-01-23 17:30:31.555769: step: 2328/1545, loss: 0.0005271473783068359 2023-01-23 17:30:32.424430: step: 2330/1545, loss: 0.022538354620337486 2023-01-23 17:30:33.283338: step: 2332/1545, loss: 0.8196367621421814 2023-01-23 17:30:34.176504: step: 2334/1545, loss: 0.13806144893169403 2023-01-23 17:30:35.060904: step: 2336/1545, loss: 0.1472809910774231 2023-01-23 17:30:35.923498: step: 2338/1545, loss: 0.10143284499645233 2023-01-23 17:30:36.805993: step: 2340/1545, loss: 0.0218342337757349 2023-01-23 17:30:37.629588: step: 2342/1545, loss: 0.11507237702608109 2023-01-23 17:30:38.552007: step: 2344/1545, loss: 0.04499567672610283 2023-01-23 17:30:39.412588: step: 2346/1545, loss: 0.00018193588766735047 2023-01-23 17:30:40.281412: step: 2348/1545, loss: 0.03188787028193474 2023-01-23 17:30:41.125716: step: 2350/1545, loss: 0.0002497188397683203 2023-01-23 17:30:42.044678: step: 2352/1545, loss: 0.226348876953125 2023-01-23 17:30:42.927179: step: 2354/1545, loss: 0.0054149082861840725 2023-01-23 17:30:43.785720: step: 2356/1545, loss: 0.5410235524177551 2023-01-23 17:30:44.747154: step: 2358/1545, loss: 0.03213198110461235 2023-01-23 17:30:45.598021: step: 2360/1545, loss: 0.006380978040397167 2023-01-23 17:30:46.456201: step: 2362/1545, loss: 0.002507310127839446 2023-01-23 17:30:47.317314: step: 2364/1545, loss: 0.07341811805963516 2023-01-23 17:30:48.206612: step: 2366/1545, loss: 0.059482116252183914 2023-01-23 17:30:49.076917: step: 2368/1545, loss: 0.06784170866012573 2023-01-23 17:30:50.012244: step: 2370/1545, loss: 0.03875169903039932 2023-01-23 17:30:50.877273: step: 2372/1545, loss: 0.0045157610438764095 2023-01-23 17:30:51.735154: step: 2374/1545, loss: 0.023212343454360962 2023-01-23 17:30:52.616652: step: 2376/1545, loss: 0.007881134748458862 2023-01-23 17:30:53.489285: step: 2378/1545, loss: 0.001077298424206674 2023-01-23 17:30:54.360024: step: 2380/1545, loss: 0.5245825052261353 2023-01-23 17:30:55.225306: step: 2382/1545, loss: 0.10578202456235886 2023-01-23 17:30:56.127862: step: 2384/1545, loss: 0.0037853564135730267 2023-01-23 17:30:56.952991: step: 2386/1545, loss: 0.003599069081246853 2023-01-23 17:30:57.815512: step: 2388/1545, loss: 0.06556868553161621 2023-01-23 17:30:58.697316: step: 2390/1545, loss: 0.10080551356077194 2023-01-23 17:30:59.571900: step: 2392/1545, loss: 0.008832283318042755 2023-01-23 17:31:00.434185: step: 2394/1545, loss: 0.05862399563193321 2023-01-23 17:31:01.289106: step: 2396/1545, loss: 0.4314901530742645 2023-01-23 17:31:02.119358: step: 2398/1545, loss: 0.0025374125689268112 2023-01-23 17:31:02.982571: step: 2400/1545, loss: 0.1308678239583969 2023-01-23 17:31:03.858509: step: 2402/1545, loss: 0.0027171659749001265 2023-01-23 17:31:04.746708: step: 2404/1545, loss: 0.0019773272797465324 2023-01-23 17:31:05.685738: step: 2406/1545, loss: 0.006342758424580097 2023-01-23 17:31:06.558641: step: 2408/1545, loss: 0.0007940831128507853 2023-01-23 17:31:07.414102: step: 2410/1545, loss: 0.0034361791331321 2023-01-23 17:31:08.293186: step: 2412/1545, loss: 0.00037003945908509195 2023-01-23 17:31:09.183387: step: 2414/1545, loss: 0.007803448475897312 2023-01-23 17:31:10.071573: step: 2416/1545, loss: 0.0878140777349472 2023-01-23 17:31:10.967773: step: 2418/1545, loss: 0.34891775250434875 2023-01-23 17:31:11.835198: step: 2420/1545, loss: 0.0002922748099081218 2023-01-23 17:31:12.739518: step: 2422/1545, loss: 0.034594643861055374 2023-01-23 17:31:13.571910: step: 2424/1545, loss: 0.14421339333057404 2023-01-23 17:31:14.479181: step: 2426/1545, loss: 0.0005325180245563388 2023-01-23 17:31:15.330437: step: 2428/1545, loss: 4.479401104617864e-05 2023-01-23 17:31:16.179828: step: 2430/1545, loss: 0.21059782803058624 2023-01-23 17:31:17.099200: step: 2432/1545, loss: 0.0009030380751937628 2023-01-23 17:31:17.965623: step: 2434/1545, loss: 0.0010075753089040518 2023-01-23 17:31:18.835996: step: 2436/1545, loss: 0.002824421040713787 2023-01-23 17:31:19.712956: step: 2438/1545, loss: 0.0003555561706889421 2023-01-23 17:31:20.569205: step: 2440/1545, loss: 0.07168497890233994 2023-01-23 17:31:21.460414: step: 2442/1545, loss: 7.476234895875677e-05 2023-01-23 17:31:22.363968: step: 2444/1545, loss: 0.10043971240520477 2023-01-23 17:31:23.232748: step: 2446/1545, loss: 0.02278638444840908 2023-01-23 17:31:24.091115: step: 2448/1545, loss: 0.0008900589891709387 2023-01-23 17:31:24.933854: step: 2450/1545, loss: 0.007815524004399776 2023-01-23 17:31:25.789231: step: 2452/1545, loss: 0.31340262293815613 2023-01-23 17:31:26.656432: step: 2454/1545, loss: 0.02162560075521469 2023-01-23 17:31:27.541824: step: 2456/1545, loss: 0.0832078829407692 2023-01-23 17:31:28.472111: step: 2458/1545, loss: 0.2557397484779358 2023-01-23 17:31:29.426142: step: 2460/1545, loss: 0.15886901319026947 2023-01-23 17:31:30.306897: step: 2462/1545, loss: 0.009460843168199062 2023-01-23 17:31:31.148587: step: 2464/1545, loss: 0.12995590269565582 2023-01-23 17:31:32.022917: step: 2466/1545, loss: 0.0021140219178050756 2023-01-23 17:31:32.892908: step: 2468/1545, loss: 0.00016289572522509843 2023-01-23 17:31:33.749922: step: 2470/1545, loss: 0.002917050151154399 2023-01-23 17:31:34.628921: step: 2472/1545, loss: 0.15673984587192535 2023-01-23 17:31:35.476871: step: 2474/1545, loss: 0.001034837681800127 2023-01-23 17:31:36.310248: step: 2476/1545, loss: 0.04452185332775116 2023-01-23 17:31:37.174913: step: 2478/1545, loss: 0.3172948956489563 2023-01-23 17:31:38.126523: step: 2480/1545, loss: 0.008453241549432278 2023-01-23 17:31:39.001374: step: 2482/1545, loss: 0.13722068071365356 2023-01-23 17:31:39.842529: step: 2484/1545, loss: 0.6115537285804749 2023-01-23 17:31:40.714567: step: 2486/1545, loss: 0.01487900223582983 2023-01-23 17:31:41.588116: step: 2488/1545, loss: 0.0007631837506778538 2023-01-23 17:31:42.532565: step: 2490/1545, loss: 0.0009569430258125067 2023-01-23 17:31:43.408922: step: 2492/1545, loss: 0.10573916882276535 2023-01-23 17:31:44.341826: step: 2494/1545, loss: 0.011116674169898033 2023-01-23 17:31:45.213079: step: 2496/1545, loss: 0.001123884809203446 2023-01-23 17:31:46.073004: step: 2498/1545, loss: 0.03640454635024071 2023-01-23 17:31:46.966605: step: 2500/1545, loss: 0.0013851032126694918 2023-01-23 17:31:47.828759: step: 2502/1545, loss: 0.2386511266231537 2023-01-23 17:31:48.733311: step: 2504/1545, loss: 0.07939494401216507 2023-01-23 17:31:49.631964: step: 2506/1545, loss: 0.027740467339754105 2023-01-23 17:31:50.520180: step: 2508/1545, loss: 0.004512956365942955 2023-01-23 17:31:51.391199: step: 2510/1545, loss: 0.008335086517035961 2023-01-23 17:31:52.286855: step: 2512/1545, loss: 0.0013730667997151613 2023-01-23 17:31:53.136963: step: 2514/1545, loss: 0.0024396958760917187 2023-01-23 17:31:53.988029: step: 2516/1545, loss: 0.0041834148578345776 2023-01-23 17:31:54.882418: step: 2518/1545, loss: 0.05353624001145363 2023-01-23 17:31:55.808467: step: 2520/1545, loss: 0.0007180739776231349 2023-01-23 17:31:56.666794: step: 2522/1545, loss: 0.0008240218739956617 2023-01-23 17:31:57.576148: step: 2524/1545, loss: 0.012982623651623726 2023-01-23 17:31:58.499773: step: 2526/1545, loss: 0.012615394778549671 2023-01-23 17:31:59.355149: step: 2528/1545, loss: 0.0061849672347307205 2023-01-23 17:32:00.239009: step: 2530/1545, loss: 0.09231635928153992 2023-01-23 17:32:01.108310: step: 2532/1545, loss: 0.011686770245432854 2023-01-23 17:32:01.993743: step: 2534/1545, loss: 0.041956111788749695 2023-01-23 17:32:02.940044: step: 2536/1545, loss: 0.019009724259376526 2023-01-23 17:32:03.842299: step: 2538/1545, loss: 0.005522361025214195 2023-01-23 17:32:04.681614: step: 2540/1545, loss: 0.0027011558413505554 2023-01-23 17:32:05.569681: step: 2542/1545, loss: 0.12709994614124298 2023-01-23 17:32:06.426472: step: 2544/1545, loss: 0.29378125071525574 2023-01-23 17:32:07.300759: step: 2546/1545, loss: 0.0008726930827833712 2023-01-23 17:32:08.147229: step: 2548/1545, loss: 0.07754797488451004 2023-01-23 17:32:09.021804: step: 2550/1545, loss: 0.00633485522121191 2023-01-23 17:32:09.877088: step: 2552/1545, loss: 0.1012447401881218 2023-01-23 17:32:10.764070: step: 2554/1545, loss: 0.2399480938911438 2023-01-23 17:32:11.704332: step: 2556/1545, loss: 0.010852531529963017 2023-01-23 17:32:12.571580: step: 2558/1545, loss: 0.002354718279093504 2023-01-23 17:32:13.446663: step: 2560/1545, loss: 0.0011946042068302631 2023-01-23 17:32:14.289557: step: 2562/1545, loss: 0.015504025854170322 2023-01-23 17:32:15.249797: step: 2564/1545, loss: 0.0007124643307179213 2023-01-23 17:32:16.197196: step: 2566/1545, loss: 0.0018027396872639656 2023-01-23 17:32:17.065203: step: 2568/1545, loss: 0.026177100837230682 2023-01-23 17:32:17.930964: step: 2570/1545, loss: 0.18008726835250854 2023-01-23 17:32:18.801882: step: 2572/1545, loss: 0.1301817148923874 2023-01-23 17:32:19.656848: step: 2574/1545, loss: 0.0007731780060566962 2023-01-23 17:32:20.512955: step: 2576/1545, loss: 0.005252272821962833 2023-01-23 17:32:21.362946: step: 2578/1545, loss: 0.01148971077054739 2023-01-23 17:32:22.306020: step: 2580/1545, loss: 0.0028857109136879444 2023-01-23 17:32:23.226799: step: 2582/1545, loss: 0.06206041947007179 2023-01-23 17:32:24.059565: step: 2584/1545, loss: 0.00012060436711180955 2023-01-23 17:32:24.950424: step: 2586/1545, loss: 0.011342623271048069 2023-01-23 17:32:25.880377: step: 2588/1545, loss: 0.00773082859814167 2023-01-23 17:32:26.715485: step: 2590/1545, loss: 0.022940367460250854 2023-01-23 17:32:27.597107: step: 2592/1545, loss: 0.008628922514617443 2023-01-23 17:32:28.541650: step: 2594/1545, loss: 0.037219393998384476 2023-01-23 17:32:29.461497: step: 2596/1545, loss: 0.177646666765213 2023-01-23 17:32:30.346764: step: 2598/1545, loss: 0.016623638570308685 2023-01-23 17:32:31.181598: step: 2600/1545, loss: 0.0005180510343052447 2023-01-23 17:32:32.089488: step: 2602/1545, loss: 0.005695568863302469 2023-01-23 17:32:32.956737: step: 2604/1545, loss: 0.31570640206336975 2023-01-23 17:32:33.888120: step: 2606/1545, loss: 5.636132846120745e-05 2023-01-23 17:32:34.740172: step: 2608/1545, loss: 0.009012870490550995 2023-01-23 17:32:35.601835: step: 2610/1545, loss: 0.11130231618881226 2023-01-23 17:32:36.454314: step: 2612/1545, loss: 0.002234895946457982 2023-01-23 17:32:37.395672: step: 2614/1545, loss: 0.007907632738351822 2023-01-23 17:32:38.217575: step: 2616/1545, loss: 0.0018659435445442796 2023-01-23 17:32:39.153530: step: 2618/1545, loss: 0.005661494564265013 2023-01-23 17:32:40.035577: step: 2620/1545, loss: 0.1228988915681839 2023-01-23 17:32:40.909216: step: 2622/1545, loss: 0.021016715094447136 2023-01-23 17:32:41.831244: step: 2624/1545, loss: 0.14001280069351196 2023-01-23 17:32:42.698218: step: 2626/1545, loss: 0.0016843172488734126 2023-01-23 17:32:43.611114: step: 2628/1545, loss: 0.008410618640482426 2023-01-23 17:32:44.500680: step: 2630/1545, loss: 0.23687103390693665 2023-01-23 17:32:45.356779: step: 2632/1545, loss: 0.0020283109042793512 2023-01-23 17:32:46.227195: step: 2634/1545, loss: 0.0209480132907629 2023-01-23 17:32:47.078625: step: 2636/1545, loss: 0.005901604890823364 2023-01-23 17:32:47.942691: step: 2638/1545, loss: 0.2695169448852539 2023-01-23 17:32:48.823393: step: 2640/1545, loss: 0.00034129113191738725 2023-01-23 17:32:49.779328: step: 2642/1545, loss: 0.0027154197450727224 2023-01-23 17:32:50.660680: step: 2644/1545, loss: 0.00174202979542315 2023-01-23 17:32:51.582194: step: 2646/1545, loss: 0.015241216868162155 2023-01-23 17:32:52.488212: step: 2648/1545, loss: 0.0303626898676157 2023-01-23 17:32:53.333047: step: 2650/1545, loss: 0.012490812689065933 2023-01-23 17:32:54.209006: step: 2652/1545, loss: 0.0004649117181543261 2023-01-23 17:32:55.048292: step: 2654/1545, loss: 0.5550377368927002 2023-01-23 17:32:55.970580: step: 2656/1545, loss: 0.05717143788933754 2023-01-23 17:32:56.865216: step: 2658/1545, loss: 0.212214395403862 2023-01-23 17:32:57.727867: step: 2660/1545, loss: 0.529736340045929 2023-01-23 17:32:58.573763: step: 2662/1545, loss: 0.11953511089086533 2023-01-23 17:32:59.419408: step: 2664/1545, loss: 0.01510544866323471 2023-01-23 17:33:00.316898: step: 2666/1545, loss: 0.020312758162617683 2023-01-23 17:33:01.198691: step: 2668/1545, loss: 0.0001343463227385655 2023-01-23 17:33:02.071936: step: 2670/1545, loss: 0.0020271423272788525 2023-01-23 17:33:02.970758: step: 2672/1545, loss: 0.008470815606415272 2023-01-23 17:33:03.852139: step: 2674/1545, loss: 0.0011009081499651074 2023-01-23 17:33:04.710589: step: 2676/1545, loss: 0.005301954224705696 2023-01-23 17:33:05.568085: step: 2678/1545, loss: 0.06170465424656868 2023-01-23 17:33:06.389787: step: 2680/1545, loss: 0.0010565361008048058 2023-01-23 17:33:07.258081: step: 2682/1545, loss: 0.0006025086622685194 2023-01-23 17:33:08.179742: step: 2684/1545, loss: 0.001125906128436327 2023-01-23 17:33:09.035704: step: 2686/1545, loss: 0.006094536278396845 2023-01-23 17:33:09.906976: step: 2688/1545, loss: 0.0018914741231128573 2023-01-23 17:33:10.798275: step: 2690/1545, loss: 0.028934258967638016 2023-01-23 17:33:11.735813: step: 2692/1545, loss: 0.06258492916822433 2023-01-23 17:33:12.613867: step: 2694/1545, loss: 0.3023216724395752 2023-01-23 17:33:13.569543: step: 2696/1545, loss: 0.011243586428463459 2023-01-23 17:33:14.434746: step: 2698/1545, loss: 1.4833534955978394 2023-01-23 17:33:15.314878: step: 2700/1545, loss: 0.0006985307554714382 2023-01-23 17:33:16.184274: step: 2702/1545, loss: 0.03202689439058304 2023-01-23 17:33:17.041755: step: 2704/1545, loss: 0.0019500806229189038 2023-01-23 17:33:17.923267: step: 2706/1545, loss: 0.0009565890650264919 2023-01-23 17:33:18.812889: step: 2708/1545, loss: 0.13729150593280792 2023-01-23 17:33:19.706542: step: 2710/1545, loss: 0.00207914924249053 2023-01-23 17:33:20.609903: step: 2712/1545, loss: 0.027255374938249588 2023-01-23 17:33:21.497627: step: 2714/1545, loss: 0.00342668779194355 2023-01-23 17:33:22.365887: step: 2716/1545, loss: 0.01674600876867771 2023-01-23 17:33:23.243386: step: 2718/1545, loss: 0.0017543520079925656 2023-01-23 17:33:24.104649: step: 2720/1545, loss: 0.0003148430259898305 2023-01-23 17:33:25.063360: step: 2722/1545, loss: 0.00829909835010767 2023-01-23 17:33:25.921605: step: 2724/1545, loss: 0.3403225839138031 2023-01-23 17:33:26.914012: step: 2726/1545, loss: 0.19347266852855682 2023-01-23 17:33:27.791107: step: 2728/1545, loss: 0.04236822575330734 2023-01-23 17:33:28.622213: step: 2730/1545, loss: 0.004252979531884193 2023-01-23 17:33:29.468954: step: 2732/1545, loss: 0.09235196560621262 2023-01-23 17:33:30.397058: step: 2734/1545, loss: 0.02289493754506111 2023-01-23 17:33:31.339974: step: 2736/1545, loss: 0.05690578743815422 2023-01-23 17:33:32.184748: step: 2738/1545, loss: 0.07981309294700623 2023-01-23 17:33:33.041505: step: 2740/1545, loss: 0.07692699879407883 2023-01-23 17:33:33.918514: step: 2742/1545, loss: 0.0004883590154349804 2023-01-23 17:33:34.783072: step: 2744/1545, loss: 0.07102673500776291 2023-01-23 17:33:35.704012: step: 2746/1545, loss: 0.02794509008526802 2023-01-23 17:33:36.569898: step: 2748/1545, loss: 0.0005337129114195704 2023-01-23 17:33:37.457041: step: 2750/1545, loss: 0.028232064098119736 2023-01-23 17:33:38.300661: step: 2752/1545, loss: 0.0047210948541760445 2023-01-23 17:33:39.170667: step: 2754/1545, loss: 0.19933807849884033 2023-01-23 17:33:40.083779: step: 2756/1545, loss: 0.21522581577301025 2023-01-23 17:33:40.971003: step: 2758/1545, loss: 0.00180918094702065 2023-01-23 17:33:41.898113: step: 2760/1545, loss: 0.08673176914453506 2023-01-23 17:33:42.786861: step: 2762/1545, loss: 0.0003607117978390306 2023-01-23 17:33:43.643484: step: 2764/1545, loss: 0.009831883013248444 2023-01-23 17:33:44.529540: step: 2766/1545, loss: 0.0010224772850051522 2023-01-23 17:33:45.407770: step: 2768/1545, loss: 0.07818154245615005 2023-01-23 17:33:46.248247: step: 2770/1545, loss: 0.0018661217764019966 2023-01-23 17:33:47.082122: step: 2772/1545, loss: 0.0030887038446962833 2023-01-23 17:33:47.993090: step: 2774/1545, loss: 0.12546879053115845 2023-01-23 17:33:48.872743: step: 2776/1545, loss: 0.004512237384915352 2023-01-23 17:33:49.741276: step: 2778/1545, loss: 0.15782612562179565 2023-01-23 17:33:50.667054: step: 2780/1545, loss: 0.020486794412136078 2023-01-23 17:33:51.536143: step: 2782/1545, loss: 0.003033561399206519 2023-01-23 17:33:52.378893: step: 2784/1545, loss: 0.011774380691349506 2023-01-23 17:33:53.287329: step: 2786/1545, loss: 0.00524320499971509 2023-01-23 17:33:54.194143: step: 2788/1545, loss: 0.048360489308834076 2023-01-23 17:33:55.073294: step: 2790/1545, loss: 0.001280701020732522 2023-01-23 17:33:55.999095: step: 2792/1545, loss: 0.036671560257673264 2023-01-23 17:33:56.868291: step: 2794/1545, loss: 0.00034074881114065647 2023-01-23 17:33:57.698397: step: 2796/1545, loss: 0.002086784690618515 2023-01-23 17:33:58.554686: step: 2798/1545, loss: 0.004960303660482168 2023-01-23 17:33:59.422121: step: 2800/1545, loss: 8.230151433963329e-05 2023-01-23 17:34:00.301035: step: 2802/1545, loss: 0.0006353585049510002 2023-01-23 17:34:01.125224: step: 2804/1545, loss: 0.05677022039890289 2023-01-23 17:34:02.044728: step: 2806/1545, loss: 0.07131904363632202 2023-01-23 17:34:02.932838: step: 2808/1545, loss: 0.004284736234694719 2023-01-23 17:34:03.800574: step: 2810/1545, loss: 0.000701491255313158 2023-01-23 17:34:04.684179: step: 2812/1545, loss: 0.001049344427883625 2023-01-23 17:34:05.566512: step: 2814/1545, loss: 0.0170015636831522 2023-01-23 17:34:06.463452: step: 2816/1545, loss: 0.06573554873466492 2023-01-23 17:34:07.347380: step: 2818/1545, loss: 0.4897845387458801 2023-01-23 17:34:08.245412: step: 2820/1545, loss: 0.10093804448843002 2023-01-23 17:34:09.111198: step: 2822/1545, loss: 0.00013867787492927164 2023-01-23 17:34:09.989450: step: 2824/1545, loss: 0.07751597464084625 2023-01-23 17:34:10.841306: step: 2826/1545, loss: 0.0010223452700302005 2023-01-23 17:34:11.709283: step: 2828/1545, loss: 0.06435590237379074 2023-01-23 17:34:12.607499: step: 2830/1545, loss: 0.09792978316545486 2023-01-23 17:34:13.576416: step: 2832/1545, loss: 0.00020712221157737076 2023-01-23 17:34:14.439028: step: 2834/1545, loss: 0.0002967976906802505 2023-01-23 17:34:15.350332: step: 2836/1545, loss: 0.13200458884239197 2023-01-23 17:34:16.207509: step: 2838/1545, loss: 0.002964131999760866 2023-01-23 17:34:17.123625: step: 2840/1545, loss: 0.0037715688813477755 2023-01-23 17:34:18.002861: step: 2842/1545, loss: 0.0015086341882124543 2023-01-23 17:34:18.862643: step: 2844/1545, loss: 0.004786865785717964 2023-01-23 17:34:19.793418: step: 2846/1545, loss: 0.047212086617946625 2023-01-23 17:34:20.672128: step: 2848/1545, loss: 0.0028414311818778515 2023-01-23 17:34:21.544704: step: 2850/1545, loss: 0.08828449249267578 2023-01-23 17:34:22.420075: step: 2852/1545, loss: 0.04284149035811424 2023-01-23 17:34:23.325711: step: 2854/1545, loss: 6.542746996274218e-05 2023-01-23 17:34:24.196085: step: 2856/1545, loss: 0.0026028717402368784 2023-01-23 17:34:25.047114: step: 2858/1545, loss: 2.2349498976836912e-05 2023-01-23 17:34:25.911957: step: 2860/1545, loss: 0.0003984454378951341 2023-01-23 17:34:26.833952: step: 2862/1545, loss: 0.00022152405290398747 2023-01-23 17:34:27.772411: step: 2864/1545, loss: 0.08637095987796783 2023-01-23 17:34:28.600716: step: 2866/1545, loss: 0.004130059387534857 2023-01-23 17:34:29.442980: step: 2868/1545, loss: 0.0016020034672692418 2023-01-23 17:34:30.297368: step: 2870/1545, loss: 0.004207175690680742 2023-01-23 17:34:31.167138: step: 2872/1545, loss: 0.00027380805113352835 2023-01-23 17:34:32.071584: step: 2874/1545, loss: 0.00025524190277792513 2023-01-23 17:34:32.946644: step: 2876/1545, loss: 8.331661956617609e-05 2023-01-23 17:34:33.807518: step: 2878/1545, loss: 0.0121989157050848 2023-01-23 17:34:34.680994: step: 2880/1545, loss: 0.06862589716911316 2023-01-23 17:34:35.563572: step: 2882/1545, loss: 0.11576897650957108 2023-01-23 17:34:36.453912: step: 2884/1545, loss: 0.037033963948488235 2023-01-23 17:34:37.301580: step: 2886/1545, loss: 1.6676597169862362e-06 2023-01-23 17:34:38.198037: step: 2888/1545, loss: 0.01870940439403057 2023-01-23 17:34:39.109231: step: 2890/1545, loss: 0.0001263080193893984 2023-01-23 17:34:39.962811: step: 2892/1545, loss: 0.0001055372049449943 2023-01-23 17:34:40.800672: step: 2894/1545, loss: 0.01098005659878254 2023-01-23 17:34:41.674435: step: 2896/1545, loss: 0.013304272666573524 2023-01-23 17:34:42.606171: step: 2898/1545, loss: 0.0005854244227521122 2023-01-23 17:34:43.530595: step: 2900/1545, loss: 0.04316644370555878 2023-01-23 17:34:44.423813: step: 2902/1545, loss: 0.0001449411502107978 2023-01-23 17:34:45.288540: step: 2904/1545, loss: 0.02887660264968872 2023-01-23 17:34:46.135946: step: 2906/1545, loss: 0.00027101728483103216 2023-01-23 17:34:47.011269: step: 2908/1545, loss: 0.08308012783527374 2023-01-23 17:34:47.915911: step: 2910/1545, loss: 0.013756959699094296 2023-01-23 17:34:48.830407: step: 2912/1545, loss: 0.00014338342589326203 2023-01-23 17:34:49.713894: step: 2914/1545, loss: 0.00015832162171136588 2023-01-23 17:34:50.595060: step: 2916/1545, loss: 0.08433505892753601 2023-01-23 17:34:51.517876: step: 2918/1545, loss: 0.00013208520249463618 2023-01-23 17:34:52.389634: step: 2920/1545, loss: 0.06782674044370651 2023-01-23 17:34:53.270986: step: 2922/1545, loss: 0.24915115535259247 2023-01-23 17:34:54.118860: step: 2924/1545, loss: 0.0049176402390003204 2023-01-23 17:34:55.006862: step: 2926/1545, loss: 0.03538665920495987 2023-01-23 17:34:55.862271: step: 2928/1545, loss: 0.0021491888910531998 2023-01-23 17:34:56.786141: step: 2930/1545, loss: 0.03096548467874527 2023-01-23 17:34:57.684941: step: 2932/1545, loss: 0.001272468245588243 2023-01-23 17:34:58.532391: step: 2934/1545, loss: 0.010413195937871933 2023-01-23 17:34:59.438491: step: 2936/1545, loss: 0.00019950282876379788 2023-01-23 17:35:00.291436: step: 2938/1545, loss: 0.04561576992273331 2023-01-23 17:35:01.196312: step: 2940/1545, loss: 0.0009600433404557407 2023-01-23 17:35:02.065725: step: 2942/1545, loss: 9.222218068316579e-05 2023-01-23 17:35:02.942147: step: 2944/1545, loss: 0.29009196162223816 2023-01-23 17:35:03.787146: step: 2946/1545, loss: 0.08250055462121964 2023-01-23 17:35:04.685804: step: 2948/1545, loss: 0.0013684842269867659 2023-01-23 17:35:05.534667: step: 2950/1545, loss: 0.0003795397060457617 2023-01-23 17:35:06.349257: step: 2952/1545, loss: 0.005842546001076698 2023-01-23 17:35:07.261196: step: 2954/1545, loss: 0.03491179272532463 2023-01-23 17:35:08.170544: step: 2956/1545, loss: 0.00013326117186807096 2023-01-23 17:35:09.040785: step: 2958/1545, loss: 0.001843542791903019 2023-01-23 17:35:09.908745: step: 2960/1545, loss: 0.0013643186539411545 2023-01-23 17:35:10.783460: step: 2962/1545, loss: 0.00041557932854630053 2023-01-23 17:35:11.646579: step: 2964/1545, loss: 0.022429311648011208 2023-01-23 17:35:12.528610: step: 2966/1545, loss: 0.3968519866466522 2023-01-23 17:35:13.412019: step: 2968/1545, loss: 0.15947185456752777 2023-01-23 17:35:14.273355: step: 2970/1545, loss: 8.045580034377053e-05 2023-01-23 17:35:15.169707: step: 2972/1545, loss: 0.14394646883010864 2023-01-23 17:35:16.051108: step: 2974/1545, loss: 0.11635208874940872 2023-01-23 17:35:16.871720: step: 2976/1545, loss: 0.011394396424293518 2023-01-23 17:35:17.759844: step: 2978/1545, loss: 0.3044854700565338 2023-01-23 17:35:18.658829: step: 2980/1545, loss: 0.030414307489991188 2023-01-23 17:35:19.526139: step: 2982/1545, loss: 0.3997637629508972 2023-01-23 17:35:20.385595: step: 2984/1545, loss: 0.008030461147427559 2023-01-23 17:35:21.279535: step: 2986/1545, loss: 0.0035816619638353586 2023-01-23 17:35:22.200451: step: 2988/1545, loss: 0.1092352420091629 2023-01-23 17:35:23.087347: step: 2990/1545, loss: 0.19569508731365204 2023-01-23 17:35:23.977523: step: 2992/1545, loss: 0.0020939090754836798 2023-01-23 17:35:24.891644: step: 2994/1545, loss: 0.0015426375903189182 2023-01-23 17:35:25.770791: step: 2996/1545, loss: 0.00062441366026178 2023-01-23 17:35:26.683174: step: 2998/1545, loss: 0.20606629550457 2023-01-23 17:35:27.565842: step: 3000/1545, loss: 0.005214821547269821 2023-01-23 17:35:28.442648: step: 3002/1545, loss: 0.012505018152296543 2023-01-23 17:35:29.339775: step: 3004/1545, loss: 0.13465258479118347 2023-01-23 17:35:30.210957: step: 3006/1545, loss: 0.33377689123153687 2023-01-23 17:35:31.097778: step: 3008/1545, loss: 0.04599512740969658 2023-01-23 17:35:31.962850: step: 3010/1545, loss: 0.000518720829859376 2023-01-23 17:35:32.834089: step: 3012/1545, loss: 1.0693838596343994 2023-01-23 17:35:33.720140: step: 3014/1545, loss: 0.004454547539353371 2023-01-23 17:35:34.575373: step: 3016/1545, loss: 0.5790232419967651 2023-01-23 17:35:35.452341: step: 3018/1545, loss: 0.005047997459769249 2023-01-23 17:35:36.318768: step: 3020/1545, loss: 0.002079525263980031 2023-01-23 17:35:37.176766: step: 3022/1545, loss: 0.02369351126253605 2023-01-23 17:35:38.059123: step: 3024/1545, loss: 0.002819389570504427 2023-01-23 17:35:38.932399: step: 3026/1545, loss: 0.08965933322906494 2023-01-23 17:35:39.758559: step: 3028/1545, loss: 0.023850400000810623 2023-01-23 17:35:40.602156: step: 3030/1545, loss: 0.0039897458627820015 2023-01-23 17:35:41.473446: step: 3032/1545, loss: 0.012050515040755272 2023-01-23 17:35:42.313221: step: 3034/1545, loss: 0.034381963312625885 2023-01-23 17:35:43.197151: step: 3036/1545, loss: 0.30222809314727783 2023-01-23 17:35:44.162963: step: 3038/1545, loss: 0.07245956361293793 2023-01-23 17:35:45.058287: step: 3040/1545, loss: 0.003957916051149368 2023-01-23 17:35:45.887689: step: 3042/1545, loss: 0.007607529405504465 2023-01-23 17:35:46.747221: step: 3044/1545, loss: 0.01472508441656828 2023-01-23 17:35:47.620048: step: 3046/1545, loss: 0.00190858100540936 2023-01-23 17:35:48.511981: step: 3048/1545, loss: 0.11851951479911804 2023-01-23 17:35:49.410935: step: 3050/1545, loss: 0.17614826560020447 2023-01-23 17:35:50.275479: step: 3052/1545, loss: 0.3613770306110382 2023-01-23 17:35:51.155774: step: 3054/1545, loss: 0.1085275262594223 2023-01-23 17:35:52.070588: step: 3056/1545, loss: 0.1213616132736206 2023-01-23 17:35:52.955986: step: 3058/1545, loss: 0.005069228354841471 2023-01-23 17:35:53.816379: step: 3060/1545, loss: 0.0052085574716329575 2023-01-23 17:35:54.713711: step: 3062/1545, loss: 0.19458405673503876 2023-01-23 17:35:55.706965: step: 3064/1545, loss: 0.018632693216204643 2023-01-23 17:35:56.574165: step: 3066/1545, loss: 0.004437214229255915 2023-01-23 17:35:57.463324: step: 3068/1545, loss: 0.01064549945294857 2023-01-23 17:35:58.352722: step: 3070/1545, loss: 0.029191765934228897 2023-01-23 17:35:59.189084: step: 3072/1545, loss: 0.1535898894071579 2023-01-23 17:36:00.069756: step: 3074/1545, loss: 0.05662386491894722 2023-01-23 17:36:00.926507: step: 3076/1545, loss: 0.007192719727754593 2023-01-23 17:36:01.825399: step: 3078/1545, loss: 0.07440754026174545 2023-01-23 17:36:02.641268: step: 3080/1545, loss: 0.00771200330927968 2023-01-23 17:36:03.510243: step: 3082/1545, loss: 0.05432051047682762 2023-01-23 17:36:04.373705: step: 3084/1545, loss: 0.0009592380374670029 2023-01-23 17:36:05.227822: step: 3086/1545, loss: 0.006302716210484505 2023-01-23 17:36:06.096137: step: 3088/1545, loss: 0.2711571455001831 2023-01-23 17:36:06.995709: step: 3090/1545, loss: 0.07705379277467728 ================================================== Loss: 0.074 -------------------- Dev Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6559451265403835, 'r': 0.6613377994790564, 'f1': 0.6586304247882229}, 'combined': 0.43355887674908195, 'epoch': 26} Test Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6980547354393568, 'r': 0.7185779178100443, 'f1': 0.7081676638737557}, 'combined': 0.49271002093834315, 'epoch': 26} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6562787457968984, 'r': 0.6646672711191144, 'f1': 0.6604463732449922}, 'combined': 0.44188424011706984, 'epoch': 26} Test Korean: {'event': {'p': 0.6301587301587301, 'r': 0.7615089514066496, 'f1': 0.6896352055587724}, 'argument': {'p': 0.6927764210970498, 'r': 0.7120863404327065, 'f1': 0.7022986727897791}, 'combined': 0.48432988957303236, 'epoch': 26} Dev Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6530729561342159, 'r': 0.668477822147389, 'f1': 0.6606856045102064}, 'combined': 0.4344746306965817, 'epoch': 26} Test Russian: {'event': {'p': 0.6292974588938715, 'r': 0.8075447570332481, 'f1': 0.7073648837860543}, 'argument': {'p': 0.7008390992866921, 'r': 0.7289251605689677, 'f1': 0.7146062708717255}, 'combined': 0.5054873817479637, 'epoch': 26} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6657901327322815, 'r': 0.6657901327322815, 'f1': 0.6657901327322815}, 'combined': 0.47412327633965495, 'epoch': 26} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6436097427476738, 'r': 0.5113611654707546, 'f1': 0.5699139706773294}, 'combined': 0.34994717497730754, 'epoch': 26} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5765709872358072, 'r': 0.5868668977221609, 'f1': 0.5816733853529382}, 'combined': 0.32396998677885164, 'epoch': 26} New best chinese model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6559451265403835, 'r': 0.6613377994790564, 'f1': 0.6586304247882229}, 'combined': 0.43355887674908195, 'epoch': 26} Test for Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6980547354393568, 'r': 0.7185779178100443, 'f1': 0.7081676638737557}, 'combined': 0.49271002093834315, 'epoch': 26} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6657901327322815, 'r': 0.6657901327322815, 'f1': 0.6657901327322815}, 'combined': 0.47412327633965495, 'epoch': 26} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 27 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 17:41:29.094545: step: 2/1545, loss: 0.0012155277654528618 2023-01-23 17:41:30.004888: step: 4/1545, loss: 0.0002963561855722219 2023-01-23 17:41:30.890701: step: 6/1545, loss: 1.1617814302444458 2023-01-23 17:41:31.833499: step: 8/1545, loss: 0.30689185857772827 2023-01-23 17:41:32.784244: step: 10/1545, loss: 0.014266174286603928 2023-01-23 17:41:33.612150: step: 12/1545, loss: 0.0037482036277651787 2023-01-23 17:41:34.522423: step: 14/1545, loss: 5.813657844555564e-05 2023-01-23 17:41:35.368064: step: 16/1545, loss: 0.0010359907755628228 2023-01-23 17:41:36.226337: step: 18/1545, loss: 0.04029079154133797 2023-01-23 17:41:37.089228: step: 20/1545, loss: 0.001323484699241817 2023-01-23 17:41:37.957160: step: 22/1545, loss: 0.001170996343716979 2023-01-23 17:41:38.873071: step: 24/1545, loss: 0.00420553982257843 2023-01-23 17:41:39.750744: step: 26/1545, loss: 0.27452942728996277 2023-01-23 17:41:40.623932: step: 28/1545, loss: 0.040623392909765244 2023-01-23 17:41:41.502349: step: 30/1545, loss: 0.01210602093487978 2023-01-23 17:41:42.438397: step: 32/1545, loss: 0.0003582458884920925 2023-01-23 17:41:43.322550: step: 34/1545, loss: 0.01981467381119728 2023-01-23 17:41:44.192955: step: 36/1545, loss: 0.001003159792162478 2023-01-23 17:41:45.040843: step: 38/1545, loss: 0.0022584267426282167 2023-01-23 17:41:45.970577: step: 40/1545, loss: 0.0007873238064348698 2023-01-23 17:41:46.840862: step: 42/1545, loss: 0.0009835781529545784 2023-01-23 17:41:47.751274: step: 44/1545, loss: 0.5449520945549011 2023-01-23 17:41:48.671165: step: 46/1545, loss: 0.021004073321819305 2023-01-23 17:41:49.564168: step: 48/1545, loss: 0.05589320883154869 2023-01-23 17:41:50.415492: step: 50/1545, loss: 0.0022210206370800734 2023-01-23 17:41:51.268299: step: 52/1545, loss: 0.03725830838084221 2023-01-23 17:41:52.192304: step: 54/1545, loss: 0.0013036068994551897 2023-01-23 17:41:53.054044: step: 56/1545, loss: 0.0001558407675474882 2023-01-23 17:41:53.923132: step: 58/1545, loss: 0.0012793147470802069 2023-01-23 17:41:54.826082: step: 60/1545, loss: 0.11646997183561325 2023-01-23 17:41:55.702050: step: 62/1545, loss: 0.15324954688549042 2023-01-23 17:41:56.586024: step: 64/1545, loss: 0.003396428655833006 2023-01-23 17:41:57.513713: step: 66/1545, loss: 0.02549910545349121 2023-01-23 17:41:58.411165: step: 68/1545, loss: 0.08561109006404877 2023-01-23 17:41:59.341635: step: 70/1545, loss: 0.0037749253679066896 2023-01-23 17:42:00.235933: step: 72/1545, loss: 3.908451981260441e-05 2023-01-23 17:42:01.109577: step: 74/1545, loss: 0.00021736288908869028 2023-01-23 17:42:01.983994: step: 76/1545, loss: 0.7343246340751648 2023-01-23 17:42:02.830608: step: 78/1545, loss: 0.003851445158943534 2023-01-23 17:42:03.694351: step: 80/1545, loss: 5.72045564695145e-06 2023-01-23 17:42:04.554974: step: 82/1545, loss: 0.29001811146736145 2023-01-23 17:42:05.412648: step: 84/1545, loss: 0.05381717160344124 2023-01-23 17:42:06.264835: step: 86/1545, loss: 0.1049284115433693 2023-01-23 17:42:07.176921: step: 88/1545, loss: 2.352612864342518e-05 2023-01-23 17:42:08.050103: step: 90/1545, loss: 0.41513165831565857 2023-01-23 17:42:09.001050: step: 92/1545, loss: 0.0033288421109318733 2023-01-23 17:42:09.897788: step: 94/1545, loss: 0.000642540049739182 2023-01-23 17:42:10.782117: step: 96/1545, loss: 0.046943921595811844 2023-01-23 17:42:11.688955: step: 98/1545, loss: 0.022422803565859795 2023-01-23 17:42:12.591954: step: 100/1545, loss: 0.28431081771850586 2023-01-23 17:42:13.535490: step: 102/1545, loss: 0.015030725859105587 2023-01-23 17:42:14.408071: step: 104/1545, loss: 0.002642800100147724 2023-01-23 17:42:15.256204: step: 106/1545, loss: 1.020387887954712 2023-01-23 17:42:16.112480: step: 108/1545, loss: 0.0017571727512404323 2023-01-23 17:42:17.020422: step: 110/1545, loss: 0.006510663311928511 2023-01-23 17:42:17.866069: step: 112/1545, loss: 0.0009727712604217231 2023-01-23 17:42:18.756036: step: 114/1545, loss: 0.0012884577736258507 2023-01-23 17:42:19.681292: step: 116/1545, loss: 0.7701396942138672 2023-01-23 17:42:20.565491: step: 118/1545, loss: 0.021544013172388077 2023-01-23 17:42:21.406617: step: 120/1545, loss: 1.1991628408432007 2023-01-23 17:42:22.356136: step: 122/1545, loss: 0.16940797865390778 2023-01-23 17:42:23.232635: step: 124/1545, loss: 0.005304460413753986 2023-01-23 17:42:24.163087: step: 126/1545, loss: 0.0044385637156665325 2023-01-23 17:42:25.090108: step: 128/1545, loss: 0.08014131337404251 2023-01-23 17:42:25.931654: step: 130/1545, loss: 0.016077889129519463 2023-01-23 17:42:26.859804: step: 132/1545, loss: 0.0036429387982934713 2023-01-23 17:42:27.718419: step: 134/1545, loss: 0.08048804104328156 2023-01-23 17:42:28.570346: step: 136/1545, loss: 0.000609876646194607 2023-01-23 17:42:29.437239: step: 138/1545, loss: 0.002436320995911956 2023-01-23 17:42:30.279705: step: 140/1545, loss: 4.083324165549129e-05 2023-01-23 17:42:31.141312: step: 142/1545, loss: 0.0010866130469366908 2023-01-23 17:42:32.087261: step: 144/1545, loss: 0.0007272522198036313 2023-01-23 17:42:32.976888: step: 146/1545, loss: 0.5725230574607849 2023-01-23 17:42:33.855580: step: 148/1545, loss: 0.002502273768186569 2023-01-23 17:42:34.740771: step: 150/1545, loss: 0.1769808828830719 2023-01-23 17:42:35.619724: step: 152/1545, loss: 0.11346548050642014 2023-01-23 17:42:36.492544: step: 154/1545, loss: 0.00045636954018846154 2023-01-23 17:42:37.383174: step: 156/1545, loss: 0.10029131174087524 2023-01-23 17:42:38.216243: step: 158/1545, loss: 6.305832357611507e-05 2023-01-23 17:42:39.101629: step: 160/1545, loss: 0.02640819363296032 2023-01-23 17:42:40.007028: step: 162/1545, loss: 0.0028795672114938498 2023-01-23 17:42:40.890234: step: 164/1545, loss: 0.001381605165079236 2023-01-23 17:42:41.809169: step: 166/1545, loss: 0.00440216762945056 2023-01-23 17:42:42.701012: step: 168/1545, loss: 0.0010388545924797654 2023-01-23 17:42:43.563514: step: 170/1545, loss: 0.03183465823531151 2023-01-23 17:42:44.434516: step: 172/1545, loss: 0.038321785628795624 2023-01-23 17:42:45.303465: step: 174/1545, loss: 0.004780981689691544 2023-01-23 17:42:46.266348: step: 176/1545, loss: 0.008210292086005211 2023-01-23 17:42:47.177626: step: 178/1545, loss: 0.046999767422676086 2023-01-23 17:42:48.098828: step: 180/1545, loss: 0.037829626351594925 2023-01-23 17:42:48.978082: step: 182/1545, loss: 9.397270332556218e-05 2023-01-23 17:42:49.876597: step: 184/1545, loss: 0.0007247217581607401 2023-01-23 17:42:50.775490: step: 186/1545, loss: 0.03250209614634514 2023-01-23 17:42:51.738530: step: 188/1545, loss: 0.20687003433704376 2023-01-23 17:42:52.599823: step: 190/1545, loss: 5.6206459703389555e-05 2023-01-23 17:42:53.462818: step: 192/1545, loss: 0.015418936498463154 2023-01-23 17:42:54.322802: step: 194/1545, loss: 0.0319129154086113 2023-01-23 17:42:55.177230: step: 196/1545, loss: 0.10403866320848465 2023-01-23 17:42:56.183701: step: 198/1545, loss: 0.024268273264169693 2023-01-23 17:42:57.128261: step: 200/1545, loss: 0.005532370880246162 2023-01-23 17:42:57.993537: step: 202/1545, loss: 0.010884729214012623 2023-01-23 17:42:58.854823: step: 204/1545, loss: 0.0007153659244067967 2023-01-23 17:42:59.769836: step: 206/1545, loss: 0.0009164668736048043 2023-01-23 17:43:00.676680: step: 208/1545, loss: 0.004370809067040682 2023-01-23 17:43:01.591351: step: 210/1545, loss: 0.002672431990504265 2023-01-23 17:43:02.502997: step: 212/1545, loss: 0.0012209740234538913 2023-01-23 17:43:03.458638: step: 214/1545, loss: 0.0819784477353096 2023-01-23 17:43:04.305115: step: 216/1545, loss: 0.0004721199511550367 2023-01-23 17:43:05.181169: step: 218/1545, loss: 0.4144608676433563 2023-01-23 17:43:06.105249: step: 220/1545, loss: 0.0003105567884631455 2023-01-23 17:43:07.020855: step: 222/1545, loss: 0.0012856373796239495 2023-01-23 17:43:07.986516: step: 224/1545, loss: 0.01480703242123127 2023-01-23 17:43:08.827792: step: 226/1545, loss: 0.06257674098014832 2023-01-23 17:43:09.737242: step: 228/1545, loss: 0.00045182163012214005 2023-01-23 17:43:10.646423: step: 230/1545, loss: 0.0029215675313025713 2023-01-23 17:43:11.506782: step: 232/1545, loss: 0.0035263681784272194 2023-01-23 17:43:12.410171: step: 234/1545, loss: 0.00010247928730677813 2023-01-23 17:43:13.262441: step: 236/1545, loss: 0.008759665302932262 2023-01-23 17:43:14.115543: step: 238/1545, loss: 0.0022045872174203396 2023-01-23 17:43:15.011060: step: 240/1545, loss: 0.014127521775662899 2023-01-23 17:43:15.974188: step: 242/1545, loss: 0.023868924006819725 2023-01-23 17:43:16.843059: step: 244/1545, loss: 0.0002504622971173376 2023-01-23 17:43:17.689147: step: 246/1545, loss: 0.0011946253944188356 2023-01-23 17:43:18.586239: step: 248/1545, loss: 0.35095739364624023 2023-01-23 17:43:19.457712: step: 250/1545, loss: 0.035344287753105164 2023-01-23 17:43:20.394829: step: 252/1545, loss: 0.134251207113266 2023-01-23 17:43:21.234353: step: 254/1545, loss: 0.0016590654850006104 2023-01-23 17:43:22.118773: step: 256/1545, loss: 0.0290166437625885 2023-01-23 17:43:23.094443: step: 258/1545, loss: 0.005307088606059551 2023-01-23 17:43:23.999938: step: 260/1545, loss: 7.387235382338986e-05 2023-01-23 17:43:24.854858: step: 262/1545, loss: 0.0007502131629735231 2023-01-23 17:43:25.732581: step: 264/1545, loss: 0.0013579013757407665 2023-01-23 17:43:26.573356: step: 266/1545, loss: 0.00032900783116929233 2023-01-23 17:43:27.442466: step: 268/1545, loss: 0.0005456459475681186 2023-01-23 17:43:28.329028: step: 270/1545, loss: 0.02673538215458393 2023-01-23 17:43:29.195490: step: 272/1545, loss: 0.00014198260032571852 2023-01-23 17:43:30.105829: step: 274/1545, loss: 0.1785580813884735 2023-01-23 17:43:30.972705: step: 276/1545, loss: 0.006316397804766893 2023-01-23 17:43:31.846743: step: 278/1545, loss: 0.020999029278755188 2023-01-23 17:43:32.748754: step: 280/1545, loss: 1.8407823517918587e-05 2023-01-23 17:43:33.633034: step: 282/1545, loss: 0.0085144629701972 2023-01-23 17:43:34.516348: step: 284/1545, loss: 0.15762518346309662 2023-01-23 17:43:35.357636: step: 286/1545, loss: 0.3619164526462555 2023-01-23 17:43:36.209968: step: 288/1545, loss: 0.0003581077035050839 2023-01-23 17:43:37.091450: step: 290/1545, loss: 0.0002689402608666569 2023-01-23 17:43:37.975985: step: 292/1545, loss: 0.16588573157787323 2023-01-23 17:43:38.913738: step: 294/1545, loss: 0.010113788768649101 2023-01-23 17:43:39.785464: step: 296/1545, loss: 6.968118395889178e-05 2023-01-23 17:43:40.631922: step: 298/1545, loss: 0.0004088794521521777 2023-01-23 17:43:41.512842: step: 300/1545, loss: 0.00019550543220248073 2023-01-23 17:43:42.386351: step: 302/1545, loss: 0.16855520009994507 2023-01-23 17:43:43.264015: step: 304/1545, loss: 3.5246714105596766e-05 2023-01-23 17:43:44.149500: step: 306/1545, loss: 0.004458197858184576 2023-01-23 17:43:44.980965: step: 308/1545, loss: 0.0002638561127241701 2023-01-23 17:43:45.914198: step: 310/1545, loss: 0.2181916981935501 2023-01-23 17:43:46.810144: step: 312/1545, loss: 0.0007371703395619988 2023-01-23 17:43:47.685835: step: 314/1545, loss: 0.0063674733974039555 2023-01-23 17:43:48.650807: step: 316/1545, loss: 0.010788007639348507 2023-01-23 17:43:49.520532: step: 318/1545, loss: 0.0053074960596859455 2023-01-23 17:43:50.400327: step: 320/1545, loss: 0.0010573738254606724 2023-01-23 17:43:51.281841: step: 322/1545, loss: 0.00012645541573874652 2023-01-23 17:43:52.170286: step: 324/1545, loss: 0.010909984819591045 2023-01-23 17:43:53.060184: step: 326/1545, loss: 0.2573194205760956 2023-01-23 17:43:53.941159: step: 328/1545, loss: 0.8234894275665283 2023-01-23 17:43:54.818657: step: 330/1545, loss: 0.01578923687338829 2023-01-23 17:43:55.741175: step: 332/1545, loss: 0.0006375878001563251 2023-01-23 17:43:56.634588: step: 334/1545, loss: 0.002117132768034935 2023-01-23 17:43:57.480508: step: 336/1545, loss: 0.06160390004515648 2023-01-23 17:43:58.398546: step: 338/1545, loss: 0.0002472095366101712 2023-01-23 17:43:59.283622: step: 340/1545, loss: 0.00887278001755476 2023-01-23 17:44:00.173580: step: 342/1545, loss: 0.0003515590215101838 2023-01-23 17:44:01.129148: step: 344/1545, loss: 0.025462940335273743 2023-01-23 17:44:01.995309: step: 346/1545, loss: 0.00011627071216935292 2023-01-23 17:44:02.918330: step: 348/1545, loss: 0.1570286750793457 2023-01-23 17:44:03.869557: step: 350/1545, loss: 0.0010053106816485524 2023-01-23 17:44:04.757581: step: 352/1545, loss: 0.26334407925605774 2023-01-23 17:44:05.634237: step: 354/1545, loss: 0.18458323180675507 2023-01-23 17:44:06.521651: step: 356/1545, loss: 0.02276402898132801 2023-01-23 17:44:07.404790: step: 358/1545, loss: 0.08596731722354889 2023-01-23 17:44:08.299650: step: 360/1545, loss: 0.15670621395111084 2023-01-23 17:44:09.163390: step: 362/1545, loss: 0.0016820296877995133 2023-01-23 17:44:10.040654: step: 364/1545, loss: 0.005980278830975294 2023-01-23 17:44:10.910902: step: 366/1545, loss: 0.09119296818971634 2023-01-23 17:44:11.807871: step: 368/1545, loss: 0.0005489310133270919 2023-01-23 17:44:12.672532: step: 370/1545, loss: 0.1071147471666336 2023-01-23 17:44:13.554589: step: 372/1545, loss: 0.0003980644978582859 2023-01-23 17:44:14.449981: step: 374/1545, loss: 0.004850768484175205 2023-01-23 17:44:15.357208: step: 376/1545, loss: 0.08176501840353012 2023-01-23 17:44:16.222110: step: 378/1545, loss: 0.09810980409383774 2023-01-23 17:44:17.063386: step: 380/1545, loss: 0.0021357371006160975 2023-01-23 17:44:17.940686: step: 382/1545, loss: 0.0001377255975967273 2023-01-23 17:44:18.802842: step: 384/1545, loss: 0.0014493863563984632 2023-01-23 17:44:19.724391: step: 386/1545, loss: 0.06245734170079231 2023-01-23 17:44:20.593848: step: 388/1545, loss: 0.000667121319565922 2023-01-23 17:44:21.494048: step: 390/1545, loss: 0.009429620578885078 2023-01-23 17:44:22.453198: step: 392/1545, loss: 0.41296663880348206 2023-01-23 17:44:23.359779: step: 394/1545, loss: 0.1541006714105606 2023-01-23 17:44:24.242707: step: 396/1545, loss: 0.5770257115364075 2023-01-23 17:44:25.137137: step: 398/1545, loss: 0.001093174098059535 2023-01-23 17:44:26.059406: step: 400/1545, loss: 0.173990398645401 2023-01-23 17:44:26.934861: step: 402/1545, loss: 0.07073384523391724 2023-01-23 17:44:27.858715: step: 404/1545, loss: 0.0002684288483578712 2023-01-23 17:44:28.729097: step: 406/1545, loss: 0.02677961252629757 2023-01-23 17:44:29.670634: step: 408/1545, loss: 0.027727162465453148 2023-01-23 17:44:30.589416: step: 410/1545, loss: 0.1810634434223175 2023-01-23 17:44:31.446625: step: 412/1545, loss: 0.2565491497516632 2023-01-23 17:44:32.294913: step: 414/1545, loss: 0.015572680160403252 2023-01-23 17:44:33.176396: step: 416/1545, loss: 0.0011922350386157632 2023-01-23 17:44:34.062685: step: 418/1545, loss: 0.7355111837387085 2023-01-23 17:44:34.908924: step: 420/1545, loss: 0.036219120025634766 2023-01-23 17:44:35.772816: step: 422/1545, loss: 0.0004440362681634724 2023-01-23 17:44:36.650741: step: 424/1545, loss: 0.04268195107579231 2023-01-23 17:44:37.492001: step: 426/1545, loss: 0.2522836923599243 2023-01-23 17:44:38.395823: step: 428/1545, loss: 0.23251615464687347 2023-01-23 17:44:39.268814: step: 430/1545, loss: 0.03394078463315964 2023-01-23 17:44:40.133003: step: 432/1545, loss: 0.07462278753519058 2023-01-23 17:44:41.034247: step: 434/1545, loss: 0.06373370438814163 2023-01-23 17:44:41.892506: step: 436/1545, loss: 0.09542666375637054 2023-01-23 17:44:42.815703: step: 438/1545, loss: 0.2795737683773041 2023-01-23 17:44:43.686172: step: 440/1545, loss: 0.0009457789128646255 2023-01-23 17:44:44.570457: step: 442/1545, loss: 0.00040902436012402177 2023-01-23 17:44:45.495543: step: 444/1545, loss: 8.326304669026285e-05 2023-01-23 17:44:46.304347: step: 446/1545, loss: 0.00013399017916526645 2023-01-23 17:44:47.148887: step: 448/1545, loss: 0.003205351997166872 2023-01-23 17:44:48.029073: step: 450/1545, loss: 0.0002453531778883189 2023-01-23 17:44:48.956354: step: 452/1545, loss: 0.0006868037162348628 2023-01-23 17:44:49.840033: step: 454/1545, loss: 0.016286153346300125 2023-01-23 17:44:50.746390: step: 456/1545, loss: 1.1236804723739624 2023-01-23 17:44:51.616076: step: 458/1545, loss: 0.0036170468665659428 2023-01-23 17:44:52.458953: step: 460/1545, loss: 0.010600374080240726 2023-01-23 17:44:53.356960: step: 462/1545, loss: 0.12283575534820557 2023-01-23 17:44:54.211028: step: 464/1545, loss: 0.0002724766673054546 2023-01-23 17:44:55.083067: step: 466/1545, loss: 0.29615849256515503 2023-01-23 17:44:55.938430: step: 468/1545, loss: 0.00011629120854195207 2023-01-23 17:44:56.785096: step: 470/1545, loss: 0.15504920482635498 2023-01-23 17:44:57.662102: step: 472/1545, loss: 0.15964438021183014 2023-01-23 17:44:58.565938: step: 474/1545, loss: 0.0018302199896425009 2023-01-23 17:44:59.462282: step: 476/1545, loss: 0.14428049325942993 2023-01-23 17:45:00.332460: step: 478/1545, loss: 0.004968229681253433 2023-01-23 17:45:01.211322: step: 480/1545, loss: 0.08309801667928696 2023-01-23 17:45:02.127113: step: 482/1545, loss: 0.6167001724243164 2023-01-23 17:45:03.053493: step: 484/1545, loss: 0.11481460928916931 2023-01-23 17:45:03.906980: step: 486/1545, loss: 0.0002706054365262389 2023-01-23 17:45:04.845729: step: 488/1545, loss: 0.014940916560590267 2023-01-23 17:45:05.692133: step: 490/1545, loss: 0.047598179429769516 2023-01-23 17:45:06.555107: step: 492/1545, loss: 0.0540928952395916 2023-01-23 17:45:07.399675: step: 494/1545, loss: 0.06122768670320511 2023-01-23 17:45:08.281191: step: 496/1545, loss: 0.7069478631019592 2023-01-23 17:45:09.165188: step: 498/1545, loss: 0.005218273028731346 2023-01-23 17:45:10.090742: step: 500/1545, loss: 0.018856922164559364 2023-01-23 17:45:10.940128: step: 502/1545, loss: 0.03404108062386513 2023-01-23 17:45:11.806531: step: 504/1545, loss: 0.01285246666520834 2023-01-23 17:45:12.685360: step: 506/1545, loss: 2.918289101216942e-05 2023-01-23 17:45:13.568021: step: 508/1545, loss: 0.005032519809901714 2023-01-23 17:45:14.433296: step: 510/1545, loss: 0.18157751858234406 2023-01-23 17:45:15.314885: step: 512/1545, loss: 0.06880056858062744 2023-01-23 17:45:16.215436: step: 514/1545, loss: 0.1512874960899353 2023-01-23 17:45:17.060018: step: 516/1545, loss: 0.14091050624847412 2023-01-23 17:45:17.902736: step: 518/1545, loss: 0.008789465762674809 2023-01-23 17:45:18.889498: step: 520/1545, loss: 0.012282518669962883 2023-01-23 17:45:19.759590: step: 522/1545, loss: 0.0007193885394372046 2023-01-23 17:45:20.656429: step: 524/1545, loss: 0.0072074588388204575 2023-01-23 17:45:21.585100: step: 526/1545, loss: 0.03948470950126648 2023-01-23 17:45:22.454766: step: 528/1545, loss: 0.09935557097196579 2023-01-23 17:45:23.373646: step: 530/1545, loss: 0.008724129758775234 2023-01-23 17:45:24.266541: step: 532/1545, loss: 0.36405736207962036 2023-01-23 17:45:25.194888: step: 534/1545, loss: 0.04274008050560951 2023-01-23 17:45:26.127781: step: 536/1545, loss: 0.0016849256353452802 2023-01-23 17:45:27.030822: step: 538/1545, loss: 0.0012224947568029165 2023-01-23 17:45:27.902600: step: 540/1545, loss: 0.0008023163536563516 2023-01-23 17:45:28.788703: step: 542/1545, loss: 0.02543860487639904 2023-01-23 17:45:29.656265: step: 544/1545, loss: 0.0010134155163541436 2023-01-23 17:45:30.484502: step: 546/1545, loss: 0.05214157700538635 2023-01-23 17:45:31.341445: step: 548/1545, loss: 0.0298643596470356 2023-01-23 17:45:32.199224: step: 550/1545, loss: 0.00044606090523302555 2023-01-23 17:45:33.126238: step: 552/1545, loss: 0.0007212547934614122 2023-01-23 17:45:34.053867: step: 554/1545, loss: 0.04506239295005798 2023-01-23 17:45:34.952969: step: 556/1545, loss: 0.010581914335489273 2023-01-23 17:45:35.850911: step: 558/1545, loss: 0.006010264158248901 2023-01-23 17:45:36.766838: step: 560/1545, loss: 0.0002013330813497305 2023-01-23 17:45:37.672265: step: 562/1545, loss: 0.01741776429116726 2023-01-23 17:45:38.568785: step: 564/1545, loss: 0.0012816940434277058 2023-01-23 17:45:39.453097: step: 566/1545, loss: 0.0067814108915627 2023-01-23 17:45:40.337540: step: 568/1545, loss: 0.0023237294517457485 2023-01-23 17:45:41.239918: step: 570/1545, loss: 0.05416107177734375 2023-01-23 17:45:42.178726: step: 572/1545, loss: 0.024459630250930786 2023-01-23 17:45:43.071249: step: 574/1545, loss: 0.31215739250183105 2023-01-23 17:45:43.916567: step: 576/1545, loss: 0.04660464823246002 2023-01-23 17:45:44.834909: step: 578/1545, loss: 0.0004784839111380279 2023-01-23 17:45:45.728352: step: 580/1545, loss: 0.01613318920135498 2023-01-23 17:45:46.596208: step: 582/1545, loss: 0.010721311904489994 2023-01-23 17:45:47.477012: step: 584/1545, loss: 0.8220899105072021 2023-01-23 17:45:48.368440: step: 586/1545, loss: 0.00020655580738093704 2023-01-23 17:45:49.281513: step: 588/1545, loss: 0.07802525907754898 2023-01-23 17:45:50.170044: step: 590/1545, loss: 0.000891246774699539 2023-01-23 17:45:51.021667: step: 592/1545, loss: 0.008383852429687977 2023-01-23 17:45:51.889190: step: 594/1545, loss: 0.003430828917771578 2023-01-23 17:45:52.840573: step: 596/1545, loss: 0.06140553206205368 2023-01-23 17:45:53.720559: step: 598/1545, loss: 0.0004706041654571891 2023-01-23 17:45:54.595620: step: 600/1545, loss: 0.008224071003496647 2023-01-23 17:45:55.496220: step: 602/1545, loss: 0.08348378539085388 2023-01-23 17:45:56.380545: step: 604/1545, loss: 0.09396791458129883 2023-01-23 17:45:57.316616: step: 606/1545, loss: 0.06721726804971695 2023-01-23 17:45:58.213018: step: 608/1545, loss: 0.01854632794857025 2023-01-23 17:45:59.064745: step: 610/1545, loss: 0.12052273005247116 2023-01-23 17:45:59.937268: step: 612/1545, loss: 0.10094510763883591 2023-01-23 17:46:00.804863: step: 614/1545, loss: 0.0011484824353829026 2023-01-23 17:46:01.697072: step: 616/1545, loss: 0.0015070432564243674 2023-01-23 17:46:02.560674: step: 618/1545, loss: 0.005803579464554787 2023-01-23 17:46:03.472367: step: 620/1545, loss: 2.4037697315216064 2023-01-23 17:46:04.407714: step: 622/1545, loss: 0.010556261986494064 2023-01-23 17:46:05.250368: step: 624/1545, loss: 0.0013425579527392983 2023-01-23 17:46:06.229041: step: 626/1545, loss: 0.002729484811425209 2023-01-23 17:46:07.091527: step: 628/1545, loss: 0.0013343467144295573 2023-01-23 17:46:07.990762: step: 630/1545, loss: 0.03459172695875168 2023-01-23 17:46:08.904858: step: 632/1545, loss: 0.38061997294425964 2023-01-23 17:46:09.748371: step: 634/1545, loss: 0.00026695418637245893 2023-01-23 17:46:10.629092: step: 636/1545, loss: 0.023068424314260483 2023-01-23 17:46:11.496696: step: 638/1545, loss: 0.15415050089359283 2023-01-23 17:46:12.357668: step: 640/1545, loss: 0.3302934765815735 2023-01-23 17:46:13.226137: step: 642/1545, loss: 0.10040735453367233 2023-01-23 17:46:14.132820: step: 644/1545, loss: 0.00044062460074201226 2023-01-23 17:46:15.024966: step: 646/1545, loss: 0.006942138075828552 2023-01-23 17:46:15.883824: step: 648/1545, loss: 0.005503213498741388 2023-01-23 17:46:16.752355: step: 650/1545, loss: 0.004010168369859457 2023-01-23 17:46:17.630291: step: 652/1545, loss: 0.14560921490192413 2023-01-23 17:46:18.585163: step: 654/1545, loss: 0.001602499047294259 2023-01-23 17:46:19.485247: step: 656/1545, loss: 0.007835464552044868 2023-01-23 17:46:20.334417: step: 658/1545, loss: 0.0015093338442966342 2023-01-23 17:46:21.195167: step: 660/1545, loss: 0.008914788253605366 2023-01-23 17:46:22.098612: step: 662/1545, loss: 0.00039634390850551426 2023-01-23 17:46:22.969855: step: 664/1545, loss: 0.1524280607700348 2023-01-23 17:46:23.819754: step: 666/1545, loss: 0.33983105421066284 2023-01-23 17:46:24.695336: step: 668/1545, loss: 0.007075101602822542 2023-01-23 17:46:25.549609: step: 670/1545, loss: 0.0034144495148211718 2023-01-23 17:46:26.419608: step: 672/1545, loss: 0.021091841161251068 2023-01-23 17:46:27.325583: step: 674/1545, loss: 0.0033380615059286356 2023-01-23 17:46:28.225851: step: 676/1545, loss: 0.04417276754975319 2023-01-23 17:46:29.097145: step: 678/1545, loss: 0.13857588171958923 2023-01-23 17:46:29.941880: step: 680/1545, loss: 0.004718538839370012 2023-01-23 17:46:30.829821: step: 682/1545, loss: 0.00169475213624537 2023-01-23 17:46:31.722504: step: 684/1545, loss: 0.02698073722422123 2023-01-23 17:46:32.621302: step: 686/1545, loss: 0.13821732997894287 2023-01-23 17:46:33.452493: step: 688/1545, loss: 0.014597665518522263 2023-01-23 17:46:34.338990: step: 690/1545, loss: 0.08981087058782578 2023-01-23 17:46:35.247777: step: 692/1545, loss: 0.0023605963215231895 2023-01-23 17:46:36.126346: step: 694/1545, loss: 0.2242378145456314 2023-01-23 17:46:37.008205: step: 696/1545, loss: 0.14470238983631134 2023-01-23 17:46:37.894322: step: 698/1545, loss: 0.009147941134870052 2023-01-23 17:46:38.809418: step: 700/1545, loss: 0.13791434466838837 2023-01-23 17:46:39.701839: step: 702/1545, loss: 0.0778079628944397 2023-01-23 17:46:40.596091: step: 704/1545, loss: 0.0005233378615230322 2023-01-23 17:46:41.471336: step: 706/1545, loss: 0.048030175268650055 2023-01-23 17:46:42.315746: step: 708/1545, loss: 0.0006704562110826373 2023-01-23 17:46:43.162084: step: 710/1545, loss: 0.15021806955337524 2023-01-23 17:46:44.041864: step: 712/1545, loss: 0.0006105750217102468 2023-01-23 17:46:44.940326: step: 714/1545, loss: 0.007019247859716415 2023-01-23 17:46:45.789756: step: 716/1545, loss: 0.0022416214924305677 2023-01-23 17:46:46.640742: step: 718/1545, loss: 0.0004080703074578196 2023-01-23 17:46:47.491765: step: 720/1545, loss: 0.0003779288672376424 2023-01-23 17:46:48.352922: step: 722/1545, loss: 0.09139572829008102 2023-01-23 17:46:49.272925: step: 724/1545, loss: 0.23074570298194885 2023-01-23 17:46:50.127751: step: 726/1545, loss: 0.04241635650396347 2023-01-23 17:46:51.009220: step: 728/1545, loss: 0.0048318710178136826 2023-01-23 17:46:51.895320: step: 730/1545, loss: 0.2392040640115738 2023-01-23 17:46:52.875803: step: 732/1545, loss: 0.0016806706553325057 2023-01-23 17:46:53.742617: step: 734/1545, loss: 0.16404742002487183 2023-01-23 17:46:54.637757: step: 736/1545, loss: 0.005025865510106087 2023-01-23 17:46:55.545710: step: 738/1545, loss: 0.08300097286701202 2023-01-23 17:46:56.503932: step: 740/1545, loss: 0.00387834245339036 2023-01-23 17:46:57.454568: step: 742/1545, loss: 0.0011549692135304213 2023-01-23 17:46:58.383842: step: 744/1545, loss: 0.053928423672914505 2023-01-23 17:46:59.339579: step: 746/1545, loss: 0.20911768078804016 2023-01-23 17:47:00.229730: step: 748/1545, loss: 0.010232547298073769 2023-01-23 17:47:01.108236: step: 750/1545, loss: 0.0013263560831546783 2023-01-23 17:47:02.050225: step: 752/1545, loss: 0.008527562953531742 2023-01-23 17:47:02.914221: step: 754/1545, loss: 0.0005149631761014462 2023-01-23 17:47:03.840109: step: 756/1545, loss: 0.0010744711617007852 2023-01-23 17:47:04.806748: step: 758/1545, loss: 0.038755353540182114 2023-01-23 17:47:05.657225: step: 760/1545, loss: 0.000115540053229779 2023-01-23 17:47:06.549937: step: 762/1545, loss: 0.018268372863531113 2023-01-23 17:47:07.455310: step: 764/1545, loss: 0.09843280911445618 2023-01-23 17:47:08.325480: step: 766/1545, loss: 0.00035736110294237733 2023-01-23 17:47:09.314750: step: 768/1545, loss: 0.011066981591284275 2023-01-23 17:47:10.219888: step: 770/1545, loss: 0.016342194750905037 2023-01-23 17:47:11.102438: step: 772/1545, loss: 0.07314638793468475 2023-01-23 17:47:11.952549: step: 774/1545, loss: 0.02953287400305271 2023-01-23 17:47:12.839962: step: 776/1545, loss: 0.1704595535993576 2023-01-23 17:47:13.672162: step: 778/1545, loss: 0.005031274631619453 2023-01-23 17:47:14.566763: step: 780/1545, loss: 0.004385512787848711 2023-01-23 17:47:15.450211: step: 782/1545, loss: 0.0004026627284474671 2023-01-23 17:47:16.300493: step: 784/1545, loss: 0.05194960907101631 2023-01-23 17:47:17.194307: step: 786/1545, loss: 0.3696983754634857 2023-01-23 17:47:18.077060: step: 788/1545, loss: 0.10093281418085098 2023-01-23 17:47:18.984538: step: 790/1545, loss: 0.00013746644253842533 2023-01-23 17:47:19.966489: step: 792/1545, loss: 0.023516999557614326 2023-01-23 17:47:20.840979: step: 794/1545, loss: 0.0028448549564927816 2023-01-23 17:47:21.742883: step: 796/1545, loss: 0.10897687077522278 2023-01-23 17:47:22.634463: step: 798/1545, loss: 0.0012772295158356428 2023-01-23 17:47:23.505899: step: 800/1545, loss: 5.974264786345884e-05 2023-01-23 17:47:24.371605: step: 802/1545, loss: 0.14820356667041779 2023-01-23 17:47:25.269910: step: 804/1545, loss: 0.007521083112806082 2023-01-23 17:47:26.121255: step: 806/1545, loss: 0.010397587902843952 2023-01-23 17:47:26.956248: step: 808/1545, loss: 0.0021843535359948874 2023-01-23 17:47:27.837875: step: 810/1545, loss: 0.005551664158701897 2023-01-23 17:47:28.671548: step: 812/1545, loss: 0.0004625079454854131 2023-01-23 17:47:29.564429: step: 814/1545, loss: 0.0019413819536566734 2023-01-23 17:47:30.434508: step: 816/1545, loss: 0.16912665963172913 2023-01-23 17:47:31.339076: step: 818/1545, loss: 0.04484408721327782 2023-01-23 17:47:32.210877: step: 820/1545, loss: 0.00022112391889095306 2023-01-23 17:47:33.077494: step: 822/1545, loss: 0.03476186841726303 2023-01-23 17:47:33.981301: step: 824/1545, loss: 0.01100714411586523 2023-01-23 17:47:34.851084: step: 826/1545, loss: 0.0022238935343921185 2023-01-23 17:47:35.689146: step: 828/1545, loss: 0.0012010448845103383 2023-01-23 17:47:36.620015: step: 830/1545, loss: 0.002551064593717456 2023-01-23 17:47:37.498326: step: 832/1545, loss: 0.7656948566436768 2023-01-23 17:47:38.340059: step: 834/1545, loss: 9.023107850225642e-05 2023-01-23 17:47:39.183658: step: 836/1545, loss: 0.3173501193523407 2023-01-23 17:47:40.155119: step: 838/1545, loss: 0.023352110758423805 2023-01-23 17:47:41.037472: step: 840/1545, loss: 0.0005412517348304391 2023-01-23 17:47:41.944250: step: 842/1545, loss: 0.025913694873452187 2023-01-23 17:47:42.865983: step: 844/1545, loss: 0.002296636812388897 2023-01-23 17:47:43.734563: step: 846/1545, loss: 0.1593702882528305 2023-01-23 17:47:44.644767: step: 848/1545, loss: 0.00022214713681023568 2023-01-23 17:47:45.547649: step: 850/1545, loss: 0.045182421803474426 2023-01-23 17:47:46.442066: step: 852/1545, loss: 0.07445286959409714 2023-01-23 17:47:47.350976: step: 854/1545, loss: 0.0005220790626481175 2023-01-23 17:47:48.358251: step: 856/1545, loss: 0.18197278678417206 2023-01-23 17:47:49.252572: step: 858/1545, loss: 0.06211187317967415 2023-01-23 17:47:50.115141: step: 860/1545, loss: 0.03092842735350132 2023-01-23 17:47:50.973883: step: 862/1545, loss: 0.0015038233250379562 2023-01-23 17:47:51.859000: step: 864/1545, loss: 0.0002690089459065348 2023-01-23 17:47:52.690254: step: 866/1545, loss: 0.0002265523507958278 2023-01-23 17:47:53.572416: step: 868/1545, loss: 0.10021326690912247 2023-01-23 17:47:54.488370: step: 870/1545, loss: 0.06999216973781586 2023-01-23 17:47:55.372859: step: 872/1545, loss: 0.0007827152730897069 2023-01-23 17:47:56.275298: step: 874/1545, loss: 0.06877855956554413 2023-01-23 17:47:57.167464: step: 876/1545, loss: 0.0009403404546901584 2023-01-23 17:47:58.021681: step: 878/1545, loss: 0.0015536686405539513 2023-01-23 17:47:58.979997: step: 880/1545, loss: 0.3318130075931549 2023-01-23 17:47:59.872859: step: 882/1545, loss: 0.0061315810307860374 2023-01-23 17:48:00.746970: step: 884/1545, loss: 0.00864402111619711 2023-01-23 17:48:01.766335: step: 886/1545, loss: 0.04402131959795952 2023-01-23 17:48:02.623807: step: 888/1545, loss: 0.36133769154548645 2023-01-23 17:48:03.539091: step: 890/1545, loss: 0.018305789679288864 2023-01-23 17:48:04.416658: step: 892/1545, loss: 0.0028142165392637253 2023-01-23 17:48:05.269329: step: 894/1545, loss: 0.033915773034095764 2023-01-23 17:48:06.133471: step: 896/1545, loss: 0.0003930598613806069 2023-01-23 17:48:07.022510: step: 898/1545, loss: 0.1333923488855362 2023-01-23 17:48:07.857065: step: 900/1545, loss: 0.005891790147870779 2023-01-23 17:48:08.743980: step: 902/1545, loss: 0.000629377958830446 2023-01-23 17:48:09.604139: step: 904/1545, loss: 0.0017577421385794878 2023-01-23 17:48:10.499024: step: 906/1545, loss: 2.632483301567845e-05 2023-01-23 17:48:11.368977: step: 908/1545, loss: 0.13963541388511658 2023-01-23 17:48:12.318756: step: 910/1545, loss: 0.05480935052037239 2023-01-23 17:48:13.174334: step: 912/1545, loss: 0.40126633644104004 2023-01-23 17:48:14.063760: step: 914/1545, loss: 0.040855102241039276 2023-01-23 17:48:14.921248: step: 916/1545, loss: 0.04904838278889656 2023-01-23 17:48:15.813721: step: 918/1545, loss: 0.0228336900472641 2023-01-23 17:48:16.712513: step: 920/1545, loss: 0.034000225365161896 2023-01-23 17:48:17.596764: step: 922/1545, loss: 0.0022493358701467514 2023-01-23 17:48:18.515979: step: 924/1545, loss: 0.03637717291712761 2023-01-23 17:48:19.435402: step: 926/1545, loss: 0.10438881814479828 2023-01-23 17:48:20.321809: step: 928/1545, loss: 0.0012247078120708466 2023-01-23 17:48:21.190596: step: 930/1545, loss: 0.002287074690684676 2023-01-23 17:48:22.111628: step: 932/1545, loss: 0.20670375227928162 2023-01-23 17:48:22.960196: step: 934/1545, loss: 0.0010746620828285813 2023-01-23 17:48:23.821633: step: 936/1545, loss: 0.0016448072856292129 2023-01-23 17:48:24.836840: step: 938/1545, loss: 0.03345562145113945 2023-01-23 17:48:25.698200: step: 940/1545, loss: 0.14720354974269867 2023-01-23 17:48:26.613539: step: 942/1545, loss: 0.04472603648900986 2023-01-23 17:48:27.513099: step: 944/1545, loss: 0.0006738405209034681 2023-01-23 17:48:28.418753: step: 946/1545, loss: 0.015421818941831589 2023-01-23 17:48:29.271205: step: 948/1545, loss: 0.0029680358711630106 2023-01-23 17:48:30.156444: step: 950/1545, loss: 0.0014495160430669785 2023-01-23 17:48:31.042405: step: 952/1545, loss: 0.05544251576066017 2023-01-23 17:48:32.010053: step: 954/1545, loss: 0.0010977177880704403 2023-01-23 17:48:32.898539: step: 956/1545, loss: 0.06111110746860504 2023-01-23 17:48:33.733791: step: 958/1545, loss: 0.0010250757914036512 2023-01-23 17:48:34.599509: step: 960/1545, loss: 0.014184728264808655 2023-01-23 17:48:35.452311: step: 962/1545, loss: 0.0003487567591946572 2023-01-23 17:48:36.324998: step: 964/1545, loss: 0.13171768188476562 2023-01-23 17:48:37.184214: step: 966/1545, loss: 0.0429089330136776 2023-01-23 17:48:38.057023: step: 968/1545, loss: 0.0626102015376091 2023-01-23 17:48:38.973845: step: 970/1545, loss: 0.20664696395397186 2023-01-23 17:48:39.872268: step: 972/1545, loss: 0.00034800777211785316 2023-01-23 17:48:40.711313: step: 974/1545, loss: 0.0008324208902195096 2023-01-23 17:48:41.615003: step: 976/1545, loss: 0.00613624369725585 2023-01-23 17:48:42.458557: step: 978/1545, loss: 0.001915482571348548 2023-01-23 17:48:43.366598: step: 980/1545, loss: 0.02661186456680298 2023-01-23 17:48:44.207388: step: 982/1545, loss: 0.07171963900327682 2023-01-23 17:48:45.049604: step: 984/1545, loss: 0.02651970461010933 2023-01-23 17:48:45.926336: step: 986/1545, loss: 0.012696822173893452 2023-01-23 17:48:46.838810: step: 988/1545, loss: 0.00012639534543268383 2023-01-23 17:48:47.686387: step: 990/1545, loss: 0.00018286629347130656 2023-01-23 17:48:48.542471: step: 992/1545, loss: 0.002376062562689185 2023-01-23 17:48:49.381093: step: 994/1545, loss: 0.0009518066071905196 2023-01-23 17:48:50.245417: step: 996/1545, loss: 0.015807710587978363 2023-01-23 17:48:51.150651: step: 998/1545, loss: 0.0007311393856070936 2023-01-23 17:48:52.032278: step: 1000/1545, loss: 0.12179150432348251 2023-01-23 17:48:52.944693: step: 1002/1545, loss: 0.007434425409883261 2023-01-23 17:48:53.808927: step: 1004/1545, loss: 0.007342632859945297 2023-01-23 17:48:54.683447: step: 1006/1545, loss: 0.024364622309803963 2023-01-23 17:48:55.603229: step: 1008/1545, loss: 0.008232003077864647 2023-01-23 17:48:56.479682: step: 1010/1545, loss: 9.493572724750265e-05 2023-01-23 17:48:57.368247: step: 1012/1545, loss: 0.057067885994911194 2023-01-23 17:48:58.292003: step: 1014/1545, loss: 0.0009213780285790563 2023-01-23 17:48:59.134958: step: 1016/1545, loss: 0.015391525812447071 2023-01-23 17:49:00.029651: step: 1018/1545, loss: 0.0009644926758483052 2023-01-23 17:49:00.911545: step: 1020/1545, loss: 0.0008476466173306108 2023-01-23 17:49:01.770758: step: 1022/1545, loss: 2.6908979415893555 2023-01-23 17:49:02.738191: step: 1024/1545, loss: 0.028054915368556976 2023-01-23 17:49:03.699806: step: 1026/1545, loss: 7.286344043677673e-05 2023-01-23 17:49:04.593266: step: 1028/1545, loss: 0.0005596276605501771 2023-01-23 17:49:05.487355: step: 1030/1545, loss: 0.007519464008510113 2023-01-23 17:49:06.421944: step: 1032/1545, loss: 0.06423339992761612 2023-01-23 17:49:07.292770: step: 1034/1545, loss: 0.0012069812510162592 2023-01-23 17:49:08.180709: step: 1036/1545, loss: 0.010793929919600487 2023-01-23 17:49:09.028902: step: 1038/1545, loss: 0.0001341447641607374 2023-01-23 17:49:09.858132: step: 1040/1545, loss: 0.003759687067940831 2023-01-23 17:49:10.718252: step: 1042/1545, loss: 0.005981770344078541 2023-01-23 17:49:11.596071: step: 1044/1545, loss: 0.005589775275439024 2023-01-23 17:49:12.460510: step: 1046/1545, loss: 0.00014789588749408722 2023-01-23 17:49:13.297597: step: 1048/1545, loss: 0.000768832047469914 2023-01-23 17:49:14.120992: step: 1050/1545, loss: 0.0038278065621852875 2023-01-23 17:49:15.035812: step: 1052/1545, loss: 0.000319973798468709 2023-01-23 17:49:15.905190: step: 1054/1545, loss: 0.036224979907274246 2023-01-23 17:49:16.756930: step: 1056/1545, loss: 0.0014808634296059608 2023-01-23 17:49:17.644259: step: 1058/1545, loss: 0.057717956602573395 2023-01-23 17:49:18.578982: step: 1060/1545, loss: 0.30555376410484314 2023-01-23 17:49:19.467476: step: 1062/1545, loss: 0.4848555326461792 2023-01-23 17:49:20.305759: step: 1064/1545, loss: 0.0257587693631649 2023-01-23 17:49:21.198608: step: 1066/1545, loss: 0.00022359171998687088 2023-01-23 17:49:22.090937: step: 1068/1545, loss: 0.0005875798524357378 2023-01-23 17:49:22.912323: step: 1070/1545, loss: 0.0002439755917293951 2023-01-23 17:49:23.756936: step: 1072/1545, loss: 1.745860390656162e-05 2023-01-23 17:49:24.660489: step: 1074/1545, loss: 0.032735541462898254 2023-01-23 17:49:25.515236: step: 1076/1545, loss: 0.0009328662417829037 2023-01-23 17:49:26.434071: step: 1078/1545, loss: 0.008114194497466087 2023-01-23 17:49:27.283323: step: 1080/1545, loss: 0.12864363193511963 2023-01-23 17:49:28.170585: step: 1082/1545, loss: 0.14578600227832794 2023-01-23 17:49:29.036511: step: 1084/1545, loss: 0.33618107438087463 2023-01-23 17:49:29.887820: step: 1086/1545, loss: 0.001804548199288547 2023-01-23 17:49:30.782419: step: 1088/1545, loss: 0.0010084992973133922 2023-01-23 17:49:31.685900: step: 1090/1545, loss: 0.0067460802383720875 2023-01-23 17:49:32.521554: step: 1092/1545, loss: 0.0007633332861587405 2023-01-23 17:49:33.378907: step: 1094/1545, loss: 0.04963426664471626 2023-01-23 17:49:34.258299: step: 1096/1545, loss: 0.00011428834841353819 2023-01-23 17:49:35.135475: step: 1098/1545, loss: 0.038982849568128586 2023-01-23 17:49:35.948689: step: 1100/1545, loss: 0.0023697305005043745 2023-01-23 17:49:36.834704: step: 1102/1545, loss: 0.18895360827445984 2023-01-23 17:49:37.729271: step: 1104/1545, loss: 0.006995570380240679 2023-01-23 17:49:38.691767: step: 1106/1545, loss: 0.18901105225086212 2023-01-23 17:49:39.564365: step: 1108/1545, loss: 0.07250846177339554 2023-01-23 17:49:40.457434: step: 1110/1545, loss: 0.0038227587938308716 2023-01-23 17:49:41.326411: step: 1112/1545, loss: 0.0011566552566364408 2023-01-23 17:49:42.174886: step: 1114/1545, loss: 0.0024722174275666475 2023-01-23 17:49:43.021669: step: 1116/1545, loss: 0.0009163530776277184 2023-01-23 17:49:43.924762: step: 1118/1545, loss: 0.015322994440793991 2023-01-23 17:49:44.833037: step: 1120/1545, loss: 0.008642406202852726 2023-01-23 17:49:45.714944: step: 1122/1545, loss: 0.0009542652405798435 2023-01-23 17:49:46.574416: step: 1124/1545, loss: 0.20682315528392792 2023-01-23 17:49:47.521925: step: 1126/1545, loss: 0.007323004771023989 2023-01-23 17:49:48.416393: step: 1128/1545, loss: 0.006751327309757471 2023-01-23 17:49:49.331523: step: 1130/1545, loss: 0.004414219409227371 2023-01-23 17:49:50.212358: step: 1132/1545, loss: 0.14515450596809387 2023-01-23 17:49:51.090888: step: 1134/1545, loss: 0.00012233595771249384 2023-01-23 17:49:51.964137: step: 1136/1545, loss: 0.0001588190789334476 2023-01-23 17:49:52.845899: step: 1138/1545, loss: 0.0033059369307011366 2023-01-23 17:49:53.710055: step: 1140/1545, loss: 0.0005888629239052534 2023-01-23 17:49:54.631095: step: 1142/1545, loss: 0.000662457023281604 2023-01-23 17:49:55.510780: step: 1144/1545, loss: 3.424865280976519e-05 2023-01-23 17:49:56.387594: step: 1146/1545, loss: 0.0003050824161618948 2023-01-23 17:49:57.235423: step: 1148/1545, loss: 0.00044944448745809495 2023-01-23 17:49:58.089364: step: 1150/1545, loss: 0.07640665024518967 2023-01-23 17:49:58.984137: step: 1152/1545, loss: 0.00781724788248539 2023-01-23 17:49:59.869588: step: 1154/1545, loss: 0.006986512802541256 2023-01-23 17:50:00.744385: step: 1156/1545, loss: 0.03579159453511238 2023-01-23 17:50:01.617559: step: 1158/1545, loss: 0.0027157163713127375 2023-01-23 17:50:02.537355: step: 1160/1545, loss: 0.4636869728565216 2023-01-23 17:50:03.418207: step: 1162/1545, loss: 0.00742397690191865 2023-01-23 17:50:04.298008: step: 1164/1545, loss: 0.40836381912231445 2023-01-23 17:50:05.199526: step: 1166/1545, loss: 0.004351871088147163 2023-01-23 17:50:06.080859: step: 1168/1545, loss: 0.001488818321377039 2023-01-23 17:50:06.987430: step: 1170/1545, loss: 0.003198568942025304 2023-01-23 17:50:07.897119: step: 1172/1545, loss: 0.0003386429452802986 2023-01-23 17:50:08.762881: step: 1174/1545, loss: 0.006424922961741686 2023-01-23 17:50:09.612180: step: 1176/1545, loss: 0.03089495375752449 2023-01-23 17:50:10.445187: step: 1178/1545, loss: 0.006121509708464146 2023-01-23 17:50:11.322537: step: 1180/1545, loss: 0.0002322526997886598 2023-01-23 17:50:12.218667: step: 1182/1545, loss: 0.00729106180369854 2023-01-23 17:50:13.096340: step: 1184/1545, loss: 0.3869536817073822 2023-01-23 17:50:14.029633: step: 1186/1545, loss: 0.005920626688748598 2023-01-23 17:50:14.900210: step: 1188/1545, loss: 0.08359375596046448 2023-01-23 17:50:15.793862: step: 1190/1545, loss: 0.02695314958691597 2023-01-23 17:50:16.674787: step: 1192/1545, loss: 0.021477755159139633 2023-01-23 17:50:17.572966: step: 1194/1545, loss: 0.00036851284676231444 2023-01-23 17:50:18.451046: step: 1196/1545, loss: 0.0002759865019470453 2023-01-23 17:50:19.337859: step: 1198/1545, loss: 8.590657671447843e-05 2023-01-23 17:50:20.271543: step: 1200/1545, loss: 0.004969241097569466 2023-01-23 17:50:21.201319: step: 1202/1545, loss: 0.003372147213667631 2023-01-23 17:50:22.079446: step: 1204/1545, loss: 0.00023278649314306676 2023-01-23 17:50:22.970039: step: 1206/1545, loss: 0.012917018495500088 2023-01-23 17:50:23.820791: step: 1208/1545, loss: 0.0005300609045661986 2023-01-23 17:50:24.717156: step: 1210/1545, loss: 0.2298760712146759 2023-01-23 17:50:25.591220: step: 1212/1545, loss: 0.02271582931280136 2023-01-23 17:50:26.466599: step: 1214/1545, loss: 0.0068434481509029865 2023-01-23 17:50:27.378385: step: 1216/1545, loss: 0.0010449911933392286 2023-01-23 17:50:28.250010: step: 1218/1545, loss: 0.24892692267894745 2023-01-23 17:50:29.126720: step: 1220/1545, loss: 0.2289014458656311 2023-01-23 17:50:29.977127: step: 1222/1545, loss: 0.0002567390911281109 2023-01-23 17:50:30.816262: step: 1224/1545, loss: 0.0008028792217373848 2023-01-23 17:50:31.689470: step: 1226/1545, loss: 0.19579936563968658 2023-01-23 17:50:32.571089: step: 1228/1545, loss: 0.5920469164848328 2023-01-23 17:50:33.426417: step: 1230/1545, loss: 0.003597534727305174 2023-01-23 17:50:34.325981: step: 1232/1545, loss: 0.024060240015387535 2023-01-23 17:50:35.189763: step: 1234/1545, loss: 0.09293581545352936 2023-01-23 17:50:36.087468: step: 1236/1545, loss: 0.0026984538417309523 2023-01-23 17:50:36.943058: step: 1238/1545, loss: 0.0003406027390155941 2023-01-23 17:50:37.881378: step: 1240/1545, loss: 0.0019295546226203442 2023-01-23 17:50:38.718492: step: 1242/1545, loss: 0.0001349778613075614 2023-01-23 17:50:39.639666: step: 1244/1545, loss: 0.004537339322268963 2023-01-23 17:50:40.493533: step: 1246/1545, loss: 0.0014489262830466032 2023-01-23 17:50:41.359964: step: 1248/1545, loss: 0.002229526871815324 2023-01-23 17:50:42.210110: step: 1250/1545, loss: 0.0032333219423890114 2023-01-23 17:50:43.114515: step: 1252/1545, loss: 0.3408490717411041 2023-01-23 17:50:43.961029: step: 1254/1545, loss: 0.0011515787336975336 2023-01-23 17:50:44.810663: step: 1256/1545, loss: 0.10171663761138916 2023-01-23 17:50:45.706142: step: 1258/1545, loss: 0.00018941953021567315 2023-01-23 17:50:46.656458: step: 1260/1545, loss: 0.0005904359859414399 2023-01-23 17:50:47.515314: step: 1262/1545, loss: 0.00027136446442455053 2023-01-23 17:50:48.360722: step: 1264/1545, loss: 0.018343018367886543 2023-01-23 17:50:49.212961: step: 1266/1545, loss: 0.0009674160392023623 2023-01-23 17:50:50.081668: step: 1268/1545, loss: 0.005537947174161673 2023-01-23 17:50:50.920683: step: 1270/1545, loss: 0.2415183037519455 2023-01-23 17:50:51.836152: step: 1272/1545, loss: 0.013121353462338448 2023-01-23 17:50:52.732144: step: 1274/1545, loss: 0.0001365483767585829 2023-01-23 17:50:53.610815: step: 1276/1545, loss: 5.222474646870978e-05 2023-01-23 17:50:54.482524: step: 1278/1545, loss: 0.0037734273355454206 2023-01-23 17:50:55.363545: step: 1280/1545, loss: 0.00023020742810331285 2023-01-23 17:50:56.224946: step: 1282/1545, loss: 0.39723291993141174 2023-01-23 17:50:57.088779: step: 1284/1545, loss: 0.5545098185539246 2023-01-23 17:50:57.933395: step: 1286/1545, loss: 0.0004227978643029928 2023-01-23 17:50:58.813708: step: 1288/1545, loss: 0.08786103129386902 2023-01-23 17:50:59.772382: step: 1290/1545, loss: 0.06203702837228775 2023-01-23 17:51:00.620869: step: 1292/1545, loss: 0.0004140663950238377 2023-01-23 17:51:01.445015: step: 1294/1545, loss: 0.0001847204694058746 2023-01-23 17:51:02.338864: step: 1296/1545, loss: 0.15625745058059692 2023-01-23 17:51:03.173360: step: 1298/1545, loss: 0.014629537239670753 2023-01-23 17:51:04.079600: step: 1300/1545, loss: 0.06821423768997192 2023-01-23 17:51:04.940946: step: 1302/1545, loss: 0.002970377216115594 2023-01-23 17:51:05.826309: step: 1304/1545, loss: 0.14382702112197876 2023-01-23 17:51:06.708735: step: 1306/1545, loss: 0.10630563646554947 2023-01-23 17:51:07.608157: step: 1308/1545, loss: 0.07125456631183624 2023-01-23 17:51:08.532162: step: 1310/1545, loss: 0.010611740872263908 2023-01-23 17:51:09.391794: step: 1312/1545, loss: 0.014880693517625332 2023-01-23 17:51:10.222212: step: 1314/1545, loss: 0.04826577007770538 2023-01-23 17:51:11.115928: step: 1316/1545, loss: 0.001139822998084128 2023-01-23 17:51:11.974232: step: 1318/1545, loss: 0.005122194066643715 2023-01-23 17:51:12.902657: step: 1320/1545, loss: 0.0011681318283081055 2023-01-23 17:51:13.779265: step: 1322/1545, loss: 0.0024470670614391565 2023-01-23 17:51:14.660969: step: 1324/1545, loss: 0.0038203392177820206 2023-01-23 17:51:15.525089: step: 1326/1545, loss: 0.0013201349647715688 2023-01-23 17:51:16.396006: step: 1328/1545, loss: 0.005996120162308216 2023-01-23 17:51:17.242646: step: 1330/1545, loss: 0.0001447070244466886 2023-01-23 17:51:18.103833: step: 1332/1545, loss: 0.00015532711404375732 2023-01-23 17:51:18.979772: step: 1334/1545, loss: 0.1545567661523819 2023-01-23 17:51:19.854905: step: 1336/1545, loss: 1.2090373039245605 2023-01-23 17:51:20.715851: step: 1338/1545, loss: 0.00012285145930945873 2023-01-23 17:51:21.574915: step: 1340/1545, loss: 0.0012411728966981173 2023-01-23 17:51:22.437155: step: 1342/1545, loss: 0.0001703541784081608 2023-01-23 17:51:23.373049: step: 1344/1545, loss: 0.008142692968249321 2023-01-23 17:51:24.233006: step: 1346/1545, loss: 0.019553566351532936 2023-01-23 17:51:25.114452: step: 1348/1545, loss: 0.01233756821602583 2023-01-23 17:51:26.011395: step: 1350/1545, loss: 0.24950678646564484 2023-01-23 17:51:26.888561: step: 1352/1545, loss: -1.4766637832508422e-06 2023-01-23 17:51:27.793911: step: 1354/1545, loss: 0.0005398939829319715 2023-01-23 17:51:28.689895: step: 1356/1545, loss: 6.826745811849833e-05 2023-01-23 17:51:29.538361: step: 1358/1545, loss: 0.018249621614813805 2023-01-23 17:51:30.417857: step: 1360/1545, loss: 0.004110680893063545 2023-01-23 17:51:31.292287: step: 1362/1545, loss: 0.000405486993258819 2023-01-23 17:51:32.218509: step: 1364/1545, loss: 0.0020434213802218437 2023-01-23 17:51:33.114390: step: 1366/1545, loss: 0.001080064452253282 2023-01-23 17:51:33.975078: step: 1368/1545, loss: 0.0010414052521809936 2023-01-23 17:51:34.834546: step: 1370/1545, loss: 8.862185495672747e-05 2023-01-23 17:51:35.738973: step: 1372/1545, loss: 0.34101539850234985 2023-01-23 17:51:36.631912: step: 1374/1545, loss: 0.24357277154922485 2023-01-23 17:51:37.534292: step: 1376/1545, loss: 0.2766760289669037 2023-01-23 17:51:38.423156: step: 1378/1545, loss: 3.5787168599199504e-05 2023-01-23 17:51:39.275631: step: 1380/1545, loss: 0.0003091059916187078 2023-01-23 17:51:40.112127: step: 1382/1545, loss: 0.0006785736768506467 2023-01-23 17:51:41.001711: step: 1384/1545, loss: 0.0012734780320897698 2023-01-23 17:51:41.870012: step: 1386/1545, loss: 0.003243357641622424 2023-01-23 17:51:42.769039: step: 1388/1545, loss: 0.0001553086913190782 2023-01-23 17:51:43.643737: step: 1390/1545, loss: 4.6883647883078083e-05 2023-01-23 17:51:44.535247: step: 1392/1545, loss: 0.0019019392784684896 2023-01-23 17:51:45.394942: step: 1394/1545, loss: 0.00016917080210987478 2023-01-23 17:51:46.256304: step: 1396/1545, loss: 0.003055511275306344 2023-01-23 17:51:47.126848: step: 1398/1545, loss: 0.00846212450414896 2023-01-23 17:51:48.093308: step: 1400/1545, loss: 0.0003765653818845749 2023-01-23 17:51:48.979966: step: 1402/1545, loss: 0.00011974696826655418 2023-01-23 17:51:49.846239: step: 1404/1545, loss: 9.105855133384466e-05 2023-01-23 17:51:50.728807: step: 1406/1545, loss: 0.08718296885490417 2023-01-23 17:51:51.614190: step: 1408/1545, loss: 0.01053337287157774 2023-01-23 17:51:52.550546: step: 1410/1545, loss: 0.01672876812517643 2023-01-23 17:51:53.468017: step: 1412/1545, loss: 0.019779805094003677 2023-01-23 17:51:54.379236: step: 1414/1545, loss: 0.00047766644274815917 2023-01-23 17:51:55.230572: step: 1416/1545, loss: 0.10698382556438446 2023-01-23 17:51:56.157055: step: 1418/1545, loss: 0.18801358342170715 2023-01-23 17:51:57.010798: step: 1420/1545, loss: 0.00035789713729172945 2023-01-23 17:51:57.885656: step: 1422/1545, loss: 0.1113024428486824 2023-01-23 17:51:58.884558: step: 1424/1545, loss: 0.007968731224536896 2023-01-23 17:51:59.749857: step: 1426/1545, loss: 0.03429596871137619 2023-01-23 17:52:00.688838: step: 1428/1545, loss: 0.5124109387397766 2023-01-23 17:52:01.509165: step: 1430/1545, loss: 1.9759734641411342e-05 2023-01-23 17:52:02.406153: step: 1432/1545, loss: 0.12284232676029205 2023-01-23 17:52:03.379528: step: 1434/1545, loss: 0.006280809640884399 2023-01-23 17:52:04.283875: step: 1436/1545, loss: 0.0007520067738369107 2023-01-23 17:52:05.132980: step: 1438/1545, loss: 2.4448278054478578e-05 2023-01-23 17:52:06.041886: step: 1440/1545, loss: 0.0022965953685343266 2023-01-23 17:52:06.923185: step: 1442/1545, loss: 0.2254042625427246 2023-01-23 17:52:07.797657: step: 1444/1545, loss: 0.0002037310623563826 2023-01-23 17:52:08.805153: step: 1446/1545, loss: 0.0006380230188369751 2023-01-23 17:52:09.685818: step: 1448/1545, loss: 1.1205140352249146 2023-01-23 17:52:10.574320: step: 1450/1545, loss: 0.004571598954498768 2023-01-23 17:52:11.413916: step: 1452/1545, loss: 0.01446791272610426 2023-01-23 17:52:12.268410: step: 1454/1545, loss: 0.009313295595347881 2023-01-23 17:52:13.107348: step: 1456/1545, loss: 0.6147128343582153 2023-01-23 17:52:14.083835: step: 1458/1545, loss: 0.24593541026115417 2023-01-23 17:52:14.940450: step: 1460/1545, loss: 0.0026195647660642862 2023-01-23 17:52:15.828026: step: 1462/1545, loss: 0.0025644092820584774 2023-01-23 17:52:16.681202: step: 1464/1545, loss: 0.08868304640054703 2023-01-23 17:52:17.532641: step: 1466/1545, loss: 2.7102383683086373e-05 2023-01-23 17:52:18.412421: step: 1468/1545, loss: 0.0003362232819199562 2023-01-23 17:52:19.329048: step: 1470/1545, loss: 0.0007352659595198929 2023-01-23 17:52:20.230933: step: 1472/1545, loss: 0.24146252870559692 2023-01-23 17:52:21.121018: step: 1474/1545, loss: 0.06962800025939941 2023-01-23 17:52:22.078419: step: 1476/1545, loss: 0.1823236346244812 2023-01-23 17:52:22.979799: step: 1478/1545, loss: 0.00046119140461087227 2023-01-23 17:52:23.830112: step: 1480/1545, loss: 0.015891965478658676 2023-01-23 17:52:24.733229: step: 1482/1545, loss: 0.45971065759658813 2023-01-23 17:52:25.571981: step: 1484/1545, loss: 0.0003357878013048321 2023-01-23 17:52:26.446300: step: 1486/1545, loss: 7.436702435370535e-05 2023-01-23 17:52:27.363258: step: 1488/1545, loss: 0.0009917622664943337 2023-01-23 17:52:28.255110: step: 1490/1545, loss: 0.33603566884994507 2023-01-23 17:52:29.182919: step: 1492/1545, loss: 0.0031340226996690035 2023-01-23 17:52:30.106948: step: 1494/1545, loss: 0.17850711941719055 2023-01-23 17:52:30.994211: step: 1496/1545, loss: 0.10244397819042206 2023-01-23 17:52:31.854650: step: 1498/1545, loss: 0.014100289903581142 2023-01-23 17:52:32.772523: step: 1500/1545, loss: 0.00012653888552449644 2023-01-23 17:52:33.625850: step: 1502/1545, loss: 0.0025237223599106073 2023-01-23 17:52:34.539978: step: 1504/1545, loss: 0.008242940530180931 2023-01-23 17:52:35.447881: step: 1506/1545, loss: 0.004627970512956381 2023-01-23 17:52:36.294666: step: 1508/1545, loss: 0.01170598715543747 2023-01-23 17:52:37.151793: step: 1510/1545, loss: 0.14796215295791626 2023-01-23 17:52:38.003144: step: 1512/1545, loss: 0.002075984375551343 2023-01-23 17:52:38.901602: step: 1514/1545, loss: 0.0005355538451112807 2023-01-23 17:52:39.791275: step: 1516/1545, loss: 0.0002593421668279916 2023-01-23 17:52:40.658867: step: 1518/1545, loss: 0.0012238163035362959 2023-01-23 17:52:41.551340: step: 1520/1545, loss: 0.17766067385673523 2023-01-23 17:52:42.426419: step: 1522/1545, loss: 0.1419127732515335 2023-01-23 17:52:43.310261: step: 1524/1545, loss: 0.11698576807975769 2023-01-23 17:52:44.202991: step: 1526/1545, loss: 0.0609152652323246 2023-01-23 17:52:45.080608: step: 1528/1545, loss: 0.006193014793097973 2023-01-23 17:52:45.958698: step: 1530/1545, loss: 0.2927083373069763 2023-01-23 17:52:46.800970: step: 1532/1545, loss: 0.00606564013287425 2023-01-23 17:52:47.703164: step: 1534/1545, loss: 0.34565699100494385 2023-01-23 17:52:48.607350: step: 1536/1545, loss: 0.045815397053956985 2023-01-23 17:52:49.495327: step: 1538/1545, loss: 0.0010324277682229877 2023-01-23 17:52:50.447979: step: 1540/1545, loss: 0.42287662625312805 2023-01-23 17:52:51.339173: step: 1542/1545, loss: 0.0012695423793047667 2023-01-23 17:52:52.265057: step: 1544/1545, loss: 0.03704908490180969 2023-01-23 17:52:53.125580: step: 1546/1545, loss: 0.0004488310660235584 2023-01-23 17:52:53.998427: step: 1548/1545, loss: 0.1506108194589615 2023-01-23 17:52:54.854853: step: 1550/1545, loss: 0.0036048684269189835 2023-01-23 17:52:55.742934: step: 1552/1545, loss: 0.0015129329403862357 2023-01-23 17:52:56.604403: step: 1554/1545, loss: 0.00030163611518219113 2023-01-23 17:52:57.477954: step: 1556/1545, loss: 0.5548970699310303 2023-01-23 17:52:58.360822: step: 1558/1545, loss: 0.029374677687883377 2023-01-23 17:52:59.241556: step: 1560/1545, loss: 0.001455045072361827 2023-01-23 17:53:00.113006: step: 1562/1545, loss: 0.020714543759822845 2023-01-23 17:53:00.999943: step: 1564/1545, loss: 0.0698886513710022 2023-01-23 17:53:01.862900: step: 1566/1545, loss: 0.31130626797676086 2023-01-23 17:53:02.726152: step: 1568/1545, loss: 0.028789790347218513 2023-01-23 17:53:03.686771: step: 1570/1545, loss: 0.018603919073939323 2023-01-23 17:53:04.609285: step: 1572/1545, loss: 0.00037707958836108446 2023-01-23 17:53:05.473881: step: 1574/1545, loss: 0.01647358201444149 2023-01-23 17:53:06.359529: step: 1576/1545, loss: 0.10774773359298706 2023-01-23 17:53:07.212081: step: 1578/1545, loss: 0.0005729831173084676 2023-01-23 17:53:08.084352: step: 1580/1545, loss: 0.10397503525018692 2023-01-23 17:53:08.962434: step: 1582/1545, loss: 0.05215620994567871 2023-01-23 17:53:09.874882: step: 1584/1545, loss: 0.009730255231261253 2023-01-23 17:53:10.726724: step: 1586/1545, loss: 0.0033822094555944204 2023-01-23 17:53:11.606104: step: 1588/1545, loss: 0.002807219047099352 2023-01-23 17:53:12.450093: step: 1590/1545, loss: 0.0016366385389119387 2023-01-23 17:53:13.394201: step: 1592/1545, loss: 0.06497769802808762 2023-01-23 17:53:14.306967: step: 1594/1545, loss: 0.0008820568909868598 2023-01-23 17:53:15.192517: step: 1596/1545, loss: 0.044833019375801086 2023-01-23 17:53:16.091223: step: 1598/1545, loss: 0.0015559872845187783 2023-01-23 17:53:17.007143: step: 1600/1545, loss: 0.4402817189693451 2023-01-23 17:53:17.845166: step: 1602/1545, loss: 0.015987783670425415 2023-01-23 17:53:18.699896: step: 1604/1545, loss: 0.0011510293697938323 2023-01-23 17:53:19.550668: step: 1606/1545, loss: 0.027343953028321266 2023-01-23 17:53:20.470156: step: 1608/1545, loss: 0.009109662845730782 2023-01-23 17:53:21.324413: step: 1610/1545, loss: 0.1584756225347519 2023-01-23 17:53:22.189510: step: 1612/1545, loss: 0.018305553123354912 2023-01-23 17:53:23.076378: step: 1614/1545, loss: 0.003784777596592903 2023-01-23 17:53:23.957962: step: 1616/1545, loss: 0.2312593311071396 2023-01-23 17:53:24.860765: step: 1618/1545, loss: 0.007190978620201349 2023-01-23 17:53:25.731700: step: 1620/1545, loss: 0.0009220661595463753 2023-01-23 17:53:26.619611: step: 1622/1545, loss: 0.015856852754950523 2023-01-23 17:53:27.490369: step: 1624/1545, loss: 0.060062117874622345 2023-01-23 17:53:28.344619: step: 1626/1545, loss: 1.6765185594558716 2023-01-23 17:53:29.261300: step: 1628/1545, loss: 0.028053898364305496 2023-01-23 17:53:30.108339: step: 1630/1545, loss: 0.0007605307619087398 2023-01-23 17:53:30.961588: step: 1632/1545, loss: 0.000713242101483047 2023-01-23 17:53:31.842672: step: 1634/1545, loss: 0.010716349817812443 2023-01-23 17:53:32.707352: step: 1636/1545, loss: 0.004107157699763775 2023-01-23 17:53:33.569334: step: 1638/1545, loss: 0.0019971714355051517 2023-01-23 17:53:34.405992: step: 1640/1545, loss: 0.0034856374841183424 2023-01-23 17:53:35.296956: step: 1642/1545, loss: 0.001987259602174163 2023-01-23 17:53:36.210760: step: 1644/1545, loss: 0.005052954889833927 2023-01-23 17:53:37.063563: step: 1646/1545, loss: 0.003588145598769188 2023-01-23 17:53:37.957786: step: 1648/1545, loss: 0.003242447739467025 2023-01-23 17:53:38.866761: step: 1650/1545, loss: 0.0016278603579849005 2023-01-23 17:53:39.741722: step: 1652/1545, loss: 0.003947022370994091 2023-01-23 17:53:40.636059: step: 1654/1545, loss: 0.00642734207212925 2023-01-23 17:53:41.474482: step: 1656/1545, loss: 0.09637109935283661 2023-01-23 17:53:42.307515: step: 1658/1545, loss: 7.986255513969809e-05 2023-01-23 17:53:43.181125: step: 1660/1545, loss: 0.0039232345297932625 2023-01-23 17:53:44.065715: step: 1662/1545, loss: 0.00409358087927103 2023-01-23 17:53:44.918565: step: 1664/1545, loss: 0.34368693828582764 2023-01-23 17:53:45.787273: step: 1666/1545, loss: 0.01671886071562767 2023-01-23 17:53:46.642258: step: 1668/1545, loss: 0.0001178998572868295 2023-01-23 17:53:47.492910: step: 1670/1545, loss: 0.23500753939151764 2023-01-23 17:53:48.397069: step: 1672/1545, loss: 0.29063326120376587 2023-01-23 17:53:49.264000: step: 1674/1545, loss: 0.0026938095688819885 2023-01-23 17:53:50.140519: step: 1676/1545, loss: 0.004503187723457813 2023-01-23 17:53:51.095468: step: 1678/1545, loss: 0.10976151376962662 2023-01-23 17:53:51.963161: step: 1680/1545, loss: 0.11405583471059799 2023-01-23 17:53:52.828849: step: 1682/1545, loss: 0.002880366984754801 2023-01-23 17:53:53.714187: step: 1684/1545, loss: 0.24883891642093658 2023-01-23 17:53:54.643842: step: 1686/1545, loss: 0.20449338853359222 2023-01-23 17:53:55.522979: step: 1688/1545, loss: 0.002034401521086693 2023-01-23 17:53:56.399646: step: 1690/1545, loss: 0.004088061396032572 2023-01-23 17:53:57.294119: step: 1692/1545, loss: 0.005572275724261999 2023-01-23 17:53:58.192294: step: 1694/1545, loss: 0.19992214441299438 2023-01-23 17:53:59.088148: step: 1696/1545, loss: 0.003148710587993264 2023-01-23 17:53:59.943383: step: 1698/1545, loss: 0.14947935938835144 2023-01-23 17:54:00.798756: step: 1700/1545, loss: 0.000432911649113521 2023-01-23 17:54:01.646167: step: 1702/1545, loss: 0.02274971827864647 2023-01-23 17:54:02.589515: step: 1704/1545, loss: 0.00028457719599828124 2023-01-23 17:54:03.469344: step: 1706/1545, loss: 0.5045602917671204 2023-01-23 17:54:04.348587: step: 1708/1545, loss: 0.01375215407460928 2023-01-23 17:54:05.309190: step: 1710/1545, loss: 0.5872335433959961 2023-01-23 17:54:06.189255: step: 1712/1545, loss: 0.012450490146875381 2023-01-23 17:54:07.085916: step: 1714/1545, loss: 0.03202781826257706 2023-01-23 17:54:08.017649: step: 1716/1545, loss: 0.04783475026488304 2023-01-23 17:54:08.861757: step: 1718/1545, loss: 0.00267242593690753 2023-01-23 17:54:09.761676: step: 1720/1545, loss: 0.00019052611605729908 2023-01-23 17:54:10.631052: step: 1722/1545, loss: 0.6347764730453491 2023-01-23 17:54:11.503666: step: 1724/1545, loss: 0.06727328151464462 2023-01-23 17:54:12.384736: step: 1726/1545, loss: 0.1399015486240387 2023-01-23 17:54:13.310264: step: 1728/1545, loss: 0.008311651647090912 2023-01-23 17:54:14.233903: step: 1730/1545, loss: 0.49647948145866394 2023-01-23 17:54:15.131489: step: 1732/1545, loss: 0.6686055064201355 2023-01-23 17:54:16.100454: step: 1734/1545, loss: 0.002897239988669753 2023-01-23 17:54:16.967599: step: 1736/1545, loss: 0.02649141661822796 2023-01-23 17:54:17.836286: step: 1738/1545, loss: 0.001389363780617714 2023-01-23 17:54:18.715433: step: 1740/1545, loss: 0.005355041474103928 2023-01-23 17:54:19.691907: step: 1742/1545, loss: 0.13627886772155762 2023-01-23 17:54:20.582372: step: 1744/1545, loss: 0.016349589452147484 2023-01-23 17:54:21.478701: step: 1746/1545, loss: 0.001118089770898223 2023-01-23 17:54:22.400970: step: 1748/1545, loss: 0.00878805760294199 2023-01-23 17:54:23.271094: step: 1750/1545, loss: 0.12149103730916977 2023-01-23 17:54:24.135628: step: 1752/1545, loss: 0.003404084127396345 2023-01-23 17:54:25.013251: step: 1754/1545, loss: 0.002579622669145465 2023-01-23 17:54:25.904587: step: 1756/1545, loss: 0.06233954802155495 2023-01-23 17:54:26.747377: step: 1758/1545, loss: 0.0021605482324957848 2023-01-23 17:54:27.638285: step: 1760/1545, loss: 0.0010042840149253607 2023-01-23 17:54:28.545509: step: 1762/1545, loss: 0.06277024745941162 2023-01-23 17:54:29.521543: step: 1764/1545, loss: 8.547632023692131e-05 2023-01-23 17:54:30.375919: step: 1766/1545, loss: 0.09892036765813828 2023-01-23 17:54:31.238522: step: 1768/1545, loss: 0.03554138168692589 2023-01-23 17:54:32.103132: step: 1770/1545, loss: 0.05106548219919205 2023-01-23 17:54:32.936544: step: 1772/1545, loss: 0.6761460900306702 2023-01-23 17:54:33.830604: step: 1774/1545, loss: 0.003031159983947873 2023-01-23 17:54:34.782112: step: 1776/1545, loss: 0.008960632607340813 2023-01-23 17:54:35.711562: step: 1778/1545, loss: 0.13249821960926056 2023-01-23 17:54:36.548687: step: 1780/1545, loss: 0.0003266863932367414 2023-01-23 17:54:37.405890: step: 1782/1545, loss: 0.3356460630893707 2023-01-23 17:54:38.274690: step: 1784/1545, loss: 0.00011468136654002592 2023-01-23 17:54:39.207293: step: 1786/1545, loss: 0.128407821059227 2023-01-23 17:54:40.110103: step: 1788/1545, loss: 0.0008445805869996548 2023-01-23 17:54:41.037736: step: 1790/1545, loss: 0.13341277837753296 2023-01-23 17:54:41.964809: step: 1792/1545, loss: 0.05632244423031807 2023-01-23 17:54:42.848173: step: 1794/1545, loss: 0.01304079219698906 2023-01-23 17:54:43.718834: step: 1796/1545, loss: 0.0006671113078482449 2023-01-23 17:54:44.617485: step: 1798/1545, loss: 0.03014501929283142 2023-01-23 17:54:45.463750: step: 1800/1545, loss: 0.05823780223727226 2023-01-23 17:54:46.327765: step: 1802/1545, loss: 0.009558617137372494 2023-01-23 17:54:47.190850: step: 1804/1545, loss: 0.003517893608659506 2023-01-23 17:54:48.110494: step: 1806/1545, loss: 0.31350940465927124 2023-01-23 17:54:49.029969: step: 1808/1545, loss: 0.0004337377904448658 2023-01-23 17:54:49.908157: step: 1810/1545, loss: 0.00014766569074708968 2023-01-23 17:54:50.796185: step: 1812/1545, loss: 0.03401576355099678 2023-01-23 17:54:51.689592: step: 1814/1545, loss: 0.007426587864756584 2023-01-23 17:54:52.539613: step: 1816/1545, loss: 0.0899718627333641 2023-01-23 17:54:53.474605: step: 1818/1545, loss: 0.07939492166042328 2023-01-23 17:54:54.319163: step: 1820/1545, loss: 0.00033645593794062734 2023-01-23 17:54:55.185038: step: 1822/1545, loss: 0.031158003956079483 2023-01-23 17:54:56.027698: step: 1824/1545, loss: 0.011116750538349152 2023-01-23 17:54:56.903394: step: 1826/1545, loss: 0.001644861069507897 2023-01-23 17:54:57.839641: step: 1828/1545, loss: 4.600459214998409e-05 2023-01-23 17:54:58.757357: step: 1830/1545, loss: 0.467586874961853 2023-01-23 17:54:59.767232: step: 1832/1545, loss: 0.0002654671552591026 2023-01-23 17:55:00.648591: step: 1834/1545, loss: 0.002738649258390069 2023-01-23 17:55:01.498166: step: 1836/1545, loss: 0.0008232896798290312 2023-01-23 17:55:02.386167: step: 1838/1545, loss: 0.0007624095887877047 2023-01-23 17:55:03.272429: step: 1840/1545, loss: 0.0018185883527621627 2023-01-23 17:55:04.210188: step: 1842/1545, loss: 0.03607409819960594 2023-01-23 17:55:05.073442: step: 1844/1545, loss: 6.070678500691429e-05 2023-01-23 17:55:06.016656: step: 1846/1545, loss: 0.6707482933998108 2023-01-23 17:55:06.890863: step: 1848/1545, loss: 0.0009881067089736462 2023-01-23 17:55:07.781437: step: 1850/1545, loss: 0.0817195475101471 2023-01-23 17:55:08.686627: step: 1852/1545, loss: 0.0008385003311559558 2023-01-23 17:55:09.569971: step: 1854/1545, loss: 0.4532914459705353 2023-01-23 17:55:10.444109: step: 1856/1545, loss: 0.009325955994427204 2023-01-23 17:55:11.345680: step: 1858/1545, loss: 0.014259440824389458 2023-01-23 17:55:12.189642: step: 1860/1545, loss: 0.0029890844598412514 2023-01-23 17:55:13.043886: step: 1862/1545, loss: 0.3943525552749634 2023-01-23 17:55:13.962409: step: 1864/1545, loss: 0.20395904779434204 2023-01-23 17:55:14.852978: step: 1866/1545, loss: 0.13048382103443146 2023-01-23 17:55:15.741792: step: 1868/1545, loss: 0.0033405288122594357 2023-01-23 17:55:16.630741: step: 1870/1545, loss: 0.024646416306495667 2023-01-23 17:55:17.473232: step: 1872/1545, loss: 0.016284162178635597 2023-01-23 17:55:18.362924: step: 1874/1545, loss: 0.09761137515306473 2023-01-23 17:55:19.287297: step: 1876/1545, loss: 0.0030772278551012278 2023-01-23 17:55:20.161220: step: 1878/1545, loss: 0.01873154565691948 2023-01-23 17:55:21.039689: step: 1880/1545, loss: 0.2947714030742645 2023-01-23 17:55:21.951791: step: 1882/1545, loss: 0.0029724009800702333 2023-01-23 17:55:22.847656: step: 1884/1545, loss: 0.2864606976509094 2023-01-23 17:55:23.729369: step: 1886/1545, loss: 0.019294343888759613 2023-01-23 17:55:24.569478: step: 1888/1545, loss: 0.008279787376523018 2023-01-23 17:55:25.367643: step: 1890/1545, loss: 0.00046545761870220304 2023-01-23 17:55:26.240253: step: 1892/1545, loss: 0.004918655380606651 2023-01-23 17:55:27.111463: step: 1894/1545, loss: 2.8102152347564697 2023-01-23 17:55:27.980877: step: 1896/1545, loss: 0.0025308863259851933 2023-01-23 17:55:28.856091: step: 1898/1545, loss: 0.0046895393170416355 2023-01-23 17:55:29.756874: step: 1900/1545, loss: 0.002918347716331482 2023-01-23 17:55:30.636644: step: 1902/1545, loss: 0.0006188030820339918 2023-01-23 17:55:31.505431: step: 1904/1545, loss: 0.005580256227403879 2023-01-23 17:55:32.384416: step: 1906/1545, loss: 0.000280199630651623 2023-01-23 17:55:33.270148: step: 1908/1545, loss: 0.048670921474695206 2023-01-23 17:55:34.152991: step: 1910/1545, loss: 0.018996544182300568 2023-01-23 17:55:35.077148: step: 1912/1545, loss: 0.07876848429441452 2023-01-23 17:55:35.944910: step: 1914/1545, loss: 0.0008482688572257757 2023-01-23 17:55:36.802942: step: 1916/1545, loss: 0.03189694881439209 2023-01-23 17:55:37.660945: step: 1918/1545, loss: 0.007746600080281496 2023-01-23 17:55:38.514678: step: 1920/1545, loss: 0.0005071301129646599 2023-01-23 17:55:39.416926: step: 1922/1545, loss: 0.0031159324571490288 2023-01-23 17:55:40.341730: step: 1924/1545, loss: 0.11502476781606674 2023-01-23 17:55:41.232857: step: 1926/1545, loss: 0.0027130544185638428 2023-01-23 17:55:42.138013: step: 1928/1545, loss: 0.005593540146946907 2023-01-23 17:55:42.991296: step: 1930/1545, loss: 0.03925834968686104 2023-01-23 17:55:43.877094: step: 1932/1545, loss: 0.07116322964429855 2023-01-23 17:55:44.764789: step: 1934/1545, loss: 0.00019443186465650797 2023-01-23 17:55:45.637094: step: 1936/1545, loss: 0.002687673084437847 2023-01-23 17:55:46.535135: step: 1938/1545, loss: 6.948188092792407e-05 2023-01-23 17:55:47.401561: step: 1940/1545, loss: 0.00028918858151882887 2023-01-23 17:55:48.257282: step: 1942/1545, loss: 0.010021788999438286 2023-01-23 17:55:49.135813: step: 1944/1545, loss: 0.009490396827459335 2023-01-23 17:55:50.012168: step: 1946/1545, loss: 0.0011553176445886493 2023-01-23 17:55:50.850542: step: 1948/1545, loss: 0.33142462372779846 2023-01-23 17:55:51.783451: step: 1950/1545, loss: 0.0010515734320506454 2023-01-23 17:55:52.635500: step: 1952/1545, loss: 0.0012898123823106289 2023-01-23 17:55:53.479946: step: 1954/1545, loss: 0.00038893811870366335 2023-01-23 17:55:54.376945: step: 1956/1545, loss: 0.007092196960002184 2023-01-23 17:55:55.254379: step: 1958/1545, loss: 0.11964806169271469 2023-01-23 17:55:56.144758: step: 1960/1545, loss: 0.11783434450626373 2023-01-23 17:55:57.016185: step: 1962/1545, loss: 0.0017608810449019074 2023-01-23 17:55:57.895401: step: 1964/1545, loss: 0.006038110237568617 2023-01-23 17:55:58.839368: step: 1966/1545, loss: 0.1118609756231308 2023-01-23 17:55:59.743317: step: 1968/1545, loss: 0.001439258805476129 2023-01-23 17:56:00.585618: step: 1970/1545, loss: 0.00011420306691434234 2023-01-23 17:56:01.449460: step: 1972/1545, loss: 0.0771966204047203 2023-01-23 17:56:02.349079: step: 1974/1545, loss: 0.002102868165820837 2023-01-23 17:56:03.219794: step: 1976/1545, loss: 0.029420092701911926 2023-01-23 17:56:04.162411: step: 1978/1545, loss: 0.0066145239397883415 2023-01-23 17:56:05.084750: step: 1980/1545, loss: 0.05510246753692627 2023-01-23 17:56:05.982372: step: 1982/1545, loss: 0.01261208113282919 2023-01-23 17:56:06.867720: step: 1984/1545, loss: 0.6386898159980774 2023-01-23 17:56:07.752108: step: 1986/1545, loss: 0.5547707676887512 2023-01-23 17:56:08.630018: step: 1988/1545, loss: 0.17433616518974304 2023-01-23 17:56:09.535576: step: 1990/1545, loss: 0.009211604483425617 2023-01-23 17:56:10.438234: step: 1992/1545, loss: 0.0015614219009876251 2023-01-23 17:56:11.345698: step: 1994/1545, loss: 0.23322004079818726 2023-01-23 17:56:12.210808: step: 1996/1545, loss: 0.16143834590911865 2023-01-23 17:56:13.117005: step: 1998/1545, loss: 0.02123037353157997 2023-01-23 17:56:14.028602: step: 2000/1545, loss: 0.04613557085394859 2023-01-23 17:56:14.910971: step: 2002/1545, loss: 0.0005184125620871782 2023-01-23 17:56:15.781201: step: 2004/1545, loss: 0.00031002817559055984 2023-01-23 17:56:16.650911: step: 2006/1545, loss: 0.5511999726295471 2023-01-23 17:56:17.489349: step: 2008/1545, loss: 0.0004003041540272534 2023-01-23 17:56:18.377353: step: 2010/1545, loss: 0.16670210659503937 2023-01-23 17:56:19.283964: step: 2012/1545, loss: 0.005640122573822737 2023-01-23 17:56:20.140990: step: 2014/1545, loss: 0.00040249680751003325 2023-01-23 17:56:21.027120: step: 2016/1545, loss: 0.000317112251650542 2023-01-23 17:56:21.947067: step: 2018/1545, loss: 0.07879992574453354 2023-01-23 17:56:22.869452: step: 2020/1545, loss: 0.0022122259251773357 2023-01-23 17:56:23.784727: step: 2022/1545, loss: 0.09267380833625793 2023-01-23 17:56:24.699315: step: 2024/1545, loss: 0.0003564275102689862 2023-01-23 17:56:25.557389: step: 2026/1545, loss: 0.03548767790198326 2023-01-23 17:56:26.457558: step: 2028/1545, loss: 0.07766350358724594 2023-01-23 17:56:27.340111: step: 2030/1545, loss: 0.0003982180205639452 2023-01-23 17:56:28.193028: step: 2032/1545, loss: 0.08519390225410461 2023-01-23 17:56:29.043116: step: 2034/1545, loss: 0.0008779150084592402 2023-01-23 17:56:29.902732: step: 2036/1545, loss: 0.015907173976302147 2023-01-23 17:56:30.755003: step: 2038/1545, loss: 0.007088073529303074 2023-01-23 17:56:31.650150: step: 2040/1545, loss: 0.0014522112905979156 2023-01-23 17:56:32.542769: step: 2042/1545, loss: 0.0008080207626335323 2023-01-23 17:56:33.461491: step: 2044/1545, loss: 0.003063166979700327 2023-01-23 17:56:34.317969: step: 2046/1545, loss: 0.0010182108962908387 2023-01-23 17:56:35.248226: step: 2048/1545, loss: 0.0007336531998589635 2023-01-23 17:56:36.121997: step: 2050/1545, loss: 0.01712001860141754 2023-01-23 17:56:37.032563: step: 2052/1545, loss: 0.12388678640127182 2023-01-23 17:56:37.933055: step: 2054/1545, loss: 0.008088569156825542 2023-01-23 17:56:38.830410: step: 2056/1545, loss: 0.007284346967935562 2023-01-23 17:56:39.699641: step: 2058/1545, loss: 0.015826061367988586 2023-01-23 17:56:40.571959: step: 2060/1545, loss: 0.06114006042480469 2023-01-23 17:56:41.539164: step: 2062/1545, loss: 0.039184849709272385 2023-01-23 17:56:42.459651: step: 2064/1545, loss: 0.06523023545742035 2023-01-23 17:56:43.351079: step: 2066/1545, loss: 0.011568514630198479 2023-01-23 17:56:44.265302: step: 2068/1545, loss: 0.04578350484371185 2023-01-23 17:56:45.365779: step: 2070/1545, loss: 0.00038657651748508215 2023-01-23 17:56:46.193759: step: 2072/1545, loss: 0.0006730139721184969 2023-01-23 17:56:47.163634: step: 2074/1545, loss: 0.0002697959425859153 2023-01-23 17:56:48.043376: step: 2076/1545, loss: 0.00036504401941783726 2023-01-23 17:56:48.947272: step: 2078/1545, loss: 0.0018543272744864225 2023-01-23 17:56:49.781134: step: 2080/1545, loss: 0.0006363015272654593 2023-01-23 17:56:50.679163: step: 2082/1545, loss: 7.634711801074445e-05 2023-01-23 17:56:51.589630: step: 2084/1545, loss: 0.0002375664480496198 2023-01-23 17:56:52.463098: step: 2086/1545, loss: -1.3559594663092867e-05 2023-01-23 17:56:53.459477: step: 2088/1545, loss: 0.0002464082499500364 2023-01-23 17:56:54.337843: step: 2090/1545, loss: 0.0005862914840690792 2023-01-23 17:56:55.210623: step: 2092/1545, loss: 0.0029381231870502234 2023-01-23 17:56:56.059542: step: 2094/1545, loss: 0.001633751206099987 2023-01-23 17:56:56.965057: step: 2096/1545, loss: 0.2570534646511078 2023-01-23 17:56:57.847457: step: 2098/1545, loss: 0.002397548407316208 2023-01-23 17:56:58.854559: step: 2100/1545, loss: 0.007704377174377441 2023-01-23 17:56:59.749617: step: 2102/1545, loss: 0.000913987634703517 2023-01-23 17:57:00.623393: step: 2104/1545, loss: 0.009202877059578896 2023-01-23 17:57:01.510410: step: 2106/1545, loss: 0.005212232004851103 2023-01-23 17:57:02.356395: step: 2108/1545, loss: 2.7471691282698885e-05 2023-01-23 17:57:03.240424: step: 2110/1545, loss: 5.744837108068168e-05 2023-01-23 17:57:04.137951: step: 2112/1545, loss: 0.0006482204189524055 2023-01-23 17:57:05.029332: step: 2114/1545, loss: 0.002608578186482191 2023-01-23 17:57:05.942649: step: 2116/1545, loss: 0.22921441495418549 2023-01-23 17:57:06.831092: step: 2118/1545, loss: 0.6391940712928772 2023-01-23 17:57:07.682992: step: 2120/1545, loss: 0.0011241508182138205 2023-01-23 17:57:08.584161: step: 2122/1545, loss: 0.006238806992769241 2023-01-23 17:57:09.479745: step: 2124/1545, loss: 0.024431951344013214 2023-01-23 17:57:10.361672: step: 2126/1545, loss: 0.06898964941501617 2023-01-23 17:57:11.281311: step: 2128/1545, loss: 0.004613072611391544 2023-01-23 17:57:12.165421: step: 2130/1545, loss: 0.08522801101207733 2023-01-23 17:57:12.992521: step: 2132/1545, loss: 0.0035653458908200264 2023-01-23 17:57:13.848557: step: 2134/1545, loss: 0.07645155489444733 2023-01-23 17:57:14.708111: step: 2136/1545, loss: 0.08069465309381485 2023-01-23 17:57:15.601763: step: 2138/1545, loss: 0.06546644866466522 2023-01-23 17:57:16.499830: step: 2140/1545, loss: 0.00010054583253804594 2023-01-23 17:57:17.396177: step: 2142/1545, loss: 0.5731473565101624 2023-01-23 17:57:18.308394: step: 2144/1545, loss: 0.0076502105221152306 2023-01-23 17:57:19.168765: step: 2146/1545, loss: 0.02822941727936268 2023-01-23 17:57:20.076981: step: 2148/1545, loss: 0.3842353820800781 2023-01-23 17:57:20.933676: step: 2150/1545, loss: 0.03384117782115936 2023-01-23 17:57:21.821906: step: 2152/1545, loss: 0.004848696291446686 2023-01-23 17:57:22.667635: step: 2154/1545, loss: 0.012040557339787483 2023-01-23 17:57:23.549409: step: 2156/1545, loss: 5.271017653285526e-05 2023-01-23 17:57:24.444578: step: 2158/1545, loss: 0.43886178731918335 2023-01-23 17:57:25.306020: step: 2160/1545, loss: 0.0004722739104181528 2023-01-23 17:57:26.204123: step: 2162/1545, loss: 0.005363863427191973 2023-01-23 17:57:27.084906: step: 2164/1545, loss: 6.75145784043707e-05 2023-01-23 17:57:27.990695: step: 2166/1545, loss: 0.012163070961833 2023-01-23 17:57:28.860790: step: 2168/1545, loss: 0.4292050302028656 2023-01-23 17:57:29.725454: step: 2170/1545, loss: 0.003791085910052061 2023-01-23 17:57:30.626961: step: 2172/1545, loss: 0.4943540394306183 2023-01-23 17:57:31.511472: step: 2174/1545, loss: 0.17124322056770325 2023-01-23 17:57:32.387013: step: 2176/1545, loss: 0.012023367919027805 2023-01-23 17:57:33.277463: step: 2178/1545, loss: 0.4247865080833435 2023-01-23 17:57:34.162839: step: 2180/1545, loss: 0.014923914335668087 2023-01-23 17:57:35.066105: step: 2182/1545, loss: 0.4208316206932068 2023-01-23 17:57:35.950220: step: 2184/1545, loss: 0.048912037163972855 2023-01-23 17:57:36.855476: step: 2186/1545, loss: 0.010711919516324997 2023-01-23 17:57:37.753243: step: 2188/1545, loss: 0.0001327377394773066 2023-01-23 17:57:38.626414: step: 2190/1545, loss: 0.01991838403046131 2023-01-23 17:57:39.463577: step: 2192/1545, loss: 0.5840269327163696 2023-01-23 17:57:40.326934: step: 2194/1545, loss: 0.0002757787879090756 2023-01-23 17:57:41.186602: step: 2196/1545, loss: 0.0016260097036138177 2023-01-23 17:57:42.048500: step: 2198/1545, loss: 0.0002694384311325848 2023-01-23 17:57:42.929848: step: 2200/1545, loss: 0.0030843049753457308 2023-01-23 17:57:43.820590: step: 2202/1545, loss: 0.0018116907449439168 2023-01-23 17:57:44.712444: step: 2204/1545, loss: 0.007471936754882336 2023-01-23 17:57:45.622367: step: 2206/1545, loss: 0.33425208926200867 2023-01-23 17:57:46.541566: step: 2208/1545, loss: 0.007797606755048037 2023-01-23 17:57:47.453254: step: 2210/1545, loss: 0.007177440915256739 2023-01-23 17:57:48.369074: step: 2212/1545, loss: 0.00021663692314177752 2023-01-23 17:57:49.235346: step: 2214/1545, loss: 0.012990118935704231 2023-01-23 17:57:50.101418: step: 2216/1545, loss: 0.046909257769584656 2023-01-23 17:57:50.958215: step: 2218/1545, loss: 0.007050857413560152 2023-01-23 17:57:51.867650: step: 2220/1545, loss: 0.0050413599237799644 2023-01-23 17:57:52.841813: step: 2222/1545, loss: 0.0005599219584837556 2023-01-23 17:57:53.727704: step: 2224/1545, loss: 0.0017454683547839522 2023-01-23 17:57:54.584803: step: 2226/1545, loss: 0.16227692365646362 2023-01-23 17:57:55.467881: step: 2228/1545, loss: 0.04534948617219925 2023-01-23 17:57:56.340727: step: 2230/1545, loss: 0.0068688238970935345 2023-01-23 17:57:57.262770: step: 2232/1545, loss: 0.0013811084209010005 2023-01-23 17:57:58.076122: step: 2234/1545, loss: 0.0039847129955887794 2023-01-23 17:57:58.945760: step: 2236/1545, loss: 0.015991756692528725 2023-01-23 17:57:59.891237: step: 2238/1545, loss: 0.0005618436844088137 2023-01-23 17:58:00.732086: step: 2240/1545, loss: 0.0011282615596428514 2023-01-23 17:58:01.582137: step: 2242/1545, loss: 0.031149109825491905 2023-01-23 17:58:02.463914: step: 2244/1545, loss: 0.02663937211036682 2023-01-23 17:58:03.329822: step: 2246/1545, loss: 0.0183954406529665 2023-01-23 17:58:04.175895: step: 2248/1545, loss: 0.12985040247440338 2023-01-23 17:58:05.030606: step: 2250/1545, loss: 0.07726861536502838 2023-01-23 17:58:05.928444: step: 2252/1545, loss: 0.04227501153945923 2023-01-23 17:58:06.805601: step: 2254/1545, loss: 0.2530263662338257 2023-01-23 17:58:07.793944: step: 2256/1545, loss: 0.0022862781770527363 2023-01-23 17:58:08.710847: step: 2258/1545, loss: 0.006554113235324621 2023-01-23 17:58:09.561393: step: 2260/1545, loss: 1.610711115063168e-05 2023-01-23 17:58:10.400715: step: 2262/1545, loss: 0.0002817331696860492 2023-01-23 17:58:11.256290: step: 2264/1545, loss: 0.028084471821784973 2023-01-23 17:58:12.114903: step: 2266/1545, loss: 0.0002394242910668254 2023-01-23 17:58:12.963716: step: 2268/1545, loss: 0.013452951796352863 2023-01-23 17:58:13.850424: step: 2270/1545, loss: 0.214473694562912 2023-01-23 17:58:14.723506: step: 2272/1545, loss: 0.3569788634777069 2023-01-23 17:58:15.621667: step: 2274/1545, loss: 0.0011178071144968271 2023-01-23 17:58:16.519371: step: 2276/1545, loss: 0.005600241478532553 2023-01-23 17:58:17.386418: step: 2278/1545, loss: 0.0009954195702448487 2023-01-23 17:58:18.318068: step: 2280/1545, loss: 0.00033714299206621945 2023-01-23 17:58:19.272585: step: 2282/1545, loss: 0.03477220609784126 2023-01-23 17:58:20.158850: step: 2284/1545, loss: 0.009018128737807274 2023-01-23 17:58:21.081674: step: 2286/1545, loss: 0.018056955188512802 2023-01-23 17:58:21.966613: step: 2288/1545, loss: 0.3378676176071167 2023-01-23 17:58:22.874112: step: 2290/1545, loss: 0.003473426913842559 2023-01-23 17:58:23.759147: step: 2292/1545, loss: 0.0008155411342158914 2023-01-23 17:58:24.627995: step: 2294/1545, loss: 0.011390414088964462 2023-01-23 17:58:25.465741: step: 2296/1545, loss: 0.03671450912952423 2023-01-23 17:58:26.344666: step: 2298/1545, loss: 0.0016464627115055919 2023-01-23 17:58:27.315521: step: 2300/1545, loss: 0.0291217602789402 2023-01-23 17:58:28.270138: step: 2302/1545, loss: 0.0011754892766475677 2023-01-23 17:58:29.167079: step: 2304/1545, loss: 0.1920747607946396 2023-01-23 17:58:30.089320: step: 2306/1545, loss: 0.020870981737971306 2023-01-23 17:58:30.936295: step: 2308/1545, loss: 0.9363047480583191 2023-01-23 17:58:31.853755: step: 2310/1545, loss: 0.0024157240986824036 2023-01-23 17:58:32.752264: step: 2312/1545, loss: 0.002296466613188386 2023-01-23 17:58:33.633583: step: 2314/1545, loss: 0.03528616577386856 2023-01-23 17:58:34.488896: step: 2316/1545, loss: 0.0054002199321985245 2023-01-23 17:58:35.330833: step: 2318/1545, loss: 0.02792872115969658 2023-01-23 17:58:36.177890: step: 2320/1545, loss: 0.3896680772304535 2023-01-23 17:58:37.074877: step: 2322/1545, loss: 0.002649959409609437 2023-01-23 17:58:37.951005: step: 2324/1545, loss: 0.04521413892507553 2023-01-23 17:58:38.836424: step: 2326/1545, loss: 0.03865157067775726 2023-01-23 17:58:39.711160: step: 2328/1545, loss: 0.0006510879611596465 2023-01-23 17:58:40.555889: step: 2330/1545, loss: 0.20008428394794464 2023-01-23 17:58:41.497229: step: 2332/1545, loss: 0.05157271400094032 2023-01-23 17:58:42.383343: step: 2334/1545, loss: 0.03953374922275543 2023-01-23 17:58:43.259941: step: 2336/1545, loss: 0.0042333947494626045 2023-01-23 17:58:44.121639: step: 2338/1545, loss: 0.007737116888165474 2023-01-23 17:58:44.982561: step: 2340/1545, loss: 0.019411517307162285 2023-01-23 17:58:45.847310: step: 2342/1545, loss: 0.0033078528940677643 2023-01-23 17:58:46.759106: step: 2344/1545, loss: 0.11574287712574005 2023-01-23 17:58:47.655931: step: 2346/1545, loss: 0.04762914031744003 2023-01-23 17:58:48.551731: step: 2348/1545, loss: 0.007853958755731583 2023-01-23 17:58:49.439407: step: 2350/1545, loss: 0.11875707656145096 2023-01-23 17:58:50.334545: step: 2352/1545, loss: 0.000686206272803247 2023-01-23 17:58:51.260179: step: 2354/1545, loss: 0.0007175080827437341 2023-01-23 17:58:52.124828: step: 2356/1545, loss: 0.0007525174878537655 2023-01-23 17:58:52.992120: step: 2358/1545, loss: 0.05172977223992348 2023-01-23 17:58:53.857175: step: 2360/1545, loss: 0.1482883244752884 2023-01-23 17:58:54.738017: step: 2362/1545, loss: 0.0028871488757431507 2023-01-23 17:58:55.606811: step: 2364/1545, loss: 0.0029908204451203346 2023-01-23 17:58:56.482238: step: 2366/1545, loss: 1.435451626777649 2023-01-23 17:58:57.377583: step: 2368/1545, loss: 0.04573826864361763 2023-01-23 17:58:58.317816: step: 2370/1545, loss: 0.07131927460432053 2023-01-23 17:58:59.264159: step: 2372/1545, loss: 0.26422372460365295 2023-01-23 17:59:00.111748: step: 2374/1545, loss: 0.00787223782390356 2023-01-23 17:59:00.967252: step: 2376/1545, loss: 0.008428455330431461 2023-01-23 17:59:01.895662: step: 2378/1545, loss: 0.04837346449494362 2023-01-23 17:59:02.797246: step: 2380/1545, loss: 0.0007606272120028734 2023-01-23 17:59:03.691897: step: 2382/1545, loss: 0.015179039910435677 2023-01-23 17:59:04.582406: step: 2384/1545, loss: 0.010755307972431183 2023-01-23 17:59:05.423385: step: 2386/1545, loss: 0.5675123929977417 2023-01-23 17:59:06.397406: step: 2388/1545, loss: 0.6461015343666077 2023-01-23 17:59:07.273229: step: 2390/1545, loss: 0.01010306365787983 2023-01-23 17:59:08.134899: step: 2392/1545, loss: 2.4986746311187744 2023-01-23 17:59:09.029724: step: 2394/1545, loss: 0.001897119451314211 2023-01-23 17:59:09.892097: step: 2396/1545, loss: 0.018602490425109863 2023-01-23 17:59:10.758712: step: 2398/1545, loss: 0.011374687775969505 2023-01-23 17:59:11.674661: step: 2400/1545, loss: 0.01428135484457016 2023-01-23 17:59:12.558680: step: 2402/1545, loss: 0.0016073352890089154 2023-01-23 17:59:13.422023: step: 2404/1545, loss: 0.0005634461413137615 2023-01-23 17:59:14.294824: step: 2406/1545, loss: 0.09863428771495819 2023-01-23 17:59:15.185972: step: 2408/1545, loss: 0.1970173716545105 2023-01-23 17:59:16.052108: step: 2410/1545, loss: 0.037437956780195236 2023-01-23 17:59:16.917245: step: 2412/1545, loss: 0.02621719241142273 2023-01-23 17:59:17.814987: step: 2414/1545, loss: 0.06545912474393845 2023-01-23 17:59:18.738558: step: 2416/1545, loss: 0.010137416422367096 2023-01-23 17:59:19.610082: step: 2418/1545, loss: 0.0016163535183295608 2023-01-23 17:59:20.497644: step: 2420/1545, loss: 0.01351416390389204 2023-01-23 17:59:21.423896: step: 2422/1545, loss: 0.0012548554223030806 2023-01-23 17:59:22.290019: step: 2424/1545, loss: 0.016568517312407494 2023-01-23 17:59:23.153644: step: 2426/1545, loss: 0.05890129506587982 2023-01-23 17:59:24.038330: step: 2428/1545, loss: 0.0006923164473846555 2023-01-23 17:59:24.946868: step: 2430/1545, loss: 0.0031246014405041933 2023-01-23 17:59:25.810251: step: 2432/1545, loss: 0.0031164244282990694 2023-01-23 17:59:26.709641: step: 2434/1545, loss: 0.3153844177722931 2023-01-23 17:59:27.616696: step: 2436/1545, loss: 0.007339136675000191 2023-01-23 17:59:28.486257: step: 2438/1545, loss: 0.00051269237883389 2023-01-23 17:59:29.377075: step: 2440/1545, loss: 0.00238622073084116 2023-01-23 17:59:30.241760: step: 2442/1545, loss: 0.39006945490837097 2023-01-23 17:59:31.091701: step: 2444/1545, loss: 0.00039163476321846247 2023-01-23 17:59:31.953242: step: 2446/1545, loss: 0.02408863976597786 2023-01-23 17:59:32.812280: step: 2448/1545, loss: 0.11181939393281937 2023-01-23 17:59:33.713812: step: 2450/1545, loss: 0.0011685378849506378 2023-01-23 17:59:34.629243: step: 2452/1545, loss: 0.0009871775982901454 2023-01-23 17:59:35.498061: step: 2454/1545, loss: 0.0001477452606195584 2023-01-23 17:59:36.377696: step: 2456/1545, loss: 0.0001124246628023684 2023-01-23 17:59:37.230857: step: 2458/1545, loss: 0.0003483834443613887 2023-01-23 17:59:38.131861: step: 2460/1545, loss: 0.00088196323486045 2023-01-23 17:59:39.075004: step: 2462/1545, loss: 0.055960074067115784 2023-01-23 17:59:40.043652: step: 2464/1545, loss: 0.04358799383044243 2023-01-23 17:59:40.983235: step: 2466/1545, loss: 0.005764736328274012 2023-01-23 17:59:41.914523: step: 2468/1545, loss: 0.05593658983707428 2023-01-23 17:59:42.770646: step: 2470/1545, loss: 0.046177465468645096 2023-01-23 17:59:43.645904: step: 2472/1545, loss: 0.014425044879317284 2023-01-23 17:59:44.513371: step: 2474/1545, loss: 0.046455658972263336 2023-01-23 17:59:45.375675: step: 2476/1545, loss: 0.14396598935127258 2023-01-23 17:59:46.256651: step: 2478/1545, loss: 0.00027241912903264165 2023-01-23 17:59:47.169848: step: 2480/1545, loss: 0.0020019751973450184 2023-01-23 17:59:48.045238: step: 2482/1545, loss: 0.0008328788680955768 2023-01-23 17:59:48.966303: step: 2484/1545, loss: 0.00025370376533828676 2023-01-23 17:59:49.842494: step: 2486/1545, loss: 0.0033295652829110622 2023-01-23 17:59:50.680035: step: 2488/1545, loss: 0.0003573876747395843 2023-01-23 17:59:51.628017: step: 2490/1545, loss: 0.003959182184189558 2023-01-23 17:59:52.464202: step: 2492/1545, loss: 0.3800005614757538 2023-01-23 17:59:53.361218: step: 2494/1545, loss: 0.03248654305934906 2023-01-23 17:59:54.269925: step: 2496/1545, loss: 0.18074901401996613 2023-01-23 17:59:55.177147: step: 2498/1545, loss: 0.06279817223548889 2023-01-23 17:59:56.090412: step: 2500/1545, loss: 0.24415753781795502 2023-01-23 17:59:56.975832: step: 2502/1545, loss: 0.4345819354057312 2023-01-23 17:59:57.872342: step: 2504/1545, loss: 8.964606968220323e-05 2023-01-23 17:59:58.745013: step: 2506/1545, loss: 0.09266944974660873 2023-01-23 17:59:59.682161: step: 2508/1545, loss: 0.0022767330519855022 2023-01-23 18:00:00.547468: step: 2510/1545, loss: 0.000515604973770678 2023-01-23 18:00:01.476611: step: 2512/1545, loss: 0.12843677401542664 2023-01-23 18:00:02.350885: step: 2514/1545, loss: 0.0006209141574800014 2023-01-23 18:00:03.235965: step: 2516/1545, loss: 4.3541840568650514e-05 2023-01-23 18:00:04.098781: step: 2518/1545, loss: 0.010527212172746658 2023-01-23 18:00:04.963922: step: 2520/1545, loss: 0.002414706628769636 2023-01-23 18:00:05.841948: step: 2522/1545, loss: 0.022054456174373627 2023-01-23 18:00:06.690382: step: 2524/1545, loss: 0.5228289365768433 2023-01-23 18:00:07.573493: step: 2526/1545, loss: 0.04083511233329773 2023-01-23 18:00:08.468471: step: 2528/1545, loss: 0.013336786068975925 2023-01-23 18:00:09.397869: step: 2530/1545, loss: 6.375854354701005e-06 2023-01-23 18:00:10.304740: step: 2532/1545, loss: 0.0014399228384718299 2023-01-23 18:00:11.169426: step: 2534/1545, loss: 0.06107326224446297 2023-01-23 18:00:12.044602: step: 2536/1545, loss: 0.0003444422036409378 2023-01-23 18:00:12.921899: step: 2538/1545, loss: 7.726932381046936e-05 2023-01-23 18:00:13.796902: step: 2540/1545, loss: 0.00878679659217596 2023-01-23 18:00:14.682992: step: 2542/1545, loss: 0.03929808363318443 2023-01-23 18:00:15.561404: step: 2544/1545, loss: 0.00015167643141467124 2023-01-23 18:00:16.457479: step: 2546/1545, loss: 0.0006716103525832295 2023-01-23 18:00:17.309386: step: 2548/1545, loss: 0.02272832579910755 2023-01-23 18:00:18.162148: step: 2550/1545, loss: 0.0013752096565440297 2023-01-23 18:00:19.034366: step: 2552/1545, loss: 0.19161546230316162 2023-01-23 18:00:19.928864: step: 2554/1545, loss: 0.005464303772896528 2023-01-23 18:00:20.858234: step: 2556/1545, loss: 0.0006118185701780021 2023-01-23 18:00:21.709008: step: 2558/1545, loss: 0.06698301434516907 2023-01-23 18:00:22.669051: step: 2560/1545, loss: 8.814435568638146e-05 2023-01-23 18:00:23.533915: step: 2562/1545, loss: 6.50925503578037e-05 2023-01-23 18:00:24.454255: step: 2564/1545, loss: 0.00017889280570670962 2023-01-23 18:00:25.342851: step: 2566/1545, loss: 0.0006621712236665189 2023-01-23 18:00:26.181130: step: 2568/1545, loss: 6.478089926531538e-05 2023-01-23 18:00:27.089037: step: 2570/1545, loss: 0.0007504539098590612 2023-01-23 18:00:27.967124: step: 2572/1545, loss: 0.0013181300600990653 2023-01-23 18:00:28.847908: step: 2574/1545, loss: 0.02118556760251522 2023-01-23 18:00:29.714361: step: 2576/1545, loss: 3.5805780498776585e-05 2023-01-23 18:00:30.585885: step: 2578/1545, loss: 0.0031198039650917053 2023-01-23 18:00:31.519666: step: 2580/1545, loss: 0.0008180167060345411 2023-01-23 18:00:32.394779: step: 2582/1545, loss: 0.000423542398493737 2023-01-23 18:00:33.252314: step: 2584/1545, loss: 0.008682435378432274 2023-01-23 18:00:34.167265: step: 2586/1545, loss: 0.0014204513281583786 2023-01-23 18:00:35.055096: step: 2588/1545, loss: 0.0827445536851883 2023-01-23 18:00:35.967094: step: 2590/1545, loss: 0.0024860454723238945 2023-01-23 18:00:36.825400: step: 2592/1545, loss: 0.0008172785746864974 2023-01-23 18:00:37.708697: step: 2594/1545, loss: 0.007228841073811054 2023-01-23 18:00:38.582858: step: 2596/1545, loss: 0.12362442165613174 2023-01-23 18:00:39.444013: step: 2598/1545, loss: 0.0012865762691944838 2023-01-23 18:00:40.307406: step: 2600/1545, loss: 0.0005232373951002955 2023-01-23 18:00:41.189634: step: 2602/1545, loss: 0.003070518374443054 2023-01-23 18:00:42.103608: step: 2604/1545, loss: 0.0013660144759342074 2023-01-23 18:00:42.968888: step: 2606/1545, loss: 0.001795307733118534 2023-01-23 18:00:43.821241: step: 2608/1545, loss: 0.0026113511994481087 2023-01-23 18:00:44.742151: step: 2610/1545, loss: 0.028483973816037178 2023-01-23 18:00:45.658622: step: 2612/1545, loss: 0.0004125814884901047 2023-01-23 18:00:46.540387: step: 2614/1545, loss: 0.03960898891091347 2023-01-23 18:00:47.427883: step: 2616/1545, loss: 0.0013572524767369032 2023-01-23 18:00:48.383314: step: 2618/1545, loss: 0.06367916613817215 2023-01-23 18:00:49.271746: step: 2620/1545, loss: 0.0004233026993460953 2023-01-23 18:00:50.128259: step: 2622/1545, loss: 0.10418679565191269 2023-01-23 18:00:51.008271: step: 2624/1545, loss: 0.0007663971045985818 2023-01-23 18:00:51.906018: step: 2626/1545, loss: 0.03450701758265495 2023-01-23 18:00:52.789434: step: 2628/1545, loss: 0.0002599695581011474 2023-01-23 18:00:53.681926: step: 2630/1545, loss: 0.671152651309967 2023-01-23 18:00:54.548831: step: 2632/1545, loss: 0.15825876593589783 2023-01-23 18:00:55.438729: step: 2634/1545, loss: 0.003356445347890258 2023-01-23 18:00:56.408260: step: 2636/1545, loss: 0.10693291574716568 2023-01-23 18:00:57.288606: step: 2638/1545, loss: 0.02323533408343792 2023-01-23 18:00:58.157704: step: 2640/1545, loss: 0.008527472615242004 2023-01-23 18:00:59.081371: step: 2642/1545, loss: 0.31957507133483887 2023-01-23 18:00:59.985876: step: 2644/1545, loss: 0.16286532580852509 2023-01-23 18:01:00.861411: step: 2646/1545, loss: 0.009138204157352448 2023-01-23 18:01:01.706093: step: 2648/1545, loss: 0.00016490346752107143 2023-01-23 18:01:02.554010: step: 2650/1545, loss: 0.044687669724226 2023-01-23 18:01:03.430066: step: 2652/1545, loss: 0.9235568046569824 2023-01-23 18:01:04.304780: step: 2654/1545, loss: 0.02977115847170353 2023-01-23 18:01:05.186579: step: 2656/1545, loss: 0.0033765265252441168 2023-01-23 18:01:06.113446: step: 2658/1545, loss: 0.09978989511728287 2023-01-23 18:01:06.971731: step: 2660/1545, loss: 0.0029254411347210407 2023-01-23 18:01:07.878481: step: 2662/1545, loss: 0.06746666133403778 2023-01-23 18:01:08.736821: step: 2664/1545, loss: 0.00045451472396962345 2023-01-23 18:01:09.653119: step: 2666/1545, loss: 0.852692186832428 2023-01-23 18:01:10.543913: step: 2668/1545, loss: 0.0018979118904098868 2023-01-23 18:01:11.400057: step: 2670/1545, loss: 0.024775195866823196 2023-01-23 18:01:12.335124: step: 2672/1545, loss: 0.0016282805008813739 2023-01-23 18:01:13.211841: step: 2674/1545, loss: 0.00023465583217330277 2023-01-23 18:01:14.113032: step: 2676/1545, loss: 0.02686467207968235 2023-01-23 18:01:15.067192: step: 2678/1545, loss: 0.2777697443962097 2023-01-23 18:01:15.968617: step: 2680/1545, loss: 0.007133470382541418 2023-01-23 18:01:16.895681: step: 2682/1545, loss: 0.00751722464337945 2023-01-23 18:01:17.750996: step: 2684/1545, loss: 0.025408783927559853 2023-01-23 18:01:18.601399: step: 2686/1545, loss: 0.042243603616952896 2023-01-23 18:01:19.524531: step: 2688/1545, loss: 0.01593928039073944 2023-01-23 18:01:20.455450: step: 2690/1545, loss: 0.2329452633857727 2023-01-23 18:01:21.308054: step: 2692/1545, loss: 0.0016146720154210925 2023-01-23 18:01:22.155528: step: 2694/1545, loss: 0.4811396598815918 2023-01-23 18:01:23.052356: step: 2696/1545, loss: 0.01718701422214508 2023-01-23 18:01:23.897992: step: 2698/1545, loss: 0.001358765410259366 2023-01-23 18:01:24.785036: step: 2700/1545, loss: 0.20291046798229218 2023-01-23 18:01:25.685963: step: 2702/1545, loss: 0.1621732860803604 2023-01-23 18:01:26.552430: step: 2704/1545, loss: 0.0036645338404923677 2023-01-23 18:01:27.417038: step: 2706/1545, loss: 0.18016204237937927 2023-01-23 18:01:28.344548: step: 2708/1545, loss: 0.002681816928088665 2023-01-23 18:01:29.269785: step: 2710/1545, loss: 0.004116096068173647 2023-01-23 18:01:30.226162: step: 2712/1545, loss: 0.12740734219551086 2023-01-23 18:01:31.143687: step: 2714/1545, loss: 0.012705720961093903 2023-01-23 18:01:32.020469: step: 2716/1545, loss: 0.01488437969237566 2023-01-23 18:01:32.933042: step: 2718/1545, loss: 0.012205520644783974 2023-01-23 18:01:33.795101: step: 2720/1545, loss: 0.000811183825135231 2023-01-23 18:01:34.662024: step: 2722/1545, loss: 0.14251482486724854 2023-01-23 18:01:35.564494: step: 2724/1545, loss: 0.021627921611070633 2023-01-23 18:01:36.420776: step: 2726/1545, loss: 0.11313050240278244 2023-01-23 18:01:37.293069: step: 2728/1545, loss: 0.04301457852125168 2023-01-23 18:01:38.163066: step: 2730/1545, loss: 0.0029512890614569187 2023-01-23 18:01:39.035479: step: 2732/1545, loss: 0.49757319688796997 2023-01-23 18:01:39.911677: step: 2734/1545, loss: 0.008747019805014133 2023-01-23 18:01:40.814038: step: 2736/1545, loss: 0.07891546189785004 2023-01-23 18:01:41.697093: step: 2738/1545, loss: 0.08647552877664566 2023-01-23 18:01:42.577360: step: 2740/1545, loss: 0.12160369008779526 2023-01-23 18:01:43.434973: step: 2742/1545, loss: 0.02281034365296364 2023-01-23 18:01:44.279353: step: 2744/1545, loss: 0.0002670411777216941 2023-01-23 18:01:45.143887: step: 2746/1545, loss: 0.1827978938817978 2023-01-23 18:01:46.092337: step: 2748/1545, loss: 0.01295638456940651 2023-01-23 18:01:46.968576: step: 2750/1545, loss: 0.001741863088682294 2023-01-23 18:01:47.834408: step: 2752/1545, loss: 0.000626967812422663 2023-01-23 18:01:48.702663: step: 2754/1545, loss: 0.01960701122879982 2023-01-23 18:01:49.640674: step: 2756/1545, loss: 0.00020688099903054535 2023-01-23 18:01:50.524403: step: 2758/1545, loss: 0.0060376962646842 2023-01-23 18:01:51.401984: step: 2760/1545, loss: 0.00538281025364995 2023-01-23 18:01:52.243847: step: 2762/1545, loss: 0.0003089018282480538 2023-01-23 18:01:53.126587: step: 2764/1545, loss: 0.0008619270520284772 2023-01-23 18:01:54.058940: step: 2766/1545, loss: 0.0007101943483576179 2023-01-23 18:01:54.980807: step: 2768/1545, loss: 0.09310030192136765 2023-01-23 18:01:55.888822: step: 2770/1545, loss: 0.2347530573606491 2023-01-23 18:01:56.753875: step: 2772/1545, loss: 0.03476705774664879 2023-01-23 18:01:57.649065: step: 2774/1545, loss: 0.00038174205110408366 2023-01-23 18:01:58.524909: step: 2776/1545, loss: 0.012044642120599747 2023-01-23 18:01:59.408694: step: 2778/1545, loss: 0.0018798557575792074 2023-01-23 18:02:00.433260: step: 2780/1545, loss: 0.3261299133300781 2023-01-23 18:02:01.305718: step: 2782/1545, loss: 0.01877320557832718 2023-01-23 18:02:02.198651: step: 2784/1545, loss: 0.009051090106368065 2023-01-23 18:02:03.088478: step: 2786/1545, loss: 0.0002979799173772335 2023-01-23 18:02:03.934952: step: 2788/1545, loss: 0.0026930596213787794 2023-01-23 18:02:04.840393: step: 2790/1545, loss: 0.012284893542528152 2023-01-23 18:02:05.737631: step: 2792/1545, loss: 0.0022757218685001135 2023-01-23 18:02:06.593701: step: 2794/1545, loss: 0.031921662390232086 2023-01-23 18:02:07.467078: step: 2796/1545, loss: 0.08607278019189835 2023-01-23 18:02:08.350885: step: 2798/1545, loss: 0.000518638698849827 2023-01-23 18:02:09.292644: step: 2800/1545, loss: 0.0020663172472268343 2023-01-23 18:02:10.137150: step: 2802/1545, loss: 0.3373194634914398 2023-01-23 18:02:11.124468: step: 2804/1545, loss: 0.13466891646385193 2023-01-23 18:02:11.985091: step: 2806/1545, loss: 3.0131986932246946e-05 2023-01-23 18:02:12.861578: step: 2808/1545, loss: 0.05309601500630379 2023-01-23 18:02:13.713145: step: 2810/1545, loss: 0.05837037414312363 2023-01-23 18:02:14.610739: step: 2812/1545, loss: 0.05972558259963989 2023-01-23 18:02:15.450689: step: 2814/1545, loss: 0.4766280949115753 2023-01-23 18:02:16.347992: step: 2816/1545, loss: 0.1264418065547943 2023-01-23 18:02:17.207435: step: 2818/1545, loss: 0.0027651686687022448 2023-01-23 18:02:18.061924: step: 2820/1545, loss: 0.000860604690387845 2023-01-23 18:02:19.020588: step: 2822/1545, loss: 0.0005504825385287404 2023-01-23 18:02:19.885601: step: 2824/1545, loss: 0.2745993137359619 2023-01-23 18:02:20.741947: step: 2826/1545, loss: 0.006382996682077646 2023-01-23 18:02:21.603115: step: 2828/1545, loss: 0.0038170632906258106 2023-01-23 18:02:22.481835: step: 2830/1545, loss: 0.09554466605186462 2023-01-23 18:02:23.420856: step: 2832/1545, loss: 0.12164256721735 2023-01-23 18:02:24.317155: step: 2834/1545, loss: 0.08242285251617432 2023-01-23 18:02:25.206658: step: 2836/1545, loss: 0.005037712398916483 2023-01-23 18:02:26.119540: step: 2838/1545, loss: 0.0006756104994565248 2023-01-23 18:02:27.123855: step: 2840/1545, loss: 0.009680268354713917 2023-01-23 18:02:28.012128: step: 2842/1545, loss: 0.10246040672063828 2023-01-23 18:02:28.864526: step: 2844/1545, loss: 0.000494308362249285 2023-01-23 18:02:29.748509: step: 2846/1545, loss: 0.06663737446069717 2023-01-23 18:02:30.644632: step: 2848/1545, loss: 0.020912060514092445 2023-01-23 18:02:31.548098: step: 2850/1545, loss: 0.03723297640681267 2023-01-23 18:02:32.448706: step: 2852/1545, loss: 0.03390475735068321 2023-01-23 18:02:33.308779: step: 2854/1545, loss: 0.0014631900703534484 2023-01-23 18:02:34.259023: step: 2856/1545, loss: 0.001210397924296558 2023-01-23 18:02:35.136103: step: 2858/1545, loss: 0.0007122386014088988 2023-01-23 18:02:35.993485: step: 2860/1545, loss: 0.021786676719784737 2023-01-23 18:02:36.841192: step: 2862/1545, loss: 0.0017824405804276466 2023-01-23 18:02:37.740420: step: 2864/1545, loss: 0.00042570685036480427 2023-01-23 18:02:38.621292: step: 2866/1545, loss: 0.10025336593389511 2023-01-23 18:02:39.479909: step: 2868/1545, loss: 0.18076179921627045 2023-01-23 18:02:40.343609: step: 2870/1545, loss: 0.20402218401432037 2023-01-23 18:02:41.186909: step: 2872/1545, loss: 0.0013157065259292722 2023-01-23 18:02:42.107275: step: 2874/1545, loss: 0.24830690026283264 2023-01-23 18:02:42.980933: step: 2876/1545, loss: 0.011465643532574177 2023-01-23 18:02:43.831485: step: 2878/1545, loss: 0.0012365473667159677 2023-01-23 18:02:44.766690: step: 2880/1545, loss: 0.0030019055120646954 2023-01-23 18:02:45.608608: step: 2882/1545, loss: 0.15231382846832275 2023-01-23 18:02:46.509274: step: 2884/1545, loss: 0.02246042527258396 2023-01-23 18:02:47.403437: step: 2886/1545, loss: 0.10399476438760757 2023-01-23 18:02:48.320578: step: 2888/1545, loss: 0.05998799949884415 2023-01-23 18:02:49.215133: step: 2890/1545, loss: 0.02641531452536583 2023-01-23 18:02:50.107812: step: 2892/1545, loss: 0.06347673386335373 2023-01-23 18:02:50.947293: step: 2894/1545, loss: 0.002443636069074273 2023-01-23 18:02:51.770846: step: 2896/1545, loss: 0.008831169456243515 2023-01-23 18:02:52.638027: step: 2898/1545, loss: 0.1768491268157959 2023-01-23 18:02:53.554068: step: 2900/1545, loss: 0.002388807013630867 2023-01-23 18:02:54.453789: step: 2902/1545, loss: 0.07027999311685562 2023-01-23 18:02:55.400679: step: 2904/1545, loss: 0.0720997154712677 2023-01-23 18:02:56.296949: step: 2906/1545, loss: 1.8310376405715942 2023-01-23 18:02:57.186852: step: 2908/1545, loss: 0.041614729911088943 2023-01-23 18:02:58.027345: step: 2910/1545, loss: 0.0029827491380274296 2023-01-23 18:02:58.882472: step: 2912/1545, loss: 0.36170414090156555 2023-01-23 18:02:59.699584: step: 2914/1545, loss: 0.0010002776980400085 2023-01-23 18:03:00.547253: step: 2916/1545, loss: 0.0003628177219070494 2023-01-23 18:03:01.430713: step: 2918/1545, loss: 0.004871861077845097 2023-01-23 18:03:02.289456: step: 2920/1545, loss: 0.00027320493245497346 2023-01-23 18:03:03.185121: step: 2922/1545, loss: 0.0010383836925029755 2023-01-23 18:03:04.132311: step: 2924/1545, loss: 0.12222840636968613 2023-01-23 18:03:05.011874: step: 2926/1545, loss: 0.004594649653881788 2023-01-23 18:03:05.870900: step: 2928/1545, loss: 0.0003954950952902436 2023-01-23 18:03:06.695883: step: 2930/1545, loss: 0.004176384303718805 2023-01-23 18:03:07.623492: step: 2932/1545, loss: 0.4392472803592682 2023-01-23 18:03:08.485192: step: 2934/1545, loss: 0.08161160349845886 2023-01-23 18:03:09.400127: step: 2936/1545, loss: 0.018081914633512497 2023-01-23 18:03:10.282447: step: 2938/1545, loss: 0.017401186749339104 2023-01-23 18:03:11.125021: step: 2940/1545, loss: 0.0014410780277103186 2023-01-23 18:03:11.989672: step: 2942/1545, loss: 0.03541158139705658 2023-01-23 18:03:12.963456: step: 2944/1545, loss: 0.03874242305755615 2023-01-23 18:03:13.827240: step: 2946/1545, loss: 0.002020384417846799 2023-01-23 18:03:14.726821: step: 2948/1545, loss: 0.0023458858486264944 2023-01-23 18:03:15.611120: step: 2950/1545, loss: 0.013540403917431831 2023-01-23 18:03:16.483070: step: 2952/1545, loss: 0.014512883499264717 2023-01-23 18:03:17.348062: step: 2954/1545, loss: 0.0010729231871664524 2023-01-23 18:03:18.268048: step: 2956/1545, loss: 0.1644219011068344 2023-01-23 18:03:19.130041: step: 2958/1545, loss: 0.00450163334608078 2023-01-23 18:03:20.040405: step: 2960/1545, loss: 0.001178946578875184 2023-01-23 18:03:20.926801: step: 2962/1545, loss: 0.005955616477876902 2023-01-23 18:03:21.793613: step: 2964/1545, loss: 0.007876794785261154 2023-01-23 18:03:22.666734: step: 2966/1545, loss: 0.08263808488845825 2023-01-23 18:03:23.588628: step: 2968/1545, loss: 0.0029335669241845608 2023-01-23 18:03:24.482442: step: 2970/1545, loss: 0.029133791103959084 2023-01-23 18:03:25.329698: step: 2972/1545, loss: 0.0021924597676843405 2023-01-23 18:03:26.187133: step: 2974/1545, loss: 0.001248515909537673 2023-01-23 18:03:27.084667: step: 2976/1545, loss: 0.004281224217265844 2023-01-23 18:03:27.973170: step: 2978/1545, loss: 0.08858213573694229 2023-01-23 18:03:28.863008: step: 2980/1545, loss: 0.04521365091204643 2023-01-23 18:03:29.691463: step: 2982/1545, loss: 0.0019123428501188755 2023-01-23 18:03:30.572348: step: 2984/1545, loss: 0.00045747397234663367 2023-01-23 18:03:31.462355: step: 2986/1545, loss: 0.008641202002763748 2023-01-23 18:03:32.320756: step: 2988/1545, loss: 0.05669603496789932 2023-01-23 18:03:33.198408: step: 2990/1545, loss: 0.3383592665195465 2023-01-23 18:03:34.024406: step: 2992/1545, loss: 0.22765560448169708 2023-01-23 18:03:34.914158: step: 2994/1545, loss: 0.0005524889566004276 2023-01-23 18:03:35.792467: step: 2996/1545, loss: 0.000546495255548507 2023-01-23 18:03:36.691766: step: 2998/1545, loss: 0.1321406215429306 2023-01-23 18:03:37.570260: step: 3000/1545, loss: 0.15046249330043793 2023-01-23 18:03:38.420064: step: 3002/1545, loss: 0.0014929698081687093 2023-01-23 18:03:39.314694: step: 3004/1545, loss: 0.0002627363137435168 2023-01-23 18:03:40.213494: step: 3006/1545, loss: 0.004740308504551649 2023-01-23 18:03:41.201477: step: 3008/1545, loss: 1.0485029220581055 2023-01-23 18:03:42.131558: step: 3010/1545, loss: 0.00014607608318328857 2023-01-23 18:03:43.021411: step: 3012/1545, loss: 0.000373249058611691 2023-01-23 18:03:43.887240: step: 3014/1545, loss: 0.7246175408363342 2023-01-23 18:03:44.764445: step: 3016/1545, loss: 0.002692381851375103 2023-01-23 18:03:45.725302: step: 3018/1545, loss: 0.013262045569717884 2023-01-23 18:03:46.595070: step: 3020/1545, loss: 0.005517088808119297 2023-01-23 18:03:47.535119: step: 3022/1545, loss: 0.00021484387980308384 2023-01-23 18:03:48.428914: step: 3024/1545, loss: 0.003240666352212429 2023-01-23 18:03:49.318275: step: 3026/1545, loss: 0.019837751984596252 2023-01-23 18:03:50.260372: step: 3028/1545, loss: 0.7692911624908447 2023-01-23 18:03:51.167520: step: 3030/1545, loss: 0.009098387323319912 2023-01-23 18:03:52.037612: step: 3032/1545, loss: 0.00030928076012060046 2023-01-23 18:03:52.951419: step: 3034/1545, loss: 0.030322957783937454 2023-01-23 18:03:53.864868: step: 3036/1545, loss: 0.04186498373746872 2023-01-23 18:03:54.753763: step: 3038/1545, loss: 0.0013033656869083643 2023-01-23 18:03:55.643461: step: 3040/1545, loss: 0.01197129301726818 2023-01-23 18:03:56.595785: step: 3042/1545, loss: 0.0005815472104586661 2023-01-23 18:03:57.576337: step: 3044/1545, loss: 0.009392661042511463 2023-01-23 18:03:58.430789: step: 3046/1545, loss: 0.002481007482856512 2023-01-23 18:03:59.311047: step: 3048/1545, loss: 0.1477186679840088 2023-01-23 18:04:00.187613: step: 3050/1545, loss: 0.0019275919767096639 2023-01-23 18:04:01.060429: step: 3052/1545, loss: 0.08676253259181976 2023-01-23 18:04:01.972137: step: 3054/1545, loss: 0.1093062311410904 2023-01-23 18:04:02.860003: step: 3056/1545, loss: 0.017717896029353142 2023-01-23 18:04:03.766623: step: 3058/1545, loss: 0.005027381703257561 2023-01-23 18:04:04.649350: step: 3060/1545, loss: 0.11772111803293228 2023-01-23 18:04:05.511316: step: 3062/1545, loss: 0.010626222006976604 2023-01-23 18:04:06.391237: step: 3064/1545, loss: 0.05419892445206642 2023-01-23 18:04:07.331971: step: 3066/1545, loss: 0.0008062947308644652 2023-01-23 18:04:08.166394: step: 3068/1545, loss: 0.0026579545810818672 2023-01-23 18:04:09.016327: step: 3070/1545, loss: 0.0002102355210809037 2023-01-23 18:04:09.881249: step: 3072/1545, loss: 0.05193733796477318 2023-01-23 18:04:10.733559: step: 3074/1545, loss: 0.013402372598648071 2023-01-23 18:04:11.597122: step: 3076/1545, loss: 0.00018788271700032055 2023-01-23 18:04:12.512889: step: 3078/1545, loss: 0.03563687577843666 2023-01-23 18:04:13.388094: step: 3080/1545, loss: 0.002855107421055436 2023-01-23 18:04:14.292043: step: 3082/1545, loss: 0.05390089005231857 2023-01-23 18:04:15.166826: step: 3084/1545, loss: 0.20751509070396423 2023-01-23 18:04:16.064532: step: 3086/1545, loss: 0.24300038814544678 2023-01-23 18:04:16.928871: step: 3088/1545, loss: 0.0001661090791458264 2023-01-23 18:04:17.835063: step: 3090/1545, loss: 0.042303383350372314 ================================================== Loss: 0.080 -------------------- Dev Chinese: {'event': {'p': 0.5965103598691385, 'r': 0.7283621837549934, 'f1': 0.6558752997601919}, 'argument': {'p': 0.6752334003169094, 'r': 0.6438742461448882, 'f1': 0.6591810725486392}, 'combined': 0.43234058355408356, 'epoch': 27} Test Chinese: {'event': {'p': 0.6387406616862327, 'r': 0.7653452685421995, 'f1': 0.6963350785340314}, 'argument': {'p': 0.7105504586733332, 'r': 0.7078353250903247, 'f1': 0.709190293170513}, 'combined': 0.4938340784904619, 'epoch': 27} Dev Korean: {'event': {'p': 0.6050328227571116, 'r': 0.7363515312916112, 'f1': 0.6642642642642642}, 'argument': {'p': 0.6772961615056954, 'r': 0.6503061640923106, 'f1': 0.6635268110799947}, 'combined': 0.4407571489816661, 'epoch': 27} Test Korean: {'event': {'p': 0.6312169312169312, 'r': 0.7627877237851662, 'f1': 0.6907932831499711}, 'argument': {'p': 0.7036217845798122, 'r': 0.7020079731472897, 'f1': 0.7028139524505588}, 'combined': 0.4854991576569292, 'epoch': 27} Dev Russian: {'event': {'p': 0.5639763779527559, 'r': 0.762982689747004, 'f1': 0.6485568760611204}, 'argument': {'p': 0.6680186568351105, 'r': 0.65417123650043, 'f1': 0.6610224339935727}, 'combined': 0.42871064479718973, 'epoch': 27} Test Russian: {'event': {'p': 0.6292974588938715, 'r': 0.8075447570332481, 'f1': 0.7073648837860543}, 'argument': {'p': 0.713305570760347, 'r': 0.7149085046272241, 'f1': 0.7141061381798312}, 'combined': 0.5051336054444843, 'epoch': 27} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7091836734693877, 'r': 0.5743801652892562, 'f1': 0.6347031963470319}, 'combined': 0.451985609519856, 'epoch': 27} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.7329122125040493, 'r': 0.4919547727766906, 'f1': 0.5887327608639084}, 'combined': 0.3615025724602946, 'epoch': 27} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5467835375265716, 'r': 0.497963578818842, 'f1': 0.521232904931872}, 'combined': 0.29030693439243505, 'epoch': 27} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6559451265403835, 'r': 0.6613377994790564, 'f1': 0.6586304247882229}, 'combined': 0.43355887674908195, 'epoch': 26} Test for Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6980547354393568, 'r': 0.7185779178100443, 'f1': 0.7081676638737557}, 'combined': 0.49271002093834315, 'epoch': 26} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6657901327322815, 'r': 0.6657901327322815, 'f1': 0.6657901327322815}, 'combined': 0.47412327633965495, 'epoch': 26} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 28 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 18:09:30.733747: step: 2/1545, loss: 0.0020655756816267967 2023-01-23 18:09:31.624416: step: 4/1545, loss: 0.000520967529155314 2023-01-23 18:09:32.566354: step: 6/1545, loss: 0.011791948229074478 2023-01-23 18:09:33.406587: step: 8/1545, loss: 0.0003897270071320236 2023-01-23 18:09:34.303980: step: 10/1545, loss: 0.10493141412734985 2023-01-23 18:09:35.253963: step: 12/1545, loss: 0.06678562611341476 2023-01-23 18:09:36.153912: step: 14/1545, loss: 0.21548496186733246 2023-01-23 18:09:36.987792: step: 16/1545, loss: 0.001078704372048378 2023-01-23 18:09:37.894997: step: 18/1545, loss: 0.06671195477247238 2023-01-23 18:09:38.774688: step: 20/1545, loss: 0.00018316440400667489 2023-01-23 18:09:39.645326: step: 22/1545, loss: 0.005571180023252964 2023-01-23 18:09:40.589027: step: 24/1545, loss: 0.043371252715587616 2023-01-23 18:09:41.464535: step: 26/1545, loss: 0.003933421336114407 2023-01-23 18:09:42.359570: step: 28/1545, loss: 0.008494507521390915 2023-01-23 18:09:43.250198: step: 30/1545, loss: 0.21701329946517944 2023-01-23 18:09:44.236921: step: 32/1545, loss: 0.08840540796518326 2023-01-23 18:09:45.104910: step: 34/1545, loss: 0.003730388358235359 2023-01-23 18:09:45.938495: step: 36/1545, loss: 0.0002393820323050022 2023-01-23 18:09:46.849761: step: 38/1545, loss: 0.001456995029002428 2023-01-23 18:09:47.720531: step: 40/1545, loss: 0.000205804462893866 2023-01-23 18:09:48.648822: step: 42/1545, loss: 0.006697679869830608 2023-01-23 18:09:49.538661: step: 44/1545, loss: 0.0005309654516167939 2023-01-23 18:09:50.423635: step: 46/1545, loss: 0.0003127268864773214 2023-01-23 18:09:51.326537: step: 48/1545, loss: 0.0398297943174839 2023-01-23 18:09:52.204985: step: 50/1545, loss: 0.0001644263684283942 2023-01-23 18:09:53.105491: step: 52/1545, loss: 0.10938587039709091 2023-01-23 18:09:53.972032: step: 54/1545, loss: 1.5798828601837158 2023-01-23 18:09:54.830880: step: 56/1545, loss: 0.018627669662237167 2023-01-23 18:09:55.714275: step: 58/1545, loss: 2.6789450203068554e-05 2023-01-23 18:09:56.588593: step: 60/1545, loss: 0.0038222847506403923 2023-01-23 18:09:57.433539: step: 62/1545, loss: 0.0013199519598856568 2023-01-23 18:09:58.272319: step: 64/1545, loss: 0.0028212484903633595 2023-01-23 18:09:59.181167: step: 66/1545, loss: 0.005592708941549063 2023-01-23 18:10:00.114834: step: 68/1545, loss: 0.03500422090291977 2023-01-23 18:10:01.020293: step: 70/1545, loss: 0.002224200638011098 2023-01-23 18:10:01.885575: step: 72/1545, loss: 0.00011503368295961991 2023-01-23 18:10:02.764207: step: 74/1545, loss: 0.0006653624586760998 2023-01-23 18:10:03.671984: step: 76/1545, loss: 0.0027571700047701597 2023-01-23 18:10:04.533273: step: 78/1545, loss: 0.3902432918548584 2023-01-23 18:10:05.416172: step: 80/1545, loss: 0.023257743567228317 2023-01-23 18:10:06.307058: step: 82/1545, loss: 0.0001490571303293109 2023-01-23 18:10:07.165183: step: 84/1545, loss: 0.002773588988929987 2023-01-23 18:10:08.107040: step: 86/1545, loss: 0.12264284491539001 2023-01-23 18:10:08.990992: step: 88/1545, loss: 0.06655149161815643 2023-01-23 18:10:09.876931: step: 90/1545, loss: 0.08402742445468903 2023-01-23 18:10:10.816669: step: 92/1545, loss: 0.0005577232223004103 2023-01-23 18:10:11.706545: step: 94/1545, loss: 0.6509607434272766 2023-01-23 18:10:12.628977: step: 96/1545, loss: 0.0011787237599492073 2023-01-23 18:10:13.564499: step: 98/1545, loss: 0.011016534641385078 2023-01-23 18:10:14.519872: step: 100/1545, loss: 7.951920269988477e-05 2023-01-23 18:10:15.380307: step: 102/1545, loss: 5.884311758563854e-05 2023-01-23 18:10:16.271696: step: 104/1545, loss: 0.00622163899242878 2023-01-23 18:10:17.147333: step: 106/1545, loss: 0.0390186607837677 2023-01-23 18:10:18.024961: step: 108/1545, loss: 0.0003037742280866951 2023-01-23 18:10:18.946883: step: 110/1545, loss: 0.13208067417144775 2023-01-23 18:10:19.829146: step: 112/1545, loss: 0.12155753374099731 2023-01-23 18:10:20.733586: step: 114/1545, loss: 0.002851250348612666 2023-01-23 18:10:21.683197: step: 116/1545, loss: 0.00026165402960032225 2023-01-23 18:10:22.585209: step: 118/1545, loss: 0.007985805161297321 2023-01-23 18:10:23.487577: step: 120/1545, loss: 0.03798019140958786 2023-01-23 18:10:24.383238: step: 122/1545, loss: 0.00010603432747302577 2023-01-23 18:10:25.351001: step: 124/1545, loss: 0.0008874664199538529 2023-01-23 18:10:26.183834: step: 126/1545, loss: 0.0003456006816122681 2023-01-23 18:10:27.069393: step: 128/1545, loss: 0.01083582267165184 2023-01-23 18:10:27.966994: step: 130/1545, loss: 0.00110049603972584 2023-01-23 18:10:28.849666: step: 132/1545, loss: 0.002515018219128251 2023-01-23 18:10:29.773085: step: 134/1545, loss: 0.056564658880233765 2023-01-23 18:10:30.632427: step: 136/1545, loss: 0.023385634645819664 2023-01-23 18:10:31.495859: step: 138/1545, loss: 0.00906005036085844 2023-01-23 18:10:32.361355: step: 140/1545, loss: 0.00011628221545834094 2023-01-23 18:10:33.257481: step: 142/1545, loss: 0.02479688450694084 2023-01-23 18:10:34.140894: step: 144/1545, loss: 0.1243501752614975 2023-01-23 18:10:35.019627: step: 146/1545, loss: 0.0036012697964906693 2023-01-23 18:10:35.912210: step: 148/1545, loss: 5.400533336796798e-05 2023-01-23 18:10:36.784558: step: 150/1545, loss: 0.0027200321201235056 2023-01-23 18:10:37.618481: step: 152/1545, loss: 0.012186317704617977 2023-01-23 18:10:38.507519: step: 154/1545, loss: 0.047861382365226746 2023-01-23 18:10:39.473531: step: 156/1545, loss: 0.0002815669868141413 2023-01-23 18:10:40.371871: step: 158/1545, loss: 0.0014734757132828236 2023-01-23 18:10:41.229993: step: 160/1545, loss: 0.3957739770412445 2023-01-23 18:10:42.092254: step: 162/1545, loss: 0.16752830147743225 2023-01-23 18:10:42.981585: step: 164/1545, loss: 0.3342415690422058 2023-01-23 18:10:43.912779: step: 166/1545, loss: 0.0021542448084801435 2023-01-23 18:10:44.817251: step: 168/1545, loss: 0.009835576638579369 2023-01-23 18:10:45.791010: step: 170/1545, loss: 0.035668861120939255 2023-01-23 18:10:46.659224: step: 172/1545, loss: 0.0006530631799250841 2023-01-23 18:10:47.543725: step: 174/1545, loss: 0.0002157260023523122 2023-01-23 18:10:48.452218: step: 176/1545, loss: 0.13933217525482178 2023-01-23 18:10:49.379817: step: 178/1545, loss: 0.001486936234869063 2023-01-23 18:10:50.324544: step: 180/1545, loss: 0.003199995029717684 2023-01-23 18:10:51.183608: step: 182/1545, loss: 0.18157179653644562 2023-01-23 18:10:52.021205: step: 184/1545, loss: 0.05552886426448822 2023-01-23 18:10:52.885205: step: 186/1545, loss: 0.006748497951775789 2023-01-23 18:10:53.763952: step: 188/1545, loss: 0.00040848154458217323 2023-01-23 18:10:54.598724: step: 190/1545, loss: 0.07917622476816177 2023-01-23 18:10:55.441757: step: 192/1545, loss: 0.01747302897274494 2023-01-23 18:10:56.340202: step: 194/1545, loss: 0.5775468945503235 2023-01-23 18:10:57.175660: step: 196/1545, loss: 0.020507169887423515 2023-01-23 18:10:58.083373: step: 198/1545, loss: 0.0462198406457901 2023-01-23 18:10:58.969566: step: 200/1545, loss: 8.124801388476044e-05 2023-01-23 18:10:59.897069: step: 202/1545, loss: 0.000879357336089015 2023-01-23 18:11:00.777542: step: 204/1545, loss: 5.159563079359941e-05 2023-01-23 18:11:01.646081: step: 206/1545, loss: 0.01119003351777792 2023-01-23 18:11:02.548185: step: 208/1545, loss: 0.7491781711578369 2023-01-23 18:11:03.409136: step: 210/1545, loss: 3.710889723151922e-05 2023-01-23 18:11:04.252112: step: 212/1545, loss: 0.0005567389889620245 2023-01-23 18:11:05.122783: step: 214/1545, loss: 0.0009711163002066314 2023-01-23 18:11:05.988696: step: 216/1545, loss: 0.2205110639333725 2023-01-23 18:11:06.852076: step: 218/1545, loss: 0.004960769787430763 2023-01-23 18:11:07.758267: step: 220/1545, loss: 0.014808735810220242 2023-01-23 18:11:08.618167: step: 222/1545, loss: 0.0005317027680575848 2023-01-23 18:11:09.499789: step: 224/1545, loss: 0.00016308495833072811 2023-01-23 18:11:10.391749: step: 226/1545, loss: 0.04012032225728035 2023-01-23 18:11:11.233316: step: 228/1545, loss: 0.00011856728815473616 2023-01-23 18:11:12.082303: step: 230/1545, loss: 0.0019215864595025778 2023-01-23 18:11:12.932887: step: 232/1545, loss: 0.0005748949479311705 2023-01-23 18:11:13.807127: step: 234/1545, loss: 0.20512545108795166 2023-01-23 18:11:14.670693: step: 236/1545, loss: 0.002861305605620146 2023-01-23 18:11:15.508206: step: 238/1545, loss: 0.0012139587197452784 2023-01-23 18:11:16.362448: step: 240/1545, loss: 0.007371901068836451 2023-01-23 18:11:17.197680: step: 242/1545, loss: -3.239986108383164e-05 2023-01-23 18:11:18.098380: step: 244/1545, loss: 0.002803347073495388 2023-01-23 18:11:18.982328: step: 246/1545, loss: 0.0010148384608328342 2023-01-23 18:11:19.852400: step: 248/1545, loss: 0.005142714362591505 2023-01-23 18:11:20.715004: step: 250/1545, loss: 0.0036852157209068537 2023-01-23 18:11:21.597582: step: 252/1545, loss: 0.00040333851939067245 2023-01-23 18:11:22.567022: step: 254/1545, loss: 0.09720992296934128 2023-01-23 18:11:23.495546: step: 256/1545, loss: 0.00010644164285622537 2023-01-23 18:11:24.351256: step: 258/1545, loss: 0.0083920331671834 2023-01-23 18:11:25.259619: step: 260/1545, loss: 0.07199276983737946 2023-01-23 18:11:26.147560: step: 262/1545, loss: 0.00022580393124371767 2023-01-23 18:11:27.160409: step: 264/1545, loss: 0.28713738918304443 2023-01-23 18:11:28.032729: step: 266/1545, loss: 0.07504823058843613 2023-01-23 18:11:28.932646: step: 268/1545, loss: 0.4408959448337555 2023-01-23 18:11:29.853162: step: 270/1545, loss: 0.00013860392209608108 2023-01-23 18:11:30.739164: step: 272/1545, loss: 0.2705616056919098 2023-01-23 18:11:31.629250: step: 274/1545, loss: 0.08274761587381363 2023-01-23 18:11:32.550538: step: 276/1545, loss: 0.028755197301506996 2023-01-23 18:11:33.460879: step: 278/1545, loss: 0.0022932272404432297 2023-01-23 18:11:34.340066: step: 280/1545, loss: 0.00083682662807405 2023-01-23 18:11:35.281659: step: 282/1545, loss: 0.0011223639594390988 2023-01-23 18:11:36.152030: step: 284/1545, loss: 0.00024383999698329717 2023-01-23 18:11:37.003002: step: 286/1545, loss: 0.004816442262381315 2023-01-23 18:11:37.887224: step: 288/1545, loss: 0.15535923838615417 2023-01-23 18:11:38.811869: step: 290/1545, loss: 0.05088963359594345 2023-01-23 18:11:39.709408: step: 292/1545, loss: 0.278323233127594 2023-01-23 18:11:40.641968: step: 294/1545, loss: 0.038432374596595764 2023-01-23 18:11:41.516816: step: 296/1545, loss: 0.00018023053416982293 2023-01-23 18:11:42.363473: step: 298/1545, loss: 0.005787189584225416 2023-01-23 18:11:43.270645: step: 300/1545, loss: 0.3051282465457916 2023-01-23 18:11:44.180718: step: 302/1545, loss: 0.08695342391729355 2023-01-23 18:11:45.171143: step: 304/1545, loss: -1.3205946743255481e-05 2023-01-23 18:11:46.114125: step: 306/1545, loss: 0.03721131011843681 2023-01-23 18:11:46.970378: step: 308/1545, loss: 0.27535003423690796 2023-01-23 18:11:47.875929: step: 310/1545, loss: 0.0016060486668720841 2023-01-23 18:11:48.795113: step: 312/1545, loss: 0.00020245609630364925 2023-01-23 18:11:49.708688: step: 314/1545, loss: 0.047707702964544296 2023-01-23 18:11:50.585109: step: 316/1545, loss: 0.000794843421317637 2023-01-23 18:11:51.412302: step: 318/1545, loss: 0.2076166868209839 2023-01-23 18:11:52.261115: step: 320/1545, loss: 0.24209043383598328 2023-01-23 18:11:53.147311: step: 322/1545, loss: 0.00039200842729769647 2023-01-23 18:11:54.012235: step: 324/1545, loss: 0.0007651326595805585 2023-01-23 18:11:54.917995: step: 326/1545, loss: 0.0004219762049615383 2023-01-23 18:11:55.826174: step: 328/1545, loss: 0.0032734335400164127 2023-01-23 18:11:56.739692: step: 330/1545, loss: 0.012042080983519554 2023-01-23 18:11:57.649687: step: 332/1545, loss: 0.004727596417069435 2023-01-23 18:11:58.580694: step: 334/1545, loss: 0.002167388331145048 2023-01-23 18:11:59.451707: step: 336/1545, loss: 0.08924781531095505 2023-01-23 18:12:00.340415: step: 338/1545, loss: 0.00038818659959360957 2023-01-23 18:12:01.198591: step: 340/1545, loss: 0.002397094387561083 2023-01-23 18:12:02.063275: step: 342/1545, loss: 0.00037758128019049764 2023-01-23 18:12:03.008055: step: 344/1545, loss: 0.09052674472332001 2023-01-23 18:12:03.902418: step: 346/1545, loss: 0.00015231489669531584 2023-01-23 18:12:04.782522: step: 348/1545, loss: 0.0005094234365969896 2023-01-23 18:12:05.628050: step: 350/1545, loss: 0.026271730661392212 2023-01-23 18:12:06.474113: step: 352/1545, loss: 0.6389873027801514 2023-01-23 18:12:07.351393: step: 354/1545, loss: 0.0019215355860069394 2023-01-23 18:12:08.239604: step: 356/1545, loss: 4.3233292672084644e-05 2023-01-23 18:12:09.085387: step: 358/1545, loss: 7.246337190736085e-05 2023-01-23 18:12:09.961657: step: 360/1545, loss: 0.0027347328141331673 2023-01-23 18:12:10.835301: step: 362/1545, loss: 0.08908525109291077 2023-01-23 18:12:11.758065: step: 364/1545, loss: 4.178644303465262e-05 2023-01-23 18:12:12.620214: step: 366/1545, loss: 0.04299865663051605 2023-01-23 18:12:13.508353: step: 368/1545, loss: 0.10333523154258728 2023-01-23 18:12:14.366372: step: 370/1545, loss: 0.33121851086616516 2023-01-23 18:12:15.255046: step: 372/1545, loss: 0.006967819295823574 2023-01-23 18:12:16.067689: step: 374/1545, loss: 0.012249622493982315 2023-01-23 18:12:16.930766: step: 376/1545, loss: 0.00043143643415533006 2023-01-23 18:12:17.803539: step: 378/1545, loss: 0.000962155289016664 2023-01-23 18:12:18.674390: step: 380/1545, loss: 0.00017428305000066757 2023-01-23 18:12:19.561196: step: 382/1545, loss: 0.00012691848678514361 2023-01-23 18:12:20.411032: step: 384/1545, loss: 0.037804510444402695 2023-01-23 18:12:21.291389: step: 386/1545, loss: 0.3205125331878662 2023-01-23 18:12:22.158965: step: 388/1545, loss: 0.0010383590124547482 2023-01-23 18:12:23.009834: step: 390/1545, loss: 0.2216346114873886 2023-01-23 18:12:23.901440: step: 392/1545, loss: 0.0014669219963252544 2023-01-23 18:12:24.844301: step: 394/1545, loss: 0.013538345694541931 2023-01-23 18:12:25.721266: step: 396/1545, loss: 0.00042549107456579804 2023-01-23 18:12:26.589446: step: 398/1545, loss: 0.00010393450793344527 2023-01-23 18:12:27.442556: step: 400/1545, loss: 0.0009038221323862672 2023-01-23 18:12:28.334736: step: 402/1545, loss: 0.04631045088171959 2023-01-23 18:12:29.244145: step: 404/1545, loss: 0.014505909755825996 2023-01-23 18:12:30.112409: step: 406/1545, loss: 0.00014287208614405245 2023-01-23 18:12:30.988684: step: 408/1545, loss: 0.00044815216097049415 2023-01-23 18:12:31.848772: step: 410/1545, loss: 0.0004902458749711514 2023-01-23 18:12:32.725377: step: 412/1545, loss: -6.88433783579967e-06 2023-01-23 18:12:33.582311: step: 414/1545, loss: 0.0005908830207772553 2023-01-23 18:12:34.504815: step: 416/1545, loss: 0.09423218667507172 2023-01-23 18:12:35.423018: step: 418/1545, loss: 0.007143879309296608 2023-01-23 18:12:36.296511: step: 420/1545, loss: 0.0033880923874676228 2023-01-23 18:12:37.196056: step: 422/1545, loss: 0.0002972641377709806 2023-01-23 18:12:38.093425: step: 424/1545, loss: 0.0008451268076896667 2023-01-23 18:12:38.981699: step: 426/1545, loss: 0.005718686617910862 2023-01-23 18:12:39.874488: step: 428/1545, loss: 0.0028937715105712414 2023-01-23 18:12:40.712001: step: 430/1545, loss: 0.00019447016529738903 2023-01-23 18:12:41.588159: step: 432/1545, loss: 0.0011409481521695852 2023-01-23 18:12:42.503649: step: 434/1545, loss: 0.005058016162365675 2023-01-23 18:12:43.506952: step: 436/1545, loss: 0.0018443330191075802 2023-01-23 18:12:44.384658: step: 438/1545, loss: 0.0002311473072040826 2023-01-23 18:12:45.266396: step: 440/1545, loss: 0.0008654851699247956 2023-01-23 18:12:46.152416: step: 442/1545, loss: 0.008146876469254494 2023-01-23 18:12:47.045070: step: 444/1545, loss: 0.0027795922942459583 2023-01-23 18:12:47.895949: step: 446/1545, loss: 0.00026055428315885365 2023-01-23 18:12:48.791367: step: 448/1545, loss: 0.0001927794946823269 2023-01-23 18:12:49.727808: step: 450/1545, loss: 0.0032737283036112785 2023-01-23 18:12:50.586113: step: 452/1545, loss: 0.0593191534280777 2023-01-23 18:12:51.428790: step: 454/1545, loss: 0.0016022816998884082 2023-01-23 18:12:52.289303: step: 456/1545, loss: 0.007191657554358244 2023-01-23 18:12:53.179059: step: 458/1545, loss: 0.3882168233394623 2023-01-23 18:12:54.049753: step: 460/1545, loss: 0.01353126298636198 2023-01-23 18:12:54.928162: step: 462/1545, loss: 0.060735009610652924 2023-01-23 18:12:55.786776: step: 464/1545, loss: 0.014339475892484188 2023-01-23 18:12:56.762983: step: 466/1545, loss: 0.005689290817826986 2023-01-23 18:12:57.637658: step: 468/1545, loss: 0.044341765344142914 2023-01-23 18:12:58.615501: step: 470/1545, loss: 0.0008760137134231627 2023-01-23 18:12:59.492068: step: 472/1545, loss: 0.0014689337695017457 2023-01-23 18:13:00.382921: step: 474/1545, loss: 0.12431232631206512 2023-01-23 18:13:01.215146: step: 476/1545, loss: 5.9901834902120754e-05 2023-01-23 18:13:02.046405: step: 478/1545, loss: 5.660920942318626e-05 2023-01-23 18:13:02.942054: step: 480/1545, loss: 0.002036512363702059 2023-01-23 18:13:03.817201: step: 482/1545, loss: 4.421470657689497e-05 2023-01-23 18:13:04.692045: step: 484/1545, loss: 0.002372348215430975 2023-01-23 18:13:05.567234: step: 486/1545, loss: 0.000321677332976833 2023-01-23 18:13:06.453328: step: 488/1545, loss: 0.00028505316004157066 2023-01-23 18:13:07.279562: step: 490/1545, loss: 0.16090422868728638 2023-01-23 18:13:08.146698: step: 492/1545, loss: 0.31457117199897766 2023-01-23 18:13:09.010811: step: 494/1545, loss: 0.01202855072915554 2023-01-23 18:13:09.883465: step: 496/1545, loss: 0.1957809329032898 2023-01-23 18:13:10.753616: step: 498/1545, loss: 7.629302854184061e-05 2023-01-23 18:13:11.625371: step: 500/1545, loss: 0.04995904117822647 2023-01-23 18:13:12.506808: step: 502/1545, loss: 0.5722449421882629 2023-01-23 18:13:13.352952: step: 504/1545, loss: 0.0006339683313854039 2023-01-23 18:13:14.212103: step: 506/1545, loss: 0.0029626134783029556 2023-01-23 18:13:15.104691: step: 508/1545, loss: 0.11605483293533325 2023-01-23 18:13:16.003901: step: 510/1545, loss: 0.0035377400927245617 2023-01-23 18:13:16.884197: step: 512/1545, loss: 0.0002824012190103531 2023-01-23 18:13:17.810167: step: 514/1545, loss: 0.031886227428913116 2023-01-23 18:13:18.693994: step: 516/1545, loss: 0.08731114864349365 2023-01-23 18:13:19.671292: step: 518/1545, loss: 0.0862080380320549 2023-01-23 18:13:20.557217: step: 520/1545, loss: 0.012262610718607903 2023-01-23 18:13:21.490035: step: 522/1545, loss: 0.0017257886938750744 2023-01-23 18:13:22.373984: step: 524/1545, loss: 0.0010116673074662685 2023-01-23 18:13:23.226273: step: 526/1545, loss: 0.00020019648945890367 2023-01-23 18:13:24.126390: step: 528/1545, loss: 0.0002385129628237337 2023-01-23 18:13:25.081375: step: 530/1545, loss: 0.07958874851465225 2023-01-23 18:13:25.955371: step: 532/1545, loss: 0.010209404863417149 2023-01-23 18:13:26.865818: step: 534/1545, loss: 2.595781916170381e-05 2023-01-23 18:13:27.747926: step: 536/1545, loss: 0.14486698806285858 2023-01-23 18:13:28.602665: step: 538/1545, loss: 0.0011889132438227534 2023-01-23 18:13:29.493605: step: 540/1545, loss: 0.23745957016944885 2023-01-23 18:13:30.378820: step: 542/1545, loss: 0.0018816911615431309 2023-01-23 18:13:31.258048: step: 544/1545, loss: 0.02433442510664463 2023-01-23 18:13:32.117664: step: 546/1545, loss: 0.0024410486221313477 2023-01-23 18:13:32.987375: step: 548/1545, loss: 0.008247723802924156 2023-01-23 18:13:33.847868: step: 550/1545, loss: 0.0011137755354866385 2023-01-23 18:13:34.728696: step: 552/1545, loss: 0.00026979768881574273 2023-01-23 18:13:35.610942: step: 554/1545, loss: 0.0005638268194161355 2023-01-23 18:13:36.473431: step: 556/1545, loss: 0.0012707889545708895 2023-01-23 18:13:37.314965: step: 558/1545, loss: 0.028744572773575783 2023-01-23 18:13:38.165967: step: 560/1545, loss: 0.002484212862327695 2023-01-23 18:13:39.093069: step: 562/1545, loss: 0.06595905125141144 2023-01-23 18:13:39.965906: step: 564/1545, loss: 0.008474322035908699 2023-01-23 18:13:40.889600: step: 566/1545, loss: 0.016460221260786057 2023-01-23 18:13:41.748129: step: 568/1545, loss: 0.13472199440002441 2023-01-23 18:13:42.600566: step: 570/1545, loss: 0.0005886571598239243 2023-01-23 18:13:43.521199: step: 572/1545, loss: 0.003954601474106312 2023-01-23 18:13:44.396059: step: 574/1545, loss: 6.718905933666974e-05 2023-01-23 18:13:45.267570: step: 576/1545, loss: 0.10536862909793854 2023-01-23 18:13:46.117823: step: 578/1545, loss: 0.004861647728830576 2023-01-23 18:13:47.040446: step: 580/1545, loss: 0.43555736541748047 2023-01-23 18:13:47.955080: step: 582/1545, loss: 0.2979060113430023 2023-01-23 18:13:48.826283: step: 584/1545, loss: 0.0008582043810747564 2023-01-23 18:13:49.724868: step: 586/1545, loss: 0.25544360280036926 2023-01-23 18:13:50.620636: step: 588/1545, loss: 0.003267045598477125 2023-01-23 18:13:51.540747: step: 590/1545, loss: 9.711047459859401e-05 2023-01-23 18:13:52.468769: step: 592/1545, loss: 0.1575787514448166 2023-01-23 18:13:53.330606: step: 594/1545, loss: 0.0029227181803435087 2023-01-23 18:13:54.237131: step: 596/1545, loss: 0.0016240550903603435 2023-01-23 18:13:55.112437: step: 598/1545, loss: 0.002642255276441574 2023-01-23 18:13:56.081451: step: 600/1545, loss: 0.012380578555166721 2023-01-23 18:13:56.937994: step: 602/1545, loss: 0.047352224588394165 2023-01-23 18:13:57.819449: step: 604/1545, loss: 0.09443757683038712 2023-01-23 18:13:58.672702: step: 606/1545, loss: 0.0009767356095835567 2023-01-23 18:13:59.544824: step: 608/1545, loss: 0.0002684015198610723 2023-01-23 18:14:00.406188: step: 610/1545, loss: 0.000575248384848237 2023-01-23 18:14:01.300568: step: 612/1545, loss: 0.11673836410045624 2023-01-23 18:14:02.146837: step: 614/1545, loss: 7.102415838744491e-05 2023-01-23 18:14:03.082955: step: 616/1545, loss: 0.03734741732478142 2023-01-23 18:14:03.999393: step: 618/1545, loss: 0.007953496649861336 2023-01-23 18:14:04.934845: step: 620/1545, loss: 0.0327356718480587 2023-01-23 18:14:05.807165: step: 622/1545, loss: 1.0558948815742042e-05 2023-01-23 18:14:06.667560: step: 624/1545, loss: 0.042389605194330215 2023-01-23 18:14:07.544978: step: 626/1545, loss: 0.019637824967503548 2023-01-23 18:14:08.393908: step: 628/1545, loss: 0.0014291066909208894 2023-01-23 18:14:09.276361: step: 630/1545, loss: 0.011224409565329552 2023-01-23 18:14:10.153015: step: 632/1545, loss: 0.04332074150443077 2023-01-23 18:14:11.045813: step: 634/1545, loss: 0.45109230279922485 2023-01-23 18:14:11.995401: step: 636/1545, loss: 0.011906227096915245 2023-01-23 18:14:12.868055: step: 638/1545, loss: 0.0008514283108524978 2023-01-23 18:14:13.749606: step: 640/1545, loss: 0.011134641245007515 2023-01-23 18:14:14.608958: step: 642/1545, loss: 0.11550170928239822 2023-01-23 18:14:15.505593: step: 644/1545, loss: 0.06519521027803421 2023-01-23 18:14:16.355740: step: 646/1545, loss: 0.002683365950360894 2023-01-23 18:14:17.233774: step: 648/1545, loss: 1.3375952243804932 2023-01-23 18:14:18.143229: step: 650/1545, loss: 8.121368591673672e-05 2023-01-23 18:14:18.993328: step: 652/1545, loss: 0.010571418330073357 2023-01-23 18:14:19.859930: step: 654/1545, loss: 0.014065856114029884 2023-01-23 18:14:20.716714: step: 656/1545, loss: 0.0005503345164470375 2023-01-23 18:14:21.577102: step: 658/1545, loss: 0.6018036007881165 2023-01-23 18:14:22.438341: step: 660/1545, loss: 0.0011913544731214643 2023-01-23 18:14:23.293438: step: 662/1545, loss: 0.0001152073236880824 2023-01-23 18:14:24.147021: step: 664/1545, loss: 0.00015830568736419082 2023-01-23 18:14:25.003565: step: 666/1545, loss: 0.0005958810215815902 2023-01-23 18:14:25.876361: step: 668/1545, loss: 0.0020898766815662384 2023-01-23 18:14:26.728082: step: 670/1545, loss: 0.0006139667821116745 2023-01-23 18:14:27.637773: step: 672/1545, loss: 0.09857751429080963 2023-01-23 18:14:28.583829: step: 674/1545, loss: 0.0008191683446057141 2023-01-23 18:14:29.495237: step: 676/1545, loss: -8.106766472337767e-06 2023-01-23 18:14:30.404757: step: 678/1545, loss: 0.001330299535766244 2023-01-23 18:14:31.244974: step: 680/1545, loss: 0.00042708893306553364 2023-01-23 18:14:32.103121: step: 682/1545, loss: 0.0001626227458473295 2023-01-23 18:14:33.010484: step: 684/1545, loss: 0.3151724338531494 2023-01-23 18:14:33.920376: step: 686/1545, loss: 2.4211598429246806e-05 2023-01-23 18:14:34.772717: step: 688/1545, loss: 0.007945215329527855 2023-01-23 18:14:35.645024: step: 690/1545, loss: 0.0006468776846304536 2023-01-23 18:14:36.574577: step: 692/1545, loss: 0.0013146793935447931 2023-01-23 18:14:37.470989: step: 694/1545, loss: 6.72563910484314e-05 2023-01-23 18:14:38.333469: step: 696/1545, loss: 0.010973258875310421 2023-01-23 18:14:39.222667: step: 698/1545, loss: 0.000245523959165439 2023-01-23 18:14:40.150058: step: 700/1545, loss: 0.0009134757565334439 2023-01-23 18:14:41.017455: step: 702/1545, loss: 0.002165642101317644 2023-01-23 18:14:41.878789: step: 704/1545, loss: 0.3765856623649597 2023-01-23 18:14:42.739731: step: 706/1545, loss: 0.2757531404495239 2023-01-23 18:14:43.592778: step: 708/1545, loss: 3.929553349735215e-05 2023-01-23 18:14:44.496994: step: 710/1545, loss: 0.09926638007164001 2023-01-23 18:14:45.321116: step: 712/1545, loss: -2.2981339498073794e-08 2023-01-23 18:14:46.182091: step: 714/1545, loss: 0.0024318075738847256 2023-01-23 18:14:47.043602: step: 716/1545, loss: 0.37562569975852966 2023-01-23 18:14:47.921207: step: 718/1545, loss: 0.0004656341334339231 2023-01-23 18:14:48.789192: step: 720/1545, loss: 0.04777131974697113 2023-01-23 18:14:49.692429: step: 722/1545, loss: 0.13008171319961548 2023-01-23 18:14:50.544010: step: 724/1545, loss: 4.060023307800293 2023-01-23 18:14:51.396912: step: 726/1545, loss: 0.01950816437602043 2023-01-23 18:14:52.319017: step: 728/1545, loss: 0.011933770962059498 2023-01-23 18:14:53.249128: step: 730/1545, loss: 0.00023455839254893363 2023-01-23 18:14:54.173771: step: 732/1545, loss: 0.004862156230956316 2023-01-23 18:14:55.074830: step: 734/1545, loss: 0.00011911727779079229 2023-01-23 18:14:55.969798: step: 736/1545, loss: 0.00012559146853163838 2023-01-23 18:14:56.845874: step: 738/1545, loss: 0.0008775662863627076 2023-01-23 18:14:57.723871: step: 740/1545, loss: 0.0008379295468330383 2023-01-23 18:14:58.645829: step: 742/1545, loss: -4.1893208617693745e-06 2023-01-23 18:14:59.538971: step: 744/1545, loss: 4.908783012069762e-05 2023-01-23 18:15:00.431437: step: 746/1545, loss: 0.0020349116530269384 2023-01-23 18:15:01.317612: step: 748/1545, loss: 0.0027854114305227995 2023-01-23 18:15:02.182113: step: 750/1545, loss: 0.03724723309278488 2023-01-23 18:15:03.105096: step: 752/1545, loss: 0.0012088470393791795 2023-01-23 18:15:03.951077: step: 754/1545, loss: 0.7378506064414978 2023-01-23 18:15:04.791852: step: 756/1545, loss: 0.0017572554061189294 2023-01-23 18:15:05.670507: step: 758/1545, loss: 0.21466580033302307 2023-01-23 18:15:06.523196: step: 760/1545, loss: 0.3095189332962036 2023-01-23 18:15:07.422161: step: 762/1545, loss: 0.0016013872809708118 2023-01-23 18:15:08.274513: step: 764/1545, loss: 0.003200926585122943 2023-01-23 18:15:09.124498: step: 766/1545, loss: 0.013236895203590393 2023-01-23 18:15:10.043610: step: 768/1545, loss: 0.005991174373775721 2023-01-23 18:15:10.934205: step: 770/1545, loss: 0.013414313085377216 2023-01-23 18:15:11.792993: step: 772/1545, loss: 0.0009143315837718546 2023-01-23 18:15:12.730027: step: 774/1545, loss: 0.00012665278336498886 2023-01-23 18:15:13.612069: step: 776/1545, loss: 0.08753755688667297 2023-01-23 18:15:14.497492: step: 778/1545, loss: 0.005207234527915716 2023-01-23 18:15:15.365079: step: 780/1545, loss: 0.25908493995666504 2023-01-23 18:15:16.242279: step: 782/1545, loss: 0.00033954938407987356 2023-01-23 18:15:17.076250: step: 784/1545, loss: 0.0016274267109110951 2023-01-23 18:15:17.968741: step: 786/1545, loss: 0.0006737806834280491 2023-01-23 18:15:18.830370: step: 788/1545, loss: 1.0600434507068712e-05 2023-01-23 18:15:19.699722: step: 790/1545, loss: 0.139201819896698 2023-01-23 18:15:20.593748: step: 792/1545, loss: 0.0001021212010527961 2023-01-23 18:15:21.461568: step: 794/1545, loss: 0.000925831904169172 2023-01-23 18:15:22.336870: step: 796/1545, loss: 0.060569338500499725 2023-01-23 18:15:23.252646: step: 798/1545, loss: 0.04646412655711174 2023-01-23 18:15:24.117343: step: 800/1545, loss: 2.9962913686176762e-05 2023-01-23 18:15:25.000908: step: 802/1545, loss: 6.000000212225132e-05 2023-01-23 18:15:25.876645: step: 804/1545, loss: 0.011343119665980339 2023-01-23 18:15:26.782061: step: 806/1545, loss: 0.010381356813013554 2023-01-23 18:15:27.656923: step: 808/1545, loss: 0.0007274942472577095 2023-01-23 18:15:28.590624: step: 810/1545, loss: 0.00036488298792392015 2023-01-23 18:15:29.466262: step: 812/1545, loss: 3.840454155579209e-05 2023-01-23 18:15:30.328122: step: 814/1545, loss: 0.0001853197900345549 2023-01-23 18:15:31.170610: step: 816/1545, loss: 0.0005917164962738752 2023-01-23 18:15:32.057290: step: 818/1545, loss: 0.008402402512729168 2023-01-23 18:15:32.936150: step: 820/1545, loss: 0.02752874605357647 2023-01-23 18:15:33.857974: step: 822/1545, loss: 7.117480708984658e-05 2023-01-23 18:15:34.762929: step: 824/1545, loss: 2.3431992303812876e-05 2023-01-23 18:15:35.759678: step: 826/1545, loss: 0.0022585391998291016 2023-01-23 18:15:36.642423: step: 828/1545, loss: 0.005220561753958464 2023-01-23 18:15:37.502862: step: 830/1545, loss: 0.022360187023878098 2023-01-23 18:15:38.386283: step: 832/1545, loss: 0.006088735535740852 2023-01-23 18:15:39.304546: step: 834/1545, loss: 0.0063529242761433125 2023-01-23 18:15:40.307629: step: 836/1545, loss: 0.002016062382608652 2023-01-23 18:15:41.176628: step: 838/1545, loss: 0.1011558398604393 2023-01-23 18:15:42.073502: step: 840/1545, loss: 0.0032136044465005398 2023-01-23 18:15:42.948300: step: 842/1545, loss: 0.010623577050864697 2023-01-23 18:15:43.838050: step: 844/1545, loss: 0.128693625330925 2023-01-23 18:15:44.736100: step: 846/1545, loss: 0.0002682046906556934 2023-01-23 18:15:45.682040: step: 848/1545, loss: 0.0004382629704196006 2023-01-23 18:15:46.615540: step: 850/1545, loss: 0.00041487260023131967 2023-01-23 18:15:47.515498: step: 852/1545, loss: 0.1295403093099594 2023-01-23 18:15:48.376088: step: 854/1545, loss: 2.1390615074778907e-05 2023-01-23 18:15:49.296125: step: 856/1545, loss: 0.010487859137356281 2023-01-23 18:15:50.146248: step: 858/1545, loss: 0.010000143200159073 2023-01-23 18:15:51.038400: step: 860/1545, loss: 0.008689234033226967 2023-01-23 18:15:51.910774: step: 862/1545, loss: 0.0065957168117165565 2023-01-23 18:15:52.784604: step: 864/1545, loss: 6.684660183964297e-05 2023-01-23 18:15:53.649523: step: 866/1545, loss: 0.08157972246408463 2023-01-23 18:15:54.580562: step: 868/1545, loss: 0.001323049422353506 2023-01-23 18:15:55.513886: step: 870/1545, loss: 0.8359201550483704 2023-01-23 18:15:56.366093: step: 872/1545, loss: 0.00040568638360127807 2023-01-23 18:15:57.248924: step: 874/1545, loss: -1.205989065056201e-05 2023-01-23 18:15:58.110511: step: 876/1545, loss: 0.005132101476192474 2023-01-23 18:15:58.953451: step: 878/1545, loss: 0.13144080340862274 2023-01-23 18:15:59.818626: step: 880/1545, loss: 0.0017557439859956503 2023-01-23 18:16:00.813307: step: 882/1545, loss: 0.018315602093935013 2023-01-23 18:16:01.686159: step: 884/1545, loss: 0.0001695899263722822 2023-01-23 18:16:02.530453: step: 886/1545, loss: 0.008530015125870705 2023-01-23 18:16:03.369614: step: 888/1545, loss: 0.06433591991662979 2023-01-23 18:16:04.223006: step: 890/1545, loss: 0.00017784394731279463 2023-01-23 18:16:05.084159: step: 892/1545, loss: 0.00012144709762651473 2023-01-23 18:16:05.998197: step: 894/1545, loss: 0.22427144646644592 2023-01-23 18:16:06.885181: step: 896/1545, loss: 0.003958337940275669 2023-01-23 18:16:07.774489: step: 898/1545, loss: 0.0007895000744611025 2023-01-23 18:16:08.665549: step: 900/1545, loss: 0.002087471541017294 2023-01-23 18:16:09.587292: step: 902/1545, loss: 0.13392898440361023 2023-01-23 18:16:10.497236: step: 904/1545, loss: 0.0003348630852997303 2023-01-23 18:16:11.526539: step: 906/1545, loss: 0.0011933366768062115 2023-01-23 18:16:12.422366: step: 908/1545, loss: 1.1550401449203491 2023-01-23 18:16:13.288249: step: 910/1545, loss: 0.00022430195531342179 2023-01-23 18:16:14.183531: step: 912/1545, loss: 0.008080514147877693 2023-01-23 18:16:15.171326: step: 914/1545, loss: 0.2665823996067047 2023-01-23 18:16:16.106240: step: 916/1545, loss: 0.0013525118120014668 2023-01-23 18:16:16.964371: step: 918/1545, loss: 0.009009708650410175 2023-01-23 18:16:17.857787: step: 920/1545, loss: 0.30199041962623596 2023-01-23 18:16:18.778702: step: 922/1545, loss: 0.0008388535352423787 2023-01-23 18:16:19.676184: step: 924/1545, loss: 0.19777469336986542 2023-01-23 18:16:20.545060: step: 926/1545, loss: 0.004780387505888939 2023-01-23 18:16:21.511413: step: 928/1545, loss: 0.0004917357582598925 2023-01-23 18:16:22.382189: step: 930/1545, loss: 0.00011327900574542582 2023-01-23 18:16:23.227403: step: 932/1545, loss: 0.00011617871496127918 2023-01-23 18:16:24.123430: step: 934/1545, loss: 8.323975634993985e-05 2023-01-23 18:16:25.007878: step: 936/1545, loss: 0.00044368591625243425 2023-01-23 18:16:25.909731: step: 938/1545, loss: 8.275040454464033e-05 2023-01-23 18:16:26.802711: step: 940/1545, loss: 0.005080035887658596 2023-01-23 18:16:27.676446: step: 942/1545, loss: 0.04203770309686661 2023-01-23 18:16:28.560531: step: 944/1545, loss: 1.799603705876507e-05 2023-01-23 18:16:29.426491: step: 946/1545, loss: 0.000578309060074389 2023-01-23 18:16:30.384652: step: 948/1545, loss: 0.6391181349754333 2023-01-23 18:16:31.260849: step: 950/1545, loss: 0.0004410072579048574 2023-01-23 18:16:32.168529: step: 952/1545, loss: 0.061973754316568375 2023-01-23 18:16:33.000203: step: 954/1545, loss: 0.0010032852878794074 2023-01-23 18:16:33.864796: step: 956/1545, loss: 1.0010508049163036e-06 2023-01-23 18:16:34.742907: step: 958/1545, loss: 0.00018703562091104686 2023-01-23 18:16:35.623234: step: 960/1545, loss: 0.025503182783722878 2023-01-23 18:16:36.484647: step: 962/1545, loss: 0.0008113516960293055 2023-01-23 18:16:37.347497: step: 964/1545, loss: 0.11217188835144043 2023-01-23 18:16:38.175547: step: 966/1545, loss: 0.00020474886696320027 2023-01-23 18:16:39.097845: step: 968/1545, loss: 0.2039516121149063 2023-01-23 18:16:39.962426: step: 970/1545, loss: 0.0100880591198802 2023-01-23 18:16:40.863030: step: 972/1545, loss: 0.0006568881217390299 2023-01-23 18:16:41.721441: step: 974/1545, loss: 0.039946287870407104 2023-01-23 18:16:42.570556: step: 976/1545, loss: 0.0013575161574408412 2023-01-23 18:16:43.468002: step: 978/1545, loss: 0.14133965969085693 2023-01-23 18:16:44.315989: step: 980/1545, loss: 0.002049836562946439 2023-01-23 18:16:45.213964: step: 982/1545, loss: 0.00029785785591229796 2023-01-23 18:16:46.145771: step: 984/1545, loss: 0.02760091796517372 2023-01-23 18:16:47.068533: step: 986/1545, loss: 0.08865603804588318 2023-01-23 18:16:47.921072: step: 988/1545, loss: 0.00046066264621913433 2023-01-23 18:16:48.807086: step: 990/1545, loss: 0.08024398982524872 2023-01-23 18:16:49.701793: step: 992/1545, loss: 0.1275734007358551 2023-01-23 18:16:50.595739: step: 994/1545, loss: 0.003730837721377611 2023-01-23 18:16:51.499555: step: 996/1545, loss: 0.007985546253621578 2023-01-23 18:16:52.359254: step: 998/1545, loss: 0.21611672639846802 2023-01-23 18:16:53.243050: step: 1000/1545, loss: 0.0015867309411987662 2023-01-23 18:16:54.126352: step: 1002/1545, loss: 0.0025435276329517365 2023-01-23 18:16:55.077999: step: 1004/1545, loss: 0.15233170986175537 2023-01-23 18:16:55.968789: step: 1006/1545, loss: 0.004178771283477545 2023-01-23 18:16:56.862957: step: 1008/1545, loss: 0.0004932735464535654 2023-01-23 18:16:57.801508: step: 1010/1545, loss: 0.017033904790878296 2023-01-23 18:16:58.720537: step: 1012/1545, loss: 0.005321761593222618 2023-01-23 18:16:59.579987: step: 1014/1545, loss: 0.0003836305986624211 2023-01-23 18:17:00.485174: step: 1016/1545, loss: 0.0002350247377762571 2023-01-23 18:17:01.356414: step: 1018/1545, loss: 0.05465662479400635 2023-01-23 18:17:02.258309: step: 1020/1545, loss: 0.20795443654060364 2023-01-23 18:17:03.139540: step: 1022/1545, loss: 0.002898979699239135 2023-01-23 18:17:04.004778: step: 1024/1545, loss: 0.047495290637016296 2023-01-23 18:17:04.910181: step: 1026/1545, loss: 0.14415885508060455 2023-01-23 18:17:05.789605: step: 1028/1545, loss: 0.0007973290048539639 2023-01-23 18:17:06.687079: step: 1030/1545, loss: 5.678606248693541e-05 2023-01-23 18:17:07.574893: step: 1032/1545, loss: 0.0007800577441230416 2023-01-23 18:17:08.449757: step: 1034/1545, loss: 0.04143843054771423 2023-01-23 18:17:09.315557: step: 1036/1545, loss: 0.15962007641792297 2023-01-23 18:17:10.257881: step: 1038/1545, loss: 0.35119426250457764 2023-01-23 18:17:11.238548: step: 1040/1545, loss: 0.2074175328016281 2023-01-23 18:17:12.107503: step: 1042/1545, loss: 0.04437081515789032 2023-01-23 18:17:13.019456: step: 1044/1545, loss: 0.0361684188246727 2023-01-23 18:17:13.983664: step: 1046/1545, loss: 0.0017596579855307937 2023-01-23 18:17:14.883193: step: 1048/1545, loss: 0.009802596643567085 2023-01-23 18:17:15.789855: step: 1050/1545, loss: 0.13880501687526703 2023-01-23 18:17:16.704164: step: 1052/1545, loss: 0.03251820057630539 2023-01-23 18:17:17.558320: step: 1054/1545, loss: 0.005265243351459503 2023-01-23 18:17:18.447716: step: 1056/1545, loss: 0.000884757493622601 2023-01-23 18:17:19.330068: step: 1058/1545, loss: 0.1549559384584427 2023-01-23 18:17:20.293713: step: 1060/1545, loss: 0.0012581280898302794 2023-01-23 18:17:21.226857: step: 1062/1545, loss: 0.06930362433195114 2023-01-23 18:17:22.198405: step: 1064/1545, loss: 0.0019297533435747027 2023-01-23 18:17:23.123289: step: 1066/1545, loss: 0.061739731580019 2023-01-23 18:17:23.996466: step: 1068/1545, loss: 0.0033462292049080133 2023-01-23 18:17:24.846122: step: 1070/1545, loss: 0.0028393904212862253 2023-01-23 18:17:25.713786: step: 1072/1545, loss: 0.0025416151620447636 2023-01-23 18:17:26.581386: step: 1074/1545, loss: 0.040243636816740036 2023-01-23 18:17:27.449441: step: 1076/1545, loss: 0.02216900885105133 2023-01-23 18:17:28.339059: step: 1078/1545, loss: 0.009517882019281387 2023-01-23 18:17:29.249476: step: 1080/1545, loss: 0.011273385025560856 2023-01-23 18:17:30.115879: step: 1082/1545, loss: 0.007779025938361883 2023-01-23 18:17:30.976812: step: 1084/1545, loss: 0.026454035192728043 2023-01-23 18:17:31.830050: step: 1086/1545, loss: 0.4199705421924591 2023-01-23 18:17:32.770795: step: 1088/1545, loss: 0.19046276807785034 2023-01-23 18:17:33.673672: step: 1090/1545, loss: 0.0007728114142082632 2023-01-23 18:17:34.584867: step: 1092/1545, loss: 0.03780754655599594 2023-01-23 18:17:35.482714: step: 1094/1545, loss: 0.00036971591180190444 2023-01-23 18:17:36.362016: step: 1096/1545, loss: 0.0024988988880068064 2023-01-23 18:17:37.236734: step: 1098/1545, loss: 0.0019991518929600716 2023-01-23 18:17:38.237473: step: 1100/1545, loss: 0.18550439178943634 2023-01-23 18:17:39.078110: step: 1102/1545, loss: 0.0005159756983630359 2023-01-23 18:17:39.950981: step: 1104/1545, loss: 0.1775619089603424 2023-01-23 18:17:40.846212: step: 1106/1545, loss: 0.03343109413981438 2023-01-23 18:17:41.724392: step: 1108/1545, loss: 0.01638731360435486 2023-01-23 18:17:42.617076: step: 1110/1545, loss: 0.0005299840122461319 2023-01-23 18:17:43.530050: step: 1112/1545, loss: 0.003183129243552685 2023-01-23 18:17:44.448678: step: 1114/1545, loss: 0.000386545667424798 2023-01-23 18:17:45.374492: step: 1116/1545, loss: 0.0003073238185606897 2023-01-23 18:17:46.209227: step: 1118/1545, loss: 0.0002840430533979088 2023-01-23 18:17:47.064647: step: 1120/1545, loss: 0.1608705222606659 2023-01-23 18:17:47.906402: step: 1122/1545, loss: 0.0009855796815827489 2023-01-23 18:17:48.766382: step: 1124/1545, loss: 0.07404068112373352 2023-01-23 18:17:49.672012: step: 1126/1545, loss: 0.03588424250483513 2023-01-23 18:17:50.548441: step: 1128/1545, loss: 0.10940996557474136 2023-01-23 18:17:51.488871: step: 1130/1545, loss: 0.0051914723590016365 2023-01-23 18:17:52.370334: step: 1132/1545, loss: 0.07739832252264023 2023-01-23 18:17:53.223681: step: 1134/1545, loss: 0.00020246859639883041 2023-01-23 18:17:54.060908: step: 1136/1545, loss: 0.0015912564704194665 2023-01-23 18:17:54.929763: step: 1138/1545, loss: 0.0001226973399752751 2023-01-23 18:17:55.760162: step: 1140/1545, loss: 0.0376620814204216 2023-01-23 18:17:56.692593: step: 1142/1545, loss: 0.09956348687410355 2023-01-23 18:17:57.549501: step: 1144/1545, loss: 0.012347330339252949 2023-01-23 18:17:58.440994: step: 1146/1545, loss: 0.00029201130382716656 2023-01-23 18:17:59.319062: step: 1148/1545, loss: 0.12289348989725113 2023-01-23 18:18:00.316812: step: 1150/1545, loss: 0.0410485602915287 2023-01-23 18:18:01.206360: step: 1152/1545, loss: 0.01242821104824543 2023-01-23 18:18:02.074571: step: 1154/1545, loss: 0.00010572056635282934 2023-01-23 18:18:02.952382: step: 1156/1545, loss: 0.02296122908592224 2023-01-23 18:18:03.834498: step: 1158/1545, loss: 0.0008564847521483898 2023-01-23 18:18:04.710660: step: 1160/1545, loss: 0.09026443213224411 2023-01-23 18:18:05.591225: step: 1162/1545, loss: 0.08456050604581833 2023-01-23 18:18:06.463562: step: 1164/1545, loss: 0.006313161924481392 2023-01-23 18:18:07.330005: step: 1166/1545, loss: 0.0013374468544498086 2023-01-23 18:18:08.246016: step: 1168/1545, loss: 0.00052397430408746 2023-01-23 18:18:09.118679: step: 1170/1545, loss: 0.09209410846233368 2023-01-23 18:18:10.043624: step: 1172/1545, loss: 0.0023842251393944025 2023-01-23 18:18:10.924622: step: 1174/1545, loss: 0.0002036608348134905 2023-01-23 18:18:11.775556: step: 1176/1545, loss: 0.015587059780955315 2023-01-23 18:18:12.668817: step: 1178/1545, loss: 0.06592515856027603 2023-01-23 18:18:13.535703: step: 1180/1545, loss: 0.018479270860552788 2023-01-23 18:18:14.426502: step: 1182/1545, loss: 0.03397736698389053 2023-01-23 18:18:15.301392: step: 1184/1545, loss: 0.0008454565540887415 2023-01-23 18:18:16.156919: step: 1186/1545, loss: 0.013842657208442688 2023-01-23 18:18:17.035755: step: 1188/1545, loss: 0.0054448568262159824 2023-01-23 18:18:17.898379: step: 1190/1545, loss: 9.761211549630389e-05 2023-01-23 18:18:18.743262: step: 1192/1545, loss: 0.41804295778274536 2023-01-23 18:18:19.723931: step: 1194/1545, loss: 0.20676574110984802 2023-01-23 18:18:20.581624: step: 1196/1545, loss: 0.001674195285886526 2023-01-23 18:18:21.412072: step: 1198/1545, loss: 0.0006634414894506335 2023-01-23 18:18:22.258026: step: 1200/1545, loss: 0.0001205604785354808 2023-01-23 18:18:23.130081: step: 1202/1545, loss: 0.14148244261741638 2023-01-23 18:18:23.961761: step: 1204/1545, loss: 0.07920505851507187 2023-01-23 18:18:24.816839: step: 1206/1545, loss: 0.05489616468548775 2023-01-23 18:18:25.680745: step: 1208/1545, loss: 4.573139449348673e-05 2023-01-23 18:18:26.599156: step: 1210/1545, loss: 6.608873809454963e-05 2023-01-23 18:18:27.476994: step: 1212/1545, loss: 0.01992446929216385 2023-01-23 18:18:28.386599: step: 1214/1545, loss: 0.33110177516937256 2023-01-23 18:18:29.266198: step: 1216/1545, loss: 0.016369951888918877 2023-01-23 18:18:30.191133: step: 1218/1545, loss: 0.00020582294382620603 2023-01-23 18:18:31.121169: step: 1220/1545, loss: 0.0004447247483767569 2023-01-23 18:18:32.001042: step: 1222/1545, loss: 2.4879700504243374e-06 2023-01-23 18:18:32.869068: step: 1224/1545, loss: 0.0008524322183802724 2023-01-23 18:18:33.774094: step: 1226/1545, loss: 0.0028363498859107494 2023-01-23 18:18:34.639176: step: 1228/1545, loss: 0.003426107345148921 2023-01-23 18:18:35.505515: step: 1230/1545, loss: 0.001740850042551756 2023-01-23 18:18:36.356711: step: 1232/1545, loss: 0.0011840090155601501 2023-01-23 18:18:37.231559: step: 1234/1545, loss: 0.00013749497884418815 2023-01-23 18:18:38.085491: step: 1236/1545, loss: 0.001336248591542244 2023-01-23 18:18:38.944431: step: 1238/1545, loss: 0.0002765383687801659 2023-01-23 18:18:39.821912: step: 1240/1545, loss: 0.0007379677263088524 2023-01-23 18:18:40.752521: step: 1242/1545, loss: 0.0011761230416595936 2023-01-23 18:18:41.656380: step: 1244/1545, loss: 0.0012772169429808855 2023-01-23 18:18:42.542852: step: 1246/1545, loss: 0.030479837208986282 2023-01-23 18:18:43.410194: step: 1248/1545, loss: 0.0001527883723611012 2023-01-23 18:18:44.359966: step: 1250/1545, loss: 0.009136730805039406 2023-01-23 18:18:45.281489: step: 1252/1545, loss: 0.0031238256487995386 2023-01-23 18:18:46.184347: step: 1254/1545, loss: 0.07693924009799957 2023-01-23 18:18:47.079545: step: 1256/1545, loss: 0.00011432720202719793 2023-01-23 18:18:48.001163: step: 1258/1545, loss: 0.0051404619589447975 2023-01-23 18:18:48.895253: step: 1260/1545, loss: 0.00013919988123234361 2023-01-23 18:18:49.780278: step: 1262/1545, loss: 0.49428415298461914 2023-01-23 18:18:50.652165: step: 1264/1545, loss: 0.0005128760822117329 2023-01-23 18:18:51.533698: step: 1266/1545, loss: 0.014275978319346905 2023-01-23 18:18:52.447803: step: 1268/1545, loss: 0.0019485161174088717 2023-01-23 18:18:53.314426: step: 1270/1545, loss: 0.00026461121160537004 2023-01-23 18:18:54.232646: step: 1272/1545, loss: 0.024650532752275467 2023-01-23 18:18:55.112295: step: 1274/1545, loss: 9.837465040618554e-05 2023-01-23 18:18:56.025027: step: 1276/1545, loss: 0.024342847988009453 2023-01-23 18:18:56.910086: step: 1278/1545, loss: 0.0023215243127197027 2023-01-23 18:18:57.793017: step: 1280/1545, loss: 0.10145138204097748 2023-01-23 18:18:58.672145: step: 1282/1545, loss: 0.00010975712939398363 2023-01-23 18:18:59.590293: step: 1284/1545, loss: 0.0037183999083936214 2023-01-23 18:19:00.465016: step: 1286/1545, loss: 0.002030400326475501 2023-01-23 18:19:01.356193: step: 1288/1545, loss: 0.0001779380108928308 2023-01-23 18:19:02.247105: step: 1290/1545, loss: 0.0026139782276004553 2023-01-23 18:19:03.156186: step: 1292/1545, loss: 0.05518029257655144 2023-01-23 18:19:04.049010: step: 1294/1545, loss: 9.786766895558685e-05 2023-01-23 18:19:04.947404: step: 1296/1545, loss: 0.002492909785360098 2023-01-23 18:19:05.803753: step: 1298/1545, loss: 0.26018521189689636 2023-01-23 18:19:06.709747: step: 1300/1545, loss: 0.00013222539564594626 2023-01-23 18:19:07.592738: step: 1302/1545, loss: 0.0009417069959454238 2023-01-23 18:19:08.484878: step: 1304/1545, loss: 0.2511594593524933 2023-01-23 18:19:09.360871: step: 1306/1545, loss: 0.06397616118192673 2023-01-23 18:19:10.223461: step: 1308/1545, loss: 0.0033358116634190083 2023-01-23 18:19:11.077751: step: 1310/1545, loss: 0.00018554902635514736 2023-01-23 18:19:11.989854: step: 1312/1545, loss: 0.005869120825082064 2023-01-23 18:19:12.854968: step: 1314/1545, loss: 0.15671344101428986 2023-01-23 18:19:13.712826: step: 1316/1545, loss: 4.594994243234396e-05 2023-01-23 18:19:14.562558: step: 1318/1545, loss: 0.0033651923295110464 2023-01-23 18:19:15.452754: step: 1320/1545, loss: 0.00023405814135912806 2023-01-23 18:19:16.328694: step: 1322/1545, loss: 0.327138215303421 2023-01-23 18:19:17.245471: step: 1324/1545, loss: 0.3249223828315735 2023-01-23 18:19:18.099300: step: 1326/1545, loss: 0.0016484166262671351 2023-01-23 18:19:18.977869: step: 1328/1545, loss: 0.000512619677465409 2023-01-23 18:19:19.872377: step: 1330/1545, loss: 0.0002547846524976194 2023-01-23 18:19:20.731742: step: 1332/1545, loss: 0.00047097800415940583 2023-01-23 18:19:21.594373: step: 1334/1545, loss: 0.1533568948507309 2023-01-23 18:19:22.467661: step: 1336/1545, loss: 0.04142488166689873 2023-01-23 18:19:23.324349: step: 1338/1545, loss: 0.014792494475841522 2023-01-23 18:19:24.166309: step: 1340/1545, loss: 0.3600635528564453 2023-01-23 18:19:24.997299: step: 1342/1545, loss: 7.99958361312747e-05 2023-01-23 18:19:25.887882: step: 1344/1545, loss: 2.5391500457772054e-05 2023-01-23 18:19:26.790924: step: 1346/1545, loss: 0.15976838767528534 2023-01-23 18:19:27.644116: step: 1348/1545, loss: 0.0052561890333890915 2023-01-23 18:19:28.495911: step: 1350/1545, loss: 0.13653960824012756 2023-01-23 18:19:29.378131: step: 1352/1545, loss: 0.12363477051258087 2023-01-23 18:19:30.209288: step: 1354/1545, loss: 0.0001576283830218017 2023-01-23 18:19:31.168948: step: 1356/1545, loss: 0.0010833425913006067 2023-01-23 18:19:32.013959: step: 1358/1545, loss: 0.019621875137090683 2023-01-23 18:19:32.871382: step: 1360/1545, loss: 0.5013699531555176 2023-01-23 18:19:33.732293: step: 1362/1545, loss: 0.8488345742225647 2023-01-23 18:19:34.630724: step: 1364/1545, loss: 0.011931969784200191 2023-01-23 18:19:35.505468: step: 1366/1545, loss: 1.8974133126903325e-05 2023-01-23 18:19:36.385700: step: 1368/1545, loss: 0.018910139799118042 2023-01-23 18:19:37.242396: step: 1370/1545, loss: 0.004100230988115072 2023-01-23 18:19:38.165785: step: 1372/1545, loss: 0.05355231463909149 2023-01-23 18:19:39.049866: step: 1374/1545, loss: 0.00015155761502683163 2023-01-23 18:19:39.910990: step: 1376/1545, loss: 0.03659466654062271 2023-01-23 18:19:40.785439: step: 1378/1545, loss: 0.00024029753694776446 2023-01-23 18:19:41.642804: step: 1380/1545, loss: 0.03313944488763809 2023-01-23 18:19:42.549961: step: 1382/1545, loss: 0.0013425912475213408 2023-01-23 18:19:43.355631: step: 1384/1545, loss: 0.011767028830945492 2023-01-23 18:19:44.190472: step: 1386/1545, loss: 0.0020650101359933615 2023-01-23 18:19:45.050391: step: 1388/1545, loss: 0.0019527396652847528 2023-01-23 18:19:45.920334: step: 1390/1545, loss: 0.0024739562068134546 2023-01-23 18:19:46.805863: step: 1392/1545, loss: 0.28793585300445557 2023-01-23 18:19:47.666915: step: 1394/1545, loss: 0.19463001191616058 2023-01-23 18:19:48.572260: step: 1396/1545, loss: 0.3885437250137329 2023-01-23 18:19:49.419490: step: 1398/1545, loss: 0.0010633853962644935 2023-01-23 18:19:50.392270: step: 1400/1545, loss: 0.1184600293636322 2023-01-23 18:19:51.259306: step: 1402/1545, loss: 0.15534381568431854 2023-01-23 18:19:52.165735: step: 1404/1545, loss: 0.0023853492457419634 2023-01-23 18:19:53.026059: step: 1406/1545, loss: 7.216027734102681e-05 2023-01-23 18:19:53.893718: step: 1408/1545, loss: 0.006180992349982262 2023-01-23 18:19:54.788825: step: 1410/1545, loss: 0.35233789682388306 2023-01-23 18:19:55.698490: step: 1412/1545, loss: 0.019561858847737312 2023-01-23 18:19:56.588062: step: 1414/1545, loss: 0.10044389218091965 2023-01-23 18:19:57.455349: step: 1416/1545, loss: 0.0001866126258391887 2023-01-23 18:19:58.324110: step: 1418/1545, loss: 0.347858726978302 2023-01-23 18:19:59.209814: step: 1420/1545, loss: 0.002137440023943782 2023-01-23 18:20:00.123775: step: 1422/1545, loss: 0.03166596591472626 2023-01-23 18:20:01.017809: step: 1424/1545, loss: 0.36634141206741333 2023-01-23 18:20:01.876282: step: 1426/1545, loss: 0.022414153441786766 2023-01-23 18:20:02.726888: step: 1428/1545, loss: 0.015729671344161034 2023-01-23 18:20:03.605906: step: 1430/1545, loss: 0.08683453500270844 2023-01-23 18:20:04.503338: step: 1432/1545, loss: 0.024170413613319397 2023-01-23 18:20:05.369241: step: 1434/1545, loss: 0.01480601541697979 2023-01-23 18:20:06.226379: step: 1436/1545, loss: 0.0964086651802063 2023-01-23 18:20:07.116599: step: 1438/1545, loss: 0.0047540320083498955 2023-01-23 18:20:07.979853: step: 1440/1545, loss: 0.00037403462920337915 2023-01-23 18:20:08.878154: step: 1442/1545, loss: 0.0004268934717401862 2023-01-23 18:20:09.709847: step: 1444/1545, loss: 0.017219088971614838 2023-01-23 18:20:10.577345: step: 1446/1545, loss: 0.10859028249979019 2023-01-23 18:20:11.503866: step: 1448/1545, loss: 0.00221097725443542 2023-01-23 18:20:12.368319: step: 1450/1545, loss: 0.03409678861498833 2023-01-23 18:20:13.217917: step: 1452/1545, loss: 0.0026167752221226692 2023-01-23 18:20:14.111878: step: 1454/1545, loss: 0.005836186930537224 2023-01-23 18:20:15.068042: step: 1456/1545, loss: 9.613308066036552e-05 2023-01-23 18:20:15.978544: step: 1458/1545, loss: 0.29116129875183105 2023-01-23 18:20:16.875139: step: 1460/1545, loss: 0.002402174286544323 2023-01-23 18:20:17.753876: step: 1462/1545, loss: 0.013423185795545578 2023-01-23 18:20:18.621505: step: 1464/1545, loss: 0.03371027484536171 2023-01-23 18:20:19.531208: step: 1466/1545, loss: 0.0002442438853904605 2023-01-23 18:20:20.384891: step: 1468/1545, loss: 0.004654446616768837 2023-01-23 18:20:21.252064: step: 1470/1545, loss: 0.10655143857002258 2023-01-23 18:20:22.175010: step: 1472/1545, loss: 0.11145610362291336 2023-01-23 18:20:23.046885: step: 1474/1545, loss: 0.0010052099823951721 2023-01-23 18:20:23.901703: step: 1476/1545, loss: 0.04504089057445526 2023-01-23 18:20:24.807822: step: 1478/1545, loss: 0.07025743275880814 2023-01-23 18:20:25.759489: step: 1480/1545, loss: 0.10672219097614288 2023-01-23 18:20:26.607098: step: 1482/1545, loss: 0.00016280580894090235 2023-01-23 18:20:27.465305: step: 1484/1545, loss: 0.000500241294503212 2023-01-23 18:20:28.438153: step: 1486/1545, loss: 0.001245700754225254 2023-01-23 18:20:29.288224: step: 1488/1545, loss: 0.0004739749419968575 2023-01-23 18:20:30.159456: step: 1490/1545, loss: 0.008188469335436821 2023-01-23 18:20:31.064287: step: 1492/1545, loss: 0.002029567025601864 2023-01-23 18:20:31.939950: step: 1494/1545, loss: 0.001749437302350998 2023-01-23 18:20:32.836488: step: 1496/1545, loss: 0.15714578330516815 2023-01-23 18:20:33.803854: step: 1498/1545, loss: 0.03805596008896828 2023-01-23 18:20:34.719488: step: 1500/1545, loss: 7.486469257855788e-05 2023-01-23 18:20:35.578530: step: 1502/1545, loss: 0.00355354743078351 2023-01-23 18:20:36.518745: step: 1504/1545, loss: 0.02431432157754898 2023-01-23 18:20:37.421820: step: 1506/1545, loss: 0.0010829214006662369 2023-01-23 18:20:38.289403: step: 1508/1545, loss: 0.0022925795055925846 2023-01-23 18:20:39.165087: step: 1510/1545, loss: 0.0038940594531595707 2023-01-23 18:20:40.096676: step: 1512/1545, loss: 0.008739282377064228 2023-01-23 18:20:40.993983: step: 1514/1545, loss: 0.03240089491009712 2023-01-23 18:20:41.837706: step: 1516/1545, loss: 8.56123588164337e-05 2023-01-23 18:20:42.731450: step: 1518/1545, loss: 0.11452754586935043 2023-01-23 18:20:43.632221: step: 1520/1545, loss: 0.0031217727810144424 2023-01-23 18:20:44.556980: step: 1522/1545, loss: 0.05725627392530441 2023-01-23 18:20:45.439781: step: 1524/1545, loss: 0.004734334070235491 2023-01-23 18:20:46.288456: step: 1526/1545, loss: 0.00014033264596946537 2023-01-23 18:20:47.166123: step: 1528/1545, loss: 0.007477568928152323 2023-01-23 18:20:48.020944: step: 1530/1545, loss: 0.0001197135861730203 2023-01-23 18:20:48.891339: step: 1532/1545, loss: 4.0222334064310417e-05 2023-01-23 18:20:49.769684: step: 1534/1545, loss: 0.4951114356517792 2023-01-23 18:20:50.670212: step: 1536/1545, loss: 9.905578917823732e-05 2023-01-23 18:20:51.571984: step: 1538/1545, loss: 0.03489147126674652 2023-01-23 18:20:52.497972: step: 1540/1545, loss: 2.5749875931069255e-05 2023-01-23 18:20:53.372141: step: 1542/1545, loss: 0.2736968696117401 2023-01-23 18:20:54.310722: step: 1544/1545, loss: 0.11131700128316879 2023-01-23 18:20:55.192503: step: 1546/1545, loss: 0.17484872043132782 2023-01-23 18:20:56.051730: step: 1548/1545, loss: 0.000677440024446696 2023-01-23 18:20:56.989438: step: 1550/1545, loss: 0.02764066681265831 2023-01-23 18:20:57.864652: step: 1552/1545, loss: 0.03920275345444679 2023-01-23 18:20:58.756395: step: 1554/1545, loss: 0.00315475813113153 2023-01-23 18:20:59.630031: step: 1556/1545, loss: 0.0007623325800523162 2023-01-23 18:21:00.510368: step: 1558/1545, loss: 0.009098445065319538 2023-01-23 18:21:01.408730: step: 1560/1545, loss: 0.00010141103848582134 2023-01-23 18:21:02.272947: step: 1562/1545, loss: 0.2641139626502991 2023-01-23 18:21:03.172756: step: 1564/1545, loss: 0.00031142274383455515 2023-01-23 18:21:04.047332: step: 1566/1545, loss: 0.06285381317138672 2023-01-23 18:21:04.929707: step: 1568/1545, loss: 0.0009532601106911898 2023-01-23 18:21:05.844758: step: 1570/1545, loss: 3.005734834005125e-05 2023-01-23 18:21:06.714950: step: 1572/1545, loss: 0.001063498784787953 2023-01-23 18:21:07.598404: step: 1574/1545, loss: 0.13008706271648407 2023-01-23 18:21:08.505515: step: 1576/1545, loss: 0.07792975753545761 2023-01-23 18:21:09.366591: step: 1578/1545, loss: 0.009047074243426323 2023-01-23 18:21:10.250477: step: 1580/1545, loss: 0.09621893614530563 2023-01-23 18:21:11.155016: step: 1582/1545, loss: 0.0011163264280185103 2023-01-23 18:21:12.020984: step: 1584/1545, loss: 0.0006413295632228255 2023-01-23 18:21:12.900390: step: 1586/1545, loss: 0.05560482293367386 2023-01-23 18:21:13.846994: step: 1588/1545, loss: 0.052485112100839615 2023-01-23 18:21:14.803985: step: 1590/1545, loss: 0.00021516819833777845 2023-01-23 18:21:15.664300: step: 1592/1545, loss: 0.13253642618656158 2023-01-23 18:21:16.543428: step: 1594/1545, loss: 0.149241641163826 2023-01-23 18:21:17.424132: step: 1596/1545, loss: 0.001782869454473257 2023-01-23 18:21:18.273339: step: 1598/1545, loss: 0.010406644083559513 2023-01-23 18:21:19.160131: step: 1600/1545, loss: 0.032911356538534164 2023-01-23 18:21:20.078728: step: 1602/1545, loss: 0.0640919953584671 2023-01-23 18:21:20.969915: step: 1604/1545, loss: 0.002549003344029188 2023-01-23 18:21:21.875581: step: 1606/1545, loss: 0.0488249734044075 2023-01-23 18:21:22.759171: step: 1608/1545, loss: 0.0025998956989496946 2023-01-23 18:21:23.633948: step: 1610/1545, loss: 0.005617000628262758 2023-01-23 18:21:24.522528: step: 1612/1545, loss: 0.01822415366768837 2023-01-23 18:21:25.450845: step: 1614/1545, loss: 0.0528784841299057 2023-01-23 18:21:26.321016: step: 1616/1545, loss: 0.0012647707480937243 2023-01-23 18:21:27.257328: step: 1618/1545, loss: 0.1569688767194748 2023-01-23 18:21:28.127531: step: 1620/1545, loss: 0.019991492852568626 2023-01-23 18:21:29.033720: step: 1622/1545, loss: 0.04559855908155441 2023-01-23 18:21:29.939303: step: 1624/1545, loss: 0.0019702266436070204 2023-01-23 18:21:30.818927: step: 1626/1545, loss: 0.062306344509124756 2023-01-23 18:21:31.678658: step: 1628/1545, loss: 0.0018584886565804482 2023-01-23 18:21:32.549889: step: 1630/1545, loss: 0.09734053909778595 2023-01-23 18:21:33.405471: step: 1632/1545, loss: 0.06697944551706314 2023-01-23 18:21:34.286811: step: 1634/1545, loss: 0.0009807378519326448 2023-01-23 18:21:35.184910: step: 1636/1545, loss: 0.001240254146978259 2023-01-23 18:21:36.073029: step: 1638/1545, loss: 0.0005142128211446106 2023-01-23 18:21:36.962295: step: 1640/1545, loss: 0.005823900457471609 2023-01-23 18:21:37.788494: step: 1642/1545, loss: 0.00923471711575985 2023-01-23 18:21:38.647530: step: 1644/1545, loss: 0.37836048007011414 2023-01-23 18:21:39.528037: step: 1646/1545, loss: 0.0034688073210418224 2023-01-23 18:21:40.411388: step: 1648/1545, loss: 0.11001006513834 2023-01-23 18:21:41.285271: step: 1650/1545, loss: 0.9528664946556091 2023-01-23 18:21:42.163599: step: 1652/1545, loss: 0.004988561384379864 2023-01-23 18:21:43.099920: step: 1654/1545, loss: 0.0004407012020237744 2023-01-23 18:21:43.961572: step: 1656/1545, loss: 0.0645790621638298 2023-01-23 18:21:44.822360: step: 1658/1545, loss: 0.04026878625154495 2023-01-23 18:21:45.688101: step: 1660/1545, loss: 0.0050429427064955235 2023-01-23 18:21:46.549380: step: 1662/1545, loss: 0.15337929129600525 2023-01-23 18:21:47.429776: step: 1664/1545, loss: 0.0034391693770885468 2023-01-23 18:21:48.299397: step: 1666/1545, loss: 0.07042694091796875 2023-01-23 18:21:49.170953: step: 1668/1545, loss: 0.00035527904401533306 2023-01-23 18:21:50.061441: step: 1670/1545, loss: 0.021286552771925926 2023-01-23 18:21:50.959713: step: 1672/1545, loss: 0.009819243103265762 2023-01-23 18:21:51.829718: step: 1674/1545, loss: 0.035083647817373276 2023-01-23 18:21:52.748115: step: 1676/1545, loss: 0.035340964794158936 2023-01-23 18:21:53.642092: step: 1678/1545, loss: 0.23284025490283966 2023-01-23 18:21:54.512945: step: 1680/1545, loss: 0.0007644631550647318 2023-01-23 18:21:55.391729: step: 1682/1545, loss: 0.5867438316345215 2023-01-23 18:21:56.260211: step: 1684/1545, loss: 0.001400787616148591 2023-01-23 18:21:57.150489: step: 1686/1545, loss: 0.0002317351318197325 2023-01-23 18:21:58.108007: step: 1688/1545, loss: 0.0021022020373493433 2023-01-23 18:21:59.016901: step: 1690/1545, loss: 0.03756440058350563 2023-01-23 18:21:59.883642: step: 1692/1545, loss: 0.08571068197488785 2023-01-23 18:22:00.785937: step: 1694/1545, loss: 0.0024699110072106123 2023-01-23 18:22:01.662165: step: 1696/1545, loss: 0.03022538311779499 2023-01-23 18:22:02.512770: step: 1698/1545, loss: 0.0017705425852909684 2023-01-23 18:22:03.381589: step: 1700/1545, loss: 3.7162946682656184e-05 2023-01-23 18:22:04.366214: step: 1702/1545, loss: 6.881056469865143e-05 2023-01-23 18:22:05.219786: step: 1704/1545, loss: 0.0756130963563919 2023-01-23 18:22:06.107728: step: 1706/1545, loss: 0.0015945092309266329 2023-01-23 18:22:06.991753: step: 1708/1545, loss: 0.004109288565814495 2023-01-23 18:22:07.898089: step: 1710/1545, loss: 0.0019133043242618442 2023-01-23 18:22:08.815133: step: 1712/1545, loss: 0.0006520830793306231 2023-01-23 18:22:09.665259: step: 1714/1545, loss: 0.002020750194787979 2023-01-23 18:22:10.533647: step: 1716/1545, loss: 0.0004323105385992676 2023-01-23 18:22:11.389713: step: 1718/1545, loss: 0.07206442207098007 2023-01-23 18:22:12.274061: step: 1720/1545, loss: 0.00020449087605811656 2023-01-23 18:22:13.161826: step: 1722/1545, loss: 0.0010629763128235936 2023-01-23 18:22:14.018917: step: 1724/1545, loss: 0.00972774438560009 2023-01-23 18:22:14.903926: step: 1726/1545, loss: 0.1541680246591568 2023-01-23 18:22:15.810495: step: 1728/1545, loss: 0.001818356802687049 2023-01-23 18:22:16.655670: step: 1730/1545, loss: 0.0017572521464899182 2023-01-23 18:22:17.616750: step: 1732/1545, loss: 0.00025200872914865613 2023-01-23 18:22:18.456263: step: 1734/1545, loss: 0.004400093574076891 2023-01-23 18:22:19.351909: step: 1736/1545, loss: 0.00047927466221153736 2023-01-23 18:22:20.225473: step: 1738/1545, loss: 0.0019464085344225168 2023-01-23 18:22:21.127007: step: 1740/1545, loss: 0.00012154089199611917 2023-01-23 18:22:22.047733: step: 1742/1545, loss: 0.5362012982368469 2023-01-23 18:22:22.916728: step: 1744/1545, loss: 0.0007875192095525563 2023-01-23 18:22:23.810658: step: 1746/1545, loss: 7.827460649423301e-05 2023-01-23 18:22:24.697074: step: 1748/1545, loss: 0.000378083175746724 2023-01-23 18:22:25.576775: step: 1750/1545, loss: 0.019793685525655746 2023-01-23 18:22:26.450683: step: 1752/1545, loss: 0.0012693895259872079 2023-01-23 18:22:27.303383: step: 1754/1545, loss: 0.06055028736591339 2023-01-23 18:22:28.114624: step: 1756/1545, loss: 0.009726961143314838 2023-01-23 18:22:28.956262: step: 1758/1545, loss: 0.0007478175684809685 2023-01-23 18:22:29.800548: step: 1760/1545, loss: 0.0015206551179289818 2023-01-23 18:22:30.649203: step: 1762/1545, loss: 0.14244553446769714 2023-01-23 18:22:31.507098: step: 1764/1545, loss: 0.0016147155547514558 2023-01-23 18:22:32.412573: step: 1766/1545, loss: 0.0006544244824908674 2023-01-23 18:22:33.262968: step: 1768/1545, loss: 0.03202234208583832 2023-01-23 18:22:34.133595: step: 1770/1545, loss: 0.416964054107666 2023-01-23 18:22:34.997468: step: 1772/1545, loss: 0.23243245482444763 2023-01-23 18:22:35.875206: step: 1774/1545, loss: 0.00968564860522747 2023-01-23 18:22:36.695357: step: 1776/1545, loss: 0.0017881300300359726 2023-01-23 18:22:37.584078: step: 1778/1545, loss: 0.8150665760040283 2023-01-23 18:22:38.448006: step: 1780/1545, loss: 0.0006568898679688573 2023-01-23 18:22:39.354651: step: 1782/1545, loss: 0.0005959026166237891 2023-01-23 18:22:40.235480: step: 1784/1545, loss: 0.0010240435367450118 2023-01-23 18:22:41.110814: step: 1786/1545, loss: 0.0030155768617987633 2023-01-23 18:22:42.017137: step: 1788/1545, loss: 0.008090857416391373 2023-01-23 18:22:42.882672: step: 1790/1545, loss: 0.0007745854090899229 2023-01-23 18:22:43.795092: step: 1792/1545, loss: 0.0023777736350893974 2023-01-23 18:22:44.666615: step: 1794/1545, loss: 0.04577916860580444 2023-01-23 18:22:45.525697: step: 1796/1545, loss: 0.0066711450926959515 2023-01-23 18:22:46.466723: step: 1798/1545, loss: 0.0008423886611126363 2023-01-23 18:22:47.341161: step: 1800/1545, loss: 0.00031683934503234923 2023-01-23 18:22:48.180589: step: 1802/1545, loss: 0.0003755188372451812 2023-01-23 18:22:49.040714: step: 1804/1545, loss: 0.0017076559597626328 2023-01-23 18:22:49.960753: step: 1806/1545, loss: 0.02687837928533554 2023-01-23 18:22:50.878343: step: 1808/1545, loss: 0.005727650597691536 2023-01-23 18:22:51.737252: step: 1810/1545, loss: 0.00197232305072248 2023-01-23 18:22:52.645514: step: 1812/1545, loss: 0.0005592941306531429 2023-01-23 18:22:53.570191: step: 1814/1545, loss: 0.0030653863213956356 2023-01-23 18:22:54.457037: step: 1816/1545, loss: 0.0007761614979244769 2023-01-23 18:22:55.320107: step: 1818/1545, loss: 0.011358755640685558 2023-01-23 18:22:56.219596: step: 1820/1545, loss: 0.010513481684029102 2023-01-23 18:22:57.108507: step: 1822/1545, loss: 0.47876933217048645 2023-01-23 18:22:57.990839: step: 1824/1545, loss: 0.00015881162835285068 2023-01-23 18:22:58.870332: step: 1826/1545, loss: 0.006223828997462988 2023-01-23 18:22:59.851941: step: 1828/1545, loss: 0.03553448244929314 2023-01-23 18:23:00.778479: step: 1830/1545, loss: 0.007537144236266613 2023-01-23 18:23:01.716848: step: 1832/1545, loss: 0.275762140750885 2023-01-23 18:23:02.608944: step: 1834/1545, loss: 0.31807640194892883 2023-01-23 18:23:03.516486: step: 1836/1545, loss: 0.004327994305640459 2023-01-23 18:23:04.380048: step: 1838/1545, loss: 0.24423806369304657 2023-01-23 18:23:05.243259: step: 1840/1545, loss: 0.015285204164683819 2023-01-23 18:23:06.134386: step: 1842/1545, loss: 0.16074976325035095 2023-01-23 18:23:07.014876: step: 1844/1545, loss: 0.018089916557073593 2023-01-23 18:23:07.905426: step: 1846/1545, loss: 0.022965403273701668 2023-01-23 18:23:08.811859: step: 1848/1545, loss: 0.0932171568274498 2023-01-23 18:23:09.693501: step: 1850/1545, loss: 0.00584804080426693 2023-01-23 18:23:10.560231: step: 1852/1545, loss: 0.0028169790748506784 2023-01-23 18:23:11.418338: step: 1854/1545, loss: 0.23361128568649292 2023-01-23 18:23:12.273327: step: 1856/1545, loss: 0.17130067944526672 2023-01-23 18:23:13.140319: step: 1858/1545, loss: 0.09465903788805008 2023-01-23 18:23:14.033168: step: 1860/1545, loss: 0.00011655082198558375 2023-01-23 18:23:14.907266: step: 1862/1545, loss: 0.000445153855253011 2023-01-23 18:23:15.745519: step: 1864/1545, loss: 0.2308589220046997 2023-01-23 18:23:16.640552: step: 1866/1545, loss: 0.41825270652770996 2023-01-23 18:23:17.544869: step: 1868/1545, loss: 0.0007957774796523154 2023-01-23 18:23:18.395772: step: 1870/1545, loss: 9.585947555024177e-05 2023-01-23 18:23:19.277684: step: 1872/1545, loss: 0.002368972171097994 2023-01-23 18:23:20.193179: step: 1874/1545, loss: 5.81249623792246e-05 2023-01-23 18:23:21.091707: step: 1876/1545, loss: 0.0020065028220415115 2023-01-23 18:23:21.959227: step: 1878/1545, loss: 0.0005771194119006395 2023-01-23 18:23:22.807674: step: 1880/1545, loss: 2.1467971801757812 2023-01-23 18:23:23.712018: step: 1882/1545, loss: 0.0001272332010557875 2023-01-23 18:23:24.578120: step: 1884/1545, loss: 0.00015592719137202948 2023-01-23 18:23:25.477722: step: 1886/1545, loss: 0.00028947507962584496 2023-01-23 18:23:26.343453: step: 1888/1545, loss: 0.004481354728341103 2023-01-23 18:23:27.175632: step: 1890/1545, loss: 0.3810140788555145 2023-01-23 18:23:28.098649: step: 1892/1545, loss: 0.08352378010749817 2023-01-23 18:23:28.996106: step: 1894/1545, loss: 0.014333933591842651 2023-01-23 18:23:29.883879: step: 1896/1545, loss: 0.1317046880722046 2023-01-23 18:23:30.731201: step: 1898/1545, loss: 0.00909770093858242 2023-01-23 18:23:31.592332: step: 1900/1545, loss: 9.750544450071175e-06 2023-01-23 18:23:32.436607: step: 1902/1545, loss: 0.0004875915474258363 2023-01-23 18:23:33.274299: step: 1904/1545, loss: 0.0008182907477021217 2023-01-23 18:23:34.170989: step: 1906/1545, loss: 0.11391708254814148 2023-01-23 18:23:35.037757: step: 1908/1545, loss: 0.6823825836181641 2023-01-23 18:23:35.945162: step: 1910/1545, loss: 0.06347355991601944 2023-01-23 18:23:36.859283: step: 1912/1545, loss: 0.004528602119535208 2023-01-23 18:23:37.751323: step: 1914/1545, loss: 0.5776625871658325 2023-01-23 18:23:38.608583: step: 1916/1545, loss: 0.018038000911474228 2023-01-23 18:23:39.498021: step: 1918/1545, loss: 0.29592272639274597 2023-01-23 18:23:40.411689: step: 1920/1545, loss: 8.176953269867226e-05 2023-01-23 18:23:41.291339: step: 1922/1545, loss: 0.00042788972496055067 2023-01-23 18:23:42.276536: step: 1924/1545, loss: 0.014760955236852169 2023-01-23 18:23:43.139320: step: 1926/1545, loss: 0.00019038673781324178 2023-01-23 18:23:44.008713: step: 1928/1545, loss: 0.11286813765764236 2023-01-23 18:23:44.898733: step: 1930/1545, loss: 0.0037991164717823267 2023-01-23 18:23:45.794977: step: 1932/1545, loss: 0.05026017129421234 2023-01-23 18:23:46.641106: step: 1934/1545, loss: 0.019818130880594254 2023-01-23 18:23:47.552422: step: 1936/1545, loss: 0.18130987882614136 2023-01-23 18:23:48.442842: step: 1938/1545, loss: 0.00503280945122242 2023-01-23 18:23:49.356308: step: 1940/1545, loss: 3.312276385258883e-05 2023-01-23 18:23:50.196978: step: 1942/1545, loss: 0.0005034230998717248 2023-01-23 18:23:51.072120: step: 1944/1545, loss: 9.912462701322511e-05 2023-01-23 18:23:51.900637: step: 1946/1545, loss: 4.007275128969923e-05 2023-01-23 18:23:52.811901: step: 1948/1545, loss: 4.8353191232308745e-05 2023-01-23 18:23:53.639763: step: 1950/1545, loss: 0.000287772185401991 2023-01-23 18:23:54.461666: step: 1952/1545, loss: 0.0013573773903772235 2023-01-23 18:23:55.397898: step: 1954/1545, loss: 1.3544178009033203 2023-01-23 18:23:56.295325: step: 1956/1545, loss: 0.01516738347709179 2023-01-23 18:23:57.217004: step: 1958/1545, loss: 0.7385779023170471 2023-01-23 18:23:58.087849: step: 1960/1545, loss: 0.05961989238858223 2023-01-23 18:23:58.945620: step: 1962/1545, loss: 0.0003912094689439982 2023-01-23 18:23:59.805435: step: 1964/1545, loss: 6.684372056042776e-05 2023-01-23 18:24:00.693635: step: 1966/1545, loss: 0.056839920580387115 2023-01-23 18:24:01.578886: step: 1968/1545, loss: 0.00918644666671753 2023-01-23 18:24:02.441832: step: 1970/1545, loss: 0.002488825935870409 2023-01-23 18:24:03.331377: step: 1972/1545, loss: 0.0003174451703671366 2023-01-23 18:24:04.188413: step: 1974/1545, loss: 0.0001494269527029246 2023-01-23 18:24:05.073122: step: 1976/1545, loss: 0.15751957893371582 2023-01-23 18:24:05.993262: step: 1978/1545, loss: 0.019298549741506577 2023-01-23 18:24:06.848862: step: 1980/1545, loss: 0.13222452998161316 2023-01-23 18:24:07.661567: step: 1982/1545, loss: 0.0004674088559113443 2023-01-23 18:24:08.538818: step: 1984/1545, loss: 2.7337853680364788e-05 2023-01-23 18:24:09.457353: step: 1986/1545, loss: 0.009900555945932865 2023-01-23 18:24:10.351096: step: 1988/1545, loss: 0.05423201620578766 2023-01-23 18:24:11.239700: step: 1990/1545, loss: 0.48312875628471375 2023-01-23 18:24:12.156637: step: 1992/1545, loss: 0.0007546130218543112 2023-01-23 18:24:13.070726: step: 1994/1545, loss: 0.0003754742501769215 2023-01-23 18:24:14.051096: step: 1996/1545, loss: 0.0013925324892625213 2023-01-23 18:24:14.955966: step: 1998/1545, loss: 9.737557411426678e-05 2023-01-23 18:24:15.842264: step: 2000/1545, loss: 0.09504028409719467 2023-01-23 18:24:16.698730: step: 2002/1545, loss: 0.3304969370365143 2023-01-23 18:24:17.559066: step: 2004/1545, loss: 0.0011538901599124074 2023-01-23 18:24:18.390249: step: 2006/1545, loss: 0.0036281170323491096 2023-01-23 18:24:19.294023: step: 2008/1545, loss: 0.072115458548069 2023-01-23 18:24:20.170602: step: 2010/1545, loss: 0.2655077576637268 2023-01-23 18:24:21.070018: step: 2012/1545, loss: 0.0015388582833111286 2023-01-23 18:24:21.989162: step: 2014/1545, loss: 0.08410341292619705 2023-01-23 18:24:22.861554: step: 2016/1545, loss: 0.17732730507850647 2023-01-23 18:24:23.816907: step: 2018/1545, loss: 0.00034550452255643904 2023-01-23 18:24:24.663826: step: 2020/1545, loss: 6.370644405251369e-05 2023-01-23 18:24:25.517602: step: 2022/1545, loss: 1.0466575622558594 2023-01-23 18:24:26.382814: step: 2024/1545, loss: 9.151545236818492e-05 2023-01-23 18:24:27.225962: step: 2026/1545, loss: 0.000651454902254045 2023-01-23 18:24:28.089604: step: 2028/1545, loss: 0.00016496970783919096 2023-01-23 18:24:28.987376: step: 2030/1545, loss: 0.1292799711227417 2023-01-23 18:24:29.844987: step: 2032/1545, loss: 1.1158941561006941e-05 2023-01-23 18:24:30.758187: step: 2034/1545, loss: 0.0022767754271626472 2023-01-23 18:24:31.610005: step: 2036/1545, loss: 0.00040097511373460293 2023-01-23 18:24:32.500652: step: 2038/1545, loss: 0.0025434214621782303 2023-01-23 18:24:33.338053: step: 2040/1545, loss: 0.0425192154943943 2023-01-23 18:24:34.197696: step: 2042/1545, loss: 0.24511483311653137 2023-01-23 18:24:35.124915: step: 2044/1545, loss: 0.34831666946411133 2023-01-23 18:24:35.999053: step: 2046/1545, loss: 0.003429135773330927 2023-01-23 18:24:36.872222: step: 2048/1545, loss: 0.031652115285396576 2023-01-23 18:24:37.757494: step: 2050/1545, loss: 0.0011000714730471373 2023-01-23 18:24:38.697319: step: 2052/1545, loss: 0.08615603297948837 2023-01-23 18:24:39.634596: step: 2054/1545, loss: 0.01302332989871502 2023-01-23 18:24:40.515113: step: 2056/1545, loss: 0.014334763400256634 2023-01-23 18:24:41.411117: step: 2058/1545, loss: 0.1405436396598816 2023-01-23 18:24:42.393595: step: 2060/1545, loss: 0.005917260888963938 2023-01-23 18:24:43.303085: step: 2062/1545, loss: 0.0021616904996335506 2023-01-23 18:24:44.129052: step: 2064/1545, loss: 0.0012750034220516682 2023-01-23 18:24:44.989527: step: 2066/1545, loss: 0.0034372296649962664 2023-01-23 18:24:45.890504: step: 2068/1545, loss: 0.05466253310441971 2023-01-23 18:24:46.753154: step: 2070/1545, loss: 0.0007811353425495327 2023-01-23 18:24:47.626665: step: 2072/1545, loss: 0.0003267750144004822 2023-01-23 18:24:48.499425: step: 2074/1545, loss: 7.873831782490015e-05 2023-01-23 18:24:49.406018: step: 2076/1545, loss: 0.4822002649307251 2023-01-23 18:24:50.325540: step: 2078/1545, loss: 7.663331052754074e-05 2023-01-23 18:24:51.154860: step: 2080/1545, loss: 0.00033684427035041153 2023-01-23 18:24:52.054791: step: 2082/1545, loss: 0.014568373560905457 2023-01-23 18:24:52.949936: step: 2084/1545, loss: 0.0004058130143675953 2023-01-23 18:24:53.928484: step: 2086/1545, loss: 0.0012303439434617758 2023-01-23 18:24:54.842784: step: 2088/1545, loss: 0.0014355942839756608 2023-01-23 18:24:55.700927: step: 2090/1545, loss: 0.0004475103924050927 2023-01-23 18:24:56.620710: step: 2092/1545, loss: 0.0016470360569655895 2023-01-23 18:24:57.574547: step: 2094/1545, loss: 0.007189513649791479 2023-01-23 18:24:58.446124: step: 2096/1545, loss: 0.005877202842384577 2023-01-23 18:24:59.484630: step: 2098/1545, loss: 0.03128305822610855 2023-01-23 18:25:00.373237: step: 2100/1545, loss: 0.0006211146828718483 2023-01-23 18:25:01.274687: step: 2102/1545, loss: 0.00900239683687687 2023-01-23 18:25:02.144799: step: 2104/1545, loss: 0.0017856867052614689 2023-01-23 18:25:03.008652: step: 2106/1545, loss: 0.00020065119315404445 2023-01-23 18:25:03.850403: step: 2108/1545, loss: 0.0004738380084745586 2023-01-23 18:25:04.713888: step: 2110/1545, loss: 0.05049411579966545 2023-01-23 18:25:05.608830: step: 2112/1545, loss: 0.39161381125450134 2023-01-23 18:25:06.500999: step: 2114/1545, loss: 0.0002134383248630911 2023-01-23 18:25:07.466262: step: 2116/1545, loss: 0.013604052364826202 2023-01-23 18:25:08.381803: step: 2118/1545, loss: 0.003035947447642684 2023-01-23 18:25:09.310787: step: 2120/1545, loss: 0.2663104236125946 2023-01-23 18:25:10.200634: step: 2122/1545, loss: 0.24237290024757385 2023-01-23 18:25:11.069091: step: 2124/1545, loss: 0.12142450362443924 2023-01-23 18:25:11.946672: step: 2126/1545, loss: 0.11041951179504395 2023-01-23 18:25:12.911816: step: 2128/1545, loss: 0.25287914276123047 2023-01-23 18:25:13.784812: step: 2130/1545, loss: 0.03134815767407417 2023-01-23 18:25:14.657874: step: 2132/1545, loss: 0.00584275322034955 2023-01-23 18:25:15.522323: step: 2134/1545, loss: 0.5911847352981567 2023-01-23 18:25:16.571262: step: 2136/1545, loss: 0.25594741106033325 2023-01-23 18:25:17.437192: step: 2138/1545, loss: 0.011914222501218319 2023-01-23 18:25:18.363000: step: 2140/1545, loss: 0.14365588128566742 2023-01-23 18:25:19.276836: step: 2142/1545, loss: 0.010344543494284153 2023-01-23 18:25:20.163035: step: 2144/1545, loss: 0.015547720715403557 2023-01-23 18:25:21.064501: step: 2146/1545, loss: 0.00011546302266651765 2023-01-23 18:25:21.892253: step: 2148/1545, loss: 0.03345922753214836 2023-01-23 18:25:22.728303: step: 2150/1545, loss: 0.08536017686128616 2023-01-23 18:25:23.633726: step: 2152/1545, loss: 0.2816091775894165 2023-01-23 18:25:24.514796: step: 2154/1545, loss: 0.0010773519752547145 2023-01-23 18:25:25.352508: step: 2156/1545, loss: 0.03864172846078873 2023-01-23 18:25:26.317940: step: 2158/1545, loss: 0.05375363305211067 2023-01-23 18:25:27.181753: step: 2160/1545, loss: 0.04616660624742508 2023-01-23 18:25:28.108113: step: 2162/1545, loss: 0.011369621381163597 2023-01-23 18:25:28.961433: step: 2164/1545, loss: 0.0022584483958780766 2023-01-23 18:25:29.871796: step: 2166/1545, loss: 0.024688994511961937 2023-01-23 18:25:30.730536: step: 2168/1545, loss: 0.0028381659649312496 2023-01-23 18:25:31.617831: step: 2170/1545, loss: 0.0008859657682478428 2023-01-23 18:25:32.468140: step: 2172/1545, loss: 0.0032758796587586403 2023-01-23 18:25:33.346818: step: 2174/1545, loss: 0.0004426037485245615 2023-01-23 18:25:34.241738: step: 2176/1545, loss: 0.0005235049175098538 2023-01-23 18:25:35.162944: step: 2178/1545, loss: 0.0040248092263937 2023-01-23 18:25:36.069708: step: 2180/1545, loss: 0.05819229409098625 2023-01-23 18:25:36.941558: step: 2182/1545, loss: 0.07447021454572678 2023-01-23 18:25:37.851833: step: 2184/1545, loss: 0.008789497427642345 2023-01-23 18:25:38.746756: step: 2186/1545, loss: 0.0027536731213331223 2023-01-23 18:25:39.633152: step: 2188/1545, loss: 0.005374705418944359 2023-01-23 18:25:40.486731: step: 2190/1545, loss: 0.002474999288097024 2023-01-23 18:25:41.378032: step: 2192/1545, loss: 0.09749740362167358 2023-01-23 18:25:42.275455: step: 2194/1545, loss: 0.012856774032115936 2023-01-23 18:25:43.228444: step: 2196/1545, loss: 0.00042645545909181237 2023-01-23 18:25:44.106022: step: 2198/1545, loss: 0.020626280456781387 2023-01-23 18:25:45.011073: step: 2200/1545, loss: 0.003679583314806223 2023-01-23 18:25:46.022900: step: 2202/1545, loss: 0.20492899417877197 2023-01-23 18:25:46.932862: step: 2204/1545, loss: 0.008431652560830116 2023-01-23 18:25:47.751407: step: 2206/1545, loss: 0.008460435084998608 2023-01-23 18:25:48.615809: step: 2208/1545, loss: 0.002969036577269435 2023-01-23 18:25:49.515134: step: 2210/1545, loss: 0.06529392302036285 2023-01-23 18:25:50.421998: step: 2212/1545, loss: 0.04972316697239876 2023-01-23 18:25:51.312727: step: 2214/1545, loss: 0.34382501244544983 2023-01-23 18:25:52.192411: step: 2216/1545, loss: 0.007189038675278425 2023-01-23 18:25:53.058742: step: 2218/1545, loss: 0.004866205155849457 2023-01-23 18:25:53.897094: step: 2220/1545, loss: 0.030392078682780266 2023-01-23 18:25:54.787714: step: 2222/1545, loss: 0.04332249239087105 2023-01-23 18:25:55.643011: step: 2224/1545, loss: 0.00798293948173523 2023-01-23 18:25:56.490199: step: 2226/1545, loss: 0.0003117538581136614 2023-01-23 18:25:57.341803: step: 2228/1545, loss: 0.10645481199026108 2023-01-23 18:25:58.240409: step: 2230/1545, loss: 0.0005432858015410602 2023-01-23 18:25:59.099974: step: 2232/1545, loss: 0.0005892399349249899 2023-01-23 18:26:00.000054: step: 2234/1545, loss: 2.3179781436920166 2023-01-23 18:26:00.896626: step: 2236/1545, loss: 0.0010225921869277954 2023-01-23 18:26:01.779619: step: 2238/1545, loss: 0.13916760683059692 2023-01-23 18:26:02.655637: step: 2240/1545, loss: 0.07727435976266861 2023-01-23 18:26:03.524952: step: 2242/1545, loss: 0.00014698089216835797 2023-01-23 18:26:04.477323: step: 2244/1545, loss: 0.0008432027534581721 2023-01-23 18:26:05.362075: step: 2246/1545, loss: 0.0004190236213617027 2023-01-23 18:26:06.250921: step: 2248/1545, loss: 0.14277991652488708 2023-01-23 18:26:07.152913: step: 2250/1545, loss: 0.197064608335495 2023-01-23 18:26:08.067593: step: 2252/1545, loss: 0.019109217450022697 2023-01-23 18:26:08.952420: step: 2254/1545, loss: 0.00033587825600989163 2023-01-23 18:26:09.798940: step: 2256/1545, loss: 0.0022206036373972893 2023-01-23 18:26:10.715007: step: 2258/1545, loss: 7.96527456259355e-05 2023-01-23 18:26:11.657318: step: 2260/1545, loss: 0.0072797080501914024 2023-01-23 18:26:12.579691: step: 2262/1545, loss: 0.0017526091542094946 2023-01-23 18:26:13.435021: step: 2264/1545, loss: 0.03886648267507553 2023-01-23 18:26:14.259932: step: 2266/1545, loss: 0.0012407717294991016 2023-01-23 18:26:15.151525: step: 2268/1545, loss: 0.1701314002275467 2023-01-23 18:26:16.056857: step: 2270/1545, loss: 0.11363057792186737 2023-01-23 18:26:16.905250: step: 2272/1545, loss: 0.13797228038311005 2023-01-23 18:26:17.746900: step: 2274/1545, loss: 0.06645277142524719 2023-01-23 18:26:18.600806: step: 2276/1545, loss: 0.0006834919331595302 2023-01-23 18:26:19.428553: step: 2278/1545, loss: 0.01170272845774889 2023-01-23 18:26:20.371864: step: 2280/1545, loss: 0.001311854226514697 2023-01-23 18:26:21.327359: step: 2282/1545, loss: 0.052759163081645966 2023-01-23 18:26:22.166353: step: 2284/1545, loss: 0.004563705064356327 2023-01-23 18:26:23.030738: step: 2286/1545, loss: 0.08904168754816055 2023-01-23 18:26:23.909973: step: 2288/1545, loss: 0.00046819064300507307 2023-01-23 18:26:24.773314: step: 2290/1545, loss: 0.023481979966163635 2023-01-23 18:26:25.672300: step: 2292/1545, loss: 0.0022346223704516888 2023-01-23 18:26:26.599437: step: 2294/1545, loss: 0.23934835195541382 2023-01-23 18:26:27.480808: step: 2296/1545, loss: 0.0038144870195537806 2023-01-23 18:26:28.307467: step: 2298/1545, loss: 0.0019769594073295593 2023-01-23 18:26:29.187367: step: 2300/1545, loss: 0.0035616732202470303 2023-01-23 18:26:30.066846: step: 2302/1545, loss: 0.00890656840056181 2023-01-23 18:26:30.958563: step: 2304/1545, loss: 0.06674212962388992 2023-01-23 18:26:31.845526: step: 2306/1545, loss: 0.00022008252562955022 2023-01-23 18:26:32.772726: step: 2308/1545, loss: 1.817158772610128e-05 2023-01-23 18:26:33.651971: step: 2310/1545, loss: 0.060916781425476074 2023-01-23 18:26:34.521462: step: 2312/1545, loss: 0.0035318350419402122 2023-01-23 18:26:35.374578: step: 2314/1545, loss: 0.4801597595214844 2023-01-23 18:26:36.268438: step: 2316/1545, loss: 0.1201617568731308 2023-01-23 18:26:37.168739: step: 2318/1545, loss: 0.05313136428594589 2023-01-23 18:26:38.028577: step: 2320/1545, loss: 0.060399457812309265 2023-01-23 18:26:38.896990: step: 2322/1545, loss: 0.00019233371131122112 2023-01-23 18:26:39.767501: step: 2324/1545, loss: 0.000996347051113844 2023-01-23 18:26:40.673632: step: 2326/1545, loss: 0.00011092446948168799 2023-01-23 18:26:41.612754: step: 2328/1545, loss: 0.005461312364786863 2023-01-23 18:26:42.498852: step: 2330/1545, loss: 0.11814476549625397 2023-01-23 18:26:43.346092: step: 2332/1545, loss: 0.0030311904847621918 2023-01-23 18:26:44.236500: step: 2334/1545, loss: 0.008636475540697575 2023-01-23 18:26:45.109178: step: 2336/1545, loss: 0.1242232471704483 2023-01-23 18:26:45.994866: step: 2338/1545, loss: 0.013362709432840347 2023-01-23 18:26:46.848410: step: 2340/1545, loss: 0.07138478010892868 2023-01-23 18:26:47.780866: step: 2342/1545, loss: 0.03458007425069809 2023-01-23 18:26:48.671898: step: 2344/1545, loss: 0.0019663721323013306 2023-01-23 18:26:49.504542: step: 2346/1545, loss: 0.0004085598629899323 2023-01-23 18:26:50.374211: step: 2348/1545, loss: 0.00012303766561672091 2023-01-23 18:26:51.303053: step: 2350/1545, loss: 0.19154854118824005 2023-01-23 18:26:52.248958: step: 2352/1545, loss: 0.027426308020949364 2023-01-23 18:26:53.152004: step: 2354/1545, loss: 0.016520237550139427 2023-01-23 18:26:54.046516: step: 2356/1545, loss: 0.0319349505007267 2023-01-23 18:26:54.941958: step: 2358/1545, loss: 0.018363462761044502 2023-01-23 18:26:55.887174: step: 2360/1545, loss: 0.003262809244915843 2023-01-23 18:26:56.756351: step: 2362/1545, loss: 0.0026520381215959787 2023-01-23 18:26:57.628032: step: 2364/1545, loss: 0.0012033185921609402 2023-01-23 18:26:58.509959: step: 2366/1545, loss: 0.00019599840743467212 2023-01-23 18:26:59.383548: step: 2368/1545, loss: 0.004801272880285978 2023-01-23 18:27:00.258400: step: 2370/1545, loss: 0.0881975069642067 2023-01-23 18:27:01.129636: step: 2372/1545, loss: 0.024843432009220123 2023-01-23 18:27:02.051440: step: 2374/1545, loss: 0.02742644213140011 2023-01-23 18:27:02.938116: step: 2376/1545, loss: 0.06760255247354507 2023-01-23 18:27:03.798591: step: 2378/1545, loss: 0.0059228213503956795 2023-01-23 18:27:04.724674: step: 2380/1545, loss: 0.0006489318911917508 2023-01-23 18:27:05.585914: step: 2382/1545, loss: 0.00026916409842669964 2023-01-23 18:27:06.469757: step: 2384/1545, loss: 0.0007365280762314796 2023-01-23 18:27:07.342361: step: 2386/1545, loss: 0.0012021325528621674 2023-01-23 18:27:08.269473: step: 2388/1545, loss: 0.003972298465669155 2023-01-23 18:27:09.148794: step: 2390/1545, loss: 0.04525509849190712 2023-01-23 18:27:10.045866: step: 2392/1545, loss: 0.0012254045577719808 2023-01-23 18:27:10.919578: step: 2394/1545, loss: 0.017846718430519104 2023-01-23 18:27:11.864354: step: 2396/1545, loss: 0.12066254764795303 2023-01-23 18:27:12.755982: step: 2398/1545, loss: 0.6035484671592712 2023-01-23 18:27:13.639633: step: 2400/1545, loss: 0.6633413434028625 2023-01-23 18:27:14.572498: step: 2402/1545, loss: 0.12376916408538818 2023-01-23 18:27:15.457913: step: 2404/1545, loss: 0.00547029497101903 2023-01-23 18:27:16.338591: step: 2406/1545, loss: 0.0006625042296946049 2023-01-23 18:27:17.187170: step: 2408/1545, loss: 0.005503839813172817 2023-01-23 18:27:18.030449: step: 2410/1545, loss: 0.00017547316383570433 2023-01-23 18:27:18.869431: step: 2412/1545, loss: 0.0370958037674427 2023-01-23 18:27:19.717888: step: 2414/1545, loss: 0.0002558408014010638 2023-01-23 18:27:20.612141: step: 2416/1545, loss: 0.09046129137277603 2023-01-23 18:27:21.505067: step: 2418/1545, loss: 0.302575021982193 2023-01-23 18:27:22.374149: step: 2420/1545, loss: 0.014105606824159622 2023-01-23 18:27:23.302056: step: 2422/1545, loss: 0.04217294603586197 2023-01-23 18:27:24.216248: step: 2424/1545, loss: 0.0015527785290032625 2023-01-23 18:27:25.144627: step: 2426/1545, loss: 0.043711788952350616 2023-01-23 18:27:26.035767: step: 2428/1545, loss: 0.06160590797662735 2023-01-23 18:27:26.933432: step: 2430/1545, loss: 0.005711641162633896 2023-01-23 18:27:27.824222: step: 2432/1545, loss: 0.00010533524618949741 2023-01-23 18:27:28.699530: step: 2434/1545, loss: 0.021551482379436493 2023-01-23 18:27:29.549580: step: 2436/1545, loss: 0.15465159714221954 2023-01-23 18:27:30.395694: step: 2438/1545, loss: 0.0012414557859301567 2023-01-23 18:27:31.262456: step: 2440/1545, loss: 0.002446538768708706 2023-01-23 18:27:32.185814: step: 2442/1545, loss: 0.0036881347186863422 2023-01-23 18:27:33.034520: step: 2444/1545, loss: 0.01205604337155819 2023-01-23 18:27:33.873716: step: 2446/1545, loss: 0.0020105703733861446 2023-01-23 18:27:34.724582: step: 2448/1545, loss: 0.00029590926715172827 2023-01-23 18:27:35.575904: step: 2450/1545, loss: 0.007426622789353132 2023-01-23 18:27:36.578652: step: 2452/1545, loss: 0.001004036283120513 2023-01-23 18:27:37.457371: step: 2454/1545, loss: 0.0004897782346233726 2023-01-23 18:27:38.288786: step: 2456/1545, loss: 0.07414676249027252 2023-01-23 18:27:39.192747: step: 2458/1545, loss: 0.000702946912497282 2023-01-23 18:27:40.118296: step: 2460/1545, loss: 0.010094041004776955 2023-01-23 18:27:41.129668: step: 2462/1545, loss: 0.05598199740052223 2023-01-23 18:27:41.993136: step: 2464/1545, loss: 0.35048985481262207 2023-01-23 18:27:42.876993: step: 2466/1545, loss: 0.0016099921194836497 2023-01-23 18:27:43.782290: step: 2468/1545, loss: 0.00017440432566218078 2023-01-23 18:27:44.670578: step: 2470/1545, loss: 0.0018668194534257054 2023-01-23 18:27:45.546582: step: 2472/1545, loss: 7.240059494506568e-05 2023-01-23 18:27:46.408384: step: 2474/1545, loss: 0.0010103504173457623 2023-01-23 18:27:47.274633: step: 2476/1545, loss: 0.040538888424634933 2023-01-23 18:27:48.151245: step: 2478/1545, loss: 0.002433446468785405 2023-01-23 18:27:49.036010: step: 2480/1545, loss: 0.0456971600651741 2023-01-23 18:27:49.936417: step: 2482/1545, loss: 0.000251468998612836 2023-01-23 18:27:50.849633: step: 2484/1545, loss: 0.02064969204366207 2023-01-23 18:27:51.712967: step: 2486/1545, loss: 0.00014903361443430185 2023-01-23 18:27:52.652215: step: 2488/1545, loss: 0.11651726067066193 2023-01-23 18:27:53.553360: step: 2490/1545, loss: 0.035695526748895645 2023-01-23 18:27:54.443130: step: 2492/1545, loss: 0.006762209348380566 2023-01-23 18:27:55.278349: step: 2494/1545, loss: 0.004779690410941839 2023-01-23 18:27:56.151532: step: 2496/1545, loss: 0.05399983003735542 2023-01-23 18:27:57.017644: step: 2498/1545, loss: 0.015562202781438828 2023-01-23 18:27:57.903539: step: 2500/1545, loss: 0.2487746924161911 2023-01-23 18:27:58.769838: step: 2502/1545, loss: 0.0033210113178938627 2023-01-23 18:27:59.665644: step: 2504/1545, loss: 0.00013545597903430462 2023-01-23 18:28:00.595375: step: 2506/1545, loss: 0.004497111774981022 2023-01-23 18:28:01.441355: step: 2508/1545, loss: 0.012995148077607155 2023-01-23 18:28:02.290935: step: 2510/1545, loss: 0.0016875980654731393 2023-01-23 18:28:03.170966: step: 2512/1545, loss: 0.020190995186567307 2023-01-23 18:28:04.073684: step: 2514/1545, loss: 0.11306219547986984 2023-01-23 18:28:05.034018: step: 2516/1545, loss: 0.018170781433582306 2023-01-23 18:28:05.885673: step: 2518/1545, loss: 0.00021499786817003042 2023-01-23 18:28:06.786474: step: 2520/1545, loss: 0.008617215789854527 2023-01-23 18:28:07.661672: step: 2522/1545, loss: 0.00436777900904417 2023-01-23 18:28:08.566718: step: 2524/1545, loss: 0.0009603779762983322 2023-01-23 18:28:09.434747: step: 2526/1545, loss: 2.6168812837568112e-05 2023-01-23 18:28:10.329753: step: 2528/1545, loss: 0.00018202084174845368 2023-01-23 18:28:11.199954: step: 2530/1545, loss: 0.42816072702407837 2023-01-23 18:28:12.065259: step: 2532/1545, loss: 0.0014775421004742384 2023-01-23 18:28:12.936070: step: 2534/1545, loss: 0.03147561848163605 2023-01-23 18:28:13.842700: step: 2536/1545, loss: 0.00037594110472127795 2023-01-23 18:28:14.731967: step: 2538/1545, loss: 0.004168609157204628 2023-01-23 18:28:15.641318: step: 2540/1545, loss: 0.18404431641101837 2023-01-23 18:28:16.509573: step: 2542/1545, loss: 0.022878069430589676 2023-01-23 18:28:17.402496: step: 2544/1545, loss: 0.029441703110933304 2023-01-23 18:28:18.264397: step: 2546/1545, loss: 0.000275499391136691 2023-01-23 18:28:19.185652: step: 2548/1545, loss: 0.008445603772997856 2023-01-23 18:28:20.052697: step: 2550/1545, loss: 0.040895506739616394 2023-01-23 18:28:20.921840: step: 2552/1545, loss: 0.020073356106877327 2023-01-23 18:28:21.773766: step: 2554/1545, loss: 0.0007745235925540328 2023-01-23 18:28:22.679820: step: 2556/1545, loss: 0.05796147510409355 2023-01-23 18:28:23.609871: step: 2558/1545, loss: 0.10188497602939606 2023-01-23 18:28:24.489333: step: 2560/1545, loss: 0.05874888226389885 2023-01-23 18:28:25.349174: step: 2562/1545, loss: 0.0004426588711794466 2023-01-23 18:28:26.210043: step: 2564/1545, loss: 0.00041090461309067905 2023-01-23 18:28:27.103249: step: 2566/1545, loss: 0.015342267230153084 2023-01-23 18:28:27.965059: step: 2568/1545, loss: 0.01856858842074871 2023-01-23 18:28:28.829399: step: 2570/1545, loss: 0.004629197530448437 2023-01-23 18:28:29.713543: step: 2572/1545, loss: 0.014581119641661644 2023-01-23 18:28:30.627877: step: 2574/1545, loss: 0.028243644163012505 2023-01-23 18:28:31.498787: step: 2576/1545, loss: 0.027897465974092484 2023-01-23 18:28:32.368033: step: 2578/1545, loss: 0.02590653859078884 2023-01-23 18:28:33.245314: step: 2580/1545, loss: 0.0047293417155742645 2023-01-23 18:28:34.147593: step: 2582/1545, loss: 0.067911297082901 2023-01-23 18:28:35.007761: step: 2584/1545, loss: 0.017811039462685585 2023-01-23 18:28:35.942983: step: 2586/1545, loss: 4.54316905234009e-05 2023-01-23 18:28:36.856765: step: 2588/1545, loss: 0.000600245373789221 2023-01-23 18:28:37.725712: step: 2590/1545, loss: 0.008849548175930977 2023-01-23 18:28:38.620593: step: 2592/1545, loss: 0.0009465237963013351 2023-01-23 18:28:39.545098: step: 2594/1545, loss: 0.00023192002845462412 2023-01-23 18:28:40.415603: step: 2596/1545, loss: 0.07382585853338242 2023-01-23 18:28:41.318869: step: 2598/1545, loss: 0.00020148135081399232 2023-01-23 18:28:42.223823: step: 2600/1545, loss: 0.003514818148687482 2023-01-23 18:28:43.104291: step: 2602/1545, loss: 0.14672335982322693 2023-01-23 18:28:43.986943: step: 2604/1545, loss: 0.00010553278843872249 2023-01-23 18:28:44.856193: step: 2606/1545, loss: 0.0011743197683244944 2023-01-23 18:28:45.728086: step: 2608/1545, loss: 0.009005829691886902 2023-01-23 18:28:46.648464: step: 2610/1545, loss: 0.13898609578609467 2023-01-23 18:28:47.509447: step: 2612/1545, loss: 0.0001900408969959244 2023-01-23 18:28:48.342085: step: 2614/1545, loss: 0.0010385052300989628 2023-01-23 18:28:49.204793: step: 2616/1545, loss: 0.00042575239785946906 2023-01-23 18:28:50.108602: step: 2618/1545, loss: 0.0024351472966372967 2023-01-23 18:28:50.993341: step: 2620/1545, loss: 0.009425443597137928 2023-01-23 18:28:51.886642: step: 2622/1545, loss: 0.0007959926151670516 2023-01-23 18:28:52.803866: step: 2624/1545, loss: 0.00640815868973732 2023-01-23 18:28:53.650906: step: 2626/1545, loss: 0.023709530010819435 2023-01-23 18:28:54.613519: step: 2628/1545, loss: 0.009744973853230476 2023-01-23 18:28:55.483334: step: 2630/1545, loss: 0.05602108687162399 2023-01-23 18:28:56.354813: step: 2632/1545, loss: 6.222156662261114e-05 2023-01-23 18:28:57.217274: step: 2634/1545, loss: 0.016206901520490646 2023-01-23 18:28:58.117836: step: 2636/1545, loss: 0.05236053839325905 2023-01-23 18:28:59.030129: step: 2638/1545, loss: 0.005932376720011234 2023-01-23 18:28:59.884580: step: 2640/1545, loss: 0.0022131509613245726 2023-01-23 18:29:00.822078: step: 2642/1545, loss: 0.2568572461605072 2023-01-23 18:29:01.643612: step: 2644/1545, loss: 9.107333607971668e-05 2023-01-23 18:29:02.545284: step: 2646/1545, loss: 0.04536713287234306 2023-01-23 18:29:03.390440: step: 2648/1545, loss: 0.0001166751972050406 2023-01-23 18:29:04.232323: step: 2650/1545, loss: 0.015269240364432335 2023-01-23 18:29:05.110483: step: 2652/1545, loss: 0.09475325793027878 2023-01-23 18:29:05.991536: step: 2654/1545, loss: 0.02132197842001915 2023-01-23 18:29:06.850874: step: 2656/1545, loss: 0.002713210415095091 2023-01-23 18:29:07.745999: step: 2658/1545, loss: 0.006818060297518969 2023-01-23 18:29:08.626415: step: 2660/1545, loss: 0.00019370080553926528 2023-01-23 18:29:09.522132: step: 2662/1545, loss: 0.004663357976824045 2023-01-23 18:29:10.479805: step: 2664/1545, loss: 0.0005830418667756021 2023-01-23 18:29:11.384133: step: 2666/1545, loss: 0.0003155077574774623 2023-01-23 18:29:12.222313: step: 2668/1545, loss: 0.006891078315675259 2023-01-23 18:29:13.108271: step: 2670/1545, loss: 0.0001507260894868523 2023-01-23 18:29:14.004095: step: 2672/1545, loss: 0.00014115023077465594 2023-01-23 18:29:14.888115: step: 2674/1545, loss: 0.002020803978666663 2023-01-23 18:29:15.768077: step: 2676/1545, loss: 0.0041396040469408035 2023-01-23 18:29:16.600124: step: 2678/1545, loss: 3.6517518310574815e-05 2023-01-23 18:29:17.436182: step: 2680/1545, loss: 0.005142251029610634 2023-01-23 18:29:18.301100: step: 2682/1545, loss: 0.011730683036148548 2023-01-23 18:29:19.138255: step: 2684/1545, loss: 0.00010063777153845876 2023-01-23 18:29:20.023692: step: 2686/1545, loss: 0.0028792163357138634 2023-01-23 18:29:20.939682: step: 2688/1545, loss: 0.013711242936551571 2023-01-23 18:29:21.792860: step: 2690/1545, loss: 0.0004377510049380362 2023-01-23 18:29:22.661484: step: 2692/1545, loss: 0.00028069288237020373 2023-01-23 18:29:23.560796: step: 2694/1545, loss: 4.594622441800311e-05 2023-01-23 18:29:24.473333: step: 2696/1545, loss: 0.0010459558106958866 2023-01-23 18:29:25.421642: step: 2698/1545, loss: 0.001996980980038643 2023-01-23 18:29:26.305874: step: 2700/1545, loss: 0.1209445521235466 2023-01-23 18:29:27.162076: step: 2702/1545, loss: 0.0023266251664608717 2023-01-23 18:29:28.039483: step: 2704/1545, loss: 0.0005767598049715161 2023-01-23 18:29:28.894069: step: 2706/1545, loss: 0.0061220997013151646 2023-01-23 18:29:29.775328: step: 2708/1545, loss: 0.002065416891127825 2023-01-23 18:29:30.697005: step: 2710/1545, loss: 0.08676200360059738 2023-01-23 18:29:31.579060: step: 2712/1545, loss: 0.10725284367799759 2023-01-23 18:29:32.482855: step: 2714/1545, loss: 0.13079144060611725 2023-01-23 18:29:33.366743: step: 2716/1545, loss: 0.5824530124664307 2023-01-23 18:29:34.239808: step: 2718/1545, loss: 0.06583733856678009 2023-01-23 18:29:35.129357: step: 2720/1545, loss: 0.03146987035870552 2023-01-23 18:29:36.089998: step: 2722/1545, loss: 0.009235908277332783 2023-01-23 18:29:37.081685: step: 2724/1545, loss: 0.004571287427097559 2023-01-23 18:29:37.979934: step: 2726/1545, loss: 0.1566033661365509 2023-01-23 18:29:38.922926: step: 2728/1545, loss: 0.008460205979645252 2023-01-23 18:29:39.806046: step: 2730/1545, loss: 0.02492389641702175 2023-01-23 18:29:40.712117: step: 2732/1545, loss: 0.032265063375234604 2023-01-23 18:29:41.576142: step: 2734/1545, loss: 0.0002686097868718207 2023-01-23 18:29:42.439236: step: 2736/1545, loss: 0.013010668568313122 2023-01-23 18:29:43.292630: step: 2738/1545, loss: 0.09838445484638214 2023-01-23 18:29:44.172154: step: 2740/1545, loss: 0.00013829352974426 2023-01-23 18:29:45.025803: step: 2742/1545, loss: 6.561801274074242e-05 2023-01-23 18:29:45.914946: step: 2744/1545, loss: 0.014704829081892967 2023-01-23 18:29:46.783747: step: 2746/1545, loss: 0.00039035052759572864 2023-01-23 18:29:47.658471: step: 2748/1545, loss: 0.15083186328411102 2023-01-23 18:29:48.517623: step: 2750/1545, loss: 0.005056813359260559 2023-01-23 18:29:49.425028: step: 2752/1545, loss: 0.1510808765888214 2023-01-23 18:29:50.300745: step: 2754/1545, loss: 0.005773657467216253 2023-01-23 18:29:51.165094: step: 2756/1545, loss: 0.00198051193729043 2023-01-23 18:29:52.039862: step: 2758/1545, loss: 0.3658771216869354 2023-01-23 18:29:52.949477: step: 2760/1545, loss: 0.06418190151453018 2023-01-23 18:29:53.817007: step: 2762/1545, loss: 0.029618244618177414 2023-01-23 18:29:54.689651: step: 2764/1545, loss: 0.00022854443523101509 2023-01-23 18:29:55.542426: step: 2766/1545, loss: 0.0407431423664093 2023-01-23 18:29:56.420928: step: 2768/1545, loss: 8.353597513632849e-05 2023-01-23 18:29:57.267007: step: 2770/1545, loss: 5.7813966122921556e-05 2023-01-23 18:29:58.146786: step: 2772/1545, loss: 0.006604339461773634 2023-01-23 18:29:59.052776: step: 2774/1545, loss: 0.23755408823490143 2023-01-23 18:30:00.001878: step: 2776/1545, loss: 0.0008649721858091652 2023-01-23 18:30:00.909777: step: 2778/1545, loss: 0.03479483723640442 2023-01-23 18:30:01.760079: step: 2780/1545, loss: 0.0005100445705465972 2023-01-23 18:30:02.679096: step: 2782/1545, loss: 0.03913319855928421 2023-01-23 18:30:03.552443: step: 2784/1545, loss: 0.005036370363086462 2023-01-23 18:30:04.394413: step: 2786/1545, loss: 0.24413570761680603 2023-01-23 18:30:05.317772: step: 2788/1545, loss: 0.046203579753637314 2023-01-23 18:30:06.209882: step: 2790/1545, loss: 0.00035312422551214695 2023-01-23 18:30:07.060687: step: 2792/1545, loss: 0.0004495063913054764 2023-01-23 18:30:07.981325: step: 2794/1545, loss: 0.0029528243467211723 2023-01-23 18:30:08.864635: step: 2796/1545, loss: 0.027468370273709297 2023-01-23 18:30:09.718479: step: 2798/1545, loss: 0.00105659372638911 2023-01-23 18:30:10.577885: step: 2800/1545, loss: 0.005116933491080999 2023-01-23 18:30:11.443234: step: 2802/1545, loss: 0.0030308119021356106 2023-01-23 18:30:12.337357: step: 2804/1545, loss: 0.0006248731515370309 2023-01-23 18:30:13.320261: step: 2806/1545, loss: 7.518053462263197e-05 2023-01-23 18:30:14.210365: step: 2808/1545, loss: 0.08185432851314545 2023-01-23 18:30:15.176237: step: 2810/1545, loss: 0.00013818177103530616 2023-01-23 18:30:16.099042: step: 2812/1545, loss: 0.00205779611133039 2023-01-23 18:30:16.973743: step: 2814/1545, loss: 0.0004291697987355292 2023-01-23 18:30:17.836979: step: 2816/1545, loss: 0.0001082588714780286 2023-01-23 18:30:18.718147: step: 2818/1545, loss: 0.0004357403959147632 2023-01-23 18:30:19.625592: step: 2820/1545, loss: 0.008975776843726635 2023-01-23 18:30:20.516427: step: 2822/1545, loss: 0.000908553833141923 2023-01-23 18:30:21.385239: step: 2824/1545, loss: 0.04590380936861038 2023-01-23 18:30:22.240421: step: 2826/1545, loss: 5.87477334192954e-05 2023-01-23 18:30:23.157694: step: 2828/1545, loss: 0.0054298629984259605 2023-01-23 18:30:24.055171: step: 2830/1545, loss: 0.008860720321536064 2023-01-23 18:30:24.887260: step: 2832/1545, loss: 0.0005136526888236403 2023-01-23 18:30:25.799392: step: 2834/1545, loss: 0.0034237541258335114 2023-01-23 18:30:26.684832: step: 2836/1545, loss: 0.02192714437842369 2023-01-23 18:30:27.580126: step: 2838/1545, loss: 0.10570076107978821 2023-01-23 18:30:28.543529: step: 2840/1545, loss: 0.040908895432949066 2023-01-23 18:30:29.422547: step: 2842/1545, loss: 0.1805056780576706 2023-01-23 18:30:30.363141: step: 2844/1545, loss: 0.005074145272374153 2023-01-23 18:30:31.323725: step: 2846/1545, loss: 0.003791223978623748 2023-01-23 18:30:32.196438: step: 2848/1545, loss: 0.05341022089123726 2023-01-23 18:30:33.055817: step: 2850/1545, loss: 0.0003962430346291512 2023-01-23 18:30:33.958395: step: 2852/1545, loss: 0.056978218257427216 2023-01-23 18:30:34.823588: step: 2854/1545, loss: 0.17179280519485474 2023-01-23 18:30:35.750179: step: 2856/1545, loss: 0.2743702828884125 2023-01-23 18:30:36.638385: step: 2858/1545, loss: 0.002224299358204007 2023-01-23 18:30:37.583831: step: 2860/1545, loss: 0.0006566016236320138 2023-01-23 18:30:38.435209: step: 2862/1545, loss: 0.0072614047676324844 2023-01-23 18:30:39.352244: step: 2864/1545, loss: 0.001905882265418768 2023-01-23 18:30:40.260106: step: 2866/1545, loss: 0.03929973766207695 2023-01-23 18:30:41.137529: step: 2868/1545, loss: 0.0007574931951239705 2023-01-23 18:30:41.979275: step: 2870/1545, loss: 0.050191693007946014 2023-01-23 18:30:42.873177: step: 2872/1545, loss: 0.003513401374220848 2023-01-23 18:30:43.775542: step: 2874/1545, loss: 0.019043002277612686 2023-01-23 18:30:44.655472: step: 2876/1545, loss: 5.117295586387627e-05 2023-01-23 18:30:45.522475: step: 2878/1545, loss: 0.0031433103140443563 2023-01-23 18:30:46.511337: step: 2880/1545, loss: 0.13028183579444885 2023-01-23 18:30:47.357412: step: 2882/1545, loss: 1.0044810771942139 2023-01-23 18:30:48.232302: step: 2884/1545, loss: 0.010838915593922138 2023-01-23 18:30:49.093391: step: 2886/1545, loss: 5.574541864916682e-05 2023-01-23 18:30:49.975893: step: 2888/1545, loss: 7.55515429773368e-05 2023-01-23 18:30:50.866931: step: 2890/1545, loss: 0.001253123627975583 2023-01-23 18:30:51.803440: step: 2892/1545, loss: 0.06984590739011765 2023-01-23 18:30:52.660455: step: 2894/1545, loss: 0.0033769109286367893 2023-01-23 18:30:53.494736: step: 2896/1545, loss: 0.0033604411873966455 2023-01-23 18:30:54.379008: step: 2898/1545, loss: 0.01900744065642357 2023-01-23 18:30:55.290004: step: 2900/1545, loss: 0.003503839485347271 2023-01-23 18:30:56.168485: step: 2902/1545, loss: 0.18146257102489471 2023-01-23 18:30:57.103310: step: 2904/1545, loss: 0.0024243155494332314 2023-01-23 18:30:57.949514: step: 2906/1545, loss: 0.1357433795928955 2023-01-23 18:30:58.814575: step: 2908/1545, loss: 0.0005548277986235917 2023-01-23 18:30:59.683911: step: 2910/1545, loss: 0.001390838180668652 2023-01-23 18:31:00.572731: step: 2912/1545, loss: 0.23072484135627747 2023-01-23 18:31:01.441892: step: 2914/1545, loss: 0.082638218998909 2023-01-23 18:31:02.412836: step: 2916/1545, loss: 0.0008986182510852814 2023-01-23 18:31:03.290461: step: 2918/1545, loss: 0.8295711874961853 2023-01-23 18:31:04.156802: step: 2920/1545, loss: 0.00408948864787817 2023-01-23 18:31:05.028464: step: 2922/1545, loss: 0.0180642269551754 2023-01-23 18:31:05.887391: step: 2924/1545, loss: 0.08133037388324738 2023-01-23 18:31:06.763432: step: 2926/1545, loss: 0.07538914680480957 2023-01-23 18:31:07.626408: step: 2928/1545, loss: 0.07634103298187256 2023-01-23 18:31:08.522235: step: 2930/1545, loss: 0.0011879182420670986 2023-01-23 18:31:09.396581: step: 2932/1545, loss: 0.344715416431427 2023-01-23 18:31:10.276623: step: 2934/1545, loss: 0.00020012336608488113 2023-01-23 18:31:11.135292: step: 2936/1545, loss: 0.005901521071791649 2023-01-23 18:31:11.979149: step: 2938/1545, loss: 0.02207113988697529 2023-01-23 18:31:12.860056: step: 2940/1545, loss: 0.00040989607805386186 2023-01-23 18:31:13.771084: step: 2942/1545, loss: 0.05834571644663811 2023-01-23 18:31:14.670775: step: 2944/1545, loss: 0.04671868681907654 2023-01-23 18:31:15.510044: step: 2946/1545, loss: 0.055494267493486404 2023-01-23 18:31:16.377330: step: 2948/1545, loss: 0.053143035620450974 2023-01-23 18:31:17.272868: step: 2950/1545, loss: 9.043161117006093e-05 2023-01-23 18:31:18.217658: step: 2952/1545, loss: 0.000535766186658293 2023-01-23 18:31:19.159601: step: 2954/1545, loss: 0.0003641433722805232 2023-01-23 18:31:20.016302: step: 2956/1545, loss: 0.11720941960811615 2023-01-23 18:31:20.951202: step: 2958/1545, loss: 0.07984497398138046 2023-01-23 18:31:21.861278: step: 2960/1545, loss: 0.26797884702682495 2023-01-23 18:31:22.791773: step: 2962/1545, loss: 0.08159298449754715 2023-01-23 18:31:23.734683: step: 2964/1545, loss: 0.013780386187136173 2023-01-23 18:31:24.635916: step: 2966/1545, loss: 0.09570392966270447 2023-01-23 18:31:25.558395: step: 2968/1545, loss: 0.00015449561760760844 2023-01-23 18:31:26.413586: step: 2970/1545, loss: 0.019761385396122932 2023-01-23 18:31:27.300583: step: 2972/1545, loss: 0.000638664118014276 2023-01-23 18:31:28.175468: step: 2974/1545, loss: 0.002061594044789672 2023-01-23 18:31:29.055344: step: 2976/1545, loss: 0.07377209514379501 2023-01-23 18:31:30.053429: step: 2978/1545, loss: 0.10958650708198547 2023-01-23 18:31:30.974014: step: 2980/1545, loss: 0.011182354763150215 2023-01-23 18:31:31.836796: step: 2982/1545, loss: 0.0002297296014148742 2023-01-23 18:31:32.745803: step: 2984/1545, loss: 0.002199048176407814 2023-01-23 18:31:33.612248: step: 2986/1545, loss: 0.007487689144909382 2023-01-23 18:31:34.466770: step: 2988/1545, loss: 0.00453257467597723 2023-01-23 18:31:35.324797: step: 2990/1545, loss: 0.00010414396092528477 2023-01-23 18:31:36.215079: step: 2992/1545, loss: 0.011643498204648495 2023-01-23 18:31:37.139197: step: 2994/1545, loss: 0.006482691504061222 2023-01-23 18:31:38.005837: step: 2996/1545, loss: 0.05309503898024559 2023-01-23 18:31:38.913293: step: 2998/1545, loss: 0.0001779407903086394 2023-01-23 18:31:39.767565: step: 3000/1545, loss: 0.10074935853481293 2023-01-23 18:31:40.619926: step: 3002/1545, loss: 0.00043490296229720116 2023-01-23 18:31:41.495996: step: 3004/1545, loss: 0.002230769721791148 2023-01-23 18:31:42.386880: step: 3006/1545, loss: 0.0014521925477311015 2023-01-23 18:31:43.219601: step: 3008/1545, loss: 5.6253920774906874e-05 2023-01-23 18:31:44.121533: step: 3010/1545, loss: 0.1454876959323883 2023-01-23 18:31:45.006305: step: 3012/1545, loss: 0.0013508941046893597 2023-01-23 18:31:45.882090: step: 3014/1545, loss: 0.017384158447384834 2023-01-23 18:31:46.779713: step: 3016/1545, loss: 0.0002598725550342351 2023-01-23 18:31:47.628783: step: 3018/1545, loss: 0.0006940375315025449 2023-01-23 18:31:48.532995: step: 3020/1545, loss: 0.004236036445945501 2023-01-23 18:31:49.448401: step: 3022/1545, loss: 0.1781487762928009 2023-01-23 18:31:50.276328: step: 3024/1545, loss: 0.00168654415756464 2023-01-23 18:31:51.198136: step: 3026/1545, loss: 0.02638111636042595 2023-01-23 18:31:52.074994: step: 3028/1545, loss: 0.0019868831150233746 2023-01-23 18:31:52.951679: step: 3030/1545, loss: 0.0003222391533199698 2023-01-23 18:31:53.841899: step: 3032/1545, loss: 0.0007027987740002573 2023-01-23 18:31:54.817963: step: 3034/1545, loss: 0.010596845299005508 2023-01-23 18:31:55.719224: step: 3036/1545, loss: 0.0019467679085209966 2023-01-23 18:31:56.582034: step: 3038/1545, loss: 0.14153271913528442 2023-01-23 18:31:57.525066: step: 3040/1545, loss: 0.1565966010093689 2023-01-23 18:31:58.459210: step: 3042/1545, loss: 0.0008586231851950288 2023-01-23 18:31:59.457210: step: 3044/1545, loss: 0.0024856533855199814 2023-01-23 18:32:00.332149: step: 3046/1545, loss: 0.2718566954135895 2023-01-23 18:32:01.240804: step: 3048/1545, loss: 0.3809446096420288 2023-01-23 18:32:02.182711: step: 3050/1545, loss: 0.00035209572524763644 2023-01-23 18:32:03.064825: step: 3052/1545, loss: 0.00012806789891328663 2023-01-23 18:32:03.945180: step: 3054/1545, loss: 0.020590296015143394 2023-01-23 18:32:04.797080: step: 3056/1545, loss: 0.0001645201991777867 2023-01-23 18:32:05.690376: step: 3058/1545, loss: 0.007199715357273817 2023-01-23 18:32:06.584190: step: 3060/1545, loss: 0.001957811415195465 2023-01-23 18:32:07.474777: step: 3062/1545, loss: 0.011905311606824398 2023-01-23 18:32:08.368209: step: 3064/1545, loss: 0.02582581527531147 2023-01-23 18:32:09.223586: step: 3066/1545, loss: 0.04546085745096207 2023-01-23 18:32:10.079534: step: 3068/1545, loss: 0.0008653621189296246 2023-01-23 18:32:10.976516: step: 3070/1545, loss: 0.00350892823189497 2023-01-23 18:32:11.913654: step: 3072/1545, loss: 0.03901705518364906 2023-01-23 18:32:12.865498: step: 3074/1545, loss: 0.001282014767639339 2023-01-23 18:32:13.742280: step: 3076/1545, loss: 0.046293705701828 2023-01-23 18:32:14.644697: step: 3078/1545, loss: 0.07354967296123505 2023-01-23 18:32:15.518707: step: 3080/1545, loss: 0.2509703040122986 2023-01-23 18:32:16.345634: step: 3082/1545, loss: 4.72398241981864e-05 2023-01-23 18:32:17.282473: step: 3084/1545, loss: 0.002963283099234104 2023-01-23 18:32:18.160790: step: 3086/1545, loss: 0.0007737764972262084 2023-01-23 18:32:19.034227: step: 3088/1545, loss: 0.2595474123954773 2023-01-23 18:32:19.881613: step: 3090/1545, loss: 0.008310087025165558 ================================================== Loss: 0.064 -------------------- Dev Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6637511851641956, 'r': 0.6582861679210773, 'f1': 0.66100738094142}, 'combined': 0.43591613851052874, 'epoch': 28} Test Chinese: {'event': {'p': 0.6414087513340448, 'r': 0.768542199488491, 'f1': 0.6992437463641652}, 'argument': {'p': 0.701797632651199, 'r': 0.7175954427719241, 'f1': 0.7096086230919498}, 'combined': 0.49618939206313184, 'epoch': 28} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6654420309320569, 'r': 0.6559428584394129, 'f1': 0.660658300857252}, 'combined': 0.4420260343273145, 'epoch': 28} Test Korean: {'event': {'p': 0.6322751322751323, 'r': 0.7640664961636828, 'f1': 0.6919513607411696}, 'argument': {'p': 0.6964149686755481, 'r': 0.7134396279556227, 'f1': 0.7048245079199321}, 'combined': 0.4877042773389223, 'epoch': 28} Dev Russian: {'event': {'p': 0.5728346456692913, 'r': 0.7749667110519307, 'f1': 0.6587436332767402}, 'argument': {'p': 0.663895185623841, 'r': 0.6676970191850369, 'f1': 0.6657906750902901}, 'combined': 0.4385853683107514, 'epoch': 28} Test Russian: {'event': {'p': 0.6292974588938715, 'r': 0.8075447570332481, 'f1': 0.7073648837860543}, 'argument': {'p': 0.7004601572194137, 'r': 0.729034317824547, 'f1': 0.714461653118353}, 'combined': 0.505385084227656, 'epoch': 28} Chinese: {'event': {'p': 0.5641025641025641, 'r': 0.8148148148148148, 'f1': 0.6666666666666667}, 'argument': {'p': 0.7147408666100254, 'r': 0.6320435762584522, 'f1': 0.67085326953748}, 'combined': 0.44723551302498676, 'epoch': 28} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6932773109243697, 'r': 0.48434442270058703, 'f1': 0.5702764976958524}, 'combined': 0.35016977928692694, 'epoch': 28} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5618667600955051, 'r': 0.5217334200886833, 'f1': 0.5410568800919678}, 'combined': 0.3013481357474251, 'epoch': 28} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6559451265403835, 'r': 0.6613377994790564, 'f1': 0.6586304247882229}, 'combined': 0.43355887674908195, 'epoch': 26} Test for Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6980547354393568, 'r': 0.7185779178100443, 'f1': 0.7081676638737557}, 'combined': 0.49271002093834315, 'epoch': 26} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6657901327322815, 'r': 0.6657901327322815, 'f1': 0.6657901327322815}, 'combined': 0.47412327633965495, 'epoch': 26} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 29 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 18:37:37.376595: step: 2/1545, loss: 0.0005658617010340095 2023-01-23 18:37:38.238068: step: 4/1545, loss: 0.11908487230539322 2023-01-23 18:37:39.135783: step: 6/1545, loss: 0.0008357217884622514 2023-01-23 18:37:39.982278: step: 8/1545, loss: 7.941525836940855e-05 2023-01-23 18:37:40.921679: step: 10/1545, loss: 0.0031601418741047382 2023-01-23 18:37:41.766814: step: 12/1545, loss: 0.039306171238422394 2023-01-23 18:37:42.652655: step: 14/1545, loss: 3.412686783121899e-05 2023-01-23 18:37:43.517185: step: 16/1545, loss: 0.03898628428578377 2023-01-23 18:37:44.388165: step: 18/1545, loss: 4.7995083150453866e-05 2023-01-23 18:37:45.239575: step: 20/1545, loss: 0.0005162957240827382 2023-01-23 18:37:46.116143: step: 22/1545, loss: 0.11923840641975403 2023-01-23 18:37:46.960868: step: 24/1545, loss: 0.0008740443736314774 2023-01-23 18:37:47.867393: step: 26/1545, loss: 0.003868093714118004 2023-01-23 18:37:48.736341: step: 28/1545, loss: 0.043008267879486084 2023-01-23 18:37:49.618530: step: 30/1545, loss: 0.1755215972661972 2023-01-23 18:37:50.515349: step: 32/1545, loss: 0.001246549654752016 2023-01-23 18:37:51.434751: step: 34/1545, loss: 0.05605141445994377 2023-01-23 18:37:52.312431: step: 36/1545, loss: 0.07127725332975388 2023-01-23 18:37:53.175374: step: 38/1545, loss: 0.018574386835098267 2023-01-23 18:37:54.073927: step: 40/1545, loss: 0.17416681349277496 2023-01-23 18:37:54.959215: step: 42/1545, loss: 5.2094324928475544e-05 2023-01-23 18:37:55.839491: step: 44/1545, loss: 0.0006036942359060049 2023-01-23 18:37:56.673998: step: 46/1545, loss: 0.0026609632186591625 2023-01-23 18:37:57.522294: step: 48/1545, loss: 0.15632781386375427 2023-01-23 18:37:58.398864: step: 50/1545, loss: 0.0002886533038690686 2023-01-23 18:37:59.307314: step: 52/1545, loss: 0.10706473141908646 2023-01-23 18:38:00.209115: step: 54/1545, loss: 0.2092045694589615 2023-01-23 18:38:01.089440: step: 56/1545, loss: 0.0056108091957867146 2023-01-23 18:38:01.936455: step: 58/1545, loss: 0.0003714340564329177 2023-01-23 18:38:02.780186: step: 60/1545, loss: 0.0008359854109585285 2023-01-23 18:38:03.696124: step: 62/1545, loss: 0.1309604048728943 2023-01-23 18:38:04.633076: step: 64/1545, loss: 0.0002958119730465114 2023-01-23 18:38:05.475988: step: 66/1545, loss: 0.016629498451948166 2023-01-23 18:38:06.360174: step: 68/1545, loss: 0.0010540364310145378 2023-01-23 18:38:07.219242: step: 70/1545, loss: 0.05777496472001076 2023-01-23 18:38:08.091315: step: 72/1545, loss: 0.000493990199174732 2023-01-23 18:38:08.959691: step: 74/1545, loss: 0.013955765403807163 2023-01-23 18:38:09.799784: step: 76/1545, loss: 0.000395759881939739 2023-01-23 18:38:10.720181: step: 78/1545, loss: 0.006469422485679388 2023-01-23 18:38:11.597051: step: 80/1545, loss: 0.00027410383336246014 2023-01-23 18:38:12.462092: step: 82/1545, loss: 0.11186562478542328 2023-01-23 18:38:13.293853: step: 84/1545, loss: 0.0014384243404492736 2023-01-23 18:38:14.153527: step: 86/1545, loss: 0.14035038650035858 2023-01-23 18:38:15.124431: step: 88/1545, loss: 0.0295125562697649 2023-01-23 18:38:16.038297: step: 90/1545, loss: 0.0016468066023662686 2023-01-23 18:38:16.899121: step: 92/1545, loss: 0.244966521859169 2023-01-23 18:38:17.773123: step: 94/1545, loss: 0.08368978649377823 2023-01-23 18:38:18.646992: step: 96/1545, loss: 0.001813556649722159 2023-01-23 18:38:19.550719: step: 98/1545, loss: 0.0013377212453633547 2023-01-23 18:38:20.401614: step: 100/1545, loss: 0.0060076345689594746 2023-01-23 18:38:21.310343: step: 102/1545, loss: 0.05575527995824814 2023-01-23 18:38:22.257026: step: 104/1545, loss: 0.001509213587269187 2023-01-23 18:38:23.106584: step: 106/1545, loss: 0.00012351322220638394 2023-01-23 18:38:23.985954: step: 108/1545, loss: 0.007681172341108322 2023-01-23 18:38:24.859889: step: 110/1545, loss: 0.020303333178162575 2023-01-23 18:38:25.738406: step: 112/1545, loss: 0.0853559821844101 2023-01-23 18:38:26.635268: step: 114/1545, loss: 0.0003370133927091956 2023-01-23 18:38:27.515819: step: 116/1545, loss: 0.0016263769939541817 2023-01-23 18:38:28.385418: step: 118/1545, loss: 0.00010218020179308951 2023-01-23 18:38:29.256626: step: 120/1545, loss: 0.002242522779852152 2023-01-23 18:38:30.145373: step: 122/1545, loss: 0.0404232032597065 2023-01-23 18:38:31.029689: step: 124/1545, loss: 0.00018414307851344347 2023-01-23 18:38:31.880760: step: 126/1545, loss: 0.0962778776884079 2023-01-23 18:38:32.793694: step: 128/1545, loss: 0.9719885587692261 2023-01-23 18:38:33.691143: step: 130/1545, loss: 0.0683244839310646 2023-01-23 18:38:34.582114: step: 132/1545, loss: 0.024614127352833748 2023-01-23 18:38:35.488310: step: 134/1545, loss: 0.0005106147145852447 2023-01-23 18:38:36.379670: step: 136/1545, loss: 0.0003909603401552886 2023-01-23 18:38:37.249824: step: 138/1545, loss: 0.0003129553806502372 2023-01-23 18:38:38.170377: step: 140/1545, loss: 0.14629565179347992 2023-01-23 18:38:39.038677: step: 142/1545, loss: 0.010086653754115105 2023-01-23 18:38:39.963067: step: 144/1545, loss: 0.2975315749645233 2023-01-23 18:38:40.924623: step: 146/1545, loss: 0.003895628033205867 2023-01-23 18:38:41.824260: step: 148/1545, loss: 0.01888781599700451 2023-01-23 18:38:42.705958: step: 150/1545, loss: 0.00020549146574921906 2023-01-23 18:38:43.624501: step: 152/1545, loss: 0.0003457478596828878 2023-01-23 18:38:44.478755: step: 154/1545, loss: 0.10898542404174805 2023-01-23 18:38:45.339208: step: 156/1545, loss: 0.003054278902709484 2023-01-23 18:38:46.171393: step: 158/1545, loss: 0.028021767735481262 2023-01-23 18:38:47.040095: step: 160/1545, loss: 0.0011289450339972973 2023-01-23 18:38:47.908433: step: 162/1545, loss: 0.00017665854829829186 2023-01-23 18:38:48.766495: step: 164/1545, loss: 0.0006759078823961318 2023-01-23 18:38:49.652473: step: 166/1545, loss: 0.00015169972903095186 2023-01-23 18:38:50.543397: step: 168/1545, loss: 0.000326684647006914 2023-01-23 18:38:51.435510: step: 170/1545, loss: 0.0007132125901989639 2023-01-23 18:38:52.297365: step: 172/1545, loss: 2.4372267944272608e-05 2023-01-23 18:38:53.163703: step: 174/1545, loss: 0.01243062224239111 2023-01-23 18:38:54.029435: step: 176/1545, loss: 0.17842286825180054 2023-01-23 18:38:54.895780: step: 178/1545, loss: 0.0001552092144265771 2023-01-23 18:38:55.771241: step: 180/1545, loss: 0.3630804717540741 2023-01-23 18:38:56.623489: step: 182/1545, loss: 0.000817681138869375 2023-01-23 18:38:57.469761: step: 184/1545, loss: 0.0037677320651710033 2023-01-23 18:38:58.369651: step: 186/1545, loss: 0.00016902810602914542 2023-01-23 18:38:59.234852: step: 188/1545, loss: 1.58681058883667 2023-01-23 18:39:00.129149: step: 190/1545, loss: 0.0007883093785494566 2023-01-23 18:39:01.009843: step: 192/1545, loss: 0.0026293746195733547 2023-01-23 18:39:01.929976: step: 194/1545, loss: 0.028010249137878418 2023-01-23 18:39:02.791334: step: 196/1545, loss: 5.765093374066055e-05 2023-01-23 18:39:03.682924: step: 198/1545, loss: 0.0004039859923068434 2023-01-23 18:39:04.588851: step: 200/1545, loss: 0.00031523173674941063 2023-01-23 18:39:05.413213: step: 202/1545, loss: 0.07457389682531357 2023-01-23 18:39:06.256389: step: 204/1545, loss: 0.00045974107342772186 2023-01-23 18:39:07.180503: step: 206/1545, loss: 0.05853710696101189 2023-01-23 18:39:08.040289: step: 208/1545, loss: 0.11734502017498016 2023-01-23 18:39:08.911757: step: 210/1545, loss: 6.494682747870684e-05 2023-01-23 18:39:09.853631: step: 212/1545, loss: 0.00014658724830951542 2023-01-23 18:39:10.749329: step: 214/1545, loss: 0.0008369683637283742 2023-01-23 18:39:11.604745: step: 216/1545, loss: 0.006528699304908514 2023-01-23 18:39:12.519423: step: 218/1545, loss: 0.05324459820985794 2023-01-23 18:39:13.473807: step: 220/1545, loss: 0.11641928553581238 2023-01-23 18:39:14.347885: step: 222/1545, loss: 0.0012093526311218739 2023-01-23 18:39:15.221327: step: 224/1545, loss: 0.0578036792576313 2023-01-23 18:39:16.074306: step: 226/1545, loss: 0.007435244042426348 2023-01-23 18:39:16.981833: step: 228/1545, loss: 1.3861671504855622e-05 2023-01-23 18:39:17.871249: step: 230/1545, loss: 0.018246598541736603 2023-01-23 18:39:18.771034: step: 232/1545, loss: 0.019653964787721634 2023-01-23 18:39:19.654776: step: 234/1545, loss: 0.0002226188953500241 2023-01-23 18:39:20.657484: step: 236/1545, loss: 0.11014477163553238 2023-01-23 18:39:21.562423: step: 238/1545, loss: 3.189908981323242 2023-01-23 18:39:22.445626: step: 240/1545, loss: 0.000135735041112639 2023-01-23 18:39:23.321285: step: 242/1545, loss: 0.23894551396369934 2023-01-23 18:39:24.150610: step: 244/1545, loss: 4.33106797572691e-05 2023-01-23 18:39:25.082122: step: 246/1545, loss: 0.017969641834497452 2023-01-23 18:39:25.979650: step: 248/1545, loss: 0.00431592483073473 2023-01-23 18:39:26.820393: step: 250/1545, loss: 0.03254515677690506 2023-01-23 18:39:27.666332: step: 252/1545, loss: 0.0009788230527192354 2023-01-23 18:39:28.637835: step: 254/1545, loss: 0.8936911225318909 2023-01-23 18:39:29.531724: step: 256/1545, loss: 0.00042031772318296134 2023-01-23 18:39:30.444571: step: 258/1545, loss: -5.961828719591722e-06 2023-01-23 18:39:31.356343: step: 260/1545, loss: 0.02018830180168152 2023-01-23 18:39:32.220622: step: 262/1545, loss: 3.899721195921302e-05 2023-01-23 18:39:33.094581: step: 264/1545, loss: 0.0005090772174298763 2023-01-23 18:39:33.975158: step: 266/1545, loss: 0.004365227185189724 2023-01-23 18:39:34.822342: step: 268/1545, loss: 0.004945321939885616 2023-01-23 18:39:35.725713: step: 270/1545, loss: 0.01669628545641899 2023-01-23 18:39:36.689906: step: 272/1545, loss: 0.1259128302335739 2023-01-23 18:39:37.582602: step: 274/1545, loss: 0.00036272386205382645 2023-01-23 18:39:38.495966: step: 276/1545, loss: 0.059967804700136185 2023-01-23 18:39:39.377540: step: 278/1545, loss: 0.0004781183961313218 2023-01-23 18:39:40.255309: step: 280/1545, loss: 0.2072819024324417 2023-01-23 18:39:41.106229: step: 282/1545, loss: 0.0001502835948485881 2023-01-23 18:39:42.002693: step: 284/1545, loss: 0.09109370410442352 2023-01-23 18:39:42.855031: step: 286/1545, loss: 0.004982194397598505 2023-01-23 18:39:43.700237: step: 288/1545, loss: 0.011809448711574078 2023-01-23 18:39:44.616130: step: 290/1545, loss: 0.06504780799150467 2023-01-23 18:39:45.526068: step: 292/1545, loss: 0.020663024857640266 2023-01-23 18:39:46.393249: step: 294/1545, loss: 0.00018200332124251872 2023-01-23 18:39:47.252920: step: 296/1545, loss: 0.06698707491159439 2023-01-23 18:39:48.178767: step: 298/1545, loss: 0.00013362991739995778 2023-01-23 18:39:49.098606: step: 300/1545, loss: 0.0003134818689431995 2023-01-23 18:39:49.982117: step: 302/1545, loss: 0.020706800743937492 2023-01-23 18:39:50.874721: step: 304/1545, loss: 0.034807875752449036 2023-01-23 18:39:51.776231: step: 306/1545, loss: 0.014253824949264526 2023-01-23 18:39:52.732982: step: 308/1545, loss: 0.007781986612826586 2023-01-23 18:39:53.606115: step: 310/1545, loss: 0.0036463302094489336 2023-01-23 18:39:54.521035: step: 312/1545, loss: 0.015815965831279755 2023-01-23 18:39:55.441029: step: 314/1545, loss: 0.04280690848827362 2023-01-23 18:39:56.289500: step: 316/1545, loss: 0.10439969599246979 2023-01-23 18:39:57.119668: step: 318/1545, loss: 0.004278683569282293 2023-01-23 18:39:58.006907: step: 320/1545, loss: 0.030444210395216942 2023-01-23 18:39:58.862334: step: 322/1545, loss: 0.0017741004703566432 2023-01-23 18:39:59.783415: step: 324/1545, loss: 0.04990439862012863 2023-01-23 18:40:00.658888: step: 326/1545, loss: 0.00915922038257122 2023-01-23 18:40:01.583005: step: 328/1545, loss: 0.0006689282599836588 2023-01-23 18:40:02.414006: step: 330/1545, loss: 0.0038196865934878588 2023-01-23 18:40:03.319918: step: 332/1545, loss: 0.38298529386520386 2023-01-23 18:40:04.183011: step: 334/1545, loss: 0.045614536851644516 2023-01-23 18:40:05.061201: step: 336/1545, loss: 0.00461895065382123 2023-01-23 18:40:05.930592: step: 338/1545, loss: 0.0013653540518134832 2023-01-23 18:40:06.820137: step: 340/1545, loss: 0.0005118993576616049 2023-01-23 18:40:07.736904: step: 342/1545, loss: 0.00046757954987697303 2023-01-23 18:40:08.630819: step: 344/1545, loss: 0.0004601837426889688 2023-01-23 18:40:09.519638: step: 346/1545, loss: 0.13382408022880554 2023-01-23 18:40:10.393115: step: 348/1545, loss: 0.023368658497929573 2023-01-23 18:40:11.364803: step: 350/1545, loss: 0.0003266263229306787 2023-01-23 18:40:12.271154: step: 352/1545, loss: 9.537494042888284e-05 2023-01-23 18:40:13.157651: step: 354/1545, loss: 0.16266554594039917 2023-01-23 18:40:14.031957: step: 356/1545, loss: 0.020527943968772888 2023-01-23 18:40:14.898121: step: 358/1545, loss: 0.0035141173284500837 2023-01-23 18:40:15.812040: step: 360/1545, loss: 3.6053850650787354 2023-01-23 18:40:16.654449: step: 362/1545, loss: 5.3522315283771604e-05 2023-01-23 18:40:17.594955: step: 364/1545, loss: 0.057106584310531616 2023-01-23 18:40:18.484609: step: 366/1545, loss: 0.002817454282194376 2023-01-23 18:40:19.351858: step: 368/1545, loss: 0.06623396277427673 2023-01-23 18:40:20.233335: step: 370/1545, loss: 0.00024474706151522696 2023-01-23 18:40:21.135418: step: 372/1545, loss: 0.1468592882156372 2023-01-23 18:40:22.009128: step: 374/1545, loss: 0.012255105189979076 2023-01-23 18:40:22.882805: step: 376/1545, loss: 0.029970871284604073 2023-01-23 18:40:23.803196: step: 378/1545, loss: 0.589410126209259 2023-01-23 18:40:24.672688: step: 380/1545, loss: 0.00016022365889512002 2023-01-23 18:40:25.572450: step: 382/1545, loss: 0.3325843811035156 2023-01-23 18:40:26.466708: step: 384/1545, loss: 0.0008841899107210338 2023-01-23 18:40:27.347366: step: 386/1545, loss: 0.00041040871292352676 2023-01-23 18:40:28.261322: step: 388/1545, loss: 0.00032491941237822175 2023-01-23 18:40:29.110633: step: 390/1545, loss: 0.04200781509280205 2023-01-23 18:40:30.121073: step: 392/1545, loss: 0.1761372685432434 2023-01-23 18:40:30.986432: step: 394/1545, loss: 0.000516661093570292 2023-01-23 18:40:31.872934: step: 396/1545, loss: 0.00012356725346762687 2023-01-23 18:40:32.744033: step: 398/1545, loss: 0.008789589628577232 2023-01-23 18:40:33.602745: step: 400/1545, loss: 0.0009951477404683828 2023-01-23 18:40:34.453258: step: 402/1545, loss: 0.013306831941008568 2023-01-23 18:40:35.333873: step: 404/1545, loss: 0.01944829151034355 2023-01-23 18:40:36.186787: step: 406/1545, loss: 0.0003383277799002826 2023-01-23 18:40:37.097374: step: 408/1545, loss: 0.0003161747590638697 2023-01-23 18:40:37.944299: step: 410/1545, loss: 0.00022836445714347064 2023-01-23 18:40:38.841316: step: 412/1545, loss: 4.4248736230656505e-05 2023-01-23 18:40:39.712485: step: 414/1545, loss: 0.026209700852632523 2023-01-23 18:40:40.590952: step: 416/1545, loss: 0.0006244441028684378 2023-01-23 18:40:41.452073: step: 418/1545, loss: 6.974307325435802e-05 2023-01-23 18:40:42.328844: step: 420/1545, loss: 0.0059966351836919785 2023-01-23 18:40:43.206028: step: 422/1545, loss: 0.015095308423042297 2023-01-23 18:40:44.089720: step: 424/1545, loss: 0.00012040651199640706 2023-01-23 18:40:45.042882: step: 426/1545, loss: 0.0026096098590642214 2023-01-23 18:40:45.922981: step: 428/1545, loss: 0.00021388738241512328 2023-01-23 18:40:46.809124: step: 430/1545, loss: 0.006307512521743774 2023-01-23 18:40:47.682245: step: 432/1545, loss: 0.04531848058104515 2023-01-23 18:40:48.596747: step: 434/1545, loss: 0.03661850467324257 2023-01-23 18:40:49.470754: step: 436/1545, loss: 0.05439874529838562 2023-01-23 18:40:50.342667: step: 438/1545, loss: 0.009460206143558025 2023-01-23 18:40:51.206405: step: 440/1545, loss: 0.09020418673753738 2023-01-23 18:40:52.079899: step: 442/1545, loss: 0.06201758235692978 2023-01-23 18:40:52.948630: step: 444/1545, loss: 0.04149270057678223 2023-01-23 18:40:53.861654: step: 446/1545, loss: 0.009467185474932194 2023-01-23 18:40:54.709083: step: 448/1545, loss: 0.000768524594604969 2023-01-23 18:40:55.542915: step: 450/1545, loss: 0.007397140376269817 2023-01-23 18:40:56.441134: step: 452/1545, loss: 0.002251570811495185 2023-01-23 18:40:57.319070: step: 454/1545, loss: 0.00917822029441595 2023-01-23 18:40:58.168756: step: 456/1545, loss: 0.09326723963022232 2023-01-23 18:40:59.053545: step: 458/1545, loss: 0.12091447412967682 2023-01-23 18:40:59.967689: step: 460/1545, loss: 0.001644869684241712 2023-01-23 18:41:00.854397: step: 462/1545, loss: 0.003394843777641654 2023-01-23 18:41:01.702784: step: 464/1545, loss: 0.05884445086121559 2023-01-23 18:41:02.564189: step: 466/1545, loss: 0.0005897324299439788 2023-01-23 18:41:03.426335: step: 468/1545, loss: 0.016417503356933594 2023-01-23 18:41:04.293272: step: 470/1545, loss: 0.0006914768600836396 2023-01-23 18:41:05.186318: step: 472/1545, loss: 0.0005134458770044148 2023-01-23 18:41:06.045529: step: 474/1545, loss: 0.000578178558498621 2023-01-23 18:41:06.921961: step: 476/1545, loss: 0.11584044247865677 2023-01-23 18:41:07.814182: step: 478/1545, loss: 0.09952826052904129 2023-01-23 18:41:08.702388: step: 480/1545, loss: 0.012348669581115246 2023-01-23 18:41:09.575829: step: 482/1545, loss: 0.09691981226205826 2023-01-23 18:41:10.438606: step: 484/1545, loss: 0.00019202209659852087 2023-01-23 18:41:11.331287: step: 486/1545, loss: 0.00024568592198193073 2023-01-23 18:41:12.161141: step: 488/1545, loss: 0.0003458088613115251 2023-01-23 18:41:13.017832: step: 490/1545, loss: 0.007772437296807766 2023-01-23 18:41:13.896090: step: 492/1545, loss: 0.05197026953101158 2023-01-23 18:41:14.779332: step: 494/1545, loss: 0.003723485628142953 2023-01-23 18:41:15.711784: step: 496/1545, loss: 0.0019808427896350622 2023-01-23 18:41:16.604994: step: 498/1545, loss: 0.0021173260174691677 2023-01-23 18:41:17.512678: step: 500/1545, loss: 5.4223331972025335e-05 2023-01-23 18:41:18.405018: step: 502/1545, loss: 0.0026705432683229446 2023-01-23 18:41:19.332461: step: 504/1545, loss: 0.18353049457073212 2023-01-23 18:41:20.218203: step: 506/1545, loss: 0.06598958373069763 2023-01-23 18:41:21.140454: step: 508/1545, loss: 0.008286351338028908 2023-01-23 18:41:22.031247: step: 510/1545, loss: 0.010833686217665672 2023-01-23 18:41:22.999591: step: 512/1545, loss: 0.00023394938034471124 2023-01-23 18:41:23.867954: step: 514/1545, loss: 0.0016907101962715387 2023-01-23 18:41:24.744752: step: 516/1545, loss: 0.0007005883380770683 2023-01-23 18:41:25.601945: step: 518/1545, loss: 0.05821322649717331 2023-01-23 18:41:26.470017: step: 520/1545, loss: 0.00029887520940974355 2023-01-23 18:41:27.328361: step: 522/1545, loss: 0.039772845804691315 2023-01-23 18:41:28.202375: step: 524/1545, loss: 0.04684578999876976 2023-01-23 18:41:29.036360: step: 526/1545, loss: 0.0002200417802669108 2023-01-23 18:41:29.907734: step: 528/1545, loss: 0.0022909422405064106 2023-01-23 18:41:30.877307: step: 530/1545, loss: 0.0006465401966124773 2023-01-23 18:41:31.803329: step: 532/1545, loss: 0.14833740890026093 2023-01-23 18:41:32.750458: step: 534/1545, loss: 0.28927236795425415 2023-01-23 18:41:33.640321: step: 536/1545, loss: 0.16694407165050507 2023-01-23 18:41:34.514225: step: 538/1545, loss: 0.003263590857386589 2023-01-23 18:41:35.389133: step: 540/1545, loss: 0.004139537923038006 2023-01-23 18:41:36.306104: step: 542/1545, loss: 0.019902050495147705 2023-01-23 18:41:37.186406: step: 544/1545, loss: 0.0005180311854928732 2023-01-23 18:41:38.062765: step: 546/1545, loss: 0.0015969075029715896 2023-01-23 18:41:38.986162: step: 548/1545, loss: 0.0029218471609055996 2023-01-23 18:41:39.848458: step: 550/1545, loss: 0.00020831404253840446 2023-01-23 18:41:40.727594: step: 552/1545, loss: 0.03674282133579254 2023-01-23 18:41:41.675591: step: 554/1545, loss: 0.6541935801506042 2023-01-23 18:41:42.536874: step: 556/1545, loss: 0.4301626980304718 2023-01-23 18:41:43.420230: step: 558/1545, loss: 0.0018719214713200927 2023-01-23 18:41:44.333982: step: 560/1545, loss: 0.0007024271180853248 2023-01-23 18:41:45.236642: step: 562/1545, loss: 0.0012431336799636483 2023-01-23 18:41:46.106792: step: 564/1545, loss: 0.001376098720356822 2023-01-23 18:41:46.966091: step: 566/1545, loss: 0.0010915708262473345 2023-01-23 18:41:47.898524: step: 568/1545, loss: 0.010546431876718998 2023-01-23 18:41:48.788463: step: 570/1545, loss: 9.440575377084315e-05 2023-01-23 18:41:49.681383: step: 572/1545, loss: 0.0004384798521641642 2023-01-23 18:41:50.547519: step: 574/1545, loss: 0.0016859499737620354 2023-01-23 18:41:51.427560: step: 576/1545, loss: 0.0036519509740173817 2023-01-23 18:41:52.264781: step: 578/1545, loss: 0.014332665130496025 2023-01-23 18:41:53.112883: step: 580/1545, loss: 0.0004151345929130912 2023-01-23 18:41:53.984962: step: 582/1545, loss: 9.415399108547717e-05 2023-01-23 18:41:54.899732: step: 584/1545, loss: 0.0021918872371315956 2023-01-23 18:41:55.776591: step: 586/1545, loss: 0.17864418029785156 2023-01-23 18:41:56.656974: step: 588/1545, loss: 0.0003297511429991573 2023-01-23 18:41:57.555731: step: 590/1545, loss: 0.03797021508216858 2023-01-23 18:41:58.488316: step: 592/1545, loss: 7.832109258743003e-05 2023-01-23 18:41:59.353351: step: 594/1545, loss: 0.0003522252372931689 2023-01-23 18:42:00.247685: step: 596/1545, loss: 0.0004654674557968974 2023-01-23 18:42:01.133246: step: 598/1545, loss: 0.0032728882506489754 2023-01-23 18:42:01.996658: step: 600/1545, loss: 0.014004794880747795 2023-01-23 18:42:02.878570: step: 602/1545, loss: 0.01283311378210783 2023-01-23 18:42:03.806051: step: 604/1545, loss: 0.00028998713241890073 2023-01-23 18:42:04.705278: step: 606/1545, loss: 1.1875280141830444 2023-01-23 18:42:05.582412: step: 608/1545, loss: 0.009917390532791615 2023-01-23 18:42:06.457770: step: 610/1545, loss: 0.001338087604381144 2023-01-23 18:42:07.434765: step: 612/1545, loss: 0.0019753901287913322 2023-01-23 18:42:08.311628: step: 614/1545, loss: 0.000169671286130324 2023-01-23 18:42:09.189707: step: 616/1545, loss: 0.000861804059240967 2023-01-23 18:42:10.159409: step: 618/1545, loss: 0.0450434610247612 2023-01-23 18:42:11.016797: step: 620/1545, loss: 0.0002689840621314943 2023-01-23 18:42:11.906760: step: 622/1545, loss: 0.0007697519613429904 2023-01-23 18:42:12.811531: step: 624/1545, loss: 0.001252329209819436 2023-01-23 18:42:13.692074: step: 626/1545, loss: 0.0013342046877369285 2023-01-23 18:42:14.623271: step: 628/1545, loss: 1.8122892379760742 2023-01-23 18:42:15.537194: step: 630/1545, loss: 0.007022772450000048 2023-01-23 18:42:16.385690: step: 632/1545, loss: 0.0055634574964642525 2023-01-23 18:42:17.212988: step: 634/1545, loss: 0.05729415640234947 2023-01-23 18:42:18.184063: step: 636/1545, loss: 5.3988049330655485e-05 2023-01-23 18:42:19.052397: step: 638/1545, loss: 8.571585931349546e-05 2023-01-23 18:42:19.939255: step: 640/1545, loss: 0.0140501344576478 2023-01-23 18:42:20.859642: step: 642/1545, loss: 1.8519809246063232 2023-01-23 18:42:21.775311: step: 644/1545, loss: 0.00010540224320720881 2023-01-23 18:42:22.688234: step: 646/1545, loss: 0.05525527521967888 2023-01-23 18:42:23.617781: step: 648/1545, loss: 0.8101032376289368 2023-01-23 18:42:24.483481: step: 650/1545, loss: 0.0007365107303485274 2023-01-23 18:42:25.332970: step: 652/1545, loss: 0.00016420430620200932 2023-01-23 18:42:26.205146: step: 654/1545, loss: 0.11113033443689346 2023-01-23 18:42:27.249322: step: 656/1545, loss: 0.9473499655723572 2023-01-23 18:42:28.123011: step: 658/1545, loss: 0.003773324890062213 2023-01-23 18:42:29.007556: step: 660/1545, loss: 0.000643590756226331 2023-01-23 18:42:29.891576: step: 662/1545, loss: 0.0004114644543733448 2023-01-23 18:42:30.791010: step: 664/1545, loss: 8.197719580493867e-05 2023-01-23 18:42:31.645418: step: 666/1545, loss: 0.004723786376416683 2023-01-23 18:42:32.511038: step: 668/1545, loss: 0.28381285071372986 2023-01-23 18:42:33.370135: step: 670/1545, loss: 0.002153584733605385 2023-01-23 18:42:34.227694: step: 672/1545, loss: 0.1694812774658203 2023-01-23 18:42:35.097212: step: 674/1545, loss: 0.00011613134120125324 2023-01-23 18:42:35.978553: step: 676/1545, loss: 0.0001476373290643096 2023-01-23 18:42:36.836476: step: 678/1545, loss: 0.0034827685449272394 2023-01-23 18:42:37.721125: step: 680/1545, loss: 0.002429673448204994 2023-01-23 18:42:38.565904: step: 682/1545, loss: 0.0034679414238780737 2023-01-23 18:42:39.438615: step: 684/1545, loss: 0.003934649284929037 2023-01-23 18:42:40.308525: step: 686/1545, loss: 0.09532977640628815 2023-01-23 18:42:41.228574: step: 688/1545, loss: 0.05964745581150055 2023-01-23 18:42:42.136692: step: 690/1545, loss: 0.0005656385328620672 2023-01-23 18:42:43.037131: step: 692/1545, loss: 0.001135342987254262 2023-01-23 18:42:43.971006: step: 694/1545, loss: 0.01271823514252901 2023-01-23 18:42:44.853887: step: 696/1545, loss: 0.00015754593187011778 2023-01-23 18:42:45.716284: step: 698/1545, loss: 0.007812614552676678 2023-01-23 18:42:46.632198: step: 700/1545, loss: 0.009408148005604744 2023-01-23 18:42:47.538617: step: 702/1545, loss: 0.11197394132614136 2023-01-23 18:42:48.393219: step: 704/1545, loss: 0.04520056024193764 2023-01-23 18:42:49.274273: step: 706/1545, loss: 0.000672727357596159 2023-01-23 18:42:50.157683: step: 708/1545, loss: 1.3063834558124654e-05 2023-01-23 18:42:50.997212: step: 710/1545, loss: 0.007578167598694563 2023-01-23 18:42:51.849685: step: 712/1545, loss: 0.0010777667630463839 2023-01-23 18:42:52.761481: step: 714/1545, loss: 0.01637917011976242 2023-01-23 18:42:53.658856: step: 716/1545, loss: 0.0012663824018090963 2023-01-23 18:42:54.542585: step: 718/1545, loss: 0.11899898201227188 2023-01-23 18:42:55.511726: step: 720/1545, loss: 0.002264495939016342 2023-01-23 18:42:56.412266: step: 722/1545, loss: 0.001076863263733685 2023-01-23 18:42:57.266035: step: 724/1545, loss: 0.25371789932250977 2023-01-23 18:42:58.133308: step: 726/1545, loss: 0.062247440218925476 2023-01-23 18:42:58.997115: step: 728/1545, loss: 0.005863402970135212 2023-01-23 18:42:59.885815: step: 730/1545, loss: 0.020999552682042122 2023-01-23 18:43:00.806323: step: 732/1545, loss: 0.024536581709980965 2023-01-23 18:43:01.707443: step: 734/1545, loss: 1.2172504663467407 2023-01-23 18:43:02.645651: step: 736/1545, loss: 0.003290874417871237 2023-01-23 18:43:03.587523: step: 738/1545, loss: 0.008708149194717407 2023-01-23 18:43:04.436650: step: 740/1545, loss: 0.01115809939801693 2023-01-23 18:43:05.331326: step: 742/1545, loss: 0.000782832212280482 2023-01-23 18:43:06.216225: step: 744/1545, loss: 0.004235351923853159 2023-01-23 18:43:07.094185: step: 746/1545, loss: 0.0004906138638034463 2023-01-23 18:43:07.958278: step: 748/1545, loss: 0.0013324081664904952 2023-01-23 18:43:08.819220: step: 750/1545, loss: 0.008129391819238663 2023-01-23 18:43:09.775244: step: 752/1545, loss: 0.0007728300406597555 2023-01-23 18:43:10.617264: step: 754/1545, loss: 0.025173498317599297 2023-01-23 18:43:11.476830: step: 756/1545, loss: 0.002961904276162386 2023-01-23 18:43:12.341166: step: 758/1545, loss: 0.002233814913779497 2023-01-23 18:43:13.207452: step: 760/1545, loss: 0.28665828704833984 2023-01-23 18:43:14.083657: step: 762/1545, loss: 0.011754983104765415 2023-01-23 18:43:14.981883: step: 764/1545, loss: 0.0879877358675003 2023-01-23 18:43:15.878476: step: 766/1545, loss: 0.09310125559568405 2023-01-23 18:43:16.774463: step: 768/1545, loss: 0.1378651112318039 2023-01-23 18:43:17.647979: step: 770/1545, loss: 0.04501139000058174 2023-01-23 18:43:18.592488: step: 772/1545, loss: 0.0005987536860629916 2023-01-23 18:43:19.447056: step: 774/1545, loss: 0.00044462631922215223 2023-01-23 18:43:20.320480: step: 776/1545, loss: 4.530049773165956e-05 2023-01-23 18:43:21.188150: step: 778/1545, loss: 9.32653492782265e-05 2023-01-23 18:43:22.059225: step: 780/1545, loss: 0.0002075688389595598 2023-01-23 18:43:23.011652: step: 782/1545, loss: 0.0630565732717514 2023-01-23 18:43:23.877657: step: 784/1545, loss: 6.431875954149291e-05 2023-01-23 18:43:24.746447: step: 786/1545, loss: 7.149110751925036e-05 2023-01-23 18:43:25.590546: step: 788/1545, loss: 0.0008515589288435876 2023-01-23 18:43:26.438322: step: 790/1545, loss: 0.005285914521664381 2023-01-23 18:43:27.357387: step: 792/1545, loss: 0.15045185387134552 2023-01-23 18:43:28.326647: step: 794/1545, loss: 0.0029383667279034853 2023-01-23 18:43:29.280819: step: 796/1545, loss: 0.03497293218970299 2023-01-23 18:43:30.212788: step: 798/1545, loss: 0.000743405194953084 2023-01-23 18:43:31.102320: step: 800/1545, loss: 0.0003585690283216536 2023-01-23 18:43:31.941915: step: 802/1545, loss: 0.00029759100289084017 2023-01-23 18:43:32.840064: step: 804/1545, loss: 0.08026471734046936 2023-01-23 18:43:33.753758: step: 806/1545, loss: 0.1096753254532814 2023-01-23 18:43:34.602980: step: 808/1545, loss: 0.012385879643261433 2023-01-23 18:43:35.476733: step: 810/1545, loss: 0.0002461611293256283 2023-01-23 18:43:36.379695: step: 812/1545, loss: 0.0022394591942429543 2023-01-23 18:43:37.297953: step: 814/1545, loss: 0.019116440787911415 2023-01-23 18:43:38.237314: step: 816/1545, loss: 0.00020874233450740576 2023-01-23 18:43:39.142439: step: 818/1545, loss: 0.0028277954552322626 2023-01-23 18:43:40.022302: step: 820/1545, loss: 0.01843753270804882 2023-01-23 18:43:40.884795: step: 822/1545, loss: 0.007695324718952179 2023-01-23 18:43:41.791445: step: 824/1545, loss: 0.09631271660327911 2023-01-23 18:43:42.666231: step: 826/1545, loss: 1.0088388919830322 2023-01-23 18:43:43.537125: step: 828/1545, loss: 0.18131178617477417 2023-01-23 18:43:44.420020: step: 830/1545, loss: 0.029567750170826912 2023-01-23 18:43:45.336463: step: 832/1545, loss: 0.15890322625637054 2023-01-23 18:43:46.187081: step: 834/1545, loss: 0.1007632240653038 2023-01-23 18:43:47.010222: step: 836/1545, loss: 0.00033013749634847045 2023-01-23 18:43:47.885884: step: 838/1545, loss: 0.00010505300451768562 2023-01-23 18:43:48.771363: step: 840/1545, loss: 0.10435279458761215 2023-01-23 18:43:49.692183: step: 842/1545, loss: 0.0006505970377475023 2023-01-23 18:43:50.552576: step: 844/1545, loss: 0.0010124321561306715 2023-01-23 18:43:51.413243: step: 846/1545, loss: 0.007678722497075796 2023-01-23 18:43:52.262961: step: 848/1545, loss: 0.0011143902083858848 2023-01-23 18:43:53.149745: step: 850/1545, loss: 0.10237076878547668 2023-01-23 18:43:54.030658: step: 852/1545, loss: 0.08696059137582779 2023-01-23 18:43:54.875211: step: 854/1545, loss: 0.0022643418051302433 2023-01-23 18:43:55.766962: step: 856/1545, loss: 0.4144577980041504 2023-01-23 18:43:56.608966: step: 858/1545, loss: 0.0015289169969037175 2023-01-23 18:43:57.473192: step: 860/1545, loss: 0.0003051371604669839 2023-01-23 18:43:58.345394: step: 862/1545, loss: 0.0724782943725586 2023-01-23 18:43:59.194529: step: 864/1545, loss: 5.3995390771888196e-05 2023-01-23 18:44:00.079960: step: 866/1545, loss: 0.00014687937800772488 2023-01-23 18:44:00.951721: step: 868/1545, loss: 0.012526893056929111 2023-01-23 18:44:01.803533: step: 870/1545, loss: 0.000950089655816555 2023-01-23 18:44:02.676094: step: 872/1545, loss: 0.3604722023010254 2023-01-23 18:44:03.536202: step: 874/1545, loss: 3.665585973067209e-05 2023-01-23 18:44:04.392690: step: 876/1545, loss: 0.22289861738681793 2023-01-23 18:44:05.367813: step: 878/1545, loss: 0.052003294229507446 2023-01-23 18:44:06.222125: step: 880/1545, loss: 0.005923487711697817 2023-01-23 18:44:07.142093: step: 882/1545, loss: 0.0005525648593902588 2023-01-23 18:44:08.007195: step: 884/1545, loss: 5.113122097100131e-05 2023-01-23 18:44:08.860695: step: 886/1545, loss: 0.0038866812828928232 2023-01-23 18:44:09.769466: step: 888/1545, loss: 0.0006317301304079592 2023-01-23 18:44:10.672160: step: 890/1545, loss: 0.00023351958952844143 2023-01-23 18:44:11.524162: step: 892/1545, loss: 0.1679445058107376 2023-01-23 18:44:12.494363: step: 894/1545, loss: 0.0009235718753188848 2023-01-23 18:44:13.435996: step: 896/1545, loss: 0.10284166038036346 2023-01-23 18:44:14.334773: step: 898/1545, loss: 7.765483314869925e-05 2023-01-23 18:44:15.198972: step: 900/1545, loss: 0.006499958224594593 2023-01-23 18:44:16.106762: step: 902/1545, loss: 0.005527010653167963 2023-01-23 18:44:16.993095: step: 904/1545, loss: 0.00032330970861949027 2023-01-23 18:44:17.873809: step: 906/1545, loss: 0.012623665854334831 2023-01-23 18:44:18.736201: step: 908/1545, loss: 0.03906480595469475 2023-01-23 18:44:19.634086: step: 910/1545, loss: 0.0001143180561484769 2023-01-23 18:44:20.567915: step: 912/1545, loss: 0.10163942724466324 2023-01-23 18:44:21.444425: step: 914/1545, loss: 0.00011618480493780226 2023-01-23 18:44:22.360024: step: 916/1545, loss: 0.007876157760620117 2023-01-23 18:44:23.245451: step: 918/1545, loss: 0.00021219173504505306 2023-01-23 18:44:24.164745: step: 920/1545, loss: 0.012415547855198383 2023-01-23 18:44:25.006868: step: 922/1545, loss: 0.000367511878721416 2023-01-23 18:44:25.873649: step: 924/1545, loss: 0.041943736374378204 2023-01-23 18:44:26.778466: step: 926/1545, loss: 0.007074154447764158 2023-01-23 18:44:27.684853: step: 928/1545, loss: 0.27007490396499634 2023-01-23 18:44:28.578842: step: 930/1545, loss: 0.16222409904003143 2023-01-23 18:44:29.457348: step: 932/1545, loss: 5.265927757136524e-05 2023-01-23 18:44:30.334085: step: 934/1545, loss: 0.00011355935566825792 2023-01-23 18:44:31.179162: step: 936/1545, loss: 0.0006118380115367472 2023-01-23 18:44:32.085772: step: 938/1545, loss: 0.11687427759170532 2023-01-23 18:44:32.986858: step: 940/1545, loss: 0.0022376212291419506 2023-01-23 18:44:33.842540: step: 942/1545, loss: 0.20102238655090332 2023-01-23 18:44:34.730291: step: 944/1545, loss: 0.42620590329170227 2023-01-23 18:44:35.669980: step: 946/1545, loss: 0.003833301132544875 2023-01-23 18:44:36.571028: step: 948/1545, loss: 0.0007839290192350745 2023-01-23 18:44:37.448750: step: 950/1545, loss: 0.0004891231656074524 2023-01-23 18:44:38.298036: step: 952/1545, loss: 0.0023691714741289616 2023-01-23 18:44:39.221900: step: 954/1545, loss: 0.017760448157787323 2023-01-23 18:44:40.085447: step: 956/1545, loss: 0.0001701569854049012 2023-01-23 18:44:40.961433: step: 958/1545, loss: 0.002416962990537286 2023-01-23 18:44:41.850739: step: 960/1545, loss: 0.0019135321490466595 2023-01-23 18:44:42.664776: step: 962/1545, loss: 0.015658609569072723 2023-01-23 18:44:43.561507: step: 964/1545, loss: 0.0013247006572782993 2023-01-23 18:44:44.522407: step: 966/1545, loss: 0.08053433895111084 2023-01-23 18:44:45.413048: step: 968/1545, loss: 0.0006005229079164565 2023-01-23 18:44:46.274698: step: 970/1545, loss: 0.050359245389699936 2023-01-23 18:44:47.142086: step: 972/1545, loss: 0.013317063450813293 2023-01-23 18:44:48.089340: step: 974/1545, loss: 0.06915351003408432 2023-01-23 18:44:48.978398: step: 976/1545, loss: 0.0007053657318465412 2023-01-23 18:44:49.833759: step: 978/1545, loss: 0.025881286710500717 2023-01-23 18:44:50.709832: step: 980/1545, loss: 0.003221286693587899 2023-01-23 18:44:51.539748: step: 982/1545, loss: 0.0010763058671727777 2023-01-23 18:44:52.430770: step: 984/1545, loss: 0.2025134265422821 2023-01-23 18:44:53.287562: step: 986/1545, loss: 0.07277833670377731 2023-01-23 18:44:54.198471: step: 988/1545, loss: 0.07729419320821762 2023-01-23 18:44:55.062912: step: 990/1545, loss: 0.08244361728429794 2023-01-23 18:44:55.922145: step: 992/1545, loss: 0.006627583876252174 2023-01-23 18:44:56.864697: step: 994/1545, loss: 0.00233425828628242 2023-01-23 18:44:57.777444: step: 996/1545, loss: 0.09438227862119675 2023-01-23 18:44:58.680373: step: 998/1545, loss: 0.009821165353059769 2023-01-23 18:44:59.566930: step: 1000/1545, loss: 0.027254516258835793 2023-01-23 18:45:00.453494: step: 1002/1545, loss: 0.0021689385175704956 2023-01-23 18:45:01.345550: step: 1004/1545, loss: 0.003425037022680044 2023-01-23 18:45:02.245970: step: 1006/1545, loss: 0.011670375242829323 2023-01-23 18:45:03.117465: step: 1008/1545, loss: 0.0015571810072287917 2023-01-23 18:45:04.032165: step: 1010/1545, loss: 0.0012601485941559076 2023-01-23 18:45:04.952547: step: 1012/1545, loss: 0.12677963078022003 2023-01-23 18:45:05.834325: step: 1014/1545, loss: 0.03901617228984833 2023-01-23 18:45:06.701004: step: 1016/1545, loss: 0.005973688792437315 2023-01-23 18:45:07.601968: step: 1018/1545, loss: 0.004099654499441385 2023-01-23 18:45:08.477592: step: 1020/1545, loss: 0.0008074025390669703 2023-01-23 18:45:09.326796: step: 1022/1545, loss: 0.052698541432619095 2023-01-23 18:45:10.210498: step: 1024/1545, loss: 0.01512367743998766 2023-01-23 18:45:11.060448: step: 1026/1545, loss: 0.0017299260944128036 2023-01-23 18:45:11.897741: step: 1028/1545, loss: 0.08213332295417786 2023-01-23 18:45:12.848107: step: 1030/1545, loss: 0.05062979459762573 2023-01-23 18:45:13.708938: step: 1032/1545, loss: 0.002422280376777053 2023-01-23 18:45:14.619262: step: 1034/1545, loss: 0.006391534116119146 2023-01-23 18:45:15.552393: step: 1036/1545, loss: 0.436361163854599 2023-01-23 18:45:16.467052: step: 1038/1545, loss: 0.039494093507528305 2023-01-23 18:45:17.366889: step: 1040/1545, loss: 0.0036569354124367237 2023-01-23 18:45:18.217864: step: 1042/1545, loss: 0.05183281749486923 2023-01-23 18:45:19.067233: step: 1044/1545, loss: 0.0007691601058468223 2023-01-23 18:45:19.951260: step: 1046/1545, loss: 0.00137977150734514 2023-01-23 18:45:20.869709: step: 1048/1545, loss: 0.0005326082464307547 2023-01-23 18:45:21.748093: step: 1050/1545, loss: 0.00031061479239724576 2023-01-23 18:45:22.749103: step: 1052/1545, loss: 0.02073683589696884 2023-01-23 18:45:23.631501: step: 1054/1545, loss: 0.0066588884219527245 2023-01-23 18:45:24.522681: step: 1056/1545, loss: 0.14225740730762482 2023-01-23 18:45:25.385183: step: 1058/1545, loss: 0.001346357399597764 2023-01-23 18:45:26.280707: step: 1060/1545, loss: 0.03498830646276474 2023-01-23 18:45:27.172863: step: 1062/1545, loss: 0.007515754550695419 2023-01-23 18:45:28.048373: step: 1064/1545, loss: 0.04094128683209419 2023-01-23 18:45:28.894301: step: 1066/1545, loss: 0.1500677913427353 2023-01-23 18:45:29.771569: step: 1068/1545, loss: 0.00188758026342839 2023-01-23 18:45:30.675859: step: 1070/1545, loss: 0.003735366277396679 2023-01-23 18:45:31.554310: step: 1072/1545, loss: 0.0042829751037061214 2023-01-23 18:45:32.433414: step: 1074/1545, loss: 0.009863510727882385 2023-01-23 18:45:33.351382: step: 1076/1545, loss: 0.009138304740190506 2023-01-23 18:45:34.193737: step: 1078/1545, loss: 0.025290129706263542 2023-01-23 18:45:35.048814: step: 1080/1545, loss: 6.504207703983411e-05 2023-01-23 18:45:35.984839: step: 1082/1545, loss: 0.0003435520629864186 2023-01-23 18:45:36.901191: step: 1084/1545, loss: 0.005919297691434622 2023-01-23 18:45:37.838976: step: 1086/1545, loss: 0.0007710627396591008 2023-01-23 18:45:38.704207: step: 1088/1545, loss: 0.00014571826613973826 2023-01-23 18:45:39.547236: step: 1090/1545, loss: 0.09200309216976166 2023-01-23 18:45:40.388184: step: 1092/1545, loss: 0.12394262850284576 2023-01-23 18:45:41.214865: step: 1094/1545, loss: 0.9349454045295715 2023-01-23 18:45:42.151946: step: 1096/1545, loss: 0.3309294283390045 2023-01-23 18:45:43.013679: step: 1098/1545, loss: 0.00043484423076733947 2023-01-23 18:45:43.922283: step: 1100/1545, loss: 0.007245400920510292 2023-01-23 18:45:44.841847: step: 1102/1545, loss: 0.0030476581305265427 2023-01-23 18:45:45.715523: step: 1104/1545, loss: 0.001601067604497075 2023-01-23 18:45:46.597546: step: 1106/1545, loss: 0.00022754781821276993 2023-01-23 18:45:47.462729: step: 1108/1545, loss: 0.0015488811768591404 2023-01-23 18:45:48.323009: step: 1110/1545, loss: 0.004722208715975285 2023-01-23 18:45:49.173099: step: 1112/1545, loss: 3.194386954419315e-05 2023-01-23 18:45:50.074197: step: 1114/1545, loss: 0.000928327557630837 2023-01-23 18:45:50.976455: step: 1116/1545, loss: 0.004724081140011549 2023-01-23 18:45:51.861029: step: 1118/1545, loss: 0.003963812720030546 2023-01-23 18:45:52.766684: step: 1120/1545, loss: 7.114520121831447e-05 2023-01-23 18:45:53.641837: step: 1122/1545, loss: 3.157501123496331e-05 2023-01-23 18:45:54.540075: step: 1124/1545, loss: 0.00873302761465311 2023-01-23 18:45:55.462544: step: 1126/1545, loss: 0.00408305786550045 2023-01-23 18:45:56.389178: step: 1128/1545, loss: 0.1494980752468109 2023-01-23 18:45:57.277157: step: 1130/1545, loss: 0.10965922474861145 2023-01-23 18:45:58.173524: step: 1132/1545, loss: 0.008380848914384842 2023-01-23 18:45:59.129056: step: 1134/1545, loss: 0.03926607593894005 2023-01-23 18:46:00.044904: step: 1136/1545, loss: 0.015755921602249146 2023-01-23 18:46:00.883269: step: 1138/1545, loss: 0.0005376817425712943 2023-01-23 18:46:01.762382: step: 1140/1545, loss: 0.04387589171528816 2023-01-23 18:46:02.640860: step: 1142/1545, loss: 0.014269649051129818 2023-01-23 18:46:03.567160: step: 1144/1545, loss: 0.0009048199863173068 2023-01-23 18:46:04.448043: step: 1146/1545, loss: 0.05194767192006111 2023-01-23 18:46:05.314265: step: 1148/1545, loss: 7.992755126906559e-05 2023-01-23 18:46:06.153451: step: 1150/1545, loss: 0.0023905488196760416 2023-01-23 18:46:07.007175: step: 1152/1545, loss: 0.010769522748887539 2023-01-23 18:46:07.839294: step: 1154/1545, loss: 0.0011841156519949436 2023-01-23 18:46:08.704051: step: 1156/1545, loss: 0.03042260743677616 2023-01-23 18:46:09.569786: step: 1158/1545, loss: 0.00011745867959689349 2023-01-23 18:46:10.467403: step: 1160/1545, loss: 0.001072661834768951 2023-01-23 18:46:11.382225: step: 1162/1545, loss: 0.2287103682756424 2023-01-23 18:46:12.258001: step: 1164/1545, loss: 0.002162754535675049 2023-01-23 18:46:13.112456: step: 1166/1545, loss: 0.036036167293787 2023-01-23 18:46:13.995176: step: 1168/1545, loss: 0.0010095132747665048 2023-01-23 18:46:14.835794: step: 1170/1545, loss: 0.0032486848067492247 2023-01-23 18:46:15.700036: step: 1172/1545, loss: 0.0023459955118596554 2023-01-23 18:46:16.563682: step: 1174/1545, loss: 0.001723935129120946 2023-01-23 18:46:17.509739: step: 1176/1545, loss: 0.017883621156215668 2023-01-23 18:46:18.364868: step: 1178/1545, loss: 0.0003894252295140177 2023-01-23 18:46:19.224251: step: 1180/1545, loss: 0.017423084005713463 2023-01-23 18:46:20.116629: step: 1182/1545, loss: 0.002299051731824875 2023-01-23 18:46:21.021079: step: 1184/1545, loss: 0.014624757692217827 2023-01-23 18:46:21.945308: step: 1186/1545, loss: 0.2345188856124878 2023-01-23 18:46:22.840972: step: 1188/1545, loss: 0.0005670986138284206 2023-01-23 18:46:23.714863: step: 1190/1545, loss: 0.05168740823864937 2023-01-23 18:46:24.598061: step: 1192/1545, loss: 0.0009835399687290192 2023-01-23 18:46:25.464265: step: 1194/1545, loss: 0.25071245431900024 2023-01-23 18:46:26.311060: step: 1196/1545, loss: 0.0007312147063203156 2023-01-23 18:46:27.173209: step: 1198/1545, loss: 0.00039057928370311856 2023-01-23 18:46:28.047563: step: 1200/1545, loss: 0.1374334692955017 2023-01-23 18:46:28.917323: step: 1202/1545, loss: 0.3498929440975189 2023-01-23 18:46:29.815079: step: 1204/1545, loss: 0.00024743672111071646 2023-01-23 18:46:30.776056: step: 1206/1545, loss: 0.08682218939065933 2023-01-23 18:46:31.668909: step: 1208/1545, loss: 0.009613496251404285 2023-01-23 18:46:32.629483: step: 1210/1545, loss: 0.21655812859535217 2023-01-23 18:46:33.580736: step: 1212/1545, loss: 0.002261415123939514 2023-01-23 18:46:34.494621: step: 1214/1545, loss: 0.2110251933336258 2023-01-23 18:46:35.348701: step: 1216/1545, loss: 0.042751602828502655 2023-01-23 18:46:36.253914: step: 1218/1545, loss: 0.0012888795463368297 2023-01-23 18:46:37.188036: step: 1220/1545, loss: 0.011796661652624607 2023-01-23 18:46:38.061856: step: 1222/1545, loss: 0.025667060166597366 2023-01-23 18:46:38.961498: step: 1224/1545, loss: 0.010061769746243954 2023-01-23 18:46:39.804163: step: 1226/1545, loss: 0.00037683924892917275 2023-01-23 18:46:40.727122: step: 1228/1545, loss: 0.07351391017436981 2023-01-23 18:46:41.605048: step: 1230/1545, loss: 0.012577760964632034 2023-01-23 18:46:42.451015: step: 1232/1545, loss: 0.0026735481806099415 2023-01-23 18:46:43.369461: step: 1234/1545, loss: 9.870437497738749e-05 2023-01-23 18:46:44.265872: step: 1236/1545, loss: 0.1352788507938385 2023-01-23 18:46:45.160011: step: 1238/1545, loss: 0.048849400132894516 2023-01-23 18:46:46.053361: step: 1240/1545, loss: 4.6899043809389696e-05 2023-01-23 18:46:46.953769: step: 1242/1545, loss: 0.00308983214199543 2023-01-23 18:46:47.807697: step: 1244/1545, loss: 0.00020873875473625958 2023-01-23 18:46:48.704788: step: 1246/1545, loss: 0.009557828307151794 2023-01-23 18:46:49.626700: step: 1248/1545, loss: 0.0007898472831584513 2023-01-23 18:46:50.478838: step: 1250/1545, loss: 0.0010252618230879307 2023-01-23 18:46:51.404729: step: 1252/1545, loss: 0.01861652359366417 2023-01-23 18:46:52.339838: step: 1254/1545, loss: 0.0208890400826931 2023-01-23 18:46:53.277646: step: 1256/1545, loss: 0.0816040188074112 2023-01-23 18:46:54.147949: step: 1258/1545, loss: 0.0005203208420425653 2023-01-23 18:46:55.004774: step: 1260/1545, loss: 0.003093367675319314 2023-01-23 18:46:55.927255: step: 1262/1545, loss: 0.00012619691551662982 2023-01-23 18:46:56.773589: step: 1264/1545, loss: 0.004451910499483347 2023-01-23 18:46:57.675754: step: 1266/1545, loss: 0.2777988612651825 2023-01-23 18:46:58.538171: step: 1268/1545, loss: 0.0006057154387235641 2023-01-23 18:46:59.435824: step: 1270/1545, loss: 0.11091291904449463 2023-01-23 18:47:00.318594: step: 1272/1545, loss: 0.0007208471652120352 2023-01-23 18:47:01.187410: step: 1274/1545, loss: 0.22678598761558533 2023-01-23 18:47:02.035908: step: 1276/1545, loss: 0.004991529043763876 2023-01-23 18:47:02.904187: step: 1278/1545, loss: 0.000940715370234102 2023-01-23 18:47:03.760316: step: 1280/1545, loss: 0.01780829206109047 2023-01-23 18:47:04.669602: step: 1282/1545, loss: 0.0007463037618435919 2023-01-23 18:47:05.603753: step: 1284/1545, loss: 0.06810580939054489 2023-01-23 18:47:06.444363: step: 1286/1545, loss: 0.0004948973655700684 2023-01-23 18:47:07.356364: step: 1288/1545, loss: 0.0019282647408545017 2023-01-23 18:47:08.278031: step: 1290/1545, loss: 0.011981245130300522 2023-01-23 18:47:09.135696: step: 1292/1545, loss: 0.0023204111494123936 2023-01-23 18:47:09.970090: step: 1294/1545, loss: 0.10622799396514893 2023-01-23 18:47:10.879863: step: 1296/1545, loss: 0.00026765631628222764 2023-01-23 18:47:11.809023: step: 1298/1545, loss: 2.480304829077795e-05 2023-01-23 18:47:12.712655: step: 1300/1545, loss: 0.09285620599985123 2023-01-23 18:47:13.626113: step: 1302/1545, loss: 0.05981646850705147 2023-01-23 18:47:14.475197: step: 1304/1545, loss: 0.21620307862758636 2023-01-23 18:47:15.371994: step: 1306/1545, loss: 0.01746509224176407 2023-01-23 18:47:16.236218: step: 1308/1545, loss: 0.05253464728593826 2023-01-23 18:47:17.125053: step: 1310/1545, loss: 0.010629101656377316 2023-01-23 18:47:18.042523: step: 1312/1545, loss: 0.09437867999076843 2023-01-23 18:47:18.855233: step: 1314/1545, loss: 0.043360743671655655 2023-01-23 18:47:19.754439: step: 1316/1545, loss: 0.01708845980465412 2023-01-23 18:47:20.617894: step: 1318/1545, loss: 0.002303080167621374 2023-01-23 18:47:21.485593: step: 1320/1545, loss: 3.148516043438576e-05 2023-01-23 18:47:22.345181: step: 1322/1545, loss: 2.134181522706058e-05 2023-01-23 18:47:23.229228: step: 1324/1545, loss: 0.5656956434249878 2023-01-23 18:47:24.157346: step: 1326/1545, loss: 0.1446664035320282 2023-01-23 18:47:25.019671: step: 1328/1545, loss: 0.00125647964887321 2023-01-23 18:47:25.911773: step: 1330/1545, loss: 0.00027850898914039135 2023-01-23 18:47:26.780877: step: 1332/1545, loss: 0.000799076515249908 2023-01-23 18:47:27.710559: step: 1334/1545, loss: 0.1059245616197586 2023-01-23 18:47:28.579783: step: 1336/1545, loss: 0.02786676213145256 2023-01-23 18:47:29.473120: step: 1338/1545, loss: 0.000254238024353981 2023-01-23 18:47:30.320925: step: 1340/1545, loss: 0.004609497729688883 2023-01-23 18:47:31.175885: step: 1342/1545, loss: 0.00018070782243739814 2023-01-23 18:47:32.012921: step: 1344/1545, loss: 0.00023227836936712265 2023-01-23 18:47:32.882153: step: 1346/1545, loss: 0.08590410649776459 2023-01-23 18:47:33.733714: step: 1348/1545, loss: 0.0021943915635347366 2023-01-23 18:47:34.587334: step: 1350/1545, loss: 0.40145424008369446 2023-01-23 18:47:35.455190: step: 1352/1545, loss: 0.02320234291255474 2023-01-23 18:47:36.357558: step: 1354/1545, loss: 0.004018830601125956 2023-01-23 18:47:37.248855: step: 1356/1545, loss: 0.0002520777634344995 2023-01-23 18:47:38.094332: step: 1358/1545, loss: 0.0051152948290109634 2023-01-23 18:47:39.010724: step: 1360/1545, loss: 0.03374260291457176 2023-01-23 18:47:39.871819: step: 1362/1545, loss: 0.07392014563083649 2023-01-23 18:47:40.778634: step: 1364/1545, loss: 0.032390695065259933 2023-01-23 18:47:41.633773: step: 1366/1545, loss: 0.0004612871562130749 2023-01-23 18:47:42.509095: step: 1368/1545, loss: 0.0006695089978165925 2023-01-23 18:47:43.392203: step: 1370/1545, loss: 0.0001143784902524203 2023-01-23 18:47:44.277385: step: 1372/1545, loss: 0.024857502430677414 2023-01-23 18:47:45.126322: step: 1374/1545, loss: 0.030568132176995277 2023-01-23 18:47:46.052236: step: 1376/1545, loss: 0.10672269016504288 2023-01-23 18:47:46.901081: step: 1378/1545, loss: 0.0015209396369755268 2023-01-23 18:47:47.808775: step: 1380/1545, loss: 0.0013715075328946114 2023-01-23 18:47:48.675768: step: 1382/1545, loss: 0.0002038732054643333 2023-01-23 18:47:49.631969: step: 1384/1545, loss: 0.00012423237785696983 2023-01-23 18:47:50.543105: step: 1386/1545, loss: 0.0005597948911599815 2023-01-23 18:47:51.405477: step: 1388/1545, loss: 0.00016418150335084647 2023-01-23 18:47:52.296671: step: 1390/1545, loss: -1.8717846614890732e-05 2023-01-23 18:47:53.178325: step: 1392/1545, loss: 0.00018796903896145523 2023-01-23 18:47:54.052119: step: 1394/1545, loss: 0.0011386799160391092 2023-01-23 18:47:54.956950: step: 1396/1545, loss: 0.000624573091045022 2023-01-23 18:47:55.856728: step: 1398/1545, loss: 0.00028367096092551947 2023-01-23 18:47:56.756852: step: 1400/1545, loss: 0.0008729782421141863 2023-01-23 18:47:57.621454: step: 1402/1545, loss: 0.0017707247752696276 2023-01-23 18:47:58.531885: step: 1404/1545, loss: 0.1322600543498993 2023-01-23 18:47:59.408734: step: 1406/1545, loss: 2.021789623540826e-05 2023-01-23 18:48:00.295600: step: 1408/1545, loss: 0.0001369876554235816 2023-01-23 18:48:01.170415: step: 1410/1545, loss: 0.05019984021782875 2023-01-23 18:48:02.022920: step: 1412/1545, loss: 0.007496572099626064 2023-01-23 18:48:02.916187: step: 1414/1545, loss: 2.094953742926009e-05 2023-01-23 18:48:03.809596: step: 1416/1545, loss: 0.006906556431204081 2023-01-23 18:48:04.680356: step: 1418/1545, loss: 0.000260299100773409 2023-01-23 18:48:05.551857: step: 1420/1545, loss: 0.0420006588101387 2023-01-23 18:48:06.463410: step: 1422/1545, loss: 0.0015470081707462668 2023-01-23 18:48:07.373135: step: 1424/1545, loss: 0.6254522204399109 2023-01-23 18:48:08.247346: step: 1426/1545, loss: 0.07689531147480011 2023-01-23 18:48:09.196829: step: 1428/1545, loss: 0.0002795153995975852 2023-01-23 18:48:10.101749: step: 1430/1545, loss: 0.0011484171263873577 2023-01-23 18:48:11.019318: step: 1432/1545, loss: 0.2330581098794937 2023-01-23 18:48:11.941681: step: 1434/1545, loss: 0.00020781412604264915 2023-01-23 18:48:12.848859: step: 1436/1545, loss: 0.006398383993655443 2023-01-23 18:48:13.719314: step: 1438/1545, loss: 0.03968146815896034 2023-01-23 18:48:14.624446: step: 1440/1545, loss: 0.0011683605844154954 2023-01-23 18:48:15.500666: step: 1442/1545, loss: 0.007778582163155079 2023-01-23 18:48:16.386419: step: 1444/1545, loss: 0.013189143501222134 2023-01-23 18:48:17.222672: step: 1446/1545, loss: 0.0697033703327179 2023-01-23 18:48:18.120418: step: 1448/1545, loss: 0.3298364579677582 2023-01-23 18:48:19.024224: step: 1450/1545, loss: 0.4740390479564667 2023-01-23 18:48:19.884494: step: 1452/1545, loss: 0.000888911890797317 2023-01-23 18:48:20.828543: step: 1454/1545, loss: 0.11438868939876556 2023-01-23 18:48:21.730630: step: 1456/1545, loss: 0.0019692634232342243 2023-01-23 18:48:22.590012: step: 1458/1545, loss: 0.07069480419158936 2023-01-23 18:48:23.438822: step: 1460/1545, loss: 6.156022664072225e-06 2023-01-23 18:48:24.331544: step: 1462/1545, loss: 0.2781297266483307 2023-01-23 18:48:25.219924: step: 1464/1545, loss: 0.22412224113941193 2023-01-23 18:48:26.122848: step: 1466/1545, loss: 2.867860166588798e-05 2023-01-23 18:48:27.049019: step: 1468/1545, loss: 0.08213318884372711 2023-01-23 18:48:27.896736: step: 1470/1545, loss: 0.041365835815668106 2023-01-23 18:48:28.777785: step: 1472/1545, loss: 0.06332693994045258 2023-01-23 18:48:29.656243: step: 1474/1545, loss: 0.001132932142354548 2023-01-23 18:48:30.556141: step: 1476/1545, loss: 0.10545811057090759 2023-01-23 18:48:31.406434: step: 1478/1545, loss: 0.0006282229442149401 2023-01-23 18:48:32.294354: step: 1480/1545, loss: 0.0001929342543007806 2023-01-23 18:48:33.176245: step: 1482/1545, loss: 0.4255326986312866 2023-01-23 18:48:34.054822: step: 1484/1545, loss: 6.930161907803267e-05 2023-01-23 18:48:34.947490: step: 1486/1545, loss: 0.0005561561556532979 2023-01-23 18:48:35.875556: step: 1488/1545, loss: 0.004387345630675554 2023-01-23 18:48:36.751036: step: 1490/1545, loss: 3.8489699363708496e-05 2023-01-23 18:48:37.623421: step: 1492/1545, loss: 0.021653220057487488 2023-01-23 18:48:38.477266: step: 1494/1545, loss: 0.0048522911965847015 2023-01-23 18:48:39.450173: step: 1496/1545, loss: 0.008412002585828304 2023-01-23 18:48:40.330526: step: 1498/1545, loss: 8.325780072482303e-05 2023-01-23 18:48:41.188262: step: 1500/1545, loss: 0.02057957835495472 2023-01-23 18:48:42.065955: step: 1502/1545, loss: 0.0004380721948109567 2023-01-23 18:48:42.942463: step: 1504/1545, loss: 0.0740688145160675 2023-01-23 18:48:43.845329: step: 1506/1545, loss: 0.03234052285552025 2023-01-23 18:48:44.727669: step: 1508/1545, loss: 0.0073505849577486515 2023-01-23 18:48:45.611094: step: 1510/1545, loss: 0.009439997375011444 2023-01-23 18:48:46.514877: step: 1512/1545, loss: 0.0003708217991515994 2023-01-23 18:48:47.363750: step: 1514/1545, loss: 0.0026884896215051413 2023-01-23 18:48:48.224353: step: 1516/1545, loss: 0.01886654458940029 2023-01-23 18:48:49.072790: step: 1518/1545, loss: 6.25811026111478e-06 2023-01-23 18:48:50.001527: step: 1520/1545, loss: 0.07760180532932281 2023-01-23 18:48:50.896723: step: 1522/1545, loss: 0.08124735206365585 2023-01-23 18:48:51.766556: step: 1524/1545, loss: 0.6704054474830627 2023-01-23 18:48:52.629595: step: 1526/1545, loss: 0.0004986777785234153 2023-01-23 18:48:53.536040: step: 1528/1545, loss: 0.04754365608096123 2023-01-23 18:48:54.426029: step: 1530/1545, loss: 0.0006081149913370609 2023-01-23 18:48:55.333215: step: 1532/1545, loss: 0.002749973675236106 2023-01-23 18:48:56.261661: step: 1534/1545, loss: 0.0203878041356802 2023-01-23 18:48:57.118359: step: 1536/1545, loss: 0.002972654066979885 2023-01-23 18:48:57.967155: step: 1538/1545, loss: 0.0005201614694669843 2023-01-23 18:48:58.799231: step: 1540/1545, loss: 0.12604911625385284 2023-01-23 18:48:59.738795: step: 1542/1545, loss: 0.0006648172275163233 2023-01-23 18:49:00.615419: step: 1544/1545, loss: 0.06844335049390793 2023-01-23 18:49:01.571136: step: 1546/1545, loss: 0.06528929620981216 2023-01-23 18:49:02.424346: step: 1548/1545, loss: 0.0040990994311869144 2023-01-23 18:49:03.290598: step: 1550/1545, loss: 0.0006367367459461093 2023-01-23 18:49:04.224004: step: 1552/1545, loss: 0.0012912200763821602 2023-01-23 18:49:05.083249: step: 1554/1545, loss: 0.005059841088950634 2023-01-23 18:49:05.953082: step: 1556/1545, loss: 0.0028024616185575724 2023-01-23 18:49:06.802995: step: 1558/1545, loss: 0.08942756801843643 2023-01-23 18:49:07.699647: step: 1560/1545, loss: 0.11294174939393997 2023-01-23 18:49:08.579724: step: 1562/1545, loss: 0.008952450938522816 2023-01-23 18:49:09.478724: step: 1564/1545, loss: 0.005853540264070034 2023-01-23 18:49:10.349705: step: 1566/1545, loss: 0.0024047470651566982 2023-01-23 18:49:11.302798: step: 1568/1545, loss: 0.10093022137880325 2023-01-23 18:49:12.157625: step: 1570/1545, loss: 0.06738217175006866 2023-01-23 18:49:13.032908: step: 1572/1545, loss: 0.12599219381809235 2023-01-23 18:49:13.906099: step: 1574/1545, loss: 0.0011882692342624068 2023-01-23 18:49:14.840984: step: 1576/1545, loss: 0.290486216545105 2023-01-23 18:49:15.737495: step: 1578/1545, loss: 0.14777539670467377 2023-01-23 18:49:16.590891: step: 1580/1545, loss: 0.0010341864544898272 2023-01-23 18:49:17.462049: step: 1582/1545, loss: 0.12147675454616547 2023-01-23 18:49:18.326168: step: 1584/1545, loss: 0.0018792487680912018 2023-01-23 18:49:19.218935: step: 1586/1545, loss: 0.01148089487105608 2023-01-23 18:49:20.109853: step: 1588/1545, loss: 0.008429894223809242 2023-01-23 18:49:20.981067: step: 1590/1545, loss: 0.00034161345683969557 2023-01-23 18:49:21.820372: step: 1592/1545, loss: 0.00021249111159704626 2023-01-23 18:49:22.715348: step: 1594/1545, loss: 0.03647089749574661 2023-01-23 18:49:23.588741: step: 1596/1545, loss: 0.39439547061920166 2023-01-23 18:49:24.445668: step: 1598/1545, loss: 0.027039671316742897 2023-01-23 18:49:25.329903: step: 1600/1545, loss: 0.7648655772209167 2023-01-23 18:49:26.231385: step: 1602/1545, loss: 0.002126521896570921 2023-01-23 18:49:27.139482: step: 1604/1545, loss: 0.006118558347225189 2023-01-23 18:49:28.012563: step: 1606/1545, loss: 0.10809510201215744 2023-01-23 18:49:28.885824: step: 1608/1545, loss: 0.0031443838961422443 2023-01-23 18:49:29.709516: step: 1610/1545, loss: 0.0033884213771671057 2023-01-23 18:49:30.579834: step: 1612/1545, loss: 0.0001179202226921916 2023-01-23 18:49:31.446141: step: 1614/1545, loss: 0.0008193954126909375 2023-01-23 18:49:32.385778: step: 1616/1545, loss: 0.00014660692249890417 2023-01-23 18:49:33.245304: step: 1618/1545, loss: 0.02260814979672432 2023-01-23 18:49:34.140243: step: 1620/1545, loss: 0.1659105271100998 2023-01-23 18:49:35.051491: step: 1622/1545, loss: 0.08753561973571777 2023-01-23 18:49:35.936665: step: 1624/1545, loss: 0.24782025814056396 2023-01-23 18:49:36.844180: step: 1626/1545, loss: 0.0014853766188025475 2023-01-23 18:49:37.717228: step: 1628/1545, loss: 0.004010041244328022 2023-01-23 18:49:38.580655: step: 1630/1545, loss: 0.15392476320266724 2023-01-23 18:49:39.479334: step: 1632/1545, loss: 0.0011374872410669923 2023-01-23 18:49:40.347067: step: 1634/1545, loss: 0.001937155146151781 2023-01-23 18:49:41.202664: step: 1636/1545, loss: 0.0003523712221067399 2023-01-23 18:49:42.065122: step: 1638/1545, loss: 0.0024397417437285185 2023-01-23 18:49:42.979086: step: 1640/1545, loss: 0.01115267351269722 2023-01-23 18:49:43.884560: step: 1642/1545, loss: 0.0025009596720337868 2023-01-23 18:49:44.826803: step: 1644/1545, loss: 0.00013500898785423487 2023-01-23 18:49:45.696122: step: 1646/1545, loss: 0.014249530620872974 2023-01-23 18:49:46.568457: step: 1648/1545, loss: 0.001527064829133451 2023-01-23 18:49:47.423949: step: 1650/1545, loss: 0.0042777894996106625 2023-01-23 18:49:48.293174: step: 1652/1545, loss: 0.0007460861233994365 2023-01-23 18:49:49.223255: step: 1654/1545, loss: 0.09248770028352737 2023-01-23 18:49:50.102171: step: 1656/1545, loss: 0.000514094193931669 2023-01-23 18:49:50.996721: step: 1658/1545, loss: 0.02066010609269142 2023-01-23 18:49:51.894310: step: 1660/1545, loss: 0.04063187912106514 2023-01-23 18:49:52.820776: step: 1662/1545, loss: 0.49556994438171387 2023-01-23 18:49:53.703695: step: 1664/1545, loss: 0.0036130354274064302 2023-01-23 18:49:54.530696: step: 1666/1545, loss: 0.010460332036018372 2023-01-23 18:49:55.411093: step: 1668/1545, loss: 0.05346857011318207 2023-01-23 18:49:56.249298: step: 1670/1545, loss: 0.001437745289877057 2023-01-23 18:49:57.124781: step: 1672/1545, loss: 0.006624570116400719 2023-01-23 18:49:58.003831: step: 1674/1545, loss: 0.2709190845489502 2023-01-23 18:49:58.878337: step: 1676/1545, loss: 0.0014578122645616531 2023-01-23 18:49:59.760030: step: 1678/1545, loss: 0.001379102934151888 2023-01-23 18:50:00.649104: step: 1680/1545, loss: 1.8073307275772095 2023-01-23 18:50:01.539781: step: 1682/1545, loss: 0.0005740204360336065 2023-01-23 18:50:02.396985: step: 1684/1545, loss: 0.0006098664598539472 2023-01-23 18:50:03.292073: step: 1686/1545, loss: 0.20231321454048157 2023-01-23 18:50:04.197633: step: 1688/1545, loss: 0.0845986008644104 2023-01-23 18:50:05.082564: step: 1690/1545, loss: 0.018399540334939957 2023-01-23 18:50:05.968294: step: 1692/1545, loss: 0.006594448816031218 2023-01-23 18:50:06.820626: step: 1694/1545, loss: 0.0025603154208511114 2023-01-23 18:50:07.677790: step: 1696/1545, loss: 0.000786133692599833 2023-01-23 18:50:08.534938: step: 1698/1545, loss: 0.00664815166965127 2023-01-23 18:50:09.407916: step: 1700/1545, loss: 0.015667129307985306 2023-01-23 18:50:10.287609: step: 1702/1545, loss: 0.28876185417175293 2023-01-23 18:50:11.157782: step: 1704/1545, loss: 0.003119983710348606 2023-01-23 18:50:12.038557: step: 1706/1545, loss: 0.018282586708664894 2023-01-23 18:50:12.957713: step: 1708/1545, loss: 2.8102545911679044e-05 2023-01-23 18:50:13.799382: step: 1710/1545, loss: 0.001727021299302578 2023-01-23 18:50:14.646261: step: 1712/1545, loss: 0.14999382197856903 2023-01-23 18:50:15.534135: step: 1714/1545, loss: 0.002284906804561615 2023-01-23 18:50:16.473057: step: 1716/1545, loss: 6.41564474790357e-05 2023-01-23 18:50:17.377173: step: 1718/1545, loss: 0.003047919599339366 2023-01-23 18:50:18.293531: step: 1720/1545, loss: 0.00010092064621858299 2023-01-23 18:50:19.133306: step: 1722/1545, loss: 0.23143258690834045 2023-01-23 18:50:20.014331: step: 1724/1545, loss: 0.41667184233665466 2023-01-23 18:50:20.930528: step: 1726/1545, loss: 0.0011993634980171919 2023-01-23 18:50:21.843852: step: 1728/1545, loss: 0.027621129527688026 2023-01-23 18:50:22.744149: step: 1730/1545, loss: 0.01010559219866991 2023-01-23 18:50:23.666139: step: 1732/1545, loss: 0.00015879403508733958 2023-01-23 18:50:24.574735: step: 1734/1545, loss: 0.08530868589878082 2023-01-23 18:50:25.457603: step: 1736/1545, loss: 0.036373790353536606 2023-01-23 18:50:26.377993: step: 1738/1545, loss: 0.0005285728839226067 2023-01-23 18:50:27.237574: step: 1740/1545, loss: 0.00011615866969805211 2023-01-23 18:50:28.174970: step: 1742/1545, loss: 0.0017389405984431505 2023-01-23 18:50:29.036390: step: 1744/1545, loss: 0.017405541613698006 2023-01-23 18:50:29.907396: step: 1746/1545, loss: 0.0043404316529631615 2023-01-23 18:50:30.778180: step: 1748/1545, loss: -8.455304850940593e-06 2023-01-23 18:50:31.682761: step: 1750/1545, loss: 0.0012038146378472447 2023-01-23 18:50:32.528596: step: 1752/1545, loss: 0.01879655010998249 2023-01-23 18:50:33.381128: step: 1754/1545, loss: 0.0004856226150877774 2023-01-23 18:50:34.241358: step: 1756/1545, loss: 0.0011064986465498805 2023-01-23 18:50:35.081163: step: 1758/1545, loss: 0.000987529056146741 2023-01-23 18:50:35.938723: step: 1760/1545, loss: 0.047426432371139526 2023-01-23 18:50:36.831289: step: 1762/1545, loss: 0.028659077361226082 2023-01-23 18:50:37.688548: step: 1764/1545, loss: 0.07137764245271683 2023-01-23 18:50:38.509985: step: 1766/1545, loss: 0.000598027603700757 2023-01-23 18:50:39.456312: step: 1768/1545, loss: 0.003213169751688838 2023-01-23 18:50:40.290671: step: 1770/1545, loss: 0.00010854480933630839 2023-01-23 18:50:41.231514: step: 1772/1545, loss: 0.02096019685268402 2023-01-23 18:50:42.148061: step: 1774/1545, loss: 4.4990130845690146e-05 2023-01-23 18:50:43.001876: step: 1776/1545, loss: 0.0007103026728145778 2023-01-23 18:50:43.870801: step: 1778/1545, loss: 0.02031048759818077 2023-01-23 18:50:44.872449: step: 1780/1545, loss: 0.2299344539642334 2023-01-23 18:50:45.754750: step: 1782/1545, loss: 0.18614934384822845 2023-01-23 18:50:46.671123: step: 1784/1545, loss: 0.4149211645126343 2023-01-23 18:50:47.579263: step: 1786/1545, loss: 0.08791626244783401 2023-01-23 18:50:48.460469: step: 1788/1545, loss: 0.11610394716262817 2023-01-23 18:50:49.334442: step: 1790/1545, loss: 0.0017245362978428602 2023-01-23 18:50:50.225002: step: 1792/1545, loss: 0.2972378432750702 2023-01-23 18:50:51.114980: step: 1794/1545, loss: 0.00027040898567065597 2023-01-23 18:50:52.049324: step: 1796/1545, loss: 0.007578688208013773 2023-01-23 18:50:52.953548: step: 1798/1545, loss: 0.009943636134266853 2023-01-23 18:50:53.829339: step: 1800/1545, loss: 0.011866484768688679 2023-01-23 18:50:54.692984: step: 1802/1545, loss: 0.42036357522010803 2023-01-23 18:50:55.599036: step: 1804/1545, loss: 0.0008582013542763889 2023-01-23 18:50:56.502336: step: 1806/1545, loss: 0.001243257662281394 2023-01-23 18:50:57.392364: step: 1808/1545, loss: 0.1761786788702011 2023-01-23 18:50:58.250998: step: 1810/1545, loss: 0.0006705345585942268 2023-01-23 18:50:59.159265: step: 1812/1545, loss: 0.002315900754183531 2023-01-23 18:51:00.035900: step: 1814/1545, loss: 0.09059605747461319 2023-01-23 18:51:00.897221: step: 1816/1545, loss: 0.21112367510795593 2023-01-23 18:51:01.771554: step: 1818/1545, loss: 0.08518532663583755 2023-01-23 18:51:02.610490: step: 1820/1545, loss: 0.0007390729151666164 2023-01-23 18:51:03.550595: step: 1822/1545, loss: 0.0025165861006826162 2023-01-23 18:51:04.390787: step: 1824/1545, loss: 0.00020088638120796531 2023-01-23 18:51:05.279548: step: 1826/1545, loss: 0.0005818214849568903 2023-01-23 18:51:06.134043: step: 1828/1545, loss: 0.1783939003944397 2023-01-23 18:51:06.999378: step: 1830/1545, loss: 0.051305726170539856 2023-01-23 18:51:07.933209: step: 1832/1545, loss: 0.0711977556347847 2023-01-23 18:51:08.802549: step: 1834/1545, loss: 0.000950163637753576 2023-01-23 18:51:09.739625: step: 1836/1545, loss: 3.6086643376620486e-05 2023-01-23 18:51:10.559431: step: 1838/1545, loss: 8.355674799531698e-05 2023-01-23 18:51:11.462760: step: 1840/1545, loss: 0.0009498748113401234 2023-01-23 18:51:12.334992: step: 1842/1545, loss: 0.00538115669041872 2023-01-23 18:51:13.192149: step: 1844/1545, loss: 0.4791420102119446 2023-01-23 18:51:14.111403: step: 1846/1545, loss: 0.0005418832297436893 2023-01-23 18:51:14.991432: step: 1848/1545, loss: 0.10926809906959534 2023-01-23 18:51:15.941515: step: 1850/1545, loss: 0.025370264425873756 2023-01-23 18:51:16.788332: step: 1852/1545, loss: 0.0017568324692547321 2023-01-23 18:51:17.625823: step: 1854/1545, loss: 0.11867599934339523 2023-01-23 18:51:18.486327: step: 1856/1545, loss: 0.00737712811678648 2023-01-23 18:51:19.417052: step: 1858/1545, loss: 0.002614544238895178 2023-01-23 18:51:20.261861: step: 1860/1545, loss: 0.001788451336324215 2023-01-23 18:51:21.131515: step: 1862/1545, loss: 0.061232663691043854 2023-01-23 18:51:22.049787: step: 1864/1545, loss: 0.0179950799793005 2023-01-23 18:51:23.051397: step: 1866/1545, loss: 0.02621319331228733 2023-01-23 18:51:23.901454: step: 1868/1545, loss: 0.0451938658952713 2023-01-23 18:51:24.779303: step: 1870/1545, loss: 0.4660818874835968 2023-01-23 18:51:25.644667: step: 1872/1545, loss: 0.0013228007592260838 2023-01-23 18:51:26.561896: step: 1874/1545, loss: 0.00540839834138751 2023-01-23 18:51:27.454591: step: 1876/1545, loss: 0.0043497234582901 2023-01-23 18:51:28.332510: step: 1878/1545, loss: 0.08600281924009323 2023-01-23 18:51:29.256707: step: 1880/1545, loss: 0.12602563202381134 2023-01-23 18:51:30.158836: step: 1882/1545, loss: 0.00029891851590946317 2023-01-23 18:51:31.024706: step: 1884/1545, loss: 0.3381046652793884 2023-01-23 18:51:31.921716: step: 1886/1545, loss: 0.0003629719722084701 2023-01-23 18:51:32.795844: step: 1888/1545, loss: 0.00047506188275292516 2023-01-23 18:51:33.755849: step: 1890/1545, loss: 0.0014678941806778312 2023-01-23 18:51:34.638398: step: 1892/1545, loss: 0.013615014031529427 2023-01-23 18:51:35.544273: step: 1894/1545, loss: 0.12268966436386108 2023-01-23 18:51:36.489791: step: 1896/1545, loss: 0.002470170147716999 2023-01-23 18:51:37.344428: step: 1898/1545, loss: 0.0050373985432088375 2023-01-23 18:51:38.218906: step: 1900/1545, loss: 0.006774798035621643 2023-01-23 18:51:39.051618: step: 1902/1545, loss: 0.00019017858721781522 2023-01-23 18:51:39.892828: step: 1904/1545, loss: 0.0006842428119853139 2023-01-23 18:51:40.789281: step: 1906/1545, loss: 0.0006791457417421043 2023-01-23 18:51:41.645995: step: 1908/1545, loss: 0.011149701662361622 2023-01-23 18:51:42.518144: step: 1910/1545, loss: 0.01075406838208437 2023-01-23 18:51:43.384016: step: 1912/1545, loss: 0.0060197715647518635 2023-01-23 18:51:44.312123: step: 1914/1545, loss: 0.049323178827762604 2023-01-23 18:51:45.141314: step: 1916/1545, loss: 0.021035904064774513 2023-01-23 18:51:46.033154: step: 1918/1545, loss: 0.00036138674477115273 2023-01-23 18:51:46.920561: step: 1920/1545, loss: 0.0014321557246148586 2023-01-23 18:51:47.816715: step: 1922/1545, loss: 0.000253881182288751 2023-01-23 18:51:48.716581: step: 1924/1545, loss: 0.06773144006729126 2023-01-23 18:51:49.615479: step: 1926/1545, loss: 0.03170411288738251 2023-01-23 18:51:50.509664: step: 1928/1545, loss: 0.008131043054163456 2023-01-23 18:51:51.371030: step: 1930/1545, loss: 0.00011601779260672629 2023-01-23 18:51:52.248449: step: 1932/1545, loss: 0.0004920761566609144 2023-01-23 18:51:53.119539: step: 1934/1545, loss: 7.080591603880748e-05 2023-01-23 18:51:53.966566: step: 1936/1545, loss: 0.0009099261369556189 2023-01-23 18:51:54.822177: step: 1938/1545, loss: 0.0034446213394403458 2023-01-23 18:51:55.688988: step: 1940/1545, loss: 0.0009828588226810098 2023-01-23 18:51:56.611353: step: 1942/1545, loss: 0.0831281766295433 2023-01-23 18:51:57.466419: step: 1944/1545, loss: 0.04770630970597267 2023-01-23 18:51:58.317262: step: 1946/1545, loss: 0.009282691404223442 2023-01-23 18:51:59.200909: step: 1948/1545, loss: 1.7630667571211234e-05 2023-01-23 18:52:00.115088: step: 1950/1545, loss: 0.03673885390162468 2023-01-23 18:52:01.003883: step: 1952/1545, loss: 0.01670854352414608 2023-01-23 18:52:01.978080: step: 1954/1545, loss: 0.0006123394705355167 2023-01-23 18:52:02.858381: step: 1956/1545, loss: 0.0709574744105339 2023-01-23 18:52:03.779283: step: 1958/1545, loss: 0.0004113062168471515 2023-01-23 18:52:04.684290: step: 1960/1545, loss: 0.02819252572953701 2023-01-23 18:52:05.610999: step: 1962/1545, loss: 0.18369849026203156 2023-01-23 18:52:06.454787: step: 1964/1545, loss: 0.0013431207044050097 2023-01-23 18:52:07.318284: step: 1966/1545, loss: 0.0008921104017645121 2023-01-23 18:52:08.171780: step: 1968/1545, loss: 0.0002580549626145512 2023-01-23 18:52:09.104073: step: 1970/1545, loss: 0.020973632112145424 2023-01-23 18:52:09.960472: step: 1972/1545, loss: 0.3655252456665039 2023-01-23 18:52:10.828654: step: 1974/1545, loss: 0.004730640444904566 2023-01-23 18:52:11.721106: step: 1976/1545, loss: 0.01575743779540062 2023-01-23 18:52:12.622447: step: 1978/1545, loss: 0.0015979227609932423 2023-01-23 18:52:13.483104: step: 1980/1545, loss: 0.00048431800678372383 2023-01-23 18:52:14.375775: step: 1982/1545, loss: 0.03928721696138382 2023-01-23 18:52:15.307288: step: 1984/1545, loss: 0.10744352638721466 2023-01-23 18:52:16.147102: step: 1986/1545, loss: 0.006906276103109121 2023-01-23 18:52:17.060317: step: 1988/1545, loss: 0.0005007668514735997 2023-01-23 18:52:17.926847: step: 1990/1545, loss: 0.03785333409905434 2023-01-23 18:52:18.841168: step: 1992/1545, loss: 0.03360118716955185 2023-01-23 18:52:19.734439: step: 1994/1545, loss: 0.4484046995639801 2023-01-23 18:52:20.610809: step: 1996/1545, loss: 0.0032496589701622725 2023-01-23 18:52:21.522937: step: 1998/1545, loss: 0.002902710810303688 2023-01-23 18:52:22.506939: step: 2000/1545, loss: 0.014613060280680656 2023-01-23 18:52:23.383881: step: 2002/1545, loss: 0.007854622788727283 2023-01-23 18:52:24.250194: step: 2004/1545, loss: 1.8361854553222656 2023-01-23 18:52:25.192127: step: 2006/1545, loss: 0.0006469295476563275 2023-01-23 18:52:26.037615: step: 2008/1545, loss: 0.2924255132675171 2023-01-23 18:52:26.928513: step: 2010/1545, loss: 0.018485717475414276 2023-01-23 18:52:27.775438: step: 2012/1545, loss: 0.11550264805555344 2023-01-23 18:52:28.621887: step: 2014/1545, loss: 0.013187085278332233 2023-01-23 18:52:29.531109: step: 2016/1545, loss: 0.4031883180141449 2023-01-23 18:52:30.390014: step: 2018/1545, loss: 0.1607312709093094 2023-01-23 18:52:31.378701: step: 2020/1545, loss: 0.0003967920783907175 2023-01-23 18:52:32.282220: step: 2022/1545, loss: 0.0008061925182119012 2023-01-23 18:52:33.151279: step: 2024/1545, loss: 0.001889682374894619 2023-01-23 18:52:34.045776: step: 2026/1545, loss: 0.05603152513504028 2023-01-23 18:52:34.939686: step: 2028/1545, loss: 0.15211361646652222 2023-01-23 18:52:35.839784: step: 2030/1545, loss: 0.12721732258796692 2023-01-23 18:52:36.698673: step: 2032/1545, loss: 0.018206628039479256 2023-01-23 18:52:37.580871: step: 2034/1545, loss: 0.1640370935201645 2023-01-23 18:52:38.469422: step: 2036/1545, loss: 0.007916461676359177 2023-01-23 18:52:39.363196: step: 2038/1545, loss: 0.026005586609244347 2023-01-23 18:52:40.292547: step: 2040/1545, loss: 0.014943819493055344 2023-01-23 18:52:41.168388: step: 2042/1545, loss: 0.024066297337412834 2023-01-23 18:52:42.036747: step: 2044/1545, loss: 0.027207953855395317 2023-01-23 18:52:42.980578: step: 2046/1545, loss: 0.24231195449829102 2023-01-23 18:52:43.858558: step: 2048/1545, loss: 0.14566777646541595 2023-01-23 18:52:44.706522: step: 2050/1545, loss: 0.0037419728469103575 2023-01-23 18:52:45.570224: step: 2052/1545, loss: 0.020697830244898796 2023-01-23 18:52:46.459803: step: 2054/1545, loss: 0.49688759446144104 2023-01-23 18:52:47.332597: step: 2056/1545, loss: 0.0241940189152956 2023-01-23 18:52:48.341990: step: 2058/1545, loss: 0.00332818366587162 2023-01-23 18:52:49.173285: step: 2060/1545, loss: 0.00025065444060601294 2023-01-23 18:52:50.053685: step: 2062/1545, loss: 0.0007424544310197234 2023-01-23 18:52:50.919010: step: 2064/1545, loss: 0.0014957876410335302 2023-01-23 18:52:51.825428: step: 2066/1545, loss: 0.2863719165325165 2023-01-23 18:52:52.676521: step: 2068/1545, loss: 0.00013798195868730545 2023-01-23 18:52:53.571615: step: 2070/1545, loss: 0.00924532301723957 2023-01-23 18:52:54.469466: step: 2072/1545, loss: 0.0005138511769473553 2023-01-23 18:52:55.398863: step: 2074/1545, loss: 0.30311110615730286 2023-01-23 18:52:56.318984: step: 2076/1545, loss: 0.004845936316996813 2023-01-23 18:52:57.190542: step: 2078/1545, loss: 0.006261925678700209 2023-01-23 18:52:58.076286: step: 2080/1545, loss: 0.019411487504839897 2023-01-23 18:52:58.957494: step: 2082/1545, loss: 0.0001151947071775794 2023-01-23 18:52:59.930509: step: 2084/1545, loss: 0.04220390319824219 2023-01-23 18:53:00.838890: step: 2086/1545, loss: 0.0008137464756146073 2023-01-23 18:53:01.699484: step: 2088/1545, loss: 0.011630105786025524 2023-01-23 18:53:02.624046: step: 2090/1545, loss: 0.03123052977025509 2023-01-23 18:53:03.502358: step: 2092/1545, loss: 0.0002377320925006643 2023-01-23 18:53:04.387474: step: 2094/1545, loss: 0.0005719434702768922 2023-01-23 18:53:05.285443: step: 2096/1545, loss: 0.0005785949761047959 2023-01-23 18:53:06.143346: step: 2098/1545, loss: 0.0029522795230150223 2023-01-23 18:53:07.026638: step: 2100/1545, loss: 0.0001245083549292758 2023-01-23 18:53:07.890767: step: 2102/1545, loss: 0.0013789782533422112 2023-01-23 18:53:08.751395: step: 2104/1545, loss: 4.8748250264907256e-05 2023-01-23 18:53:09.643696: step: 2106/1545, loss: 0.2622984051704407 2023-01-23 18:53:10.531823: step: 2108/1545, loss: 0.00045119840069673955 2023-01-23 18:53:11.402366: step: 2110/1545, loss: 0.00028276367811486125 2023-01-23 18:53:12.311135: step: 2112/1545, loss: 0.014810957945883274 2023-01-23 18:53:13.166843: step: 2114/1545, loss: 0.23009462654590607 2023-01-23 18:53:14.047399: step: 2116/1545, loss: 0.0007086204132065177 2023-01-23 18:53:14.911305: step: 2118/1545, loss: 0.0037920314352959394 2023-01-23 18:53:15.815350: step: 2120/1545, loss: 0.1956479400396347 2023-01-23 18:53:16.710646: step: 2122/1545, loss: 0.11414722353219986 2023-01-23 18:53:17.560401: step: 2124/1545, loss: 0.014094368554651737 2023-01-23 18:53:18.455737: step: 2126/1545, loss: 0.011656520888209343 2023-01-23 18:53:19.319832: step: 2128/1545, loss: 0.013806617818772793 2023-01-23 18:53:20.178648: step: 2130/1545, loss: 0.004936852492392063 2023-01-23 18:53:21.031536: step: 2132/1545, loss: 6.525030767079443e-05 2023-01-23 18:53:21.926087: step: 2134/1545, loss: 0.00014419468061532825 2023-01-23 18:53:22.826925: step: 2136/1545, loss: 9.564055653754622e-05 2023-01-23 18:53:23.692453: step: 2138/1545, loss: 1.1414381265640259 2023-01-23 18:53:24.579269: step: 2140/1545, loss: 0.008240626193583012 2023-01-23 18:53:25.448939: step: 2142/1545, loss: 0.003032388398423791 2023-01-23 18:53:26.317405: step: 2144/1545, loss: 0.18539643287658691 2023-01-23 18:53:27.154788: step: 2146/1545, loss: 0.0017662077443674207 2023-01-23 18:53:28.044043: step: 2148/1545, loss: 0.001066989148966968 2023-01-23 18:53:28.915968: step: 2150/1545, loss: 0.004369812086224556 2023-01-23 18:53:29.772213: step: 2152/1545, loss: 0.0021070779766887426 2023-01-23 18:53:30.670598: step: 2154/1545, loss: 0.1530061960220337 2023-01-23 18:53:31.547520: step: 2156/1545, loss: 0.12763965129852295 2023-01-23 18:53:32.447151: step: 2158/1545, loss: 0.0009655386093072593 2023-01-23 18:53:33.326335: step: 2160/1545, loss: 0.010819769464433193 2023-01-23 18:53:34.156554: step: 2162/1545, loss: 0.01576353795826435 2023-01-23 18:53:35.042378: step: 2164/1545, loss: 0.00034120556665584445 2023-01-23 18:53:35.940452: step: 2166/1545, loss: 0.16446347534656525 2023-01-23 18:53:36.799143: step: 2168/1545, loss: 0.0004388506058603525 2023-01-23 18:53:37.733313: step: 2170/1545, loss: 0.0008602021844126284 2023-01-23 18:53:38.617165: step: 2172/1545, loss: 0.0016412511467933655 2023-01-23 18:53:39.451627: step: 2174/1545, loss: 0.0016088031698018312 2023-01-23 18:53:40.303106: step: 2176/1545, loss: 0.038034290075302124 2023-01-23 18:53:41.242048: step: 2178/1545, loss: 0.0007706258911639452 2023-01-23 18:53:42.134210: step: 2180/1545, loss: 0.23813986778259277 2023-01-23 18:53:42.991414: step: 2182/1545, loss: 0.07953047007322311 2023-01-23 18:53:43.848558: step: 2184/1545, loss: 0.00031621818197891116 2023-01-23 18:53:44.702324: step: 2186/1545, loss: 0.007533219642937183 2023-01-23 18:53:45.582087: step: 2188/1545, loss: 0.19189003109931946 2023-01-23 18:53:46.403889: step: 2190/1545, loss: 0.04836740344762802 2023-01-23 18:53:47.296117: step: 2192/1545, loss: 0.00014942881534807384 2023-01-23 18:53:48.320119: step: 2194/1545, loss: 0.0030443579889833927 2023-01-23 18:53:49.249415: step: 2196/1545, loss: 0.009705743752419949 2023-01-23 18:53:50.122721: step: 2198/1545, loss: 0.010199368931353092 2023-01-23 18:53:51.007005: step: 2200/1545, loss: 0.03688567876815796 2023-01-23 18:53:51.883002: step: 2202/1545, loss: 0.13011814653873444 2023-01-23 18:53:52.762501: step: 2204/1545, loss: 0.020221540704369545 2023-01-23 18:53:53.623578: step: 2206/1545, loss: 0.0010196309303864837 2023-01-23 18:53:54.521388: step: 2208/1545, loss: 0.8309713006019592 2023-01-23 18:53:55.417297: step: 2210/1545, loss: 0.00377942924387753 2023-01-23 18:53:56.276650: step: 2212/1545, loss: 0.0012217622715979815 2023-01-23 18:53:57.181864: step: 2214/1545, loss: 0.0005637913127429783 2023-01-23 18:53:58.001412: step: 2216/1545, loss: 0.0004319525614846498 2023-01-23 18:53:58.863962: step: 2218/1545, loss: 0.0028603519313037395 2023-01-23 18:53:59.720267: step: 2220/1545, loss: 0.2480260729789734 2023-01-23 18:54:00.624106: step: 2222/1545, loss: 0.02546265721321106 2023-01-23 18:54:01.566420: step: 2224/1545, loss: 0.01359560526907444 2023-01-23 18:54:02.412650: step: 2226/1545, loss: 0.003924945835024118 2023-01-23 18:54:03.256412: step: 2228/1545, loss: 0.12165912985801697 2023-01-23 18:54:04.133752: step: 2230/1545, loss: 0.004629759583622217 2023-01-23 18:54:05.024678: step: 2232/1545, loss: 0.18600350618362427 2023-01-23 18:54:05.892193: step: 2234/1545, loss: 0.2372773140668869 2023-01-23 18:54:06.902341: step: 2236/1545, loss: 0.18625596165657043 2023-01-23 18:54:07.783185: step: 2238/1545, loss: 0.0010069163981825113 2023-01-23 18:54:08.695003: step: 2240/1545, loss: 0.16660335659980774 2023-01-23 18:54:09.553360: step: 2242/1545, loss: 0.003971122670918703 2023-01-23 18:54:10.495265: step: 2244/1545, loss: 0.006243172567337751 2023-01-23 18:54:11.381392: step: 2246/1545, loss: 0.00032144266879186034 2023-01-23 18:54:12.216865: step: 2248/1545, loss: 0.0018515132833272219 2023-01-23 18:54:13.082764: step: 2250/1545, loss: 0.00012614457227755338 2023-01-23 18:54:13.964748: step: 2252/1545, loss: 0.26458096504211426 2023-01-23 18:54:14.794284: step: 2254/1545, loss: 0.00016201143444050103 2023-01-23 18:54:15.652234: step: 2256/1545, loss: 0.0025426584761589766 2023-01-23 18:54:16.544023: step: 2258/1545, loss: 0.00017542960995342582 2023-01-23 18:54:17.381474: step: 2260/1545, loss: 0.07306888699531555 2023-01-23 18:54:18.262919: step: 2262/1545, loss: 9.644497185945511e-05 2023-01-23 18:54:19.157717: step: 2264/1545, loss: 0.0032157988753169775 2023-01-23 18:54:20.075386: step: 2266/1545, loss: 0.043103527277708054 2023-01-23 18:54:20.913984: step: 2268/1545, loss: 0.010339178144931793 2023-01-23 18:54:21.726886: step: 2270/1545, loss: 0.008486323989927769 2023-01-23 18:54:22.575198: step: 2272/1545, loss: 0.0010084023233503103 2023-01-23 18:54:23.457219: step: 2274/1545, loss: 0.003298885887488723 2023-01-23 18:54:24.358679: step: 2276/1545, loss: 0.002762336516752839 2023-01-23 18:54:25.325146: step: 2278/1545, loss: 0.007151449099183083 2023-01-23 18:54:26.219073: step: 2280/1545, loss: 0.02931090258061886 2023-01-23 18:54:27.148614: step: 2282/1545, loss: 0.0752568244934082 2023-01-23 18:54:28.053232: step: 2284/1545, loss: 0.0019057767931371927 2023-01-23 18:54:28.891229: step: 2286/1545, loss: 0.0490841418504715 2023-01-23 18:54:29.787508: step: 2288/1545, loss: 0.0017755480948835611 2023-01-23 18:54:30.712987: step: 2290/1545, loss: 0.037630196660757065 2023-01-23 18:54:31.730168: step: 2292/1545, loss: 0.16480740904808044 2023-01-23 18:54:32.609649: step: 2294/1545, loss: 0.029480021446943283 2023-01-23 18:54:33.454124: step: 2296/1545, loss: 0.016623416915535927 2023-01-23 18:54:34.338558: step: 2298/1545, loss: 0.0016265601152554154 2023-01-23 18:54:35.216582: step: 2300/1545, loss: 0.00045134080573916435 2023-01-23 18:54:36.122200: step: 2302/1545, loss: 0.0009392903884872794 2023-01-23 18:54:36.989979: step: 2304/1545, loss: 0.10469906777143478 2023-01-23 18:54:37.892428: step: 2306/1545, loss: 0.3026597797870636 2023-01-23 18:54:38.763192: step: 2308/1545, loss: 0.020295491442084312 2023-01-23 18:54:39.647742: step: 2310/1545, loss: 0.3277100920677185 2023-01-23 18:54:40.490004: step: 2312/1545, loss: 0.4639120101928711 2023-01-23 18:54:41.330122: step: 2314/1545, loss: 0.01598888449370861 2023-01-23 18:54:42.201057: step: 2316/1545, loss: 0.029153719544410706 2023-01-23 18:54:43.078726: step: 2318/1545, loss: 0.0332648791372776 2023-01-23 18:54:43.986422: step: 2320/1545, loss: 0.025180507451295853 2023-01-23 18:54:44.823152: step: 2322/1545, loss: 0.06247948855161667 2023-01-23 18:54:45.667035: step: 2324/1545, loss: 0.00644701486453414 2023-01-23 18:54:46.512970: step: 2326/1545, loss: 0.0006601653876714408 2023-01-23 18:54:47.387402: step: 2328/1545, loss: 0.014563299715518951 2023-01-23 18:54:48.280067: step: 2330/1545, loss: 0.03573725372552872 2023-01-23 18:54:49.208878: step: 2332/1545, loss: 5.57610546820797e-05 2023-01-23 18:54:50.077699: step: 2334/1545, loss: 3.4255950595252216e-05 2023-01-23 18:54:50.971944: step: 2336/1545, loss: 0.5214006900787354 2023-01-23 18:54:51.861432: step: 2338/1545, loss: 0.08960049599409103 2023-01-23 18:54:52.701140: step: 2340/1545, loss: 0.00033265913953073323 2023-01-23 18:54:53.578377: step: 2342/1545, loss: 7.412921695504338e-05 2023-01-23 18:54:54.425824: step: 2344/1545, loss: 0.002098534954711795 2023-01-23 18:54:55.302559: step: 2346/1545, loss: 0.00011470299796201289 2023-01-23 18:54:56.178895: step: 2348/1545, loss: 0.0065427557565271854 2023-01-23 18:54:57.094371: step: 2350/1545, loss: 0.1144125685095787 2023-01-23 18:54:57.981914: step: 2352/1545, loss: 2.3774136934662238e-05 2023-01-23 18:54:58.854696: step: 2354/1545, loss: -5.5971058827708475e-06 2023-01-23 18:54:59.743242: step: 2356/1545, loss: 0.043152451515197754 2023-01-23 18:55:00.641913: step: 2358/1545, loss: 0.002428145846351981 2023-01-23 18:55:01.542286: step: 2360/1545, loss: 0.665964663028717 2023-01-23 18:55:02.427988: step: 2362/1545, loss: 0.00017418497009202838 2023-01-23 18:55:03.324012: step: 2364/1545, loss: 0.08271501213312149 2023-01-23 18:55:04.249707: step: 2366/1545, loss: 0.07051517814397812 2023-01-23 18:55:05.142480: step: 2368/1545, loss: 0.027871903032064438 2023-01-23 18:55:06.062560: step: 2370/1545, loss: 0.011733613908290863 2023-01-23 18:55:06.954458: step: 2372/1545, loss: 0.00015785689174663275 2023-01-23 18:55:07.786410: step: 2374/1545, loss: 0.006839764304459095 2023-01-23 18:55:08.618896: step: 2376/1545, loss: 0.0007620741380378604 2023-01-23 18:55:09.523763: step: 2378/1545, loss: 0.036281101405620575 2023-01-23 18:55:10.422130: step: 2380/1545, loss: 0.017890263348817825 2023-01-23 18:55:11.273393: step: 2382/1545, loss: 0.00019207513832952827 2023-01-23 18:55:12.166804: step: 2384/1545, loss: 0.000622499268501997 2023-01-23 18:55:13.072049: step: 2386/1545, loss: 0.0025481185875833035 2023-01-23 18:55:13.945321: step: 2388/1545, loss: 0.0006998028256930411 2023-01-23 18:55:14.835998: step: 2390/1545, loss: 0.009767427109181881 2023-01-23 18:55:15.702181: step: 2392/1545, loss: 0.019991174340248108 2023-01-23 18:55:16.616155: step: 2394/1545, loss: 0.0020049239974468946 2023-01-23 18:55:17.572451: step: 2396/1545, loss: 0.0025128554552793503 2023-01-23 18:55:18.453676: step: 2398/1545, loss: 0.12267634272575378 2023-01-23 18:55:19.347962: step: 2400/1545, loss: 0.07796967774629593 2023-01-23 18:55:20.254035: step: 2402/1545, loss: 0.007795712910592556 2023-01-23 18:55:21.089445: step: 2404/1545, loss: 0.0008006636635400355 2023-01-23 18:55:22.008308: step: 2406/1545, loss: 0.07489228248596191 2023-01-23 18:55:22.922999: step: 2408/1545, loss: 0.27704301476478577 2023-01-23 18:55:23.798483: step: 2410/1545, loss: 0.0009202312212437391 2023-01-23 18:55:24.725065: step: 2412/1545, loss: 0.0011839298531413078 2023-01-23 18:55:25.595671: step: 2414/1545, loss: 0.0036808878649026155 2023-01-23 18:55:26.523228: step: 2416/1545, loss: 0.0004831462283618748 2023-01-23 18:55:27.389764: step: 2418/1545, loss: 0.00013485729868989438 2023-01-23 18:55:28.249860: step: 2420/1545, loss: 0.00032214325619861484 2023-01-23 18:55:29.180940: step: 2422/1545, loss: 0.37063533067703247 2023-01-23 18:55:30.046942: step: 2424/1545, loss: 0.00023642064479645342 2023-01-23 18:55:30.933546: step: 2426/1545, loss: 0.00794107187539339 2023-01-23 18:55:31.806680: step: 2428/1545, loss: 0.03474608063697815 2023-01-23 18:55:32.698044: step: 2430/1545, loss: 0.11610618233680725 2023-01-23 18:55:33.545273: step: 2432/1545, loss: 0.00014932603517081589 2023-01-23 18:55:34.501872: step: 2434/1545, loss: 0.027639281004667282 2023-01-23 18:55:35.338001: step: 2436/1545, loss: 0.0036376994103193283 2023-01-23 18:55:36.216037: step: 2438/1545, loss: 0.0015180802438408136 2023-01-23 18:55:37.119911: step: 2440/1545, loss: 0.002129187574610114 2023-01-23 18:55:37.996137: step: 2442/1545, loss: 0.002228089375421405 2023-01-23 18:55:38.861883: step: 2444/1545, loss: 0.003566276514902711 2023-01-23 18:55:39.723781: step: 2446/1545, loss: 0.014357696287333965 2023-01-23 18:55:40.574164: step: 2448/1545, loss: 0.002190707717090845 2023-01-23 18:55:41.453115: step: 2450/1545, loss: 0.000912702176719904 2023-01-23 18:55:42.317550: step: 2452/1545, loss: 0.01645267754793167 2023-01-23 18:55:43.173748: step: 2454/1545, loss: 2.0152128854533657e-05 2023-01-23 18:55:44.022768: step: 2456/1545, loss: 0.11087614297866821 2023-01-23 18:55:44.894958: step: 2458/1545, loss: 0.7020429372787476 2023-01-23 18:55:45.750007: step: 2460/1545, loss: 0.00012595858424901962 2023-01-23 18:55:46.613223: step: 2462/1545, loss: 0.008238418027758598 2023-01-23 18:55:47.573765: step: 2464/1545, loss: 0.04943369701504707 2023-01-23 18:55:48.511267: step: 2466/1545, loss: 0.00023023824905976653 2023-01-23 18:55:49.379424: step: 2468/1545, loss: 0.006094259675592184 2023-01-23 18:55:50.244611: step: 2470/1545, loss: 7.594001363031566e-05 2023-01-23 18:55:51.214111: step: 2472/1545, loss: 1.9037590026855469 2023-01-23 18:55:52.075501: step: 2474/1545, loss: 0.03906136378645897 2023-01-23 18:55:52.984321: step: 2476/1545, loss: 0.20913231372833252 2023-01-23 18:55:53.887821: step: 2478/1545, loss: 0.006554849445819855 2023-01-23 18:55:54.754577: step: 2480/1545, loss: 0.16994337737560272 2023-01-23 18:55:55.602522: step: 2482/1545, loss: 0.012574734166264534 2023-01-23 18:55:56.472168: step: 2484/1545, loss: 0.008877640590071678 2023-01-23 18:55:57.339752: step: 2486/1545, loss: 0.0002819342480506748 2023-01-23 18:55:58.238515: step: 2488/1545, loss: 0.019892387092113495 2023-01-23 18:55:59.116177: step: 2490/1545, loss: 0.0007853655843064189 2023-01-23 18:55:59.982309: step: 2492/1545, loss: 0.3930136561393738 2023-01-23 18:56:00.869411: step: 2494/1545, loss: 0.007832935079932213 2023-01-23 18:56:01.715397: step: 2496/1545, loss: 0.03826143965125084 2023-01-23 18:56:02.625558: step: 2498/1545, loss: 0.000319681188557297 2023-01-23 18:56:03.491899: step: 2500/1545, loss: 0.07335178554058075 2023-01-23 18:56:04.388736: step: 2502/1545, loss: 0.21641004085540771 2023-01-23 18:56:05.260760: step: 2504/1545, loss: 0.05541001632809639 2023-01-23 18:56:06.149736: step: 2506/1545, loss: 0.0006685908883810043 2023-01-23 18:56:07.013659: step: 2508/1545, loss: 0.0005799770588055253 2023-01-23 18:56:07.926593: step: 2510/1545, loss: 0.039108701050281525 2023-01-23 18:56:08.764608: step: 2512/1545, loss: 7.690012716921046e-05 2023-01-23 18:56:09.640938: step: 2514/1545, loss: 0.6265128254890442 2023-01-23 18:56:10.628554: step: 2516/1545, loss: 0.11647585034370422 2023-01-23 18:56:11.492331: step: 2518/1545, loss: 0.012386529706418514 2023-01-23 18:56:12.344210: step: 2520/1545, loss: 0.0023370275739580393 2023-01-23 18:56:13.245419: step: 2522/1545, loss: 2.086672975565307e-05 2023-01-23 18:56:14.220465: step: 2524/1545, loss: 0.23127147555351257 2023-01-23 18:56:15.141778: step: 2526/1545, loss: 0.005473861936479807 2023-01-23 18:56:16.057465: step: 2528/1545, loss: 0.10925161093473434 2023-01-23 18:56:16.906966: step: 2530/1545, loss: 0.013233154080808163 2023-01-23 18:56:17.782031: step: 2532/1545, loss: 0.00022853730479255319 2023-01-23 18:56:18.686351: step: 2534/1545, loss: 0.03141453117132187 2023-01-23 18:56:19.673899: step: 2536/1545, loss: 0.00047347325016744435 2023-01-23 18:56:20.520086: step: 2538/1545, loss: 0.02736697904765606 2023-01-23 18:56:21.394055: step: 2540/1545, loss: 0.0008679975289851427 2023-01-23 18:56:22.318366: step: 2542/1545, loss: 0.17745338380336761 2023-01-23 18:56:23.207122: step: 2544/1545, loss: 0.009192184545099735 2023-01-23 18:56:24.067368: step: 2546/1545, loss: 0.0006733193877153099 2023-01-23 18:56:24.943705: step: 2548/1545, loss: 0.00022529534180648625 2023-01-23 18:56:25.810683: step: 2550/1545, loss: 0.001159965293481946 2023-01-23 18:56:26.649180: step: 2552/1545, loss: 0.0009495263802818954 2023-01-23 18:56:27.502740: step: 2554/1545, loss: 0.0066577475517988205 2023-01-23 18:56:28.365332: step: 2556/1545, loss: 0.0842486172914505 2023-01-23 18:56:29.267188: step: 2558/1545, loss: 0.0017645322950556874 2023-01-23 18:56:30.175531: step: 2560/1545, loss: 0.09453434497117996 2023-01-23 18:56:31.092787: step: 2562/1545, loss: 0.0010606833966448903 2023-01-23 18:56:31.941745: step: 2564/1545, loss: 9.271200542571023e-05 2023-01-23 18:56:32.830629: step: 2566/1545, loss: 0.0010096131591126323 2023-01-23 18:56:33.666385: step: 2568/1545, loss: 0.09950078278779984 2023-01-23 18:56:34.585850: step: 2570/1545, loss: 0.00039728020783513784 2023-01-23 18:56:35.423734: step: 2572/1545, loss: 0.0026886174455285072 2023-01-23 18:56:36.298814: step: 2574/1545, loss: 0.06450601667165756 2023-01-23 18:56:37.151717: step: 2576/1545, loss: 0.05423152819275856 2023-01-23 18:56:38.011007: step: 2578/1545, loss: -2.1870197087991983e-05 2023-01-23 18:56:38.911218: step: 2580/1545, loss: 0.12650558352470398 2023-01-23 18:56:39.795536: step: 2582/1545, loss: 0.043015025556087494 2023-01-23 18:56:40.655844: step: 2584/1545, loss: 0.002434373367577791 2023-01-23 18:56:41.541012: step: 2586/1545, loss: 0.004520817659795284 2023-01-23 18:56:42.425094: step: 2588/1545, loss: 0.4196210503578186 2023-01-23 18:56:43.345052: step: 2590/1545, loss: 0.01787896640598774 2023-01-23 18:56:44.242315: step: 2592/1545, loss: 0.011507660150527954 2023-01-23 18:56:45.201682: step: 2594/1545, loss: 0.007970544509589672 2023-01-23 18:56:46.067472: step: 2596/1545, loss: 0.0003982683119829744 2023-01-23 18:56:47.116747: step: 2598/1545, loss: 0.021470539271831512 2023-01-23 18:56:47.968326: step: 2600/1545, loss: 0.0031365654431283474 2023-01-23 18:56:48.842072: step: 2602/1545, loss: 0.04728993773460388 2023-01-23 18:56:49.749107: step: 2604/1545, loss: 0.12129482626914978 2023-01-23 18:56:50.606082: step: 2606/1545, loss: 0.10635402798652649 2023-01-23 18:56:51.505476: step: 2608/1545, loss: 0.0001940661168191582 2023-01-23 18:56:52.378745: step: 2610/1545, loss: 0.0002373821916989982 2023-01-23 18:56:53.196816: step: 2612/1545, loss: 0.004168241750448942 2023-01-23 18:56:54.113159: step: 2614/1545, loss: 0.03715270012617111 2023-01-23 18:56:55.005146: step: 2616/1545, loss: 0.010667877271771431 2023-01-23 18:56:55.972014: step: 2618/1545, loss: 0.00018800444377120584 2023-01-23 18:56:56.850625: step: 2620/1545, loss: 0.05062122642993927 2023-01-23 18:56:57.707173: step: 2622/1545, loss: 0.04152500256896019 2023-01-23 18:56:58.646353: step: 2624/1545, loss: 0.0007394682615995407 2023-01-23 18:56:59.527690: step: 2626/1545, loss: 0.05546680837869644 2023-01-23 18:57:00.419323: step: 2628/1545, loss: 0.5449965000152588 2023-01-23 18:57:01.233096: step: 2630/1545, loss: 0.07103670388460159 2023-01-23 18:57:02.105952: step: 2632/1545, loss: 0.0009934552945196629 2023-01-23 18:57:02.926858: step: 2634/1545, loss: 0.00025835324777290225 2023-01-23 18:57:03.786095: step: 2636/1545, loss: 0.002485373755916953 2023-01-23 18:57:04.707504: step: 2638/1545, loss: 0.12433052808046341 2023-01-23 18:57:05.613852: step: 2640/1545, loss: 0.00353599083609879 2023-01-23 18:57:06.502546: step: 2642/1545, loss: 0.02032650262117386 2023-01-23 18:57:07.536893: step: 2644/1545, loss: 0.019888820126652718 2023-01-23 18:57:08.401859: step: 2646/1545, loss: 0.012369115836918354 2023-01-23 18:57:09.289195: step: 2648/1545, loss: 0.055896613746881485 2023-01-23 18:57:10.167171: step: 2650/1545, loss: 0.01118572149425745 2023-01-23 18:57:11.016474: step: 2652/1545, loss: 0.0012275673216208816 2023-01-23 18:57:11.971570: step: 2654/1545, loss: 0.0014214213006198406 2023-01-23 18:57:12.826289: step: 2656/1545, loss: 0.0012435032986104488 2023-01-23 18:57:13.705956: step: 2658/1545, loss: 0.013020769692957401 2023-01-23 18:57:14.571529: step: 2660/1545, loss: 4.570839155348949e-05 2023-01-23 18:57:15.417338: step: 2662/1545, loss: 0.0008542650612071157 2023-01-23 18:57:16.294560: step: 2664/1545, loss: 0.0006748994928784668 2023-01-23 18:57:17.161890: step: 2666/1545, loss: 0.05819154903292656 2023-01-23 18:57:18.034639: step: 2668/1545, loss: 0.0015897040721029043 2023-01-23 18:57:18.896871: step: 2670/1545, loss: 0.04128090292215347 2023-01-23 18:57:19.769329: step: 2672/1545, loss: 0.002810048870742321 2023-01-23 18:57:20.642887: step: 2674/1545, loss: 0.10832718759775162 2023-01-23 18:57:21.538756: step: 2676/1545, loss: 0.0013675522059202194 2023-01-23 18:57:22.427674: step: 2678/1545, loss: 0.007128846365958452 2023-01-23 18:57:23.328435: step: 2680/1545, loss: 0.00044591855839826167 2023-01-23 18:57:24.219381: step: 2682/1545, loss: 0.08260141313076019 2023-01-23 18:57:25.097608: step: 2684/1545, loss: 0.3311360478401184 2023-01-23 18:57:25.954427: step: 2686/1545, loss: 0.07661420851945877 2023-01-23 18:57:26.852207: step: 2688/1545, loss: 0.0037079742178320885 2023-01-23 18:57:27.798196: step: 2690/1545, loss: 0.027562104165554047 2023-01-23 18:57:28.726424: step: 2692/1545, loss: 0.017175987362861633 2023-01-23 18:57:29.578590: step: 2694/1545, loss: 0.0040432969108223915 2023-01-23 18:57:30.467641: step: 2696/1545, loss: 0.11256303638219833 2023-01-23 18:57:31.328204: step: 2698/1545, loss: 0.000978671945631504 2023-01-23 18:57:32.252999: step: 2700/1545, loss: 0.03870179131627083 2023-01-23 18:57:33.102604: step: 2702/1545, loss: 0.16584356129169464 2023-01-23 18:57:34.000361: step: 2704/1545, loss: 0.00040459304000250995 2023-01-23 18:57:34.892153: step: 2706/1545, loss: 0.00011585005995584652 2023-01-23 18:57:35.783251: step: 2708/1545, loss: 0.031081773340702057 2023-01-23 18:57:36.692603: step: 2710/1545, loss: 0.0026888977736234665 2023-01-23 18:57:37.567687: step: 2712/1545, loss: 0.00015418627299368382 2023-01-23 18:57:38.487991: step: 2714/1545, loss: 0.0016001492040231824 2023-01-23 18:57:39.357899: step: 2716/1545, loss: 0.002103119157254696 2023-01-23 18:57:40.240441: step: 2718/1545, loss: 0.0005270327092148364 2023-01-23 18:57:41.126200: step: 2720/1545, loss: 6.915438279975206e-05 2023-01-23 18:57:41.963469: step: 2722/1545, loss: 0.004885047674179077 2023-01-23 18:57:42.834460: step: 2724/1545, loss: 0.020746635273098946 2023-01-23 18:57:43.714121: step: 2726/1545, loss: 0.009043379686772823 2023-01-23 18:57:44.550658: step: 2728/1545, loss: 0.12190350890159607 2023-01-23 18:57:45.416241: step: 2730/1545, loss: 0.09081470221281052 2023-01-23 18:57:46.267239: step: 2732/1545, loss: 0.0005738525651395321 2023-01-23 18:57:47.117190: step: 2734/1545, loss: 0.01029921043664217 2023-01-23 18:57:47.958652: step: 2736/1545, loss: 0.002724971156567335 2023-01-23 18:57:48.808990: step: 2738/1545, loss: 0.03468459099531174 2023-01-23 18:57:49.722063: step: 2740/1545, loss: 0.0011183929163962603 2023-01-23 18:57:50.621669: step: 2742/1545, loss: 0.0011629972141236067 2023-01-23 18:57:51.520954: step: 2744/1545, loss: 0.33605796098709106 2023-01-23 18:57:52.381066: step: 2746/1545, loss: 0.03295879065990448 2023-01-23 18:57:53.304120: step: 2748/1545, loss: 0.0018173572607338428 2023-01-23 18:57:54.195256: step: 2750/1545, loss: 0.0004907309776172042 2023-01-23 18:57:55.089092: step: 2752/1545, loss: 0.003865598700940609 2023-01-23 18:57:56.003108: step: 2754/1545, loss: 3.340200419188477e-05 2023-01-23 18:57:56.870902: step: 2756/1545, loss: 0.0027666380628943443 2023-01-23 18:57:57.716855: step: 2758/1545, loss: 0.9040818214416504 2023-01-23 18:57:58.589774: step: 2760/1545, loss: 0.006928237155079842 2023-01-23 18:57:59.452633: step: 2762/1545, loss: 0.7974271178245544 2023-01-23 18:58:00.319228: step: 2764/1545, loss: 0.0004471991560421884 2023-01-23 18:58:01.223232: step: 2766/1545, loss: 0.3728979527950287 2023-01-23 18:58:02.113995: step: 2768/1545, loss: 0.0007293539238162339 2023-01-23 18:58:03.005396: step: 2770/1545, loss: 0.02379206381738186 2023-01-23 18:58:03.872481: step: 2772/1545, loss: 0.00043598024058155715 2023-01-23 18:58:04.736584: step: 2774/1545, loss: 0.04897044971585274 2023-01-23 18:58:05.597661: step: 2776/1545, loss: 0.20252767205238342 2023-01-23 18:58:06.481449: step: 2778/1545, loss: 0.15884926915168762 2023-01-23 18:58:07.343480: step: 2780/1545, loss: 0.00662757596001029 2023-01-23 18:58:08.200032: step: 2782/1545, loss: 0.0003384702722541988 2023-01-23 18:58:09.081219: step: 2784/1545, loss: 0.012974324636161327 2023-01-23 18:58:09.974000: step: 2786/1545, loss: 0.0006959165330044925 2023-01-23 18:58:10.884244: step: 2788/1545, loss: 0.028077594935894012 2023-01-23 18:58:11.775944: step: 2790/1545, loss: 0.022907108068466187 2023-01-23 18:58:12.707897: step: 2792/1545, loss: 0.0007743474561721087 2023-01-23 18:58:13.666425: step: 2794/1545, loss: 0.019117554649710655 2023-01-23 18:58:14.551789: step: 2796/1545, loss: 0.000539461150765419 2023-01-23 18:58:15.470912: step: 2798/1545, loss: 0.02960633672773838 2023-01-23 18:58:16.336273: step: 2800/1545, loss: 0.0046433089300990105 2023-01-23 18:58:17.219525: step: 2802/1545, loss: 0.0037635902408510447 2023-01-23 18:58:18.116219: step: 2804/1545, loss: 0.0016104624373838305 2023-01-23 18:58:18.984845: step: 2806/1545, loss: 0.0012534158304333687 2023-01-23 18:58:19.877807: step: 2808/1545, loss: 0.09275217354297638 2023-01-23 18:58:20.748944: step: 2810/1545, loss: 0.15791265666484833 2023-01-23 18:58:21.694352: step: 2812/1545, loss: 0.06397245824337006 2023-01-23 18:58:22.534063: step: 2814/1545, loss: 0.1911764144897461 2023-01-23 18:58:23.400609: step: 2816/1545, loss: 0.006132930051535368 2023-01-23 18:58:24.297108: step: 2818/1545, loss: 0.0004949940484948456 2023-01-23 18:58:25.155870: step: 2820/1545, loss: 0.0001486783439759165 2023-01-23 18:58:26.033479: step: 2822/1545, loss: 0.0017716768197715282 2023-01-23 18:58:26.899289: step: 2824/1545, loss: 0.04247142747044563 2023-01-23 18:58:27.818944: step: 2826/1545, loss: 0.15915992856025696 2023-01-23 18:58:28.709503: step: 2828/1545, loss: 0.0017433804459869862 2023-01-23 18:58:29.584967: step: 2830/1545, loss: 0.005992521066218615 2023-01-23 18:58:30.437946: step: 2832/1545, loss: 0.002692145062610507 2023-01-23 18:58:31.362631: step: 2834/1545, loss: 0.01725931651890278 2023-01-23 18:58:32.237238: step: 2836/1545, loss: 0.0014058827655389905 2023-01-23 18:58:33.110478: step: 2838/1545, loss: 0.041919391602277756 2023-01-23 18:58:34.016109: step: 2840/1545, loss: 0.0013121888041496277 2023-01-23 18:58:34.959765: step: 2842/1545, loss: 0.0008213527617044747 2023-01-23 18:58:35.805457: step: 2844/1545, loss: 0.0008051013574004173 2023-01-23 18:58:36.699310: step: 2846/1545, loss: 0.1618523746728897 2023-01-23 18:58:37.578982: step: 2848/1545, loss: 0.011559596285223961 2023-01-23 18:58:38.487554: step: 2850/1545, loss: 0.002422063611447811 2023-01-23 18:58:39.385571: step: 2852/1545, loss: 0.016383061185479164 2023-01-23 18:58:40.247922: step: 2854/1545, loss: 0.00896676816046238 2023-01-23 18:58:41.122242: step: 2856/1545, loss: 0.25464555621147156 2023-01-23 18:58:42.019382: step: 2858/1545, loss: 0.0008287214441224933 2023-01-23 18:58:42.904921: step: 2860/1545, loss: 0.026259751990437508 2023-01-23 18:58:43.878471: step: 2862/1545, loss: 0.037973273545503616 2023-01-23 18:58:44.789302: step: 2864/1545, loss: 0.1788954883813858 2023-01-23 18:58:45.666966: step: 2866/1545, loss: 0.029963573440909386 2023-01-23 18:58:46.512961: step: 2868/1545, loss: 0.1160782128572464 2023-01-23 18:58:47.418084: step: 2870/1545, loss: 0.003584763500839472 2023-01-23 18:58:48.284599: step: 2872/1545, loss: 0.001053893705829978 2023-01-23 18:58:49.152845: step: 2874/1545, loss: 0.012388291768729687 2023-01-23 18:58:50.074373: step: 2876/1545, loss: 0.005904070101678371 2023-01-23 18:58:51.057637: step: 2878/1545, loss: 0.00011488562449812889 2023-01-23 18:58:51.933776: step: 2880/1545, loss: 0.0029776294250041246 2023-01-23 18:58:52.781448: step: 2882/1545, loss: 0.002047160407528281 2023-01-23 18:58:53.704077: step: 2884/1545, loss: 0.014582074247300625 2023-01-23 18:58:54.609486: step: 2886/1545, loss: 0.2567439079284668 2023-01-23 18:58:55.509535: step: 2888/1545, loss: 0.0007264047744683921 2023-01-23 18:58:56.387855: step: 2890/1545, loss: 8.058025559876114e-05 2023-01-23 18:58:57.217732: step: 2892/1545, loss: 0.0007375365239568055 2023-01-23 18:58:58.108649: step: 2894/1545, loss: 0.045605823397636414 2023-01-23 18:58:58.981774: step: 2896/1545, loss: 0.011289854533970356 2023-01-23 18:58:59.849866: step: 2898/1545, loss: 0.09109289199113846 2023-01-23 18:59:00.725806: step: 2900/1545, loss: 9.051009692484513e-05 2023-01-23 18:59:01.585117: step: 2902/1545, loss: 0.0015946079511195421 2023-01-23 18:59:02.532729: step: 2904/1545, loss: 0.004544263705611229 2023-01-23 18:59:03.465378: step: 2906/1545, loss: 0.013691180385649204 2023-01-23 18:59:04.317037: step: 2908/1545, loss: 0.0013737175613641739 2023-01-23 18:59:05.161324: step: 2910/1545, loss: 0.0015989996027201414 2023-01-23 18:59:06.028777: step: 2912/1545, loss: 0.003894764930009842 2023-01-23 18:59:06.987625: step: 2914/1545, loss: 0.00023681519087404013 2023-01-23 18:59:07.918418: step: 2916/1545, loss: 0.017199093475937843 2023-01-23 18:59:08.776450: step: 2918/1545, loss: 0.04788803309202194 2023-01-23 18:59:09.630447: step: 2920/1545, loss: 0.0011958875693380833 2023-01-23 18:59:10.475262: step: 2922/1545, loss: 0.0014840508811175823 2023-01-23 18:59:11.386914: step: 2924/1545, loss: 0.012417281977832317 2023-01-23 18:59:12.298819: step: 2926/1545, loss: 0.4060910642147064 2023-01-23 18:59:13.153814: step: 2928/1545, loss: 2.1141848264960572e-05 2023-01-23 18:59:14.122185: step: 2930/1545, loss: 0.00013356056297197938 2023-01-23 18:59:14.969497: step: 2932/1545, loss: 0.002683077473193407 2023-01-23 18:59:15.860321: step: 2934/1545, loss: 0.000705927552189678 2023-01-23 18:59:16.719199: step: 2936/1545, loss: 0.01642521657049656 2023-01-23 18:59:17.620923: step: 2938/1545, loss: 0.09409746527671814 2023-01-23 18:59:18.510244: step: 2940/1545, loss: 0.0049995798617601395 2023-01-23 18:59:19.373339: step: 2942/1545, loss: 0.0035668143536895514 2023-01-23 18:59:20.233687: step: 2944/1545, loss: 0.0021200603805482388 2023-01-23 18:59:21.101352: step: 2946/1545, loss: 0.0877460315823555 2023-01-23 18:59:22.003875: step: 2948/1545, loss: 0.0023055733181536198 2023-01-23 18:59:22.908255: step: 2950/1545, loss: 0.40689411759376526 2023-01-23 18:59:23.716342: step: 2952/1545, loss: 0.00016975600738078356 2023-01-23 18:59:24.577321: step: 2954/1545, loss: 0.007883919402956963 2023-01-23 18:59:25.428156: step: 2956/1545, loss: 0.0053643654100596905 2023-01-23 18:59:26.310520: step: 2958/1545, loss: 0.022012917324900627 2023-01-23 18:59:27.180767: step: 2960/1545, loss: 0.0008155135437846184 2023-01-23 18:59:28.082272: step: 2962/1545, loss: 0.004020164255052805 2023-01-23 18:59:28.957483: step: 2964/1545, loss: 0.12257961928844452 2023-01-23 18:59:29.841497: step: 2966/1545, loss: 0.0003435637627262622 2023-01-23 18:59:30.736996: step: 2968/1545, loss: 0.030983584001660347 2023-01-23 18:59:31.583879: step: 2970/1545, loss: 0.0011886785505339503 2023-01-23 18:59:32.505081: step: 2972/1545, loss: 0.07097775489091873 2023-01-23 18:59:33.378304: step: 2974/1545, loss: 0.035259876400232315 2023-01-23 18:59:34.265830: step: 2976/1545, loss: 1.5507179498672485 2023-01-23 18:59:35.143828: step: 2978/1545, loss: 0.029260845854878426 2023-01-23 18:59:36.029585: step: 2980/1545, loss: 8.661784522701055e-05 2023-01-23 18:59:37.016060: step: 2982/1545, loss: 0.002806649776175618 2023-01-23 18:59:37.888529: step: 2984/1545, loss: 0.00817599892616272 2023-01-23 18:59:38.762678: step: 2986/1545, loss: 0.018204716965556145 2023-01-23 18:59:39.691456: step: 2988/1545, loss: 0.0035442004445940256 2023-01-23 18:59:40.570041: step: 2990/1545, loss: 0.023143991827964783 2023-01-23 18:59:41.433793: step: 2992/1545, loss: 0.0027130236849188805 2023-01-23 18:59:42.271034: step: 2994/1545, loss: 0.0022243300918489695 2023-01-23 18:59:43.174196: step: 2996/1545, loss: 0.1115199476480484 2023-01-23 18:59:44.039403: step: 2998/1545, loss: 0.01678447239100933 2023-01-23 18:59:44.932480: step: 3000/1545, loss: 0.050968874245882034 2023-01-23 18:59:45.824801: step: 3002/1545, loss: 0.0006829233607277274 2023-01-23 18:59:46.676564: step: 3004/1545, loss: 0.0019378734286874533 2023-01-23 18:59:47.586403: step: 3006/1545, loss: 0.04883083701133728 2023-01-23 18:59:48.481826: step: 3008/1545, loss: 0.184221088886261 2023-01-23 18:59:49.318306: step: 3010/1545, loss: 0.007876481860876083 2023-01-23 18:59:50.174470: step: 3012/1545, loss: 0.24903209507465363 2023-01-23 18:59:50.996149: step: 3014/1545, loss: 0.001743633416481316 2023-01-23 18:59:51.965022: step: 3016/1545, loss: 0.003060729941353202 2023-01-23 18:59:52.844523: step: 3018/1545, loss: 4.9018093704944476e-05 2023-01-23 18:59:53.717647: step: 3020/1545, loss: 0.17427198588848114 2023-01-23 18:59:54.593579: step: 3022/1545, loss: 0.24008306860923767 2023-01-23 18:59:55.478850: step: 3024/1545, loss: 0.03199384734034538 2023-01-23 18:59:56.318610: step: 3026/1545, loss: 0.03171359747648239 2023-01-23 18:59:57.189647: step: 3028/1545, loss: 0.01870778389275074 2023-01-23 18:59:58.066264: step: 3030/1545, loss: 0.0032275391276925802 2023-01-23 18:59:58.944281: step: 3032/1545, loss: 0.0005891986656934023 2023-01-23 18:59:59.845400: step: 3034/1545, loss: 0.028773274272680283 2023-01-23 19:00:00.764835: step: 3036/1545, loss: 0.005837128031998873 2023-01-23 19:00:01.604655: step: 3038/1545, loss: 0.15316256880760193 2023-01-23 19:00:02.449473: step: 3040/1545, loss: 0.0006702853715978563 2023-01-23 19:00:03.357935: step: 3042/1545, loss: 2.6716570573626086e-06 2023-01-23 19:00:04.240005: step: 3044/1545, loss: 0.0007689480553381145 2023-01-23 19:00:05.124270: step: 3046/1545, loss: 0.17752613127231598 2023-01-23 19:00:06.040634: step: 3048/1545, loss: 0.00045934479567222297 2023-01-23 19:00:06.933835: step: 3050/1545, loss: 0.0003884430625475943 2023-01-23 19:00:07.804411: step: 3052/1545, loss: 0.00027282428345642984 2023-01-23 19:00:08.677375: step: 3054/1545, loss: 0.0068372152745723724 2023-01-23 19:00:09.571411: step: 3056/1545, loss: 0.00046497603761963546 2023-01-23 19:00:10.468825: step: 3058/1545, loss: 0.0012425307650119066 2023-01-23 19:00:11.371686: step: 3060/1545, loss: 0.009138843975961208 2023-01-23 19:00:12.314840: step: 3062/1545, loss: 0.007529098074883223 2023-01-23 19:00:13.156742: step: 3064/1545, loss: 0.0032890262082219124 2023-01-23 19:00:14.028300: step: 3066/1545, loss: 0.021999487653374672 2023-01-23 19:00:14.878235: step: 3068/1545, loss: 0.0939326137304306 2023-01-23 19:00:15.742317: step: 3070/1545, loss: 0.014757386408746243 2023-01-23 19:00:16.595402: step: 3072/1545, loss: 0.0007651025080122054 2023-01-23 19:00:17.500604: step: 3074/1545, loss: 0.00429751630872488 2023-01-23 19:00:18.386960: step: 3076/1545, loss: 0.0003715366474352777 2023-01-23 19:00:19.316715: step: 3078/1545, loss: 0.00040661089587956667 2023-01-23 19:00:20.165310: step: 3080/1545, loss: 0.000488847610540688 2023-01-23 19:00:21.049016: step: 3082/1545, loss: 0.03844956308603287 2023-01-23 19:00:21.874753: step: 3084/1545, loss: 0.0016878936439752579 2023-01-23 19:00:22.787743: step: 3086/1545, loss: 0.020121388137340546 2023-01-23 19:00:23.657157: step: 3088/1545, loss: 0.04839588701725006 2023-01-23 19:00:24.497577: step: 3090/1545, loss: 0.4524455964565277 ================================================== Loss: 0.066 -------------------- Dev Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6422869359839323, 'r': 0.6644016059354748, 'f1': 0.6531571343118429}, 'combined': 0.43073911735193476, 'epoch': 29} Test Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6963799774551439, 'r': 0.7216015168597335, 'f1': 0.7087664402632768}, 'combined': 0.4931266216142403, 'epoch': 29} Dev Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.6419906505971872, 'r': 0.6651254488169057, 'f1': 0.6533533169794383}, 'combined': 0.4355688779862922, 'epoch': 29} Test Korean: {'event': {'p': 0.6275132275132275, 'r': 0.7583120204603581, 'f1': 0.6867400115807759}, 'argument': {'p': 0.6896292603073065, 'r': 0.7133188150506873, 'f1': 0.7012740320573361}, 'combined': 0.4815929368963524, 'epoch': 29} Dev Russian: {'event': {'p': 0.5679133858267716, 'r': 0.7683089214380826, 'f1': 0.653084323712507}, 'argument': {'p': 0.6431259565585519, 'r': 0.6725891356707547, 'f1': 0.6575276574751885}, 'combined': 0.42942100550445245, 'epoch': 29} Test Russian: {'event': {'p': 0.6253114100647733, 'r': 0.8024296675191815, 'f1': 0.7028843461215345}, 'argument': {'p': 0.695042191367221, 'r': 0.7306787109096271, 'f1': 0.7124150759169946}, 'combined': 0.5007454048030401, 'epoch': 29} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.7034534534534534, 'r': 0.6453168044077134, 'f1': 0.673132183908046}, 'combined': 0.4691527342389412, 'epoch': 29} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6985714285714286, 'r': 0.47847358121330724, 'f1': 0.5679442508710801}, 'combined': 0.34873769790329484, 'epoch': 29} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5763393342633109, 'r': 0.5557557866110497, 'f1': 0.5658604372767052}, 'combined': 0.31516277519208896, 'epoch': 29} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6559451265403835, 'r': 0.6613377994790564, 'f1': 0.6586304247882229}, 'combined': 0.43355887674908195, 'epoch': 26} Test for Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6980547354393568, 'r': 0.7185779178100443, 'f1': 0.7081676638737557}, 'combined': 0.49271002093834315, 'epoch': 26} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6657901327322815, 'r': 0.6657901327322815, 'f1': 0.6657901327322815}, 'combined': 0.47412327633965495, 'epoch': 26} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 30 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 19:05:41.320482: step: 2/1545, loss: 0.00036260465276427567 2023-01-23 19:05:42.189463: step: 4/1545, loss: 0.017346249893307686 2023-01-23 19:05:43.074051: step: 6/1545, loss: 0.0002318038314115256 2023-01-23 19:05:44.001698: step: 8/1545, loss: 0.03147987276315689 2023-01-23 19:05:44.848963: step: 10/1545, loss: 0.0002728836552705616 2023-01-23 19:05:45.735437: step: 12/1545, loss: 0.00045913743088021874 2023-01-23 19:05:46.585544: step: 14/1545, loss: 0.005035256966948509 2023-01-23 19:05:47.444145: step: 16/1545, loss: 0.0008308943943120539 2023-01-23 19:05:48.320741: step: 18/1545, loss: 0.0003811714123003185 2023-01-23 19:05:49.147114: step: 20/1545, loss: 0.24265551567077637 2023-01-23 19:05:49.994853: step: 22/1545, loss: 0.00019583549874369055 2023-01-23 19:05:50.893129: step: 24/1545, loss: 5.691542901331559e-05 2023-01-23 19:05:51.796338: step: 26/1545, loss: 0.0013658225070685148 2023-01-23 19:05:52.674369: step: 28/1545, loss: 0.0003263893595431 2023-01-23 19:05:53.547247: step: 30/1545, loss: 0.01694370061159134 2023-01-23 19:05:54.444275: step: 32/1545, loss: 7.588767766719684e-05 2023-01-23 19:05:55.295778: step: 34/1545, loss: 0.003553926246240735 2023-01-23 19:05:56.197194: step: 36/1545, loss: 0.09678065031766891 2023-01-23 19:05:57.082706: step: 38/1545, loss: 0.062053706496953964 2023-01-23 19:05:57.982038: step: 40/1545, loss: 0.0038579567335546017 2023-01-23 19:05:58.867084: step: 42/1545, loss: 0.0004985566483810544 2023-01-23 19:05:59.762853: step: 44/1545, loss: 0.020217305049300194 2023-01-23 19:06:00.622519: step: 46/1545, loss: 0.017206575721502304 2023-01-23 19:06:01.489143: step: 48/1545, loss: 0.0005482184351421893 2023-01-23 19:06:02.306716: step: 50/1545, loss: 0.00019348863861523569 2023-01-23 19:06:03.126371: step: 52/1545, loss: 0.016852062195539474 2023-01-23 19:06:04.008674: step: 54/1545, loss: 0.0006585203809663653 2023-01-23 19:06:04.947876: step: 56/1545, loss: 0.04105420783162117 2023-01-23 19:06:05.796033: step: 58/1545, loss: 0.0001988535950658843 2023-01-23 19:06:06.686769: step: 60/1545, loss: 0.0012866087490692735 2023-01-23 19:06:07.622223: step: 62/1545, loss: 0.0005017421790398657 2023-01-23 19:06:08.521730: step: 64/1545, loss: 1.1829032700916287e-05 2023-01-23 19:06:09.348371: step: 66/1545, loss: 0.09170318394899368 2023-01-23 19:06:10.206706: step: 68/1545, loss: 0.0054555959068238735 2023-01-23 19:06:11.098674: step: 70/1545, loss: 0.003544695908203721 2023-01-23 19:06:12.028357: step: 72/1545, loss: 0.00047889852430671453 2023-01-23 19:06:12.896160: step: 74/1545, loss: 0.006742110475897789 2023-01-23 19:06:13.797361: step: 76/1545, loss: 0.07708004862070084 2023-01-23 19:06:14.683896: step: 78/1545, loss: 0.019998861476778984 2023-01-23 19:06:15.546562: step: 80/1545, loss: 0.04831758886575699 2023-01-23 19:06:16.489623: step: 82/1545, loss: 0.207277312874794 2023-01-23 19:06:17.362490: step: 84/1545, loss: 0.0013830047100782394 2023-01-23 19:06:18.246299: step: 86/1545, loss: 0.0011801726650446653 2023-01-23 19:06:19.075267: step: 88/1545, loss: 0.0007465105736628175 2023-01-23 19:06:19.964800: step: 90/1545, loss: 0.013807853683829308 2023-01-23 19:06:20.910417: step: 92/1545, loss: 0.0020715196151286364 2023-01-23 19:06:21.770875: step: 94/1545, loss: 0.04027989134192467 2023-01-23 19:06:22.653194: step: 96/1545, loss: 2.72180259344168e-05 2023-01-23 19:06:23.557297: step: 98/1545, loss: 0.01010134443640709 2023-01-23 19:06:24.472169: step: 100/1545, loss: 0.00029554913635365665 2023-01-23 19:06:25.322392: step: 102/1545, loss: 7.002165511948988e-05 2023-01-23 19:06:26.182277: step: 104/1545, loss: -9.393776053912006e-06 2023-01-23 19:06:27.017694: step: 106/1545, loss: 0.04273701459169388 2023-01-23 19:06:27.893188: step: 108/1545, loss: 0.0024412297643721104 2023-01-23 19:06:28.737230: step: 110/1545, loss: 0.06938444823026657 2023-01-23 19:06:29.632441: step: 112/1545, loss: 0.1400614231824875 2023-01-23 19:06:30.488811: step: 114/1545, loss: 0.06229284033179283 2023-01-23 19:06:31.389197: step: 116/1545, loss: 0.0775790736079216 2023-01-23 19:06:32.280486: step: 118/1545, loss: 2.5822515453910455e-05 2023-01-23 19:06:33.127249: step: 120/1545, loss: 4.58432623418048e-05 2023-01-23 19:06:34.006791: step: 122/1545, loss: 0.12318822741508484 2023-01-23 19:06:34.880660: step: 124/1545, loss: 0.006389323156327009 2023-01-23 19:06:35.751622: step: 126/1545, loss: 0.006759497802704573 2023-01-23 19:06:36.597217: step: 128/1545, loss: -1.2187429092591628e-05 2023-01-23 19:06:37.548771: step: 130/1545, loss: 0.00031930976547300816 2023-01-23 19:06:38.394372: step: 132/1545, loss: 0.0014820897486060858 2023-01-23 19:06:39.230051: step: 134/1545, loss: 0.025070171803236008 2023-01-23 19:06:40.117221: step: 136/1545, loss: 0.00021668337285518646 2023-01-23 19:06:40.983600: step: 138/1545, loss: 7.911198918009177e-05 2023-01-23 19:06:41.837513: step: 140/1545, loss: 0.001473974552936852 2023-01-23 19:06:42.720844: step: 142/1545, loss: 0.001809227280318737 2023-01-23 19:06:43.601712: step: 144/1545, loss: 0.12347754091024399 2023-01-23 19:06:44.513436: step: 146/1545, loss: 0.13044972717761993 2023-01-23 19:06:45.393062: step: 148/1545, loss: 0.001282178214751184 2023-01-23 19:06:46.303122: step: 150/1545, loss: 0.0003557919408194721 2023-01-23 19:06:47.131940: step: 152/1545, loss: 0.0033676675520837307 2023-01-23 19:06:47.960423: step: 154/1545, loss: 0.0005137643311172724 2023-01-23 19:06:48.828359: step: 156/1545, loss: 0.18617555499076843 2023-01-23 19:06:49.720094: step: 158/1545, loss: 0.2661007344722748 2023-01-23 19:06:50.597501: step: 160/1545, loss: 0.00017348940309602767 2023-01-23 19:06:51.506323: step: 162/1545, loss: 0.0005578901036642492 2023-01-23 19:06:52.404991: step: 164/1545, loss: 0.26526227593421936 2023-01-23 19:06:53.314089: step: 166/1545, loss: 0.007285896223038435 2023-01-23 19:06:54.245269: step: 168/1545, loss: 0.006859316024929285 2023-01-23 19:06:55.183199: step: 170/1545, loss: 0.10321628302335739 2023-01-23 19:06:56.095881: step: 172/1545, loss: 0.00795475672930479 2023-01-23 19:06:56.967590: step: 174/1545, loss: 0.21439167857170105 2023-01-23 19:06:57.855369: step: 176/1545, loss: 0.004737480543553829 2023-01-23 19:06:58.758167: step: 178/1545, loss: 0.00020464129920583218 2023-01-23 19:06:59.652566: step: 180/1545, loss: 0.2495763897895813 2023-01-23 19:07:00.526345: step: 182/1545, loss: 0.000993480789475143 2023-01-23 19:07:01.388770: step: 184/1545, loss: 0.010805088095366955 2023-01-23 19:07:02.239930: step: 186/1545, loss: 0.3054555356502533 2023-01-23 19:07:03.071935: step: 188/1545, loss: 0.008616101928055286 2023-01-23 19:07:03.921057: step: 190/1545, loss: 0.0004794600827153772 2023-01-23 19:07:04.943983: step: 192/1545, loss: 0.0011971235508099198 2023-01-23 19:07:05.796124: step: 194/1545, loss: 0.0008335348684340715 2023-01-23 19:07:06.670595: step: 196/1545, loss: 0.005022253841161728 2023-01-23 19:07:07.521359: step: 198/1545, loss: 5.155483813723549e-05 2023-01-23 19:07:08.400514: step: 200/1545, loss: 0.0428331233561039 2023-01-23 19:07:09.242703: step: 202/1545, loss: 0.008885453455150127 2023-01-23 19:07:10.137383: step: 204/1545, loss: 0.9759181141853333 2023-01-23 19:07:11.020962: step: 206/1545, loss: 0.00012130352843087167 2023-01-23 19:07:11.889485: step: 208/1545, loss: 0.0006372020579874516 2023-01-23 19:07:12.802887: step: 210/1545, loss: 0.04059042036533356 2023-01-23 19:07:13.707556: step: 212/1545, loss: 8.585277100792155e-05 2023-01-23 19:07:14.559992: step: 214/1545, loss: 0.06389708817005157 2023-01-23 19:07:15.449435: step: 216/1545, loss: 0.005036494694650173 2023-01-23 19:07:16.346470: step: 218/1545, loss: 0.00014704687055200338 2023-01-23 19:07:17.253719: step: 220/1545, loss: 0.00019839096057694405 2023-01-23 19:07:18.200232: step: 222/1545, loss: 0.13851815462112427 2023-01-23 19:07:19.047524: step: 224/1545, loss: 0.01397984940558672 2023-01-23 19:07:19.900895: step: 226/1545, loss: 0.1584284007549286 2023-01-23 19:07:20.781509: step: 228/1545, loss: 0.0023622766602784395 2023-01-23 19:07:21.684773: step: 230/1545, loss: 0.0011236134450882673 2023-01-23 19:07:22.564910: step: 232/1545, loss: 0.37321704626083374 2023-01-23 19:07:23.452450: step: 234/1545, loss: 0.0003953553969040513 2023-01-23 19:07:24.311661: step: 236/1545, loss: 0.002521326532587409 2023-01-23 19:07:25.186147: step: 238/1545, loss: 0.9095276594161987 2023-01-23 19:07:26.079770: step: 240/1545, loss: 0.08825042098760605 2023-01-23 19:07:26.995583: step: 242/1545, loss: 0.021188609302043915 2023-01-23 19:07:27.922833: step: 244/1545, loss: 0.0009659290662966669 2023-01-23 19:07:28.825298: step: 246/1545, loss: 0.03692401945590973 2023-01-23 19:07:29.672332: step: 248/1545, loss: 0.008929645642638206 2023-01-23 19:07:30.556029: step: 250/1545, loss: 0.00041628896724432707 2023-01-23 19:07:31.465006: step: 252/1545, loss: 0.05584968999028206 2023-01-23 19:07:32.337725: step: 254/1545, loss: 0.00338686048053205 2023-01-23 19:07:33.220300: step: 256/1545, loss: 0.004590024705976248 2023-01-23 19:07:34.120846: step: 258/1545, loss: 0.007091199979186058 2023-01-23 19:07:35.049226: step: 260/1545, loss: 0.006280106492340565 2023-01-23 19:07:35.924617: step: 262/1545, loss: 0.0025409841910004616 2023-01-23 19:07:36.825594: step: 264/1545, loss: 0.0006611255230382085 2023-01-23 19:07:37.761525: step: 266/1545, loss: 0.00027831527404487133 2023-01-23 19:07:38.653178: step: 268/1545, loss: 0.00029576331144198775 2023-01-23 19:07:39.541063: step: 270/1545, loss: 0.0925820842385292 2023-01-23 19:07:40.457196: step: 272/1545, loss: 0.029029985889792442 2023-01-23 19:07:41.331815: step: 274/1545, loss: 0.26749393343925476 2023-01-23 19:07:42.187040: step: 276/1545, loss: 0.03866618126630783 2023-01-23 19:07:43.111871: step: 278/1545, loss: 0.00882280245423317 2023-01-23 19:07:43.956331: step: 280/1545, loss: 0.0734795555472374 2023-01-23 19:07:44.809251: step: 282/1545, loss: 5.458544364955742e-06 2023-01-23 19:07:45.683493: step: 284/1545, loss: 0.0032429727725684643 2023-01-23 19:07:46.517484: step: 286/1545, loss: 2.75037091341801e-05 2023-01-23 19:07:47.369000: step: 288/1545, loss: 0.008706789463758469 2023-01-23 19:07:48.285315: step: 290/1545, loss: 0.005182556342333555 2023-01-23 19:07:49.232611: step: 292/1545, loss: 0.03041226789355278 2023-01-23 19:07:50.152991: step: 294/1545, loss: 0.00012941999011673033 2023-01-23 19:07:51.002908: step: 296/1545, loss: 0.0001790129317669198 2023-01-23 19:07:51.860389: step: 298/1545, loss: 0.028218723833560944 2023-01-23 19:07:52.763518: step: 300/1545, loss: 0.0016400894382968545 2023-01-23 19:07:53.648229: step: 302/1545, loss: 0.00020541071717161685 2023-01-23 19:07:54.535719: step: 304/1545, loss: 0.024546422064304352 2023-01-23 19:07:55.441366: step: 306/1545, loss: 2.5700763217173517e-05 2023-01-23 19:07:56.347443: step: 308/1545, loss: 0.0002502161078155041 2023-01-23 19:07:57.233768: step: 310/1545, loss: 0.0006401802529580891 2023-01-23 19:07:58.093984: step: 312/1545, loss: 0.009855075739324093 2023-01-23 19:07:59.077691: step: 314/1545, loss: 0.029350770637392998 2023-01-23 19:08:00.041621: step: 316/1545, loss: 0.00011942583660129458 2023-01-23 19:08:00.903372: step: 318/1545, loss: 0.4112246632575989 2023-01-23 19:08:01.755239: step: 320/1545, loss: 0.00011263891065027565 2023-01-23 19:08:02.593055: step: 322/1545, loss: 0.0001756868150550872 2023-01-23 19:08:03.482210: step: 324/1545, loss: 3.5896897315979004e-05 2023-01-23 19:08:04.362426: step: 326/1545, loss: 0.02206423133611679 2023-01-23 19:08:05.254497: step: 328/1545, loss: 0.0005482625565491617 2023-01-23 19:08:06.128381: step: 330/1545, loss: 0.24902155995368958 2023-01-23 19:08:07.022491: step: 332/1545, loss: 0.00012743182014673948 2023-01-23 19:08:07.895996: step: 334/1545, loss: 0.017416367307305336 2023-01-23 19:08:08.771518: step: 336/1545, loss: 0.002061166800558567 2023-01-23 19:08:09.613265: step: 338/1545, loss: 0.0001780221937224269 2023-01-23 19:08:10.489451: step: 340/1545, loss: 0.030683794990181923 2023-01-23 19:08:11.398834: step: 342/1545, loss: 0.0007933517335914075 2023-01-23 19:08:12.302337: step: 344/1545, loss: 0.0016156978672370315 2023-01-23 19:08:13.193070: step: 346/1545, loss: 0.015791356563568115 2023-01-23 19:08:14.055784: step: 348/1545, loss: 0.00041854949085973203 2023-01-23 19:08:14.931694: step: 350/1545, loss: 0.22899603843688965 2023-01-23 19:08:15.805391: step: 352/1545, loss: 0.0005346925463527441 2023-01-23 19:08:16.674333: step: 354/1545, loss: 0.00016110001888591796 2023-01-23 19:08:17.563257: step: 356/1545, loss: 0.4175843298435211 2023-01-23 19:08:18.423165: step: 358/1545, loss: 0.002521716058254242 2023-01-23 19:08:19.274358: step: 360/1545, loss: 0.0023485415149480104 2023-01-23 19:08:20.128156: step: 362/1545, loss: 0.00025738339172676206 2023-01-23 19:08:20.994564: step: 364/1545, loss: 0.0048803165555000305 2023-01-23 19:08:21.839347: step: 366/1545, loss: 5.999719724059105e-05 2023-01-23 19:08:22.734904: step: 368/1545, loss: 0.21958348155021667 2023-01-23 19:08:23.679842: step: 370/1545, loss: 0.00947327259927988 2023-01-23 19:08:24.556245: step: 372/1545, loss: 0.01004581805318594 2023-01-23 19:08:25.419862: step: 374/1545, loss: 0.052651502192020416 2023-01-23 19:08:26.280067: step: 376/1545, loss: 0.02130655013024807 2023-01-23 19:08:27.139567: step: 378/1545, loss: 0.10402179509401321 2023-01-23 19:08:28.043583: step: 380/1545, loss: 0.006021004170179367 2023-01-23 19:08:28.934086: step: 382/1545, loss: 0.29497140645980835 2023-01-23 19:08:29.798409: step: 384/1545, loss: 0.120893195271492 2023-01-23 19:08:30.680051: step: 386/1545, loss: 0.00013324577594175935 2023-01-23 19:08:31.531369: step: 388/1545, loss: 0.001025001285597682 2023-01-23 19:08:32.446940: step: 390/1545, loss: 0.0005943958531133831 2023-01-23 19:08:33.307653: step: 392/1545, loss: 0.014108067378401756 2023-01-23 19:08:34.225742: step: 394/1545, loss: 0.06271710991859436 2023-01-23 19:08:35.153332: step: 396/1545, loss: 0.00010940924403257668 2023-01-23 19:08:36.049553: step: 398/1545, loss: 0.01936781406402588 2023-01-23 19:08:36.925184: step: 400/1545, loss: 0.024083511903882027 2023-01-23 19:08:37.780020: step: 402/1545, loss: 0.016976529732346535 2023-01-23 19:08:38.662264: step: 404/1545, loss: 0.00041701283771544695 2023-01-23 19:08:39.586110: step: 406/1545, loss: 0.006225263699889183 2023-01-23 19:08:40.536599: step: 408/1545, loss: 0.012203408405184746 2023-01-23 19:08:41.412957: step: 410/1545, loss: 0.040797315537929535 2023-01-23 19:08:42.283971: step: 412/1545, loss: 0.0006533346022479236 2023-01-23 19:08:43.207836: step: 414/1545, loss: 0.0015891543589532375 2023-01-23 19:08:44.048028: step: 416/1545, loss: 0.004161481279879808 2023-01-23 19:08:44.971911: step: 418/1545, loss: 0.0979854092001915 2023-01-23 19:08:45.835613: step: 420/1545, loss: 0.010450172238051891 2023-01-23 19:08:46.676418: step: 422/1545, loss: 0.0003009175125043839 2023-01-23 19:08:47.554308: step: 424/1545, loss: 0.00014779505727346987 2023-01-23 19:08:48.429970: step: 426/1545, loss: 0.00018502540478948504 2023-01-23 19:08:49.315183: step: 428/1545, loss: 0.00040749195613898337 2023-01-23 19:08:50.190851: step: 430/1545, loss: 0.055047255009412766 2023-01-23 19:08:51.053877: step: 432/1545, loss: 0.0020463201217353344 2023-01-23 19:08:51.953021: step: 434/1545, loss: 0.0035801841877400875 2023-01-23 19:08:52.810376: step: 436/1545, loss: 0.08151557296514511 2023-01-23 19:08:53.695728: step: 438/1545, loss: 0.0003014908288605511 2023-01-23 19:08:54.537464: step: 440/1545, loss: 0.0010114875622093678 2023-01-23 19:08:55.435582: step: 442/1545, loss: 0.09351053833961487 2023-01-23 19:08:56.310896: step: 444/1545, loss: 0.2413712441921234 2023-01-23 19:08:57.214823: step: 446/1545, loss: 0.0004138264630455524 2023-01-23 19:08:58.086389: step: 448/1545, loss: 0.6610814332962036 2023-01-23 19:08:58.991866: step: 450/1545, loss: 0.12285462021827698 2023-01-23 19:08:59.875310: step: 452/1545, loss: 0.028829721733927727 2023-01-23 19:09:00.744613: step: 454/1545, loss: 0.0009014451643452048 2023-01-23 19:09:01.635063: step: 456/1545, loss: 0.010023287497460842 2023-01-23 19:09:02.466376: step: 458/1545, loss: 0.00044147015432827175 2023-01-23 19:09:03.381643: step: 460/1545, loss: 0.006786767393350601 2023-01-23 19:09:04.282725: step: 462/1545, loss: 0.002893146825954318 2023-01-23 19:09:05.129386: step: 464/1545, loss: 0.03886387124657631 2023-01-23 19:09:06.006890: step: 466/1545, loss: 0.00017407075210940093 2023-01-23 19:09:06.894182: step: 468/1545, loss: 0.0036058048717677593 2023-01-23 19:09:07.769545: step: 470/1545, loss: 0.2237551510334015 2023-01-23 19:09:08.612175: step: 472/1545, loss: 0.004309484735131264 2023-01-23 19:09:09.517229: step: 474/1545, loss: 0.2700890600681305 2023-01-23 19:09:10.368711: step: 476/1545, loss: 0.0020218936260789633 2023-01-23 19:09:11.287388: step: 478/1545, loss: 0.0002440944517729804 2023-01-23 19:09:12.184196: step: 480/1545, loss: 0.04802916571497917 2023-01-23 19:09:13.048215: step: 482/1545, loss: 0.009536480531096458 2023-01-23 19:09:13.977313: step: 484/1545, loss: 0.00019734202942345291 2023-01-23 19:09:14.850022: step: 486/1545, loss: 0.051159314811229706 2023-01-23 19:09:15.741429: step: 488/1545, loss: 0.009362855926156044 2023-01-23 19:09:16.594275: step: 490/1545, loss: 0.24427902698516846 2023-01-23 19:09:17.438509: step: 492/1545, loss: 0.14371652901172638 2023-01-23 19:09:18.290363: step: 494/1545, loss: 0.018711049109697342 2023-01-23 19:09:19.219351: step: 496/1545, loss: 0.21812595427036285 2023-01-23 19:09:20.041237: step: 498/1545, loss: 0.000867542577907443 2023-01-23 19:09:20.897648: step: 500/1545, loss: 8.282967610284686e-05 2023-01-23 19:09:21.727474: step: 502/1545, loss: 0.0025000679306685925 2023-01-23 19:09:22.578636: step: 504/1545, loss: 0.0030039893463253975 2023-01-23 19:09:23.421576: step: 506/1545, loss: 0.10742393881082535 2023-01-23 19:09:24.272225: step: 508/1545, loss: 7.61867850087583e-05 2023-01-23 19:09:25.259635: step: 510/1545, loss: 0.00017002111417241395 2023-01-23 19:09:26.149224: step: 512/1545, loss: 0.0010668919421732426 2023-01-23 19:09:27.033031: step: 514/1545, loss: 2.6254314434481785e-05 2023-01-23 19:09:27.931161: step: 516/1545, loss: 0.055284518748521805 2023-01-23 19:09:28.772773: step: 518/1545, loss: 0.006607651244848967 2023-01-23 19:09:29.766985: step: 520/1545, loss: 0.00013517786283046007 2023-01-23 19:09:30.615547: step: 522/1545, loss: 0.024831563234329224 2023-01-23 19:09:31.510404: step: 524/1545, loss: 0.006448030471801758 2023-01-23 19:09:32.399394: step: 526/1545, loss: 0.005069446749985218 2023-01-23 19:09:33.277086: step: 528/1545, loss: 0.08066822588443756 2023-01-23 19:09:34.159868: step: 530/1545, loss: 0.0032559873070567846 2023-01-23 19:09:34.990597: step: 532/1545, loss: 0.0012180324411019683 2023-01-23 19:09:35.902843: step: 534/1545, loss: 0.0001857696333900094 2023-01-23 19:09:36.759691: step: 536/1545, loss: 0.0008373624295927584 2023-01-23 19:09:37.601945: step: 538/1545, loss: 0.029729707166552544 2023-01-23 19:09:38.452501: step: 540/1545, loss: 1.771051756804809e-06 2023-01-23 19:09:39.335684: step: 542/1545, loss: 0.17423616349697113 2023-01-23 19:09:40.275286: step: 544/1545, loss: 0.22523173689842224 2023-01-23 19:09:41.228628: step: 546/1545, loss: 0.011153762228786945 2023-01-23 19:09:42.085608: step: 548/1545, loss: 0.00017925331485457718 2023-01-23 19:09:42.919258: step: 550/1545, loss: 0.00043722125701606274 2023-01-23 19:09:43.807885: step: 552/1545, loss: 5.292183777783066e-05 2023-01-23 19:09:44.679681: step: 554/1545, loss: 0.016975849866867065 2023-01-23 19:09:45.531376: step: 556/1545, loss: 0.05112995579838753 2023-01-23 19:09:46.405276: step: 558/1545, loss: 0.008904825896024704 2023-01-23 19:09:47.301698: step: 560/1545, loss: 0.01057171169668436 2023-01-23 19:09:48.166004: step: 562/1545, loss: 0.2869764566421509 2023-01-23 19:09:49.032084: step: 564/1545, loss: 2.8912654670421034e-06 2023-01-23 19:09:49.921569: step: 566/1545, loss: 0.0008192483219318092 2023-01-23 19:09:50.807700: step: 568/1545, loss: 0.02383444644510746 2023-01-23 19:09:51.631508: step: 570/1545, loss: 0.00019274471560493112 2023-01-23 19:09:52.590856: step: 572/1545, loss: 0.004083485342562199 2023-01-23 19:09:53.482482: step: 574/1545, loss: 0.004216291941702366 2023-01-23 19:09:54.418261: step: 576/1545, loss: 0.04993319511413574 2023-01-23 19:09:55.281996: step: 578/1545, loss: 0.0012697060592472553 2023-01-23 19:09:56.165432: step: 580/1545, loss: 0.0003302820841781795 2023-01-23 19:09:57.104874: step: 582/1545, loss: 0.06287609785795212 2023-01-23 19:09:58.022003: step: 584/1545, loss: 1.0721057653427124 2023-01-23 19:09:58.943699: step: 586/1545, loss: 0.001653596991673112 2023-01-23 19:09:59.783721: step: 588/1545, loss: 0.0005622231983579695 2023-01-23 19:10:00.698270: step: 590/1545, loss: 0.006396031007170677 2023-01-23 19:10:01.605520: step: 592/1545, loss: 0.0006295538041740656 2023-01-23 19:10:02.549509: step: 594/1545, loss: 0.1781037300825119 2023-01-23 19:10:03.382550: step: 596/1545, loss: 0.0001478032791055739 2023-01-23 19:10:04.296561: step: 598/1545, loss: 0.014173969626426697 2023-01-23 19:10:05.162097: step: 600/1545, loss: 3.8644848245894536e-05 2023-01-23 19:10:06.110991: step: 602/1545, loss: 6.888250209158286e-05 2023-01-23 19:10:06.976786: step: 604/1545, loss: 0.10060054063796997 2023-01-23 19:10:07.884522: step: 606/1545, loss: 0.0009782559936866164 2023-01-23 19:10:08.767818: step: 608/1545, loss: 0.014720272272825241 2023-01-23 19:10:09.641757: step: 610/1545, loss: 0.012737171724438667 2023-01-23 19:10:10.490694: step: 612/1545, loss: 0.0003405640600249171 2023-01-23 19:10:11.326377: step: 614/1545, loss: 0.01200156006962061 2023-01-23 19:10:12.245615: step: 616/1545, loss: 0.23706144094467163 2023-01-23 19:10:13.109997: step: 618/1545, loss: 0.0007307771593332291 2023-01-23 19:10:13.982897: step: 620/1545, loss: 0.01652287319302559 2023-01-23 19:10:14.905278: step: 622/1545, loss: 0.011756914667785168 2023-01-23 19:10:15.797239: step: 624/1545, loss: 0.25588661432266235 2023-01-23 19:10:16.652411: step: 626/1545, loss: 0.0018460210412740707 2023-01-23 19:10:17.483944: step: 628/1545, loss: 0.0001467754627810791 2023-01-23 19:10:18.391366: step: 630/1545, loss: 0.022766711190342903 2023-01-23 19:10:19.308092: step: 632/1545, loss: 0.00027085805777460337 2023-01-23 19:10:20.199514: step: 634/1545, loss: 0.0012870554346591234 2023-01-23 19:10:21.068198: step: 636/1545, loss: 0.0012694548349827528 2023-01-23 19:10:21.996045: step: 638/1545, loss: 0.005729404743760824 2023-01-23 19:10:22.851051: step: 640/1545, loss: 0.20241262018680573 2023-01-23 19:10:23.733049: step: 642/1545, loss: 0.0012175643350929022 2023-01-23 19:10:24.616214: step: 644/1545, loss: 0.03891976550221443 2023-01-23 19:10:25.523282: step: 646/1545, loss: 0.08897169679403305 2023-01-23 19:10:26.423357: step: 648/1545, loss: 0.00039745893445797265 2023-01-23 19:10:27.261459: step: 650/1545, loss: 0.005552796646952629 2023-01-23 19:10:28.140799: step: 652/1545, loss: 0.00024954392574727535 2023-01-23 19:10:29.131125: step: 654/1545, loss: 0.019571661949157715 2023-01-23 19:10:30.054487: step: 656/1545, loss: 0.0268411785364151 2023-01-23 19:10:30.908129: step: 658/1545, loss: 0.02227872423827648 2023-01-23 19:10:31.827734: step: 660/1545, loss: 0.19987855851650238 2023-01-23 19:10:32.716526: step: 662/1545, loss: 0.00020645603945013136 2023-01-23 19:10:33.575275: step: 664/1545, loss: 0.0015659581404179335 2023-01-23 19:10:34.458726: step: 666/1545, loss: 1.1969395875930786 2023-01-23 19:10:35.342341: step: 668/1545, loss: 0.09551423788070679 2023-01-23 19:10:36.238798: step: 670/1545, loss: 0.004893602337688208 2023-01-23 19:10:37.111523: step: 672/1545, loss: 0.18940114974975586 2023-01-23 19:10:37.986739: step: 674/1545, loss: 0.049845632165670395 2023-01-23 19:10:38.812282: step: 676/1545, loss: 0.002059096936136484 2023-01-23 19:10:39.663116: step: 678/1545, loss: 0.0002336949110031128 2023-01-23 19:10:40.574542: step: 680/1545, loss: 0.08079734444618225 2023-01-23 19:10:41.437945: step: 682/1545, loss: 0.7510579228401184 2023-01-23 19:10:42.309299: step: 684/1545, loss: 0.2429652065038681 2023-01-23 19:10:43.166644: step: 686/1545, loss: 0.0006231706938706338 2023-01-23 19:10:44.022990: step: 688/1545, loss: 0.003327279584482312 2023-01-23 19:10:44.944063: step: 690/1545, loss: 0.2264004945755005 2023-01-23 19:10:45.892904: step: 692/1545, loss: 0.015300503931939602 2023-01-23 19:10:46.784700: step: 694/1545, loss: 0.003065015422180295 2023-01-23 19:10:47.648458: step: 696/1545, loss: 0.0005846611456945539 2023-01-23 19:10:48.574170: step: 698/1545, loss: 0.006978344637900591 2023-01-23 19:10:49.432165: step: 700/1545, loss: 0.29482394456863403 2023-01-23 19:10:50.281610: step: 702/1545, loss: 0.0017319991020485759 2023-01-23 19:10:51.168973: step: 704/1545, loss: 0.00022333729430101812 2023-01-23 19:10:52.069762: step: 706/1545, loss: 0.00061602215282619 2023-01-23 19:10:52.922985: step: 708/1545, loss: 0.028520822525024414 2023-01-23 19:10:53.782293: step: 710/1545, loss: 0.0028934753499925137 2023-01-23 19:10:54.664809: step: 712/1545, loss: 0.05211123079061508 2023-01-23 19:10:55.640216: step: 714/1545, loss: 0.015275178477168083 2023-01-23 19:10:56.508764: step: 716/1545, loss: 0.1517922580242157 2023-01-23 19:10:57.368036: step: 718/1545, loss: 0.00042235947330482304 2023-01-23 19:10:58.249504: step: 720/1545, loss: 0.004125501494854689 2023-01-23 19:10:59.175315: step: 722/1545, loss: 0.018126070499420166 2023-01-23 19:11:00.057363: step: 724/1545, loss: 0.001060422626323998 2023-01-23 19:11:00.995491: step: 726/1545, loss: 0.04516058787703514 2023-01-23 19:11:01.868811: step: 728/1545, loss: 0.004939266014844179 2023-01-23 19:11:02.760672: step: 730/1545, loss: 0.0024375272914767265 2023-01-23 19:11:03.662234: step: 732/1545, loss: 0.0008380748913623393 2023-01-23 19:11:04.562379: step: 734/1545, loss: 0.0003481550666037947 2023-01-23 19:11:05.467231: step: 736/1545, loss: 0.003911304287612438 2023-01-23 19:11:06.361732: step: 738/1545, loss: 0.004634062293916941 2023-01-23 19:11:07.275560: step: 740/1545, loss: 0.01267242431640625 2023-01-23 19:11:08.121479: step: 742/1545, loss: 0.035965532064437866 2023-01-23 19:11:08.978378: step: 744/1545, loss: 0.025358693674206734 2023-01-23 19:11:09.829183: step: 746/1545, loss: 0.0003701251989696175 2023-01-23 19:11:10.708815: step: 748/1545, loss: 0.0001446451060473919 2023-01-23 19:11:11.570347: step: 750/1545, loss: 0.0011820584768429399 2023-01-23 19:11:12.471670: step: 752/1545, loss: 0.054850634187459946 2023-01-23 19:11:13.328316: step: 754/1545, loss: 0.0007744847680442035 2023-01-23 19:11:14.187984: step: 756/1545, loss: 0.12502896785736084 2023-01-23 19:11:15.135260: step: 758/1545, loss: 0.00016189386951737106 2023-01-23 19:11:16.060534: step: 760/1545, loss: 0.0015442355070263147 2023-01-23 19:11:16.937110: step: 762/1545, loss: 0.00980526115745306 2023-01-23 19:11:17.799632: step: 764/1545, loss: 0.0003398528497200459 2023-01-23 19:11:18.696749: step: 766/1545, loss: 0.0010015086736530066 2023-01-23 19:11:19.613540: step: 768/1545, loss: 0.19289320707321167 2023-01-23 19:11:20.501681: step: 770/1545, loss: 0.00025667386944405735 2023-01-23 19:11:21.382038: step: 772/1545, loss: 0.0008896550280041993 2023-01-23 19:11:22.263133: step: 774/1545, loss: 0.6553465723991394 2023-01-23 19:11:23.229560: step: 776/1545, loss: 0.0695444867014885 2023-01-23 19:11:24.158144: step: 778/1545, loss: 0.30548760294914246 2023-01-23 19:11:25.058676: step: 780/1545, loss: 0.13190290331840515 2023-01-23 19:11:25.920353: step: 782/1545, loss: 9.483368921792135e-05 2023-01-23 19:11:26.802843: step: 784/1545, loss: 0.2854980230331421 2023-01-23 19:11:27.673038: step: 786/1545, loss: 0.003057638881728053 2023-01-23 19:11:28.582664: step: 788/1545, loss: 0.00013063818914815784 2023-01-23 19:11:29.552308: step: 790/1545, loss: 7.530878065153956e-05 2023-01-23 19:11:30.421240: step: 792/1545, loss: 0.00014272707630880177 2023-01-23 19:11:31.299206: step: 794/1545, loss: 0.0062904078513383865 2023-01-23 19:11:32.222023: step: 796/1545, loss: 0.1882741004228592 2023-01-23 19:11:33.135939: step: 798/1545, loss: 0.0022855321876704693 2023-01-23 19:11:34.004447: step: 800/1545, loss: 0.0004013259313069284 2023-01-23 19:11:34.897002: step: 802/1545, loss: 0.06985463947057724 2023-01-23 19:11:35.781389: step: 804/1545, loss: 0.0002896757796406746 2023-01-23 19:11:36.742590: step: 806/1545, loss: 0.3788682222366333 2023-01-23 19:11:37.621253: step: 808/1545, loss: 0.32797423005104065 2023-01-23 19:11:38.494182: step: 810/1545, loss: 6.59171273582615e-05 2023-01-23 19:11:39.357567: step: 812/1545, loss: 0.44524797797203064 2023-01-23 19:11:40.256302: step: 814/1545, loss: 0.0002458709932398051 2023-01-23 19:11:41.206610: step: 816/1545, loss: 1.2727699279785156 2023-01-23 19:11:42.119706: step: 818/1545, loss: 0.06563964486122131 2023-01-23 19:11:43.058209: step: 820/1545, loss: 0.017633195966482162 2023-01-23 19:11:43.968161: step: 822/1545, loss: 0.094331294298172 2023-01-23 19:11:44.842912: step: 824/1545, loss: 0.002430680440738797 2023-01-23 19:11:45.702912: step: 826/1545, loss: 0.020148199051618576 2023-01-23 19:11:46.615961: step: 828/1545, loss: 0.011222165077924728 2023-01-23 19:11:47.588645: step: 830/1545, loss: 0.00011410775186959654 2023-01-23 19:11:48.472105: step: 832/1545, loss: 0.002168345032259822 2023-01-23 19:11:49.339948: step: 834/1545, loss: 0.00023312105622608215 2023-01-23 19:11:50.200936: step: 836/1545, loss: 0.22652152180671692 2023-01-23 19:11:51.055749: step: 838/1545, loss: 7.868883403716609e-05 2023-01-23 19:11:51.991779: step: 840/1545, loss: 0.0006492761895060539 2023-01-23 19:11:52.900727: step: 842/1545, loss: 9.312322072219104e-05 2023-01-23 19:11:53.765228: step: 844/1545, loss: 0.0015005660243332386 2023-01-23 19:11:54.636300: step: 846/1545, loss: 0.0021125315688550472 2023-01-23 19:11:55.502037: step: 848/1545, loss: 0.001461838255636394 2023-01-23 19:11:56.353548: step: 850/1545, loss: 0.18300490081310272 2023-01-23 19:11:57.249043: step: 852/1545, loss: 1.4557584524154663 2023-01-23 19:11:58.180064: step: 854/1545, loss: 0.027604958042502403 2023-01-23 19:11:59.051012: step: 856/1545, loss: 0.004536550957709551 2023-01-23 19:11:59.917655: step: 858/1545, loss: 0.0512036494910717 2023-01-23 19:12:00.840635: step: 860/1545, loss: 0.11144096404314041 2023-01-23 19:12:01.697810: step: 862/1545, loss: 0.08885053545236588 2023-01-23 19:12:02.541943: step: 864/1545, loss: 0.001864808495156467 2023-01-23 19:12:03.429167: step: 866/1545, loss: 4.473302760743536e-05 2023-01-23 19:12:04.373109: step: 868/1545, loss: 0.0006175453308969736 2023-01-23 19:12:05.300097: step: 870/1545, loss: 0.0011788851115852594 2023-01-23 19:12:06.228087: step: 872/1545, loss: 0.014318839646875858 2023-01-23 19:12:07.157889: step: 874/1545, loss: 0.0002231853432022035 2023-01-23 19:12:08.124544: step: 876/1545, loss: 0.012531363405287266 2023-01-23 19:12:08.978690: step: 878/1545, loss: 8.112141222227365e-05 2023-01-23 19:12:09.880212: step: 880/1545, loss: 0.000863507913891226 2023-01-23 19:12:10.772493: step: 882/1545, loss: 0.6128362417221069 2023-01-23 19:12:11.647887: step: 884/1545, loss: 0.010631721466779709 2023-01-23 19:12:12.511034: step: 886/1545, loss: 0.002684112638235092 2023-01-23 19:12:13.409133: step: 888/1545, loss: 0.016961287707090378 2023-01-23 19:12:14.299490: step: 890/1545, loss: 0.0753273144364357 2023-01-23 19:12:15.197135: step: 892/1545, loss: 0.032236482948064804 2023-01-23 19:12:16.042332: step: 894/1545, loss: 0.002450559986755252 2023-01-23 19:12:16.952512: step: 896/1545, loss: 0.0005399989895522594 2023-01-23 19:12:17.826588: step: 898/1545, loss: 0.1409933865070343 2023-01-23 19:12:18.673206: step: 900/1545, loss: 1.2446329593658447 2023-01-23 19:12:19.567834: step: 902/1545, loss: 0.030896183103322983 2023-01-23 19:12:20.496115: step: 904/1545, loss: 0.2721743583679199 2023-01-23 19:12:21.374301: step: 906/1545, loss: 0.025800105184316635 2023-01-23 19:12:22.232782: step: 908/1545, loss: 0.04986492916941643 2023-01-23 19:12:23.153474: step: 910/1545, loss: 0.4179810881614685 2023-01-23 19:12:24.006392: step: 912/1545, loss: 1.6532485460629687e-05 2023-01-23 19:12:24.857020: step: 914/1545, loss: 0.009830246679484844 2023-01-23 19:12:25.780884: step: 916/1545, loss: 0.05420053005218506 2023-01-23 19:12:26.638166: step: 918/1545, loss: 0.000942783139180392 2023-01-23 19:12:27.496009: step: 920/1545, loss: 0.03230242803692818 2023-01-23 19:12:28.417819: step: 922/1545, loss: 0.0006087133660912514 2023-01-23 19:12:29.314125: step: 924/1545, loss: 0.36846286058425903 2023-01-23 19:12:30.197592: step: 926/1545, loss: 0.00040737114613875747 2023-01-23 19:12:31.056298: step: 928/1545, loss: 0.003735619131475687 2023-01-23 19:12:31.949680: step: 930/1545, loss: 0.011987344361841679 2023-01-23 19:12:32.830687: step: 932/1545, loss: 0.005340700037777424 2023-01-23 19:12:33.701961: step: 934/1545, loss: 0.12043526023626328 2023-01-23 19:12:34.625835: step: 936/1545, loss: 0.0008827205165289342 2023-01-23 19:12:35.495082: step: 938/1545, loss: 0.007485151290893555 2023-01-23 19:12:36.334110: step: 940/1545, loss: 0.005640501156449318 2023-01-23 19:12:37.287466: step: 942/1545, loss: 0.003740191925317049 2023-01-23 19:12:38.204876: step: 944/1545, loss: 0.024383848533034325 2023-01-23 19:12:39.067849: step: 946/1545, loss: 0.03603712096810341 2023-01-23 19:12:39.977020: step: 948/1545, loss: 0.00036411129985935986 2023-01-23 19:12:40.860569: step: 950/1545, loss: 0.0035138893872499466 2023-01-23 19:12:41.715954: step: 952/1545, loss: 0.08107847720384598 2023-01-23 19:12:42.619949: step: 954/1545, loss: 0.00016945989045780152 2023-01-23 19:12:43.500165: step: 956/1545, loss: 0.14569593966007233 2023-01-23 19:12:44.345919: step: 958/1545, loss: 0.0010319973807781935 2023-01-23 19:12:45.215595: step: 960/1545, loss: 0.0013739069690927863 2023-01-23 19:12:46.084824: step: 962/1545, loss: 0.046219002455472946 2023-01-23 19:12:47.004375: step: 964/1545, loss: 0.0089128278195858 2023-01-23 19:12:47.892279: step: 966/1545, loss: 0.0004923247033730149 2023-01-23 19:12:48.822607: step: 968/1545, loss: 0.03949396684765816 2023-01-23 19:12:49.758753: step: 970/1545, loss: 0.02407734841108322 2023-01-23 19:12:50.653405: step: 972/1545, loss: 0.46674829721450806 2023-01-23 19:12:51.540609: step: 974/1545, loss: 0.002444675425067544 2023-01-23 19:12:52.455336: step: 976/1545, loss: 0.0005807591369375587 2023-01-23 19:12:53.307955: step: 978/1545, loss: 0.00026741635520011187 2023-01-23 19:12:54.187731: step: 980/1545, loss: 0.00109320308547467 2023-01-23 19:12:55.030160: step: 982/1545, loss: 0.18682250380516052 2023-01-23 19:12:55.931384: step: 984/1545, loss: 0.09628193080425262 2023-01-23 19:12:56.837299: step: 986/1545, loss: 0.00514263566583395 2023-01-23 19:12:57.704000: step: 988/1545, loss: 0.0018746666610240936 2023-01-23 19:12:58.609193: step: 990/1545, loss: 0.0011970760533586144 2023-01-23 19:12:59.470127: step: 992/1545, loss: 0.0007450021803379059 2023-01-23 19:13:00.346336: step: 994/1545, loss: 0.002392949303612113 2023-01-23 19:13:01.210589: step: 996/1545, loss: 7.653485954506323e-05 2023-01-23 19:13:02.196832: step: 998/1545, loss: 0.0022282705176621675 2023-01-23 19:13:03.095424: step: 1000/1545, loss: 6.84316546539776e-05 2023-01-23 19:13:04.004411: step: 1002/1545, loss: 0.00014502505655400455 2023-01-23 19:13:04.852695: step: 1004/1545, loss: 0.0002703855570871383 2023-01-23 19:13:05.767714: step: 1006/1545, loss: 0.01183704286813736 2023-01-23 19:13:06.611906: step: 1008/1545, loss: 0.006107013672590256 2023-01-23 19:13:07.469764: step: 1010/1545, loss: 0.00017475664208177477 2023-01-23 19:13:08.362942: step: 1012/1545, loss: 0.00040400412399321795 2023-01-23 19:13:09.234713: step: 1014/1545, loss: 0.0001886377140181139 2023-01-23 19:13:10.132189: step: 1016/1545, loss: 0.004459078889340162 2023-01-23 19:13:10.979194: step: 1018/1545, loss: 8.686182263772935e-05 2023-01-23 19:13:11.840969: step: 1020/1545, loss: 0.001857032417319715 2023-01-23 19:13:12.742445: step: 1022/1545, loss: 0.043191395699977875 2023-01-23 19:13:13.672201: step: 1024/1545, loss: 0.06081823259592056 2023-01-23 19:13:14.558609: step: 1026/1545, loss: 0.0008190863882191479 2023-01-23 19:13:15.430443: step: 1028/1545, loss: 0.21023361384868622 2023-01-23 19:13:16.360959: step: 1030/1545, loss: 0.062375687062740326 2023-01-23 19:13:17.209311: step: 1032/1545, loss: 0.09401915222406387 2023-01-23 19:13:18.074961: step: 1034/1545, loss: 0.018905436620116234 2023-01-23 19:13:18.977431: step: 1036/1545, loss: 6.692008901154622e-05 2023-01-23 19:13:19.880756: step: 1038/1545, loss: 0.00022996350890025496 2023-01-23 19:13:20.745574: step: 1040/1545, loss: 0.001708302297629416 2023-01-23 19:13:21.629211: step: 1042/1545, loss: 0.02094760723412037 2023-01-23 19:13:22.450060: step: 1044/1545, loss: 9.274444892071187e-05 2023-01-23 19:13:23.346498: step: 1046/1545, loss: 0.00030644505750387907 2023-01-23 19:13:24.204564: step: 1048/1545, loss: 0.033162228763103485 2023-01-23 19:13:25.118894: step: 1050/1545, loss: 6.900052540004253e-05 2023-01-23 19:13:26.005693: step: 1052/1545, loss: 5.961023816780653e-06 2023-01-23 19:13:26.883242: step: 1054/1545, loss: 0.006207711528986692 2023-01-23 19:13:27.813355: step: 1056/1545, loss: 0.019757971167564392 2023-01-23 19:13:28.718455: step: 1058/1545, loss: 0.004877444356679916 2023-01-23 19:13:29.636709: step: 1060/1545, loss: 0.0001793463743524626 2023-01-23 19:13:30.528170: step: 1062/1545, loss: 6.410287460312247e-05 2023-01-23 19:13:31.404990: step: 1064/1545, loss: 0.011205285787582397 2023-01-23 19:13:32.354658: step: 1066/1545, loss: 2.1435153030324727e-07 2023-01-23 19:13:33.239183: step: 1068/1545, loss: 0.048698049038648605 2023-01-23 19:13:34.143488: step: 1070/1545, loss: -1.4433263459068257e-05 2023-01-23 19:13:35.039165: step: 1072/1545, loss: 0.007776045240461826 2023-01-23 19:13:35.925119: step: 1074/1545, loss: 0.00013738351117353886 2023-01-23 19:13:36.799522: step: 1076/1545, loss: 0.03443710505962372 2023-01-23 19:13:37.674989: step: 1078/1545, loss: 0.0034142970107495785 2023-01-23 19:13:38.555399: step: 1080/1545, loss: 0.03790991008281708 2023-01-23 19:13:39.461480: step: 1082/1545, loss: 0.0008891999023035169 2023-01-23 19:13:40.331999: step: 1084/1545, loss: 0.0006881713634356856 2023-01-23 19:13:41.205239: step: 1086/1545, loss: 0.004725800361484289 2023-01-23 19:13:42.066414: step: 1088/1545, loss: 0.01620534621179104 2023-01-23 19:13:42.970579: step: 1090/1545, loss: 0.00019618475926108658 2023-01-23 19:13:43.877314: step: 1092/1545, loss: 0.00015429849736392498 2023-01-23 19:13:44.753326: step: 1094/1545, loss: 0.19349965453147888 2023-01-23 19:13:45.575321: step: 1096/1545, loss: 0.01661144383251667 2023-01-23 19:13:46.463725: step: 1098/1545, loss: 0.0060950168408453465 2023-01-23 19:13:47.329368: step: 1100/1545, loss: 0.2711898386478424 2023-01-23 19:13:48.198768: step: 1102/1545, loss: 0.01772371120750904 2023-01-23 19:13:49.047482: step: 1104/1545, loss: 6.664180546067655e-05 2023-01-23 19:13:49.959595: step: 1106/1545, loss: 0.001374960644170642 2023-01-23 19:13:50.802624: step: 1108/1545, loss: 0.0001360176975140348 2023-01-23 19:13:51.662743: step: 1110/1545, loss: 0.07846085727214813 2023-01-23 19:13:52.518463: step: 1112/1545, loss: 0.1318662166595459 2023-01-23 19:13:53.353699: step: 1114/1545, loss: 0.002110469387844205 2023-01-23 19:13:54.244804: step: 1116/1545, loss: 0.0009577638120390475 2023-01-23 19:13:55.151277: step: 1118/1545, loss: 0.08914719521999359 2023-01-23 19:13:56.089816: step: 1120/1545, loss: 0.07075770944356918 2023-01-23 19:13:56.957439: step: 1122/1545, loss: 0.122836172580719 2023-01-23 19:13:57.805993: step: 1124/1545, loss: 0.00016437028534710407 2023-01-23 19:13:58.649681: step: 1126/1545, loss: 0.0021176820155233145 2023-01-23 19:13:59.547442: step: 1128/1545, loss: 0.00286883651278913 2023-01-23 19:14:00.495916: step: 1130/1545, loss: 0.19685079157352448 2023-01-23 19:14:01.375629: step: 1132/1545, loss: 0.005537544842809439 2023-01-23 19:14:02.281332: step: 1134/1545, loss: 0.0004497482441365719 2023-01-23 19:14:03.150973: step: 1136/1545, loss: 0.00016795509145595133 2023-01-23 19:14:04.059549: step: 1138/1545, loss: 0.0393860824406147 2023-01-23 19:14:04.948655: step: 1140/1545, loss: 0.01585136167705059 2023-01-23 19:14:05.826614: step: 1142/1545, loss: 0.0009796891827136278 2023-01-23 19:14:06.673053: step: 1144/1545, loss: 0.00011709659884218127 2023-01-23 19:14:07.521972: step: 1146/1545, loss: 0.08886104077100754 2023-01-23 19:14:08.355220: step: 1148/1545, loss: 0.0023008515127003193 2023-01-23 19:14:09.198380: step: 1150/1545, loss: 0.004955301061272621 2023-01-23 19:14:10.099744: step: 1152/1545, loss: 0.002486767014488578 2023-01-23 19:14:10.981992: step: 1154/1545, loss: 0.0034077938180416822 2023-01-23 19:14:11.872024: step: 1156/1545, loss: 0.011152222752571106 2023-01-23 19:14:12.705274: step: 1158/1545, loss: 0.00026549139874987304 2023-01-23 19:14:13.585463: step: 1160/1545, loss: 0.0004908006521873176 2023-01-23 19:14:14.432412: step: 1162/1545, loss: 0.00010499532072572038 2023-01-23 19:14:15.377758: step: 1164/1545, loss: 0.0007684988668188453 2023-01-23 19:14:16.273194: step: 1166/1545, loss: 0.0009746256982907653 2023-01-23 19:14:17.139150: step: 1168/1545, loss: 0.00034658703953027725 2023-01-23 19:14:18.008002: step: 1170/1545, loss: 0.003430568380281329 2023-01-23 19:14:18.868344: step: 1172/1545, loss: 0.000848533003591001 2023-01-23 19:14:19.806580: step: 1174/1545, loss: 0.0015427801990881562 2023-01-23 19:14:20.650147: step: 1176/1545, loss: 0.00243488815613091 2023-01-23 19:14:21.516529: step: 1178/1545, loss: 0.0026911518070846796 2023-01-23 19:14:22.392689: step: 1180/1545, loss: 0.00453027430921793 2023-01-23 19:14:23.236203: step: 1182/1545, loss: 0.005313053727149963 2023-01-23 19:14:24.099931: step: 1184/1545, loss: 0.03456074371933937 2023-01-23 19:14:24.979139: step: 1186/1545, loss: 0.0008472480112686753 2023-01-23 19:14:25.887486: step: 1188/1545, loss: 0.03328516706824303 2023-01-23 19:14:26.714764: step: 1190/1545, loss: 0.00016433504060842097 2023-01-23 19:14:27.600163: step: 1192/1545, loss: 4.0566832467447966e-05 2023-01-23 19:14:28.450218: step: 1194/1545, loss: 0.09499210864305496 2023-01-23 19:14:29.343596: step: 1196/1545, loss: 0.01761135831475258 2023-01-23 19:14:30.360442: step: 1198/1545, loss: 0.00021065512555651367 2023-01-23 19:14:31.218517: step: 1200/1545, loss: 0.0015035424148663878 2023-01-23 19:14:32.076681: step: 1202/1545, loss: 0.0010304513853043318 2023-01-23 19:14:32.946044: step: 1204/1545, loss: 0.32927176356315613 2023-01-23 19:14:33.805143: step: 1206/1545, loss: 0.007404712960124016 2023-01-23 19:14:34.703357: step: 1208/1545, loss: 0.006361131090670824 2023-01-23 19:14:35.557842: step: 1210/1545, loss: 0.00415072264149785 2023-01-23 19:14:36.415283: step: 1212/1545, loss: 7.349434599746019e-05 2023-01-23 19:14:37.255464: step: 1214/1545, loss: 0.0003676224732771516 2023-01-23 19:14:38.106464: step: 1216/1545, loss: 0.41618117690086365 2023-01-23 19:14:38.934160: step: 1218/1545, loss: 0.0006872438825666904 2023-01-23 19:14:39.822450: step: 1220/1545, loss: 0.00018404025468043983 2023-01-23 19:14:40.673122: step: 1222/1545, loss: 0.004239446949213743 2023-01-23 19:14:41.556588: step: 1224/1545, loss: 3.0843155400361866e-05 2023-01-23 19:14:42.443252: step: 1226/1545, loss: 6.943315383978188e-05 2023-01-23 19:14:43.294812: step: 1228/1545, loss: 2.2537340555572882e-05 2023-01-23 19:14:44.164524: step: 1230/1545, loss: 0.12978720664978027 2023-01-23 19:14:45.025018: step: 1232/1545, loss: 0.00011535225348779932 2023-01-23 19:14:45.852266: step: 1234/1545, loss: 0.0012796601513400674 2023-01-23 19:14:46.677404: step: 1236/1545, loss: 0.2779741585254669 2023-01-23 19:14:47.604902: step: 1238/1545, loss: 0.0003401456051506102 2023-01-23 19:14:48.498140: step: 1240/1545, loss: 0.00011751341662602499 2023-01-23 19:14:49.422333: step: 1242/1545, loss: 0.16500607132911682 2023-01-23 19:14:50.299338: step: 1244/1545, loss: 0.00011111108324257657 2023-01-23 19:14:51.163743: step: 1246/1545, loss: 0.05245205760002136 2023-01-23 19:14:52.018934: step: 1248/1545, loss: 0.024407586082816124 2023-01-23 19:14:52.881328: step: 1250/1545, loss: 0.0004781559109687805 2023-01-23 19:14:53.746417: step: 1252/1545, loss: 0.06592976301908493 2023-01-23 19:14:54.669806: step: 1254/1545, loss: 0.2107178270816803 2023-01-23 19:14:55.586402: step: 1256/1545, loss: 0.06523731350898743 2023-01-23 19:14:56.517732: step: 1258/1545, loss: 0.19390156865119934 2023-01-23 19:14:57.380798: step: 1260/1545, loss: 0.00024137302534654737 2023-01-23 19:14:58.281369: step: 1262/1545, loss: 0.09377589821815491 2023-01-23 19:14:59.114539: step: 1264/1545, loss: 0.011303628794848919 2023-01-23 19:15:00.040967: step: 1266/1545, loss: 0.00038103078259155154 2023-01-23 19:15:00.916124: step: 1268/1545, loss: 0.09241803735494614 2023-01-23 19:15:01.829709: step: 1270/1545, loss: 0.0030817911028862 2023-01-23 19:15:02.731108: step: 1272/1545, loss: 0.2306455820798874 2023-01-23 19:15:03.620626: step: 1274/1545, loss: 0.052920665591955185 2023-01-23 19:15:04.522837: step: 1276/1545, loss: 0.16779832541942596 2023-01-23 19:15:05.380738: step: 1278/1545, loss: 0.0071496907621622086 2023-01-23 19:15:06.300288: step: 1280/1545, loss: 0.40935903787612915 2023-01-23 19:15:07.218481: step: 1282/1545, loss: 0.08577589690685272 2023-01-23 19:15:08.170838: step: 1284/1545, loss: 0.03386440873146057 2023-01-23 19:15:08.976387: step: 1286/1545, loss: 0.0002180873998440802 2023-01-23 19:15:09.845858: step: 1288/1545, loss: 0.051275864243507385 2023-01-23 19:15:10.766907: step: 1290/1545, loss: 0.0015860236017033458 2023-01-23 19:15:11.630377: step: 1292/1545, loss: 0.024611853063106537 2023-01-23 19:15:12.468533: step: 1294/1545, loss: 0.01267009973526001 2023-01-23 19:15:13.372755: step: 1296/1545, loss: 0.21604891121387482 2023-01-23 19:15:14.241428: step: 1298/1545, loss: 0.004092494957149029 2023-01-23 19:15:15.079537: step: 1300/1545, loss: 0.0010425153886899352 2023-01-23 19:15:15.946083: step: 1302/1545, loss: 0.0006926603964529932 2023-01-23 19:15:16.851102: step: 1304/1545, loss: 0.0025401529856026173 2023-01-23 19:15:17.727344: step: 1306/1545, loss: 0.002242493676021695 2023-01-23 19:15:18.623497: step: 1308/1545, loss: 0.00045534822857007384 2023-01-23 19:15:19.539059: step: 1310/1545, loss: 0.046103790402412415 2023-01-23 19:15:20.392935: step: 1312/1545, loss: 0.0010310736251994967 2023-01-23 19:15:21.267764: step: 1314/1545, loss: 0.06156909093260765 2023-01-23 19:15:22.101408: step: 1316/1545, loss: 0.002550747012719512 2023-01-23 19:15:22.983446: step: 1318/1545, loss: 0.18423451483249664 2023-01-23 19:15:23.825989: step: 1320/1545, loss: 0.000516530591994524 2023-01-23 19:15:24.815702: step: 1322/1545, loss: 0.44759058952331543 2023-01-23 19:15:25.705289: step: 1324/1545, loss: 0.00392758846282959 2023-01-23 19:15:26.627927: step: 1326/1545, loss: 0.5291252732276917 2023-01-23 19:15:27.478173: step: 1328/1545, loss: 0.04863816127181053 2023-01-23 19:15:28.314305: step: 1330/1545, loss: 0.027849646285176277 2023-01-23 19:15:29.224242: step: 1332/1545, loss: 0.007865198887884617 2023-01-23 19:15:30.120327: step: 1334/1545, loss: 0.1601136326789856 2023-01-23 19:15:31.026813: step: 1336/1545, loss: 0.032082848250865936 2023-01-23 19:15:31.904373: step: 1338/1545, loss: 0.0005201667663641274 2023-01-23 19:15:32.753177: step: 1340/1545, loss: 0.09886928647756577 2023-01-23 19:15:33.665969: step: 1342/1545, loss: 0.007973269559442997 2023-01-23 19:15:34.541854: step: 1344/1545, loss: 0.015915293246507645 2023-01-23 19:15:35.408339: step: 1346/1545, loss: 3.215337710571475e-05 2023-01-23 19:15:36.241913: step: 1348/1545, loss: 0.0003291614120826125 2023-01-23 19:15:37.119167: step: 1350/1545, loss: 0.882987380027771 2023-01-23 19:15:37.997020: step: 1352/1545, loss: 0.00059042579960078 2023-01-23 19:15:38.867046: step: 1354/1545, loss: 0.0008132775546982884 2023-01-23 19:15:39.706443: step: 1356/1545, loss: 0.00011937538511119783 2023-01-23 19:15:40.594404: step: 1358/1545, loss: 0.007877246476709843 2023-01-23 19:15:41.485017: step: 1360/1545, loss: 0.009328201413154602 2023-01-23 19:15:42.489981: step: 1362/1545, loss: 0.03067454881966114 2023-01-23 19:15:43.405328: step: 1364/1545, loss: 0.0013639454264193773 2023-01-23 19:15:44.319576: step: 1366/1545, loss: 0.0549696646630764 2023-01-23 19:15:45.183108: step: 1368/1545, loss: 0.02504114992916584 2023-01-23 19:15:46.130310: step: 1370/1545, loss: 0.2889403998851776 2023-01-23 19:15:47.004517: step: 1372/1545, loss: 0.329593688249588 2023-01-23 19:15:47.892780: step: 1374/1545, loss: 0.0001993101031985134 2023-01-23 19:15:48.810553: step: 1376/1545, loss: 0.0006262981914915144 2023-01-23 19:15:49.729596: step: 1378/1545, loss: 0.023923762142658234 2023-01-23 19:15:50.606419: step: 1380/1545, loss: 0.1296447366476059 2023-01-23 19:15:51.473232: step: 1382/1545, loss: 0.00031229309388436377 2023-01-23 19:15:52.360117: step: 1384/1545, loss: 0.0007143339607864618 2023-01-23 19:15:53.218889: step: 1386/1545, loss: 0.011533753015100956 2023-01-23 19:15:54.085932: step: 1388/1545, loss: 0.055890779942274094 2023-01-23 19:15:54.995536: step: 1390/1545, loss: 7.367575744865462e-05 2023-01-23 19:15:55.871056: step: 1392/1545, loss: 3.323520650155842e-05 2023-01-23 19:15:56.780930: step: 1394/1545, loss: 0.016978276893496513 2023-01-23 19:15:57.750591: step: 1396/1545, loss: 0.19139964878559113 2023-01-23 19:15:58.688085: step: 1398/1545, loss: 0.24471235275268555 2023-01-23 19:15:59.570431: step: 1400/1545, loss: 0.3205888569355011 2023-01-23 19:16:00.440629: step: 1402/1545, loss: 0.4031064808368683 2023-01-23 19:16:01.298469: step: 1404/1545, loss: 0.0077613284811377525 2023-01-23 19:16:02.208435: step: 1406/1545, loss: 0.03131866827607155 2023-01-23 19:16:03.110353: step: 1408/1545, loss: 0.0005147538031451404 2023-01-23 19:16:03.994221: step: 1410/1545, loss: 0.005746014881879091 2023-01-23 19:16:04.869929: step: 1412/1545, loss: 0.354676216840744 2023-01-23 19:16:05.787077: step: 1414/1545, loss: 0.0016896126326173544 2023-01-23 19:16:06.651977: step: 1416/1545, loss: 0.00019173536566086113 2023-01-23 19:16:07.490882: step: 1418/1545, loss: 0.0016402472974732518 2023-01-23 19:16:08.400833: step: 1420/1545, loss: 0.0012857905821874738 2023-01-23 19:16:09.317993: step: 1422/1545, loss: 0.0006093926494941115 2023-01-23 19:16:10.245528: step: 1424/1545, loss: 0.0325792171061039 2023-01-23 19:16:11.108075: step: 1426/1545, loss: 0.0021899305284023285 2023-01-23 19:16:11.994738: step: 1428/1545, loss: 0.01422227080911398 2023-01-23 19:16:12.848370: step: 1430/1545, loss: 0.0012923456961289048 2023-01-23 19:16:13.698992: step: 1432/1545, loss: 0.010193923488259315 2023-01-23 19:16:14.568897: step: 1434/1545, loss: 0.004152197390794754 2023-01-23 19:16:15.432656: step: 1436/1545, loss: 0.01413104310631752 2023-01-23 19:16:16.279195: step: 1438/1545, loss: 0.02569715678691864 2023-01-23 19:16:17.134635: step: 1440/1545, loss: 0.0014707912923768163 2023-01-23 19:16:17.988673: step: 1442/1545, loss: 0.3517686426639557 2023-01-23 19:16:18.888205: step: 1444/1545, loss: 0.0010594683699309826 2023-01-23 19:16:19.778325: step: 1446/1545, loss: 0.10202785581350327 2023-01-23 19:16:20.742835: step: 1448/1545, loss: 0.05477607250213623 2023-01-23 19:16:21.628542: step: 1450/1545, loss: 0.001669644028879702 2023-01-23 19:16:22.479374: step: 1452/1545, loss: 0.0005654741544276476 2023-01-23 19:16:23.364683: step: 1454/1545, loss: 0.0012615424348041415 2023-01-23 19:16:24.263262: step: 1456/1545, loss: 0.18177276849746704 2023-01-23 19:16:25.155854: step: 1458/1545, loss: 0.4247453808784485 2023-01-23 19:16:26.029937: step: 1460/1545, loss: 0.00044340704334899783 2023-01-23 19:16:26.834383: step: 1462/1545, loss: 0.031221887096762657 2023-01-23 19:16:27.696437: step: 1464/1545, loss: 0.00016706674068700522 2023-01-23 19:16:28.562540: step: 1466/1545, loss: 0.013117344118654728 2023-01-23 19:16:29.452244: step: 1468/1545, loss: 0.011294020339846611 2023-01-23 19:16:30.321351: step: 1470/1545, loss: 0.00029290004749782383 2023-01-23 19:16:31.185031: step: 1472/1545, loss: 0.03469839692115784 2023-01-23 19:16:32.078404: step: 1474/1545, loss: 0.0012295395135879517 2023-01-23 19:16:32.933634: step: 1476/1545, loss: 0.02794894017279148 2023-01-23 19:16:33.770231: step: 1478/1545, loss: 0.0013742108130827546 2023-01-23 19:16:34.662889: step: 1480/1545, loss: 0.01274560671299696 2023-01-23 19:16:35.655397: step: 1482/1545, loss: 0.031205110251903534 2023-01-23 19:16:36.542668: step: 1484/1545, loss: 0.040227171033620834 2023-01-23 19:16:37.408921: step: 1486/1545, loss: 0.0054606106132268906 2023-01-23 19:16:38.299575: step: 1488/1545, loss: 0.029080631211400032 2023-01-23 19:16:39.158485: step: 1490/1545, loss: 0.00012674267054535449 2023-01-23 19:16:40.033016: step: 1492/1545, loss: 0.013914818875491619 2023-01-23 19:16:40.923917: step: 1494/1545, loss: 0.00330571411177516 2023-01-23 19:16:41.783464: step: 1496/1545, loss: 0.0007363093318417668 2023-01-23 19:16:42.669368: step: 1498/1545, loss: 0.0019278331892564893 2023-01-23 19:16:43.605343: step: 1500/1545, loss: 0.012103987857699394 2023-01-23 19:16:44.498774: step: 1502/1545, loss: 0.0162091962993145 2023-01-23 19:16:45.422960: step: 1504/1545, loss: 0.00016657958622090518 2023-01-23 19:16:46.321207: step: 1506/1545, loss: 0.007480274885892868 2023-01-23 19:16:47.230215: step: 1508/1545, loss: 0.7908492088317871 2023-01-23 19:16:48.108220: step: 1510/1545, loss: 0.00011115832603536546 2023-01-23 19:16:49.025328: step: 1512/1545, loss: 0.0013494507875293493 2023-01-23 19:16:49.931645: step: 1514/1545, loss: 0.00015307955618482083 2023-01-23 19:16:50.772649: step: 1516/1545, loss: 0.0006130602560006082 2023-01-23 19:16:51.627817: step: 1518/1545, loss: 0.0006711803725920618 2023-01-23 19:16:52.481706: step: 1520/1545, loss: 0.00019057343888562173 2023-01-23 19:16:53.351493: step: 1522/1545, loss: 0.12827087938785553 2023-01-23 19:16:54.227498: step: 1524/1545, loss: 0.011419490911066532 2023-01-23 19:16:55.092513: step: 1526/1545, loss: 0.0004822486953344196 2023-01-23 19:16:55.968329: step: 1528/1545, loss: 0.018122263252735138 2023-01-23 19:16:56.816650: step: 1530/1545, loss: 0.003409791272133589 2023-01-23 19:16:57.656079: step: 1532/1545, loss: 0.00016989849973469973 2023-01-23 19:16:58.516761: step: 1534/1545, loss: 0.4562187194824219 2023-01-23 19:16:59.446871: step: 1536/1545, loss: 0.24516800045967102 2023-01-23 19:17:00.352117: step: 1538/1545, loss: 0.28526756167411804 2023-01-23 19:17:01.288020: step: 1540/1545, loss: 0.029160255566239357 2023-01-23 19:17:02.225341: step: 1542/1545, loss: 0.00020526773005258292 2023-01-23 19:17:03.153306: step: 1544/1545, loss: 0.0013222123961895704 2023-01-23 19:17:04.040220: step: 1546/1545, loss: 0.00019709246407728642 2023-01-23 19:17:04.901735: step: 1548/1545, loss: 0.0007612464250996709 2023-01-23 19:17:05.757438: step: 1550/1545, loss: 7.2616727265995e-05 2023-01-23 19:17:06.682824: step: 1552/1545, loss: 0.0004784046614076942 2023-01-23 19:17:07.551821: step: 1554/1545, loss: 0.0003362746210768819 2023-01-23 19:17:08.409647: step: 1556/1545, loss: 0.04646264389157295 2023-01-23 19:17:09.303023: step: 1558/1545, loss: 0.0006746803992427886 2023-01-23 19:17:10.243253: step: 1560/1545, loss: 0.010553215630352497 2023-01-23 19:17:11.089798: step: 1562/1545, loss: 0.011847675777971745 2023-01-23 19:17:11.969302: step: 1564/1545, loss: 0.006492356304079294 2023-01-23 19:17:12.878340: step: 1566/1545, loss: 0.0012538119917735457 2023-01-23 19:17:13.739401: step: 1568/1545, loss: 0.00784982182085514 2023-01-23 19:17:14.574694: step: 1570/1545, loss: 0.00025294002261944115 2023-01-23 19:17:15.450368: step: 1572/1545, loss: 0.0680619329214096 2023-01-23 19:17:16.289196: step: 1574/1545, loss: 2.2351377992890775e-07 2023-01-23 19:17:17.197736: step: 1576/1545, loss: 0.00731497211381793 2023-01-23 19:17:18.097690: step: 1578/1545, loss: 0.3363568186759949 2023-01-23 19:17:19.016646: step: 1580/1545, loss: 0.00041596463415771723 2023-01-23 19:17:19.922710: step: 1582/1545, loss: 0.05390729755163193 2023-01-23 19:17:20.814591: step: 1584/1545, loss: 0.0002735266461968422 2023-01-23 19:17:21.685811: step: 1586/1545, loss: 0.0008950914489105344 2023-01-23 19:17:22.565226: step: 1588/1545, loss: 0.1780492663383484 2023-01-23 19:17:23.439079: step: 1590/1545, loss: 0.0037442033644765615 2023-01-23 19:17:24.283211: step: 1592/1545, loss: 0.005645101889967918 2023-01-23 19:17:25.182899: step: 1594/1545, loss: 0.0006624504458159208 2023-01-23 19:17:26.081986: step: 1596/1545, loss: 4.301028820918873e-05 2023-01-23 19:17:26.927819: step: 1598/1545, loss: 0.32483819127082825 2023-01-23 19:17:27.782328: step: 1600/1545, loss: 0.031121915206313133 2023-01-23 19:17:28.672675: step: 1602/1545, loss: 0.0007823748746886849 2023-01-23 19:17:29.574197: step: 1604/1545, loss: 0.0018672241130843759 2023-01-23 19:17:30.443219: step: 1606/1545, loss: 0.20305174589157104 2023-01-23 19:17:31.329762: step: 1608/1545, loss: 0.1148424744606018 2023-01-23 19:17:32.246426: step: 1610/1545, loss: 0.00017435276822652668 2023-01-23 19:17:33.123836: step: 1612/1545, loss: 0.007962189614772797 2023-01-23 19:17:34.078585: step: 1614/1545, loss: 0.0009716112981550395 2023-01-23 19:17:34.936166: step: 1616/1545, loss: 0.0016804095357656479 2023-01-23 19:17:35.847869: step: 1618/1545, loss: 0.00010093252058140934 2023-01-23 19:17:36.812928: step: 1620/1545, loss: 0.0219529177993536 2023-01-23 19:17:37.698042: step: 1622/1545, loss: 4.021713539259508e-05 2023-01-23 19:17:38.563767: step: 1624/1545, loss: 8.027200237847865e-06 2023-01-23 19:17:39.481448: step: 1626/1545, loss: 0.28369370102882385 2023-01-23 19:17:40.375669: step: 1628/1545, loss: 0.00027095002587884665 2023-01-23 19:17:41.259181: step: 1630/1545, loss: 0.22792473435401917 2023-01-23 19:17:42.127382: step: 1632/1545, loss: 0.03509146347641945 2023-01-23 19:17:43.012827: step: 1634/1545, loss: 0.006589253433048725 2023-01-23 19:17:43.899459: step: 1636/1545, loss: 0.07089240849018097 2023-01-23 19:17:44.778270: step: 1638/1545, loss: 0.025299496948719025 2023-01-23 19:17:45.663952: step: 1640/1545, loss: 9.160154149867594e-05 2023-01-23 19:17:46.526687: step: 1642/1545, loss: 0.00011206715134903789 2023-01-23 19:17:47.410577: step: 1644/1545, loss: 0.0006122771883383393 2023-01-23 19:17:48.247926: step: 1646/1545, loss: 0.0005560087156482041 2023-01-23 19:17:49.144691: step: 1648/1545, loss: 0.00021171054686419666 2023-01-23 19:17:50.031664: step: 1650/1545, loss: 0.13501039147377014 2023-01-23 19:17:50.934867: step: 1652/1545, loss: 0.0007677708053961396 2023-01-23 19:17:51.778515: step: 1654/1545, loss: 0.0021159423049539328 2023-01-23 19:17:52.659524: step: 1656/1545, loss: 0.22439831495285034 2023-01-23 19:17:53.583081: step: 1658/1545, loss: 0.005963013507425785 2023-01-23 19:17:54.487226: step: 1660/1545, loss: 0.015844034031033516 2023-01-23 19:17:55.398294: step: 1662/1545, loss: 0.00022285185696091503 2023-01-23 19:17:56.257544: step: 1664/1545, loss: 0.507001519203186 2023-01-23 19:17:57.094878: step: 1666/1545, loss: 0.0038240680005401373 2023-01-23 19:17:57.961414: step: 1668/1545, loss: 0.00019496146705932915 2023-01-23 19:17:58.871906: step: 1670/1545, loss: 0.0038665644824504852 2023-01-23 19:17:59.778089: step: 1672/1545, loss: 0.0003167242684867233 2023-01-23 19:18:00.680967: step: 1674/1545, loss: 0.01874333806335926 2023-01-23 19:18:01.577353: step: 1676/1545, loss: 0.0008542153518646955 2023-01-23 19:18:02.470644: step: 1678/1545, loss: 0.028930550441145897 2023-01-23 19:18:03.337493: step: 1680/1545, loss: 0.04073387384414673 2023-01-23 19:18:04.188348: step: 1682/1545, loss: 0.008125298656523228 2023-01-23 19:18:05.062927: step: 1684/1545, loss: 0.00014617489068768919 2023-01-23 19:18:06.025199: step: 1686/1545, loss: 0.026605527848005295 2023-01-23 19:18:06.892554: step: 1688/1545, loss: 0.0009255528566427529 2023-01-23 19:18:07.743971: step: 1690/1545, loss: 0.0021721862722188234 2023-01-23 19:18:08.604025: step: 1692/1545, loss: 0.008505979552865028 2023-01-23 19:18:09.526604: step: 1694/1545, loss: 0.000598532089497894 2023-01-23 19:18:10.375865: step: 1696/1545, loss: 0.00033164984779432416 2023-01-23 19:18:11.230721: step: 1698/1545, loss: 0.00038685707841068506 2023-01-23 19:18:12.110523: step: 1700/1545, loss: 0.0003762253327295184 2023-01-23 19:18:12.979126: step: 1702/1545, loss: 0.13024677336215973 2023-01-23 19:18:13.832362: step: 1704/1545, loss: 0.0005064071738161147 2023-01-23 19:18:14.684223: step: 1706/1545, loss: 0.09839365631341934 2023-01-23 19:18:15.590889: step: 1708/1545, loss: 0.00034683983540162444 2023-01-23 19:18:16.503023: step: 1710/1545, loss: 0.25970515608787537 2023-01-23 19:18:17.375504: step: 1712/1545, loss: 0.0004635625518858433 2023-01-23 19:18:18.243471: step: 1714/1545, loss: 0.0004753274843096733 2023-01-23 19:18:19.214321: step: 1716/1545, loss: 0.0005096510867588222 2023-01-23 19:18:20.081360: step: 1718/1545, loss: 0.12178247421979904 2023-01-23 19:18:20.921461: step: 1720/1545, loss: 0.25036245584487915 2023-01-23 19:18:21.824118: step: 1722/1545, loss: 0.10612669587135315 2023-01-23 19:18:22.768928: step: 1724/1545, loss: 0.03784065321087837 2023-01-23 19:18:23.617683: step: 1726/1545, loss: 0.005638035014271736 2023-01-23 19:18:24.507196: step: 1728/1545, loss: 0.0011437875218689442 2023-01-23 19:18:25.326371: step: 1730/1545, loss: 0.015829479321837425 2023-01-23 19:18:26.149116: step: 1732/1545, loss: 0.0054205311462283134 2023-01-23 19:18:26.977616: step: 1734/1545, loss: 0.0003586381208151579 2023-01-23 19:18:27.856399: step: 1736/1545, loss: 0.0004623682762030512 2023-01-23 19:18:28.731572: step: 1738/1545, loss: 0.009445704519748688 2023-01-23 19:18:29.766323: step: 1740/1545, loss: 0.007605529855936766 2023-01-23 19:18:30.673152: step: 1742/1545, loss: 1.1830202341079712 2023-01-23 19:18:31.545914: step: 1744/1545, loss: 0.16952231526374817 2023-01-23 19:18:32.400973: step: 1746/1545, loss: 0.00930430181324482 2023-01-23 19:18:33.244178: step: 1748/1545, loss: 0.031238878145813942 2023-01-23 19:18:34.124265: step: 1750/1545, loss: 0.0619257315993309 2023-01-23 19:18:34.998406: step: 1752/1545, loss: 0.07659469544887543 2023-01-23 19:18:35.929332: step: 1754/1545, loss: 0.15077091753482819 2023-01-23 19:18:36.772357: step: 1756/1545, loss: 0.008609865792095661 2023-01-23 19:18:37.601936: step: 1758/1545, loss: 0.0028662593103945255 2023-01-23 19:18:38.498559: step: 1760/1545, loss: 0.07625959813594818 2023-01-23 19:18:39.365802: step: 1762/1545, loss: 0.0004971963353455067 2023-01-23 19:18:40.218923: step: 1764/1545, loss: 0.2577013671398163 2023-01-23 19:18:41.112425: step: 1766/1545, loss: 0.10888136923313141 2023-01-23 19:18:42.002294: step: 1768/1545, loss: 0.00011852193711092696 2023-01-23 19:18:42.907922: step: 1770/1545, loss: 0.09306956082582474 2023-01-23 19:18:43.803156: step: 1772/1545, loss: 0.21319587528705597 2023-01-23 19:18:44.736935: step: 1774/1545, loss: 0.013945306651294231 2023-01-23 19:18:45.594693: step: 1776/1545, loss: 0.12481899559497833 2023-01-23 19:18:46.483669: step: 1778/1545, loss: 0.06172126159071922 2023-01-23 19:18:47.363942: step: 1780/1545, loss: 0.15313604474067688 2023-01-23 19:18:48.254924: step: 1782/1545, loss: 0.0006458904244937003 2023-01-23 19:18:49.211041: step: 1784/1545, loss: 0.004512648563832045 2023-01-23 19:18:50.093167: step: 1786/1545, loss: 0.019169332459568977 2023-01-23 19:18:50.966319: step: 1788/1545, loss: 0.06432830542325974 2023-01-23 19:18:51.895344: step: 1790/1545, loss: 0.27187421917915344 2023-01-23 19:18:52.778875: step: 1792/1545, loss: 0.17284850776195526 2023-01-23 19:18:53.628243: step: 1794/1545, loss: 0.0005371018196456134 2023-01-23 19:18:54.491367: step: 1796/1545, loss: 0.0008086786838248372 2023-01-23 19:18:55.342364: step: 1798/1545, loss: 0.005771517287939787 2023-01-23 19:18:56.203519: step: 1800/1545, loss: 0.014946053735911846 2023-01-23 19:18:57.108696: step: 1802/1545, loss: 0.00020799890626221895 2023-01-23 19:18:57.977187: step: 1804/1545, loss: 0.004099337849766016 2023-01-23 19:18:58.819722: step: 1806/1545, loss: 0.0027236214373260736 2023-01-23 19:18:59.669069: step: 1808/1545, loss: 1.95632383110933e-05 2023-01-23 19:19:00.555228: step: 1810/1545, loss: 0.17118552327156067 2023-01-23 19:19:01.514406: step: 1812/1545, loss: 0.0003758547827601433 2023-01-23 19:19:02.361636: step: 1814/1545, loss: 0.0014210738008841872 2023-01-23 19:19:03.262154: step: 1816/1545, loss: 0.00011214904225198552 2023-01-23 19:19:04.112407: step: 1818/1545, loss: 5.99050908931531e-05 2023-01-23 19:19:04.990908: step: 1820/1545, loss: 0.011713073588907719 2023-01-23 19:19:05.854143: step: 1822/1545, loss: 0.011993617750704288 2023-01-23 19:19:06.715471: step: 1824/1545, loss: 0.00044639885891228914 2023-01-23 19:19:07.618953: step: 1826/1545, loss: 0.005253667943179607 2023-01-23 19:19:08.503376: step: 1828/1545, loss: 0.0004134716873522848 2023-01-23 19:19:09.340071: step: 1830/1545, loss: 0.046805109828710556 2023-01-23 19:19:10.208781: step: 1832/1545, loss: 1.2540936470031738 2023-01-23 19:19:11.075874: step: 1834/1545, loss: 0.012312457896769047 2023-01-23 19:19:11.964816: step: 1836/1545, loss: 0.0007081105723045766 2023-01-23 19:19:12.858479: step: 1838/1545, loss: 0.0005601553712040186 2023-01-23 19:19:13.745719: step: 1840/1545, loss: -1.4446696695813444e-05 2023-01-23 19:19:14.581606: step: 1842/1545, loss: 0.0004293452366255224 2023-01-23 19:19:15.425173: step: 1844/1545, loss: 0.014194109477102757 2023-01-23 19:19:16.321507: step: 1846/1545, loss: 0.2017752230167389 2023-01-23 19:19:17.236432: step: 1848/1545, loss: 0.2630503475666046 2023-01-23 19:19:18.107810: step: 1850/1545, loss: -4.9569465772947297e-05 2023-01-23 19:19:18.984415: step: 1852/1545, loss: 0.24252280592918396 2023-01-23 19:19:19.828840: step: 1854/1545, loss: 1.1829421964648645e-05 2023-01-23 19:19:20.777076: step: 1856/1545, loss: 0.3553773760795593 2023-01-23 19:19:21.666604: step: 1858/1545, loss: -7.185053163993871e-06 2023-01-23 19:19:22.560849: step: 1860/1545, loss: 0.0002854138729162514 2023-01-23 19:19:23.474811: step: 1862/1545, loss: 0.0001622942800167948 2023-01-23 19:19:24.390992: step: 1864/1545, loss: 4.360124148661271e-05 2023-01-23 19:19:25.296513: step: 1866/1545, loss: 9.826668247114867e-05 2023-01-23 19:19:26.205304: step: 1868/1545, loss: 0.010559957474470139 2023-01-23 19:19:27.044524: step: 1870/1545, loss: 0.0031773149967193604 2023-01-23 19:19:27.958996: step: 1872/1545, loss: 0.13507592678070068 2023-01-23 19:19:28.811902: step: 1874/1545, loss: 0.00023917289217934012 2023-01-23 19:19:29.702646: step: 1876/1545, loss: 0.0006291920435614884 2023-01-23 19:19:30.559853: step: 1878/1545, loss: 0.00038142313132993877 2023-01-23 19:19:31.381502: step: 1880/1545, loss: 0.00010684543667593971 2023-01-23 19:19:32.373170: step: 1882/1545, loss: 0.7225072383880615 2023-01-23 19:19:33.233683: step: 1884/1545, loss: 0.19552084803581238 2023-01-23 19:19:34.116850: step: 1886/1545, loss: 0.0057359738275408745 2023-01-23 19:19:34.968622: step: 1888/1545, loss: 0.028246261179447174 2023-01-23 19:19:35.925708: step: 1890/1545, loss: 0.01994217000901699 2023-01-23 19:19:36.738395: step: 1892/1545, loss: 0.24726340174674988 2023-01-23 19:19:37.591748: step: 1894/1545, loss: 9.1691137640737e-05 2023-01-23 19:19:38.486852: step: 1896/1545, loss: 7.635593647137284e-05 2023-01-23 19:19:39.395867: step: 1898/1545, loss: 0.009063978679478168 2023-01-23 19:19:40.221322: step: 1900/1545, loss: 0.004821797367185354 2023-01-23 19:19:41.103437: step: 1902/1545, loss: 0.08189147710800171 2023-01-23 19:19:41.958786: step: 1904/1545, loss: 0.01844959706068039 2023-01-23 19:19:42.818458: step: 1906/1545, loss: 0.000907605979591608 2023-01-23 19:19:43.734538: step: 1908/1545, loss: 0.0031879316084086895 2023-01-23 19:19:44.620536: step: 1910/1545, loss: 0.0029757593292742968 2023-01-23 19:19:45.511590: step: 1912/1545, loss: 0.032444678246974945 2023-01-23 19:19:46.417859: step: 1914/1545, loss: 0.002110138302668929 2023-01-23 19:19:47.283426: step: 1916/1545, loss: 0.07854840904474258 2023-01-23 19:19:48.141493: step: 1918/1545, loss: 0.012066589668393135 2023-01-23 19:19:49.030569: step: 1920/1545, loss: 0.012037576176226139 2023-01-23 19:19:49.943326: step: 1922/1545, loss: 0.0003839409037027508 2023-01-23 19:19:50.842404: step: 1924/1545, loss: 0.005575067829340696 2023-01-23 19:19:51.721908: step: 1926/1545, loss: 0.00047199917025864124 2023-01-23 19:19:52.682923: step: 1928/1545, loss: 0.07513373345136642 2023-01-23 19:19:53.613994: step: 1930/1545, loss: 0.001699470216408372 2023-01-23 19:19:54.514500: step: 1932/1545, loss: 0.06225625425577164 2023-01-23 19:19:55.394329: step: 1934/1545, loss: 0.04059230536222458 2023-01-23 19:19:56.247157: step: 1936/1545, loss: 0.0019771039951592684 2023-01-23 19:19:57.162057: step: 1938/1545, loss: 0.01093444973230362 2023-01-23 19:19:58.055370: step: 1940/1545, loss: 0.006324250251054764 2023-01-23 19:19:58.924048: step: 1942/1545, loss: 0.12679550051689148 2023-01-23 19:19:59.785926: step: 1944/1545, loss: 0.0151686891913414 2023-01-23 19:20:00.641595: step: 1946/1545, loss: 0.0008434904157184064 2023-01-23 19:20:01.554725: step: 1948/1545, loss: 0.0001519093057140708 2023-01-23 19:20:02.457063: step: 1950/1545, loss: 0.0012094925623387098 2023-01-23 19:20:03.343327: step: 1952/1545, loss: 0.1100676879286766 2023-01-23 19:20:04.231946: step: 1954/1545, loss: 0.0026906735729426146 2023-01-23 19:20:05.141785: step: 1956/1545, loss: 1.2379851341247559 2023-01-23 19:20:06.083233: step: 1958/1545, loss: 0.028135955333709717 2023-01-23 19:20:06.964699: step: 1960/1545, loss: 0.21878103911876678 2023-01-23 19:20:07.819722: step: 1962/1545, loss: 0.002624507760629058 2023-01-23 19:20:08.750011: step: 1964/1545, loss: 0.005293818190693855 2023-01-23 19:20:09.616542: step: 1966/1545, loss: 0.0001872027787612751 2023-01-23 19:20:10.493251: step: 1968/1545, loss: 0.018369117751717567 2023-01-23 19:20:11.369836: step: 1970/1545, loss: 0.0059319245629012585 2023-01-23 19:20:12.256711: step: 1972/1545, loss: 0.0007174908532761037 2023-01-23 19:20:13.158852: step: 1974/1545, loss: 0.0036455874796956778 2023-01-23 19:20:14.036521: step: 1976/1545, loss: 0.20118097960948944 2023-01-23 19:20:14.947032: step: 1978/1545, loss: 0.027234181761741638 2023-01-23 19:20:15.788870: step: 1980/1545, loss: 0.0054957447573542595 2023-01-23 19:20:16.670145: step: 1982/1545, loss: 0.0020900366362184286 2023-01-23 19:20:17.531670: step: 1984/1545, loss: 0.04467678815126419 2023-01-23 19:20:18.395751: step: 1986/1545, loss: 0.030843356624245644 2023-01-23 19:20:19.300059: step: 1988/1545, loss: 0.0001679551205597818 2023-01-23 19:20:20.199532: step: 1990/1545, loss: 0.00018889685452450067 2023-01-23 19:20:21.097010: step: 1992/1545, loss: 0.08718767017126083 2023-01-23 19:20:21.931449: step: 1994/1545, loss: 7.126018317649141e-05 2023-01-23 19:20:22.830724: step: 1996/1545, loss: 4.824613642995246e-05 2023-01-23 19:20:23.723786: step: 1998/1545, loss: 0.0006363073480315506 2023-01-23 19:20:24.635795: step: 2000/1545, loss: 0.0015541991451755166 2023-01-23 19:20:25.533944: step: 2002/1545, loss: 0.03883745148777962 2023-01-23 19:20:26.407897: step: 2004/1545, loss: 0.03949502483010292 2023-01-23 19:20:27.277074: step: 2006/1545, loss: 0.0036458857357501984 2023-01-23 19:20:28.152584: step: 2008/1545, loss: 0.0005380375077947974 2023-01-23 19:20:29.044773: step: 2010/1545, loss: 0.23574651777744293 2023-01-23 19:20:29.943744: step: 2012/1545, loss: 0.0025176675990223885 2023-01-23 19:20:30.871531: step: 2014/1545, loss: 0.0006048879586160183 2023-01-23 19:20:31.749332: step: 2016/1545, loss: 0.0014740405604243279 2023-01-23 19:20:32.579624: step: 2018/1545, loss: 0.001639760099351406 2023-01-23 19:20:33.488241: step: 2020/1545, loss: 0.36454659700393677 2023-01-23 19:20:34.368427: step: 2022/1545, loss: 0.0014890757156535983 2023-01-23 19:20:35.260036: step: 2024/1545, loss: 0.05936190113425255 2023-01-23 19:20:36.121375: step: 2026/1545, loss: 0.0002615413104649633 2023-01-23 19:20:37.017333: step: 2028/1545, loss: 0.02289140596985817 2023-01-23 19:20:37.909868: step: 2030/1545, loss: 0.006321471184492111 2023-01-23 19:20:38.732740: step: 2032/1545, loss: 0.009527199901640415 2023-01-23 19:20:39.592295: step: 2034/1545, loss: 0.009811918251216412 2023-01-23 19:20:40.440091: step: 2036/1545, loss: 0.011088998056948185 2023-01-23 19:20:41.300334: step: 2038/1545, loss: 0.04943171516060829 2023-01-23 19:20:42.202141: step: 2040/1545, loss: 0.0012757588410750031 2023-01-23 19:20:43.104812: step: 2042/1545, loss: 0.0018731998279690742 2023-01-23 19:20:43.996609: step: 2044/1545, loss: 0.00029694908880628645 2023-01-23 19:20:44.890025: step: 2046/1545, loss: 0.013838742859661579 2023-01-23 19:20:45.754586: step: 2048/1545, loss: 0.07038992643356323 2023-01-23 19:20:46.605104: step: 2050/1545, loss: 0.0007693006773479283 2023-01-23 19:20:47.450805: step: 2052/1545, loss: 0.001577909803017974 2023-01-23 19:20:48.359480: step: 2054/1545, loss: 0.001073553808964789 2023-01-23 19:20:49.261352: step: 2056/1545, loss: 0.10589306801557541 2023-01-23 19:20:50.134153: step: 2058/1545, loss: 0.0005703307106159627 2023-01-23 19:20:51.033164: step: 2060/1545, loss: 0.0003128194948658347 2023-01-23 19:20:51.893680: step: 2062/1545, loss: 0.057057805359363556 2023-01-23 19:20:52.781601: step: 2064/1545, loss: 0.08537127077579498 2023-01-23 19:20:53.638704: step: 2066/1545, loss: 0.0004379327001515776 2023-01-23 19:20:54.511386: step: 2068/1545, loss: 0.0004905974492430687 2023-01-23 19:20:55.421926: step: 2070/1545, loss: 0.13780026137828827 2023-01-23 19:20:56.301135: step: 2072/1545, loss: 0.006062927655875683 2023-01-23 19:20:57.222487: step: 2074/1545, loss: 0.018565230071544647 2023-01-23 19:20:58.123081: step: 2076/1545, loss: 0.0412365086376667 2023-01-23 19:20:58.988585: step: 2078/1545, loss: 0.00020674972620327026 2023-01-23 19:20:59.874157: step: 2080/1545, loss: 0.021757042035460472 2023-01-23 19:21:00.748976: step: 2082/1545, loss: 1.8461574654793367e-05 2023-01-23 19:21:01.637747: step: 2084/1545, loss: 0.20319640636444092 2023-01-23 19:21:02.602131: step: 2086/1545, loss: 0.0009237908525392413 2023-01-23 19:21:03.495166: step: 2088/1545, loss: 0.0009961965261027217 2023-01-23 19:21:04.399388: step: 2090/1545, loss: 0.01523125171661377 2023-01-23 19:21:05.283729: step: 2092/1545, loss: 0.00015683184028603137 2023-01-23 19:21:06.118535: step: 2094/1545, loss: 0.00047841694322414696 2023-01-23 19:21:06.988524: step: 2096/1545, loss: 0.3043978810310364 2023-01-23 19:21:07.841433: step: 2098/1545, loss: 0.00024795279023237526 2023-01-23 19:21:08.797455: step: 2100/1545, loss: 0.0190725140273571 2023-01-23 19:21:09.682731: step: 2102/1545, loss: 0.00030935180257074535 2023-01-23 19:21:10.547588: step: 2104/1545, loss: 0.0027385219000279903 2023-01-23 19:21:11.419464: step: 2106/1545, loss: 7.193287456175312e-05 2023-01-23 19:21:12.318376: step: 2108/1545, loss: 0.00014409715367946774 2023-01-23 19:21:13.251486: step: 2110/1545, loss: 0.04773090034723282 2023-01-23 19:21:14.086792: step: 2112/1545, loss: 0.0008492264314554632 2023-01-23 19:21:15.048098: step: 2114/1545, loss: 0.003566375467926264 2023-01-23 19:21:15.917534: step: 2116/1545, loss: 0.22167794406414032 2023-01-23 19:21:16.797134: step: 2118/1545, loss: 0.009721280075609684 2023-01-23 19:21:17.717597: step: 2120/1545, loss: 0.26118478178977966 2023-01-23 19:21:18.611418: step: 2122/1545, loss: 0.006989188026636839 2023-01-23 19:21:19.495709: step: 2124/1545, loss: 0.0063972752541303635 2023-01-23 19:21:20.348332: step: 2126/1545, loss: 0.0010241600684821606 2023-01-23 19:21:21.261101: step: 2128/1545, loss: 0.0014761254424229264 2023-01-23 19:21:22.158038: step: 2130/1545, loss: 7.669121259823442e-05 2023-01-23 19:21:23.061954: step: 2132/1545, loss: 0.11252400279045105 2023-01-23 19:21:23.919257: step: 2134/1545, loss: 0.20942789316177368 2023-01-23 19:21:24.801918: step: 2136/1545, loss: 0.00010640887194313109 2023-01-23 19:21:25.713384: step: 2138/1545, loss: 0.0026374738663434982 2023-01-23 19:21:26.578749: step: 2140/1545, loss: 0.0005460333195514977 2023-01-23 19:21:27.462376: step: 2142/1545, loss: 0.00011167323827976361 2023-01-23 19:21:28.348382: step: 2144/1545, loss: 0.030771315097808838 2023-01-23 19:21:29.190189: step: 2146/1545, loss: 0.00215154979377985 2023-01-23 19:21:30.091322: step: 2148/1545, loss: 4.5644716010428965e-05 2023-01-23 19:21:30.951217: step: 2150/1545, loss: 3.0003673600731418e-05 2023-01-23 19:21:31.832413: step: 2152/1545, loss: 0.39821910858154297 2023-01-23 19:21:32.679081: step: 2154/1545, loss: 0.002089308574795723 2023-01-23 19:21:33.559519: step: 2156/1545, loss: -1.9688006432261318e-05 2023-01-23 19:21:34.427423: step: 2158/1545, loss: 0.1662961095571518 2023-01-23 19:21:35.293750: step: 2160/1545, loss: 3.8515245250891894e-05 2023-01-23 19:21:36.245215: step: 2162/1545, loss: 0.05807994306087494 2023-01-23 19:21:37.137359: step: 2164/1545, loss: 0.0033210297115147114 2023-01-23 19:21:38.059172: step: 2166/1545, loss: 0.0032447685953229666 2023-01-23 19:21:38.966336: step: 2168/1545, loss: 0.3724322021007538 2023-01-23 19:21:39.857165: step: 2170/1545, loss: 0.00234955339692533 2023-01-23 19:21:40.709679: step: 2172/1545, loss: 0.002659610938280821 2023-01-23 19:21:41.572155: step: 2174/1545, loss: 0.002235349966213107 2023-01-23 19:21:42.483563: step: 2176/1545, loss: 0.02689572609961033 2023-01-23 19:21:43.388504: step: 2178/1545, loss: 0.00015622633509337902 2023-01-23 19:21:44.233826: step: 2180/1545, loss: 6.564415525645018e-05 2023-01-23 19:21:45.123379: step: 2182/1545, loss: 0.0037807307671755552 2023-01-23 19:21:46.046360: step: 2184/1545, loss: 0.00011245433415751904 2023-01-23 19:21:46.952333: step: 2186/1545, loss: 0.07888441532850266 2023-01-23 19:21:47.813514: step: 2188/1545, loss: 0.0016653776401653886 2023-01-23 19:21:48.730823: step: 2190/1545, loss: 0.09830130636692047 2023-01-23 19:21:49.673484: step: 2192/1545, loss: 0.10734312236309052 2023-01-23 19:21:50.502833: step: 2194/1545, loss: 0.00020609858620446175 2023-01-23 19:21:51.391844: step: 2196/1545, loss: 0.021950693801045418 2023-01-23 19:21:52.252476: step: 2198/1545, loss: 0.02258884906768799 2023-01-23 19:21:53.153484: step: 2200/1545, loss: 0.6762378215789795 2023-01-23 19:21:54.039598: step: 2202/1545, loss: 0.1696341335773468 2023-01-23 19:21:54.899003: step: 2204/1545, loss: 0.08712386339902878 2023-01-23 19:21:55.776629: step: 2206/1545, loss: 0.0003895307891070843 2023-01-23 19:21:56.763687: step: 2208/1545, loss: 0.016028981655836105 2023-01-23 19:21:57.663002: step: 2210/1545, loss: 0.14465266466140747 2023-01-23 19:21:58.519409: step: 2212/1545, loss: 0.020722011104226112 2023-01-23 19:21:59.427498: step: 2214/1545, loss: 0.07242098450660706 2023-01-23 19:22:00.361892: step: 2216/1545, loss: 0.11342190951108932 2023-01-23 19:22:01.241556: step: 2218/1545, loss: 0.0001279644638998434 2023-01-23 19:22:02.153923: step: 2220/1545, loss: 0.01768648810684681 2023-01-23 19:22:03.039120: step: 2222/1545, loss: 0.03144354000687599 2023-01-23 19:22:03.937440: step: 2224/1545, loss: 0.0026400310453027487 2023-01-23 19:22:04.880066: step: 2226/1545, loss: 0.0025716954842209816 2023-01-23 19:22:05.863864: step: 2228/1545, loss: 0.10095729678869247 2023-01-23 19:22:06.782198: step: 2230/1545, loss: 0.02364148199558258 2023-01-23 19:22:07.809139: step: 2232/1545, loss: 0.007381887175142765 2023-01-23 19:22:08.647404: step: 2234/1545, loss: 0.0007927637780085206 2023-01-23 19:22:09.517162: step: 2236/1545, loss: 0.4257268011569977 2023-01-23 19:22:10.422389: step: 2238/1545, loss: 0.374223917722702 2023-01-23 19:22:11.313789: step: 2240/1545, loss: 0.00040643001557327807 2023-01-23 19:22:12.151044: step: 2242/1545, loss: 0.00027438599499873817 2023-01-23 19:22:13.022900: step: 2244/1545, loss: 0.007966209203004837 2023-01-23 19:22:13.870753: step: 2246/1545, loss: 0.014608141966164112 2023-01-23 19:22:14.734174: step: 2248/1545, loss: 0.054107919335365295 2023-01-23 19:22:15.588899: step: 2250/1545, loss: 0.007570543792098761 2023-01-23 19:22:16.491367: step: 2252/1545, loss: 0.005161214619874954 2023-01-23 19:22:17.372749: step: 2254/1545, loss: 0.04975690320134163 2023-01-23 19:22:18.217962: step: 2256/1545, loss: 0.0017372333677485585 2023-01-23 19:22:19.106738: step: 2258/1545, loss: 0.11597271263599396 2023-01-23 19:22:19.958467: step: 2260/1545, loss: 0.017928604036569595 2023-01-23 19:22:20.826550: step: 2262/1545, loss: 0.0008211209787987173 2023-01-23 19:22:21.699715: step: 2264/1545, loss: 0.000755632296204567 2023-01-23 19:22:22.610239: step: 2266/1545, loss: 0.0002007168804993853 2023-01-23 19:22:23.453396: step: 2268/1545, loss: 0.00039265520172193646 2023-01-23 19:22:24.317109: step: 2270/1545, loss: 0.10135936737060547 2023-01-23 19:22:25.196322: step: 2272/1545, loss: 0.01000666432082653 2023-01-23 19:22:26.078512: step: 2274/1545, loss: 0.00038627348840236664 2023-01-23 19:22:26.958145: step: 2276/1545, loss: 0.0021143313497304916 2023-01-23 19:22:27.799614: step: 2278/1545, loss: 0.001194298965856433 2023-01-23 19:22:28.664822: step: 2280/1545, loss: 0.4892180263996124 2023-01-23 19:22:29.568066: step: 2282/1545, loss: 0.11470799893140793 2023-01-23 19:22:30.525812: step: 2284/1545, loss: 0.0011979840928688645 2023-01-23 19:22:31.395126: step: 2286/1545, loss: 0.05540931969881058 2023-01-23 19:22:32.249743: step: 2288/1545, loss: 0.16838546097278595 2023-01-23 19:22:33.119254: step: 2290/1545, loss: 0.0002736818860284984 2023-01-23 19:22:34.014637: step: 2292/1545, loss: 0.012793460860848427 2023-01-23 19:22:34.887574: step: 2294/1545, loss: 0.17031796276569366 2023-01-23 19:22:35.765596: step: 2296/1545, loss: 0.00013054715236648917 2023-01-23 19:22:36.654143: step: 2298/1545, loss: 0.1374123990535736 2023-01-23 19:22:37.686905: step: 2300/1545, loss: 0.6121684312820435 2023-01-23 19:22:38.586337: step: 2302/1545, loss: 0.031102897599339485 2023-01-23 19:22:39.472962: step: 2304/1545, loss: 0.17028018832206726 2023-01-23 19:22:40.425713: step: 2306/1545, loss: 0.0001918422058224678 2023-01-23 19:22:41.298991: step: 2308/1545, loss: 0.002301208209246397 2023-01-23 19:22:42.138956: step: 2310/1545, loss: 0.0009753538761287928 2023-01-23 19:22:43.028534: step: 2312/1545, loss: 0.0030518698040395975 2023-01-23 19:22:43.929605: step: 2314/1545, loss: 0.10600349307060242 2023-01-23 19:22:44.823124: step: 2316/1545, loss: 0.011316441930830479 2023-01-23 19:22:45.725034: step: 2318/1545, loss: 0.003961271606385708 2023-01-23 19:22:46.606918: step: 2320/1545, loss: 0.014002853073179722 2023-01-23 19:22:47.473009: step: 2322/1545, loss: 0.0019580598454922438 2023-01-23 19:22:48.415999: step: 2324/1545, loss: 0.02227891981601715 2023-01-23 19:22:49.286913: step: 2326/1545, loss: 0.0023923905100673437 2023-01-23 19:22:50.169706: step: 2328/1545, loss: 0.07685382664203644 2023-01-23 19:22:51.007603: step: 2330/1545, loss: 0.0014355193125084043 2023-01-23 19:22:51.881061: step: 2332/1545, loss: 0.00022766708570998162 2023-01-23 19:22:52.718998: step: 2334/1545, loss: 0.0008915724465623498 2023-01-23 19:22:53.569011: step: 2336/1545, loss: 0.0004052084404975176 2023-01-23 19:22:54.483870: step: 2338/1545, loss: 0.07538098096847534 2023-01-23 19:22:55.393452: step: 2340/1545, loss: 0.07248099893331528 2023-01-23 19:22:56.333137: step: 2342/1545, loss: 0.039777349680662155 2023-01-23 19:22:57.289713: step: 2344/1545, loss: 0.07522665709257126 2023-01-23 19:22:58.197840: step: 2346/1545, loss: 0.0004589800664689392 2023-01-23 19:22:59.121511: step: 2348/1545, loss: 0.06836338341236115 2023-01-23 19:22:59.965973: step: 2350/1545, loss: 0.0005808025016449392 2023-01-23 19:23:00.820424: step: 2352/1545, loss: 0.03947290778160095 2023-01-23 19:23:01.713286: step: 2354/1545, loss: 0.047418124973773956 2023-01-23 19:23:02.585756: step: 2356/1545, loss: 0.14129877090454102 2023-01-23 19:23:03.446805: step: 2358/1545, loss: 0.0013871180126443505 2023-01-23 19:23:04.372162: step: 2360/1545, loss: 0.0004069161368533969 2023-01-23 19:23:05.243108: step: 2362/1545, loss: 0.025993622839450836 2023-01-23 19:23:06.110386: step: 2364/1545, loss: 0.0013983978424221277 2023-01-23 19:23:07.024914: step: 2366/1545, loss: 0.1585826575756073 2023-01-23 19:23:07.881920: step: 2368/1545, loss: 0.0023016403429210186 2023-01-23 19:23:08.751142: step: 2370/1545, loss: 0.0007002833299338818 2023-01-23 19:23:09.626148: step: 2372/1545, loss: 0.010158429853618145 2023-01-23 19:23:10.489576: step: 2374/1545, loss: 0.022894246503710747 2023-01-23 19:23:11.383939: step: 2376/1545, loss: 0.08838565647602081 2023-01-23 19:23:12.300035: step: 2378/1545, loss: 0.00012316058564465493 2023-01-23 19:23:13.136049: step: 2380/1545, loss: 0.0950293242931366 2023-01-23 19:23:14.031064: step: 2382/1545, loss: 0.0048136780969798565 2023-01-23 19:23:14.944963: step: 2384/1545, loss: 0.571317195892334 2023-01-23 19:23:15.881905: step: 2386/1545, loss: 0.002334233373403549 2023-01-23 19:23:16.784368: step: 2388/1545, loss: 0.00042455332004465163 2023-01-23 19:23:17.689602: step: 2390/1545, loss: 0.2693009078502655 2023-01-23 19:23:18.544893: step: 2392/1545, loss: 0.03660003840923309 2023-01-23 19:23:19.400487: step: 2394/1545, loss: 0.17058728635311127 2023-01-23 19:23:20.281949: step: 2396/1545, loss: 0.00036699121119454503 2023-01-23 19:23:21.164573: step: 2398/1545, loss: 0.12002449482679367 2023-01-23 19:23:22.051386: step: 2400/1545, loss: 0.22482317686080933 2023-01-23 19:23:22.931574: step: 2402/1545, loss: 0.05364259332418442 2023-01-23 19:23:23.799767: step: 2404/1545, loss: 0.0004353407712187618 2023-01-23 19:23:24.739178: step: 2406/1545, loss: 0.1243867427110672 2023-01-23 19:23:25.625565: step: 2408/1545, loss: 0.0003567000094335526 2023-01-23 19:23:26.557481: step: 2410/1545, loss: 0.00013673992361873388 2023-01-23 19:23:27.437409: step: 2412/1545, loss: 1.982471439987421e-05 2023-01-23 19:23:28.338391: step: 2414/1545, loss: 2.5370080038555898e-05 2023-01-23 19:23:29.239867: step: 2416/1545, loss: 5.522121500689536e-05 2023-01-23 19:23:30.114961: step: 2418/1545, loss: 0.007665206678211689 2023-01-23 19:23:30.977833: step: 2420/1545, loss: 0.2562656104564667 2023-01-23 19:23:31.889090: step: 2422/1545, loss: -2.2488511604024097e-05 2023-01-23 19:23:32.768292: step: 2424/1545, loss: 0.08003762364387512 2023-01-23 19:23:33.689226: step: 2426/1545, loss: 0.07302913069725037 2023-01-23 19:23:34.567094: step: 2428/1545, loss: 0.006843323819339275 2023-01-23 19:23:35.545086: step: 2430/1545, loss: 5.214711563894525e-06 2023-01-23 19:23:36.449191: step: 2432/1545, loss: 0.09951608628034592 2023-01-23 19:23:37.367825: step: 2434/1545, loss: 0.023342592641711235 2023-01-23 19:23:38.278853: step: 2436/1545, loss: 0.027390042319893837 2023-01-23 19:23:39.161603: step: 2438/1545, loss: 0.013475404120981693 2023-01-23 19:23:40.051596: step: 2440/1545, loss: 0.020992174744606018 2023-01-23 19:23:40.890488: step: 2442/1545, loss: 0.002606693422421813 2023-01-23 19:23:41.815412: step: 2444/1545, loss: 0.017104439437389374 2023-01-23 19:23:42.660602: step: 2446/1545, loss: 0.010057655163109303 2023-01-23 19:23:43.542727: step: 2448/1545, loss: 0.004458090756088495 2023-01-23 19:23:44.381413: step: 2450/1545, loss: 0.0005055332439951599 2023-01-23 19:23:45.243322: step: 2452/1545, loss: 9.751073230290785e-05 2023-01-23 19:23:46.092893: step: 2454/1545, loss: 0.0024072567466646433 2023-01-23 19:23:46.936514: step: 2456/1545, loss: 0.025236351415514946 2023-01-23 19:23:47.775584: step: 2458/1545, loss: 0.001566283404827118 2023-01-23 19:23:48.637337: step: 2460/1545, loss: 0.07398521155118942 2023-01-23 19:23:49.514787: step: 2462/1545, loss: 0.001987478230148554 2023-01-23 19:23:50.387090: step: 2464/1545, loss: 0.40227124094963074 2023-01-23 19:23:51.262434: step: 2466/1545, loss: 0.0035912508610635996 2023-01-23 19:23:52.176380: step: 2468/1545, loss: 0.0071904342621564865 2023-01-23 19:23:53.036264: step: 2470/1545, loss: 0.0022142527159303427 2023-01-23 19:23:53.891690: step: 2472/1545, loss: 0.0028101271018385887 2023-01-23 19:23:54.770659: step: 2474/1545, loss: 0.11340651661157608 2023-01-23 19:23:55.644877: step: 2476/1545, loss: 0.00046039914013817906 2023-01-23 19:23:56.541661: step: 2478/1545, loss: 0.07789824157953262 2023-01-23 19:23:57.426347: step: 2480/1545, loss: 0.0280454121530056 2023-01-23 19:23:58.393958: step: 2482/1545, loss: 0.03443246707320213 2023-01-23 19:23:59.278563: step: 2484/1545, loss: 0.024559112265706062 2023-01-23 19:24:00.129816: step: 2486/1545, loss: 0.007456414867192507 2023-01-23 19:24:00.976630: step: 2488/1545, loss: 0.005235110875219107 2023-01-23 19:24:01.861385: step: 2490/1545, loss: 0.0008441351819783449 2023-01-23 19:24:02.706808: step: 2492/1545, loss: 0.0007042838842608035 2023-01-23 19:24:03.650993: step: 2494/1545, loss: 0.009127620607614517 2023-01-23 19:24:04.565874: step: 2496/1545, loss: 0.0009530234383419156 2023-01-23 19:24:05.499064: step: 2498/1545, loss: 9.544753265799955e-05 2023-01-23 19:24:06.390504: step: 2500/1545, loss: 0.013549340888857841 2023-01-23 19:24:07.242436: step: 2502/1545, loss: 0.00027734553441405296 2023-01-23 19:24:08.136313: step: 2504/1545, loss: 0.017792606726288795 2023-01-23 19:24:09.023899: step: 2506/1545, loss: 0.0017310092225670815 2023-01-23 19:24:09.893808: step: 2508/1545, loss: 0.089746855199337 2023-01-23 19:24:10.773390: step: 2510/1545, loss: 0.00903062429279089 2023-01-23 19:24:11.643514: step: 2512/1545, loss: 0.03182056173682213 2023-01-23 19:24:12.503576: step: 2514/1545, loss: 0.0014440234517678618 2023-01-23 19:24:13.376678: step: 2516/1545, loss: 0.11898763477802277 2023-01-23 19:24:14.296228: step: 2518/1545, loss: 0.012018542736768723 2023-01-23 19:24:15.255914: step: 2520/1545, loss: 0.023579901084303856 2023-01-23 19:24:16.163411: step: 2522/1545, loss: 0.15327060222625732 2023-01-23 19:24:17.079895: step: 2524/1545, loss: 0.02329123392701149 2023-01-23 19:24:18.032931: step: 2526/1545, loss: 0.00021324161207303405 2023-01-23 19:24:18.906133: step: 2528/1545, loss: 0.08922957628965378 2023-01-23 19:24:19.805518: step: 2530/1545, loss: 0.0007386885117739439 2023-01-23 19:24:20.647362: step: 2532/1545, loss: 0.0007613110356032848 2023-01-23 19:24:21.532352: step: 2534/1545, loss: 0.004858586937189102 2023-01-23 19:24:22.447592: step: 2536/1545, loss: 0.0010605915449559689 2023-01-23 19:24:23.285761: step: 2538/1545, loss: 0.27910855412483215 2023-01-23 19:24:24.177424: step: 2540/1545, loss: 0.1670958250761032 2023-01-23 19:24:25.059514: step: 2542/1545, loss: 0.01655501499772072 2023-01-23 19:24:25.994426: step: 2544/1545, loss: 0.0010680020786821842 2023-01-23 19:24:26.861071: step: 2546/1545, loss: 0.0058901626616716385 2023-01-23 19:24:27.750346: step: 2548/1545, loss: 3.3164404158014804e-05 2023-01-23 19:24:28.659554: step: 2550/1545, loss: 0.1205185279250145 2023-01-23 19:24:29.543026: step: 2552/1545, loss: 0.10094626992940903 2023-01-23 19:24:30.402942: step: 2554/1545, loss: 0.0001877887116279453 2023-01-23 19:24:31.285879: step: 2556/1545, loss: 0.17025092244148254 2023-01-23 19:24:32.146338: step: 2558/1545, loss: 0.025278925895690918 2023-01-23 19:24:33.020097: step: 2560/1545, loss: 0.15207955241203308 2023-01-23 19:24:33.899897: step: 2562/1545, loss: 0.15636573731899261 2023-01-23 19:24:34.846898: step: 2564/1545, loss: 0.4304616153240204 2023-01-23 19:24:35.710710: step: 2566/1545, loss: 0.5908854603767395 2023-01-23 19:24:36.617800: step: 2568/1545, loss: 0.38049638271331787 2023-01-23 19:24:37.475138: step: 2570/1545, loss: 0.0005421722889877856 2023-01-23 19:24:38.325318: step: 2572/1545, loss: 8.331006392836571e-05 2023-01-23 19:24:39.200917: step: 2574/1545, loss: 4.203497155685909e-05 2023-01-23 19:24:40.046483: step: 2576/1545, loss: 3.88579246646259e-05 2023-01-23 19:24:40.951192: step: 2578/1545, loss: 0.0006687995628453791 2023-01-23 19:24:41.914675: step: 2580/1545, loss: 0.0017822880763560534 2023-01-23 19:24:42.782722: step: 2582/1545, loss: 0.23475652933120728 2023-01-23 19:24:43.618021: step: 2584/1545, loss: 0.0019877355080097914 2023-01-23 19:24:44.541140: step: 2586/1545, loss: 0.0009313740883953869 2023-01-23 19:24:45.407389: step: 2588/1545, loss: 2.847655923687853e-05 2023-01-23 19:24:46.326939: step: 2590/1545, loss: 0.0074277836829423904 2023-01-23 19:24:47.139332: step: 2592/1545, loss: 0.0005881020333617926 2023-01-23 19:24:48.053437: step: 2594/1545, loss: 0.038945961743593216 2023-01-23 19:24:48.937645: step: 2596/1545, loss: 0.0011366052785888314 2023-01-23 19:24:49.770528: step: 2598/1545, loss: 0.0011272833216935396 2023-01-23 19:24:50.602502: step: 2600/1545, loss: 0.000993769965134561 2023-01-23 19:24:51.501629: step: 2602/1545, loss: 0.046252865344285965 2023-01-23 19:24:52.465710: step: 2604/1545, loss: 0.04247717559337616 2023-01-23 19:24:53.330289: step: 2606/1545, loss: 0.0004494866880122572 2023-01-23 19:24:54.189016: step: 2608/1545, loss: 0.014366681687533855 2023-01-23 19:24:55.008617: step: 2610/1545, loss: 0.002862758468836546 2023-01-23 19:24:55.883083: step: 2612/1545, loss: 0.0002399447257630527 2023-01-23 19:24:56.812072: step: 2614/1545, loss: 0.4276615083217621 2023-01-23 19:24:57.678837: step: 2616/1545, loss: 0.004322191700339317 2023-01-23 19:24:58.554140: step: 2618/1545, loss: 0.003747522598132491 2023-01-23 19:24:59.454708: step: 2620/1545, loss: 0.12793713808059692 2023-01-23 19:25:00.337455: step: 2622/1545, loss: 0.0027335539925843477 2023-01-23 19:25:01.199029: step: 2624/1545, loss: 0.031212065368890762 2023-01-23 19:25:02.072056: step: 2626/1545, loss: 0.00011076639202656224 2023-01-23 19:25:02.949614: step: 2628/1545, loss: 0.5358856320381165 2023-01-23 19:25:03.843481: step: 2630/1545, loss: 0.000293708493700251 2023-01-23 19:25:04.706058: step: 2632/1545, loss: 0.001186389708891511 2023-01-23 19:25:05.607133: step: 2634/1545, loss: 0.025247668847441673 2023-01-23 19:25:06.459870: step: 2636/1545, loss: 0.0011859614169225097 2023-01-23 19:25:07.343013: step: 2638/1545, loss: 0.012808228842914104 2023-01-23 19:25:08.254457: step: 2640/1545, loss: 0.0005741611239500344 2023-01-23 19:25:09.178873: step: 2642/1545, loss: 0.007864290848374367 2023-01-23 19:25:10.083226: step: 2644/1545, loss: 0.007600605953484774 2023-01-23 19:25:10.948976: step: 2646/1545, loss: 0.05925193056464195 2023-01-23 19:25:11.829037: step: 2648/1545, loss: 0.0008130878559313715 2023-01-23 19:25:12.676297: step: 2650/1545, loss: 0.0002209683007095009 2023-01-23 19:25:13.558030: step: 2652/1545, loss: 0.20532894134521484 2023-01-23 19:25:14.415919: step: 2654/1545, loss: 0.0002154480607714504 2023-01-23 19:25:15.303261: step: 2656/1545, loss: 0.030075743794441223 2023-01-23 19:25:16.142375: step: 2658/1545, loss: 0.03648609668016434 2023-01-23 19:25:17.052390: step: 2660/1545, loss: 0.01827191561460495 2023-01-23 19:25:17.930298: step: 2662/1545, loss: 0.00015265954425558448 2023-01-23 19:25:18.810166: step: 2664/1545, loss: 0.007513532415032387 2023-01-23 19:25:19.752685: step: 2666/1545, loss: 0.0268767811357975 2023-01-23 19:25:20.626905: step: 2668/1545, loss: 0.0836360976099968 2023-01-23 19:25:21.570796: step: 2670/1545, loss: 0.010128594934940338 2023-01-23 19:25:22.460334: step: 2672/1545, loss: 0.0006798210670240223 2023-01-23 19:25:23.347421: step: 2674/1545, loss: 8.39851054479368e-07 2023-01-23 19:25:24.239968: step: 2676/1545, loss: 0.15795116126537323 2023-01-23 19:25:25.086979: step: 2678/1545, loss: 0.018506532534956932 2023-01-23 19:25:26.039329: step: 2680/1545, loss: 0.12867788970470428 2023-01-23 19:25:26.920855: step: 2682/1545, loss: 0.00017091781774070114 2023-01-23 19:25:27.789695: step: 2684/1545, loss: 0.00024153426056727767 2023-01-23 19:25:28.697492: step: 2686/1545, loss: 0.0006791491177864373 2023-01-23 19:25:29.568929: step: 2688/1545, loss: 0.1619478166103363 2023-01-23 19:25:30.472862: step: 2690/1545, loss: 0.0006410536007024348 2023-01-23 19:25:31.343406: step: 2692/1545, loss: 0.02180221676826477 2023-01-23 19:25:32.262300: step: 2694/1545, loss: 0.19872219860553741 2023-01-23 19:25:33.131716: step: 2696/1545, loss: 0.002032059244811535 2023-01-23 19:25:34.032741: step: 2698/1545, loss: 0.14196106791496277 2023-01-23 19:25:35.024801: step: 2700/1545, loss: 0.010517534799873829 2023-01-23 19:25:35.891613: step: 2702/1545, loss: 0.057398080825805664 2023-01-23 19:25:36.787714: step: 2704/1545, loss: 0.0007279525743797421 2023-01-23 19:25:37.686538: step: 2706/1545, loss: 0.008860468864440918 2023-01-23 19:25:38.527171: step: 2708/1545, loss: 0.0009779416723176837 2023-01-23 19:25:39.377059: step: 2710/1545, loss: 0.007587679661810398 2023-01-23 19:25:40.254504: step: 2712/1545, loss: 0.003985166549682617 2023-01-23 19:25:41.131954: step: 2714/1545, loss: 0.0042521278373897076 2023-01-23 19:25:41.988909: step: 2716/1545, loss: 0.05894320830702782 2023-01-23 19:25:42.841110: step: 2718/1545, loss: 0.006228439975529909 2023-01-23 19:25:43.689917: step: 2720/1545, loss: 0.18322370946407318 2023-01-23 19:25:44.527097: step: 2722/1545, loss: 0.010696201585233212 2023-01-23 19:25:45.435678: step: 2724/1545, loss: 0.0011710033286362886 2023-01-23 19:25:46.317301: step: 2726/1545, loss: 0.010478568263351917 2023-01-23 19:25:47.212623: step: 2728/1545, loss: 0.05983734130859375 2023-01-23 19:25:48.090366: step: 2730/1545, loss: 0.09155953675508499 2023-01-23 19:25:48.964627: step: 2732/1545, loss: 0.0007720690919086337 2023-01-23 19:25:49.857477: step: 2734/1545, loss: 0.0005537578254006803 2023-01-23 19:25:50.722807: step: 2736/1545, loss: 0.0013369711814448237 2023-01-23 19:25:51.548504: step: 2738/1545, loss: 0.059764109551906586 2023-01-23 19:25:52.440027: step: 2740/1545, loss: 0.0037207992281764746 2023-01-23 19:25:53.280402: step: 2742/1545, loss: 0.18808837234973907 2023-01-23 19:25:54.179590: step: 2744/1545, loss: 0.10743873566389084 2023-01-23 19:25:55.101273: step: 2746/1545, loss: 0.00032653784728609025 2023-01-23 19:25:56.012834: step: 2748/1545, loss: 0.06237199902534485 2023-01-23 19:25:56.866862: step: 2750/1545, loss: 0.01176481693983078 2023-01-23 19:25:57.750045: step: 2752/1545, loss: 0.0003739050298463553 2023-01-23 19:25:58.610211: step: 2754/1545, loss: 0.3499033451080322 2023-01-23 19:25:59.502032: step: 2756/1545, loss: 0.014980986714363098 2023-01-23 19:26:00.379649: step: 2758/1545, loss: 0.00016025327204260975 2023-01-23 19:26:01.279762: step: 2760/1545, loss: 0.008410271257162094 2023-01-23 19:26:02.148280: step: 2762/1545, loss: 0.04986630007624626 2023-01-23 19:26:03.052582: step: 2764/1545, loss: 0.12267260253429413 2023-01-23 19:26:03.929343: step: 2766/1545, loss: 0.07344833761453629 2023-01-23 19:26:04.794390: step: 2768/1545, loss: 0.0005097961984574795 2023-01-23 19:26:05.659194: step: 2770/1545, loss: 0.02966810204088688 2023-01-23 19:26:06.511792: step: 2772/1545, loss: 0.0018713303143158555 2023-01-23 19:26:07.371277: step: 2774/1545, loss: 0.1550533026456833 2023-01-23 19:26:08.295976: step: 2776/1545, loss: 8.657592115923762e-05 2023-01-23 19:26:09.193201: step: 2778/1545, loss: 0.2719894051551819 2023-01-23 19:26:10.111178: step: 2780/1545, loss: 0.1518172025680542 2023-01-23 19:26:11.007175: step: 2782/1545, loss: 0.0001793461269699037 2023-01-23 19:26:11.874794: step: 2784/1545, loss: 0.08168861269950867 2023-01-23 19:26:12.743577: step: 2786/1545, loss: 0.0011252580443397164 2023-01-23 19:26:13.628124: step: 2788/1545, loss: 0.0012035365216434002 2023-01-23 19:26:14.560264: step: 2790/1545, loss: 0.20900015532970428 2023-01-23 19:26:15.449466: step: 2792/1545, loss: 0.00019647982844617218 2023-01-23 19:26:16.337991: step: 2794/1545, loss: 0.003871193155646324 2023-01-23 19:26:17.209180: step: 2796/1545, loss: 0.17859667539596558 2023-01-23 19:26:18.130013: step: 2798/1545, loss: 0.0012353698257356882 2023-01-23 19:26:19.036645: step: 2800/1545, loss: 0.005927569232881069 2023-01-23 19:26:19.904140: step: 2802/1545, loss: 0.0036690831184387207 2023-01-23 19:26:20.811802: step: 2804/1545, loss: 0.4934654235839844 2023-01-23 19:26:21.671532: step: 2806/1545, loss: 0.0006718944641761482 2023-01-23 19:26:22.530753: step: 2808/1545, loss: 0.010921403765678406 2023-01-23 19:26:23.398948: step: 2810/1545, loss: 0.06575851142406464 2023-01-23 19:26:24.261668: step: 2812/1545, loss: 0.05918285250663757 2023-01-23 19:26:25.114828: step: 2814/1545, loss: 0.3098819851875305 2023-01-23 19:26:26.041921: step: 2816/1545, loss: 0.04989691078662872 2023-01-23 19:26:26.918308: step: 2818/1545, loss: 0.2591823935508728 2023-01-23 19:26:27.815112: step: 2820/1545, loss: 0.0008544442825950682 2023-01-23 19:26:28.759042: step: 2822/1545, loss: 0.5610397458076477 2023-01-23 19:26:29.689752: step: 2824/1545, loss: 0.027151649817824364 2023-01-23 19:26:30.614706: step: 2826/1545, loss: 0.0011337014148011804 2023-01-23 19:26:31.553030: step: 2828/1545, loss: 0.0010730574140325189 2023-01-23 19:26:32.450714: step: 2830/1545, loss: 0.23031535744667053 2023-01-23 19:26:33.354234: step: 2832/1545, loss: 0.0013034662697464228 2023-01-23 19:26:34.217308: step: 2834/1545, loss: 0.0007738615968264639 2023-01-23 19:26:35.083867: step: 2836/1545, loss: 0.004210509825497866 2023-01-23 19:26:35.941289: step: 2838/1545, loss: 0.016048604622483253 2023-01-23 19:26:36.784621: step: 2840/1545, loss: 0.011885806918144226 2023-01-23 19:26:37.668120: step: 2842/1545, loss: 0.0005361661314964294 2023-01-23 19:26:38.551919: step: 2844/1545, loss: 0.04040120542049408 2023-01-23 19:26:39.476207: step: 2846/1545, loss: 0.0004151803732383996 2023-01-23 19:26:40.374897: step: 2848/1545, loss: 0.3811520040035248 2023-01-23 19:26:41.282549: step: 2850/1545, loss: 0.134108766913414 2023-01-23 19:26:42.197468: step: 2852/1545, loss: 0.09713634103536606 2023-01-23 19:26:43.079274: step: 2854/1545, loss: 0.000585018249694258 2023-01-23 19:26:43.972215: step: 2856/1545, loss: 0.001148028182797134 2023-01-23 19:26:44.852106: step: 2858/1545, loss: 0.5272240042686462 2023-01-23 19:26:45.720008: step: 2860/1545, loss: 0.006620208732783794 2023-01-23 19:26:46.623496: step: 2862/1545, loss: 0.6080799698829651 2023-01-23 19:26:47.599103: step: 2864/1545, loss: 0.0030469694174826145 2023-01-23 19:26:48.506091: step: 2866/1545, loss: 0.004385619889944792 2023-01-23 19:26:49.381118: step: 2868/1545, loss: 0.03155564144253731 2023-01-23 19:26:50.293053: step: 2870/1545, loss: 0.00032790625118650496 2023-01-23 19:26:51.257512: step: 2872/1545, loss: 0.018126197159290314 2023-01-23 19:26:52.136032: step: 2874/1545, loss: 0.03262631967663765 2023-01-23 19:26:53.021571: step: 2876/1545, loss: 0.0208246149122715 2023-01-23 19:26:53.947315: step: 2878/1545, loss: 0.018686046823859215 2023-01-23 19:26:54.845883: step: 2880/1545, loss: 0.0008878543740138412 2023-01-23 19:26:55.722132: step: 2882/1545, loss: 0.0008742207428440452 2023-01-23 19:26:56.719706: step: 2884/1545, loss: 0.002051590010523796 2023-01-23 19:26:57.643757: step: 2886/1545, loss: 0.002493629464879632 2023-01-23 19:26:58.564851: step: 2888/1545, loss: 0.008220765739679337 2023-01-23 19:26:59.424318: step: 2890/1545, loss: 0.64014732837677 2023-01-23 19:27:00.354196: step: 2892/1545, loss: 0.006728081498295069 2023-01-23 19:27:01.256470: step: 2894/1545, loss: 0.0065309274941682816 2023-01-23 19:27:02.140305: step: 2896/1545, loss: 0.0006040779408067465 2023-01-23 19:27:03.025478: step: 2898/1545, loss: 0.08230313658714294 2023-01-23 19:27:03.917608: step: 2900/1545, loss: 0.31941813230514526 2023-01-23 19:27:04.868109: step: 2902/1545, loss: 0.35237884521484375 2023-01-23 19:27:05.727757: step: 2904/1545, loss: 7.732691301498562e-05 2023-01-23 19:27:06.585121: step: 2906/1545, loss: 0.0002364992251386866 2023-01-23 19:27:07.449477: step: 2908/1545, loss: 0.015487344935536385 2023-01-23 19:27:08.327217: step: 2910/1545, loss: 0.007987330667674541 2023-01-23 19:27:09.214633: step: 2912/1545, loss: 0.0004956236225552857 2023-01-23 19:27:10.116174: step: 2914/1545, loss: 0.05489996075630188 2023-01-23 19:27:11.016893: step: 2916/1545, loss: 8.684863860253245e-05 2023-01-23 19:27:11.906027: step: 2918/1545, loss: 0.0048343222588300705 2023-01-23 19:27:12.786971: step: 2920/1545, loss: 0.0004005026421509683 2023-01-23 19:27:13.696794: step: 2922/1545, loss: 0.0966026708483696 2023-01-23 19:27:14.575323: step: 2924/1545, loss: 0.0016426935326308012 2023-01-23 19:27:15.452878: step: 2926/1545, loss: 0.0017172412481158972 2023-01-23 19:27:16.339755: step: 2928/1545, loss: 0.0022559280041605234 2023-01-23 19:27:17.232636: step: 2930/1545, loss: 0.6998571157455444 2023-01-23 19:27:18.103792: step: 2932/1545, loss: 0.0011605521431192756 2023-01-23 19:27:18.974266: step: 2934/1545, loss: 0.00012556779256556183 2023-01-23 19:27:19.860791: step: 2936/1545, loss: 0.0006906604976393282 2023-01-23 19:27:20.801579: step: 2938/1545, loss: 0.014152674935758114 2023-01-23 19:27:21.673066: step: 2940/1545, loss: 0.08757651597261429 2023-01-23 19:27:22.539310: step: 2942/1545, loss: 4.573373371385969e-05 2023-01-23 19:27:23.422484: step: 2944/1545, loss: 0.0008294278522953391 2023-01-23 19:27:24.284288: step: 2946/1545, loss: 0.0007850045221857727 2023-01-23 19:27:25.172256: step: 2948/1545, loss: 0.3900042176246643 2023-01-23 19:27:26.089262: step: 2950/1545, loss: 0.011479916051030159 2023-01-23 19:27:26.958022: step: 2952/1545, loss: 0.0005444258567877114 2023-01-23 19:27:27.843699: step: 2954/1545, loss: 0.00016894785221666098 2023-01-23 19:27:28.684891: step: 2956/1545, loss: 0.005421797279268503 2023-01-23 19:27:29.545842: step: 2958/1545, loss: 0.0008926467271521688 2023-01-23 19:27:30.459318: step: 2960/1545, loss: 0.12815415859222412 2023-01-23 19:27:31.326280: step: 2962/1545, loss: 0.005134889390319586 2023-01-23 19:27:32.236582: step: 2964/1545, loss: 0.004174669738858938 2023-01-23 19:27:33.146138: step: 2966/1545, loss: 0.09842552989721298 2023-01-23 19:27:34.028230: step: 2968/1545, loss: 0.11204074323177338 2023-01-23 19:27:34.937164: step: 2970/1545, loss: 0.04742477461695671 2023-01-23 19:27:35.803920: step: 2972/1545, loss: 0.0003720985259860754 2023-01-23 19:27:36.674994: step: 2974/1545, loss: 0.7656404376029968 2023-01-23 19:27:37.565863: step: 2976/1545, loss: 0.02146993577480316 2023-01-23 19:27:38.422936: step: 2978/1545, loss: 0.0002869204035960138 2023-01-23 19:27:39.303945: step: 2980/1545, loss: 7.037357136141509e-05 2023-01-23 19:27:40.144474: step: 2982/1545, loss: 0.2408706098794937 2023-01-23 19:27:40.983244: step: 2984/1545, loss: 0.0008205602061934769 2023-01-23 19:27:41.862259: step: 2986/1545, loss: 0.0627203956246376 2023-01-23 19:27:42.729889: step: 2988/1545, loss: 0.005459269508719444 2023-01-23 19:27:43.594903: step: 2990/1545, loss: 0.17615407705307007 2023-01-23 19:27:44.462231: step: 2992/1545, loss: 0.001581816584803164 2023-01-23 19:27:45.336558: step: 2994/1545, loss: 0.0126254353672266 2023-01-23 19:27:46.255306: step: 2996/1545, loss: 0.007774396799504757 2023-01-23 19:27:47.174879: step: 2998/1545, loss: 0.12066121399402618 2023-01-23 19:27:48.038077: step: 3000/1545, loss: 0.0002156505943275988 2023-01-23 19:27:48.967566: step: 3002/1545, loss: 0.003811987116932869 2023-01-23 19:27:49.846028: step: 3004/1545, loss: 0.0008277941378764808 2023-01-23 19:27:50.764874: step: 3006/1545, loss: 0.00031633261824026704 2023-01-23 19:27:51.647250: step: 3008/1545, loss: 0.7617658376693726 2023-01-23 19:27:52.556451: step: 3010/1545, loss: 0.007828938774764538 2023-01-23 19:27:53.411564: step: 3012/1545, loss: 0.14962582290172577 2023-01-23 19:27:54.291862: step: 3014/1545, loss: 0.008572712540626526 2023-01-23 19:27:55.193328: step: 3016/1545, loss: 0.002811754122376442 2023-01-23 19:27:56.050847: step: 3018/1545, loss: 0.02055109664797783 2023-01-23 19:27:56.978439: step: 3020/1545, loss: 0.0056006028316915035 2023-01-23 19:27:57.857413: step: 3022/1545, loss: 0.0023694667033851147 2023-01-23 19:27:58.748401: step: 3024/1545, loss: 0.01987205259501934 2023-01-23 19:27:59.675547: step: 3026/1545, loss: 0.025414733216166496 2023-01-23 19:28:00.550645: step: 3028/1545, loss: 0.04791386052966118 2023-01-23 19:28:01.420870: step: 3030/1545, loss: 0.0004917776095680892 2023-01-23 19:28:02.414368: step: 3032/1545, loss: 0.004701814614236355 2023-01-23 19:28:03.294383: step: 3034/1545, loss: 0.146093487739563 2023-01-23 19:28:04.212313: step: 3036/1545, loss: 0.0006663495441898704 2023-01-23 19:28:05.093050: step: 3038/1545, loss: 0.015766581520438194 2023-01-23 19:28:06.002875: step: 3040/1545, loss: 0.010529562830924988 2023-01-23 19:28:06.885447: step: 3042/1545, loss: 0.0004619307001121342 2023-01-23 19:28:07.782690: step: 3044/1545, loss: 0.0008851097663864493 2023-01-23 19:28:08.655433: step: 3046/1545, loss: 0.12256951630115509 2023-01-23 19:28:09.499931: step: 3048/1545, loss: 0.016375485807657242 2023-01-23 19:28:10.330944: step: 3050/1545, loss: 0.03426593542098999 2023-01-23 19:28:11.197933: step: 3052/1545, loss: 0.026892319321632385 2023-01-23 19:28:12.097742: step: 3054/1545, loss: 0.002698882482945919 2023-01-23 19:28:12.937116: step: 3056/1545, loss: 0.0008388545829802752 2023-01-23 19:28:13.801209: step: 3058/1545, loss: 0.0005899563548155129 2023-01-23 19:28:14.653054: step: 3060/1545, loss: 0.0005209405208006501 2023-01-23 19:28:15.517823: step: 3062/1545, loss: 0.0005250131944194436 2023-01-23 19:28:16.382251: step: 3064/1545, loss: 0.004815840162336826 2023-01-23 19:28:17.257491: step: 3066/1545, loss: 0.002901441417634487 2023-01-23 19:28:18.159508: step: 3068/1545, loss: 0.0811939537525177 2023-01-23 19:28:19.064763: step: 3070/1545, loss: 0.010561591014266014 2023-01-23 19:28:20.045591: step: 3072/1545, loss: 0.0003193838056176901 2023-01-23 19:28:20.899674: step: 3074/1545, loss: 0.028419876471161842 2023-01-23 19:28:21.737516: step: 3076/1545, loss: 0.09844852238893509 2023-01-23 19:28:22.586564: step: 3078/1545, loss: 0.002262439578771591 2023-01-23 19:28:23.504222: step: 3080/1545, loss: 0.10180294513702393 2023-01-23 19:28:24.360578: step: 3082/1545, loss: 0.014142283238470554 2023-01-23 19:28:25.206965: step: 3084/1545, loss: 0.021872229874134064 2023-01-23 19:28:26.093415: step: 3086/1545, loss: 0.04665625840425491 2023-01-23 19:28:26.976525: step: 3088/1545, loss: 0.17690452933311462 2023-01-23 19:28:27.870936: step: 3090/1545, loss: 0.0011728546814993024 ================================================== Loss: 0.060 -------------------- Dev Chinese: {'event': {'p': 0.5965103598691385, 'r': 0.7283621837549934, 'f1': 0.6558752997601919}, 'argument': {'p': 0.6568691654364283, 'r': 0.6529299200664946, 'f1': 0.6548936190742135}, 'combined': 0.4295285487213367, 'epoch': 30} Test Chinese: {'event': {'p': 0.6398078975453575, 'r': 0.7666240409207161, 'f1': 0.6974985456660848}, 'argument': {'p': 0.6989078550712907, 'r': 0.7154532109378123, 'f1': 0.7070837582815586}, 'combined': 0.49318989306549654, 'epoch': 30} Dev Korean: {'event': {'p': 0.6039387308533917, 'r': 0.7350199733688415, 'f1': 0.6630630630630631}, 'argument': {'p': 0.6603470462480774, 'r': 0.6504170154774296, 'f1': 0.6553444171098344}, 'combined': 0.4345346765701244, 'epoch': 30} Test Korean: {'event': {'p': 0.6322751322751323, 'r': 0.7640664961636828, 'f1': 0.6919513607411696}, 'argument': {'p': 0.6924051969707655, 'r': 0.7143653159423259, 'f1': 0.7032138543618833}, 'combined': 0.48658978341774783, 'epoch': 30} Dev Russian: {'event': {'p': 0.562992125984252, 'r': 0.7616511318242344, 'f1': 0.6474250141482739}, 'argument': {'p': 0.6530003386611138, 'r': 0.6600067800630571, 'f1': 0.656484865548313}, 'combined': 0.4250247233657442, 'epoch': 30} Test Russian: {'event': {'p': 0.6263079222720478, 'r': 0.8037084398976982, 'f1': 0.7040044805376645}, 'argument': {'p': 0.7005633317324845, 'r': 0.7254804101729885, 'f1': 0.7128041845032378}, 'combined': 0.5018173396362755, 'epoch': 30} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6680506993006993, 'r': 0.5741923365890308, 'f1': 0.6175757575757576}, 'combined': 0.4397887970615243, 'epoch': 30} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6238229755178908, 'r': 0.504185692541857, 'f1': 0.5576599326599326}, 'combined': 0.35220627325890486, 'epoch': 30} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5686085018372468, 'r': 0.527993608848872, 'f1': 0.5475489276951265}, 'combined': 0.3049639597289312, 'epoch': 30} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6559451265403835, 'r': 0.6613377994790564, 'f1': 0.6586304247882229}, 'combined': 0.43355887674908195, 'epoch': 26} Test for Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6980547354393568, 'r': 0.7185779178100443, 'f1': 0.7081676638737557}, 'combined': 0.49271002093834315, 'epoch': 26} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6657901327322815, 'r': 0.6657901327322815, 'f1': 0.6657901327322815}, 'combined': 0.47412327633965495, 'epoch': 26} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 31 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 19:33:42.018756: step: 2/1545, loss: 0.0457974374294281 2023-01-23 19:33:42.876170: step: 4/1545, loss: 0.0021151911932975054 2023-01-23 19:33:43.738271: step: 6/1545, loss: 0.07819032669067383 2023-01-23 19:33:44.631254: step: 8/1545, loss: 0.06359471380710602 2023-01-23 19:33:45.460289: step: 10/1545, loss: 0.0003389218763913959 2023-01-23 19:33:46.318364: step: 12/1545, loss: 0.10460180789232254 2023-01-23 19:33:47.216997: step: 14/1545, loss: 6.120905163697898e-05 2023-01-23 19:33:48.116794: step: 16/1545, loss: 0.01769229955971241 2023-01-23 19:33:48.989967: step: 18/1545, loss: 0.00012870374484919012 2023-01-23 19:33:49.876319: step: 20/1545, loss: 0.004751331172883511 2023-01-23 19:33:50.778026: step: 22/1545, loss: 0.06277773529291153 2023-01-23 19:33:51.651050: step: 24/1545, loss: 0.005788966082036495 2023-01-23 19:33:52.532546: step: 26/1545, loss: 0.00024154630955308676 2023-01-23 19:33:53.429792: step: 28/1545, loss: 0.00014129167539067566 2023-01-23 19:33:54.282762: step: 30/1545, loss: 0.000144646706758067 2023-01-23 19:33:55.150456: step: 32/1545, loss: 0.1673530638217926 2023-01-23 19:33:56.090089: step: 34/1545, loss: 0.0005857189535163343 2023-01-23 19:33:56.964530: step: 36/1545, loss: 0.0004113032191526145 2023-01-23 19:33:57.828794: step: 38/1545, loss: 0.038793087005615234 2023-01-23 19:33:58.718349: step: 40/1545, loss: 0.04214152693748474 2023-01-23 19:33:59.634013: step: 42/1545, loss: 0.44482672214508057 2023-01-23 19:34:00.512068: step: 44/1545, loss: 0.057780344039201736 2023-01-23 19:34:01.363985: step: 46/1545, loss: 0.031856469810009 2023-01-23 19:34:02.231471: step: 48/1545, loss: 0.0031823511235415936 2023-01-23 19:34:03.101824: step: 50/1545, loss: 0.027138983830809593 2023-01-23 19:34:03.971067: step: 52/1545, loss: 0.023204371333122253 2023-01-23 19:34:04.894282: step: 54/1545, loss: 0.0002675289288163185 2023-01-23 19:34:05.764667: step: 56/1545, loss: 0.0014646246563643217 2023-01-23 19:34:06.585856: step: 58/1545, loss: 0.0010550584411248565 2023-01-23 19:34:07.449213: step: 60/1545, loss: 0.0002871446777135134 2023-01-23 19:34:08.324223: step: 62/1545, loss: 4.491515574045479e-05 2023-01-23 19:34:09.174191: step: 64/1545, loss: 0.2775777578353882 2023-01-23 19:34:10.018948: step: 66/1545, loss: 0.0002639474405441433 2023-01-23 19:34:10.920481: step: 68/1545, loss: 0.0036310385912656784 2023-01-23 19:34:11.796689: step: 70/1545, loss: 0.35336732864379883 2023-01-23 19:34:12.676133: step: 72/1545, loss: 0.070757195353508 2023-01-23 19:34:13.580334: step: 74/1545, loss: 0.001273397821933031 2023-01-23 19:34:14.460272: step: 76/1545, loss: 0.0006652980810031295 2023-01-23 19:34:15.339131: step: 78/1545, loss: 0.00018738603102974594 2023-01-23 19:34:16.258306: step: 80/1545, loss: 0.0008295850129798055 2023-01-23 19:34:17.137275: step: 82/1545, loss: 3.116576671600342 2023-01-23 19:34:17.995265: step: 84/1545, loss: 6.123351340647787e-05 2023-01-23 19:34:18.868374: step: 86/1545, loss: 0.00031481526093557477 2023-01-23 19:34:19.786275: step: 88/1545, loss: 0.0005135429091751575 2023-01-23 19:34:20.651932: step: 90/1545, loss: 0.00016770910588093102 2023-01-23 19:34:21.534067: step: 92/1545, loss: 0.4636172652244568 2023-01-23 19:34:22.412233: step: 94/1545, loss: 0.006615385878831148 2023-01-23 19:34:23.290644: step: 96/1545, loss: 0.00018352002371102571 2023-01-23 19:34:24.193990: step: 98/1545, loss: 0.01529366709291935 2023-01-23 19:34:25.044646: step: 100/1545, loss: 0.7000575661659241 2023-01-23 19:34:25.980286: step: 102/1545, loss: 0.022973135113716125 2023-01-23 19:34:26.854888: step: 104/1545, loss: 0.0007173694320954382 2023-01-23 19:34:27.766037: step: 106/1545, loss: 0.0001263895392185077 2023-01-23 19:34:28.631922: step: 108/1545, loss: 0.00410790229216218 2023-01-23 19:34:29.520477: step: 110/1545, loss: 0.040035150945186615 2023-01-23 19:34:30.519273: step: 112/1545, loss: 0.03671889379620552 2023-01-23 19:34:31.437989: step: 114/1545, loss: 0.004114670678973198 2023-01-23 19:34:32.286755: step: 116/1545, loss: 0.00014741370978299528 2023-01-23 19:34:33.140572: step: 118/1545, loss: 0.03478746861219406 2023-01-23 19:34:33.988380: step: 120/1545, loss: 0.0010404034983366728 2023-01-23 19:34:34.864988: step: 122/1545, loss: 1.622253179550171 2023-01-23 19:34:35.737329: step: 124/1545, loss: 0.0003646104014478624 2023-01-23 19:34:36.615633: step: 126/1545, loss: 0.0002556119579821825 2023-01-23 19:34:37.464152: step: 128/1545, loss: 0.023174580186605453 2023-01-23 19:34:38.326339: step: 130/1545, loss: 0.00016725609020795673 2023-01-23 19:34:39.214316: step: 132/1545, loss: 0.0010378587758168578 2023-01-23 19:34:40.077853: step: 134/1545, loss: 0.0004770256346091628 2023-01-23 19:34:40.950664: step: 136/1545, loss: 0.0244903564453125 2023-01-23 19:34:41.817593: step: 138/1545, loss: 0.0001585801219334826 2023-01-23 19:34:42.695978: step: 140/1545, loss: 0.20785948634147644 2023-01-23 19:34:43.615283: step: 142/1545, loss: 0.056756436824798584 2023-01-23 19:34:44.475600: step: 144/1545, loss: 0.00046278355875983834 2023-01-23 19:34:45.344703: step: 146/1545, loss: 1.573554072820116e-05 2023-01-23 19:34:46.207578: step: 148/1545, loss: 0.0002465139259584248 2023-01-23 19:34:47.122117: step: 150/1545, loss: 0.0036693450529128313 2023-01-23 19:34:48.031306: step: 152/1545, loss: 0.10442958772182465 2023-01-23 19:34:48.977423: step: 154/1545, loss: 0.18338975310325623 2023-01-23 19:34:49.807958: step: 156/1545, loss: 0.07266511023044586 2023-01-23 19:34:50.703679: step: 158/1545, loss: 0.3039599359035492 2023-01-23 19:34:51.657027: step: 160/1545, loss: 0.03847745060920715 2023-01-23 19:34:52.540665: step: 162/1545, loss: 0.0007347515784204006 2023-01-23 19:34:53.405675: step: 164/1545, loss: 0.00031194754410535097 2023-01-23 19:34:54.290915: step: 166/1545, loss: 0.008281228132545948 2023-01-23 19:34:55.169696: step: 168/1545, loss: 0.2039927840232849 2023-01-23 19:34:56.068924: step: 170/1545, loss: 0.00019525657990016043 2023-01-23 19:34:56.962359: step: 172/1545, loss: 0.009427543729543686 2023-01-23 19:34:57.841988: step: 174/1545, loss: 9.504953777650371e-05 2023-01-23 19:34:58.736593: step: 176/1545, loss: 0.006181923672556877 2023-01-23 19:34:59.606032: step: 178/1545, loss: 0.000681847392115742 2023-01-23 19:35:00.496323: step: 180/1545, loss: 0.0035205965396016836 2023-01-23 19:35:01.362768: step: 182/1545, loss: 0.0479288212954998 2023-01-23 19:35:02.237233: step: 184/1545, loss: 0.009675730019807816 2023-01-23 19:35:03.109710: step: 186/1545, loss: 0.010814924724400043 2023-01-23 19:35:03.965526: step: 188/1545, loss: 0.0013684021541848779 2023-01-23 19:35:04.863886: step: 190/1545, loss: 0.0001871084386948496 2023-01-23 19:35:05.725347: step: 192/1545, loss: 0.009882464073598385 2023-01-23 19:35:06.578827: step: 194/1545, loss: 0.00040502933552488685 2023-01-23 19:35:07.504414: step: 196/1545, loss: 0.001624761731363833 2023-01-23 19:35:08.419160: step: 198/1545, loss: 0.0014548037433996797 2023-01-23 19:35:09.298832: step: 200/1545, loss: 0.00024403455608990043 2023-01-23 19:35:10.173661: step: 202/1545, loss: 0.0001447204704163596 2023-01-23 19:35:11.046469: step: 204/1545, loss: 0.2601771056652069 2023-01-23 19:35:11.924466: step: 206/1545, loss: 0.05979766696691513 2023-01-23 19:35:12.808384: step: 208/1545, loss: 0.006266883574426174 2023-01-23 19:35:13.699133: step: 210/1545, loss: 0.19396701455116272 2023-01-23 19:35:14.598281: step: 212/1545, loss: 4.956348129780963e-05 2023-01-23 19:35:15.436208: step: 214/1545, loss: 0.2643026113510132 2023-01-23 19:35:16.268915: step: 216/1545, loss: 0.3679148256778717 2023-01-23 19:35:17.143612: step: 218/1545, loss: 0.10550114512443542 2023-01-23 19:35:18.007220: step: 220/1545, loss: 0.47335851192474365 2023-01-23 19:35:18.910110: step: 222/1545, loss: 0.00016732190852053463 2023-01-23 19:35:19.779146: step: 224/1545, loss: 0.0016131800366565585 2023-01-23 19:35:20.666777: step: 226/1545, loss: 0.0003196595353074372 2023-01-23 19:35:21.523197: step: 228/1545, loss: 0.06807957589626312 2023-01-23 19:35:22.360100: step: 230/1545, loss: 3.6225970688974485e-05 2023-01-23 19:35:23.225199: step: 232/1545, loss: 0.00012741035607177764 2023-01-23 19:35:24.103694: step: 234/1545, loss: 0.015099373646080494 2023-01-23 19:35:24.986919: step: 236/1545, loss: 0.0018111898098140955 2023-01-23 19:35:25.855614: step: 238/1545, loss: 0.0007763224421069026 2023-01-23 19:35:26.719576: step: 240/1545, loss: 0.06097942963242531 2023-01-23 19:35:27.613586: step: 242/1545, loss: 0.14444732666015625 2023-01-23 19:35:28.480940: step: 244/1545, loss: 0.0019195952918380499 2023-01-23 19:35:29.334297: step: 246/1545, loss: 0.000809492077678442 2023-01-23 19:35:30.206520: step: 248/1545, loss: 0.04838670417666435 2023-01-23 19:35:31.116058: step: 250/1545, loss: 0.008227641694247723 2023-01-23 19:35:31.999200: step: 252/1545, loss: 0.01178094744682312 2023-01-23 19:35:32.849228: step: 254/1545, loss: 0.00017457343346904963 2023-01-23 19:35:33.748840: step: 256/1545, loss: 0.004527936689555645 2023-01-23 19:35:34.660065: step: 258/1545, loss: 0.0023708664812147617 2023-01-23 19:35:35.519481: step: 260/1545, loss: 0.0007931609288789332 2023-01-23 19:35:36.399697: step: 262/1545, loss: 0.00032683974131941795 2023-01-23 19:35:37.286635: step: 264/1545, loss: 3.206650580978021e-05 2023-01-23 19:35:38.184170: step: 266/1545, loss: 0.0002651710528880358 2023-01-23 19:35:39.032414: step: 268/1545, loss: 0.0005769761046394706 2023-01-23 19:35:39.898235: step: 270/1545, loss: 0.015562839806079865 2023-01-23 19:35:40.788576: step: 272/1545, loss: 0.011031717993319035 2023-01-23 19:35:41.688748: step: 274/1545, loss: 0.08875874429941177 2023-01-23 19:35:42.548588: step: 276/1545, loss: 6.176784518174827e-05 2023-01-23 19:35:43.408262: step: 278/1545, loss: 0.024161888286471367 2023-01-23 19:35:44.280995: step: 280/1545, loss: 0.09386615455150604 2023-01-23 19:35:45.190445: step: 282/1545, loss: 0.0010476530296728015 2023-01-23 19:35:46.090744: step: 284/1545, loss: 0.01961343176662922 2023-01-23 19:35:47.004661: step: 286/1545, loss: 0.00020426228002179414 2023-01-23 19:35:47.872986: step: 288/1545, loss: 0.003809460438787937 2023-01-23 19:35:48.757220: step: 290/1545, loss: 0.0007620682008564472 2023-01-23 19:35:49.666467: step: 292/1545, loss: 4.861547131440602e-05 2023-01-23 19:35:50.559616: step: 294/1545, loss: 1.582166260050144e-05 2023-01-23 19:35:51.403481: step: 296/1545, loss: 0.14677047729492188 2023-01-23 19:35:52.297602: step: 298/1545, loss: 0.007014798000454903 2023-01-23 19:35:53.172444: step: 300/1545, loss: 0.0023151766508817673 2023-01-23 19:35:54.052821: step: 302/1545, loss: 4.489059210754931e-05 2023-01-23 19:35:54.930809: step: 304/1545, loss: 0.007965188473463058 2023-01-23 19:35:55.828067: step: 306/1545, loss: 0.008631122298538685 2023-01-23 19:35:56.666266: step: 308/1545, loss: 0.0017974645597860217 2023-01-23 19:35:57.556729: step: 310/1545, loss: 0.0016898898174986243 2023-01-23 19:35:58.495340: step: 312/1545, loss: 0.024355847388505936 2023-01-23 19:35:59.409519: step: 314/1545, loss: 0.08204574137926102 2023-01-23 19:36:00.264671: step: 316/1545, loss: 0.00035384544753469527 2023-01-23 19:36:01.163347: step: 318/1545, loss: 5.476009755511768e-05 2023-01-23 19:36:02.038211: step: 320/1545, loss: 0.0008103079744614661 2023-01-23 19:36:02.888690: step: 322/1545, loss: 0.00021643568470608443 2023-01-23 19:36:03.771362: step: 324/1545, loss: 0.00035616103559732437 2023-01-23 19:36:04.642315: step: 326/1545, loss: 0.0003996389568783343 2023-01-23 19:36:05.548991: step: 328/1545, loss: 0.12572064995765686 2023-01-23 19:36:06.431109: step: 330/1545, loss: 2.3159753254731186e-05 2023-01-23 19:36:07.307176: step: 332/1545, loss: 0.0005551694193854928 2023-01-23 19:36:08.142369: step: 334/1545, loss: 0.22978614270687103 2023-01-23 19:36:09.017413: step: 336/1545, loss: 0.006896049715578556 2023-01-23 19:36:09.871249: step: 338/1545, loss: 0.00015086535131558776 2023-01-23 19:36:10.763556: step: 340/1545, loss: 0.26000407338142395 2023-01-23 19:36:11.681301: step: 342/1545, loss: 0.0019270750926807523 2023-01-23 19:36:12.567085: step: 344/1545, loss: 0.0038004079833626747 2023-01-23 19:36:13.439883: step: 346/1545, loss: 0.001972415717318654 2023-01-23 19:36:14.327686: step: 348/1545, loss: 8.039498061407357e-05 2023-01-23 19:36:15.166035: step: 350/1545, loss: 0.10840743780136108 2023-01-23 19:36:16.001739: step: 352/1545, loss: 9.390201739734039e-05 2023-01-23 19:36:16.854048: step: 354/1545, loss: 0.0899808406829834 2023-01-23 19:36:17.692961: step: 356/1545, loss: 0.002434891415759921 2023-01-23 19:36:18.549045: step: 358/1545, loss: 0.0029633298981934786 2023-01-23 19:36:19.458080: step: 360/1545, loss: 5.280278128338978e-05 2023-01-23 19:36:20.341264: step: 362/1545, loss: 0.0023695919662714005 2023-01-23 19:36:21.247870: step: 364/1545, loss: 0.008618725463747978 2023-01-23 19:36:22.106484: step: 366/1545, loss: 0.2743538022041321 2023-01-23 19:36:22.969241: step: 368/1545, loss: 0.007012295536696911 2023-01-23 19:36:23.872067: step: 370/1545, loss: 0.015286926180124283 2023-01-23 19:36:24.781114: step: 372/1545, loss: 7.148295117076486e-05 2023-01-23 19:36:25.686663: step: 374/1545, loss: 0.0008781066280789673 2023-01-23 19:36:26.598713: step: 376/1545, loss: 0.03998512774705887 2023-01-23 19:36:27.491051: step: 378/1545, loss: 0.0020735592115670443 2023-01-23 19:36:28.385842: step: 380/1545, loss: 0.010515042580664158 2023-01-23 19:36:29.271389: step: 382/1545, loss: 0.019234808161854744 2023-01-23 19:36:30.118767: step: 384/1545, loss: 0.00024313890025950968 2023-01-23 19:36:30.938280: step: 386/1545, loss: 0.003085765754804015 2023-01-23 19:36:31.818204: step: 388/1545, loss: 0.24245332181453705 2023-01-23 19:36:32.676800: step: 390/1545, loss: 0.009567315690219402 2023-01-23 19:36:33.524433: step: 392/1545, loss: 0.0021632625721395016 2023-01-23 19:36:34.424387: step: 394/1545, loss: 0.09944910556077957 2023-01-23 19:36:35.308132: step: 396/1545, loss: 0.15818603336811066 2023-01-23 19:36:36.151994: step: 398/1545, loss: 0.000983591889962554 2023-01-23 19:36:37.021777: step: 400/1545, loss: 0.019567808136343956 2023-01-23 19:36:37.882224: step: 402/1545, loss: 0.00044433315633796155 2023-01-23 19:36:38.733487: step: 404/1545, loss: 0.02239181101322174 2023-01-23 19:36:39.646710: step: 406/1545, loss: 0.006991520989686251 2023-01-23 19:36:40.495768: step: 408/1545, loss: 0.2819092571735382 2023-01-23 19:36:41.452823: step: 410/1545, loss: 0.0004677716933656484 2023-01-23 19:36:42.319455: step: 412/1545, loss: 8.752061694394797e-05 2023-01-23 19:36:43.200882: step: 414/1545, loss: 0.0020336871966719627 2023-01-23 19:36:44.067005: step: 416/1545, loss: 0.01102028600871563 2023-01-23 19:36:44.942753: step: 418/1545, loss: 2.832287282217294e-05 2023-01-23 19:36:45.893296: step: 420/1545, loss: 0.0002153143286705017 2023-01-23 19:36:46.771740: step: 422/1545, loss: 0.004224508069455624 2023-01-23 19:36:47.665582: step: 424/1545, loss: 0.052604276686906815 2023-01-23 19:36:48.532480: step: 426/1545, loss: 2.1442518118419684e-05 2023-01-23 19:36:49.434208: step: 428/1545, loss: 0.00024526051129214466 2023-01-23 19:36:50.267863: step: 430/1545, loss: 0.003033525077626109 2023-01-23 19:36:51.157345: step: 432/1545, loss: 0.1950288861989975 2023-01-23 19:36:52.056717: step: 434/1545, loss: 0.0068237814120948315 2023-01-23 19:36:52.975267: step: 436/1545, loss: 0.0008962274296209216 2023-01-23 19:36:53.823731: step: 438/1545, loss: 0.0007166139548644423 2023-01-23 19:36:54.664298: step: 440/1545, loss: 0.00036447655293159187 2023-01-23 19:36:55.582147: step: 442/1545, loss: 0.04743954911828041 2023-01-23 19:36:56.497942: step: 444/1545, loss: 0.04824198782444 2023-01-23 19:36:57.484079: step: 446/1545, loss: 0.08168282359838486 2023-01-23 19:36:58.375306: step: 448/1545, loss: 0.23297253251075745 2023-01-23 19:36:59.222835: step: 450/1545, loss: 8.577705011703074e-05 2023-01-23 19:37:00.143862: step: 452/1545, loss: 0.00031072390265762806 2023-01-23 19:37:01.031055: step: 454/1545, loss: 0.04334821179509163 2023-01-23 19:37:01.897685: step: 456/1545, loss: 0.8818139433860779 2023-01-23 19:37:02.767826: step: 458/1545, loss: 0.00038728181971237063 2023-01-23 19:37:03.645096: step: 460/1545, loss: 0.004800140857696533 2023-01-23 19:37:04.510513: step: 462/1545, loss: 2.225201933470089e-05 2023-01-23 19:37:05.390150: step: 464/1545, loss: 0.0010891517158597708 2023-01-23 19:37:06.281888: step: 466/1545, loss: 0.054109279066324234 2023-01-23 19:37:07.160019: step: 468/1545, loss: 0.08140832185745239 2023-01-23 19:37:08.008319: step: 470/1545, loss: 0.00032643935992382467 2023-01-23 19:37:08.959342: step: 472/1545, loss: 0.0009413030929863453 2023-01-23 19:37:09.841278: step: 474/1545, loss: 0.004145655781030655 2023-01-23 19:37:10.699946: step: 476/1545, loss: 0.0014267328660935163 2023-01-23 19:37:11.602515: step: 478/1545, loss: 1.0414576530456543 2023-01-23 19:37:12.460869: step: 480/1545, loss: 1.6052752471296117e-05 2023-01-23 19:37:13.358692: step: 482/1545, loss: 0.0005290363915264606 2023-01-23 19:37:14.248044: step: 484/1545, loss: 0.00020553066860884428 2023-01-23 19:37:15.149331: step: 486/1545, loss: 0.00016123070963658392 2023-01-23 19:37:16.021991: step: 488/1545, loss: 0.0019417440053075552 2023-01-23 19:37:16.949986: step: 490/1545, loss: 3.5535122151486576e-05 2023-01-23 19:37:17.811387: step: 492/1545, loss: 0.00026450195582583547 2023-01-23 19:37:18.687499: step: 494/1545, loss: 0.0010942477965727448 2023-01-23 19:37:19.554566: step: 496/1545, loss: 0.005317332688719034 2023-01-23 19:37:20.523129: step: 498/1545, loss: 0.0020082127302885056 2023-01-23 19:37:21.427945: step: 500/1545, loss: 0.00028956920141354203 2023-01-23 19:37:22.331503: step: 502/1545, loss: 0.0012151652481406927 2023-01-23 19:37:23.184429: step: 504/1545, loss: 0.0001817358861444518 2023-01-23 19:37:24.037282: step: 506/1545, loss: 0.0002981803263537586 2023-01-23 19:37:24.914074: step: 508/1545, loss: 0.0002684803039301187 2023-01-23 19:37:25.787408: step: 510/1545, loss: 6.508354999823496e-05 2023-01-23 19:37:26.649671: step: 512/1545, loss: 0.0011515120277181268 2023-01-23 19:37:27.540219: step: 514/1545, loss: 0.0003735796781256795 2023-01-23 19:37:28.439531: step: 516/1545, loss: -1.4264318451751024e-05 2023-01-23 19:37:29.339797: step: 518/1545, loss: 0.29958465695381165 2023-01-23 19:37:30.225030: step: 520/1545, loss: 0.0002835392369888723 2023-01-23 19:37:31.104873: step: 522/1545, loss: 0.019167905673384666 2023-01-23 19:37:31.962284: step: 524/1545, loss: 0.28128787875175476 2023-01-23 19:37:32.850656: step: 526/1545, loss: 0.0034620026126503944 2023-01-23 19:37:33.711800: step: 528/1545, loss: 0.0017779862973839045 2023-01-23 19:37:34.561199: step: 530/1545, loss: 0.010123809799551964 2023-01-23 19:37:35.459158: step: 532/1545, loss: 0.0005428428994491696 2023-01-23 19:37:36.358286: step: 534/1545, loss: 0.11712717264890671 2023-01-23 19:37:37.264851: step: 536/1545, loss: 0.00018081997404806316 2023-01-23 19:37:38.117641: step: 538/1545, loss: 0.0023417682386934757 2023-01-23 19:37:38.986272: step: 540/1545, loss: 0.0007088069687597454 2023-01-23 19:37:39.940620: step: 542/1545, loss: 0.3415057063102722 2023-01-23 19:37:40.881765: step: 544/1545, loss: 1.079846739768982 2023-01-23 19:37:41.722492: step: 546/1545, loss: 0.0010576540371403098 2023-01-23 19:37:42.614546: step: 548/1545, loss: 0.0035016576293855906 2023-01-23 19:37:43.555265: step: 550/1545, loss: 0.01154184527695179 2023-01-23 19:37:44.397533: step: 552/1545, loss: 0.014114169403910637 2023-01-23 19:37:45.230759: step: 554/1545, loss: 0.004148286301642656 2023-01-23 19:37:46.123726: step: 556/1545, loss: 0.0008145220344886184 2023-01-23 19:37:46.977431: step: 558/1545, loss: 5.186907947063446e-05 2023-01-23 19:37:47.840949: step: 560/1545, loss: 0.00018758286023512483 2023-01-23 19:37:48.711547: step: 562/1545, loss: 0.003153498750180006 2023-01-23 19:37:49.619700: step: 564/1545, loss: 0.031604718416929245 2023-01-23 19:37:50.482719: step: 566/1545, loss: 0.0008699659374542534 2023-01-23 19:37:51.327345: step: 568/1545, loss: 0.0003034144756384194 2023-01-23 19:37:52.181707: step: 570/1545, loss: 0.030617162585258484 2023-01-23 19:37:53.065334: step: 572/1545, loss: 0.0006599276093766093 2023-01-23 19:37:53.911273: step: 574/1545, loss: 0.004314290825277567 2023-01-23 19:37:54.786532: step: 576/1545, loss: 0.19033941626548767 2023-01-23 19:37:55.691509: step: 578/1545, loss: 5.123665323480964e-05 2023-01-23 19:37:56.556628: step: 580/1545, loss: 8.968756446847692e-06 2023-01-23 19:37:57.452406: step: 582/1545, loss: 0.0004911816213279963 2023-01-23 19:37:58.332383: step: 584/1545, loss: 2.7138283252716064 2023-01-23 19:37:59.185065: step: 586/1545, loss: 0.00013934067101217806 2023-01-23 19:38:00.049514: step: 588/1545, loss: 0.04381193965673447 2023-01-23 19:38:00.899683: step: 590/1545, loss: 0.0002972673100885004 2023-01-23 19:38:01.808024: step: 592/1545, loss: 0.00010884180665016174 2023-01-23 19:38:02.706215: step: 594/1545, loss: 0.15844722092151642 2023-01-23 19:38:03.645279: step: 596/1545, loss: 0.0018985588103532791 2023-01-23 19:38:04.526469: step: 598/1545, loss: 0.0006406446336768568 2023-01-23 19:38:05.392159: step: 600/1545, loss: 0.0011398105416446924 2023-01-23 19:38:06.295735: step: 602/1545, loss: -3.4039042020594934e-06 2023-01-23 19:38:07.157204: step: 604/1545, loss: 2.4935698093031533e-05 2023-01-23 19:38:07.989969: step: 606/1545, loss: 0.121921606361866 2023-01-23 19:38:08.819070: step: 608/1545, loss: 0.0005459932144731283 2023-01-23 19:38:09.696736: step: 610/1545, loss: 0.7985661029815674 2023-01-23 19:38:10.593564: step: 612/1545, loss: 0.0003570847329683602 2023-01-23 19:38:11.522804: step: 614/1545, loss: 0.4672592580318451 2023-01-23 19:38:12.383469: step: 616/1545, loss: 0.0006871307850815356 2023-01-23 19:38:13.300225: step: 618/1545, loss: 0.0010555736953392625 2023-01-23 19:38:14.171049: step: 620/1545, loss: 0.22505402565002441 2023-01-23 19:38:15.086085: step: 622/1545, loss: 0.00104277185164392 2023-01-23 19:38:15.969566: step: 624/1545, loss: 0.19420014321804047 2023-01-23 19:38:16.849537: step: 626/1545, loss: 0.2099311500787735 2023-01-23 19:38:17.732935: step: 628/1545, loss: 0.00010046592069556937 2023-01-23 19:38:18.592323: step: 630/1545, loss: 0.0026859098579734564 2023-01-23 19:38:19.483266: step: 632/1545, loss: 0.07934855669736862 2023-01-23 19:38:20.336492: step: 634/1545, loss: 0.0002972376823890954 2023-01-23 19:38:21.207356: step: 636/1545, loss: 0.0271395742893219 2023-01-23 19:38:22.094653: step: 638/1545, loss: 0.007684105075895786 2023-01-23 19:38:22.948312: step: 640/1545, loss: 0.0002618907892610878 2023-01-23 19:38:23.829857: step: 642/1545, loss: 0.14456795156002045 2023-01-23 19:38:24.697811: step: 644/1545, loss: 0.0057686688378453255 2023-01-23 19:38:25.570124: step: 646/1545, loss: 0.004608853254467249 2023-01-23 19:38:26.414587: step: 648/1545, loss: 0.0001938152126967907 2023-01-23 19:38:27.315540: step: 650/1545, loss: 0.0028186067938804626 2023-01-23 19:38:28.179646: step: 652/1545, loss: 0.00033908477053046227 2023-01-23 19:38:29.063246: step: 654/1545, loss: 0.23667603731155396 2023-01-23 19:38:29.903926: step: 656/1545, loss: 0.046700622886419296 2023-01-23 19:38:30.810789: step: 658/1545, loss: 0.0014161837752908468 2023-01-23 19:38:31.703605: step: 660/1545, loss: 0.0008907349547371268 2023-01-23 19:38:32.632561: step: 662/1545, loss: 0.00018010669737122953 2023-01-23 19:38:33.534665: step: 664/1545, loss: 0.04019419476389885 2023-01-23 19:38:34.422436: step: 666/1545, loss: 0.0010621831752359867 2023-01-23 19:38:35.274770: step: 668/1545, loss: 0.0003502305771689862 2023-01-23 19:38:36.156671: step: 670/1545, loss: 0.2422792911529541 2023-01-23 19:38:36.998569: step: 672/1545, loss: 0.0018868650076910853 2023-01-23 19:38:37.860973: step: 674/1545, loss: 0.00048506236635148525 2023-01-23 19:38:38.725721: step: 676/1545, loss: 0.0004215664230287075 2023-01-23 19:38:39.719132: step: 678/1545, loss: -1.6944395611062646e-05 2023-01-23 19:38:40.579330: step: 680/1545, loss: 0.00287802261300385 2023-01-23 19:38:41.463144: step: 682/1545, loss: 0.0019288243493065238 2023-01-23 19:38:42.383521: step: 684/1545, loss: 0.024412687867879868 2023-01-23 19:38:43.256774: step: 686/1545, loss: 0.0027332385070621967 2023-01-23 19:38:44.130681: step: 688/1545, loss: 0.029339579865336418 2023-01-23 19:38:45.025373: step: 690/1545, loss: 0.00013282947475090623 2023-01-23 19:38:45.973076: step: 692/1545, loss: 7.029248808976263e-05 2023-01-23 19:38:46.852116: step: 694/1545, loss: 0.0014138396363705397 2023-01-23 19:38:47.716491: step: 696/1545, loss: 9.909923392115161e-05 2023-01-23 19:38:48.584782: step: 698/1545, loss: 0.0009038259740918875 2023-01-23 19:38:49.544773: step: 700/1545, loss: 0.023193607106804848 2023-01-23 19:38:50.377645: step: 702/1545, loss: 0.0020168868359178305 2023-01-23 19:38:51.232876: step: 704/1545, loss: 0.00019606568093877286 2023-01-23 19:38:52.137300: step: 706/1545, loss: 0.03209662437438965 2023-01-23 19:38:52.997719: step: 708/1545, loss: 0.137266606092453 2023-01-23 19:38:53.852127: step: 710/1545, loss: 0.21510013937950134 2023-01-23 19:38:54.768009: step: 712/1545, loss: 0.18617111444473267 2023-01-23 19:38:55.620213: step: 714/1545, loss: 0.06801417469978333 2023-01-23 19:38:56.559287: step: 716/1545, loss: 0.00023760505428072065 2023-01-23 19:38:57.437811: step: 718/1545, loss: 0.06075630336999893 2023-01-23 19:38:58.298275: step: 720/1545, loss: 0.004550195299088955 2023-01-23 19:38:59.179920: step: 722/1545, loss: 0.009096701629459858 2023-01-23 19:39:00.055593: step: 724/1545, loss: 0.0009332321933470666 2023-01-23 19:39:00.886351: step: 726/1545, loss: 0.013214402832090855 2023-01-23 19:39:01.763337: step: 728/1545, loss: 0.0032889349386096 2023-01-23 19:39:02.640099: step: 730/1545, loss: 0.02590288035571575 2023-01-23 19:39:03.509993: step: 732/1545, loss: 0.0010555100161582232 2023-01-23 19:39:04.461498: step: 734/1545, loss: 0.00046750117326155305 2023-01-23 19:39:05.353869: step: 736/1545, loss: 0.0033790862653404474 2023-01-23 19:39:06.251591: step: 738/1545, loss: 0.00046465027844533324 2023-01-23 19:39:07.080983: step: 740/1545, loss: 0.011586854234337807 2023-01-23 19:39:07.962213: step: 742/1545, loss: 0.0032326646614819765 2023-01-23 19:39:08.891939: step: 744/1545, loss: 0.1280481219291687 2023-01-23 19:39:09.799452: step: 746/1545, loss: 0.2072131186723709 2023-01-23 19:39:10.643397: step: 748/1545, loss: 0.0005227680085226893 2023-01-23 19:39:11.518327: step: 750/1545, loss: 0.00039664676296524704 2023-01-23 19:39:12.381387: step: 752/1545, loss: 7.115459447959438e-05 2023-01-23 19:39:13.258361: step: 754/1545, loss: 0.44148877263069153 2023-01-23 19:39:14.086848: step: 756/1545, loss: 0.005278759635984898 2023-01-23 19:39:14.956868: step: 758/1545, loss: 0.008812490850687027 2023-01-23 19:39:15.806582: step: 760/1545, loss: 0.015042591840028763 2023-01-23 19:39:16.716128: step: 762/1545, loss: 0.012591042555868626 2023-01-23 19:39:17.593682: step: 764/1545, loss: 0.0031330615747720003 2023-01-23 19:39:18.497306: step: 766/1545, loss: 0.003208613721653819 2023-01-23 19:39:19.358842: step: 768/1545, loss: 0.06074338033795357 2023-01-23 19:39:20.259597: step: 770/1545, loss: 0.33714786171913147 2023-01-23 19:39:21.233361: step: 772/1545, loss: 0.3780564069747925 2023-01-23 19:39:22.109109: step: 774/1545, loss: 0.005194623488932848 2023-01-23 19:39:23.015582: step: 776/1545, loss: 6.331503391265869e-05 2023-01-23 19:39:23.968121: step: 778/1545, loss: 0.026023568585515022 2023-01-23 19:39:24.858132: step: 780/1545, loss: 0.00011708032980095595 2023-01-23 19:39:25.734987: step: 782/1545, loss: 0.0012683881213888526 2023-01-23 19:39:26.635446: step: 784/1545, loss: 0.01923311874270439 2023-01-23 19:39:27.519879: step: 786/1545, loss: 0.00022815173724666238 2023-01-23 19:39:28.374290: step: 788/1545, loss: 0.0006023870082572103 2023-01-23 19:39:29.201636: step: 790/1545, loss: 0.1443546563386917 2023-01-23 19:39:30.093887: step: 792/1545, loss: 0.004576537758111954 2023-01-23 19:39:31.001132: step: 794/1545, loss: 0.0004988393629901111 2023-01-23 19:39:31.838393: step: 796/1545, loss: 0.002125705126672983 2023-01-23 19:39:32.714446: step: 798/1545, loss: 5.0220562116010115e-05 2023-01-23 19:39:33.620696: step: 800/1545, loss: 0.003664490533992648 2023-01-23 19:39:34.544792: step: 802/1545, loss: 0.00314095220528543 2023-01-23 19:39:35.449311: step: 804/1545, loss: 0.0008986343163996935 2023-01-23 19:39:36.363334: step: 806/1545, loss: 0.07845158874988556 2023-01-23 19:39:37.254161: step: 808/1545, loss: 0.0017611364601179957 2023-01-23 19:39:38.151522: step: 810/1545, loss: 0.4395856261253357 2023-01-23 19:39:39.022327: step: 812/1545, loss: 0.03318602219223976 2023-01-23 19:39:39.939704: step: 814/1545, loss: 0.3709391951560974 2023-01-23 19:39:40.799208: step: 816/1545, loss: 0.057046808302402496 2023-01-23 19:39:41.677203: step: 818/1545, loss: 0.00039511630893684924 2023-01-23 19:39:42.560774: step: 820/1545, loss: 5.879071250092238e-05 2023-01-23 19:39:43.489352: step: 822/1545, loss: 1.3089463209325913e-05 2023-01-23 19:39:44.373050: step: 824/1545, loss: 0.3388035297393799 2023-01-23 19:39:45.229988: step: 826/1545, loss: 0.006439006421715021 2023-01-23 19:39:46.084930: step: 828/1545, loss: 0.01821071282029152 2023-01-23 19:39:47.018657: step: 830/1545, loss: 0.09203635901212692 2023-01-23 19:39:47.945734: step: 832/1545, loss: 0.004203555174171925 2023-01-23 19:39:48.788121: step: 834/1545, loss: 0.00025882740737870336 2023-01-23 19:39:49.703848: step: 836/1545, loss: 0.09111339598894119 2023-01-23 19:39:50.618862: step: 838/1545, loss: 0.0006044518086127937 2023-01-23 19:39:51.474603: step: 840/1545, loss: 0.00019133627938572317 2023-01-23 19:39:52.338387: step: 842/1545, loss: 1.0870590209960938 2023-01-23 19:39:53.227901: step: 844/1545, loss: 0.0005297737079672515 2023-01-23 19:39:54.082039: step: 846/1545, loss: 0.0010314926039427519 2023-01-23 19:39:54.986536: step: 848/1545, loss: 0.05259430781006813 2023-01-23 19:39:55.862641: step: 850/1545, loss: 0.0007547988789156079 2023-01-23 19:39:56.705574: step: 852/1545, loss: 0.0018913493258878589 2023-01-23 19:39:57.606322: step: 854/1545, loss: 0.003137168474495411 2023-01-23 19:39:58.485686: step: 856/1545, loss: 0.04771208390593529 2023-01-23 19:39:59.391328: step: 858/1545, loss: 0.04197291284799576 2023-01-23 19:40:00.271824: step: 860/1545, loss: 0.3162331283092499 2023-01-23 19:40:01.185662: step: 862/1545, loss: 0.009482201188802719 2023-01-23 19:40:02.080766: step: 864/1545, loss: 0.003126045921817422 2023-01-23 19:40:03.028175: step: 866/1545, loss: 0.0007918368792161345 2023-01-23 19:40:03.901132: step: 868/1545, loss: 0.0005597537965513766 2023-01-23 19:40:04.754943: step: 870/1545, loss: 6.894580292282626e-05 2023-01-23 19:40:05.639806: step: 872/1545, loss: 0.0012983179185539484 2023-01-23 19:40:06.536346: step: 874/1545, loss: 0.14726503193378448 2023-01-23 19:40:07.433505: step: 876/1545, loss: 0.0035367256496101618 2023-01-23 19:40:08.279709: step: 878/1545, loss: 0.0005975379608571529 2023-01-23 19:40:09.154881: step: 880/1545, loss: 0.0011229094816371799 2023-01-23 19:40:10.040842: step: 882/1545, loss: 0.12250259518623352 2023-01-23 19:40:10.901619: step: 884/1545, loss: 0.0030079425778239965 2023-01-23 19:40:11.759195: step: 886/1545, loss: 0.6234157681465149 2023-01-23 19:40:12.686783: step: 888/1545, loss: 0.0006419851561076939 2023-01-23 19:40:13.606119: step: 890/1545, loss: 0.006561900023370981 2023-01-23 19:40:14.602235: step: 892/1545, loss: 0.003018328221514821 2023-01-23 19:40:15.573062: step: 894/1545, loss: 0.0017015578923746943 2023-01-23 19:40:16.530624: step: 896/1545, loss: 0.0038197555113583803 2023-01-23 19:40:17.382589: step: 898/1545, loss: 0.018906835466623306 2023-01-23 19:40:18.222374: step: 900/1545, loss: 0.05485290288925171 2023-01-23 19:40:19.117509: step: 902/1545, loss: 0.0063574835658073425 2023-01-23 19:40:20.086650: step: 904/1545, loss: 0.007453209720551968 2023-01-23 19:40:20.969765: step: 906/1545, loss: 1.8144288333132863e-05 2023-01-23 19:40:21.850523: step: 908/1545, loss: 0.0007315575494430959 2023-01-23 19:40:22.750638: step: 910/1545, loss: 0.578246533870697 2023-01-23 19:40:23.621096: step: 912/1545, loss: 0.001900301780551672 2023-01-23 19:40:24.474727: step: 914/1545, loss: 0.001056169276125729 2023-01-23 19:40:25.388778: step: 916/1545, loss: 0.0010005829390138388 2023-01-23 19:40:26.303228: step: 918/1545, loss: 0.0023689938243478537 2023-01-23 19:40:27.225179: step: 920/1545, loss: 0.18659496307373047 2023-01-23 19:40:28.087222: step: 922/1545, loss: 0.003428750904276967 2023-01-23 19:40:28.958602: step: 924/1545, loss: 0.0003794873773586005 2023-01-23 19:40:29.855788: step: 926/1545, loss: 0.1731703281402588 2023-01-23 19:40:30.761011: step: 928/1545, loss: 0.030779963359236717 2023-01-23 19:40:31.618203: step: 930/1545, loss: 0.00016230795881710947 2023-01-23 19:40:32.545330: step: 932/1545, loss: 0.19033606350421906 2023-01-23 19:40:33.422508: step: 934/1545, loss: 0.000879343249835074 2023-01-23 19:40:34.319701: step: 936/1545, loss: 0.1144963875412941 2023-01-23 19:40:35.147239: step: 938/1545, loss: 0.14429177343845367 2023-01-23 19:40:36.034214: step: 940/1545, loss: 0.004831439815461636 2023-01-23 19:40:36.902938: step: 942/1545, loss: 0.016966527327895164 2023-01-23 19:40:37.792814: step: 944/1545, loss: 0.036907050758600235 2023-01-23 19:40:38.648167: step: 946/1545, loss: 0.11156424880027771 2023-01-23 19:40:39.496977: step: 948/1545, loss: 0.0007040881901048124 2023-01-23 19:40:40.386367: step: 950/1545, loss: 0.12434562295675278 2023-01-23 19:40:41.307512: step: 952/1545, loss: 0.0007837871089577675 2023-01-23 19:40:42.205836: step: 954/1545, loss: 0.01751016080379486 2023-01-23 19:40:43.099639: step: 956/1545, loss: 0.00667449040338397 2023-01-23 19:40:44.112166: step: 958/1545, loss: 0.00047873961739242077 2023-01-23 19:40:45.016373: step: 960/1545, loss: 0.003573472611606121 2023-01-23 19:40:45.894656: step: 962/1545, loss: 0.002773009706288576 2023-01-23 19:40:46.821072: step: 964/1545, loss: 0.3333989381790161 2023-01-23 19:40:47.724039: step: 966/1545, loss: 0.000558211118914187 2023-01-23 19:40:48.605772: step: 968/1545, loss: 0.035561706870794296 2023-01-23 19:40:49.492153: step: 970/1545, loss: 0.00017439194198232144 2023-01-23 19:40:50.397331: step: 972/1545, loss: 0.11688064783811569 2023-01-23 19:40:51.259496: step: 974/1545, loss: 0.004226884339004755 2023-01-23 19:40:52.160867: step: 976/1545, loss: 0.0025998284108936787 2023-01-23 19:40:53.004597: step: 978/1545, loss: 0.0020120569970458746 2023-01-23 19:40:53.856864: step: 980/1545, loss: 0.0015843139262869954 2023-01-23 19:40:54.688020: step: 982/1545, loss: 0.016447734087705612 2023-01-23 19:40:55.586610: step: 984/1545, loss: 0.003629904706031084 2023-01-23 19:40:56.490810: step: 986/1545, loss: 0.0018036477267742157 2023-01-23 19:40:57.350672: step: 988/1545, loss: 0.03210696578025818 2023-01-23 19:40:58.220865: step: 990/1545, loss: 0.06355632841587067 2023-01-23 19:40:59.052513: step: 992/1545, loss: 0.0011227717623114586 2023-01-23 19:40:59.914103: step: 994/1545, loss: 0.1754908710718155 2023-01-23 19:41:00.828251: step: 996/1545, loss: 0.008995800279080868 2023-01-23 19:41:01.692640: step: 998/1545, loss: 0.2497483640909195 2023-01-23 19:41:02.552366: step: 1000/1545, loss: 0.0008555161766707897 2023-01-23 19:41:03.427559: step: 1002/1545, loss: 0.006328778341412544 2023-01-23 19:41:04.282766: step: 1004/1545, loss: 0.000842552341055125 2023-01-23 19:41:05.160919: step: 1006/1545, loss: 0.035588230937719345 2023-01-23 19:41:06.076031: step: 1008/1545, loss: 0.010787217877805233 2023-01-23 19:41:06.917762: step: 1010/1545, loss: 0.003022501477971673 2023-01-23 19:41:07.819294: step: 1012/1545, loss: 0.17787767946720123 2023-01-23 19:41:08.692772: step: 1014/1545, loss: 0.0019449079409241676 2023-01-23 19:41:09.575350: step: 1016/1545, loss: 0.00022569234715774655 2023-01-23 19:41:10.484922: step: 1018/1545, loss: 0.0026402492076158524 2023-01-23 19:41:11.374117: step: 1020/1545, loss: 0.010862967930734158 2023-01-23 19:41:12.304088: step: 1022/1545, loss: 0.018562132492661476 2023-01-23 19:41:13.176615: step: 1024/1545, loss: 0.001341746305115521 2023-01-23 19:41:14.072740: step: 1026/1545, loss: 9.799066901905462e-06 2023-01-23 19:41:14.943993: step: 1028/1545, loss: 0.0003840250428766012 2023-01-23 19:41:15.820717: step: 1030/1545, loss: 0.0003198344202246517 2023-01-23 19:41:16.705528: step: 1032/1545, loss: 8.859280933393165e-05 2023-01-23 19:41:17.589338: step: 1034/1545, loss: 0.012157262302935123 2023-01-23 19:41:18.453072: step: 1036/1545, loss: 0.0031655426137149334 2023-01-23 19:41:19.325568: step: 1038/1545, loss: 0.0013603589031845331 2023-01-23 19:41:20.205996: step: 1040/1545, loss: 0.008408620953559875 2023-01-23 19:41:21.155560: step: 1042/1545, loss: 0.0004075508040841669 2023-01-23 19:41:22.016161: step: 1044/1545, loss: 0.029524488374590874 2023-01-23 19:41:22.921418: step: 1046/1545, loss: 0.30019742250442505 2023-01-23 19:41:23.805352: step: 1048/1545, loss: 0.05187934264540672 2023-01-23 19:41:24.700845: step: 1050/1545, loss: 0.015257521532475948 2023-01-23 19:41:25.532588: step: 1052/1545, loss: 1.017164504446555e-05 2023-01-23 19:41:26.382809: step: 1054/1545, loss: 0.0010003740899264812 2023-01-23 19:41:27.233952: step: 1056/1545, loss: 0.00040726090082898736 2023-01-23 19:41:28.091328: step: 1058/1545, loss: 0.16756679117679596 2023-01-23 19:41:28.949478: step: 1060/1545, loss: 0.3069811165332794 2023-01-23 19:41:29.849136: step: 1062/1545, loss: 0.0022359092254191637 2023-01-23 19:41:30.732439: step: 1064/1545, loss: 0.4789717495441437 2023-01-23 19:41:31.588519: step: 1066/1545, loss: 0.03778877854347229 2023-01-23 19:41:32.473331: step: 1068/1545, loss: 0.0018568017985671759 2023-01-23 19:41:33.414689: step: 1070/1545, loss: 0.00027599435998126864 2023-01-23 19:41:34.308976: step: 1072/1545, loss: 0.0024921223521232605 2023-01-23 19:41:35.202580: step: 1074/1545, loss: 0.06603526324033737 2023-01-23 19:41:36.119275: step: 1076/1545, loss: 0.054065801203250885 2023-01-23 19:41:36.995085: step: 1078/1545, loss: 0.00019760649593081325 2023-01-23 19:41:37.899105: step: 1080/1545, loss: 0.005065150558948517 2023-01-23 19:41:38.778876: step: 1082/1545, loss: 0.21153369545936584 2023-01-23 19:41:39.624401: step: 1084/1545, loss: 0.001931227627210319 2023-01-23 19:41:40.563094: step: 1086/1545, loss: 0.015797045081853867 2023-01-23 19:41:41.471280: step: 1088/1545, loss: 0.048300888389348984 2023-01-23 19:41:42.343347: step: 1090/1545, loss: 0.03255252167582512 2023-01-23 19:41:43.182583: step: 1092/1545, loss: 0.004706721752882004 2023-01-23 19:41:44.012148: step: 1094/1545, loss: 0.0740869864821434 2023-01-23 19:41:44.911482: step: 1096/1545, loss: 0.036778807640075684 2023-01-23 19:41:45.783399: step: 1098/1545, loss: 0.0008732809219509363 2023-01-23 19:41:46.720423: step: 1100/1545, loss: 0.03525354713201523 2023-01-23 19:41:47.578652: step: 1102/1545, loss: 0.1546928882598877 2023-01-23 19:41:48.486414: step: 1104/1545, loss: 0.002659076824784279 2023-01-23 19:41:49.372119: step: 1106/1545, loss: 0.0026350885163992643 2023-01-23 19:41:50.235286: step: 1108/1545, loss: 0.0007852844428271055 2023-01-23 19:41:51.187878: step: 1110/1545, loss: 0.1113252192735672 2023-01-23 19:41:52.043869: step: 1112/1545, loss: 0.06107775866985321 2023-01-23 19:41:52.915079: step: 1114/1545, loss: 0.0029623531736433506 2023-01-23 19:41:53.787474: step: 1116/1545, loss: 0.0014134596567600965 2023-01-23 19:41:54.648830: step: 1118/1545, loss: 0.002399974036961794 2023-01-23 19:41:55.509916: step: 1120/1545, loss: 0.019877294078469276 2023-01-23 19:41:56.379503: step: 1122/1545, loss: 0.012119807302951813 2023-01-23 19:41:57.265341: step: 1124/1545, loss: 0.051815103739500046 2023-01-23 19:41:58.248986: step: 1126/1545, loss: 0.0008441892568953335 2023-01-23 19:41:59.156345: step: 1128/1545, loss: 4.0148959669750184e-05 2023-01-23 19:42:00.029972: step: 1130/1545, loss: 0.11694728583097458 2023-01-23 19:42:00.971618: step: 1132/1545, loss: 0.00120589230209589 2023-01-23 19:42:01.845296: step: 1134/1545, loss: 0.002073588315397501 2023-01-23 19:42:02.751061: step: 1136/1545, loss: 0.0004938881029374897 2023-01-23 19:42:03.641937: step: 1138/1545, loss: 0.10223965346813202 2023-01-23 19:42:04.498858: step: 1140/1545, loss: 0.049014996737241745 2023-01-23 19:42:05.350750: step: 1142/1545, loss: 0.00020183621381875128 2023-01-23 19:42:06.213509: step: 1144/1545, loss: 0.00024954433320090175 2023-01-23 19:42:07.081350: step: 1146/1545, loss: 0.0023851010482758284 2023-01-23 19:42:07.942203: step: 1148/1545, loss: 0.003226619679480791 2023-01-23 19:42:08.807587: step: 1150/1545, loss: 0.006621356122195721 2023-01-23 19:42:09.722959: step: 1152/1545, loss: 0.0636579766869545 2023-01-23 19:42:10.619312: step: 1154/1545, loss: 0.11229579150676727 2023-01-23 19:42:11.476532: step: 1156/1545, loss: 0.0023364643566310406 2023-01-23 19:42:12.400630: step: 1158/1545, loss: 0.0002486517478246242 2023-01-23 19:42:13.254184: step: 1160/1545, loss: 0.17667093873023987 2023-01-23 19:42:14.129661: step: 1162/1545, loss: 0.08361614495515823 2023-01-23 19:42:15.011817: step: 1164/1545, loss: 0.0006872258963994682 2023-01-23 19:42:15.880722: step: 1166/1545, loss: 0.00027285146643407643 2023-01-23 19:42:16.816465: step: 1168/1545, loss: 0.0024563728366047144 2023-01-23 19:42:17.652245: step: 1170/1545, loss: 5.944092117715627e-05 2023-01-23 19:42:18.566194: step: 1172/1545, loss: 0.09968426078557968 2023-01-23 19:42:19.456479: step: 1174/1545, loss: 0.1512882113456726 2023-01-23 19:42:20.321297: step: 1176/1545, loss: 0.009189637377858162 2023-01-23 19:42:21.178377: step: 1178/1545, loss: 0.25232186913490295 2023-01-23 19:42:22.101474: step: 1180/1545, loss: 0.00010043953807326034 2023-01-23 19:42:22.975699: step: 1182/1545, loss: 0.00025850124075077474 2023-01-23 19:42:23.831403: step: 1184/1545, loss: 4.243850344209932e-05 2023-01-23 19:42:24.731056: step: 1186/1545, loss: 0.000739589158911258 2023-01-23 19:42:25.628854: step: 1188/1545, loss: 0.027503114193677902 2023-01-23 19:42:26.526741: step: 1190/1545, loss: 0.056185416877269745 2023-01-23 19:42:27.411646: step: 1192/1545, loss: 0.0006089534726925194 2023-01-23 19:42:28.264236: step: 1194/1545, loss: 0.0034277839586138725 2023-01-23 19:42:29.177484: step: 1196/1545, loss: 0.7005075812339783 2023-01-23 19:42:30.059389: step: 1198/1545, loss: 0.0026628402993083 2023-01-23 19:42:30.998964: step: 1200/1545, loss: 0.008721643127501011 2023-01-23 19:42:31.893506: step: 1202/1545, loss: 0.0019262805581092834 2023-01-23 19:42:32.805841: step: 1204/1545, loss: 0.3517746925354004 2023-01-23 19:42:33.635375: step: 1206/1545, loss: 0.0003160294727422297 2023-01-23 19:42:34.511568: step: 1208/1545, loss: 0.0005444457056000829 2023-01-23 19:42:35.386538: step: 1210/1545, loss: 8.944051660364494e-05 2023-01-23 19:42:36.285267: step: 1212/1545, loss: 0.012071775272488594 2023-01-23 19:42:37.146316: step: 1214/1545, loss: 0.011772289872169495 2023-01-23 19:42:38.003679: step: 1216/1545, loss: 0.03418438136577606 2023-01-23 19:42:38.889223: step: 1218/1545, loss: 0.16243675351142883 2023-01-23 19:42:39.801762: step: 1220/1545, loss: 0.018592339009046555 2023-01-23 19:42:40.669009: step: 1222/1545, loss: 0.00986423995345831 2023-01-23 19:42:41.545087: step: 1224/1545, loss: 0.0009547576773911715 2023-01-23 19:42:42.436317: step: 1226/1545, loss: 0.0024977955035865307 2023-01-23 19:42:43.287133: step: 1228/1545, loss: 0.0067231981083750725 2023-01-23 19:42:44.181373: step: 1230/1545, loss: 0.00035265859332866967 2023-01-23 19:42:45.049328: step: 1232/1545, loss: 0.00034588947892189026 2023-01-23 19:42:45.926834: step: 1234/1545, loss: 0.024177342653274536 2023-01-23 19:42:46.834134: step: 1236/1545, loss: 3.052551983273588e-05 2023-01-23 19:42:47.736553: step: 1238/1545, loss: 0.016693992540240288 2023-01-23 19:42:48.577509: step: 1240/1545, loss: 0.1038426086306572 2023-01-23 19:42:49.397840: step: 1242/1545, loss: 0.00030558343860320747 2023-01-23 19:42:50.296156: step: 1244/1545, loss: 0.19127912819385529 2023-01-23 19:42:51.173726: step: 1246/1545, loss: 0.0027041654102504253 2023-01-23 19:42:52.082771: step: 1248/1545, loss: 0.008152124471962452 2023-01-23 19:42:53.011005: step: 1250/1545, loss: 0.25074777007102966 2023-01-23 19:42:53.879111: step: 1252/1545, loss: 0.08872797340154648 2023-01-23 19:42:54.770823: step: 1254/1545, loss: 0.04754128307104111 2023-01-23 19:42:55.746530: step: 1256/1545, loss: 0.04760194942355156 2023-01-23 19:42:56.693309: step: 1258/1545, loss: 0.005156887229532003 2023-01-23 19:42:57.663399: step: 1260/1545, loss: 7.907550025265664e-05 2023-01-23 19:42:58.559950: step: 1262/1545, loss: 0.00012631918070837855 2023-01-23 19:42:59.488430: step: 1264/1545, loss: 0.1185043454170227 2023-01-23 19:43:00.360876: step: 1266/1545, loss: 0.00021783130068797618 2023-01-23 19:43:01.243432: step: 1268/1545, loss: 0.015913642942905426 2023-01-23 19:43:02.123395: step: 1270/1545, loss: 0.22156015038490295 2023-01-23 19:43:02.965187: step: 1272/1545, loss: 0.0002957746328320354 2023-01-23 19:43:03.826146: step: 1274/1545, loss: 9.181609493680298e-05 2023-01-23 19:43:04.669937: step: 1276/1545, loss: 0.030740367248654366 2023-01-23 19:43:05.541709: step: 1278/1545, loss: 0.00013297682744450867 2023-01-23 19:43:06.439066: step: 1280/1545, loss: 0.07261618226766586 2023-01-23 19:43:07.314815: step: 1282/1545, loss: 0.022898664698004723 2023-01-23 19:43:08.179942: step: 1284/1545, loss: 6.054661571397446e-05 2023-01-23 19:43:09.059718: step: 1286/1545, loss: 0.0002091690112138167 2023-01-23 19:43:09.897966: step: 1288/1545, loss: 0.0007113731116987765 2023-01-23 19:43:10.767155: step: 1290/1545, loss: 0.08094355463981628 2023-01-23 19:43:11.632454: step: 1292/1545, loss: 0.0007025095983408391 2023-01-23 19:43:12.525121: step: 1294/1545, loss: 0.032097648829221725 2023-01-23 19:43:13.434919: step: 1296/1545, loss: 0.00015191372949630022 2023-01-23 19:43:14.337548: step: 1298/1545, loss: 0.002453453605994582 2023-01-23 19:43:15.195769: step: 1300/1545, loss: 0.0005655948189087212 2023-01-23 19:43:16.137276: step: 1302/1545, loss: 0.000576649559661746 2023-01-23 19:43:17.048937: step: 1304/1545, loss: 0.0007179655367508531 2023-01-23 19:43:17.929774: step: 1306/1545, loss: 9.069219959201291e-05 2023-01-23 19:43:18.768737: step: 1308/1545, loss: 0.0007377052679657936 2023-01-23 19:43:19.671790: step: 1310/1545, loss: 0.05399584025144577 2023-01-23 19:43:20.588133: step: 1312/1545, loss: 0.28255972266197205 2023-01-23 19:43:21.598456: step: 1314/1545, loss: 0.0006142708007246256 2023-01-23 19:43:22.492865: step: 1316/1545, loss: 0.23644137382507324 2023-01-23 19:43:23.371666: step: 1318/1545, loss: 0.011836037039756775 2023-01-23 19:43:24.261929: step: 1320/1545, loss: 0.07908980548381805 2023-01-23 19:43:25.110772: step: 1322/1545, loss: 0.1204667016863823 2023-01-23 19:43:25.979548: step: 1324/1545, loss: 1.0074973033624701e-05 2023-01-23 19:43:26.953263: step: 1326/1545, loss: 0.000616214529145509 2023-01-23 19:43:27.851888: step: 1328/1545, loss: 0.10629138350486755 2023-01-23 19:43:28.773921: step: 1330/1545, loss: 8.054287172853947e-05 2023-01-23 19:43:29.679344: step: 1332/1545, loss: 0.05909213051199913 2023-01-23 19:43:30.559567: step: 1334/1545, loss: 0.0005806178669445217 2023-01-23 19:43:31.443529: step: 1336/1545, loss: 0.0012890901416540146 2023-01-23 19:43:32.324638: step: 1338/1545, loss: 0.34254559874534607 2023-01-23 19:43:33.197353: step: 1340/1545, loss: 0.0004526229458861053 2023-01-23 19:43:34.122030: step: 1342/1545, loss: 0.0030318787321448326 2023-01-23 19:43:34.996312: step: 1344/1545, loss: 0.005261724814772606 2023-01-23 19:43:35.911281: step: 1346/1545, loss: 0.03403770551085472 2023-01-23 19:43:36.773877: step: 1348/1545, loss: 0.0010681857820600271 2023-01-23 19:43:37.658834: step: 1350/1545, loss: 0.036678895354270935 2023-01-23 19:43:38.543497: step: 1352/1545, loss: 0.0923692062497139 2023-01-23 19:43:39.387068: step: 1354/1545, loss: 0.030180789530277252 2023-01-23 19:43:40.246931: step: 1356/1545, loss: 0.21692293882369995 2023-01-23 19:43:41.123114: step: 1358/1545, loss: 0.0007511588046327233 2023-01-23 19:43:41.989243: step: 1360/1545, loss: 5.089853948447853e-05 2023-01-23 19:43:42.887220: step: 1362/1545, loss: 0.006710141897201538 2023-01-23 19:43:43.782173: step: 1364/1545, loss: 0.00012224756937939674 2023-01-23 19:43:44.613969: step: 1366/1545, loss: 0.0022044589277356863 2023-01-23 19:43:45.539818: step: 1368/1545, loss: 0.0004753457906190306 2023-01-23 19:43:46.424278: step: 1370/1545, loss: 0.01529576163738966 2023-01-23 19:43:47.277012: step: 1372/1545, loss: 0.01301614660769701 2023-01-23 19:43:48.146504: step: 1374/1545, loss: 0.0002004895795835182 2023-01-23 19:43:49.044936: step: 1376/1545, loss: 0.013783751986920834 2023-01-23 19:43:49.929054: step: 1378/1545, loss: 0.013038401491940022 2023-01-23 19:43:50.814091: step: 1380/1545, loss: 0.05059751868247986 2023-01-23 19:43:51.668307: step: 1382/1545, loss: 0.001348872552625835 2023-01-23 19:43:52.615762: step: 1384/1545, loss: 0.0015790852485224605 2023-01-23 19:43:53.479575: step: 1386/1545, loss: 0.042246013879776 2023-01-23 19:43:54.367101: step: 1388/1545, loss: -1.4347520846058615e-05 2023-01-23 19:43:55.294560: step: 1390/1545, loss: 0.00037216750206425786 2023-01-23 19:43:56.273258: step: 1392/1545, loss: 0.00016722858708817512 2023-01-23 19:43:57.101391: step: 1394/1545, loss: 0.0005983891314826906 2023-01-23 19:43:57.921090: step: 1396/1545, loss: 1.7800892237573862e-05 2023-01-23 19:43:58.775673: step: 1398/1545, loss: 0.0002479833783581853 2023-01-23 19:43:59.691340: step: 1400/1545, loss: -1.261396027985029e-05 2023-01-23 19:44:00.576991: step: 1402/1545, loss: 0.00043269371963106096 2023-01-23 19:44:01.426818: step: 1404/1545, loss: -8.655712008476257e-06 2023-01-23 19:44:02.313147: step: 1406/1545, loss: 0.9245769381523132 2023-01-23 19:44:03.190467: step: 1408/1545, loss: 5.1688082749024034e-05 2023-01-23 19:44:04.080990: step: 1410/1545, loss: 6.163865236885613e-06 2023-01-23 19:44:05.069340: step: 1412/1545, loss: 0.5049208402633667 2023-01-23 19:44:05.953171: step: 1414/1545, loss: 0.0001722529559629038 2023-01-23 19:44:06.861400: step: 1416/1545, loss: 4.933926174999215e-05 2023-01-23 19:44:07.738596: step: 1418/1545, loss: -6.359286999213509e-06 2023-01-23 19:44:08.629493: step: 1420/1545, loss: 0.001457045553252101 2023-01-23 19:44:09.463600: step: 1422/1545, loss: 0.0001559572556288913 2023-01-23 19:44:10.333501: step: 1424/1545, loss: 0.00015355947834905237 2023-01-23 19:44:11.223069: step: 1426/1545, loss: 0.00021914760873187333 2023-01-23 19:44:12.083983: step: 1428/1545, loss: 0.0025303256697952747 2023-01-23 19:44:12.947925: step: 1430/1545, loss: -3.2124302379088476e-05 2023-01-23 19:44:13.837734: step: 1432/1545, loss: 0.00018315823399461806 2023-01-23 19:44:14.750838: step: 1434/1545, loss: 4.204691867926158e-05 2023-01-23 19:44:15.620692: step: 1436/1545, loss: 0.0005829611327499151 2023-01-23 19:44:16.504917: step: 1438/1545, loss: 0.17447784543037415 2023-01-23 19:44:17.410726: step: 1440/1545, loss: 0.0002751538995653391 2023-01-23 19:44:18.278803: step: 1442/1545, loss: 0.002984641119837761 2023-01-23 19:44:19.128184: step: 1444/1545, loss: 0.005606739316135645 2023-01-23 19:44:20.007730: step: 1446/1545, loss: 0.0006757994997315109 2023-01-23 19:44:20.846445: step: 1448/1545, loss: 0.008985708467662334 2023-01-23 19:44:21.719066: step: 1450/1545, loss: 0.0003600005293264985 2023-01-23 19:44:22.573503: step: 1452/1545, loss: 0.00021489930804818869 2023-01-23 19:44:23.402451: step: 1454/1545, loss: 6.895902333781123e-05 2023-01-23 19:44:24.272579: step: 1456/1545, loss: 0.0008306197123602033 2023-01-23 19:44:25.206699: step: 1458/1545, loss: 0.004335073754191399 2023-01-23 19:44:26.242388: step: 1460/1545, loss: 0.31229934096336365 2023-01-23 19:44:27.159967: step: 1462/1545, loss: 0.03446492925286293 2023-01-23 19:44:28.052271: step: 1464/1545, loss: 0.00027877988759428263 2023-01-23 19:44:28.926182: step: 1466/1545, loss: 0.0002336617180844769 2023-01-23 19:44:29.797032: step: 1468/1545, loss: 0.0005692840786650777 2023-01-23 19:44:30.669098: step: 1470/1545, loss: 0.00028840862796641886 2023-01-23 19:44:31.547304: step: 1472/1545, loss: 0.020677514374256134 2023-01-23 19:44:32.386086: step: 1474/1545, loss: 9.275177581002936e-05 2023-01-23 19:44:33.279162: step: 1476/1545, loss: 6.221830699359998e-05 2023-01-23 19:44:34.227680: step: 1478/1545, loss: 0.0004068999260198325 2023-01-23 19:44:35.150466: step: 1480/1545, loss: 0.0006714214687235653 2023-01-23 19:44:36.011980: step: 1482/1545, loss: 0.15150496363639832 2023-01-23 19:44:36.855925: step: 1484/1545, loss: 0.0015305918641388416 2023-01-23 19:44:37.788830: step: 1486/1545, loss: 0.006714147049933672 2023-01-23 19:44:38.632484: step: 1488/1545, loss: 0.008061772212386131 2023-01-23 19:44:39.624482: step: 1490/1545, loss: 0.010741163976490498 2023-01-23 19:44:40.506456: step: 1492/1545, loss: 0.013264658860862255 2023-01-23 19:44:41.371332: step: 1494/1545, loss: 0.0007256647222675383 2023-01-23 19:44:42.229461: step: 1496/1545, loss: 0.00011934254871448502 2023-01-23 19:44:43.106123: step: 1498/1545, loss: 0.26689964532852173 2023-01-23 19:44:44.000092: step: 1500/1545, loss: 0.007992910221219063 2023-01-23 19:44:44.879474: step: 1502/1545, loss: 0.020396271720528603 2023-01-23 19:44:45.814450: step: 1504/1545, loss: 0.002057237084954977 2023-01-23 19:44:46.682577: step: 1506/1545, loss: 0.00041736263665370643 2023-01-23 19:44:47.579772: step: 1508/1545, loss: 0.004491832572966814 2023-01-23 19:44:48.441114: step: 1510/1545, loss: 0.5931002497673035 2023-01-23 19:44:49.336472: step: 1512/1545, loss: 0.0034597141202539206 2023-01-23 19:44:50.242711: step: 1514/1545, loss: 0.00025020301109179854 2023-01-23 19:44:51.169311: step: 1516/1545, loss: 0.05082811042666435 2023-01-23 19:44:52.031867: step: 1518/1545, loss: 0.00039265156374312937 2023-01-23 19:44:52.871442: step: 1520/1545, loss: 8.344646289515367e-07 2023-01-23 19:44:53.796377: step: 1522/1545, loss: 0.0017485328717157245 2023-01-23 19:44:54.653549: step: 1524/1545, loss: 0.0055394042283296585 2023-01-23 19:44:55.571432: step: 1526/1545, loss: 0.5857334733009338 2023-01-23 19:44:56.441464: step: 1528/1545, loss: 8.628846990177408e-05 2023-01-23 19:44:57.297054: step: 1530/1545, loss: 0.24171938002109528 2023-01-23 19:44:58.173876: step: 1532/1545, loss: 0.17826960980892181 2023-01-23 19:44:59.050252: step: 1534/1545, loss: -2.0375107851577923e-05 2023-01-23 19:44:59.919411: step: 1536/1545, loss: 0.03193832188844681 2023-01-23 19:45:00.817428: step: 1538/1545, loss: 0.0016136333579197526 2023-01-23 19:45:01.779620: step: 1540/1545, loss: 0.2868846654891968 2023-01-23 19:45:02.646698: step: 1542/1545, loss: 0.0008880023960955441 2023-01-23 19:45:03.516014: step: 1544/1545, loss: 0.3854876458644867 2023-01-23 19:45:04.427131: step: 1546/1545, loss: 0.0002250879188068211 2023-01-23 19:45:05.289860: step: 1548/1545, loss: 0.20562444627285004 2023-01-23 19:45:06.177330: step: 1550/1545, loss: 0.0005690710968337953 2023-01-23 19:45:07.036356: step: 1552/1545, loss: 0.002427685307338834 2023-01-23 19:45:07.908525: step: 1554/1545, loss: 0.03899943456053734 2023-01-23 19:45:08.758337: step: 1556/1545, loss: 1.7866139387479052e-05 2023-01-23 19:45:09.617919: step: 1558/1545, loss: 0.004828042350709438 2023-01-23 19:45:10.526216: step: 1560/1545, loss: 0.0002441673423163593 2023-01-23 19:45:11.373464: step: 1562/1545, loss: 0.015445373952388763 2023-01-23 19:45:12.237546: step: 1564/1545, loss: 0.005554920993745327 2023-01-23 19:45:13.109547: step: 1566/1545, loss: 0.01015445962548256 2023-01-23 19:45:13.982636: step: 1568/1545, loss: 0.00028632915928028524 2023-01-23 19:45:14.869964: step: 1570/1545, loss: 0.0035497008357197046 2023-01-23 19:45:15.771279: step: 1572/1545, loss: 0.002671334659680724 2023-01-23 19:45:16.651436: step: 1574/1545, loss: 0.2027895748615265 2023-01-23 19:45:17.526982: step: 1576/1545, loss: 0.029824331402778625 2023-01-23 19:45:18.382470: step: 1578/1545, loss: 0.34052085876464844 2023-01-23 19:45:19.316239: step: 1580/1545, loss: 0.035713065415620804 2023-01-23 19:45:20.227413: step: 1582/1545, loss: 4.594777419697493e-05 2023-01-23 19:45:21.100821: step: 1584/1545, loss: 0.005400617141276598 2023-01-23 19:45:22.008040: step: 1586/1545, loss: 0.0016470910049974918 2023-01-23 19:45:22.877501: step: 1588/1545, loss: 0.0003410757053643465 2023-01-23 19:45:23.758567: step: 1590/1545, loss: 0.16682349145412445 2023-01-23 19:45:24.610895: step: 1592/1545, loss: 0.00048307838733308017 2023-01-23 19:45:25.440894: step: 1594/1545, loss: 0.0003809511545114219 2023-01-23 19:45:26.426869: step: 1596/1545, loss: 0.000824411166831851 2023-01-23 19:45:27.266372: step: 1598/1545, loss: 0.00012827968748752028 2023-01-23 19:45:28.138942: step: 1600/1545, loss: 0.0017817930784076452 2023-01-23 19:45:29.007387: step: 1602/1545, loss: 0.0004742974997498095 2023-01-23 19:45:29.831869: step: 1604/1545, loss: 0.00024770048912614584 2023-01-23 19:45:30.761399: step: 1606/1545, loss: 0.0035837795585393906 2023-01-23 19:45:31.648317: step: 1608/1545, loss: 0.0006380536360666156 2023-01-23 19:45:32.508719: step: 1610/1545, loss: 3.90593268093653e-05 2023-01-23 19:45:33.374064: step: 1612/1545, loss: 0.009721723385155201 2023-01-23 19:45:34.249116: step: 1614/1545, loss: 1.2249513864517212 2023-01-23 19:45:35.139303: step: 1616/1545, loss: 0.0001359268935630098 2023-01-23 19:45:36.020190: step: 1618/1545, loss: 0.20327788591384888 2023-01-23 19:45:36.854029: step: 1620/1545, loss: 8.790145511738956e-05 2023-01-23 19:45:37.757234: step: 1622/1545, loss: 0.027355602011084557 2023-01-23 19:45:38.687999: step: 1624/1545, loss: 0.006128428503870964 2023-01-23 19:45:39.613729: step: 1626/1545, loss: 0.030758732929825783 2023-01-23 19:45:40.455706: step: 1628/1545, loss: -7.653707143617794e-07 2023-01-23 19:45:41.331576: step: 1630/1545, loss: 0.27438417077064514 2023-01-23 19:45:42.238601: step: 1632/1545, loss: 0.1415381282567978 2023-01-23 19:45:43.108085: step: 1634/1545, loss: 6.15171084064059e-05 2023-01-23 19:45:43.955020: step: 1636/1545, loss: 0.4760962426662445 2023-01-23 19:45:44.837645: step: 1638/1545, loss: 0.23631827533245087 2023-01-23 19:45:45.717748: step: 1640/1545, loss: 0.0001993168261833489 2023-01-23 19:45:46.639649: step: 1642/1545, loss: 0.03578051179647446 2023-01-23 19:45:47.517065: step: 1644/1545, loss: 0.00017667679639998823 2023-01-23 19:45:48.380995: step: 1646/1545, loss: 0.005194211844354868 2023-01-23 19:45:49.263271: step: 1648/1545, loss: 0.7459302544593811 2023-01-23 19:45:50.136232: step: 1650/1545, loss: 0.006769311614334583 2023-01-23 19:45:51.030318: step: 1652/1545, loss: 0.0017094641225412488 2023-01-23 19:45:51.933190: step: 1654/1545, loss: 0.23517943918704987 2023-01-23 19:45:52.810058: step: 1656/1545, loss: 4.960387013852596e-05 2023-01-23 19:45:53.633078: step: 1658/1545, loss: 0.003817348275333643 2023-01-23 19:45:54.482793: step: 1660/1545, loss: 0.019829438999295235 2023-01-23 19:45:55.435239: step: 1662/1545, loss: 0.10765630751848221 2023-01-23 19:45:56.287006: step: 1664/1545, loss: 0.001357460394501686 2023-01-23 19:45:57.188537: step: 1666/1545, loss: 0.0066626789048314095 2023-01-23 19:45:58.125142: step: 1668/1545, loss: 0.00819956324994564 2023-01-23 19:45:58.993909: step: 1670/1545, loss: 0.10719168931245804 2023-01-23 19:45:59.911470: step: 1672/1545, loss: 0.0010668487520888448 2023-01-23 19:46:00.777948: step: 1674/1545, loss: 0.0006023940513841808 2023-01-23 19:46:01.668103: step: 1676/1545, loss: 0.0015415070811286569 2023-01-23 19:46:02.513735: step: 1678/1545, loss: 0.0063797663897275925 2023-01-23 19:46:03.375246: step: 1680/1545, loss: 0.001177147962152958 2023-01-23 19:46:04.262641: step: 1682/1545, loss: 0.09099803864955902 2023-01-23 19:46:05.162691: step: 1684/1545, loss: 0.10329850018024445 2023-01-23 19:46:06.059099: step: 1686/1545, loss: 0.18308556079864502 2023-01-23 19:46:06.903570: step: 1688/1545, loss: 0.05888187512755394 2023-01-23 19:46:07.756598: step: 1690/1545, loss: 0.10240159928798676 2023-01-23 19:46:08.671334: step: 1692/1545, loss: 0.0035195734817534685 2023-01-23 19:46:09.563201: step: 1694/1545, loss: 0.005804203450679779 2023-01-23 19:46:10.410382: step: 1696/1545, loss: 0.00020029416191391647 2023-01-23 19:46:11.284456: step: 1698/1545, loss: 0.32587769627571106 2023-01-23 19:46:12.181792: step: 1700/1545, loss: 0.0003206607070751488 2023-01-23 19:46:13.072078: step: 1702/1545, loss: 0.0047054048627614975 2023-01-23 19:46:13.945777: step: 1704/1545, loss: 0.0001225426676683128 2023-01-23 19:46:14.799158: step: 1706/1545, loss: 0.00020739233877975494 2023-01-23 19:46:15.692245: step: 1708/1545, loss: 0.0009666856494732201 2023-01-23 19:46:16.647335: step: 1710/1545, loss: 0.014800403267145157 2023-01-23 19:46:17.527804: step: 1712/1545, loss: 0.00010417743760626763 2023-01-23 19:46:18.392359: step: 1714/1545, loss: 0.00030527933267876506 2023-01-23 19:46:19.313186: step: 1716/1545, loss: 0.0016840952448546886 2023-01-23 19:46:20.140118: step: 1718/1545, loss: 0.0005543709266930819 2023-01-23 19:46:21.027818: step: 1720/1545, loss: 4.842378984903917e-06 2023-01-23 19:46:21.908670: step: 1722/1545, loss: 0.14011909067630768 2023-01-23 19:46:22.777950: step: 1724/1545, loss: 0.20951397716999054 2023-01-23 19:46:23.621076: step: 1726/1545, loss: 0.0014044088311493397 2023-01-23 19:46:24.586742: step: 1728/1545, loss: 0.000724462850484997 2023-01-23 19:46:25.512530: step: 1730/1545, loss: 0.06944655627012253 2023-01-23 19:46:26.443115: step: 1732/1545, loss: 0.17401275038719177 2023-01-23 19:46:27.300469: step: 1734/1545, loss: 0.1306179165840149 2023-01-23 19:46:28.179776: step: 1736/1545, loss: 0.00014181311416905373 2023-01-23 19:46:29.091444: step: 1738/1545, loss: 0.0013063492951914668 2023-01-23 19:46:29.966476: step: 1740/1545, loss: 0.0009623384685255587 2023-01-23 19:46:30.877480: step: 1742/1545, loss: 0.021516893059015274 2023-01-23 19:46:31.754730: step: 1744/1545, loss: 0.0003052993561141193 2023-01-23 19:46:32.654082: step: 1746/1545, loss: 0.0030927895568311214 2023-01-23 19:46:33.518716: step: 1748/1545, loss: 1.4678722620010376 2023-01-23 19:46:34.401334: step: 1750/1545, loss: 0.00604404928162694 2023-01-23 19:46:35.248112: step: 1752/1545, loss: 0.019260620698332787 2023-01-23 19:46:36.127521: step: 1754/1545, loss: 0.07245367020368576 2023-01-23 19:46:36.990577: step: 1756/1545, loss: 0.0032499968074262142 2023-01-23 19:46:37.861877: step: 1758/1545, loss: 1.1992431609542109e-05 2023-01-23 19:46:38.746672: step: 1760/1545, loss: 0.00019469835388008505 2023-01-23 19:46:39.598173: step: 1762/1545, loss: 0.09831568598747253 2023-01-23 19:46:40.462967: step: 1764/1545, loss: 0.009700165130198002 2023-01-23 19:46:41.303014: step: 1766/1545, loss: 0.0974312275648117 2023-01-23 19:46:42.168545: step: 1768/1545, loss: 9.037779818754643e-05 2023-01-23 19:46:43.049128: step: 1770/1545, loss: 0.02932032197713852 2023-01-23 19:46:43.928565: step: 1772/1545, loss: 0.00020234021940268576 2023-01-23 19:46:44.791779: step: 1774/1545, loss: 0.05682383477687836 2023-01-23 19:46:45.676376: step: 1776/1545, loss: 0.0003723200352396816 2023-01-23 19:46:46.536507: step: 1778/1545, loss: 0.0045596216805279255 2023-01-23 19:46:47.413902: step: 1780/1545, loss: 0.0005608258070424199 2023-01-23 19:46:48.271251: step: 1782/1545, loss: 3.330360777908936e-05 2023-01-23 19:46:49.127013: step: 1784/1545, loss: 0.07043803483247757 2023-01-23 19:46:50.030073: step: 1786/1545, loss: 0.07167968899011612 2023-01-23 19:46:50.955576: step: 1788/1545, loss: 0.0009694461477920413 2023-01-23 19:46:51.976505: step: 1790/1545, loss: 0.0008401656523346901 2023-01-23 19:46:52.914695: step: 1792/1545, loss: 0.040506668388843536 2023-01-23 19:46:53.776304: step: 1794/1545, loss: 0.0003826061147265136 2023-01-23 19:46:54.640754: step: 1796/1545, loss: 0.07782824337482452 2023-01-23 19:46:55.498128: step: 1798/1545, loss: 0.0008798141498118639 2023-01-23 19:46:56.366538: step: 1800/1545, loss: 0.0001093557511921972 2023-01-23 19:46:57.189834: step: 1802/1545, loss: 0.000355313706677407 2023-01-23 19:46:58.041910: step: 1804/1545, loss: 0.8318795561790466 2023-01-23 19:46:58.899975: step: 1806/1545, loss: 0.029365314170718193 2023-01-23 19:46:59.827468: step: 1808/1545, loss: 0.004601882304996252 2023-01-23 19:47:00.708319: step: 1810/1545, loss: 0.10853693634271622 2023-01-23 19:47:01.634932: step: 1812/1545, loss: 0.01998993009328842 2023-01-23 19:47:02.535094: step: 1814/1545, loss: 0.0972696915268898 2023-01-23 19:47:03.433164: step: 1816/1545, loss: 0.037902869284152985 2023-01-23 19:47:04.296647: step: 1818/1545, loss: 0.07267104834318161 2023-01-23 19:47:05.164523: step: 1820/1545, loss: 0.00026065000565722585 2023-01-23 19:47:06.053459: step: 1822/1545, loss: 0.003638682421296835 2023-01-23 19:47:06.955488: step: 1824/1545, loss: 0.12253772467374802 2023-01-23 19:47:07.858409: step: 1826/1545, loss: 0.9287300109863281 2023-01-23 19:47:08.740496: step: 1828/1545, loss: 0.0003002328739967197 2023-01-23 19:47:09.626182: step: 1830/1545, loss: 0.00034861089079640806 2023-01-23 19:47:10.522763: step: 1832/1545, loss: 0.008293749764561653 2023-01-23 19:47:11.383676: step: 1834/1545, loss: 0.03441324457526207 2023-01-23 19:47:12.230348: step: 1836/1545, loss: 0.024278374388813972 2023-01-23 19:47:13.174895: step: 1838/1545, loss: 0.00041547929868102074 2023-01-23 19:47:14.055853: step: 1840/1545, loss: 0.0006632928270846605 2023-01-23 19:47:14.933874: step: 1842/1545, loss: 0.04714583232998848 2023-01-23 19:47:15.814925: step: 1844/1545, loss: 0.07034207135438919 2023-01-23 19:47:16.658635: step: 1846/1545, loss: 0.0002743166987784207 2023-01-23 19:47:17.510403: step: 1848/1545, loss: 0.0008148096967488527 2023-01-23 19:47:18.402603: step: 1850/1545, loss: 0.00012728160072583705 2023-01-23 19:47:19.283688: step: 1852/1545, loss: 0.002884928835555911 2023-01-23 19:47:20.157932: step: 1854/1545, loss: 0.0028981578070670366 2023-01-23 19:47:21.017464: step: 1856/1545, loss: 0.0017014960758388042 2023-01-23 19:47:21.896082: step: 1858/1545, loss: 0.0037522646598517895 2023-01-23 19:47:22.719422: step: 1860/1545, loss: 0.0022907350212335587 2023-01-23 19:47:23.595467: step: 1862/1545, loss: 0.10796932876110077 2023-01-23 19:47:24.519621: step: 1864/1545, loss: 0.007330423220992088 2023-01-23 19:47:25.436659: step: 1866/1545, loss: 0.17834222316741943 2023-01-23 19:47:26.326497: step: 1868/1545, loss: 0.00040739940595813096 2023-01-23 19:47:27.253152: step: 1870/1545, loss: 0.05419542267918587 2023-01-23 19:47:28.138521: step: 1872/1545, loss: 0.0004748934297822416 2023-01-23 19:47:29.026997: step: 1874/1545, loss: 0.0007276065880432725 2023-01-23 19:47:29.924265: step: 1876/1545, loss: 0.00017996280803345144 2023-01-23 19:47:30.815399: step: 1878/1545, loss: 0.06172127649188042 2023-01-23 19:47:31.705814: step: 1880/1545, loss: 0.0009333325433544815 2023-01-23 19:47:32.575134: step: 1882/1545, loss: 0.049995165318250656 2023-01-23 19:47:33.500188: step: 1884/1545, loss: 0.0030883499421179295 2023-01-23 19:47:34.398567: step: 1886/1545, loss: 0.00023995245283003896 2023-01-23 19:47:35.254848: step: 1888/1545, loss: 0.003242578823119402 2023-01-23 19:47:36.163462: step: 1890/1545, loss: 0.000113122740003746 2023-01-23 19:47:37.101400: step: 1892/1545, loss: 0.00022121674555819482 2023-01-23 19:47:37.976305: step: 1894/1545, loss: 0.32461708784103394 2023-01-23 19:47:38.834032: step: 1896/1545, loss: 0.006335571873933077 2023-01-23 19:47:39.721475: step: 1898/1545, loss: 1.876921123766806e-05 2023-01-23 19:47:40.597522: step: 1900/1545, loss: 0.018835531547665596 2023-01-23 19:47:41.569423: step: 1902/1545, loss: 9.385809971718118e-05 2023-01-23 19:47:42.464190: step: 1904/1545, loss: 0.04782576113939285 2023-01-23 19:47:43.331513: step: 1906/1545, loss: 0.2851625084877014 2023-01-23 19:47:44.251165: step: 1908/1545, loss: 0.2104709893465042 2023-01-23 19:47:45.133074: step: 1910/1545, loss: 9.065399353858083e-05 2023-01-23 19:47:46.016286: step: 1912/1545, loss: 0.002829981967806816 2023-01-23 19:47:46.898276: step: 1914/1545, loss: 0.058211639523506165 2023-01-23 19:47:47.823580: step: 1916/1545, loss: 0.010780243203043938 2023-01-23 19:47:48.684749: step: 1918/1545, loss: 0.0007775994017720222 2023-01-23 19:47:49.573250: step: 1920/1545, loss: 0.06711515784263611 2023-01-23 19:47:50.458433: step: 1922/1545, loss: 0.03832468017935753 2023-01-23 19:47:51.360212: step: 1924/1545, loss: 8.514473302057013e-05 2023-01-23 19:47:52.236146: step: 1926/1545, loss: 0.0027983421459794044 2023-01-23 19:47:53.153172: step: 1928/1545, loss: 0.024945447221398354 2023-01-23 19:47:54.030081: step: 1930/1545, loss: 0.0028254578355699778 2023-01-23 19:47:54.949990: step: 1932/1545, loss: 0.0028363442979753017 2023-01-23 19:47:55.795842: step: 1934/1545, loss: 0.0024077347479760647 2023-01-23 19:47:56.714846: step: 1936/1545, loss: 0.00039496266981586814 2023-01-23 19:47:57.567313: step: 1938/1545, loss: 0.0014479015953838825 2023-01-23 19:47:58.473358: step: 1940/1545, loss: 0.08513268083333969 2023-01-23 19:47:59.404099: step: 1942/1545, loss: 0.07313552498817444 2023-01-23 19:48:00.354113: step: 1944/1545, loss: 0.055223073810338974 2023-01-23 19:48:01.280584: step: 1946/1545, loss: 0.0015561208128929138 2023-01-23 19:48:02.143771: step: 1948/1545, loss: 0.00046551553532481194 2023-01-23 19:48:02.983411: step: 1950/1545, loss: 0.0003088564844802022 2023-01-23 19:48:03.898274: step: 1952/1545, loss: 0.04815905913710594 2023-01-23 19:48:04.829722: step: 1954/1545, loss: 0.00012825500743929297 2023-01-23 19:48:05.706008: step: 1956/1545, loss: 0.018303189426660538 2023-01-23 19:48:06.554577: step: 1958/1545, loss: 0.0011439915979281068 2023-01-23 19:48:07.391707: step: 1960/1545, loss: 0.010480898432433605 2023-01-23 19:48:08.261815: step: 1962/1545, loss: 0.00021056615514680743 2023-01-23 19:48:09.194630: step: 1964/1545, loss: 0.006500209681689739 2023-01-23 19:48:10.105998: step: 1966/1545, loss: 0.3709259629249573 2023-01-23 19:48:10.961950: step: 1968/1545, loss: 0.0001373414706904441 2023-01-23 19:48:11.849106: step: 1970/1545, loss: 0.0011363765224814415 2023-01-23 19:48:12.697362: step: 1972/1545, loss: 1.2117129564285278 2023-01-23 19:48:13.567217: step: 1974/1545, loss: 0.04072336480021477 2023-01-23 19:48:14.439032: step: 1976/1545, loss: 0.04959608241915703 2023-01-23 19:48:15.304115: step: 1978/1545, loss: 0.17684713006019592 2023-01-23 19:48:16.174066: step: 1980/1545, loss: 0.03666480630636215 2023-01-23 19:48:17.053721: step: 1982/1545, loss: 0.0006823446601629257 2023-01-23 19:48:17.940171: step: 1984/1545, loss: 0.08574690669775009 2023-01-23 19:48:18.809445: step: 1986/1545, loss: 0.0781853124499321 2023-01-23 19:48:19.699662: step: 1988/1545, loss: 0.00012049460201524198 2023-01-23 19:48:20.561549: step: 1990/1545, loss: 0.009866208769381046 2023-01-23 19:48:21.426656: step: 1992/1545, loss: 0.0006331652984954417 2023-01-23 19:48:22.265097: step: 1994/1545, loss: 0.025038760155439377 2023-01-23 19:48:23.112436: step: 1996/1545, loss: 0.6340944766998291 2023-01-23 19:48:24.009664: step: 1998/1545, loss: 0.11286555230617523 2023-01-23 19:48:24.850541: step: 2000/1545, loss: 0.0008781206561252475 2023-01-23 19:48:25.709090: step: 2002/1545, loss: 5.010604581912048e-05 2023-01-23 19:48:26.563926: step: 2004/1545, loss: 0.033548180013895035 2023-01-23 19:48:27.471102: step: 2006/1545, loss: 0.00023505593708250672 2023-01-23 19:48:28.347166: step: 2008/1545, loss: 0.11681448668241501 2023-01-23 19:48:29.201595: step: 2010/1545, loss: 0.743787944316864 2023-01-23 19:48:30.054251: step: 2012/1545, loss: 0.0004017814644612372 2023-01-23 19:48:30.919039: step: 2014/1545, loss: 0.042488642036914825 2023-01-23 19:48:31.816207: step: 2016/1545, loss: 0.00033420510590076447 2023-01-23 19:48:32.656839: step: 2018/1545, loss: 0.0037091104313731194 2023-01-23 19:48:33.533226: step: 2020/1545, loss: 0.2637355625629425 2023-01-23 19:48:34.430081: step: 2022/1545, loss: 0.09371950477361679 2023-01-23 19:48:35.267146: step: 2024/1545, loss: 0.0018910376820713282 2023-01-23 19:48:36.128047: step: 2026/1545, loss: 0.0034076033625751734 2023-01-23 19:48:37.032521: step: 2028/1545, loss: 0.09001964330673218 2023-01-23 19:48:37.893466: step: 2030/1545, loss: 0.00020626776677090675 2023-01-23 19:48:38.772914: step: 2032/1545, loss: 0.01894965209066868 2023-01-23 19:48:39.632462: step: 2034/1545, loss: 0.036230552941560745 2023-01-23 19:48:40.523383: step: 2036/1545, loss: 0.015600924380123615 2023-01-23 19:48:41.418373: step: 2038/1545, loss: 0.009142318740487099 2023-01-23 19:48:42.293451: step: 2040/1545, loss: 0.047630418092012405 2023-01-23 19:48:43.158801: step: 2042/1545, loss: 0.006825093179941177 2023-01-23 19:48:44.068156: step: 2044/1545, loss: 0.006360188126564026 2023-01-23 19:48:44.961302: step: 2046/1545, loss: 0.008823907934129238 2023-01-23 19:48:45.806926: step: 2048/1545, loss: 0.0009752116748131812 2023-01-23 19:48:46.723259: step: 2050/1545, loss: 0.7431371808052063 2023-01-23 19:48:47.585965: step: 2052/1545, loss: 0.07654264569282532 2023-01-23 19:48:48.498485: step: 2054/1545, loss: 0.0003575209993869066 2023-01-23 19:48:49.397815: step: 2056/1545, loss: 0.0009349248721264303 2023-01-23 19:48:50.382083: step: 2058/1545, loss: 0.029159298166632652 2023-01-23 19:48:51.249422: step: 2060/1545, loss: 0.008774438872933388 2023-01-23 19:48:52.111503: step: 2062/1545, loss: 0.0012368683237582445 2023-01-23 19:48:52.968343: step: 2064/1545, loss: 0.0007197201484814286 2023-01-23 19:48:53.841690: step: 2066/1545, loss: 0.0035346224904060364 2023-01-23 19:48:54.721957: step: 2068/1545, loss: 0.003031098283827305 2023-01-23 19:48:55.649138: step: 2070/1545, loss: 0.013134252279996872 2023-01-23 19:48:56.506140: step: 2072/1545, loss: 3.7045596400275826e-05 2023-01-23 19:48:57.348426: step: 2074/1545, loss: 0.022394340485334396 2023-01-23 19:48:58.225860: step: 2076/1545, loss: 4.9419595598010346e-05 2023-01-23 19:48:59.117072: step: 2078/1545, loss: 0.0001607785525266081 2023-01-23 19:49:00.014043: step: 2080/1545, loss: 0.00048499455442652106 2023-01-23 19:49:00.914033: step: 2082/1545, loss: 0.03858199343085289 2023-01-23 19:49:01.773256: step: 2084/1545, loss: 5.222402251092717e-05 2023-01-23 19:49:02.662721: step: 2086/1545, loss: 1.3231086086307187e-05 2023-01-23 19:49:03.609401: step: 2088/1545, loss: 0.6695894598960876 2023-01-23 19:49:04.524343: step: 2090/1545, loss: 0.6591000556945801 2023-01-23 19:49:05.413013: step: 2092/1545, loss: 0.5076610445976257 2023-01-23 19:49:06.333467: step: 2094/1545, loss: 0.09543497860431671 2023-01-23 19:49:07.235061: step: 2096/1545, loss: 0.001732162549160421 2023-01-23 19:49:08.114778: step: 2098/1545, loss: 0.01254518423229456 2023-01-23 19:49:09.071990: step: 2100/1545, loss: 0.06334232538938522 2023-01-23 19:49:09.942194: step: 2102/1545, loss: 0.01245124638080597 2023-01-23 19:49:10.811086: step: 2104/1545, loss: 0.0023816076572984457 2023-01-23 19:49:11.658423: step: 2106/1545, loss: 0.08998849242925644 2023-01-23 19:49:12.507224: step: 2108/1545, loss: 0.0007661502459086478 2023-01-23 19:49:13.463829: step: 2110/1545, loss: 0.24233952164649963 2023-01-23 19:49:14.398336: step: 2112/1545, loss: 0.005267185624688864 2023-01-23 19:49:15.261013: step: 2114/1545, loss: 0.0006177178584039211 2023-01-23 19:49:16.232547: step: 2116/1545, loss: 0.0210848581045866 2023-01-23 19:49:17.240681: step: 2118/1545, loss: 0.011069636791944504 2023-01-23 19:49:18.172351: step: 2120/1545, loss: 0.017048723995685577 2023-01-23 19:49:19.075420: step: 2122/1545, loss: 0.0025043203495442867 2023-01-23 19:49:19.934460: step: 2124/1545, loss: 0.013265157118439674 2023-01-23 19:49:20.809216: step: 2126/1545, loss: 0.03862632438540459 2023-01-23 19:49:21.803654: step: 2128/1545, loss: 0.30068734288215637 2023-01-23 19:49:22.670094: step: 2130/1545, loss: 0.0004246506141498685 2023-01-23 19:49:23.550318: step: 2132/1545, loss: 0.02126217447221279 2023-01-23 19:49:24.450830: step: 2134/1545, loss: 0.04150804877281189 2023-01-23 19:49:25.349705: step: 2136/1545, loss: 0.3591548204421997 2023-01-23 19:49:26.299549: step: 2138/1545, loss: 0.1828305423259735 2023-01-23 19:49:27.155189: step: 2140/1545, loss: 0.0011821831576526165 2023-01-23 19:49:28.033932: step: 2142/1545, loss: 1.0574268102645874 2023-01-23 19:49:28.911522: step: 2144/1545, loss: 0.005070175975561142 2023-01-23 19:49:29.765033: step: 2146/1545, loss: 0.0022610498126596212 2023-01-23 19:49:30.606039: step: 2148/1545, loss: 0.003270601388067007 2023-01-23 19:49:31.487720: step: 2150/1545, loss: 0.00021595008729491383 2023-01-23 19:49:32.349513: step: 2152/1545, loss: 0.00015284382971003652 2023-01-23 19:49:33.219262: step: 2154/1545, loss: 0.04287494719028473 2023-01-23 19:49:34.156220: step: 2156/1545, loss: 0.025125548243522644 2023-01-23 19:49:35.060914: step: 2158/1545, loss: 0.001184582244604826 2023-01-23 19:49:35.942662: step: 2160/1545, loss: 0.0008124324958771467 2023-01-23 19:49:36.871230: step: 2162/1545, loss: 0.02602141909301281 2023-01-23 19:49:37.770423: step: 2164/1545, loss: 0.0023845932446420193 2023-01-23 19:49:38.633987: step: 2166/1545, loss: 0.0002471469924785197 2023-01-23 19:49:39.518851: step: 2168/1545, loss: 0.006736127194017172 2023-01-23 19:49:40.387125: step: 2170/1545, loss: 6.092289913794957e-05 2023-01-23 19:49:41.282215: step: 2172/1545, loss: 2.4098155790852616e-06 2023-01-23 19:49:42.147030: step: 2174/1545, loss: 0.001177069148980081 2023-01-23 19:49:43.111113: step: 2176/1545, loss: 0.035308755934238434 2023-01-23 19:49:43.975960: step: 2178/1545, loss: 0.09463716298341751 2023-01-23 19:49:44.799308: step: 2180/1545, loss: 0.001182603882625699 2023-01-23 19:49:45.649163: step: 2182/1545, loss: 0.05061902478337288 2023-01-23 19:49:46.533810: step: 2184/1545, loss: 0.20950765907764435 2023-01-23 19:49:47.396426: step: 2186/1545, loss: 0.0009698816575109959 2023-01-23 19:49:48.248316: step: 2188/1545, loss: 0.41285383701324463 2023-01-23 19:49:49.134563: step: 2190/1545, loss: 0.12144219130277634 2023-01-23 19:49:49.990267: step: 2192/1545, loss: 0.00045880343532189727 2023-01-23 19:49:50.872953: step: 2194/1545, loss: 0.0019841021858155727 2023-01-23 19:49:51.785242: step: 2196/1545, loss: 0.012267702259123325 2023-01-23 19:49:52.669402: step: 2198/1545, loss: 0.0006927369977347553 2023-01-23 19:49:53.525006: step: 2200/1545, loss: 0.0009267213172279298 2023-01-23 19:49:54.426949: step: 2202/1545, loss: 0.00019915628945454955 2023-01-23 19:49:55.386710: step: 2204/1545, loss: 0.020713916048407555 2023-01-23 19:49:56.268321: step: 2206/1545, loss: 0.0004446335369721055 2023-01-23 19:49:57.137036: step: 2208/1545, loss: 6.789765757275745e-05 2023-01-23 19:49:57.981717: step: 2210/1545, loss: 0.002187964506447315 2023-01-23 19:49:58.870157: step: 2212/1545, loss: 0.12287335097789764 2023-01-23 19:49:59.741965: step: 2214/1545, loss: 0.00010088384442497045 2023-01-23 19:50:00.588457: step: 2216/1545, loss: 0.005235816817730665 2023-01-23 19:50:01.488076: step: 2218/1545, loss: 6.159887561807409e-05 2023-01-23 19:50:02.354088: step: 2220/1545, loss: 0.0012740215752273798 2023-01-23 19:50:03.248773: step: 2222/1545, loss: 0.02428421750664711 2023-01-23 19:50:04.145430: step: 2224/1545, loss: 0.01635661907494068 2023-01-23 19:50:05.019601: step: 2226/1545, loss: 0.0002804205287247896 2023-01-23 19:50:05.898799: step: 2228/1545, loss: 0.08680767565965652 2023-01-23 19:50:06.848539: step: 2230/1545, loss: 0.005941514391452074 2023-01-23 19:50:07.775670: step: 2232/1545, loss: 0.00010983783431584015 2023-01-23 19:50:08.738140: step: 2234/1545, loss: 0.0004032722790725529 2023-01-23 19:50:09.628743: step: 2236/1545, loss: 0.001568200415931642 2023-01-23 19:50:10.523116: step: 2238/1545, loss: 0.00034557655453681946 2023-01-23 19:50:11.407624: step: 2240/1545, loss: 0.19875496625900269 2023-01-23 19:50:12.282995: step: 2242/1545, loss: 0.03234683722257614 2023-01-23 19:50:13.130088: step: 2244/1545, loss: 8.736650488572195e-05 2023-01-23 19:50:13.965565: step: 2246/1545, loss: 0.0002158936986234039 2023-01-23 19:50:14.854011: step: 2248/1545, loss: 0.0004114562179893255 2023-01-23 19:50:15.720444: step: 2250/1545, loss: 0.0009304156992584467 2023-01-23 19:50:16.608089: step: 2252/1545, loss: 0.002226215088739991 2023-01-23 19:50:17.443983: step: 2254/1545, loss: 0.025481941178441048 2023-01-23 19:50:18.353165: step: 2256/1545, loss: 0.0025924115907400846 2023-01-23 19:50:19.270302: step: 2258/1545, loss: 0.009368645027279854 2023-01-23 19:50:20.128510: step: 2260/1545, loss: 0.00029580542468465865 2023-01-23 19:50:21.005724: step: 2262/1545, loss: 6.556670996360481e-05 2023-01-23 19:50:21.896176: step: 2264/1545, loss: 0.0024367982987314463 2023-01-23 19:50:22.800616: step: 2266/1545, loss: 0.007399660535156727 2023-01-23 19:50:23.630052: step: 2268/1545, loss: 0.0002607189235277474 2023-01-23 19:50:24.572649: step: 2270/1545, loss: 0.040998224169015884 2023-01-23 19:50:25.475235: step: 2272/1545, loss: 0.0012716683559119701 2023-01-23 19:50:26.354164: step: 2274/1545, loss: 6.418008979380829e-06 2023-01-23 19:50:27.216734: step: 2276/1545, loss: 0.00038850356941111386 2023-01-23 19:50:28.069976: step: 2278/1545, loss: 0.0006775445071980357 2023-01-23 19:50:28.965665: step: 2280/1545, loss: 0.0002869442687369883 2023-01-23 19:50:29.960673: step: 2282/1545, loss: 0.015071985311806202 2023-01-23 19:50:30.864797: step: 2284/1545, loss: 0.12399079650640488 2023-01-23 19:50:31.775777: step: 2286/1545, loss: 0.004663711879402399 2023-01-23 19:50:32.678720: step: 2288/1545, loss: 0.08608689159154892 2023-01-23 19:50:33.527768: step: 2290/1545, loss: 0.001390032353810966 2023-01-23 19:50:34.406546: step: 2292/1545, loss: 0.002097355667501688 2023-01-23 19:50:35.260050: step: 2294/1545, loss: 0.013628832064568996 2023-01-23 19:50:36.175972: step: 2296/1545, loss: 0.0009014985407702625 2023-01-23 19:50:37.063139: step: 2298/1545, loss: 0.03894812986254692 2023-01-23 19:50:37.980182: step: 2300/1545, loss: 0.6255582571029663 2023-01-23 19:50:38.862721: step: 2302/1545, loss: 0.683965265750885 2023-01-23 19:50:39.754448: step: 2304/1545, loss: 0.027036411687731743 2023-01-23 19:50:40.620404: step: 2306/1545, loss: 1.846998929977417e-05 2023-01-23 19:50:41.497800: step: 2308/1545, loss: 0.0002520451380405575 2023-01-23 19:50:42.371883: step: 2310/1545, loss: 0.0013379543088376522 2023-01-23 19:50:43.251920: step: 2312/1545, loss: 0.0005630058003589511 2023-01-23 19:50:44.115239: step: 2314/1545, loss: 0.025457492098212242 2023-01-23 19:50:44.948958: step: 2316/1545, loss: 0.00220558512955904 2023-01-23 19:50:45.839337: step: 2318/1545, loss: 0.00010406253568362445 2023-01-23 19:50:46.729351: step: 2320/1545, loss: 0.00022874926798976958 2023-01-23 19:50:47.574568: step: 2322/1545, loss: 0.0319790244102478 2023-01-23 19:50:48.405308: step: 2324/1545, loss: 0.004825992044061422 2023-01-23 19:50:49.337635: step: 2326/1545, loss: 0.006936296354979277 2023-01-23 19:50:50.228742: step: 2328/1545, loss: 0.0038879080675542355 2023-01-23 19:50:51.113384: step: 2330/1545, loss: 0.0010271298233419657 2023-01-23 19:50:52.023430: step: 2332/1545, loss: 0.1298476904630661 2023-01-23 19:50:52.894107: step: 2334/1545, loss: 0.0002557680709287524 2023-01-23 19:50:53.762657: step: 2336/1545, loss: 0.00015535250713583082 2023-01-23 19:50:54.647014: step: 2338/1545, loss: 0.022221708670258522 2023-01-23 19:50:55.524910: step: 2340/1545, loss: 0.04020927473902702 2023-01-23 19:50:56.421263: step: 2342/1545, loss: 0.0075565846636891365 2023-01-23 19:50:57.292859: step: 2344/1545, loss: 0.3903454542160034 2023-01-23 19:50:58.178178: step: 2346/1545, loss: 0.00021667680994141847 2023-01-23 19:50:59.068088: step: 2348/1545, loss: 0.001455787569284439 2023-01-23 19:50:59.955268: step: 2350/1545, loss: 0.003143934765830636 2023-01-23 19:51:00.949980: step: 2352/1545, loss: 0.001301789889112115 2023-01-23 19:51:01.870488: step: 2354/1545, loss: 0.00016943739319685847 2023-01-23 19:51:02.760139: step: 2356/1545, loss: 0.023872124031186104 2023-01-23 19:51:03.696860: step: 2358/1545, loss: 0.10977137833833694 2023-01-23 19:51:04.613080: step: 2360/1545, loss: 0.04299353063106537 2023-01-23 19:51:05.520114: step: 2362/1545, loss: 0.0012283448595553637 2023-01-23 19:51:06.411822: step: 2364/1545, loss: 0.0002659046440385282 2023-01-23 19:51:07.287922: step: 2366/1545, loss: 0.08110756427049637 2023-01-23 19:51:08.181943: step: 2368/1545, loss: 0.0004496221081353724 2023-01-23 19:51:09.055424: step: 2370/1545, loss: -2.167001184716355e-06 2023-01-23 19:51:09.928494: step: 2372/1545, loss: 0.0020571190398186445 2023-01-23 19:51:10.760271: step: 2374/1545, loss: 0.07513050734996796 2023-01-23 19:51:11.640062: step: 2376/1545, loss: 0.003078410867601633 2023-01-23 19:51:12.524379: step: 2378/1545, loss: 0.0001564669655635953 2023-01-23 19:51:13.439276: step: 2380/1545, loss: 0.12095450609922409 2023-01-23 19:51:14.316960: step: 2382/1545, loss: 0.02917194366455078 2023-01-23 19:51:15.216418: step: 2384/1545, loss: 0.00012585450895130634 2023-01-23 19:51:16.167628: step: 2386/1545, loss: 0.008040967397391796 2023-01-23 19:51:17.043859: step: 2388/1545, loss: 0.02947816252708435 2023-01-23 19:51:17.902733: step: 2390/1545, loss: 0.19613778591156006 2023-01-23 19:51:18.799260: step: 2392/1545, loss: 0.20799563825130463 2023-01-23 19:51:19.705700: step: 2394/1545, loss: 0.09346464276313782 2023-01-23 19:51:20.619053: step: 2396/1545, loss: 0.044480424374341965 2023-01-23 19:51:21.480434: step: 2398/1545, loss: 0.00012430729111656547 2023-01-23 19:51:22.344008: step: 2400/1545, loss: 0.0008402633829973638 2023-01-23 19:51:23.185615: step: 2402/1545, loss: 7.024802471278235e-05 2023-01-23 19:51:24.056003: step: 2404/1545, loss: 9.849011257756501e-05 2023-01-23 19:51:24.957056: step: 2406/1545, loss: 0.0008552912040613592 2023-01-23 19:51:25.863939: step: 2408/1545, loss: 0.26973432302474976 2023-01-23 19:51:26.787871: step: 2410/1545, loss: 0.11960823088884354 2023-01-23 19:51:27.665942: step: 2412/1545, loss: 0.000359923840733245 2023-01-23 19:51:28.572056: step: 2414/1545, loss: 0.5038964152336121 2023-01-23 19:51:29.415333: step: 2416/1545, loss: 6.171664426801726e-05 2023-01-23 19:51:30.286997: step: 2418/1545, loss: 0.00013923784717917442 2023-01-23 19:51:31.217078: step: 2420/1545, loss: 0.011258773505687714 2023-01-23 19:51:32.150800: step: 2422/1545, loss: 1.8090788216795772e-05 2023-01-23 19:51:33.082412: step: 2424/1545, loss: 0.01447969675064087 2023-01-23 19:51:34.010234: step: 2426/1545, loss: 7.037878822302446e-05 2023-01-23 19:51:34.902893: step: 2428/1545, loss: 0.009267350658774376 2023-01-23 19:51:35.744112: step: 2430/1545, loss: 0.00023698581208009273 2023-01-23 19:51:36.597268: step: 2432/1545, loss: 0.10240693390369415 2023-01-23 19:51:37.482411: step: 2434/1545, loss: 0.006227441597729921 2023-01-23 19:51:38.321610: step: 2436/1545, loss: 9.731246973387897e-05 2023-01-23 19:51:39.253339: step: 2438/1545, loss: 0.0014678791631013155 2023-01-23 19:51:40.110067: step: 2440/1545, loss: 0.0009921295568346977 2023-01-23 19:51:40.963707: step: 2442/1545, loss: 0.0011326945386826992 2023-01-23 19:51:41.847483: step: 2444/1545, loss: 0.00015331010217778385 2023-01-23 19:51:42.808339: step: 2446/1545, loss: 0.0008611032390035689 2023-01-23 19:51:43.695739: step: 2448/1545, loss: 0.0023719333112239838 2023-01-23 19:51:44.593589: step: 2450/1545, loss: 0.0482485331594944 2023-01-23 19:51:45.478041: step: 2452/1545, loss: 0.0006393378716893494 2023-01-23 19:51:46.351113: step: 2454/1545, loss: 0.01553091499954462 2023-01-23 19:51:47.211350: step: 2456/1545, loss: 0.03509960696101189 2023-01-23 19:51:48.045982: step: 2458/1545, loss: 8.716597949387506e-05 2023-01-23 19:51:48.950572: step: 2460/1545, loss: 0.05180756002664566 2023-01-23 19:51:49.806406: step: 2462/1545, loss: 2.563606176408939e-05 2023-01-23 19:51:50.658939: step: 2464/1545, loss: 0.03323658928275108 2023-01-23 19:51:51.543472: step: 2466/1545, loss: 1.1726558208465576 2023-01-23 19:51:52.433263: step: 2468/1545, loss: 0.0008264388889074326 2023-01-23 19:51:53.278688: step: 2470/1545, loss: 0.3436436057090759 2023-01-23 19:51:54.187291: step: 2472/1545, loss: 0.27862244844436646 2023-01-23 19:51:55.047216: step: 2474/1545, loss: 0.010528577491641045 2023-01-23 19:51:55.916769: step: 2476/1545, loss: 0.023352298885583878 2023-01-23 19:51:56.771306: step: 2478/1545, loss: 0.00114396121352911 2023-01-23 19:51:57.653632: step: 2480/1545, loss: 0.001910316408611834 2023-01-23 19:51:58.517167: step: 2482/1545, loss: 0.0007254264783114195 2023-01-23 19:51:59.377908: step: 2484/1545, loss: 0.000661418482195586 2023-01-23 19:52:00.294978: step: 2486/1545, loss: 0.0004435984301380813 2023-01-23 19:52:01.174272: step: 2488/1545, loss: 0.0008533105137757957 2023-01-23 19:52:02.057874: step: 2490/1545, loss: 0.0006142015918157995 2023-01-23 19:52:02.968531: step: 2492/1545, loss: 0.15499213337898254 2023-01-23 19:52:03.994053: step: 2494/1545, loss: 0.0043299258686602116 2023-01-23 19:52:04.856043: step: 2496/1545, loss: 0.00036826779250986874 2023-01-23 19:52:05.705359: step: 2498/1545, loss: 0.00023110710026230663 2023-01-23 19:52:06.575867: step: 2500/1545, loss: 0.00017690451932139695 2023-01-23 19:52:07.454330: step: 2502/1545, loss: 0.012292558327317238 2023-01-23 19:52:08.416330: step: 2504/1545, loss: 0.00019345758482813835 2023-01-23 19:52:09.317071: step: 2506/1545, loss: 0.002541706431657076 2023-01-23 19:52:10.201006: step: 2508/1545, loss: 0.0018707908457145095 2023-01-23 19:52:11.093774: step: 2510/1545, loss: 0.04657164216041565 2023-01-23 19:52:12.008876: step: 2512/1545, loss: 0.0002949449699372053 2023-01-23 19:52:12.911897: step: 2514/1545, loss: 4.803345291293226e-05 2023-01-23 19:52:13.791258: step: 2516/1545, loss: 0.2037305235862732 2023-01-23 19:52:14.638090: step: 2518/1545, loss: 0.022496091201901436 2023-01-23 19:52:15.569147: step: 2520/1545, loss: 2.8761485737049952e-05 2023-01-23 19:52:16.464542: step: 2522/1545, loss: 0.005304198246449232 2023-01-23 19:52:17.343776: step: 2524/1545, loss: 0.001552149304188788 2023-01-23 19:52:18.239650: step: 2526/1545, loss: 0.011690674349665642 2023-01-23 19:52:19.140705: step: 2528/1545, loss: 0.15560714900493622 2023-01-23 19:52:20.069358: step: 2530/1545, loss: 0.18975390493869781 2023-01-23 19:52:20.960354: step: 2532/1545, loss: 0.00010055009624920785 2023-01-23 19:52:21.857951: step: 2534/1545, loss: 0.1812061369419098 2023-01-23 19:52:22.721673: step: 2536/1545, loss: 0.16220128536224365 2023-01-23 19:52:23.642716: step: 2538/1545, loss: 0.003711046651005745 2023-01-23 19:52:24.515334: step: 2540/1545, loss: 0.00041824893560260534 2023-01-23 19:52:25.386880: step: 2542/1545, loss: 0.0005363629898056388 2023-01-23 19:52:26.247286: step: 2544/1545, loss: 0.09511245042085648 2023-01-23 19:52:27.118764: step: 2546/1545, loss: 0.10606493800878525 2023-01-23 19:52:28.076885: step: 2548/1545, loss: 5.648123624268919e-05 2023-01-23 19:52:28.950054: step: 2550/1545, loss: 0.00020267473882995546 2023-01-23 19:52:29.877724: step: 2552/1545, loss: 0.09409014880657196 2023-01-23 19:52:30.729505: step: 2554/1545, loss: 0.002132355235517025 2023-01-23 19:52:31.578040: step: 2556/1545, loss: 0.002257944317534566 2023-01-23 19:52:32.478269: step: 2558/1545, loss: 0.005902627017349005 2023-01-23 19:52:33.386227: step: 2560/1545, loss: 0.002435159171000123 2023-01-23 19:52:34.268603: step: 2562/1545, loss: 0.2861834466457367 2023-01-23 19:52:35.132128: step: 2564/1545, loss: 0.0036631193943321705 2023-01-23 19:52:36.056225: step: 2566/1545, loss: 0.1385558545589447 2023-01-23 19:52:36.943103: step: 2568/1545, loss: 0.15739227831363678 2023-01-23 19:52:37.885991: step: 2570/1545, loss: 0.09719908237457275 2023-01-23 19:52:38.736801: step: 2572/1545, loss: 0.01788468472659588 2023-01-23 19:52:39.584741: step: 2574/1545, loss: 8.339100168086588e-05 2023-01-23 19:52:40.491582: step: 2576/1545, loss: 0.027717232704162598 2023-01-23 19:52:41.342750: step: 2578/1545, loss: 0.014947125688195229 2023-01-23 19:52:42.275047: step: 2580/1545, loss: 1.6494588635396212e-05 2023-01-23 19:52:43.219575: step: 2582/1545, loss: 0.007286070846021175 2023-01-23 19:52:44.098413: step: 2584/1545, loss: 0.0005398640059866011 2023-01-23 19:52:44.988047: step: 2586/1545, loss: 0.3549242913722992 2023-01-23 19:52:45.849502: step: 2588/1545, loss: 0.047853656113147736 2023-01-23 19:52:46.737602: step: 2590/1545, loss: 0.0007574546616524458 2023-01-23 19:52:47.624761: step: 2592/1545, loss: 0.0021155073773115873 2023-01-23 19:52:48.587903: step: 2594/1545, loss: 0.00014636108244303614 2023-01-23 19:52:49.450358: step: 2596/1545, loss: 0.00022839699522592127 2023-01-23 19:52:50.305109: step: 2598/1545, loss: 0.0001853530848165974 2023-01-23 19:52:51.165049: step: 2600/1545, loss: 0.003451989497989416 2023-01-23 19:52:52.042212: step: 2602/1545, loss: 0.01184651255607605 2023-01-23 19:52:52.893090: step: 2604/1545, loss: 0.0005916690570302308 2023-01-23 19:52:53.774405: step: 2606/1545, loss: 0.0007104063406586647 2023-01-23 19:52:54.654863: step: 2608/1545, loss: 0.0007038462208583951 2023-01-23 19:52:55.549129: step: 2610/1545, loss: 0.2980872094631195 2023-01-23 19:52:56.407147: step: 2612/1545, loss: 0.03284496068954468 2023-01-23 19:52:57.285561: step: 2614/1545, loss: 0.011100969277322292 2023-01-23 19:52:58.172438: step: 2616/1545, loss: 0.0004934453754685819 2023-01-23 19:52:59.098607: step: 2618/1545, loss: 0.00020492715702857822 2023-01-23 19:53:00.076110: step: 2620/1545, loss: 0.0013756771804764867 2023-01-23 19:53:00.958608: step: 2622/1545, loss: 0.11165513098239899 2023-01-23 19:53:01.854295: step: 2624/1545, loss: 0.0059880767948925495 2023-01-23 19:53:02.742025: step: 2626/1545, loss: 0.021645639091730118 2023-01-23 19:53:03.645336: step: 2628/1545, loss: 0.0005050899344496429 2023-01-23 19:53:04.516088: step: 2630/1545, loss: 0.00019671625341288745 2023-01-23 19:53:05.387991: step: 2632/1545, loss: 0.0036793826147913933 2023-01-23 19:53:06.312686: step: 2634/1545, loss: 0.02759253978729248 2023-01-23 19:53:07.224478: step: 2636/1545, loss: 0.008495653048157692 2023-01-23 19:53:08.111657: step: 2638/1545, loss: 0.061990104615688324 2023-01-23 19:53:09.038856: step: 2640/1545, loss: 0.0049503822810947895 2023-01-23 19:53:09.872845: step: 2642/1545, loss: 0.00016705157759133726 2023-01-23 19:53:10.747369: step: 2644/1545, loss: 0.06383290141820908 2023-01-23 19:53:11.635021: step: 2646/1545, loss: 0.43099245429039 2023-01-23 19:53:12.539320: step: 2648/1545, loss: 0.14246585965156555 2023-01-23 19:53:13.456336: step: 2650/1545, loss: 0.0003653322346508503 2023-01-23 19:53:14.339034: step: 2652/1545, loss: 0.004019040614366531 2023-01-23 19:53:15.204782: step: 2654/1545, loss: 0.2048361897468567 2023-01-23 19:53:16.111339: step: 2656/1545, loss: 0.018706806004047394 2023-01-23 19:53:17.047544: step: 2658/1545, loss: 0.0005438159569166601 2023-01-23 19:53:17.887644: step: 2660/1545, loss: 0.0017722748452797532 2023-01-23 19:53:18.758101: step: 2662/1545, loss: 0.08679690957069397 2023-01-23 19:53:19.618197: step: 2664/1545, loss: 0.012838633731007576 2023-01-23 19:53:20.502424: step: 2666/1545, loss: 0.05128048360347748 2023-01-23 19:53:21.373114: step: 2668/1545, loss: 0.00010280386777594686 2023-01-23 19:53:22.244661: step: 2670/1545, loss: 0.005537485238164663 2023-01-23 19:53:23.145518: step: 2672/1545, loss: 0.000978849595412612 2023-01-23 19:53:23.992519: step: 2674/1545, loss: 0.5662553310394287 2023-01-23 19:53:24.847362: step: 2676/1545, loss: 0.004940963350236416 2023-01-23 19:53:25.747627: step: 2678/1545, loss: 0.032070085406303406 2023-01-23 19:53:26.621066: step: 2680/1545, loss: 0.000831749988719821 2023-01-23 19:53:27.517944: step: 2682/1545, loss: 8.503376739099622e-05 2023-01-23 19:53:28.564645: step: 2684/1545, loss: 0.07504095882177353 2023-01-23 19:53:29.477641: step: 2686/1545, loss: 0.0021086023189127445 2023-01-23 19:53:30.332963: step: 2688/1545, loss: 0.00021051132353022695 2023-01-23 19:53:31.231937: step: 2690/1545, loss: 0.00017064245184883475 2023-01-23 19:53:32.179296: step: 2692/1545, loss: 0.0002840876404661685 2023-01-23 19:53:33.119718: step: 2694/1545, loss: 0.00013357566785998642 2023-01-23 19:53:33.999460: step: 2696/1545, loss: 0.0041748820804059505 2023-01-23 19:53:34.858176: step: 2698/1545, loss: 0.000958280055783689 2023-01-23 19:53:35.678203: step: 2700/1545, loss: 0.010293695144355297 2023-01-23 19:53:36.514984: step: 2702/1545, loss: 0.002444435842335224 2023-01-23 19:53:37.432449: step: 2704/1545, loss: 0.011032281443476677 2023-01-23 19:53:38.290736: step: 2706/1545, loss: 0.000670109293423593 2023-01-23 19:53:39.210508: step: 2708/1545, loss: 0.000779544236138463 2023-01-23 19:53:40.132453: step: 2710/1545, loss: 0.00019580131629481912 2023-01-23 19:53:41.108499: step: 2712/1545, loss: 0.02811242640018463 2023-01-23 19:53:42.002740: step: 2714/1545, loss: 0.0007218709215521812 2023-01-23 19:53:42.847996: step: 2716/1545, loss: 0.0032589950133115053 2023-01-23 19:53:43.723150: step: 2718/1545, loss: 0.024873705580830574 2023-01-23 19:53:44.654695: step: 2720/1545, loss: 0.042565394192934036 2023-01-23 19:53:45.514846: step: 2722/1545, loss: 0.010311579331755638 2023-01-23 19:53:46.395418: step: 2724/1545, loss: 0.00026450451696291566 2023-01-23 19:53:47.280733: step: 2726/1545, loss: 0.00014286399527918547 2023-01-23 19:53:48.182322: step: 2728/1545, loss: 0.0007001510239206254 2023-01-23 19:53:49.035404: step: 2730/1545, loss: 0.00039294955786317587 2023-01-23 19:53:49.945762: step: 2732/1545, loss: 0.000363489321898669 2023-01-23 19:53:50.806715: step: 2734/1545, loss: 0.001401198678649962 2023-01-23 19:53:51.707924: step: 2736/1545, loss: 8.075366349657997e-05 2023-01-23 19:53:52.593401: step: 2738/1545, loss: 0.01676560752093792 2023-01-23 19:53:53.457689: step: 2740/1545, loss: 0.0013310095528140664 2023-01-23 19:53:54.350641: step: 2742/1545, loss: 0.0014598555862903595 2023-01-23 19:53:55.268597: step: 2744/1545, loss: 0.5829547047615051 2023-01-23 19:53:56.112871: step: 2746/1545, loss: 7.652070053154603e-05 2023-01-23 19:53:56.982495: step: 2748/1545, loss: 0.018497958779335022 2023-01-23 19:53:57.847585: step: 2750/1545, loss: 0.0005878166412003338 2023-01-23 19:53:58.702677: step: 2752/1545, loss: 0.0007388216909021139 2023-01-23 19:53:59.617693: step: 2754/1545, loss: 0.022990217432379723 2023-01-23 19:54:00.470382: step: 2756/1545, loss: 0.04217573627829552 2023-01-23 19:54:01.341385: step: 2758/1545, loss: 0.000989694963209331 2023-01-23 19:54:02.260220: step: 2760/1545, loss: 0.006865149363875389 2023-01-23 19:54:03.115384: step: 2762/1545, loss: 0.16155597567558289 2023-01-23 19:54:04.023566: step: 2764/1545, loss: 0.011467739008367062 2023-01-23 19:54:04.919371: step: 2766/1545, loss: 0.0008027435978874564 2023-01-23 19:54:05.817482: step: 2768/1545, loss: 0.13755591213703156 2023-01-23 19:54:06.728328: step: 2770/1545, loss: 0.010190695524215698 2023-01-23 19:54:07.619240: step: 2772/1545, loss: 0.008860515430569649 2023-01-23 19:54:08.514805: step: 2774/1545, loss: 0.00033059512497857213 2023-01-23 19:54:09.361561: step: 2776/1545, loss: 0.0009141053888015449 2023-01-23 19:54:10.242803: step: 2778/1545, loss: 0.00029862800147384405 2023-01-23 19:54:11.122914: step: 2780/1545, loss: 0.020289838314056396 2023-01-23 19:54:12.012877: step: 2782/1545, loss: 0.25732654333114624 2023-01-23 19:54:12.903587: step: 2784/1545, loss: 0.006589527241885662 2023-01-23 19:54:13.790409: step: 2786/1545, loss: 0.10131615400314331 2023-01-23 19:54:14.715040: step: 2788/1545, loss: 0.0010942536173388362 2023-01-23 19:54:15.611514: step: 2790/1545, loss: 0.0660778358578682 2023-01-23 19:54:16.483377: step: 2792/1545, loss: 0.0008331257267855108 2023-01-23 19:54:17.362399: step: 2794/1545, loss: 6.66125924908556e-05 2023-01-23 19:54:18.226067: step: 2796/1545, loss: 0.00020869374566245824 2023-01-23 19:54:19.170038: step: 2798/1545, loss: 0.00020600597781594843 2023-01-23 19:54:20.042959: step: 2800/1545, loss: 0.0020395764149725437 2023-01-23 19:54:20.967126: step: 2802/1545, loss: 0.20452140271663666 2023-01-23 19:54:21.828303: step: 2804/1545, loss: 0.0001784786581993103 2023-01-23 19:54:22.703522: step: 2806/1545, loss: 0.013868361711502075 2023-01-23 19:54:23.580282: step: 2808/1545, loss: 0.00010122740786755458 2023-01-23 19:54:24.492733: step: 2810/1545, loss: 0.00021781456598546356 2023-01-23 19:54:25.312489: step: 2812/1545, loss: 0.0013627951266244054 2023-01-23 19:54:26.165770: step: 2814/1545, loss: 0.018991151824593544 2023-01-23 19:54:27.045018: step: 2816/1545, loss: 0.0011164074530825019 2023-01-23 19:54:27.950134: step: 2818/1545, loss: 0.0350026935338974 2023-01-23 19:54:28.865217: step: 2820/1545, loss: 0.030884483829140663 2023-01-23 19:54:29.772594: step: 2822/1545, loss: 0.08880124986171722 2023-01-23 19:54:30.646149: step: 2824/1545, loss: 0.00014798974734731019 2023-01-23 19:54:31.549106: step: 2826/1545, loss: 0.01880071684718132 2023-01-23 19:54:32.431937: step: 2828/1545, loss: 0.016762781888246536 2023-01-23 19:54:33.340184: step: 2830/1545, loss: 0.0036576741840690374 2023-01-23 19:54:34.204833: step: 2832/1545, loss: 0.15997052192687988 2023-01-23 19:54:35.119075: step: 2834/1545, loss: 0.019342800602316856 2023-01-23 19:54:35.962188: step: 2836/1545, loss: 0.00010705189924919978 2023-01-23 19:54:36.841740: step: 2838/1545, loss: 1.1748629808425903 2023-01-23 19:54:37.732439: step: 2840/1545, loss: 0.005313490517437458 2023-01-23 19:54:38.751872: step: 2842/1545, loss: 0.21377044916152954 2023-01-23 19:54:39.667627: step: 2844/1545, loss: 0.0005161051522009075 2023-01-23 19:54:40.668875: step: 2846/1545, loss: 0.1747376173734665 2023-01-23 19:54:41.601999: step: 2848/1545, loss: 0.04571417719125748 2023-01-23 19:54:42.454261: step: 2850/1545, loss: 0.00013824844791088253 2023-01-23 19:54:43.319178: step: 2852/1545, loss: 0.04646080359816551 2023-01-23 19:54:44.232057: step: 2854/1545, loss: 0.025250835344195366 2023-01-23 19:54:45.080269: step: 2856/1545, loss: 0.00015331314352806658 2023-01-23 19:54:45.966624: step: 2858/1545, loss: 0.9288192391395569 2023-01-23 19:54:46.854850: step: 2860/1545, loss: 0.0004934282624162734 2023-01-23 19:54:47.697125: step: 2862/1545, loss: 0.00048711872659623623 2023-01-23 19:54:48.606095: step: 2864/1545, loss: 8.559443813282996e-05 2023-01-23 19:54:49.541024: step: 2866/1545, loss: 0.017851827666163445 2023-01-23 19:54:50.371482: step: 2868/1545, loss: 0.002172267995774746 2023-01-23 19:54:51.243656: step: 2870/1545, loss: 0.0004425466468092054 2023-01-23 19:54:52.145773: step: 2872/1545, loss: 2.379564284638036e-05 2023-01-23 19:54:53.046070: step: 2874/1545, loss: 0.36500000953674316 2023-01-23 19:54:53.934512: step: 2876/1545, loss: 0.00977338943630457 2023-01-23 19:54:54.847525: step: 2878/1545, loss: 0.0026611112989485264 2023-01-23 19:54:55.716189: step: 2880/1545, loss: 0.004368470050394535 2023-01-23 19:54:56.596497: step: 2882/1545, loss: 0.0008690391550771892 2023-01-23 19:54:57.475196: step: 2884/1545, loss: 0.0012094159610569477 2023-01-23 19:54:58.330668: step: 2886/1545, loss: 0.05534694716334343 2023-01-23 19:54:59.197772: step: 2888/1545, loss: 0.0003834976232610643 2023-01-23 19:55:00.087358: step: 2890/1545, loss: 0.08344414830207825 2023-01-23 19:55:00.955625: step: 2892/1545, loss: 0.0014656143030151725 2023-01-23 19:55:01.867661: step: 2894/1545, loss: 0.06597906351089478 2023-01-23 19:55:02.732912: step: 2896/1545, loss: 0.0009280629456043243 2023-01-23 19:55:03.602444: step: 2898/1545, loss: 0.0019382486352697015 2023-01-23 19:55:04.437797: step: 2900/1545, loss: 0.02135212905704975 2023-01-23 19:55:05.314396: step: 2902/1545, loss: 0.07233167439699173 2023-01-23 19:55:06.231147: step: 2904/1545, loss: 0.047490887343883514 2023-01-23 19:55:07.075028: step: 2906/1545, loss: 9.339219832327217e-05 2023-01-23 19:55:07.917821: step: 2908/1545, loss: 0.000316726160235703 2023-01-23 19:55:08.804354: step: 2910/1545, loss: 0.00027589406818151474 2023-01-23 19:55:09.675408: step: 2912/1545, loss: 0.5359147787094116 2023-01-23 19:55:10.548059: step: 2914/1545, loss: 0.00011723838542820886 2023-01-23 19:55:11.406976: step: 2916/1545, loss: 0.0019137401832267642 2023-01-23 19:55:12.286440: step: 2918/1545, loss: 0.004798444453626871 2023-01-23 19:55:13.154795: step: 2920/1545, loss: 0.027278892695903778 2023-01-23 19:55:14.055261: step: 2922/1545, loss: 0.14400336146354675 2023-01-23 19:55:14.978416: step: 2924/1545, loss: 0.001057725283317268 2023-01-23 19:55:15.890568: step: 2926/1545, loss: 0.12941721081733704 2023-01-23 19:55:16.777371: step: 2928/1545, loss: 0.0010755214607343078 2023-01-23 19:55:17.665301: step: 2930/1545, loss: 0.03686928749084473 2023-01-23 19:55:18.631944: step: 2932/1545, loss: 0.04636899381875992 2023-01-23 19:55:19.507353: step: 2934/1545, loss: 0.00011046597501263022 2023-01-23 19:55:20.432273: step: 2936/1545, loss: 0.004903947003185749 2023-01-23 19:55:21.311000: step: 2938/1545, loss: 0.0023010445293039083 2023-01-23 19:55:22.169946: step: 2940/1545, loss: 0.0002164768666261807 2023-01-23 19:55:23.044168: step: 2942/1545, loss: 0.004318579100072384 2023-01-23 19:55:23.932187: step: 2944/1545, loss: 0.011499335058033466 2023-01-23 19:55:24.838711: step: 2946/1545, loss: 0.00016952455916907638 2023-01-23 19:55:25.688405: step: 2948/1545, loss: 0.0005712485290132463 2023-01-23 19:55:26.614694: step: 2950/1545, loss: 7.803920016158372e-05 2023-01-23 19:55:27.509075: step: 2952/1545, loss: 0.2103719860315323 2023-01-23 19:55:28.423637: step: 2954/1545, loss: 0.08603834360837936 2023-01-23 19:55:29.303041: step: 2956/1545, loss: 4.72406973131001e-05 2023-01-23 19:55:30.180576: step: 2958/1545, loss: 1.626064419746399 2023-01-23 19:55:31.078213: step: 2960/1545, loss: 0.32850518822669983 2023-01-23 19:55:31.924268: step: 2962/1545, loss: 0.00026412494480609894 2023-01-23 19:55:32.822687: step: 2964/1545, loss: 0.00044469244312494993 2023-01-23 19:55:33.707848: step: 2966/1545, loss: 0.07494563609361649 2023-01-23 19:55:34.572054: step: 2968/1545, loss: 0.0001992601464735344 2023-01-23 19:55:35.523186: step: 2970/1545, loss: 0.5241707563400269 2023-01-23 19:55:36.400828: step: 2972/1545, loss: 1.676581086940132e-05 2023-01-23 19:55:37.247901: step: 2974/1545, loss: 0.01885732263326645 2023-01-23 19:55:38.116217: step: 2976/1545, loss: 0.03918866068124771 2023-01-23 19:55:38.953983: step: 2978/1545, loss: 0.0440250001847744 2023-01-23 19:55:39.827946: step: 2980/1545, loss: 0.0003960828762501478 2023-01-23 19:55:40.681441: step: 2982/1545, loss: 0.00014190775982569903 2023-01-23 19:55:41.588014: step: 2984/1545, loss: 0.002231674501672387 2023-01-23 19:55:42.503581: step: 2986/1545, loss: 0.0001101119487429969 2023-01-23 19:55:43.390598: step: 2988/1545, loss: 0.009675548411905766 2023-01-23 19:55:44.346250: step: 2990/1545, loss: 0.36010023951530457 2023-01-23 19:55:45.224085: step: 2992/1545, loss: 0.007674014195799828 2023-01-23 19:55:46.163203: step: 2994/1545, loss: 0.009772644378244877 2023-01-23 19:55:47.025024: step: 2996/1545, loss: 0.057003095746040344 2023-01-23 19:55:47.882645: step: 2998/1545, loss: 0.033562060445547104 2023-01-23 19:55:48.774141: step: 3000/1545, loss: 0.4222916066646576 2023-01-23 19:55:49.754606: step: 3002/1545, loss: 0.042141348123550415 2023-01-23 19:55:50.714685: step: 3004/1545, loss: 0.028149528428912163 2023-01-23 19:55:51.589114: step: 3006/1545, loss: 0.01632874645292759 2023-01-23 19:55:52.471008: step: 3008/1545, loss: 0.0004133886832278222 2023-01-23 19:55:53.358292: step: 3010/1545, loss: 0.0030978291761130095 2023-01-23 19:55:54.256591: step: 3012/1545, loss: 0.11477131396532059 2023-01-23 19:55:55.107752: step: 3014/1545, loss: 0.001208942150697112 2023-01-23 19:55:56.068081: step: 3016/1545, loss: 0.0009757083607837558 2023-01-23 19:55:56.971876: step: 3018/1545, loss: 0.005297867581248283 2023-01-23 19:55:57.908642: step: 3020/1545, loss: 0.0024074099492281675 2023-01-23 19:55:58.795995: step: 3022/1545, loss: 0.0014599605929106474 2023-01-23 19:55:59.708795: step: 3024/1545, loss: 0.0001680591085460037 2023-01-23 19:56:00.630585: step: 3026/1545, loss: 0.0014349271077662706 2023-01-23 19:56:01.550708: step: 3028/1545, loss: 0.002260145964100957 2023-01-23 19:56:02.449279: step: 3030/1545, loss: 0.014696499332785606 2023-01-23 19:56:03.340234: step: 3032/1545, loss: 0.009316232986748219 2023-01-23 19:56:04.251908: step: 3034/1545, loss: 0.0003041372401639819 2023-01-23 19:56:05.117400: step: 3036/1545, loss: 6.388258043443784e-05 2023-01-23 19:56:05.969389: step: 3038/1545, loss: 0.06602469831705093 2023-01-23 19:56:06.854227: step: 3040/1545, loss: 0.00081114680506289 2023-01-23 19:56:07.784429: step: 3042/1545, loss: 0.8514373898506165 2023-01-23 19:56:08.693720: step: 3044/1545, loss: 0.008227379992604256 2023-01-23 19:56:09.562184: step: 3046/1545, loss: 0.05736212432384491 2023-01-23 19:56:10.412051: step: 3048/1545, loss: 0.09551301598548889 2023-01-23 19:56:11.271976: step: 3050/1545, loss: 0.0014066911535337567 2023-01-23 19:56:12.250744: step: 3052/1545, loss: 0.0013050106354057789 2023-01-23 19:56:13.148755: step: 3054/1545, loss: 0.003887525061145425 2023-01-23 19:56:14.007997: step: 3056/1545, loss: 0.2393803745508194 2023-01-23 19:56:14.932391: step: 3058/1545, loss: 0.4460127651691437 2023-01-23 19:56:15.809519: step: 3060/1545, loss: 0.011009770445525646 2023-01-23 19:56:16.702351: step: 3062/1545, loss: 0.0005255969590507448 2023-01-23 19:56:17.610184: step: 3064/1545, loss: 0.022113405168056488 2023-01-23 19:56:18.539169: step: 3066/1545, loss: 7.921303040347993e-05 2023-01-23 19:56:19.406944: step: 3068/1545, loss: 0.00048814096953719854 2023-01-23 19:56:20.270981: step: 3070/1545, loss: 0.00023587985197082162 2023-01-23 19:56:21.128874: step: 3072/1545, loss: 0.11389070749282837 2023-01-23 19:56:22.013881: step: 3074/1545, loss: 0.0037040275055915117 2023-01-23 19:56:22.923255: step: 3076/1545, loss: 0.00036524771712720394 2023-01-23 19:56:23.788765: step: 3078/1545, loss: 8.989435445982963e-05 2023-01-23 19:56:24.686489: step: 3080/1545, loss: 0.0018208689289167523 2023-01-23 19:56:25.513677: step: 3082/1545, loss: 0.0007575619965791702 2023-01-23 19:56:26.376319: step: 3084/1545, loss: 0.0003583995276130736 2023-01-23 19:56:27.266463: step: 3086/1545, loss: 0.0011432861210778356 2023-01-23 19:56:28.151443: step: 3088/1545, loss: 0.49811333417892456 2023-01-23 19:56:29.032271: step: 3090/1545, loss: 0.004055042751133442 ================================================== Loss: 0.063 -------------------- Dev Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6520749314359015, 'r': 0.6652827507523076, 'f1': 0.6586126303400119}, 'combined': 0.43512656992487597, 'epoch': 31} Test Chinese: {'event': {'p': 0.6414087513340448, 'r': 0.768542199488491, 'f1': 0.6992437463641652}, 'argument': {'p': 0.7110094532177335, 'r': 0.7229591919272752, 'f1': 0.7169345319945478}, 'combined': 0.5013119880497071, 'epoch': 31} Dev Korean: {'event': {'p': 0.6105032822757112, 'r': 0.7430093209054593, 'f1': 0.6702702702702702}, 'argument': {'p': 0.6514317684862074, 'r': 0.6592626537572662, 'f1': 0.6553238178871705}, 'combined': 0.4392440725297791, 'epoch': 31} Test Korean: {'event': {'p': 0.6322751322751323, 'r': 0.7640664961636828, 'f1': 0.6919513607411696}, 'argument': {'p': 0.7013586510852526, 'r': 0.7182750350892232, 'f1': 0.7097160550985628}, 'combined': 0.49108899006530543, 'epoch': 31} Dev Russian: {'event': {'p': 0.5688976377952756, 'r': 0.7696404793608522, 'f1': 0.6542161856253538}, 'argument': {'p': 0.6502762935859703, 'r': 0.6614398351067595, 'f1': 0.6558105599143614}, 'combined': 0.42904188300000107, 'epoch': 31} Test Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7093639649934588, 'r': 0.734053653894803, 'f1': 0.7214976506186919}, 'combined': 0.5099580146069947, 'epoch': 31} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6526806526806527, 'r': 0.6311044327573253, 'f1': 0.6417112299465241}, 'combined': 0.45697617890131254, 'epoch': 31} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6652186020607074, 'r': 0.5194172646227441, 'f1': 0.5833455433455434}, 'combined': 0.3581946318788425, 'epoch': 31} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5291288024840657, 'r': 0.5291288024840657, 'f1': 0.5291288024840657}, 'combined': 0.30810031537046856, 'epoch': 31} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5986913849509269, 'r': 0.7310252996005326, 'f1': 0.658273381294964}, 'argument': {'p': 0.6559451265403835, 'r': 0.6613377994790564, 'f1': 0.6586304247882229}, 'combined': 0.43355887674908195, 'epoch': 26} Test for Chinese: {'event': {'p': 0.6382070437566703, 'r': 0.7647058823529411, 'f1': 0.6957533449680047}, 'argument': {'p': 0.6980547354393568, 'r': 0.7185779178100443, 'f1': 0.7081676638737557}, 'combined': 0.49271002093834315, 'epoch': 26} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.6657901327322815, 'r': 0.6657901327322815, 'f1': 0.6657901327322815}, 'combined': 0.47412327633965495, 'epoch': 26} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 32 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 20:01:44.246618: step: 2/1545, loss: 0.0009108028607442975 2023-01-23 20:01:45.101666: step: 4/1545, loss: 9.49410823523067e-05 2023-01-23 20:01:45.950476: step: 6/1545, loss: 0.00018773427291307598 2023-01-23 20:01:46.782537: step: 8/1545, loss: 0.011837727390229702 2023-01-23 20:01:47.680057: step: 10/1545, loss: 0.3349662721157074 2023-01-23 20:01:48.609009: step: 12/1545, loss: 0.393801212310791 2023-01-23 20:01:49.535793: step: 14/1545, loss: 0.00013034367293585092 2023-01-23 20:01:50.432196: step: 16/1545, loss: 0.027653034776449203 2023-01-23 20:01:51.349642: step: 18/1545, loss: 0.3327631950378418 2023-01-23 20:01:52.229658: step: 20/1545, loss: 0.0001711147924652323 2023-01-23 20:01:53.105387: step: 22/1545, loss: 0.00017587255570106208 2023-01-23 20:01:53.975069: step: 24/1545, loss: 0.0006305229617282748 2023-01-23 20:01:54.820488: step: 26/1545, loss: 0.026304170489311218 2023-01-23 20:01:55.629251: step: 28/1545, loss: 0.01862633414566517 2023-01-23 20:01:56.516787: step: 30/1545, loss: 0.23055657744407654 2023-01-23 20:01:57.361333: step: 32/1545, loss: 0.0007261217688210309 2023-01-23 20:01:58.277527: step: 34/1545, loss: 0.0015097518917173147 2023-01-23 20:01:59.178555: step: 36/1545, loss: -3.11529693135526e-05 2023-01-23 20:02:00.037617: step: 38/1545, loss: 3.989963443018496e-05 2023-01-23 20:02:00.941244: step: 40/1545, loss: 5.483913264470175e-05 2023-01-23 20:02:01.780982: step: 42/1545, loss: 0.008607808500528336 2023-01-23 20:02:02.708885: step: 44/1545, loss: 0.009205624461174011 2023-01-23 20:02:03.589567: step: 46/1545, loss: 0.11260809749364853 2023-01-23 20:02:04.450589: step: 48/1545, loss: 0.00012600341869983822 2023-01-23 20:02:05.339840: step: 50/1545, loss: 0.0031480020843446255 2023-01-23 20:02:06.239785: step: 52/1545, loss: 0.00010814989218488336 2023-01-23 20:02:07.059258: step: 54/1545, loss: 6.429052154999226e-05 2023-01-23 20:02:07.916462: step: 56/1545, loss: 0.0007721281726844609 2023-01-23 20:02:08.770599: step: 58/1545, loss: 0.09759657829999924 2023-01-23 20:02:09.641535: step: 60/1545, loss: 0.0002563198213465512 2023-01-23 20:02:10.510651: step: 62/1545, loss: 0.04848610609769821 2023-01-23 20:02:11.415621: step: 64/1545, loss: 0.0038348152302205563 2023-01-23 20:02:12.252147: step: 66/1545, loss: 0.00011097818787675351 2023-01-23 20:02:13.110925: step: 68/1545, loss: 9.922605386236683e-05 2023-01-23 20:02:13.954781: step: 70/1545, loss: 4.115729097975418e-05 2023-01-23 20:02:14.837909: step: 72/1545, loss: -2.6308025553589687e-06 2023-01-23 20:02:15.677283: step: 74/1545, loss: 0.00024338994990102947 2023-01-23 20:02:16.545427: step: 76/1545, loss: 0.0004950398579239845 2023-01-23 20:02:17.449240: step: 78/1545, loss: 6.97000214131549e-05 2023-01-23 20:02:18.329678: step: 80/1545, loss: 8.0366269685328e-05 2023-01-23 20:02:19.239865: step: 82/1545, loss: 0.02486490271985531 2023-01-23 20:02:20.137356: step: 84/1545, loss: 0.0002759105700533837 2023-01-23 20:02:20.994025: step: 86/1545, loss: 0.08028639853000641 2023-01-23 20:02:21.880113: step: 88/1545, loss: 0.0007385578355751932 2023-01-23 20:02:22.742528: step: 90/1545, loss: 5.0208964239573106e-05 2023-01-23 20:02:23.604486: step: 92/1545, loss: 4.8268557293340564e-05 2023-01-23 20:02:24.590026: step: 94/1545, loss: 0.25540801882743835 2023-01-23 20:02:25.428811: step: 96/1545, loss: 0.00017157614638563246 2023-01-23 20:02:26.288719: step: 98/1545, loss: 0.0002520591369830072 2023-01-23 20:02:27.128920: step: 100/1545, loss: 0.0001498254423495382 2023-01-23 20:02:28.025884: step: 102/1545, loss: 0.00023077130026649684 2023-01-23 20:02:28.878475: step: 104/1545, loss: 0.008432278409600258 2023-01-23 20:02:29.842627: step: 106/1545, loss: 0.005164093803614378 2023-01-23 20:02:30.747038: step: 108/1545, loss: 0.2470419853925705 2023-01-23 20:02:31.655848: step: 110/1545, loss: 0.01945745386183262 2023-01-23 20:02:32.508414: step: 112/1545, loss: 0.11171126365661621 2023-01-23 20:02:33.368714: step: 114/1545, loss: 0.0006806715973652899 2023-01-23 20:02:34.246048: step: 116/1545, loss: 0.0013057542964816093 2023-01-23 20:02:35.104683: step: 118/1545, loss: 0.000251233228482306 2023-01-23 20:02:35.950868: step: 120/1545, loss: 0.0004189165192656219 2023-01-23 20:02:36.819795: step: 122/1545, loss: 0.00048744239029474556 2023-01-23 20:02:37.668560: step: 124/1545, loss: 0.057488396763801575 2023-01-23 20:02:38.526025: step: 126/1545, loss: 0.009435939602553844 2023-01-23 20:02:39.403175: step: 128/1545, loss: 0.004159329924732447 2023-01-23 20:02:40.255034: step: 130/1545, loss: 0.05292954295873642 2023-01-23 20:02:41.103063: step: 132/1545, loss: 0.00025889044627547264 2023-01-23 20:02:41.928139: step: 134/1545, loss: 0.00010126530833076686 2023-01-23 20:02:42.803345: step: 136/1545, loss: 0.00011493753845570609 2023-01-23 20:02:43.681741: step: 138/1545, loss: 0.0002012620388995856 2023-01-23 20:02:44.563675: step: 140/1545, loss: 7.320398435695097e-05 2023-01-23 20:02:45.433135: step: 142/1545, loss: 0.000544471200555563 2023-01-23 20:02:46.329220: step: 144/1545, loss: 0.001324341748841107 2023-01-23 20:02:47.220131: step: 146/1545, loss: 0.003768783062696457 2023-01-23 20:02:48.066523: step: 148/1545, loss: 0.016499612480401993 2023-01-23 20:02:48.971782: step: 150/1545, loss: 0.03655744343996048 2023-01-23 20:02:49.861931: step: 152/1545, loss: 0.08331155776977539 2023-01-23 20:02:50.895940: step: 154/1545, loss: 0.00017535971710458398 2023-01-23 20:02:51.727522: step: 156/1545, loss: 0.00031180231599137187 2023-01-23 20:02:52.626469: step: 158/1545, loss: 0.003140954999253154 2023-01-23 20:02:53.544381: step: 160/1545, loss: 0.0003070844104513526 2023-01-23 20:02:54.470620: step: 162/1545, loss: 0.20161548256874084 2023-01-23 20:02:55.318912: step: 164/1545, loss: 7.887637184467167e-05 2023-01-23 20:02:56.206675: step: 166/1545, loss: 0.0005087243625894189 2023-01-23 20:02:57.062279: step: 168/1545, loss: 0.1454218178987503 2023-01-23 20:02:57.920349: step: 170/1545, loss: 0.00012822904682252556 2023-01-23 20:02:58.797908: step: 172/1545, loss: 0.17011864483356476 2023-01-23 20:02:59.680107: step: 174/1545, loss: 0.0003002359881065786 2023-01-23 20:03:00.569407: step: 176/1545, loss: 0.0016091495053842664 2023-01-23 20:03:01.450258: step: 178/1545, loss: 0.0005100764101371169 2023-01-23 20:03:02.372794: step: 180/1545, loss: 0.008703820407390594 2023-01-23 20:03:03.331331: step: 182/1545, loss: 0.007635280955582857 2023-01-23 20:03:04.246571: step: 184/1545, loss: 0.0005191998789086938 2023-01-23 20:03:05.129068: step: 186/1545, loss: 0.007111585233360529 2023-01-23 20:03:06.095578: step: 188/1545, loss: 0.004841124638915062 2023-01-23 20:03:06.982704: step: 190/1545, loss: 0.0001308695791522041 2023-01-23 20:03:07.970502: step: 192/1545, loss: 0.0004091713053639978 2023-01-23 20:03:08.853805: step: 194/1545, loss: 0.0007905559614300728 2023-01-23 20:03:09.724525: step: 196/1545, loss: 0.0013832382392138243 2023-01-23 20:03:10.619314: step: 198/1545, loss: 0.026833729818463326 2023-01-23 20:03:11.462747: step: 200/1545, loss: 0.001611777930520475 2023-01-23 20:03:12.328760: step: 202/1545, loss: 0.024279147386550903 2023-01-23 20:03:13.252139: step: 204/1545, loss: 0.000273960642516613 2023-01-23 20:03:14.087534: step: 206/1545, loss: 0.00498613528907299 2023-01-23 20:03:14.941565: step: 208/1545, loss: 0.0007305189501494169 2023-01-23 20:03:15.822420: step: 210/1545, loss: 0.5121949911117554 2023-01-23 20:03:16.728597: step: 212/1545, loss: 0.04620392993092537 2023-01-23 20:03:17.600776: step: 214/1545, loss: 0.011665523052215576 2023-01-23 20:03:18.463824: step: 216/1545, loss: 0.0031584613025188446 2023-01-23 20:03:19.375071: step: 218/1545, loss: 0.26592105627059937 2023-01-23 20:03:20.245794: step: 220/1545, loss: 0.0016312990337610245 2023-01-23 20:03:21.106463: step: 222/1545, loss: 0.0005427075084298849 2023-01-23 20:03:22.019323: step: 224/1545, loss: 0.1285562962293625 2023-01-23 20:03:22.858095: step: 226/1545, loss: 0.022017130628228188 2023-01-23 20:03:23.747941: step: 228/1545, loss: 0.0016741823637858033 2023-01-23 20:03:24.582348: step: 230/1545, loss: 9.615778253646567e-05 2023-01-23 20:03:25.449943: step: 232/1545, loss: 0.004150284454226494 2023-01-23 20:03:26.363234: step: 234/1545, loss: 0.0013132040621712804 2023-01-23 20:03:27.206035: step: 236/1545, loss: 0.0009662265074439347 2023-01-23 20:03:28.041952: step: 238/1545, loss: 9.893022797768936e-05 2023-01-23 20:03:28.935679: step: 240/1545, loss: 0.019512318074703217 2023-01-23 20:03:29.819064: step: 242/1545, loss: 0.02060704678297043 2023-01-23 20:03:30.711806: step: 244/1545, loss: 0.00041319653973914683 2023-01-23 20:03:31.608158: step: 246/1545, loss: 0.00023964187130331993 2023-01-23 20:03:32.467293: step: 248/1545, loss: 0.00019628672453109175 2023-01-23 20:03:33.339711: step: 250/1545, loss: 5.934517685091123e-05 2023-01-23 20:03:34.244609: step: 252/1545, loss: 0.0006429559434764087 2023-01-23 20:03:35.101874: step: 254/1545, loss: 0.0001469455601181835 2023-01-23 20:03:36.002853: step: 256/1545, loss: 0.01329097431153059 2023-01-23 20:03:36.849929: step: 258/1545, loss: 0.0006598334875889122 2023-01-23 20:03:37.760653: step: 260/1545, loss: 0.00041394829167984426 2023-01-23 20:03:38.653963: step: 262/1545, loss: 0.00014148215996101499 2023-01-23 20:03:39.496196: step: 264/1545, loss: 0.0002457702357787639 2023-01-23 20:03:40.352060: step: 266/1545, loss: 0.010544407181441784 2023-01-23 20:03:41.240650: step: 268/1545, loss: 3.211199782526819e-06 2023-01-23 20:03:42.097430: step: 270/1545, loss: 0.000282419438008219 2023-01-23 20:03:42.950292: step: 272/1545, loss: 0.030188895761966705 2023-01-23 20:03:43.790216: step: 274/1545, loss: 2.6386967874714173e-05 2023-01-23 20:03:44.739483: step: 276/1545, loss: 0.3372021019458771 2023-01-23 20:03:45.607074: step: 278/1545, loss: 0.5157732963562012 2023-01-23 20:03:46.501038: step: 280/1545, loss: 0.024775013327598572 2023-01-23 20:03:47.386313: step: 282/1545, loss: 0.00015465515025425702 2023-01-23 20:03:48.307796: step: 284/1545, loss: 0.0010666128946468234 2023-01-23 20:03:49.209766: step: 286/1545, loss: 0.00013812385441269726 2023-01-23 20:03:50.075059: step: 288/1545, loss: 0.01036515086889267 2023-01-23 20:03:50.993326: step: 290/1545, loss: 0.0022774829994887114 2023-01-23 20:03:51.899980: step: 292/1545, loss: 0.04989054054021835 2023-01-23 20:03:52.809918: step: 294/1545, loss: 0.016334598883986473 2023-01-23 20:03:53.775221: step: 296/1545, loss: 0.0007500059437006712 2023-01-23 20:03:54.633310: step: 298/1545, loss: 0.0024775259662419558 2023-01-23 20:03:55.590979: step: 300/1545, loss: 0.00018692910089157522 2023-01-23 20:03:56.480188: step: 302/1545, loss: 0.0004477050679270178 2023-01-23 20:03:57.338381: step: 304/1545, loss: 0.06832356005907059 2023-01-23 20:03:58.217084: step: 306/1545, loss: 0.00021197648311499506 2023-01-23 20:03:59.099192: step: 308/1545, loss: 0.0004016431048512459 2023-01-23 20:04:00.006507: step: 310/1545, loss: 3.4013388358289376e-05 2023-01-23 20:04:00.884961: step: 312/1545, loss: 0.0019190857419744134 2023-01-23 20:04:01.731617: step: 314/1545, loss: 0.001532397698611021 2023-01-23 20:04:02.611230: step: 316/1545, loss: 9.106547804549336e-05 2023-01-23 20:04:03.477497: step: 318/1545, loss: 0.011311170645058155 2023-01-23 20:04:04.363922: step: 320/1545, loss: 5.997359039611183e-05 2023-01-23 20:04:05.260717: step: 322/1545, loss: 0.0004000542685389519 2023-01-23 20:04:06.133718: step: 324/1545, loss: 0.2400934100151062 2023-01-23 20:04:07.050302: step: 326/1545, loss: 7.394510612357408e-05 2023-01-23 20:04:07.879767: step: 328/1545, loss: 0.0035015465691685677 2023-01-23 20:04:08.714508: step: 330/1545, loss: 0.0017103083664551377 2023-01-23 20:04:09.583651: step: 332/1545, loss: 4.9239006330026314e-05 2023-01-23 20:04:10.419531: step: 334/1545, loss: 0.0008180950535461307 2023-01-23 20:04:11.271951: step: 336/1545, loss: 0.001607890473678708 2023-01-23 20:04:12.137404: step: 338/1545, loss: 9.699913789518178e-05 2023-01-23 20:04:13.010592: step: 340/1545, loss: 0.00041569353197701275 2023-01-23 20:04:13.867300: step: 342/1545, loss: 0.00046786328312009573 2023-01-23 20:04:14.710589: step: 344/1545, loss: 0.000177973517565988 2023-01-23 20:04:15.574778: step: 346/1545, loss: 0.0008121627033688128 2023-01-23 20:04:16.427439: step: 348/1545, loss: 0.10828506946563721 2023-01-23 20:04:17.286505: step: 350/1545, loss: 0.00019869148673024029 2023-01-23 20:04:18.199038: step: 352/1545, loss: 0.0006231826264411211 2023-01-23 20:04:19.033627: step: 354/1545, loss: 0.08570119738578796 2023-01-23 20:04:19.904411: step: 356/1545, loss: 0.0003279444354120642 2023-01-23 20:04:20.824135: step: 358/1545, loss: 0.0015931115485727787 2023-01-23 20:04:21.736225: step: 360/1545, loss: 6.650303839705884e-05 2023-01-23 20:04:22.604522: step: 362/1545, loss: 0.00011029593588318676 2023-01-23 20:04:23.472498: step: 364/1545, loss: 7.973809988470748e-05 2023-01-23 20:04:24.364672: step: 366/1545, loss: 0.002526454161852598 2023-01-23 20:04:25.240931: step: 368/1545, loss: 0.1841079145669937 2023-01-23 20:04:26.089535: step: 370/1545, loss: 0.0056726401671767235 2023-01-23 20:04:26.988041: step: 372/1545, loss: 0.0006118010496720672 2023-01-23 20:04:27.817379: step: 374/1545, loss: 3.2839656341820955e-05 2023-01-23 20:04:28.685532: step: 376/1545, loss: 0.03961930796504021 2023-01-23 20:04:29.544196: step: 378/1545, loss: 0.10377666354179382 2023-01-23 20:04:30.422338: step: 380/1545, loss: 0.00014524749713018537 2023-01-23 20:04:31.285021: step: 382/1545, loss: 6.119607132859528e-05 2023-01-23 20:04:32.166714: step: 384/1545, loss: 7.189971074694768e-05 2023-01-23 20:04:33.088467: step: 386/1545, loss: 0.002197566442191601 2023-01-23 20:04:33.974570: step: 388/1545, loss: 0.0006682653911411762 2023-01-23 20:04:34.876433: step: 390/1545, loss: 0.0003619746712502092 2023-01-23 20:04:35.722699: step: 392/1545, loss: 0.008638267405331135 2023-01-23 20:04:36.601082: step: 394/1545, loss: 0.0007546755368821323 2023-01-23 20:04:37.508364: step: 396/1545, loss: 0.06548044085502625 2023-01-23 20:04:38.356037: step: 398/1545, loss: 0.001268562744371593 2023-01-23 20:04:39.224362: step: 400/1545, loss: 0.03647772595286369 2023-01-23 20:04:40.118079: step: 402/1545, loss: 0.034481700509786606 2023-01-23 20:04:41.039350: step: 404/1545, loss: 0.0728832557797432 2023-01-23 20:04:41.891803: step: 406/1545, loss: 0.035214006900787354 2023-01-23 20:04:42.735149: step: 408/1545, loss: 0.00035991676850244403 2023-01-23 20:04:43.583516: step: 410/1545, loss: 0.0005832249880768359 2023-01-23 20:04:44.444409: step: 412/1545, loss: 0.00020980180124752223 2023-01-23 20:04:45.320462: step: 414/1545, loss: 5.591676745098084e-05 2023-01-23 20:04:46.179718: step: 416/1545, loss: 0.0010817397851496935 2023-01-23 20:04:47.097242: step: 418/1545, loss: 5.5012023949529976e-05 2023-01-23 20:04:47.951792: step: 420/1545, loss: 0.00011836179328383878 2023-01-23 20:04:48.793458: step: 422/1545, loss: 0.014433378353714943 2023-01-23 20:04:49.653802: step: 424/1545, loss: 0.005258756224066019 2023-01-23 20:04:50.542841: step: 426/1545, loss: 1.1564542546693701e-05 2023-01-23 20:04:51.418085: step: 428/1545, loss: 0.03157864511013031 2023-01-23 20:04:52.302772: step: 430/1545, loss: 0.0003649264690466225 2023-01-23 20:04:53.149109: step: 432/1545, loss: 0.00037987728137522936 2023-01-23 20:04:54.019778: step: 434/1545, loss: 0.00027949624927714467 2023-01-23 20:04:54.936951: step: 436/1545, loss: 0.0001638660760363564 2023-01-23 20:04:55.812463: step: 438/1545, loss: 0.0953642800450325 2023-01-23 20:04:56.666607: step: 440/1545, loss: 0.02688840590417385 2023-01-23 20:04:57.570512: step: 442/1545, loss: 0.0007512712036259472 2023-01-23 20:04:58.451982: step: 444/1545, loss: 0.0002604499168228358 2023-01-23 20:04:59.341332: step: 446/1545, loss: 0.021525828167796135 2023-01-23 20:05:00.246540: step: 448/1545, loss: 0.0027600897010415792 2023-01-23 20:05:01.116147: step: 450/1545, loss: 0.0014682383043691516 2023-01-23 20:05:01.990836: step: 452/1545, loss: 0.00024452610523439944 2023-01-23 20:05:02.857376: step: 454/1545, loss: 0.08051183819770813 2023-01-23 20:05:03.714171: step: 456/1545, loss: 0.0015739774098619819 2023-01-23 20:05:04.714576: step: 458/1545, loss: 0.007117576897144318 2023-01-23 20:05:05.567279: step: 460/1545, loss: 0.0005058862152509391 2023-01-23 20:05:06.434994: step: 462/1545, loss: 0.07508574426174164 2023-01-23 20:05:07.336175: step: 464/1545, loss: 3.220209327992052e-05 2023-01-23 20:05:08.190555: step: 466/1545, loss: 0.017102854326367378 2023-01-23 20:05:09.038089: step: 468/1545, loss: 6.48567802272737e-05 2023-01-23 20:05:09.940403: step: 470/1545, loss: 0.40904954075813293 2023-01-23 20:05:10.938076: step: 472/1545, loss: 0.012362383306026459 2023-01-23 20:05:11.914149: step: 474/1545, loss: 0.0008210990927182138 2023-01-23 20:05:12.798619: step: 476/1545, loss: 0.00011545206507435068 2023-01-23 20:05:13.648488: step: 478/1545, loss: 7.640865806024522e-05 2023-01-23 20:05:14.552243: step: 480/1545, loss: 0.607231080532074 2023-01-23 20:05:15.407479: step: 482/1545, loss: 2.7427764507592656e-05 2023-01-23 20:05:16.284951: step: 484/1545, loss: 0.0390678271651268 2023-01-23 20:05:17.238513: step: 486/1545, loss: 6.12558433203958e-05 2023-01-23 20:05:18.136604: step: 488/1545, loss: 9.940654126694426e-05 2023-01-23 20:05:19.023930: step: 490/1545, loss: 0.00017601801664568484 2023-01-23 20:05:19.892116: step: 492/1545, loss: 0.0013457507593557239 2023-01-23 20:05:20.781382: step: 494/1545, loss: 0.04939964786171913 2023-01-23 20:05:21.632000: step: 496/1545, loss: -2.8028525775880553e-05 2023-01-23 20:05:22.481164: step: 498/1545, loss: 0.00908911507576704 2023-01-23 20:05:23.353047: step: 500/1545, loss: 0.0004216934321448207 2023-01-23 20:05:24.234444: step: 502/1545, loss: 0.0012377952225506306 2023-01-23 20:05:25.082885: step: 504/1545, loss: 0.004516461864113808 2023-01-23 20:05:26.016873: step: 506/1545, loss: 0.022546442225575447 2023-01-23 20:05:26.885346: step: 508/1545, loss: 0.0010965403635054827 2023-01-23 20:05:27.833842: step: 510/1545, loss: 0.00040978568722493947 2023-01-23 20:05:28.699293: step: 512/1545, loss: 0.0004863448557443917 2023-01-23 20:05:29.567578: step: 514/1545, loss: 0.0003527661319822073 2023-01-23 20:05:30.411897: step: 516/1545, loss: 0.0001760393352014944 2023-01-23 20:05:31.314811: step: 518/1545, loss: 0.00014961458509787917 2023-01-23 20:05:32.153425: step: 520/1545, loss: 0.0002545401221141219 2023-01-23 20:05:33.044175: step: 522/1545, loss: 0.0004913884913548827 2023-01-23 20:05:33.906397: step: 524/1545, loss: 0.016783425584435463 2023-01-23 20:05:34.769614: step: 526/1545, loss: 0.008396027609705925 2023-01-23 20:05:35.611619: step: 528/1545, loss: 5.0830840336857364e-05 2023-01-23 20:05:36.494948: step: 530/1545, loss: 0.003553772112354636 2023-01-23 20:05:37.376612: step: 532/1545, loss: 0.013959420844912529 2023-01-23 20:05:38.305074: step: 534/1545, loss: 0.00038920881343074143 2023-01-23 20:05:39.156748: step: 536/1545, loss: 0.00014400632062461227 2023-01-23 20:05:40.048735: step: 538/1545, loss: 0.0016557594062760472 2023-01-23 20:05:40.916838: step: 540/1545, loss: 7.594905582664069e-06 2023-01-23 20:05:41.762647: step: 542/1545, loss: 0.00042042118730023503 2023-01-23 20:05:42.714304: step: 544/1545, loss: 4.885216912953183e-05 2023-01-23 20:05:43.600577: step: 546/1545, loss: 0.26712557673454285 2023-01-23 20:05:44.494177: step: 548/1545, loss: 0.0001005389349302277 2023-01-23 20:05:45.359217: step: 550/1545, loss: 0.12467099726200104 2023-01-23 20:05:46.260190: step: 552/1545, loss: 8.876121682988014e-06 2023-01-23 20:05:47.137114: step: 554/1545, loss: 0.0004972035530954599 2023-01-23 20:05:48.082070: step: 556/1545, loss: 0.08481977880001068 2023-01-23 20:05:49.009880: step: 558/1545, loss: 1.4731629562447779e-05 2023-01-23 20:05:49.926824: step: 560/1545, loss: 0.05978862941265106 2023-01-23 20:05:50.804527: step: 562/1545, loss: 0.0002778118650894612 2023-01-23 20:05:51.699860: step: 564/1545, loss: 0.032763414084911346 2023-01-23 20:05:52.562185: step: 566/1545, loss: 0.22047783434391022 2023-01-23 20:05:53.432453: step: 568/1545, loss: 0.00013995195331517607 2023-01-23 20:05:54.304609: step: 570/1545, loss: 0.00036325756809674203 2023-01-23 20:05:55.170406: step: 572/1545, loss: 0.0019222336122766137 2023-01-23 20:05:56.064296: step: 574/1545, loss: 8.69168434292078e-05 2023-01-23 20:05:57.001891: step: 576/1545, loss: 0.000129169988213107 2023-01-23 20:05:57.887224: step: 578/1545, loss: 0.13608521223068237 2023-01-23 20:05:58.812975: step: 580/1545, loss: 0.055453162640333176 2023-01-23 20:05:59.732771: step: 582/1545, loss: 0.0008698076126165688 2023-01-23 20:06:00.610588: step: 584/1545, loss: 0.2090594619512558 2023-01-23 20:06:01.528649: step: 586/1545, loss: 0.01234931405633688 2023-01-23 20:06:02.407385: step: 588/1545, loss: 0.001602989505045116 2023-01-23 20:06:03.258200: step: 590/1545, loss: 0.011463671922683716 2023-01-23 20:06:04.101263: step: 592/1545, loss: 9.886675252346322e-05 2023-01-23 20:06:04.985515: step: 594/1545, loss: 0.00042520996066741645 2023-01-23 20:06:05.861859: step: 596/1545, loss: 0.23541949689388275 2023-01-23 20:06:06.767030: step: 598/1545, loss: 0.000902318861335516 2023-01-23 20:06:07.605953: step: 600/1545, loss: 0.1366429328918457 2023-01-23 20:06:08.455791: step: 602/1545, loss: 0.00044788417289964855 2023-01-23 20:06:09.282786: step: 604/1545, loss: 0.06901779770851135 2023-01-23 20:06:10.187913: step: 606/1545, loss: 0.0004523652314674109 2023-01-23 20:06:11.082841: step: 608/1545, loss: 0.049295976758003235 2023-01-23 20:06:11.939146: step: 610/1545, loss: 0.00043749084579758346 2023-01-23 20:06:12.857604: step: 612/1545, loss: 0.0002609780931379646 2023-01-23 20:06:13.691012: step: 614/1545, loss: 0.004191823303699493 2023-01-23 20:06:14.563678: step: 616/1545, loss: 0.1175801008939743 2023-01-23 20:06:15.512043: step: 618/1545, loss: 0.00784276518970728 2023-01-23 20:06:16.350760: step: 620/1545, loss: 0.007181293796747923 2023-01-23 20:06:17.212801: step: 622/1545, loss: 0.1425677239894867 2023-01-23 20:06:18.086085: step: 624/1545, loss: 0.00399304274469614 2023-01-23 20:06:18.967877: step: 626/1545, loss: 0.00032108600134961307 2023-01-23 20:06:19.849721: step: 628/1545, loss: 2.2315478418022394e-05 2023-01-23 20:06:20.728239: step: 630/1545, loss: 0.0029416207689791918 2023-01-23 20:06:21.615098: step: 632/1545, loss: 0.0013982406817376614 2023-01-23 20:06:22.537567: step: 634/1545, loss: 0.006375678814947605 2023-01-23 20:06:23.396971: step: 636/1545, loss: 0.0007885042577981949 2023-01-23 20:06:24.272603: step: 638/1545, loss: 0.08513995260000229 2023-01-23 20:06:25.149716: step: 640/1545, loss: 0.00034572044387459755 2023-01-23 20:06:26.046876: step: 642/1545, loss: 0.07259763032197952 2023-01-23 20:06:26.909294: step: 644/1545, loss: 0.1333780288696289 2023-01-23 20:06:27.756918: step: 646/1545, loss: 5.6949156714836136e-05 2023-01-23 20:06:28.619446: step: 648/1545, loss: 5.2929437515558675e-05 2023-01-23 20:06:29.447468: step: 650/1545, loss: 2.472249798302073e-05 2023-01-23 20:06:30.317767: step: 652/1545, loss: 0.06035889312624931 2023-01-23 20:06:31.159955: step: 654/1545, loss: 0.0015462993178516626 2023-01-23 20:06:32.040047: step: 656/1545, loss: 0.00023618637351319194 2023-01-23 20:06:32.929661: step: 658/1545, loss: 0.0009389388142153621 2023-01-23 20:06:33.786041: step: 660/1545, loss: 4.93533443659544e-05 2023-01-23 20:06:34.653591: step: 662/1545, loss: 0.0012551038525998592 2023-01-23 20:06:35.576667: step: 664/1545, loss: 0.0005597317940555513 2023-01-23 20:06:36.441144: step: 666/1545, loss: 0.0064475941471755505 2023-01-23 20:06:37.283770: step: 668/1545, loss: 0.0001298174902331084 2023-01-23 20:06:38.200175: step: 670/1545, loss: 0.8725444674491882 2023-01-23 20:06:39.041638: step: 672/1545, loss: 0.008313055150210857 2023-01-23 20:06:39.955121: step: 674/1545, loss: 0.00017000685329549015 2023-01-23 20:06:40.823015: step: 676/1545, loss: 0.00035267372732050717 2023-01-23 20:06:41.690780: step: 678/1545, loss: 0.016814280301332474 2023-01-23 20:06:42.517978: step: 680/1545, loss: 0.01723664440214634 2023-01-23 20:06:43.381071: step: 682/1545, loss: 0.08359652012586594 2023-01-23 20:06:44.205415: step: 684/1545, loss: 0.024320008233189583 2023-01-23 20:06:45.078941: step: 686/1545, loss: 0.0009282408864237368 2023-01-23 20:06:45.985672: step: 688/1545, loss: 0.006858011242002249 2023-01-23 20:06:46.920824: step: 690/1545, loss: 0.03180455416440964 2023-01-23 20:06:47.799383: step: 692/1545, loss: 8.747413085075095e-05 2023-01-23 20:06:48.644310: step: 694/1545, loss: 0.19887188076972961 2023-01-23 20:06:49.546565: step: 696/1545, loss: 0.0001572158362250775 2023-01-23 20:06:50.420162: step: 698/1545, loss: 0.001601463183760643 2023-01-23 20:06:51.299285: step: 700/1545, loss: 0.002260409062728286 2023-01-23 20:06:52.143794: step: 702/1545, loss: 0.011879157274961472 2023-01-23 20:06:53.089814: step: 704/1545, loss: 0.06222700700163841 2023-01-23 20:06:54.015619: step: 706/1545, loss: 0.05641528591513634 2023-01-23 20:06:54.919590: step: 708/1545, loss: 0.0005477574304677546 2023-01-23 20:06:55.806725: step: 710/1545, loss: 0.09807439148426056 2023-01-23 20:06:56.670562: step: 712/1545, loss: 7.800657476764172e-05 2023-01-23 20:06:57.554012: step: 714/1545, loss: 0.013149728067219257 2023-01-23 20:06:58.457050: step: 716/1545, loss: 0.0012774420902132988 2023-01-23 20:06:59.439343: step: 718/1545, loss: 0.004452837165445089 2023-01-23 20:07:00.323488: step: 720/1545, loss: 5.0373248086543754e-05 2023-01-23 20:07:01.210131: step: 722/1545, loss: 0.008291742764413357 2023-01-23 20:07:02.105405: step: 724/1545, loss: 0.00013002383639104664 2023-01-23 20:07:02.938153: step: 726/1545, loss: 0.07149878889322281 2023-01-23 20:07:03.845586: step: 728/1545, loss: 0.00507701700553298 2023-01-23 20:07:04.826038: step: 730/1545, loss: 0.011768843978643417 2023-01-23 20:07:05.716622: step: 732/1545, loss: 0.06988359242677689 2023-01-23 20:07:06.594858: step: 734/1545, loss: 0.00048575428081676364 2023-01-23 20:07:07.489159: step: 736/1545, loss: 0.016243787482380867 2023-01-23 20:07:08.347616: step: 738/1545, loss: 0.0024004848673939705 2023-01-23 20:07:09.186054: step: 740/1545, loss: 7.953734893817455e-06 2023-01-23 20:07:10.042841: step: 742/1545, loss: 0.00012940264423377812 2023-01-23 20:07:10.917025: step: 744/1545, loss: 0.0007761348970234394 2023-01-23 20:07:11.778597: step: 746/1545, loss: 9.753539052326232e-05 2023-01-23 20:07:12.643037: step: 748/1545, loss: 0.00216531939804554 2023-01-23 20:07:13.482437: step: 750/1545, loss: 0.0010480850469321012 2023-01-23 20:07:14.374430: step: 752/1545, loss: 0.0695146843791008 2023-01-23 20:07:15.261176: step: 754/1545, loss: 0.00020141720597166568 2023-01-23 20:07:16.133945: step: 756/1545, loss: 3.929432295990409e-06 2023-01-23 20:07:16.995406: step: 758/1545, loss: 6.404057785402983e-05 2023-01-23 20:07:17.865351: step: 760/1545, loss: 0.025804290547966957 2023-01-23 20:07:18.749140: step: 762/1545, loss: 3.8785237848060206e-05 2023-01-23 20:07:19.647071: step: 764/1545, loss: 0.0010907386895269156 2023-01-23 20:07:20.531902: step: 766/1545, loss: 0.0068196807987987995 2023-01-23 20:07:21.396082: step: 768/1545, loss: 0.0008626312483102083 2023-01-23 20:07:22.290252: step: 770/1545, loss: 0.011793152429163456 2023-01-23 20:07:23.168776: step: 772/1545, loss: 0.19428697228431702 2023-01-23 20:07:24.054628: step: 774/1545, loss: 0.14521589875221252 2023-01-23 20:07:24.971794: step: 776/1545, loss: 0.005373302847146988 2023-01-23 20:07:25.890210: step: 778/1545, loss: 0.0013025514781475067 2023-01-23 20:07:26.792803: step: 780/1545, loss: 0.0029580367263406515 2023-01-23 20:07:27.631446: step: 782/1545, loss: 0.00011244229972362518 2023-01-23 20:07:28.503345: step: 784/1545, loss: 0.046074964106082916 2023-01-23 20:07:29.345456: step: 786/1545, loss: 0.001406767638400197 2023-01-23 20:07:30.248247: step: 788/1545, loss: 0.02171947807073593 2023-01-23 20:07:31.101138: step: 790/1545, loss: 0.15169468522071838 2023-01-23 20:07:31.926414: step: 792/1545, loss: 0.00023408296692650765 2023-01-23 20:07:32.783023: step: 794/1545, loss: 0.0006668756250292063 2023-01-23 20:07:33.709539: step: 796/1545, loss: 0.004606199450790882 2023-01-23 20:07:34.573865: step: 798/1545, loss: 0.0006060018786229193 2023-01-23 20:07:35.462371: step: 800/1545, loss: 0.07534074783325195 2023-01-23 20:07:36.350113: step: 802/1545, loss: 0.00022317130060400814 2023-01-23 20:07:37.211240: step: 804/1545, loss: 0.0025469129905104637 2023-01-23 20:07:38.140361: step: 806/1545, loss: 5.377082743507344e-06 2023-01-23 20:07:39.038117: step: 808/1545, loss: 0.0007207301096059382 2023-01-23 20:07:39.915205: step: 810/1545, loss: 0.0013890528352931142 2023-01-23 20:07:40.767343: step: 812/1545, loss: 0.010539652779698372 2023-01-23 20:07:41.662271: step: 814/1545, loss: 0.029241757467389107 2023-01-23 20:07:42.575878: step: 816/1545, loss: 0.0007340512238442898 2023-01-23 20:07:43.507677: step: 818/1545, loss: 4.6679262595716864e-05 2023-01-23 20:07:44.398448: step: 820/1545, loss: 0.00043740065302699804 2023-01-23 20:07:45.283489: step: 822/1545, loss: 0.0009675536421127617 2023-01-23 20:07:46.209137: step: 824/1545, loss: 0.03870776668190956 2023-01-23 20:07:47.082187: step: 826/1545, loss: 0.0003757459344342351 2023-01-23 20:07:48.015725: step: 828/1545, loss: 0.0018397162202745676 2023-01-23 20:07:48.890034: step: 830/1545, loss: 0.0004878409090451896 2023-01-23 20:07:49.733531: step: 832/1545, loss: 8.433115726802498e-05 2023-01-23 20:07:50.647361: step: 834/1545, loss: 5.0855232984758914e-05 2023-01-23 20:07:51.539863: step: 836/1545, loss: 0.025577474385499954 2023-01-23 20:07:52.416744: step: 838/1545, loss: 0.03312232345342636 2023-01-23 20:07:53.272201: step: 840/1545, loss: 0.00016391798271797597 2023-01-23 20:07:54.177910: step: 842/1545, loss: 0.0007499842904508114 2023-01-23 20:07:55.024781: step: 844/1545, loss: 3.869235297315754e-05 2023-01-23 20:07:55.902194: step: 846/1545, loss: 0.00031175315962173045 2023-01-23 20:07:56.853771: step: 848/1545, loss: 2.7721216611098498e-05 2023-01-23 20:07:57.739149: step: 850/1545, loss: 0.0006349952891469002 2023-01-23 20:07:58.648047: step: 852/1545, loss: 0.028512226417660713 2023-01-23 20:07:59.494798: step: 854/1545, loss: 0.12043039500713348 2023-01-23 20:08:00.374009: step: 856/1545, loss: 0.005973142571747303 2023-01-23 20:08:01.275284: step: 858/1545, loss: 0.2111523151397705 2023-01-23 20:08:02.176647: step: 860/1545, loss: 0.02191278524696827 2023-01-23 20:08:03.091062: step: 862/1545, loss: 0.000942935817874968 2023-01-23 20:08:03.996249: step: 864/1545, loss: 0.010588969103991985 2023-01-23 20:08:04.907622: step: 866/1545, loss: 7.833751442376524e-05 2023-01-23 20:08:05.791079: step: 868/1545, loss: 0.017440762370824814 2023-01-23 20:08:06.694708: step: 870/1545, loss: 0.11900760978460312 2023-01-23 20:08:07.585165: step: 872/1545, loss: 0.03217737749218941 2023-01-23 20:08:08.431152: step: 874/1545, loss: 8.381693623960018e-05 2023-01-23 20:08:09.291166: step: 876/1545, loss: 0.00838104635477066 2023-01-23 20:08:10.162744: step: 878/1545, loss: 1.893818989628926e-05 2023-01-23 20:08:11.014973: step: 880/1545, loss: 2.6710629754234105e-05 2023-01-23 20:08:11.948115: step: 882/1545, loss: 0.007604279089719057 2023-01-23 20:08:12.870665: step: 884/1545, loss: 0.00011152925435453653 2023-01-23 20:08:13.741328: step: 886/1545, loss: 0.0537983775138855 2023-01-23 20:08:14.605410: step: 888/1545, loss: 0.00010528713755775243 2023-01-23 20:08:15.467381: step: 890/1545, loss: 5.024880010751076e-05 2023-01-23 20:08:16.351115: step: 892/1545, loss: 3.620785355451517e-05 2023-01-23 20:08:17.210627: step: 894/1545, loss: 0.07308943569660187 2023-01-23 20:08:18.077403: step: 896/1545, loss: 0.011204931885004044 2023-01-23 20:08:19.018477: step: 898/1545, loss: 0.19699543714523315 2023-01-23 20:08:19.862800: step: 900/1545, loss: -7.98523524281336e-06 2023-01-23 20:08:20.750834: step: 902/1545, loss: 0.02436397783458233 2023-01-23 20:08:21.614600: step: 904/1545, loss: 0.08261970430612564 2023-01-23 20:08:22.530788: step: 906/1545, loss: 0.010390741750597954 2023-01-23 20:08:23.422506: step: 908/1545, loss: 0.0005501184496097267 2023-01-23 20:08:24.358766: step: 910/1545, loss: 0.005673907697200775 2023-01-23 20:08:25.179827: step: 912/1545, loss: 3.438434941926971e-05 2023-01-23 20:08:26.046390: step: 914/1545, loss: 0.001744242268614471 2023-01-23 20:08:26.929908: step: 916/1545, loss: 0.05524377524852753 2023-01-23 20:08:27.777649: step: 918/1545, loss: 0.6367141604423523 2023-01-23 20:08:28.627963: step: 920/1545, loss: 5.228221561992541e-05 2023-01-23 20:08:29.560701: step: 922/1545, loss: 0.00015037579578347504 2023-01-23 20:08:30.444152: step: 924/1545, loss: 0.021606096997857094 2023-01-23 20:08:31.336404: step: 926/1545, loss: 0.0004186744918115437 2023-01-23 20:08:32.181372: step: 928/1545, loss: 7.180530519690365e-05 2023-01-23 20:08:33.023621: step: 930/1545, loss: 0.002080024452880025 2023-01-23 20:08:33.952612: step: 932/1545, loss: 0.0016225671861320734 2023-01-23 20:08:34.828100: step: 934/1545, loss: 0.000146682548802346 2023-01-23 20:08:35.712465: step: 936/1545, loss: 0.11387594789266586 2023-01-23 20:08:36.578268: step: 938/1545, loss: 0.0011132352519780397 2023-01-23 20:08:37.421216: step: 940/1545, loss: 0.01156158559024334 2023-01-23 20:08:38.299220: step: 942/1545, loss: 0.09069798141717911 2023-01-23 20:08:39.199010: step: 944/1545, loss: 0.13406094908714294 2023-01-23 20:08:40.046296: step: 946/1545, loss: 0.0002605885383673012 2023-01-23 20:08:40.897414: step: 948/1545, loss: 0.029883429408073425 2023-01-23 20:08:41.751403: step: 950/1545, loss: 9.036857954924926e-05 2023-01-23 20:08:42.618656: step: 952/1545, loss: 3.629219645517878e-05 2023-01-23 20:08:43.489012: step: 954/1545, loss: 0.00046898022992536426 2023-01-23 20:08:44.337973: step: 956/1545, loss: -2.0135061276960187e-05 2023-01-23 20:08:45.224342: step: 958/1545, loss: 0.00025961120263673365 2023-01-23 20:08:46.114094: step: 960/1545, loss: 0.06750521808862686 2023-01-23 20:08:46.988677: step: 962/1545, loss: 0.000233607497648336 2023-01-23 20:08:47.880114: step: 964/1545, loss: 0.020662885159254074 2023-01-23 20:08:48.832093: step: 966/1545, loss: 0.12302906811237335 2023-01-23 20:08:49.696723: step: 968/1545, loss: 6.2674280343344435e-06 2023-01-23 20:08:50.548201: step: 970/1545, loss: 0.002118108095601201 2023-01-23 20:08:51.447448: step: 972/1545, loss: -6.728860171278939e-05 2023-01-23 20:08:52.365634: step: 974/1545, loss: 0.0019745007157325745 2023-01-23 20:08:53.235444: step: 976/1545, loss: 0.002423099707812071 2023-01-23 20:08:54.095113: step: 978/1545, loss: 0.0040757181122899055 2023-01-23 20:08:54.996558: step: 980/1545, loss: -2.3240914742927998e-05 2023-01-23 20:08:55.853765: step: 982/1545, loss: 0.07255683094263077 2023-01-23 20:08:56.755533: step: 984/1545, loss: 0.006688093766570091 2023-01-23 20:08:57.625722: step: 986/1545, loss: 0.0014172762166708708 2023-01-23 20:08:58.487761: step: 988/1545, loss: 1.6147891074069776e-05 2023-01-23 20:08:59.385088: step: 990/1545, loss: 7.245465531013906e-05 2023-01-23 20:09:00.256075: step: 992/1545, loss: 0.00110283971298486 2023-01-23 20:09:01.219008: step: 994/1545, loss: 9.575039439368993e-05 2023-01-23 20:09:02.075035: step: 996/1545, loss: 5.092618812341243e-05 2023-01-23 20:09:02.903725: step: 998/1545, loss: 2.3225943550642114e-06 2023-01-23 20:09:03.777456: step: 1000/1545, loss: 0.0004257328109815717 2023-01-23 20:09:04.768952: step: 1002/1545, loss: 0.011585722677409649 2023-01-23 20:09:05.651142: step: 1004/1545, loss: 0.1354466676712036 2023-01-23 20:09:06.529687: step: 1006/1545, loss: 0.14209724962711334 2023-01-23 20:09:07.482617: step: 1008/1545, loss: 0.15265710651874542 2023-01-23 20:09:08.341760: step: 1010/1545, loss: 0.19060803949832916 2023-01-23 20:09:09.223246: step: 1012/1545, loss: 0.2149529606103897 2023-01-23 20:09:10.056425: step: 1014/1545, loss: 0.01220360305160284 2023-01-23 20:09:10.888298: step: 1016/1545, loss: 0.00018776545766741037 2023-01-23 20:09:11.736107: step: 1018/1545, loss: 3.077982910326682e-05 2023-01-23 20:09:12.563412: step: 1020/1545, loss: 0.006157150026410818 2023-01-23 20:09:13.492531: step: 1022/1545, loss: 0.009931011125445366 2023-01-23 20:09:14.426472: step: 1024/1545, loss: 0.1480419784784317 2023-01-23 20:09:15.287792: step: 1026/1545, loss: 0.00014340082998387516 2023-01-23 20:09:16.158997: step: 1028/1545, loss: 0.00010893880244111642 2023-01-23 20:09:17.055901: step: 1030/1545, loss: 0.0014386317925527692 2023-01-23 20:09:17.949844: step: 1032/1545, loss: 0.07309245318174362 2023-01-23 20:09:18.807327: step: 1034/1545, loss: 0.22616370022296906 2023-01-23 20:09:19.723876: step: 1036/1545, loss: 7.575157360406592e-05 2023-01-23 20:09:20.644287: step: 1038/1545, loss: 0.020455943420529366 2023-01-23 20:09:21.494143: step: 1040/1545, loss: 6.826013122918084e-05 2023-01-23 20:09:22.348404: step: 1042/1545, loss: 0.0020936112850904465 2023-01-23 20:09:23.233663: step: 1044/1545, loss: 8.07841497589834e-05 2023-01-23 20:09:24.099217: step: 1046/1545, loss: 0.18749591708183289 2023-01-23 20:09:24.999109: step: 1048/1545, loss: 0.0004353497934062034 2023-01-23 20:09:25.872260: step: 1050/1545, loss: 0.00022334829554893076 2023-01-23 20:09:26.722463: step: 1052/1545, loss: 0.10111012309789658 2023-01-23 20:09:27.591634: step: 1054/1545, loss: 0.019588980823755264 2023-01-23 20:09:28.444427: step: 1056/1545, loss: 0.0003546941152308136 2023-01-23 20:09:29.304230: step: 1058/1545, loss: 0.0025913540739566088 2023-01-23 20:09:30.166459: step: 1060/1545, loss: 0.00274201319552958 2023-01-23 20:09:31.077797: step: 1062/1545, loss: 0.11379839479923248 2023-01-23 20:09:31.949892: step: 1064/1545, loss: 0.05924900993704796 2023-01-23 20:09:32.791887: step: 1066/1545, loss: 0.005211370997130871 2023-01-23 20:09:33.643325: step: 1068/1545, loss: 0.0513908714056015 2023-01-23 20:09:34.504046: step: 1070/1545, loss: 5.091845378046855e-05 2023-01-23 20:09:35.376256: step: 1072/1545, loss: 0.14663150906562805 2023-01-23 20:09:36.201241: step: 1074/1545, loss: 0.0004442268400453031 2023-01-23 20:09:37.115721: step: 1076/1545, loss: 0.029067620635032654 2023-01-23 20:09:37.954877: step: 1078/1545, loss: 0.005571929272264242 2023-01-23 20:09:38.972340: step: 1080/1545, loss: 0.046137936413288116 2023-01-23 20:09:39.883859: step: 1082/1545, loss: 0.00036699051270261407 2023-01-23 20:09:40.722238: step: 1084/1545, loss: 0.00048237634473480284 2023-01-23 20:09:41.571442: step: 1086/1545, loss: 0.1694236844778061 2023-01-23 20:09:42.421568: step: 1088/1545, loss: 0.01139860413968563 2023-01-23 20:09:43.288105: step: 1090/1545, loss: 0.1851339191198349 2023-01-23 20:09:44.200852: step: 1092/1545, loss: 0.02796100825071335 2023-01-23 20:09:45.072276: step: 1094/1545, loss: 0.0631253570318222 2023-01-23 20:09:45.967007: step: 1096/1545, loss: 0.09510556608438492 2023-01-23 20:09:46.833637: step: 1098/1545, loss: 0.20208866894245148 2023-01-23 20:09:47.682980: step: 1100/1545, loss: 0.0005765723180957139 2023-01-23 20:09:48.533559: step: 1102/1545, loss: 0.004896634258329868 2023-01-23 20:09:49.382038: step: 1104/1545, loss: 0.2885374426841736 2023-01-23 20:09:50.205400: step: 1106/1545, loss: 0.00011514524521771818 2023-01-23 20:09:51.040655: step: 1108/1545, loss: -1.4886367353028618e-05 2023-01-23 20:09:51.897258: step: 1110/1545, loss: 0.032054029405117035 2023-01-23 20:09:52.770810: step: 1112/1545, loss: 0.09141414612531662 2023-01-23 20:09:53.652693: step: 1114/1545, loss: 0.13940341770648956 2023-01-23 20:09:54.497737: step: 1116/1545, loss: 0.00013229477917775512 2023-01-23 20:09:55.330350: step: 1118/1545, loss: 0.012139273807406425 2023-01-23 20:09:56.225079: step: 1120/1545, loss: 0.000318195263389498 2023-01-23 20:09:57.116103: step: 1122/1545, loss: 0.39199572801589966 2023-01-23 20:09:57.971523: step: 1124/1545, loss: 0.001189052127301693 2023-01-23 20:09:58.900069: step: 1126/1545, loss: 0.0017305026995018125 2023-01-23 20:09:59.733583: step: 1128/1545, loss: 0.5078719854354858 2023-01-23 20:10:00.570366: step: 1130/1545, loss: 0.0020254398696124554 2023-01-23 20:10:01.464776: step: 1132/1545, loss: 0.0064596752636134624 2023-01-23 20:10:02.374455: step: 1134/1545, loss: 0.06451892107725143 2023-01-23 20:10:03.233574: step: 1136/1545, loss: 0.00020239590958226472 2023-01-23 20:10:04.118139: step: 1138/1545, loss: 0.0016972552984952927 2023-01-23 20:10:05.008184: step: 1140/1545, loss: 0.3194778263568878 2023-01-23 20:10:05.863277: step: 1142/1545, loss: 0.0009103846969082952 2023-01-23 20:10:06.706410: step: 1144/1545, loss: 0.0008773389854468405 2023-01-23 20:10:07.594983: step: 1146/1545, loss: 0.26986390352249146 2023-01-23 20:10:08.477194: step: 1148/1545, loss: 0.0010131405433639884 2023-01-23 20:10:09.303632: step: 1150/1545, loss: 0.014017244800925255 2023-01-23 20:10:10.177951: step: 1152/1545, loss: 0.014077216386795044 2023-01-23 20:10:11.014177: step: 1154/1545, loss: 1.735087607812602e-05 2023-01-23 20:10:11.948014: step: 1156/1545, loss: 0.00037265571882016957 2023-01-23 20:10:12.811421: step: 1158/1545, loss: 0.010997338220477104 2023-01-23 20:10:13.696722: step: 1160/1545, loss: 1.363376941299066e-05 2023-01-23 20:10:14.577258: step: 1162/1545, loss: 0.11612386256456375 2023-01-23 20:10:15.449712: step: 1164/1545, loss: 0.00014292706327978522 2023-01-23 20:10:16.330851: step: 1166/1545, loss: 0.0013513440499082208 2023-01-23 20:10:17.201119: step: 1168/1545, loss: 0.0035984832793474197 2023-01-23 20:10:18.065575: step: 1170/1545, loss: 0.03145989775657654 2023-01-23 20:10:18.966462: step: 1172/1545, loss: 0.023874692618846893 2023-01-23 20:10:19.798087: step: 1174/1545, loss: 0.008345786482095718 2023-01-23 20:10:20.687093: step: 1176/1545, loss: 0.0003722080437000841 2023-01-23 20:10:21.515852: step: 1178/1545, loss: 0.0002871716860681772 2023-01-23 20:10:22.400582: step: 1180/1545, loss: 0.001782772014848888 2023-01-23 20:10:23.305216: step: 1182/1545, loss: 0.01788976788520813 2023-01-23 20:10:24.204290: step: 1184/1545, loss: 0.3111303448677063 2023-01-23 20:10:25.049819: step: 1186/1545, loss: 3.9668386307312176e-05 2023-01-23 20:10:25.899682: step: 1188/1545, loss: 0.0001782188774086535 2023-01-23 20:10:26.754136: step: 1190/1545, loss: 0.0004497890477068722 2023-01-23 20:10:27.574790: step: 1192/1545, loss: 3.9303387893596664e-05 2023-01-23 20:10:28.478104: step: 1194/1545, loss: 0.00033607822842895985 2023-01-23 20:10:29.335627: step: 1196/1545, loss: -1.7435635527363047e-05 2023-01-23 20:10:30.229755: step: 1198/1545, loss: 0.19031472504138947 2023-01-23 20:10:31.073496: step: 1200/1545, loss: 0.00010290015779901296 2023-01-23 20:10:31.961023: step: 1202/1545, loss: 0.02885754592716694 2023-01-23 20:10:32.832902: step: 1204/1545, loss: 0.00012799003161489964 2023-01-23 20:10:33.666057: step: 1206/1545, loss: 0.08132173866033554 2023-01-23 20:10:34.560936: step: 1208/1545, loss: 0.001996224746108055 2023-01-23 20:10:35.455573: step: 1210/1545, loss: 2.8617381758522242e-05 2023-01-23 20:10:36.339003: step: 1212/1545, loss: 0.28992173075675964 2023-01-23 20:10:37.181256: step: 1214/1545, loss: 0.12946972250938416 2023-01-23 20:10:38.088936: step: 1216/1545, loss: 9.144743671640754e-05 2023-01-23 20:10:38.994333: step: 1218/1545, loss: 7.177190127549693e-05 2023-01-23 20:10:39.871796: step: 1220/1545, loss: 0.001907668891362846 2023-01-23 20:10:40.771306: step: 1222/1545, loss: 0.00038741822936572134 2023-01-23 20:10:41.726148: step: 1224/1545, loss: 0.02536538615822792 2023-01-23 20:10:42.617558: step: 1226/1545, loss: 0.0003699997905641794 2023-01-23 20:10:43.532216: step: 1228/1545, loss: 0.002959918463602662 2023-01-23 20:10:44.363073: step: 1230/1545, loss: 0.0006042594322934747 2023-01-23 20:10:45.263177: step: 1232/1545, loss: 0.13040079176425934 2023-01-23 20:10:46.122193: step: 1234/1545, loss: 0.0012814283836632967 2023-01-23 20:10:47.029473: step: 1236/1545, loss: 0.0006797536043450236 2023-01-23 20:10:47.957234: step: 1238/1545, loss: 0.010313011705875397 2023-01-23 20:10:48.873762: step: 1240/1545, loss: 0.060603804886341095 2023-01-23 20:10:49.779958: step: 1242/1545, loss: 0.14469122886657715 2023-01-23 20:10:50.732269: step: 1244/1545, loss: 0.00015088218788150698 2023-01-23 20:10:51.551807: step: 1246/1545, loss: 2.1733327230322175e-05 2023-01-23 20:10:52.441497: step: 1248/1545, loss: 3.6831130273640156e-05 2023-01-23 20:10:53.294331: step: 1250/1545, loss: 0.5683426260948181 2023-01-23 20:10:54.163231: step: 1252/1545, loss: 0.0015555170830339193 2023-01-23 20:10:55.005968: step: 1254/1545, loss: 0.00011542750871740282 2023-01-23 20:10:55.896720: step: 1256/1545, loss: 0.002672431757673621 2023-01-23 20:10:56.771670: step: 1258/1545, loss: 0.0017413042951375246 2023-01-23 20:10:57.608898: step: 1260/1545, loss: -2.625436354719568e-05 2023-01-23 20:10:58.502417: step: 1262/1545, loss: 0.00017809600103646517 2023-01-23 20:10:59.402726: step: 1264/1545, loss: 1.5387615349027328e-05 2023-01-23 20:11:00.293137: step: 1266/1545, loss: 4.890933996648528e-05 2023-01-23 20:11:01.160724: step: 1268/1545, loss: 0.0011203810572624207 2023-01-23 20:11:02.086187: step: 1270/1545, loss: 0.00011504888243507594 2023-01-23 20:11:02.992186: step: 1272/1545, loss: 0.00017855814076028764 2023-01-23 20:11:03.844402: step: 1274/1545, loss: 0.3227388858795166 2023-01-23 20:11:04.714008: step: 1276/1545, loss: 0.00021373401978053153 2023-01-23 20:11:05.580947: step: 1278/1545, loss: 0.00475945882499218 2023-01-23 20:11:06.399873: step: 1280/1545, loss: 0.0002664462081156671 2023-01-23 20:11:07.289666: step: 1282/1545, loss: 1.98288125830004e-06 2023-01-23 20:11:08.180692: step: 1284/1545, loss: 0.00014963443391025066 2023-01-23 20:11:09.020847: step: 1286/1545, loss: 0.0010406828951090574 2023-01-23 20:11:09.898312: step: 1288/1545, loss: 0.00010110087168868631 2023-01-23 20:11:10.765115: step: 1290/1545, loss: 2.672433402040042e-05 2023-01-23 20:11:11.618421: step: 1292/1545, loss: 0.060064103454351425 2023-01-23 20:11:12.477838: step: 1294/1545, loss: 0.00020171234791632742 2023-01-23 20:11:13.345378: step: 1296/1545, loss: 0.0006519176531583071 2023-01-23 20:11:14.229973: step: 1298/1545, loss: 3.084142008447088e-05 2023-01-23 20:11:15.135062: step: 1300/1545, loss: 2.051881529041566e-05 2023-01-23 20:11:15.989976: step: 1302/1545, loss: 0.0008461714023724198 2023-01-23 20:11:16.843998: step: 1304/1545, loss: 0.014164489693939686 2023-01-23 20:11:17.761110: step: 1306/1545, loss: 0.33654046058654785 2023-01-23 20:11:18.590827: step: 1308/1545, loss: 0.24443672597408295 2023-01-23 20:11:19.469289: step: 1310/1545, loss: 0.0017696981085464358 2023-01-23 20:11:20.342256: step: 1312/1545, loss: 0.0011023383121937513 2023-01-23 20:11:21.289817: step: 1314/1545, loss: 0.007715935818850994 2023-01-23 20:11:22.161746: step: 1316/1545, loss: -2.1553338228841312e-05 2023-01-23 20:11:23.002858: step: 1318/1545, loss: 0.552228569984436 2023-01-23 20:11:23.857557: step: 1320/1545, loss: 0.037695977836847305 2023-01-23 20:11:24.835434: step: 1322/1545, loss: 0.0016199942911043763 2023-01-23 20:11:25.695285: step: 1324/1545, loss: 0.01460279617458582 2023-01-23 20:11:26.581298: step: 1326/1545, loss: 0.01821381412446499 2023-01-23 20:11:27.491500: step: 1328/1545, loss: 0.04458104446530342 2023-01-23 20:11:28.330372: step: 1330/1545, loss: 0.3127213418483734 2023-01-23 20:11:29.241447: step: 1332/1545, loss: 0.0029420857317745686 2023-01-23 20:11:30.072948: step: 1334/1545, loss: 0.00011500329128466547 2023-01-23 20:11:30.951072: step: 1336/1545, loss: 0.011176126077771187 2023-01-23 20:11:31.839052: step: 1338/1545, loss: 0.15107430517673492 2023-01-23 20:11:32.693781: step: 1340/1545, loss: 0.0009652984444983304 2023-01-23 20:11:33.596229: step: 1342/1545, loss: 0.01176043413579464 2023-01-23 20:11:34.461568: step: 1344/1545, loss: 1.6285158395767212 2023-01-23 20:11:35.293036: step: 1346/1545, loss: 0.009558465331792831 2023-01-23 20:11:36.152466: step: 1348/1545, loss: 0.005756061058491468 2023-01-23 20:11:37.057689: step: 1350/1545, loss: 0.01238197647035122 2023-01-23 20:11:37.906841: step: 1352/1545, loss: 0.000590226030908525 2023-01-23 20:11:38.767970: step: 1354/1545, loss: 0.00021751572785433382 2023-01-23 20:11:39.655583: step: 1356/1545, loss: 0.0010136817581951618 2023-01-23 20:11:40.549701: step: 1358/1545, loss: 0.0033559200819581747 2023-01-23 20:11:41.406257: step: 1360/1545, loss: 0.10025683045387268 2023-01-23 20:11:42.271660: step: 1362/1545, loss: 0.00010330081568099558 2023-01-23 20:11:43.134057: step: 1364/1545, loss: 0.10686267167329788 2023-01-23 20:11:44.018561: step: 1366/1545, loss: 0.0011422036914154887 2023-01-23 20:11:44.885166: step: 1368/1545, loss: 0.007135638035833836 2023-01-23 20:11:45.753299: step: 1370/1545, loss: 0.2702163755893707 2023-01-23 20:11:46.584471: step: 1372/1545, loss: 0.001113284844905138 2023-01-23 20:11:47.469509: step: 1374/1545, loss: 0.00021168812236282974 2023-01-23 20:11:48.360226: step: 1376/1545, loss: 0.00019733567023649812 2023-01-23 20:11:49.247881: step: 1378/1545, loss: 0.14882871508598328 2023-01-23 20:11:50.106662: step: 1380/1545, loss: 0.009490271098911762 2023-01-23 20:11:50.987600: step: 1382/1545, loss: 0.001808283501304686 2023-01-23 20:11:51.903745: step: 1384/1545, loss: 0.11018256843090057 2023-01-23 20:11:52.827002: step: 1386/1545, loss: 0.00044386283843778074 2023-01-23 20:11:53.676169: step: 1388/1545, loss: 0.0015344808343797922 2023-01-23 20:11:54.548727: step: 1390/1545, loss: 0.015408307313919067 2023-01-23 20:11:55.424802: step: 1392/1545, loss: 9.063595643965527e-05 2023-01-23 20:11:56.325615: step: 1394/1545, loss: 0.008078196085989475 2023-01-23 20:11:57.247583: step: 1396/1545, loss: 6.114436837378889e-05 2023-01-23 20:11:58.177956: step: 1398/1545, loss: 0.11093616485595703 2023-01-23 20:11:59.035959: step: 1400/1545, loss: 0.00011218666622880846 2023-01-23 20:11:59.873182: step: 1402/1545, loss: 0.06334437429904938 2023-01-23 20:12:00.756729: step: 1404/1545, loss: 0.05057404190301895 2023-01-23 20:12:01.702193: step: 1406/1545, loss: 2.264542672492098e-05 2023-01-23 20:12:02.603116: step: 1408/1545, loss: 0.0097803371027112 2023-01-23 20:12:03.502230: step: 1410/1545, loss: 0.012632627971470356 2023-01-23 20:12:04.404023: step: 1412/1545, loss: 0.02356112375855446 2023-01-23 20:12:05.250208: step: 1414/1545, loss: 6.601809582207352e-05 2023-01-23 20:12:06.132366: step: 1416/1545, loss: 0.00019358133431524038 2023-01-23 20:12:06.942499: step: 1418/1545, loss: 0.002853441284969449 2023-01-23 20:12:07.834185: step: 1420/1545, loss: 0.0009376324596814811 2023-01-23 20:12:08.679742: step: 1422/1545, loss: 0.17507542669773102 2023-01-23 20:12:09.559270: step: 1424/1545, loss: 0.0008206261554732919 2023-01-23 20:12:10.409169: step: 1426/1545, loss: 0.00018602996715344489 2023-01-23 20:12:11.275924: step: 1428/1545, loss: 0.024189801886677742 2023-01-23 20:12:12.107265: step: 1430/1545, loss: 0.09088557958602905 2023-01-23 20:12:12.971501: step: 1432/1545, loss: 0.07121126353740692 2023-01-23 20:12:13.799890: step: 1434/1545, loss: 0.03347648307681084 2023-01-23 20:12:14.656727: step: 1436/1545, loss: 0.019424639642238617 2023-01-23 20:12:15.576394: step: 1438/1545, loss: 0.19869735836982727 2023-01-23 20:12:16.387784: step: 1440/1545, loss: 0.000578251201659441 2023-01-23 20:12:17.254637: step: 1442/1545, loss: 0.00034577312180772424 2023-01-23 20:12:18.124187: step: 1444/1545, loss: 0.0003206882392987609 2023-01-23 20:12:19.023083: step: 1446/1545, loss: 7.355258276220411e-05 2023-01-23 20:12:19.933661: step: 1448/1545, loss: 0.0002824514522217214 2023-01-23 20:12:20.833287: step: 1450/1545, loss: 0.00039443615241907537 2023-01-23 20:12:21.710797: step: 1452/1545, loss: 0.00012319118832238019 2023-01-23 20:12:22.585472: step: 1454/1545, loss: 0.0003158556646667421 2023-01-23 20:12:23.461617: step: 1456/1545, loss: 0.07775592058897018 2023-01-23 20:12:24.308355: step: 1458/1545, loss: 0.0008465704158879817 2023-01-23 20:12:25.225378: step: 1460/1545, loss: 0.00847022607922554 2023-01-23 20:12:26.176508: step: 1462/1545, loss: 0.009109791368246078 2023-01-23 20:12:27.029236: step: 1464/1545, loss: 0.00023109216999728233 2023-01-23 20:12:27.936330: step: 1466/1545, loss: 0.2185443490743637 2023-01-23 20:12:28.857964: step: 1468/1545, loss: 0.21506692469120026 2023-01-23 20:12:29.733783: step: 1470/1545, loss: 0.0004756080743391067 2023-01-23 20:12:30.602961: step: 1472/1545, loss: 0.10048314929008484 2023-01-23 20:12:31.464019: step: 1474/1545, loss: 0.00020077569934073836 2023-01-23 20:12:32.383962: step: 1476/1545, loss: 0.001263342797756195 2023-01-23 20:12:33.246794: step: 1478/1545, loss: 0.00042765363468788564 2023-01-23 20:12:34.119413: step: 1480/1545, loss: 0.0003995249280706048 2023-01-23 20:12:35.005073: step: 1482/1545, loss: 0.680670976638794 2023-01-23 20:12:35.909913: step: 1484/1545, loss: 0.11695846170186996 2023-01-23 20:12:36.791842: step: 1486/1545, loss: 0.012259037233889103 2023-01-23 20:12:37.705585: step: 1488/1545, loss: 0.10607069730758667 2023-01-23 20:12:38.585984: step: 1490/1545, loss: 0.0007022034842520952 2023-01-23 20:12:39.467607: step: 1492/1545, loss: 0.0003786197048611939 2023-01-23 20:12:40.323913: step: 1494/1545, loss: 0.001271920744329691 2023-01-23 20:12:41.211047: step: 1496/1545, loss: 0.001329958438873291 2023-01-23 20:12:42.048670: step: 1498/1545, loss: 0.00038331010728143156 2023-01-23 20:12:42.933863: step: 1500/1545, loss: 0.027439890429377556 2023-01-23 20:12:43.868091: step: 1502/1545, loss: 0.005600243341177702 2023-01-23 20:12:44.723227: step: 1504/1545, loss: 0.0047058286145329475 2023-01-23 20:12:45.610511: step: 1506/1545, loss: 0.13421346247196198 2023-01-23 20:12:46.448441: step: 1508/1545, loss: 0.0005290164845064282 2023-01-23 20:12:47.340271: step: 1510/1545, loss: 0.00884795468300581 2023-01-23 20:12:48.280715: step: 1512/1545, loss: 0.00018571317195892334 2023-01-23 20:12:49.209860: step: 1514/1545, loss: 0.0003480053856037557 2023-01-23 20:12:50.109060: step: 1516/1545, loss: 0.00035190387279726565 2023-01-23 20:12:50.973420: step: 1518/1545, loss: 0.0010739826830103993 2023-01-23 20:12:51.845454: step: 1520/1545, loss: 0.08315125107765198 2023-01-23 20:12:52.723079: step: 1522/1545, loss: 0.0003152692806906998 2023-01-23 20:12:53.589914: step: 1524/1545, loss: 0.06700398027896881 2023-01-23 20:12:54.462443: step: 1526/1545, loss: 0.0003050906234420836 2023-01-23 20:12:55.353589: step: 1528/1545, loss: 9.870718349702656e-05 2023-01-23 20:12:56.214783: step: 1530/1545, loss: 0.0016316906549036503 2023-01-23 20:12:57.122922: step: 1532/1545, loss: 0.0005653572152368724 2023-01-23 20:12:57.942262: step: 1534/1545, loss: 0.0012382674030959606 2023-01-23 20:12:58.782292: step: 1536/1545, loss: 0.05925348028540611 2023-01-23 20:12:59.623015: step: 1538/1545, loss: 0.001129204872995615 2023-01-23 20:13:00.457912: step: 1540/1545, loss: 0.02075119875371456 2023-01-23 20:13:01.325583: step: 1542/1545, loss: 6.678685895167291e-05 2023-01-23 20:13:02.234492: step: 1544/1545, loss: 0.029708977788686752 2023-01-23 20:13:03.160002: step: 1546/1545, loss: 0.016644949093461037 2023-01-23 20:13:04.058746: step: 1548/1545, loss: 0.007148343604058027 2023-01-23 20:13:04.964022: step: 1550/1545, loss: 0.01713836006820202 2023-01-23 20:13:05.806166: step: 1552/1545, loss: 0.17583082616329193 2023-01-23 20:13:06.685796: step: 1554/1545, loss: 0.10259237140417099 2023-01-23 20:13:07.561437: step: 1556/1545, loss: 0.0007221490377560258 2023-01-23 20:13:08.523605: step: 1558/1545, loss: 7.308897329494357e-05 2023-01-23 20:13:09.421330: step: 1560/1545, loss: 0.00014930832548998296 2023-01-23 20:13:10.288624: step: 1562/1545, loss: 0.0031901232432574034 2023-01-23 20:13:11.185395: step: 1564/1545, loss: 0.00014501989062409848 2023-01-23 20:13:12.053981: step: 1566/1545, loss: 0.0010108503047376871 2023-01-23 20:13:12.979013: step: 1568/1545, loss: 0.2473381608724594 2023-01-23 20:13:13.909228: step: 1570/1545, loss: 0.0009119246387854218 2023-01-23 20:13:14.769296: step: 1572/1545, loss: 0.021789081394672394 2023-01-23 20:13:15.603382: step: 1574/1545, loss: 0.0047836084850132465 2023-01-23 20:13:16.475626: step: 1576/1545, loss: 0.022201649844646454 2023-01-23 20:13:17.328739: step: 1578/1545, loss: 0.0002521823043935001 2023-01-23 20:13:18.183019: step: 1580/1545, loss: 0.0037724017165601254 2023-01-23 20:13:19.049767: step: 1582/1545, loss: 0.004320552106946707 2023-01-23 20:13:19.890237: step: 1584/1545, loss: 0.00033857367816381156 2023-01-23 20:13:20.786444: step: 1586/1545, loss: 0.29057636857032776 2023-01-23 20:13:21.635397: step: 1588/1545, loss: 0.000626028107944876 2023-01-23 20:13:22.543066: step: 1590/1545, loss: 0.004783842712640762 2023-01-23 20:13:23.462002: step: 1592/1545, loss: 0.002486985409632325 2023-01-23 20:13:24.375665: step: 1594/1545, loss: 0.054849155247211456 2023-01-23 20:13:25.229728: step: 1596/1545, loss: 0.0002145972102880478 2023-01-23 20:13:26.117974: step: 1598/1545, loss: 0.028301561251282692 2023-01-23 20:13:26.984429: step: 1600/1545, loss: 0.0003210213326383382 2023-01-23 20:13:27.882539: step: 1602/1545, loss: 0.0037607259582728148 2023-01-23 20:13:28.790126: step: 1604/1545, loss: 0.00016603319090791047 2023-01-23 20:13:29.685421: step: 1606/1545, loss: 0.0015678928466513753 2023-01-23 20:13:30.519610: step: 1608/1545, loss: 0.004130564630031586 2023-01-23 20:13:31.393020: step: 1610/1545, loss: 0.40586090087890625 2023-01-23 20:13:32.221900: step: 1612/1545, loss: 0.003791710827499628 2023-01-23 20:13:33.232824: step: 1614/1545, loss: 0.0006181782810017467 2023-01-23 20:13:34.085223: step: 1616/1545, loss: 0.02760266326367855 2023-01-23 20:13:34.986628: step: 1618/1545, loss: 0.0007626569713465869 2023-01-23 20:13:35.817135: step: 1620/1545, loss: 0.00048172811511904 2023-01-23 20:13:36.701359: step: 1622/1545, loss: 0.11377836763858795 2023-01-23 20:13:37.560441: step: 1624/1545, loss: 3.933297557523474e-05 2023-01-23 20:13:38.420752: step: 1626/1545, loss: 0.0010094641475006938 2023-01-23 20:13:39.279303: step: 1628/1545, loss: 0.00019361040904186666 2023-01-23 20:13:40.149351: step: 1630/1545, loss: 0.08485601842403412 2023-01-23 20:13:41.028587: step: 1632/1545, loss: 0.08486581593751907 2023-01-23 20:13:41.922227: step: 1634/1545, loss: 0.0004728912317659706 2023-01-23 20:13:42.783947: step: 1636/1545, loss: 0.0007366075878962874 2023-01-23 20:13:43.661783: step: 1638/1545, loss: 0.0008422799874097109 2023-01-23 20:13:44.536963: step: 1640/1545, loss: 0.022741932421922684 2023-01-23 20:13:45.502281: step: 1642/1545, loss: 9.745920397108421e-05 2023-01-23 20:13:46.363704: step: 1644/1545, loss: 0.010544180870056152 2023-01-23 20:13:47.238968: step: 1646/1545, loss: 0.003961053676903248 2023-01-23 20:13:48.087636: step: 1648/1545, loss: 0.13196763396263123 2023-01-23 20:13:48.988537: step: 1650/1545, loss: 0.0026998589746654034 2023-01-23 20:13:49.868013: step: 1652/1545, loss: 0.14344918727874756 2023-01-23 20:13:50.731250: step: 1654/1545, loss: 0.002952015958726406 2023-01-23 20:13:51.562475: step: 1656/1545, loss: 0.00022261850244831294 2023-01-23 20:13:52.442005: step: 1658/1545, loss: 0.006499846000224352 2023-01-23 20:13:53.327615: step: 1660/1545, loss: 0.0004548250581137836 2023-01-23 20:13:54.192744: step: 1662/1545, loss: 0.0038085361011326313 2023-01-23 20:13:55.129602: step: 1664/1545, loss: 0.0010107810376212 2023-01-23 20:13:55.992024: step: 1666/1545, loss: 0.0022815607953816652 2023-01-23 20:13:56.868200: step: 1668/1545, loss: 0.005862698424607515 2023-01-23 20:13:57.747405: step: 1670/1545, loss: 0.05864947289228439 2023-01-23 20:13:58.605315: step: 1672/1545, loss: -3.7722347769886255e-06 2023-01-23 20:13:59.499444: step: 1674/1545, loss: 0.041014473885297775 2023-01-23 20:14:00.333060: step: 1676/1545, loss: 0.17114049196243286 2023-01-23 20:14:01.243840: step: 1678/1545, loss: 0.07678467035293579 2023-01-23 20:14:02.089660: step: 1680/1545, loss: 0.0002326730900676921 2023-01-23 20:14:02.945034: step: 1682/1545, loss: 0.00033729971619322896 2023-01-23 20:14:03.925296: step: 1684/1545, loss: 0.0006907517672516406 2023-01-23 20:14:04.821650: step: 1686/1545, loss: 0.10865452885627747 2023-01-23 20:14:05.710068: step: 1688/1545, loss: 0.00010326078336220235 2023-01-23 20:14:06.595116: step: 1690/1545, loss: 0.30734771490097046 2023-01-23 20:14:07.434142: step: 1692/1545, loss: 0.0016309544444084167 2023-01-23 20:14:08.319054: step: 1694/1545, loss: 0.0005081279668956995 2023-01-23 20:14:09.171361: step: 1696/1545, loss: 0.003561625024303794 2023-01-23 20:14:10.034263: step: 1698/1545, loss: 0.0005669361562468112 2023-01-23 20:14:10.886570: step: 1700/1545, loss: 4.456326860236004e-05 2023-01-23 20:14:11.755669: step: 1702/1545, loss: 0.0007442861679010093 2023-01-23 20:14:12.694358: step: 1704/1545, loss: 0.5425222516059875 2023-01-23 20:14:13.596109: step: 1706/1545, loss: 0.00013906805543228984 2023-01-23 20:14:14.454053: step: 1708/1545, loss: 0.00011149559577461332 2023-01-23 20:14:15.353013: step: 1710/1545, loss: 0.014005273580551147 2023-01-23 20:14:16.226192: step: 1712/1545, loss: 0.19636356830596924 2023-01-23 20:14:17.073817: step: 1714/1545, loss: 0.0033049851190298796 2023-01-23 20:14:17.922162: step: 1716/1545, loss: 0.10613514482975006 2023-01-23 20:14:18.773014: step: 1718/1545, loss: 0.10097983479499817 2023-01-23 20:14:19.720360: step: 1720/1545, loss: 0.0016900955233722925 2023-01-23 20:14:20.549627: step: 1722/1545, loss: 0.0012694962788373232 2023-01-23 20:14:21.506519: step: 1724/1545, loss: 0.00017232593381777406 2023-01-23 20:14:22.396193: step: 1726/1545, loss: 0.06789673864841461 2023-01-23 20:14:23.358625: step: 1728/1545, loss: 0.00032224252936430275 2023-01-23 20:14:24.255700: step: 1730/1545, loss: 0.03262350335717201 2023-01-23 20:14:25.153996: step: 1732/1545, loss: 0.012054764665663242 2023-01-23 20:14:26.021741: step: 1734/1545, loss: 0.004914214834570885 2023-01-23 20:14:26.835936: step: 1736/1545, loss: 0.0002149277279386297 2023-01-23 20:14:27.696367: step: 1738/1545, loss: 0.12957912683486938 2023-01-23 20:14:28.593017: step: 1740/1545, loss: 0.019014934077858925 2023-01-23 20:14:29.482533: step: 1742/1545, loss: 0.0003631665895227343 2023-01-23 20:14:30.370934: step: 1744/1545, loss: 0.009173652157187462 2023-01-23 20:14:31.214149: step: 1746/1545, loss: 0.00039797418867237866 2023-01-23 20:14:32.066810: step: 1748/1545, loss: 0.00032039493089541793 2023-01-23 20:14:32.915822: step: 1750/1545, loss: 7.296527473954484e-05 2023-01-23 20:14:33.760638: step: 1752/1545, loss: 0.0008861214155331254 2023-01-23 20:14:34.616308: step: 1754/1545, loss: 0.00029313849518075585 2023-01-23 20:14:35.470582: step: 1756/1545, loss: 0.07778644561767578 2023-01-23 20:14:36.307497: step: 1758/1545, loss: 9.469568612985313e-05 2023-01-23 20:14:37.173197: step: 1760/1545, loss: 6.380691047525033e-05 2023-01-23 20:14:38.107299: step: 1762/1545, loss: 0.00928007997572422 2023-01-23 20:14:39.001431: step: 1764/1545, loss: 0.008536613546311855 2023-01-23 20:14:39.911646: step: 1766/1545, loss: 0.12008517980575562 2023-01-23 20:14:40.813935: step: 1768/1545, loss: 0.6003884077072144 2023-01-23 20:14:41.690615: step: 1770/1545, loss: 0.004782301373779774 2023-01-23 20:14:42.587317: step: 1772/1545, loss: 0.00796380452811718 2023-01-23 20:14:43.516646: step: 1774/1545, loss: 0.0003414106322452426 2023-01-23 20:14:44.425698: step: 1776/1545, loss: 0.06393536925315857 2023-01-23 20:14:45.278393: step: 1778/1545, loss: 0.0018526088679209352 2023-01-23 20:14:46.202122: step: 1780/1545, loss: 0.011572773568332195 2023-01-23 20:14:47.085231: step: 1782/1545, loss: 1.3909705558035057e-05 2023-01-23 20:14:48.086507: step: 1784/1545, loss: 4.969797737430781e-05 2023-01-23 20:14:48.982681: step: 1786/1545, loss: 0.014644000679254532 2023-01-23 20:14:49.822623: step: 1788/1545, loss: 1.3741330803895835e-05 2023-01-23 20:14:50.688974: step: 1790/1545, loss: 0.00010912019934039563 2023-01-23 20:14:51.563564: step: 1792/1545, loss: 0.0001114530605264008 2023-01-23 20:14:52.477558: step: 1794/1545, loss: 0.16409513354301453 2023-01-23 20:14:53.386728: step: 1796/1545, loss: 0.2676866054534912 2023-01-23 20:14:54.236386: step: 1798/1545, loss: 0.0005024527199566364 2023-01-23 20:14:55.120470: step: 1800/1545, loss: 0.5208700299263 2023-01-23 20:14:55.982226: step: 1802/1545, loss: 0.0001257916446775198 2023-01-23 20:14:56.853248: step: 1804/1545, loss: 0.00014319957699626684 2023-01-23 20:14:57.742981: step: 1806/1545, loss: 0.4623074531555176 2023-01-23 20:14:58.669851: step: 1808/1545, loss: 0.41188517212867737 2023-01-23 20:14:59.617453: step: 1810/1545, loss: 7.072061998769641e-05 2023-01-23 20:15:00.498427: step: 1812/1545, loss: 0.036845862865448 2023-01-23 20:15:01.369546: step: 1814/1545, loss: 0.00033198940218426287 2023-01-23 20:15:02.248824: step: 1816/1545, loss: 0.0011722069466486573 2023-01-23 20:15:03.198474: step: 1818/1545, loss: 0.0004562348185572773 2023-01-23 20:15:04.124431: step: 1820/1545, loss: 0.08261990547180176 2023-01-23 20:15:05.004475: step: 1822/1545, loss: 0.0018739942461252213 2023-01-23 20:15:05.900299: step: 1824/1545, loss: 0.0021542448084801435 2023-01-23 20:15:06.733628: step: 1826/1545, loss: 0.0002031322510447353 2023-01-23 20:15:07.644254: step: 1828/1545, loss: 0.008631393313407898 2023-01-23 20:15:08.588525: step: 1830/1545, loss: 0.0002056285593425855 2023-01-23 20:15:09.470356: step: 1832/1545, loss: 0.035496462136507034 2023-01-23 20:15:10.337248: step: 1834/1545, loss: 0.0014841894153505564 2023-01-23 20:15:11.235950: step: 1836/1545, loss: 0.00012449124187696725 2023-01-23 20:15:12.116637: step: 1838/1545, loss: 0.0020121894776821136 2023-01-23 20:15:13.025104: step: 1840/1545, loss: 0.0010538413189351559 2023-01-23 20:15:13.967589: step: 1842/1545, loss: 0.003600836033001542 2023-01-23 20:15:14.854929: step: 1844/1545, loss: 0.0029704375192523003 2023-01-23 20:15:15.695629: step: 1846/1545, loss: 0.07390229403972626 2023-01-23 20:15:16.576009: step: 1848/1545, loss: 0.00013708416372537613 2023-01-23 20:15:17.429232: step: 1850/1545, loss: 0.020932257175445557 2023-01-23 20:15:18.272486: step: 1852/1545, loss: 0.001033399603329599 2023-01-23 20:15:19.147416: step: 1854/1545, loss: 0.000292336568236351 2023-01-23 20:15:20.036908: step: 1856/1545, loss: 0.06698281317949295 2023-01-23 20:15:20.904563: step: 1858/1545, loss: 0.0010940864449366927 2023-01-23 20:15:21.760206: step: 1860/1545, loss: 0.08265312016010284 2023-01-23 20:15:22.612425: step: 1862/1545, loss: 0.040801238268613815 2023-01-23 20:15:23.501926: step: 1864/1545, loss: 8.565656753489748e-05 2023-01-23 20:15:24.360686: step: 1866/1545, loss: 0.0004900870844721794 2023-01-23 20:15:25.209118: step: 1868/1545, loss: 0.18028543889522552 2023-01-23 20:15:26.096959: step: 1870/1545, loss: 0.0002154862304450944 2023-01-23 20:15:26.973821: step: 1872/1545, loss: 4.471494321478531e-05 2023-01-23 20:15:27.839766: step: 1874/1545, loss: 0.006917322985827923 2023-01-23 20:15:28.763011: step: 1876/1545, loss: 0.02033557929098606 2023-01-23 20:15:29.651195: step: 1878/1545, loss: 0.0032713122200220823 2023-01-23 20:15:30.505753: step: 1880/1545, loss: 0.0013919175835326314 2023-01-23 20:15:31.413124: step: 1882/1545, loss: 0.0006106320070102811 2023-01-23 20:15:32.334881: step: 1884/1545, loss: 0.03188491612672806 2023-01-23 20:15:33.204072: step: 1886/1545, loss: 0.00012538691225927323 2023-01-23 20:15:34.098807: step: 1888/1545, loss: 0.02417938783764839 2023-01-23 20:15:35.026273: step: 1890/1545, loss: 0.009887184016406536 2023-01-23 20:15:35.892273: step: 1892/1545, loss: 0.0006910996744409204 2023-01-23 20:15:36.881264: step: 1894/1545, loss: 0.0005304171936586499 2023-01-23 20:15:37.772895: step: 1896/1545, loss: 0.00047752648242749274 2023-01-23 20:15:38.612986: step: 1898/1545, loss: 0.2594091296195984 2023-01-23 20:15:39.458962: step: 1900/1545, loss: 0.028029924258589745 2023-01-23 20:15:40.315746: step: 1902/1545, loss: 0.00020174772362224758 2023-01-23 20:15:41.190268: step: 1904/1545, loss: 0.020918400958180428 2023-01-23 20:15:42.030129: step: 1906/1545, loss: 9.199201303999871e-05 2023-01-23 20:15:42.928821: step: 1908/1545, loss: 0.026896916329860687 2023-01-23 20:15:43.824717: step: 1910/1545, loss: 0.0023174877278506756 2023-01-23 20:15:44.719965: step: 1912/1545, loss: 0.013315051794052124 2023-01-23 20:15:45.609768: step: 1914/1545, loss: 0.3412874937057495 2023-01-23 20:15:46.502646: step: 1916/1545, loss: 0.024881187826395035 2023-01-23 20:15:47.381394: step: 1918/1545, loss: 0.14468003809452057 2023-01-23 20:15:48.289340: step: 1920/1545, loss: 0.22445249557495117 2023-01-23 20:15:49.238203: step: 1922/1545, loss: 0.0199753325432539 2023-01-23 20:15:50.105658: step: 1924/1545, loss: 0.0029660752043128014 2023-01-23 20:15:50.979472: step: 1926/1545, loss: 0.009388590231537819 2023-01-23 20:15:51.867045: step: 1928/1545, loss: 1.1011077731382102e-05 2023-01-23 20:15:52.748334: step: 1930/1545, loss: 0.018006563186645508 2023-01-23 20:15:53.616029: step: 1932/1545, loss: 0.5317986011505127 2023-01-23 20:15:54.486032: step: 1934/1545, loss: 8.852031896822155e-06 2023-01-23 20:15:55.406052: step: 1936/1545, loss: 0.22014038264751434 2023-01-23 20:15:56.263438: step: 1938/1545, loss: 2.426244827802293e-05 2023-01-23 20:15:57.144621: step: 1940/1545, loss: 0.25948038697242737 2023-01-23 20:15:58.021090: step: 1942/1545, loss: 0.03906940296292305 2023-01-23 20:15:58.915353: step: 1944/1545, loss: 0.086831234395504 2023-01-23 20:15:59.925504: step: 1946/1545, loss: 0.000603052438236773 2023-01-23 20:16:00.834492: step: 1948/1545, loss: 0.00018404277216177434 2023-01-23 20:16:01.659743: step: 1950/1545, loss: 0.00017577456310391426 2023-01-23 20:16:02.599067: step: 1952/1545, loss: 0.0001145051937783137 2023-01-23 20:16:03.494791: step: 1954/1545, loss: 0.009937279857695103 2023-01-23 20:16:04.388479: step: 1956/1545, loss: 0.0007103391690179706 2023-01-23 20:16:05.285713: step: 1958/1545, loss: 0.002444740617647767 2023-01-23 20:16:06.157688: step: 1960/1545, loss: 1.1077225281042047e-05 2023-01-23 20:16:07.040072: step: 1962/1545, loss: 0.04019608721137047 2023-01-23 20:16:07.895121: step: 1964/1545, loss: 0.0002801662776619196 2023-01-23 20:16:08.753113: step: 1966/1545, loss: 0.0024949151556938887 2023-01-23 20:16:09.616236: step: 1968/1545, loss: 0.10609831660985947 2023-01-23 20:16:10.461104: step: 1970/1545, loss: 0.00238474877551198 2023-01-23 20:16:11.311153: step: 1972/1545, loss: 6.140429468359798e-05 2023-01-23 20:16:12.225072: step: 1974/1545, loss: 0.0010784167097881436 2023-01-23 20:16:13.105211: step: 1976/1545, loss: 0.008862718939781189 2023-01-23 20:16:13.981113: step: 1978/1545, loss: 0.0010724951280280948 2023-01-23 20:16:14.890214: step: 1980/1545, loss: 0.013795486651360989 2023-01-23 20:16:15.740259: step: 1982/1545, loss: 0.09873105585575104 2023-01-23 20:16:16.606274: step: 1984/1545, loss: 7.628860475961119e-05 2023-01-23 20:16:17.491118: step: 1986/1545, loss: 0.08259094506502151 2023-01-23 20:16:18.388276: step: 1988/1545, loss: 0.010239524766802788 2023-01-23 20:16:19.291178: step: 1990/1545, loss: 0.0003347666934132576 2023-01-23 20:16:20.132782: step: 1992/1545, loss: 0.07376664876937866 2023-01-23 20:16:21.026602: step: 1994/1545, loss: 0.0005401511443778872 2023-01-23 20:16:21.897115: step: 1996/1545, loss: 9.420866990694776e-05 2023-01-23 20:16:22.765130: step: 1998/1545, loss: 0.03264818340539932 2023-01-23 20:16:23.676986: step: 2000/1545, loss: 0.0007068751147016883 2023-01-23 20:16:24.512505: step: 2002/1545, loss: 0.011979917995631695 2023-01-23 20:16:25.349970: step: 2004/1545, loss: 0.04336843267083168 2023-01-23 20:16:26.217456: step: 2006/1545, loss: 0.07827022671699524 2023-01-23 20:16:27.069864: step: 2008/1545, loss: 0.0032404593657702208 2023-01-23 20:16:27.961351: step: 2010/1545, loss: 0.010798320174217224 2023-01-23 20:16:28.847688: step: 2012/1545, loss: 0.09626930207014084 2023-01-23 20:16:29.785466: step: 2014/1545, loss: 0.00025784390163607895 2023-01-23 20:16:30.693680: step: 2016/1545, loss: 0.0004972559399902821 2023-01-23 20:16:31.639623: step: 2018/1545, loss: 0.1816597282886505 2023-01-23 20:16:32.557686: step: 2020/1545, loss: 0.0010663738939911127 2023-01-23 20:16:33.492755: step: 2022/1545, loss: 5.965927994111553e-05 2023-01-23 20:16:34.345599: step: 2024/1545, loss: 0.0003126148949377239 2023-01-23 20:16:35.252879: step: 2026/1545, loss: 0.057132236659526825 2023-01-23 20:16:36.142646: step: 2028/1545, loss: 0.0004724783939309418 2023-01-23 20:16:37.027652: step: 2030/1545, loss: 0.016735589131712914 2023-01-23 20:16:37.919452: step: 2032/1545, loss: 0.11963745951652527 2023-01-23 20:16:38.797402: step: 2034/1545, loss: 0.0013006934896111488 2023-01-23 20:16:39.679168: step: 2036/1545, loss: 0.09381897747516632 2023-01-23 20:16:40.534799: step: 2038/1545, loss: 0.03874163329601288 2023-01-23 20:16:41.400961: step: 2040/1545, loss: 0.016958365216851234 2023-01-23 20:16:42.341589: step: 2042/1545, loss: 0.060406263917684555 2023-01-23 20:16:43.216723: step: 2044/1545, loss: 0.002837687497958541 2023-01-23 20:16:44.109205: step: 2046/1545, loss: 0.0002962345606647432 2023-01-23 20:16:44.976190: step: 2048/1545, loss: 0.09488268196582794 2023-01-23 20:16:45.850140: step: 2050/1545, loss: 0.002297411672770977 2023-01-23 20:16:46.766763: step: 2052/1545, loss: 0.0005420967354439199 2023-01-23 20:16:47.646120: step: 2054/1545, loss: 0.05328724905848503 2023-01-23 20:16:48.530028: step: 2056/1545, loss: 0.07035890966653824 2023-01-23 20:16:49.440671: step: 2058/1545, loss: 0.028259556740522385 2023-01-23 20:16:50.363082: step: 2060/1545, loss: 0.0004761149175465107 2023-01-23 20:16:51.278208: step: 2062/1545, loss: 0.00019123525999020785 2023-01-23 20:16:52.215187: step: 2064/1545, loss: 0.0006434719543904066 2023-01-23 20:16:53.085357: step: 2066/1545, loss: 0.00014986291353125125 2023-01-23 20:16:53.961173: step: 2068/1545, loss: 0.05544105917215347 2023-01-23 20:16:54.846516: step: 2070/1545, loss: 0.006165791302919388 2023-01-23 20:16:55.815237: step: 2072/1545, loss: 0.005555439740419388 2023-01-23 20:16:56.694306: step: 2074/1545, loss: -4.956728389515774e-06 2023-01-23 20:16:57.548982: step: 2076/1545, loss: 0.0009398815454915166 2023-01-23 20:16:58.421174: step: 2078/1545, loss: 5.841597885591909e-05 2023-01-23 20:16:59.302796: step: 2080/1545, loss: 0.0030498250853270292 2023-01-23 20:17:00.233357: step: 2082/1545, loss: 0.35169902443885803 2023-01-23 20:17:01.158071: step: 2084/1545, loss: 0.00018675556930247694 2023-01-23 20:17:02.034491: step: 2086/1545, loss: 0.006307821720838547 2023-01-23 20:17:02.891130: step: 2088/1545, loss: 0.017417127266526222 2023-01-23 20:17:03.785462: step: 2090/1545, loss: 0.003748430637642741 2023-01-23 20:17:04.672995: step: 2092/1545, loss: 0.004630868323147297 2023-01-23 20:17:05.572444: step: 2094/1545, loss: 0.001471790368668735 2023-01-23 20:17:06.490500: step: 2096/1545, loss: 0.20946048200130463 2023-01-23 20:17:07.472745: step: 2098/1545, loss: 0.00908395741134882 2023-01-23 20:17:08.278970: step: 2100/1545, loss: 7.596176874358207e-05 2023-01-23 20:17:09.163051: step: 2102/1545, loss: 0.0005334343877620995 2023-01-23 20:17:10.090226: step: 2104/1545, loss: 0.01174151711165905 2023-01-23 20:17:11.012068: step: 2106/1545, loss: 0.00017245468916371465 2023-01-23 20:17:11.886937: step: 2108/1545, loss: 0.058986105024814606 2023-01-23 20:17:12.795881: step: 2110/1545, loss: 0.00025352585362270474 2023-01-23 20:17:13.659463: step: 2112/1545, loss: 0.0023139039985835552 2023-01-23 20:17:14.519196: step: 2114/1545, loss: 0.001992474077269435 2023-01-23 20:17:15.408447: step: 2116/1545, loss: 0.005205526016652584 2023-01-23 20:17:16.295638: step: 2118/1545, loss: 0.001567472005262971 2023-01-23 20:17:17.170023: step: 2120/1545, loss: 0.019049126654863358 2023-01-23 20:17:18.065875: step: 2122/1545, loss: 8.575849642511457e-05 2023-01-23 20:17:18.991942: step: 2124/1545, loss: 0.002779250033199787 2023-01-23 20:17:19.902905: step: 2126/1545, loss: 0.09553272277116776 2023-01-23 20:17:20.806064: step: 2128/1545, loss: 0.0004132107424084097 2023-01-23 20:17:21.666279: step: 2130/1545, loss: 0.03043031506240368 2023-01-23 20:17:22.559686: step: 2132/1545, loss: 0.007149443496018648 2023-01-23 20:17:23.450404: step: 2134/1545, loss: 0.6636026501655579 2023-01-23 20:17:24.345394: step: 2136/1545, loss: 0.003075546119362116 2023-01-23 20:17:25.219726: step: 2138/1545, loss: 0.0004160945536568761 2023-01-23 20:17:26.097951: step: 2140/1545, loss: 3.1321076676249504e-05 2023-01-23 20:17:27.001654: step: 2142/1545, loss: 0.00026888030697591603 2023-01-23 20:17:27.864874: step: 2144/1545, loss: 0.07461774349212646 2023-01-23 20:17:28.711282: step: 2146/1545, loss: 2.7367179427528754e-05 2023-01-23 20:17:29.605482: step: 2148/1545, loss: 0.0005033633206039667 2023-01-23 20:17:30.458719: step: 2150/1545, loss: 0.0002723297802731395 2023-01-23 20:17:31.328143: step: 2152/1545, loss: 0.0009087342768907547 2023-01-23 20:17:32.173638: step: 2154/1545, loss: 0.00011068600724684075 2023-01-23 20:17:33.059439: step: 2156/1545, loss: 0.0014172266237437725 2023-01-23 20:17:34.012697: step: 2158/1545, loss: 0.00021419601398520172 2023-01-23 20:17:34.871557: step: 2160/1545, loss: 0.0009947346989065409 2023-01-23 20:17:35.717959: step: 2162/1545, loss: 6.353053322527558e-05 2023-01-23 20:17:36.568657: step: 2164/1545, loss: 0.00018663590890355408 2023-01-23 20:17:37.510619: step: 2166/1545, loss: 0.00019014085410162807 2023-01-23 20:17:38.401303: step: 2168/1545, loss: 0.022890249267220497 2023-01-23 20:17:39.320044: step: 2170/1545, loss: 0.018485287204384804 2023-01-23 20:17:40.216005: step: 2172/1545, loss: 9.581086487742141e-05 2023-01-23 20:17:41.080458: step: 2174/1545, loss: 0.0015439349226653576 2023-01-23 20:17:41.908958: step: 2176/1545, loss: 0.00052282476099208 2023-01-23 20:17:42.801940: step: 2178/1545, loss: 0.033037569373846054 2023-01-23 20:17:43.669919: step: 2180/1545, loss: 0.02864084765315056 2023-01-23 20:17:44.586673: step: 2182/1545, loss: 0.0006832574727013707 2023-01-23 20:17:45.478912: step: 2184/1545, loss: 0.0028997836634516716 2023-01-23 20:17:46.349371: step: 2186/1545, loss: 0.022232430055737495 2023-01-23 20:17:47.246622: step: 2188/1545, loss: 0.03872038051486015 2023-01-23 20:17:48.104767: step: 2190/1545, loss: 0.00010714308155002072 2023-01-23 20:17:48.996421: step: 2192/1545, loss: 0.027580590918660164 2023-01-23 20:17:49.884675: step: 2194/1545, loss: 0.00024452805519104004 2023-01-23 20:17:50.749637: step: 2196/1545, loss: 0.00018624031508807093 2023-01-23 20:17:51.641629: step: 2198/1545, loss: 0.010786187835037708 2023-01-23 20:17:52.566172: step: 2200/1545, loss: 0.00011780486238421872 2023-01-23 20:17:53.430388: step: 2202/1545, loss: 0.7464401125907898 2023-01-23 20:17:54.376180: step: 2204/1545, loss: 0.0008264004718512297 2023-01-23 20:17:55.295282: step: 2206/1545, loss: 0.04445532336831093 2023-01-23 20:17:56.167430: step: 2208/1545, loss: 0.00011415460903663188 2023-01-23 20:17:57.011675: step: 2210/1545, loss: 0.0030837194062769413 2023-01-23 20:17:57.868918: step: 2212/1545, loss: 9.987423254642636e-05 2023-01-23 20:17:58.719230: step: 2214/1545, loss: 6.835920066805556e-05 2023-01-23 20:17:59.564341: step: 2216/1545, loss: 0.0001824685896281153 2023-01-23 20:18:00.403217: step: 2218/1545, loss: 0.00010997551726177335 2023-01-23 20:18:01.297437: step: 2220/1545, loss: 0.20914128422737122 2023-01-23 20:18:02.166140: step: 2222/1545, loss: 0.03453400731086731 2023-01-23 20:18:03.011658: step: 2224/1545, loss: 0.09724533557891846 2023-01-23 20:18:03.894177: step: 2226/1545, loss: 0.04242556914687157 2023-01-23 20:18:04.730954: step: 2228/1545, loss: 0.07020421326160431 2023-01-23 20:18:05.677261: step: 2230/1545, loss: 0.001125491107814014 2023-01-23 20:18:06.544892: step: 2232/1545, loss: 0.00017005587869789451 2023-01-23 20:18:07.408067: step: 2234/1545, loss: 0.027574028819799423 2023-01-23 20:18:08.297036: step: 2236/1545, loss: 0.0004995141644030809 2023-01-23 20:18:09.141593: step: 2238/1545, loss: 0.000880759151186794 2023-01-23 20:18:10.016120: step: 2240/1545, loss: 0.3193354904651642 2023-01-23 20:18:10.879007: step: 2242/1545, loss: 0.00042758489144034684 2023-01-23 20:18:11.789110: step: 2244/1545, loss: 0.4425017535686493 2023-01-23 20:18:12.615936: step: 2246/1545, loss: 0.0002095751406159252 2023-01-23 20:18:13.572344: step: 2248/1545, loss: 0.04306377097964287 2023-01-23 20:18:14.434432: step: 2250/1545, loss: 0.004847004543989897 2023-01-23 20:18:15.311568: step: 2252/1545, loss: 0.024503661319613457 2023-01-23 20:18:16.184853: step: 2254/1545, loss: 0.0017499267123639584 2023-01-23 20:18:17.077347: step: 2256/1545, loss: 0.0008236582507379353 2023-01-23 20:18:17.913606: step: 2258/1545, loss: 8.603190508438274e-05 2023-01-23 20:18:18.785731: step: 2260/1545, loss: 0.006817927118390799 2023-01-23 20:18:19.677816: step: 2262/1545, loss: 0.009631301276385784 2023-01-23 20:18:20.552662: step: 2264/1545, loss: 0.00053116719936952 2023-01-23 20:18:21.444583: step: 2266/1545, loss: 8.775854075793177e-05 2023-01-23 20:18:22.295972: step: 2268/1545, loss: 0.503581702709198 2023-01-23 20:18:23.139625: step: 2270/1545, loss: 0.09285040199756622 2023-01-23 20:18:24.070794: step: 2272/1545, loss: 0.05802971124649048 2023-01-23 20:18:24.970564: step: 2274/1545, loss: 0.0017389672575518489 2023-01-23 20:18:25.845710: step: 2276/1545, loss: 5.409861114458181e-05 2023-01-23 20:18:26.665973: step: 2278/1545, loss: 0.2783891260623932 2023-01-23 20:18:27.506642: step: 2280/1545, loss: 0.0002343654923606664 2023-01-23 20:18:28.408520: step: 2282/1545, loss: 0.0007148266304284334 2023-01-23 20:18:29.264136: step: 2284/1545, loss: 0.0031736569944769144 2023-01-23 20:18:30.154601: step: 2286/1545, loss: 0.11103176325559616 2023-01-23 20:18:31.011564: step: 2288/1545, loss: 0.0006768639432266355 2023-01-23 20:18:31.880244: step: 2290/1545, loss: 0.0009965637000277638 2023-01-23 20:18:32.740134: step: 2292/1545, loss: 0.4360486567020416 2023-01-23 20:18:33.653762: step: 2294/1545, loss: 0.01817581057548523 2023-01-23 20:18:34.543001: step: 2296/1545, loss: 0.126713827252388 2023-01-23 20:18:35.452112: step: 2298/1545, loss: 0.037906207144260406 2023-01-23 20:18:36.323872: step: 2300/1545, loss: 2.286707422172185e-05 2023-01-23 20:18:37.163874: step: 2302/1545, loss: 0.011628524400293827 2023-01-23 20:18:38.055272: step: 2304/1545, loss: 0.00025782344164326787 2023-01-23 20:18:38.958352: step: 2306/1545, loss: 0.000543406989891082 2023-01-23 20:18:39.918457: step: 2308/1545, loss: 0.0003456790582276881 2023-01-23 20:18:40.754471: step: 2310/1545, loss: 0.0001983062829822302 2023-01-23 20:18:41.691281: step: 2312/1545, loss: 0.31721779704093933 2023-01-23 20:18:42.572369: step: 2314/1545, loss: 0.007414679508656263 2023-01-23 20:18:43.445126: step: 2316/1545, loss: 0.06748482584953308 2023-01-23 20:18:44.329040: step: 2318/1545, loss: 0.03993529453873634 2023-01-23 20:18:45.211878: step: 2320/1545, loss: 0.0011612329399213195 2023-01-23 20:18:46.063943: step: 2322/1545, loss: 0.003257723990827799 2023-01-23 20:18:46.935190: step: 2324/1545, loss: 0.03118811920285225 2023-01-23 20:18:47.880072: step: 2326/1545, loss: 0.00017295184079557657 2023-01-23 20:18:48.835440: step: 2328/1545, loss: 0.0007088665151968598 2023-01-23 20:18:49.693740: step: 2330/1545, loss: 0.0009084559278562665 2023-01-23 20:18:50.555124: step: 2332/1545, loss: 0.00013663823483511806 2023-01-23 20:18:51.427156: step: 2334/1545, loss: 0.4208233952522278 2023-01-23 20:18:52.304997: step: 2336/1545, loss: 0.0003278791846241802 2023-01-23 20:18:53.201601: step: 2338/1545, loss: 0.0008801304502412677 2023-01-23 20:18:54.063702: step: 2340/1545, loss: 0.0014646019553765655 2023-01-23 20:18:54.923402: step: 2342/1545, loss: 0.0001076254848157987 2023-01-23 20:18:55.815550: step: 2344/1545, loss: 0.0011897144140675664 2023-01-23 20:18:56.679731: step: 2346/1545, loss: 0.11050459742546082 2023-01-23 20:18:57.615594: step: 2348/1545, loss: 0.032197434455156326 2023-01-23 20:18:58.512952: step: 2350/1545, loss: 0.0003506145440042019 2023-01-23 20:18:59.478210: step: 2352/1545, loss: 0.00745558924973011 2023-01-23 20:19:00.332318: step: 2354/1545, loss: 0.22280697524547577 2023-01-23 20:19:01.158087: step: 2356/1545, loss: 0.00024200185725931078 2023-01-23 20:19:02.108181: step: 2358/1545, loss: 0.0005264509818516672 2023-01-23 20:19:03.024084: step: 2360/1545, loss: 0.006523136515170336 2023-01-23 20:19:03.913075: step: 2362/1545, loss: 0.017009243369102478 2023-01-23 20:19:04.781992: step: 2364/1545, loss: 0.07691121846437454 2023-01-23 20:19:05.655866: step: 2366/1545, loss: 0.0017194527899846435 2023-01-23 20:19:06.641734: step: 2368/1545, loss: 0.0004951140726916492 2023-01-23 20:19:07.557828: step: 2370/1545, loss: 0.02155517227947712 2023-01-23 20:19:08.473274: step: 2372/1545, loss: 0.2064322829246521 2023-01-23 20:19:09.362401: step: 2374/1545, loss: 9.638754272600636e-05 2023-01-23 20:19:10.243923: step: 2376/1545, loss: 0.022886045277118683 2023-01-23 20:19:11.114064: step: 2378/1545, loss: -1.7775191736291163e-06 2023-01-23 20:19:12.010074: step: 2380/1545, loss: 4.5960405259393156e-05 2023-01-23 20:19:12.890721: step: 2382/1545, loss: -5.1873888878617436e-05 2023-01-23 20:19:13.811769: step: 2384/1545, loss: 7.163935515563935e-05 2023-01-23 20:19:14.739287: step: 2386/1545, loss: 0.22628535330295563 2023-01-23 20:19:15.673023: step: 2388/1545, loss: 0.034648995846509933 2023-01-23 20:19:16.553492: step: 2390/1545, loss: 0.02175382897257805 2023-01-23 20:19:17.468015: step: 2392/1545, loss: 6.260631561279297 2023-01-23 20:19:18.368623: step: 2394/1545, loss: 0.06990057229995728 2023-01-23 20:19:19.310203: step: 2396/1545, loss: 0.0018265142571181059 2023-01-23 20:19:20.149475: step: 2398/1545, loss: -3.1042559385241475e-06 2023-01-23 20:19:21.058612: step: 2400/1545, loss: 0.0018694935133680701 2023-01-23 20:19:21.906804: step: 2402/1545, loss: 0.00017499896057415754 2023-01-23 20:19:22.776509: step: 2404/1545, loss: 0.004706658888608217 2023-01-23 20:19:23.677662: step: 2406/1545, loss: 0.0068602790124714375 2023-01-23 20:19:24.534823: step: 2408/1545, loss: 0.002611851552501321 2023-01-23 20:19:25.466462: step: 2410/1545, loss: 0.0009031036752276123 2023-01-23 20:19:26.355570: step: 2412/1545, loss: 0.012813176959753036 2023-01-23 20:19:27.210434: step: 2414/1545, loss: 0.27649566531181335 2023-01-23 20:19:28.068881: step: 2416/1545, loss: 0.052534040063619614 2023-01-23 20:19:28.966525: step: 2418/1545, loss: 0.03394822031259537 2023-01-23 20:19:29.873769: step: 2420/1545, loss: 0.005264969542622566 2023-01-23 20:19:30.731800: step: 2422/1545, loss: 0.005031460430473089 2023-01-23 20:19:31.590227: step: 2424/1545, loss: 0.00037531129783019423 2023-01-23 20:19:32.466393: step: 2426/1545, loss: 5.427364158094861e-06 2023-01-23 20:19:33.339695: step: 2428/1545, loss: 0.0005058994283899665 2023-01-23 20:19:34.204779: step: 2430/1545, loss: 0.8318207263946533 2023-01-23 20:19:35.123836: step: 2432/1545, loss: 0.0005846195854246616 2023-01-23 20:19:35.947667: step: 2434/1545, loss: 0.00033177746809087694 2023-01-23 20:19:36.833149: step: 2436/1545, loss: 0.08847995102405548 2023-01-23 20:19:37.703784: step: 2438/1545, loss: 0.00029780142358504236 2023-01-23 20:19:38.583836: step: 2440/1545, loss: 0.41181525588035583 2023-01-23 20:19:39.460244: step: 2442/1545, loss: 0.03006035089492798 2023-01-23 20:19:40.315799: step: 2444/1545, loss: 0.034835007041692734 2023-01-23 20:19:41.193572: step: 2446/1545, loss: 0.0006163123180158436 2023-01-23 20:19:42.046196: step: 2448/1545, loss: 0.0378524474799633 2023-01-23 20:19:42.952587: step: 2450/1545, loss: 9.844235319178551e-05 2023-01-23 20:19:43.812807: step: 2452/1545, loss: 0.2654207944869995 2023-01-23 20:19:44.724004: step: 2454/1545, loss: 0.001755035831592977 2023-01-23 20:19:45.652788: step: 2456/1545, loss: 0.0007432640413753688 2023-01-23 20:19:46.521446: step: 2458/1545, loss: 0.0020877975039184093 2023-01-23 20:19:47.407545: step: 2460/1545, loss: 0.12157455086708069 2023-01-23 20:19:48.276673: step: 2462/1545, loss: 0.0010152512695640326 2023-01-23 20:19:49.183023: step: 2464/1545, loss: 0.02645890973508358 2023-01-23 20:19:50.062586: step: 2466/1545, loss: 0.123158760368824 2023-01-23 20:19:50.980887: step: 2468/1545, loss: 0.0021758093498647213 2023-01-23 20:19:51.934211: step: 2470/1545, loss: 0.017350148409605026 2023-01-23 20:19:52.795768: step: 2472/1545, loss: 0.017604758962988853 2023-01-23 20:19:53.666800: step: 2474/1545, loss: 0.15599432587623596 2023-01-23 20:19:54.523753: step: 2476/1545, loss: 0.14310762286186218 2023-01-23 20:19:55.390103: step: 2478/1545, loss: 0.00021685060346499085 2023-01-23 20:19:56.248174: step: 2480/1545, loss: 0.0040257698856294155 2023-01-23 20:19:57.111889: step: 2482/1545, loss: 0.004390184301882982 2023-01-23 20:19:58.043802: step: 2484/1545, loss: 0.001409073593094945 2023-01-23 20:19:58.991306: step: 2486/1545, loss: 0.000630536291282624 2023-01-23 20:19:59.865631: step: 2488/1545, loss: 0.007321564015001059 2023-01-23 20:20:00.756110: step: 2490/1545, loss: 0.004637222737073898 2023-01-23 20:20:01.633815: step: 2492/1545, loss: 9.819988190429285e-05 2023-01-23 20:20:02.534570: step: 2494/1545, loss: 0.009016968309879303 2023-01-23 20:20:03.421744: step: 2496/1545, loss: 0.00029766414081677794 2023-01-23 20:20:04.304429: step: 2498/1545, loss: 0.00030256001628004014 2023-01-23 20:20:05.208646: step: 2500/1545, loss: 0.046001136302948 2023-01-23 20:20:06.074027: step: 2502/1545, loss: 0.01113588735461235 2023-01-23 20:20:06.941560: step: 2504/1545, loss: 0.00024705601390451193 2023-01-23 20:20:07.830577: step: 2506/1545, loss: 0.03871998190879822 2023-01-23 20:20:08.711491: step: 2508/1545, loss: 0.04907134175300598 2023-01-23 20:20:09.668295: step: 2510/1545, loss: 0.017215820029377937 2023-01-23 20:20:10.559736: step: 2512/1545, loss: 0.0017874951008707285 2023-01-23 20:20:11.415068: step: 2514/1545, loss: 6.673727330053225e-05 2023-01-23 20:20:12.380210: step: 2516/1545, loss: 0.00010446501983096823 2023-01-23 20:20:13.255876: step: 2518/1545, loss: 0.000758605427108705 2023-01-23 20:20:14.123297: step: 2520/1545, loss: 0.0016768425703048706 2023-01-23 20:20:15.031191: step: 2522/1545, loss: 0.004127185326069593 2023-01-23 20:20:15.901902: step: 2524/1545, loss: 0.0806664526462555 2023-01-23 20:20:16.770878: step: 2526/1545, loss: 8.712508861208335e-05 2023-01-23 20:20:17.694987: step: 2528/1545, loss: 0.00012291574967093766 2023-01-23 20:20:18.621228: step: 2530/1545, loss: 0.0074062468484044075 2023-01-23 20:20:19.469361: step: 2532/1545, loss: 0.0009610899724066257 2023-01-23 20:20:20.331408: step: 2534/1545, loss: 0.030088018625974655 2023-01-23 20:20:21.220523: step: 2536/1545, loss: 0.10148204863071442 2023-01-23 20:20:22.111759: step: 2538/1545, loss: 0.00010856486187549308 2023-01-23 20:20:22.996742: step: 2540/1545, loss: 3.4694028727244586e-05 2023-01-23 20:20:23.890288: step: 2542/1545, loss: 0.005362885072827339 2023-01-23 20:20:24.823264: step: 2544/1545, loss: 0.019014408811926842 2023-01-23 20:20:25.696632: step: 2546/1545, loss: 0.045390013605356216 2023-01-23 20:20:26.578139: step: 2548/1545, loss: 0.11523636430501938 2023-01-23 20:20:27.440928: step: 2550/1545, loss: 1.5871843099594116 2023-01-23 20:20:28.397009: step: 2552/1545, loss: 0.0004250474157743156 2023-01-23 20:20:29.285677: step: 2554/1545, loss: 8.1457088526804e-05 2023-01-23 20:20:30.215311: step: 2556/1545, loss: 0.5618854761123657 2023-01-23 20:20:31.059017: step: 2558/1545, loss: 0.0005379714420996606 2023-01-23 20:20:31.936697: step: 2560/1545, loss: 0.009889848530292511 2023-01-23 20:20:32.798711: step: 2562/1545, loss: 4.257165710441768e-05 2023-01-23 20:20:33.742446: step: 2564/1545, loss: 0.20562970638275146 2023-01-23 20:20:34.638490: step: 2566/1545, loss: 0.2056412398815155 2023-01-23 20:20:35.497889: step: 2568/1545, loss: -9.32269813347375e-07 2023-01-23 20:20:36.365395: step: 2570/1545, loss: 0.5871610641479492 2023-01-23 20:20:37.206016: step: 2572/1545, loss: 0.0016871021362021565 2023-01-23 20:20:38.044451: step: 2574/1545, loss: 0.0027489098720252514 2023-01-23 20:20:38.898255: step: 2576/1545, loss: 0.009643730707466602 2023-01-23 20:20:39.832309: step: 2578/1545, loss: 0.10051410645246506 2023-01-23 20:20:40.753095: step: 2580/1545, loss: 0.04805350676178932 2023-01-23 20:20:41.646968: step: 2582/1545, loss: 0.1075158342719078 2023-01-23 20:20:42.527410: step: 2584/1545, loss: 0.0003266744315624237 2023-01-23 20:20:43.393169: step: 2586/1545, loss: 0.00035799332545138896 2023-01-23 20:20:44.241806: step: 2588/1545, loss: 0.00030006279121153057 2023-01-23 20:20:45.094829: step: 2590/1545, loss: 0.016679586842656136 2023-01-23 20:20:45.998517: step: 2592/1545, loss: 0.21420714259147644 2023-01-23 20:20:46.910232: step: 2594/1545, loss: 0.02058994583785534 2023-01-23 20:20:47.782095: step: 2596/1545, loss: 0.00041204140870831907 2023-01-23 20:20:48.626923: step: 2598/1545, loss: 0.0026829929556697607 2023-01-23 20:20:49.529532: step: 2600/1545, loss: 0.00024701206712052226 2023-01-23 20:20:50.413605: step: 2602/1545, loss: 0.24044451117515564 2023-01-23 20:20:51.346515: step: 2604/1545, loss: 0.006379963364452124 2023-01-23 20:20:52.226768: step: 2606/1545, loss: 0.00860600546002388 2023-01-23 20:20:53.121297: step: 2608/1545, loss: 0.12038354575634003 2023-01-23 20:20:54.044169: step: 2610/1545, loss: 0.004934888333082199 2023-01-23 20:20:54.922837: step: 2612/1545, loss: 0.07319313287734985 2023-01-23 20:20:55.747023: step: 2614/1545, loss: 0.0010667518945410848 2023-01-23 20:20:56.619126: step: 2616/1545, loss: 0.010635213926434517 2023-01-23 20:20:57.497952: step: 2618/1545, loss: 0.0008429369190707803 2023-01-23 20:20:58.383809: step: 2620/1545, loss: 0.31327930092811584 2023-01-23 20:20:59.287554: step: 2622/1545, loss: 2.364913780183997e-05 2023-01-23 20:21:00.198589: step: 2624/1545, loss: 0.05381528288125992 2023-01-23 20:21:01.053391: step: 2626/1545, loss: 0.00011149421334266663 2023-01-23 20:21:01.904638: step: 2628/1545, loss: 0.005750523880124092 2023-01-23 20:21:02.822405: step: 2630/1545, loss: 0.019365765154361725 2023-01-23 20:21:03.678689: step: 2632/1545, loss: 9.059705917024985e-06 2023-01-23 20:21:04.574281: step: 2634/1545, loss: 0.0038382187485694885 2023-01-23 20:21:05.455692: step: 2636/1545, loss: 0.00393375288695097 2023-01-23 20:21:06.328028: step: 2638/1545, loss: 0.00017578598635736853 2023-01-23 20:21:07.264035: step: 2640/1545, loss: 0.0027791927568614483 2023-01-23 20:21:08.093753: step: 2642/1545, loss: 0.009069482795894146 2023-01-23 20:21:08.996142: step: 2644/1545, loss: 0.06535441428422928 2023-01-23 20:21:09.847426: step: 2646/1545, loss: 0.0015063374303281307 2023-01-23 20:21:10.724318: step: 2648/1545, loss: 0.007509925402700901 2023-01-23 20:21:11.648960: step: 2650/1545, loss: 0.4703836739063263 2023-01-23 20:21:12.550069: step: 2652/1545, loss: 0.0017863453831523657 2023-01-23 20:21:13.404135: step: 2654/1545, loss: 0.0018762558465823531 2023-01-23 20:21:14.314661: step: 2656/1545, loss: 0.0024562315084040165 2023-01-23 20:21:15.249734: step: 2658/1545, loss: 0.6119763851165771 2023-01-23 20:21:16.177105: step: 2660/1545, loss: 0.021662011742591858 2023-01-23 20:21:17.068711: step: 2662/1545, loss: 0.00024601665791124105 2023-01-23 20:21:17.965595: step: 2664/1545, loss: 0.00474770599976182 2023-01-23 20:21:18.844104: step: 2666/1545, loss: 0.007959634065628052 2023-01-23 20:21:19.692048: step: 2668/1545, loss: 0.00066499033709988 2023-01-23 20:21:20.565143: step: 2670/1545, loss: 0.000651561189442873 2023-01-23 20:21:21.401833: step: 2672/1545, loss: 0.04442177340388298 2023-01-23 20:21:22.283595: step: 2674/1545, loss: 5.5344262364087626e-05 2023-01-23 20:21:23.148847: step: 2676/1545, loss: 0.005026604980230331 2023-01-23 20:21:24.018744: step: 2678/1545, loss: 0.013179111294448376 2023-01-23 20:21:24.919389: step: 2680/1545, loss: 3.2379273761762306e-05 2023-01-23 20:21:25.789701: step: 2682/1545, loss: 9.597241296432912e-05 2023-01-23 20:21:26.654725: step: 2684/1545, loss: 0.02861182577908039 2023-01-23 20:21:27.525946: step: 2686/1545, loss: 0.09473427385091782 2023-01-23 20:21:28.383607: step: 2688/1545, loss: 0.0014096875675022602 2023-01-23 20:21:29.266490: step: 2690/1545, loss: 0.00030269924900494516 2023-01-23 20:21:30.106220: step: 2692/1545, loss: -1.2770616194757167e-05 2023-01-23 20:21:30.989993: step: 2694/1545, loss: 0.2761135697364807 2023-01-23 20:21:31.845053: step: 2696/1545, loss: 0.002797006396576762 2023-01-23 20:21:32.793753: step: 2698/1545, loss: 0.4356989562511444 2023-01-23 20:21:33.662488: step: 2700/1545, loss: 0.029368679970502853 2023-01-23 20:21:34.539904: step: 2702/1545, loss: 0.0009230535943061113 2023-01-23 20:21:35.415264: step: 2704/1545, loss: 0.00014796839968767017 2023-01-23 20:21:36.280854: step: 2706/1545, loss: 0.000999091425910592 2023-01-23 20:21:37.128966: step: 2708/1545, loss: 0.1806192696094513 2023-01-23 20:21:38.011620: step: 2710/1545, loss: 0.20298413932323456 2023-01-23 20:21:38.890835: step: 2712/1545, loss: 0.04225641489028931 2023-01-23 20:21:39.772082: step: 2714/1545, loss: 0.06399740278720856 2023-01-23 20:21:40.761279: step: 2716/1545, loss: 0.1472659707069397 2023-01-23 20:21:41.688044: step: 2718/1545, loss: 0.0015969173982739449 2023-01-23 20:21:42.590432: step: 2720/1545, loss: -3.2122788979904726e-05 2023-01-23 20:21:43.458928: step: 2722/1545, loss: 0.00010560233931755647 2023-01-23 20:21:44.364994: step: 2724/1545, loss: 0.8419638276100159 2023-01-23 20:21:45.201011: step: 2726/1545, loss: 0.011064382269978523 2023-01-23 20:21:46.038470: step: 2728/1545, loss: 0.0013635167852044106 2023-01-23 20:21:46.928181: step: 2730/1545, loss: 0.002373676747083664 2023-01-23 20:21:47.774154: step: 2732/1545, loss: 5.815525582875125e-05 2023-01-23 20:21:48.652806: step: 2734/1545, loss: 0.0010206097504124045 2023-01-23 20:21:49.551688: step: 2736/1545, loss: 0.01636653207242489 2023-01-23 20:21:50.478965: step: 2738/1545, loss: 0.1254829466342926 2023-01-23 20:21:51.342656: step: 2740/1545, loss: 0.06156846135854721 2023-01-23 20:21:52.256355: step: 2742/1545, loss: 0.1014266312122345 2023-01-23 20:21:53.152638: step: 2744/1545, loss: 0.0029064808040857315 2023-01-23 20:21:54.096700: step: 2746/1545, loss: 7.386390643659979e-05 2023-01-23 20:21:54.974816: step: 2748/1545, loss: 0.02075868286192417 2023-01-23 20:21:55.833359: step: 2750/1545, loss: 0.00042597149149514735 2023-01-23 20:21:56.712717: step: 2752/1545, loss: 0.0004861758789047599 2023-01-23 20:21:57.584947: step: 2754/1545, loss: 0.515935480594635 2023-01-23 20:21:58.447331: step: 2756/1545, loss: 0.008422205224633217 2023-01-23 20:21:59.396555: step: 2758/1545, loss: 0.10701099783182144 2023-01-23 20:22:00.262693: step: 2760/1545, loss: 0.08736997097730637 2023-01-23 20:22:01.163644: step: 2762/1545, loss: 0.06070523336529732 2023-01-23 20:22:02.031218: step: 2764/1545, loss: 5.2140581829007715e-05 2023-01-23 20:22:02.876406: step: 2766/1545, loss: 0.00020691232930403203 2023-01-23 20:22:03.763698: step: 2768/1545, loss: 0.0002661180042196065 2023-01-23 20:22:04.678355: step: 2770/1545, loss: 0.0004315153637435287 2023-01-23 20:22:05.562401: step: 2772/1545, loss: 4.637339952751063e-05 2023-01-23 20:22:06.451576: step: 2774/1545, loss: 0.13087493181228638 2023-01-23 20:22:07.297515: step: 2776/1545, loss: 5.791087824036367e-05 2023-01-23 20:22:08.168477: step: 2778/1545, loss: 0.04983368143439293 2023-01-23 20:22:09.076189: step: 2780/1545, loss: 0.06877905130386353 2023-01-23 20:22:10.032586: step: 2782/1545, loss: 0.018810926005244255 2023-01-23 20:22:10.999263: step: 2784/1545, loss: 0.0013527192641049623 2023-01-23 20:22:11.877957: step: 2786/1545, loss: 0.0008248496451415122 2023-01-23 20:22:12.740389: step: 2788/1545, loss: 0.0013860076433047652 2023-01-23 20:22:13.611211: step: 2790/1545, loss: 0.04756670072674751 2023-01-23 20:22:14.578016: step: 2792/1545, loss: 0.05048763379454613 2023-01-23 20:22:15.412656: step: 2794/1545, loss: 0.0008908355375751853 2023-01-23 20:22:16.320266: step: 2796/1545, loss: 0.0083624217659235 2023-01-23 20:22:17.223616: step: 2798/1545, loss: 0.005669435951858759 2023-01-23 20:22:18.154695: step: 2800/1545, loss: 0.00923994742333889 2023-01-23 20:22:19.065728: step: 2802/1545, loss: 0.015712685883045197 2023-01-23 20:22:19.933313: step: 2804/1545, loss: 0.7712292671203613 2023-01-23 20:22:20.800379: step: 2806/1545, loss: 0.0019476787419989705 2023-01-23 20:22:21.657640: step: 2808/1545, loss: 0.0020284531638026237 2023-01-23 20:22:22.547918: step: 2810/1545, loss: 0.016713064163923264 2023-01-23 20:22:23.446731: step: 2812/1545, loss: 0.00150723394472152 2023-01-23 20:22:24.341160: step: 2814/1545, loss: 0.005965988151729107 2023-01-23 20:22:25.285398: step: 2816/1545, loss: 0.007918249815702438 2023-01-23 20:22:26.170840: step: 2818/1545, loss: 0.07270269840955734 2023-01-23 20:22:27.014872: step: 2820/1545, loss: 0.11289554089307785 2023-01-23 20:22:27.856387: step: 2822/1545, loss: 0.0004576940555125475 2023-01-23 20:22:28.720773: step: 2824/1545, loss: 0.0019313887460157275 2023-01-23 20:22:29.618868: step: 2826/1545, loss: 0.0002970831701532006 2023-01-23 20:22:30.458624: step: 2828/1545, loss: 0.013638220727443695 2023-01-23 20:22:31.304118: step: 2830/1545, loss: 0.2205304503440857 2023-01-23 20:22:32.147589: step: 2832/1545, loss: 0.0007208256865851581 2023-01-23 20:22:33.068498: step: 2834/1545, loss: 0.0012019859859719872 2023-01-23 20:22:34.003064: step: 2836/1545, loss: 0.00540868379175663 2023-01-23 20:22:34.854967: step: 2838/1545, loss: 0.0018250159919261932 2023-01-23 20:22:35.788738: step: 2840/1545, loss: 0.08203205466270447 2023-01-23 20:22:36.691773: step: 2842/1545, loss: 0.005852865055203438 2023-01-23 20:22:37.547652: step: 2844/1545, loss: 0.11327607184648514 2023-01-23 20:22:38.413186: step: 2846/1545, loss: 0.10929323732852936 2023-01-23 20:22:39.288006: step: 2848/1545, loss: 0.0004020273045171052 2023-01-23 20:22:40.150062: step: 2850/1545, loss: 0.0011583516607061028 2023-01-23 20:22:41.066750: step: 2852/1545, loss: 0.0004460597119759768 2023-01-23 20:22:41.926882: step: 2854/1545, loss: 0.026302389800548553 2023-01-23 20:22:42.809152: step: 2856/1545, loss: 0.04370442405343056 2023-01-23 20:22:43.682321: step: 2858/1545, loss: 0.005742186680436134 2023-01-23 20:22:44.581208: step: 2860/1545, loss: 0.009858516044914722 2023-01-23 20:22:45.486889: step: 2862/1545, loss: 0.0002590990625321865 2023-01-23 20:22:46.374580: step: 2864/1545, loss: 0.009271510876715183 2023-01-23 20:22:47.235079: step: 2866/1545, loss: 0.00079713313607499 2023-01-23 20:22:48.183912: step: 2868/1545, loss: 0.00204560742713511 2023-01-23 20:22:49.087529: step: 2870/1545, loss: 0.00046069748350419104 2023-01-23 20:22:49.925396: step: 2872/1545, loss: 0.05206892639398575 2023-01-23 20:22:50.845237: step: 2874/1545, loss: 0.004967675544321537 2023-01-23 20:22:51.752169: step: 2876/1545, loss: 0.00721344631165266 2023-01-23 20:22:52.620593: step: 2878/1545, loss: 0.4015563130378723 2023-01-23 20:22:53.597709: step: 2880/1545, loss: 0.08905406296253204 2023-01-23 20:22:54.457323: step: 2882/1545, loss: 0.050843849778175354 2023-01-23 20:22:55.364143: step: 2884/1545, loss: 0.0031520621851086617 2023-01-23 20:22:56.276359: step: 2886/1545, loss: 0.00013259252591524273 2023-01-23 20:22:57.144033: step: 2888/1545, loss: 0.206429585814476 2023-01-23 20:22:57.996977: step: 2890/1545, loss: 0.055540718138217926 2023-01-23 20:22:58.953562: step: 2892/1545, loss: 0.00021196631132625043 2023-01-23 20:22:59.809142: step: 2894/1545, loss: 0.0012383630964905024 2023-01-23 20:23:00.694266: step: 2896/1545, loss: 0.03111811727285385 2023-01-23 20:23:01.596019: step: 2898/1545, loss: 0.019481029361486435 2023-01-23 20:23:02.528613: step: 2900/1545, loss: 0.001937767374329269 2023-01-23 20:23:03.428811: step: 2902/1545, loss: 0.01067359559237957 2023-01-23 20:23:04.328742: step: 2904/1545, loss: 0.0017612482188269496 2023-01-23 20:23:05.223384: step: 2906/1545, loss: 0.006115744821727276 2023-01-23 20:23:06.131185: step: 2908/1545, loss: 0.004123165737837553 2023-01-23 20:23:07.007562: step: 2910/1545, loss: 0.1379113495349884 2023-01-23 20:23:07.884387: step: 2912/1545, loss: 0.0038451470900326967 2023-01-23 20:23:08.742214: step: 2914/1545, loss: 0.0023601704742759466 2023-01-23 20:23:09.639453: step: 2916/1545, loss: 0.051288243383169174 2023-01-23 20:23:10.565706: step: 2918/1545, loss: 0.0014784015947952867 2023-01-23 20:23:11.410712: step: 2920/1545, loss: 0.0002498168614692986 2023-01-23 20:23:12.311876: step: 2922/1545, loss: 0.10276265442371368 2023-01-23 20:23:13.173479: step: 2924/1545, loss: 0.0012995502911508083 2023-01-23 20:23:14.087933: step: 2926/1545, loss: 0.004330829717218876 2023-01-23 20:23:14.950578: step: 2928/1545, loss: 9.03951731743291e-05 2023-01-23 20:23:15.861405: step: 2930/1545, loss: 0.002624426269903779 2023-01-23 20:23:16.742119: step: 2932/1545, loss: 0.12117013335227966 2023-01-23 20:23:17.618733: step: 2934/1545, loss: 0.0012310004094615579 2023-01-23 20:23:18.475116: step: 2936/1545, loss: 0.0009871299844235182 2023-01-23 20:23:19.336730: step: 2938/1545, loss: 0.00016131284064613283 2023-01-23 20:23:20.206660: step: 2940/1545, loss: 0.011094067245721817 2023-01-23 20:23:21.108757: step: 2942/1545, loss: 0.002028667600825429 2023-01-23 20:23:22.011880: step: 2944/1545, loss: 0.0021373906638473272 2023-01-23 20:23:22.920379: step: 2946/1545, loss: 0.025877151638269424 2023-01-23 20:23:23.826823: step: 2948/1545, loss: 9.409186532138847e-06 2023-01-23 20:23:24.801783: step: 2950/1545, loss: 0.0003031965170521289 2023-01-23 20:23:25.666836: step: 2952/1545, loss: 0.6195151209831238 2023-01-23 20:23:26.553408: step: 2954/1545, loss: 0.016664182767271996 2023-01-23 20:23:27.408798: step: 2956/1545, loss: 0.00915738008916378 2023-01-23 20:23:28.235870: step: 2958/1545, loss: 0.00010813056724146008 2023-01-23 20:23:29.043412: step: 2960/1545, loss: 0.0018000224372372031 2023-01-23 20:23:29.935871: step: 2962/1545, loss: -3.797233512159437e-05 2023-01-23 20:23:30.793690: step: 2964/1545, loss: 0.07449114322662354 2023-01-23 20:23:31.664814: step: 2966/1545, loss: 7.336374983424321e-05 2023-01-23 20:23:32.535275: step: 2968/1545, loss: 0.0014292291598394513 2023-01-23 20:23:33.396649: step: 2970/1545, loss: 0.00047948621795512736 2023-01-23 20:23:34.252414: step: 2972/1545, loss: 0.000308836781186983 2023-01-23 20:23:35.165264: step: 2974/1545, loss: 0.044024061411619186 2023-01-23 20:23:36.065827: step: 2976/1545, loss: 0.0006456116680055857 2023-01-23 20:23:36.943643: step: 2978/1545, loss: 0.004230601247400045 2023-01-23 20:23:37.802148: step: 2980/1545, loss: 9.674907232692931e-06 2023-01-23 20:23:38.701177: step: 2982/1545, loss: 6.10322313150391e-05 2023-01-23 20:23:39.531658: step: 2984/1545, loss: 0.0002809087745845318 2023-01-23 20:23:40.388215: step: 2986/1545, loss: 0.00022703278227709234 2023-01-23 20:23:41.267919: step: 2988/1545, loss: 0.0004993454203940928 2023-01-23 20:23:42.193427: step: 2990/1545, loss: 0.0014691625256091356 2023-01-23 20:23:43.047941: step: 2992/1545, loss: 0.07014702260494232 2023-01-23 20:23:43.917713: step: 2994/1545, loss: 0.0018658079206943512 2023-01-23 20:23:44.813408: step: 2996/1545, loss: 0.03929615393280983 2023-01-23 20:23:45.716231: step: 2998/1545, loss: 0.001140120206400752 2023-01-23 20:23:46.574267: step: 3000/1545, loss: 0.00010636955266818404 2023-01-23 20:23:47.519883: step: 3002/1545, loss: 0.009960353374481201 2023-01-23 20:23:48.403222: step: 3004/1545, loss: 1.8722812455962412e-05 2023-01-23 20:23:49.325941: step: 3006/1545, loss: 0.00046777346869930625 2023-01-23 20:23:50.207085: step: 3008/1545, loss: 0.00013815113925375044 2023-01-23 20:23:51.057079: step: 3010/1545, loss: 0.0006320569664239883 2023-01-23 20:23:51.895906: step: 3012/1545, loss: 0.020056074485182762 2023-01-23 20:23:52.769956: step: 3014/1545, loss: 9.844601299846545e-05 2023-01-23 20:23:53.656531: step: 3016/1545, loss: 0.0004520222428254783 2023-01-23 20:23:54.563337: step: 3018/1545, loss: 0.00026421857182867825 2023-01-23 20:23:55.442634: step: 3020/1545, loss: 0.06761465221643448 2023-01-23 20:23:56.314790: step: 3022/1545, loss: 3.901799937011674e-05 2023-01-23 20:23:57.219846: step: 3024/1545, loss: 0.11822612583637238 2023-01-23 20:23:58.142834: step: 3026/1545, loss: 0.0043317279778420925 2023-01-23 20:23:59.027504: step: 3028/1545, loss: 0.6367215514183044 2023-01-23 20:23:59.923730: step: 3030/1545, loss: 0.0003020546573679894 2023-01-23 20:24:00.773094: step: 3032/1545, loss: 0.017351046204566956 2023-01-23 20:24:01.647714: step: 3034/1545, loss: 0.00019551337754819542 2023-01-23 20:24:02.528201: step: 3036/1545, loss: 0.000693605572450906 2023-01-23 20:24:03.399260: step: 3038/1545, loss: 8.841660746838897e-05 2023-01-23 20:24:04.242571: step: 3040/1545, loss: 0.00247995276004076 2023-01-23 20:24:05.152193: step: 3042/1545, loss: 0.0015620217891409993 2023-01-23 20:24:06.066244: step: 3044/1545, loss: 0.01357526145875454 2023-01-23 20:24:06.918080: step: 3046/1545, loss: 0.04231236129999161 2023-01-23 20:24:07.755605: step: 3048/1545, loss: 0.013157128356397152 2023-01-23 20:24:08.608374: step: 3050/1545, loss: 0.00010313272650819272 2023-01-23 20:24:09.538432: step: 3052/1545, loss: 0.0015842155553400517 2023-01-23 20:24:10.438000: step: 3054/1545, loss: 0.013130180537700653 2023-01-23 20:24:11.344696: step: 3056/1545, loss: 0.2380038946866989 2023-01-23 20:24:12.290964: step: 3058/1545, loss: 0.0004852995334658772 2023-01-23 20:24:13.127259: step: 3060/1545, loss: 0.1358855813741684 2023-01-23 20:24:14.025801: step: 3062/1545, loss: 0.4232354164123535 2023-01-23 20:24:14.941051: step: 3064/1545, loss: 7.332091627176851e-06 2023-01-23 20:24:15.816891: step: 3066/1545, loss: 0.00013171050522942096 2023-01-23 20:24:16.712941: step: 3068/1545, loss: -1.554445771034807e-05 2023-01-23 20:24:17.580433: step: 3070/1545, loss: 4.993244874640368e-05 2023-01-23 20:24:18.446992: step: 3072/1545, loss: 0.003799506463110447 2023-01-23 20:24:19.419990: step: 3074/1545, loss: 8.157345291692764e-06 2023-01-23 20:24:20.299617: step: 3076/1545, loss: 0.048502642661333084 2023-01-23 20:24:21.180900: step: 3078/1545, loss: 0.06925970315933228 2023-01-23 20:24:22.113361: step: 3080/1545, loss: 0.06378588080406189 2023-01-23 20:24:22.992504: step: 3082/1545, loss: 0.46082764863967896 2023-01-23 20:24:23.832412: step: 3084/1545, loss: 0.02799302525818348 2023-01-23 20:24:24.747062: step: 3086/1545, loss: 0.10243058949708939 2023-01-23 20:24:25.623288: step: 3088/1545, loss: 0.00012577485176734626 2023-01-23 20:24:26.504460: step: 3090/1545, loss: 0.0044409772381186485 ================================================== Loss: 0.049 -------------------- Dev Chinese: {'event': {'p': 0.6019629225736096, 'r': 0.7350199733688415, 'f1': 0.6618705035971223}, 'argument': {'p': 0.6768856506816677, 'r': 0.6515909701629208, 'f1': 0.6639975004402042}, 'combined': 0.4394803600035884, 'epoch': 32} Test Chinese: {'event': {'p': 0.6430096051227321, 'r': 0.770460358056266, 'f1': 0.7009889470622455}, 'argument': {'p': 0.7188174928872716, 'r': 0.7075602288657368, 'f1': 0.7131444385641958}, 'combined': 0.4999063690924118, 'epoch': 32} Dev Korean: {'event': {'p': 0.6094091903719913, 'r': 0.7416777629826897, 'f1': 0.669069069069069}, 'argument': {'p': 0.6792670818181646, 'r': 0.6527491476931312, 'f1': 0.6657441536962104}, 'combined': 0.44542882115169874, 'epoch': 32} Test Korean: {'event': {'p': 0.6338624338624339, 'r': 0.7659846547314578, 'f1': 0.6936884771279677}, 'argument': {'p': 0.7140723622898609, 'r': 0.7045259403341141, 'f1': 0.7092670301075603}, 'combined': 0.4920103659923899, 'epoch': 32} Dev Russian: {'event': {'p': 0.5688976377952756, 'r': 0.7696404793608522, 'f1': 0.6542161856253538}, 'argument': {'p': 0.6814615854379754, 'r': 0.6614759452355741, 'f1': 0.6713200518615844}, 'combined': 0.43918844366270043, 'epoch': 32} Test Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7217740480829588, 'r': 0.7190707744946331, 'f1': 0.720419875384867}, 'combined': 0.5083892707840562, 'epoch': 32} Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.699276418026418, 'r': 0.6010309708656816, 'f1': 0.6464421997755332}, 'combined': 0.4701397816549333, 'epoch': 32} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6967960023515579, 'r': 0.5154381387258099, 'f1': 0.5925509311336083}, 'combined': 0.36384706297677705, 'epoch': 32} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5467097046336813, 'r': 0.5271843580396213, 'f1': 0.5367695281857962}, 'combined': 0.3125493455259066, 'epoch': 32} New best chinese model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.6019629225736096, 'r': 0.7350199733688415, 'f1': 0.6618705035971223}, 'argument': {'p': 0.6768856506816677, 'r': 0.6515909701629208, 'f1': 0.6639975004402042}, 'combined': 0.4394803600035884, 'epoch': 32} Test for Chinese: {'event': {'p': 0.6430096051227321, 'r': 0.770460358056266, 'f1': 0.7009889470622455}, 'argument': {'p': 0.7188174928872716, 'r': 0.7075602288657368, 'f1': 0.7131444385641958}, 'combined': 0.4999063690924118, 'epoch': 32} Chinese: {'event': {'p': 0.6153846153846154, 'r': 0.8888888888888888, 'f1': 0.7272727272727274}, 'argument': {'p': 0.699276418026418, 'r': 0.6010309708656816, 'f1': 0.6464421997755332}, 'combined': 0.4701397816549333, 'epoch': 32} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 33 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 20:29:46.205802: step: 2/1545, loss: 0.1391550600528717 2023-01-23 20:29:47.165186: step: 4/1545, loss: 0.004901042208075523 2023-01-23 20:29:48.074061: step: 6/1545, loss: 0.06397296488285065 2023-01-23 20:29:48.973023: step: 8/1545, loss: 0.0011224026093259454 2023-01-23 20:29:49.878455: step: 10/1545, loss: -7.64037758926861e-05 2023-01-23 20:29:50.728824: step: 12/1545, loss: 3.5963079426437616e-05 2023-01-23 20:29:51.570297: step: 14/1545, loss: 0.0002543702139519155 2023-01-23 20:29:52.415051: step: 16/1545, loss: 2.8035647119395435e-05 2023-01-23 20:29:53.251383: step: 18/1545, loss: 0.01008440088480711 2023-01-23 20:29:54.109727: step: 20/1545, loss: 0.000531629950273782 2023-01-23 20:29:55.019203: step: 22/1545, loss: 0.04274652898311615 2023-01-23 20:29:55.893557: step: 24/1545, loss: 0.0011227017967030406 2023-01-23 20:29:56.766293: step: 26/1545, loss: 4.343140608398244e-05 2023-01-23 20:29:57.650472: step: 28/1545, loss: 0.45833665132522583 2023-01-23 20:29:58.528745: step: 30/1545, loss: 0.0034836716949939728 2023-01-23 20:29:59.435330: step: 32/1545, loss: 0.021884514018893242 2023-01-23 20:30:00.316298: step: 34/1545, loss: 0.02781733125448227 2023-01-23 20:30:01.195320: step: 36/1545, loss: 0.0026528032030910254 2023-01-23 20:30:02.079575: step: 38/1545, loss: 0.0006226105615496635 2023-01-23 20:30:02.957017: step: 40/1545, loss: 0.0008720437181182206 2023-01-23 20:30:03.857512: step: 42/1545, loss: 0.00011985450692009181 2023-01-23 20:30:04.745826: step: 44/1545, loss: 0.00032384382211603224 2023-01-23 20:30:05.656448: step: 46/1545, loss: 0.003198652295395732 2023-01-23 20:30:06.529651: step: 48/1545, loss: 0.070436991751194 2023-01-23 20:30:07.361868: step: 50/1545, loss: 0.000573660247027874 2023-01-23 20:30:08.235669: step: 52/1545, loss: 0.006078777369111776 2023-01-23 20:30:09.105525: step: 54/1545, loss: 1.7515310901217163e-05 2023-01-23 20:30:10.003512: step: 56/1545, loss: 0.0018140588654205203 2023-01-23 20:30:10.890141: step: 58/1545, loss: -2.50866032729391e-05 2023-01-23 20:30:11.736507: step: 60/1545, loss: 0.0002092620707117021 2023-01-23 20:30:12.612060: step: 62/1545, loss: 0.0147763816639781 2023-01-23 20:30:13.477666: step: 64/1545, loss: 0.0007887586252763867 2023-01-23 20:30:14.355596: step: 66/1545, loss: 0.021362919360399246 2023-01-23 20:30:15.242143: step: 68/1545, loss: 0.008592482656240463 2023-01-23 20:30:16.077014: step: 70/1545, loss: 6.994409886829089e-06 2023-01-23 20:30:16.977266: step: 72/1545, loss: 0.00015617519966326654 2023-01-23 20:30:17.837113: step: 74/1545, loss: 0.00011185956827830523 2023-01-23 20:30:18.717529: step: 76/1545, loss: 0.00016530536231584847 2023-01-23 20:30:19.658958: step: 78/1545, loss: 0.07288775593042374 2023-01-23 20:30:20.498085: step: 80/1545, loss: 0.0014239456504583359 2023-01-23 20:30:21.363980: step: 82/1545, loss: -1.360293390462175e-05 2023-01-23 20:30:22.218988: step: 84/1545, loss: 0.007464972324669361 2023-01-23 20:30:23.094284: step: 86/1545, loss: 0.0017370610730722547 2023-01-23 20:30:23.967010: step: 88/1545, loss: 0.0010668712202459574 2023-01-23 20:30:24.842031: step: 90/1545, loss: 3.655645559774712e-05 2023-01-23 20:30:25.733289: step: 92/1545, loss: 0.06009809672832489 2023-01-23 20:30:26.595106: step: 94/1545, loss: 0.03546992689371109 2023-01-23 20:30:27.472334: step: 96/1545, loss: 2.3100594262359664e-05 2023-01-23 20:30:28.316205: step: 98/1545, loss: 0.0006407732143998146 2023-01-23 20:30:29.169738: step: 100/1545, loss: 0.08409009873867035 2023-01-23 20:30:30.006353: step: 102/1545, loss: 2.795448381220922e-05 2023-01-23 20:30:30.885676: step: 104/1545, loss: 0.01198419276624918 2023-01-23 20:30:31.732001: step: 106/1545, loss: 4.7123179683694616e-05 2023-01-23 20:30:32.556778: step: 108/1545, loss: 1.6928775039559696e-06 2023-01-23 20:30:33.444839: step: 110/1545, loss: 0.00538621935993433 2023-01-23 20:30:34.328490: step: 112/1545, loss: 0.004421853460371494 2023-01-23 20:30:35.201008: step: 114/1545, loss: 0.07579652965068817 2023-01-23 20:30:36.100680: step: 116/1545, loss: 0.05467831343412399 2023-01-23 20:30:36.977092: step: 118/1545, loss: 0.016354471445083618 2023-01-23 20:30:37.837929: step: 120/1545, loss: 0.005052268039435148 2023-01-23 20:30:38.700677: step: 122/1545, loss: 0.06197492033243179 2023-01-23 20:30:39.564248: step: 124/1545, loss: 0.00041544268606230617 2023-01-23 20:30:40.510463: step: 126/1545, loss: -1.2467801752791274e-05 2023-01-23 20:30:41.533619: step: 128/1545, loss: 0.000846334092784673 2023-01-23 20:30:42.443812: step: 130/1545, loss: 0.005243901629000902 2023-01-23 20:30:43.343006: step: 132/1545, loss: 7.708749762969092e-05 2023-01-23 20:30:44.236387: step: 134/1545, loss: 0.3189750015735626 2023-01-23 20:30:45.131929: step: 136/1545, loss: 0.013360206037759781 2023-01-23 20:30:45.998044: step: 138/1545, loss: 8.879073720891029e-05 2023-01-23 20:30:46.980308: step: 140/1545, loss: 0.001615889254026115 2023-01-23 20:30:47.878951: step: 142/1545, loss: 0.0013882052153348923 2023-01-23 20:30:48.726047: step: 144/1545, loss: 0.12843206524848938 2023-01-23 20:30:49.641233: step: 146/1545, loss: 0.014015781693160534 2023-01-23 20:30:50.535800: step: 148/1545, loss: 9.20581805985421e-05 2023-01-23 20:30:51.411142: step: 150/1545, loss: 0.001497805118560791 2023-01-23 20:30:52.280803: step: 152/1545, loss: 0.22058768570423126 2023-01-23 20:30:53.146992: step: 154/1545, loss: 0.20611098408699036 2023-01-23 20:30:54.020121: step: 156/1545, loss: 0.000243452814174816 2023-01-23 20:30:54.896862: step: 158/1545, loss: 0.0005098256515339017 2023-01-23 20:30:55.748989: step: 160/1545, loss: 0.0001180269755423069 2023-01-23 20:30:56.618058: step: 162/1545, loss: -1.8266780898557045e-05 2023-01-23 20:30:57.561829: step: 164/1545, loss: 0.013686076737940311 2023-01-23 20:30:58.454321: step: 166/1545, loss: 0.0001387159718433395 2023-01-23 20:30:59.330961: step: 168/1545, loss: 0.0002569028874859214 2023-01-23 20:31:00.226030: step: 170/1545, loss: 0.12478090077638626 2023-01-23 20:31:01.103505: step: 172/1545, loss: 0.00125824601855129 2023-01-23 20:31:01.957749: step: 174/1545, loss: 0.001955534564331174 2023-01-23 20:31:02.912829: step: 176/1545, loss: 0.21445247530937195 2023-01-23 20:31:03.785117: step: 178/1545, loss: 0.0017187531339004636 2023-01-23 20:31:04.790878: step: 180/1545, loss: 0.2543319761753082 2023-01-23 20:31:05.682475: step: 182/1545, loss: 0.01224000845104456 2023-01-23 20:31:06.569714: step: 184/1545, loss: 0.24740095436573029 2023-01-23 20:31:07.447529: step: 186/1545, loss: 4.474960223888047e-05 2023-01-23 20:31:08.322906: step: 188/1545, loss: 4.339829320088029e-05 2023-01-23 20:31:09.217462: step: 190/1545, loss: 1.2033560276031494 2023-01-23 20:31:10.170850: step: 192/1545, loss: 0.09671793133020401 2023-01-23 20:31:11.029989: step: 194/1545, loss: 0.03492338955402374 2023-01-23 20:31:11.958000: step: 196/1545, loss: 0.00016820739256218076 2023-01-23 20:31:12.821051: step: 198/1545, loss: 0.0022919103503227234 2023-01-23 20:31:13.694961: step: 200/1545, loss: 2.3954349671839736e-05 2023-01-23 20:31:14.555561: step: 202/1545, loss: 0.0002610156370792538 2023-01-23 20:31:15.466147: step: 204/1545, loss: 0.00013061675417702645 2023-01-23 20:31:16.329679: step: 206/1545, loss: 0.31455856561660767 2023-01-23 20:31:17.204583: step: 208/1545, loss: 0.03165541961789131 2023-01-23 20:31:18.125228: step: 210/1545, loss: 1.0711541175842285 2023-01-23 20:31:19.020413: step: 212/1545, loss: 0.00013653188943862915 2023-01-23 20:31:19.910122: step: 214/1545, loss: 0.0007679014815948904 2023-01-23 20:31:20.896067: step: 216/1545, loss: -4.302329216443468e-06 2023-01-23 20:31:21.771079: step: 218/1545, loss: 0.0168891754001379 2023-01-23 20:31:22.692487: step: 220/1545, loss: 3.6731347790919244e-05 2023-01-23 20:31:23.614956: step: 222/1545, loss: 0.041202712804079056 2023-01-23 20:31:24.513739: step: 224/1545, loss: 0.018786994740366936 2023-01-23 20:31:25.446957: step: 226/1545, loss: 0.19678345322608948 2023-01-23 20:31:26.319892: step: 228/1545, loss: 0.0006560060428455472 2023-01-23 20:31:27.229799: step: 230/1545, loss: 0.0007396684377454221 2023-01-23 20:31:28.145119: step: 232/1545, loss: 0.002467526588588953 2023-01-23 20:31:29.053475: step: 234/1545, loss: 0.0005899796378798783 2023-01-23 20:31:29.917205: step: 236/1545, loss: 0.0010277203982695937 2023-01-23 20:31:30.840310: step: 238/1545, loss: 0.0006222862284630537 2023-01-23 20:31:31.690988: step: 240/1545, loss: 0.06839596480131149 2023-01-23 20:31:32.606912: step: 242/1545, loss: 0.057280682027339935 2023-01-23 20:31:33.534115: step: 244/1545, loss: 4.222491043037735e-06 2023-01-23 20:31:34.438836: step: 246/1545, loss: 0.3289473056793213 2023-01-23 20:31:35.340265: step: 248/1545, loss: 0.0016551573062315583 2023-01-23 20:31:36.243628: step: 250/1545, loss: 0.25612208247184753 2023-01-23 20:31:37.145237: step: 252/1545, loss: 0.0010365236084908247 2023-01-23 20:31:38.057369: step: 254/1545, loss: 0.0471949465572834 2023-01-23 20:31:38.969199: step: 256/1545, loss: 0.011403420940041542 2023-01-23 20:31:39.815095: step: 258/1545, loss: 0.22596286237239838 2023-01-23 20:31:40.690329: step: 260/1545, loss: 0.0012699977960437536 2023-01-23 20:31:41.599578: step: 262/1545, loss: 0.03636876121163368 2023-01-23 20:31:42.462458: step: 264/1545, loss: 0.08053955435752869 2023-01-23 20:31:43.351974: step: 266/1545, loss: 0.004581470508128405 2023-01-23 20:31:44.214997: step: 268/1545, loss: 0.0003116315638180822 2023-01-23 20:31:45.092211: step: 270/1545, loss: 0.05368926748633385 2023-01-23 20:31:45.978500: step: 272/1545, loss: 0.08542908728122711 2023-01-23 20:31:46.867122: step: 274/1545, loss: 0.09820719808340073 2023-01-23 20:31:47.734501: step: 276/1545, loss: 0.17656919360160828 2023-01-23 20:31:48.622087: step: 278/1545, loss: 0.11662235856056213 2023-01-23 20:31:49.502319: step: 280/1545, loss: 0.028993401676416397 2023-01-23 20:31:50.396201: step: 282/1545, loss: 0.00023210627841763198 2023-01-23 20:31:51.272583: step: 284/1545, loss: 0.0037929180543869734 2023-01-23 20:31:52.138309: step: 286/1545, loss: 0.11251659691333771 2023-01-23 20:31:52.988906: step: 288/1545, loss: 0.0007890027482062578 2023-01-23 20:31:53.854201: step: 290/1545, loss: 0.007612502668052912 2023-01-23 20:31:54.760422: step: 292/1545, loss: 0.001668327720835805 2023-01-23 20:31:55.595130: step: 294/1545, loss: 0.03760584443807602 2023-01-23 20:31:56.519654: step: 296/1545, loss: 0.4345760941505432 2023-01-23 20:31:57.416862: step: 298/1545, loss: 0.0006190894637256861 2023-01-23 20:31:58.302561: step: 300/1545, loss: 0.139438197016716 2023-01-23 20:31:59.191003: step: 302/1545, loss: 0.0003882974269799888 2023-01-23 20:32:00.114796: step: 304/1545, loss: 0.0001429715775884688 2023-01-23 20:32:00.990979: step: 306/1545, loss: 0.0294529739767313 2023-01-23 20:32:01.848291: step: 308/1545, loss: 0.04081185162067413 2023-01-23 20:32:02.746859: step: 310/1545, loss: 0.2169538140296936 2023-01-23 20:32:03.633908: step: 312/1545, loss: 0.0022420494351536036 2023-01-23 20:32:04.492221: step: 314/1545, loss: 0.00011312861170154065 2023-01-23 20:32:05.340036: step: 316/1545, loss: 0.14649009704589844 2023-01-23 20:32:06.277932: step: 318/1545, loss: 0.00020527574815787375 2023-01-23 20:32:07.191794: step: 320/1545, loss: 0.007998785004019737 2023-01-23 20:32:08.111139: step: 322/1545, loss: 0.006878496613353491 2023-01-23 20:32:08.970994: step: 324/1545, loss: 0.00013354716065805405 2023-01-23 20:32:09.913132: step: 326/1545, loss: 0.002759713213890791 2023-01-23 20:32:10.756867: step: 328/1545, loss: 0.0007190174655988812 2023-01-23 20:32:11.630047: step: 330/1545, loss: 0.09900062531232834 2023-01-23 20:32:12.505372: step: 332/1545, loss: 0.004073786549270153 2023-01-23 20:32:13.388836: step: 334/1545, loss: 0.11105311661958694 2023-01-23 20:32:14.243825: step: 336/1545, loss: 0.000747025478631258 2023-01-23 20:32:15.125223: step: 338/1545, loss: 0.015646863728761673 2023-01-23 20:32:16.041987: step: 340/1545, loss: 0.30354130268096924 2023-01-23 20:32:16.905940: step: 342/1545, loss: 0.006994539871811867 2023-01-23 20:32:17.803891: step: 344/1545, loss: 0.5607782602310181 2023-01-23 20:32:18.663407: step: 346/1545, loss: 0.12906965613365173 2023-01-23 20:32:19.507568: step: 348/1545, loss: 1.8779186575557105e-05 2023-01-23 20:32:20.373917: step: 350/1545, loss: 0.00250220182351768 2023-01-23 20:32:21.276057: step: 352/1545, loss: 0.015656474977731705 2023-01-23 20:32:22.185416: step: 354/1545, loss: 0.000124311976833269 2023-01-23 20:32:23.052260: step: 356/1545, loss: 0.0032999226823449135 2023-01-23 20:32:23.918866: step: 358/1545, loss: 0.00320525374263525 2023-01-23 20:32:24.781670: step: 360/1545, loss: 0.03766149282455444 2023-01-23 20:32:25.675966: step: 362/1545, loss: 0.0001145820424426347 2023-01-23 20:32:26.523216: step: 364/1545, loss: 0.000854545331094414 2023-01-23 20:32:27.392639: step: 366/1545, loss: 0.00016014753782656044 2023-01-23 20:32:28.255542: step: 368/1545, loss: 0.0002645305066835135 2023-01-23 20:32:29.128888: step: 370/1545, loss: 0.3421217203140259 2023-01-23 20:32:30.005790: step: 372/1545, loss: 0.00010082268272526562 2023-01-23 20:32:30.910082: step: 374/1545, loss: 0.0011301470221951604 2023-01-23 20:32:31.767302: step: 376/1545, loss: 0.00021600334730464965 2023-01-23 20:32:32.674153: step: 378/1545, loss: 0.001150236465036869 2023-01-23 20:32:33.571832: step: 380/1545, loss: 0.0019352211384102702 2023-01-23 20:32:34.522146: step: 382/1545, loss: 0.16938388347625732 2023-01-23 20:32:35.396005: step: 384/1545, loss: 0.17532028257846832 2023-01-23 20:32:36.281444: step: 386/1545, loss: 0.04264554753899574 2023-01-23 20:32:37.149805: step: 388/1545, loss: 0.000188169302418828 2023-01-23 20:32:38.025221: step: 390/1545, loss: 0.0019993686582893133 2023-01-23 20:32:38.944341: step: 392/1545, loss: 0.0007568093715235591 2023-01-23 20:32:39.844094: step: 394/1545, loss: 0.0001355005952063948 2023-01-23 20:32:40.718847: step: 396/1545, loss: 0.009053103625774384 2023-01-23 20:32:41.605625: step: 398/1545, loss: 0.15810252726078033 2023-01-23 20:32:42.485593: step: 400/1545, loss: 0.025615030899643898 2023-01-23 20:32:43.425040: step: 402/1545, loss: 0.11669434607028961 2023-01-23 20:32:44.304739: step: 404/1545, loss: 0.0015258756466209888 2023-01-23 20:32:45.164782: step: 406/1545, loss: 0.019385721534490585 2023-01-23 20:32:45.992018: step: 408/1545, loss: 0.00020728283561766148 2023-01-23 20:32:46.929899: step: 410/1545, loss: 0.00036592932883650064 2023-01-23 20:32:47.802692: step: 412/1545, loss: 0.001518864999525249 2023-01-23 20:32:48.695896: step: 414/1545, loss: 0.00099577521905303 2023-01-23 20:32:49.643428: step: 416/1545, loss: 0.000131477223476395 2023-01-23 20:32:50.612855: step: 418/1545, loss: 0.0005699346074834466 2023-01-23 20:32:51.475700: step: 420/1545, loss: 0.0007666922174394131 2023-01-23 20:32:52.388093: step: 422/1545, loss: 0.0030693928711116314 2023-01-23 20:32:53.299281: step: 424/1545, loss: 0.14968256652355194 2023-01-23 20:32:54.182998: step: 426/1545, loss: 0.0009471366065554321 2023-01-23 20:32:55.161935: step: 428/1545, loss: 0.0014890780439600348 2023-01-23 20:32:56.048261: step: 430/1545, loss: 0.00014782622747588903 2023-01-23 20:32:56.957825: step: 432/1545, loss: 0.003000629134476185 2023-01-23 20:32:57.853597: step: 434/1545, loss: 0.024831503629684448 2023-01-23 20:32:58.756747: step: 436/1545, loss: 0.001738705555908382 2023-01-23 20:32:59.710291: step: 438/1545, loss: 0.03452584519982338 2023-01-23 20:33:00.656174: step: 440/1545, loss: 0.00018012136570177972 2023-01-23 20:33:01.570905: step: 442/1545, loss: 0.11151536554098129 2023-01-23 20:33:02.469483: step: 444/1545, loss: 1.6327940102200955e-05 2023-01-23 20:33:03.307006: step: 446/1545, loss: 0.0016755762044340372 2023-01-23 20:33:04.176492: step: 448/1545, loss: 0.0020026611164212227 2023-01-23 20:33:05.088865: step: 450/1545, loss: 0.05551620200276375 2023-01-23 20:33:05.949918: step: 452/1545, loss: 3.8237871194723994e-05 2023-01-23 20:33:06.834718: step: 454/1545, loss: 0.16977959871292114 2023-01-23 20:33:07.700187: step: 456/1545, loss: 1.0456637937750202e-05 2023-01-23 20:33:08.551132: step: 458/1545, loss: 0.07008948922157288 2023-01-23 20:33:09.460205: step: 460/1545, loss: 0.7234735488891602 2023-01-23 20:33:10.325519: step: 462/1545, loss: 0.2225368469953537 2023-01-23 20:33:11.202102: step: 464/1545, loss: 0.00027665781090036035 2023-01-23 20:33:12.081541: step: 466/1545, loss: 0.0021636919118463993 2023-01-23 20:33:12.969718: step: 468/1545, loss: 0.017527155578136444 2023-01-23 20:33:13.851916: step: 470/1545, loss: 0.0005409183213487267 2023-01-23 20:33:14.752796: step: 472/1545, loss: 0.21716159582138062 2023-01-23 20:33:15.598241: step: 474/1545, loss: 0.1605946272611618 2023-01-23 20:33:16.453865: step: 476/1545, loss: 0.010002878494560719 2023-01-23 20:33:17.347058: step: 478/1545, loss: 4.0357896068599075e-05 2023-01-23 20:33:18.219111: step: 480/1545, loss: 0.011075492016971111 2023-01-23 20:33:19.066222: step: 482/1545, loss: 0.21343889832496643 2023-01-23 20:33:19.920221: step: 484/1545, loss: 0.04724109172821045 2023-01-23 20:33:20.787982: step: 486/1545, loss: 0.0030252188444137573 2023-01-23 20:33:21.642576: step: 488/1545, loss: 9.42061233217828e-05 2023-01-23 20:33:22.503591: step: 490/1545, loss: 0.0017276245635002851 2023-01-23 20:33:23.383650: step: 492/1545, loss: 0.00019662492559291422 2023-01-23 20:33:24.251837: step: 494/1545, loss: 0.013668136671185493 2023-01-23 20:33:25.187047: step: 496/1545, loss: 0.002183222211897373 2023-01-23 20:33:26.121920: step: 498/1545, loss: 0.0034395880065858364 2023-01-23 20:33:26.980704: step: 500/1545, loss: 0.0012578858295455575 2023-01-23 20:33:27.880809: step: 502/1545, loss: 0.17614734172821045 2023-01-23 20:33:28.776756: step: 504/1545, loss: 0.053559809923172 2023-01-23 20:33:29.725249: step: 506/1545, loss: 0.01498023048043251 2023-01-23 20:33:30.637535: step: 508/1545, loss: -5.0654120968829375e-06 2023-01-23 20:33:31.540089: step: 510/1545, loss: 0.0003087965305894613 2023-01-23 20:33:32.408029: step: 512/1545, loss: 0.007342596538364887 2023-01-23 20:33:33.279159: step: 514/1545, loss: 0.000301958731142804 2023-01-23 20:33:34.192599: step: 516/1545, loss: 0.0003154231235384941 2023-01-23 20:33:35.060991: step: 518/1545, loss: 3.657512479549041e-06 2023-01-23 20:33:35.886981: step: 520/1545, loss: 0.00025127024855464697 2023-01-23 20:33:36.771178: step: 522/1545, loss: 0.019994553178548813 2023-01-23 20:33:37.691824: step: 524/1545, loss: 0.00030762533424422145 2023-01-23 20:33:38.562472: step: 526/1545, loss: 0.0017977651441469789 2023-01-23 20:33:39.418783: step: 528/1545, loss: 0.08481920510530472 2023-01-23 20:33:40.324313: step: 530/1545, loss: 2.4233349904534407e-05 2023-01-23 20:33:41.182617: step: 532/1545, loss: 0.05327204614877701 2023-01-23 20:33:42.025398: step: 534/1545, loss: 0.00015761505346745253 2023-01-23 20:33:42.955249: step: 536/1545, loss: 0.0007950044819153845 2023-01-23 20:33:43.868743: step: 538/1545, loss: 0.28980863094329834 2023-01-23 20:33:44.777226: step: 540/1545, loss: 0.00754338875412941 2023-01-23 20:33:45.655440: step: 542/1545, loss: 0.0016507696127519011 2023-01-23 20:33:46.565471: step: 544/1545, loss: 0.0005491654155775905 2023-01-23 20:33:47.387115: step: 546/1545, loss: 8.054474164964631e-05 2023-01-23 20:33:48.286127: step: 548/1545, loss: 0.09447590261697769 2023-01-23 20:33:49.160531: step: 550/1545, loss: 0.011853070929646492 2023-01-23 20:33:50.045921: step: 552/1545, loss: 0.00014138294500298798 2023-01-23 20:33:50.929814: step: 554/1545, loss: 0.18385851383209229 2023-01-23 20:33:51.781492: step: 556/1545, loss: 0.10416700690984726 2023-01-23 20:33:52.681423: step: 558/1545, loss: 2.3483760356903076 2023-01-23 20:33:53.548670: step: 560/1545, loss: 0.0005309482803568244 2023-01-23 20:33:54.430191: step: 562/1545, loss: 0.06242901086807251 2023-01-23 20:33:55.311509: step: 564/1545, loss: 9.849991329247132e-05 2023-01-23 20:33:56.208760: step: 566/1545, loss: 0.00387639575637877 2023-01-23 20:33:57.059917: step: 568/1545, loss: 0.0001807008229661733 2023-01-23 20:33:57.918346: step: 570/1545, loss: 0.0019053807482123375 2023-01-23 20:33:58.798477: step: 572/1545, loss: 3.20642429869622e-05 2023-01-23 20:33:59.702779: step: 574/1545, loss: 0.0005492604686878622 2023-01-23 20:34:00.626971: step: 576/1545, loss: 0.0007045326638035476 2023-01-23 20:34:01.489472: step: 578/1545, loss: 0.0016909572295844555 2023-01-23 20:34:02.417393: step: 580/1545, loss: 0.014954089187085629 2023-01-23 20:34:03.272040: step: 582/1545, loss: 0.06883454322814941 2023-01-23 20:34:04.181243: step: 584/1545, loss: 0.003636081237345934 2023-01-23 20:34:05.081641: step: 586/1545, loss: 0.00017161411233246326 2023-01-23 20:34:05.976889: step: 588/1545, loss: 0.0015272949822247028 2023-01-23 20:34:06.846896: step: 590/1545, loss: 0.0004225363372825086 2023-01-23 20:34:07.729736: step: 592/1545, loss: 0.0026832548901438713 2023-01-23 20:34:08.639406: step: 594/1545, loss: 0.0008902246481738985 2023-01-23 20:34:09.545064: step: 596/1545, loss: 0.0011738165048882365 2023-01-23 20:34:10.426071: step: 598/1545, loss: 0.00047044697566889226 2023-01-23 20:34:11.302500: step: 600/1545, loss: 0.005709059536457062 2023-01-23 20:34:12.168237: step: 602/1545, loss: 0.13036485016345978 2023-01-23 20:34:13.020811: step: 604/1545, loss: 0.0030785559210926294 2023-01-23 20:34:13.923885: step: 606/1545, loss: 0.034377746284008026 2023-01-23 20:34:14.822217: step: 608/1545, loss: 0.007240693550556898 2023-01-23 20:34:15.715102: step: 610/1545, loss: 0.1606174260377884 2023-01-23 20:34:16.590156: step: 612/1545, loss: 0.0002493268111720681 2023-01-23 20:34:17.511876: step: 614/1545, loss: 1.0542219877243042 2023-01-23 20:34:18.388987: step: 616/1545, loss: 0.023611802607774734 2023-01-23 20:34:19.316381: step: 618/1545, loss: 0.0039176493883132935 2023-01-23 20:34:20.191487: step: 620/1545, loss: 0.13809627294540405 2023-01-23 20:34:21.066200: step: 622/1545, loss: 2.2254518626141362e-05 2023-01-23 20:34:21.902043: step: 624/1545, loss: 0.0015881985891610384 2023-01-23 20:34:22.779095: step: 626/1545, loss: 0.0004673512012232095 2023-01-23 20:34:23.626523: step: 628/1545, loss: 0.0016283700242638588 2023-01-23 20:34:24.483369: step: 630/1545, loss: 0.003537831362336874 2023-01-23 20:34:25.395476: step: 632/1545, loss: 0.00022629662998951972 2023-01-23 20:34:26.264797: step: 634/1545, loss: 0.3561306297779083 2023-01-23 20:34:27.160326: step: 636/1545, loss: 8.117415563901886e-05 2023-01-23 20:34:28.026994: step: 638/1545, loss: 0.00025245462893508375 2023-01-23 20:34:28.900316: step: 640/1545, loss: 0.44562187790870667 2023-01-23 20:34:29.769965: step: 642/1545, loss: 0.0011486493749544024 2023-01-23 20:34:30.636844: step: 644/1545, loss: 0.00011147315672133118 2023-01-23 20:34:31.483732: step: 646/1545, loss: -6.44798865323537e-06 2023-01-23 20:34:32.418087: step: 648/1545, loss: 0.001530293608084321 2023-01-23 20:34:33.272935: step: 650/1545, loss: -3.103708877461031e-06 2023-01-23 20:34:34.197213: step: 652/1545, loss: 0.0009526460780762136 2023-01-23 20:34:35.128148: step: 654/1545, loss: 0.0012624274240806699 2023-01-23 20:34:36.062529: step: 656/1545, loss: 0.006986720021814108 2023-01-23 20:34:36.939141: step: 658/1545, loss: 0.0001965576084330678 2023-01-23 20:34:37.840346: step: 660/1545, loss: 0.00654384633526206 2023-01-23 20:34:38.754029: step: 662/1545, loss: 0.07436367869377136 2023-01-23 20:34:39.712268: step: 664/1545, loss: 0.0002718035539146513 2023-01-23 20:34:40.738505: step: 666/1545, loss: 0.0002785841643344611 2023-01-23 20:34:41.611132: step: 668/1545, loss: 0.00865122489631176 2023-01-23 20:34:42.520668: step: 670/1545, loss: 0.0009204063680954278 2023-01-23 20:34:43.427595: step: 672/1545, loss: 4.92223261971958e-06 2023-01-23 20:34:44.307840: step: 674/1545, loss: 0.002189585706219077 2023-01-23 20:34:45.190436: step: 676/1545, loss: 0.0002577920095063746 2023-01-23 20:34:46.090987: step: 678/1545, loss: 0.11347514390945435 2023-01-23 20:34:47.065245: step: 680/1545, loss: 0.006169906351715326 2023-01-23 20:34:47.941807: step: 682/1545, loss: 5.533498551812954e-05 2023-01-23 20:34:48.827478: step: 684/1545, loss: 0.13442815840244293 2023-01-23 20:34:49.784669: step: 686/1545, loss: 0.03902791440486908 2023-01-23 20:34:50.756698: step: 688/1545, loss: 1.782178514986299e-05 2023-01-23 20:34:51.684460: step: 690/1545, loss: 7.505570829380304e-05 2023-01-23 20:34:52.549072: step: 692/1545, loss: 0.0018242725636810064 2023-01-23 20:34:53.479710: step: 694/1545, loss: 0.00044628267642110586 2023-01-23 20:34:54.350514: step: 696/1545, loss: 4.638777318177745e-05 2023-01-23 20:34:55.242542: step: 698/1545, loss: 0.0002828891738317907 2023-01-23 20:34:56.118300: step: 700/1545, loss: 0.001074340776540339 2023-01-23 20:34:57.017068: step: 702/1545, loss: 0.00020008289720863104 2023-01-23 20:34:57.896462: step: 704/1545, loss: 0.0009829840855672956 2023-01-23 20:34:58.738422: step: 706/1545, loss: 0.00167065707501024 2023-01-23 20:34:59.618940: step: 708/1545, loss: 4.951345908921212e-05 2023-01-23 20:35:00.452651: step: 710/1545, loss: 5.66839735256508e-05 2023-01-23 20:35:01.346908: step: 712/1545, loss: 0.0028780465945601463 2023-01-23 20:35:02.216918: step: 714/1545, loss: 0.061922766268253326 2023-01-23 20:35:03.124156: step: 716/1545, loss: 0.0034155414905399084 2023-01-23 20:35:04.077804: step: 718/1545, loss: 0.0034034070558845997 2023-01-23 20:35:04.969037: step: 720/1545, loss: 0.034564629197120667 2023-01-23 20:35:05.860046: step: 722/1545, loss: 0.1197618618607521 2023-01-23 20:35:06.755008: step: 724/1545, loss: 0.034664418548345566 2023-01-23 20:35:07.636013: step: 726/1545, loss: 2.6260830054525286e-05 2023-01-23 20:35:08.498212: step: 728/1545, loss: 0.0011097504757344723 2023-01-23 20:35:09.373095: step: 730/1545, loss: 0.02032971940934658 2023-01-23 20:35:10.304324: step: 732/1545, loss: 0.42290088534355164 2023-01-23 20:35:11.175138: step: 734/1545, loss: 0.0177215114235878 2023-01-23 20:35:12.057984: step: 736/1545, loss: 0.17191193997859955 2023-01-23 20:35:13.064058: step: 738/1545, loss: 9.492158278590068e-05 2023-01-23 20:35:14.022492: step: 740/1545, loss: 0.23547685146331787 2023-01-23 20:35:14.870474: step: 742/1545, loss: 0.35796117782592773 2023-01-23 20:35:15.748110: step: 744/1545, loss: 0.17260463535785675 2023-01-23 20:35:16.578937: step: 746/1545, loss: 0.00010146270506083965 2023-01-23 20:35:17.425690: step: 748/1545, loss: 3.947269942727871e-05 2023-01-23 20:35:18.359001: step: 750/1545, loss: 0.0016060250345617533 2023-01-23 20:35:19.236776: step: 752/1545, loss: 0.11278177797794342 2023-01-23 20:35:20.132219: step: 754/1545, loss: 0.000214374580536969 2023-01-23 20:35:21.026755: step: 756/1545, loss: 0.000273712765192613 2023-01-23 20:35:21.950243: step: 758/1545, loss: 0.027747632935643196 2023-01-23 20:35:22.849132: step: 760/1545, loss: 0.00016056746244430542 2023-01-23 20:35:23.741325: step: 762/1545, loss: 0.0003478050057310611 2023-01-23 20:35:24.661918: step: 764/1545, loss: 0.15895012021064758 2023-01-23 20:35:25.598090: step: 766/1545, loss: 0.07515369355678558 2023-01-23 20:35:26.469368: step: 768/1545, loss: 4.5265718654263765e-05 2023-01-23 20:35:27.367040: step: 770/1545, loss: 0.8711293935775757 2023-01-23 20:35:28.200601: step: 772/1545, loss: 0.0013916062889620662 2023-01-23 20:35:29.074588: step: 774/1545, loss: 0.00029801364871673286 2023-01-23 20:35:29.949101: step: 776/1545, loss: 0.0011418438516557217 2023-01-23 20:35:30.840270: step: 778/1545, loss: 0.0027232065331190825 2023-01-23 20:35:31.717965: step: 780/1545, loss: 6.966810178710148e-05 2023-01-23 20:35:32.617964: step: 782/1545, loss: 0.1032852753996849 2023-01-23 20:35:33.478507: step: 784/1545, loss: 0.10341549664735794 2023-01-23 20:35:34.336890: step: 786/1545, loss: 0.0017330575501546264 2023-01-23 20:35:35.206772: step: 788/1545, loss: 0.02474193461239338 2023-01-23 20:35:36.015638: step: 790/1545, loss: 0.03292299434542656 2023-01-23 20:35:36.879644: step: 792/1545, loss: 0.04957323521375656 2023-01-23 20:35:37.709240: step: 794/1545, loss: 0.0005776043399237096 2023-01-23 20:35:38.586650: step: 796/1545, loss: 0.4405074119567871 2023-01-23 20:35:39.464639: step: 798/1545, loss: 7.841096521588042e-05 2023-01-23 20:35:40.352977: step: 800/1545, loss: 5.364564640331082e-05 2023-01-23 20:35:41.273234: step: 802/1545, loss: 2.982640580739826e-05 2023-01-23 20:35:42.227531: step: 804/1545, loss: 0.00048610116937197745 2023-01-23 20:35:43.115502: step: 806/1545, loss: 0.06669419258832932 2023-01-23 20:35:44.090964: step: 808/1545, loss: 0.00012741153477691114 2023-01-23 20:35:44.926589: step: 810/1545, loss: 0.004652348347008228 2023-01-23 20:35:45.784416: step: 812/1545, loss: 0.0013264025328680873 2023-01-23 20:35:46.673218: step: 814/1545, loss: 0.06071851775050163 2023-01-23 20:35:47.540566: step: 816/1545, loss: 0.0005070171901024878 2023-01-23 20:35:48.452328: step: 818/1545, loss: 0.0010552614694461226 2023-01-23 20:35:49.365769: step: 820/1545, loss: 0.014347714371979237 2023-01-23 20:35:50.287626: step: 822/1545, loss: 0.00010214207577519119 2023-01-23 20:35:51.149304: step: 824/1545, loss: 0.08245106786489487 2023-01-23 20:35:52.029927: step: 826/1545, loss: 0.00030925628379918635 2023-01-23 20:35:52.899723: step: 828/1545, loss: 0.0642094612121582 2023-01-23 20:35:53.773266: step: 830/1545, loss: 0.0014824580866843462 2023-01-23 20:35:54.632810: step: 832/1545, loss: 0.0001817193115130067 2023-01-23 20:35:55.489066: step: 834/1545, loss: 0.04122912138700485 2023-01-23 20:35:56.370854: step: 836/1545, loss: 0.00020527956075966358 2023-01-23 20:35:57.249628: step: 838/1545, loss: 0.043545566499233246 2023-01-23 20:35:58.126459: step: 840/1545, loss: 0.00012035427062073722 2023-01-23 20:35:58.998077: step: 842/1545, loss: 0.00022896466543897986 2023-01-23 20:35:59.859096: step: 844/1545, loss: 0.013119703158736229 2023-01-23 20:36:00.724235: step: 846/1545, loss: 0.006383657455444336 2023-01-23 20:36:01.559442: step: 848/1545, loss: 0.00029040200752206147 2023-01-23 20:36:02.434088: step: 850/1545, loss: 0.10685012489557266 2023-01-23 20:36:03.324569: step: 852/1545, loss: 7.634132634848356e-05 2023-01-23 20:36:04.260908: step: 854/1545, loss: 0.0006185777601785958 2023-01-23 20:36:05.188348: step: 856/1545, loss: 0.00014178239507600665 2023-01-23 20:36:06.041796: step: 858/1545, loss: 0.006291212979704142 2023-01-23 20:36:06.984630: step: 860/1545, loss: 0.00021827708405908197 2023-01-23 20:36:07.871079: step: 862/1545, loss: 0.0006602761568501592 2023-01-23 20:36:08.768467: step: 864/1545, loss: -1.4715556062583346e-06 2023-01-23 20:36:09.574435: step: 866/1545, loss: 0.005076305475085974 2023-01-23 20:36:10.421205: step: 868/1545, loss: 0.0003684900002554059 2023-01-23 20:36:11.307913: step: 870/1545, loss: 0.00011529910989338532 2023-01-23 20:36:12.175009: step: 872/1545, loss: 0.11840388923883438 2023-01-23 20:36:13.097222: step: 874/1545, loss: 0.16011042892932892 2023-01-23 20:36:13.951687: step: 876/1545, loss: 0.16511622071266174 2023-01-23 20:36:14.822395: step: 878/1545, loss: 0.00024522727471776307 2023-01-23 20:36:15.773622: step: 880/1545, loss: 0.00020414814935065806 2023-01-23 20:36:16.632844: step: 882/1545, loss: 0.0005159721476957202 2023-01-23 20:36:17.522344: step: 884/1545, loss: 0.0064879897981882095 2023-01-23 20:36:18.416805: step: 886/1545, loss: 0.014759959653019905 2023-01-23 20:36:19.329693: step: 888/1545, loss: 3.0345810955623165e-05 2023-01-23 20:36:20.169811: step: 890/1545, loss: 0.0027577977161854506 2023-01-23 20:36:21.077506: step: 892/1545, loss: 1.0627477169036865 2023-01-23 20:36:21.896828: step: 894/1545, loss: 0.0003152832796331495 2023-01-23 20:36:22.746070: step: 896/1545, loss: 0.00048333106678910553 2023-01-23 20:36:23.600451: step: 898/1545, loss: 0.00022870665998198092 2023-01-23 20:36:24.534757: step: 900/1545, loss: 0.20072606205940247 2023-01-23 20:36:25.396833: step: 902/1545, loss: 0.0005174196558073163 2023-01-23 20:36:26.305615: step: 904/1545, loss: 0.08551566302776337 2023-01-23 20:36:27.187919: step: 906/1545, loss: 0.09952077269554138 2023-01-23 20:36:28.110539: step: 908/1545, loss: 7.574139453936368e-05 2023-01-23 20:36:28.975451: step: 910/1545, loss: 0.001976173371076584 2023-01-23 20:36:29.840195: step: 912/1545, loss: 0.003127660369500518 2023-01-23 20:36:30.733733: step: 914/1545, loss: 0.008538423106074333 2023-01-23 20:36:31.645557: step: 916/1545, loss: 0.00038940872764214873 2023-01-23 20:36:32.501737: step: 918/1545, loss: 0.0009257208439521492 2023-01-23 20:36:33.400727: step: 920/1545, loss: 0.0003304950660094619 2023-01-23 20:36:34.297711: step: 922/1545, loss: 0.009197581559419632 2023-01-23 20:36:35.176095: step: 924/1545, loss: 0.02057754062116146 2023-01-23 20:36:36.077621: step: 926/1545, loss: 1.5320937633514404 2023-01-23 20:36:36.976802: step: 928/1545, loss: 0.021694118157029152 2023-01-23 20:36:37.862672: step: 930/1545, loss: 0.0010353467660024762 2023-01-23 20:36:38.732605: step: 932/1545, loss: 0.10404753684997559 2023-01-23 20:36:39.648755: step: 934/1545, loss: 0.002932937117293477 2023-01-23 20:36:40.498208: step: 936/1545, loss: 0.00048321348731406033 2023-01-23 20:36:41.360667: step: 938/1545, loss: 0.0023124234285205603 2023-01-23 20:36:42.232665: step: 940/1545, loss: 0.0006339968531392515 2023-01-23 20:36:43.093825: step: 942/1545, loss: 0.008339066058397293 2023-01-23 20:36:43.958994: step: 944/1545, loss: 0.000226061514695175 2023-01-23 20:36:44.825700: step: 946/1545, loss: 0.0005726612871512771 2023-01-23 20:36:45.687672: step: 948/1545, loss: 0.0008180650183930993 2023-01-23 20:36:46.546924: step: 950/1545, loss: 0.002319122664630413 2023-01-23 20:36:47.408605: step: 952/1545, loss: 0.014347954653203487 2023-01-23 20:36:48.330098: step: 954/1545, loss: 0.009941592812538147 2023-01-23 20:36:49.288882: step: 956/1545, loss: 0.0009157544700428843 2023-01-23 20:36:50.179897: step: 958/1545, loss: 0.000354877847712487 2023-01-23 20:36:51.058837: step: 960/1545, loss: 0.0011064114514738321 2023-01-23 20:36:51.942315: step: 962/1545, loss: 0.019446175545454025 2023-01-23 20:36:52.832773: step: 964/1545, loss: 0.03733896464109421 2023-01-23 20:36:53.715665: step: 966/1545, loss: 0.0029872541781514883 2023-01-23 20:36:54.587205: step: 968/1545, loss: 0.002957236021757126 2023-01-23 20:36:55.469123: step: 970/1545, loss: 0.00444247480481863 2023-01-23 20:36:56.371167: step: 972/1545, loss: 0.0047304644249379635 2023-01-23 20:36:57.244584: step: 974/1545, loss: 0.012338278815150261 2023-01-23 20:36:58.098522: step: 976/1545, loss: 0.00044995208736509085 2023-01-23 20:36:58.997172: step: 978/1545, loss: 0.05712711438536644 2023-01-23 20:36:59.871501: step: 980/1545, loss: 0.0023749596439301968 2023-01-23 20:37:00.753682: step: 982/1545, loss: 0.002523741452023387 2023-01-23 20:37:01.639137: step: 984/1545, loss: 0.023617921397089958 2023-01-23 20:37:02.524393: step: 986/1545, loss: 0.03589809313416481 2023-01-23 20:37:03.392110: step: 988/1545, loss: 0.0005242583574727178 2023-01-23 20:37:04.246894: step: 990/1545, loss: 0.0015599019825458527 2023-01-23 20:37:05.115181: step: 992/1545, loss: 0.004254720639437437 2023-01-23 20:37:05.989474: step: 994/1545, loss: 0.09263045340776443 2023-01-23 20:37:06.897451: step: 996/1545, loss: 0.12787725031375885 2023-01-23 20:37:07.772681: step: 998/1545, loss: 0.003310817526653409 2023-01-23 20:37:08.632530: step: 1000/1545, loss: 0.1277714967727661 2023-01-23 20:37:09.489655: step: 1002/1545, loss: 0.0017045604763552547 2023-01-23 20:37:10.424906: step: 1004/1545, loss: 0.0009486719500273466 2023-01-23 20:37:11.348341: step: 1006/1545, loss: 0.007455047219991684 2023-01-23 20:37:12.297526: step: 1008/1545, loss: 0.0009265391272492707 2023-01-23 20:37:13.169614: step: 1010/1545, loss: 0.02065279148519039 2023-01-23 20:37:14.011536: step: 1012/1545, loss: 0.006675556767731905 2023-01-23 20:37:14.906926: step: 1014/1545, loss: 0.006350125651806593 2023-01-23 20:37:15.866502: step: 1016/1545, loss: 0.023490455001592636 2023-01-23 20:37:16.720684: step: 1018/1545, loss: 4.6117107558529824e-05 2023-01-23 20:37:17.565572: step: 1020/1545, loss: 0.0010810389649122953 2023-01-23 20:37:18.442363: step: 1022/1545, loss: 0.00015505979536101222 2023-01-23 20:37:19.324486: step: 1024/1545, loss: 8.347952825715765e-05 2023-01-23 20:37:20.202786: step: 1026/1545, loss: 0.0021098286379128695 2023-01-23 20:37:21.079274: step: 1028/1545, loss: 0.0027412406634539366 2023-01-23 20:37:22.013638: step: 1030/1545, loss: 8.47937335493043e-05 2023-01-23 20:37:22.862097: step: 1032/1545, loss: 0.0005280207260511816 2023-01-23 20:37:23.725111: step: 1034/1545, loss: 0.00016318292182404548 2023-01-23 20:37:24.575723: step: 1036/1545, loss: 0.0028523795772343874 2023-01-23 20:37:25.461710: step: 1038/1545, loss: 5.080554728920106e-06 2023-01-23 20:37:26.342268: step: 1040/1545, loss: 0.02534395456314087 2023-01-23 20:37:27.203990: step: 1042/1545, loss: 0.0003928398073185235 2023-01-23 20:37:28.127621: step: 1044/1545, loss: 0.003912526182830334 2023-01-23 20:37:29.044952: step: 1046/1545, loss: 0.019826438277959824 2023-01-23 20:37:29.916760: step: 1048/1545, loss: 0.005512018222361803 2023-01-23 20:37:30.772677: step: 1050/1545, loss: 6.260140798985958e-05 2023-01-23 20:37:31.677948: step: 1052/1545, loss: 0.0015080157900229096 2023-01-23 20:37:32.526781: step: 1054/1545, loss: 1.630391489015892e-05 2023-01-23 20:37:33.441741: step: 1056/1545, loss: 0.10819005221128464 2023-01-23 20:37:34.349572: step: 1058/1545, loss: 0.20092672109603882 2023-01-23 20:37:35.244510: step: 1060/1545, loss: 0.00496266083791852 2023-01-23 20:37:36.226297: step: 1062/1545, loss: 0.0027142763137817383 2023-01-23 20:37:37.098422: step: 1064/1545, loss: 0.0021100416779518127 2023-01-23 20:37:37.997977: step: 1066/1545, loss: 0.007467001676559448 2023-01-23 20:37:38.858109: step: 1068/1545, loss: 0.00018068330246023834 2023-01-23 20:37:39.721733: step: 1070/1545, loss: 0.003444942645728588 2023-01-23 20:37:40.570231: step: 1072/1545, loss: 0.0045898305252194405 2023-01-23 20:37:41.494489: step: 1074/1545, loss: 0.3472941219806671 2023-01-23 20:37:42.375450: step: 1076/1545, loss: 0.0005800973158329725 2023-01-23 20:37:43.254766: step: 1078/1545, loss: 0.0003524233470670879 2023-01-23 20:37:44.186958: step: 1080/1545, loss: 2.2140036890050396e-05 2023-01-23 20:37:45.068126: step: 1082/1545, loss: 0.0016178677324205637 2023-01-23 20:37:45.958588: step: 1084/1545, loss: 0.19748921692371368 2023-01-23 20:37:46.857387: step: 1086/1545, loss: 7.288325286936015e-05 2023-01-23 20:37:47.744749: step: 1088/1545, loss: 0.00018930925580207258 2023-01-23 20:37:48.652208: step: 1090/1545, loss: 0.18344834446907043 2023-01-23 20:37:49.540135: step: 1092/1545, loss: 0.08178756386041641 2023-01-23 20:37:50.425467: step: 1094/1545, loss: -1.9373839677427895e-05 2023-01-23 20:37:51.280290: step: 1096/1545, loss: 7.814729906385764e-05 2023-01-23 20:37:52.199607: step: 1098/1545, loss: 0.003479898674413562 2023-01-23 20:37:53.105592: step: 1100/1545, loss: 0.0026173314545303583 2023-01-23 20:37:53.969657: step: 1102/1545, loss: 0.0005676451255567372 2023-01-23 20:37:54.892194: step: 1104/1545, loss: 0.009031519293785095 2023-01-23 20:37:55.783009: step: 1106/1545, loss: 0.26603633165359497 2023-01-23 20:37:56.653384: step: 1108/1545, loss: 0.004309503361582756 2023-01-23 20:37:57.524185: step: 1110/1545, loss: 8.639540465082973e-05 2023-01-23 20:37:58.417756: step: 1112/1545, loss: 0.13402853906154633 2023-01-23 20:37:59.323887: step: 1114/1545, loss: 0.0036482904106378555 2023-01-23 20:38:00.263165: step: 1116/1545, loss: 0.00018984783673658967 2023-01-23 20:38:01.143813: step: 1118/1545, loss: 0.02561715804040432 2023-01-23 20:38:01.979577: step: 1120/1545, loss: 0.010343439877033234 2023-01-23 20:38:02.900811: step: 1122/1545, loss: 4.303061723476276e-05 2023-01-23 20:38:03.737932: step: 1124/1545, loss: 0.00017393803864251822 2023-01-23 20:38:04.594287: step: 1126/1545, loss: 0.00014496510266326368 2023-01-23 20:38:05.455603: step: 1128/1545, loss: 0.0005682943155989051 2023-01-23 20:38:06.389120: step: 1130/1545, loss: 0.002318792277947068 2023-01-23 20:38:07.308112: step: 1132/1545, loss: 0.0004885851521976292 2023-01-23 20:38:08.195885: step: 1134/1545, loss: 0.0012692223535850644 2023-01-23 20:38:09.059542: step: 1136/1545, loss: 0.00015068257926031947 2023-01-23 20:38:09.918234: step: 1138/1545, loss: 5.568032429437153e-05 2023-01-23 20:38:10.765199: step: 1140/1545, loss: 0.04613517224788666 2023-01-23 20:38:11.718141: step: 1142/1545, loss: 0.0007451508427038789 2023-01-23 20:38:12.576943: step: 1144/1545, loss: 0.00016181379032786936 2023-01-23 20:38:13.462241: step: 1146/1545, loss: 0.0004487939877435565 2023-01-23 20:38:14.350251: step: 1148/1545, loss: 0.0001424938382115215 2023-01-23 20:38:15.223509: step: 1150/1545, loss: 0.0037088142707943916 2023-01-23 20:38:16.121496: step: 1152/1545, loss: 0.07236870378255844 2023-01-23 20:38:17.077855: step: 1154/1545, loss: 0.0014409306459128857 2023-01-23 20:38:17.988418: step: 1156/1545, loss: 7.538632053183392e-05 2023-01-23 20:38:18.979730: step: 1158/1545, loss: 0.000543472939170897 2023-01-23 20:38:19.917096: step: 1160/1545, loss: 0.003533255308866501 2023-01-23 20:38:20.825679: step: 1162/1545, loss: 6.170695996843278e-05 2023-01-23 20:38:21.734512: step: 1164/1545, loss: 0.00023337775201071054 2023-01-23 20:38:22.579139: step: 1166/1545, loss: 0.018182456493377686 2023-01-23 20:38:23.498932: step: 1168/1545, loss: 0.0008405813714489341 2023-01-23 20:38:24.366334: step: 1170/1545, loss: 6.95640774210915e-05 2023-01-23 20:38:25.279033: step: 1172/1545, loss: 0.001503884675912559 2023-01-23 20:38:26.166292: step: 1174/1545, loss: 0.005533399526029825 2023-01-23 20:38:27.070565: step: 1176/1545, loss: 0.014449442736804485 2023-01-23 20:38:27.943026: step: 1178/1545, loss: 2.5730114430189133e-05 2023-01-23 20:38:28.809769: step: 1180/1545, loss: 0.4755696654319763 2023-01-23 20:38:29.682839: step: 1182/1545, loss: 0.11715707927942276 2023-01-23 20:38:30.577279: step: 1184/1545, loss: 0.021453220397233963 2023-01-23 20:38:31.494974: step: 1186/1545, loss: 0.008510179817676544 2023-01-23 20:38:32.441352: step: 1188/1545, loss: 0.0008172285743057728 2023-01-23 20:38:33.329970: step: 1190/1545, loss: 0.04036368057131767 2023-01-23 20:38:34.229985: step: 1192/1545, loss: 0.0012560440227389336 2023-01-23 20:38:35.110658: step: 1194/1545, loss: 0.004944823682308197 2023-01-23 20:38:35.974956: step: 1196/1545, loss: 0.02462255209684372 2023-01-23 20:38:36.827232: step: 1198/1545, loss: 0.015974685549736023 2023-01-23 20:38:37.706082: step: 1200/1545, loss: 0.2099367082118988 2023-01-23 20:38:38.606015: step: 1202/1545, loss: 0.03722541034221649 2023-01-23 20:38:39.464496: step: 1204/1545, loss: 0.09187915921211243 2023-01-23 20:38:40.403691: step: 1206/1545, loss: 0.22825096547603607 2023-01-23 20:38:41.244885: step: 1208/1545, loss: 0.0018492807867005467 2023-01-23 20:38:42.125168: step: 1210/1545, loss: 0.010709783993661404 2023-01-23 20:38:42.987503: step: 1212/1545, loss: 0.03333675488829613 2023-01-23 20:38:43.833603: step: 1214/1545, loss: 0.002520166104659438 2023-01-23 20:38:44.710735: step: 1216/1545, loss: 0.0004999208031222224 2023-01-23 20:38:45.564682: step: 1218/1545, loss: 0.03831126540899277 2023-01-23 20:38:46.442870: step: 1220/1545, loss: 0.02865646220743656 2023-01-23 20:38:47.348978: step: 1222/1545, loss: 0.014754390344023705 2023-01-23 20:38:48.199935: step: 1224/1545, loss: 0.410963773727417 2023-01-23 20:38:49.085228: step: 1226/1545, loss: 0.006488085724413395 2023-01-23 20:38:49.960862: step: 1228/1545, loss: 0.0018648579716682434 2023-01-23 20:38:50.888927: step: 1230/1545, loss: 0.005571517162024975 2023-01-23 20:38:51.857910: step: 1232/1545, loss: 0.010873244144022465 2023-01-23 20:38:52.701531: step: 1234/1545, loss: 0.019334059208631516 2023-01-23 20:38:53.554779: step: 1236/1545, loss: 0.0551164411008358 2023-01-23 20:38:54.462310: step: 1238/1545, loss: 0.000529549375642091 2023-01-23 20:38:55.354537: step: 1240/1545, loss: 0.023977095261216164 2023-01-23 20:38:56.257575: step: 1242/1545, loss: 0.1421588808298111 2023-01-23 20:38:57.156926: step: 1244/1545, loss: 0.26963329315185547 2023-01-23 20:38:58.034215: step: 1246/1545, loss: 0.03393752500414848 2023-01-23 20:38:58.980103: step: 1248/1545, loss: 0.004843075759708881 2023-01-23 20:38:59.839720: step: 1250/1545, loss: 0.03621028736233711 2023-01-23 20:39:00.733182: step: 1252/1545, loss: 0.12089993804693222 2023-01-23 20:39:01.654660: step: 1254/1545, loss: 0.010257977060973644 2023-01-23 20:39:02.574023: step: 1256/1545, loss: 0.00917292945086956 2023-01-23 20:39:03.478911: step: 1258/1545, loss: 0.002248922362923622 2023-01-23 20:39:04.319182: step: 1260/1545, loss: 0.0015998169546946883 2023-01-23 20:39:05.260125: step: 1262/1545, loss: 0.004709456115961075 2023-01-23 20:39:06.129910: step: 1264/1545, loss: 0.0006423032027669251 2023-01-23 20:39:07.026154: step: 1266/1545, loss: 0.0009056890266947448 2023-01-23 20:39:07.933818: step: 1268/1545, loss: 0.12211329489946365 2023-01-23 20:39:08.793955: step: 1270/1545, loss: 0.03471807762980461 2023-01-23 20:39:09.686502: step: 1272/1545, loss: 0.0004940564977005124 2023-01-23 20:39:10.550991: step: 1274/1545, loss: 0.0058082775212824345 2023-01-23 20:39:11.420609: step: 1276/1545, loss: 0.0012055240804329515 2023-01-23 20:39:12.312131: step: 1278/1545, loss: 0.011442940682172775 2023-01-23 20:39:13.264725: step: 1280/1545, loss: 0.0812845379114151 2023-01-23 20:39:14.119363: step: 1282/1545, loss: 0.0010506851831451058 2023-01-23 20:39:15.001650: step: 1284/1545, loss: 0.10680735111236572 2023-01-23 20:39:15.909734: step: 1286/1545, loss: 0.00022727683244738728 2023-01-23 20:39:16.781015: step: 1288/1545, loss: 0.0004236150998622179 2023-01-23 20:39:17.636485: step: 1290/1545, loss: 0.0016160889063030481 2023-01-23 20:39:18.519261: step: 1292/1545, loss: 0.1720072478055954 2023-01-23 20:39:19.443501: step: 1294/1545, loss: 0.0001301086595049128 2023-01-23 20:39:20.333696: step: 1296/1545, loss: 0.00011231849202886224 2023-01-23 20:39:21.188593: step: 1298/1545, loss: 0.020460525527596474 2023-01-23 20:39:22.089996: step: 1300/1545, loss: 7.543405808974057e-05 2023-01-23 20:39:22.981212: step: 1302/1545, loss: 0.13744300603866577 2023-01-23 20:39:23.866391: step: 1304/1545, loss: 0.056853216141462326 2023-01-23 20:39:24.715957: step: 1306/1545, loss: 0.00010735205432865769 2023-01-23 20:39:25.599362: step: 1308/1545, loss: 0.014715062454342842 2023-01-23 20:39:26.495549: step: 1310/1545, loss: 0.00013445198419503868 2023-01-23 20:39:27.377634: step: 1312/1545, loss: 0.00025772975641302764 2023-01-23 20:39:28.284866: step: 1314/1545, loss: 0.0008543690200895071 2023-01-23 20:39:29.159573: step: 1316/1545, loss: 0.0008047893061302602 2023-01-23 20:39:30.043401: step: 1318/1545, loss: 0.007916326634585857 2023-01-23 20:39:30.891050: step: 1320/1545, loss: 1.7861944797914475e-05 2023-01-23 20:39:31.741572: step: 1322/1545, loss: 0.02132144197821617 2023-01-23 20:39:32.590101: step: 1324/1545, loss: 0.265257328748703 2023-01-23 20:39:33.452782: step: 1326/1545, loss: 0.01189727708697319 2023-01-23 20:39:34.320138: step: 1328/1545, loss: 0.0005519664264284074 2023-01-23 20:39:35.193278: step: 1330/1545, loss: 0.00017143486184068024 2023-01-23 20:39:36.129051: step: 1332/1545, loss: 0.02076997049152851 2023-01-23 20:39:36.973238: step: 1334/1545, loss: 0.0022759386338293552 2023-01-23 20:39:37.825364: step: 1336/1545, loss: 0.40256452560424805 2023-01-23 20:39:38.682258: step: 1338/1545, loss: 0.04810822382569313 2023-01-23 20:39:39.536885: step: 1340/1545, loss: 0.001223861938342452 2023-01-23 20:39:40.424683: step: 1342/1545, loss: 0.0002745763922575861 2023-01-23 20:39:41.332437: step: 1344/1545, loss: 0.08136694133281708 2023-01-23 20:39:42.241793: step: 1346/1545, loss: 0.00034874770790338516 2023-01-23 20:39:43.078994: step: 1348/1545, loss: 0.0008194674155674875 2023-01-23 20:39:43.948478: step: 1350/1545, loss: 0.00016752978262957186 2023-01-23 20:39:44.851021: step: 1352/1545, loss: 0.24611592292785645 2023-01-23 20:39:45.764115: step: 1354/1545, loss: 0.03242874518036842 2023-01-23 20:39:46.688420: step: 1356/1545, loss: 0.024208491668105125 2023-01-23 20:39:47.572850: step: 1358/1545, loss: 0.010171343572437763 2023-01-23 20:39:48.474204: step: 1360/1545, loss: 0.02666464075446129 2023-01-23 20:39:49.367935: step: 1362/1545, loss: 0.006468562874943018 2023-01-23 20:39:50.251919: step: 1364/1545, loss: 9.46017971727997e-05 2023-01-23 20:39:51.209419: step: 1366/1545, loss: 0.00011066727165598422 2023-01-23 20:39:52.085497: step: 1368/1545, loss: 0.00013142774696461856 2023-01-23 20:39:53.017060: step: 1370/1545, loss: 0.12688495218753815 2023-01-23 20:39:53.915041: step: 1372/1545, loss: 0.11069236695766449 2023-01-23 20:39:54.785254: step: 1374/1545, loss: 0.0003087880904786289 2023-01-23 20:39:55.715086: step: 1376/1545, loss: 0.015755442902445793 2023-01-23 20:39:56.558442: step: 1378/1545, loss: 0.0001441172935301438 2023-01-23 20:39:57.405256: step: 1380/1545, loss: 0.0005355451721698046 2023-01-23 20:39:58.314832: step: 1382/1545, loss: 0.0016595611814409494 2023-01-23 20:39:59.209301: step: 1384/1545, loss: 0.00024052552180364728 2023-01-23 20:40:00.107248: step: 1386/1545, loss: 0.0018495022086426616 2023-01-23 20:40:01.007130: step: 1388/1545, loss: 0.013884633779525757 2023-01-23 20:40:01.919890: step: 1390/1545, loss: 0.007558788172900677 2023-01-23 20:40:02.817386: step: 1392/1545, loss: 0.04360852763056755 2023-01-23 20:40:03.683696: step: 1394/1545, loss: 1.6230686014750972e-05 2023-01-23 20:40:04.547514: step: 1396/1545, loss: 0.04276841878890991 2023-01-23 20:40:05.385955: step: 1398/1545, loss: 0.002766375197097659 2023-01-23 20:40:06.250168: step: 1400/1545, loss: 0.0011350606800988317 2023-01-23 20:40:07.092254: step: 1402/1545, loss: 0.0021964169573038816 2023-01-23 20:40:08.007430: step: 1404/1545, loss: -3.5838191251968965e-05 2023-01-23 20:40:08.864821: step: 1406/1545, loss: 0.009705630131065845 2023-01-23 20:40:09.705075: step: 1408/1545, loss: 0.0014743874780833721 2023-01-23 20:40:10.605771: step: 1410/1545, loss: 0.00015325317508541048 2023-01-23 20:40:11.487827: step: 1412/1545, loss: 0.00021369954629335552 2023-01-23 20:40:12.385850: step: 1414/1545, loss: 0.05070836842060089 2023-01-23 20:40:13.247770: step: 1416/1545, loss: 0.000597204256337136 2023-01-23 20:40:14.143003: step: 1418/1545, loss: 0.003671198384836316 2023-01-23 20:40:15.031382: step: 1420/1545, loss: 0.00030302387312985957 2023-01-23 20:40:15.950667: step: 1422/1545, loss: 0.0002575483813416213 2023-01-23 20:40:16.796427: step: 1424/1545, loss: -1.0293745617673267e-05 2023-01-23 20:40:17.670043: step: 1426/1545, loss: 0.0026949213352054358 2023-01-23 20:40:18.523059: step: 1428/1545, loss: 0.004524892661720514 2023-01-23 20:40:19.425182: step: 1430/1545, loss: 0.00035670664510689676 2023-01-23 20:40:20.295679: step: 1432/1545, loss: 0.013253474608063698 2023-01-23 20:40:21.168452: step: 1434/1545, loss: 0.00019149677245877683 2023-01-23 20:40:22.039652: step: 1436/1545, loss: 0.4598471522331238 2023-01-23 20:40:22.943199: step: 1438/1545, loss: 0.05007179453969002 2023-01-23 20:40:23.792095: step: 1440/1545, loss: 0.0009354092180728912 2023-01-23 20:40:24.652573: step: 1442/1545, loss: 0.00010649010073393583 2023-01-23 20:40:25.545942: step: 1444/1545, loss: 0.15187759697437286 2023-01-23 20:40:26.398652: step: 1446/1545, loss: 5.4342493967851624e-05 2023-01-23 20:40:27.298792: step: 1448/1545, loss: 0.03509334847331047 2023-01-23 20:40:28.164308: step: 1450/1545, loss: 0.0006807863828726113 2023-01-23 20:40:29.059212: step: 1452/1545, loss: 6.83136167936027e-05 2023-01-23 20:40:29.903724: step: 1454/1545, loss: 0.04123193025588989 2023-01-23 20:40:30.885123: step: 1456/1545, loss: 0.01852458156645298 2023-01-23 20:40:31.811863: step: 1458/1545, loss: 0.000607676338404417 2023-01-23 20:40:32.677835: step: 1460/1545, loss: 0.0001660130947129801 2023-01-23 20:40:33.557706: step: 1462/1545, loss: 0.0022153628524392843 2023-01-23 20:40:34.426214: step: 1464/1545, loss: 0.0006141710327938199 2023-01-23 20:40:35.324668: step: 1466/1545, loss: 9.304409468313679e-05 2023-01-23 20:40:36.254465: step: 1468/1545, loss: 0.001564321806654334 2023-01-23 20:40:37.117787: step: 1470/1545, loss: 0.0013612319016829133 2023-01-23 20:40:37.983432: step: 1472/1545, loss: 0.04430722817778587 2023-01-23 20:40:38.867228: step: 1474/1545, loss: 0.07318940758705139 2023-01-23 20:40:39.754321: step: 1476/1545, loss: 6.53865427011624e-05 2023-01-23 20:40:40.645581: step: 1478/1545, loss: 0.0009305941639468074 2023-01-23 20:40:41.543258: step: 1480/1545, loss: 0.0008493721252307296 2023-01-23 20:40:42.511147: step: 1482/1545, loss: 0.08885372430086136 2023-01-23 20:40:43.374463: step: 1484/1545, loss: 9.794905054150149e-05 2023-01-23 20:40:44.314237: step: 1486/1545, loss: 0.008680901490151882 2023-01-23 20:40:45.179913: step: 1488/1545, loss: 0.011333187110722065 2023-01-23 20:40:46.095816: step: 1490/1545, loss: 0.1635243445634842 2023-01-23 20:40:46.982159: step: 1492/1545, loss: 0.00835068803280592 2023-01-23 20:40:47.864271: step: 1494/1545, loss: 0.04857463762164116 2023-01-23 20:40:48.722596: step: 1496/1545, loss: 0.04688206687569618 2023-01-23 20:40:49.604124: step: 1498/1545, loss: 3.556410229066387e-05 2023-01-23 20:40:50.491651: step: 1500/1545, loss: 0.12692618370056152 2023-01-23 20:40:51.424698: step: 1502/1545, loss: 0.00010846256191143766 2023-01-23 20:40:52.291626: step: 1504/1545, loss: 0.0003980492474511266 2023-01-23 20:40:53.165770: step: 1506/1545, loss: 0.00860318448394537 2023-01-23 20:40:54.066086: step: 1508/1545, loss: 0.0020280913449823856 2023-01-23 20:40:54.959983: step: 1510/1545, loss: 0.0022789202630519867 2023-01-23 20:40:55.840746: step: 1512/1545, loss: 0.44838130474090576 2023-01-23 20:40:56.838791: step: 1514/1545, loss: 0.00024551039678044617 2023-01-23 20:40:57.713518: step: 1516/1545, loss: 0.00022753843222744763 2023-01-23 20:40:58.591179: step: 1518/1545, loss: 0.00019251024059485644 2023-01-23 20:40:59.496832: step: 1520/1545, loss: 0.37709638476371765 2023-01-23 20:41:00.359580: step: 1522/1545, loss: 0.0005864492850378156 2023-01-23 20:41:01.253418: step: 1524/1545, loss: 0.0011406991397961974 2023-01-23 20:41:02.099879: step: 1526/1545, loss: 0.011186111718416214 2023-01-23 20:41:03.007245: step: 1528/1545, loss: 0.0001910485589178279 2023-01-23 20:41:03.873123: step: 1530/1545, loss: 0.0012904838658869267 2023-01-23 20:41:04.736710: step: 1532/1545, loss: 0.29912427067756653 2023-01-23 20:41:05.667532: step: 1534/1545, loss: 0.07592184841632843 2023-01-23 20:41:06.548543: step: 1536/1545, loss: 0.000399504613596946 2023-01-23 20:41:07.383507: step: 1538/1545, loss: 0.18981534242630005 2023-01-23 20:41:08.234139: step: 1540/1545, loss: 0.0011779546039178967 2023-01-23 20:41:09.095304: step: 1542/1545, loss: 4.1211398638552055e-05 2023-01-23 20:41:09.955084: step: 1544/1545, loss: 0.052498456090688705 2023-01-23 20:41:10.791849: step: 1546/1545, loss: 0.11535052955150604 2023-01-23 20:41:11.721734: step: 1548/1545, loss: 3.4382898807525635 2023-01-23 20:41:12.631918: step: 1550/1545, loss: 3.3344007533742115e-05 2023-01-23 20:41:13.507147: step: 1552/1545, loss: 0.01084128674119711 2023-01-23 20:41:14.406450: step: 1554/1545, loss: 0.17687015235424042 2023-01-23 20:41:15.315642: step: 1556/1545, loss: 0.0026203934103250504 2023-01-23 20:41:16.215400: step: 1558/1545, loss: 0.45744284987449646 2023-01-23 20:41:17.079393: step: 1560/1545, loss: 0.00015384622383862734 2023-01-23 20:41:17.947674: step: 1562/1545, loss: 0.7615845203399658 2023-01-23 20:41:18.818131: step: 1564/1545, loss: 0.158992201089859 2023-01-23 20:41:19.687325: step: 1566/1545, loss: 0.00023381528444588184 2023-01-23 20:41:20.574230: step: 1568/1545, loss: 0.0005593968089669943 2023-01-23 20:41:21.422993: step: 1570/1545, loss: 0.016393199563026428 2023-01-23 20:41:22.284824: step: 1572/1545, loss: 0.02413494512438774 2023-01-23 20:41:23.193521: step: 1574/1545, loss: 0.02131102792918682 2023-01-23 20:41:24.061492: step: 1576/1545, loss: 0.002688850974664092 2023-01-23 20:41:24.933860: step: 1578/1545, loss: 0.024651378393173218 2023-01-23 20:41:25.810110: step: 1580/1545, loss: 0.0027745203115046024 2023-01-23 20:41:26.676324: step: 1582/1545, loss: 0.004641218576580286 2023-01-23 20:41:27.600178: step: 1584/1545, loss: 0.053725581616163254 2023-01-23 20:41:28.477613: step: 1586/1545, loss: 0.0006992414710111916 2023-01-23 20:41:29.360534: step: 1588/1545, loss: 8.270084799733013e-05 2023-01-23 20:41:30.267394: step: 1590/1545, loss: 0.0018934034742414951 2023-01-23 20:41:31.137294: step: 1592/1545, loss: 0.0006962284678593278 2023-01-23 20:41:32.009362: step: 1594/1545, loss: 0.1559409499168396 2023-01-23 20:41:32.917781: step: 1596/1545, loss: 0.00040816981345415115 2023-01-23 20:41:33.782438: step: 1598/1545, loss: 0.0002574041427578777 2023-01-23 20:41:34.651079: step: 1600/1545, loss: 0.005771808326244354 2023-01-23 20:41:35.518034: step: 1602/1545, loss: 0.01278910506516695 2023-01-23 20:41:36.434386: step: 1604/1545, loss: 0.05105351284146309 2023-01-23 20:41:37.326227: step: 1606/1545, loss: 0.005075160879641771 2023-01-23 20:41:38.205723: step: 1608/1545, loss: 0.0006650235154666007 2023-01-23 20:41:39.092447: step: 1610/1545, loss: 0.0009413959342055023 2023-01-23 20:41:40.010195: step: 1612/1545, loss: 0.0004080557555425912 2023-01-23 20:41:40.875670: step: 1614/1545, loss: 1.6678424799465574e-05 2023-01-23 20:41:41.728377: step: 1616/1545, loss: 0.3859929144382477 2023-01-23 20:41:42.708517: step: 1618/1545, loss: 0.00013604582636617124 2023-01-23 20:41:43.596632: step: 1620/1545, loss: 0.00013760065485257655 2023-01-23 20:41:44.538878: step: 1622/1545, loss: 0.00022426855866797268 2023-01-23 20:41:45.437629: step: 1624/1545, loss: -4.6290324462461285e-06 2023-01-23 20:41:46.312816: step: 1626/1545, loss: 0.10304586589336395 2023-01-23 20:41:47.185211: step: 1628/1545, loss: 0.00761990062892437 2023-01-23 20:41:48.090281: step: 1630/1545, loss: 0.00012945086928084493 2023-01-23 20:41:48.954185: step: 1632/1545, loss: 0.0023219778668135405 2023-01-23 20:41:49.805914: step: 1634/1545, loss: 8.331882418133318e-05 2023-01-23 20:41:50.690590: step: 1636/1545, loss: 5.871942266821861e-05 2023-01-23 20:41:51.562560: step: 1638/1545, loss: 0.029504546895623207 2023-01-23 20:41:52.444713: step: 1640/1545, loss: 0.00014498044038191438 2023-01-23 20:41:53.354479: step: 1642/1545, loss: 1.2455822798074223e-05 2023-01-23 20:41:54.287300: step: 1644/1545, loss: 0.0001286119077121839 2023-01-23 20:41:55.216460: step: 1646/1545, loss: 0.9536548852920532 2023-01-23 20:41:56.124485: step: 1648/1545, loss: 0.002779980655759573 2023-01-23 20:41:56.972922: step: 1650/1545, loss: 2.1917699996265583e-05 2023-01-23 20:41:57.814687: step: 1652/1545, loss: 0.0016634904313832521 2023-01-23 20:41:58.680251: step: 1654/1545, loss: 0.00023467425489798188 2023-01-23 20:41:59.567441: step: 1656/1545, loss: 2.4477019906044006e-05 2023-01-23 20:42:00.544823: step: 1658/1545, loss: 9.516262070974335e-05 2023-01-23 20:42:01.399222: step: 1660/1545, loss: 0.00011893918417626992 2023-01-23 20:42:02.362322: step: 1662/1545, loss: 0.00026379269547760487 2023-01-23 20:42:03.228766: step: 1664/1545, loss: 0.026978561654686928 2023-01-23 20:42:04.105106: step: 1666/1545, loss: 0.006499787326902151 2023-01-23 20:42:04.960419: step: 1668/1545, loss: 4.289532080292702e-05 2023-01-23 20:42:05.813211: step: 1670/1545, loss: 0.09958894550800323 2023-01-23 20:42:06.760104: step: 1672/1545, loss: 0.008741800673305988 2023-01-23 20:42:07.622887: step: 1674/1545, loss: 0.15375462174415588 2023-01-23 20:42:08.499244: step: 1676/1545, loss: 0.0012403057189658284 2023-01-23 20:42:09.414833: step: 1678/1545, loss: 0.0026367977261543274 2023-01-23 20:42:10.289280: step: 1680/1545, loss: 3.86923311452847e-05 2023-01-23 20:42:11.176775: step: 1682/1545, loss: 0.000401299970690161 2023-01-23 20:42:12.038539: step: 1684/1545, loss: 0.0016885825898498297 2023-01-23 20:42:12.932856: step: 1686/1545, loss: 0.0013563375687226653 2023-01-23 20:42:13.898355: step: 1688/1545, loss: 0.00026358538889326155 2023-01-23 20:42:14.826001: step: 1690/1545, loss: 0.5320509076118469 2023-01-23 20:42:15.751414: step: 1692/1545, loss: 0.00078892259625718 2023-01-23 20:42:16.651139: step: 1694/1545, loss: 0.010683945380151272 2023-01-23 20:42:17.555198: step: 1696/1545, loss: 0.24961717426776886 2023-01-23 20:42:18.384036: step: 1698/1545, loss: 0.0001677455147728324 2023-01-23 20:42:19.255954: step: 1700/1545, loss: 0.0003422364534344524 2023-01-23 20:42:20.117317: step: 1702/1545, loss: 0.00024987681536003947 2023-01-23 20:42:21.001081: step: 1704/1545, loss: 0.0038182216230779886 2023-01-23 20:42:21.868747: step: 1706/1545, loss: 0.19939161837100983 2023-01-23 20:42:22.781660: step: 1708/1545, loss: 0.19964082539081573 2023-01-23 20:42:23.659582: step: 1710/1545, loss: 0.009220032021403313 2023-01-23 20:42:24.585148: step: 1712/1545, loss: 0.01088679675012827 2023-01-23 20:42:25.442044: step: 1714/1545, loss: 0.08942652493715286 2023-01-23 20:42:26.354387: step: 1716/1545, loss: 0.00019038440950680524 2023-01-23 20:42:27.212827: step: 1718/1545, loss: 9.901046723825857e-05 2023-01-23 20:42:28.121251: step: 1720/1545, loss: 0.0068259527906775475 2023-01-23 20:42:29.051374: step: 1722/1545, loss: 0.01505956333130598 2023-01-23 20:42:30.035252: step: 1724/1545, loss: 0.021599844098091125 2023-01-23 20:42:30.895616: step: 1726/1545, loss: 0.02415154129266739 2023-01-23 20:42:31.793233: step: 1728/1545, loss: 0.0029222597368061543 2023-01-23 20:42:32.672876: step: 1730/1545, loss: 0.014181860722601414 2023-01-23 20:42:33.554392: step: 1732/1545, loss: 0.0005007670843042433 2023-01-23 20:42:34.403315: step: 1734/1545, loss: 0.024160664528608322 2023-01-23 20:42:35.296522: step: 1736/1545, loss: 0.00027231787680648267 2023-01-23 20:42:36.149620: step: 1738/1545, loss: 0.0011509519536048174 2023-01-23 20:42:37.040379: step: 1740/1545, loss: 0.0027543685864657164 2023-01-23 20:42:38.015351: step: 1742/1545, loss: 0.0016709454357624054 2023-01-23 20:42:38.900437: step: 1744/1545, loss: 0.0045400504022836685 2023-01-23 20:42:39.782661: step: 1746/1545, loss: 0.00011775216262321919 2023-01-23 20:42:40.647283: step: 1748/1545, loss: 0.00010657086386345327 2023-01-23 20:42:41.508889: step: 1750/1545, loss: 0.00046293085324577987 2023-01-23 20:42:42.392100: step: 1752/1545, loss: 0.011228200048208237 2023-01-23 20:42:43.251890: step: 1754/1545, loss: 0.00030938981217332184 2023-01-23 20:42:44.143568: step: 1756/1545, loss: 0.00014007423305884004 2023-01-23 20:42:45.006800: step: 1758/1545, loss: 0.007123436313122511 2023-01-23 20:42:45.912792: step: 1760/1545, loss: 0.004701606929302216 2023-01-23 20:42:46.811365: step: 1762/1545, loss: 0.0018361081602051854 2023-01-23 20:42:47.692573: step: 1764/1545, loss: 0.2907845079898834 2023-01-23 20:42:48.628239: step: 1766/1545, loss: 9.944140765583143e-05 2023-01-23 20:42:49.547588: step: 1768/1545, loss: 8.206229540519416e-05 2023-01-23 20:42:50.412492: step: 1770/1545, loss: 0.007613634690642357 2023-01-23 20:42:51.341021: step: 1772/1545, loss: 0.0075752404518425465 2023-01-23 20:42:52.185284: step: 1774/1545, loss: 0.0005599647993221879 2023-01-23 20:42:53.047914: step: 1776/1545, loss: 0.00015032110968604684 2023-01-23 20:42:53.915956: step: 1778/1545, loss: 0.0012072469107806683 2023-01-23 20:42:54.765382: step: 1780/1545, loss: 0.0017676338320598006 2023-01-23 20:42:55.652168: step: 1782/1545, loss: 0.0012485956540331244 2023-01-23 20:42:56.566279: step: 1784/1545, loss: 0.023935310542583466 2023-01-23 20:42:57.424948: step: 1786/1545, loss: 0.018935350701212883 2023-01-23 20:42:58.307834: step: 1788/1545, loss: 0.03778192028403282 2023-01-23 20:42:59.169265: step: 1790/1545, loss: 0.016315307468175888 2023-01-23 20:43:00.098840: step: 1792/1545, loss: 0.38291770219802856 2023-01-23 20:43:01.000886: step: 1794/1545, loss: 0.0004629764298442751 2023-01-23 20:43:01.847949: step: 1796/1545, loss: 0.03795280307531357 2023-01-23 20:43:02.833431: step: 1798/1545, loss: 0.0019925273954868317 2023-01-23 20:43:03.719048: step: 1800/1545, loss: 0.6347102522850037 2023-01-23 20:43:04.559583: step: 1802/1545, loss: 0.005513194482773542 2023-01-23 20:43:05.562701: step: 1804/1545, loss: 0.043329205363988876 2023-01-23 20:43:06.437211: step: 1806/1545, loss: 0.008338124491274357 2023-01-23 20:43:07.374037: step: 1808/1545, loss: 0.003987387288361788 2023-01-23 20:43:08.268292: step: 1810/1545, loss: 0.001252180663868785 2023-01-23 20:43:09.125162: step: 1812/1545, loss: 0.04063253849744797 2023-01-23 20:43:09.988023: step: 1814/1545, loss: 0.14233717322349548 2023-01-23 20:43:10.871350: step: 1816/1545, loss: 0.0005762953660450876 2023-01-23 20:43:11.725532: step: 1818/1545, loss: 0.007652834057807922 2023-01-23 20:43:12.644086: step: 1820/1545, loss: 0.10247673094272614 2023-01-23 20:43:13.507090: step: 1822/1545, loss: 0.00014482233382295817 2023-01-23 20:43:14.364328: step: 1824/1545, loss: 0.000303763838019222 2023-01-23 20:43:15.274252: step: 1826/1545, loss: 0.00021187383390497416 2023-01-23 20:43:16.190073: step: 1828/1545, loss: 0.001066368306055665 2023-01-23 20:43:17.091972: step: 1830/1545, loss: 0.006113831885159016 2023-01-23 20:43:17.974777: step: 1832/1545, loss: 0.13337472081184387 2023-01-23 20:43:18.841226: step: 1834/1545, loss: 0.005163322202861309 2023-01-23 20:43:19.676221: step: 1836/1545, loss: 0.1335434913635254 2023-01-23 20:43:20.537767: step: 1838/1545, loss: 0.1290794312953949 2023-01-23 20:43:21.409501: step: 1840/1545, loss: 0.9158542156219482 2023-01-23 20:43:22.291738: step: 1842/1545, loss: 0.018063310533761978 2023-01-23 20:43:23.224002: step: 1844/1545, loss: 0.0002820838999468833 2023-01-23 20:43:24.063919: step: 1846/1545, loss: 0.13210910558700562 2023-01-23 20:43:24.956009: step: 1848/1545, loss: 0.00014774984447285533 2023-01-23 20:43:25.846796: step: 1850/1545, loss: 0.009049755521118641 2023-01-23 20:43:26.765504: step: 1852/1545, loss: 0.04849192127585411 2023-01-23 20:43:27.649025: step: 1854/1545, loss: 0.0010009572142735124 2023-01-23 20:43:28.512889: step: 1856/1545, loss: 0.0015507105272263288 2023-01-23 20:43:29.387210: step: 1858/1545, loss: 0.021878790110349655 2023-01-23 20:43:30.268902: step: 1860/1545, loss: 0.11326908320188522 2023-01-23 20:43:31.151773: step: 1862/1545, loss: 0.0022145246621221304 2023-01-23 20:43:32.037243: step: 1864/1545, loss: 0.00675598019734025 2023-01-23 20:43:32.921953: step: 1866/1545, loss: 0.004049857147037983 2023-01-23 20:43:33.812456: step: 1868/1545, loss: 0.0015223239315673709 2023-01-23 20:43:34.680343: step: 1870/1545, loss: 0.027720220386981964 2023-01-23 20:43:35.644318: step: 1872/1545, loss: 0.00417649932205677 2023-01-23 20:43:36.628279: step: 1874/1545, loss: 0.014260214753448963 2023-01-23 20:43:37.639483: step: 1876/1545, loss: 0.12037045508623123 2023-01-23 20:43:38.521175: step: 1878/1545, loss: 0.004935809411108494 2023-01-23 20:43:39.398416: step: 1880/1545, loss: 0.003909865859895945 2023-01-23 20:43:40.357132: step: 1882/1545, loss: 0.21396172046661377 2023-01-23 20:43:41.283354: step: 1884/1545, loss: 0.19539551436901093 2023-01-23 20:43:42.188360: step: 1886/1545, loss: 0.000326927489368245 2023-01-23 20:43:43.103418: step: 1888/1545, loss: 0.005450861994177103 2023-01-23 20:43:43.949934: step: 1890/1545, loss: 0.012642962858080864 2023-01-23 20:43:44.823729: step: 1892/1545, loss: 0.19572781026363373 2023-01-23 20:43:45.746514: step: 1894/1545, loss: 0.0669531300663948 2023-01-23 20:43:46.705631: step: 1896/1545, loss: 0.028690122067928314 2023-01-23 20:43:47.616477: step: 1898/1545, loss: 0.0001062554947566241 2023-01-23 20:43:48.477137: step: 1900/1545, loss: 0.1745244711637497 2023-01-23 20:43:49.394254: step: 1902/1545, loss: 0.00017917007789947093 2023-01-23 20:43:50.293730: step: 1904/1545, loss: 0.00019040853658225387 2023-01-23 20:43:51.227826: step: 1906/1545, loss: 0.17508059740066528 2023-01-23 20:43:52.139144: step: 1908/1545, loss: 0.00013467867393046618 2023-01-23 20:43:53.076193: step: 1910/1545, loss: 0.0017156652174890041 2023-01-23 20:43:53.990353: step: 1912/1545, loss: 0.00670205894857645 2023-01-23 20:43:54.860011: step: 1914/1545, loss: 0.005376799497753382 2023-01-23 20:43:55.719108: step: 1916/1545, loss: 0.0002918114187195897 2023-01-23 20:43:56.565976: step: 1918/1545, loss: 0.000506219919770956 2023-01-23 20:43:57.465223: step: 1920/1545, loss: 0.05340597778558731 2023-01-23 20:43:58.445346: step: 1922/1545, loss: 0.0027615376748144627 2023-01-23 20:43:59.321773: step: 1924/1545, loss: 0.0007711265352554619 2023-01-23 20:44:00.168029: step: 1926/1545, loss: 0.0012985349167138338 2023-01-23 20:44:01.078092: step: 1928/1545, loss: 0.00024951770319603384 2023-01-23 20:44:01.968829: step: 1930/1545, loss: 0.00020857427443843335 2023-01-23 20:44:02.839628: step: 1932/1545, loss: 0.1730252206325531 2023-01-23 20:44:03.738526: step: 1934/1545, loss: 0.00021341329556889832 2023-01-23 20:44:04.609302: step: 1936/1545, loss: 0.002240670844912529 2023-01-23 20:44:05.482854: step: 1938/1545, loss: 0.03280335292220116 2023-01-23 20:44:06.451977: step: 1940/1545, loss: 0.006193172186613083 2023-01-23 20:44:07.341555: step: 1942/1545, loss: 0.0639193132519722 2023-01-23 20:44:08.249479: step: 1944/1545, loss: 0.003345597768202424 2023-01-23 20:44:09.165270: step: 1946/1545, loss: 0.05552365630865097 2023-01-23 20:44:10.060234: step: 1948/1545, loss: 0.002520075999200344 2023-01-23 20:44:10.919695: step: 1950/1545, loss: 0.00021330040181055665 2023-01-23 20:44:11.772055: step: 1952/1545, loss: 0.0006282521644607186 2023-01-23 20:44:12.651716: step: 1954/1545, loss: 0.0002274349972140044 2023-01-23 20:44:13.559990: step: 1956/1545, loss: 0.02397831901907921 2023-01-23 20:44:14.503086: step: 1958/1545, loss: 0.0018266302067786455 2023-01-23 20:44:15.412471: step: 1960/1545, loss: 0.004611401353031397 2023-01-23 20:44:16.286076: step: 1962/1545, loss: 0.0006535917636938393 2023-01-23 20:44:17.209727: step: 1964/1545, loss: 0.0005155306425876915 2023-01-23 20:44:18.149838: step: 1966/1545, loss: 0.05979121848940849 2023-01-23 20:44:19.101417: step: 1968/1545, loss: 0.020643915981054306 2023-01-23 20:44:20.025307: step: 1970/1545, loss: 0.24186797440052032 2023-01-23 20:44:20.904430: step: 1972/1545, loss: 0.0025059611070901155 2023-01-23 20:44:21.845204: step: 1974/1545, loss: 5.9344358305679634e-05 2023-01-23 20:44:22.731666: step: 1976/1545, loss: 0.021247128024697304 2023-01-23 20:44:23.558792: step: 1978/1545, loss: 0.0005565881147049367 2023-01-23 20:44:24.444857: step: 1980/1545, loss: 7.225579611258581e-05 2023-01-23 20:44:25.397082: step: 1982/1545, loss: 0.05376162752509117 2023-01-23 20:44:26.299979: step: 1984/1545, loss: 0.000529807002749294 2023-01-23 20:44:27.160370: step: 1986/1545, loss: 0.00024575143470428884 2023-01-23 20:44:28.086723: step: 1988/1545, loss: 0.014962676912546158 2023-01-23 20:44:29.028154: step: 1990/1545, loss: 0.6926739811897278 2023-01-23 20:44:29.899893: step: 1992/1545, loss: 0.021968742832541466 2023-01-23 20:44:30.751933: step: 1994/1545, loss: 0.18253755569458008 2023-01-23 20:44:31.662631: step: 1996/1545, loss: 0.002016795799136162 2023-01-23 20:44:32.541392: step: 1998/1545, loss: 0.07546966522932053 2023-01-23 20:44:33.445418: step: 2000/1545, loss: 0.045007482171058655 2023-01-23 20:44:34.336391: step: 2002/1545, loss: 0.00768367201089859 2023-01-23 20:44:35.276638: step: 2004/1545, loss: 0.01990777999162674 2023-01-23 20:44:36.174462: step: 2006/1545, loss: 0.00025178989744745195 2023-01-23 20:44:37.071734: step: 2008/1545, loss: 0.0032031007576733828 2023-01-23 20:44:37.923012: step: 2010/1545, loss: 0.22198480367660522 2023-01-23 20:44:38.827839: step: 2012/1545, loss: 0.1033540740609169 2023-01-23 20:44:39.717203: step: 2014/1545, loss: 0.004523304756730795 2023-01-23 20:44:40.552600: step: 2016/1545, loss: 0.0012670084834098816 2023-01-23 20:44:41.451364: step: 2018/1545, loss: 0.04973568022251129 2023-01-23 20:44:42.324617: step: 2020/1545, loss: 0.03228135034441948 2023-01-23 20:44:43.200822: step: 2022/1545, loss: 0.0009933138499036431 2023-01-23 20:44:44.125523: step: 2024/1545, loss: 0.0007151190075092018 2023-01-23 20:44:44.986015: step: 2026/1545, loss: 0.0001632893254281953 2023-01-23 20:44:45.938010: step: 2028/1545, loss: 0.010750615037977695 2023-01-23 20:44:46.846849: step: 2030/1545, loss: 0.0003276415227446705 2023-01-23 20:44:47.717116: step: 2032/1545, loss: 0.0002645280328579247 2023-01-23 20:44:48.578413: step: 2034/1545, loss: 0.00029080049716867507 2023-01-23 20:44:49.453830: step: 2036/1545, loss: 0.0003361858252901584 2023-01-23 20:44:50.291905: step: 2038/1545, loss: 3.983562783105299e-05 2023-01-23 20:44:51.191879: step: 2040/1545, loss: 0.0001808369270293042 2023-01-23 20:44:52.059319: step: 2042/1545, loss: 2.0638703063013963e-05 2023-01-23 20:44:52.925829: step: 2044/1545, loss: 0.08188661187887192 2023-01-23 20:44:53.819697: step: 2046/1545, loss: 0.002571127377450466 2023-01-23 20:44:54.701945: step: 2048/1545, loss: 0.07327178120613098 2023-01-23 20:44:55.563339: step: 2050/1545, loss: 0.004116506315767765 2023-01-23 20:44:56.399184: step: 2052/1545, loss: 0.0008683025953359902 2023-01-23 20:44:57.258291: step: 2054/1545, loss: 0.03952815756201744 2023-01-23 20:44:58.175303: step: 2056/1545, loss: 0.19391411542892456 2023-01-23 20:44:59.006830: step: 2058/1545, loss: 0.03376851975917816 2023-01-23 20:44:59.927561: step: 2060/1545, loss: 0.0002228851371910423 2023-01-23 20:45:00.753301: step: 2062/1545, loss: 6.045894042472355e-05 2023-01-23 20:45:01.630381: step: 2064/1545, loss: 0.000398700445657596 2023-01-23 20:45:02.485064: step: 2066/1545, loss: 0.0016688158502802253 2023-01-23 20:45:03.353975: step: 2068/1545, loss: 0.000741728872526437 2023-01-23 20:45:04.223758: step: 2070/1545, loss: 3.679282235680148e-05 2023-01-23 20:45:05.152065: step: 2072/1545, loss: 0.010853497311472893 2023-01-23 20:45:06.036806: step: 2074/1545, loss: -8.773876288614701e-06 2023-01-23 20:45:06.929495: step: 2076/1545, loss: 0.28287386894226074 2023-01-23 20:45:07.772617: step: 2078/1545, loss: 0.005319348536431789 2023-01-23 20:45:08.639346: step: 2080/1545, loss: 0.0002267853997182101 2023-01-23 20:45:09.539442: step: 2082/1545, loss: 0.0024261712096631527 2023-01-23 20:45:10.418062: step: 2084/1545, loss: 0.06388732045888901 2023-01-23 20:45:11.281782: step: 2086/1545, loss: 0.007385824806988239 2023-01-23 20:45:12.152014: step: 2088/1545, loss: 0.00021840838599018753 2023-01-23 20:45:13.024270: step: 2090/1545, loss: 0.08903945237398148 2023-01-23 20:45:13.894887: step: 2092/1545, loss: 0.00015613572031725198 2023-01-23 20:45:14.795954: step: 2094/1545, loss: 0.00024759816005825996 2023-01-23 20:45:15.701947: step: 2096/1545, loss: 8.375108154723421e-05 2023-01-23 20:45:16.566852: step: 2098/1545, loss: 0.15481236577033997 2023-01-23 20:45:17.413687: step: 2100/1545, loss: 6.276180647546425e-05 2023-01-23 20:45:18.360232: step: 2102/1545, loss: 0.0011339990887790918 2023-01-23 20:45:19.244024: step: 2104/1545, loss: 0.0016847944352775812 2023-01-23 20:45:20.134841: step: 2106/1545, loss: 0.001084722694940865 2023-01-23 20:45:21.036324: step: 2108/1545, loss: 0.0005669723614118993 2023-01-23 20:45:21.888063: step: 2110/1545, loss: 0.0002043641870841384 2023-01-23 20:45:22.748669: step: 2112/1545, loss: 0.13851438462734222 2023-01-23 20:45:23.610866: step: 2114/1545, loss: 0.00018556414579506963 2023-01-23 20:45:24.459291: step: 2116/1545, loss: 0.0007459866465069354 2023-01-23 20:45:25.326427: step: 2118/1545, loss: 0.009196505881845951 2023-01-23 20:45:26.232678: step: 2120/1545, loss: 0.00010246232704957947 2023-01-23 20:45:27.080314: step: 2122/1545, loss: 0.003546970197930932 2023-01-23 20:45:27.969541: step: 2124/1545, loss: 0.0001400372275384143 2023-01-23 20:45:28.825815: step: 2126/1545, loss: 0.006628706119954586 2023-01-23 20:45:29.706725: step: 2128/1545, loss: 0.15410032868385315 2023-01-23 20:45:30.542957: step: 2130/1545, loss: 0.0002287778479512781 2023-01-23 20:45:31.393802: step: 2132/1545, loss: 0.10705438256263733 2023-01-23 20:45:32.364097: step: 2134/1545, loss: 0.0016186849679797888 2023-01-23 20:45:33.227830: step: 2136/1545, loss: 0.0006064669578336179 2023-01-23 20:45:34.132370: step: 2138/1545, loss: 0.000679945747833699 2023-01-23 20:45:35.073647: step: 2140/1545, loss: 0.0016387832583859563 2023-01-23 20:45:35.956097: step: 2142/1545, loss: 0.0008966833120211959 2023-01-23 20:45:36.821308: step: 2144/1545, loss: 0.001746511785313487 2023-01-23 20:45:37.702012: step: 2146/1545, loss: 0.0014270470710471272 2023-01-23 20:45:38.550788: step: 2148/1545, loss: 0.020039409399032593 2023-01-23 20:45:39.441252: step: 2150/1545, loss: 0.030338069424033165 2023-01-23 20:45:40.299998: step: 2152/1545, loss: 0.06992995738983154 2023-01-23 20:45:41.158121: step: 2154/1545, loss: 0.09637877345085144 2023-01-23 20:45:42.029416: step: 2156/1545, loss: -3.406561882002279e-05 2023-01-23 20:45:42.865886: step: 2158/1545, loss: 0.003355054883286357 2023-01-23 20:45:43.750271: step: 2160/1545, loss: 0.00734339002519846 2023-01-23 20:45:44.646098: step: 2162/1545, loss: 0.0005999705754220486 2023-01-23 20:45:45.498167: step: 2164/1545, loss: 0.00017465495329815894 2023-01-23 20:45:46.366809: step: 2166/1545, loss: 0.0009043063037097454 2023-01-23 20:45:47.264222: step: 2168/1545, loss: 0.00014276959700509906 2023-01-23 20:45:48.180003: step: 2170/1545, loss: -1.7218049833900295e-05 2023-01-23 20:45:49.107327: step: 2172/1545, loss: 0.4440753161907196 2023-01-23 20:45:49.963794: step: 2174/1545, loss: 0.0005289055407047272 2023-01-23 20:45:50.877135: step: 2176/1545, loss: 4.5648281229659915e-05 2023-01-23 20:45:51.757971: step: 2178/1545, loss: 0.2297925502061844 2023-01-23 20:45:52.716735: step: 2180/1545, loss: 0.019267844036221504 2023-01-23 20:45:53.571532: step: 2182/1545, loss: 0.17314544320106506 2023-01-23 20:45:54.531442: step: 2184/1545, loss: 0.6762393712997437 2023-01-23 20:45:55.432798: step: 2186/1545, loss: 0.0006906542112119496 2023-01-23 20:45:56.331764: step: 2188/1545, loss: 0.001083816634491086 2023-01-23 20:45:57.217168: step: 2190/1545, loss: 0.0374339297413826 2023-01-23 20:45:58.127680: step: 2192/1545, loss: 0.003436235710978508 2023-01-23 20:45:58.983162: step: 2194/1545, loss: 0.0002876601938623935 2023-01-23 20:45:59.845417: step: 2196/1545, loss: 0.01093149371445179 2023-01-23 20:46:00.724717: step: 2198/1545, loss: 0.004515361972153187 2023-01-23 20:46:01.580418: step: 2200/1545, loss: 0.37799420952796936 2023-01-23 20:46:02.456275: step: 2202/1545, loss: 0.13007359206676483 2023-01-23 20:46:03.298490: step: 2204/1545, loss: 0.12527598440647125 2023-01-23 20:46:04.212668: step: 2206/1545, loss: 0.0004219420370645821 2023-01-23 20:46:05.108818: step: 2208/1545, loss: 0.0007126200362108648 2023-01-23 20:46:06.007727: step: 2210/1545, loss: 0.0032921170350164175 2023-01-23 20:46:06.885236: step: 2212/1545, loss: 0.040830034762620926 2023-01-23 20:46:07.781640: step: 2214/1545, loss: 0.000877218262758106 2023-01-23 20:46:08.675011: step: 2216/1545, loss: 0.00014207925414666533 2023-01-23 20:46:09.519803: step: 2218/1545, loss: 0.0009701478993520141 2023-01-23 20:46:10.385192: step: 2220/1545, loss: 0.0012058409629389644 2023-01-23 20:46:11.297952: step: 2222/1545, loss: 0.005704835057258606 2023-01-23 20:46:12.174523: step: 2224/1545, loss: 0.00227487669326365 2023-01-23 20:46:13.038118: step: 2226/1545, loss: 0.0015607953537255526 2023-01-23 20:46:13.995789: step: 2228/1545, loss: 0.0009346462320536375 2023-01-23 20:46:14.875240: step: 2230/1545, loss: 0.03661808371543884 2023-01-23 20:46:15.777970: step: 2232/1545, loss: 0.016148678958415985 2023-01-23 20:46:16.692476: step: 2234/1545, loss: 0.07587160170078278 2023-01-23 20:46:17.545731: step: 2236/1545, loss: 0.004510391969233751 2023-01-23 20:46:18.416456: step: 2238/1545, loss: 0.0010933802695944905 2023-01-23 20:46:19.292712: step: 2240/1545, loss: 6.494382978416979e-05 2023-01-23 20:46:20.269399: step: 2242/1545, loss: 0.0028119562193751335 2023-01-23 20:46:21.128817: step: 2244/1545, loss: 0.0011436119675636292 2023-01-23 20:46:22.028557: step: 2246/1545, loss: 0.0004921140498481691 2023-01-23 20:46:22.875923: step: 2248/1545, loss: 0.005019799806177616 2023-01-23 20:46:23.792042: step: 2250/1545, loss: 0.00020153906370978802 2023-01-23 20:46:24.684697: step: 2252/1545, loss: 0.010824158787727356 2023-01-23 20:46:25.580649: step: 2254/1545, loss: 0.0037604914978146553 2023-01-23 20:46:26.490933: step: 2256/1545, loss: 0.0006668996065855026 2023-01-23 20:46:27.416617: step: 2258/1545, loss: 0.12493917346000671 2023-01-23 20:46:28.331638: step: 2260/1545, loss: 0.027612274512648582 2023-01-23 20:46:29.221517: step: 2262/1545, loss: 0.191864475607872 2023-01-23 20:46:30.049735: step: 2264/1545, loss: 0.005175381433218718 2023-01-23 20:46:30.901526: step: 2266/1545, loss: 0.0006336984224617481 2023-01-23 20:46:31.856742: step: 2268/1545, loss: 0.0033084240276366472 2023-01-23 20:46:32.704738: step: 2270/1545, loss: 0.0007423239876516163 2023-01-23 20:46:33.598902: step: 2272/1545, loss: 0.011451286263763905 2023-01-23 20:46:34.490627: step: 2274/1545, loss: 0.00016047996177803725 2023-01-23 20:46:35.333301: step: 2276/1545, loss: 0.000902748666703701 2023-01-23 20:46:36.250748: step: 2278/1545, loss: 0.02487867698073387 2023-01-23 20:46:37.122532: step: 2280/1545, loss: 4.84740266983863e-05 2023-01-23 20:46:38.009536: step: 2282/1545, loss: 0.0004076925397384912 2023-01-23 20:46:38.890779: step: 2284/1545, loss: 4.2887440940830857e-05 2023-01-23 20:46:39.786749: step: 2286/1545, loss: 0.008977806195616722 2023-01-23 20:46:40.684334: step: 2288/1545, loss: 0.03147411718964577 2023-01-23 20:46:41.542402: step: 2290/1545, loss: 0.0019686201121658087 2023-01-23 20:46:42.463357: step: 2292/1545, loss: 0.011747320182621479 2023-01-23 20:46:43.284868: step: 2294/1545, loss: 0.009244217537343502 2023-01-23 20:46:44.128272: step: 2296/1545, loss: 0.00018405170703772455 2023-01-23 20:46:44.968533: step: 2298/1545, loss: 0.06426206976175308 2023-01-23 20:46:45.852404: step: 2300/1545, loss: 0.001430242438800633 2023-01-23 20:46:46.706833: step: 2302/1545, loss: 0.06255660951137543 2023-01-23 20:46:47.610461: step: 2304/1545, loss: 0.09413264691829681 2023-01-23 20:46:48.475727: step: 2306/1545, loss: 0.27973344922065735 2023-01-23 20:46:49.355325: step: 2308/1545, loss: 0.0019787298515439034 2023-01-23 20:46:50.206048: step: 2310/1545, loss: 0.0002829481672961265 2023-01-23 20:46:51.072038: step: 2312/1545, loss: 0.00020452841999940574 2023-01-23 20:46:51.891663: step: 2314/1545, loss: 4.967749191564508e-06 2023-01-23 20:46:52.752123: step: 2316/1545, loss: -9.512902579444926e-06 2023-01-23 20:46:53.618728: step: 2318/1545, loss: 0.0010123117826879025 2023-01-23 20:46:54.487466: step: 2320/1545, loss: 0.00029457625350914896 2023-01-23 20:46:55.357546: step: 2322/1545, loss: 0.0028305561281740665 2023-01-23 20:46:56.193753: step: 2324/1545, loss: 0.0015510121593251824 2023-01-23 20:46:57.110309: step: 2326/1545, loss: 0.2070557177066803 2023-01-23 20:46:57.998382: step: 2328/1545, loss: 9.898724965751171e-05 2023-01-23 20:46:58.905737: step: 2330/1545, loss: 0.017162788659334183 2023-01-23 20:46:59.785485: step: 2332/1545, loss: 0.02037256397306919 2023-01-23 20:47:00.671072: step: 2334/1545, loss: 0.0009868427878245711 2023-01-23 20:47:01.497800: step: 2336/1545, loss: 0.00010445468069519848 2023-01-23 20:47:02.360518: step: 2338/1545, loss: 1.1247082948684692 2023-01-23 20:47:03.187992: step: 2340/1545, loss: 0.0014613913372159004 2023-01-23 20:47:04.124003: step: 2342/1545, loss: 0.002684373175725341 2023-01-23 20:47:04.969746: step: 2344/1545, loss: 0.08700024336576462 2023-01-23 20:47:05.839962: step: 2346/1545, loss: 1.7887492504087277e-05 2023-01-23 20:47:06.752779: step: 2348/1545, loss: 0.02825670689344406 2023-01-23 20:47:07.640812: step: 2350/1545, loss: 0.0004402439808472991 2023-01-23 20:47:08.506416: step: 2352/1545, loss: 0.05623064562678337 2023-01-23 20:47:09.438554: step: 2354/1545, loss: 5.14496277901344e-05 2023-01-23 20:47:10.379309: step: 2356/1545, loss: 4.201311821816489e-05 2023-01-23 20:47:11.243477: step: 2358/1545, loss: -1.3986621524963994e-05 2023-01-23 20:47:12.162062: step: 2360/1545, loss: 0.0002658381999935955 2023-01-23 20:47:13.013221: step: 2362/1545, loss: 0.00020630136714316905 2023-01-23 20:47:13.948007: step: 2364/1545, loss: 3.099664900219068e-05 2023-01-23 20:47:14.827146: step: 2366/1545, loss: 0.14184288680553436 2023-01-23 20:47:15.723132: step: 2368/1545, loss: 0.13739784061908722 2023-01-23 20:47:16.608269: step: 2370/1545, loss: 0.04710765182971954 2023-01-23 20:47:17.503450: step: 2372/1545, loss: 0.0001812265400076285 2023-01-23 20:47:18.395671: step: 2374/1545, loss: 0.8779939413070679 2023-01-23 20:47:19.308929: step: 2376/1545, loss: 0.004098038654774427 2023-01-23 20:47:20.183219: step: 2378/1545, loss: 2.7543305805011187e-06 2023-01-23 20:47:21.031695: step: 2380/1545, loss: 0.06933823227882385 2023-01-23 20:47:21.921701: step: 2382/1545, loss: 0.08512576669454575 2023-01-23 20:47:22.808782: step: 2384/1545, loss: 0.029510967433452606 2023-01-23 20:47:23.654001: step: 2386/1545, loss: 0.001580381765961647 2023-01-23 20:47:24.531748: step: 2388/1545, loss: 0.0058370670303702354 2023-01-23 20:47:25.421914: step: 2390/1545, loss: 0.16224417090415955 2023-01-23 20:47:26.313054: step: 2392/1545, loss: 0.00011144149175379425 2023-01-23 20:47:27.148987: step: 2394/1545, loss: 0.004971407353878021 2023-01-23 20:47:28.027173: step: 2396/1545, loss: 2.6917437935480848e-05 2023-01-23 20:47:28.899843: step: 2398/1545, loss: 0.009289851412177086 2023-01-23 20:47:29.779520: step: 2400/1545, loss: 0.024993030354380608 2023-01-23 20:47:30.633891: step: 2402/1545, loss: 4.465360689209774e-05 2023-01-23 20:47:31.472650: step: 2404/1545, loss: 0.0024467636831104755 2023-01-23 20:47:32.350258: step: 2406/1545, loss: 0.012445667758584023 2023-01-23 20:47:33.268599: step: 2408/1545, loss: 0.062423523515462875 2023-01-23 20:47:34.145198: step: 2410/1545, loss: 0.5946753621101379 2023-01-23 20:47:35.039086: step: 2412/1545, loss: 0.23139631748199463 2023-01-23 20:47:35.908094: step: 2414/1545, loss: 0.00026944480487145483 2023-01-23 20:47:36.798227: step: 2416/1545, loss: 1.2620263078133576e-05 2023-01-23 20:47:37.635419: step: 2418/1545, loss: 0.0025773767847567797 2023-01-23 20:47:38.489837: step: 2420/1545, loss: 0.15378634631633759 2023-01-23 20:47:39.407181: step: 2422/1545, loss: 0.5612740516662598 2023-01-23 20:47:40.241804: step: 2424/1545, loss: 0.04514497518539429 2023-01-23 20:47:41.130450: step: 2426/1545, loss: 0.07545805722475052 2023-01-23 20:47:42.052630: step: 2428/1545, loss: 0.00045531935757026076 2023-01-23 20:47:42.950279: step: 2430/1545, loss: 0.01592574082314968 2023-01-23 20:47:43.825556: step: 2432/1545, loss: 0.008779925294220448 2023-01-23 20:47:44.741930: step: 2434/1545, loss: 0.09263349324464798 2023-01-23 20:47:45.624529: step: 2436/1545, loss: 0.00020847954147029668 2023-01-23 20:47:46.474579: step: 2438/1545, loss: 0.0006956954021006823 2023-01-23 20:47:47.354209: step: 2440/1545, loss: 0.0008668869268149137 2023-01-23 20:47:48.221567: step: 2442/1545, loss: 0.0009355664951726794 2023-01-23 20:47:49.043115: step: 2444/1545, loss: 0.0004396000294946134 2023-01-23 20:47:49.895558: step: 2446/1545, loss: 0.0005427052383311093 2023-01-23 20:47:50.749344: step: 2448/1545, loss: 0.0007389439269900322 2023-01-23 20:47:51.606361: step: 2450/1545, loss: 0.024661235511302948 2023-01-23 20:47:52.519845: step: 2452/1545, loss: 0.00015045475447550416 2023-01-23 20:47:53.370400: step: 2454/1545, loss: 0.001627463730983436 2023-01-23 20:47:54.283240: step: 2456/1545, loss: 1.726076880004257e-05 2023-01-23 20:47:55.132870: step: 2458/1545, loss: 9.230552677763626e-05 2023-01-23 20:47:56.002711: step: 2460/1545, loss: 0.01178791280835867 2023-01-23 20:47:56.884143: step: 2462/1545, loss: 0.0006715935887768865 2023-01-23 20:47:57.758316: step: 2464/1545, loss: 0.009222928434610367 2023-01-23 20:47:58.619117: step: 2466/1545, loss: 0.0014566945610567927 2023-01-23 20:47:59.519047: step: 2468/1545, loss: 0.0006633737939409912 2023-01-23 20:48:00.495189: step: 2470/1545, loss: 0.0005276315496303141 2023-01-23 20:48:01.367859: step: 2472/1545, loss: 0.012426057830452919 2023-01-23 20:48:02.238202: step: 2474/1545, loss: 0.013408356346189976 2023-01-23 20:48:03.167626: step: 2476/1545, loss: 4.276575054973364e-05 2023-01-23 20:48:04.014059: step: 2478/1545, loss: 0.4677908718585968 2023-01-23 20:48:04.889011: step: 2480/1545, loss: 0.005259677302092314 2023-01-23 20:48:05.821255: step: 2482/1545, loss: 2.7066629627370276e-05 2023-01-23 20:48:06.668399: step: 2484/1545, loss: 0.0028391366358846426 2023-01-23 20:48:07.575601: step: 2486/1545, loss: 0.004847191274166107 2023-01-23 20:48:08.457215: step: 2488/1545, loss: 0.025693736970424652 2023-01-23 20:48:09.326445: step: 2490/1545, loss: 0.00012829121260438114 2023-01-23 20:48:10.176168: step: 2492/1545, loss: 0.000471610197564587 2023-01-23 20:48:11.071370: step: 2494/1545, loss: 0.0023800355847924948 2023-01-23 20:48:11.940602: step: 2496/1545, loss: 0.9284035563468933 2023-01-23 20:48:12.795070: step: 2498/1545, loss: 0.00036225488292984664 2023-01-23 20:48:13.628643: step: 2500/1545, loss: 0.0007345033809542656 2023-01-23 20:48:14.471415: step: 2502/1545, loss: -9.487082934356295e-06 2023-01-23 20:48:15.334830: step: 2504/1545, loss: 0.010128241032361984 2023-01-23 20:48:16.206749: step: 2506/1545, loss: 0.0011343449587002397 2023-01-23 20:48:17.081715: step: 2508/1545, loss: 0.11154942214488983 2023-01-23 20:48:17.928212: step: 2510/1545, loss: 9.420024434803054e-05 2023-01-23 20:48:18.792515: step: 2512/1545, loss: 0.0019800132140517235 2023-01-23 20:48:19.740874: step: 2514/1545, loss: 0.0002612923562992364 2023-01-23 20:48:20.631737: step: 2516/1545, loss: 0.03272389620542526 2023-01-23 20:48:21.558242: step: 2518/1545, loss: 0.0008161187288351357 2023-01-23 20:48:22.414817: step: 2520/1545, loss: 0.02621288225054741 2023-01-23 20:48:23.266147: step: 2522/1545, loss: 0.00013872599811293185 2023-01-23 20:48:24.097807: step: 2524/1545, loss: 0.0003897820133715868 2023-01-23 20:48:24.971234: step: 2526/1545, loss: 0.0008929267642088234 2023-01-23 20:48:25.856515: step: 2528/1545, loss: 0.010268797166645527 2023-01-23 20:48:26.716778: step: 2530/1545, loss: 0.09271711111068726 2023-01-23 20:48:27.568995: step: 2532/1545, loss: 0.00418971199542284 2023-01-23 20:48:28.447889: step: 2534/1545, loss: 0.028850076720118523 2023-01-23 20:48:29.325344: step: 2536/1545, loss: 7.57108282414265e-05 2023-01-23 20:48:30.189642: step: 2538/1545, loss: 0.0015474633546546102 2023-01-23 20:48:31.083598: step: 2540/1545, loss: 0.0017330219270661473 2023-01-23 20:48:31.952099: step: 2542/1545, loss: 0.48285168409347534 2023-01-23 20:48:32.822960: step: 2544/1545, loss: 0.12511605024337769 2023-01-23 20:48:33.750231: step: 2546/1545, loss: 0.009454675018787384 2023-01-23 20:48:34.605257: step: 2548/1545, loss: 0.001703458372503519 2023-01-23 20:48:35.477246: step: 2550/1545, loss: 0.0051477160304784775 2023-01-23 20:48:36.371367: step: 2552/1545, loss: 3.4619126381585374e-05 2023-01-23 20:48:37.249994: step: 2554/1545, loss: 0.2355204075574875 2023-01-23 20:48:38.178530: step: 2556/1545, loss: 0.15620467066764832 2023-01-23 20:48:39.120146: step: 2558/1545, loss: 0.7242690324783325 2023-01-23 20:48:39.995889: step: 2560/1545, loss: 0.025991229340434074 2023-01-23 20:48:40.822850: step: 2562/1545, loss: 0.007230894640088081 2023-01-23 20:48:41.756514: step: 2564/1545, loss: 0.39490336179733276 2023-01-23 20:48:42.766180: step: 2566/1545, loss: 0.16274338960647583 2023-01-23 20:48:43.688995: step: 2568/1545, loss: 0.1689338982105255 2023-01-23 20:48:44.575391: step: 2570/1545, loss: 0.16937346756458282 2023-01-23 20:48:45.455263: step: 2572/1545, loss: 0.13253408670425415 2023-01-23 20:48:46.327534: step: 2574/1545, loss: 8.878296648617834e-05 2023-01-23 20:48:47.204440: step: 2576/1545, loss: 8.084381261141971e-05 2023-01-23 20:48:48.066630: step: 2578/1545, loss: 0.0002935542433988303 2023-01-23 20:48:48.963884: step: 2580/1545, loss: 8.023980626603588e-06 2023-01-23 20:48:49.833400: step: 2582/1545, loss: 0.43811124563217163 2023-01-23 20:48:50.678076: step: 2584/1545, loss: 0.00022175164485815912 2023-01-23 20:48:51.563758: step: 2586/1545, loss: 0.006613180506974459 2023-01-23 20:48:52.456995: step: 2588/1545, loss: 0.11399001628160477 2023-01-23 20:48:53.320442: step: 2590/1545, loss: 5.3678115364164114e-05 2023-01-23 20:48:54.170760: step: 2592/1545, loss: 0.0017497092485427856 2023-01-23 20:48:55.059979: step: 2594/1545, loss: 0.012943337671458721 2023-01-23 20:48:55.916734: step: 2596/1545, loss: 0.005995097570121288 2023-01-23 20:48:56.773350: step: 2598/1545, loss: 0.003540296806022525 2023-01-23 20:48:57.666463: step: 2600/1545, loss: 0.0059737758710980415 2023-01-23 20:48:58.543726: step: 2602/1545, loss: 2.5343442757730372e-05 2023-01-23 20:48:59.448955: step: 2604/1545, loss: 0.003738485975190997 2023-01-23 20:49:00.335126: step: 2606/1545, loss: 0.4452309012413025 2023-01-23 20:49:01.246942: step: 2608/1545, loss: -3.122628550045192e-05 2023-01-23 20:49:02.100214: step: 2610/1545, loss: 0.0800878033041954 2023-01-23 20:49:02.998853: step: 2612/1545, loss: 0.05541576072573662 2023-01-23 20:49:03.869240: step: 2614/1545, loss: 0.000604582775849849 2023-01-23 20:49:04.714466: step: 2616/1545, loss: 0.0017005272675305605 2023-01-23 20:49:05.575398: step: 2618/1545, loss: 1.68831211340148e-05 2023-01-23 20:49:06.459124: step: 2620/1545, loss: 0.1167658120393753 2023-01-23 20:49:07.330379: step: 2622/1545, loss: 0.009438388980925083 2023-01-23 20:49:08.187017: step: 2624/1545, loss: 0.00021517901041079313 2023-01-23 20:49:09.061613: step: 2626/1545, loss: 6.27964036539197e-05 2023-01-23 20:49:09.920628: step: 2628/1545, loss: 0.0010352623648941517 2023-01-23 20:49:10.796941: step: 2630/1545, loss: 0.4562568962574005 2023-01-23 20:49:11.655098: step: 2632/1545, loss: 0.3839224874973297 2023-01-23 20:49:12.575976: step: 2634/1545, loss: 0.0003478986327536404 2023-01-23 20:49:13.431890: step: 2636/1545, loss: 0.0002222504117526114 2023-01-23 20:49:14.254294: step: 2638/1545, loss: 0.02303014136850834 2023-01-23 20:49:15.103534: step: 2640/1545, loss: 0.024752167984843254 2023-01-23 20:49:15.952285: step: 2642/1545, loss: 0.0003969172539655119 2023-01-23 20:49:16.808805: step: 2644/1545, loss: 0.00030663111829198897 2023-01-23 20:49:17.726383: step: 2646/1545, loss: 0.12160445004701614 2023-01-23 20:49:18.589420: step: 2648/1545, loss: 0.00016036926535889506 2023-01-23 20:49:19.455666: step: 2650/1545, loss: 0.14441128075122833 2023-01-23 20:49:20.298809: step: 2652/1545, loss: 4.9584541557123885e-05 2023-01-23 20:49:21.148726: step: 2654/1545, loss: 0.0008307307143695652 2023-01-23 20:49:22.057874: step: 2656/1545, loss: 0.005234931595623493 2023-01-23 20:49:22.963432: step: 2658/1545, loss: 4.582121255225502e-05 2023-01-23 20:49:23.839021: step: 2660/1545, loss: 0.010233918204903603 2023-01-23 20:49:24.696805: step: 2662/1545, loss: 0.00030980168958194554 2023-01-23 20:49:25.572089: step: 2664/1545, loss: 0.0002926427696365863 2023-01-23 20:49:26.452256: step: 2666/1545, loss: 0.09565311670303345 2023-01-23 20:49:27.357549: step: 2668/1545, loss: 0.0003343131102155894 2023-01-23 20:49:28.226763: step: 2670/1545, loss: 0.19106397032737732 2023-01-23 20:49:29.051249: step: 2672/1545, loss: 0.00016679101099725813 2023-01-23 20:49:29.912968: step: 2674/1545, loss: 0.015288588590919971 2023-01-23 20:49:30.815343: step: 2676/1545, loss: 0.0003439346910454333 2023-01-23 20:49:31.693409: step: 2678/1545, loss: 0.007998129352927208 2023-01-23 20:49:32.553059: step: 2680/1545, loss: 0.01622169278562069 2023-01-23 20:49:33.433036: step: 2682/1545, loss: 0.0008061387925408781 2023-01-23 20:49:34.306504: step: 2684/1545, loss: 0.002677536802366376 2023-01-23 20:49:35.169049: step: 2686/1545, loss: 0.016059232875704765 2023-01-23 20:49:36.067898: step: 2688/1545, loss: 0.00015926780179142952 2023-01-23 20:49:36.954883: step: 2690/1545, loss: 0.000518782006110996 2023-01-23 20:49:37.819189: step: 2692/1545, loss: 9.703096293378621e-05 2023-01-23 20:49:38.676835: step: 2694/1545, loss: 0.0435374490916729 2023-01-23 20:49:39.575147: step: 2696/1545, loss: 0.00016612622130196542 2023-01-23 20:49:40.446564: step: 2698/1545, loss: 0.019043002277612686 2023-01-23 20:49:41.370573: step: 2700/1545, loss: 0.0012874249368906021 2023-01-23 20:49:42.210098: step: 2702/1545, loss: 7.562279643025249e-05 2023-01-23 20:49:43.066095: step: 2704/1545, loss: 0.04186399653553963 2023-01-23 20:49:43.930549: step: 2706/1545, loss: 0.14268599450588226 2023-01-23 20:49:44.819695: step: 2708/1545, loss: 0.029261156916618347 2023-01-23 20:49:45.717592: step: 2710/1545, loss: 0.0001363186602247879 2023-01-23 20:49:46.597208: step: 2712/1545, loss: 0.0002202262548962608 2023-01-23 20:49:47.512115: step: 2714/1545, loss: 0.021758945658802986 2023-01-23 20:49:48.360842: step: 2716/1545, loss: 0.0005177855491638184 2023-01-23 20:49:49.277665: step: 2718/1545, loss: 0.1494467556476593 2023-01-23 20:49:50.183155: step: 2720/1545, loss: 8.610608347225934e-05 2023-01-23 20:49:51.036223: step: 2722/1545, loss: 0.07871983200311661 2023-01-23 20:49:51.915138: step: 2724/1545, loss: 3.599882256821729e-05 2023-01-23 20:49:52.903773: step: 2726/1545, loss: 0.48177897930145264 2023-01-23 20:49:53.787929: step: 2728/1545, loss: 0.005984250921756029 2023-01-23 20:49:54.661196: step: 2730/1545, loss: 0.0005090683698654175 2023-01-23 20:49:55.528966: step: 2732/1545, loss: 0.055614154785871506 2023-01-23 20:49:56.374338: step: 2734/1545, loss: 0.0006029608193784952 2023-01-23 20:49:57.239375: step: 2736/1545, loss: 0.06456048041582108 2023-01-23 20:49:58.136601: step: 2738/1545, loss: 0.00011793006706284359 2023-01-23 20:49:58.992892: step: 2740/1545, loss: 2.0557938114507124e-05 2023-01-23 20:49:59.869867: step: 2742/1545, loss: 0.30742040276527405 2023-01-23 20:50:00.792416: step: 2744/1545, loss: 0.013581236824393272 2023-01-23 20:50:01.644155: step: 2746/1545, loss: -2.3342427084571682e-05 2023-01-23 20:50:02.542056: step: 2748/1545, loss: 0.0003147645911667496 2023-01-23 20:50:03.421001: step: 2750/1545, loss: 9.956409485312179e-05 2023-01-23 20:50:04.303730: step: 2752/1545, loss: 0.0003307110455352813 2023-01-23 20:50:05.178142: step: 2754/1545, loss: 0.0031659137457609177 2023-01-23 20:50:06.122888: step: 2756/1545, loss: 0.00014674778503831476 2023-01-23 20:50:07.024043: step: 2758/1545, loss: 0.000596294819843024 2023-01-23 20:50:07.914104: step: 2760/1545, loss: 0.004242838826030493 2023-01-23 20:50:08.781462: step: 2762/1545, loss: 0.0018117026193067431 2023-01-23 20:50:09.667215: step: 2764/1545, loss: 3.2705785997677594e-05 2023-01-23 20:50:10.521751: step: 2766/1545, loss: 0.0003095963329542428 2023-01-23 20:50:11.406193: step: 2768/1545, loss: 0.06158731132745743 2023-01-23 20:50:12.287706: step: 2770/1545, loss: 0.15631847083568573 2023-01-23 20:50:13.167883: step: 2772/1545, loss: 0.013662944547832012 2023-01-23 20:50:14.017460: step: 2774/1545, loss: 0.016017012298107147 2023-01-23 20:50:14.926692: step: 2776/1545, loss: 0.00027516274712979794 2023-01-23 20:50:15.919130: step: 2778/1545, loss: 0.00025319584528915584 2023-01-23 20:50:16.752588: step: 2780/1545, loss: 0.0007195523357950151 2023-01-23 20:50:17.668203: step: 2782/1545, loss: 0.00024152481637429446 2023-01-23 20:50:18.610271: step: 2784/1545, loss: 0.0002479467075318098 2023-01-23 20:50:19.483879: step: 2786/1545, loss: 0.0017171860672533512 2023-01-23 20:50:20.383138: step: 2788/1545, loss: 0.0023999002296477556 2023-01-23 20:50:21.228614: step: 2790/1545, loss: 0.0008747227839194238 2023-01-23 20:50:22.111178: step: 2792/1545, loss: 0.005238599609583616 2023-01-23 20:50:23.029066: step: 2794/1545, loss: 0.0004928349517285824 2023-01-23 20:50:23.856432: step: 2796/1545, loss: 0.001206304063089192 2023-01-23 20:50:24.736883: step: 2798/1545, loss: 0.00016604250413365662 2023-01-23 20:50:25.591710: step: 2800/1545, loss: 0.00043390796054154634 2023-01-23 20:50:26.486202: step: 2802/1545, loss: 0.008448834531009197 2023-01-23 20:50:27.340128: step: 2804/1545, loss: 0.004396276082843542 2023-01-23 20:50:28.193112: step: 2806/1545, loss: 0.01830880343914032 2023-01-23 20:50:29.060730: step: 2808/1545, loss: 0.007369702681899071 2023-01-23 20:50:29.940994: step: 2810/1545, loss: 0.012197605334222317 2023-01-23 20:50:30.792395: step: 2812/1545, loss: 0.02416851557791233 2023-01-23 20:50:31.647296: step: 2814/1545, loss: 0.0006081592873670161 2023-01-23 20:50:32.483093: step: 2816/1545, loss: 0.00020128762116655707 2023-01-23 20:50:33.342125: step: 2818/1545, loss: 0.15396806597709656 2023-01-23 20:50:34.267720: step: 2820/1545, loss: 0.00012728170258924365 2023-01-23 20:50:35.134623: step: 2822/1545, loss: 0.0012729642912745476 2023-01-23 20:50:35.979394: step: 2824/1545, loss: 0.00016134197358042002 2023-01-23 20:50:36.860180: step: 2826/1545, loss: 0.031144117936491966 2023-01-23 20:50:37.898575: step: 2828/1545, loss: 0.00021810215548612177 2023-01-23 20:50:38.791447: step: 2830/1545, loss: 0.0009827547473832965 2023-01-23 20:50:39.647103: step: 2832/1545, loss: 0.0007190383039414883 2023-01-23 20:50:40.544084: step: 2834/1545, loss: 1.8756369352340698 2023-01-23 20:50:41.374107: step: 2836/1545, loss: 0.00038850997225381434 2023-01-23 20:50:42.258155: step: 2838/1545, loss: 0.29437536001205444 2023-01-23 20:50:43.108387: step: 2840/1545, loss: 0.18572242558002472 2023-01-23 20:50:43.988045: step: 2842/1545, loss: 0.3672489821910858 2023-01-23 20:50:44.850733: step: 2844/1545, loss: 0.00019141494703944772 2023-01-23 20:50:45.727531: step: 2846/1545, loss: 0.0038589956238865852 2023-01-23 20:50:46.596709: step: 2848/1545, loss: 0.30500829219818115 2023-01-23 20:50:47.479611: step: 2850/1545, loss: 0.008737362921237946 2023-01-23 20:50:48.342126: step: 2852/1545, loss: 0.01791289448738098 2023-01-23 20:50:49.235423: step: 2854/1545, loss: 0.24053902924060822 2023-01-23 20:50:50.114002: step: 2856/1545, loss: 0.0142951225861907 2023-01-23 20:50:50.980839: step: 2858/1545, loss: 0.004080117214471102 2023-01-23 20:50:51.880923: step: 2860/1545, loss: 0.0047743916511535645 2023-01-23 20:50:52.788651: step: 2862/1545, loss: 0.0008255425491370261 2023-01-23 20:50:53.636193: step: 2864/1545, loss: 6.830742495367303e-05 2023-01-23 20:50:54.488242: step: 2866/1545, loss: 0.0011766154784709215 2023-01-23 20:50:55.326538: step: 2868/1545, loss: 0.016519246622920036 2023-01-23 20:50:56.188448: step: 2870/1545, loss: 0.0003051042149309069 2023-01-23 20:50:57.044533: step: 2872/1545, loss: 0.0002053938660537824 2023-01-23 20:50:57.913979: step: 2874/1545, loss: 0.0034897224977612495 2023-01-23 20:50:58.820909: step: 2876/1545, loss: 0.0003206109395250678 2023-01-23 20:50:59.716619: step: 2878/1545, loss: 4.368061854620464e-05 2023-01-23 20:51:00.652973: step: 2880/1545, loss: 0.16532614827156067 2023-01-23 20:51:01.505953: step: 2882/1545, loss: 0.031366363167762756 2023-01-23 20:51:02.385292: step: 2884/1545, loss: 0.25140857696533203 2023-01-23 20:51:03.278291: step: 2886/1545, loss: 0.00030697649344801903 2023-01-23 20:51:04.146386: step: 2888/1545, loss: 0.021631671115756035 2023-01-23 20:51:05.030750: step: 2890/1545, loss: 0.013214493170380592 2023-01-23 20:51:05.967433: step: 2892/1545, loss: 0.004247176926583052 2023-01-23 20:51:06.821725: step: 2894/1545, loss: 0.00010698822734411806 2023-01-23 20:51:07.670917: step: 2896/1545, loss: 0.001008543185889721 2023-01-23 20:51:08.533398: step: 2898/1545, loss: 0.001829063519835472 2023-01-23 20:51:09.454600: step: 2900/1545, loss: 0.0001821652112994343 2023-01-23 20:51:10.313843: step: 2902/1545, loss: 0.01536671444773674 2023-01-23 20:51:11.191602: step: 2904/1545, loss: 0.0036010267212986946 2023-01-23 20:51:12.039067: step: 2906/1545, loss: 0.0007290028152056038 2023-01-23 20:51:12.911397: step: 2908/1545, loss: 0.00021466673933900893 2023-01-23 20:51:13.841849: step: 2910/1545, loss: 7.111806917237118e-05 2023-01-23 20:51:14.701437: step: 2912/1545, loss: 0.00011686558718793094 2023-01-23 20:51:15.574817: step: 2914/1545, loss: 0.016105972230434418 2023-01-23 20:51:16.478319: step: 2916/1545, loss: 0.0004060897626914084 2023-01-23 20:51:17.316350: step: 2918/1545, loss: 0.002030771691352129 2023-01-23 20:51:18.166647: step: 2920/1545, loss: 0.012690401636064053 2023-01-23 20:51:19.017325: step: 2922/1545, loss: 0.04666856676340103 2023-01-23 20:51:19.897910: step: 2924/1545, loss: 0.23638945817947388 2023-01-23 20:51:20.787256: step: 2926/1545, loss: 0.029859360307455063 2023-01-23 20:51:21.629973: step: 2928/1545, loss: 0.00022779589926358312 2023-01-23 20:51:22.510842: step: 2930/1545, loss: 0.0003345747827552259 2023-01-23 20:51:23.375264: step: 2932/1545, loss: 0.1141682118177414 2023-01-23 20:51:24.277765: step: 2934/1545, loss: 0.2680228054523468 2023-01-23 20:51:25.142792: step: 2936/1545, loss: 0.0008020729292184114 2023-01-23 20:51:26.004398: step: 2938/1545, loss: 1.395791241520783e-05 2023-01-23 20:51:26.882693: step: 2940/1545, loss: 0.0017300922190770507 2023-01-23 20:51:27.762186: step: 2942/1545, loss: 0.00027537913410924375 2023-01-23 20:51:28.722288: step: 2944/1545, loss: 0.004535742569714785 2023-01-23 20:51:29.605769: step: 2946/1545, loss: 0.07144208997488022 2023-01-23 20:51:30.434423: step: 2948/1545, loss: 0.0004963607061654329 2023-01-23 20:51:31.340949: step: 2950/1545, loss: 0.155659019947052 2023-01-23 20:51:32.200332: step: 2952/1545, loss: 0.016738353297114372 2023-01-23 20:51:33.060237: step: 2954/1545, loss: 0.18848244845867157 2023-01-23 20:51:33.945402: step: 2956/1545, loss: 0.006828381214290857 2023-01-23 20:51:34.889310: step: 2958/1545, loss: 0.00048370816512033343 2023-01-23 20:51:35.850530: step: 2960/1545, loss: 0.010927190072834492 2023-01-23 20:51:36.741277: step: 2962/1545, loss: 0.004776502028107643 2023-01-23 20:51:37.614239: step: 2964/1545, loss: 0.08269356936216354 2023-01-23 20:51:38.481037: step: 2966/1545, loss: 0.0010283275041729212 2023-01-23 20:51:39.381908: step: 2968/1545, loss: 0.00023374331067316234 2023-01-23 20:51:40.315359: step: 2970/1545, loss: 0.0004855368169955909 2023-01-23 20:51:41.173446: step: 2972/1545, loss: 0.0008173002861440182 2023-01-23 20:51:42.034120: step: 2974/1545, loss: 0.0028520706109702587 2023-01-23 20:51:42.939889: step: 2976/1545, loss: 0.049451619386672974 2023-01-23 20:51:43.800126: step: 2978/1545, loss: 0.026699082925915718 2023-01-23 20:51:44.700057: step: 2980/1545, loss: 0.0013816604623571038 2023-01-23 20:51:45.614280: step: 2982/1545, loss: 0.030710430815815926 2023-01-23 20:51:46.641999: step: 2984/1545, loss: 0.028410879895091057 2023-01-23 20:51:47.490208: step: 2986/1545, loss: 0.21196044981479645 2023-01-23 20:51:48.342058: step: 2988/1545, loss: 0.0007319805445149541 2023-01-23 20:51:49.204807: step: 2990/1545, loss: 9.85350416158326e-05 2023-01-23 20:51:50.071317: step: 2992/1545, loss: 0.0010870093246921897 2023-01-23 20:51:50.903200: step: 2994/1545, loss: 0.0009913214016705751 2023-01-23 20:51:51.791852: step: 2996/1545, loss: 0.0013844246277585626 2023-01-23 20:51:52.649302: step: 2998/1545, loss: 4.483412703848444e-05 2023-01-23 20:51:53.539631: step: 3000/1545, loss: 0.0006354755605570972 2023-01-23 20:51:54.403040: step: 3002/1545, loss: 0.00023680515005253255 2023-01-23 20:51:55.254464: step: 3004/1545, loss: 0.0026813566219061613 2023-01-23 20:51:56.118314: step: 3006/1545, loss: 0.3029747009277344 2023-01-23 20:51:57.057631: step: 3008/1545, loss: 0.00037276765215210617 2023-01-23 20:51:57.922847: step: 3010/1545, loss: 0.17075876891613007 2023-01-23 20:51:58.807146: step: 3012/1545, loss: 0.003143549896776676 2023-01-23 20:51:59.689854: step: 3014/1545, loss: 0.003402502741664648 2023-01-23 20:52:00.533351: step: 3016/1545, loss: 0.0011623413302004337 2023-01-23 20:52:01.411957: step: 3018/1545, loss: 0.20202842354774475 2023-01-23 20:52:02.238526: step: 3020/1545, loss: 0.005957161076366901 2023-01-23 20:52:03.090200: step: 3022/1545, loss: 0.004815300926566124 2023-01-23 20:52:03.955592: step: 3024/1545, loss: 0.0007716035470366478 2023-01-23 20:52:04.849649: step: 3026/1545, loss: 0.0001384291099384427 2023-01-23 20:52:05.721084: step: 3028/1545, loss: 8.841156159178354e-06 2023-01-23 20:52:06.562228: step: 3030/1545, loss: 0.08233742415904999 2023-01-23 20:52:07.454049: step: 3032/1545, loss: 0.004215799272060394 2023-01-23 20:52:08.383078: step: 3034/1545, loss: 0.003563419682905078 2023-01-23 20:52:09.284159: step: 3036/1545, loss: 0.02488061785697937 2023-01-23 20:52:10.170268: step: 3038/1545, loss: 0.0003509664093144238 2023-01-23 20:52:11.034118: step: 3040/1545, loss: 0.0009402832365594804 2023-01-23 20:52:12.066292: step: 3042/1545, loss: 0.0064771282486617565 2023-01-23 20:52:13.021630: step: 3044/1545, loss: 0.2582753598690033 2023-01-23 20:52:13.959647: step: 3046/1545, loss: 0.005033785477280617 2023-01-23 20:52:14.885826: step: 3048/1545, loss: 0.0024885348975658417 2023-01-23 20:52:15.827901: step: 3050/1545, loss: 0.11434236168861389 2023-01-23 20:52:16.667389: step: 3052/1545, loss: 3.7168611015658826e-05 2023-01-23 20:52:17.516081: step: 3054/1545, loss: 0.006682008039206266 2023-01-23 20:52:18.404176: step: 3056/1545, loss: 0.0069344830699265 2023-01-23 20:52:19.331028: step: 3058/1545, loss: 0.0020575763192027807 2023-01-23 20:52:20.178961: step: 3060/1545, loss: 6.030052827554755e-05 2023-01-23 20:52:21.084815: step: 3062/1545, loss: 0.2194368541240692 2023-01-23 20:52:21.939114: step: 3064/1545, loss: 0.00015809900651220232 2023-01-23 20:52:22.840844: step: 3066/1545, loss: 0.0012581736082211137 2023-01-23 20:52:23.731361: step: 3068/1545, loss: 0.10963773727416992 2023-01-23 20:52:24.627948: step: 3070/1545, loss: 0.00066707021323964 2023-01-23 20:52:25.492021: step: 3072/1545, loss: 8.956711099017411e-05 2023-01-23 20:52:26.355558: step: 3074/1545, loss: 0.00020662706810981035 2023-01-23 20:52:27.276918: step: 3076/1545, loss: 0.009794679470360279 2023-01-23 20:52:28.152500: step: 3078/1545, loss: -1.1337315299897455e-05 2023-01-23 20:52:29.132898: step: 3080/1545, loss: 0.0001053572486853227 2023-01-23 20:52:30.000458: step: 3082/1545, loss: 0.0002592896926216781 2023-01-23 20:52:30.871202: step: 3084/1545, loss: 0.14219439029693604 2023-01-23 20:52:31.766919: step: 3086/1545, loss: 4.049696144647896e-05 2023-01-23 20:52:32.598361: step: 3088/1545, loss: 0.017552947625517845 2023-01-23 20:52:33.472706: step: 3090/1545, loss: 2.2707690732204355e-05 ================================================== Loss: 0.052 -------------------- Dev Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6758987924276707, 'r': 0.6414709887684336, 'f1': 0.6582350269068861}, 'combined': 0.43408784748056034, 'epoch': 33} Test Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7201409239897084, 'r': 0.7110669833666995, 'f1': 0.7155751890249322}, 'combined': 0.49952892776609586, 'epoch': 33} Dev Korean: {'event': {'p': 0.6083150984682714, 'r': 0.7403462050599201, 'f1': 0.667867867867868}, 'argument': {'p': 0.6759653888065972, 'r': 0.6404149927010662, 'f1': 0.6577101506829622}, 'combined': 0.4392634760116842, 'epoch': 33} Test Korean: {'event': {'p': 0.6322751322751323, 'r': 0.7640664961636828, 'f1': 0.6919513607411696}, 'argument': {'p': 0.7140529651685205, 'r': 0.7064131168594955, 'f1': 0.7102124958975411}, 'combined': 0.4914325029516859, 'epoch': 33} Dev Russian: {'event': {'p': 0.5728346456692913, 'r': 0.7749667110519307, 'f1': 0.6587436332767402}, 'argument': {'p': 0.6686780590067114, 'r': 0.6533611671754911, 'f1': 0.6609308838118473}, 'combined': 0.43538401174702335, 'epoch': 33} Test Russian: {'event': {'p': 0.6287992027902342, 'r': 0.8069053708439897, 'f1': 0.7068048165779893}, 'argument': {'p': 0.7210169141479743, 'r': 0.7193972580323292, 'f1': 0.7202061754888874}, 'combined': 0.5090451937647583, 'epoch': 33} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7175290642271774, 'r': 0.6285791802320727, 'f1': 0.6701152494104036}, 'combined': 0.4772032836710449, 'epoch': 33} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6791554357592093, 'r': 0.4999338624338624, 'f1': 0.5759238095238095}, 'combined': 0.3536374269005848, 'epoch': 33} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5817314502918499, 'r': 0.5505672654547865, 'f1': 0.5657204929443678}, 'combined': 0.3294068693093786, 'epoch': 33} New best chinese model... ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6758987924276707, 'r': 0.6414709887684336, 'f1': 0.6582350269068861}, 'combined': 0.43408784748056034, 'epoch': 33} Test for Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7201409239897084, 'r': 0.7110669833666995, 'f1': 0.7155751890249322}, 'combined': 0.49952892776609586, 'epoch': 33} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7175290642271774, 'r': 0.6285791802320727, 'f1': 0.6701152494104036}, 'combined': 0.4772032836710449, 'epoch': 33} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 34 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 20:57:52.740879: step: 2/1545, loss: 0.00012886109470855445 2023-01-23 20:57:53.592255: step: 4/1545, loss: 0.04270683974027634 2023-01-23 20:57:54.484003: step: 6/1545, loss: 6.162719364510849e-05 2023-01-23 20:57:55.326529: step: 8/1545, loss: 0.004928680136799812 2023-01-23 20:57:56.178239: step: 10/1545, loss: 0.00011537015234353021 2023-01-23 20:57:57.048077: step: 12/1545, loss: 4.3291773181408644e-05 2023-01-23 20:57:57.925481: step: 14/1545, loss: 0.2720906734466553 2023-01-23 20:57:58.797059: step: 16/1545, loss: 2.4620292606414296e-05 2023-01-23 20:57:59.731228: step: 18/1545, loss: 0.03622271120548248 2023-01-23 20:58:00.566336: step: 20/1545, loss: 0.0003415083047002554 2023-01-23 20:58:01.450049: step: 22/1545, loss: 0.00025196163915097713 2023-01-23 20:58:02.375776: step: 24/1545, loss: 1.1022546459571458e-05 2023-01-23 20:58:03.265529: step: 26/1545, loss: 0.47917431592941284 2023-01-23 20:58:04.129819: step: 28/1545, loss: 0.00020849634893238544 2023-01-23 20:58:04.988103: step: 30/1545, loss: 0.6652834415435791 2023-01-23 20:58:05.864705: step: 32/1545, loss: 0.00024629320250824094 2023-01-23 20:58:06.729423: step: 34/1545, loss: 0.06760367006063461 2023-01-23 20:58:07.587660: step: 36/1545, loss: -6.6195998442708515e-06 2023-01-23 20:58:08.538137: step: 38/1545, loss: 0.0006934913108125329 2023-01-23 20:58:09.419232: step: 40/1545, loss: 0.024404902011156082 2023-01-23 20:58:10.291931: step: 42/1545, loss: 1.1452092621766496e-05 2023-01-23 20:58:11.189810: step: 44/1545, loss: 6.040452353772707e-05 2023-01-23 20:58:12.040520: step: 46/1545, loss: -1.8307175196241587e-05 2023-01-23 20:58:12.952632: step: 48/1545, loss: 3.9286911487579346e-05 2023-01-23 20:58:13.839498: step: 50/1545, loss: 0.004007137846201658 2023-01-23 20:58:14.752186: step: 52/1545, loss: 4.9827991460915655e-05 2023-01-23 20:58:15.633685: step: 54/1545, loss: 4.5462635171134025e-05 2023-01-23 20:58:16.538912: step: 56/1545, loss: 9.165797382593155e-05 2023-01-23 20:58:17.371480: step: 58/1545, loss: 4.8910354962572455e-05 2023-01-23 20:58:18.266505: step: 60/1545, loss: 5.0384744099574164e-05 2023-01-23 20:58:19.097472: step: 62/1545, loss: 0.00022508838446810842 2023-01-23 20:58:19.944324: step: 64/1545, loss: 0.000153462024172768 2023-01-23 20:58:20.775104: step: 66/1545, loss: 1.7076519725378603e-05 2023-01-23 20:58:21.644208: step: 68/1545, loss: 3.09463866869919e-05 2023-01-23 20:58:22.519784: step: 70/1545, loss: 2.6094985514646396e-05 2023-01-23 20:58:23.375577: step: 72/1545, loss: 6.697764547425322e-07 2023-01-23 20:58:24.245777: step: 74/1545, loss: 0.18392200767993927 2023-01-23 20:58:25.136532: step: 76/1545, loss: 4.857858220930211e-05 2023-01-23 20:58:26.007707: step: 78/1545, loss: 0.000554129364900291 2023-01-23 20:58:26.884355: step: 80/1545, loss: 0.0004810813697986305 2023-01-23 20:58:27.729254: step: 82/1545, loss: 0.0006709591252729297 2023-01-23 20:58:28.619781: step: 84/1545, loss: 0.009641289710998535 2023-01-23 20:58:29.464647: step: 86/1545, loss: 1.6005207726266235e-05 2023-01-23 20:58:30.359247: step: 88/1545, loss: 5.212984251556918e-05 2023-01-23 20:58:31.232995: step: 90/1545, loss: 0.13115158677101135 2023-01-23 20:58:32.196292: step: 92/1545, loss: 0.0900779515504837 2023-01-23 20:58:33.045103: step: 94/1545, loss: 3.7888981751166284e-05 2023-01-23 20:58:33.944696: step: 96/1545, loss: 0.040155474096536636 2023-01-23 20:58:34.853397: step: 98/1545, loss: 0.0002122153964592144 2023-01-23 20:58:35.744309: step: 100/1545, loss: 0.20246310532093048 2023-01-23 20:58:36.687019: step: 102/1545, loss: 0.00012391901691444218 2023-01-23 20:58:37.533630: step: 104/1545, loss: 3.567634485079907e-05 2023-01-23 20:58:38.385475: step: 106/1545, loss: 0.0016497430624440312 2023-01-23 20:58:39.229697: step: 108/1545, loss: 0.004819541238248348 2023-01-23 20:58:40.127327: step: 110/1545, loss: 0.001824387814849615 2023-01-23 20:58:40.984538: step: 112/1545, loss: 0.00016188318841159344 2023-01-23 20:58:41.835374: step: 114/1545, loss: 0.001270053442567587 2023-01-23 20:58:42.690266: step: 116/1545, loss: 0.004829865880310535 2023-01-23 20:58:43.687310: step: 118/1545, loss: 6.783232038287679e-07 2023-01-23 20:58:44.661335: step: 120/1545, loss: 0.00032668988569639623 2023-01-23 20:58:45.542953: step: 122/1545, loss: 0.147538423538208 2023-01-23 20:58:46.411771: step: 124/1545, loss: 0.0017122046556323767 2023-01-23 20:58:47.280020: step: 126/1545, loss: 0.0014454296324402094 2023-01-23 20:58:48.176680: step: 128/1545, loss: 0.03753111511468887 2023-01-23 20:58:49.047235: step: 130/1545, loss: 0.00010597318032523617 2023-01-23 20:58:49.910594: step: 132/1545, loss: 0.08763119578361511 2023-01-23 20:58:50.792909: step: 134/1545, loss: 0.006803770549595356 2023-01-23 20:58:51.668978: step: 136/1545, loss: 0.007477156352251768 2023-01-23 20:58:52.537858: step: 138/1545, loss: 0.0018494873074814677 2023-01-23 20:58:53.408069: step: 140/1545, loss: 0.3296079635620117 2023-01-23 20:58:54.296719: step: 142/1545, loss: 0.0004897655453532934 2023-01-23 20:58:55.165055: step: 144/1545, loss: 0.009135257452726364 2023-01-23 20:58:56.059458: step: 146/1545, loss: 0.00020440827938728034 2023-01-23 20:58:56.937751: step: 148/1545, loss: 5.80698178964667e-05 2023-01-23 20:58:57.821660: step: 150/1545, loss: 5.027833321946673e-05 2023-01-23 20:58:58.685137: step: 152/1545, loss: 0.02825811132788658 2023-01-23 20:58:59.537153: step: 154/1545, loss: 0.011165092699229717 2023-01-23 20:59:00.455280: step: 156/1545, loss: 0.00015964095655363053 2023-01-23 20:59:01.345575: step: 158/1545, loss: 0.06899382174015045 2023-01-23 20:59:02.213911: step: 160/1545, loss: 0.00017725935322232544 2023-01-23 20:59:03.079193: step: 162/1545, loss: 0.0012454444076865911 2023-01-23 20:59:03.933968: step: 164/1545, loss: 0.11157107353210449 2023-01-23 20:59:04.819813: step: 166/1545, loss: 0.19541753828525543 2023-01-23 20:59:05.699906: step: 168/1545, loss: 0.23183508217334747 2023-01-23 20:59:06.564748: step: 170/1545, loss: 4.793889820575714e-05 2023-01-23 20:59:07.489761: step: 172/1545, loss: 0.00010338738502468914 2023-01-23 20:59:08.368310: step: 174/1545, loss: 0.0007379716844297945 2023-01-23 20:59:09.278621: step: 176/1545, loss: 0.00023538124514743686 2023-01-23 20:59:10.105979: step: 178/1545, loss: 0.00029089226154610515 2023-01-23 20:59:10.960494: step: 180/1545, loss: 0.021075915545225143 2023-01-23 20:59:11.907167: step: 182/1545, loss: 0.009559436701238155 2023-01-23 20:59:12.783833: step: 184/1545, loss: 8.711109694559127e-05 2023-01-23 20:59:13.690709: step: 186/1545, loss: 0.0018193727592006326 2023-01-23 20:59:14.559714: step: 188/1545, loss: 3.0167773729772307e-05 2023-01-23 20:59:15.441021: step: 190/1545, loss: 0.063755102455616 2023-01-23 20:59:16.465854: step: 192/1545, loss: 0.3809157907962799 2023-01-23 20:59:17.378431: step: 194/1545, loss: 0.0024449327029287815 2023-01-23 20:59:18.285198: step: 196/1545, loss: 0.0003590728738345206 2023-01-23 20:59:19.133388: step: 198/1545, loss: 0.0021502028685063124 2023-01-23 20:59:19.986909: step: 200/1545, loss: 0.0010059487540274858 2023-01-23 20:59:20.807958: step: 202/1545, loss: 0.0020552740897983313 2023-01-23 20:59:21.689011: step: 204/1545, loss: 0.00033573067048564553 2023-01-23 20:59:22.560580: step: 206/1545, loss: 9.348560524813365e-06 2023-01-23 20:59:23.444224: step: 208/1545, loss: 5.841948586748913e-05 2023-01-23 20:59:24.334524: step: 210/1545, loss: 5.664186392095871e-05 2023-01-23 20:59:25.161759: step: 212/1545, loss: 4.613123383023776e-05 2023-01-23 20:59:26.040486: step: 214/1545, loss: 0.0009694327600300312 2023-01-23 20:59:26.925993: step: 216/1545, loss: 0.0024172780103981495 2023-01-23 20:59:27.834025: step: 218/1545, loss: 0.02973025292158127 2023-01-23 20:59:28.693045: step: 220/1545, loss: 9.954824054148048e-05 2023-01-23 20:59:29.540015: step: 222/1545, loss: 0.0006285655545070767 2023-01-23 20:59:30.414085: step: 224/1545, loss: 0.0014786396641284227 2023-01-23 20:59:31.303770: step: 226/1545, loss: 0.0006156442104838789 2023-01-23 20:59:32.193871: step: 228/1545, loss: 0.03841645270586014 2023-01-23 20:59:33.090811: step: 230/1545, loss: 0.001696406863629818 2023-01-23 20:59:34.012745: step: 232/1545, loss: 0.0013776434352621436 2023-01-23 20:59:34.881242: step: 234/1545, loss: 0.0003983665956184268 2023-01-23 20:59:35.808341: step: 236/1545, loss: 7.332524546654895e-05 2023-01-23 20:59:36.732836: step: 238/1545, loss: 0.008705023676156998 2023-01-23 20:59:37.565391: step: 240/1545, loss: 4.149490632698871e-05 2023-01-23 20:59:38.432503: step: 242/1545, loss: 3.99846576328855e-05 2023-01-23 20:59:39.294443: step: 244/1545, loss: 0.019070720300078392 2023-01-23 20:59:40.136655: step: 246/1545, loss: 0.09997362643480301 2023-01-23 20:59:41.027164: step: 248/1545, loss: 0.0026239308062940836 2023-01-23 20:59:41.884276: step: 250/1545, loss: 0.00020794141164515167 2023-01-23 20:59:42.718709: step: 252/1545, loss: 4.802647526958026e-05 2023-01-23 20:59:43.594452: step: 254/1545, loss: 4.349201844888739e-05 2023-01-23 20:59:44.523445: step: 256/1545, loss: 0.0012017861008644104 2023-01-23 20:59:45.355907: step: 258/1545, loss: 2.518644032534212e-05 2023-01-23 20:59:46.254473: step: 260/1545, loss: 0.0005453945486806333 2023-01-23 20:59:47.218894: step: 262/1545, loss: 0.09071701020002365 2023-01-23 20:59:48.099417: step: 264/1545, loss: 6.747020233888179e-05 2023-01-23 20:59:49.008842: step: 266/1545, loss: 0.15161779522895813 2023-01-23 20:59:49.854592: step: 268/1545, loss: 0.00021207629470154643 2023-01-23 20:59:50.673894: step: 270/1545, loss: 0.2773173153400421 2023-01-23 20:59:51.549223: step: 272/1545, loss: 2.653942647157237e-05 2023-01-23 20:59:52.406582: step: 274/1545, loss: 0.0002937674580607563 2023-01-23 20:59:53.267537: step: 276/1545, loss: 0.0008157645934261382 2023-01-23 20:59:54.097242: step: 278/1545, loss: 0.00012737690121866763 2023-01-23 20:59:54.992006: step: 280/1545, loss: 0.21308954060077667 2023-01-23 20:59:55.866343: step: 282/1545, loss: 0.00031991975265555084 2023-01-23 20:59:56.769181: step: 284/1545, loss: 0.09934698790311813 2023-01-23 20:59:57.626716: step: 286/1545, loss: 9.150168625637889e-05 2023-01-23 20:59:58.465316: step: 288/1545, loss: 0.0006675418699160218 2023-01-23 20:59:59.318234: step: 290/1545, loss: 0.0001901600626297295 2023-01-23 21:00:00.168960: step: 292/1545, loss: 0.0008045356371439993 2023-01-23 21:00:01.102227: step: 294/1545, loss: 0.0009107715450227261 2023-01-23 21:00:01.965192: step: 296/1545, loss: 0.39725905656814575 2023-01-23 21:00:02.835636: step: 298/1545, loss: 0.00030992148094810545 2023-01-23 21:00:03.736005: step: 300/1545, loss: 0.0002061351842712611 2023-01-23 21:00:04.635635: step: 302/1545, loss: 0.011751137673854828 2023-01-23 21:00:05.478922: step: 304/1545, loss: 7.352120883297175e-05 2023-01-23 21:00:06.348924: step: 306/1545, loss: 0.0013329838402569294 2023-01-23 21:00:07.195235: step: 308/1545, loss: 0.00014354765880852938 2023-01-23 21:00:08.044388: step: 310/1545, loss: 0.00038871390279382467 2023-01-23 21:00:08.900599: step: 312/1545, loss: 0.0898248627781868 2023-01-23 21:00:09.750992: step: 314/1545, loss: 0.00014808477135375142 2023-01-23 21:00:10.626996: step: 316/1545, loss: 0.0014961743727326393 2023-01-23 21:00:11.483981: step: 318/1545, loss: 0.19626973569393158 2023-01-23 21:00:12.353868: step: 320/1545, loss: 0.0006666571134701371 2023-01-23 21:00:13.205066: step: 322/1545, loss: 1.261070792679675e-05 2023-01-23 21:00:14.087729: step: 324/1545, loss: 0.1485362946987152 2023-01-23 21:00:14.935062: step: 326/1545, loss: 0.005671399645507336 2023-01-23 21:00:15.810341: step: 328/1545, loss: 0.00021910760551691055 2023-01-23 21:00:16.686850: step: 330/1545, loss: 0.0013916719472035766 2023-01-23 21:00:17.538323: step: 332/1545, loss: 0.0002210935635957867 2023-01-23 21:00:18.424324: step: 334/1545, loss: 0.002234705025330186 2023-01-23 21:00:19.332471: step: 336/1545, loss: 0.0068993777967989445 2023-01-23 21:00:20.182033: step: 338/1545, loss: 0.00013957469491288066 2023-01-23 21:00:21.040586: step: 340/1545, loss: 0.09458224475383759 2023-01-23 21:00:21.898310: step: 342/1545, loss: 5.0421193009242415e-05 2023-01-23 21:00:22.760325: step: 344/1545, loss: 0.03937374800443649 2023-01-23 21:00:23.706862: step: 346/1545, loss: 0.12469323724508286 2023-01-23 21:00:24.569333: step: 348/1545, loss: 0.024683088064193726 2023-01-23 21:00:25.453907: step: 350/1545, loss: 7.698556873947382e-05 2023-01-23 21:00:26.292090: step: 352/1545, loss: 0.0006399800768122077 2023-01-23 21:00:27.182915: step: 354/1545, loss: 3.1116414902498946e-05 2023-01-23 21:00:28.064241: step: 356/1545, loss: 0.0006188065162859857 2023-01-23 21:00:29.023112: step: 358/1545, loss: 0.011285333894193172 2023-01-23 21:00:29.860195: step: 360/1545, loss: 0.001254473114386201 2023-01-23 21:00:30.749705: step: 362/1545, loss: 0.0009548075031489134 2023-01-23 21:00:31.628560: step: 364/1545, loss: 0.0008902045665308833 2023-01-23 21:00:32.509719: step: 366/1545, loss: 0.03560348600149155 2023-01-23 21:00:33.415560: step: 368/1545, loss: 0.0003257057396695018 2023-01-23 21:00:34.277958: step: 370/1545, loss: 2.25154963118257e-06 2023-01-23 21:00:35.150325: step: 372/1545, loss: 5.408917058957741e-05 2023-01-23 21:00:36.024664: step: 374/1545, loss: 0.3578127324581146 2023-01-23 21:00:36.868866: step: 376/1545, loss: 0.34441572427749634 2023-01-23 21:00:37.745148: step: 378/1545, loss: 0.009108467027544975 2023-01-23 21:00:38.614614: step: 380/1545, loss: 0.016492623835802078 2023-01-23 21:00:39.494189: step: 382/1545, loss: 0.00013063737424090505 2023-01-23 21:00:40.406875: step: 384/1545, loss: 0.12410498410463333 2023-01-23 21:00:41.336312: step: 386/1545, loss: 0.45810508728027344 2023-01-23 21:00:42.194096: step: 388/1545, loss: 0.0013713976368308067 2023-01-23 21:00:43.050721: step: 390/1545, loss: 0.0019534341990947723 2023-01-23 21:00:43.895106: step: 392/1545, loss: 0.015691641718149185 2023-01-23 21:00:44.748005: step: 394/1545, loss: 0.0015007512411102653 2023-01-23 21:00:45.623555: step: 396/1545, loss: 0.0007931689033284783 2023-01-23 21:00:46.517315: step: 398/1545, loss: 4.896015161648393e-05 2023-01-23 21:00:47.389293: step: 400/1545, loss: 0.0133364824578166 2023-01-23 21:00:48.268116: step: 402/1545, loss: 0.006257370579987764 2023-01-23 21:00:49.214245: step: 404/1545, loss: 0.0031921202316880226 2023-01-23 21:00:50.073509: step: 406/1545, loss: 0.004964555148035288 2023-01-23 21:00:50.885919: step: 408/1545, loss: 0.0007425526855513453 2023-01-23 21:00:51.758118: step: 410/1545, loss: 0.0001729052310111001 2023-01-23 21:00:52.640488: step: 412/1545, loss: 0.000110889486677479 2023-01-23 21:00:53.571247: step: 414/1545, loss: 0.028211386874318123 2023-01-23 21:00:54.401328: step: 416/1545, loss: 0.006619643419981003 2023-01-23 21:00:55.311331: step: 418/1545, loss: 1.65088949870551e-05 2023-01-23 21:00:56.248255: step: 420/1545, loss: 0.0044448706321418285 2023-01-23 21:00:57.198833: step: 422/1545, loss: 0.02833716943860054 2023-01-23 21:00:58.077837: step: 424/1545, loss: 9.613233123673126e-05 2023-01-23 21:00:58.920918: step: 426/1545, loss: 0.0006708901491947472 2023-01-23 21:00:59.836890: step: 428/1545, loss: 0.001095845946110785 2023-01-23 21:01:00.726739: step: 430/1545, loss: 0.014592540450394154 2023-01-23 21:01:01.599229: step: 432/1545, loss: 0.13296356797218323 2023-01-23 21:01:02.524013: step: 434/1545, loss: 0.6018403768539429 2023-01-23 21:01:03.376157: step: 436/1545, loss: 0.0005314943846315145 2023-01-23 21:01:04.248305: step: 438/1545, loss: 0.020781338214874268 2023-01-23 21:01:05.220856: step: 440/1545, loss: 0.0002635973214637488 2023-01-23 21:01:06.078729: step: 442/1545, loss: 0.0003655249020084739 2023-01-23 21:01:06.934840: step: 444/1545, loss: 0.03856508806347847 2023-01-23 21:01:07.791860: step: 446/1545, loss: 0.009844878688454628 2023-01-23 21:01:08.685101: step: 448/1545, loss: 0.0005714499857276678 2023-01-23 21:01:09.543242: step: 450/1545, loss: 0.004184511955827475 2023-01-23 21:01:10.408037: step: 452/1545, loss: 0.4342454969882965 2023-01-23 21:01:11.269402: step: 454/1545, loss: 0.0009221662767231464 2023-01-23 21:01:12.140538: step: 456/1545, loss: 0.00013892949209548533 2023-01-23 21:01:13.032261: step: 458/1545, loss: 0.0006527718505822122 2023-01-23 21:01:13.887640: step: 460/1545, loss: 0.0005770496791228652 2023-01-23 21:01:14.775203: step: 462/1545, loss: 0.0031453969422727823 2023-01-23 21:01:15.665575: step: 464/1545, loss: 0.0013013709103688598 2023-01-23 21:01:16.575517: step: 466/1545, loss: 0.0002877280057873577 2023-01-23 21:01:17.448775: step: 468/1545, loss: 4.404633727972396e-05 2023-01-23 21:01:18.339457: step: 470/1545, loss: 0.11356588453054428 2023-01-23 21:01:19.162363: step: 472/1545, loss: 0.002557536819949746 2023-01-23 21:01:20.104757: step: 474/1545, loss: -6.582541391253471e-05 2023-01-23 21:01:20.966953: step: 476/1545, loss: 0.004882326815277338 2023-01-23 21:01:21.835276: step: 478/1545, loss: 0.9037150740623474 2023-01-23 21:01:22.677012: step: 480/1545, loss: 0.4388721287250519 2023-01-23 21:01:23.535110: step: 482/1545, loss: 3.338187525514513e-05 2023-01-23 21:01:24.417696: step: 484/1545, loss: 0.6900789141654968 2023-01-23 21:01:25.326055: step: 486/1545, loss: 0.0002706546802073717 2023-01-23 21:01:26.275638: step: 488/1545, loss: 0.2274787873029709 2023-01-23 21:01:27.149306: step: 490/1545, loss: 0.0010393258417025208 2023-01-23 21:01:28.002343: step: 492/1545, loss: 0.002538637723773718 2023-01-23 21:01:28.841846: step: 494/1545, loss: 0.0009692865423858166 2023-01-23 21:01:29.722576: step: 496/1545, loss: 0.0005300361663103104 2023-01-23 21:01:30.578974: step: 498/1545, loss: 0.13826942443847656 2023-01-23 21:01:31.438670: step: 500/1545, loss: 0.018469059839844704 2023-01-23 21:01:32.326351: step: 502/1545, loss: 0.01742124930024147 2023-01-23 21:01:33.222409: step: 504/1545, loss: 0.0006493667606264353 2023-01-23 21:01:34.082717: step: 506/1545, loss: 9.889697139442433e-06 2023-01-23 21:01:34.944341: step: 508/1545, loss: 0.0009871649090200663 2023-01-23 21:01:35.798545: step: 510/1545, loss: 0.00333389057777822 2023-01-23 21:01:36.664662: step: 512/1545, loss: 0.002892993623390794 2023-01-23 21:01:37.502729: step: 514/1545, loss: 0.006560962647199631 2023-01-23 21:01:38.374702: step: 516/1545, loss: 0.001882237265817821 2023-01-23 21:01:39.268444: step: 518/1545, loss: 0.00026033908943645656 2023-01-23 21:01:40.170951: step: 520/1545, loss: 0.0009257639176212251 2023-01-23 21:01:41.068283: step: 522/1545, loss: 0.00441920617595315 2023-01-23 21:01:41.917617: step: 524/1545, loss: 0.0002659717865753919 2023-01-23 21:01:42.775507: step: 526/1545, loss: 0.00025222331169061363 2023-01-23 21:01:43.645697: step: 528/1545, loss: 0.0007847506203688681 2023-01-23 21:01:44.490693: step: 530/1545, loss: 0.0013530837604776025 2023-01-23 21:01:45.389889: step: 532/1545, loss: 0.00033717459882609546 2023-01-23 21:01:46.288163: step: 534/1545, loss: 0.08467122167348862 2023-01-23 21:01:47.116641: step: 536/1545, loss: 5.052377673564479e-05 2023-01-23 21:01:47.979136: step: 538/1545, loss: 0.05077575519680977 2023-01-23 21:01:48.838061: step: 540/1545, loss: -7.87142835179111e-06 2023-01-23 21:01:49.713257: step: 542/1545, loss: 0.0950232595205307 2023-01-23 21:01:50.615825: step: 544/1545, loss: 0.23939453065395355 2023-01-23 21:01:51.479065: step: 546/1545, loss: 0.3939392566680908 2023-01-23 21:01:52.344598: step: 548/1545, loss: 0.00012855013483203948 2023-01-23 21:01:53.189205: step: 550/1545, loss: 0.0017276457510888577 2023-01-23 21:01:54.046615: step: 552/1545, loss: 0.0018972496036440134 2023-01-23 21:01:54.933706: step: 554/1545, loss: 0.003318502800539136 2023-01-23 21:01:55.849272: step: 556/1545, loss: 0.00013571260205935687 2023-01-23 21:01:56.767570: step: 558/1545, loss: 0.00041874626185745 2023-01-23 21:01:57.648977: step: 560/1545, loss: 0.001129072392359376 2023-01-23 21:01:58.533318: step: 562/1545, loss: 0.0003041839227080345 2023-01-23 21:01:59.372321: step: 564/1545, loss: 0.0002678181335795671 2023-01-23 21:02:00.222364: step: 566/1545, loss: 0.00121123471762985 2023-01-23 21:02:01.081253: step: 568/1545, loss: 0.0011077460367232561 2023-01-23 21:02:01.961088: step: 570/1545, loss: 0.0011989240301772952 2023-01-23 21:02:02.841769: step: 572/1545, loss: 1.1473688573460095e-05 2023-01-23 21:02:03.824151: step: 574/1545, loss: 4.546642230707221e-05 2023-01-23 21:02:04.738794: step: 576/1545, loss: -2.2672149952995824e-06 2023-01-23 21:02:05.602484: step: 578/1545, loss: 9.031673107529059e-05 2023-01-23 21:02:06.548818: step: 580/1545, loss: 1.154066562652588 2023-01-23 21:02:07.417306: step: 582/1545, loss: 0.6029528379440308 2023-01-23 21:02:08.368853: step: 584/1545, loss: 0.0001790556707419455 2023-01-23 21:02:09.201577: step: 586/1545, loss: 0.00034243633854202926 2023-01-23 21:02:10.062796: step: 588/1545, loss: 6.684268009848893e-05 2023-01-23 21:02:10.935352: step: 590/1545, loss: 0.0001222028222400695 2023-01-23 21:02:11.809531: step: 592/1545, loss: 0.2418140023946762 2023-01-23 21:02:12.715868: step: 594/1545, loss: 6.207499973243102e-05 2023-01-23 21:02:13.593634: step: 596/1545, loss: 0.0003541039186529815 2023-01-23 21:02:14.502809: step: 598/1545, loss: 0.12746113538742065 2023-01-23 21:02:15.388947: step: 600/1545, loss: 0.055609330534935 2023-01-23 21:02:16.222930: step: 602/1545, loss: 0.00015247357077896595 2023-01-23 21:02:17.125638: step: 604/1545, loss: 0.0051864986307919025 2023-01-23 21:02:18.062838: step: 606/1545, loss: 0.018085241317749023 2023-01-23 21:02:18.959956: step: 608/1545, loss: 0.003477515419945121 2023-01-23 21:02:19.866938: step: 610/1545, loss: 0.11485544592142105 2023-01-23 21:02:20.706201: step: 612/1545, loss: 0.00018227666441816837 2023-01-23 21:02:21.644670: step: 614/1545, loss: 0.0012733475305140018 2023-01-23 21:02:22.529340: step: 616/1545, loss: 0.0004413753340486437 2023-01-23 21:02:23.391190: step: 618/1545, loss: 0.016223739832639694 2023-01-23 21:02:24.237673: step: 620/1545, loss: 0.00025479961186647415 2023-01-23 21:02:25.133929: step: 622/1545, loss: 5.2632760343840346e-05 2023-01-23 21:02:26.006667: step: 624/1545, loss: 0.00045461487025022507 2023-01-23 21:02:26.839062: step: 626/1545, loss: 0.00010957782797049731 2023-01-23 21:02:27.736868: step: 628/1545, loss: 0.036891959607601166 2023-01-23 21:02:28.603954: step: 630/1545, loss: 0.0010033887811005116 2023-01-23 21:02:29.416269: step: 632/1545, loss: 0.006220430135726929 2023-01-23 21:02:30.311211: step: 634/1545, loss: 0.009906444698572159 2023-01-23 21:02:31.179393: step: 636/1545, loss: 0.0020367391407489777 2023-01-23 21:02:32.047805: step: 638/1545, loss: 0.00021213540458120406 2023-01-23 21:02:32.934938: step: 640/1545, loss: 0.00042878190288320184 2023-01-23 21:02:33.801379: step: 642/1545, loss: 0.0019243445713073015 2023-01-23 21:02:34.661841: step: 644/1545, loss: 0.004310780670493841 2023-01-23 21:02:35.489195: step: 646/1545, loss: -5.135239007358905e-06 2023-01-23 21:02:36.409531: step: 648/1545, loss: 0.010648067109286785 2023-01-23 21:02:37.265260: step: 650/1545, loss: 0.07006954401731491 2023-01-23 21:02:38.178463: step: 652/1545, loss: 0.000554849742911756 2023-01-23 21:02:39.169524: step: 654/1545, loss: 0.02372800186276436 2023-01-23 21:02:40.037928: step: 656/1545, loss: 0.0001539142249384895 2023-01-23 21:02:40.947464: step: 658/1545, loss: 1.422549848939525e-05 2023-01-23 21:02:41.815796: step: 660/1545, loss: 0.008792605251073837 2023-01-23 21:02:42.721876: step: 662/1545, loss: 0.00022224098211154342 2023-01-23 21:02:43.611187: step: 664/1545, loss: 0.014485560357570648 2023-01-23 21:02:44.499327: step: 666/1545, loss: 0.002238268032670021 2023-01-23 21:02:45.361525: step: 668/1545, loss: 0.00034632981987670064 2023-01-23 21:02:46.223440: step: 670/1545, loss: 0.0015941897872835398 2023-01-23 21:02:47.078053: step: 672/1545, loss: 0.016005506739020348 2023-01-23 21:02:47.910497: step: 674/1545, loss: 6.0546379245352e-05 2023-01-23 21:02:48.794234: step: 676/1545, loss: 0.00015552851255051792 2023-01-23 21:02:49.683276: step: 678/1545, loss: 0.02372722327709198 2023-01-23 21:02:50.524013: step: 680/1545, loss: 0.009880968369543552 2023-01-23 21:02:51.390335: step: 682/1545, loss: 0.09551644325256348 2023-01-23 21:02:52.279915: step: 684/1545, loss: 0.16618841886520386 2023-01-23 21:02:53.161481: step: 686/1545, loss: 0.0007993514882400632 2023-01-23 21:02:54.070330: step: 688/1545, loss: 0.16222697496414185 2023-01-23 21:02:54.948570: step: 690/1545, loss: 0.6695066094398499 2023-01-23 21:02:55.846641: step: 692/1545, loss: 0.0043215262703597546 2023-01-23 21:02:56.664792: step: 694/1545, loss: 0.00021354341879487038 2023-01-23 21:02:57.490722: step: 696/1545, loss: 4.184709905530326e-05 2023-01-23 21:02:58.353137: step: 698/1545, loss: 0.024205349385738373 2023-01-23 21:02:59.183204: step: 700/1545, loss: 0.6245972514152527 2023-01-23 21:03:00.068307: step: 702/1545, loss: 0.00025165657280012965 2023-01-23 21:03:00.918514: step: 704/1545, loss: 3.137085877824575e-05 2023-01-23 21:03:01.792092: step: 706/1545, loss: 0.13123878836631775 2023-01-23 21:03:02.703931: step: 708/1545, loss: 0.00035819452023133636 2023-01-23 21:03:03.579102: step: 710/1545, loss: 0.012485467828810215 2023-01-23 21:03:04.464927: step: 712/1545, loss: 0.0013024990912526846 2023-01-23 21:03:05.347379: step: 714/1545, loss: 0.020439647138118744 2023-01-23 21:03:06.212363: step: 716/1545, loss: 0.005527450703084469 2023-01-23 21:03:07.080037: step: 718/1545, loss: 0.03268234431743622 2023-01-23 21:03:07.916017: step: 720/1545, loss: 0.018146194517612457 2023-01-23 21:03:08.796266: step: 722/1545, loss: 0.0012481112498790026 2023-01-23 21:03:09.666995: step: 724/1545, loss: 0.1815686821937561 2023-01-23 21:03:10.589083: step: 726/1545, loss: 0.004652610048651695 2023-01-23 21:03:11.403983: step: 728/1545, loss: 0.007909252308309078 2023-01-23 21:03:12.301018: step: 730/1545, loss: 0.001295361202210188 2023-01-23 21:03:13.156988: step: 732/1545, loss: 0.0118618905544281 2023-01-23 21:03:13.993827: step: 734/1545, loss: 0.05676225945353508 2023-01-23 21:03:14.866942: step: 736/1545, loss: 0.0006126286461949348 2023-01-23 21:03:15.752007: step: 738/1545, loss: 1.403579592704773 2023-01-23 21:03:16.621716: step: 740/1545, loss: 0.1257670372724533 2023-01-23 21:03:17.497396: step: 742/1545, loss: 0.008268806152045727 2023-01-23 21:03:18.347765: step: 744/1545, loss: 0.002768441801890731 2023-01-23 21:03:19.254650: step: 746/1545, loss: 0.0005485704750753939 2023-01-23 21:03:20.143336: step: 748/1545, loss: 0.00013075074821244925 2023-01-23 21:03:21.024439: step: 750/1545, loss: 0.04298901557922363 2023-01-23 21:03:21.906057: step: 752/1545, loss: 0.0004362415929790586 2023-01-23 21:03:22.766891: step: 754/1545, loss: 0.0015229606069624424 2023-01-23 21:03:23.670277: step: 756/1545, loss: 0.04696285352110863 2023-01-23 21:03:24.580229: step: 758/1545, loss: 0.00014726718654856086 2023-01-23 21:03:25.465713: step: 760/1545, loss: 0.009505689144134521 2023-01-23 21:03:26.328915: step: 762/1545, loss: 0.34857743978500366 2023-01-23 21:03:27.151911: step: 764/1545, loss: 0.0021311792079359293 2023-01-23 21:03:28.036112: step: 766/1545, loss: 0.00017998993280343711 2023-01-23 21:03:28.929982: step: 768/1545, loss: 6.168033905851189e-07 2023-01-23 21:03:29.799417: step: 770/1545, loss: 0.058817461133003235 2023-01-23 21:03:30.663508: step: 772/1545, loss: 0.08615972846746445 2023-01-23 21:03:31.581027: step: 774/1545, loss: 0.009569300338625908 2023-01-23 21:03:32.430055: step: 776/1545, loss: 0.004311595112085342 2023-01-23 21:03:33.355937: step: 778/1545, loss: 0.00029463492683134973 2023-01-23 21:03:34.186170: step: 780/1545, loss: 0.0005489613395184278 2023-01-23 21:03:35.083589: step: 782/1545, loss: 0.00030205235816538334 2023-01-23 21:03:35.960044: step: 784/1545, loss: 0.0202674251049757 2023-01-23 21:03:36.800546: step: 786/1545, loss: 0.03916472941637039 2023-01-23 21:03:37.700396: step: 788/1545, loss: 0.00014698924496769905 2023-01-23 21:03:38.550953: step: 790/1545, loss: 2.828078140737489e-05 2023-01-23 21:03:39.416299: step: 792/1545, loss: 1.6494333976879716e-05 2023-01-23 21:03:40.305618: step: 794/1545, loss: 0.00030568341026082635 2023-01-23 21:03:41.196099: step: 796/1545, loss: 0.0012626495445147157 2023-01-23 21:03:42.054486: step: 798/1545, loss: 0.0002989734639413655 2023-01-23 21:03:42.923054: step: 800/1545, loss: 0.00024509773356840014 2023-01-23 21:03:43.813919: step: 802/1545, loss: 5.210759263718501e-05 2023-01-23 21:03:44.666545: step: 804/1545, loss: 6.28873094683513e-05 2023-01-23 21:03:45.584974: step: 806/1545, loss: -3.9980797737371176e-05 2023-01-23 21:03:46.468028: step: 808/1545, loss: 0.01167279202491045 2023-01-23 21:03:47.351173: step: 810/1545, loss: 0.02827785164117813 2023-01-23 21:03:48.214191: step: 812/1545, loss: 4.013627767562866e-05 2023-01-23 21:03:49.063955: step: 814/1545, loss: 0.014335999265313148 2023-01-23 21:03:49.893444: step: 816/1545, loss: 0.00019937328761443496 2023-01-23 21:03:50.724686: step: 818/1545, loss: 0.0008666705107316375 2023-01-23 21:03:51.662755: step: 820/1545, loss: 0.008825009688735008 2023-01-23 21:03:52.587197: step: 822/1545, loss: 0.00012980720202904195 2023-01-23 21:03:53.484343: step: 824/1545, loss: 0.04353313520550728 2023-01-23 21:03:54.350339: step: 826/1545, loss: 8.945818990468979e-05 2023-01-23 21:03:55.243095: step: 828/1545, loss: 3.9304526580963284e-05 2023-01-23 21:03:56.106469: step: 830/1545, loss: 0.307976633310318 2023-01-23 21:03:56.976704: step: 832/1545, loss: 0.0003195991739630699 2023-01-23 21:03:57.874398: step: 834/1545, loss: 0.036839257925748825 2023-01-23 21:03:58.758917: step: 836/1545, loss: 0.010217373259365559 2023-01-23 21:03:59.635326: step: 838/1545, loss: 0.0006461336161009967 2023-01-23 21:04:00.520811: step: 840/1545, loss: 0.00226283585652709 2023-01-23 21:04:01.378100: step: 842/1545, loss: 0.018355252221226692 2023-01-23 21:04:02.239306: step: 844/1545, loss: 0.0007835064316168427 2023-01-23 21:04:03.136576: step: 846/1545, loss: 0.00739508680999279 2023-01-23 21:04:03.957555: step: 848/1545, loss: 0.0014096018858253956 2023-01-23 21:04:04.869238: step: 850/1545, loss: 0.7737162709236145 2023-01-23 21:04:05.710368: step: 852/1545, loss: 0.0055961585603654385 2023-01-23 21:04:06.621119: step: 854/1545, loss: 9.483644680585712e-05 2023-01-23 21:04:07.436975: step: 856/1545, loss: 0.00046369500341825187 2023-01-23 21:04:08.313389: step: 858/1545, loss: 0.5375105142593384 2023-01-23 21:04:09.182324: step: 860/1545, loss: 0.0005879103555344045 2023-01-23 21:04:10.051767: step: 862/1545, loss: 0.0037745593581348658 2023-01-23 21:04:10.930433: step: 864/1545, loss: 0.00042226581717841327 2023-01-23 21:04:11.789645: step: 866/1545, loss: 0.00039221521001309156 2023-01-23 21:04:12.666165: step: 868/1545, loss: 0.0002818022039718926 2023-01-23 21:04:13.590311: step: 870/1545, loss: 0.008105148561298847 2023-01-23 21:04:14.477481: step: 872/1545, loss: 0.023738829419016838 2023-01-23 21:04:15.332508: step: 874/1545, loss: 9.440950816497207e-05 2023-01-23 21:04:16.176082: step: 876/1545, loss: 0.0038920172955840826 2023-01-23 21:04:17.029632: step: 878/1545, loss: 0.03733590245246887 2023-01-23 21:04:17.918919: step: 880/1545, loss: 0.016642216593027115 2023-01-23 21:04:18.842326: step: 882/1545, loss: 0.0952761098742485 2023-01-23 21:04:19.730214: step: 884/1545, loss: 0.00018329202430322766 2023-01-23 21:04:20.618145: step: 886/1545, loss: 0.001154859783127904 2023-01-23 21:04:21.524542: step: 888/1545, loss: 0.00038447321276180446 2023-01-23 21:04:22.384796: step: 890/1545, loss: 0.00029601206188090146 2023-01-23 21:04:23.262105: step: 892/1545, loss: 0.0005410140147432685 2023-01-23 21:04:24.125774: step: 894/1545, loss: 0.0019983388483524323 2023-01-23 21:04:25.002250: step: 896/1545, loss: 0.006545280572026968 2023-01-23 21:04:25.865264: step: 898/1545, loss: 0.7977287173271179 2023-01-23 21:04:26.724853: step: 900/1545, loss: 5.195453195483424e-05 2023-01-23 21:04:27.577505: step: 902/1545, loss: 0.006294459104537964 2023-01-23 21:04:28.435996: step: 904/1545, loss: 0.1366930603981018 2023-01-23 21:04:29.334501: step: 906/1545, loss: 1.4643791473645251e-05 2023-01-23 21:04:30.216701: step: 908/1545, loss: 8.437803626293316e-05 2023-01-23 21:04:31.071899: step: 910/1545, loss: 0.00016294671513605863 2023-01-23 21:04:31.938199: step: 912/1545, loss: 0.00043454751721583307 2023-01-23 21:04:32.953761: step: 914/1545, loss: 0.0003707202849909663 2023-01-23 21:04:33.788279: step: 916/1545, loss: 0.009572836570441723 2023-01-23 21:04:34.678125: step: 918/1545, loss: 0.0003080387250520289 2023-01-23 21:04:35.624161: step: 920/1545, loss: 8.402163075516e-05 2023-01-23 21:04:36.479407: step: 922/1545, loss: 6.289083830779418e-05 2023-01-23 21:04:37.390027: step: 924/1545, loss: 0.0006406168104149401 2023-01-23 21:04:38.253945: step: 926/1545, loss: 0.0034048922825604677 2023-01-23 21:04:39.202066: step: 928/1545, loss: -6.2717663240619e-06 2023-01-23 21:04:40.130310: step: 930/1545, loss: 0.003654615953564644 2023-01-23 21:04:41.045454: step: 932/1545, loss: 0.00032041914528235793 2023-01-23 21:04:41.932626: step: 934/1545, loss: 0.00011913330672541633 2023-01-23 21:04:42.812060: step: 936/1545, loss: 0.23711809515953064 2023-01-23 21:04:43.705541: step: 938/1545, loss: 0.01509072259068489 2023-01-23 21:04:44.543580: step: 940/1545, loss: 0.00044421417987905443 2023-01-23 21:04:45.424155: step: 942/1545, loss: 0.00023458166106138378 2023-01-23 21:04:46.271819: step: 944/1545, loss: 0.0001787233049981296 2023-01-23 21:04:47.163098: step: 946/1545, loss: 0.5420915484428406 2023-01-23 21:04:48.022391: step: 948/1545, loss: 0.02104073576629162 2023-01-23 21:04:48.944349: step: 950/1545, loss: 2.182235948566813e-05 2023-01-23 21:04:49.806886: step: 952/1545, loss: 0.05129633843898773 2023-01-23 21:04:50.750159: step: 954/1545, loss: 0.3041754961013794 2023-01-23 21:04:51.629879: step: 956/1545, loss: 2.0271576431696303e-05 2023-01-23 21:04:52.477746: step: 958/1545, loss: 3.426724788369029e-07 2023-01-23 21:04:53.360941: step: 960/1545, loss: 2.9685084882657975e-05 2023-01-23 21:04:54.270124: step: 962/1545, loss: 0.010741944424808025 2023-01-23 21:04:55.122494: step: 964/1545, loss: 0.00019881843763869256 2023-01-23 21:04:56.056806: step: 966/1545, loss: 0.0003910697705578059 2023-01-23 21:04:56.938094: step: 968/1545, loss: 0.0003861551231238991 2023-01-23 21:04:57.798965: step: 970/1545, loss: 0.03145630285143852 2023-01-23 21:04:58.633497: step: 972/1545, loss: 0.28043505549430847 2023-01-23 21:04:59.526513: step: 974/1545, loss: 0.022899368777871132 2023-01-23 21:05:00.392405: step: 976/1545, loss: 1.1754230260849 2023-01-23 21:05:01.243164: step: 978/1545, loss: 0.12446915358304977 2023-01-23 21:05:02.136407: step: 980/1545, loss: 0.00015377432282548398 2023-01-23 21:05:03.065386: step: 982/1545, loss: 0.0001321691379416734 2023-01-23 21:05:03.961712: step: 984/1545, loss: 0.08028878271579742 2023-01-23 21:05:04.818447: step: 986/1545, loss: 0.00012189419794594869 2023-01-23 21:05:05.704433: step: 988/1545, loss: 0.04064928740262985 2023-01-23 21:05:06.587448: step: 990/1545, loss: 0.0024664453230798244 2023-01-23 21:05:07.495171: step: 992/1545, loss: 0.041028525680303574 2023-01-23 21:05:08.403694: step: 994/1545, loss: 0.05848034843802452 2023-01-23 21:05:09.283460: step: 996/1545, loss: 0.00034514523576945066 2023-01-23 21:05:10.184789: step: 998/1545, loss: 0.0006620122585445642 2023-01-23 21:05:11.069010: step: 1000/1545, loss: 0.000463061616756022 2023-01-23 21:05:11.934163: step: 1002/1545, loss: 0.021543506532907486 2023-01-23 21:05:12.801792: step: 1004/1545, loss: 2.135181421181187e-05 2023-01-23 21:05:13.756975: step: 1006/1545, loss: 3.674914478324354e-05 2023-01-23 21:05:14.610723: step: 1008/1545, loss: 0.06049197539687157 2023-01-23 21:05:15.484304: step: 1010/1545, loss: 0.2712262272834778 2023-01-23 21:05:16.335910: step: 1012/1545, loss: 0.022021450102329254 2023-01-23 21:05:17.207896: step: 1014/1545, loss: 6.0898164520040154e-06 2023-01-23 21:05:18.071983: step: 1016/1545, loss: 0.0007743141031824052 2023-01-23 21:05:18.939649: step: 1018/1545, loss: 4.0563532820669934e-05 2023-01-23 21:05:19.847620: step: 1020/1545, loss: 0.1077052503824234 2023-01-23 21:05:20.780768: step: 1022/1545, loss: 0.06556909531354904 2023-01-23 21:05:21.651206: step: 1024/1545, loss: 9.45301799220033e-05 2023-01-23 21:05:22.618662: step: 1026/1545, loss: 2.261484223708976e-05 2023-01-23 21:05:23.474855: step: 1028/1545, loss: 5.2617226174334064e-05 2023-01-23 21:05:24.386292: step: 1030/1545, loss: 0.0018442869186401367 2023-01-23 21:05:25.240340: step: 1032/1545, loss: 0.12519113719463348 2023-01-23 21:05:26.108560: step: 1034/1545, loss: 0.0002216033317381516 2023-01-23 21:05:26.996564: step: 1036/1545, loss: 6.35027899988927e-05 2023-01-23 21:05:27.886871: step: 1038/1545, loss: 0.014403656125068665 2023-01-23 21:05:28.749828: step: 1040/1545, loss: 0.08439389616250992 2023-01-23 21:05:29.632309: step: 1042/1545, loss: 5.934148794040084e-05 2023-01-23 21:05:30.562159: step: 1044/1545, loss: 0.0034295590594410896 2023-01-23 21:05:31.440409: step: 1046/1545, loss: 0.0001803430641302839 2023-01-23 21:05:32.298232: step: 1048/1545, loss: 0.00011321165948174894 2023-01-23 21:05:33.195470: step: 1050/1545, loss: 0.06144190952181816 2023-01-23 21:05:34.099520: step: 1052/1545, loss: 0.0006563694914802909 2023-01-23 21:05:34.933269: step: 1054/1545, loss: 5.158106432645582e-05 2023-01-23 21:05:35.843563: step: 1056/1545, loss: 0.47051167488098145 2023-01-23 21:05:36.681358: step: 1058/1545, loss: 0.00015362251724582165 2023-01-23 21:05:37.564958: step: 1060/1545, loss: 0.0012229783460497856 2023-01-23 21:05:38.409614: step: 1062/1545, loss: 8.467720908811316e-05 2023-01-23 21:05:39.288580: step: 1064/1545, loss: 0.0008958891849033535 2023-01-23 21:05:40.216447: step: 1066/1545, loss: 0.008394562639296055 2023-01-23 21:05:41.122158: step: 1068/1545, loss: 0.00012417190009728074 2023-01-23 21:05:42.032018: step: 1070/1545, loss: 0.0007983045652508736 2023-01-23 21:05:42.938101: step: 1072/1545, loss: 0.10698654502630234 2023-01-23 21:05:43.831294: step: 1074/1545, loss: 4.869389158557169e-05 2023-01-23 21:05:44.708280: step: 1076/1545, loss: 0.00016239738033618778 2023-01-23 21:05:45.574082: step: 1078/1545, loss: 0.0011603807797655463 2023-01-23 21:05:46.454433: step: 1080/1545, loss: 0.0006891124648973346 2023-01-23 21:05:47.346616: step: 1082/1545, loss: 0.0020631083752959967 2023-01-23 21:05:48.205366: step: 1084/1545, loss: 0.07354430854320526 2023-01-23 21:05:49.078189: step: 1086/1545, loss: 9.633103763917461e-05 2023-01-23 21:05:49.962487: step: 1088/1545, loss: 0.09086308628320694 2023-01-23 21:05:50.812543: step: 1090/1545, loss: 0.0007368286023847759 2023-01-23 21:05:51.698016: step: 1092/1545, loss: 0.0004285566683392972 2023-01-23 21:05:52.699451: step: 1094/1545, loss: 0.00016711046919226646 2023-01-23 21:05:53.558257: step: 1096/1545, loss: 9.862842853181064e-05 2023-01-23 21:05:54.391011: step: 1098/1545, loss: 0.0019439354073256254 2023-01-23 21:05:55.233647: step: 1100/1545, loss: 0.22428394854068756 2023-01-23 21:05:56.089136: step: 1102/1545, loss: 7.939814531709999e-05 2023-01-23 21:05:56.945501: step: 1104/1545, loss: 0.00012460311700124294 2023-01-23 21:05:57.817097: step: 1106/1545, loss: 0.1273011416196823 2023-01-23 21:05:58.714123: step: 1108/1545, loss: 0.001139945350587368 2023-01-23 21:05:59.618128: step: 1110/1545, loss: 0.007042587734758854 2023-01-23 21:06:00.472239: step: 1112/1545, loss: 0.22342686355113983 2023-01-23 21:06:01.353992: step: 1114/1545, loss: 0.0006687992135994136 2023-01-23 21:06:02.250282: step: 1116/1545, loss: 0.0016136247431859374 2023-01-23 21:06:03.121523: step: 1118/1545, loss: 0.0014599069254472852 2023-01-23 21:06:03.995656: step: 1120/1545, loss: 0.001228989101946354 2023-01-23 21:06:04.849302: step: 1122/1545, loss: 0.02539268508553505 2023-01-23 21:06:05.711787: step: 1124/1545, loss: 0.0013186781434342265 2023-01-23 21:06:06.580486: step: 1126/1545, loss: 0.022569481283426285 2023-01-23 21:06:07.428626: step: 1128/1545, loss: 0.0012438256526365876 2023-01-23 21:06:08.267796: step: 1130/1545, loss: 0.0002062213170574978 2023-01-23 21:06:09.134330: step: 1132/1545, loss: 0.002689824439585209 2023-01-23 21:06:10.028831: step: 1134/1545, loss: 0.11416362971067429 2023-01-23 21:06:10.873707: step: 1136/1545, loss: 0.0013951940927654505 2023-01-23 21:06:11.732960: step: 1138/1545, loss: 0.0017841781955212355 2023-01-23 21:06:12.602149: step: 1140/1545, loss: 0.14346998929977417 2023-01-23 21:06:13.450941: step: 1142/1545, loss: 0.00044691769289784133 2023-01-23 21:06:14.402144: step: 1144/1545, loss: 0.16954165697097778 2023-01-23 21:06:15.245353: step: 1146/1545, loss: 0.007575036026537418 2023-01-23 21:06:16.090183: step: 1148/1545, loss: 9.88339088507928e-05 2023-01-23 21:06:16.979365: step: 1150/1545, loss: 0.009140296839177608 2023-01-23 21:06:17.842874: step: 1152/1545, loss: 0.0016287111211568117 2023-01-23 21:06:18.703436: step: 1154/1545, loss: 9.443386079510674e-05 2023-01-23 21:06:19.660297: step: 1156/1545, loss: 0.308199942111969 2023-01-23 21:06:20.545562: step: 1158/1545, loss: 0.0004602587141562253 2023-01-23 21:06:21.409076: step: 1160/1545, loss: 0.00036025966983288527 2023-01-23 21:06:22.302742: step: 1162/1545, loss: 0.0703122466802597 2023-01-23 21:06:23.170834: step: 1164/1545, loss: 0.0004423024656716734 2023-01-23 21:06:24.037001: step: 1166/1545, loss: 0.029312772676348686 2023-01-23 21:06:24.881255: step: 1168/1545, loss: 0.009154223836958408 2023-01-23 21:06:25.772812: step: 1170/1545, loss: 0.0022536220494657755 2023-01-23 21:06:26.658458: step: 1172/1545, loss: 0.000964959675911814 2023-01-23 21:06:27.630100: step: 1174/1545, loss: 0.0056471372954547405 2023-01-23 21:06:28.473153: step: 1176/1545, loss: 3.6687779356725514e-05 2023-01-23 21:06:29.313463: step: 1178/1545, loss: 0.00042542017763480544 2023-01-23 21:06:30.226931: step: 1180/1545, loss: 0.002434080233797431 2023-01-23 21:06:31.071779: step: 1182/1545, loss: 0.0028172677848488092 2023-01-23 21:06:31.988452: step: 1184/1545, loss: 0.30123117566108704 2023-01-23 21:06:32.858165: step: 1186/1545, loss: 0.007813786156475544 2023-01-23 21:06:33.725094: step: 1188/1545, loss: 0.0024982690811157227 2023-01-23 21:06:34.587823: step: 1190/1545, loss: 0.021176910027861595 2023-01-23 21:06:35.458928: step: 1192/1545, loss: 0.0011819059727713466 2023-01-23 21:06:36.327079: step: 1194/1545, loss: 0.12274686247110367 2023-01-23 21:06:37.219734: step: 1196/1545, loss: 0.0002279457257827744 2023-01-23 21:06:38.104315: step: 1198/1545, loss: 0.01343191135674715 2023-01-23 21:06:38.956752: step: 1200/1545, loss: 0.0008518269169144332 2023-01-23 21:06:39.944224: step: 1202/1545, loss: 0.0009182236972264946 2023-01-23 21:06:40.799763: step: 1204/1545, loss: 0.0003884677716996521 2023-01-23 21:06:41.660765: step: 1206/1545, loss: 0.0026234472170472145 2023-01-23 21:06:42.532659: step: 1208/1545, loss: 3.622282747528516e-05 2023-01-23 21:06:43.440497: step: 1210/1545, loss: 0.04577689617872238 2023-01-23 21:06:44.316870: step: 1212/1545, loss: 0.046193793416023254 2023-01-23 21:06:45.192917: step: 1214/1545, loss: 0.00014098812243901193 2023-01-23 21:06:46.040187: step: 1216/1545, loss: 0.00040114857256412506 2023-01-23 21:06:46.941894: step: 1218/1545, loss: 0.02791442908346653 2023-01-23 21:06:47.812168: step: 1220/1545, loss: 0.017967255786061287 2023-01-23 21:06:48.663013: step: 1222/1545, loss: 0.00020933104678988457 2023-01-23 21:06:49.529872: step: 1224/1545, loss: 0.0038394280709326267 2023-01-23 21:06:50.402802: step: 1226/1545, loss: 0.001435405807569623 2023-01-23 21:06:51.256015: step: 1228/1545, loss: 0.0006931999232620001 2023-01-23 21:06:52.190634: step: 1230/1545, loss: 0.05400525778532028 2023-01-23 21:06:53.063494: step: 1232/1545, loss: 0.0052466862834990025 2023-01-23 21:06:53.989422: step: 1234/1545, loss: 0.008629261516034603 2023-01-23 21:06:54.845647: step: 1236/1545, loss: 0.0010454305447638035 2023-01-23 21:06:55.715094: step: 1238/1545, loss: 0.02949351631104946 2023-01-23 21:06:56.622847: step: 1240/1545, loss: 0.0278864037245512 2023-01-23 21:06:57.553524: step: 1242/1545, loss: 0.38461557030677795 2023-01-23 21:06:58.552450: step: 1244/1545, loss: 0.0001810499234125018 2023-01-23 21:06:59.416997: step: 1246/1545, loss: 0.1166946291923523 2023-01-23 21:07:00.263367: step: 1248/1545, loss: 1.256062478205422e-05 2023-01-23 21:07:01.150328: step: 1250/1545, loss: 0.00030185122159309685 2023-01-23 21:07:02.012055: step: 1252/1545, loss: 0.003947174176573753 2023-01-23 21:07:02.875257: step: 1254/1545, loss: 0.009175696410238743 2023-01-23 21:07:03.780355: step: 1256/1545, loss: 0.0009361194097436965 2023-01-23 21:07:04.658364: step: 1258/1545, loss: 0.09079746156930923 2023-01-23 21:07:05.523667: step: 1260/1545, loss: 0.0003502755716908723 2023-01-23 21:07:06.389458: step: 1262/1545, loss: 0.2773549258708954 2023-01-23 21:07:07.274115: step: 1264/1545, loss: 0.05288911983370781 2023-01-23 21:07:08.120997: step: 1266/1545, loss: 7.364468183368444e-05 2023-01-23 21:07:08.960548: step: 1268/1545, loss: 0.0029230783693492413 2023-01-23 21:07:09.858196: step: 1270/1545, loss: 0.0002526132739149034 2023-01-23 21:07:10.729333: step: 1272/1545, loss: 0.017545167356729507 2023-01-23 21:07:11.566633: step: 1274/1545, loss: 8.291913400171325e-05 2023-01-23 21:07:12.448810: step: 1276/1545, loss: 0.00031211605528369546 2023-01-23 21:07:13.316191: step: 1278/1545, loss: 0.0005151863442733884 2023-01-23 21:07:14.225384: step: 1280/1545, loss: 0.009554761461913586 2023-01-23 21:07:15.102606: step: 1282/1545, loss: 0.031142162159085274 2023-01-23 21:07:16.022580: step: 1284/1545, loss: 0.004226827062666416 2023-01-23 21:07:16.866713: step: 1286/1545, loss: 0.0335407629609108 2023-01-23 21:07:17.739071: step: 1288/1545, loss: 0.06313730031251907 2023-01-23 21:07:18.620437: step: 1290/1545, loss: 0.07704239338636398 2023-01-23 21:07:19.470878: step: 1292/1545, loss: 0.013005194254219532 2023-01-23 21:07:20.325558: step: 1294/1545, loss: 0.000989742809906602 2023-01-23 21:07:21.222281: step: 1296/1545, loss: 0.0001661725400481373 2023-01-23 21:07:22.103793: step: 1298/1545, loss: 0.002935541793704033 2023-01-23 21:07:22.960856: step: 1300/1545, loss: 0.0030825685244053602 2023-01-23 21:07:23.832981: step: 1302/1545, loss: 0.003193381940945983 2023-01-23 21:07:24.704657: step: 1304/1545, loss: 0.000972575624473393 2023-01-23 21:07:25.547129: step: 1306/1545, loss: 0.2543770670890808 2023-01-23 21:07:26.425254: step: 1308/1545, loss: 0.02152634970843792 2023-01-23 21:07:27.300587: step: 1310/1545, loss: 0.015428563579916954 2023-01-23 21:07:28.227432: step: 1312/1545, loss: -3.235384792787954e-05 2023-01-23 21:07:29.101216: step: 1314/1545, loss: 0.00836937129497528 2023-01-23 21:07:29.968886: step: 1316/1545, loss: 0.003231849754229188 2023-01-23 21:07:30.884823: step: 1318/1545, loss: 0.03665474057197571 2023-01-23 21:07:31.767641: step: 1320/1545, loss: 0.029225893318653107 2023-01-23 21:07:32.640113: step: 1322/1545, loss: 0.0006387097528204322 2023-01-23 21:07:33.481586: step: 1324/1545, loss: 0.22592371702194214 2023-01-23 21:07:34.355106: step: 1326/1545, loss: 0.0002580261789262295 2023-01-23 21:07:35.199170: step: 1328/1545, loss: 4.159930904279463e-05 2023-01-23 21:07:36.071956: step: 1330/1545, loss: 0.17123320698738098 2023-01-23 21:07:36.956796: step: 1332/1545, loss: 4.1202380089089274e-05 2023-01-23 21:07:37.911651: step: 1334/1545, loss: 0.026886356994509697 2023-01-23 21:07:38.774752: step: 1336/1545, loss: 0.11143981665372849 2023-01-23 21:07:39.648407: step: 1338/1545, loss: 0.0011580762220546603 2023-01-23 21:07:40.548901: step: 1340/1545, loss: 8.937846723711118e-05 2023-01-23 21:07:41.490040: step: 1342/1545, loss: 0.004637766629457474 2023-01-23 21:07:42.396542: step: 1344/1545, loss: 1.2339304685592651 2023-01-23 21:07:43.306367: step: 1346/1545, loss: 0.10539098083972931 2023-01-23 21:07:44.195250: step: 1348/1545, loss: 0.009070922620594501 2023-01-23 21:07:45.066939: step: 1350/1545, loss: 0.00010568714060354978 2023-01-23 21:07:45.949503: step: 1352/1545, loss: 0.036269668489694595 2023-01-23 21:07:46.839620: step: 1354/1545, loss: 0.16908815503120422 2023-01-23 21:07:47.669258: step: 1356/1545, loss: 0.007287539541721344 2023-01-23 21:07:48.502399: step: 1358/1545, loss: 0.007106555625796318 2023-01-23 21:07:49.348790: step: 1360/1545, loss: 0.08097377419471741 2023-01-23 21:07:50.231372: step: 1362/1545, loss: 0.0005449134623631835 2023-01-23 21:07:51.101371: step: 1364/1545, loss: 0.005734815262258053 2023-01-23 21:07:51.962721: step: 1366/1545, loss: 0.0003081863687839359 2023-01-23 21:07:52.815096: step: 1368/1545, loss: 0.00517024053260684 2023-01-23 21:07:53.712267: step: 1370/1545, loss: 0.34218209981918335 2023-01-23 21:07:54.593020: step: 1372/1545, loss: 0.0011929292231798172 2023-01-23 21:07:55.440121: step: 1374/1545, loss: 0.0029449539724737406 2023-01-23 21:07:56.349838: step: 1376/1545, loss: 0.0010324121685698628 2023-01-23 21:07:57.239198: step: 1378/1545, loss: 0.018039053305983543 2023-01-23 21:07:58.137048: step: 1380/1545, loss: 0.002735510468482971 2023-01-23 21:07:59.021149: step: 1382/1545, loss: 0.016306452453136444 2023-01-23 21:07:59.901709: step: 1384/1545, loss: 0.0005165536422282457 2023-01-23 21:08:00.805706: step: 1386/1545, loss: 0.0001812180271372199 2023-01-23 21:08:01.675615: step: 1388/1545, loss: 0.000643759616650641 2023-01-23 21:08:02.514902: step: 1390/1545, loss: 0.34811824560165405 2023-01-23 21:08:03.370789: step: 1392/1545, loss: 1.1788484698627144e-05 2023-01-23 21:08:04.248492: step: 1394/1545, loss: 0.0005489621544256806 2023-01-23 21:08:05.128639: step: 1396/1545, loss: 0.032502949237823486 2023-01-23 21:08:05.987826: step: 1398/1545, loss: 0.0029045294504612684 2023-01-23 21:08:06.853790: step: 1400/1545, loss: 0.15682901442050934 2023-01-23 21:08:07.765334: step: 1402/1545, loss: -3.1798481359146535e-05 2023-01-23 21:08:08.635962: step: 1404/1545, loss: 0.00044539914233610034 2023-01-23 21:08:09.497316: step: 1406/1545, loss: 0.020006228238344193 2023-01-23 21:08:10.386321: step: 1408/1545, loss: 0.0012055309489369392 2023-01-23 21:08:11.262236: step: 1410/1545, loss: 0.2769573926925659 2023-01-23 21:08:12.117352: step: 1412/1545, loss: 2.0447696442715824e-05 2023-01-23 21:08:13.070247: step: 1414/1545, loss: 0.24473507702350616 2023-01-23 21:08:13.919441: step: 1416/1545, loss: 0.05793573707342148 2023-01-23 21:08:14.825390: step: 1418/1545, loss: 0.00010249421757180244 2023-01-23 21:08:15.665095: step: 1420/1545, loss: 0.0010851328261196613 2023-01-23 21:08:16.512074: step: 1422/1545, loss: 0.08834118396043777 2023-01-23 21:08:17.364483: step: 1424/1545, loss: 0.00020785046217497438 2023-01-23 21:08:18.218475: step: 1426/1545, loss: 0.003433517413213849 2023-01-23 21:08:19.058967: step: 1428/1545, loss: 0.0009747949079610407 2023-01-23 21:08:19.932376: step: 1430/1545, loss: 0.0003872967790812254 2023-01-23 21:08:20.782563: step: 1432/1545, loss: 7.017354073468596e-05 2023-01-23 21:08:21.721821: step: 1434/1545, loss: 0.00014689314411953092 2023-01-23 21:08:22.651377: step: 1436/1545, loss: 0.0008185146143659949 2023-01-23 21:08:23.570364: step: 1438/1545, loss: 5.6192911870311946e-05 2023-01-23 21:08:24.528040: step: 1440/1545, loss: 0.05850893631577492 2023-01-23 21:08:25.387997: step: 1442/1545, loss: 0.11795064061880112 2023-01-23 21:08:26.276921: step: 1444/1545, loss: 0.00022133141465019435 2023-01-23 21:08:27.159486: step: 1446/1545, loss: 0.0001237777032656595 2023-01-23 21:08:28.036815: step: 1448/1545, loss: 0.000150979874888435 2023-01-23 21:08:28.928348: step: 1450/1545, loss: 0.0031424483750015497 2023-01-23 21:08:29.789388: step: 1452/1545, loss: 0.050776079297065735 2023-01-23 21:08:30.682870: step: 1454/1545, loss: 9.106662037083879e-05 2023-01-23 21:08:31.555506: step: 1456/1545, loss: 0.001177317462861538 2023-01-23 21:08:32.377075: step: 1458/1545, loss: 0.001720501808449626 2023-01-23 21:08:33.226622: step: 1460/1545, loss: 0.0023488837759941816 2023-01-23 21:08:34.082852: step: 1462/1545, loss: 0.1724037528038025 2023-01-23 21:08:34.976600: step: 1464/1545, loss: 0.194418802857399 2023-01-23 21:08:35.829793: step: 1466/1545, loss: 0.15200182795524597 2023-01-23 21:08:36.680205: step: 1468/1545, loss: 0.3219333291053772 2023-01-23 21:08:37.542656: step: 1470/1545, loss: 0.12039843946695328 2023-01-23 21:08:38.453133: step: 1472/1545, loss: 0.2740076184272766 2023-01-23 21:08:39.317364: step: 1474/1545, loss: 0.00026941843680106103 2023-01-23 21:08:40.195268: step: 1476/1545, loss: 0.0625154972076416 2023-01-23 21:08:41.050686: step: 1478/1545, loss: 0.3034762740135193 2023-01-23 21:08:41.920311: step: 1480/1545, loss: 0.000580645224545151 2023-01-23 21:08:42.808924: step: 1482/1545, loss: 0.0009045257465913892 2023-01-23 21:08:43.699911: step: 1484/1545, loss: 0.0593724399805069 2023-01-23 21:08:44.564959: step: 1486/1545, loss: 0.0028316208627074957 2023-01-23 21:08:45.447975: step: 1488/1545, loss: -5.0832836677727755e-06 2023-01-23 21:08:46.287687: step: 1490/1545, loss: 0.00013118278002366424 2023-01-23 21:08:47.206846: step: 1492/1545, loss: 0.12422928214073181 2023-01-23 21:08:48.065396: step: 1494/1545, loss: 0.0010276412358507514 2023-01-23 21:08:48.938561: step: 1496/1545, loss: 0.46703076362609863 2023-01-23 21:08:49.804677: step: 1498/1545, loss: 0.015112169086933136 2023-01-23 21:08:50.702917: step: 1500/1545, loss: 0.0114650409668684 2023-01-23 21:08:51.579333: step: 1502/1545, loss: 0.07129517197608948 2023-01-23 21:08:52.498783: step: 1504/1545, loss: 0.00013559758372139186 2023-01-23 21:08:53.408269: step: 1506/1545, loss: 0.0017514138016849756 2023-01-23 21:08:54.293105: step: 1508/1545, loss: 0.0006344522698782384 2023-01-23 21:08:55.199062: step: 1510/1545, loss: 0.023471524938941002 2023-01-23 21:08:56.134722: step: 1512/1545, loss: 0.0006879299180582166 2023-01-23 21:08:57.037260: step: 1514/1545, loss: 0.0015155794098973274 2023-01-23 21:08:58.017452: step: 1516/1545, loss: 0.017055148258805275 2023-01-23 21:08:58.903766: step: 1518/1545, loss: 0.00417741946876049 2023-01-23 21:08:59.817262: step: 1520/1545, loss: 0.005765843205153942 2023-01-23 21:09:00.692981: step: 1522/1545, loss: 0.004133977461606264 2023-01-23 21:09:01.560705: step: 1524/1545, loss: 0.1212235614657402 2023-01-23 21:09:02.422236: step: 1526/1545, loss: 0.0028130761347711086 2023-01-23 21:09:03.314367: step: 1528/1545, loss: 0.00019399280427023768 2023-01-23 21:09:04.213324: step: 1530/1545, loss: 0.0045946137979626656 2023-01-23 21:09:05.112188: step: 1532/1545, loss: 0.0092787966132164 2023-01-23 21:09:05.948985: step: 1534/1545, loss: 7.439738692482933e-05 2023-01-23 21:09:06.830235: step: 1536/1545, loss: 0.08432146906852722 2023-01-23 21:09:07.832891: step: 1538/1545, loss: 0.0006292975740507245 2023-01-23 21:09:08.843692: step: 1540/1545, loss: 2.661632776260376 2023-01-23 21:09:09.705148: step: 1542/1545, loss: 0.17885512113571167 2023-01-23 21:09:10.565997: step: 1544/1545, loss: 0.21082396805286407 2023-01-23 21:09:11.489710: step: 1546/1545, loss: 0.004848015960305929 2023-01-23 21:09:12.398637: step: 1548/1545, loss: 0.030181247740983963 2023-01-23 21:09:13.321365: step: 1550/1545, loss: 9.639784548198804e-05 2023-01-23 21:09:14.193079: step: 1552/1545, loss: 0.0002757734037004411 2023-01-23 21:09:15.109958: step: 1554/1545, loss: 0.04619913175702095 2023-01-23 21:09:16.021194: step: 1556/1545, loss: 2.1696970462799072 2023-01-23 21:09:16.966440: step: 1558/1545, loss: 0.004046148620545864 2023-01-23 21:09:17.862053: step: 1560/1545, loss: 0.28809747099876404 2023-01-23 21:09:18.897148: step: 1562/1545, loss: 0.061229534447193146 2023-01-23 21:09:19.765617: step: 1564/1545, loss: 0.00015863048611208797 2023-01-23 21:09:20.671949: step: 1566/1545, loss: 9.127067460212857e-05 2023-01-23 21:09:21.559828: step: 1568/1545, loss: 0.00015341388643719256 2023-01-23 21:09:22.452572: step: 1570/1545, loss: 0.1930473893880844 2023-01-23 21:09:23.361690: step: 1572/1545, loss: 0.02402249164879322 2023-01-23 21:09:24.282940: step: 1574/1545, loss: 0.0011161763686686754 2023-01-23 21:09:25.163097: step: 1576/1545, loss: 0.0012064989423379302 2023-01-23 21:09:26.050639: step: 1578/1545, loss: 0.000997968832962215 2023-01-23 21:09:26.928974: step: 1580/1545, loss: 0.00021139299497008324 2023-01-23 21:09:27.857852: step: 1582/1545, loss: 0.01155728381127119 2023-01-23 21:09:28.710931: step: 1584/1545, loss: 0.026911044493317604 2023-01-23 21:09:29.607892: step: 1586/1545, loss: 0.2538101375102997 2023-01-23 21:09:30.480171: step: 1588/1545, loss: 0.0007436844171024859 2023-01-23 21:09:31.384378: step: 1590/1545, loss: 0.2858181595802307 2023-01-23 21:09:32.277732: step: 1592/1545, loss: 0.0011742550414055586 2023-01-23 21:09:33.117462: step: 1594/1545, loss: 0.0008972521172836423 2023-01-23 21:09:33.996937: step: 1596/1545, loss: 0.0005665879580192268 2023-01-23 21:09:34.846913: step: 1598/1545, loss: 0.0017258761217817664 2023-01-23 21:09:35.687840: step: 1600/1545, loss: 0.0017425210680812597 2023-01-23 21:09:36.588715: step: 1602/1545, loss: 0.0027685787063091993 2023-01-23 21:09:37.460082: step: 1604/1545, loss: 0.13253572583198547 2023-01-23 21:09:38.316982: step: 1606/1545, loss: 0.0005688769742846489 2023-01-23 21:09:39.167432: step: 1608/1545, loss: 0.025962047278881073 2023-01-23 21:09:40.075029: step: 1610/1545, loss: 0.0004547263670247048 2023-01-23 21:09:40.902780: step: 1612/1545, loss: 0.0006630141870118678 2023-01-23 21:09:41.773236: step: 1614/1545, loss: 0.0012250712607055902 2023-01-23 21:09:42.685439: step: 1616/1545, loss: 0.06392746418714523 2023-01-23 21:09:43.558026: step: 1618/1545, loss: 0.08454466611146927 2023-01-23 21:09:44.428501: step: 1620/1545, loss: 0.001089319121092558 2023-01-23 21:09:45.306751: step: 1622/1545, loss: 0.005458825267851353 2023-01-23 21:09:46.157246: step: 1624/1545, loss: 0.00013391865650191903 2023-01-23 21:09:46.999291: step: 1626/1545, loss: 0.0024341295938938856 2023-01-23 21:09:47.858768: step: 1628/1545, loss: 0.45833417773246765 2023-01-23 21:09:48.722986: step: 1630/1545, loss: 0.002566833049058914 2023-01-23 21:09:49.579205: step: 1632/1545, loss: 0.0041374946013092995 2023-01-23 21:09:50.450374: step: 1634/1545, loss: 0.018357502296566963 2023-01-23 21:09:51.370227: step: 1636/1545, loss: 0.07383343577384949 2023-01-23 21:09:52.254461: step: 1638/1545, loss: 0.0025475849397480488 2023-01-23 21:09:53.110800: step: 1640/1545, loss: 0.004164845682680607 2023-01-23 21:09:53.982101: step: 1642/1545, loss: 0.0037929655518382788 2023-01-23 21:09:54.910032: step: 1644/1545, loss: 0.06664401292800903 2023-01-23 21:09:55.788209: step: 1646/1545, loss: 0.0003933559637516737 2023-01-23 21:09:56.675760: step: 1648/1545, loss: 0.07524657249450684 2023-01-23 21:09:57.577463: step: 1650/1545, loss: 0.00032068719156086445 2023-01-23 21:09:58.454454: step: 1652/1545, loss: 8.730494300834835e-05 2023-01-23 21:09:59.343702: step: 1654/1545, loss: 0.06440248340368271 2023-01-23 21:10:00.268338: step: 1656/1545, loss: 0.01816578581929207 2023-01-23 21:10:01.145955: step: 1658/1545, loss: 0.0009137079468928277 2023-01-23 21:10:02.032855: step: 1660/1545, loss: 0.0005670450045727193 2023-01-23 21:10:02.962959: step: 1662/1545, loss: 0.7484560012817383 2023-01-23 21:10:03.840646: step: 1664/1545, loss: 0.1808815449476242 2023-01-23 21:10:04.717987: step: 1666/1545, loss: 0.0031889923848211765 2023-01-23 21:10:05.609457: step: 1668/1545, loss: 0.009886713698506355 2023-01-23 21:10:06.475233: step: 1670/1545, loss: 0.001124440343119204 2023-01-23 21:10:07.372682: step: 1672/1545, loss: 0.07999374717473984 2023-01-23 21:10:08.278131: step: 1674/1545, loss: 0.027464641258120537 2023-01-23 21:10:09.179804: step: 1676/1545, loss: 0.15462398529052734 2023-01-23 21:10:10.076330: step: 1678/1545, loss: 0.0006958392914384604 2023-01-23 21:10:10.975584: step: 1680/1545, loss: 0.028683168813586235 2023-01-23 21:10:11.821328: step: 1682/1545, loss: 0.0029657776467502117 2023-01-23 21:10:12.695356: step: 1684/1545, loss: 0.06887120753526688 2023-01-23 21:10:13.582675: step: 1686/1545, loss: 0.0066115823574364185 2023-01-23 21:10:14.441296: step: 1688/1545, loss: 7.903174264356494e-05 2023-01-23 21:10:15.290735: step: 1690/1545, loss: 0.030986173078417778 2023-01-23 21:10:16.157466: step: 1692/1545, loss: 5.037018854636699e-05 2023-01-23 21:10:17.016362: step: 1694/1545, loss: 0.008734378963708878 2023-01-23 21:10:17.888855: step: 1696/1545, loss: 0.004110113717615604 2023-01-23 21:10:18.752132: step: 1698/1545, loss: 0.023798583075404167 2023-01-23 21:10:19.630719: step: 1700/1545, loss: 0.0006666675908491015 2023-01-23 21:10:20.489994: step: 1702/1545, loss: 0.0018169995164498687 2023-01-23 21:10:21.365840: step: 1704/1545, loss: 0.0329425223171711 2023-01-23 21:10:22.274256: step: 1706/1545, loss: 0.04353274032473564 2023-01-23 21:10:23.143931: step: 1708/1545, loss: 0.08792033046483994 2023-01-23 21:10:24.018319: step: 1710/1545, loss: 0.01495343167334795 2023-01-23 21:10:24.880489: step: 1712/1545, loss: 0.19326086342334747 2023-01-23 21:10:25.745583: step: 1714/1545, loss: 0.0010069861309602857 2023-01-23 21:10:26.585637: step: 1716/1545, loss: 0.00010740898142103106 2023-01-23 21:10:27.459504: step: 1718/1545, loss: 0.00017891924653667957 2023-01-23 21:10:28.355080: step: 1720/1545, loss: 1.4395200196304359e-06 2023-01-23 21:10:29.242668: step: 1722/1545, loss: 0.04374626651406288 2023-01-23 21:10:30.165188: step: 1724/1545, loss: 0.24393120408058167 2023-01-23 21:10:31.019995: step: 1726/1545, loss: 0.0008718855096958578 2023-01-23 21:10:31.871985: step: 1728/1545, loss: -3.2169962651096284e-05 2023-01-23 21:10:32.759081: step: 1730/1545, loss: 4.769066072185524e-05 2023-01-23 21:10:33.650529: step: 1732/1545, loss: 0.0017218701541423798 2023-01-23 21:10:34.535728: step: 1734/1545, loss: 0.00013048647087998688 2023-01-23 21:10:35.435949: step: 1736/1545, loss: 0.0013607485452666879 2023-01-23 21:10:36.299502: step: 1738/1545, loss: 0.45406192541122437 2023-01-23 21:10:37.196557: step: 1740/1545, loss: 6.171762652229518e-05 2023-01-23 21:10:38.176713: step: 1742/1545, loss: 0.7210204601287842 2023-01-23 21:10:39.056481: step: 1744/1545, loss: 0.0012796816881746054 2023-01-23 21:10:39.914991: step: 1746/1545, loss: -2.87182647298323e-05 2023-01-23 21:10:40.817956: step: 1748/1545, loss: 0.3153780400753021 2023-01-23 21:10:41.679676: step: 1750/1545, loss: 0.11181716620922089 2023-01-23 21:10:42.553869: step: 1752/1545, loss: 0.0007779577863402665 2023-01-23 21:10:43.424922: step: 1754/1545, loss: 0.031922727823257446 2023-01-23 21:10:44.305539: step: 1756/1545, loss: 0.010810752399265766 2023-01-23 21:10:45.205094: step: 1758/1545, loss: 0.07084054499864578 2023-01-23 21:10:46.064149: step: 1760/1545, loss: 0.03990699723362923 2023-01-23 21:10:46.940333: step: 1762/1545, loss: 0.001808172557502985 2023-01-23 21:10:47.826723: step: 1764/1545, loss: 0.0003517057921271771 2023-01-23 21:10:48.740003: step: 1766/1545, loss: 0.014181175269186497 2023-01-23 21:10:49.662784: step: 1768/1545, loss: 0.43444859981536865 2023-01-23 21:10:50.535761: step: 1770/1545, loss: 0.02132718451321125 2023-01-23 21:10:51.401053: step: 1772/1545, loss: 0.21028314530849457 2023-01-23 21:10:52.299164: step: 1774/1545, loss: 0.010705756954848766 2023-01-23 21:10:53.189928: step: 1776/1545, loss: 0.0022558511700481176 2023-01-23 21:10:54.060350: step: 1778/1545, loss: 0.009131297469139099 2023-01-23 21:10:54.932705: step: 1780/1545, loss: 0.000690111075527966 2023-01-23 21:10:55.873790: step: 1782/1545, loss: 0.0027001742273569107 2023-01-23 21:10:56.777541: step: 1784/1545, loss: 0.0002666381187736988 2023-01-23 21:10:57.673157: step: 1786/1545, loss: 0.001443776534870267 2023-01-23 21:10:58.561197: step: 1788/1545, loss: 0.000418115290813148 2023-01-23 21:10:59.486659: step: 1790/1545, loss: 0.1808851659297943 2023-01-23 21:11:00.374274: step: 1792/1545, loss: 0.00031119424966163933 2023-01-23 21:11:01.227524: step: 1794/1545, loss: 0.19649307429790497 2023-01-23 21:11:02.124645: step: 1796/1545, loss: 0.6233108639717102 2023-01-23 21:11:02.980303: step: 1798/1545, loss: 0.023073909804224968 2023-01-23 21:11:03.899426: step: 1800/1545, loss: 0.055010076612234116 2023-01-23 21:11:04.799293: step: 1802/1545, loss: 0.018139945343136787 2023-01-23 21:11:05.678363: step: 1804/1545, loss: 0.04970002919435501 2023-01-23 21:11:06.560745: step: 1806/1545, loss: 0.0007625290309078991 2023-01-23 21:11:07.404824: step: 1808/1545, loss: 0.003964817617088556 2023-01-23 21:11:08.322662: step: 1810/1545, loss: 0.009320040233433247 2023-01-23 21:11:09.178361: step: 1812/1545, loss: 0.004490248393267393 2023-01-23 21:11:10.066398: step: 1814/1545, loss: 0.003676679916679859 2023-01-23 21:11:10.977877: step: 1816/1545, loss: 0.012128408066928387 2023-01-23 21:11:11.858946: step: 1818/1545, loss: 0.0001541351666674018 2023-01-23 21:11:12.735516: step: 1820/1545, loss: 0.14067986607551575 2023-01-23 21:11:13.573444: step: 1822/1545, loss: 0.29511234164237976 2023-01-23 21:11:14.391999: step: 1824/1545, loss: 0.0027565478812903166 2023-01-23 21:11:15.256708: step: 1826/1545, loss: 0.02243686467409134 2023-01-23 21:11:16.134766: step: 1828/1545, loss: 0.005032464861869812 2023-01-23 21:11:17.019091: step: 1830/1545, loss: 0.02631259895861149 2023-01-23 21:11:17.852715: step: 1832/1545, loss: 0.0001219832556671463 2023-01-23 21:11:18.772096: step: 1834/1545, loss: 0.002852550707757473 2023-01-23 21:11:19.666426: step: 1836/1545, loss: 0.007072138600051403 2023-01-23 21:11:20.516423: step: 1838/1545, loss: 0.15697520971298218 2023-01-23 21:11:21.380763: step: 1840/1545, loss: 0.004291003569960594 2023-01-23 21:11:22.243891: step: 1842/1545, loss: 0.005310604814440012 2023-01-23 21:11:23.081833: step: 1844/1545, loss: 0.00010893872968154028 2023-01-23 21:11:23.961329: step: 1846/1545, loss: 0.012634648010134697 2023-01-23 21:11:24.871296: step: 1848/1545, loss: 0.00015888153575360775 2023-01-23 21:11:25.761931: step: 1850/1545, loss: 0.004302626010030508 2023-01-23 21:11:26.662112: step: 1852/1545, loss: 0.005182128399610519 2023-01-23 21:11:27.565003: step: 1854/1545, loss: 9.927004430210218e-05 2023-01-23 21:11:28.428806: step: 1856/1545, loss: 0.4146353602409363 2023-01-23 21:11:29.270529: step: 1858/1545, loss: 8.377239282708615e-05 2023-01-23 21:11:30.156074: step: 1860/1545, loss: 0.19458039104938507 2023-01-23 21:11:31.016847: step: 1862/1545, loss: 0.0022037930320948362 2023-01-23 21:11:31.900654: step: 1864/1545, loss: 0.00024927922640927136 2023-01-23 21:11:32.737326: step: 1866/1545, loss: 7.97395478002727e-05 2023-01-23 21:11:33.578535: step: 1868/1545, loss: 0.002020083600655198 2023-01-23 21:11:34.444594: step: 1870/1545, loss: 9.171912097372115e-05 2023-01-23 21:11:35.403905: step: 1872/1545, loss: 0.0001441745407646522 2023-01-23 21:11:36.289338: step: 1874/1545, loss: 0.14187045395374298 2023-01-23 21:11:37.189635: step: 1876/1545, loss: 0.0016688629984855652 2023-01-23 21:11:38.079983: step: 1878/1545, loss: 0.009119932539761066 2023-01-23 21:11:38.949540: step: 1880/1545, loss: 0.011048577725887299 2023-01-23 21:11:39.790510: step: 1882/1545, loss: 0.04932209849357605 2023-01-23 21:11:40.657806: step: 1884/1545, loss: 0.09332109987735748 2023-01-23 21:11:41.477300: step: 1886/1545, loss: 0.08379387855529785 2023-01-23 21:11:42.373023: step: 1888/1545, loss: 0.033350203186273575 2023-01-23 21:11:43.245071: step: 1890/1545, loss: 8.132444054353982e-05 2023-01-23 21:11:44.167023: step: 1892/1545, loss: 0.014121610671281815 2023-01-23 21:11:45.093219: step: 1894/1545, loss: 0.0007722225855104625 2023-01-23 21:11:45.956063: step: 1896/1545, loss: 0.00029148097382858396 2023-01-23 21:11:46.844239: step: 1898/1545, loss: 0.00027382891857996583 2023-01-23 21:11:47.701215: step: 1900/1545, loss: 6.329931784421206e-05 2023-01-23 21:11:48.535129: step: 1902/1545, loss: 0.0004572242614813149 2023-01-23 21:11:49.434309: step: 1904/1545, loss: 0.07865874469280243 2023-01-23 21:11:50.268118: step: 1906/1545, loss: 2.067751483991742e-05 2023-01-23 21:11:51.125262: step: 1908/1545, loss: 0.0023416965268552303 2023-01-23 21:11:51.992599: step: 1910/1545, loss: 0.08208488672971725 2023-01-23 21:11:52.870275: step: 1912/1545, loss: 0.0010064090602099895 2023-01-23 21:11:53.714838: step: 1914/1545, loss: 0.0029684340115636587 2023-01-23 21:11:54.601747: step: 1916/1545, loss: 5.354239692678675e-05 2023-01-23 21:11:55.481102: step: 1918/1545, loss: 7.4685929575935e-05 2023-01-23 21:11:56.372817: step: 1920/1545, loss: 6.639250204898417e-05 2023-01-23 21:11:57.256233: step: 1922/1545, loss: 0.00026508301380090415 2023-01-23 21:11:58.152136: step: 1924/1545, loss: 0.3874954581260681 2023-01-23 21:11:59.112107: step: 1926/1545, loss: 1.4527071471093222e-05 2023-01-23 21:11:59.960088: step: 1928/1545, loss: 0.004371868446469307 2023-01-23 21:12:00.836912: step: 1930/1545, loss: 0.024406153708696365 2023-01-23 21:12:01.693837: step: 1932/1545, loss: 0.041371915489435196 2023-01-23 21:12:02.625336: step: 1934/1545, loss: 0.25625863671302795 2023-01-23 21:12:03.482899: step: 1936/1545, loss: 4.588004594552331e-05 2023-01-23 21:12:04.355188: step: 1938/1545, loss: 3.846264735329896e-05 2023-01-23 21:12:05.252468: step: 1940/1545, loss: 0.02364794909954071 2023-01-23 21:12:06.237135: step: 1942/1545, loss: 0.0018627146491780877 2023-01-23 21:12:07.163873: step: 1944/1545, loss: 0.0007390811806544662 2023-01-23 21:12:08.057734: step: 1946/1545, loss: 0.00018057874694932252 2023-01-23 21:12:08.926955: step: 1948/1545, loss: 6.361603300319985e-05 2023-01-23 21:12:09.808362: step: 1950/1545, loss: 3.9094287785701454e-05 2023-01-23 21:12:10.705856: step: 1952/1545, loss: 0.07696399837732315 2023-01-23 21:12:11.567481: step: 1954/1545, loss: 0.0010504706297069788 2023-01-23 21:12:12.412585: step: 1956/1545, loss: 0.34611034393310547 2023-01-23 21:12:13.302518: step: 1958/1545, loss: 0.00018006731988862157 2023-01-23 21:12:14.149810: step: 1960/1545, loss: 0.002639226382598281 2023-01-23 21:12:15.012588: step: 1962/1545, loss: 0.00013329568901099265 2023-01-23 21:12:15.879179: step: 1964/1545, loss: 0.0005774241290055215 2023-01-23 21:12:16.740055: step: 1966/1545, loss: 4.586031354847364e-05 2023-01-23 21:12:17.589016: step: 1968/1545, loss: 0.08375607430934906 2023-01-23 21:12:18.474593: step: 1970/1545, loss: 0.0003595904854591936 2023-01-23 21:12:19.326685: step: 1972/1545, loss: 0.15822148323059082 2023-01-23 21:12:20.201665: step: 1974/1545, loss: 1.3057563304901123 2023-01-23 21:12:21.075983: step: 1976/1545, loss: 0.10279223322868347 2023-01-23 21:12:21.939262: step: 1978/1545, loss: 0.0011268338421359658 2023-01-23 21:12:22.835855: step: 1980/1545, loss: 6.184490484884009e-05 2023-01-23 21:12:23.751402: step: 1982/1545, loss: 0.0004983426770195365 2023-01-23 21:12:24.610667: step: 1984/1545, loss: 0.039903365075588226 2023-01-23 21:12:25.488874: step: 1986/1545, loss: 0.0013583145337179303 2023-01-23 21:12:26.358355: step: 1988/1545, loss: 0.04892497882246971 2023-01-23 21:12:27.225212: step: 1990/1545, loss: 0.004872729070484638 2023-01-23 21:12:28.053561: step: 1992/1545, loss: 6.991726695559919e-05 2023-01-23 21:12:29.017770: step: 1994/1545, loss: 0.0005683538620360196 2023-01-23 21:12:29.968227: step: 1996/1545, loss: 0.00023768754908815026 2023-01-23 21:12:30.842361: step: 1998/1545, loss: 0.00038494536420330405 2023-01-23 21:12:31.682017: step: 2000/1545, loss: 0.0007225670269690454 2023-01-23 21:12:32.601153: step: 2002/1545, loss: 0.47660356760025024 2023-01-23 21:12:33.494988: step: 2004/1545, loss: 0.0008083540014922619 2023-01-23 21:12:34.406385: step: 2006/1545, loss: 0.1907401978969574 2023-01-23 21:12:35.284112: step: 2008/1545, loss: 0.0001842445635702461 2023-01-23 21:12:36.183856: step: 2010/1545, loss: 0.00036268416442908347 2023-01-23 21:12:37.066389: step: 2012/1545, loss: 0.007780182640999556 2023-01-23 21:12:37.896780: step: 2014/1545, loss: 0.00011099361290689558 2023-01-23 21:12:38.772873: step: 2016/1545, loss: 0.004934858530759811 2023-01-23 21:12:39.647015: step: 2018/1545, loss: 0.002413701731711626 2023-01-23 21:12:40.510325: step: 2020/1545, loss: 0.0052508763037621975 2023-01-23 21:12:41.378595: step: 2022/1545, loss: 0.000424823141656816 2023-01-23 21:12:42.274571: step: 2024/1545, loss: 0.1267237514257431 2023-01-23 21:12:43.144160: step: 2026/1545, loss: 3.042768730665557e-05 2023-01-23 21:12:43.978566: step: 2028/1545, loss: 4.348958100308664e-06 2023-01-23 21:12:44.916895: step: 2030/1545, loss: 0.18208661675453186 2023-01-23 21:12:45.870221: step: 2032/1545, loss: 0.0003074807464145124 2023-01-23 21:12:46.777224: step: 2034/1545, loss: 0.05445307865738869 2023-01-23 21:12:47.646744: step: 2036/1545, loss: 0.1849389374256134 2023-01-23 21:12:48.508821: step: 2038/1545, loss: 0.00020456197671592236 2023-01-23 21:12:49.355734: step: 2040/1545, loss: 0.025721080601215363 2023-01-23 21:12:50.214218: step: 2042/1545, loss: 0.0006043593748472631 2023-01-23 21:12:51.098511: step: 2044/1545, loss: 0.08607496321201324 2023-01-23 21:12:52.034771: step: 2046/1545, loss: 0.0016714358935132623 2023-01-23 21:12:52.914510: step: 2048/1545, loss: 0.0003503095649648458 2023-01-23 21:12:53.822914: step: 2050/1545, loss: 0.08897191286087036 2023-01-23 21:12:54.652977: step: 2052/1545, loss: 0.0001226898020831868 2023-01-23 21:12:55.520571: step: 2054/1545, loss: 0.38741931319236755 2023-01-23 21:12:56.353519: step: 2056/1545, loss: 0.00022238535166252404 2023-01-23 21:12:57.251820: step: 2058/1545, loss: 0.05804657191038132 2023-01-23 21:12:58.154014: step: 2060/1545, loss: 0.0002954035298898816 2023-01-23 21:12:59.018132: step: 2062/1545, loss: 0.0005790893919765949 2023-01-23 21:12:59.940779: step: 2064/1545, loss: 0.04413716867566109 2023-01-23 21:13:00.802133: step: 2066/1545, loss: 0.11867638677358627 2023-01-23 21:13:01.781652: step: 2068/1545, loss: 0.2978849709033966 2023-01-23 21:13:02.652263: step: 2070/1545, loss: 0.007087607868015766 2023-01-23 21:13:03.545228: step: 2072/1545, loss: 0.0023700708989053965 2023-01-23 21:13:04.418332: step: 2074/1545, loss: 0.002088653389364481 2023-01-23 21:13:05.280809: step: 2076/1545, loss: 0.08493184298276901 2023-01-23 21:13:06.149133: step: 2078/1545, loss: 0.18589626252651215 2023-01-23 21:13:07.070599: step: 2080/1545, loss: 0.00022453586279880255 2023-01-23 21:13:07.997471: step: 2082/1545, loss: 0.0004402476188261062 2023-01-23 21:13:08.830737: step: 2084/1545, loss: 0.000185116907232441 2023-01-23 21:13:09.697390: step: 2086/1545, loss: 0.011112546548247337 2023-01-23 21:13:10.531616: step: 2088/1545, loss: 0.00198738113977015 2023-01-23 21:13:11.488946: step: 2090/1545, loss: 0.015764562413096428 2023-01-23 21:13:12.381049: step: 2092/1545, loss: 0.0020020711235702038 2023-01-23 21:13:13.300885: step: 2094/1545, loss: 0.002903170883655548 2023-01-23 21:13:14.241532: step: 2096/1545, loss: 0.00015681450895499438 2023-01-23 21:13:15.158531: step: 2098/1545, loss: 0.0142064169049263 2023-01-23 21:13:16.060053: step: 2100/1545, loss: 0.0005478446837514639 2023-01-23 21:13:16.959870: step: 2102/1545, loss: 0.0013310632202774286 2023-01-23 21:13:17.831436: step: 2104/1545, loss: 0.02245027758181095 2023-01-23 21:13:18.715920: step: 2106/1545, loss: 0.057617463171482086 2023-01-23 21:13:19.569792: step: 2108/1545, loss: 0.005637547001242638 2023-01-23 21:13:20.434062: step: 2110/1545, loss: 0.000544952810741961 2023-01-23 21:13:21.302860: step: 2112/1545, loss: 0.0020433785393834114 2023-01-23 21:13:22.188692: step: 2114/1545, loss: 0.0002341631188755855 2023-01-23 21:13:23.041346: step: 2116/1545, loss: 0.007636105176061392 2023-01-23 21:13:23.939243: step: 2118/1545, loss: 0.041713058948516846 2023-01-23 21:13:24.856271: step: 2120/1545, loss: 1.0862423181533813 2023-01-23 21:13:25.696786: step: 2122/1545, loss: 0.04066629707813263 2023-01-23 21:13:26.582165: step: 2124/1545, loss: 0.00026244448963552713 2023-01-23 21:13:27.516399: step: 2126/1545, loss: 0.8977401852607727 2023-01-23 21:13:28.378797: step: 2128/1545, loss: 0.0009144980576820672 2023-01-23 21:13:29.291741: step: 2130/1545, loss: 0.0007024405058473349 2023-01-23 21:13:30.241759: step: 2132/1545, loss: 0.0038841795176267624 2023-01-23 21:13:31.108873: step: 2134/1545, loss: 0.00013699292321689427 2023-01-23 21:13:31.974907: step: 2136/1545, loss: 0.0014802920632064342 2023-01-23 21:13:32.809716: step: 2138/1545, loss: 0.0002860503736883402 2023-01-23 21:13:33.642257: step: 2140/1545, loss: 6.223692616913468e-05 2023-01-23 21:13:34.527243: step: 2142/1545, loss: 0.0006419796263799071 2023-01-23 21:13:35.391261: step: 2144/1545, loss: 0.0025561018846929073 2023-01-23 21:13:36.230783: step: 2146/1545, loss: 0.4403633177280426 2023-01-23 21:13:37.143218: step: 2148/1545, loss: 0.0058849831111729145 2023-01-23 21:13:38.021642: step: 2150/1545, loss: 0.00017319100152235478 2023-01-23 21:13:38.891275: step: 2152/1545, loss: 0.034839458763599396 2023-01-23 21:13:39.732302: step: 2154/1545, loss: 0.0014405152760446072 2023-01-23 21:13:40.659383: step: 2156/1545, loss: 0.09279448539018631 2023-01-23 21:13:41.513398: step: 2158/1545, loss: 0.0003443380119279027 2023-01-23 21:13:42.373683: step: 2160/1545, loss: 0.00016147346468642354 2023-01-23 21:13:43.258649: step: 2162/1545, loss: 4.096322754776338e-06 2023-01-23 21:13:44.116941: step: 2164/1545, loss: 0.0014099598629400134 2023-01-23 21:13:44.950472: step: 2166/1545, loss: 0.0001426483504474163 2023-01-23 21:13:45.815000: step: 2168/1545, loss: 0.10019984841346741 2023-01-23 21:13:46.684944: step: 2170/1545, loss: 0.0030256095342338085 2023-01-23 21:13:47.545005: step: 2172/1545, loss: 0.0025488242972642183 2023-01-23 21:13:48.420210: step: 2174/1545, loss: 4.421776975505054e-05 2023-01-23 21:13:49.335571: step: 2176/1545, loss: 0.0476558692753315 2023-01-23 21:13:50.183919: step: 2178/1545, loss: 0.0015509622171521187 2023-01-23 21:13:51.061801: step: 2180/1545, loss: 0.3387626111507416 2023-01-23 21:13:51.926688: step: 2182/1545, loss: 0.0008627986535429955 2023-01-23 21:13:52.766528: step: 2184/1545, loss: 4.951949813403189e-05 2023-01-23 21:13:53.604560: step: 2186/1545, loss: 0.005894598551094532 2023-01-23 21:13:54.553072: step: 2188/1545, loss: 0.0006595111335627735 2023-01-23 21:13:55.441187: step: 2190/1545, loss: 0.11285120993852615 2023-01-23 21:13:56.314853: step: 2192/1545, loss: 2.8959511837456375e-05 2023-01-23 21:13:57.198746: step: 2194/1545, loss: 9.430941645405255e-06 2023-01-23 21:13:58.072936: step: 2196/1545, loss: 0.00018364218703936785 2023-01-23 21:13:58.979645: step: 2198/1545, loss: -4.802445255336352e-05 2023-01-23 21:13:59.869368: step: 2200/1545, loss: 0.0017448489088565111 2023-01-23 21:14:00.791429: step: 2202/1545, loss: 3.1419196602655575e-05 2023-01-23 21:14:01.805483: step: 2204/1545, loss: 0.0007404740317724645 2023-01-23 21:14:02.668675: step: 2206/1545, loss: 0.0028953191358596087 2023-01-23 21:14:03.554891: step: 2208/1545, loss: 0.0008794186869636178 2023-01-23 21:14:04.412104: step: 2210/1545, loss: 0.00021043329616077244 2023-01-23 21:14:05.311425: step: 2212/1545, loss: 0.01802932098507881 2023-01-23 21:14:06.217241: step: 2214/1545, loss: 0.00012853302177973092 2023-01-23 21:14:07.052210: step: 2216/1545, loss: 0.1618373990058899 2023-01-23 21:14:07.920114: step: 2218/1545, loss: 0.10131517052650452 2023-01-23 21:14:08.794446: step: 2220/1545, loss: 0.00030731657170690596 2023-01-23 21:14:09.626462: step: 2222/1545, loss: 3.055000343010761e-05 2023-01-23 21:14:10.479784: step: 2224/1545, loss: 0.025523435324430466 2023-01-23 21:14:11.339171: step: 2226/1545, loss: 0.001830104272812605 2023-01-23 21:14:12.253806: step: 2228/1545, loss: 5.0275149988010526e-05 2023-01-23 21:14:13.104607: step: 2230/1545, loss: 0.00011456242646090686 2023-01-23 21:14:13.974717: step: 2232/1545, loss: 0.13283751904964447 2023-01-23 21:14:14.841349: step: 2234/1545, loss: 0.0009427513577975333 2023-01-23 21:14:15.692805: step: 2236/1545, loss: 0.003866913029924035 2023-01-23 21:14:16.549247: step: 2238/1545, loss: 0.007083424367010593 2023-01-23 21:14:17.390896: step: 2240/1545, loss: 0.001287009916268289 2023-01-23 21:14:18.261318: step: 2242/1545, loss: 0.0003421179426368326 2023-01-23 21:14:19.141564: step: 2244/1545, loss: 3.787865352933295e-05 2023-01-23 21:14:20.008167: step: 2246/1545, loss: 0.20481140911579132 2023-01-23 21:14:20.911810: step: 2248/1545, loss: 0.0013555879704654217 2023-01-23 21:14:21.820912: step: 2250/1545, loss: 0.0004833897401113063 2023-01-23 21:14:22.687720: step: 2252/1545, loss: 0.00039535900577902794 2023-01-23 21:14:23.550435: step: 2254/1545, loss: 0.004477938637137413 2023-01-23 21:14:24.428753: step: 2256/1545, loss: 0.0006650349241681397 2023-01-23 21:14:25.296390: step: 2258/1545, loss: 4.4222491851542145e-05 2023-01-23 21:14:26.178644: step: 2260/1545, loss: 0.015279842540621758 2023-01-23 21:14:27.006756: step: 2262/1545, loss: 0.000540047709364444 2023-01-23 21:14:27.865080: step: 2264/1545, loss: 0.008929493837058544 2023-01-23 21:14:28.728476: step: 2266/1545, loss: 0.0004927091067656875 2023-01-23 21:14:29.589959: step: 2268/1545, loss: 0.0058302367106080055 2023-01-23 21:14:30.550014: step: 2270/1545, loss: 0.0026876209303736687 2023-01-23 21:14:31.451296: step: 2272/1545, loss: -1.7989291336562019e-06 2023-01-23 21:14:32.353906: step: 2274/1545, loss: 6.237805791897699e-06 2023-01-23 21:14:33.243016: step: 2276/1545, loss: 0.08540578931570053 2023-01-23 21:14:34.152176: step: 2278/1545, loss: 3.907549398718402e-05 2023-01-23 21:14:35.010321: step: 2280/1545, loss: 0.010692217387259007 2023-01-23 21:14:35.904818: step: 2282/1545, loss: 0.04795169457793236 2023-01-23 21:14:36.802537: step: 2284/1545, loss: 9.89638501778245e-05 2023-01-23 21:14:37.662439: step: 2286/1545, loss: 6.25972606940195e-05 2023-01-23 21:14:38.539168: step: 2288/1545, loss: 2.1726558208465576 2023-01-23 21:14:39.434465: step: 2290/1545, loss: 0.00027678013429977 2023-01-23 21:14:40.304121: step: 2292/1545, loss: 0.09871850162744522 2023-01-23 21:14:41.160958: step: 2294/1545, loss: 0.00022392974642571062 2023-01-23 21:14:42.052968: step: 2296/1545, loss: 0.1420818418264389 2023-01-23 21:14:42.941190: step: 2298/1545, loss: 0.00020466824935283512 2023-01-23 21:14:43.817164: step: 2300/1545, loss: 0.00023918859369587153 2023-01-23 21:14:44.715946: step: 2302/1545, loss: 0.820942223072052 2023-01-23 21:14:45.586386: step: 2304/1545, loss: 0.7587419152259827 2023-01-23 21:14:46.408556: step: 2306/1545, loss: 0.0006702301907353103 2023-01-23 21:14:47.276500: step: 2308/1545, loss: 0.15328988432884216 2023-01-23 21:14:48.181709: step: 2310/1545, loss: 0.0001495635078754276 2023-01-23 21:14:49.041043: step: 2312/1545, loss: 8.958370017353445e-06 2023-01-23 21:14:49.917450: step: 2314/1545, loss: 0.001692174468189478 2023-01-23 21:14:50.858640: step: 2316/1545, loss: 0.010756457224488258 2023-01-23 21:14:51.713317: step: 2318/1545, loss: 0.04162907600402832 2023-01-23 21:14:52.591960: step: 2320/1545, loss: 0.1292436122894287 2023-01-23 21:14:53.499985: step: 2322/1545, loss: 0.15115229785442352 2023-01-23 21:14:54.442474: step: 2324/1545, loss: 0.0006432413938455284 2023-01-23 21:14:55.311984: step: 2326/1545, loss: 0.011642630212008953 2023-01-23 21:14:56.216651: step: 2328/1545, loss: 0.08611787110567093 2023-01-23 21:14:57.093265: step: 2330/1545, loss: 0.0023641420993953943 2023-01-23 21:14:57.981541: step: 2332/1545, loss: 0.019340762868523598 2023-01-23 21:14:58.819256: step: 2334/1545, loss: 0.0004241834976710379 2023-01-23 21:14:59.723589: step: 2336/1545, loss: 0.08141361176967621 2023-01-23 21:15:00.612063: step: 2338/1545, loss: 0.008313489146530628 2023-01-23 21:15:01.432393: step: 2340/1545, loss: 2.1837649910594337e-05 2023-01-23 21:15:02.276602: step: 2342/1545, loss: 0.5417159199714661 2023-01-23 21:15:03.177065: step: 2344/1545, loss: 0.2778804302215576 2023-01-23 21:15:04.054498: step: 2346/1545, loss: 0.009338820353150368 2023-01-23 21:15:04.895059: step: 2348/1545, loss: 0.00044953092583455145 2023-01-23 21:15:05.773092: step: 2350/1545, loss: 0.13138079643249512 2023-01-23 21:15:06.637777: step: 2352/1545, loss: 0.14508932828903198 2023-01-23 21:15:07.544800: step: 2354/1545, loss: 0.0005729614640586078 2023-01-23 21:15:08.485114: step: 2356/1545, loss: 0.032802894711494446 2023-01-23 21:15:09.345394: step: 2358/1545, loss: 0.00013561456580646336 2023-01-23 21:15:10.204572: step: 2360/1545, loss: 0.0060498579405248165 2023-01-23 21:15:11.100103: step: 2362/1545, loss: 0.0008945229928940535 2023-01-23 21:15:11.935981: step: 2364/1545, loss: 0.002297742757946253 2023-01-23 21:15:12.783418: step: 2366/1545, loss: 9.091232641367242e-05 2023-01-23 21:15:13.684843: step: 2368/1545, loss: 0.06436412781476974 2023-01-23 21:15:14.521534: step: 2370/1545, loss: 0.0004908376140519977 2023-01-23 21:15:15.399524: step: 2372/1545, loss: 0.010851294733583927 2023-01-23 21:15:16.272872: step: 2374/1545, loss: 0.010489384643733501 2023-01-23 21:15:17.160498: step: 2376/1545, loss: 0.0008919755928218365 2023-01-23 21:15:17.964310: step: 2378/1545, loss: 0.005719784181565046 2023-01-23 21:15:18.837666: step: 2380/1545, loss: 0.07586425542831421 2023-01-23 21:15:19.734769: step: 2382/1545, loss: 0.013030215166509151 2023-01-23 21:15:20.580271: step: 2384/1545, loss: 0.027365069836378098 2023-01-23 21:15:21.426538: step: 2386/1545, loss: 0.14235147833824158 2023-01-23 21:15:22.319629: step: 2388/1545, loss: 0.03292601555585861 2023-01-23 21:15:23.194013: step: 2390/1545, loss: 0.3828853666782379 2023-01-23 21:15:24.078036: step: 2392/1545, loss: 0.0022241880651563406 2023-01-23 21:15:24.946750: step: 2394/1545, loss: 0.0005612742970697582 2023-01-23 21:15:25.830819: step: 2396/1545, loss: 0.00020733877317979932 2023-01-23 21:15:26.687345: step: 2398/1545, loss: 0.00044131220784038305 2023-01-23 21:15:27.596902: step: 2400/1545, loss: 0.1716269999742508 2023-01-23 21:15:28.510028: step: 2402/1545, loss: 0.0006677782512269914 2023-01-23 21:15:29.417490: step: 2404/1545, loss: 0.0011879553785547614 2023-01-23 21:15:30.306439: step: 2406/1545, loss: 0.0004610552277881652 2023-01-23 21:15:31.233105: step: 2408/1545, loss: 0.0007853679126128554 2023-01-23 21:15:32.105412: step: 2410/1545, loss: 0.007396578323096037 2023-01-23 21:15:33.072155: step: 2412/1545, loss: 0.0006712917820550501 2023-01-23 21:15:33.947509: step: 2414/1545, loss: 0.0008957541431300342 2023-01-23 21:15:34.841934: step: 2416/1545, loss: 0.0005732579156756401 2023-01-23 21:15:35.699643: step: 2418/1545, loss: 3.548927998053841e-05 2023-01-23 21:15:36.590238: step: 2420/1545, loss: 0.0010253714863210917 2023-01-23 21:15:37.425416: step: 2422/1545, loss: 0.0002006351569434628 2023-01-23 21:15:38.310973: step: 2424/1545, loss: 0.11193911731243134 2023-01-23 21:15:39.195968: step: 2426/1545, loss: 0.22343659400939941 2023-01-23 21:15:40.073137: step: 2428/1545, loss: 0.02927209995687008 2023-01-23 21:15:40.969656: step: 2430/1545, loss: 0.00047360488679260015 2023-01-23 21:15:41.843651: step: 2432/1545, loss: 0.015314527787268162 2023-01-23 21:15:42.700874: step: 2434/1545, loss: 0.0028826058842241764 2023-01-23 21:15:43.583454: step: 2436/1545, loss: 0.002320168074220419 2023-01-23 21:15:44.481903: step: 2438/1545, loss: 0.3625751733779907 2023-01-23 21:15:45.359058: step: 2440/1545, loss: 0.00042857465450651944 2023-01-23 21:15:46.270116: step: 2442/1545, loss: 0.21481570601463318 2023-01-23 21:15:47.177758: step: 2444/1545, loss: 9.782120469026268e-05 2023-01-23 21:15:48.036364: step: 2446/1545, loss: 0.20253247022628784 2023-01-23 21:15:48.907621: step: 2448/1545, loss: 0.003023060504347086 2023-01-23 21:15:49.760740: step: 2450/1545, loss: 0.011544009670615196 2023-01-23 21:15:50.606775: step: 2452/1545, loss: 0.04590468853712082 2023-01-23 21:15:51.502780: step: 2454/1545, loss: 0.022973904386162758 2023-01-23 21:15:52.384245: step: 2456/1545, loss: 0.003317803144454956 2023-01-23 21:15:53.245322: step: 2458/1545, loss: 0.00030611883266828954 2023-01-23 21:15:54.116410: step: 2460/1545, loss: 0.020778849720954895 2023-01-23 21:15:55.004689: step: 2462/1545, loss: 0.0013709785416722298 2023-01-23 21:15:55.887537: step: 2464/1545, loss: 0.0009735055500641465 2023-01-23 21:15:56.747041: step: 2466/1545, loss: 0.00292599736712873 2023-01-23 21:15:57.656337: step: 2468/1545, loss: 0.05932450667023659 2023-01-23 21:15:58.500645: step: 2470/1545, loss: 0.7138104438781738 2023-01-23 21:15:59.348659: step: 2472/1545, loss: 0.0027695433236658573 2023-01-23 21:16:00.194327: step: 2474/1545, loss: 0.0036404908169060946 2023-01-23 21:16:01.070586: step: 2476/1545, loss: 0.0009263789397664368 2023-01-23 21:16:01.986098: step: 2478/1545, loss: 0.040157150477170944 2023-01-23 21:16:02.906809: step: 2480/1545, loss: 0.0025303629226982594 2023-01-23 21:16:03.779533: step: 2482/1545, loss: 0.0006690163281746209 2023-01-23 21:16:04.641669: step: 2484/1545, loss: 0.10325631499290466 2023-01-23 21:16:05.504485: step: 2486/1545, loss: 0.0008244695491157472 2023-01-23 21:16:06.427238: step: 2488/1545, loss: 0.00015258863277267665 2023-01-23 21:16:07.315178: step: 2490/1545, loss: 0.0012314782943576574 2023-01-23 21:16:08.226613: step: 2492/1545, loss: 0.02715887688100338 2023-01-23 21:16:09.121097: step: 2494/1545, loss: 0.0022403111215680838 2023-01-23 21:16:10.021389: step: 2496/1545, loss: 2.285696506500244 2023-01-23 21:16:10.857369: step: 2498/1545, loss: 0.0001415752776665613 2023-01-23 21:16:11.700760: step: 2500/1545, loss: 4.7126897698035464e-05 2023-01-23 21:16:12.559469: step: 2502/1545, loss: 0.00023079563106875867 2023-01-23 21:16:13.431158: step: 2504/1545, loss: 1.6910295486450195 2023-01-23 21:16:14.324664: step: 2506/1545, loss: 0.0007330044754780829 2023-01-23 21:16:15.201176: step: 2508/1545, loss: 0.022044548764824867 2023-01-23 21:16:16.099172: step: 2510/1545, loss: 0.0006769100436940789 2023-01-23 21:16:16.989649: step: 2512/1545, loss: 0.01258699782192707 2023-01-23 21:16:17.839171: step: 2514/1545, loss: 0.00017609892529435456 2023-01-23 21:16:18.727968: step: 2516/1545, loss: 0.0001450068230042234 2023-01-23 21:16:19.541246: step: 2518/1545, loss: 0.000999364536255598 2023-01-23 21:16:20.413656: step: 2520/1545, loss: 0.0001458643819205463 2023-01-23 21:16:21.325931: step: 2522/1545, loss: 0.0004407395899761468 2023-01-23 21:16:22.192973: step: 2524/1545, loss: 0.00028443842893466353 2023-01-23 21:16:23.098280: step: 2526/1545, loss: 0.004258940927684307 2023-01-23 21:16:23.956078: step: 2528/1545, loss: 0.15524159371852875 2023-01-23 21:16:24.860990: step: 2530/1545, loss: 0.126416876912117 2023-01-23 21:16:25.738014: step: 2532/1545, loss: 0.00018550695676822215 2023-01-23 21:16:26.583146: step: 2534/1545, loss: 0.0004212133935652673 2023-01-23 21:16:27.463959: step: 2536/1545, loss: 0.0019132684683427215 2023-01-23 21:16:28.368364: step: 2538/1545, loss: 0.001200202270410955 2023-01-23 21:16:29.302121: step: 2540/1545, loss: 0.04231932386755943 2023-01-23 21:16:30.182563: step: 2542/1545, loss: 0.0018712060991674662 2023-01-23 21:16:31.095461: step: 2544/1545, loss: 0.0012439732672646642 2023-01-23 21:16:31.944477: step: 2546/1545, loss: 0.00019204517593607306 2023-01-23 21:16:32.899615: step: 2548/1545, loss: 0.0010424653301015496 2023-01-23 21:16:33.744849: step: 2550/1545, loss: 3.159537664032541e-05 2023-01-23 21:16:34.621044: step: 2552/1545, loss: 0.0005767402471974492 2023-01-23 21:16:35.498709: step: 2554/1545, loss: 0.0003938724403269589 2023-01-23 21:16:36.366406: step: 2556/1545, loss: 0.051166921854019165 2023-01-23 21:16:37.254603: step: 2558/1545, loss: 0.06291908770799637 2023-01-23 21:16:38.144694: step: 2560/1545, loss: 0.00034670508466660976 2023-01-23 21:16:38.998884: step: 2562/1545, loss: 0.00010899452900048345 2023-01-23 21:16:39.912334: step: 2564/1545, loss: 0.7541772127151489 2023-01-23 21:16:40.808309: step: 2566/1545, loss: 0.017070049419999123 2023-01-23 21:16:41.713492: step: 2568/1545, loss: 0.548876166343689 2023-01-23 21:16:42.574268: step: 2570/1545, loss: 0.0011410085717216134 2023-01-23 21:16:43.428779: step: 2572/1545, loss: 0.0004231907951179892 2023-01-23 21:16:44.362390: step: 2574/1545, loss: 0.0004998511867597699 2023-01-23 21:16:45.250793: step: 2576/1545, loss: 0.09008084237575531 2023-01-23 21:16:46.145646: step: 2578/1545, loss: 0.2812052369117737 2023-01-23 21:16:47.042212: step: 2580/1545, loss: 7.342866592807695e-05 2023-01-23 21:16:47.920687: step: 2582/1545, loss: 0.018179113045334816 2023-01-23 21:16:48.769426: step: 2584/1545, loss: 0.01454545184969902 2023-01-23 21:16:49.668157: step: 2586/1545, loss: 0.027149135246872902 2023-01-23 21:16:50.528702: step: 2588/1545, loss: 0.025276266038417816 2023-01-23 21:16:51.467591: step: 2590/1545, loss: 0.0014760956401005387 2023-01-23 21:16:52.390305: step: 2592/1545, loss: 0.00022432405967265368 2023-01-23 21:16:53.220386: step: 2594/1545, loss: 0.000978089403361082 2023-01-23 21:16:54.092568: step: 2596/1545, loss: 4.4882766815135255e-05 2023-01-23 21:16:54.957094: step: 2598/1545, loss: 0.0009034745744429529 2023-01-23 21:16:55.850032: step: 2600/1545, loss: 0.019006188958883286 2023-01-23 21:16:56.713744: step: 2602/1545, loss: 0.07592855393886566 2023-01-23 21:16:57.609567: step: 2604/1545, loss: 0.001185683999210596 2023-01-23 21:16:58.514777: step: 2606/1545, loss: 0.00014956445374991745 2023-01-23 21:16:59.432739: step: 2608/1545, loss: 0.25153034925460815 2023-01-23 21:17:00.306535: step: 2610/1545, loss: 0.0011784519301727414 2023-01-23 21:17:01.257462: step: 2612/1545, loss: 7.982767419889569e-05 2023-01-23 21:17:02.151500: step: 2614/1545, loss: 0.00112101249396801 2023-01-23 21:17:03.009681: step: 2616/1545, loss: 0.017843114212155342 2023-01-23 21:17:03.890641: step: 2618/1545, loss: 0.0015024165622889996 2023-01-23 21:17:04.762139: step: 2620/1545, loss: 6.602369830943644e-05 2023-01-23 21:17:05.609782: step: 2622/1545, loss: 0.00026629865169525146 2023-01-23 21:17:06.546878: step: 2624/1545, loss: 0.00027879432309418917 2023-01-23 21:17:07.461745: step: 2626/1545, loss: 0.003625385696068406 2023-01-23 21:17:08.354622: step: 2628/1545, loss: 0.0031843828037381172 2023-01-23 21:17:09.252064: step: 2630/1545, loss: 0.0001442879729438573 2023-01-23 21:17:10.145417: step: 2632/1545, loss: 0.8152688145637512 2023-01-23 21:17:11.010811: step: 2634/1545, loss: 0.1454143077135086 2023-01-23 21:17:11.857392: step: 2636/1545, loss: 0.002161273965612054 2023-01-23 21:17:12.742489: step: 2638/1545, loss: 0.0012218093033879995 2023-01-23 21:17:13.593636: step: 2640/1545, loss: 0.013988500460982323 2023-01-23 21:17:14.446771: step: 2642/1545, loss: 0.0008007517899386585 2023-01-23 21:17:15.316023: step: 2644/1545, loss: 0.0002313973818672821 2023-01-23 21:17:16.212694: step: 2646/1545, loss: 0.028616461902856827 2023-01-23 21:17:17.057138: step: 2648/1545, loss: 0.008069153875112534 2023-01-23 21:17:17.910174: step: 2650/1545, loss: 0.011498787440359592 2023-01-23 21:17:18.828580: step: 2652/1545, loss: 0.0002656555734574795 2023-01-23 21:17:19.700782: step: 2654/1545, loss: 0.0027053984813392162 2023-01-23 21:17:20.578146: step: 2656/1545, loss: 0.0003208923153579235 2023-01-23 21:17:21.484166: step: 2658/1545, loss: 0.13746720552444458 2023-01-23 21:17:22.327506: step: 2660/1545, loss: 0.00010293092782376334 2023-01-23 21:17:23.223810: step: 2662/1545, loss: 0.0024110455997288227 2023-01-23 21:17:24.066009: step: 2664/1545, loss: 0.0012640395434573293 2023-01-23 21:17:24.926984: step: 2666/1545, loss: 7.539223588537425e-05 2023-01-23 21:17:25.811960: step: 2668/1545, loss: 0.01340729370713234 2023-01-23 21:17:26.670814: step: 2670/1545, loss: 0.6993021368980408 2023-01-23 21:17:27.540700: step: 2672/1545, loss: 0.012202517129480839 2023-01-23 21:17:28.401333: step: 2674/1545, loss: 0.18538320064544678 2023-01-23 21:17:29.296189: step: 2676/1545, loss: 0.0013843468623235822 2023-01-23 21:17:30.180440: step: 2678/1545, loss: 0.011308716610074043 2023-01-23 21:17:31.051163: step: 2680/1545, loss: 0.00023870044969953597 2023-01-23 21:17:31.911940: step: 2682/1545, loss: 0.002041787141934037 2023-01-23 21:17:32.902485: step: 2684/1545, loss: 7.506214024033397e-05 2023-01-23 21:17:33.775665: step: 2686/1545, loss: 0.0012477664276957512 2023-01-23 21:17:34.620845: step: 2688/1545, loss: 0.013101624324917793 2023-01-23 21:17:35.590671: step: 2690/1545, loss: 0.00029464586987160146 2023-01-23 21:17:36.460911: step: 2692/1545, loss: 0.0001613785425433889 2023-01-23 21:17:37.350383: step: 2694/1545, loss: 9.25125932553783e-05 2023-01-23 21:17:38.263561: step: 2696/1545, loss: 0.0005087126628495753 2023-01-23 21:17:39.100457: step: 2698/1545, loss: 0.0005497892270796001 2023-01-23 21:17:39.962931: step: 2700/1545, loss: 0.366482138633728 2023-01-23 21:17:40.908720: step: 2702/1545, loss: 0.0002568609197624028 2023-01-23 21:17:41.739523: step: 2704/1545, loss: 0.01292989868670702 2023-01-23 21:17:42.570473: step: 2706/1545, loss: 0.013336858712136745 2023-01-23 21:17:43.449367: step: 2708/1545, loss: 0.06321381777524948 2023-01-23 21:17:44.292030: step: 2710/1545, loss: 0.0005383819225244224 2023-01-23 21:17:45.169374: step: 2712/1545, loss: 0.05539996549487114 2023-01-23 21:17:46.044794: step: 2714/1545, loss: 0.00012944985064677894 2023-01-23 21:17:46.911516: step: 2716/1545, loss: 0.041695959866046906 2023-01-23 21:17:47.808197: step: 2718/1545, loss: 0.0011050840839743614 2023-01-23 21:17:48.649767: step: 2720/1545, loss: 0.000562713947147131 2023-01-23 21:17:49.560419: step: 2722/1545, loss: 0.002374304225668311 2023-01-23 21:17:50.434820: step: 2724/1545, loss: 0.028634624555706978 2023-01-23 21:17:51.277088: step: 2726/1545, loss: 0.0008442680700682104 2023-01-23 21:17:52.206165: step: 2728/1545, loss: 2.0853289242950268e-05 2023-01-23 21:17:53.091507: step: 2730/1545, loss: 0.011236799880862236 2023-01-23 21:17:53.955973: step: 2732/1545, loss: 0.0006627356051467359 2023-01-23 21:17:54.867116: step: 2734/1545, loss: 0.0005681433249264956 2023-01-23 21:17:55.715522: step: 2736/1545, loss: 0.00020626182958949357 2023-01-23 21:17:56.599865: step: 2738/1545, loss: 0.12416405230760574 2023-01-23 21:17:57.452952: step: 2740/1545, loss: 0.00975716020911932 2023-01-23 21:17:58.352629: step: 2742/1545, loss: 0.00031737415702082217 2023-01-23 21:17:59.244965: step: 2744/1545, loss: 0.01522600557655096 2023-01-23 21:18:00.132429: step: 2746/1545, loss: 0.0034070226829499006 2023-01-23 21:18:01.027798: step: 2748/1545, loss: 3.0501025321427733e-05 2023-01-23 21:18:01.934992: step: 2750/1545, loss: 0.00011005596024915576 2023-01-23 21:18:02.806774: step: 2752/1545, loss: 0.00011456264473963529 2023-01-23 21:18:03.703525: step: 2754/1545, loss: 0.19778969883918762 2023-01-23 21:18:04.578419: step: 2756/1545, loss: 9.103090633288957e-06 2023-01-23 21:18:05.449633: step: 2758/1545, loss: 0.11275880038738251 2023-01-23 21:18:06.337257: step: 2760/1545, loss: 0.12049572914838791 2023-01-23 21:18:07.216251: step: 2762/1545, loss: 0.17699897289276123 2023-01-23 21:18:08.069187: step: 2764/1545, loss: 0.005477226339280605 2023-01-23 21:18:08.962239: step: 2766/1545, loss: 9.961272735381499e-05 2023-01-23 21:18:09.845442: step: 2768/1545, loss: 0.0012831164058297873 2023-01-23 21:18:10.713452: step: 2770/1545, loss: 0.1815224140882492 2023-01-23 21:18:11.578096: step: 2772/1545, loss: 0.006389941554516554 2023-01-23 21:18:12.480748: step: 2774/1545, loss: 0.18483324348926544 2023-01-23 21:18:13.414010: step: 2776/1545, loss: 0.0010185432620346546 2023-01-23 21:18:14.280186: step: 2778/1545, loss: 0.00022611915483139455 2023-01-23 21:18:15.143110: step: 2780/1545, loss: 3.024616489710752e-05 2023-01-23 21:18:16.025651: step: 2782/1545, loss: 0.2801095247268677 2023-01-23 21:18:16.918401: step: 2784/1545, loss: 0.0015312545001506805 2023-01-23 21:18:17.818970: step: 2786/1545, loss: 0.00014830470900051296 2023-01-23 21:18:18.668456: step: 2788/1545, loss: 9.505293564870954e-05 2023-01-23 21:18:19.604142: step: 2790/1545, loss: 0.0039031794294714928 2023-01-23 21:18:20.459228: step: 2792/1545, loss: 0.002829355886206031 2023-01-23 21:18:21.316293: step: 2794/1545, loss: 5.9019625041401014e-05 2023-01-23 21:18:22.245159: step: 2796/1545, loss: 0.001438757637515664 2023-01-23 21:18:23.119700: step: 2798/1545, loss: 0.1652633547782898 2023-01-23 21:18:23.969305: step: 2800/1545, loss: 0.0009635730530135334 2023-01-23 21:18:24.858267: step: 2802/1545, loss: 0.0016756306868046522 2023-01-23 21:18:25.729840: step: 2804/1545, loss: 0.004222471732646227 2023-01-23 21:18:26.631049: step: 2806/1545, loss: 0.21458853781223297 2023-01-23 21:18:27.462744: step: 2808/1545, loss: 0.007649286650121212 2023-01-23 21:18:28.378063: step: 2810/1545, loss: 0.04635241627693176 2023-01-23 21:18:29.310849: step: 2812/1545, loss: 0.17417815327644348 2023-01-23 21:18:30.280104: step: 2814/1545, loss: 7.335605914704502e-05 2023-01-23 21:18:31.185083: step: 2816/1545, loss: 0.007723081856966019 2023-01-23 21:18:32.066871: step: 2818/1545, loss: 0.0001130735399783589 2023-01-23 21:18:32.938961: step: 2820/1545, loss: 0.03828055039048195 2023-01-23 21:18:33.827344: step: 2822/1545, loss: 0.0679558590054512 2023-01-23 21:18:34.708610: step: 2824/1545, loss: 0.004717822652310133 2023-01-23 21:18:35.576381: step: 2826/1545, loss: 0.038831476122140884 2023-01-23 21:18:36.477974: step: 2828/1545, loss: 0.0019615530036389828 2023-01-23 21:18:37.364303: step: 2830/1545, loss: 0.006766477134078741 2023-01-23 21:18:38.222947: step: 2832/1545, loss: 3.204196400474757e-05 2023-01-23 21:18:39.091248: step: 2834/1545, loss: 3.0786253773840144e-05 2023-01-23 21:18:40.000221: step: 2836/1545, loss: 9.018820855999365e-05 2023-01-23 21:18:40.865400: step: 2838/1545, loss: 0.0035352359991520643 2023-01-23 21:18:41.783348: step: 2840/1545, loss: 0.00014801423822063953 2023-01-23 21:18:42.587793: step: 2842/1545, loss: 0.0001730924705043435 2023-01-23 21:18:43.469763: step: 2844/1545, loss: 0.4419403672218323 2023-01-23 21:18:44.326687: step: 2846/1545, loss: 1.4412146811082494e-05 2023-01-23 21:18:45.195630: step: 2848/1545, loss: 4.871083365287632e-05 2023-01-23 21:18:46.123802: step: 2850/1545, loss: 0.22512182593345642 2023-01-23 21:18:46.979820: step: 2852/1545, loss: 0.00022870949760545045 2023-01-23 21:18:47.831036: step: 2854/1545, loss: 0.00015676890325266868 2023-01-23 21:18:48.692135: step: 2856/1545, loss: 0.0015417017275467515 2023-01-23 21:18:49.634932: step: 2858/1545, loss: 0.0013454806758090854 2023-01-23 21:18:50.514811: step: 2860/1545, loss: 0.11675815284252167 2023-01-23 21:18:51.375392: step: 2862/1545, loss: 6.385859160218388e-05 2023-01-23 21:18:52.242130: step: 2864/1545, loss: 5.224644337431528e-05 2023-01-23 21:18:53.128407: step: 2866/1545, loss: 0.18793153762817383 2023-01-23 21:18:54.029592: step: 2868/1545, loss: 0.0007052377914078534 2023-01-23 21:18:54.896356: step: 2870/1545, loss: 0.01785706914961338 2023-01-23 21:18:55.753728: step: 2872/1545, loss: 3.385369200259447e-05 2023-01-23 21:18:56.591843: step: 2874/1545, loss: 0.00025414544506929815 2023-01-23 21:18:57.483901: step: 2876/1545, loss: 0.1705479919910431 2023-01-23 21:18:58.515387: step: 2878/1545, loss: -8.289660399896093e-06 2023-01-23 21:18:59.362592: step: 2880/1545, loss: 0.02412450686097145 2023-01-23 21:19:00.243505: step: 2882/1545, loss: 0.04518367350101471 2023-01-23 21:19:01.114910: step: 2884/1545, loss: 0.00011945227743126452 2023-01-23 21:19:02.020032: step: 2886/1545, loss: 0.00021327089052647352 2023-01-23 21:19:02.882033: step: 2888/1545, loss: 8.065639121923596e-06 2023-01-23 21:19:03.755830: step: 2890/1545, loss: 0.570713460445404 2023-01-23 21:19:04.702678: step: 2892/1545, loss: 6.96920687914826e-05 2023-01-23 21:19:05.633403: step: 2894/1545, loss: 0.011924583464860916 2023-01-23 21:19:06.503610: step: 2896/1545, loss: 0.35723933577537537 2023-01-23 21:19:07.509367: step: 2898/1545, loss: 0.4563106298446655 2023-01-23 21:19:08.406956: step: 2900/1545, loss: 0.000568985182326287 2023-01-23 21:19:09.250232: step: 2902/1545, loss: 0.0053561655804514885 2023-01-23 21:19:10.107667: step: 2904/1545, loss: 0.0015995957655832171 2023-01-23 21:19:10.946693: step: 2906/1545, loss: 0.00017356622265651822 2023-01-23 21:19:11.836150: step: 2908/1545, loss: 0.0005430729943327606 2023-01-23 21:19:12.733491: step: 2910/1545, loss: 6.010883953422308e-05 2023-01-23 21:19:13.650383: step: 2912/1545, loss: 0.0034822216257452965 2023-01-23 21:19:14.549780: step: 2914/1545, loss: 0.0002653747797012329 2023-01-23 21:19:15.465670: step: 2916/1545, loss: 0.000759866030421108 2023-01-23 21:19:16.335126: step: 2918/1545, loss: 0.0010255599627271295 2023-01-23 21:19:17.206751: step: 2920/1545, loss: 0.015997029840946198 2023-01-23 21:19:18.101895: step: 2922/1545, loss: 0.0007363601471297443 2023-01-23 21:19:18.984161: step: 2924/1545, loss: 0.01192107517272234 2023-01-23 21:19:19.876103: step: 2926/1545, loss: 0.001282842829823494 2023-01-23 21:19:20.803236: step: 2928/1545, loss: 0.0007220108527690172 2023-01-23 21:19:21.717055: step: 2930/1545, loss: 0.004391366150230169 2023-01-23 21:19:22.592113: step: 2932/1545, loss: 0.0012702641543000937 2023-01-23 21:19:23.432916: step: 2934/1545, loss: 0.009206203743815422 2023-01-23 21:19:24.333951: step: 2936/1545, loss: 0.0004262964357621968 2023-01-23 21:19:25.197940: step: 2938/1545, loss: 0.013177922926843166 2023-01-23 21:19:26.047640: step: 2940/1545, loss: 0.001198147889226675 2023-01-23 21:19:26.924069: step: 2942/1545, loss: 0.00021472723165061325 2023-01-23 21:19:27.775023: step: 2944/1545, loss: 0.0003107112424913794 2023-01-23 21:19:28.678152: step: 2946/1545, loss: 0.13273847103118896 2023-01-23 21:19:29.527336: step: 2948/1545, loss: 0.0025365548208355904 2023-01-23 21:19:30.426970: step: 2950/1545, loss: 0.004296726081520319 2023-01-23 21:19:31.342322: step: 2952/1545, loss: 0.14798282086849213 2023-01-23 21:19:32.209103: step: 2954/1545, loss: 0.034770138561725616 2023-01-23 21:19:33.088077: step: 2956/1545, loss: 0.0012211950961500406 2023-01-23 21:19:33.983952: step: 2958/1545, loss: 0.0006648129201494157 2023-01-23 21:19:34.838654: step: 2960/1545, loss: 0.00016139722720254213 2023-01-23 21:19:35.719288: step: 2962/1545, loss: 0.08199377357959747 2023-01-23 21:19:36.585686: step: 2964/1545, loss: 0.003350240411236882 2023-01-23 21:19:37.477639: step: 2966/1545, loss: 7.883372018113732e-05 2023-01-23 21:19:38.340585: step: 2968/1545, loss: 0.1412833034992218 2023-01-23 21:19:39.263398: step: 2970/1545, loss: 0.2077115923166275 2023-01-23 21:19:40.129756: step: 2972/1545, loss: 0.00016722235886845738 2023-01-23 21:19:41.008800: step: 2974/1545, loss: 0.19312970340251923 2023-01-23 21:19:41.858219: step: 2976/1545, loss: 0.0004678999539464712 2023-01-23 21:19:42.754309: step: 2978/1545, loss: 0.29652392864227295 2023-01-23 21:19:43.613471: step: 2980/1545, loss: 0.000575935177039355 2023-01-23 21:19:44.464561: step: 2982/1545, loss: 0.11504729092121124 2023-01-23 21:19:45.337833: step: 2984/1545, loss: 0.0003214285825379193 2023-01-23 21:19:46.211303: step: 2986/1545, loss: 0.20554082095623016 2023-01-23 21:19:47.136031: step: 2988/1545, loss: 0.078077033162117 2023-01-23 21:19:48.000166: step: 2990/1545, loss: 0.028872257098555565 2023-01-23 21:19:48.947180: step: 2992/1545, loss: 0.012339497916400433 2023-01-23 21:19:49.795445: step: 2994/1545, loss: 0.005798084195703268 2023-01-23 21:19:50.712727: step: 2996/1545, loss: 0.02774524688720703 2023-01-23 21:19:51.602113: step: 2998/1545, loss: 0.10368822515010834 2023-01-23 21:19:52.416801: step: 3000/1545, loss: 6.94232658133842e-05 2023-01-23 21:19:53.290486: step: 3002/1545, loss: 8.823721873341128e-05 2023-01-23 21:19:54.176594: step: 3004/1545, loss: 0.8575794100761414 2023-01-23 21:19:55.149898: step: 3006/1545, loss: 0.00016468216199427843 2023-01-23 21:19:56.051776: step: 3008/1545, loss: 0.0019427817314863205 2023-01-23 21:19:56.925150: step: 3010/1545, loss: 0.001311097526922822 2023-01-23 21:19:57.820914: step: 3012/1545, loss: 0.00011111200001323596 2023-01-23 21:19:58.695593: step: 3014/1545, loss: 0.09533243626356125 2023-01-23 21:19:59.570223: step: 3016/1545, loss: 0.040155164897441864 2023-01-23 21:20:00.535901: step: 3018/1545, loss: 0.0001694637758191675 2023-01-23 21:20:01.428581: step: 3020/1545, loss: 0.0002778321213554591 2023-01-23 21:20:02.375460: step: 3022/1545, loss: 0.003670636797323823 2023-01-23 21:20:03.241664: step: 3024/1545, loss: 0.00016981562657747418 2023-01-23 21:20:04.138201: step: 3026/1545, loss: 0.2442682683467865 2023-01-23 21:20:04.980196: step: 3028/1545, loss: 0.0011259838938713074 2023-01-23 21:20:05.816568: step: 3030/1545, loss: 4.111824819119647e-05 2023-01-23 21:20:06.668606: step: 3032/1545, loss: 0.006022356450557709 2023-01-23 21:20:07.612796: step: 3034/1545, loss: 0.8894954919815063 2023-01-23 21:20:08.471308: step: 3036/1545, loss: 0.00024279400531668216 2023-01-23 21:20:09.321597: step: 3038/1545, loss: 0.043356455862522125 2023-01-23 21:20:10.218797: step: 3040/1545, loss: 0.00033165785134769976 2023-01-23 21:20:11.207953: step: 3042/1545, loss: 0.0014216701965779066 2023-01-23 21:20:12.111720: step: 3044/1545, loss: 7.128570723580196e-05 2023-01-23 21:20:12.986911: step: 3046/1545, loss: 0.0033916723914444447 2023-01-23 21:20:13.833986: step: 3048/1545, loss: 3.6506848118733615e-05 2023-01-23 21:20:14.685926: step: 3050/1545, loss: 0.00018360759713687003 2023-01-23 21:20:15.582381: step: 3052/1545, loss: 0.11354748159646988 2023-01-23 21:20:16.479956: step: 3054/1545, loss: 0.008440027944743633 2023-01-23 21:20:17.334794: step: 3056/1545, loss: 1.3701862371817697e-05 2023-01-23 21:20:18.198216: step: 3058/1545, loss: 0.0810147151350975 2023-01-23 21:20:19.078059: step: 3060/1545, loss: 0.05255899578332901 2023-01-23 21:20:19.960520: step: 3062/1545, loss: 0.00013221503468230367 2023-01-23 21:20:20.827430: step: 3064/1545, loss: 3.47294844686985e-05 2023-01-23 21:20:21.738498: step: 3066/1545, loss: 0.1940745860338211 2023-01-23 21:20:22.578983: step: 3068/1545, loss: 0.000458867521956563 2023-01-23 21:20:23.445730: step: 3070/1545, loss: 0.1331682950258255 2023-01-23 21:20:24.300252: step: 3072/1545, loss: 0.0001653057843213901 2023-01-23 21:20:25.191236: step: 3074/1545, loss: 0.05594516545534134 2023-01-23 21:20:26.065544: step: 3076/1545, loss: 0.027075180783867836 2023-01-23 21:20:26.951082: step: 3078/1545, loss: 0.03286608308553696 2023-01-23 21:20:27.768697: step: 3080/1545, loss: 0.11180433630943298 2023-01-23 21:20:28.644771: step: 3082/1545, loss: 0.013995649293065071 2023-01-23 21:20:29.526700: step: 3084/1545, loss: 0.0820547565817833 2023-01-23 21:20:30.407914: step: 3086/1545, loss: 0.0001297267444897443 2023-01-23 21:20:31.287441: step: 3088/1545, loss: 4.4712418457493186e-05 2023-01-23 21:20:32.143409: step: 3090/1545, loss: 0.024229073897004128 ================================================== Loss: 0.059 -------------------- Dev Chinese: {'event': {'p': 0.604143947655398, 'r': 0.7376830892143809, 'f1': 0.6642685851318945}, 'argument': {'p': 0.692643354981853, 'r': 0.6418356837331842, 'f1': 0.666272318156592}, 'combined': 0.44258377009442684, 'epoch': 34} Test Chinese: {'event': {'p': 0.6398078975453575, 'r': 0.7666240409207161, 'f1': 0.6974985456660848}, 'argument': {'p': 0.7283177912220395, 'r': 0.6999417733822199, 'f1': 0.7138479013302109}, 'combined': 0.4979078730046089, 'epoch': 34} Dev Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.6949801740994155, 'r': 0.6400306874424587, 'f1': 0.666374561288581}, 'combined': 0.4442497075257206, 'epoch': 34} Test Korean: {'event': {'p': 0.6328042328042328, 'r': 0.7647058823529411, 'f1': 0.6925303995367689}, 'argument': {'p': 0.7233338635735137, 'r': 0.6959913463937589, 'f1': 0.70939923572884}, 'combined': 0.49128053615037204, 'epoch': 34} Dev Russian: {'event': {'p': 0.5708661417322834, 'r': 0.7723035952063915, 'f1': 0.656479909451047}, 'argument': {'p': 0.6868872536107843, 'r': 0.6485630720788521, 'f1': 0.6671752573702983}, 'combined': 0.43798715254643233, 'epoch': 34} Test Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7334263866419518, 'r': 0.7108932417544883, 'f1': 0.7219840419492881}, 'combined': 0.509493079168918, 'epoch': 34} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7149041434755721, 'r': 0.5790132732281493, 'f1': 0.639822886398229}, 'combined': 0.45563144940479944, 'epoch': 34} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.7491556906450524, 'r': 0.49591996422982343, 'f1': 0.596785041700296}, 'combined': 0.3664469554300063, 'epoch': 34} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5787600329172, 'r': 0.5064150288025501, 'f1': 0.5401760307227199}, 'combined': 0.30085753609873006, 'epoch': 34} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6758987924276707, 'r': 0.6414709887684336, 'f1': 0.6582350269068861}, 'combined': 0.43408784748056034, 'epoch': 33} Test for Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7201409239897084, 'r': 0.7110669833666995, 'f1': 0.7155751890249322}, 'combined': 0.49952892776609586, 'epoch': 33} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7175290642271774, 'r': 0.6285791802320727, 'f1': 0.6701152494104036}, 'combined': 0.4772032836710449, 'epoch': 33} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 35 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 21:25:42.842224: step: 2/1545, loss: 5.040541145717725e-05 2023-01-23 21:25:43.835928: step: 4/1545, loss: 0.13711418211460114 2023-01-23 21:25:44.707302: step: 6/1545, loss: 0.13833855092525482 2023-01-23 21:25:45.570281: step: 8/1545, loss: 3.8700527511537075e-05 2023-01-23 21:25:46.427285: step: 10/1545, loss: 0.0016633578343316913 2023-01-23 21:25:47.304082: step: 12/1545, loss: 1.1907724142074585 2023-01-23 21:25:48.170587: step: 14/1545, loss: 0.004788549151271582 2023-01-23 21:25:49.083587: step: 16/1545, loss: 0.0010091199073940516 2023-01-23 21:25:50.038061: step: 18/1545, loss: 0.00012225423415657133 2023-01-23 21:25:50.894672: step: 20/1545, loss: -6.983679668337572e-06 2023-01-23 21:25:51.798722: step: 22/1545, loss: 0.0007519216160289943 2023-01-23 21:25:52.662596: step: 24/1545, loss: 0.0021949775982648134 2023-01-23 21:25:53.516288: step: 26/1545, loss: 1.4517705494654365e-05 2023-01-23 21:25:54.358991: step: 28/1545, loss: 0.0005313888541422784 2023-01-23 21:25:55.269302: step: 30/1545, loss: 0.0008807789999991655 2023-01-23 21:25:56.174095: step: 32/1545, loss: 0.000600870349444449 2023-01-23 21:25:57.085201: step: 34/1545, loss: 0.024078859016299248 2023-01-23 21:25:57.961378: step: 36/1545, loss: 0.0001013085784506984 2023-01-23 21:25:58.835314: step: 38/1545, loss: 0.0023916333448141813 2023-01-23 21:25:59.689591: step: 40/1545, loss: 0.03748514875769615 2023-01-23 21:26:00.574237: step: 42/1545, loss: 0.01957590878009796 2023-01-23 21:26:01.493734: step: 44/1545, loss: 0.00041911762673407793 2023-01-23 21:26:02.377450: step: 46/1545, loss: 3.7712601624662057e-05 2023-01-23 21:26:03.252395: step: 48/1545, loss: 0.00015831067867111415 2023-01-23 21:26:04.118724: step: 50/1545, loss: 0.0030582956969738007 2023-01-23 21:26:04.994434: step: 52/1545, loss: 0.8544248342514038 2023-01-23 21:26:05.868033: step: 54/1545, loss: 0.004128774628043175 2023-01-23 21:26:06.762964: step: 56/1545, loss: 0.0003719298983924091 2023-01-23 21:26:07.619748: step: 58/1545, loss: 0.004826059564948082 2023-01-23 21:26:08.569706: step: 60/1545, loss: 0.0011775405146181583 2023-01-23 21:26:09.438066: step: 62/1545, loss: 0.00017357681645080447 2023-01-23 21:26:10.326342: step: 64/1545, loss: 0.002032480202615261 2023-01-23 21:26:11.216156: step: 66/1545, loss: 0.5108071565628052 2023-01-23 21:26:12.127894: step: 68/1545, loss: 0.0008191301021724939 2023-01-23 21:26:13.005696: step: 70/1545, loss: 0.07849380373954773 2023-01-23 21:26:13.903078: step: 72/1545, loss: 0.05767017975449562 2023-01-23 21:26:14.801640: step: 74/1545, loss: 0.023197218775749207 2023-01-23 21:26:15.695480: step: 76/1545, loss: 0.0024087391793727875 2023-01-23 21:26:16.511465: step: 78/1545, loss: 0.00025279223336838186 2023-01-23 21:26:17.352917: step: 80/1545, loss: 0.05712933838367462 2023-01-23 21:26:18.230963: step: 82/1545, loss: 0.000325204455293715 2023-01-23 21:26:19.099782: step: 84/1545, loss: 0.029126370325684547 2023-01-23 21:26:19.996829: step: 86/1545, loss: 0.11854971200227737 2023-01-23 21:26:20.853819: step: 88/1545, loss: 0.00033321045339107513 2023-01-23 21:26:21.695831: step: 90/1545, loss: 0.0002860786917153746 2023-01-23 21:26:22.541249: step: 92/1545, loss: 0.050408005714416504 2023-01-23 21:26:23.387604: step: 94/1545, loss: 0.0001014071749523282 2023-01-23 21:26:24.297708: step: 96/1545, loss: 6.660610233666375e-05 2023-01-23 21:26:25.121182: step: 98/1545, loss: 0.12159111350774765 2023-01-23 21:26:25.990086: step: 100/1545, loss: 0.000703659316059202 2023-01-23 21:26:26.869224: step: 102/1545, loss: 0.009500071406364441 2023-01-23 21:26:27.834025: step: 104/1545, loss: 0.0004242817813064903 2023-01-23 21:26:28.740412: step: 106/1545, loss: 8.260306640295312e-05 2023-01-23 21:26:29.571469: step: 108/1545, loss: 0.0007391546969301999 2023-01-23 21:26:30.427032: step: 110/1545, loss: 0.00040574787999503314 2023-01-23 21:26:31.319559: step: 112/1545, loss: 0.0002608934009913355 2023-01-23 21:26:32.252437: step: 114/1545, loss: 0.00033732407609932125 2023-01-23 21:26:33.158706: step: 116/1545, loss: 0.00017024872067850083 2023-01-23 21:26:34.036369: step: 118/1545, loss: 0.0001817635347833857 2023-01-23 21:26:34.939107: step: 120/1545, loss: 0.0002589340729173273 2023-01-23 21:26:35.820477: step: 122/1545, loss: 0.00044114954653196037 2023-01-23 21:26:36.787758: step: 124/1545, loss: 0.012341518886387348 2023-01-23 21:26:37.730917: step: 126/1545, loss: -1.8600636394694448e-05 2023-01-23 21:26:38.597658: step: 128/1545, loss: 0.00011710689432220533 2023-01-23 21:26:39.438114: step: 130/1545, loss: 0.08825154602527618 2023-01-23 21:26:40.335621: step: 132/1545, loss: 5.395217885961756e-05 2023-01-23 21:26:41.224034: step: 134/1545, loss: 0.07568272203207016 2023-01-23 21:26:42.093815: step: 136/1545, loss: 0.00011384013487258926 2023-01-23 21:26:42.951820: step: 138/1545, loss: 0.1871492713689804 2023-01-23 21:26:43.822276: step: 140/1545, loss: 0.07618895918130875 2023-01-23 21:26:44.690014: step: 142/1545, loss: 7.545226981164888e-05 2023-01-23 21:26:45.538167: step: 144/1545, loss: 2.3709833840257488e-05 2023-01-23 21:26:46.416655: step: 146/1545, loss: 0.06689352542161942 2023-01-23 21:26:47.322391: step: 148/1545, loss: 0.08477373421192169 2023-01-23 21:26:48.190525: step: 150/1545, loss: 1.4883878066029865e-05 2023-01-23 21:26:49.075040: step: 152/1545, loss: 0.00011423029354773462 2023-01-23 21:26:50.023768: step: 154/1545, loss: 0.018196510151028633 2023-01-23 21:26:50.884033: step: 156/1545, loss: 0.004260661546140909 2023-01-23 21:26:51.766650: step: 158/1545, loss: 0.10279775410890579 2023-01-23 21:26:52.713257: step: 160/1545, loss: 0.020612038671970367 2023-01-23 21:26:53.555802: step: 162/1545, loss: 0.006555081810802221 2023-01-23 21:26:54.417207: step: 164/1545, loss: 0.00022699122200720012 2023-01-23 21:26:55.278171: step: 166/1545, loss: 4.272740625310689e-05 2023-01-23 21:26:56.161784: step: 168/1545, loss: 0.17884139716625214 2023-01-23 21:26:57.054648: step: 170/1545, loss: 0.0007100275834091008 2023-01-23 21:26:57.896795: step: 172/1545, loss: 7.384912896668538e-05 2023-01-23 21:26:58.782709: step: 174/1545, loss: 0.0003979323955718428 2023-01-23 21:26:59.642023: step: 176/1545, loss: 9.396188397658989e-05 2023-01-23 21:27:00.557855: step: 178/1545, loss: 0.0012470840010792017 2023-01-23 21:27:01.470858: step: 180/1545, loss: 0.23267248272895813 2023-01-23 21:27:02.334301: step: 182/1545, loss: 0.000482911360450089 2023-01-23 21:27:03.214605: step: 184/1545, loss: 9.296496864408255e-05 2023-01-23 21:27:04.069113: step: 186/1545, loss: 0.0303319301456213 2023-01-23 21:27:04.931500: step: 188/1545, loss: 0.001788050984032452 2023-01-23 21:27:05.794361: step: 190/1545, loss: 5.731701821787283e-05 2023-01-23 21:27:06.686993: step: 192/1545, loss: 0.00017202561139129102 2023-01-23 21:27:07.572947: step: 194/1545, loss: 3.897926217177883e-05 2023-01-23 21:27:08.505883: step: 196/1545, loss: 5.9647361922543496e-05 2023-01-23 21:27:09.376486: step: 198/1545, loss: 5.039022653363645e-05 2023-01-23 21:27:10.298679: step: 200/1545, loss: 0.0014780450146645308 2023-01-23 21:27:11.196991: step: 202/1545, loss: 0.01981944404542446 2023-01-23 21:27:12.026158: step: 204/1545, loss: 0.0008089249022305012 2023-01-23 21:27:12.862208: step: 206/1545, loss: 0.06766798347234726 2023-01-23 21:27:13.742440: step: 208/1545, loss: 0.0015507953939959407 2023-01-23 21:27:14.618757: step: 210/1545, loss: 0.0008093392825685441 2023-01-23 21:27:15.477834: step: 212/1545, loss: 0.00038880319334566593 2023-01-23 21:27:16.330654: step: 214/1545, loss: 3.869334250339307e-05 2023-01-23 21:27:17.172087: step: 216/1545, loss: 0.007241846993565559 2023-01-23 21:27:18.048758: step: 218/1545, loss: 4.581362190947402e-06 2023-01-23 21:27:18.968822: step: 220/1545, loss: 0.00010354124242439866 2023-01-23 21:27:19.810816: step: 222/1545, loss: 7.391111722654387e-08 2023-01-23 21:27:20.673745: step: 224/1545, loss: 0.00015049851208459586 2023-01-23 21:27:21.498952: step: 226/1545, loss: 0.0009613044676370919 2023-01-23 21:27:22.447555: step: 228/1545, loss: 0.7394207715988159 2023-01-23 21:27:23.336046: step: 230/1545, loss: 0.0016548375133424997 2023-01-23 21:27:24.195881: step: 232/1545, loss: -8.455484930891544e-06 2023-01-23 21:27:25.032085: step: 234/1545, loss: 2.8916932933498174e-05 2023-01-23 21:27:25.912083: step: 236/1545, loss: 0.8099921345710754 2023-01-23 21:27:26.791665: step: 238/1545, loss: 0.105842724442482 2023-01-23 21:27:27.666829: step: 240/1545, loss: 0.0060714539140462875 2023-01-23 21:27:28.507098: step: 242/1545, loss: 0.0003120422479696572 2023-01-23 21:27:29.369894: step: 244/1545, loss: 0.12026507407426834 2023-01-23 21:27:30.273393: step: 246/1545, loss: 2.3234222680912353e-05 2023-01-23 21:27:31.128164: step: 248/1545, loss: 0.052552204579114914 2023-01-23 21:27:31.999788: step: 250/1545, loss: 0.003110731951892376 2023-01-23 21:27:32.889224: step: 252/1545, loss: 8.428789442405105e-05 2023-01-23 21:27:33.785754: step: 254/1545, loss: 0.025502076372504234 2023-01-23 21:27:34.653049: step: 256/1545, loss: 0.00026975403307005763 2023-01-23 21:27:35.504182: step: 258/1545, loss: 0.00872587040066719 2023-01-23 21:27:36.367583: step: 260/1545, loss: 0.0004302127053961158 2023-01-23 21:27:37.229848: step: 262/1545, loss: 0.0008286616066470742 2023-01-23 21:27:38.133058: step: 264/1545, loss: 0.3014678657054901 2023-01-23 21:27:39.006537: step: 266/1545, loss: 0.008466880768537521 2023-01-23 21:27:39.882840: step: 268/1545, loss: 0.2827928066253662 2023-01-23 21:27:40.809397: step: 270/1545, loss: 0.120109923183918 2023-01-23 21:27:41.694395: step: 272/1545, loss: 0.02085426077246666 2023-01-23 21:27:42.629244: step: 274/1545, loss: 0.0950424000620842 2023-01-23 21:27:43.495599: step: 276/1545, loss: 0.021184906363487244 2023-01-23 21:27:44.368988: step: 278/1545, loss: 0.00029596168315038085 2023-01-23 21:27:45.227645: step: 280/1545, loss: 0.10510417073965073 2023-01-23 21:27:46.105577: step: 282/1545, loss: 4.451322092791088e-05 2023-01-23 21:27:47.056996: step: 284/1545, loss: 5.568352571572177e-05 2023-01-23 21:27:47.951090: step: 286/1545, loss: 0.049505069851875305 2023-01-23 21:27:48.776663: step: 288/1545, loss: 0.00030885954038240016 2023-01-23 21:27:49.806786: step: 290/1545, loss: 0.0002360626240260899 2023-01-23 21:27:50.661074: step: 292/1545, loss: 0.07706039398908615 2023-01-23 21:27:51.573831: step: 294/1545, loss: 0.2389022707939148 2023-01-23 21:27:52.461803: step: 296/1545, loss: 4.800408532901201e-06 2023-01-23 21:27:53.339313: step: 298/1545, loss: 0.02659248560667038 2023-01-23 21:27:54.228821: step: 300/1545, loss: 0.0018929762300103903 2023-01-23 21:27:55.133523: step: 302/1545, loss: 0.08834875375032425 2023-01-23 21:27:56.003801: step: 304/1545, loss: 0.012218523770570755 2023-01-23 21:27:56.863148: step: 306/1545, loss: 0.0001903974189190194 2023-01-23 21:27:57.739028: step: 308/1545, loss: 0.10416711121797562 2023-01-23 21:27:58.656355: step: 310/1545, loss: 0.0001869857223937288 2023-01-23 21:27:59.521100: step: 312/1545, loss: 0.0021148736122995615 2023-01-23 21:28:00.403688: step: 314/1545, loss: 0.022849857807159424 2023-01-23 21:28:01.278694: step: 316/1545, loss: 0.0013710613129660487 2023-01-23 21:28:02.170739: step: 318/1545, loss: 0.00036637825542129576 2023-01-23 21:28:03.000912: step: 320/1545, loss: 0.00037551435525529087 2023-01-23 21:28:03.888969: step: 322/1545, loss: 0.18828251957893372 2023-01-23 21:28:04.715078: step: 324/1545, loss: 0.00571439228951931 2023-01-23 21:28:05.593480: step: 326/1545, loss: 0.008528600446879864 2023-01-23 21:28:06.493914: step: 328/1545, loss: 0.03504836559295654 2023-01-23 21:28:07.366955: step: 330/1545, loss: 0.04810938239097595 2023-01-23 21:28:08.223084: step: 332/1545, loss: 0.20346246659755707 2023-01-23 21:28:09.058731: step: 334/1545, loss: 0.30617910623550415 2023-01-23 21:28:09.915321: step: 336/1545, loss: 0.0021595631260424852 2023-01-23 21:28:10.752009: step: 338/1545, loss: 8.669037924846634e-05 2023-01-23 21:28:11.647981: step: 340/1545, loss: 0.019371382892131805 2023-01-23 21:28:12.568962: step: 342/1545, loss: 3.6395067581906915e-05 2023-01-23 21:28:13.435636: step: 344/1545, loss: 0.0001708019117359072 2023-01-23 21:28:14.280804: step: 346/1545, loss: 0.8051329851150513 2023-01-23 21:28:15.147598: step: 348/1545, loss: 0.15354909002780914 2023-01-23 21:28:16.040849: step: 350/1545, loss: 0.14834916591644287 2023-01-23 21:28:16.906581: step: 352/1545, loss: 0.00038985078572295606 2023-01-23 21:28:17.845171: step: 354/1545, loss: 0.02512715756893158 2023-01-23 21:28:18.727098: step: 356/1545, loss: 0.003089208621531725 2023-01-23 21:28:19.647696: step: 358/1545, loss: 0.00019878946477547288 2023-01-23 21:28:20.504743: step: 360/1545, loss: 0.0011386389378458261 2023-01-23 21:28:21.411246: step: 362/1545, loss: 0.30556195974349976 2023-01-23 21:28:22.242986: step: 364/1545, loss: 5.17378248332534e-05 2023-01-23 21:28:23.083810: step: 366/1545, loss: 0.0010303198359906673 2023-01-23 21:28:23.971145: step: 368/1545, loss: 5.753397272201255e-05 2023-01-23 21:28:24.890481: step: 370/1545, loss: 0.031189454719424248 2023-01-23 21:28:25.790493: step: 372/1545, loss: 0.005573838017880917 2023-01-23 21:28:26.637649: step: 374/1545, loss: 0.17356522381305695 2023-01-23 21:28:27.521744: step: 376/1545, loss: 6.917510472703725e-05 2023-01-23 21:28:28.401182: step: 378/1545, loss: 0.00029586965683847666 2023-01-23 21:28:29.304577: step: 380/1545, loss: 0.0018582198536023498 2023-01-23 21:28:30.156464: step: 382/1545, loss: 0.0022885396610945463 2023-01-23 21:28:31.028578: step: 384/1545, loss: 0.0010375999845564365 2023-01-23 21:28:31.887105: step: 386/1545, loss: -4.740315034723608e-06 2023-01-23 21:28:32.757829: step: 388/1545, loss: 0.005125970579683781 2023-01-23 21:28:33.690487: step: 390/1545, loss: 0.00014785240637138486 2023-01-23 21:28:34.552333: step: 392/1545, loss: 0.001086593372747302 2023-01-23 21:28:35.424820: step: 394/1545, loss: 0.0005132033838890493 2023-01-23 21:28:36.291055: step: 396/1545, loss: 0.031960003077983856 2023-01-23 21:28:37.129176: step: 398/1545, loss: 0.00015270456788130105 2023-01-23 21:28:37.980258: step: 400/1545, loss: 0.000398453586967662 2023-01-23 21:28:38.858136: step: 402/1545, loss: 0.0002729549596551806 2023-01-23 21:28:39.731425: step: 404/1545, loss: 0.1411202996969223 2023-01-23 21:28:40.602633: step: 406/1545, loss: 0.003210598835721612 2023-01-23 21:28:41.448133: step: 408/1545, loss: 6.016773113515228e-05 2023-01-23 21:28:42.349873: step: 410/1545, loss: 0.023831849917769432 2023-01-23 21:28:43.212517: step: 412/1545, loss: 0.16702334582805634 2023-01-23 21:28:44.040517: step: 414/1545, loss: 0.000556934392079711 2023-01-23 21:28:44.930583: step: 416/1545, loss: 0.18420614302158356 2023-01-23 21:28:45.789280: step: 418/1545, loss: 0.0016081747598946095 2023-01-23 21:28:46.671237: step: 420/1545, loss: 0.0029052281752228737 2023-01-23 21:28:47.528559: step: 422/1545, loss: 0.0013187172589823604 2023-01-23 21:28:48.430018: step: 424/1545, loss: 0.10730846971273422 2023-01-23 21:28:49.347768: step: 426/1545, loss: 0.001277628936804831 2023-01-23 21:28:50.205805: step: 428/1545, loss: 0.00020617297559510916 2023-01-23 21:28:51.081690: step: 430/1545, loss: 0.00018344834097661078 2023-01-23 21:28:52.022530: step: 432/1545, loss: 0.059950415045022964 2023-01-23 21:28:52.898493: step: 434/1545, loss: 0.0022215961944311857 2023-01-23 21:28:53.756096: step: 436/1545, loss: 0.012197584845125675 2023-01-23 21:28:54.666853: step: 438/1545, loss: 0.3119504153728485 2023-01-23 21:28:55.527863: step: 440/1545, loss: 0.07329345494508743 2023-01-23 21:28:56.377269: step: 442/1545, loss: 0.2618703544139862 2023-01-23 21:28:57.293760: step: 444/1545, loss: 4.0325772715732455e-05 2023-01-23 21:28:58.181625: step: 446/1545, loss: 0.004370343405753374 2023-01-23 21:28:59.026461: step: 448/1545, loss: 7.320741133298725e-05 2023-01-23 21:28:59.907991: step: 450/1545, loss: 0.00016050762496888638 2023-01-23 21:29:00.754157: step: 452/1545, loss: 0.0005658479640260339 2023-01-23 21:29:01.644668: step: 454/1545, loss: 5.727224925067276e-05 2023-01-23 21:29:02.537308: step: 456/1545, loss: 0.000780779286287725 2023-01-23 21:29:03.379017: step: 458/1545, loss: 9.843518637353554e-05 2023-01-23 21:29:04.312581: step: 460/1545, loss: 0.0033433118369430304 2023-01-23 21:29:05.210137: step: 462/1545, loss: 0.001929986639879644 2023-01-23 21:29:06.089838: step: 464/1545, loss: 0.07890476286411285 2023-01-23 21:29:06.977852: step: 466/1545, loss: 0.0007665202720090747 2023-01-23 21:29:07.820999: step: 468/1545, loss: 0.00048005711869336665 2023-01-23 21:29:08.690563: step: 470/1545, loss: 9.891668742056936e-05 2023-01-23 21:29:09.634797: step: 472/1545, loss: 0.0023928785230964422 2023-01-23 21:29:10.576340: step: 474/1545, loss: 0.002502822782844305 2023-01-23 21:29:11.448980: step: 476/1545, loss: 0.09898247569799423 2023-01-23 21:29:12.278472: step: 478/1545, loss: 0.00016126403352245688 2023-01-23 21:29:13.247392: step: 480/1545, loss: 0.01364957820624113 2023-01-23 21:29:14.081642: step: 482/1545, loss: 0.00020602374570444226 2023-01-23 21:29:14.959730: step: 484/1545, loss: 3.356665183673613e-05 2023-01-23 21:29:15.855769: step: 486/1545, loss: 0.0013153133913874626 2023-01-23 21:29:16.723662: step: 488/1545, loss: 0.1296192705631256 2023-01-23 21:29:17.593339: step: 490/1545, loss: 0.04382482171058655 2023-01-23 21:29:18.462945: step: 492/1545, loss: 0.00015732705651316792 2023-01-23 21:29:19.357399: step: 494/1545, loss: 0.0037441838067024946 2023-01-23 21:29:20.257257: step: 496/1545, loss: 0.0368179976940155 2023-01-23 21:29:21.160641: step: 498/1545, loss: 0.3276119530200958 2023-01-23 21:29:22.017074: step: 500/1545, loss: 0.0038039579521864653 2023-01-23 21:29:22.889039: step: 502/1545, loss: 0.00018531910609453917 2023-01-23 21:29:23.771744: step: 504/1545, loss: 0.00027868367033079267 2023-01-23 21:29:24.645940: step: 506/1545, loss: 0.10852459073066711 2023-01-23 21:29:25.524596: step: 508/1545, loss: 0.36252057552337646 2023-01-23 21:29:26.419162: step: 510/1545, loss: 0.00018748390721157193 2023-01-23 21:29:27.333320: step: 512/1545, loss: 0.0006465049227699637 2023-01-23 21:29:28.186497: step: 514/1545, loss: 0.0001974248152691871 2023-01-23 21:29:29.044970: step: 516/1545, loss: 0.0005728466203436255 2023-01-23 21:29:29.931403: step: 518/1545, loss: 0.0014187669148668647 2023-01-23 21:29:30.818685: step: 520/1545, loss: 0.002518901601433754 2023-01-23 21:29:31.716150: step: 522/1545, loss: 0.0002709651889745146 2023-01-23 21:29:32.609986: step: 524/1545, loss: 5.032955959904939e-05 2023-01-23 21:29:33.469957: step: 526/1545, loss: -1.2387831702653784e-05 2023-01-23 21:29:34.337356: step: 528/1545, loss: 0.013893584720790386 2023-01-23 21:29:35.246062: step: 530/1545, loss: 0.06699372082948685 2023-01-23 21:29:36.124476: step: 532/1545, loss: 0.00013171356113161892 2023-01-23 21:29:36.950269: step: 534/1545, loss: 6.110116828494938e-06 2023-01-23 21:29:37.844901: step: 536/1545, loss: 0.00020140543347224593 2023-01-23 21:29:38.739157: step: 538/1545, loss: 0.00034321288694627583 2023-01-23 21:29:39.656619: step: 540/1545, loss: 5.306601451593451e-05 2023-01-23 21:29:40.545566: step: 542/1545, loss: 0.0021742950193583965 2023-01-23 21:29:41.403582: step: 544/1545, loss: 0.00014635994739364833 2023-01-23 21:29:42.278885: step: 546/1545, loss: 0.0699421763420105 2023-01-23 21:29:43.162931: step: 548/1545, loss: 0.0003903874312527478 2023-01-23 21:29:44.038319: step: 550/1545, loss: 0.0002999177959281951 2023-01-23 21:29:44.912994: step: 552/1545, loss: 2.2653302949038334e-05 2023-01-23 21:29:45.787369: step: 554/1545, loss: 0.0054621039889752865 2023-01-23 21:29:46.696742: step: 556/1545, loss: 0.004837105982005596 2023-01-23 21:29:47.619685: step: 558/1545, loss: 0.004972644150257111 2023-01-23 21:29:48.494927: step: 560/1545, loss: 0.00013938893971499056 2023-01-23 21:29:49.348596: step: 562/1545, loss: 9.01037419680506e-05 2023-01-23 21:29:50.168452: step: 564/1545, loss: 0.0003195021999999881 2023-01-23 21:29:51.107071: step: 566/1545, loss: 0.0001032827130984515 2023-01-23 21:29:51.972902: step: 568/1545, loss: 0.04192117229104042 2023-01-23 21:29:52.842957: step: 570/1545, loss: 0.0008233122061938047 2023-01-23 21:29:53.722658: step: 572/1545, loss: 0.00026781708584167063 2023-01-23 21:29:54.605572: step: 574/1545, loss: 0.0019418118754401803 2023-01-23 21:29:55.496909: step: 576/1545, loss: 4.921316940453835e-05 2023-01-23 21:29:56.328546: step: 578/1545, loss: 3.6128614738117903e-05 2023-01-23 21:29:57.177199: step: 580/1545, loss: 8.004727715160698e-05 2023-01-23 21:29:58.113179: step: 582/1545, loss: 0.10369113087654114 2023-01-23 21:29:58.994105: step: 584/1545, loss: 5.3783602197654545e-05 2023-01-23 21:29:59.881925: step: 586/1545, loss: 0.0009821110870689154 2023-01-23 21:30:00.827610: step: 588/1545, loss: 0.05753675103187561 2023-01-23 21:30:01.688596: step: 590/1545, loss: 1.949236320797354e-05 2023-01-23 21:30:02.558766: step: 592/1545, loss: 0.04433923214673996 2023-01-23 21:30:03.377260: step: 594/1545, loss: 0.003500404767692089 2023-01-23 21:30:04.243686: step: 596/1545, loss: 0.0015129692619666457 2023-01-23 21:30:05.103915: step: 598/1545, loss: 0.21751171350479126 2023-01-23 21:30:05.999860: step: 600/1545, loss: 0.025807127356529236 2023-01-23 21:30:06.907721: step: 602/1545, loss: 0.005691428668797016 2023-01-23 21:30:07.795838: step: 604/1545, loss: 8.989907655632123e-05 2023-01-23 21:30:08.730873: step: 606/1545, loss: 0.06254522502422333 2023-01-23 21:30:09.589712: step: 608/1545, loss: 3.5946319258073345e-05 2023-01-23 21:30:10.440429: step: 610/1545, loss: 7.219936378533021e-06 2023-01-23 21:30:11.355190: step: 612/1545, loss: 0.0002963903534691781 2023-01-23 21:30:12.207007: step: 614/1545, loss: 0.0017510823672637343 2023-01-23 21:30:13.086358: step: 616/1545, loss: 9.83498539426364e-05 2023-01-23 21:30:13.932253: step: 618/1545, loss: 0.1000179648399353 2023-01-23 21:30:14.839944: step: 620/1545, loss: 0.00022265315055847168 2023-01-23 21:30:15.707001: step: 622/1545, loss: 0.0009710770682431757 2023-01-23 21:30:16.635445: step: 624/1545, loss: 0.008111364208161831 2023-01-23 21:30:17.486819: step: 626/1545, loss: 0.012516969814896584 2023-01-23 21:30:18.382105: step: 628/1545, loss: 0.0005586278857663274 2023-01-23 21:30:19.290629: step: 630/1545, loss: 8.39431959320791e-06 2023-01-23 21:30:20.125042: step: 632/1545, loss: 0.005596539005637169 2023-01-23 21:30:21.045933: step: 634/1545, loss: 0.31307411193847656 2023-01-23 21:30:21.910330: step: 636/1545, loss: 0.4548474848270416 2023-01-23 21:30:22.822645: step: 638/1545, loss: 0.057171959429979324 2023-01-23 21:30:23.730643: step: 640/1545, loss: 1.3527393341064453 2023-01-23 21:30:24.608348: step: 642/1545, loss: 0.0001612152555026114 2023-01-23 21:30:25.471579: step: 644/1545, loss: 9.068219515029341e-05 2023-01-23 21:30:26.342226: step: 646/1545, loss: 0.000515290186740458 2023-01-23 21:30:27.229450: step: 648/1545, loss: 0.00033547470229677856 2023-01-23 21:30:28.079411: step: 650/1545, loss: 9.220823994837701e-05 2023-01-23 21:30:28.999584: step: 652/1545, loss: 0.00012840052659157664 2023-01-23 21:30:29.921569: step: 654/1545, loss: 6.032653618603945e-05 2023-01-23 21:30:30.805125: step: 656/1545, loss: 3.866253973683342e-05 2023-01-23 21:30:31.658016: step: 658/1545, loss: 0.21360395848751068 2023-01-23 21:30:32.499023: step: 660/1545, loss: 0.4170060455799103 2023-01-23 21:30:33.409344: step: 662/1545, loss: 0.00029255589470267296 2023-01-23 21:30:34.333851: step: 664/1545, loss: 0.041161101311445236 2023-01-23 21:30:35.182658: step: 666/1545, loss: 0.0002917317033279687 2023-01-23 21:30:36.042132: step: 668/1545, loss: 0.008703729137778282 2023-01-23 21:30:36.912132: step: 670/1545, loss: 0.003454032354056835 2023-01-23 21:30:37.805761: step: 672/1545, loss: 0.00038656973629258573 2023-01-23 21:30:38.663016: step: 674/1545, loss: 0.000875510333571583 2023-01-23 21:30:39.535816: step: 676/1545, loss: 0.1467166543006897 2023-01-23 21:30:40.376815: step: 678/1545, loss: 0.0030353954061865807 2023-01-23 21:30:41.245079: step: 680/1545, loss: 0.024961519986391068 2023-01-23 21:30:42.149023: step: 682/1545, loss: 0.09962265938520432 2023-01-23 21:30:42.996655: step: 684/1545, loss: 0.04995336756110191 2023-01-23 21:30:43.852382: step: 686/1545, loss: 0.0032402509823441505 2023-01-23 21:30:44.748791: step: 688/1545, loss: 0.00047239847481250763 2023-01-23 21:30:45.613152: step: 690/1545, loss: 1.149187684059143 2023-01-23 21:30:46.475502: step: 692/1545, loss: 0.0007823303458280861 2023-01-23 21:30:47.352440: step: 694/1545, loss: 0.0012082316679880023 2023-01-23 21:30:48.292231: step: 696/1545, loss: 0.018610117956995964 2023-01-23 21:30:49.213747: step: 698/1545, loss: 0.2518114149570465 2023-01-23 21:30:50.086710: step: 700/1545, loss: 0.00035022536758333445 2023-01-23 21:30:50.994963: step: 702/1545, loss: 0.0002702913188841194 2023-01-23 21:30:51.860182: step: 704/1545, loss: 0.00022966443793848157 2023-01-23 21:30:52.715641: step: 706/1545, loss: 0.0028798040002584457 2023-01-23 21:30:53.560120: step: 708/1545, loss: 0.00796382874250412 2023-01-23 21:30:54.449395: step: 710/1545, loss: 0.00040225195698440075 2023-01-23 21:30:55.321164: step: 712/1545, loss: 0.0006162812351249158 2023-01-23 21:30:56.167204: step: 714/1545, loss: 0.00010504372767172754 2023-01-23 21:30:57.053833: step: 716/1545, loss: 0.07070259749889374 2023-01-23 21:30:57.952896: step: 718/1545, loss: 0.03327929228544235 2023-01-23 21:30:58.832913: step: 720/1545, loss: 0.24634984135627747 2023-01-23 21:30:59.708636: step: 722/1545, loss: 0.0011544669978320599 2023-01-23 21:31:00.598227: step: 724/1545, loss: 0.0056928666308522224 2023-01-23 21:31:01.502684: step: 726/1545, loss: 0.002902492880821228 2023-01-23 21:31:02.366979: step: 728/1545, loss: 9.863922605291009e-05 2023-01-23 21:31:03.219485: step: 730/1545, loss: 1.5982879400253296 2023-01-23 21:31:04.095162: step: 732/1545, loss: 0.0013629798777401447 2023-01-23 21:31:04.978683: step: 734/1545, loss: 0.000281009532045573 2023-01-23 21:31:05.899588: step: 736/1545, loss: 0.0002619289152789861 2023-01-23 21:31:06.807999: step: 738/1545, loss: 0.0004556290805339813 2023-01-23 21:31:07.648640: step: 740/1545, loss: 0.0007362954784184694 2023-01-23 21:31:08.538975: step: 742/1545, loss: 0.0013671943452209234 2023-01-23 21:31:09.409021: step: 744/1545, loss: 0.005673800129443407 2023-01-23 21:31:10.244214: step: 746/1545, loss: 9.078797302208841e-05 2023-01-23 21:31:11.109842: step: 748/1545, loss: 0.0002795654581859708 2023-01-23 21:31:11.964213: step: 750/1545, loss: 0.33352673053741455 2023-01-23 21:31:12.912921: step: 752/1545, loss: 0.0005571397487074137 2023-01-23 21:31:13.741649: step: 754/1545, loss: 0.00044202525168657303 2023-01-23 21:31:14.599253: step: 756/1545, loss: 0.0006981383194215596 2023-01-23 21:31:15.505048: step: 758/1545, loss: 0.40013357996940613 2023-01-23 21:31:16.386073: step: 760/1545, loss: 0.0010253950022161007 2023-01-23 21:31:17.318969: step: 762/1545, loss: 0.0005880874814465642 2023-01-23 21:31:18.221501: step: 764/1545, loss: 0.24236322939395905 2023-01-23 21:31:19.080928: step: 766/1545, loss: 0.0012796702794730663 2023-01-23 21:31:19.952011: step: 768/1545, loss: 0.0003127253439743072 2023-01-23 21:31:20.796176: step: 770/1545, loss: 0.00021824600116815418 2023-01-23 21:31:21.673270: step: 772/1545, loss: 0.004788727033883333 2023-01-23 21:31:22.525467: step: 774/1545, loss: 0.002554751932621002 2023-01-23 21:31:23.435280: step: 776/1545, loss: 0.00043592078145593405 2023-01-23 21:31:24.252254: step: 778/1545, loss: 8.292446727864444e-05 2023-01-23 21:31:25.112914: step: 780/1545, loss: 0.020631538704037666 2023-01-23 21:31:25.995484: step: 782/1545, loss: 0.05180460214614868 2023-01-23 21:31:26.847024: step: 784/1545, loss: 0.0261733029037714 2023-01-23 21:31:27.741977: step: 786/1545, loss: 5.850866364198737e-05 2023-01-23 21:31:28.565020: step: 788/1545, loss: 0.020234322175383568 2023-01-23 21:31:29.445329: step: 790/1545, loss: 0.0002735781017690897 2023-01-23 21:31:30.318677: step: 792/1545, loss: 0.24425263702869415 2023-01-23 21:31:31.273381: step: 794/1545, loss: 4.159764648647979e-05 2023-01-23 21:31:32.137496: step: 796/1545, loss: 0.00033163229818455875 2023-01-23 21:31:33.025578: step: 798/1545, loss: 0.00016077746113296598 2023-01-23 21:31:33.901634: step: 800/1545, loss: 0.07352814078330994 2023-01-23 21:31:34.788491: step: 802/1545, loss: 0.18126097321510315 2023-01-23 21:31:35.664916: step: 804/1545, loss: 0.060121409595012665 2023-01-23 21:31:36.497320: step: 806/1545, loss: 0.0001667395408730954 2023-01-23 21:31:37.372053: step: 808/1545, loss: 0.000697146519087255 2023-01-23 21:31:38.216172: step: 810/1545, loss: 0.00019739607523661107 2023-01-23 21:31:39.140768: step: 812/1545, loss: 0.0016698655672371387 2023-01-23 21:31:39.995729: step: 814/1545, loss: 0.0001504238462075591 2023-01-23 21:31:40.915070: step: 816/1545, loss: 0.0003799934056587517 2023-01-23 21:31:41.742993: step: 818/1545, loss: 0.011038477532565594 2023-01-23 21:31:42.637153: step: 820/1545, loss: 0.0004725719627458602 2023-01-23 21:31:43.537801: step: 822/1545, loss: 0.000980013282969594 2023-01-23 21:31:44.388816: step: 824/1545, loss: 0.008723986335098743 2023-01-23 21:31:45.266764: step: 826/1545, loss: 0.009370946325361729 2023-01-23 21:31:46.150364: step: 828/1545, loss: 0.0002035343204624951 2023-01-23 21:31:47.019898: step: 830/1545, loss: 0.031093072146177292 2023-01-23 21:31:47.923458: step: 832/1545, loss: 0.00011716783046722412 2023-01-23 21:31:48.796175: step: 834/1545, loss: 0.0010900695342570543 2023-01-23 21:31:49.701811: step: 836/1545, loss: 0.00010283332812832668 2023-01-23 21:31:50.596471: step: 838/1545, loss: 0.03931815177202225 2023-01-23 21:31:51.490770: step: 840/1545, loss: 0.003335770918056369 2023-01-23 21:31:52.420517: step: 842/1545, loss: 0.23318009078502655 2023-01-23 21:31:53.294583: step: 844/1545, loss: 0.11986044049263 2023-01-23 21:31:54.130852: step: 846/1545, loss: 0.0005989578203298151 2023-01-23 21:31:55.017074: step: 848/1545, loss: 0.01617947593331337 2023-01-23 21:31:55.903401: step: 850/1545, loss: 0.7885462641716003 2023-01-23 21:31:56.763687: step: 852/1545, loss: 0.2179243266582489 2023-01-23 21:31:57.760456: step: 854/1545, loss: 0.0011025698622688651 2023-01-23 21:31:58.614331: step: 856/1545, loss: 0.007751301396638155 2023-01-23 21:31:59.478013: step: 858/1545, loss: 0.00010423047933727503 2023-01-23 21:32:00.339202: step: 860/1545, loss: 0.01725500449538231 2023-01-23 21:32:01.220334: step: 862/1545, loss: 0.0007002680795267224 2023-01-23 21:32:02.078193: step: 864/1545, loss: 0.001132133649662137 2023-01-23 21:32:02.962402: step: 866/1545, loss: 0.004343423992395401 2023-01-23 21:32:03.827660: step: 868/1545, loss: 0.0008141517755575478 2023-01-23 21:32:04.650993: step: 870/1545, loss: 0.1825098842382431 2023-01-23 21:32:05.530358: step: 872/1545, loss: 0.004292218014597893 2023-01-23 21:32:06.392810: step: 874/1545, loss: 0.00011109743354609236 2023-01-23 21:32:07.277265: step: 876/1545, loss: 0.00018134865968022496 2023-01-23 21:32:08.160899: step: 878/1545, loss: 0.0002758850168902427 2023-01-23 21:32:09.019578: step: 880/1545, loss: 0.0005419283406808972 2023-01-23 21:32:09.878260: step: 882/1545, loss: 0.004467100836336613 2023-01-23 21:32:10.739656: step: 884/1545, loss: 6.843075243523344e-05 2023-01-23 21:32:11.681637: step: 886/1545, loss: 0.0058234562166035175 2023-01-23 21:32:12.575558: step: 888/1545, loss: 0.004826061427593231 2023-01-23 21:32:13.534126: step: 890/1545, loss: 0.09650865942239761 2023-01-23 21:32:14.379738: step: 892/1545, loss: 0.00016214846982620656 2023-01-23 21:32:15.239217: step: 894/1545, loss: 0.0016664681024849415 2023-01-23 21:32:16.162011: step: 896/1545, loss: 0.017982006072998047 2023-01-23 21:32:17.019521: step: 898/1545, loss: 0.006308551412075758 2023-01-23 21:32:17.872651: step: 900/1545, loss: 0.02825947292149067 2023-01-23 21:32:18.762995: step: 902/1545, loss: 0.0010503910016268492 2023-01-23 21:32:19.615810: step: 904/1545, loss: 0.003619167720898986 2023-01-23 21:32:20.443712: step: 906/1545, loss: 2.0004836187581532e-07 2023-01-23 21:32:21.335076: step: 908/1545, loss: 0.00564486114308238 2023-01-23 21:32:22.250479: step: 910/1545, loss: 0.0014907452277839184 2023-01-23 21:32:23.162896: step: 912/1545, loss: 0.062006499618291855 2023-01-23 21:32:24.005881: step: 914/1545, loss: 0.00426458241418004 2023-01-23 21:32:24.867403: step: 916/1545, loss: 0.00391526659950614 2023-01-23 21:32:25.741116: step: 918/1545, loss: 0.006782743148505688 2023-01-23 21:32:26.586674: step: 920/1545, loss: 0.00013952402514405549 2023-01-23 21:32:27.536070: step: 922/1545, loss: 0.27457278966903687 2023-01-23 21:32:28.413028: step: 924/1545, loss: 0.00010203487181570381 2023-01-23 21:32:29.273340: step: 926/1545, loss: 0.01684442162513733 2023-01-23 21:32:30.125728: step: 928/1545, loss: 0.00019698696269188076 2023-01-23 21:32:31.028632: step: 930/1545, loss: 0.010182037949562073 2023-01-23 21:32:31.925056: step: 932/1545, loss: 0.00011641033052001148 2023-01-23 21:32:32.847011: step: 934/1545, loss: 9.487599891144782e-05 2023-01-23 21:32:33.703491: step: 936/1545, loss: 0.0014950226759538054 2023-01-23 21:32:34.609773: step: 938/1545, loss: 0.017406487837433815 2023-01-23 21:32:35.508880: step: 940/1545, loss: 0.0889902114868164 2023-01-23 21:32:36.424935: step: 942/1545, loss: 0.22371837496757507 2023-01-23 21:32:37.295792: step: 944/1545, loss: 0.04600321874022484 2023-01-23 21:32:38.193573: step: 946/1545, loss: 0.05532832816243172 2023-01-23 21:32:39.095893: step: 948/1545, loss: 0.5215191841125488 2023-01-23 21:32:39.965669: step: 950/1545, loss: 0.004585552960634232 2023-01-23 21:32:40.866614: step: 952/1545, loss: 0.0001874990703072399 2023-01-23 21:32:41.770092: step: 954/1545, loss: 0.004865163471549749 2023-01-23 21:32:42.645125: step: 956/1545, loss: 3.122029738733545e-05 2023-01-23 21:32:43.517966: step: 958/1545, loss: 0.0047597275115549564 2023-01-23 21:32:44.373984: step: 960/1545, loss: 0.0005929352482780814 2023-01-23 21:32:45.233436: step: 962/1545, loss: 0.007450421340763569 2023-01-23 21:32:46.063201: step: 964/1545, loss: 0.0001411404664395377 2023-01-23 21:32:46.934427: step: 966/1545, loss: 0.0002728026593104005 2023-01-23 21:32:47.773779: step: 968/1545, loss: 5.306891034706496e-05 2023-01-23 21:32:48.662161: step: 970/1545, loss: 0.04662870243191719 2023-01-23 21:32:49.529339: step: 972/1545, loss: 0.001017776201479137 2023-01-23 21:32:50.402330: step: 974/1545, loss: 9.772107296157628e-05 2023-01-23 21:32:51.293571: step: 976/1545, loss: 1.6041109561920166 2023-01-23 21:32:52.179645: step: 978/1545, loss: 0.00014511293557006866 2023-01-23 21:32:53.048217: step: 980/1545, loss: 0.7192043662071228 2023-01-23 21:32:53.937938: step: 982/1545, loss: 0.005836463999003172 2023-01-23 21:32:54.843267: step: 984/1545, loss: 0.03869139030575752 2023-01-23 21:32:55.713734: step: 986/1545, loss: 0.012719210237264633 2023-01-23 21:32:56.581526: step: 988/1545, loss: 0.011289016343653202 2023-01-23 21:32:57.478114: step: 990/1545, loss: 0.38745012879371643 2023-01-23 21:32:58.343016: step: 992/1545, loss: 0.0011791951255872846 2023-01-23 21:32:59.188579: step: 994/1545, loss: 0.0005438024527393281 2023-01-23 21:33:00.088515: step: 996/1545, loss: 0.0015171001432463527 2023-01-23 21:33:00.983433: step: 998/1545, loss: 0.26852700114250183 2023-01-23 21:33:01.861651: step: 1000/1545, loss: 0.008995740674436092 2023-01-23 21:33:02.776590: step: 1002/1545, loss: 0.00021570009994320571 2023-01-23 21:33:03.686838: step: 1004/1545, loss: 0.005627341568470001 2023-01-23 21:33:04.521279: step: 1006/1545, loss: 0.0003226275439374149 2023-01-23 21:33:05.415306: step: 1008/1545, loss: 0.022410742938518524 2023-01-23 21:33:06.308665: step: 1010/1545, loss: 0.00013219592801760882 2023-01-23 21:33:07.188595: step: 1012/1545, loss: 0.00023064880224410444 2023-01-23 21:33:08.071110: step: 1014/1545, loss: 0.00011223653564229608 2023-01-23 21:33:08.941218: step: 1016/1545, loss: 0.02654172107577324 2023-01-23 21:33:09.814397: step: 1018/1545, loss: 0.1654735803604126 2023-01-23 21:33:10.726045: step: 1020/1545, loss: 0.005072640720754862 2023-01-23 21:33:11.582835: step: 1022/1545, loss: 0.00028292517527006567 2023-01-23 21:33:12.468397: step: 1024/1545, loss: 0.0019199857488274574 2023-01-23 21:33:13.319806: step: 1026/1545, loss: 0.0011305117513984442 2023-01-23 21:33:14.269496: step: 1028/1545, loss: 0.0014185818145051599 2023-01-23 21:33:15.168166: step: 1030/1545, loss: 0.0021885039750486612 2023-01-23 21:33:16.068796: step: 1032/1545, loss: 0.0001886033860500902 2023-01-23 21:33:16.964698: step: 1034/1545, loss: 0.00035472592571750283 2023-01-23 21:33:17.867772: step: 1036/1545, loss: 0.0007813283591531217 2023-01-23 21:33:18.737216: step: 1038/1545, loss: 0.00014794818707741797 2023-01-23 21:33:19.638459: step: 1040/1545, loss: 0.170053169131279 2023-01-23 21:33:20.567843: step: 1042/1545, loss: 0.0009205567766912282 2023-01-23 21:33:21.424442: step: 1044/1545, loss: 0.0033858190290629864 2023-01-23 21:33:22.320905: step: 1046/1545, loss: 0.0008797911577858031 2023-01-23 21:33:23.199650: step: 1048/1545, loss: 0.008049549534916878 2023-01-23 21:33:24.095559: step: 1050/1545, loss: 0.001551621244288981 2023-01-23 21:33:24.965962: step: 1052/1545, loss: 9.75367147475481e-05 2023-01-23 21:33:25.898617: step: 1054/1545, loss: 0.0004431565757840872 2023-01-23 21:33:26.755604: step: 1056/1545, loss: 0.00023519000387750566 2023-01-23 21:33:27.611812: step: 1058/1545, loss: 0.00990887638181448 2023-01-23 21:33:28.526855: step: 1060/1545, loss: 3.692953760037199e-05 2023-01-23 21:33:29.394763: step: 1062/1545, loss: 0.0002706959203351289 2023-01-23 21:33:30.246491: step: 1064/1545, loss: 0.0003533810959197581 2023-01-23 21:33:31.162421: step: 1066/1545, loss: 0.06512954086065292 2023-01-23 21:33:32.020600: step: 1068/1545, loss: 0.00012892537051811814 2023-01-23 21:33:32.873509: step: 1070/1545, loss: 0.009009884670376778 2023-01-23 21:33:33.697718: step: 1072/1545, loss: 0.0008140120189636946 2023-01-23 21:33:34.543453: step: 1074/1545, loss: 0.0005955866072326899 2023-01-23 21:33:35.375738: step: 1076/1545, loss: 6.358812970574945e-05 2023-01-23 21:33:36.227426: step: 1078/1545, loss: 0.00012536229041870683 2023-01-23 21:33:37.114756: step: 1080/1545, loss: 0.00021847404423169792 2023-01-23 21:33:38.028096: step: 1082/1545, loss: 0.4429295063018799 2023-01-23 21:33:38.931070: step: 1084/1545, loss: 0.00012936891289427876 2023-01-23 21:33:39.808935: step: 1086/1545, loss: 0.00032028142595663667 2023-01-23 21:33:40.672579: step: 1088/1545, loss: 0.004354135133326054 2023-01-23 21:33:41.559048: step: 1090/1545, loss: 0.0010167988948523998 2023-01-23 21:33:42.438953: step: 1092/1545, loss: 0.0011454789200797677 2023-01-23 21:33:43.310069: step: 1094/1545, loss: 0.00013520369247999042 2023-01-23 21:33:44.231867: step: 1096/1545, loss: 0.00013396273425314575 2023-01-23 21:33:45.124092: step: 1098/1545, loss: 0.16898943483829498 2023-01-23 21:33:45.977449: step: 1100/1545, loss: 0.0008571022190153599 2023-01-23 21:33:46.845835: step: 1102/1545, loss: 0.05483413115143776 2023-01-23 21:33:47.713004: step: 1104/1545, loss: 0.004683620762079954 2023-01-23 21:33:48.562812: step: 1106/1545, loss: 0.001012834720313549 2023-01-23 21:33:49.422593: step: 1108/1545, loss: 0.34256571531295776 2023-01-23 21:33:50.241532: step: 1110/1545, loss: 9.376894740853459e-05 2023-01-23 21:33:51.110893: step: 1112/1545, loss: 0.2671453058719635 2023-01-23 21:33:51.998152: step: 1114/1545, loss: 0.002675294876098633 2023-01-23 21:33:52.954163: step: 1116/1545, loss: 0.0009660355863161385 2023-01-23 21:33:53.926676: step: 1118/1545, loss: 0.0005298960604704916 2023-01-23 21:33:54.781355: step: 1120/1545, loss: 0.0021028530318289995 2023-01-23 21:33:55.680300: step: 1122/1545, loss: 0.0001143217014032416 2023-01-23 21:33:56.543647: step: 1124/1545, loss: 0.00011238252045586705 2023-01-23 21:33:57.406530: step: 1126/1545, loss: 0.020636310800909996 2023-01-23 21:33:58.272055: step: 1128/1545, loss: 0.0002149891370208934 2023-01-23 21:33:59.156047: step: 1130/1545, loss: 0.0076597207225859165 2023-01-23 21:34:00.022016: step: 1132/1545, loss: 9.278398647438735e-05 2023-01-23 21:34:00.898892: step: 1134/1545, loss: 0.006525296252220869 2023-01-23 21:34:01.751353: step: 1136/1545, loss: 0.00010761842713691294 2023-01-23 21:34:02.606837: step: 1138/1545, loss: 0.0005394425243139267 2023-01-23 21:34:03.451635: step: 1140/1545, loss: 0.005034766625612974 2023-01-23 21:34:04.316757: step: 1142/1545, loss: 0.0393124520778656 2023-01-23 21:34:05.181533: step: 1144/1545, loss: 7.111495506251231e-05 2023-01-23 21:34:06.015197: step: 1146/1545, loss: 6.204505189089105e-05 2023-01-23 21:34:06.862843: step: 1148/1545, loss: 0.004003370180726051 2023-01-23 21:34:07.734818: step: 1150/1545, loss: 0.0026422441005706787 2023-01-23 21:34:08.654136: step: 1152/1545, loss: 0.7521353363990784 2023-01-23 21:34:09.494997: step: 1154/1545, loss: 0.04152299836277962 2023-01-23 21:34:10.346907: step: 1156/1545, loss: 0.007125138770788908 2023-01-23 21:34:11.228686: step: 1158/1545, loss: 0.00010521004878683016 2023-01-23 21:34:12.122043: step: 1160/1545, loss: 0.0001342253090115264 2023-01-23 21:34:13.024361: step: 1162/1545, loss: 0.12105224281549454 2023-01-23 21:34:13.962160: step: 1164/1545, loss: 0.00011200152221135795 2023-01-23 21:34:14.871783: step: 1166/1545, loss: 0.14098051190376282 2023-01-23 21:34:15.768357: step: 1168/1545, loss: 0.008866654708981514 2023-01-23 21:34:16.650267: step: 1170/1545, loss: 0.06387866288423538 2023-01-23 21:34:17.543287: step: 1172/1545, loss: 0.00016530154971405864 2023-01-23 21:34:18.370391: step: 1174/1545, loss: 0.3534201979637146 2023-01-23 21:34:19.277218: step: 1176/1545, loss: 0.49046674370765686 2023-01-23 21:34:20.194750: step: 1178/1545, loss: 0.1473960280418396 2023-01-23 21:34:21.038036: step: 1180/1545, loss: 0.001488212263211608 2023-01-23 21:34:21.905445: step: 1182/1545, loss: 0.0053438167087733746 2023-01-23 21:34:22.750220: step: 1184/1545, loss: 0.00010411738185212016 2023-01-23 21:34:23.634768: step: 1186/1545, loss: 0.0002214069536421448 2023-01-23 21:34:24.498206: step: 1188/1545, loss: 0.0002278867323184386 2023-01-23 21:34:25.423302: step: 1190/1545, loss: 0.035190075635910034 2023-01-23 21:34:26.265087: step: 1192/1545, loss: 0.12163075059652328 2023-01-23 21:34:27.122023: step: 1194/1545, loss: 0.0004120650119148195 2023-01-23 21:34:28.053004: step: 1196/1545, loss: 0.011307023465633392 2023-01-23 21:34:28.939410: step: 1198/1545, loss: 3.308752638986334e-05 2023-01-23 21:34:29.828871: step: 1200/1545, loss: 0.09029491990804672 2023-01-23 21:34:30.759625: step: 1202/1545, loss: -2.1123387341503985e-05 2023-01-23 21:34:31.617847: step: 1204/1545, loss: 0.008537862449884415 2023-01-23 21:34:32.509247: step: 1206/1545, loss: 0.003223539562895894 2023-01-23 21:34:33.424165: step: 1208/1545, loss: 0.36316004395484924 2023-01-23 21:34:34.363214: step: 1210/1545, loss: 0.0035493597388267517 2023-01-23 21:34:35.279014: step: 1212/1545, loss: 0.003631019964814186 2023-01-23 21:34:36.320539: step: 1214/1545, loss: 0.702544093132019 2023-01-23 21:34:37.194701: step: 1216/1545, loss: 0.4398740828037262 2023-01-23 21:34:38.081170: step: 1218/1545, loss: 0.00013115734327584505 2023-01-23 21:34:38.965888: step: 1220/1545, loss: 0.0016534299356862903 2023-01-23 21:34:39.869256: step: 1222/1545, loss: 0.00047212414210662246 2023-01-23 21:34:40.774021: step: 1224/1545, loss: 0.0005380978691391647 2023-01-23 21:34:41.680189: step: 1226/1545, loss: 0.04008626937866211 2023-01-23 21:34:42.585446: step: 1228/1545, loss: 0.01423039473593235 2023-01-23 21:34:43.479052: step: 1230/1545, loss: 0.0029432589653879404 2023-01-23 21:34:44.343213: step: 1232/1545, loss: 0.08760618418455124 2023-01-23 21:34:45.204985: step: 1234/1545, loss: 0.13952511548995972 2023-01-23 21:34:46.070200: step: 1236/1545, loss: 0.0036915400996804237 2023-01-23 21:34:46.928533: step: 1238/1545, loss: 0.0010434307623654604 2023-01-23 21:34:47.821900: step: 1240/1545, loss: 0.05345461145043373 2023-01-23 21:34:48.662156: step: 1242/1545, loss: 0.0010990708833560348 2023-01-23 21:34:49.519769: step: 1244/1545, loss: 0.0005970605998300016 2023-01-23 21:34:50.422861: step: 1246/1545, loss: 0.004772487562149763 2023-01-23 21:34:51.328809: step: 1248/1545, loss: 0.0014473368646577 2023-01-23 21:34:52.275294: step: 1250/1545, loss: 0.1302599161863327 2023-01-23 21:34:53.195263: step: 1252/1545, loss: 0.22762222588062286 2023-01-23 21:34:54.044448: step: 1254/1545, loss: 0.0024911670479923487 2023-01-23 21:34:54.883968: step: 1256/1545, loss: 0.0016592538449913263 2023-01-23 21:34:55.775260: step: 1258/1545, loss: 0.001347524463199079 2023-01-23 21:34:56.690017: step: 1260/1545, loss: 0.0007218992104753852 2023-01-23 21:34:57.596270: step: 1262/1545, loss: 0.00969675648957491 2023-01-23 21:34:58.502287: step: 1264/1545, loss: 0.08109775930643082 2023-01-23 21:34:59.565527: step: 1266/1545, loss: 0.13164076209068298 2023-01-23 21:35:00.430731: step: 1268/1545, loss: 0.000645918189547956 2023-01-23 21:35:01.301042: step: 1270/1545, loss: 0.0024064311292022467 2023-01-23 21:35:02.161168: step: 1272/1545, loss: 0.06165864318609238 2023-01-23 21:35:03.037645: step: 1274/1545, loss: 0.0011759235057979822 2023-01-23 21:35:03.978132: step: 1276/1545, loss: 0.0026997874956578016 2023-01-23 21:35:04.892675: step: 1278/1545, loss: 0.000615057535469532 2023-01-23 21:35:05.760619: step: 1280/1545, loss: 0.0002868928131647408 2023-01-23 21:35:06.629335: step: 1282/1545, loss: 0.06692949682474136 2023-01-23 21:35:07.481059: step: 1284/1545, loss: 0.003655696753412485 2023-01-23 21:35:08.320387: step: 1286/1545, loss: 0.03849148750305176 2023-01-23 21:35:09.175846: step: 1288/1545, loss: 0.036623165011405945 2023-01-23 21:35:10.024688: step: 1290/1545, loss: 0.0009691489394754171 2023-01-23 21:35:10.874426: step: 1292/1545, loss: 0.0027255334425717592 2023-01-23 21:35:11.785642: step: 1294/1545, loss: 0.00043447306961752474 2023-01-23 21:35:12.623127: step: 1296/1545, loss: 0.00014267444203142077 2023-01-23 21:35:13.522101: step: 1298/1545, loss: 0.06344226002693176 2023-01-23 21:35:14.385004: step: 1300/1545, loss: 0.00020689665689133108 2023-01-23 21:35:15.229232: step: 1302/1545, loss: 0.0015658813063055277 2023-01-23 21:35:16.110307: step: 1304/1545, loss: 0.0003856339317280799 2023-01-23 21:35:17.008693: step: 1306/1545, loss: 0.005913509987294674 2023-01-23 21:35:17.851683: step: 1308/1545, loss: 0.0169410090893507 2023-01-23 21:35:18.669441: step: 1310/1545, loss: 0.0009445796604268253 2023-01-23 21:35:19.551459: step: 1312/1545, loss: 0.31150105595588684 2023-01-23 21:35:20.411754: step: 1314/1545, loss: 0.09617254137992859 2023-01-23 21:35:21.338178: step: 1316/1545, loss: 0.01407615840435028 2023-01-23 21:35:22.209305: step: 1318/1545, loss: 0.0001669312041485682 2023-01-23 21:35:23.099777: step: 1320/1545, loss: 0.1509072482585907 2023-01-23 21:35:23.979848: step: 1322/1545, loss: 0.0017677065916359425 2023-01-23 21:35:24.866628: step: 1324/1545, loss: 0.22262968122959137 2023-01-23 21:35:25.717961: step: 1326/1545, loss: 0.00010299077257514 2023-01-23 21:35:26.552999: step: 1328/1545, loss: 0.12237005680799484 2023-01-23 21:35:27.434018: step: 1330/1545, loss: 0.0008160242578014731 2023-01-23 21:35:28.348619: step: 1332/1545, loss: 0.015978563576936722 2023-01-23 21:35:29.241883: step: 1334/1545, loss: 0.039597541093826294 2023-01-23 21:35:30.102783: step: 1336/1545, loss: 0.0004841136687900871 2023-01-23 21:35:30.979762: step: 1338/1545, loss: 0.0005764280795119703 2023-01-23 21:35:31.815516: step: 1340/1545, loss: 0.0008559510461054742 2023-01-23 21:35:32.645156: step: 1342/1545, loss: 0.0018748228903859854 2023-01-23 21:35:33.538648: step: 1344/1545, loss: 4.758519207825884e-05 2023-01-23 21:35:34.408503: step: 1346/1545, loss: 0.04542487859725952 2023-01-23 21:35:35.264474: step: 1348/1545, loss: 0.0009916089475154877 2023-01-23 21:35:36.131592: step: 1350/1545, loss: 0.0017379161436110735 2023-01-23 21:35:37.022983: step: 1352/1545, loss: 0.328876256942749 2023-01-23 21:35:37.892771: step: 1354/1545, loss: 6.736814975738525e-05 2023-01-23 21:35:38.801378: step: 1356/1545, loss: 0.00018795592768583447 2023-01-23 21:35:39.654735: step: 1358/1545, loss: 2.9242306482046843e-05 2023-01-23 21:35:40.524263: step: 1360/1545, loss: 0.00013370576198212802 2023-01-23 21:35:41.407116: step: 1362/1545, loss: 0.00462647620588541 2023-01-23 21:35:42.271149: step: 1364/1545, loss: 0.21186824142932892 2023-01-23 21:35:43.139805: step: 1366/1545, loss: 5.3895582823315635e-05 2023-01-23 21:35:43.985527: step: 1368/1545, loss: 0.0002131042565451935 2023-01-23 21:35:44.844309: step: 1370/1545, loss: 0.001861875643953681 2023-01-23 21:35:45.768945: step: 1372/1545, loss: 0.10403572022914886 2023-01-23 21:35:46.660495: step: 1374/1545, loss: 0.2595231235027313 2023-01-23 21:35:47.529929: step: 1376/1545, loss: 0.00032478111097589135 2023-01-23 21:35:48.365669: step: 1378/1545, loss: 0.006010301876813173 2023-01-23 21:35:49.276457: step: 1380/1545, loss: 0.031232738867402077 2023-01-23 21:35:50.175575: step: 1382/1545, loss: 0.0001588898157933727 2023-01-23 21:35:51.026661: step: 1384/1545, loss: 0.16850218176841736 2023-01-23 21:35:51.885113: step: 1386/1545, loss: 0.22506766021251678 2023-01-23 21:35:52.751235: step: 1388/1545, loss: 0.13449910283088684 2023-01-23 21:35:53.628039: step: 1390/1545, loss: 0.0030164122581481934 2023-01-23 21:35:54.550545: step: 1392/1545, loss: 0.002433331683278084 2023-01-23 21:35:55.443763: step: 1394/1545, loss: 0.09293867647647858 2023-01-23 21:35:56.340415: step: 1396/1545, loss: 8.927400631364435e-05 2023-01-23 21:35:57.305602: step: 1398/1545, loss: 0.0008686164510436356 2023-01-23 21:35:58.161972: step: 1400/1545, loss: 0.06290613859891891 2023-01-23 21:35:59.088613: step: 1402/1545, loss: 0.012300635688006878 2023-01-23 21:35:59.981575: step: 1404/1545, loss: 0.518427312374115 2023-01-23 21:36:00.884870: step: 1406/1545, loss: 3.610252679209225e-05 2023-01-23 21:36:01.730200: step: 1408/1545, loss: 0.00021059828577563167 2023-01-23 21:36:02.612154: step: 1410/1545, loss: 0.014217257499694824 2023-01-23 21:36:03.497490: step: 1412/1545, loss: 1.8538645505905151 2023-01-23 21:36:04.397537: step: 1414/1545, loss: 0.003198533784598112 2023-01-23 21:36:05.328454: step: 1416/1545, loss: 0.024868322536349297 2023-01-23 21:36:06.223501: step: 1418/1545, loss: 0.0045264894142746925 2023-01-23 21:36:07.079799: step: 1420/1545, loss: 0.0018670873250812292 2023-01-23 21:36:07.948288: step: 1422/1545, loss: 0.0025285177398473024 2023-01-23 21:36:08.835740: step: 1424/1545, loss: 0.14259064197540283 2023-01-23 21:36:09.778821: step: 1426/1545, loss: 0.021798040717840195 2023-01-23 21:36:10.705655: step: 1428/1545, loss: 0.005253848619759083 2023-01-23 21:36:11.550795: step: 1430/1545, loss: 0.0006332963821478188 2023-01-23 21:36:12.422797: step: 1432/1545, loss: 0.001250537345185876 2023-01-23 21:36:13.280120: step: 1434/1545, loss: 0.0009588786633685231 2023-01-23 21:36:14.167652: step: 1436/1545, loss: 0.0011433016043156385 2023-01-23 21:36:15.107909: step: 1438/1545, loss: 0.0012659466592594981 2023-01-23 21:36:15.975826: step: 1440/1545, loss: 0.00047014636220410466 2023-01-23 21:36:16.856507: step: 1442/1545, loss: 0.2689378261566162 2023-01-23 21:36:17.741052: step: 1444/1545, loss: 0.00014733847638126463 2023-01-23 21:36:18.613894: step: 1446/1545, loss: 1.0332336387364194e-05 2023-01-23 21:36:19.537970: step: 1448/1545, loss: 0.00025563244707882404 2023-01-23 21:36:20.402729: step: 1450/1545, loss: 0.013057501055300236 2023-01-23 21:36:21.298723: step: 1452/1545, loss: 0.001607772195711732 2023-01-23 21:36:22.146331: step: 1454/1545, loss: 0.0384572334587574 2023-01-23 21:36:23.055356: step: 1456/1545, loss: 0.0008626717608422041 2023-01-23 21:36:23.929325: step: 1458/1545, loss: 0.0020015030167996883 2023-01-23 21:36:24.820911: step: 1460/1545, loss: 0.09380268305540085 2023-01-23 21:36:25.706472: step: 1462/1545, loss: 0.0010974754113703966 2023-01-23 21:36:26.634359: step: 1464/1545, loss: 2.095195770263672 2023-01-23 21:36:27.504810: step: 1466/1545, loss: 0.10813111066818237 2023-01-23 21:36:28.379309: step: 1468/1545, loss: 5.507466630660929e-05 2023-01-23 21:36:29.251490: step: 1470/1545, loss: 0.15097610652446747 2023-01-23 21:36:30.149239: step: 1472/1545, loss: 7.414726132992655e-05 2023-01-23 21:36:31.012042: step: 1474/1545, loss: 0.0007579299272038043 2023-01-23 21:36:31.931266: step: 1476/1545, loss: 4.092752715223469e-05 2023-01-23 21:36:32.823839: step: 1478/1545, loss: 5.2687177230836824e-05 2023-01-23 21:36:33.733573: step: 1480/1545, loss: 0.13039997220039368 2023-01-23 21:36:34.610802: step: 1482/1545, loss: 6.527842197101563e-05 2023-01-23 21:36:35.463537: step: 1484/1545, loss: 0.0005360614159144461 2023-01-23 21:36:36.393451: step: 1486/1545, loss: 0.13237795233726501 2023-01-23 21:36:37.265593: step: 1488/1545, loss: 0.01275953371077776 2023-01-23 21:36:38.123244: step: 1490/1545, loss: 0.0003620318602770567 2023-01-23 21:36:39.024879: step: 1492/1545, loss: 4.7123019612627104e-05 2023-01-23 21:36:39.902909: step: 1494/1545, loss: 0.23159658908843994 2023-01-23 21:36:40.747135: step: 1496/1545, loss: 2.9533968699979596e-05 2023-01-23 21:36:41.639938: step: 1498/1545, loss: 0.033046264201402664 2023-01-23 21:36:42.537952: step: 1500/1545, loss: 0.0019083210499957204 2023-01-23 21:36:43.503433: step: 1502/1545, loss: 0.19137851893901825 2023-01-23 21:36:44.349474: step: 1504/1545, loss: 0.0001328826620010659 2023-01-23 21:36:45.262588: step: 1506/1545, loss: 0.0003616222820710391 2023-01-23 21:36:46.114132: step: 1508/1545, loss: -2.858562220353633e-05 2023-01-23 21:36:46.980461: step: 1510/1545, loss: 0.0002089662739308551 2023-01-23 21:36:47.843191: step: 1512/1545, loss: 6.720571400364861e-05 2023-01-23 21:36:48.736268: step: 1514/1545, loss: 0.011436880566179752 2023-01-23 21:36:49.650396: step: 1516/1545, loss: 0.002052701311185956 2023-01-23 21:36:50.509860: step: 1518/1545, loss: 0.0004439485492184758 2023-01-23 21:36:51.380880: step: 1520/1545, loss: 0.000945637992117554 2023-01-23 21:36:52.276176: step: 1522/1545, loss: 0.15161147713661194 2023-01-23 21:36:53.180612: step: 1524/1545, loss: 0.04241475090384483 2023-01-23 21:36:54.063198: step: 1526/1545, loss: 0.008870890364050865 2023-01-23 21:36:54.899787: step: 1528/1545, loss: 4.6747572923777625e-05 2023-01-23 21:36:55.768973: step: 1530/1545, loss: 0.0007325529004447162 2023-01-23 21:36:56.634299: step: 1532/1545, loss: 0.0003644348762463778 2023-01-23 21:36:57.529919: step: 1534/1545, loss: 6.437091360567138e-05 2023-01-23 21:36:58.402667: step: 1536/1545, loss: 0.015057947486639023 2023-01-23 21:36:59.288456: step: 1538/1545, loss: 0.0008207346545532346 2023-01-23 21:37:00.138544: step: 1540/1545, loss: 4.195299698039889e-05 2023-01-23 21:37:01.023075: step: 1542/1545, loss: 0.00014527497114613652 2023-01-23 21:37:01.859508: step: 1544/1545, loss: 0.0003124498180113733 2023-01-23 21:37:02.728087: step: 1546/1545, loss: 0.39777106046676636 2023-01-23 21:37:03.583733: step: 1548/1545, loss: 0.005393909756094217 2023-01-23 21:37:04.478339: step: 1550/1545, loss: 0.0009984644129872322 2023-01-23 21:37:05.301279: step: 1552/1545, loss: 0.0007159797241911292 2023-01-23 21:37:06.170783: step: 1554/1545, loss: -3.067028592340648e-05 2023-01-23 21:37:07.031392: step: 1556/1545, loss: 0.0004879845364484936 2023-01-23 21:37:07.878420: step: 1558/1545, loss: 1.74442811839981e-06 2023-01-23 21:37:08.764614: step: 1560/1545, loss: 0.0011112798238173127 2023-01-23 21:37:09.746519: step: 1562/1545, loss: 0.00011059577082050964 2023-01-23 21:37:10.585982: step: 1564/1545, loss: 0.00014363607624545693 2023-01-23 21:37:11.447448: step: 1566/1545, loss: 0.00034181535011157393 2023-01-23 21:37:12.336465: step: 1568/1545, loss: 0.0027097840793430805 2023-01-23 21:37:13.224776: step: 1570/1545, loss: 0.004350560251623392 2023-01-23 21:37:14.076069: step: 1572/1545, loss: 0.012288627214729786 2023-01-23 21:37:14.946616: step: 1574/1545, loss: 2.940185549960006e-05 2023-01-23 21:37:15.857747: step: 1576/1545, loss: 0.005411251448094845 2023-01-23 21:37:16.780267: step: 1578/1545, loss: 0.0005562643054872751 2023-01-23 21:37:17.654826: step: 1580/1545, loss: 0.1335163712501526 2023-01-23 21:37:18.533208: step: 1582/1545, loss: 0.00029104723944328725 2023-01-23 21:37:19.385223: step: 1584/1545, loss: 5.7265107898274437e-05 2023-01-23 21:37:20.211019: step: 1586/1545, loss: 0.0015414456138387322 2023-01-23 21:37:21.046516: step: 1588/1545, loss: 0.00691045681014657 2023-01-23 21:37:21.861577: step: 1590/1545, loss: 0.00027212785789743066 2023-01-23 21:37:22.715167: step: 1592/1545, loss: 7.71253980929032e-05 2023-01-23 21:37:23.599731: step: 1594/1545, loss: 5.9037323808297515e-05 2023-01-23 21:37:24.503627: step: 1596/1545, loss: 0.0025195260532200336 2023-01-23 21:37:25.476502: step: 1598/1545, loss: 0.0002993512316606939 2023-01-23 21:37:26.379602: step: 1600/1545, loss: 0.26377493143081665 2023-01-23 21:37:27.298993: step: 1602/1545, loss: 0.08741790801286697 2023-01-23 21:37:28.276299: step: 1604/1545, loss: 0.05455755442380905 2023-01-23 21:37:29.145298: step: 1606/1545, loss: 0.00010286083852406591 2023-01-23 21:37:30.004378: step: 1608/1545, loss: 0.0020458316430449486 2023-01-23 21:37:30.844753: step: 1610/1545, loss: 5.960942871752195e-06 2023-01-23 21:37:31.799129: step: 1612/1545, loss: 9.43359627854079e-05 2023-01-23 21:37:32.719003: step: 1614/1545, loss: 0.00010750424553407356 2023-01-23 21:37:33.564386: step: 1616/1545, loss: 7.19940653652884e-05 2023-01-23 21:37:34.467348: step: 1618/1545, loss: 0.00043172237928956747 2023-01-23 21:37:35.342746: step: 1620/1545, loss: 0.004513293970376253 2023-01-23 21:37:36.223390: step: 1622/1545, loss: -1.4702995940751862e-05 2023-01-23 21:37:37.091519: step: 1624/1545, loss: 0.0004101503000129014 2023-01-23 21:37:37.999083: step: 1626/1545, loss: 0.1450829803943634 2023-01-23 21:37:38.868481: step: 1628/1545, loss: 0.0011699801543727517 2023-01-23 21:37:39.720587: step: 1630/1545, loss: 0.0002281089691678062 2023-01-23 21:37:40.624598: step: 1632/1545, loss: 2.7371417672839016e-05 2023-01-23 21:37:41.495606: step: 1634/1545, loss: 0.001993885962292552 2023-01-23 21:37:42.451441: step: 1636/1545, loss: 3.498688602121547e-05 2023-01-23 21:37:43.362971: step: 1638/1545, loss: 0.00017159241542685777 2023-01-23 21:37:44.244565: step: 1640/1545, loss: 0.0030593136325478554 2023-01-23 21:37:45.099202: step: 1642/1545, loss: 6.743452831869945e-05 2023-01-23 21:37:45.983062: step: 1644/1545, loss: 0.0019006658112630248 2023-01-23 21:37:46.865122: step: 1646/1545, loss: 8.414981130044907e-05 2023-01-23 21:37:47.703546: step: 1648/1545, loss: 0.0002785753458738327 2023-01-23 21:37:48.596689: step: 1650/1545, loss: 0.06749343127012253 2023-01-23 21:37:49.456705: step: 1652/1545, loss: 1.6681835404597223e-05 2023-01-23 21:37:50.318480: step: 1654/1545, loss: 2.378730641794391e-05 2023-01-23 21:37:51.208621: step: 1656/1545, loss: 0.00011898473167093471 2023-01-23 21:37:52.057860: step: 1658/1545, loss: 0.15372951328754425 2023-01-23 21:37:52.920486: step: 1660/1545, loss: 7.1431186370318756e-06 2023-01-23 21:37:53.802969: step: 1662/1545, loss: 0.02088494785130024 2023-01-23 21:37:54.706930: step: 1664/1545, loss: 0.01925833337008953 2023-01-23 21:37:55.570965: step: 1666/1545, loss: 0.19164995849132538 2023-01-23 21:37:56.468131: step: 1668/1545, loss: 0.00041471252916380763 2023-01-23 21:37:57.403285: step: 1670/1545, loss: 0.016738640144467354 2023-01-23 21:37:58.234793: step: 1672/1545, loss: 2.5244795324397273e-05 2023-01-23 21:37:59.121388: step: 1674/1545, loss: 0.017948348075151443 2023-01-23 21:37:59.991828: step: 1676/1545, loss: 3.926901626982726e-05 2023-01-23 21:38:00.869433: step: 1678/1545, loss: 0.15666614472866058 2023-01-23 21:38:01.715408: step: 1680/1545, loss: 0.003116826992481947 2023-01-23 21:38:02.552167: step: 1682/1545, loss: 0.01107278186827898 2023-01-23 21:38:03.423503: step: 1684/1545, loss: 0.06134449318051338 2023-01-23 21:38:04.302792: step: 1686/1545, loss: 0.004004215355962515 2023-01-23 21:38:05.147711: step: 1688/1545, loss: 0.0008117934921756387 2023-01-23 21:38:06.039276: step: 1690/1545, loss: 0.005439405329525471 2023-01-23 21:38:06.997062: step: 1692/1545, loss: 4.728046042146161e-05 2023-01-23 21:38:07.818872: step: 1694/1545, loss: 0.0004123553226236254 2023-01-23 21:38:08.699365: step: 1696/1545, loss: 0.29088619351387024 2023-01-23 21:38:09.560262: step: 1698/1545, loss: 0.00018951624224428087 2023-01-23 21:38:10.430211: step: 1700/1545, loss: 0.0007236147066578269 2023-01-23 21:38:11.288588: step: 1702/1545, loss: 0.261147141456604 2023-01-23 21:38:12.174861: step: 1704/1545, loss: 9.161986235994846e-05 2023-01-23 21:38:13.060150: step: 1706/1545, loss: 0.00023525403230451047 2023-01-23 21:38:13.915394: step: 1708/1545, loss: -2.9410177376121283e-05 2023-01-23 21:38:14.787688: step: 1710/1545, loss: 0.016604108735919 2023-01-23 21:38:15.642811: step: 1712/1545, loss: -8.220126801461447e-09 2023-01-23 21:38:16.512015: step: 1714/1545, loss: 0.0027631993871182203 2023-01-23 21:38:17.401683: step: 1716/1545, loss: 0.0012807250022888184 2023-01-23 21:38:18.280038: step: 1718/1545, loss: 0.007368961814790964 2023-01-23 21:38:19.139700: step: 1720/1545, loss: 1.495718152000336e-05 2023-01-23 21:38:19.961957: step: 1722/1545, loss: 0.0003478802100289613 2023-01-23 21:38:20.840573: step: 1724/1545, loss: 0.019086694344878197 2023-01-23 21:38:21.700442: step: 1726/1545, loss: 0.00011563664156710729 2023-01-23 21:38:22.558420: step: 1728/1545, loss: 0.001063286210410297 2023-01-23 21:38:23.438881: step: 1730/1545, loss: 0.00019384981715120375 2023-01-23 21:38:24.287897: step: 1732/1545, loss: 2.4604758436908014e-05 2023-01-23 21:38:25.208346: step: 1734/1545, loss: 0.0008966774912551045 2023-01-23 21:38:26.082406: step: 1736/1545, loss: 0.0010378728620707989 2023-01-23 21:38:26.960539: step: 1738/1545, loss: 1.4432371244765818e-05 2023-01-23 21:38:27.821068: step: 1740/1545, loss: 0.00034514753497205675 2023-01-23 21:38:28.722902: step: 1742/1545, loss: 0.0008942252025008202 2023-01-23 21:38:29.584051: step: 1744/1545, loss: 1.3566058441938367e-05 2023-01-23 21:38:30.493399: step: 1746/1545, loss: 0.00019824010087177157 2023-01-23 21:38:31.379572: step: 1748/1545, loss: 0.007590459659695625 2023-01-23 21:38:32.226114: step: 1750/1545, loss: 0.032112136483192444 2023-01-23 21:38:33.079929: step: 1752/1545, loss: 0.0007868438842706382 2023-01-23 21:38:33.946221: step: 1754/1545, loss: 0.00021922588348388672 2023-01-23 21:38:34.830191: step: 1756/1545, loss: 0.0006096575525589287 2023-01-23 21:38:35.672613: step: 1758/1545, loss: 1.8401600755169056e-05 2023-01-23 21:38:36.552677: step: 1760/1545, loss: 0.03270273655653 2023-01-23 21:38:37.398162: step: 1762/1545, loss: 8.352266740985215e-05 2023-01-23 21:38:38.274800: step: 1764/1545, loss: 0.002354820491746068 2023-01-23 21:38:39.121657: step: 1766/1545, loss: 0.004560620523989201 2023-01-23 21:38:39.996907: step: 1768/1545, loss: 0.0003115871804766357 2023-01-23 21:38:40.875897: step: 1770/1545, loss: 0.0003263658145442605 2023-01-23 21:38:41.739504: step: 1772/1545, loss: 0.00035226158797740936 2023-01-23 21:38:42.598271: step: 1774/1545, loss: 0.006319491192698479 2023-01-23 21:38:43.424122: step: 1776/1545, loss: 0.0002963246079161763 2023-01-23 21:38:44.273874: step: 1778/1545, loss: -1.646196142246481e-05 2023-01-23 21:38:45.174239: step: 1780/1545, loss: 0.0006409602938219905 2023-01-23 21:38:46.008206: step: 1782/1545, loss: -2.5635786187194753e-06 2023-01-23 21:38:46.928829: step: 1784/1545, loss: 0.00020078770467080176 2023-01-23 21:38:47.785487: step: 1786/1545, loss: 1.9363835235708393e-05 2023-01-23 21:38:48.665826: step: 1788/1545, loss: 0.3425118625164032 2023-01-23 21:38:49.528068: step: 1790/1545, loss: 0.0005628041690215468 2023-01-23 21:38:50.419009: step: 1792/1545, loss: 0.011587980203330517 2023-01-23 21:38:51.259862: step: 1794/1545, loss: -1.7727609247231157e-06 2023-01-23 21:38:52.146242: step: 1796/1545, loss: 2.595260775706265e-05 2023-01-23 21:38:53.005012: step: 1798/1545, loss: 3.470465890131891e-05 2023-01-23 21:38:53.882668: step: 1800/1545, loss: 7.3822366175591014e-06 2023-01-23 21:38:54.732580: step: 1802/1545, loss: 0.00571442861109972 2023-01-23 21:38:55.547816: step: 1804/1545, loss: 5.349516868591309e-06 2023-01-23 21:38:56.419932: step: 1806/1545, loss: 0.00016330118523910642 2023-01-23 21:38:57.283420: step: 1808/1545, loss: 0.0001245534367626533 2023-01-23 21:38:58.178084: step: 1810/1545, loss: 0.027697768062353134 2023-01-23 21:38:59.048147: step: 1812/1545, loss: 0.001798613928258419 2023-01-23 21:38:59.933910: step: 1814/1545, loss: 6.415743700927123e-05 2023-01-23 21:39:00.802229: step: 1816/1545, loss: 7.869388355175033e-05 2023-01-23 21:39:01.667821: step: 1818/1545, loss: 0.5141481161117554 2023-01-23 21:39:02.530513: step: 1820/1545, loss: 3.580734301067423e-06 2023-01-23 21:39:03.447289: step: 1822/1545, loss: 0.31183338165283203 2023-01-23 21:39:04.351206: step: 1824/1545, loss: 0.0010081238579005003 2023-01-23 21:39:05.230290: step: 1826/1545, loss: 1.341044935543323e-05 2023-01-23 21:39:06.078329: step: 1828/1545, loss: 0.004330603871494532 2023-01-23 21:39:06.922793: step: 1830/1545, loss: 4.472769796848297e-05 2023-01-23 21:39:07.786207: step: 1832/1545, loss: 0.014308340847492218 2023-01-23 21:39:08.675802: step: 1834/1545, loss: 0.10050486773252487 2023-01-23 21:39:09.580641: step: 1836/1545, loss: 0.08069898933172226 2023-01-23 21:39:10.450792: step: 1838/1545, loss: 0.13292521238327026 2023-01-23 21:39:11.299238: step: 1840/1545, loss: 0.0006914804689586163 2023-01-23 21:39:12.131560: step: 1842/1545, loss: 0.003110297489911318 2023-01-23 21:39:13.040986: step: 1844/1545, loss: 1.9161403542966582e-05 2023-01-23 21:39:13.911016: step: 1846/1545, loss: 0.010022232308983803 2023-01-23 21:39:14.775643: step: 1848/1545, loss: 0.0001117836800403893 2023-01-23 21:39:15.655215: step: 1850/1545, loss: 0.0006456648115999997 2023-01-23 21:39:16.576901: step: 1852/1545, loss: 3.593436485971324e-05 2023-01-23 21:39:17.475914: step: 1854/1545, loss: 0.07251568883657455 2023-01-23 21:39:18.365610: step: 1856/1545, loss: 0.00041175982914865017 2023-01-23 21:39:19.223258: step: 1858/1545, loss: 6.020151704433374e-05 2023-01-23 21:39:20.127161: step: 1860/1545, loss: 0.18856580555438995 2023-01-23 21:39:20.983159: step: 1862/1545, loss: 5.579264325206168e-05 2023-01-23 21:39:21.925753: step: 1864/1545, loss: 1.978078762476798e-05 2023-01-23 21:39:22.784760: step: 1866/1545, loss: 0.006218039430677891 2023-01-23 21:39:23.656743: step: 1868/1545, loss: 0.007978946901857853 2023-01-23 21:39:24.483780: step: 1870/1545, loss: 0.06497980654239655 2023-01-23 21:39:25.350208: step: 1872/1545, loss: 0.0030850295443087816 2023-01-23 21:39:26.181336: step: 1874/1545, loss: 0.0003909068473149091 2023-01-23 21:39:27.066145: step: 1876/1545, loss: 0.009865598753094673 2023-01-23 21:39:27.934698: step: 1878/1545, loss: 0.0013266908936202526 2023-01-23 21:39:28.815814: step: 1880/1545, loss: 0.17096514999866486 2023-01-23 21:39:29.764910: step: 1882/1545, loss: 0.05801285058259964 2023-01-23 21:39:30.655607: step: 1884/1545, loss: 0.05796024948358536 2023-01-23 21:39:31.582564: step: 1886/1545, loss: 0.00904861744493246 2023-01-23 21:39:32.427408: step: 1888/1545, loss: 4.0209528378909454e-05 2023-01-23 21:39:33.282292: step: 1890/1545, loss: 9.867890912573785e-05 2023-01-23 21:39:34.233123: step: 1892/1545, loss: 4.361184983281419e-05 2023-01-23 21:39:35.116398: step: 1894/1545, loss: 1.4256459508033004e-05 2023-01-23 21:39:36.014163: step: 1896/1545, loss: 0.3085666298866272 2023-01-23 21:39:36.886911: step: 1898/1545, loss: 0.09122808277606964 2023-01-23 21:39:37.757013: step: 1900/1545, loss: 0.009959293529391289 2023-01-23 21:39:38.637498: step: 1902/1545, loss: 3.7814628740306944e-05 2023-01-23 21:39:39.507608: step: 1904/1545, loss: 0.00015734184125903994 2023-01-23 21:39:40.418738: step: 1906/1545, loss: 0.00014126503083389252 2023-01-23 21:39:41.317748: step: 1908/1545, loss: 0.00700520072132349 2023-01-23 21:39:42.166480: step: 1910/1545, loss: 0.0002503482101019472 2023-01-23 21:39:43.160749: step: 1912/1545, loss: 0.5737066864967346 2023-01-23 21:39:44.075587: step: 1914/1545, loss: 0.001734230318106711 2023-01-23 21:39:45.023445: step: 1916/1545, loss: 0.1486591398715973 2023-01-23 21:39:45.861997: step: 1918/1545, loss: 0.00042644236236810684 2023-01-23 21:39:46.756668: step: 1920/1545, loss: 0.006511842366307974 2023-01-23 21:39:47.769297: step: 1922/1545, loss: 0.014076282270252705 2023-01-23 21:39:48.700931: step: 1924/1545, loss: 0.004138519521802664 2023-01-23 21:39:49.583441: step: 1926/1545, loss: 0.0001206758533953689 2023-01-23 21:39:50.413037: step: 1928/1545, loss: 0.0002509007463231683 2023-01-23 21:39:51.298296: step: 1930/1545, loss: 0.00018486219050828367 2023-01-23 21:39:52.199203: step: 1932/1545, loss: 0.022205088287591934 2023-01-23 21:39:53.011356: step: 1934/1545, loss: 2.2537726181326434e-05 2023-01-23 21:39:53.856237: step: 1936/1545, loss: 0.00425467174500227 2023-01-23 21:39:54.698158: step: 1938/1545, loss: 0.0011755272280424833 2023-01-23 21:39:55.555990: step: 1940/1545, loss: -2.516310996725224e-05 2023-01-23 21:39:56.449351: step: 1942/1545, loss: 0.0016916455933824182 2023-01-23 21:39:57.295091: step: 1944/1545, loss: 0.11683125048875809 2023-01-23 21:39:58.281422: step: 1946/1545, loss: 0.15331503748893738 2023-01-23 21:39:59.179985: step: 1948/1545, loss: 0.00870536919683218 2023-01-23 21:40:00.025663: step: 1950/1545, loss: 2.3278591470443644e-05 2023-01-23 21:40:00.888813: step: 1952/1545, loss: 0.01963150128722191 2023-01-23 21:40:01.749629: step: 1954/1545, loss: 0.0010992020834237337 2023-01-23 21:40:02.673731: step: 1956/1545, loss: 0.00025763470330275595 2023-01-23 21:40:03.554398: step: 1958/1545, loss: 0.00012174640141893178 2023-01-23 21:40:04.457104: step: 1960/1545, loss: 0.0032203930895775557 2023-01-23 21:40:05.343038: step: 1962/1545, loss: 0.0006642910884693265 2023-01-23 21:40:06.219093: step: 1964/1545, loss: 0.10433345288038254 2023-01-23 21:40:07.087910: step: 1966/1545, loss: 0.5089153051376343 2023-01-23 21:40:08.024415: step: 1968/1545, loss: 0.0004306910268496722 2023-01-23 21:40:08.907092: step: 1970/1545, loss: 0.0002250353863928467 2023-01-23 21:40:09.812685: step: 1972/1545, loss: 0.0006061061285436153 2023-01-23 21:40:10.707935: step: 1974/1545, loss: 0.007585692219436169 2023-01-23 21:40:11.570195: step: 1976/1545, loss: 0.1791389286518097 2023-01-23 21:40:12.448761: step: 1978/1545, loss: 0.001481100101955235 2023-01-23 21:40:13.289802: step: 1980/1545, loss: 0.0030565618071705103 2023-01-23 21:40:14.139774: step: 1982/1545, loss: 0.0008206064230762422 2023-01-23 21:40:15.019702: step: 1984/1545, loss: 0.009604285471141338 2023-01-23 21:40:15.936638: step: 1986/1545, loss: 0.4089954197406769 2023-01-23 21:40:16.783773: step: 1988/1545, loss: 0.000608994800131768 2023-01-23 21:40:17.638417: step: 1990/1545, loss: 0.004992152098566294 2023-01-23 21:40:18.490352: step: 1992/1545, loss: 0.0019377588760107756 2023-01-23 21:40:19.405056: step: 1994/1545, loss: 0.0003307185834273696 2023-01-23 21:40:20.230045: step: 1996/1545, loss: 0.000545805087313056 2023-01-23 21:40:21.169574: step: 1998/1545, loss: 0.011379062198102474 2023-01-23 21:40:22.031645: step: 2000/1545, loss: 0.004029877483844757 2023-01-23 21:40:22.933885: step: 2002/1545, loss: 0.0013503560330718756 2023-01-23 21:40:23.827248: step: 2004/1545, loss: 0.3809930980205536 2023-01-23 21:40:24.668233: step: 2006/1545, loss: 0.03298363462090492 2023-01-23 21:40:25.539478: step: 2008/1545, loss: 0.0007108484860509634 2023-01-23 21:40:26.438930: step: 2010/1545, loss: 0.30186906456947327 2023-01-23 21:40:27.300866: step: 2012/1545, loss: 0.009456590749323368 2023-01-23 21:40:28.307496: step: 2014/1545, loss: 0.00011510893818922341 2023-01-23 21:40:29.258723: step: 2016/1545, loss: 0.002884120447561145 2023-01-23 21:40:30.224618: step: 2018/1545, loss: 0.00035430077696219087 2023-01-23 21:40:31.083713: step: 2020/1545, loss: 0.0027466481551527977 2023-01-23 21:40:31.942144: step: 2022/1545, loss: 5.063911885372363e-05 2023-01-23 21:40:32.794541: step: 2024/1545, loss: 0.0004309325304348022 2023-01-23 21:40:33.674528: step: 2026/1545, loss: 0.01842380501329899 2023-01-23 21:40:34.523689: step: 2028/1545, loss: 0.0022830693051218987 2023-01-23 21:40:35.421218: step: 2030/1545, loss: 0.005865831859409809 2023-01-23 21:40:36.346413: step: 2032/1545, loss: 0.0014122070278972387 2023-01-23 21:40:37.204513: step: 2034/1545, loss: 0.01340862549841404 2023-01-23 21:40:38.043878: step: 2036/1545, loss: 0.0006029545329511166 2023-01-23 21:40:38.943706: step: 2038/1545, loss: 0.225399449467659 2023-01-23 21:40:39.875797: step: 2040/1545, loss: 0.002318166894838214 2023-01-23 21:40:40.726756: step: 2042/1545, loss: 0.002437189919874072 2023-01-23 21:40:41.625087: step: 2044/1545, loss: 0.00013661175034940243 2023-01-23 21:40:42.545928: step: 2046/1545, loss: 0.002680719830095768 2023-01-23 21:40:43.413993: step: 2048/1545, loss: 0.1639990657567978 2023-01-23 21:40:44.317869: step: 2050/1545, loss: 0.00017637912242207676 2023-01-23 21:40:45.149411: step: 2052/1545, loss: 0.0003192694275639951 2023-01-23 21:40:46.046342: step: 2054/1545, loss: 0.06210516020655632 2023-01-23 21:40:46.913772: step: 2056/1545, loss: 0.19420738518238068 2023-01-23 21:40:47.773756: step: 2058/1545, loss: 5.021902688895352e-05 2023-01-23 21:40:48.713470: step: 2060/1545, loss: 0.00021144120546523482 2023-01-23 21:40:49.589881: step: 2062/1545, loss: 0.0968957170844078 2023-01-23 21:40:50.482565: step: 2064/1545, loss: 0.03045390173792839 2023-01-23 21:40:51.310749: step: 2066/1545, loss: 0.00011054820788558573 2023-01-23 21:40:52.195144: step: 2068/1545, loss: 0.00024398663663305342 2023-01-23 21:40:53.049121: step: 2070/1545, loss: 0.0006257476634345949 2023-01-23 21:40:53.960453: step: 2072/1545, loss: 0.008427873253822327 2023-01-23 21:40:54.897622: step: 2074/1545, loss: 0.08326946198940277 2023-01-23 21:40:55.820679: step: 2076/1545, loss: 0.00014551998174283653 2023-01-23 21:40:56.688656: step: 2078/1545, loss: 8.551131759304553e-05 2023-01-23 21:40:57.582333: step: 2080/1545, loss: 5.9923622757196426e-05 2023-01-23 21:40:58.545277: step: 2082/1545, loss: 0.0004957071505486965 2023-01-23 21:40:59.379401: step: 2084/1545, loss: 0.005555286072194576 2023-01-23 21:41:00.300363: step: 2086/1545, loss: 0.0013433954445645213 2023-01-23 21:41:01.213937: step: 2088/1545, loss: 0.10866750776767731 2023-01-23 21:41:02.138208: step: 2090/1545, loss: 0.0012306327698752284 2023-01-23 21:41:03.026936: step: 2092/1545, loss: 0.03435178101062775 2023-01-23 21:41:03.859822: step: 2094/1545, loss: 0.00015384654398076236 2023-01-23 21:41:04.693112: step: 2096/1545, loss: 7.027201354503632e-05 2023-01-23 21:41:05.554881: step: 2098/1545, loss: 0.0007487027905881405 2023-01-23 21:41:06.384935: step: 2100/1545, loss: 1.233997227245709e-05 2023-01-23 21:41:07.238712: step: 2102/1545, loss: 4.429817636264488e-05 2023-01-23 21:41:08.095508: step: 2104/1545, loss: 1.6486228560097516e-07 2023-01-23 21:41:08.982124: step: 2106/1545, loss: 0.19411000609397888 2023-01-23 21:41:09.835152: step: 2108/1545, loss: 0.05026726424694061 2023-01-23 21:41:10.703137: step: 2110/1545, loss: 0.0009910663357004523 2023-01-23 21:41:11.541904: step: 2112/1545, loss: 0.008569066412746906 2023-01-23 21:41:12.395741: step: 2114/1545, loss: 4.783636541105807e-06 2023-01-23 21:41:13.248318: step: 2116/1545, loss: 0.37566274404525757 2023-01-23 21:41:14.084006: step: 2118/1545, loss: 0.012754986993968487 2023-01-23 21:41:14.928645: step: 2120/1545, loss: 0.0001247975742444396 2023-01-23 21:41:15.769353: step: 2122/1545, loss: 5.06416690768674e-05 2023-01-23 21:41:16.624662: step: 2124/1545, loss: 0.03441166877746582 2023-01-23 21:41:17.585860: step: 2126/1545, loss: 3.894239489454776e-05 2023-01-23 21:41:18.460151: step: 2128/1545, loss: 0.00020177915575914085 2023-01-23 21:41:19.329888: step: 2130/1545, loss: 0.08711101859807968 2023-01-23 21:41:20.186332: step: 2132/1545, loss: 0.0004286831244826317 2023-01-23 21:41:21.038347: step: 2134/1545, loss: 9.626746759749949e-05 2023-01-23 21:41:21.936952: step: 2136/1545, loss: 0.0026493638288229704 2023-01-23 21:41:22.852007: step: 2138/1545, loss: 0.08474738895893097 2023-01-23 21:41:23.692005: step: 2140/1545, loss: 0.0012911232188344002 2023-01-23 21:41:24.558576: step: 2142/1545, loss: 0.0014763735234737396 2023-01-23 21:41:25.430143: step: 2144/1545, loss: 0.0002708032843656838 2023-01-23 21:41:26.300797: step: 2146/1545, loss: 0.014603978954255581 2023-01-23 21:41:27.221464: step: 2148/1545, loss: 0.0019008450908586383 2023-01-23 21:41:28.090260: step: 2150/1545, loss: 0.03423616290092468 2023-01-23 21:41:28.964477: step: 2152/1545, loss: 0.022952210158109665 2023-01-23 21:41:29.825117: step: 2154/1545, loss: 1.4744278814760037e-05 2023-01-23 21:41:30.673331: step: 2156/1545, loss: 0.16927726566791534 2023-01-23 21:41:31.570993: step: 2158/1545, loss: 0.003296070033684373 2023-01-23 21:41:32.427305: step: 2160/1545, loss: 0.010987070389091969 2023-01-23 21:41:33.293075: step: 2162/1545, loss: 0.10749341547489166 2023-01-23 21:41:34.199415: step: 2164/1545, loss: 0.015310166403651237 2023-01-23 21:41:35.046017: step: 2166/1545, loss: 7.606303552165627e-05 2023-01-23 21:41:35.899399: step: 2168/1545, loss: 0.0002104491286445409 2023-01-23 21:41:36.755088: step: 2170/1545, loss: 0.008724437095224857 2023-01-23 21:41:37.629673: step: 2172/1545, loss: 0.0001271784567506984 2023-01-23 21:41:38.501265: step: 2174/1545, loss: 0.000419297837652266 2023-01-23 21:41:39.347737: step: 2176/1545, loss: 0.00013317455886863172 2023-01-23 21:41:40.262488: step: 2178/1545, loss: 0.004347148351371288 2023-01-23 21:41:41.119056: step: 2180/1545, loss: 0.005388411693274975 2023-01-23 21:41:41.999377: step: 2182/1545, loss: 0.0006411102949641645 2023-01-23 21:41:42.834154: step: 2184/1545, loss: 0.003308527637273073 2023-01-23 21:41:43.716395: step: 2186/1545, loss: 9.090459934668615e-05 2023-01-23 21:41:44.588702: step: 2188/1545, loss: 0.002943225670605898 2023-01-23 21:41:45.451590: step: 2190/1545, loss: 0.00013790356751997024 2023-01-23 21:41:46.313826: step: 2192/1545, loss: 0.020438186824321747 2023-01-23 21:41:47.158168: step: 2194/1545, loss: 0.00022848843946121633 2023-01-23 21:41:48.033393: step: 2196/1545, loss: 0.025119278579950333 2023-01-23 21:41:48.875784: step: 2198/1545, loss: 0.08707288652658463 2023-01-23 21:41:49.733157: step: 2200/1545, loss: 0.004958838224411011 2023-01-23 21:41:50.606767: step: 2202/1545, loss: 0.00023958546807989478 2023-01-23 21:41:51.464491: step: 2204/1545, loss: 0.0033350561279803514 2023-01-23 21:41:52.328463: step: 2206/1545, loss: 4.778370202984661e-05 2023-01-23 21:41:53.173724: step: 2208/1545, loss: 6.878872227389365e-05 2023-01-23 21:41:54.109645: step: 2210/1545, loss: 0.12860780954360962 2023-01-23 21:41:55.060123: step: 2212/1545, loss: 2.108846426010132 2023-01-23 21:41:55.934434: step: 2214/1545, loss: 0.00018660782370716333 2023-01-23 21:41:56.798201: step: 2216/1545, loss: 0.00495564891025424 2023-01-23 21:41:57.632108: step: 2218/1545, loss: 0.0016592140309512615 2023-01-23 21:41:58.498787: step: 2220/1545, loss: 0.0023681162856519222 2023-01-23 21:41:59.384939: step: 2222/1545, loss: 0.007527788635343313 2023-01-23 21:42:00.259663: step: 2224/1545, loss: 0.007565283216536045 2023-01-23 21:42:01.131675: step: 2226/1545, loss: 0.0016316873952746391 2023-01-23 21:42:01.969603: step: 2228/1545, loss: 0.00010873822611756623 2023-01-23 21:42:02.802680: step: 2230/1545, loss: 0.00023390202841255814 2023-01-23 21:42:03.665220: step: 2232/1545, loss: 7.85888551035896e-05 2023-01-23 21:42:04.553538: step: 2234/1545, loss: 0.008958167396485806 2023-01-23 21:42:05.456048: step: 2236/1545, loss: 0.24775418639183044 2023-01-23 21:42:06.340875: step: 2238/1545, loss: 0.029746776446700096 2023-01-23 21:42:07.252135: step: 2240/1545, loss: 0.0003548781096469611 2023-01-23 21:42:08.144768: step: 2242/1545, loss: 0.00010744809696916491 2023-01-23 21:42:09.013406: step: 2244/1545, loss: 0.004182761535048485 2023-01-23 21:42:09.886752: step: 2246/1545, loss: 0.0012032174272462726 2023-01-23 21:42:10.831196: step: 2248/1545, loss: 0.011081770993769169 2023-01-23 21:42:11.700452: step: 2250/1545, loss: 0.0015425544697791338 2023-01-23 21:42:12.620775: step: 2252/1545, loss: 0.00040738863754086196 2023-01-23 21:42:13.549184: step: 2254/1545, loss: 5.559701094171032e-05 2023-01-23 21:42:14.421307: step: 2256/1545, loss: 0.299191951751709 2023-01-23 21:42:15.290688: step: 2258/1545, loss: 0.1689506620168686 2023-01-23 21:42:16.138245: step: 2260/1545, loss: 0.0013844252098351717 2023-01-23 21:42:17.044351: step: 2262/1545, loss: 0.002790294587612152 2023-01-23 21:42:17.909013: step: 2264/1545, loss: 0.0004704880411736667 2023-01-23 21:42:18.737288: step: 2266/1545, loss: 0.06350761651992798 2023-01-23 21:42:19.596809: step: 2268/1545, loss: 4.0249993617180735e-05 2023-01-23 21:42:20.488226: step: 2270/1545, loss: 0.00042670444236136973 2023-01-23 21:42:21.337220: step: 2272/1545, loss: 0.0015336974756792188 2023-01-23 21:42:22.219000: step: 2274/1545, loss: 0.00020626577315852046 2023-01-23 21:42:23.130668: step: 2276/1545, loss: 0.0006572259007953107 2023-01-23 21:42:24.048308: step: 2278/1545, loss: 0.0037962356582283974 2023-01-23 21:42:24.917545: step: 2280/1545, loss: 0.00020588577899616212 2023-01-23 21:42:25.749543: step: 2282/1545, loss: 0.008475186303257942 2023-01-23 21:42:26.611820: step: 2284/1545, loss: 0.006679709069430828 2023-01-23 21:42:27.478339: step: 2286/1545, loss: 0.0004831136902794242 2023-01-23 21:42:28.385040: step: 2288/1545, loss: 0.1902315318584442 2023-01-23 21:42:29.233831: step: 2290/1545, loss: 0.00038141425466164947 2023-01-23 21:42:30.120199: step: 2292/1545, loss: 0.00013857109297532588 2023-01-23 21:42:30.964967: step: 2294/1545, loss: 0.040131885558366776 2023-01-23 21:42:31.816610: step: 2296/1545, loss: 0.014833648689091206 2023-01-23 21:42:32.643300: step: 2298/1545, loss: 0.00010319747525500134 2023-01-23 21:42:33.505454: step: 2300/1545, loss: 0.000835361541248858 2023-01-23 21:42:34.493345: step: 2302/1545, loss: 0.0007844083593226969 2023-01-23 21:42:35.359742: step: 2304/1545, loss: 0.0019375805277377367 2023-01-23 21:42:36.241613: step: 2306/1545, loss: 0.0010800176532939076 2023-01-23 21:42:37.111679: step: 2308/1545, loss: 0.00015850277850404382 2023-01-23 21:42:37.999948: step: 2310/1545, loss: 0.013558516278862953 2023-01-23 21:42:38.845822: step: 2312/1545, loss: 0.14612634479999542 2023-01-23 21:42:39.723792: step: 2314/1545, loss: 0.2642766237258911 2023-01-23 21:42:40.570235: step: 2316/1545, loss: 0.005497832782566547 2023-01-23 21:42:41.413298: step: 2318/1545, loss: 0.0003462283930275589 2023-01-23 21:42:42.295893: step: 2320/1545, loss: 0.00011057446681661531 2023-01-23 21:42:43.177564: step: 2322/1545, loss: 0.05636243894696236 2023-01-23 21:42:44.079090: step: 2324/1545, loss: 0.03759344294667244 2023-01-23 21:42:44.940832: step: 2326/1545, loss: 0.08044637739658356 2023-01-23 21:42:45.883348: step: 2328/1545, loss: 0.051562339067459106 2023-01-23 21:42:46.729972: step: 2330/1545, loss: 0.0010635590879246593 2023-01-23 21:42:47.605555: step: 2332/1545, loss: 0.008652877993881702 2023-01-23 21:42:48.467307: step: 2334/1545, loss: 0.0004362027102615684 2023-01-23 21:42:49.337410: step: 2336/1545, loss: 0.021332042291760445 2023-01-23 21:42:50.191881: step: 2338/1545, loss: 7.676029053982347e-05 2023-01-23 21:42:51.062362: step: 2340/1545, loss: 0.0008283544448204339 2023-01-23 21:42:51.931168: step: 2342/1545, loss: 0.005862735211849213 2023-01-23 21:42:52.807864: step: 2344/1545, loss: -1.1040458048228174e-05 2023-01-23 21:42:53.684762: step: 2346/1545, loss: 0.00022663951676804572 2023-01-23 21:42:54.583665: step: 2348/1545, loss: 7.332923996727914e-05 2023-01-23 21:42:55.471761: step: 2350/1545, loss: 0.044324591755867004 2023-01-23 21:42:56.314744: step: 2352/1545, loss: 0.021800251677632332 2023-01-23 21:42:57.170604: step: 2354/1545, loss: 0.0006698858342133462 2023-01-23 21:42:58.068518: step: 2356/1545, loss: 0.004996136762201786 2023-01-23 21:42:59.037253: step: 2358/1545, loss: 0.11415702104568481 2023-01-23 21:42:59.905685: step: 2360/1545, loss: 0.00020703786867670715 2023-01-23 21:43:00.761241: step: 2362/1545, loss: 0.08108477294445038 2023-01-23 21:43:01.686713: step: 2364/1545, loss: 0.1850261241197586 2023-01-23 21:43:02.539156: step: 2366/1545, loss: 6.58948629279621e-05 2023-01-23 21:43:03.415035: step: 2368/1545, loss: 0.17081695795059204 2023-01-23 21:43:04.300140: step: 2370/1545, loss: 0.012311817146837711 2023-01-23 21:43:05.174897: step: 2372/1545, loss: 0.0029484648257493973 2023-01-23 21:43:06.061938: step: 2374/1545, loss: 6.379126716637984e-05 2023-01-23 21:43:06.913881: step: 2376/1545, loss: 0.003903608536347747 2023-01-23 21:43:07.813580: step: 2378/1545, loss: 0.0005193883553147316 2023-01-23 21:43:08.667008: step: 2380/1545, loss: 0.00034614859032444656 2023-01-23 21:43:09.550926: step: 2382/1545, loss: 0.015564493834972382 2023-01-23 21:43:10.388718: step: 2384/1545, loss: 0.004061688203364611 2023-01-23 21:43:11.321127: step: 2386/1545, loss: 9.065369522431865e-05 2023-01-23 21:43:12.197299: step: 2388/1545, loss: 0.00011350997374393046 2023-01-23 21:43:13.040089: step: 2390/1545, loss: 0.00013891955313738436 2023-01-23 21:43:13.883370: step: 2392/1545, loss: 0.0007510040886700153 2023-01-23 21:43:14.839958: step: 2394/1545, loss: 0.5273915529251099 2023-01-23 21:43:15.702043: step: 2396/1545, loss: 0.00043455613194964826 2023-01-23 21:43:16.542206: step: 2398/1545, loss: 0.34682169556617737 2023-01-23 21:43:17.402727: step: 2400/1545, loss: 0.0005934890941716731 2023-01-23 21:43:18.287614: step: 2402/1545, loss: 0.029088100418448448 2023-01-23 21:43:19.118972: step: 2404/1545, loss: 0.003058524802327156 2023-01-23 21:43:20.003076: step: 2406/1545, loss: 0.001075735897757113 2023-01-23 21:43:20.859006: step: 2408/1545, loss: 0.0011285743676126003 2023-01-23 21:43:21.737903: step: 2410/1545, loss: 0.08217830955982208 2023-01-23 21:43:22.627815: step: 2412/1545, loss: 0.001090419478714466 2023-01-23 21:43:23.506814: step: 2414/1545, loss: 0.3153904378414154 2023-01-23 21:43:24.412323: step: 2416/1545, loss: 0.000313501397613436 2023-01-23 21:43:25.282576: step: 2418/1545, loss: 0.007732596714049578 2023-01-23 21:43:26.133848: step: 2420/1545, loss: 0.010983486659824848 2023-01-23 21:43:26.964572: step: 2422/1545, loss: 9.34741910896264e-05 2023-01-23 21:43:27.810762: step: 2424/1545, loss: 0.0005968894110992551 2023-01-23 21:43:28.724117: step: 2426/1545, loss: 0.0015888889320194721 2023-01-23 21:43:29.592020: step: 2428/1545, loss: 0.003996659070253372 2023-01-23 21:43:30.464274: step: 2430/1545, loss: 0.006219146307557821 2023-01-23 21:43:31.417163: step: 2432/1545, loss: 0.0028959037736058235 2023-01-23 21:43:32.361739: step: 2434/1545, loss: 0.006109613459557295 2023-01-23 21:43:33.217955: step: 2436/1545, loss: 7.457916126440978e-06 2023-01-23 21:43:34.083334: step: 2438/1545, loss: 0.00025238023954443634 2023-01-23 21:43:35.001876: step: 2440/1545, loss: 0.08267441391944885 2023-01-23 21:43:35.889969: step: 2442/1545, loss: 0.00017582077998667955 2023-01-23 21:43:36.818151: step: 2444/1545, loss: 0.02241840586066246 2023-01-23 21:43:37.707299: step: 2446/1545, loss: 0.0005879358504898846 2023-01-23 21:43:38.633049: step: 2448/1545, loss: 0.011441638693213463 2023-01-23 21:43:39.530399: step: 2450/1545, loss: 0.004310954827815294 2023-01-23 21:43:40.401063: step: 2452/1545, loss: 0.07657669484615326 2023-01-23 21:43:41.259339: step: 2454/1545, loss: 0.009636598639190197 2023-01-23 21:43:42.130592: step: 2456/1545, loss: 2.150258660549298e-05 2023-01-23 21:43:43.029459: step: 2458/1545, loss: 0.0019666014704853296 2023-01-23 21:43:43.919384: step: 2460/1545, loss: 0.560206413269043 2023-01-23 21:43:44.828182: step: 2462/1545, loss: 2.6036888812086545e-05 2023-01-23 21:43:45.709622: step: 2464/1545, loss: 0.015853948891162872 2023-01-23 21:43:46.574477: step: 2466/1545, loss: 0.007537463214248419 2023-01-23 21:43:47.503227: step: 2468/1545, loss: 0.4008001983165741 2023-01-23 21:43:48.325202: step: 2470/1545, loss: 0.001793685252778232 2023-01-23 21:43:49.294671: step: 2472/1545, loss: -4.806017386727035e-06 2023-01-23 21:43:50.139311: step: 2474/1545, loss: 0.1638677716255188 2023-01-23 21:43:51.031093: step: 2476/1545, loss: 9.27402070374228e-05 2023-01-23 21:43:51.885649: step: 2478/1545, loss: 1.9281249478808604e-05 2023-01-23 21:43:52.791071: step: 2480/1545, loss: 0.06246143952012062 2023-01-23 21:43:53.788629: step: 2482/1545, loss: 0.5736625790596008 2023-01-23 21:43:54.652433: step: 2484/1545, loss: 0.07094775140285492 2023-01-23 21:43:55.555676: step: 2486/1545, loss: 0.0007870127446949482 2023-01-23 21:43:56.361862: step: 2488/1545, loss: 2.4932622181950137e-05 2023-01-23 21:43:57.271737: step: 2490/1545, loss: 0.00016565396799705923 2023-01-23 21:43:58.151581: step: 2492/1545, loss: 0.3757457137107849 2023-01-23 21:43:59.051239: step: 2494/1545, loss: 0.020392827689647675 2023-01-23 21:43:59.946973: step: 2496/1545, loss: 0.003594940062612295 2023-01-23 21:44:00.754564: step: 2498/1545, loss: 0.00034650246379897 2023-01-23 21:44:01.601331: step: 2500/1545, loss: 0.29576465487480164 2023-01-23 21:44:02.450771: step: 2502/1545, loss: 0.057826604694128036 2023-01-23 21:44:03.305866: step: 2504/1545, loss: 0.00427062064409256 2023-01-23 21:44:04.193811: step: 2506/1545, loss: 0.00020073528867214918 2023-01-23 21:44:05.080855: step: 2508/1545, loss: 0.0689755454659462 2023-01-23 21:44:05.980533: step: 2510/1545, loss: 0.00034477069857530296 2023-01-23 21:44:06.825982: step: 2512/1545, loss: 0.0014921354595571756 2023-01-23 21:44:07.759015: step: 2514/1545, loss: 0.02064027637243271 2023-01-23 21:44:08.627915: step: 2516/1545, loss: 0.018583688884973526 2023-01-23 21:44:09.508060: step: 2518/1545, loss: 4.052111034980044e-05 2023-01-23 21:44:10.400036: step: 2520/1545, loss: 0.00021631391427945346 2023-01-23 21:44:11.273923: step: 2522/1545, loss: 0.029819682240486145 2023-01-23 21:44:12.142383: step: 2524/1545, loss: 0.0004413046990521252 2023-01-23 21:44:12.982004: step: 2526/1545, loss: 0.8493931889533997 2023-01-23 21:44:13.911259: step: 2528/1545, loss: 0.00375212449580431 2023-01-23 21:44:14.741491: step: 2530/1545, loss: 0.0012984644854441285 2023-01-23 21:44:15.632956: step: 2532/1545, loss: 0.0404047891497612 2023-01-23 21:44:16.540013: step: 2534/1545, loss: 0.011832542717456818 2023-01-23 21:44:17.453631: step: 2536/1545, loss: 0.03982163965702057 2023-01-23 21:44:18.365731: step: 2538/1545, loss: 0.00025992299197241664 2023-01-23 21:44:19.247327: step: 2540/1545, loss: 0.00012880493886768818 2023-01-23 21:44:20.131402: step: 2542/1545, loss: 0.07415366917848587 2023-01-23 21:44:21.021736: step: 2544/1545, loss: 0.00034030014649033546 2023-01-23 21:44:21.906291: step: 2546/1545, loss: 0.0008426558924838901 2023-01-23 21:44:22.745609: step: 2548/1545, loss: 0.0011608951026573777 2023-01-23 21:44:23.622685: step: 2550/1545, loss: 0.001548335305415094 2023-01-23 21:44:24.528764: step: 2552/1545, loss: 0.007817137986421585 2023-01-23 21:44:25.359473: step: 2554/1545, loss: 3.2282892789226025e-05 2023-01-23 21:44:26.207093: step: 2556/1545, loss: 0.0002889227762352675 2023-01-23 21:44:27.109105: step: 2558/1545, loss: 0.0005669047823175788 2023-01-23 21:44:27.963024: step: 2560/1545, loss: 0.18921445310115814 2023-01-23 21:44:28.802583: step: 2562/1545, loss: 0.0016914884326979518 2023-01-23 21:44:29.751587: step: 2564/1545, loss: 0.008202305994927883 2023-01-23 21:44:30.614838: step: 2566/1545, loss: 0.024045126512646675 2023-01-23 21:44:31.499913: step: 2568/1545, loss: 0.03574893996119499 2023-01-23 21:44:32.378580: step: 2570/1545, loss: 0.0374770388007164 2023-01-23 21:44:33.237393: step: 2572/1545, loss: 0.011281556449830532 2023-01-23 21:44:34.110661: step: 2574/1545, loss: 3.8047870475566015e-05 2023-01-23 21:44:34.985099: step: 2576/1545, loss: 0.2537848651409149 2023-01-23 21:44:35.864634: step: 2578/1545, loss: 0.00023716520809102803 2023-01-23 21:44:36.747491: step: 2580/1545, loss: 0.027474889531731606 2023-01-23 21:44:37.583628: step: 2582/1545, loss: 0.0009602185455150902 2023-01-23 21:44:38.411629: step: 2584/1545, loss: 0.0002730382839217782 2023-01-23 21:44:39.326440: step: 2586/1545, loss: 0.004004990216344595 2023-01-23 21:44:40.219030: step: 2588/1545, loss: 0.08290877938270569 2023-01-23 21:44:41.088292: step: 2590/1545, loss: 0.12910358607769012 2023-01-23 21:44:41.985162: step: 2592/1545, loss: 8.98256985237822e-05 2023-01-23 21:44:42.863773: step: 2594/1545, loss: 8.495777728967369e-05 2023-01-23 21:44:43.758734: step: 2596/1545, loss: 7.294669194379821e-05 2023-01-23 21:44:44.661138: step: 2598/1545, loss: 0.0006849033525213599 2023-01-23 21:44:45.635266: step: 2600/1545, loss: 0.019060296937823296 2023-01-23 21:44:46.534641: step: 2602/1545, loss: 0.008435077965259552 2023-01-23 21:44:47.453939: step: 2604/1545, loss: 0.4476975202560425 2023-01-23 21:44:48.346844: step: 2606/1545, loss: 0.00023736146977171302 2023-01-23 21:44:49.235808: step: 2608/1545, loss: 0.021859101951122284 2023-01-23 21:44:50.133154: step: 2610/1545, loss: 0.0037288935855031013 2023-01-23 21:44:50.988132: step: 2612/1545, loss: 0.0003779672260861844 2023-01-23 21:44:51.858028: step: 2614/1545, loss: 5.457610768644372e-06 2023-01-23 21:44:52.716078: step: 2616/1545, loss: 0.00014592675142921507 2023-01-23 21:44:53.590305: step: 2618/1545, loss: 0.00021193799329921603 2023-01-23 21:44:54.453506: step: 2620/1545, loss: 0.226113960146904 2023-01-23 21:44:55.333497: step: 2622/1545, loss: 0.6201204657554626 2023-01-23 21:44:56.217817: step: 2624/1545, loss: 0.000918546924367547 2023-01-23 21:44:57.157592: step: 2626/1545, loss: 0.00010915688471868634 2023-01-23 21:44:58.002025: step: 2628/1545, loss: 0.0008254572749137878 2023-01-23 21:44:58.907449: step: 2630/1545, loss: 0.05600999295711517 2023-01-23 21:44:59.810123: step: 2632/1545, loss: 0.01588635891675949 2023-01-23 21:45:00.677484: step: 2634/1545, loss: 4.342554530012421e-05 2023-01-23 21:45:01.557736: step: 2636/1545, loss: 0.02826845645904541 2023-01-23 21:45:02.396651: step: 2638/1545, loss: 7.385518256342039e-05 2023-01-23 21:45:03.237837: step: 2640/1545, loss: 0.010959011502563953 2023-01-23 21:45:04.116821: step: 2642/1545, loss: 0.00013647816376760602 2023-01-23 21:45:05.009060: step: 2644/1545, loss: 0.008519182913005352 2023-01-23 21:45:05.855225: step: 2646/1545, loss: 0.004000321961939335 2023-01-23 21:45:06.714416: step: 2648/1545, loss: 0.04974604770541191 2023-01-23 21:45:07.559691: step: 2650/1545, loss: 0.001026930520310998 2023-01-23 21:45:08.408479: step: 2652/1545, loss: 0.0009122088667936623 2023-01-23 21:45:09.314518: step: 2654/1545, loss: 0.00025484320940449834 2023-01-23 21:45:10.156938: step: 2656/1545, loss: 0.002572437049821019 2023-01-23 21:45:11.025864: step: 2658/1545, loss: 0.010382005013525486 2023-01-23 21:45:11.860537: step: 2660/1545, loss: 0.0003423040616326034 2023-01-23 21:45:12.724413: step: 2662/1545, loss: 0.08595900982618332 2023-01-23 21:45:13.594163: step: 2664/1545, loss: 0.0014351573772728443 2023-01-23 21:45:14.474234: step: 2666/1545, loss: 0.13575316965579987 2023-01-23 21:45:15.332841: step: 2668/1545, loss: 0.0005469847237691283 2023-01-23 21:45:16.192188: step: 2670/1545, loss: 0.0013688316103070974 2023-01-23 21:45:17.097306: step: 2672/1545, loss: 0.017412396147847176 2023-01-23 21:45:17.982740: step: 2674/1545, loss: 0.12472345679998398 2023-01-23 21:45:18.860069: step: 2676/1545, loss: 0.0063451603055000305 2023-01-23 21:45:19.698095: step: 2678/1545, loss: 0.0002724375808611512 2023-01-23 21:45:20.589206: step: 2680/1545, loss: 0.011613760143518448 2023-01-23 21:45:21.467224: step: 2682/1545, loss: 0.002913756761699915 2023-01-23 21:45:22.326003: step: 2684/1545, loss: 0.005321661476045847 2023-01-23 21:45:23.234310: step: 2686/1545, loss: 0.07866064459085464 2023-01-23 21:45:24.217311: step: 2688/1545, loss: 0.45085394382476807 2023-01-23 21:45:25.038666: step: 2690/1545, loss: 0.008440801873803139 2023-01-23 21:45:25.869945: step: 2692/1545, loss: 0.008409305475652218 2023-01-23 21:45:26.742693: step: 2694/1545, loss: 0.12603572010993958 2023-01-23 21:45:27.602799: step: 2696/1545, loss: 0.0007905942038632929 2023-01-23 21:45:28.500244: step: 2698/1545, loss: 0.00025961329811252654 2023-01-23 21:45:29.339504: step: 2700/1545, loss: 0.0004211405757814646 2023-01-23 21:45:30.194323: step: 2702/1545, loss: 0.00588324386626482 2023-01-23 21:45:31.035712: step: 2704/1545, loss: 0.0001101648886105977 2023-01-23 21:45:31.947898: step: 2706/1545, loss: 0.0024122202303260565 2023-01-23 21:45:32.820762: step: 2708/1545, loss: 2.8961394491489045e-05 2023-01-23 21:45:33.704925: step: 2710/1545, loss: 0.002331251511350274 2023-01-23 21:45:34.604057: step: 2712/1545, loss: 0.0005517984391190112 2023-01-23 21:45:35.509331: step: 2714/1545, loss: 0.0011465640272945166 2023-01-23 21:45:36.361844: step: 2716/1545, loss: 0.00036664449726231396 2023-01-23 21:45:37.241944: step: 2718/1545, loss: 0.00018387580348644406 2023-01-23 21:45:38.074582: step: 2720/1545, loss: 0.005018220748752356 2023-01-23 21:45:38.980974: step: 2722/1545, loss: 0.3180783689022064 2023-01-23 21:45:39.861033: step: 2724/1545, loss: 0.16371196508407593 2023-01-23 21:45:40.763322: step: 2726/1545, loss: 0.005903016775846481 2023-01-23 21:45:41.640525: step: 2728/1545, loss: 0.004145748447626829 2023-01-23 21:45:42.503668: step: 2730/1545, loss: 0.0023793019354343414 2023-01-23 21:45:43.405098: step: 2732/1545, loss: 0.003243451938033104 2023-01-23 21:45:44.293350: step: 2734/1545, loss: 0.004065331537276506 2023-01-23 21:45:45.171751: step: 2736/1545, loss: 0.00011125665332656354 2023-01-23 21:45:46.039827: step: 2738/1545, loss: 0.8974513411521912 2023-01-23 21:45:46.918321: step: 2740/1545, loss: 0.001137754530645907 2023-01-23 21:45:47.801664: step: 2742/1545, loss: 0.020199017599225044 2023-01-23 21:45:48.666720: step: 2744/1545, loss: 0.00040563804213888943 2023-01-23 21:45:49.508235: step: 2746/1545, loss: 0.08381374180316925 2023-01-23 21:45:50.393126: step: 2748/1545, loss: 0.0005290822009555995 2023-01-23 21:45:51.257566: step: 2750/1545, loss: 4.623873610398732e-05 2023-01-23 21:45:52.130281: step: 2752/1545, loss: 0.0001682847214397043 2023-01-23 21:45:53.016723: step: 2754/1545, loss: 0.006481867749243975 2023-01-23 21:45:53.862336: step: 2756/1545, loss: 0.0021246697288006544 2023-01-23 21:45:54.712049: step: 2758/1545, loss: 0.0008920892141759396 2023-01-23 21:45:55.604672: step: 2760/1545, loss: 0.0003838891861960292 2023-01-23 21:45:56.501203: step: 2762/1545, loss: 0.008175086230039597 2023-01-23 21:45:57.372770: step: 2764/1545, loss: 0.00020989701442886144 2023-01-23 21:45:58.267423: step: 2766/1545, loss: 0.4888509213924408 2023-01-23 21:45:59.177417: step: 2768/1545, loss: 6.17604746366851e-05 2023-01-23 21:46:00.108449: step: 2770/1545, loss: 0.0018345421412959695 2023-01-23 21:46:00.982491: step: 2772/1545, loss: 0.03819267079234123 2023-01-23 21:46:01.821384: step: 2774/1545, loss: 0.0027198968455195427 2023-01-23 21:46:02.692606: step: 2776/1545, loss: 0.003462213324382901 2023-01-23 21:46:03.586513: step: 2778/1545, loss: 0.051841724663972855 2023-01-23 21:46:04.419031: step: 2780/1545, loss: 0.06480900198221207 2023-01-23 21:46:05.344222: step: 2782/1545, loss: 4.470656858757138e-05 2023-01-23 21:46:06.207425: step: 2784/1545, loss: 0.0005423558177426457 2023-01-23 21:46:07.087678: step: 2786/1545, loss: 0.01297506783157587 2023-01-23 21:46:07.987724: step: 2788/1545, loss: 0.00023099264944903553 2023-01-23 21:46:08.845210: step: 2790/1545, loss: 0.05178646743297577 2023-01-23 21:46:09.726714: step: 2792/1545, loss: 9.200697240885347e-05 2023-01-23 21:46:10.719718: step: 2794/1545, loss: 0.034329865127801895 2023-01-23 21:46:11.635373: step: 2796/1545, loss: 0.0401301383972168 2023-01-23 21:46:12.542550: step: 2798/1545, loss: 0.000352364091668278 2023-01-23 21:46:13.450354: step: 2800/1545, loss: 0.030056852847337723 2023-01-23 21:46:14.332176: step: 2802/1545, loss: 0.06343439221382141 2023-01-23 21:46:15.192158: step: 2804/1545, loss: 0.08338313549757004 2023-01-23 21:46:16.025415: step: 2806/1545, loss: 8.887046715244651e-05 2023-01-23 21:46:16.919823: step: 2808/1545, loss: 0.00010409804235678166 2023-01-23 21:46:17.795181: step: 2810/1545, loss: 0.0008050791802816093 2023-01-23 21:46:18.626175: step: 2812/1545, loss: -4.260033165337518e-05 2023-01-23 21:46:19.508977: step: 2814/1545, loss: 0.00010096706682816148 2023-01-23 21:46:20.359420: step: 2816/1545, loss: 0.1736728698015213 2023-01-23 21:46:21.235649: step: 2818/1545, loss: 7.738843123661354e-05 2023-01-23 21:46:22.076906: step: 2820/1545, loss: 0.0007814989658072591 2023-01-23 21:46:22.935146: step: 2822/1545, loss: 0.05411968380212784 2023-01-23 21:46:23.775217: step: 2824/1545, loss: 0.02547674998641014 2023-01-23 21:46:24.602700: step: 2826/1545, loss: 0.0064386893063783646 2023-01-23 21:46:25.473315: step: 2828/1545, loss: 0.0005378213827498257 2023-01-23 21:46:26.316542: step: 2830/1545, loss: 0.00286530377343297 2023-01-23 21:46:27.293033: step: 2832/1545, loss: 0.13546279072761536 2023-01-23 21:46:28.215286: step: 2834/1545, loss: 0.740476131439209 2023-01-23 21:46:29.076769: step: 2836/1545, loss: 0.001343766925856471 2023-01-23 21:46:29.947104: step: 2838/1545, loss: 0.03198651224374771 2023-01-23 21:46:30.780203: step: 2840/1545, loss: 0.0004563252441585064 2023-01-23 21:46:31.635939: step: 2842/1545, loss: 0.04006988927721977 2023-01-23 21:46:32.464931: step: 2844/1545, loss: 0.0029535628855228424 2023-01-23 21:46:33.370651: step: 2846/1545, loss: 0.0002632479299791157 2023-01-23 21:46:34.226162: step: 2848/1545, loss: 0.06388632208108902 2023-01-23 21:46:35.128240: step: 2850/1545, loss: 0.0004070787981618196 2023-01-23 21:46:36.036122: step: 2852/1545, loss: 0.00656554801389575 2023-01-23 21:46:36.919327: step: 2854/1545, loss: 0.0007548657595179975 2023-01-23 21:46:37.773450: step: 2856/1545, loss: 0.010809741914272308 2023-01-23 21:46:38.633532: step: 2858/1545, loss: 0.004594214726239443 2023-01-23 21:46:39.461114: step: 2860/1545, loss: 0.0010552576277405024 2023-01-23 21:46:40.317582: step: 2862/1545, loss: 0.0003693046746775508 2023-01-23 21:46:41.187316: step: 2864/1545, loss: 0.00026898362557403743 2023-01-23 21:46:42.035525: step: 2866/1545, loss: 0.0007087372941896319 2023-01-23 21:46:42.920878: step: 2868/1545, loss: 0.006559578701853752 2023-01-23 21:46:43.760325: step: 2870/1545, loss: 0.2775537073612213 2023-01-23 21:46:44.686265: step: 2872/1545, loss: 0.09778343886137009 2023-01-23 21:46:45.580349: step: 2874/1545, loss: 0.36284422874450684 2023-01-23 21:46:46.465511: step: 2876/1545, loss: 0.001324344426393509 2023-01-23 21:46:47.341509: step: 2878/1545, loss: 0.00016040937043726444 2023-01-23 21:46:48.185975: step: 2880/1545, loss: 0.03284655511379242 2023-01-23 21:46:49.057278: step: 2882/1545, loss: 0.0006112187402322888 2023-01-23 21:46:49.907452: step: 2884/1545, loss: 0.0005789683782495558 2023-01-23 21:46:50.776863: step: 2886/1545, loss: 0.19322092831134796 2023-01-23 21:46:51.620543: step: 2888/1545, loss: 0.00023396559117827564 2023-01-23 21:46:52.520890: step: 2890/1545, loss: 2.916975245170761e-05 2023-01-23 21:46:53.464901: step: 2892/1545, loss: 0.021064667031168938 2023-01-23 21:46:54.315416: step: 2894/1545, loss: 0.0070685772225260735 2023-01-23 21:46:55.178182: step: 2896/1545, loss: 0.00017871703312266618 2023-01-23 21:46:56.031206: step: 2898/1545, loss: 0.00047397331218235195 2023-01-23 21:46:56.898956: step: 2900/1545, loss: 0.28010016679763794 2023-01-23 21:46:57.778930: step: 2902/1545, loss: 0.00012729012814816087 2023-01-23 21:46:58.687970: step: 2904/1545, loss: 7.721129077253863e-05 2023-01-23 21:46:59.570564: step: 2906/1545, loss: 0.01850692182779312 2023-01-23 21:47:00.448926: step: 2908/1545, loss: 0.0025883843190968037 2023-01-23 21:47:01.344018: step: 2910/1545, loss: 0.33986982703208923 2023-01-23 21:47:02.196536: step: 2912/1545, loss: 0.0032503362745046616 2023-01-23 21:47:03.050701: step: 2914/1545, loss: 0.0008295676088891923 2023-01-23 21:47:03.990790: step: 2916/1545, loss: 0.026064449921250343 2023-01-23 21:47:04.837104: step: 2918/1545, loss: 0.6058675050735474 2023-01-23 21:47:05.787368: step: 2920/1545, loss: 0.0002006902068387717 2023-01-23 21:47:06.646290: step: 2922/1545, loss: 0.0287768691778183 2023-01-23 21:47:07.527745: step: 2924/1545, loss: 0.0010374777484685183 2023-01-23 21:47:08.397156: step: 2926/1545, loss: 0.006261787842959166 2023-01-23 21:47:09.254334: step: 2928/1545, loss: 0.09232833981513977 2023-01-23 21:47:10.172313: step: 2930/1545, loss: 0.005132083315402269 2023-01-23 21:47:11.155154: step: 2932/1545, loss: 0.00011138135596411303 2023-01-23 21:47:11.981932: step: 2934/1545, loss: 2.4487822884111665e-05 2023-01-23 21:47:12.818613: step: 2936/1545, loss: 0.002450290834531188 2023-01-23 21:47:13.735775: step: 2938/1545, loss: 0.021176792681217194 2023-01-23 21:47:14.633200: step: 2940/1545, loss: 0.13807998597621918 2023-01-23 21:47:15.512175: step: 2942/1545, loss: 0.01615932025015354 2023-01-23 21:47:16.382455: step: 2944/1545, loss: 0.5267327427864075 2023-01-23 21:47:17.228761: step: 2946/1545, loss: 0.00048728781985118985 2023-01-23 21:47:18.091402: step: 2948/1545, loss: 0.004483395721763372 2023-01-23 21:47:18.977731: step: 2950/1545, loss: 0.019777027890086174 2023-01-23 21:47:19.829792: step: 2952/1545, loss: -5.531612259801477e-06 2023-01-23 21:47:20.730704: step: 2954/1545, loss: 2.231150574516505e-05 2023-01-23 21:47:21.618290: step: 2956/1545, loss: 0.1971648633480072 2023-01-23 21:47:22.575864: step: 2958/1545, loss: 0.01608411781489849 2023-01-23 21:47:23.479891: step: 2960/1545, loss: 0.00018230677233077586 2023-01-23 21:47:24.364038: step: 2962/1545, loss: 0.005884220357984304 2023-01-23 21:47:25.222513: step: 2964/1545, loss: 3.137810199405067e-05 2023-01-23 21:47:26.041897: step: 2966/1545, loss: 0.006936376914381981 2023-01-23 21:47:26.889831: step: 2968/1545, loss: 0.020819349214434624 2023-01-23 21:47:27.744480: step: 2970/1545, loss: 2.2704793082084507e-05 2023-01-23 21:47:28.663600: step: 2972/1545, loss: 0.2362537980079651 2023-01-23 21:47:29.489561: step: 2974/1545, loss: 0.0021194310393184423 2023-01-23 21:47:30.400743: step: 2976/1545, loss: 0.28881126642227173 2023-01-23 21:47:31.261906: step: 2978/1545, loss: 0.00029761402402073145 2023-01-23 21:47:32.141030: step: 2980/1545, loss: 0.07514992356300354 2023-01-23 21:47:33.055413: step: 2982/1545, loss: 0.13121575117111206 2023-01-23 21:47:33.987867: step: 2984/1545, loss: 0.010160930454730988 2023-01-23 21:47:34.856774: step: 2986/1545, loss: 0.0014927462907508016 2023-01-23 21:47:35.731990: step: 2988/1545, loss: 6.168383697513491e-05 2023-01-23 21:47:36.673291: step: 2990/1545, loss: 0.013733531348407269 2023-01-23 21:47:37.554187: step: 2992/1545, loss: 0.00042597673018462956 2023-01-23 21:47:38.395101: step: 2994/1545, loss: 0.0003019312280230224 2023-01-23 21:47:39.266843: step: 2996/1545, loss: 0.003176252357661724 2023-01-23 21:47:40.106665: step: 2998/1545, loss: 0.0008280290057882667 2023-01-23 21:47:40.970332: step: 3000/1545, loss: 0.037638578563928604 2023-01-23 21:47:41.831633: step: 3002/1545, loss: 0.019269518554210663 2023-01-23 21:47:42.669998: step: 3004/1545, loss: 0.0006581225316040218 2023-01-23 21:47:43.548398: step: 3006/1545, loss: 0.109820656478405 2023-01-23 21:47:44.469316: step: 3008/1545, loss: 0.0001555798080516979 2023-01-23 21:47:45.377380: step: 3010/1545, loss: 0.0001562109391670674 2023-01-23 21:47:46.228209: step: 3012/1545, loss: 0.0005883651319891214 2023-01-23 21:47:47.086201: step: 3014/1545, loss: 0.0003648745478130877 2023-01-23 21:47:47.981649: step: 3016/1545, loss: 0.03150077909231186 2023-01-23 21:47:48.858367: step: 3018/1545, loss: 0.0014413174940273166 2023-01-23 21:47:49.702568: step: 3020/1545, loss: 0.0043527851812541485 2023-01-23 21:47:50.609330: step: 3022/1545, loss: 0.07909266650676727 2023-01-23 21:47:51.442844: step: 3024/1545, loss: 0.00014033842307981104 2023-01-23 21:47:52.304724: step: 3026/1545, loss: 0.12576355040073395 2023-01-23 21:47:53.218460: step: 3028/1545, loss: 8.874237391864881e-05 2023-01-23 21:47:54.122806: step: 3030/1545, loss: 0.0015931435627862811 2023-01-23 21:47:54.977537: step: 3032/1545, loss: 0.0038083887193351984 2023-01-23 21:47:55.846335: step: 3034/1545, loss: 0.007577912416309118 2023-01-23 21:47:56.695442: step: 3036/1545, loss: 0.0015867300098761916 2023-01-23 21:47:57.572234: step: 3038/1545, loss: 0.003873605513945222 2023-01-23 21:47:58.452433: step: 3040/1545, loss: 0.0036104819737374783 2023-01-23 21:47:59.342368: step: 3042/1545, loss: 0.0004233850340824574 2023-01-23 21:48:00.292445: step: 3044/1545, loss: 5.940596020082012e-05 2023-01-23 21:48:01.213376: step: 3046/1545, loss: 0.4266431927680969 2023-01-23 21:48:02.057950: step: 3048/1545, loss: 2.049949034699239e-05 2023-01-23 21:48:02.936065: step: 3050/1545, loss: 0.0006448209751397371 2023-01-23 21:48:03.834872: step: 3052/1545, loss: 0.2560412287712097 2023-01-23 21:48:04.666643: step: 3054/1545, loss: 0.0015658068004995584 2023-01-23 21:48:05.559878: step: 3056/1545, loss: 0.00211787479929626 2023-01-23 21:48:06.434795: step: 3058/1545, loss: 1.477260775573086e-05 2023-01-23 21:48:07.318642: step: 3060/1545, loss: 0.00021958534489385784 2023-01-23 21:48:08.182984: step: 3062/1545, loss: 3.027989441761747e-05 2023-01-23 21:48:09.033156: step: 3064/1545, loss: 7.150886813178658e-05 2023-01-23 21:48:09.885269: step: 3066/1545, loss: 2.7495503672980703e-05 2023-01-23 21:48:10.777341: step: 3068/1545, loss: 0.06190627068281174 2023-01-23 21:48:11.655595: step: 3070/1545, loss: 0.002756178379058838 2023-01-23 21:48:12.498565: step: 3072/1545, loss: 0.000963573285844177 2023-01-23 21:48:13.356870: step: 3074/1545, loss: 8.696092845639214e-05 2023-01-23 21:48:14.198797: step: 3076/1545, loss: 0.00010174064664170146 2023-01-23 21:48:15.084335: step: 3078/1545, loss: 0.00019894556317012757 2023-01-23 21:48:15.996309: step: 3080/1545, loss: 0.006272038910537958 2023-01-23 21:48:16.876355: step: 3082/1545, loss: 0.07290254533290863 2023-01-23 21:48:17.742169: step: 3084/1545, loss: 6.753650086466223e-05 2023-01-23 21:48:18.584120: step: 3086/1545, loss: 2.2804773834650405e-05 2023-01-23 21:48:19.455583: step: 3088/1545, loss: 0.0001765898778103292 2023-01-23 21:48:20.365731: step: 3090/1545, loss: 0.03884175419807434 ================================================== Loss: 0.051 -------------------- Dev Chinese: {'event': {'p': 0.6019629225736096, 'r': 0.7350199733688415, 'f1': 0.6618705035971223}, 'argument': {'p': 0.66422522252087, 'r': 0.6488243385282396, 'f1': 0.6564344613032586}, 'combined': 0.4344746074812934, 'epoch': 35} Test Chinese: {'event': {'p': 0.6366061899679829, 'r': 0.7627877237851662, 'f1': 0.6940081442699244}, 'argument': {'p': 0.7234055447323137, 'r': 0.7131856114924909, 'f1': 0.7182592257253736}, 'combined': 0.4984777523504193, 'epoch': 35} Dev Korean: {'event': {'p': 0.6050328227571116, 'r': 0.7363515312916112, 'f1': 0.6642642642642642}, 'argument': {'p': 0.6693489929114083, 'r': 0.647708386373671, 'f1': 0.6583509009377015}, 'combined': 0.4373189768390978, 'epoch': 35} Test Korean: {'event': {'p': 0.6285714285714286, 'r': 0.7595907928388747, 'f1': 0.6878980891719745}, 'argument': {'p': 0.714131533396885, 'r': 0.7056689655317078, 'f1': 0.7098750293524121}, 'combined': 0.48832167624242356, 'epoch': 35} Dev Russian: {'event': {'p': 0.5698818897637795, 'r': 0.7709720372836218, 'f1': 0.6553480475382004}, 'argument': {'p': 0.6639555099566563, 'r': 0.6539819293349899, 'f1': 0.6589309817732005}, 'combined': 0.4318291323674965, 'epoch': 35} Test Russian: {'event': {'p': 0.6238166417538615, 'r': 0.8005115089514067, 'f1': 0.7012041444973396}, 'argument': {'p': 0.7261557140920908, 'r': 0.7234350107796439, 'f1': 0.7247928092232994}, 'combined': 0.5082277217292471, 'epoch': 35} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6915450804339692, 'r': 0.6172468486518072, 'f1': 0.652287062767412}, 'combined': 0.45462431647425694, 'epoch': 35} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6574900793650793, 'r': 0.5404028049575994, 'f1': 0.5932241317579663}, 'combined': 0.36426043178120737, 'epoch': 35} Russian: {'event': {'p': 0.4883720930232558, 'r': 0.5833333333333334, 'f1': 0.5316455696202531}, 'argument': {'p': 0.5699463722992983, 'r': 0.5394135309261217, 'f1': 0.5542597748965654}, 'combined': 0.2946697537424778, 'epoch': 35} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6758987924276707, 'r': 0.6414709887684336, 'f1': 0.6582350269068861}, 'combined': 0.43408784748056034, 'epoch': 33} Test for Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7201409239897084, 'r': 0.7110669833666995, 'f1': 0.7155751890249322}, 'combined': 0.49952892776609586, 'epoch': 33} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7175290642271774, 'r': 0.6285791802320727, 'f1': 0.6701152494104036}, 'combined': 0.4772032836710449, 'epoch': 33} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 36 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 21:53:32.401018: step: 2/1545, loss: 0.23937709629535675 2023-01-23 21:53:33.311021: step: 4/1545, loss: 0.02136196382343769 2023-01-23 21:53:34.176519: step: 6/1545, loss: 0.01535502728074789 2023-01-23 21:53:35.087525: step: 8/1545, loss: 0.19826461374759674 2023-01-23 21:53:35.919810: step: 10/1545, loss: 0.00028337596450001 2023-01-23 21:53:36.804789: step: 12/1545, loss: 0.004678553435951471 2023-01-23 21:53:37.655072: step: 14/1545, loss: 3.805994856520556e-05 2023-01-23 21:53:38.555477: step: 16/1545, loss: 0.005933463107794523 2023-01-23 21:53:39.464131: step: 18/1545, loss: 0.0021314644254744053 2023-01-23 21:53:40.339599: step: 20/1545, loss: 0.00019563615205697715 2023-01-23 21:53:41.215549: step: 22/1545, loss: 0.00020831458095926791 2023-01-23 21:53:42.040634: step: 24/1545, loss: 0.022890890017151833 2023-01-23 21:53:42.951087: step: 26/1545, loss: 0.013234274461865425 2023-01-23 21:53:43.794972: step: 28/1545, loss: 6.522614057757892e-07 2023-01-23 21:53:44.629933: step: 30/1545, loss: -1.1784251910285093e-05 2023-01-23 21:53:45.514000: step: 32/1545, loss: -4.8140705075638834e-06 2023-01-23 21:53:46.403847: step: 34/1545, loss: 0.004169297404587269 2023-01-23 21:53:47.302352: step: 36/1545, loss: 0.4916335344314575 2023-01-23 21:53:48.172751: step: 38/1545, loss: 0.29354602098464966 2023-01-23 21:53:49.100316: step: 40/1545, loss: 1.908259218907915e-05 2023-01-23 21:53:49.955951: step: 42/1545, loss: 0.00011906445433851331 2023-01-23 21:53:50.822328: step: 44/1545, loss: 4.883510700892657e-05 2023-01-23 21:53:51.664903: step: 46/1545, loss: 0.023204227909445763 2023-01-23 21:53:52.519610: step: 48/1545, loss: 3.477950667729601e-05 2023-01-23 21:53:53.419125: step: 50/1545, loss: 0.040987372398376465 2023-01-23 21:53:54.306076: step: 52/1545, loss: 6.567165837623179e-05 2023-01-23 21:53:55.193968: step: 54/1545, loss: 0.029166296124458313 2023-01-23 21:53:56.025214: step: 56/1545, loss: 0.00012020469148410484 2023-01-23 21:53:56.874701: step: 58/1545, loss: 0.06656568497419357 2023-01-23 21:53:57.741979: step: 60/1545, loss: 0.0014595595421269536 2023-01-23 21:53:58.585221: step: 62/1545, loss: 4.8924426664598286e-05 2023-01-23 21:53:59.442457: step: 64/1545, loss: -4.701023499364965e-06 2023-01-23 21:54:00.340939: step: 66/1545, loss: 0.037456002086400986 2023-01-23 21:54:01.211762: step: 68/1545, loss: 0.00029234885005280375 2023-01-23 21:54:02.090001: step: 70/1545, loss: 0.10684474557638168 2023-01-23 21:54:02.953083: step: 72/1545, loss: 0.0017760443734005094 2023-01-23 21:54:03.809375: step: 74/1545, loss: 0.00011586543405428529 2023-01-23 21:54:04.714658: step: 76/1545, loss: -5.25764608028112e-06 2023-01-23 21:54:05.576630: step: 78/1545, loss: 6.781661068089306e-05 2023-01-23 21:54:06.475151: step: 80/1545, loss: 0.0022903596982359886 2023-01-23 21:54:07.381721: step: 82/1545, loss: 0.001313052955083549 2023-01-23 21:54:08.216356: step: 84/1545, loss: 0.00821568164974451 2023-01-23 21:54:09.090867: step: 86/1545, loss: 2.0138872059760615e-05 2023-01-23 21:54:09.983056: step: 88/1545, loss: 0.007953723892569542 2023-01-23 21:54:10.848969: step: 90/1545, loss: 7.876098243286833e-05 2023-01-23 21:54:11.717335: step: 92/1545, loss: 0.00028123732772655785 2023-01-23 21:54:12.579018: step: 94/1545, loss: 3.7677153159165755e-05 2023-01-23 21:54:13.462296: step: 96/1545, loss: 0.0017652584938332438 2023-01-23 21:54:14.334256: step: 98/1545, loss: 0.016872437670826912 2023-01-23 21:54:15.210953: step: 100/1545, loss: 4.577228537527844e-05 2023-01-23 21:54:16.053038: step: 102/1545, loss: 3.523109626257792e-05 2023-01-23 21:54:16.962606: step: 104/1545, loss: 0.025344587862491608 2023-01-23 21:54:17.825107: step: 106/1545, loss: 0.00018716059275902808 2023-01-23 21:54:18.664725: step: 108/1545, loss: 6.533116538776085e-05 2023-01-23 21:54:19.526511: step: 110/1545, loss: 0.12715627253055573 2023-01-23 21:54:20.384583: step: 112/1545, loss: 0.056957047432661057 2023-01-23 21:54:21.246747: step: 114/1545, loss: -1.0623053640301805e-05 2023-01-23 21:54:22.166514: step: 116/1545, loss: 0.0004601019318215549 2023-01-23 21:54:23.032381: step: 118/1545, loss: 3.7397439882624894e-05 2023-01-23 21:54:23.946827: step: 120/1545, loss: 1.9839404558297247e-05 2023-01-23 21:54:24.794515: step: 122/1545, loss: 0.02717437781393528 2023-01-23 21:54:25.643526: step: 124/1545, loss: 0.00117421371396631 2023-01-23 21:54:26.473356: step: 126/1545, loss: -2.5754712623893283e-05 2023-01-23 21:54:27.385619: step: 128/1545, loss: 0.0010671024210751057 2023-01-23 21:54:28.268877: step: 130/1545, loss: 0.29093411564826965 2023-01-23 21:54:29.134810: step: 132/1545, loss: 9.769945609150454e-05 2023-01-23 21:54:30.009311: step: 134/1545, loss: 0.03660169988870621 2023-01-23 21:54:30.886509: step: 136/1545, loss: 8.060864274739288e-06 2023-01-23 21:54:31.779682: step: 138/1545, loss: 0.043009571731090546 2023-01-23 21:54:32.622069: step: 140/1545, loss: 0.43445998430252075 2023-01-23 21:54:33.540425: step: 142/1545, loss: 0.10673437267541885 2023-01-23 21:54:34.408099: step: 144/1545, loss: 0.03481144830584526 2023-01-23 21:54:35.294938: step: 146/1545, loss: 0.005767738446593285 2023-01-23 21:54:36.260836: step: 148/1545, loss: 0.00017795502208173275 2023-01-23 21:54:37.141201: step: 150/1545, loss: 7.711225771345198e-05 2023-01-23 21:54:38.086369: step: 152/1545, loss: 0.000110501772724092 2023-01-23 21:54:38.941646: step: 154/1545, loss: 3.903582546627149e-05 2023-01-23 21:54:39.801612: step: 156/1545, loss: -9.026130101119634e-06 2023-01-23 21:54:40.683476: step: 158/1545, loss: 0.047570183873176575 2023-01-23 21:54:41.570318: step: 160/1545, loss: 0.0032487069256603718 2023-01-23 21:54:42.424194: step: 162/1545, loss: 0.021533429622650146 2023-01-23 21:54:43.318444: step: 164/1545, loss: -3.2397729228250682e-06 2023-01-23 21:54:44.153835: step: 166/1545, loss: -1.8161537127525662e-06 2023-01-23 21:54:45.023075: step: 168/1545, loss: 1.8311540770810097e-05 2023-01-23 21:54:45.895659: step: 170/1545, loss: 0.008248833008110523 2023-01-23 21:54:46.758106: step: 172/1545, loss: 0.0019006188958883286 2023-01-23 21:54:47.596033: step: 174/1545, loss: 3.9989343349589035e-05 2023-01-23 21:54:48.438160: step: 176/1545, loss: 0.002000718377530575 2023-01-23 21:54:49.320040: step: 178/1545, loss: 5.08644588990137e-05 2023-01-23 21:54:50.197324: step: 180/1545, loss: 9.183154907077551e-05 2023-01-23 21:54:51.056438: step: 182/1545, loss: 0.03623942285776138 2023-01-23 21:54:51.937255: step: 184/1545, loss: 0.0008615776314400136 2023-01-23 21:54:52.863663: step: 186/1545, loss: 0.2726740539073944 2023-01-23 21:54:53.715841: step: 188/1545, loss: 9.990398211812135e-06 2023-01-23 21:54:54.610926: step: 190/1545, loss: 0.7918778657913208 2023-01-23 21:54:55.509145: step: 192/1545, loss: 5.0573529733810574e-05 2023-01-23 21:54:56.370846: step: 194/1545, loss: 0.0006177241448312998 2023-01-23 21:54:57.241832: step: 196/1545, loss: 0.0002275284205097705 2023-01-23 21:54:58.114994: step: 198/1545, loss: 7.710896170465276e-06 2023-01-23 21:54:58.978048: step: 200/1545, loss: 8.976606477517635e-05 2023-01-23 21:54:59.895209: step: 202/1545, loss: 0.32069963216781616 2023-01-23 21:55:00.779583: step: 204/1545, loss: -2.114973176503554e-05 2023-01-23 21:55:01.646801: step: 206/1545, loss: 2.3572260033688508e-05 2023-01-23 21:55:02.526473: step: 208/1545, loss: 0.0002390261070104316 2023-01-23 21:55:03.404598: step: 210/1545, loss: 5.6712826335569844e-05 2023-01-23 21:55:04.299004: step: 212/1545, loss: 0.0008491825428791344 2023-01-23 21:55:05.191626: step: 214/1545, loss: 0.04794018343091011 2023-01-23 21:55:06.076567: step: 216/1545, loss: 6.637931073782966e-05 2023-01-23 21:55:06.953672: step: 218/1545, loss: 0.1462422013282776 2023-01-23 21:55:07.808018: step: 220/1545, loss: 0.0005537499091587961 2023-01-23 21:55:08.678696: step: 222/1545, loss: 0.00010255574306938797 2023-01-23 21:55:09.674231: step: 224/1545, loss: 0.0004439711628947407 2023-01-23 21:55:10.540058: step: 226/1545, loss: 0.03914078325033188 2023-01-23 21:55:11.383686: step: 228/1545, loss: 0.00022422548499889672 2023-01-23 21:55:12.239805: step: 230/1545, loss: 0.001347799669019878 2023-01-23 21:55:13.107152: step: 232/1545, loss: 5.6017397582763806e-05 2023-01-23 21:55:13.987040: step: 234/1545, loss: 0.3033430874347687 2023-01-23 21:55:14.862221: step: 236/1545, loss: 0.0571022592484951 2023-01-23 21:55:15.721256: step: 238/1545, loss: 6.06941721343901e-05 2023-01-23 21:55:16.579469: step: 240/1545, loss: 1.6177948054973967e-05 2023-01-23 21:55:17.416278: step: 242/1545, loss: 0.06971559673547745 2023-01-23 21:55:18.256091: step: 244/1545, loss: 7.469973934348673e-05 2023-01-23 21:55:19.140590: step: 246/1545, loss: 3.2198331609833986e-05 2023-01-23 21:55:19.955260: step: 248/1545, loss: 9.73939950199565e-06 2023-01-23 21:55:20.802621: step: 250/1545, loss: 0.05744462460279465 2023-01-23 21:55:21.678265: step: 252/1545, loss: 0.13196220993995667 2023-01-23 21:55:22.617483: step: 254/1545, loss: 2.9638411433552392e-05 2023-01-23 21:55:23.486836: step: 256/1545, loss: 0.003209017915651202 2023-01-23 21:55:24.375837: step: 258/1545, loss: 0.15414127707481384 2023-01-23 21:55:25.226211: step: 260/1545, loss: 2.363321436860133e-05 2023-01-23 21:55:26.246261: step: 262/1545, loss: 9.349081665277481e-05 2023-01-23 21:55:27.088294: step: 264/1545, loss: 0.0135688167065382 2023-01-23 21:55:27.977352: step: 266/1545, loss: 0.0015141903422772884 2023-01-23 21:55:28.862522: step: 268/1545, loss: 0.12316678464412689 2023-01-23 21:55:29.746606: step: 270/1545, loss: 0.011916388757526875 2023-01-23 21:55:30.638664: step: 272/1545, loss: 3.0572486139135435e-05 2023-01-23 21:55:31.495137: step: 274/1545, loss: 8.087158494163305e-05 2023-01-23 21:55:32.334973: step: 276/1545, loss: 1.2463614439184312e-05 2023-01-23 21:55:33.169943: step: 278/1545, loss: 0.0005484926514327526 2023-01-23 21:55:34.035497: step: 280/1545, loss: 0.0004332854878157377 2023-01-23 21:55:34.849625: step: 282/1545, loss: 0.0033651557750999928 2023-01-23 21:55:35.683357: step: 284/1545, loss: -4.01225747737044e-07 2023-01-23 21:55:36.545481: step: 286/1545, loss: 0.0023262049071490765 2023-01-23 21:55:37.416559: step: 288/1545, loss: 8.119131962303072e-05 2023-01-23 21:55:38.302179: step: 290/1545, loss: 0.005043910816311836 2023-01-23 21:55:39.189497: step: 292/1545, loss: 3.5095217754133046e-05 2023-01-23 21:55:40.097210: step: 294/1545, loss: 3.294046473456547e-05 2023-01-23 21:55:40.988090: step: 296/1545, loss: 1.6891456198209198e-06 2023-01-23 21:55:41.874918: step: 298/1545, loss: 0.026559017598628998 2023-01-23 21:55:42.744531: step: 300/1545, loss: 0.00011774417362175882 2023-01-23 21:55:43.603695: step: 302/1545, loss: 0.0002996590919792652 2023-01-23 21:55:44.532759: step: 304/1545, loss: 5.26929106854368e-05 2023-01-23 21:55:45.391806: step: 306/1545, loss: 0.0007697954424656928 2023-01-23 21:55:46.245746: step: 308/1545, loss: 3.961671973229386e-05 2023-01-23 21:55:47.094467: step: 310/1545, loss: 5.954131484031677e-05 2023-01-23 21:55:47.955870: step: 312/1545, loss: 0.07316083461046219 2023-01-23 21:55:48.848525: step: 314/1545, loss: 0.0013108003186061978 2023-01-23 21:55:49.715632: step: 316/1545, loss: 0.03248526528477669 2023-01-23 21:55:50.573211: step: 318/1545, loss: 7.224638102343306e-05 2023-01-23 21:55:51.425684: step: 320/1545, loss: 0.058443523943424225 2023-01-23 21:55:52.374079: step: 322/1545, loss: -1.0927476978395134e-05 2023-01-23 21:55:53.272440: step: 324/1545, loss: 6.912669778103009e-05 2023-01-23 21:55:54.130079: step: 326/1545, loss: 1.4150141396385152e-05 2023-01-23 21:55:54.996263: step: 328/1545, loss: 0.12049546837806702 2023-01-23 21:55:55.876438: step: 330/1545, loss: 0.008838598616421223 2023-01-23 21:55:56.763068: step: 332/1545, loss: 0.0005447875009849668 2023-01-23 21:55:57.638368: step: 334/1545, loss: 3.414072853047401e-05 2023-01-23 21:55:58.502475: step: 336/1545, loss: 0.08469545841217041 2023-01-23 21:55:59.400079: step: 338/1545, loss: 0.0005831752205267549 2023-01-23 21:56:00.308572: step: 340/1545, loss: 0.0013355484697967768 2023-01-23 21:56:01.216582: step: 342/1545, loss: 0.00019841891480609775 2023-01-23 21:56:02.142166: step: 344/1545, loss: 0.00014026886492501944 2023-01-23 21:56:03.020050: step: 346/1545, loss: 0.002524077892303467 2023-01-23 21:56:03.923063: step: 348/1545, loss: 0.016086608171463013 2023-01-23 21:56:04.839465: step: 350/1545, loss: 0.000638605619315058 2023-01-23 21:56:05.730743: step: 352/1545, loss: 2.1212774299783632e-05 2023-01-23 21:56:06.582435: step: 354/1545, loss: 0.1036318987607956 2023-01-23 21:56:07.468052: step: 356/1545, loss: 0.003043713280931115 2023-01-23 21:56:08.318158: step: 358/1545, loss: 0.0034987791441380978 2023-01-23 21:56:09.163445: step: 360/1545, loss: 9.506077185506001e-05 2023-01-23 21:56:10.011858: step: 362/1545, loss: 6.916884740348905e-05 2023-01-23 21:56:10.877688: step: 364/1545, loss: 0.3122473657131195 2023-01-23 21:56:11.779372: step: 366/1545, loss: 0.008315252140164375 2023-01-23 21:56:12.652946: step: 368/1545, loss: 0.00020115521328989416 2023-01-23 21:56:13.494015: step: 370/1545, loss: 0.1989540010690689 2023-01-23 21:56:14.358575: step: 372/1545, loss: 8.19805936771445e-05 2023-01-23 21:56:15.219613: step: 374/1545, loss: 0.00025853115948848426 2023-01-23 21:56:16.083785: step: 376/1545, loss: 1.2434205928002484e-05 2023-01-23 21:56:16.925104: step: 378/1545, loss: -7.99261215433944e-06 2023-01-23 21:56:17.779482: step: 380/1545, loss: 0.0004430365515872836 2023-01-23 21:56:18.647164: step: 382/1545, loss: 0.014507723972201347 2023-01-23 21:56:19.565981: step: 384/1545, loss: 0.08372309803962708 2023-01-23 21:56:20.427545: step: 386/1545, loss: 1.5338093362515792e-05 2023-01-23 21:56:21.348613: step: 388/1545, loss: 0.0079655135050416 2023-01-23 21:56:22.223749: step: 390/1545, loss: 1.1914457082748413 2023-01-23 21:56:23.160583: step: 392/1545, loss: 0.16097205877304077 2023-01-23 21:56:24.011615: step: 394/1545, loss: 0.00015872198855504394 2023-01-23 21:56:24.919371: step: 396/1545, loss: 0.020739469677209854 2023-01-23 21:56:25.778473: step: 398/1545, loss: 0.05989071726799011 2023-01-23 21:56:26.642173: step: 400/1545, loss: 0.14642499387264252 2023-01-23 21:56:27.490526: step: 402/1545, loss: 0.005190681666135788 2023-01-23 21:56:28.361610: step: 404/1545, loss: 0.0016647520242258906 2023-01-23 21:56:29.285599: step: 406/1545, loss: 0.013338708318769932 2023-01-23 21:56:30.154799: step: 408/1545, loss: 0.0019257627427577972 2023-01-23 21:56:31.008947: step: 410/1545, loss: 0.06743622571229935 2023-01-23 21:56:31.877300: step: 412/1545, loss: 0.08677096664905548 2023-01-23 21:56:32.778167: step: 414/1545, loss: 6.591516284970567e-05 2023-01-23 21:56:33.617224: step: 416/1545, loss: 0.0009038273710757494 2023-01-23 21:56:34.498695: step: 418/1545, loss: 0.29629337787628174 2023-01-23 21:56:35.337336: step: 420/1545, loss: 0.19055694341659546 2023-01-23 21:56:36.201506: step: 422/1545, loss: 0.00019299928680993617 2023-01-23 21:56:37.124860: step: 424/1545, loss: 0.10486076027154922 2023-01-23 21:56:37.983262: step: 426/1545, loss: 0.003861416131258011 2023-01-23 21:56:38.866027: step: 428/1545, loss: 0.00016024685464799404 2023-01-23 21:56:39.754920: step: 430/1545, loss: 0.06153002381324768 2023-01-23 21:56:40.637299: step: 432/1545, loss: 0.05363021790981293 2023-01-23 21:56:41.493968: step: 434/1545, loss: 0.004589411895722151 2023-01-23 21:56:42.369896: step: 436/1545, loss: 0.0012801007833331823 2023-01-23 21:56:43.217848: step: 438/1545, loss: 0.0002514968509785831 2023-01-23 21:56:44.072640: step: 440/1545, loss: 0.0006797307869419456 2023-01-23 21:56:44.979101: step: 442/1545, loss: 0.005100573878735304 2023-01-23 21:56:45.864726: step: 444/1545, loss: 9.947860962711275e-05 2023-01-23 21:56:46.716684: step: 446/1545, loss: 0.0009768736781552434 2023-01-23 21:56:47.618044: step: 448/1545, loss: 0.02226024493575096 2023-01-23 21:56:48.476308: step: 450/1545, loss: 0.01617000252008438 2023-01-23 21:56:49.352349: step: 452/1545, loss: 0.0901898741722107 2023-01-23 21:56:50.226701: step: 454/1545, loss: 0.0003368677571415901 2023-01-23 21:56:51.078597: step: 456/1545, loss: 0.19105255603790283 2023-01-23 21:56:51.936602: step: 458/1545, loss: 3.5303244658280164e-05 2023-01-23 21:56:52.793222: step: 460/1545, loss: 0.015514292754232883 2023-01-23 21:56:53.660368: step: 462/1545, loss: 0.0008849487057887018 2023-01-23 21:56:54.524752: step: 464/1545, loss: 0.4067791998386383 2023-01-23 21:56:55.380250: step: 466/1545, loss: 0.001272896071895957 2023-01-23 21:56:56.251940: step: 468/1545, loss: 0.0014142965665087104 2023-01-23 21:56:57.152731: step: 470/1545, loss: 0.01999921351671219 2023-01-23 21:56:58.036709: step: 472/1545, loss: 0.001368938246741891 2023-01-23 21:56:58.949190: step: 474/1545, loss: 0.0035353894345462322 2023-01-23 21:56:59.810500: step: 476/1545, loss: 0.05291678011417389 2023-01-23 21:57:00.789367: step: 478/1545, loss: 0.001580731594003737 2023-01-23 21:57:01.662917: step: 480/1545, loss: 0.007996045053005219 2023-01-23 21:57:02.535902: step: 482/1545, loss: 0.005264020524919033 2023-01-23 21:57:03.400009: step: 484/1545, loss: 0.001279007992707193 2023-01-23 21:57:04.282915: step: 486/1545, loss: 0.0026917553041130304 2023-01-23 21:57:05.128491: step: 488/1545, loss: 0.0009519853047095239 2023-01-23 21:57:05.982717: step: 490/1545, loss: 0.0003038429713342339 2023-01-23 21:57:06.808014: step: 492/1545, loss: 0.0024704961106181145 2023-01-23 21:57:07.632978: step: 494/1545, loss: 0.00285287294536829 2023-01-23 21:57:08.534118: step: 496/1545, loss: 0.0004583639674820006 2023-01-23 21:57:09.400980: step: 498/1545, loss: 0.00026057439390569925 2023-01-23 21:57:10.260278: step: 500/1545, loss: 0.00017903346451930702 2023-01-23 21:57:11.126243: step: 502/1545, loss: 7.27992528481991e-06 2023-01-23 21:57:11.982442: step: 504/1545, loss: 0.3436298072338104 2023-01-23 21:57:12.858475: step: 506/1545, loss: 0.0018837800016626716 2023-01-23 21:57:13.748598: step: 508/1545, loss: 0.0003786422312259674 2023-01-23 21:57:14.638485: step: 510/1545, loss: 1.3835624486091547e-05 2023-01-23 21:57:15.454185: step: 512/1545, loss: 4.253458246239461e-05 2023-01-23 21:57:16.327910: step: 514/1545, loss: 0.2287043035030365 2023-01-23 21:57:17.193905: step: 516/1545, loss: 0.026991993188858032 2023-01-23 21:57:18.097697: step: 518/1545, loss: 0.0008193618268705904 2023-01-23 21:57:19.003927: step: 520/1545, loss: 0.19306956231594086 2023-01-23 21:57:19.888906: step: 522/1545, loss: 0.00011714757420122623 2023-01-23 21:57:20.727735: step: 524/1545, loss: 0.001518790377303958 2023-01-23 21:57:21.663014: step: 526/1545, loss: 0.0003258886863477528 2023-01-23 21:57:22.528541: step: 528/1545, loss: 0.00014869893493596464 2023-01-23 21:57:23.384708: step: 530/1545, loss: 7.515717152273282e-05 2023-01-23 21:57:24.253046: step: 532/1545, loss: 0.001062504481524229 2023-01-23 21:57:25.134590: step: 534/1545, loss: 0.00020809119450859725 2023-01-23 21:57:25.986122: step: 536/1545, loss: 0.004793405067175627 2023-01-23 21:57:26.871406: step: 538/1545, loss: 0.00047511974116787314 2023-01-23 21:57:27.741807: step: 540/1545, loss: 0.007826783694326878 2023-01-23 21:57:28.722257: step: 542/1545, loss: 5.428529220807832e-06 2023-01-23 21:57:29.640892: step: 544/1545, loss: 0.029836848378181458 2023-01-23 21:57:30.545709: step: 546/1545, loss: 0.00019775121472775936 2023-01-23 21:57:31.423431: step: 548/1545, loss: 0.00013428104284685105 2023-01-23 21:57:32.339478: step: 550/1545, loss: 0.07819043099880219 2023-01-23 21:57:33.213701: step: 552/1545, loss: 0.0004237465327605605 2023-01-23 21:57:34.075099: step: 554/1545, loss: 0.0011512608034536242 2023-01-23 21:57:34.950038: step: 556/1545, loss: 0.0192892886698246 2023-01-23 21:57:35.908485: step: 558/1545, loss: -9.843899988482008e-07 2023-01-23 21:57:36.856383: step: 560/1545, loss: 0.008923301473259926 2023-01-23 21:57:37.726350: step: 562/1545, loss: 0.00017171241051983088 2023-01-23 21:57:38.632895: step: 564/1545, loss: 0.06948447972536087 2023-01-23 21:57:39.500482: step: 566/1545, loss: 0.00011278990132268518 2023-01-23 21:57:40.469313: step: 568/1545, loss: 0.003927514888346195 2023-01-23 21:57:41.338725: step: 570/1545, loss: 0.002127614803612232 2023-01-23 21:57:42.209918: step: 572/1545, loss: 0.610891580581665 2023-01-23 21:57:43.079170: step: 574/1545, loss: 3.8639369449811056e-05 2023-01-23 21:57:43.952163: step: 576/1545, loss: 1.3736882465309463e-05 2023-01-23 21:57:44.805535: step: 578/1545, loss: 0.000550418917555362 2023-01-23 21:57:45.719383: step: 580/1545, loss: 1.857612733147107e-05 2023-01-23 21:57:46.593412: step: 582/1545, loss: 0.03322536498308182 2023-01-23 21:57:47.525128: step: 584/1545, loss: 0.00021462299628183246 2023-01-23 21:57:48.358296: step: 586/1545, loss: 3.231364826206118e-05 2023-01-23 21:57:49.239213: step: 588/1545, loss: 0.19951587915420532 2023-01-23 21:57:50.129562: step: 590/1545, loss: 0.01538321003317833 2023-01-23 21:57:51.017960: step: 592/1545, loss: 0.0011829588329419494 2023-01-23 21:57:51.876331: step: 594/1545, loss: 0.00011912714398931712 2023-01-23 21:57:52.704870: step: 596/1545, loss: 0.5689144134521484 2023-01-23 21:57:53.570367: step: 598/1545, loss: 0.0003851552028208971 2023-01-23 21:57:54.388665: step: 600/1545, loss: 0.00016015174333006144 2023-01-23 21:57:55.267835: step: 602/1545, loss: 9.218194463755935e-05 2023-01-23 21:57:56.125681: step: 604/1545, loss: 9.475467231823131e-05 2023-01-23 21:57:57.020862: step: 606/1545, loss: 0.003847384126856923 2023-01-23 21:57:57.885594: step: 608/1545, loss: 0.007703699171543121 2023-01-23 21:57:58.713018: step: 610/1545, loss: 0.0007067584665492177 2023-01-23 21:57:59.567980: step: 612/1545, loss: 0.0009335796348750591 2023-01-23 21:58:00.411417: step: 614/1545, loss: 3.842770820483565e-05 2023-01-23 21:58:01.308090: step: 616/1545, loss: 0.1620446741580963 2023-01-23 21:58:02.168699: step: 618/1545, loss: 0.0002693567075766623 2023-01-23 21:58:03.034192: step: 620/1545, loss: 0.1274775266647339 2023-01-23 21:58:03.909953: step: 622/1545, loss: 0.00018927064957097173 2023-01-23 21:58:04.760577: step: 624/1545, loss: 0.0025717723183333874 2023-01-23 21:58:05.665637: step: 626/1545, loss: 0.03713204339146614 2023-01-23 21:58:06.532533: step: 628/1545, loss: 0.020149968564510345 2023-01-23 21:58:07.437565: step: 630/1545, loss: 0.03694632276892662 2023-01-23 21:58:08.298238: step: 632/1545, loss: 0.004027788992971182 2023-01-23 21:58:09.168980: step: 634/1545, loss: 0.015690619125962257 2023-01-23 21:58:10.000729: step: 636/1545, loss: 2.3111148038879037e-05 2023-01-23 21:58:10.832100: step: 638/1545, loss: 8.861790411174297e-05 2023-01-23 21:58:11.693739: step: 640/1545, loss: 0.15987540781497955 2023-01-23 21:58:12.610183: step: 642/1545, loss: 0.0005379472277127206 2023-01-23 21:58:13.501754: step: 644/1545, loss: 0.030670568346977234 2023-01-23 21:58:14.407041: step: 646/1545, loss: 0.0001033554581226781 2023-01-23 21:58:15.267616: step: 648/1545, loss: 4.627430462278426e-05 2023-01-23 21:58:16.127044: step: 650/1545, loss: 0.1274433732032776 2023-01-23 21:58:17.013001: step: 652/1545, loss: 0.20107026398181915 2023-01-23 21:58:17.863523: step: 654/1545, loss: 0.0005177465500310063 2023-01-23 21:58:18.745066: step: 656/1545, loss: 0.15961742401123047 2023-01-23 21:58:19.619439: step: 658/1545, loss: 0.00021276497864164412 2023-01-23 21:58:20.487857: step: 660/1545, loss: 0.0008647951763123274 2023-01-23 21:58:21.407956: step: 662/1545, loss: 0.3478052616119385 2023-01-23 21:58:22.328503: step: 664/1545, loss: 0.0018161655170843005 2023-01-23 21:58:23.180162: step: 666/1545, loss: 0.0005155506660230458 2023-01-23 21:58:24.039048: step: 668/1545, loss: 0.0011852483730763197 2023-01-23 21:58:24.952356: step: 670/1545, loss: 0.00038886285619810224 2023-01-23 21:58:25.822310: step: 672/1545, loss: 0.008676084689795971 2023-01-23 21:58:26.659567: step: 674/1545, loss: 0.00012423086445778608 2023-01-23 21:58:27.562951: step: 676/1545, loss: 0.004211612977087498 2023-01-23 21:58:28.457111: step: 678/1545, loss: 0.00040882962639443576 2023-01-23 21:58:29.312820: step: 680/1545, loss: 0.001052465639077127 2023-01-23 21:58:30.235829: step: 682/1545, loss: 0.0002520091366022825 2023-01-23 21:58:31.068466: step: 684/1545, loss: 0.00047120824456214905 2023-01-23 21:58:31.939000: step: 686/1545, loss: 0.000304482935462147 2023-01-23 21:58:32.817665: step: 688/1545, loss: 0.03949541226029396 2023-01-23 21:58:33.677924: step: 690/1545, loss: 0.0008556383545510471 2023-01-23 21:58:34.592623: step: 692/1545, loss: 0.003839478362351656 2023-01-23 21:58:35.512882: step: 694/1545, loss: 0.0005008995649404824 2023-01-23 21:58:36.372818: step: 696/1545, loss: 0.007339605130255222 2023-01-23 21:58:37.247591: step: 698/1545, loss: 0.008222311735153198 2023-01-23 21:58:38.127652: step: 700/1545, loss: 0.00012147502275183797 2023-01-23 21:58:38.985273: step: 702/1545, loss: 0.0013369657099246979 2023-01-23 21:58:39.826945: step: 704/1545, loss: 0.00014786788960918784 2023-01-23 21:58:40.700036: step: 706/1545, loss: 0.00011047988664358854 2023-01-23 21:58:41.546237: step: 708/1545, loss: 0.0013206085423007607 2023-01-23 21:58:42.421483: step: 710/1545, loss: 0.0010767276398837566 2023-01-23 21:58:43.261379: step: 712/1545, loss: 0.0009938946459442377 2023-01-23 21:58:44.199042: step: 714/1545, loss: 0.0001393538259435445 2023-01-23 21:58:45.096084: step: 716/1545, loss: -1.2275006156414747e-05 2023-01-23 21:58:45.984337: step: 718/1545, loss: 0.001398879219777882 2023-01-23 21:58:46.859694: step: 720/1545, loss: 0.03984968364238739 2023-01-23 21:58:47.751270: step: 722/1545, loss: 0.006756867282092571 2023-01-23 21:58:48.649633: step: 724/1545, loss: -1.347666602669051e-05 2023-01-23 21:58:49.508334: step: 726/1545, loss: 0.0001892033324111253 2023-01-23 21:58:50.368191: step: 728/1545, loss: 0.00367467338219285 2023-01-23 21:58:51.259370: step: 730/1545, loss: 0.000762412790209055 2023-01-23 21:58:52.168779: step: 732/1545, loss: 0.007191776297986507 2023-01-23 21:58:53.024339: step: 734/1545, loss: 4.586502836900763e-05 2023-01-23 21:58:53.875801: step: 736/1545, loss: 0.0032464361283928156 2023-01-23 21:58:54.729431: step: 738/1545, loss: 0.010341017507016659 2023-01-23 21:58:55.669401: step: 740/1545, loss: 0.0017646786291152239 2023-01-23 21:58:56.521833: step: 742/1545, loss: -3.7225699998089112e-06 2023-01-23 21:58:57.353004: step: 744/1545, loss: 0.00046051846584305167 2023-01-23 21:58:58.201779: step: 746/1545, loss: 0.00011534905934240669 2023-01-23 21:58:59.108053: step: 748/1545, loss: 0.0010556104825809598 2023-01-23 21:58:59.998444: step: 750/1545, loss: 0.9157465696334839 2023-01-23 21:59:00.866215: step: 752/1545, loss: 0.0017294028075411916 2023-01-23 21:59:01.735474: step: 754/1545, loss: 0.0003067842626478523 2023-01-23 21:59:02.628779: step: 756/1545, loss: 0.0005058377282693982 2023-01-23 21:59:03.500145: step: 758/1545, loss: 0.1566244214773178 2023-01-23 21:59:04.409328: step: 760/1545, loss: 0.004710282664746046 2023-01-23 21:59:05.329264: step: 762/1545, loss: 2.31232352234656e-05 2023-01-23 21:59:06.167611: step: 764/1545, loss: 2.9178905606386252e-05 2023-01-23 21:59:07.084630: step: 766/1545, loss: 0.0001865854428615421 2023-01-23 21:59:07.971757: step: 768/1545, loss: 0.0015961421886458993 2023-01-23 21:59:08.813460: step: 770/1545, loss: 0.0005562948063015938 2023-01-23 21:59:09.745775: step: 772/1545, loss: 0.00010914272570516914 2023-01-23 21:59:10.647428: step: 774/1545, loss: -4.839284883928485e-07 2023-01-23 21:59:11.512711: step: 776/1545, loss: 0.002958620898425579 2023-01-23 21:59:12.337808: step: 778/1545, loss: 0.05249772593379021 2023-01-23 21:59:13.246114: step: 780/1545, loss: 0.00011719091708073393 2023-01-23 21:59:14.120160: step: 782/1545, loss: 0.1191694512963295 2023-01-23 21:59:14.996526: step: 784/1545, loss: 0.00011037007789127529 2023-01-23 21:59:15.860072: step: 786/1545, loss: 0.20991426706314087 2023-01-23 21:59:16.718265: step: 788/1545, loss: 0.0004863546637352556 2023-01-23 21:59:17.528003: step: 790/1545, loss: 0.0006713181501254439 2023-01-23 21:59:18.374740: step: 792/1545, loss: 0.00011091132910223678 2023-01-23 21:59:19.358901: step: 794/1545, loss: 0.011895124800503254 2023-01-23 21:59:20.247807: step: 796/1545, loss: 0.00018588973034638911 2023-01-23 21:59:21.137228: step: 798/1545, loss: 0.0002839436929207295 2023-01-23 21:59:21.982520: step: 800/1545, loss: 0.03835656866431236 2023-01-23 21:59:22.880919: step: 802/1545, loss: 0.00012797345698345453 2023-01-23 21:59:23.756229: step: 804/1545, loss: 4.8684541980037466e-05 2023-01-23 21:59:24.566042: step: 806/1545, loss: 0.06348898261785507 2023-01-23 21:59:25.385861: step: 808/1545, loss: 3.511786417220719e-05 2023-01-23 21:59:26.305056: step: 810/1545, loss: 0.00019674358190968633 2023-01-23 21:59:27.150220: step: 812/1545, loss: 0.009478619322180748 2023-01-23 21:59:28.061293: step: 814/1545, loss: 0.02611156553030014 2023-01-23 21:59:28.969545: step: 816/1545, loss: 8.704548235982656e-05 2023-01-23 21:59:29.871267: step: 818/1545, loss: 0.03939797729253769 2023-01-23 21:59:30.751757: step: 820/1545, loss: 8.243567572208121e-05 2023-01-23 21:59:31.564712: step: 822/1545, loss: 0.001597949187271297 2023-01-23 21:59:32.438080: step: 824/1545, loss: 0.00012171918933745474 2023-01-23 21:59:33.328301: step: 826/1545, loss: 0.0016862773336470127 2023-01-23 21:59:34.182422: step: 828/1545, loss: 0.21898245811462402 2023-01-23 21:59:35.090506: step: 830/1545, loss: 0.0029261671006679535 2023-01-23 21:59:35.937863: step: 832/1545, loss: 0.006336743477731943 2023-01-23 21:59:36.869099: step: 834/1545, loss: 0.3269652724266052 2023-01-23 21:59:37.713494: step: 836/1545, loss: 3.312880653538741e-05 2023-01-23 21:59:38.601477: step: 838/1545, loss: 0.000179850438144058 2023-01-23 21:59:39.477646: step: 840/1545, loss: 0.0008812558371573687 2023-01-23 21:59:40.331026: step: 842/1545, loss: 0.0010012288112193346 2023-01-23 21:59:41.205624: step: 844/1545, loss: 0.0001253341615665704 2023-01-23 21:59:42.121463: step: 846/1545, loss: 0.0015716484049335122 2023-01-23 21:59:43.038464: step: 848/1545, loss: 9.56166404648684e-05 2023-01-23 21:59:43.927637: step: 850/1545, loss: 0.00042007077718153596 2023-01-23 21:59:44.793805: step: 852/1545, loss: 0.0021981874015182257 2023-01-23 21:59:45.675179: step: 854/1545, loss: 0.00014864496188238263 2023-01-23 21:59:46.536906: step: 856/1545, loss: 6.079792001401074e-05 2023-01-23 21:59:47.421298: step: 858/1545, loss: 0.03560330346226692 2023-01-23 21:59:48.310374: step: 860/1545, loss: 0.00032090747845359147 2023-01-23 21:59:49.238223: step: 862/1545, loss: 0.006212710868567228 2023-01-23 21:59:50.120226: step: 864/1545, loss: 0.10342143476009369 2023-01-23 21:59:50.967801: step: 866/1545, loss: 0.00667251693084836 2023-01-23 21:59:51.834347: step: 868/1545, loss: 0.013885551132261753 2023-01-23 21:59:52.745424: step: 870/1545, loss: 0.00035601953277364373 2023-01-23 21:59:53.604232: step: 872/1545, loss: 9.862080332823098e-05 2023-01-23 21:59:54.502235: step: 874/1545, loss: 0.0005704330396838486 2023-01-23 21:59:55.355000: step: 876/1545, loss: 0.03174649551510811 2023-01-23 21:59:56.287472: step: 878/1545, loss: 0.0001952300372067839 2023-01-23 21:59:57.117950: step: 880/1545, loss: 0.0001971568854060024 2023-01-23 21:59:58.056150: step: 882/1545, loss: 0.0003066302742809057 2023-01-23 21:59:58.982046: step: 884/1545, loss: 0.0007591766770929098 2023-01-23 21:59:59.882250: step: 886/1545, loss: 0.00047208007890731096 2023-01-23 22:00:00.751272: step: 888/1545, loss: 0.03154937922954559 2023-01-23 22:00:01.632621: step: 890/1545, loss: 0.00015660125063732266 2023-01-23 22:00:02.563052: step: 892/1545, loss: 0.0003172568103764206 2023-01-23 22:00:03.433840: step: 894/1545, loss: 0.13240821659564972 2023-01-23 22:00:04.298951: step: 896/1545, loss: 0.0015213011065497994 2023-01-23 22:00:05.251918: step: 898/1545, loss: 0.0014906693249940872 2023-01-23 22:00:06.172612: step: 900/1545, loss: 0.008609892800450325 2023-01-23 22:00:07.015323: step: 902/1545, loss: 7.836787699488923e-05 2023-01-23 22:00:07.895656: step: 904/1545, loss: 0.0001054799577104859 2023-01-23 22:00:08.817978: step: 906/1545, loss: 0.011887152679264545 2023-01-23 22:00:09.690686: step: 908/1545, loss: 2.137697696685791 2023-01-23 22:00:10.615664: step: 910/1545, loss: 0.0012842199066653848 2023-01-23 22:00:11.466391: step: 912/1545, loss: 0.018493475392460823 2023-01-23 22:00:12.368630: step: 914/1545, loss: 8.0048521340359e-05 2023-01-23 22:00:13.244546: step: 916/1545, loss: 0.00015709978470113128 2023-01-23 22:00:14.100146: step: 918/1545, loss: 8.495352085446939e-05 2023-01-23 22:00:15.003968: step: 920/1545, loss: 0.0004973866743966937 2023-01-23 22:00:15.866144: step: 922/1545, loss: 0.049944501370191574 2023-01-23 22:00:16.819216: step: 924/1545, loss: 0.026419486850500107 2023-01-23 22:00:17.703179: step: 926/1545, loss: 0.000579535320866853 2023-01-23 22:00:18.564977: step: 928/1545, loss: 0.00035105147981084883 2023-01-23 22:00:19.458413: step: 930/1545, loss: 0.0010323304450139403 2023-01-23 22:00:20.328599: step: 932/1545, loss: 0.00018632110732141882 2023-01-23 22:00:21.207327: step: 934/1545, loss: 0.004494781140238047 2023-01-23 22:00:22.064757: step: 936/1545, loss: 0.00018552123219706118 2023-01-23 22:00:22.990588: step: 938/1545, loss: 0.0002390048757661134 2023-01-23 22:00:23.849985: step: 940/1545, loss: 0.00016286940081045032 2023-01-23 22:00:24.807132: step: 942/1545, loss: 0.0007915639434941113 2023-01-23 22:00:25.664045: step: 944/1545, loss: 0.00012485357001423836 2023-01-23 22:00:26.550534: step: 946/1545, loss: 7.633081986568868e-05 2023-01-23 22:00:27.399084: step: 948/1545, loss: 0.010859200730919838 2023-01-23 22:00:28.267377: step: 950/1545, loss: 0.029672496020793915 2023-01-23 22:00:29.169495: step: 952/1545, loss: 0.0005615842528641224 2023-01-23 22:00:30.008097: step: 954/1545, loss: 0.000898745667655021 2023-01-23 22:00:30.868691: step: 956/1545, loss: 0.0840090811252594 2023-01-23 22:00:31.685894: step: 958/1545, loss: 0.00047544343397021294 2023-01-23 22:00:32.584168: step: 960/1545, loss: 6.411941285477951e-05 2023-01-23 22:00:33.484914: step: 962/1545, loss: 0.0019620961975306273 2023-01-23 22:00:34.346859: step: 964/1545, loss: 0.14373397827148438 2023-01-23 22:00:35.209742: step: 966/1545, loss: 0.00014918549277354032 2023-01-23 22:00:36.122297: step: 968/1545, loss: 0.00014774076407775283 2023-01-23 22:00:37.001591: step: 970/1545, loss: 1.0807052850723267 2023-01-23 22:00:37.878962: step: 972/1545, loss: 4.978585639037192e-05 2023-01-23 22:00:38.757370: step: 974/1545, loss: 0.1369645893573761 2023-01-23 22:00:39.645603: step: 976/1545, loss: 0.009641599841415882 2023-01-23 22:00:40.524965: step: 978/1545, loss: 0.06235276907682419 2023-01-23 22:00:41.419342: step: 980/1545, loss: 0.2968049645423889 2023-01-23 22:00:42.320741: step: 982/1545, loss: 0.0015889869537204504 2023-01-23 22:00:43.223117: step: 984/1545, loss: 0.0009307396248914301 2023-01-23 22:00:44.085495: step: 986/1545, loss: 0.08601361513137817 2023-01-23 22:00:45.017396: step: 988/1545, loss: 0.0020973235368728638 2023-01-23 22:00:46.007581: step: 990/1545, loss: 0.011767031624913216 2023-01-23 22:00:46.884439: step: 992/1545, loss: 0.30932140350341797 2023-01-23 22:00:47.759560: step: 994/1545, loss: 0.00011593200906645507 2023-01-23 22:00:48.623593: step: 996/1545, loss: 0.005510407034307718 2023-01-23 22:00:49.508098: step: 998/1545, loss: 3.367824319866486e-05 2023-01-23 22:00:50.444793: step: 1000/1545, loss: 0.04099300503730774 2023-01-23 22:00:51.370669: step: 1002/1545, loss: 0.02001487836241722 2023-01-23 22:00:52.233659: step: 1004/1545, loss: 0.39071887731552124 2023-01-23 22:00:53.096123: step: 1006/1545, loss: 0.0007308717467822134 2023-01-23 22:00:53.942318: step: 1008/1545, loss: -1.687010080786422e-05 2023-01-23 22:00:54.898204: step: 1010/1545, loss: 0.021556364372372627 2023-01-23 22:00:55.795556: step: 1012/1545, loss: 0.00024044619931373745 2023-01-23 22:00:56.661154: step: 1014/1545, loss: 0.0002807159908115864 2023-01-23 22:00:57.528860: step: 1016/1545, loss: 0.00027430010959506035 2023-01-23 22:00:58.404053: step: 1018/1545, loss: 5.7423098041908816e-05 2023-01-23 22:00:59.338082: step: 1020/1545, loss: 0.0001131667013396509 2023-01-23 22:01:00.248967: step: 1022/1545, loss: 0.0015714886831119657 2023-01-23 22:01:01.118482: step: 1024/1545, loss: 0.001174640259705484 2023-01-23 22:01:02.024630: step: 1026/1545, loss: 0.0008654529810883105 2023-01-23 22:01:02.879594: step: 1028/1545, loss: 0.002792451996356249 2023-01-23 22:01:03.811484: step: 1030/1545, loss: 0.0025113397277891636 2023-01-23 22:01:04.699197: step: 1032/1545, loss: 0.24027757346630096 2023-01-23 22:01:05.575822: step: 1034/1545, loss: 0.0026793386787176132 2023-01-23 22:01:06.448331: step: 1036/1545, loss: 0.006051227916032076 2023-01-23 22:01:07.296734: step: 1038/1545, loss: 0.0002492797211743891 2023-01-23 22:01:08.222964: step: 1040/1545, loss: 0.021721551194787025 2023-01-23 22:01:09.123436: step: 1042/1545, loss: 0.00023587344912812114 2023-01-23 22:01:10.038250: step: 1044/1545, loss: -2.317527832929045e-05 2023-01-23 22:01:10.973681: step: 1046/1545, loss: 4.220836126478389e-05 2023-01-23 22:01:11.883921: step: 1048/1545, loss: 0.0010524166282266378 2023-01-23 22:01:12.750842: step: 1050/1545, loss: 0.0004498126218095422 2023-01-23 22:01:13.624451: step: 1052/1545, loss: 0.00946630910038948 2023-01-23 22:01:14.476447: step: 1054/1545, loss: 0.07170239090919495 2023-01-23 22:01:15.322349: step: 1056/1545, loss: 0.0014129888731986284 2023-01-23 22:01:16.219687: step: 1058/1545, loss: 0.1471324861049652 2023-01-23 22:01:17.147299: step: 1060/1545, loss: 0.00015284355322364718 2023-01-23 22:01:17.982188: step: 1062/1545, loss: 0.09409964084625244 2023-01-23 22:01:18.827157: step: 1064/1545, loss: -6.328430117719108e-07 2023-01-23 22:01:19.739041: step: 1066/1545, loss: 0.366863876581192 2023-01-23 22:01:20.621887: step: 1068/1545, loss: 0.00040422577876597643 2023-01-23 22:01:21.501942: step: 1070/1545, loss: 8.956357487477362e-05 2023-01-23 22:01:22.402103: step: 1072/1545, loss: 0.0004261108406353742 2023-01-23 22:01:23.249981: step: 1074/1545, loss: 0.03289500251412392 2023-01-23 22:01:24.124755: step: 1076/1545, loss: 0.778741717338562 2023-01-23 22:01:25.036630: step: 1078/1545, loss: 3.308938175905496e-05 2023-01-23 22:01:25.991394: step: 1080/1545, loss: 0.0005746682872995734 2023-01-23 22:01:26.898266: step: 1082/1545, loss: 0.00037501801853068173 2023-01-23 22:01:27.806665: step: 1084/1545, loss: 2.0447128918021917e-05 2023-01-23 22:01:28.706634: step: 1086/1545, loss: 0.000963084283284843 2023-01-23 22:01:29.576022: step: 1088/1545, loss: 0.09391885995864868 2023-01-23 22:01:30.484875: step: 1090/1545, loss: 0.22866889834403992 2023-01-23 22:01:31.325282: step: 1092/1545, loss: 0.639274001121521 2023-01-23 22:01:32.198125: step: 1094/1545, loss: 0.0379476323723793 2023-01-23 22:01:33.074685: step: 1096/1545, loss: 0.6043102741241455 2023-01-23 22:01:33.929627: step: 1098/1545, loss: 0.0013813276309520006 2023-01-23 22:01:34.789360: step: 1100/1545, loss: 0.062187861651182175 2023-01-23 22:01:35.715999: step: 1102/1545, loss: 0.002302536740899086 2023-01-23 22:01:36.579409: step: 1104/1545, loss: 0.00016259131371043622 2023-01-23 22:01:37.464055: step: 1106/1545, loss: 0.11083583533763885 2023-01-23 22:01:38.333446: step: 1108/1545, loss: 0.5441286563873291 2023-01-23 22:01:39.222044: step: 1110/1545, loss: 0.00013789327931590378 2023-01-23 22:01:40.166322: step: 1112/1545, loss: 0.0068972171284258366 2023-01-23 22:01:41.015635: step: 1114/1545, loss: 0.0007198344683274627 2023-01-23 22:01:41.879581: step: 1116/1545, loss: 2.813538594637066e-05 2023-01-23 22:01:42.794005: step: 1118/1545, loss: 0.07531413435935974 2023-01-23 22:01:43.702487: step: 1120/1545, loss: 0.16531267762184143 2023-01-23 22:01:44.578047: step: 1122/1545, loss: 0.00012933554535266012 2023-01-23 22:01:45.433419: step: 1124/1545, loss: 0.06279313564300537 2023-01-23 22:01:46.323432: step: 1126/1545, loss: 0.0030224863439798355 2023-01-23 22:01:47.227742: step: 1128/1545, loss: 0.008606698364019394 2023-01-23 22:01:48.077256: step: 1130/1545, loss: 0.0670866146683693 2023-01-23 22:01:48.942181: step: 1132/1545, loss: 0.0009173104772344232 2023-01-23 22:01:49.791700: step: 1134/1545, loss: 0.00015056143456604332 2023-01-23 22:01:50.700004: step: 1136/1545, loss: 0.001954254461452365 2023-01-23 22:01:51.610655: step: 1138/1545, loss: 0.006713454145938158 2023-01-23 22:01:52.465451: step: 1140/1545, loss: 0.001399798202328384 2023-01-23 22:01:53.310578: step: 1142/1545, loss: 0.000808653945568949 2023-01-23 22:01:54.184351: step: 1144/1545, loss: 0.0052613914012908936 2023-01-23 22:01:55.089015: step: 1146/1545, loss: 0.005786376539617777 2023-01-23 22:01:55.990457: step: 1148/1545, loss: 0.23844538629055023 2023-01-23 22:01:56.835533: step: 1150/1545, loss: 0.0016363646136596799 2023-01-23 22:01:57.684677: step: 1152/1545, loss: 0.006454978138208389 2023-01-23 22:01:58.592004: step: 1154/1545, loss: 0.0004953033640049398 2023-01-23 22:01:59.475722: step: 1156/1545, loss: 3.37088895321358e-05 2023-01-23 22:02:00.381608: step: 1158/1545, loss: 0.0006416760152205825 2023-01-23 22:02:01.298155: step: 1160/1545, loss: 0.01870041713118553 2023-01-23 22:02:02.138753: step: 1162/1545, loss: 0.0011379033094272017 2023-01-23 22:02:02.977484: step: 1164/1545, loss: 0.19330377876758575 2023-01-23 22:02:03.841332: step: 1166/1545, loss: 4.074507887708023e-05 2023-01-23 22:02:04.728663: step: 1168/1545, loss: 0.0022885652724653482 2023-01-23 22:02:05.606150: step: 1170/1545, loss: 0.00018537223513703793 2023-01-23 22:02:06.539584: step: 1172/1545, loss: 0.0001060768699971959 2023-01-23 22:02:07.423846: step: 1174/1545, loss: 0.08732900023460388 2023-01-23 22:02:08.333844: step: 1176/1545, loss: 0.0010821286123245955 2023-01-23 22:02:09.259270: step: 1178/1545, loss: 0.002113212365657091 2023-01-23 22:02:10.184213: step: 1180/1545, loss: 3.9812278747558594 2023-01-23 22:02:11.047777: step: 1182/1545, loss: 0.09322264790534973 2023-01-23 22:02:11.968384: step: 1184/1545, loss: 0.014622833579778671 2023-01-23 22:02:12.850776: step: 1186/1545, loss: 0.12082083523273468 2023-01-23 22:02:13.720698: step: 1188/1545, loss: 0.00036230660043656826 2023-01-23 22:02:14.607036: step: 1190/1545, loss: 0.001933917636051774 2023-01-23 22:02:15.456057: step: 1192/1545, loss: 0.00012134525604778901 2023-01-23 22:02:16.327953: step: 1194/1545, loss: 0.08489999175071716 2023-01-23 22:02:17.290142: step: 1196/1545, loss: 0.00041128817247226834 2023-01-23 22:02:18.145672: step: 1198/1545, loss: 9.359965042676777e-05 2023-01-23 22:02:19.014068: step: 1200/1545, loss: 0.0018845110898837447 2023-01-23 22:02:19.960170: step: 1202/1545, loss: 0.0013457181630656123 2023-01-23 22:02:20.885885: step: 1204/1545, loss: 0.025996290147304535 2023-01-23 22:02:21.837484: step: 1206/1545, loss: 2.7521948140929453e-05 2023-01-23 22:02:22.685778: step: 1208/1545, loss: 2.6461466404725797e-05 2023-01-23 22:02:23.602931: step: 1210/1545, loss: 0.0002669022069312632 2023-01-23 22:02:24.518740: step: 1212/1545, loss: 6.204089004313573e-06 2023-01-23 22:02:25.411233: step: 1214/1545, loss: 1.567601429997012e-05 2023-01-23 22:02:26.311688: step: 1216/1545, loss: 0.007224628236144781 2023-01-23 22:02:27.218600: step: 1218/1545, loss: 0.329253226518631 2023-01-23 22:02:28.124368: step: 1220/1545, loss: 0.0005881408578716218 2023-01-23 22:02:29.053076: step: 1222/1545, loss: 3.567002931958996e-05 2023-01-23 22:02:29.976748: step: 1224/1545, loss: 0.00036516625550575554 2023-01-23 22:02:30.886619: step: 1226/1545, loss: 0.0006507975631393492 2023-01-23 22:02:31.799354: step: 1228/1545, loss: 0.015359214507043362 2023-01-23 22:02:32.690767: step: 1230/1545, loss: 0.00010392148396931589 2023-01-23 22:02:33.551730: step: 1232/1545, loss: 0.001759020029567182 2023-01-23 22:02:34.405845: step: 1234/1545, loss: 0.00560262193903327 2023-01-23 22:02:35.286011: step: 1236/1545, loss: 0.46469026803970337 2023-01-23 22:02:36.119126: step: 1238/1545, loss: 0.00014771813584957272 2023-01-23 22:02:36.987521: step: 1240/1545, loss: 0.0005396915948949754 2023-01-23 22:02:37.854825: step: 1242/1545, loss: 0.2843235433101654 2023-01-23 22:02:38.745043: step: 1244/1545, loss: 0.011724201031029224 2023-01-23 22:02:39.642254: step: 1246/1545, loss: 0.0009877390693873167 2023-01-23 22:02:40.518340: step: 1248/1545, loss: 0.005132502876222134 2023-01-23 22:02:41.407888: step: 1250/1545, loss: 7.323013414861634e-05 2023-01-23 22:02:42.289691: step: 1252/1545, loss: 0.00028098333859816194 2023-01-23 22:02:43.154992: step: 1254/1545, loss: 0.0007720977300778031 2023-01-23 22:02:43.978049: step: 1256/1545, loss: 0.002288843970745802 2023-01-23 22:02:44.901655: step: 1258/1545, loss: 0.011383463628590107 2023-01-23 22:02:45.776696: step: 1260/1545, loss: 0.000573395227547735 2023-01-23 22:02:46.689309: step: 1262/1545, loss: 0.04894047603011131 2023-01-23 22:02:47.555354: step: 1264/1545, loss: 0.001307494007050991 2023-01-23 22:02:48.431717: step: 1266/1545, loss: 0.0020914420019835234 2023-01-23 22:02:49.386684: step: 1268/1545, loss: 0.20708416402339935 2023-01-23 22:02:50.306009: step: 1270/1545, loss: 0.045326657593250275 2023-01-23 22:02:51.164262: step: 1272/1545, loss: 0.00015032864757813513 2023-01-23 22:02:52.009493: step: 1274/1545, loss: 0.0005677774315699935 2023-01-23 22:02:52.914947: step: 1276/1545, loss: 0.0016947508556768298 2023-01-23 22:02:53.811861: step: 1278/1545, loss: 0.03657424822449684 2023-01-23 22:02:54.735549: step: 1280/1545, loss: 0.00029323145281523466 2023-01-23 22:02:55.608796: step: 1282/1545, loss: 0.0019295765087008476 2023-01-23 22:02:56.519772: step: 1284/1545, loss: 0.08988633006811142 2023-01-23 22:02:57.391352: step: 1286/1545, loss: 0.00023129390319809318 2023-01-23 22:02:58.224722: step: 1288/1545, loss: 0.001688542659394443 2023-01-23 22:02:59.117761: step: 1290/1545, loss: 0.009017368778586388 2023-01-23 22:03:00.026088: step: 1292/1545, loss: 0.03879377618432045 2023-01-23 22:03:00.934526: step: 1294/1545, loss: 0.6506505608558655 2023-01-23 22:03:01.778877: step: 1296/1545, loss: 0.00011995964450761676 2023-01-23 22:03:02.676672: step: 1298/1545, loss: 9.069522639038041e-05 2023-01-23 22:03:03.664696: step: 1300/1545, loss: 0.16180287301540375 2023-01-23 22:03:04.545046: step: 1302/1545, loss: 3.5965018469141796e-05 2023-01-23 22:03:05.434816: step: 1304/1545, loss: 0.0013863128842785954 2023-01-23 22:03:06.322380: step: 1306/1545, loss: 6.233921885723248e-05 2023-01-23 22:03:07.207593: step: 1308/1545, loss: 0.00035307477810420096 2023-01-23 22:03:08.079301: step: 1310/1545, loss: 6.23707746854052e-05 2023-01-23 22:03:08.956718: step: 1312/1545, loss: 0.00011100676056230441 2023-01-23 22:03:09.841420: step: 1314/1545, loss: 2.0632147425203584e-05 2023-01-23 22:03:10.750465: step: 1316/1545, loss: 0.0002799217472784221 2023-01-23 22:03:11.630818: step: 1318/1545, loss: 2.353191484871786e-05 2023-01-23 22:03:12.520793: step: 1320/1545, loss: 0.1289398968219757 2023-01-23 22:03:13.379771: step: 1322/1545, loss: 0.0022110077552497387 2023-01-23 22:03:14.249252: step: 1324/1545, loss: 8.572815204388462e-06 2023-01-23 22:03:15.130261: step: 1326/1545, loss: 8.098551188595593e-05 2023-01-23 22:03:16.001761: step: 1328/1545, loss: 0.007898490875959396 2023-01-23 22:03:16.868258: step: 1330/1545, loss: 0.0014573965454474092 2023-01-23 22:03:17.780015: step: 1332/1545, loss: 0.14055822789669037 2023-01-23 22:03:18.682830: step: 1334/1545, loss: 0.15400609374046326 2023-01-23 22:03:19.581450: step: 1336/1545, loss: 0.050735462456941605 2023-01-23 22:03:20.482192: step: 1338/1545, loss: 0.03627842292189598 2023-01-23 22:03:21.371912: step: 1340/1545, loss: 0.050313327461481094 2023-01-23 22:03:22.252030: step: 1342/1545, loss: 0.00812100525945425 2023-01-23 22:03:23.208050: step: 1344/1545, loss: 0.010551624931395054 2023-01-23 22:03:24.099147: step: 1346/1545, loss: 0.005230613052845001 2023-01-23 22:03:25.013789: step: 1348/1545, loss: 0.013584698550403118 2023-01-23 22:03:26.049023: step: 1350/1545, loss: 0.02594289742410183 2023-01-23 22:03:26.934549: step: 1352/1545, loss: 4.039850318804383e-05 2023-01-23 22:03:27.830301: step: 1354/1545, loss: 7.614460628246889e-05 2023-01-23 22:03:28.692917: step: 1356/1545, loss: 0.0002540353452786803 2023-01-23 22:03:29.579483: step: 1358/1545, loss: 0.00018662787624634802 2023-01-23 22:03:30.432871: step: 1360/1545, loss: 0.0009199577616527677 2023-01-23 22:03:31.364482: step: 1362/1545, loss: 0.3374934196472168 2023-01-23 22:03:32.262856: step: 1364/1545, loss: 0.04395764321088791 2023-01-23 22:03:33.206381: step: 1366/1545, loss: 0.047082722187042236 2023-01-23 22:03:34.102256: step: 1368/1545, loss: 0.008076692000031471 2023-01-23 22:03:34.949617: step: 1370/1545, loss: 0.00012735337077174336 2023-01-23 22:03:35.803527: step: 1372/1545, loss: 0.00029118655947968364 2023-01-23 22:03:36.680265: step: 1374/1545, loss: 0.047483593225479126 2023-01-23 22:03:37.556188: step: 1376/1545, loss: 0.00016541691729798913 2023-01-23 22:03:38.445908: step: 1378/1545, loss: 3.112756894552149e-05 2023-01-23 22:03:39.333163: step: 1380/1545, loss: 0.0001844127255026251 2023-01-23 22:03:40.231326: step: 1382/1545, loss: 0.014584685675799847 2023-01-23 22:03:41.120975: step: 1384/1545, loss: 0.019867567345499992 2023-01-23 22:03:41.968438: step: 1386/1545, loss: 0.0240784902125597 2023-01-23 22:03:42.874738: step: 1388/1545, loss: 0.0023109258618205786 2023-01-23 22:03:43.752366: step: 1390/1545, loss: 0.024239595979452133 2023-01-23 22:03:44.614755: step: 1392/1545, loss: 0.00013489658886101097 2023-01-23 22:03:45.446054: step: 1394/1545, loss: 0.07656846195459366 2023-01-23 22:03:46.356611: step: 1396/1545, loss: 3.574637230485678e-05 2023-01-23 22:03:47.237617: step: 1398/1545, loss: 0.0013483695220202208 2023-01-23 22:03:48.158431: step: 1400/1545, loss: 0.030170902609825134 2023-01-23 22:03:49.037466: step: 1402/1545, loss: 0.008997985161840916 2023-01-23 22:03:49.949922: step: 1404/1545, loss: 0.5192733407020569 2023-01-23 22:03:50.815668: step: 1406/1545, loss: 0.00023456179769709706 2023-01-23 22:03:51.680412: step: 1408/1545, loss: 0.005892320070415735 2023-01-23 22:03:52.584066: step: 1410/1545, loss: -5.769437848357484e-06 2023-01-23 22:03:53.449091: step: 1412/1545, loss: 1.227892518043518 2023-01-23 22:03:54.316515: step: 1414/1545, loss: 0.001387739204801619 2023-01-23 22:03:55.331460: step: 1416/1545, loss: 0.00015068674110807478 2023-01-23 22:03:56.249185: step: 1418/1545, loss: 0.40941551327705383 2023-01-23 22:03:57.110923: step: 1420/1545, loss: 1.264290690422058 2023-01-23 22:03:57.973568: step: 1422/1545, loss: 0.006268245633691549 2023-01-23 22:03:58.839563: step: 1424/1545, loss: 0.00041792940464802086 2023-01-23 22:03:59.710498: step: 1426/1545, loss: 6.462670717155561e-05 2023-01-23 22:04:00.596434: step: 1428/1545, loss: 0.00016622176917735487 2023-01-23 22:04:01.464607: step: 1430/1545, loss: 0.12855622172355652 2023-01-23 22:04:02.351031: step: 1432/1545, loss: 0.10018076002597809 2023-01-23 22:04:03.245794: step: 1434/1545, loss: 0.03235316276550293 2023-01-23 22:04:04.132487: step: 1436/1545, loss: 0.0003778178943321109 2023-01-23 22:04:05.017891: step: 1438/1545, loss: 5.236651486484334e-05 2023-01-23 22:04:05.870293: step: 1440/1545, loss: 0.0018343605333939195 2023-01-23 22:04:06.760112: step: 1442/1545, loss: 0.008681843057274818 2023-01-23 22:04:07.645060: step: 1444/1545, loss: 0.0017496696673333645 2023-01-23 22:04:08.537875: step: 1446/1545, loss: 8.417107164859772e-05 2023-01-23 22:04:09.401472: step: 1448/1545, loss: 0.00031454680720344186 2023-01-23 22:04:10.285644: step: 1450/1545, loss: 0.004357566125690937 2023-01-23 22:04:11.172958: step: 1452/1545, loss: 5.7450306485407054e-05 2023-01-23 22:04:12.074844: step: 1454/1545, loss: 0.0031828475184738636 2023-01-23 22:04:12.945149: step: 1456/1545, loss: 0.0015252195298671722 2023-01-23 22:04:13.809915: step: 1458/1545, loss: -4.1027702536666766e-05 2023-01-23 22:04:14.712228: step: 1460/1545, loss: 0.00019935965246986598 2023-01-23 22:04:15.595968: step: 1462/1545, loss: 0.00077372434316203 2023-01-23 22:04:16.469017: step: 1464/1545, loss: 0.007343417964875698 2023-01-23 22:04:17.343204: step: 1466/1545, loss: 0.009924918413162231 2023-01-23 22:04:18.235190: step: 1468/1545, loss: 0.6125566363334656 2023-01-23 22:04:19.130580: step: 1470/1545, loss: 1.6346560869351379e-06 2023-01-23 22:04:19.997900: step: 1472/1545, loss: 0.1175847128033638 2023-01-23 22:04:20.969548: step: 1474/1545, loss: 1.8782915503834374e-05 2023-01-23 22:04:21.836547: step: 1476/1545, loss: 0.07715889066457748 2023-01-23 22:04:22.726556: step: 1478/1545, loss: 0.0016064359806478024 2023-01-23 22:04:23.588727: step: 1480/1545, loss: 0.10236938297748566 2023-01-23 22:04:24.488444: step: 1482/1545, loss: 0.012959359213709831 2023-01-23 22:04:25.386391: step: 1484/1545, loss: 0.002017961349338293 2023-01-23 22:04:26.295104: step: 1486/1545, loss: 0.013100712560117245 2023-01-23 22:04:27.251955: step: 1488/1545, loss: 0.11778322607278824 2023-01-23 22:04:28.140618: step: 1490/1545, loss: 0.0008823787793517113 2023-01-23 22:04:29.022408: step: 1492/1545, loss: 0.22936461865901947 2023-01-23 22:04:29.880201: step: 1494/1545, loss: 2.485923505446408e-05 2023-01-23 22:04:30.787063: step: 1496/1545, loss: 0.0007759778527542949 2023-01-23 22:04:31.677246: step: 1498/1545, loss: -1.027558755595237e-05 2023-01-23 22:04:32.541439: step: 1500/1545, loss: -8.969026566774119e-06 2023-01-23 22:04:33.422506: step: 1502/1545, loss: 0.04144257307052612 2023-01-23 22:04:34.307480: step: 1504/1545, loss: 8.152772352332249e-05 2023-01-23 22:04:35.177366: step: 1506/1545, loss: 3.4088843676727265e-05 2023-01-23 22:04:36.099936: step: 1508/1545, loss: 7.617082155775279e-05 2023-01-23 22:04:36.992004: step: 1510/1545, loss: 0.00014718680176883936 2023-01-23 22:04:37.872293: step: 1512/1545, loss: 0.27595263719558716 2023-01-23 22:04:38.750292: step: 1514/1545, loss: 2.0180397768854164e-05 2023-01-23 22:04:39.623186: step: 1516/1545, loss: 0.3831794559955597 2023-01-23 22:04:40.525591: step: 1518/1545, loss: 0.0026711844839155674 2023-01-23 22:04:41.410865: step: 1520/1545, loss: 0.16201473772525787 2023-01-23 22:04:42.278182: step: 1522/1545, loss: 0.00020259640587028116 2023-01-23 22:04:43.166308: step: 1524/1545, loss: 0.0038861834909766912 2023-01-23 22:04:44.068683: step: 1526/1545, loss: 4.330545198172331e-05 2023-01-23 22:04:44.926725: step: 1528/1545, loss: 1.240218261955306e-05 2023-01-23 22:04:45.890332: step: 1530/1545, loss: 0.0004246759053785354 2023-01-23 22:04:46.789820: step: 1532/1545, loss: 0.005815505515784025 2023-01-23 22:04:47.663896: step: 1534/1545, loss: 0.08095984905958176 2023-01-23 22:04:48.516439: step: 1536/1545, loss: 0.11895490437746048 2023-01-23 22:04:49.391025: step: 1538/1545, loss: 0.001608163584023714 2023-01-23 22:04:50.327837: step: 1540/1545, loss: 0.06111665442585945 2023-01-23 22:04:51.192759: step: 1542/1545, loss: 0.003965608775615692 2023-01-23 22:04:52.069460: step: 1544/1545, loss: 0.053629498928785324 2023-01-23 22:04:52.970970: step: 1546/1545, loss: 2.790629878290929e-05 2023-01-23 22:04:53.831935: step: 1548/1545, loss: 0.00027473835507407784 2023-01-23 22:04:54.712673: step: 1550/1545, loss: 0.19534748792648315 2023-01-23 22:04:55.594092: step: 1552/1545, loss: 0.011397039517760277 2023-01-23 22:04:56.494049: step: 1554/1545, loss: 4.321585178375244 2023-01-23 22:04:57.392516: step: 1556/1545, loss: 4.3875566916540265e-05 2023-01-23 22:04:58.291249: step: 1558/1545, loss: 0.5210003852844238 2023-01-23 22:04:59.227782: step: 1560/1545, loss: 0.05415448918938637 2023-01-23 22:05:00.125074: step: 1562/1545, loss: 4.838345557800494e-05 2023-01-23 22:05:01.018712: step: 1564/1545, loss: 0.19833609461784363 2023-01-23 22:05:01.917408: step: 1566/1545, loss: 0.003088670317083597 2023-01-23 22:05:02.866254: step: 1568/1545, loss: 0.1310022473335266 2023-01-23 22:05:03.773237: step: 1570/1545, loss: 5.3603193919116165e-06 2023-01-23 22:05:04.620102: step: 1572/1545, loss: -1.0924977686954662e-06 2023-01-23 22:05:05.501989: step: 1574/1545, loss: 0.00010114859469467774 2023-01-23 22:05:06.416738: step: 1576/1545, loss: 0.0028722251299768686 2023-01-23 22:05:07.297242: step: 1578/1545, loss: 0.00018531772366259247 2023-01-23 22:05:08.245788: step: 1580/1545, loss: 0.1230950877070427 2023-01-23 22:05:09.106727: step: 1582/1545, loss: 0.006533531472086906 2023-01-23 22:05:09.947188: step: 1584/1545, loss: 0.000325423083268106 2023-01-23 22:05:10.846960: step: 1586/1545, loss: 0.00023664215405005962 2023-01-23 22:05:11.716206: step: 1588/1545, loss: 0.0005379727226682007 2023-01-23 22:05:12.601835: step: 1590/1545, loss: 0.0008416931377723813 2023-01-23 22:05:13.487067: step: 1592/1545, loss: 0.2123953402042389 2023-01-23 22:05:14.366156: step: 1594/1545, loss: 0.009666788391768932 2023-01-23 22:05:15.208573: step: 1596/1545, loss: -4.925330813421169e-06 2023-01-23 22:05:16.077958: step: 1598/1545, loss: 6.628645678574685e-06 2023-01-23 22:05:16.966723: step: 1600/1545, loss: 0.0008339555351994932 2023-01-23 22:05:17.838533: step: 1602/1545, loss: 0.00030109504587017 2023-01-23 22:05:18.824575: step: 1604/1545, loss: 9.390723425894976e-05 2023-01-23 22:05:19.669199: step: 1606/1545, loss: 0.0012570221442729235 2023-01-23 22:05:20.539506: step: 1608/1545, loss: 8.39759231894277e-05 2023-01-23 22:05:21.395637: step: 1610/1545, loss: 4.307893686927855e-05 2023-01-23 22:05:22.288653: step: 1612/1545, loss: 0.0042123631574213505 2023-01-23 22:05:23.151883: step: 1614/1545, loss: 0.0007566436543129385 2023-01-23 22:05:24.017554: step: 1616/1545, loss: 2.373695679125376e-05 2023-01-23 22:05:24.870461: step: 1618/1545, loss: 0.06778981536626816 2023-01-23 22:05:25.763388: step: 1620/1545, loss: 0.005921393632888794 2023-01-23 22:05:26.684315: step: 1622/1545, loss: 2.1852796635357663e-05 2023-01-23 22:05:27.571933: step: 1624/1545, loss: 5.5797467211959884e-05 2023-01-23 22:05:28.486539: step: 1626/1545, loss: 0.004387164022773504 2023-01-23 22:05:29.328918: step: 1628/1545, loss: -1.0406971341581084e-05 2023-01-23 22:05:30.231306: step: 1630/1545, loss: 0.1868920773267746 2023-01-23 22:05:31.190761: step: 1632/1545, loss: -5.893140769330785e-05 2023-01-23 22:05:32.073806: step: 1634/1545, loss: 0.004714777693152428 2023-01-23 22:05:33.012639: step: 1636/1545, loss: 0.030115436762571335 2023-01-23 22:05:33.891584: step: 1638/1545, loss: 0.24338865280151367 2023-01-23 22:05:34.808932: step: 1640/1545, loss: 7.5292591645848e-05 2023-01-23 22:05:35.683890: step: 1642/1545, loss: 3.0767914722673595e-05 2023-01-23 22:05:36.586339: step: 1644/1545, loss: 0.05921795964241028 2023-01-23 22:05:37.495794: step: 1646/1545, loss: 0.0004773174587171525 2023-01-23 22:05:38.380318: step: 1648/1545, loss: 0.03921615332365036 2023-01-23 22:05:39.261238: step: 1650/1545, loss: 0.0001306826015934348 2023-01-23 22:05:40.137565: step: 1652/1545, loss: 0.1573989987373352 2023-01-23 22:05:41.034753: step: 1654/1545, loss: 8.289714605780318e-05 2023-01-23 22:05:41.875139: step: 1656/1545, loss: 0.0007226080051623285 2023-01-23 22:05:42.752433: step: 1658/1545, loss: 3.1714637316326844e-06 2023-01-23 22:05:43.623890: step: 1660/1545, loss: 0.0008569604833610356 2023-01-23 22:05:44.466837: step: 1662/1545, loss: 0.0217728428542614 2023-01-23 22:05:45.349676: step: 1664/1545, loss: 0.0002749435661826283 2023-01-23 22:05:46.253878: step: 1666/1545, loss: 0.0020790703129023314 2023-01-23 22:05:47.183687: step: 1668/1545, loss: 0.0005168729112483561 2023-01-23 22:05:48.085704: step: 1670/1545, loss: 0.06190349906682968 2023-01-23 22:05:49.014632: step: 1672/1545, loss: 0.0023315795697271824 2023-01-23 22:05:49.923259: step: 1674/1545, loss: 0.001669695833697915 2023-01-23 22:05:50.862014: step: 1676/1545, loss: 6.661102088401094e-05 2023-01-23 22:05:51.810821: step: 1678/1545, loss: 0.019980870187282562 2023-01-23 22:05:52.713098: step: 1680/1545, loss: 0.18098211288452148 2023-01-23 22:05:53.603981: step: 1682/1545, loss: 0.07550998032093048 2023-01-23 22:05:54.483024: step: 1684/1545, loss: 0.09465187042951584 2023-01-23 22:05:55.391515: step: 1686/1545, loss: 0.001427522161975503 2023-01-23 22:05:56.312285: step: 1688/1545, loss: 0.0810212716460228 2023-01-23 22:05:57.196344: step: 1690/1545, loss: 0.03518206998705864 2023-01-23 22:05:58.070102: step: 1692/1545, loss: 0.015327970497310162 2023-01-23 22:05:59.071510: step: 1694/1545, loss: 0.21356762945652008 2023-01-23 22:05:59.936412: step: 1696/1545, loss: 0.02494857646524906 2023-01-23 22:06:00.806109: step: 1698/1545, loss: 0.0005668698577210307 2023-01-23 22:06:01.650770: step: 1700/1545, loss: 0.0011060358956456184 2023-01-23 22:06:02.506843: step: 1702/1545, loss: 0.0006229713326320052 2023-01-23 22:06:03.385652: step: 1704/1545, loss: 0.00721015315502882 2023-01-23 22:06:04.250795: step: 1706/1545, loss: 0.18635140359401703 2023-01-23 22:06:05.203563: step: 1708/1545, loss: 0.24011477828025818 2023-01-23 22:06:06.082585: step: 1710/1545, loss: 0.00013097918417770416 2023-01-23 22:06:06.964997: step: 1712/1545, loss: 0.00029800893389619887 2023-01-23 22:06:07.839409: step: 1714/1545, loss: 0.008771002292633057 2023-01-23 22:06:08.742067: step: 1716/1545, loss: 0.3499879539012909 2023-01-23 22:06:09.645150: step: 1718/1545, loss: 0.0005535224336199462 2023-01-23 22:06:10.533554: step: 1720/1545, loss: 1.196329951286316 2023-01-23 22:06:11.420499: step: 1722/1545, loss: 0.04968300461769104 2023-01-23 22:06:12.308370: step: 1724/1545, loss: 0.028972871601581573 2023-01-23 22:06:13.154490: step: 1726/1545, loss: 0.0016916213789954782 2023-01-23 22:06:14.008489: step: 1728/1545, loss: 0.00011187980999238789 2023-01-23 22:06:14.836645: step: 1730/1545, loss: 1.1867285138578154e-05 2023-01-23 22:06:15.806784: step: 1732/1545, loss: 5.562352453125641e-05 2023-01-23 22:06:16.736090: step: 1734/1545, loss: 0.0010658408282324672 2023-01-23 22:06:17.612468: step: 1736/1545, loss: 0.00017268113151658326 2023-01-23 22:06:18.560687: step: 1738/1545, loss: 0.17677956819534302 2023-01-23 22:06:19.554571: step: 1740/1545, loss: 1.0545790195465088 2023-01-23 22:06:20.423769: step: 1742/1545, loss: 0.42928725481033325 2023-01-23 22:06:21.291491: step: 1744/1545, loss: 0.03032623790204525 2023-01-23 22:06:22.196568: step: 1746/1545, loss: 0.0001825936051318422 2023-01-23 22:06:23.098405: step: 1748/1545, loss: 0.004368651192635298 2023-01-23 22:06:24.033733: step: 1750/1545, loss: 0.025207428261637688 2023-01-23 22:06:24.918652: step: 1752/1545, loss: 5.3691863286076114e-05 2023-01-23 22:06:25.798525: step: 1754/1545, loss: 0.00992134865373373 2023-01-23 22:06:26.694362: step: 1756/1545, loss: 0.00198908569291234 2023-01-23 22:06:27.529273: step: 1758/1545, loss: 0.00040637055644765496 2023-01-23 22:06:28.426354: step: 1760/1545, loss: 0.011679468676447868 2023-01-23 22:06:29.278544: step: 1762/1545, loss: 0.00014318781904876232 2023-01-23 22:06:30.147284: step: 1764/1545, loss: 0.12439793348312378 2023-01-23 22:06:31.047838: step: 1766/1545, loss: 0.14249162375926971 2023-01-23 22:06:31.966762: step: 1768/1545, loss: 0.059615395963191986 2023-01-23 22:06:32.858056: step: 1770/1545, loss: 0.026927605271339417 2023-01-23 22:06:33.770791: step: 1772/1545, loss: 0.00014042462862562388 2023-01-23 22:06:34.661983: step: 1774/1545, loss: 0.012896204367280006 2023-01-23 22:06:35.558097: step: 1776/1545, loss: 1.3267290341900662e-05 2023-01-23 22:06:36.509970: step: 1778/1545, loss: 0.11481556296348572 2023-01-23 22:06:37.394441: step: 1780/1545, loss: 0.00020539408433251083 2023-01-23 22:06:38.313236: step: 1782/1545, loss: 0.0001860253541963175 2023-01-23 22:06:39.228251: step: 1784/1545, loss: 0.0014159505954012275 2023-01-23 22:06:40.101554: step: 1786/1545, loss: 0.0028627959545701742 2023-01-23 22:06:40.959007: step: 1788/1545, loss: 0.0003778254031203687 2023-01-23 22:06:41.845191: step: 1790/1545, loss: 4.238983092363924e-05 2023-01-23 22:06:42.748175: step: 1792/1545, loss: 0.011976337060332298 2023-01-23 22:06:43.605109: step: 1794/1545, loss: 0.00010763800673885271 2023-01-23 22:06:44.518791: step: 1796/1545, loss: 0.5364528894424438 2023-01-23 22:06:45.473009: step: 1798/1545, loss: 0.0007812721887603402 2023-01-23 22:06:46.361173: step: 1800/1545, loss: 0.002624495653435588 2023-01-23 22:06:47.227771: step: 1802/1545, loss: 2.8229254894540645e-05 2023-01-23 22:06:48.115429: step: 1804/1545, loss: 0.03789028525352478 2023-01-23 22:06:49.069302: step: 1806/1545, loss: 0.0018017611000686884 2023-01-23 22:06:49.975960: step: 1808/1545, loss: 0.00046431628288701177 2023-01-23 22:06:50.854802: step: 1810/1545, loss: 0.014424806460738182 2023-01-23 22:06:51.750082: step: 1812/1545, loss: -9.948767910827883e-06 2023-01-23 22:06:52.626785: step: 1814/1545, loss: 4.358540172688663e-05 2023-01-23 22:06:53.564687: step: 1816/1545, loss: 0.002583584049716592 2023-01-23 22:06:54.439221: step: 1818/1545, loss: 0.0012279371730983257 2023-01-23 22:06:55.308564: step: 1820/1545, loss: 0.0012342092813923955 2023-01-23 22:06:56.151186: step: 1822/1545, loss: 5.8390622143633664e-05 2023-01-23 22:06:57.013242: step: 1824/1545, loss: 0.006007565651088953 2023-01-23 22:06:57.863816: step: 1826/1545, loss: 0.00045894322101958096 2023-01-23 22:06:58.730687: step: 1828/1545, loss: 0.0037004253827035427 2023-01-23 22:06:59.656555: step: 1830/1545, loss: 2.6831006834981963e-05 2023-01-23 22:07:00.547826: step: 1832/1545, loss: 0.00042182349716313183 2023-01-23 22:07:01.444278: step: 1834/1545, loss: 2.651214526849799e-05 2023-01-23 22:07:02.296884: step: 1836/1545, loss: 0.001801559585146606 2023-01-23 22:07:03.151320: step: 1838/1545, loss: 0.00022227152658160776 2023-01-23 22:07:04.072962: step: 1840/1545, loss: -7.486207323381677e-05 2023-01-23 22:07:04.983630: step: 1842/1545, loss: 1.7732370451994939e-06 2023-01-23 22:07:05.880782: step: 1844/1545, loss: 7.40199102438055e-05 2023-01-23 22:07:06.759579: step: 1846/1545, loss: 0.022370724007487297 2023-01-23 22:07:07.631001: step: 1848/1545, loss: 0.42574799060821533 2023-01-23 22:07:08.467836: step: 1850/1545, loss: 2.612339631014038e-05 2023-01-23 22:07:09.346756: step: 1852/1545, loss: 4.0749426261754707e-05 2023-01-23 22:07:10.213666: step: 1854/1545, loss: 0.003327133134007454 2023-01-23 22:07:11.099491: step: 1856/1545, loss: 0.007776767015457153 2023-01-23 22:07:12.017937: step: 1858/1545, loss: 0.0905533879995346 2023-01-23 22:07:12.862182: step: 1860/1545, loss: 0.0001697771658655256 2023-01-23 22:07:13.699893: step: 1862/1545, loss: 0.06807246804237366 2023-01-23 22:07:14.655898: step: 1864/1545, loss: 0.060625508427619934 2023-01-23 22:07:15.544935: step: 1866/1545, loss: 1.8271768567501567e-05 2023-01-23 22:07:16.437672: step: 1868/1545, loss: 0.0003002525772899389 2023-01-23 22:07:17.383736: step: 1870/1545, loss: 0.021833037957549095 2023-01-23 22:07:18.259515: step: 1872/1545, loss: 0.002294282428920269 2023-01-23 22:07:19.100202: step: 1874/1545, loss: 9.537985897623003e-05 2023-01-23 22:07:20.010389: step: 1876/1545, loss: 0.000283190980553627 2023-01-23 22:07:20.862558: step: 1878/1545, loss: 2.055542790913023e-05 2023-01-23 22:07:21.794993: step: 1880/1545, loss: 0.0004908282426185906 2023-01-23 22:07:22.689258: step: 1882/1545, loss: 0.0033499349374324083 2023-01-23 22:07:23.594102: step: 1884/1545, loss: 0.3163483142852783 2023-01-23 22:07:24.459422: step: 1886/1545, loss: 0.0045316750183701515 2023-01-23 22:07:25.314291: step: 1888/1545, loss: 8.433536277152598e-05 2023-01-23 22:07:26.235996: step: 1890/1545, loss: 0.006198599934577942 2023-01-23 22:07:27.199861: step: 1892/1545, loss: 0.002145106205716729 2023-01-23 22:07:28.089477: step: 1894/1545, loss: 0.09491654485464096 2023-01-23 22:07:28.969250: step: 1896/1545, loss: 0.04677557945251465 2023-01-23 22:07:29.837720: step: 1898/1545, loss: 7.49474493204616e-05 2023-01-23 22:07:30.766145: step: 1900/1545, loss: 0.020135633647441864 2023-01-23 22:07:31.634548: step: 1902/1545, loss: 0.002338546561077237 2023-01-23 22:07:32.600001: step: 1904/1545, loss: 0.03167680278420448 2023-01-23 22:07:33.496884: step: 1906/1545, loss: 0.001139029860496521 2023-01-23 22:07:34.369384: step: 1908/1545, loss: 0.00014507488231174648 2023-01-23 22:07:35.269301: step: 1910/1545, loss: 0.0006971278344281018 2023-01-23 22:07:36.125948: step: 1912/1545, loss: 0.06606277078390121 2023-01-23 22:07:37.069070: step: 1914/1545, loss: 0.00034275054349564016 2023-01-23 22:07:37.936623: step: 1916/1545, loss: 0.0037423132453113794 2023-01-23 22:07:38.849922: step: 1918/1545, loss: 0.053363997489213943 2023-01-23 22:07:39.813685: step: 1920/1545, loss: 0.17881649732589722 2023-01-23 22:07:40.790489: step: 1922/1545, loss: 0.02433779463171959 2023-01-23 22:07:41.653491: step: 1924/1545, loss: 1.3164007214072626e-05 2023-01-23 22:07:42.565037: step: 1926/1545, loss: -2.6880896257353015e-05 2023-01-23 22:07:43.493007: step: 1928/1545, loss: -1.4549432307831012e-05 2023-01-23 22:07:44.335312: step: 1930/1545, loss: 5.335284731700085e-05 2023-01-23 22:07:45.206777: step: 1932/1545, loss: 0.06182684376835823 2023-01-23 22:07:46.102012: step: 1934/1545, loss: 0.08414585888385773 2023-01-23 22:07:46.950587: step: 1936/1545, loss: 0.02533632703125477 2023-01-23 22:07:47.853134: step: 1938/1545, loss: 0.00728843966498971 2023-01-23 22:07:48.725777: step: 1940/1545, loss: 1.0324490176571999e-05 2023-01-23 22:07:49.710674: step: 1942/1545, loss: 0.004866193514317274 2023-01-23 22:07:50.610682: step: 1944/1545, loss: 0.00024007857427932322 2023-01-23 22:07:51.483395: step: 1946/1545, loss: 1.2511011846072506e-05 2023-01-23 22:07:52.331970: step: 1948/1545, loss: 3.5045333788730204e-05 2023-01-23 22:07:53.178210: step: 1950/1545, loss: -4.921852450934239e-06 2023-01-23 22:07:54.104602: step: 1952/1545, loss: -7.392263796646148e-06 2023-01-23 22:07:55.020133: step: 1954/1545, loss: 0.26270413398742676 2023-01-23 22:07:55.952490: step: 1956/1545, loss: 0.17608436942100525 2023-01-23 22:07:56.812315: step: 1958/1545, loss: 0.0010752654634416103 2023-01-23 22:07:57.703437: step: 1960/1545, loss: 0.00035605006269179285 2023-01-23 22:07:58.593312: step: 1962/1545, loss: 3.1276795198209584e-05 2023-01-23 22:07:59.453299: step: 1964/1545, loss: 0.0017975954106077552 2023-01-23 22:08:00.330998: step: 1966/1545, loss: 0.000642577710095793 2023-01-23 22:08:01.227890: step: 1968/1545, loss: 0.30167996883392334 2023-01-23 22:08:02.162592: step: 1970/1545, loss: 0.0001606784062460065 2023-01-23 22:08:03.080006: step: 1972/1545, loss: 0.00016467510431539267 2023-01-23 22:08:03.963186: step: 1974/1545, loss: 0.002822957932949066 2023-01-23 22:08:04.886481: step: 1976/1545, loss: 0.6316940784454346 2023-01-23 22:08:05.782621: step: 1978/1545, loss: 0.000421686505433172 2023-01-23 22:08:06.613076: step: 1980/1545, loss: 0.0005034725181758404 2023-01-23 22:08:07.497309: step: 1982/1545, loss: 0.16315969824790955 2023-01-23 22:08:08.477810: step: 1984/1545, loss: 8.235717541538179e-05 2023-01-23 22:08:09.346047: step: 1986/1545, loss: -6.27341796644032e-06 2023-01-23 22:08:10.231227: step: 1988/1545, loss: 6.281633250182495e-05 2023-01-23 22:08:11.151201: step: 1990/1545, loss: 0.00840425118803978 2023-01-23 22:08:12.132962: step: 1992/1545, loss: 5.401157613960095e-05 2023-01-23 22:08:12.979919: step: 1994/1545, loss: 0.0001455913734389469 2023-01-23 22:08:13.954700: step: 1996/1545, loss: 0.0181549321860075 2023-01-23 22:08:14.788621: step: 1998/1545, loss: 0.0015392819186672568 2023-01-23 22:08:15.665634: step: 2000/1545, loss: 6.417216354748234e-05 2023-01-23 22:08:16.557857: step: 2002/1545, loss: 2.978738302772399e-05 2023-01-23 22:08:17.511916: step: 2004/1545, loss: 0.00035225332248955965 2023-01-23 22:08:18.408284: step: 2006/1545, loss: 0.0005658338195644319 2023-01-23 22:08:19.281635: step: 2008/1545, loss: 0.06205964833498001 2023-01-23 22:08:20.170502: step: 2010/1545, loss: 0.04948742315173149 2023-01-23 22:08:21.036224: step: 2012/1545, loss: 0.002384113846346736 2023-01-23 22:08:21.891855: step: 2014/1545, loss: 0.012051484547555447 2023-01-23 22:08:22.732846: step: 2016/1545, loss: 0.34646016359329224 2023-01-23 22:08:23.595082: step: 2018/1545, loss: 0.00021177604503463954 2023-01-23 22:08:24.483060: step: 2020/1545, loss: 0.396063894033432 2023-01-23 22:08:25.360610: step: 2022/1545, loss: 0.00033747177803888917 2023-01-23 22:08:26.265122: step: 2024/1545, loss: 0.5208570957183838 2023-01-23 22:08:27.151427: step: 2026/1545, loss: 2.2641321265837178e-05 2023-01-23 22:08:28.054885: step: 2028/1545, loss: 0.000833765312563628 2023-01-23 22:08:28.971799: step: 2030/1545, loss: 0.001813597627915442 2023-01-23 22:08:29.851990: step: 2032/1545, loss: 0.07935497909784317 2023-01-23 22:08:30.711350: step: 2034/1545, loss: 0.0002891365729738027 2023-01-23 22:08:31.607053: step: 2036/1545, loss: 0.0003999423061031848 2023-01-23 22:08:32.466341: step: 2038/1545, loss: 0.012234257534146309 2023-01-23 22:08:33.362450: step: 2040/1545, loss: 8.023138798307627e-05 2023-01-23 22:08:34.239110: step: 2042/1545, loss: 0.011491179466247559 2023-01-23 22:08:35.132089: step: 2044/1545, loss: 0.0021953661926090717 2023-01-23 22:08:36.020100: step: 2046/1545, loss: 0.0015697488561272621 2023-01-23 22:08:36.868901: step: 2048/1545, loss: 0.00041809878894127905 2023-01-23 22:08:37.732336: step: 2050/1545, loss: 0.34433481097221375 2023-01-23 22:08:38.600743: step: 2052/1545, loss: 6.540659342135768e-06 2023-01-23 22:08:39.501127: step: 2054/1545, loss: 0.002008975949138403 2023-01-23 22:08:40.384295: step: 2056/1545, loss: 0.22756041586399078 2023-01-23 22:08:41.217279: step: 2058/1545, loss: 0.5551555752754211 2023-01-23 22:08:42.123971: step: 2060/1545, loss: 2.633075200719759e-05 2023-01-23 22:08:43.016499: step: 2062/1545, loss: 0.002813682658597827 2023-01-23 22:08:43.908788: step: 2064/1545, loss: 0.00012379292456898838 2023-01-23 22:08:44.782589: step: 2066/1545, loss: 0.0025143781676888466 2023-01-23 22:08:45.597159: step: 2068/1545, loss: 0.0005955555243417621 2023-01-23 22:08:46.500701: step: 2070/1545, loss: 0.003946617245674133 2023-01-23 22:08:47.391938: step: 2072/1545, loss: 0.09081262350082397 2023-01-23 22:08:48.333961: step: 2074/1545, loss: 0.047951459884643555 2023-01-23 22:08:49.241632: step: 2076/1545, loss: 7.843828643672168e-05 2023-01-23 22:08:50.122159: step: 2078/1545, loss: 0.00045176371349953115 2023-01-23 22:08:51.011130: step: 2080/1545, loss: 0.0008515086374245584 2023-01-23 22:08:51.867730: step: 2082/1545, loss: 0.00018157204613089561 2023-01-23 22:08:52.792072: step: 2084/1545, loss: 0.0006414975505322218 2023-01-23 22:08:53.699878: step: 2086/1545, loss: 0.0023455535992980003 2023-01-23 22:08:54.562682: step: 2088/1545, loss: 0.00017001244123093784 2023-01-23 22:08:55.468469: step: 2090/1545, loss: 0.0606115348637104 2023-01-23 22:08:56.356600: step: 2092/1545, loss: 0.010402772575616837 2023-01-23 22:08:57.257129: step: 2094/1545, loss: 0.32383763790130615 2023-01-23 22:08:58.132160: step: 2096/1545, loss: 0.0005600829608738422 2023-01-23 22:08:59.052279: step: 2098/1545, loss: 0.0032696493435651064 2023-01-23 22:08:59.908281: step: 2100/1545, loss: 0.4263854920864105 2023-01-23 22:09:00.775036: step: 2102/1545, loss: 0.0018247222760692239 2023-01-23 22:09:01.632443: step: 2104/1545, loss: 1.2267158031463623 2023-01-23 22:09:02.502946: step: 2106/1545, loss: 0.000193979314644821 2023-01-23 22:09:03.368744: step: 2108/1545, loss: 0.001221591723151505 2023-01-23 22:09:04.228419: step: 2110/1545, loss: 0.03333572670817375 2023-01-23 22:09:05.113121: step: 2112/1545, loss: 0.00014280667528510094 2023-01-23 22:09:05.966274: step: 2114/1545, loss: 0.003211667761206627 2023-01-23 22:09:06.854854: step: 2116/1545, loss: 0.0004908437258563936 2023-01-23 22:09:07.765084: step: 2118/1545, loss: 0.2899256944656372 2023-01-23 22:09:08.637699: step: 2120/1545, loss: 0.0033295750617980957 2023-01-23 22:09:09.506742: step: 2122/1545, loss: 0.0023941202089190483 2023-01-23 22:09:10.390124: step: 2124/1545, loss: 0.010045851580798626 2023-01-23 22:09:11.370351: step: 2126/1545, loss: 0.005392234772443771 2023-01-23 22:09:12.309751: step: 2128/1545, loss: 0.15296296775341034 2023-01-23 22:09:13.171748: step: 2130/1545, loss: 0.0011758891632780433 2023-01-23 22:09:14.048336: step: 2132/1545, loss: 0.03608974069356918 2023-01-23 22:09:15.037813: step: 2134/1545, loss: 0.034183990210294724 2023-01-23 22:09:15.909543: step: 2136/1545, loss: 0.35865119099617004 2023-01-23 22:09:16.814574: step: 2138/1545, loss: 0.0639806017279625 2023-01-23 22:09:17.693290: step: 2140/1545, loss: 0.0004351011593826115 2023-01-23 22:09:18.575395: step: 2142/1545, loss: 0.0026065434794873 2023-01-23 22:09:19.473382: step: 2144/1545, loss: 0.03885914757847786 2023-01-23 22:09:20.330151: step: 2146/1545, loss: 0.009515705518424511 2023-01-23 22:09:21.176454: step: 2148/1545, loss: 0.10297530144453049 2023-01-23 22:09:22.030644: step: 2150/1545, loss: 0.0017116469098255038 2023-01-23 22:09:22.930311: step: 2152/1545, loss: 0.010011173784732819 2023-01-23 22:09:23.859075: step: 2154/1545, loss: 0.004557822830975056 2023-01-23 22:09:24.790707: step: 2156/1545, loss: 0.013849602080881596 2023-01-23 22:09:25.723240: step: 2158/1545, loss: 0.0016174594638869166 2023-01-23 22:09:26.641534: step: 2160/1545, loss: 0.00993486400693655 2023-01-23 22:09:27.510473: step: 2162/1545, loss: 0.0034057521261274815 2023-01-23 22:09:28.416078: step: 2164/1545, loss: 0.0013248231261968613 2023-01-23 22:09:29.305451: step: 2166/1545, loss: 0.07213502377271652 2023-01-23 22:09:30.146116: step: 2168/1545, loss: 0.07517798244953156 2023-01-23 22:09:31.025920: step: 2170/1545, loss: 0.014583908021450043 2023-01-23 22:09:31.905643: step: 2172/1545, loss: 0.011915216222405434 2023-01-23 22:09:32.802556: step: 2174/1545, loss: 0.1808939129114151 2023-01-23 22:09:33.726377: step: 2176/1545, loss: 0.04228820651769638 2023-01-23 22:09:34.646203: step: 2178/1545, loss: 0.0017310897819697857 2023-01-23 22:09:35.517681: step: 2180/1545, loss: 0.005082786548882723 2023-01-23 22:09:36.371001: step: 2182/1545, loss: 0.015520427376031876 2023-01-23 22:09:37.290897: step: 2184/1545, loss: 0.02037050575017929 2023-01-23 22:09:38.268143: step: 2186/1545, loss: 0.000421580538386479 2023-01-23 22:09:39.164197: step: 2188/1545, loss: 0.18376852571964264 2023-01-23 22:09:40.036657: step: 2190/1545, loss: 0.2108926773071289 2023-01-23 22:09:40.966779: step: 2192/1545, loss: 0.10182332247495651 2023-01-23 22:09:41.786667: step: 2194/1545, loss: 0.0001768048241501674 2023-01-23 22:09:42.658824: step: 2196/1545, loss: 0.003157661994919181 2023-01-23 22:09:43.562211: step: 2198/1545, loss: 0.12939657270908356 2023-01-23 22:09:44.489649: step: 2200/1545, loss: 0.0003024648758582771 2023-01-23 22:09:45.375957: step: 2202/1545, loss: 3.0755381885683164e-05 2023-01-23 22:09:46.245056: step: 2204/1545, loss: 0.07974261045455933 2023-01-23 22:09:47.108068: step: 2206/1545, loss: 0.0011059923563152552 2023-01-23 22:09:47.985161: step: 2208/1545, loss: 0.006820503622293472 2023-01-23 22:09:48.845891: step: 2210/1545, loss: 4.162878394708969e-05 2023-01-23 22:09:49.740507: step: 2212/1545, loss: 0.0007955498294904828 2023-01-23 22:09:50.580953: step: 2214/1545, loss: 0.0005853950278833508 2023-01-23 22:09:51.519569: step: 2216/1545, loss: 0.0004665581218432635 2023-01-23 22:09:52.424159: step: 2218/1545, loss: 0.13346827030181885 2023-01-23 22:09:53.284556: step: 2220/1545, loss: 0.00017532873607706279 2023-01-23 22:09:54.142279: step: 2222/1545, loss: 0.00029936758801341057 2023-01-23 22:09:55.037055: step: 2224/1545, loss: 0.0010861853370442986 2023-01-23 22:09:55.992479: step: 2226/1545, loss: 0.00036715000169351697 2023-01-23 22:09:56.850357: step: 2228/1545, loss: 0.00013926447718404233 2023-01-23 22:09:57.768109: step: 2230/1545, loss: 0.00045319172204472125 2023-01-23 22:09:58.652283: step: 2232/1545, loss: 0.00018228677799925208 2023-01-23 22:09:59.539578: step: 2234/1545, loss: 4.727755003841594e-05 2023-01-23 22:10:00.444486: step: 2236/1545, loss: 0.07902552932500839 2023-01-23 22:10:01.330738: step: 2238/1545, loss: 0.0013708480400964618 2023-01-23 22:10:02.218332: step: 2240/1545, loss: 0.003810394322499633 2023-01-23 22:10:03.108427: step: 2242/1545, loss: 0.00025359008577652276 2023-01-23 22:10:03.994718: step: 2244/1545, loss: 0.004978163633495569 2023-01-23 22:10:04.888060: step: 2246/1545, loss: 0.0408153235912323 2023-01-23 22:10:05.752539: step: 2248/1545, loss: 0.007863014005124569 2023-01-23 22:10:06.610908: step: 2250/1545, loss: 0.001997952116653323 2023-01-23 22:10:07.504251: step: 2252/1545, loss: 0.0001427423267159611 2023-01-23 22:10:08.410851: step: 2254/1545, loss: 0.0005500668194144964 2023-01-23 22:10:09.270815: step: 2256/1545, loss: 0.04205445200204849 2023-01-23 22:10:10.163890: step: 2258/1545, loss: 0.00022372286184690893 2023-01-23 22:10:11.006081: step: 2260/1545, loss: 0.23531588912010193 2023-01-23 22:10:11.906030: step: 2262/1545, loss: 0.01168777421116829 2023-01-23 22:10:12.841442: step: 2264/1545, loss: 0.0006446588668040931 2023-01-23 22:10:13.703183: step: 2266/1545, loss: 0.00023758226598147303 2023-01-23 22:10:14.553279: step: 2268/1545, loss: 0.0012808196479454637 2023-01-23 22:10:15.441674: step: 2270/1545, loss: 0.09208519756793976 2023-01-23 22:10:16.346361: step: 2272/1545, loss: 0.22130361199378967 2023-01-23 22:10:17.302740: step: 2274/1545, loss: 0.0027095030527561903 2023-01-23 22:10:18.177448: step: 2276/1545, loss: 0.0034518607426434755 2023-01-23 22:10:19.042853: step: 2278/1545, loss: -5.969417998130666e-06 2023-01-23 22:10:19.904542: step: 2280/1545, loss: 6.322984700091183e-05 2023-01-23 22:10:20.798485: step: 2282/1545, loss: 0.0035060241352766752 2023-01-23 22:10:21.633833: step: 2284/1545, loss: 0.0158616304397583 2023-01-23 22:10:22.468864: step: 2286/1545, loss: 0.00031167565612122416 2023-01-23 22:10:23.315181: step: 2288/1545, loss: 0.09386871755123138 2023-01-23 22:10:24.173675: step: 2290/1545, loss: 4.2650848627090454e-05 2023-01-23 22:10:25.033659: step: 2292/1545, loss: 0.0014410634757950902 2023-01-23 22:10:25.901721: step: 2294/1545, loss: 6.755481444997713e-05 2023-01-23 22:10:26.751739: step: 2296/1545, loss: 0.033479537814855576 2023-01-23 22:10:27.597938: step: 2298/1545, loss: 7.254441879922524e-05 2023-01-23 22:10:28.467850: step: 2300/1545, loss: 0.016053013503551483 2023-01-23 22:10:29.319963: step: 2302/1545, loss: 0.00010974157339660451 2023-01-23 22:10:30.201419: step: 2304/1545, loss: 0.0017647049389779568 2023-01-23 22:10:31.053017: step: 2306/1545, loss: 5.116728789289482e-05 2023-01-23 22:10:31.936396: step: 2308/1545, loss: 0.0038563546258956194 2023-01-23 22:10:32.921530: step: 2310/1545, loss: 0.01271907426416874 2023-01-23 22:10:33.851739: step: 2312/1545, loss: 0.0001993958285311237 2023-01-23 22:10:34.712842: step: 2314/1545, loss: 0.0008477565133944154 2023-01-23 22:10:35.601529: step: 2316/1545, loss: 0.03523619845509529 2023-01-23 22:10:36.487918: step: 2318/1545, loss: 1.4987928867340088 2023-01-23 22:10:37.444363: step: 2320/1545, loss: 0.0001797288714442402 2023-01-23 22:10:38.327467: step: 2322/1545, loss: 0.0006693329778499901 2023-01-23 22:10:39.192755: step: 2324/1545, loss: 0.00019079050980508327 2023-01-23 22:10:40.067594: step: 2326/1545, loss: 0.00020216609118506312 2023-01-23 22:10:40.930522: step: 2328/1545, loss: 0.001058122725225985 2023-01-23 22:10:41.801306: step: 2330/1545, loss: 0.0022321196738630533 2023-01-23 22:10:42.639299: step: 2332/1545, loss: 0.37911731004714966 2023-01-23 22:10:43.490931: step: 2334/1545, loss: 0.00044046228867955506 2023-01-23 22:10:44.333254: step: 2336/1545, loss: 0.00010396983270766214 2023-01-23 22:10:45.213111: step: 2338/1545, loss: 0.000948457105550915 2023-01-23 22:10:46.099690: step: 2340/1545, loss: -5.115921339893248e-06 2023-01-23 22:10:46.992876: step: 2342/1545, loss: 0.14686179161071777 2023-01-23 22:10:47.914536: step: 2344/1545, loss: 0.05247684568166733 2023-01-23 22:10:48.759614: step: 2346/1545, loss: 0.0006398708210326731 2023-01-23 22:10:49.656942: step: 2348/1545, loss: 0.00027583184419199824 2023-01-23 22:10:50.530589: step: 2350/1545, loss: 0.23438702523708344 2023-01-23 22:10:51.387298: step: 2352/1545, loss: 0.005663624964654446 2023-01-23 22:10:52.258935: step: 2354/1545, loss: 0.008152603171765804 2023-01-23 22:10:53.169818: step: 2356/1545, loss: 0.06258255243301392 2023-01-23 22:10:54.042745: step: 2358/1545, loss: 0.002597348066046834 2023-01-23 22:10:54.932699: step: 2360/1545, loss: 7.771849777782336e-05 2023-01-23 22:10:55.802114: step: 2362/1545, loss: 0.07553936541080475 2023-01-23 22:10:56.654680: step: 2364/1545, loss: 0.709923267364502 2023-01-23 22:10:57.610257: step: 2366/1545, loss: 0.0009615854360163212 2023-01-23 22:10:58.484485: step: 2368/1545, loss: 0.008073621429502964 2023-01-23 22:10:59.368687: step: 2370/1545, loss: 0.09501849859952927 2023-01-23 22:11:00.280606: step: 2372/1545, loss: 0.0015450668288394809 2023-01-23 22:11:01.184979: step: 2374/1545, loss: 0.0005826469277963042 2023-01-23 22:11:02.030451: step: 2376/1545, loss: 0.0019938298501074314 2023-01-23 22:11:02.908679: step: 2378/1545, loss: 0.0009582533384673297 2023-01-23 22:11:03.780297: step: 2380/1545, loss: 0.000865382025949657 2023-01-23 22:11:04.690719: step: 2382/1545, loss: 0.007848928682506084 2023-01-23 22:11:05.531885: step: 2384/1545, loss: 0.0005165889742784202 2023-01-23 22:11:06.425406: step: 2386/1545, loss: 2.909302565967664e-05 2023-01-23 22:11:07.329686: step: 2388/1545, loss: 0.0014531519263982773 2023-01-23 22:11:08.206743: step: 2390/1545, loss: 0.009031569585204124 2023-01-23 22:11:09.125799: step: 2392/1545, loss: 0.00010912468133028597 2023-01-23 22:11:10.022165: step: 2394/1545, loss: 0.9946312308311462 2023-01-23 22:11:10.904636: step: 2396/1545, loss: 0.000299578852718696 2023-01-23 22:11:11.773193: step: 2398/1545, loss: 0.00015655734750907868 2023-01-23 22:11:12.660507: step: 2400/1545, loss: 0.0004812072729691863 2023-01-23 22:11:13.524004: step: 2402/1545, loss: 0.001556888222694397 2023-01-23 22:11:14.389731: step: 2404/1545, loss: 0.000189877042430453 2023-01-23 22:11:15.247194: step: 2406/1545, loss: 0.005233499221503735 2023-01-23 22:11:16.145188: step: 2408/1545, loss: 0.18221549689769745 2023-01-23 22:11:16.989266: step: 2410/1545, loss: 0.0008442460675723851 2023-01-23 22:11:17.818472: step: 2412/1545, loss: 0.0020566757302731276 2023-01-23 22:11:18.678521: step: 2414/1545, loss: 0.00035302131436765194 2023-01-23 22:11:19.609389: step: 2416/1545, loss: 0.00028680695686489344 2023-01-23 22:11:20.479976: step: 2418/1545, loss: 0.10106255859136581 2023-01-23 22:11:21.419836: step: 2420/1545, loss: 0.0001772894902387634 2023-01-23 22:11:22.295149: step: 2422/1545, loss: 0.00038469635182991624 2023-01-23 22:11:23.167205: step: 2424/1545, loss: 0.0050130682066082954 2023-01-23 22:11:24.058927: step: 2426/1545, loss: 0.0010318625718355179 2023-01-23 22:11:25.003164: step: 2428/1545, loss: 0.002119693672284484 2023-01-23 22:11:25.922119: step: 2430/1545, loss: 0.3271186053752899 2023-01-23 22:11:26.824606: step: 2432/1545, loss: 0.004643112886697054 2023-01-23 22:11:27.674742: step: 2434/1545, loss: 0.1425596922636032 2023-01-23 22:11:28.514578: step: 2436/1545, loss: 0.5469379425048828 2023-01-23 22:11:29.444412: step: 2438/1545, loss: 0.023242946714162827 2023-01-23 22:11:30.307069: step: 2440/1545, loss: 0.009497134014964104 2023-01-23 22:11:31.189042: step: 2442/1545, loss: 0.00491866422817111 2023-01-23 22:11:32.072158: step: 2444/1545, loss: 0.02098180539906025 2023-01-23 22:11:32.998119: step: 2446/1545, loss: 0.0003718534135259688 2023-01-23 22:11:33.857345: step: 2448/1545, loss: 0.02467312105000019 2023-01-23 22:11:34.758200: step: 2450/1545, loss: 0.00041042640805244446 2023-01-23 22:11:35.668480: step: 2452/1545, loss: 0.12307503819465637 2023-01-23 22:11:36.527223: step: 2454/1545, loss: 0.06647520512342453 2023-01-23 22:11:37.449005: step: 2456/1545, loss: 0.0001667750475462526 2023-01-23 22:11:38.338509: step: 2458/1545, loss: 0.00018666124378796667 2023-01-23 22:11:39.203833: step: 2460/1545, loss: 0.0014073087368160486 2023-01-23 22:11:40.116325: step: 2462/1545, loss: 0.006464539095759392 2023-01-23 22:11:40.979441: step: 2464/1545, loss: 0.10135611891746521 2023-01-23 22:11:41.878764: step: 2466/1545, loss: 0.016757968813180923 2023-01-23 22:11:42.731950: step: 2468/1545, loss: 0.0007075280300341547 2023-01-23 22:11:43.636603: step: 2470/1545, loss: 0.017642579972743988 2023-01-23 22:11:44.513111: step: 2472/1545, loss: 0.06640789657831192 2023-01-23 22:11:45.394868: step: 2474/1545, loss: 0.09500329941511154 2023-01-23 22:11:46.310914: step: 2476/1545, loss: 0.057014577090740204 2023-01-23 22:11:47.197982: step: 2478/1545, loss: 0.002132965251803398 2023-01-23 22:11:48.070123: step: 2480/1545, loss: 0.0037912195548415184 2023-01-23 22:11:48.940112: step: 2482/1545, loss: 0.0008578160195611417 2023-01-23 22:11:49.792203: step: 2484/1545, loss: 0.0008431922760792077 2023-01-23 22:11:50.690964: step: 2486/1545, loss: 0.022546200081706047 2023-01-23 22:11:51.615093: step: 2488/1545, loss: 0.07138559967279434 2023-01-23 22:11:52.510175: step: 2490/1545, loss: 0.0016595023917034268 2023-01-23 22:11:53.400380: step: 2492/1545, loss: 0.005392869934439659 2023-01-23 22:11:54.252640: step: 2494/1545, loss: 0.017070621252059937 2023-01-23 22:11:55.122322: step: 2496/1545, loss: 0.017034118995070457 2023-01-23 22:11:56.104233: step: 2498/1545, loss: 0.05775903910398483 2023-01-23 22:11:56.987778: step: 2500/1545, loss: 0.12074238806962967 2023-01-23 22:11:57.834117: step: 2502/1545, loss: 0.00013570545706897974 2023-01-23 22:11:58.672015: step: 2504/1545, loss: 0.0008108071051537991 2023-01-23 22:11:59.551803: step: 2506/1545, loss: 0.0004849180404562503 2023-01-23 22:12:00.486706: step: 2508/1545, loss: 0.00044349225936457515 2023-01-23 22:12:01.376192: step: 2510/1545, loss: 0.7889499664306641 2023-01-23 22:12:02.223053: step: 2512/1545, loss: 7.552426541224122e-05 2023-01-23 22:12:03.127503: step: 2514/1545, loss: 0.0827094092965126 2023-01-23 22:12:04.021629: step: 2516/1545, loss: 0.010397445410490036 2023-01-23 22:12:04.895649: step: 2518/1545, loss: 0.21128524839878082 2023-01-23 22:12:05.804829: step: 2520/1545, loss: 0.0002567713090684265 2023-01-23 22:12:06.696602: step: 2522/1545, loss: 0.0006251363083720207 2023-01-23 22:12:07.538827: step: 2524/1545, loss: 0.00014982072752900422 2023-01-23 22:12:08.374899: step: 2526/1545, loss: 0.00010424620995763689 2023-01-23 22:12:09.201838: step: 2528/1545, loss: 1.188515579997329e-05 2023-01-23 22:12:10.069809: step: 2530/1545, loss: 0.0002448158338665962 2023-01-23 22:12:10.970106: step: 2532/1545, loss: 0.00035727056092582643 2023-01-23 22:12:11.851377: step: 2534/1545, loss: 0.06323365867137909 2023-01-23 22:12:12.777186: step: 2536/1545, loss: 0.6620944142341614 2023-01-23 22:12:13.674985: step: 2538/1545, loss: 0.014700758270919323 2023-01-23 22:12:14.568768: step: 2540/1545, loss: 0.019446389749646187 2023-01-23 22:12:15.406291: step: 2542/1545, loss: 9.481593224336393e-06 2023-01-23 22:12:16.293565: step: 2544/1545, loss: 0.00018274229660164565 2023-01-23 22:12:17.148038: step: 2546/1545, loss: 0.030155042186379433 2023-01-23 22:12:18.030692: step: 2548/1545, loss: 0.03891584649682045 2023-01-23 22:12:19.031431: step: 2550/1545, loss: 0.04670616239309311 2023-01-23 22:12:19.897494: step: 2552/1545, loss: 0.002936091274023056 2023-01-23 22:12:20.797775: step: 2554/1545, loss: 0.00030667055398225784 2023-01-23 22:12:21.682126: step: 2556/1545, loss: 0.071941077709198 2023-01-23 22:12:22.536698: step: 2558/1545, loss: 8.469776366837323e-05 2023-01-23 22:12:23.484530: step: 2560/1545, loss: 0.0003916991990990937 2023-01-23 22:12:24.386902: step: 2562/1545, loss: 0.0071132793091237545 2023-01-23 22:12:25.261138: step: 2564/1545, loss: 0.08905357867479324 2023-01-23 22:12:26.140784: step: 2566/1545, loss: 0.416500449180603 2023-01-23 22:12:27.024629: step: 2568/1545, loss: 0.007503528147935867 2023-01-23 22:12:27.910092: step: 2570/1545, loss: 0.08057377487421036 2023-01-23 22:12:28.788979: step: 2572/1545, loss: 0.045321930199861526 2023-01-23 22:12:29.778981: step: 2574/1545, loss: 0.000153396264067851 2023-01-23 22:12:30.667968: step: 2576/1545, loss: 0.012695185840129852 2023-01-23 22:12:31.565848: step: 2578/1545, loss: 0.013745066709816456 2023-01-23 22:12:32.421818: step: 2580/1545, loss: 0.17749184370040894 2023-01-23 22:12:33.283196: step: 2582/1545, loss: 0.0007322634919546545 2023-01-23 22:12:34.136623: step: 2584/1545, loss: 0.009796098805963993 2023-01-23 22:12:35.005874: step: 2586/1545, loss: 6.228969141375273e-05 2023-01-23 22:12:35.907656: step: 2588/1545, loss: 0.0009639983763918281 2023-01-23 22:12:36.776957: step: 2590/1545, loss: 0.008426511660218239 2023-01-23 22:12:37.655804: step: 2592/1545, loss: 2.7541505914996378e-05 2023-01-23 22:12:38.509530: step: 2594/1545, loss: 0.00010696984099922702 2023-01-23 22:12:39.380006: step: 2596/1545, loss: 0.00789407454431057 2023-01-23 22:12:40.251802: step: 2598/1545, loss: 0.0003471425734460354 2023-01-23 22:12:41.209911: step: 2600/1545, loss: 0.0033222329802811146 2023-01-23 22:12:42.067804: step: 2602/1545, loss: 0.017688926309347153 2023-01-23 22:12:42.946194: step: 2604/1545, loss: 0.0007203115383163095 2023-01-23 22:12:43.871612: step: 2606/1545, loss: 0.00013536667393054813 2023-01-23 22:12:44.750788: step: 2608/1545, loss: 0.000204152223886922 2023-01-23 22:12:45.628142: step: 2610/1545, loss: 0.0009382308926433325 2023-01-23 22:12:46.505131: step: 2612/1545, loss: 0.0006030783406458795 2023-01-23 22:12:47.368347: step: 2614/1545, loss: 0.0002494842919986695 2023-01-23 22:12:48.224844: step: 2616/1545, loss: 0.008225604891777039 2023-01-23 22:12:49.104501: step: 2618/1545, loss: 0.00021697631746064872 2023-01-23 22:12:49.956844: step: 2620/1545, loss: 6.56365737086162e-05 2023-01-23 22:12:50.866321: step: 2622/1545, loss: 0.00514210807159543 2023-01-23 22:12:51.749764: step: 2624/1545, loss: 0.003355805529281497 2023-01-23 22:12:52.588354: step: 2626/1545, loss: 0.23646748065948486 2023-01-23 22:12:53.463076: step: 2628/1545, loss: 4.774906483362429e-05 2023-01-23 22:12:54.319964: step: 2630/1545, loss: 0.06732917577028275 2023-01-23 22:12:55.233007: step: 2632/1545, loss: 3.3055948733817786e-05 2023-01-23 22:12:56.140927: step: 2634/1545, loss: 0.0013419360620900989 2023-01-23 22:12:57.011124: step: 2636/1545, loss: 1.9830073142657056e-05 2023-01-23 22:12:57.931800: step: 2638/1545, loss: 0.0055233994498848915 2023-01-23 22:12:58.843475: step: 2640/1545, loss: 0.011305713094770908 2023-01-23 22:12:59.730476: step: 2642/1545, loss: 0.028287680819630623 2023-01-23 22:13:00.631350: step: 2644/1545, loss: 0.3670562207698822 2023-01-23 22:13:01.632527: step: 2646/1545, loss: 0.4664144515991211 2023-01-23 22:13:02.518859: step: 2648/1545, loss: 0.00022153236204758286 2023-01-23 22:13:03.458005: step: 2650/1545, loss: 0.0001871919521363452 2023-01-23 22:13:04.329617: step: 2652/1545, loss: 0.003981493413448334 2023-01-23 22:13:05.217445: step: 2654/1545, loss: 0.19170424342155457 2023-01-23 22:13:06.111248: step: 2656/1545, loss: 0.003174216952174902 2023-01-23 22:13:06.952405: step: 2658/1545, loss: 0.0019702413119375706 2023-01-23 22:13:07.943099: step: 2660/1545, loss: 0.0011544282315298915 2023-01-23 22:13:08.796925: step: 2662/1545, loss: 0.00033780012745410204 2023-01-23 22:13:09.608442: step: 2664/1545, loss: 0.09817107766866684 2023-01-23 22:13:10.473040: step: 2666/1545, loss: 0.03375696390867233 2023-01-23 22:13:11.363289: step: 2668/1545, loss: 0.00038763292832300067 2023-01-23 22:13:12.244538: step: 2670/1545, loss: 0.20618021488189697 2023-01-23 22:13:13.123071: step: 2672/1545, loss: 0.45319420099258423 2023-01-23 22:13:13.982153: step: 2674/1545, loss: 0.02754468098282814 2023-01-23 22:13:14.832258: step: 2676/1545, loss: 0.002304645022377372 2023-01-23 22:13:15.717974: step: 2678/1545, loss: 0.0008207450155168772 2023-01-23 22:13:16.629085: step: 2680/1545, loss: 0.00011270463437540457 2023-01-23 22:13:17.504882: step: 2682/1545, loss: 0.0006332729826681316 2023-01-23 22:13:18.375369: step: 2684/1545, loss: 0.10343305766582489 2023-01-23 22:13:19.324091: step: 2686/1545, loss: 0.0002316613245056942 2023-01-23 22:13:20.197126: step: 2688/1545, loss: 0.00020914498600177467 2023-01-23 22:13:21.084409: step: 2690/1545, loss: 0.0008192903478629887 2023-01-23 22:13:22.034346: step: 2692/1545, loss: 0.002933881478384137 2023-01-23 22:13:22.905343: step: 2694/1545, loss: 0.00010121570085175335 2023-01-23 22:13:23.757824: step: 2696/1545, loss: 0.0002273705176776275 2023-01-23 22:13:24.626238: step: 2698/1545, loss: 0.0017119795083999634 2023-01-23 22:13:25.524395: step: 2700/1545, loss: 0.3116936981678009 2023-01-23 22:13:26.426198: step: 2702/1545, loss: 0.0016520617064088583 2023-01-23 22:13:27.346346: step: 2704/1545, loss: 0.00017208863573614508 2023-01-23 22:13:28.252622: step: 2706/1545, loss: 0.00024026085156947374 2023-01-23 22:13:29.097354: step: 2708/1545, loss: 0.6650351881980896 2023-01-23 22:13:29.972245: step: 2710/1545, loss: 0.0012728505535051227 2023-01-23 22:13:30.865821: step: 2712/1545, loss: 0.0011489043245092034 2023-01-23 22:13:31.747832: step: 2714/1545, loss: 0.0016786688938736916 2023-01-23 22:13:32.627483: step: 2716/1545, loss: 0.011976426467299461 2023-01-23 22:13:33.637381: step: 2718/1545, loss: 0.00034612492891028523 2023-01-23 22:13:34.489445: step: 2720/1545, loss: 7.404939242405817e-05 2023-01-23 22:13:35.340004: step: 2722/1545, loss: 0.0009816258680075407 2023-01-23 22:13:36.289411: step: 2724/1545, loss: 0.0039075035601854324 2023-01-23 22:13:37.191115: step: 2726/1545, loss: 0.0006532420520670712 2023-01-23 22:13:38.061772: step: 2728/1545, loss: 0.0004177858354523778 2023-01-23 22:13:38.979183: step: 2730/1545, loss: 0.00030812062323093414 2023-01-23 22:13:39.873766: step: 2732/1545, loss: 0.00020147819304838777 2023-01-23 22:13:40.759204: step: 2734/1545, loss: 0.020923567935824394 2023-01-23 22:13:41.619809: step: 2736/1545, loss: 6.495744310086593e-05 2023-01-23 22:13:42.598908: step: 2738/1545, loss: 0.2956067621707916 2023-01-23 22:13:43.465144: step: 2740/1545, loss: 0.0027834484353661537 2023-01-23 22:13:44.471485: step: 2742/1545, loss: 0.015521280467510223 2023-01-23 22:13:45.350569: step: 2744/1545, loss: 0.0009302576654590666 2023-01-23 22:13:46.254105: step: 2746/1545, loss: 0.0007075752364471555 2023-01-23 22:13:47.116171: step: 2748/1545, loss: 0.00022696555242873728 2023-01-23 22:13:48.029404: step: 2750/1545, loss: 0.00022659989190287888 2023-01-23 22:13:48.945409: step: 2752/1545, loss: 0.0007358872098848224 2023-01-23 22:13:49.822884: step: 2754/1545, loss: 0.1370142698287964 2023-01-23 22:13:50.702208: step: 2756/1545, loss: 0.003801075043156743 2023-01-23 22:13:51.589634: step: 2758/1545, loss: 9.799201507121325e-05 2023-01-23 22:13:52.439300: step: 2760/1545, loss: 0.0003741164109669626 2023-01-23 22:13:53.302317: step: 2762/1545, loss: 6.474849942605942e-05 2023-01-23 22:13:54.177763: step: 2764/1545, loss: 0.0008000010857358575 2023-01-23 22:13:55.059813: step: 2766/1545, loss: 0.0018218898912891746 2023-01-23 22:13:55.978945: step: 2768/1545, loss: 0.0036372486501932144 2023-01-23 22:13:56.832995: step: 2770/1545, loss: 0.00043774282676167786 2023-01-23 22:13:57.709407: step: 2772/1545, loss: 0.007455851417034864 2023-01-23 22:13:58.616080: step: 2774/1545, loss: 0.06967977434396744 2023-01-23 22:13:59.523117: step: 2776/1545, loss: 0.0058520399034023285 2023-01-23 22:14:00.434771: step: 2778/1545, loss: 0.0015609828988090158 2023-01-23 22:14:01.311866: step: 2780/1545, loss: 2.82362088910304e-05 2023-01-23 22:14:02.189768: step: 2782/1545, loss: 0.021143950521945953 2023-01-23 22:14:03.088579: step: 2784/1545, loss: 0.08047917485237122 2023-01-23 22:14:03.969836: step: 2786/1545, loss: 0.00947773177176714 2023-01-23 22:14:04.885582: step: 2788/1545, loss: 0.00028533570002764463 2023-01-23 22:14:05.762223: step: 2790/1545, loss: 7.813174306647852e-06 2023-01-23 22:14:06.636970: step: 2792/1545, loss: 0.00022158207139000297 2023-01-23 22:14:07.519831: step: 2794/1545, loss: 0.00045143411261960864 2023-01-23 22:14:08.363579: step: 2796/1545, loss: 0.05989393964409828 2023-01-23 22:14:09.294360: step: 2798/1545, loss: 0.0026373700238764286 2023-01-23 22:14:10.192769: step: 2800/1545, loss: 5.841230085934512e-05 2023-01-23 22:14:11.142965: step: 2802/1545, loss: 1.8531639575958252 2023-01-23 22:14:12.015723: step: 2804/1545, loss: 7.886965613579378e-05 2023-01-23 22:14:12.944911: step: 2806/1545, loss: 0.0008660673629492521 2023-01-23 22:14:13.840494: step: 2808/1545, loss: 0.0008296652231365442 2023-01-23 22:14:14.790486: step: 2810/1545, loss: 0.00011557622929103673 2023-01-23 22:14:15.671861: step: 2812/1545, loss: 2.0295357899158262e-05 2023-01-23 22:14:16.560410: step: 2814/1545, loss: 0.0002624809858389199 2023-01-23 22:14:17.496986: step: 2816/1545, loss: 0.23832353949546814 2023-01-23 22:14:18.412244: step: 2818/1545, loss: 0.062427371740341187 2023-01-23 22:14:19.331933: step: 2820/1545, loss: 0.004113279283046722 2023-01-23 22:14:20.212536: step: 2822/1545, loss: 0.00011356033792253584 2023-01-23 22:14:21.074984: step: 2824/1545, loss: 2.428988773317542e-05 2023-01-23 22:14:21.957434: step: 2826/1545, loss: 0.00030951027292758226 2023-01-23 22:14:22.874163: step: 2828/1545, loss: 2.2190810341271572e-05 2023-01-23 22:14:23.769755: step: 2830/1545, loss: 2.569482967373915e-05 2023-01-23 22:14:24.672608: step: 2832/1545, loss: 0.0001535311312181875 2023-01-23 22:14:25.551460: step: 2834/1545, loss: 0.000147631173604168 2023-01-23 22:14:26.454887: step: 2836/1545, loss: 0.00013737571134697646 2023-01-23 22:14:27.326499: step: 2838/1545, loss: 0.00011833047028630972 2023-01-23 22:14:28.176310: step: 2840/1545, loss: 0.00031393259996548295 2023-01-23 22:14:28.994444: step: 2842/1545, loss: 0.00041219612467102706 2023-01-23 22:14:29.882244: step: 2844/1545, loss: 0.0009211355936713517 2023-01-23 22:14:30.740581: step: 2846/1545, loss: 0.001387588563375175 2023-01-23 22:14:31.679993: step: 2848/1545, loss: 0.0009972817497327924 2023-01-23 22:14:32.552873: step: 2850/1545, loss: 0.09561799466609955 2023-01-23 22:14:33.452440: step: 2852/1545, loss: 0.2945564091205597 2023-01-23 22:14:34.353285: step: 2854/1545, loss: 0.0017314726719632745 2023-01-23 22:14:35.251051: step: 2856/1545, loss: 0.055960763245821 2023-01-23 22:14:36.160728: step: 2858/1545, loss: 0.40726327896118164 2023-01-23 22:14:37.042231: step: 2860/1545, loss: 5.7099590776488185e-05 2023-01-23 22:14:37.934496: step: 2862/1545, loss: 2.628908305268851e-06 2023-01-23 22:14:38.902748: step: 2864/1545, loss: 0.08057473599910736 2023-01-23 22:14:39.792363: step: 2866/1545, loss: 0.12411440908908844 2023-01-23 22:14:40.668755: step: 2868/1545, loss: 0.0001807640219340101 2023-01-23 22:14:41.604133: step: 2870/1545, loss: 0.0005465546855702996 2023-01-23 22:14:42.501822: step: 2872/1545, loss: 0.00015220716886688024 2023-01-23 22:14:43.416472: step: 2874/1545, loss: 0.0005878637894056737 2023-01-23 22:14:44.289751: step: 2876/1545, loss: 0.17669890820980072 2023-01-23 22:14:45.175181: step: 2878/1545, loss: 0.001119032735005021 2023-01-23 22:14:46.070707: step: 2880/1545, loss: 0.00014033089973963797 2023-01-23 22:14:46.964172: step: 2882/1545, loss: -5.335316018317826e-06 2023-01-23 22:14:47.831694: step: 2884/1545, loss: 4.156852810410783e-05 2023-01-23 22:14:48.722948: step: 2886/1545, loss: 0.0014180538710206747 2023-01-23 22:14:49.669304: step: 2888/1545, loss: 0.0008725113002583385 2023-01-23 22:14:50.559189: step: 2890/1545, loss: 0.0029374691657721996 2023-01-23 22:14:51.462656: step: 2892/1545, loss: 5.991595025989227e-05 2023-01-23 22:14:52.315391: step: 2894/1545, loss: 1.6922680515563115e-05 2023-01-23 22:14:53.197945: step: 2896/1545, loss: 8.708177483640611e-05 2023-01-23 22:14:54.119406: step: 2898/1545, loss: 2.456870788591914e-06 2023-01-23 22:14:55.006654: step: 2900/1545, loss: 0.0011053141206502914 2023-01-23 22:14:55.849765: step: 2902/1545, loss: 0.00046960837789811194 2023-01-23 22:14:56.745103: step: 2904/1545, loss: 0.0005380889633670449 2023-01-23 22:14:57.631745: step: 2906/1545, loss: 0.00494789844378829 2023-01-23 22:14:58.516446: step: 2908/1545, loss: 0.007065169047564268 2023-01-23 22:14:59.403360: step: 2910/1545, loss: 0.005539735779166222 2023-01-23 22:15:00.283823: step: 2912/1545, loss: 0.01434615720063448 2023-01-23 22:15:01.144487: step: 2914/1545, loss: 0.051721129566431046 2023-01-23 22:15:02.036848: step: 2916/1545, loss: 0.0002213902771472931 2023-01-23 22:15:02.886308: step: 2918/1545, loss: -3.159044581479975e-07 2023-01-23 22:15:03.763399: step: 2920/1545, loss: 0.07976620644330978 2023-01-23 22:15:04.639366: step: 2922/1545, loss: 1.3420358300209045e-05 2023-01-23 22:15:05.528848: step: 2924/1545, loss: 0.03284667432308197 2023-01-23 22:15:06.450154: step: 2926/1545, loss: 6.775582005502656e-05 2023-01-23 22:15:07.390415: step: 2928/1545, loss: 3.2343045859306585e-06 2023-01-23 22:15:08.295126: step: 2930/1545, loss: 1.001861810684204 2023-01-23 22:15:09.164681: step: 2932/1545, loss: 3.621276482590474e-05 2023-01-23 22:15:10.041619: step: 2934/1545, loss: 0.0002832063182722777 2023-01-23 22:15:10.919444: step: 2936/1545, loss: 1.9670973415486515e-05 2023-01-23 22:15:11.869880: step: 2938/1545, loss: 0.016066022217273712 2023-01-23 22:15:12.775076: step: 2940/1545, loss: 0.15420877933502197 2023-01-23 22:15:13.626717: step: 2942/1545, loss: 0.017349274829030037 2023-01-23 22:15:14.496572: step: 2944/1545, loss: 0.00809285044670105 2023-01-23 22:15:15.410605: step: 2946/1545, loss: 0.002738971496000886 2023-01-23 22:15:16.286124: step: 2948/1545, loss: 0.0016677073435857892 2023-01-23 22:15:17.208183: step: 2950/1545, loss: 0.0010482294019311666 2023-01-23 22:15:18.123325: step: 2952/1545, loss: 0.00044524454278871417 2023-01-23 22:15:19.031180: step: 2954/1545, loss: 0.000570073607377708 2023-01-23 22:15:19.965381: step: 2956/1545, loss: 7.008391548879445e-05 2023-01-23 22:15:20.829372: step: 2958/1545, loss: 0.0002304147055838257 2023-01-23 22:15:21.710424: step: 2960/1545, loss: 0.0027681966312229633 2023-01-23 22:15:22.596141: step: 2962/1545, loss: 0.0023730439133942127 2023-01-23 22:15:23.495101: step: 2964/1545, loss: 0.0027320408262312412 2023-01-23 22:15:24.385287: step: 2966/1545, loss: 0.08969694375991821 2023-01-23 22:15:25.276114: step: 2968/1545, loss: 0.1864251345396042 2023-01-23 22:15:26.131123: step: 2970/1545, loss: 4.9059912271331996e-05 2023-01-23 22:15:26.996700: step: 2972/1545, loss: 0.00025230098981410265 2023-01-23 22:15:27.860055: step: 2974/1545, loss: 0.000997216091491282 2023-01-23 22:15:28.729859: step: 2976/1545, loss: 4.050481948070228e-05 2023-01-23 22:15:29.599373: step: 2978/1545, loss: 0.0014050528407096863 2023-01-23 22:15:30.502895: step: 2980/1545, loss: 0.00024313079484272748 2023-01-23 22:15:31.350806: step: 2982/1545, loss: 8.031438483158126e-06 2023-01-23 22:15:32.260162: step: 2984/1545, loss: 6.270817539189011e-05 2023-01-23 22:15:33.154136: step: 2986/1545, loss: 0.1964116394519806 2023-01-23 22:15:34.052750: step: 2988/1545, loss: 0.018458891659975052 2023-01-23 22:15:34.961746: step: 2990/1545, loss: 0.003009843872860074 2023-01-23 22:15:35.813177: step: 2992/1545, loss: 0.0005803910898976028 2023-01-23 22:15:36.676629: step: 2994/1545, loss: 0.00023272080579772592 2023-01-23 22:15:37.609773: step: 2996/1545, loss: 0.10481929033994675 2023-01-23 22:15:38.503556: step: 2998/1545, loss: 0.00032049434958025813 2023-01-23 22:15:39.381161: step: 3000/1545, loss: 7.221089617814869e-05 2023-01-23 22:15:40.277249: step: 3002/1545, loss: 0.002066499087959528 2023-01-23 22:15:41.179311: step: 3004/1545, loss: 0.00043382737203501165 2023-01-23 22:15:42.024056: step: 3006/1545, loss: 1.1552120668056887e-05 2023-01-23 22:15:42.900401: step: 3008/1545, loss: 0.0661567971110344 2023-01-23 22:15:43.829928: step: 3010/1545, loss: 0.01862603798508644 2023-01-23 22:15:44.770706: step: 3012/1545, loss: 7.38124072086066e-05 2023-01-23 22:15:45.659549: step: 3014/1545, loss: 0.00341864675283432 2023-01-23 22:15:46.557638: step: 3016/1545, loss: 0.0009802839485928416 2023-01-23 22:15:47.466209: step: 3018/1545, loss: -2.9058719519525766e-06 2023-01-23 22:15:48.332141: step: 3020/1545, loss: 0.004190107341855764 2023-01-23 22:15:49.248646: step: 3022/1545, loss: 0.0013505907263606787 2023-01-23 22:15:50.141104: step: 3024/1545, loss: 0.022519780322909355 2023-01-23 22:15:51.047330: step: 3026/1545, loss: 0.13815130293369293 2023-01-23 22:15:51.926945: step: 3028/1545, loss: 0.10624538362026215 2023-01-23 22:15:52.806778: step: 3030/1545, loss: 5.953834988758899e-05 2023-01-23 22:15:53.665304: step: 3032/1545, loss: 0.04760394245386124 2023-01-23 22:15:54.533825: step: 3034/1545, loss: 0.0005052961641922593 2023-01-23 22:15:55.411578: step: 3036/1545, loss: 0.010095271281898022 2023-01-23 22:15:56.397019: step: 3038/1545, loss: 0.011927454732358456 2023-01-23 22:15:57.262719: step: 3040/1545, loss: -8.843824161886005e-08 2023-01-23 22:15:58.179643: step: 3042/1545, loss: 0.01648949645459652 2023-01-23 22:15:59.065074: step: 3044/1545, loss: 0.00043087213998660445 2023-01-23 22:15:59.922905: step: 3046/1545, loss: 0.05517356097698212 2023-01-23 22:16:00.834051: step: 3048/1545, loss: 0.001219215919263661 2023-01-23 22:16:01.678808: step: 3050/1545, loss: 0.0001817917509470135 2023-01-23 22:16:02.518820: step: 3052/1545, loss: 5.462466288008727e-05 2023-01-23 22:16:03.388211: step: 3054/1545, loss: -1.8140079191653058e-05 2023-01-23 22:16:04.236811: step: 3056/1545, loss: 0.0008563132723793387 2023-01-23 22:16:05.095451: step: 3058/1545, loss: 0.0065162163227796555 2023-01-23 22:16:06.032656: step: 3060/1545, loss: 0.03968292847275734 2023-01-23 22:16:06.919050: step: 3062/1545, loss: 0.0007226982852444053 2023-01-23 22:16:07.816077: step: 3064/1545, loss: 0.00017963050049729645 2023-01-23 22:16:08.704694: step: 3066/1545, loss: 0.00016854438581503928 2023-01-23 22:16:09.549108: step: 3068/1545, loss: 0.000315530807711184 2023-01-23 22:16:10.474174: step: 3070/1545, loss: 0.00015839192201383412 2023-01-23 22:16:11.366835: step: 3072/1545, loss: 1.9846749637508765e-05 2023-01-23 22:16:12.226279: step: 3074/1545, loss: -1.142335167969577e-05 2023-01-23 22:16:13.064987: step: 3076/1545, loss: 0.021832061931490898 2023-01-23 22:16:13.954756: step: 3078/1545, loss: 0.07109713554382324 2023-01-23 22:16:14.848894: step: 3080/1545, loss: 2.234182834625244 2023-01-23 22:16:15.710793: step: 3082/1545, loss: 0.05717666074633598 2023-01-23 22:16:16.593119: step: 3084/1545, loss: 0.1163191944360733 2023-01-23 22:16:17.457526: step: 3086/1545, loss: 0.003424359718337655 2023-01-23 22:16:18.363865: step: 3088/1545, loss: 0.18992167711257935 2023-01-23 22:16:19.265919: step: 3090/1545, loss: 0.0011297168675810099 ================================================== Loss: 0.057 -------------------- Dev Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6538672241198886, 'r': 0.6558219841322053, 'f1': 0.6548431453499183}, 'combined': 0.4326361787623561, 'epoch': 36} Test Chinese: {'event': {'p': 0.6414087513340448, 'r': 0.768542199488491, 'f1': 0.6992437463641652}, 'argument': {'p': 0.7148759095527157, 'r': 0.7102409398874235, 'f1': 0.7125508874631048}, 'combined': 0.49824675202481206, 'epoch': 36} Dev Korean: {'event': {'p': 0.6105032822757112, 'r': 0.7430093209054593, 'f1': 0.6702702702702702}, 'argument': {'p': 0.6524414022670175, 'r': 0.6548905066298817, 'f1': 0.653663660420384}, 'combined': 0.4381313183358249, 'epoch': 36} Test Korean: {'event': {'p': 0.6285714285714286, 'r': 0.7595907928388747, 'f1': 0.6878980891719745}, 'argument': {'p': 0.7084413106854012, 'r': 0.7087123287843626, 'f1': 0.7085767938199747}, 'combined': 0.4874286225003648, 'epoch': 36} Dev Russian: {'event': {'p': 0.5708661417322834, 'r': 0.7723035952063915, 'f1': 0.656479909451047}, 'argument': {'p': 0.6517103789889689, 'r': 0.6619661932505978, 'f1': 0.656798252778095}, 'combined': 0.43117485751136964, 'epoch': 36} Test Russian: {'event': {'p': 0.6253114100647733, 'r': 0.8024296675191815, 'f1': 0.7028843461215345}, 'argument': {'p': 0.7177601603131445, 'r': 0.7201777656435405, 'f1': 0.7189669306181732}, 'combined': 0.5053506009105613, 'epoch': 36} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6891643709825528, 'r': 0.6265130645295934, 'f1': 0.6563470199833835}, 'combined': 0.45745398362478257, 'epoch': 36} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6670524691358024, 'r': 0.49343607305936066, 'f1': 0.567257217847769}, 'combined': 0.3483158355205599, 'epoch': 36} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5519637400308907, 'r': 0.5716767307462796, 'f1': 0.5616473144173976}, 'combined': 0.3128162257514619, 'epoch': 36} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6758987924276707, 'r': 0.6414709887684336, 'f1': 0.6582350269068861}, 'combined': 0.43408784748056034, 'epoch': 33} Test for Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7201409239897084, 'r': 0.7110669833666995, 'f1': 0.7155751890249322}, 'combined': 0.49952892776609586, 'epoch': 33} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7175290642271774, 'r': 0.6285791802320727, 'f1': 0.6701152494104036}, 'combined': 0.4772032836710449, 'epoch': 33} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 37 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 22:21:33.951669: step: 2/1545, loss: 0.030910369008779526 2023-01-23 22:21:34.808350: step: 4/1545, loss: 0.13626205921173096 2023-01-23 22:21:35.743820: step: 6/1545, loss: 0.02494177222251892 2023-01-23 22:21:36.631855: step: 8/1545, loss: 0.0063595520332455635 2023-01-23 22:21:37.469196: step: 10/1545, loss: 0.01269958820194006 2023-01-23 22:21:38.368403: step: 12/1545, loss: 0.0003873265814036131 2023-01-23 22:21:39.255642: step: 14/1545, loss: -5.940200935583562e-06 2023-01-23 22:21:40.117895: step: 16/1545, loss: 0.020442495122551918 2023-01-23 22:21:41.004751: step: 18/1545, loss: 9.844341548159719e-05 2023-01-23 22:21:41.898775: step: 20/1545, loss: 0.005414335988461971 2023-01-23 22:21:42.791707: step: 22/1545, loss: 0.00481416704133153 2023-01-23 22:21:43.666281: step: 24/1545, loss: 0.0348656140267849 2023-01-23 22:21:44.541486: step: 26/1545, loss: 0.004485920071601868 2023-01-23 22:21:45.402066: step: 28/1545, loss: 0.00017001033120322973 2023-01-23 22:21:46.270619: step: 30/1545, loss: 0.014459304511547089 2023-01-23 22:21:47.159389: step: 32/1545, loss: 0.19739241898059845 2023-01-23 22:21:48.087080: step: 34/1545, loss: 0.37165582180023193 2023-01-23 22:21:48.953722: step: 36/1545, loss: 8.281072223326191e-05 2023-01-23 22:21:49.805779: step: 38/1545, loss: 0.000267153256572783 2023-01-23 22:21:50.669358: step: 40/1545, loss: 1.4906336218700744e-05 2023-01-23 22:21:51.545280: step: 42/1545, loss: 0.004399733152240515 2023-01-23 22:21:52.415783: step: 44/1545, loss: -1.3783245776721742e-05 2023-01-23 22:21:53.327615: step: 46/1545, loss: 0.012448909692466259 2023-01-23 22:21:54.234958: step: 48/1545, loss: 0.008634553290903568 2023-01-23 22:21:55.121338: step: 50/1545, loss: 0.08109769970178604 2023-01-23 22:21:56.044403: step: 52/1545, loss: 0.0001145454662037082 2023-01-23 22:21:56.991841: step: 54/1545, loss: 0.01236644946038723 2023-01-23 22:21:57.894615: step: 56/1545, loss: 0.000676196301355958 2023-01-23 22:21:58.831593: step: 58/1545, loss: 0.0006127245724201202 2023-01-23 22:21:59.715261: step: 60/1545, loss: 0.0004354446427896619 2023-01-23 22:22:00.616130: step: 62/1545, loss: 2.021748514380306e-05 2023-01-23 22:22:01.500403: step: 64/1545, loss: 0.0014093487989157438 2023-01-23 22:22:02.356066: step: 66/1545, loss: 0.0006619320483878255 2023-01-23 22:22:03.224479: step: 68/1545, loss: 0.003104791045188904 2023-01-23 22:22:04.114695: step: 70/1545, loss: 6.458460848079994e-05 2023-01-23 22:22:04.972698: step: 72/1545, loss: 0.0340815931558609 2023-01-23 22:22:05.841487: step: 74/1545, loss: 6.075225246604532e-05 2023-01-23 22:22:06.672317: step: 76/1545, loss: 4.0654809708939865e-05 2023-01-23 22:22:07.542528: step: 78/1545, loss: 2.5021741748787463e-05 2023-01-23 22:22:08.402610: step: 80/1545, loss: 0.15100646018981934 2023-01-23 22:22:09.256388: step: 82/1545, loss: 0.00019165067351423204 2023-01-23 22:22:10.133542: step: 84/1545, loss: 0.00012606015661731362 2023-01-23 22:22:11.011690: step: 86/1545, loss: 0.00043807923793792725 2023-01-23 22:22:11.944070: step: 88/1545, loss: 0.0011888205772265792 2023-01-23 22:22:12.827638: step: 90/1545, loss: 0.0863838717341423 2023-01-23 22:22:13.706197: step: 92/1545, loss: 0.00018252723384648561 2023-01-23 22:22:14.592223: step: 94/1545, loss: 2.196613311767578 2023-01-23 22:22:15.465960: step: 96/1545, loss: 4.0170722058974206e-05 2023-01-23 22:22:16.324621: step: 98/1545, loss: 0.00038050359580665827 2023-01-23 22:22:17.207439: step: 100/1545, loss: 0.004267230164259672 2023-01-23 22:22:18.156180: step: 102/1545, loss: 0.40883100032806396 2023-01-23 22:22:19.066498: step: 104/1545, loss: 0.00026188584160991013 2023-01-23 22:22:19.947007: step: 106/1545, loss: 0.00048284183139912784 2023-01-23 22:22:20.839395: step: 108/1545, loss: 0.23840072751045227 2023-01-23 22:22:21.719558: step: 110/1545, loss: 3.679690416902304e-05 2023-01-23 22:22:22.610842: step: 112/1545, loss: 0.004254559520632029 2023-01-23 22:22:23.476045: step: 114/1545, loss: 2.2133704987936653e-05 2023-01-23 22:22:24.413548: step: 116/1545, loss: 0.011801167391240597 2023-01-23 22:22:25.277627: step: 118/1545, loss: 0.1890689581632614 2023-01-23 22:22:26.171709: step: 120/1545, loss: 0.006132878828793764 2023-01-23 22:22:27.118339: step: 122/1545, loss: 0.0001770070957718417 2023-01-23 22:22:28.043280: step: 124/1545, loss: 0.10722500085830688 2023-01-23 22:22:28.957005: step: 126/1545, loss: 0.013063122518360615 2023-01-23 22:22:29.857039: step: 128/1545, loss: 0.0002607327769510448 2023-01-23 22:22:30.707814: step: 130/1545, loss: 3.503448533592746e-05 2023-01-23 22:22:31.562353: step: 132/1545, loss: 5.7824912801152095e-05 2023-01-23 22:22:32.428152: step: 134/1545, loss: 0.05292343348264694 2023-01-23 22:22:33.280883: step: 136/1545, loss: 0.00027963591855950654 2023-01-23 22:22:34.153854: step: 138/1545, loss: 0.0021962663158774376 2023-01-23 22:22:35.039381: step: 140/1545, loss: 0.0002192354149883613 2023-01-23 22:22:35.921230: step: 142/1545, loss: 0.025142600759863853 2023-01-23 22:22:36.834931: step: 144/1545, loss: 0.0007119086803868413 2023-01-23 22:22:37.745045: step: 146/1545, loss: 0.00017577710968907923 2023-01-23 22:22:38.646989: step: 148/1545, loss: 0.0035823772195726633 2023-01-23 22:22:39.529481: step: 150/1545, loss: 0.04116396978497505 2023-01-23 22:22:40.492147: step: 152/1545, loss: 0.02388809807598591 2023-01-23 22:22:41.371196: step: 154/1545, loss: 0.0023569241166114807 2023-01-23 22:22:42.246184: step: 156/1545, loss: 2.415209928585682e-05 2023-01-23 22:22:43.163563: step: 158/1545, loss: 0.03362935408949852 2023-01-23 22:22:44.045898: step: 160/1545, loss: 0.0002529170596972108 2023-01-23 22:22:44.966283: step: 162/1545, loss: 0.0001529412402305752 2023-01-23 22:22:45.839272: step: 164/1545, loss: 0.00042438876698724926 2023-01-23 22:22:46.708057: step: 166/1545, loss: 6.285037670750171e-05 2023-01-23 22:22:47.612118: step: 168/1545, loss: 0.00017013099568430334 2023-01-23 22:22:48.491821: step: 170/1545, loss: 0.0023225650656968355 2023-01-23 22:22:49.347544: step: 172/1545, loss: 0.0002005884307436645 2023-01-23 22:22:50.232217: step: 174/1545, loss: 0.0005096457898616791 2023-01-23 22:22:51.125001: step: 176/1545, loss: 0.0036611284594982862 2023-01-23 22:22:52.140250: step: 178/1545, loss: 0.08473876118659973 2023-01-23 22:22:53.061663: step: 180/1545, loss: 0.09211104363203049 2023-01-23 22:22:53.965839: step: 182/1545, loss: 0.009611510671675205 2023-01-23 22:22:54.919741: step: 184/1545, loss: 5.965776654193178e-05 2023-01-23 22:22:55.828816: step: 186/1545, loss: -1.8598353562992997e-05 2023-01-23 22:22:56.722983: step: 188/1545, loss: 3.673285391414538e-05 2023-01-23 22:22:57.567314: step: 190/1545, loss: 0.00026766795781441033 2023-01-23 22:22:58.457810: step: 192/1545, loss: 0.0003262540849391371 2023-01-23 22:22:59.281086: step: 194/1545, loss: 7.351297881541541e-06 2023-01-23 22:23:00.154988: step: 196/1545, loss: 0.14255233108997345 2023-01-23 22:23:01.035092: step: 198/1545, loss: 2.2774676835979335e-05 2023-01-23 22:23:01.888836: step: 200/1545, loss: 4.815471766050905e-05 2023-01-23 22:23:02.734028: step: 202/1545, loss: -2.4336579372175038e-05 2023-01-23 22:23:03.653545: step: 204/1545, loss: 0.2080094814300537 2023-01-23 22:23:04.523665: step: 206/1545, loss: -2.5063773136935197e-06 2023-01-23 22:23:05.362410: step: 208/1545, loss: 0.014562460593879223 2023-01-23 22:23:06.220229: step: 210/1545, loss: -6.854534603917273e-06 2023-01-23 22:23:07.081633: step: 212/1545, loss: 0.000135039517772384 2023-01-23 22:23:08.002079: step: 214/1545, loss: 0.00045334649621509016 2023-01-23 22:23:08.866167: step: 216/1545, loss: 0.2586069703102112 2023-01-23 22:23:09.758821: step: 218/1545, loss: 4.9419169954489917e-05 2023-01-23 22:23:10.646696: step: 220/1545, loss: 3.851454493997153e-06 2023-01-23 22:23:11.528303: step: 222/1545, loss: 4.330501178628765e-05 2023-01-23 22:23:12.476327: step: 224/1545, loss: 0.0267452634871006 2023-01-23 22:23:13.341104: step: 226/1545, loss: 0.10416156053543091 2023-01-23 22:23:14.229134: step: 228/1545, loss: 0.0002388636494288221 2023-01-23 22:23:15.103044: step: 230/1545, loss: 0.04568874090909958 2023-01-23 22:23:15.951972: step: 232/1545, loss: 0.00021511116938199848 2023-01-23 22:23:16.836620: step: 234/1545, loss: 0.00038851730641908944 2023-01-23 22:23:17.688853: step: 236/1545, loss: 0.0020106330048292875 2023-01-23 22:23:18.516760: step: 238/1545, loss: 0.046217210590839386 2023-01-23 22:23:19.351276: step: 240/1545, loss: 0.011628218926489353 2023-01-23 22:23:20.212823: step: 242/1545, loss: 2.8079040930606425e-05 2023-01-23 22:23:21.024824: step: 244/1545, loss: 0.0006862774607725441 2023-01-23 22:23:21.914327: step: 246/1545, loss: 0.0490855872631073 2023-01-23 22:23:22.766519: step: 248/1545, loss: 8.601057197665796e-05 2023-01-23 22:23:23.650880: step: 250/1545, loss: 0.0004409773973748088 2023-01-23 22:23:24.534214: step: 252/1545, loss: 0.023018665611743927 2023-01-23 22:23:25.400583: step: 254/1545, loss: 0.059634335339069366 2023-01-23 22:23:26.231627: step: 256/1545, loss: 0.010847978293895721 2023-01-23 22:23:27.082130: step: 258/1545, loss: 0.04278295487165451 2023-01-23 22:23:27.928748: step: 260/1545, loss: 8.224988414440304e-05 2023-01-23 22:23:28.780289: step: 262/1545, loss: 0.00034535539452917874 2023-01-23 22:23:29.643130: step: 264/1545, loss: 0.00010398418817203492 2023-01-23 22:23:30.496769: step: 266/1545, loss: 0.0011332586873322725 2023-01-23 22:23:31.357894: step: 268/1545, loss: 0.00015956921561155468 2023-01-23 22:23:32.274794: step: 270/1545, loss: 0.21212954819202423 2023-01-23 22:23:33.166177: step: 272/1545, loss: 0.2611108124256134 2023-01-23 22:23:34.031865: step: 274/1545, loss: 0.20426227152347565 2023-01-23 22:23:34.897981: step: 276/1545, loss: 0.008706914260983467 2023-01-23 22:23:35.824720: step: 278/1545, loss: 0.013740689493715763 2023-01-23 22:23:36.705527: step: 280/1545, loss: 0.0006340452237054706 2023-01-23 22:23:37.573563: step: 282/1545, loss: 0.0004368394729681313 2023-01-23 22:23:38.391369: step: 284/1545, loss: 0.008179759606719017 2023-01-23 22:23:39.257178: step: 286/1545, loss: 7.269371417351067e-05 2023-01-23 22:23:40.117125: step: 288/1545, loss: 0.029637815430760384 2023-01-23 22:23:40.993273: step: 290/1545, loss: 0.002595628146082163 2023-01-23 22:23:41.879777: step: 292/1545, loss: 0.00028858930454589427 2023-01-23 22:23:42.723679: step: 294/1545, loss: 0.0017893160693347454 2023-01-23 22:23:43.615379: step: 296/1545, loss: 0.014052223414182663 2023-01-23 22:23:44.489657: step: 298/1545, loss: 0.00011000385711668059 2023-01-23 22:23:45.390301: step: 300/1545, loss: 7.62939453125e-06 2023-01-23 22:23:46.222422: step: 302/1545, loss: 0.0009400959243066609 2023-01-23 22:23:47.084319: step: 304/1545, loss: 0.0004026085080113262 2023-01-23 22:23:47.916133: step: 306/1545, loss: 0.00014294699940364808 2023-01-23 22:23:48.781064: step: 308/1545, loss: 0.0007071062573231757 2023-01-23 22:23:49.715138: step: 310/1545, loss: 0.001849764259532094 2023-01-23 22:23:50.588847: step: 312/1545, loss: 0.000270531396381557 2023-01-23 22:23:51.460873: step: 314/1545, loss: 0.07061699777841568 2023-01-23 22:23:52.344555: step: 316/1545, loss: 0.0002450493338983506 2023-01-23 22:23:53.192381: step: 318/1545, loss: 0.008160979487001896 2023-01-23 22:23:54.111795: step: 320/1545, loss: 9.039075666805729e-05 2023-01-23 22:23:54.951006: step: 322/1545, loss: 0.006127871107310057 2023-01-23 22:23:55.820424: step: 324/1545, loss: 0.00010721459693741053 2023-01-23 22:23:56.682544: step: 326/1545, loss: 0.00015314447227865458 2023-01-23 22:23:57.547527: step: 328/1545, loss: 0.007020889315754175 2023-01-23 22:23:58.445567: step: 330/1545, loss: 0.14693056046962738 2023-01-23 22:23:59.276460: step: 332/1545, loss: -1.487731969973538e-05 2023-01-23 22:24:00.188709: step: 334/1545, loss: 0.00025214103516191244 2023-01-23 22:24:01.038989: step: 336/1545, loss: 0.00029304486815817654 2023-01-23 22:24:01.892581: step: 338/1545, loss: 3.899134389939718e-05 2023-01-23 22:24:02.759391: step: 340/1545, loss: 0.014996392652392387 2023-01-23 22:24:03.661704: step: 342/1545, loss: 0.0004995621857233346 2023-01-23 22:24:04.594697: step: 344/1545, loss: 9.423345909453928e-05 2023-01-23 22:24:05.583091: step: 346/1545, loss: 0.00016261190467048436 2023-01-23 22:24:06.469914: step: 348/1545, loss: 0.0024765213020145893 2023-01-23 22:24:07.345641: step: 350/1545, loss: 0.0005243130726739764 2023-01-23 22:24:08.215726: step: 352/1545, loss: 0.11292814463376999 2023-01-23 22:24:09.081878: step: 354/1545, loss: 5.638476068270393e-06 2023-01-23 22:24:09.940387: step: 356/1545, loss: 0.7586498856544495 2023-01-23 22:24:10.912881: step: 358/1545, loss: 3.643035961431451e-05 2023-01-23 22:24:11.769098: step: 360/1545, loss: 9.539368329569697e-05 2023-01-23 22:24:12.645446: step: 362/1545, loss: 0.0007762938621453941 2023-01-23 22:24:13.562352: step: 364/1545, loss: 0.10623151808977127 2023-01-23 22:24:14.454188: step: 366/1545, loss: 8.416607306571677e-05 2023-01-23 22:24:15.373560: step: 368/1545, loss: 0.05987733602523804 2023-01-23 22:24:16.267887: step: 370/1545, loss: 0.5581002831459045 2023-01-23 22:24:17.162434: step: 372/1545, loss: 5.802129453513771e-05 2023-01-23 22:24:17.994380: step: 374/1545, loss: 5.568935648625484e-06 2023-01-23 22:24:18.865321: step: 376/1545, loss: 0.00018954757251776755 2023-01-23 22:24:19.751728: step: 378/1545, loss: 0.038031332194805145 2023-01-23 22:24:20.613480: step: 380/1545, loss: 0.3587646484375 2023-01-23 22:24:21.466252: step: 382/1545, loss: 0.00248344917781651 2023-01-23 22:24:22.335809: step: 384/1545, loss: 0.01614431105554104 2023-01-23 22:24:23.190616: step: 386/1545, loss: 4.644994987756945e-05 2023-01-23 22:24:24.029325: step: 388/1545, loss: 2.7006723030353896e-05 2023-01-23 22:24:24.925103: step: 390/1545, loss: 3.167093018419109e-05 2023-01-23 22:24:25.819514: step: 392/1545, loss: 9.127159864874557e-05 2023-01-23 22:24:26.685457: step: 394/1545, loss: 0.00025393435498699546 2023-01-23 22:24:27.557185: step: 396/1545, loss: 5.629541556118056e-05 2023-01-23 22:24:28.452861: step: 398/1545, loss: 0.002311847871169448 2023-01-23 22:24:29.346053: step: 400/1545, loss: 0.8497082591056824 2023-01-23 22:24:30.207477: step: 402/1545, loss: 0.0006313510239124298 2023-01-23 22:24:31.095086: step: 404/1545, loss: 5.090135528007522e-05 2023-01-23 22:24:31.997550: step: 406/1545, loss: 0.327961802482605 2023-01-23 22:24:32.881597: step: 408/1545, loss: 0.18746814131736755 2023-01-23 22:24:33.791021: step: 410/1545, loss: 0.00010304063471267 2023-01-23 22:24:34.624567: step: 412/1545, loss: 0.028030332177877426 2023-01-23 22:24:35.514401: step: 414/1545, loss: 8.552492363378406e-05 2023-01-23 22:24:36.365005: step: 416/1545, loss: 0.03018813766539097 2023-01-23 22:24:37.227143: step: 418/1545, loss: 0.0002690439869184047 2023-01-23 22:24:38.042718: step: 420/1545, loss: 3.308229133835994e-05 2023-01-23 22:24:38.912332: step: 422/1545, loss: 0.005014321766793728 2023-01-23 22:24:39.792111: step: 424/1545, loss: 1.449457704438828e-05 2023-01-23 22:24:40.713723: step: 426/1545, loss: 2.003023837460205e-05 2023-01-23 22:24:41.560363: step: 428/1545, loss: 0.0003610509156715125 2023-01-23 22:24:42.416597: step: 430/1545, loss: 0.07393499463796616 2023-01-23 22:24:43.305957: step: 432/1545, loss: 0.00018219587218482047 2023-01-23 22:24:44.151963: step: 434/1545, loss: 0.012200307101011276 2023-01-23 22:24:45.021432: step: 436/1545, loss: 0.0010801937896758318 2023-01-23 22:24:45.903043: step: 438/1545, loss: 1.5626063031959347e-05 2023-01-23 22:24:46.752834: step: 440/1545, loss: 7.941600779304281e-05 2023-01-23 22:24:47.624050: step: 442/1545, loss: 0.006776844151318073 2023-01-23 22:24:48.516101: step: 444/1545, loss: 0.0048419334925711155 2023-01-23 22:24:49.447274: step: 446/1545, loss: 0.0019296067766845226 2023-01-23 22:24:50.312689: step: 448/1545, loss: 0.0006879996508359909 2023-01-23 22:24:51.206299: step: 450/1545, loss: 0.007362664677202702 2023-01-23 22:24:52.070200: step: 452/1545, loss: 0.00010291426588082686 2023-01-23 22:24:52.928486: step: 454/1545, loss: 0.00034525839146226645 2023-01-23 22:24:53.820108: step: 456/1545, loss: 0.0003073925618082285 2023-01-23 22:24:54.683480: step: 458/1545, loss: 0.00024235899036284536 2023-01-23 22:24:55.558499: step: 460/1545, loss: 0.0002481034316588193 2023-01-23 22:24:56.413932: step: 462/1545, loss: 7.706980250077322e-05 2023-01-23 22:24:57.315640: step: 464/1545, loss: 0.0002487748861312866 2023-01-23 22:24:58.154839: step: 466/1545, loss: 9.676376794232056e-05 2023-01-23 22:24:59.014237: step: 468/1545, loss: 0.01408276055008173 2023-01-23 22:24:59.923659: step: 470/1545, loss: 0.000388768850825727 2023-01-23 22:25:00.776893: step: 472/1545, loss: 0.00018719144281931221 2023-01-23 22:25:01.641156: step: 474/1545, loss: 0.3084612786769867 2023-01-23 22:25:02.483769: step: 476/1545, loss: 0.0017830171855166554 2023-01-23 22:25:03.442294: step: 478/1545, loss: 7.868629472795874e-05 2023-01-23 22:25:04.348314: step: 480/1545, loss: 0.004602776374667883 2023-01-23 22:25:05.241619: step: 482/1545, loss: 0.0027960194274783134 2023-01-23 22:25:06.151473: step: 484/1545, loss: 0.2325727492570877 2023-01-23 22:25:07.053837: step: 486/1545, loss: 0.10940159857273102 2023-01-23 22:25:07.998160: step: 488/1545, loss: 0.024995574727654457 2023-01-23 22:25:08.906476: step: 490/1545, loss: 0.00012946574133820832 2023-01-23 22:25:09.738170: step: 492/1545, loss: 0.0013794443802908063 2023-01-23 22:25:10.584980: step: 494/1545, loss: 0.000288826267933473 2023-01-23 22:25:11.543879: step: 496/1545, loss: 0.09194813668727875 2023-01-23 22:25:12.414113: step: 498/1545, loss: 0.01499155256897211 2023-01-23 22:25:13.341882: step: 500/1545, loss: 0.0036193968262523413 2023-01-23 22:25:14.191750: step: 502/1545, loss: 0.00973153579980135 2023-01-23 22:25:15.077378: step: 504/1545, loss: 0.03754904121160507 2023-01-23 22:25:15.977296: step: 506/1545, loss: 0.0008143670856952667 2023-01-23 22:25:16.835924: step: 508/1545, loss: 0.03184664994478226 2023-01-23 22:25:17.697695: step: 510/1545, loss: 0.019761107861995697 2023-01-23 22:25:18.623666: step: 512/1545, loss: 0.3256242573261261 2023-01-23 22:25:19.508775: step: 514/1545, loss: 0.21520523726940155 2023-01-23 22:25:20.372225: step: 516/1545, loss: 0.0004239857953507453 2023-01-23 22:25:21.227199: step: 518/1545, loss: 0.00028031918918713927 2023-01-23 22:25:22.113914: step: 520/1545, loss: 2.200488597736694e-05 2023-01-23 22:25:23.103101: step: 522/1545, loss: 0.0001318475406151265 2023-01-23 22:25:23.945424: step: 524/1545, loss: 0.1176242008805275 2023-01-23 22:25:24.785576: step: 526/1545, loss: 0.0009690939332358539 2023-01-23 22:25:25.624638: step: 528/1545, loss: 0.0016160043887794018 2023-01-23 22:25:26.501435: step: 530/1545, loss: 0.0017984642181545496 2023-01-23 22:25:27.382126: step: 532/1545, loss: 0.0031985044479370117 2023-01-23 22:25:28.224528: step: 534/1545, loss: 8.74175202625338e-06 2023-01-23 22:25:29.114922: step: 536/1545, loss: 0.0004237901885062456 2023-01-23 22:25:29.975973: step: 538/1545, loss: 0.00012166780652478337 2023-01-23 22:25:30.822567: step: 540/1545, loss: 0.0002717060851864517 2023-01-23 22:25:31.699323: step: 542/1545, loss: 0.0001917929039336741 2023-01-23 22:25:32.574503: step: 544/1545, loss: 0.002539754379540682 2023-01-23 22:25:33.430548: step: 546/1545, loss: 0.0001415909209754318 2023-01-23 22:25:34.318145: step: 548/1545, loss: 0.00021983298938721418 2023-01-23 22:25:35.217042: step: 550/1545, loss: 0.0007061305805109441 2023-01-23 22:25:36.081347: step: 552/1545, loss: 0.001449395902454853 2023-01-23 22:25:37.012105: step: 554/1545, loss: 0.23510953783988953 2023-01-23 22:25:37.921175: step: 556/1545, loss: 0.0002157139970222488 2023-01-23 22:25:38.815075: step: 558/1545, loss: 0.00010407290392322466 2023-01-23 22:25:39.722669: step: 560/1545, loss: 0.006426333915442228 2023-01-23 22:25:40.585454: step: 562/1545, loss: 0.002133419271558523 2023-01-23 22:25:41.560314: step: 564/1545, loss: 0.02461647242307663 2023-01-23 22:25:42.426203: step: 566/1545, loss: 7.198809908004478e-05 2023-01-23 22:25:43.306661: step: 568/1545, loss: 0.0016258100513368845 2023-01-23 22:25:44.200469: step: 570/1545, loss: 0.0002900059917010367 2023-01-23 22:25:45.089012: step: 572/1545, loss: 8.860031084623188e-05 2023-01-23 22:25:45.967353: step: 574/1545, loss: 0.0007658894755877554 2023-01-23 22:25:46.889416: step: 576/1545, loss: 0.0006037217099219561 2023-01-23 22:25:47.749779: step: 578/1545, loss: 0.000890091119799763 2023-01-23 22:25:48.617438: step: 580/1545, loss: 7.216532685561106e-05 2023-01-23 22:25:49.503755: step: 582/1545, loss: 0.012872140854597092 2023-01-23 22:25:50.425538: step: 584/1545, loss: 0.001523985993117094 2023-01-23 22:25:51.325273: step: 586/1545, loss: 2.9240705771371722e-05 2023-01-23 22:25:52.160046: step: 588/1545, loss: -2.250743818876799e-06 2023-01-23 22:25:53.034874: step: 590/1545, loss: 0.00054543575970456 2023-01-23 22:25:53.899780: step: 592/1545, loss: 0.07837346941232681 2023-01-23 22:25:54.761103: step: 594/1545, loss: 0.06134194880723953 2023-01-23 22:25:55.736544: step: 596/1545, loss: 0.0007870759582147002 2023-01-23 22:25:56.648258: step: 598/1545, loss: 0.00011556032404769212 2023-01-23 22:25:57.503421: step: 600/1545, loss: 0.032790787518024445 2023-01-23 22:25:58.353890: step: 602/1545, loss: 0.00033224461367353797 2023-01-23 22:25:59.225210: step: 604/1545, loss: 0.0012334738858044147 2023-01-23 22:26:00.151966: step: 606/1545, loss: 0.015847142785787582 2023-01-23 22:26:01.078395: step: 608/1545, loss: 0.02056763879954815 2023-01-23 22:26:01.914103: step: 610/1545, loss: 0.005039864219725132 2023-01-23 22:26:02.790618: step: 612/1545, loss: 0.00039708465919829905 2023-01-23 22:26:03.707811: step: 614/1545, loss: 0.0011075849179178476 2023-01-23 22:26:04.634934: step: 616/1545, loss: 0.024095788598060608 2023-01-23 22:26:05.548604: step: 618/1545, loss: 8.591843652538955e-05 2023-01-23 22:26:06.407260: step: 620/1545, loss: 0.005381335038691759 2023-01-23 22:26:07.307415: step: 622/1545, loss: 0.00799472164362669 2023-01-23 22:26:08.194827: step: 624/1545, loss: 6.450797081924975e-05 2023-01-23 22:26:09.043952: step: 626/1545, loss: 0.019284427165985107 2023-01-23 22:26:09.942783: step: 628/1545, loss: 0.0003658694331534207 2023-01-23 22:26:10.812333: step: 630/1545, loss: 0.004884196445345879 2023-01-23 22:26:11.724846: step: 632/1545, loss: 0.6368292570114136 2023-01-23 22:26:12.576244: step: 634/1545, loss: 0.0003118241729680449 2023-01-23 22:26:13.447880: step: 636/1545, loss: 0.003289328422397375 2023-01-23 22:26:14.311384: step: 638/1545, loss: 0.002845501760020852 2023-01-23 22:26:15.199678: step: 640/1545, loss: 0.0020156214013695717 2023-01-23 22:26:16.094322: step: 642/1545, loss: 0.0003976821026299149 2023-01-23 22:26:16.968113: step: 644/1545, loss: 0.002468749415129423 2023-01-23 22:26:17.854297: step: 646/1545, loss: 0.26005715131759644 2023-01-23 22:26:18.756732: step: 648/1545, loss: 3.077629298786633e-05 2023-01-23 22:26:19.654522: step: 650/1545, loss: 2.6982925191987306e-05 2023-01-23 22:26:20.521068: step: 652/1545, loss: -1.841240555222612e-05 2023-01-23 22:26:21.435850: step: 654/1545, loss: 0.013036255724728107 2023-01-23 22:26:22.327526: step: 656/1545, loss: 3.4185046388302e-05 2023-01-23 22:26:23.256954: step: 658/1545, loss: 0.16869711875915527 2023-01-23 22:26:24.122218: step: 660/1545, loss: 4.32866727351211e-07 2023-01-23 22:26:25.036174: step: 662/1545, loss: 0.0011471910402178764 2023-01-23 22:26:25.940019: step: 664/1545, loss: 3.115901563432999e-05 2023-01-23 22:26:26.803588: step: 666/1545, loss: 3.959644527640194e-05 2023-01-23 22:26:27.639378: step: 668/1545, loss: -9.67809228313854e-06 2023-01-23 22:26:28.499143: step: 670/1545, loss: 0.013272184878587723 2023-01-23 22:26:29.334505: step: 672/1545, loss: 0.00024640155606903136 2023-01-23 22:26:30.232545: step: 674/1545, loss: 0.12860533595085144 2023-01-23 22:26:31.091843: step: 676/1545, loss: 2.8435888452804647e-05 2023-01-23 22:26:31.974659: step: 678/1545, loss: 0.0016799088334664702 2023-01-23 22:26:32.856828: step: 680/1545, loss: 0.01718730852007866 2023-01-23 22:26:33.713837: step: 682/1545, loss: 1.1083465324190911e-05 2023-01-23 22:26:34.574371: step: 684/1545, loss: 0.008824880234897137 2023-01-23 22:26:35.420067: step: 686/1545, loss: 0.00020715780556201935 2023-01-23 22:26:36.264353: step: 688/1545, loss: 0.0055696917697787285 2023-01-23 22:26:37.162733: step: 690/1545, loss: 0.02665807120501995 2023-01-23 22:26:38.057407: step: 692/1545, loss: 0.0001622391864657402 2023-01-23 22:26:38.907898: step: 694/1545, loss: 0.03433997184038162 2023-01-23 22:26:39.827350: step: 696/1545, loss: 3.9680020563537255e-05 2023-01-23 22:26:40.733153: step: 698/1545, loss: 0.33762767910957336 2023-01-23 22:26:41.606723: step: 700/1545, loss: 7.762337918393314e-05 2023-01-23 22:26:42.466143: step: 702/1545, loss: 0.10345412790775299 2023-01-23 22:26:43.352137: step: 704/1545, loss: 0.10057084262371063 2023-01-23 22:26:44.248440: step: 706/1545, loss: 0.3726636469364166 2023-01-23 22:26:45.143252: step: 708/1545, loss: 0.000998667674139142 2023-01-23 22:26:45.980326: step: 710/1545, loss: 4.681816790252924e-05 2023-01-23 22:26:46.886849: step: 712/1545, loss: 0.0010658390820026398 2023-01-23 22:26:47.735317: step: 714/1545, loss: 0.00020973183563910425 2023-01-23 22:26:48.603879: step: 716/1545, loss: 0.1803865283727646 2023-01-23 22:26:49.468220: step: 718/1545, loss: 0.1276368647813797 2023-01-23 22:26:50.365343: step: 720/1545, loss: 0.007626324892044067 2023-01-23 22:26:51.277319: step: 722/1545, loss: 0.0005948984180577099 2023-01-23 22:26:52.180474: step: 724/1545, loss: 0.0040049185045063496 2023-01-23 22:26:53.084500: step: 726/1545, loss: 0.11714573204517365 2023-01-23 22:26:53.980254: step: 728/1545, loss: 0.10398849844932556 2023-01-23 22:26:54.835155: step: 730/1545, loss: 0.0048036533407866955 2023-01-23 22:26:55.735456: step: 732/1545, loss: 0.005112149752676487 2023-01-23 22:26:56.574759: step: 734/1545, loss: 0.0002969041815958917 2023-01-23 22:26:57.522478: step: 736/1545, loss: 0.021091395989060402 2023-01-23 22:26:58.380046: step: 738/1545, loss: 0.0019365731859579682 2023-01-23 22:26:59.222956: step: 740/1545, loss: 0.04890456050634384 2023-01-23 22:27:00.077808: step: 742/1545, loss: 0.261292964220047 2023-01-23 22:27:01.045778: step: 744/1545, loss: 0.00012296406202949584 2023-01-23 22:27:01.937383: step: 746/1545, loss: 0.0010747310006991029 2023-01-23 22:27:02.911182: step: 748/1545, loss: 0.0003510966489557177 2023-01-23 22:27:03.855279: step: 750/1545, loss: 7.465662201866508e-05 2023-01-23 22:27:04.760558: step: 752/1545, loss: 0.0004592780314851552 2023-01-23 22:27:05.652062: step: 754/1545, loss: 0.0009190977434627712 2023-01-23 22:27:06.597598: step: 756/1545, loss: 0.7123711705207825 2023-01-23 22:27:07.442882: step: 758/1545, loss: 4.728583007818088e-05 2023-01-23 22:27:08.291495: step: 760/1545, loss: -1.568409970786888e-05 2023-01-23 22:27:09.164083: step: 762/1545, loss: 0.10228094458580017 2023-01-23 22:27:10.032826: step: 764/1545, loss: 0.0005412498721852899 2023-01-23 22:27:10.875208: step: 766/1545, loss: 0.0002204863994847983 2023-01-23 22:27:11.807076: step: 768/1545, loss: 0.00036547015770338476 2023-01-23 22:27:12.696983: step: 770/1545, loss: 0.13803628087043762 2023-01-23 22:27:13.548902: step: 772/1545, loss: 0.00016527740808669478 2023-01-23 22:27:14.443965: step: 774/1545, loss: 2.5201796233886853e-05 2023-01-23 22:27:15.330219: step: 776/1545, loss: 2.3402499209623784e-05 2023-01-23 22:27:16.214167: step: 778/1545, loss: 0.0014527150196954608 2023-01-23 22:27:17.129630: step: 780/1545, loss: 0.00227173650637269 2023-01-23 22:27:18.028956: step: 782/1545, loss: 0.10680928826332092 2023-01-23 22:27:18.886928: step: 784/1545, loss: 9.800780389923602e-05 2023-01-23 22:27:19.761343: step: 786/1545, loss: 0.0017714439891278744 2023-01-23 22:27:20.667540: step: 788/1545, loss: 0.00032635568641126156 2023-01-23 22:27:21.568608: step: 790/1545, loss: 0.07362038642168045 2023-01-23 22:27:22.399272: step: 792/1545, loss: 0.004921161103993654 2023-01-23 22:27:23.295693: step: 794/1545, loss: 0.014721265062689781 2023-01-23 22:27:24.169075: step: 796/1545, loss: 0.0022781556472182274 2023-01-23 22:27:25.030282: step: 798/1545, loss: 6.928071525180712e-05 2023-01-23 22:27:25.978564: step: 800/1545, loss: 3.8312686228891835e-05 2023-01-23 22:27:26.977271: step: 802/1545, loss: 0.017069557681679726 2023-01-23 22:27:27.856824: step: 804/1545, loss: 0.019545141607522964 2023-01-23 22:27:28.751518: step: 806/1545, loss: 2.006877366511617e-05 2023-01-23 22:27:29.579623: step: 808/1545, loss: 0.20659410953521729 2023-01-23 22:27:30.443324: step: 810/1545, loss: 0.006169144529849291 2023-01-23 22:27:31.311064: step: 812/1545, loss: 0.3679840564727783 2023-01-23 22:27:32.193300: step: 814/1545, loss: 0.15451021492481232 2023-01-23 22:27:33.047733: step: 816/1545, loss: 0.0024151327088475227 2023-01-23 22:27:33.905174: step: 818/1545, loss: 0.0001696282997727394 2023-01-23 22:27:34.787487: step: 820/1545, loss: 0.05090870335698128 2023-01-23 22:27:35.676454: step: 822/1545, loss: 0.0015434749657288194 2023-01-23 22:27:36.523445: step: 824/1545, loss: 0.07473429292440414 2023-01-23 22:27:37.440768: step: 826/1545, loss: 0.0009723416878841817 2023-01-23 22:27:38.309218: step: 828/1545, loss: 0.00019840619643218815 2023-01-23 22:27:39.173749: step: 830/1545, loss: 0.000889875867869705 2023-01-23 22:27:40.027777: step: 832/1545, loss: 0.0006410658825188875 2023-01-23 22:27:40.883407: step: 834/1545, loss: 0.01618863455951214 2023-01-23 22:27:41.742298: step: 836/1545, loss: 0.004831791389733553 2023-01-23 22:27:42.659133: step: 838/1545, loss: 0.004976995289325714 2023-01-23 22:27:43.526247: step: 840/1545, loss: 0.025067569687962532 2023-01-23 22:27:44.438528: step: 842/1545, loss: 0.11617451906204224 2023-01-23 22:27:45.303508: step: 844/1545, loss: 3.5179655242245644e-05 2023-01-23 22:27:46.224689: step: 846/1545, loss: 0.0056251659989356995 2023-01-23 22:27:47.097754: step: 848/1545, loss: 0.00019031958072446287 2023-01-23 22:27:47.978191: step: 850/1545, loss: 0.00023721008619759232 2023-01-23 22:27:48.821708: step: 852/1545, loss: 5.269100074656308e-05 2023-01-23 22:27:49.710241: step: 854/1545, loss: 7.728737614343117e-07 2023-01-23 22:27:50.555999: step: 856/1545, loss: 0.001203149906359613 2023-01-23 22:27:51.458570: step: 858/1545, loss: 0.012374788522720337 2023-01-23 22:27:52.320631: step: 860/1545, loss: 0.0026673409156501293 2023-01-23 22:27:53.197401: step: 862/1545, loss: 2.4354732886422426e-05 2023-01-23 22:27:54.081025: step: 864/1545, loss: 0.0008782516233623028 2023-01-23 22:27:54.970665: step: 866/1545, loss: 9.689390572020784e-05 2023-01-23 22:27:55.840104: step: 868/1545, loss: 2.7296649932395667e-05 2023-01-23 22:27:56.733699: step: 870/1545, loss: 0.00016978499479591846 2023-01-23 22:27:57.660361: step: 872/1545, loss: 4.5815853809472173e-05 2023-01-23 22:27:58.606998: step: 874/1545, loss: 6.100481641624356e-06 2023-01-23 22:27:59.487345: step: 876/1545, loss: 2.2325310707092285 2023-01-23 22:28:00.396061: step: 878/1545, loss: 0.1364312618970871 2023-01-23 22:28:01.268502: step: 880/1545, loss: 0.00032760907197371125 2023-01-23 22:28:02.223928: step: 882/1545, loss: 0.0036278078332543373 2023-01-23 22:28:03.166268: step: 884/1545, loss: 0.30368489027023315 2023-01-23 22:28:04.049996: step: 886/1545, loss: 0.5861683487892151 2023-01-23 22:28:04.963194: step: 888/1545, loss: 0.046070147305727005 2023-01-23 22:28:05.882467: step: 890/1545, loss: 0.0013105982216075063 2023-01-23 22:28:06.795294: step: 892/1545, loss: 0.10072692483663559 2023-01-23 22:28:07.639628: step: 894/1545, loss: 0.0008166041225194931 2023-01-23 22:28:08.501017: step: 896/1545, loss: 0.002423846861347556 2023-01-23 22:28:09.397344: step: 898/1545, loss: 0.0016746576875448227 2023-01-23 22:28:10.267518: step: 900/1545, loss: 0.004298376385122538 2023-01-23 22:28:11.144080: step: 902/1545, loss: 8.000885281944647e-05 2023-01-23 22:28:12.016870: step: 904/1545, loss: 0.0002996950352098793 2023-01-23 22:28:12.921765: step: 906/1545, loss: 0.0003547837259247899 2023-01-23 22:28:13.873451: step: 908/1545, loss: 0.000507442164234817 2023-01-23 22:28:14.735643: step: 910/1545, loss: 0.004161512944847345 2023-01-23 22:28:15.649768: step: 912/1545, loss: 0.02528432011604309 2023-01-23 22:28:16.474080: step: 914/1545, loss: 0.00014759956684429199 2023-01-23 22:28:17.400303: step: 916/1545, loss: 0.04234304651618004 2023-01-23 22:28:18.267593: step: 918/1545, loss: 0.0015053539536893368 2023-01-23 22:28:19.150368: step: 920/1545, loss: 0.4423094689846039 2023-01-23 22:28:20.050297: step: 922/1545, loss: 3.282129910076037e-05 2023-01-23 22:28:20.934195: step: 924/1545, loss: 0.0008915948565118015 2023-01-23 22:28:21.812585: step: 926/1545, loss: 0.1635132133960724 2023-01-23 22:28:22.712937: step: 928/1545, loss: 0.02523980662226677 2023-01-23 22:28:23.597321: step: 930/1545, loss: 0.004445162136107683 2023-01-23 22:28:24.460208: step: 932/1545, loss: 0.0005363398813642561 2023-01-23 22:28:25.354542: step: 934/1545, loss: 1.1575716598599683e-05 2023-01-23 22:28:26.234225: step: 936/1545, loss: 0.0036021899431943893 2023-01-23 22:28:27.098218: step: 938/1545, loss: 0.000432584376540035 2023-01-23 22:28:27.967061: step: 940/1545, loss: 8.32576333777979e-05 2023-01-23 22:28:28.920823: step: 942/1545, loss: 0.08703009784221649 2023-01-23 22:28:29.772544: step: 944/1545, loss: 0.04684115946292877 2023-01-23 22:28:30.663706: step: 946/1545, loss: 0.0067490264773368835 2023-01-23 22:28:31.564604: step: 948/1545, loss: 0.15959657728672028 2023-01-23 22:28:32.425816: step: 950/1545, loss: 5.932329804636538e-05 2023-01-23 22:28:33.337373: step: 952/1545, loss: 0.0009853895753622055 2023-01-23 22:28:34.203954: step: 954/1545, loss: 0.15553666651248932 2023-01-23 22:28:35.149151: step: 956/1545, loss: 0.05403614044189453 2023-01-23 22:28:36.049243: step: 958/1545, loss: 0.0020747832022607327 2023-01-23 22:28:36.927413: step: 960/1545, loss: 0.00010513400775380433 2023-01-23 22:28:37.811622: step: 962/1545, loss: 0.01748129352927208 2023-01-23 22:28:38.669428: step: 964/1545, loss: 0.000612145580817014 2023-01-23 22:28:39.551024: step: 966/1545, loss: 0.001313124899752438 2023-01-23 22:28:40.473500: step: 968/1545, loss: 0.06982345879077911 2023-01-23 22:28:41.337224: step: 970/1545, loss: 0.003457636572420597 2023-01-23 22:28:42.191670: step: 972/1545, loss: 0.006202142685651779 2023-01-23 22:28:43.073472: step: 974/1545, loss: -1.972119207493961e-05 2023-01-23 22:28:43.945157: step: 976/1545, loss: 0.0019837741274386644 2023-01-23 22:28:44.837053: step: 978/1545, loss: 0.0008111611241474748 2023-01-23 22:28:45.719710: step: 980/1545, loss: 0.00025807920610532165 2023-01-23 22:28:46.566904: step: 982/1545, loss: 0.09430944174528122 2023-01-23 22:28:47.442894: step: 984/1545, loss: 0.12409229576587677 2023-01-23 22:28:48.329259: step: 986/1545, loss: 0.00018556798750068992 2023-01-23 22:28:49.231835: step: 988/1545, loss: 0.00013216289517004043 2023-01-23 22:28:50.131102: step: 990/1545, loss: 0.00023385704844258726 2023-01-23 22:28:51.033156: step: 992/1545, loss: 0.026626847684383392 2023-01-23 22:28:51.909406: step: 994/1545, loss: 0.16362492740154266 2023-01-23 22:28:52.746479: step: 996/1545, loss: 0.00473291939124465 2023-01-23 22:28:53.579014: step: 998/1545, loss: 0.00044086421257816255 2023-01-23 22:28:54.471631: step: 1000/1545, loss: 0.015130927786231041 2023-01-23 22:28:55.383931: step: 1002/1545, loss: 0.004237394779920578 2023-01-23 22:28:56.242342: step: 1004/1545, loss: 0.05722835659980774 2023-01-23 22:28:57.130714: step: 1006/1545, loss: 0.00021317713253665715 2023-01-23 22:28:57.984541: step: 1008/1545, loss: 0.00025849265512079 2023-01-23 22:28:58.896526: step: 1010/1545, loss: 0.0075732688419520855 2023-01-23 22:28:59.820243: step: 1012/1545, loss: 0.0005104933516122401 2023-01-23 22:29:00.701211: step: 1014/1545, loss: 0.000611284573096782 2023-01-23 22:29:01.568591: step: 1016/1545, loss: 0.0001035712703014724 2023-01-23 22:29:02.451800: step: 1018/1545, loss: 0.17005275189876556 2023-01-23 22:29:03.332114: step: 1020/1545, loss: 7.343364995904267e-05 2023-01-23 22:29:04.216164: step: 1022/1545, loss: 0.009761825203895569 2023-01-23 22:29:05.106227: step: 1024/1545, loss: 0.02910217083990574 2023-01-23 22:29:05.942595: step: 1026/1545, loss: 0.001878239563666284 2023-01-23 22:29:06.841426: step: 1028/1545, loss: 5.1161376177333295e-05 2023-01-23 22:29:07.728596: step: 1030/1545, loss: 0.0823693573474884 2023-01-23 22:29:08.593774: step: 1032/1545, loss: 2.9818434995831922e-05 2023-01-23 22:29:09.506107: step: 1034/1545, loss: 1.0918286534433719e-05 2023-01-23 22:29:10.401110: step: 1036/1545, loss: 0.2954312860965729 2023-01-23 22:29:11.315083: step: 1038/1545, loss: 0.0353551022708416 2023-01-23 22:29:12.253470: step: 1040/1545, loss: 0.04614380747079849 2023-01-23 22:29:13.184853: step: 1042/1545, loss: 1.3733654668612871e-05 2023-01-23 22:29:14.048411: step: 1044/1545, loss: 4.2736533941933885e-05 2023-01-23 22:29:14.901813: step: 1046/1545, loss: -4.3404103053035215e-05 2023-01-23 22:29:15.833807: step: 1048/1545, loss: 0.00010312272934243083 2023-01-23 22:29:16.695215: step: 1050/1545, loss: 0.0007670613122172654 2023-01-23 22:29:17.579227: step: 1052/1545, loss: 4.66823585156817e-05 2023-01-23 22:29:18.434966: step: 1054/1545, loss: 0.00015392442583106458 2023-01-23 22:29:19.307263: step: 1056/1545, loss: 0.0006928285001777112 2023-01-23 22:29:20.199060: step: 1058/1545, loss: 0.007433508522808552 2023-01-23 22:29:21.069583: step: 1060/1545, loss: 5.582479843724286e-06 2023-01-23 22:29:21.949671: step: 1062/1545, loss: 0.0035046860575675964 2023-01-23 22:29:22.819766: step: 1064/1545, loss: 0.017712360247969627 2023-01-23 22:29:23.772537: step: 1066/1545, loss: 3.0498883724212646 2023-01-23 22:29:24.627645: step: 1068/1545, loss: 7.412433478748426e-05 2023-01-23 22:29:25.511615: step: 1070/1545, loss: 0.014909534715116024 2023-01-23 22:29:26.403202: step: 1072/1545, loss: 0.00012722759856842458 2023-01-23 22:29:27.299457: step: 1074/1545, loss: -1.5423929653479718e-05 2023-01-23 22:29:28.198891: step: 1076/1545, loss: 0.00010005354124587029 2023-01-23 22:29:29.089837: step: 1078/1545, loss: 0.00040588557021692395 2023-01-23 22:29:30.005146: step: 1080/1545, loss: 0.14498694241046906 2023-01-23 22:29:30.841596: step: 1082/1545, loss: 7.783770706737414e-05 2023-01-23 22:29:31.772859: step: 1084/1545, loss: 0.0318782664835453 2023-01-23 22:29:32.636938: step: 1086/1545, loss: 5.087613681098446e-05 2023-01-23 22:29:33.492019: step: 1088/1545, loss: 1.9816225176327862e-05 2023-01-23 22:29:34.333737: step: 1090/1545, loss: 4.696100586443208e-05 2023-01-23 22:29:35.247303: step: 1092/1545, loss: 0.014000714756548405 2023-01-23 22:29:36.155293: step: 1094/1545, loss: 1.2995090401091147e-05 2023-01-23 22:29:37.045290: step: 1096/1545, loss: 0.03573967516422272 2023-01-23 22:29:37.949164: step: 1098/1545, loss: 0.09857124090194702 2023-01-23 22:29:38.837908: step: 1100/1545, loss: 3.0285596949397586e-05 2023-01-23 22:29:39.707366: step: 1102/1545, loss: 0.0010780488373711705 2023-01-23 22:29:40.610503: step: 1104/1545, loss: 0.5082459449768066 2023-01-23 22:29:41.534360: step: 1106/1545, loss: 0.00024811920593492687 2023-01-23 22:29:42.363602: step: 1108/1545, loss: 2.5193394321831875e-05 2023-01-23 22:29:43.253005: step: 1110/1545, loss: 0.1923229843378067 2023-01-23 22:29:44.169237: step: 1112/1545, loss: 0.0062156678177416325 2023-01-23 22:29:45.085787: step: 1114/1545, loss: 0.030117660760879517 2023-01-23 22:29:45.945888: step: 1116/1545, loss: 0.0001623473217478022 2023-01-23 22:29:46.801792: step: 1118/1545, loss: 0.1988111287355423 2023-01-23 22:29:47.704809: step: 1120/1545, loss: -2.1506846678676084e-05 2023-01-23 22:29:48.584267: step: 1122/1545, loss: 5.80340611122665e-06 2023-01-23 22:29:49.446606: step: 1124/1545, loss: 1.3437270354188513e-05 2023-01-23 22:29:50.319961: step: 1126/1545, loss: 0.00022687861928716302 2023-01-23 22:29:51.193251: step: 1128/1545, loss: -2.1340945750125684e-05 2023-01-23 22:29:52.067754: step: 1130/1545, loss: 0.10519032925367355 2023-01-23 22:29:52.991933: step: 1132/1545, loss: 0.0010599142406135798 2023-01-23 22:29:53.859320: step: 1134/1545, loss: 2.791941187751945e-05 2023-01-23 22:29:54.738094: step: 1136/1545, loss: 0.3843035399913788 2023-01-23 22:29:55.677945: step: 1138/1545, loss: 0.0001569062878843397 2023-01-23 22:29:56.569289: step: 1140/1545, loss: -3.119508983218111e-05 2023-01-23 22:29:57.456583: step: 1142/1545, loss: 0.0009431307553313673 2023-01-23 22:29:58.317251: step: 1144/1545, loss: 0.0007392275729216635 2023-01-23 22:29:59.170843: step: 1146/1545, loss: 0.00017487180593889207 2023-01-23 22:30:00.083574: step: 1148/1545, loss: 0.002020475687459111 2023-01-23 22:30:00.957399: step: 1150/1545, loss: 0.00012423057341948152 2023-01-23 22:30:01.776208: step: 1152/1545, loss: 0.0017698699375614524 2023-01-23 22:30:02.652107: step: 1154/1545, loss: 0.00013459513138514012 2023-01-23 22:30:03.548886: step: 1156/1545, loss: 0.0005311769782565534 2023-01-23 22:30:04.451944: step: 1158/1545, loss: 0.16974994540214539 2023-01-23 22:30:05.340624: step: 1160/1545, loss: 0.0027133377734571695 2023-01-23 22:30:06.234076: step: 1162/1545, loss: 0.00045074737863615155 2023-01-23 22:30:07.144214: step: 1164/1545, loss: 0.0019124394748359919 2023-01-23 22:30:08.111705: step: 1166/1545, loss: 0.11015304177999496 2023-01-23 22:30:09.037886: step: 1168/1545, loss: 0.10870273411273956 2023-01-23 22:30:09.896349: step: 1170/1545, loss: 0.05190865322947502 2023-01-23 22:30:10.747201: step: 1172/1545, loss: 2.2147827621665783e-05 2023-01-23 22:30:11.656645: step: 1174/1545, loss: 0.00010720193677116185 2023-01-23 22:30:12.541956: step: 1176/1545, loss: 0.0001134926569648087 2023-01-23 22:30:13.431431: step: 1178/1545, loss: 0.00011303680366836488 2023-01-23 22:30:14.433994: step: 1180/1545, loss: 0.0010904300725087523 2023-01-23 22:30:15.285166: step: 1182/1545, loss: 3.129095057374798e-05 2023-01-23 22:30:16.129983: step: 1184/1545, loss: 0.03930272161960602 2023-01-23 22:30:16.999020: step: 1186/1545, loss: 0.06481890380382538 2023-01-23 22:30:17.904415: step: 1188/1545, loss: 0.016262464225292206 2023-01-23 22:30:18.760282: step: 1190/1545, loss: 9.093910193769261e-05 2023-01-23 22:30:19.667139: step: 1192/1545, loss: 0.05359678715467453 2023-01-23 22:30:20.577215: step: 1194/1545, loss: 0.000162000025738962 2023-01-23 22:30:21.476709: step: 1196/1545, loss: 0.0002608188078738749 2023-01-23 22:30:22.330875: step: 1198/1545, loss: 3.80709461751394e-05 2023-01-23 22:30:23.198112: step: 1200/1545, loss: 0.0001795323332771659 2023-01-23 22:30:24.100328: step: 1202/1545, loss: 0.1887529045343399 2023-01-23 22:30:25.005995: step: 1204/1545, loss: 0.2282710075378418 2023-01-23 22:30:25.961842: step: 1206/1545, loss: 0.5426086783409119 2023-01-23 22:30:26.841399: step: 1208/1545, loss: 2.2126436306280084e-05 2023-01-23 22:30:27.699051: step: 1210/1545, loss: 6.602455687243491e-05 2023-01-23 22:30:28.648605: step: 1212/1545, loss: 0.0003002113662660122 2023-01-23 22:30:29.498090: step: 1214/1545, loss: -1.2748927474603988e-05 2023-01-23 22:30:30.385412: step: 1216/1545, loss: 0.0002863571862690151 2023-01-23 22:30:31.274311: step: 1218/1545, loss: 0.08126185089349747 2023-01-23 22:30:32.187409: step: 1220/1545, loss: 0.16896478831768036 2023-01-23 22:30:33.097663: step: 1222/1545, loss: 0.00010418057354399934 2023-01-23 22:30:33.977409: step: 1224/1545, loss: 0.0016854722052812576 2023-01-23 22:30:34.853309: step: 1226/1545, loss: 0.0004143883124925196 2023-01-23 22:30:35.726580: step: 1228/1545, loss: 0.00023498834343627095 2023-01-23 22:30:36.692449: step: 1230/1545, loss: 0.0010468576801940799 2023-01-23 22:30:37.572024: step: 1232/1545, loss: 0.000898376980330795 2023-01-23 22:30:38.472172: step: 1234/1545, loss: 0.0005782082444056869 2023-01-23 22:30:39.326278: step: 1236/1545, loss: 0.00029533004271797836 2023-01-23 22:30:40.185123: step: 1238/1545, loss: 0.11194814741611481 2023-01-23 22:30:41.068972: step: 1240/1545, loss: 0.8334663510322571 2023-01-23 22:30:41.976939: step: 1242/1545, loss: 7.172311597969383e-05 2023-01-23 22:30:42.868307: step: 1244/1545, loss: 0.0016087493859231472 2023-01-23 22:30:43.812469: step: 1246/1545, loss: 0.3742360472679138 2023-01-23 22:30:44.704451: step: 1248/1545, loss: 1.973810140043497e-05 2023-01-23 22:30:45.557302: step: 1250/1545, loss: 0.00025944042135961354 2023-01-23 22:30:46.441269: step: 1252/1545, loss: -7.1290523919742554e-06 2023-01-23 22:30:47.321042: step: 1254/1545, loss: -7.593631835334236e-06 2023-01-23 22:30:48.243877: step: 1256/1545, loss: 0.5147742033004761 2023-01-23 22:30:49.072585: step: 1258/1545, loss: 0.0021509258076548576 2023-01-23 22:30:49.911100: step: 1260/1545, loss: 0.0001670433848630637 2023-01-23 22:30:50.833618: step: 1262/1545, loss: 0.026691950857639313 2023-01-23 22:30:51.728001: step: 1264/1545, loss: 0.07162419706583023 2023-01-23 22:30:52.583703: step: 1266/1545, loss: 0.001102882088162005 2023-01-23 22:30:53.422242: step: 1268/1545, loss: -2.6518704544287175e-05 2023-01-23 22:30:54.336166: step: 1270/1545, loss: -1.2343480193521827e-05 2023-01-23 22:30:55.206006: step: 1272/1545, loss: 0.02258954383432865 2023-01-23 22:30:56.089892: step: 1274/1545, loss: 2.4413271603407338e-05 2023-01-23 22:30:57.043338: step: 1276/1545, loss: 0.2669329345226288 2023-01-23 22:30:57.922640: step: 1278/1545, loss: 0.11385098099708557 2023-01-23 22:30:58.753729: step: 1280/1545, loss: 0.003738212399184704 2023-01-23 22:30:59.622810: step: 1282/1545, loss: 0.000465178833110258 2023-01-23 22:31:00.570800: step: 1284/1545, loss: 3.9514503441751e-05 2023-01-23 22:31:01.431124: step: 1286/1545, loss: -2.7432581191533245e-05 2023-01-23 22:31:02.329606: step: 1288/1545, loss: 0.0050140125676989555 2023-01-23 22:31:03.219589: step: 1290/1545, loss: 3.1285198929253966e-05 2023-01-23 22:31:04.090215: step: 1292/1545, loss: 0.0005351485451683402 2023-01-23 22:31:04.949914: step: 1294/1545, loss: 4.3499760067788884e-05 2023-01-23 22:31:05.836450: step: 1296/1545, loss: 0.0012017376720905304 2023-01-23 22:31:06.708897: step: 1298/1545, loss: -9.799567123991437e-06 2023-01-23 22:31:07.520272: step: 1300/1545, loss: 7.325484330067411e-05 2023-01-23 22:31:08.496410: step: 1302/1545, loss: 7.207222370197996e-05 2023-01-23 22:31:09.358908: step: 1304/1545, loss: 0.0001823224447434768 2023-01-23 22:31:10.242723: step: 1306/1545, loss: 0.46154749393463135 2023-01-23 22:31:11.125788: step: 1308/1545, loss: 0.005684844218194485 2023-01-23 22:31:12.007673: step: 1310/1545, loss: 0.000347301916917786 2023-01-23 22:31:12.895131: step: 1312/1545, loss: 0.0001654374791542068 2023-01-23 22:31:13.779129: step: 1314/1545, loss: 0.038685236126184464 2023-01-23 22:31:14.690377: step: 1316/1545, loss: 0.0004157302901148796 2023-01-23 22:31:15.559669: step: 1318/1545, loss: 2.522260729165282e-05 2023-01-23 22:31:16.504461: step: 1320/1545, loss: 0.0004872117715422064 2023-01-23 22:31:17.369011: step: 1322/1545, loss: 2.403631697234232e-05 2023-01-23 22:31:18.240187: step: 1324/1545, loss: 4.6301815018523484e-05 2023-01-23 22:31:19.075311: step: 1326/1545, loss: 0.00011852571333292872 2023-01-23 22:31:20.042654: step: 1328/1545, loss: 0.00036012622877024114 2023-01-23 22:31:20.932584: step: 1330/1545, loss: 0.053865715861320496 2023-01-23 22:31:21.785325: step: 1332/1545, loss: 0.00027977817808277905 2023-01-23 22:31:22.687356: step: 1334/1545, loss: 0.010937328450381756 2023-01-23 22:31:23.603621: step: 1336/1545, loss: 0.10596729069948196 2023-01-23 22:31:24.463232: step: 1338/1545, loss: 0.01679246686398983 2023-01-23 22:31:25.359612: step: 1340/1545, loss: 0.001095291692763567 2023-01-23 22:31:26.286282: step: 1342/1545, loss: 0.03226887807250023 2023-01-23 22:31:27.184411: step: 1344/1545, loss: 0.00031083522480912507 2023-01-23 22:31:28.053968: step: 1346/1545, loss: 0.0001499916543252766 2023-01-23 22:31:28.968589: step: 1348/1545, loss: 0.00016102349036373198 2023-01-23 22:31:29.855738: step: 1350/1545, loss: 0.034197431057691574 2023-01-23 22:31:30.794246: step: 1352/1545, loss: 0.0062155998311936855 2023-01-23 22:31:31.623485: step: 1354/1545, loss: 2.2367465135175735e-05 2023-01-23 22:31:32.483842: step: 1356/1545, loss: 0.00011312346759950742 2023-01-23 22:31:33.333877: step: 1358/1545, loss: 0.0006888883654028177 2023-01-23 22:31:34.276791: step: 1360/1545, loss: 0.004991953726857901 2023-01-23 22:31:35.220810: step: 1362/1545, loss: -1.4119375009613577e-05 2023-01-23 22:31:36.096903: step: 1364/1545, loss: 0.0021183930803090334 2023-01-23 22:31:36.999865: step: 1366/1545, loss: 0.0007913237786851823 2023-01-23 22:31:37.836180: step: 1368/1545, loss: 0.0015227730618789792 2023-01-23 22:31:38.731298: step: 1370/1545, loss: 7.39628667361103e-05 2023-01-23 22:31:39.586681: step: 1372/1545, loss: 2.5009734599734657e-05 2023-01-23 22:31:40.424906: step: 1374/1545, loss: 3.287627623649314e-05 2023-01-23 22:31:41.400622: step: 1376/1545, loss: 0.0036637841258198023 2023-01-23 22:31:42.285397: step: 1378/1545, loss: 0.0017011214513331652 2023-01-23 22:31:43.143394: step: 1380/1545, loss: 0.0006975936703383923 2023-01-23 22:31:44.039816: step: 1382/1545, loss: 0.003990189637988806 2023-01-23 22:31:44.899456: step: 1384/1545, loss: 0.06649857014417648 2023-01-23 22:31:45.785671: step: 1386/1545, loss: 0.005392235238105059 2023-01-23 22:31:46.648240: step: 1388/1545, loss: 0.36684170365333557 2023-01-23 22:31:47.518901: step: 1390/1545, loss: 0.16258268058300018 2023-01-23 22:31:48.422720: step: 1392/1545, loss: 2.3362215870292857e-05 2023-01-23 22:31:49.296976: step: 1394/1545, loss: 0.0006286579300649464 2023-01-23 22:31:50.176226: step: 1396/1545, loss: 0.00032395901507698 2023-01-23 22:31:51.013896: step: 1398/1545, loss: 0.25408002734184265 2023-01-23 22:31:51.925467: step: 1400/1545, loss: 5.914867142564617e-05 2023-01-23 22:31:52.810906: step: 1402/1545, loss: 0.00044998948578722775 2023-01-23 22:31:53.789876: step: 1404/1545, loss: 1.012026405078359e-05 2023-01-23 22:31:54.691083: step: 1406/1545, loss: 0.09456826746463776 2023-01-23 22:31:55.529730: step: 1408/1545, loss: 0.00010921017383225262 2023-01-23 22:31:56.460750: step: 1410/1545, loss: 0.002315154066309333 2023-01-23 22:31:57.326298: step: 1412/1545, loss: 0.00011941701086470857 2023-01-23 22:31:58.206562: step: 1414/1545, loss: 0.00013520345964934677 2023-01-23 22:31:59.069801: step: 1416/1545, loss: 2.1478033886523917e-05 2023-01-23 22:31:59.936504: step: 1418/1545, loss: 0.04547473415732384 2023-01-23 22:32:00.815812: step: 1420/1545, loss: 0.00018469992210157216 2023-01-23 22:32:01.699803: step: 1422/1545, loss: 0.11958513408899307 2023-01-23 22:32:02.545925: step: 1424/1545, loss: 1.973666985577438e-05 2023-01-23 22:32:03.496785: step: 1426/1545, loss: 0.022508133202791214 2023-01-23 22:32:04.402979: step: 1428/1545, loss: 0.5243561267852783 2023-01-23 22:32:05.346791: step: 1430/1545, loss: 0.16041259467601776 2023-01-23 22:32:06.195040: step: 1432/1545, loss: 0.3311472535133362 2023-01-23 22:32:07.069375: step: 1434/1545, loss: 0.0007164220442064106 2023-01-23 22:32:07.956685: step: 1436/1545, loss: 0.0001724639005260542 2023-01-23 22:32:08.822869: step: 1438/1545, loss: 0.00013787891657557338 2023-01-23 22:32:09.683155: step: 1440/1545, loss: 0.037615515291690826 2023-01-23 22:32:10.607996: step: 1442/1545, loss: 0.00043778863619081676 2023-01-23 22:32:11.485510: step: 1444/1545, loss: 0.0011123181320726871 2023-01-23 22:32:12.370514: step: 1446/1545, loss: 0.28949546813964844 2023-01-23 22:32:13.226071: step: 1448/1545, loss: 0.0002454809728078544 2023-01-23 22:32:14.133977: step: 1450/1545, loss: 0.21452060341835022 2023-01-23 22:32:15.075172: step: 1452/1545, loss: 0.22239136695861816 2023-01-23 22:32:15.937449: step: 1454/1545, loss: 0.002359638689085841 2023-01-23 22:32:16.812590: step: 1456/1545, loss: 0.008708319626748562 2023-01-23 22:32:17.708019: step: 1458/1545, loss: 0.0005789936985820532 2023-01-23 22:32:18.641405: step: 1460/1545, loss: 0.007571665104478598 2023-01-23 22:32:19.591225: step: 1462/1545, loss: 0.0009469827637076378 2023-01-23 22:32:20.448125: step: 1464/1545, loss: 0.0007178204250521958 2023-01-23 22:32:21.309472: step: 1466/1545, loss: 6.294420745689422e-05 2023-01-23 22:32:22.185075: step: 1468/1545, loss: 0.00011882781836902723 2023-01-23 22:32:23.157874: step: 1470/1545, loss: 0.0002749448758549988 2023-01-23 22:32:24.026777: step: 1472/1545, loss: 0.3882274031639099 2023-01-23 22:32:24.901290: step: 1474/1545, loss: 0.00027287035482004285 2023-01-23 22:32:25.768563: step: 1476/1545, loss: 0.0002072616625810042 2023-01-23 22:32:26.634953: step: 1478/1545, loss: 0.00016506531392224133 2023-01-23 22:32:27.542136: step: 1480/1545, loss: 0.002142037032172084 2023-01-23 22:32:28.384969: step: 1482/1545, loss: 0.04793247580528259 2023-01-23 22:32:29.370181: step: 1484/1545, loss: 0.3050287961959839 2023-01-23 22:32:30.211198: step: 1486/1545, loss: 4.7493973397649825e-05 2023-01-23 22:32:31.073481: step: 1488/1545, loss: 0.00020003729150630534 2023-01-23 22:32:31.950411: step: 1490/1545, loss: 0.5680691003799438 2023-01-23 22:32:32.798836: step: 1492/1545, loss: 0.025426706299185753 2023-01-23 22:32:33.690706: step: 1494/1545, loss: 0.859573245048523 2023-01-23 22:32:34.612747: step: 1496/1545, loss: 0.002694252412766218 2023-01-23 22:32:35.465295: step: 1498/1545, loss: 3.244148683734238e-05 2023-01-23 22:32:36.367324: step: 1500/1545, loss: 0.00018398450629319996 2023-01-23 22:32:37.240990: step: 1502/1545, loss: 0.00012926921772304922 2023-01-23 22:32:38.120778: step: 1504/1545, loss: 0.03829741105437279 2023-01-23 22:32:39.029172: step: 1506/1545, loss: 0.01787961833178997 2023-01-23 22:32:39.841851: step: 1508/1545, loss: 0.016375144943594933 2023-01-23 22:32:40.701869: step: 1510/1545, loss: 0.031128693372011185 2023-01-23 22:32:41.561309: step: 1512/1545, loss: 0.10720283538103104 2023-01-23 22:32:42.471222: step: 1514/1545, loss: 9.772418707143515e-05 2023-01-23 22:32:43.352213: step: 1516/1545, loss: 0.0027355756610631943 2023-01-23 22:32:44.207709: step: 1518/1545, loss: 0.13044731318950653 2023-01-23 22:32:45.069564: step: 1520/1545, loss: 0.000309167051455006 2023-01-23 22:32:45.902658: step: 1522/1545, loss: 0.00434473343193531 2023-01-23 22:32:46.822810: step: 1524/1545, loss: 0.29260075092315674 2023-01-23 22:32:47.711371: step: 1526/1545, loss: 0.020939715206623077 2023-01-23 22:32:48.587198: step: 1528/1545, loss: 0.00042898920946754515 2023-01-23 22:32:49.497821: step: 1530/1545, loss: 0.5002787113189697 2023-01-23 22:32:50.374986: step: 1532/1545, loss: 0.0010419652098789811 2023-01-23 22:32:51.245271: step: 1534/1545, loss: 0.01242890115827322 2023-01-23 22:32:52.158118: step: 1536/1545, loss: 0.0026841263752430677 2023-01-23 22:32:53.076744: step: 1538/1545, loss: 0.02191931940615177 2023-01-23 22:32:53.924201: step: 1540/1545, loss: 0.0006836995016783476 2023-01-23 22:32:54.825068: step: 1542/1545, loss: 0.14413011074066162 2023-01-23 22:32:55.681036: step: 1544/1545, loss: 0.05726546421647072 2023-01-23 22:32:56.545917: step: 1546/1545, loss: 0.000844467431306839 2023-01-23 22:32:57.407618: step: 1548/1545, loss: 0.0006245093536563218 2023-01-23 22:32:58.280751: step: 1550/1545, loss: 0.00024916441179811954 2023-01-23 22:32:59.164787: step: 1552/1545, loss: 0.0002142070879926905 2023-01-23 22:33:00.058712: step: 1554/1545, loss: 0.0005630654632113874 2023-01-23 22:33:00.955622: step: 1556/1545, loss: 0.019204668700695038 2023-01-23 22:33:01.867236: step: 1558/1545, loss: 0.01585284061729908 2023-01-23 22:33:02.779711: step: 1560/1545, loss: 0.03786442428827286 2023-01-23 22:33:03.690932: step: 1562/1545, loss: 0.00012314644118305296 2023-01-23 22:33:04.573822: step: 1564/1545, loss: 0.010425971820950508 2023-01-23 22:33:05.499365: step: 1566/1545, loss: 5.350027640815824e-05 2023-01-23 22:33:06.379206: step: 1568/1545, loss: 4.726258703158237e-05 2023-01-23 22:33:07.225769: step: 1570/1545, loss: -1.635581247683149e-05 2023-01-23 22:33:08.124316: step: 1572/1545, loss: 0.2478187382221222 2023-01-23 22:33:09.024768: step: 1574/1545, loss: 1.7502775335742626e-06 2023-01-23 22:33:09.887311: step: 1576/1545, loss: 3.060773087781854e-05 2023-01-23 22:33:10.819404: step: 1578/1545, loss: 0.0010060729691758752 2023-01-23 22:33:11.710852: step: 1580/1545, loss: 0.0002305645466549322 2023-01-23 22:33:12.655253: step: 1582/1545, loss: 0.26420244574546814 2023-01-23 22:33:13.536067: step: 1584/1545, loss: 2.8705560907837935e-05 2023-01-23 22:33:14.382830: step: 1586/1545, loss: 0.0005832122405990958 2023-01-23 22:33:15.250969: step: 1588/1545, loss: 9.852808580035344e-05 2023-01-23 22:33:16.135066: step: 1590/1545, loss: 6.736739305779338e-05 2023-01-23 22:33:16.992563: step: 1592/1545, loss: 1.56722599058412e-05 2023-01-23 22:33:17.872770: step: 1594/1545, loss: 0.006388334557414055 2023-01-23 22:33:18.737955: step: 1596/1545, loss: 0.06838081777095795 2023-01-23 22:33:19.688779: step: 1598/1545, loss: 0.01034806203097105 2023-01-23 22:33:20.605386: step: 1600/1545, loss: 0.0031284773722290993 2023-01-23 22:33:21.435405: step: 1602/1545, loss: 0.0013034016592428088 2023-01-23 22:33:22.379321: step: 1604/1545, loss: 0.5606138706207275 2023-01-23 22:33:23.297415: step: 1606/1545, loss: 0.0010272478684782982 2023-01-23 22:33:24.153323: step: 1608/1545, loss: 3.0553339911421062e-06 2023-01-23 22:33:25.032163: step: 1610/1545, loss: 0.20231249928474426 2023-01-23 22:33:25.931883: step: 1612/1545, loss: 0.008763966150581837 2023-01-23 22:33:26.779524: step: 1614/1545, loss: 0.028000356629490852 2023-01-23 22:33:27.682932: step: 1616/1545, loss: 0.41070759296417236 2023-01-23 22:33:28.587790: step: 1618/1545, loss: 0.00014425840345211327 2023-01-23 22:33:29.537083: step: 1620/1545, loss: 0.0030026021413505077 2023-01-23 22:33:30.474433: step: 1622/1545, loss: 0.014453931711614132 2023-01-23 22:33:31.344929: step: 1624/1545, loss: 0.023014817386865616 2023-01-23 22:33:32.236453: step: 1626/1545, loss: 0.00010906028182944283 2023-01-23 22:33:33.101826: step: 1628/1545, loss: -2.3654600227018818e-05 2023-01-23 22:33:33.962898: step: 1630/1545, loss: 0.028526803478598595 2023-01-23 22:33:34.795125: step: 1632/1545, loss: 6.527749064844102e-05 2023-01-23 22:33:35.718901: step: 1634/1545, loss: 0.0433846153318882 2023-01-23 22:33:36.569959: step: 1636/1545, loss: 0.00028820239822380245 2023-01-23 22:33:37.495894: step: 1638/1545, loss: 8.413382602157071e-05 2023-01-23 22:33:38.353373: step: 1640/1545, loss: 0.0038680394645780325 2023-01-23 22:33:39.215225: step: 1642/1545, loss: 0.03118523769080639 2023-01-23 22:33:40.082721: step: 1644/1545, loss: 0.0026980871334671974 2023-01-23 22:33:40.992526: step: 1646/1545, loss: 4.811670078197494e-05 2023-01-23 22:33:41.877247: step: 1648/1545, loss: 0.00016018797759898007 2023-01-23 22:33:42.753995: step: 1650/1545, loss: -2.1414960428955965e-05 2023-01-23 22:33:43.716346: step: 1652/1545, loss: 0.12218461185693741 2023-01-23 22:33:44.593876: step: 1654/1545, loss: 0.002899972489103675 2023-01-23 22:33:45.480622: step: 1656/1545, loss: 0.011535107158124447 2023-01-23 22:33:46.352322: step: 1658/1545, loss: 0.8654152750968933 2023-01-23 22:33:47.254401: step: 1660/1545, loss: 2.5351759177283384e-05 2023-01-23 22:33:48.151651: step: 1662/1545, loss: 0.1579189896583557 2023-01-23 22:33:49.052767: step: 1664/1545, loss: 0.009178047999739647 2023-01-23 22:33:49.906178: step: 1666/1545, loss: 0.0006156552699394524 2023-01-23 22:33:50.829360: step: 1668/1545, loss: 6.561924237757921e-05 2023-01-23 22:33:51.690849: step: 1670/1545, loss: 3.806703170994297e-05 2023-01-23 22:33:52.605033: step: 1672/1545, loss: 7.298315176740289e-05 2023-01-23 22:33:53.466396: step: 1674/1545, loss: 0.034365661442279816 2023-01-23 22:33:54.321108: step: 1676/1545, loss: 2.9601154892588966e-05 2023-01-23 22:33:55.176150: step: 1678/1545, loss: 0.07614319026470184 2023-01-23 22:33:56.116759: step: 1680/1545, loss: 0.0006644628592766821 2023-01-23 22:33:56.982711: step: 1682/1545, loss: -2.531856625864748e-05 2023-01-23 22:33:57.859811: step: 1684/1545, loss: 0.0003466305206529796 2023-01-23 22:33:58.740582: step: 1686/1545, loss: 0.00039382168324664235 2023-01-23 22:33:59.658173: step: 1688/1545, loss: 0.032115694135427475 2023-01-23 22:34:00.538384: step: 1690/1545, loss: 0.0036762715317308903 2023-01-23 22:34:01.392572: step: 1692/1545, loss: 0.0023359202314168215 2023-01-23 22:34:02.257795: step: 1694/1545, loss: 5.042701741331257e-05 2023-01-23 22:34:03.112183: step: 1696/1545, loss: 5.2065552154090255e-05 2023-01-23 22:34:03.995999: step: 1698/1545, loss: 3.849681525025517e-05 2023-01-23 22:34:04.894023: step: 1700/1545, loss: 0.0002637992729432881 2023-01-23 22:34:05.776008: step: 1702/1545, loss: 0.24554108083248138 2023-01-23 22:34:06.715833: step: 1704/1545, loss: 0.002866339171305299 2023-01-23 22:34:07.607804: step: 1706/1545, loss: 0.006338902749121189 2023-01-23 22:34:08.474221: step: 1708/1545, loss: 5.688400051440112e-06 2023-01-23 22:34:09.350852: step: 1710/1545, loss: 0.02977360226213932 2023-01-23 22:34:10.196730: step: 1712/1545, loss: 0.08827332407236099 2023-01-23 22:34:11.096951: step: 1714/1545, loss: 0.00015478544810321182 2023-01-23 22:34:11.967748: step: 1716/1545, loss: 1.7173559172078967e-05 2023-01-23 22:34:12.799421: step: 1718/1545, loss: 0.0002442641125526279 2023-01-23 22:34:13.648381: step: 1720/1545, loss: 0.0004691146605182439 2023-01-23 22:34:14.511107: step: 1722/1545, loss: 0.15047067403793335 2023-01-23 22:34:15.377376: step: 1724/1545, loss: 0.00020094051433261484 2023-01-23 22:34:16.272775: step: 1726/1545, loss: 0.0003207289846614003 2023-01-23 22:34:17.093329: step: 1728/1545, loss: 1.4121829735813662e-05 2023-01-23 22:34:17.966524: step: 1730/1545, loss: 0.00015523808542639017 2023-01-23 22:34:18.812891: step: 1732/1545, loss: 0.0023729947861284018 2023-01-23 22:34:19.709609: step: 1734/1545, loss: 0.0037504113279283047 2023-01-23 22:34:20.604930: step: 1736/1545, loss: 0.0524805448949337 2023-01-23 22:34:21.502366: step: 1738/1545, loss: 0.006925027817487717 2023-01-23 22:34:22.370156: step: 1740/1545, loss: 0.3566035032272339 2023-01-23 22:34:23.262709: step: 1742/1545, loss: 0.03443865478038788 2023-01-23 22:34:24.224152: step: 1744/1545, loss: -3.3013930078595877e-06 2023-01-23 22:34:25.110850: step: 1746/1545, loss: 3.1667100302001927e-06 2023-01-23 22:34:25.958310: step: 1748/1545, loss: 0.0008360955398529768 2023-01-23 22:34:26.809082: step: 1750/1545, loss: 0.004468121565878391 2023-01-23 22:34:27.690717: step: 1752/1545, loss: 2.817213135131169e-05 2023-01-23 22:34:28.508895: step: 1754/1545, loss: 0.02763008512556553 2023-01-23 22:34:29.396698: step: 1756/1545, loss: 0.00482040923088789 2023-01-23 22:34:30.258011: step: 1758/1545, loss: 2.1513793399208225e-05 2023-01-23 22:34:31.201779: step: 1760/1545, loss: 1.4521659068122972e-05 2023-01-23 22:34:32.074526: step: 1762/1545, loss: 1.6204267012653872e-05 2023-01-23 22:34:32.971448: step: 1764/1545, loss: 0.05353369936347008 2023-01-23 22:34:33.860364: step: 1766/1545, loss: -5.77233959120349e-06 2023-01-23 22:34:34.730213: step: 1768/1545, loss: 1.3351439520192798e-05 2023-01-23 22:34:35.600670: step: 1770/1545, loss: 0.00036453158827498555 2023-01-23 22:34:36.511191: step: 1772/1545, loss: 0.018179751932621002 2023-01-23 22:34:37.403046: step: 1774/1545, loss: 3.0017046810826287e-05 2023-01-23 22:34:38.270837: step: 1776/1545, loss: 8.452415931969881e-05 2023-01-23 22:34:39.116959: step: 1778/1545, loss: 0.0008776594186201692 2023-01-23 22:34:39.975410: step: 1780/1545, loss: 3.053904219996184e-05 2023-01-23 22:34:40.820500: step: 1782/1545, loss: 0.0005372604355216026 2023-01-23 22:34:41.679653: step: 1784/1545, loss: 0.00015809638716746122 2023-01-23 22:34:42.565719: step: 1786/1545, loss: 3.0469378543784842e-05 2023-01-23 22:34:43.427348: step: 1788/1545, loss: 5.86599089729134e-05 2023-01-23 22:34:44.278989: step: 1790/1545, loss: 0.03318503871560097 2023-01-23 22:34:45.127259: step: 1792/1545, loss: 3.62521423085127e-05 2023-01-23 22:34:46.011865: step: 1794/1545, loss: 0.07926163822412491 2023-01-23 22:34:46.974801: step: 1796/1545, loss: 0.04883149266242981 2023-01-23 22:34:47.836699: step: 1798/1545, loss: 0.00010285843745805323 2023-01-23 22:34:48.754044: step: 1800/1545, loss: 0.003859288292005658 2023-01-23 22:34:49.653245: step: 1802/1545, loss: 2.848142321454361e-05 2023-01-23 22:34:50.578897: step: 1804/1545, loss: 0.0003360332630109042 2023-01-23 22:34:51.566615: step: 1806/1545, loss: 8.02616195869632e-05 2023-01-23 22:34:52.481988: step: 1808/1545, loss: 0.0002571625227574259 2023-01-23 22:34:53.371383: step: 1810/1545, loss: 0.00024872669018805027 2023-01-23 22:34:54.213602: step: 1812/1545, loss: 0.0018435445381328464 2023-01-23 22:34:55.104458: step: 1814/1545, loss: 0.3557637631893158 2023-01-23 22:34:56.008506: step: 1816/1545, loss: 0.4187035858631134 2023-01-23 22:34:56.863724: step: 1818/1545, loss: 0.00017643003957346082 2023-01-23 22:34:57.719795: step: 1820/1545, loss: 6.561577902175486e-05 2023-01-23 22:34:58.565734: step: 1822/1545, loss: 0.00013224632130004466 2023-01-23 22:34:59.436596: step: 1824/1545, loss: 0.00011413246829761192 2023-01-23 22:35:00.268198: step: 1826/1545, loss: 0.001479840255342424 2023-01-23 22:35:01.171222: step: 1828/1545, loss: 0.00016811017121654004 2023-01-23 22:35:02.024753: step: 1830/1545, loss: 0.005101304966956377 2023-01-23 22:35:02.909977: step: 1832/1545, loss: 0.0029595617670565844 2023-01-23 22:35:03.749353: step: 1834/1545, loss: 2.7642010536510497e-05 2023-01-23 22:35:04.611087: step: 1836/1545, loss: 0.0024516405537724495 2023-01-23 22:35:05.475938: step: 1838/1545, loss: 0.00047209305921569467 2023-01-23 22:35:06.361763: step: 1840/1545, loss: 0.00012777703523170203 2023-01-23 22:35:07.238323: step: 1842/1545, loss: 0.334393709897995 2023-01-23 22:35:08.102806: step: 1844/1545, loss: 0.0012396472739055753 2023-01-23 22:35:08.989446: step: 1846/1545, loss: 0.013231467455625534 2023-01-23 22:35:09.942919: step: 1848/1545, loss: 0.00023416493786498904 2023-01-23 22:35:10.818474: step: 1850/1545, loss: 3.8539837987627834e-05 2023-01-23 22:35:11.744494: step: 1852/1545, loss: 0.00016481036436744034 2023-01-23 22:35:12.625243: step: 1854/1545, loss: 0.005749441683292389 2023-01-23 22:35:13.484847: step: 1856/1545, loss: 0.00023035255435388535 2023-01-23 22:35:14.358681: step: 1858/1545, loss: 2.811176273098681e-05 2023-01-23 22:35:15.230226: step: 1860/1545, loss: 7.410766556859016e-05 2023-01-23 22:35:16.088294: step: 1862/1545, loss: 0.00035583923454396427 2023-01-23 22:35:16.958458: step: 1864/1545, loss: 0.16176921129226685 2023-01-23 22:35:17.795705: step: 1866/1545, loss: -5.802531177323544e-06 2023-01-23 22:35:18.685181: step: 1868/1545, loss: 0.0007089314167387784 2023-01-23 22:35:19.593501: step: 1870/1545, loss: 0.000281681859632954 2023-01-23 22:35:20.537673: step: 1872/1545, loss: 0.00021184980869293213 2023-01-23 22:35:21.430772: step: 1874/1545, loss: 7.983528485056013e-05 2023-01-23 22:35:22.372950: step: 1876/1545, loss: 0.012403545901179314 2023-01-23 22:35:23.228618: step: 1878/1545, loss: 0.0009072052780538797 2023-01-23 22:35:24.075183: step: 1880/1545, loss: 0.0003293124318588525 2023-01-23 22:35:24.942627: step: 1882/1545, loss: 7.014192669885233e-05 2023-01-23 22:35:25.768373: step: 1884/1545, loss: 5.566248364630155e-05 2023-01-23 22:35:26.630939: step: 1886/1545, loss: 0.001483955536969006 2023-01-23 22:35:27.479914: step: 1888/1545, loss: 0.0014311640989035368 2023-01-23 22:35:28.324126: step: 1890/1545, loss: 3.8009038689779118e-06 2023-01-23 22:35:29.225767: step: 1892/1545, loss: 0.0001931930601131171 2023-01-23 22:35:30.152642: step: 1894/1545, loss: 0.32314053177833557 2023-01-23 22:35:31.065921: step: 1896/1545, loss: 0.00030890811467543244 2023-01-23 22:35:31.932631: step: 1898/1545, loss: 0.002676859498023987 2023-01-23 22:35:32.807293: step: 1900/1545, loss: 0.06740807741880417 2023-01-23 22:35:33.660002: step: 1902/1545, loss: 8.613004320068285e-05 2023-01-23 22:35:34.533906: step: 1904/1545, loss: 0.013845265842974186 2023-01-23 22:35:35.450873: step: 1906/1545, loss: 0.03505535423755646 2023-01-23 22:35:36.319522: step: 1908/1545, loss: 0.08151888847351074 2023-01-23 22:35:37.175132: step: 1910/1545, loss: 2.909004433604423e-05 2023-01-23 22:35:38.051874: step: 1912/1545, loss: 0.006111910101026297 2023-01-23 22:35:38.917570: step: 1914/1545, loss: 0.0009385677985846996 2023-01-23 22:35:39.822845: step: 1916/1545, loss: 0.003149611409753561 2023-01-23 22:35:40.702013: step: 1918/1545, loss: 0.0007431750418618321 2023-01-23 22:35:41.560036: step: 1920/1545, loss: 0.002273047110065818 2023-01-23 22:35:42.419320: step: 1922/1545, loss: 0.13144651055335999 2023-01-23 22:35:43.276192: step: 1924/1545, loss: 0.09433155506849289 2023-01-23 22:35:44.130544: step: 1926/1545, loss: 0.019667785614728928 2023-01-23 22:35:44.961716: step: 1928/1545, loss: 7.622285193065181e-05 2023-01-23 22:35:45.816001: step: 1930/1545, loss: 0.17750120162963867 2023-01-23 22:35:46.687064: step: 1932/1545, loss: 0.0003581415512599051 2023-01-23 22:35:47.569373: step: 1934/1545, loss: 0.00031829962972551584 2023-01-23 22:35:48.401870: step: 1936/1545, loss: 0.010088483802974224 2023-01-23 22:35:49.282127: step: 1938/1545, loss: 0.001556705217808485 2023-01-23 22:35:50.202873: step: 1940/1545, loss: 0.1361580640077591 2023-01-23 22:35:51.139097: step: 1942/1545, loss: 0.2522618770599365 2023-01-23 22:35:52.022083: step: 1944/1545, loss: 0.009469208307564259 2023-01-23 22:35:52.927104: step: 1946/1545, loss: 0.0034618156496435404 2023-01-23 22:35:53.802157: step: 1948/1545, loss: 0.0020359137561172247 2023-01-23 22:35:54.680421: step: 1950/1545, loss: 0.06337983906269073 2023-01-23 22:35:55.554015: step: 1952/1545, loss: 0.0025159353390336037 2023-01-23 22:35:56.415268: step: 1954/1545, loss: 0.028715400025248528 2023-01-23 22:35:57.278559: step: 1956/1545, loss: 0.0016259521944448352 2023-01-23 22:35:58.186837: step: 1958/1545, loss: 0.00046398252015933394 2023-01-23 22:35:59.040883: step: 1960/1545, loss: 0.02715831995010376 2023-01-23 22:35:59.903708: step: 1962/1545, loss: 0.0003761947446037084 2023-01-23 22:36:00.782055: step: 1964/1545, loss: 0.0008702374179847538 2023-01-23 22:36:01.657635: step: 1966/1545, loss: 4.463748155103531e-06 2023-01-23 22:36:02.561046: step: 1968/1545, loss: 0.016380976885557175 2023-01-23 22:36:03.460192: step: 1970/1545, loss: 2.7251840947428718e-05 2023-01-23 22:36:04.324384: step: 1972/1545, loss: 0.002198416506871581 2023-01-23 22:36:05.213641: step: 1974/1545, loss: 6.0257629229454324e-05 2023-01-23 22:36:06.078175: step: 1976/1545, loss: 0.05258198454976082 2023-01-23 22:36:06.944538: step: 1978/1545, loss: 0.2494598627090454 2023-01-23 22:36:07.778716: step: 1980/1545, loss: 0.00016680658154655248 2023-01-23 22:36:08.639883: step: 1982/1545, loss: 9.762666013557464e-05 2023-01-23 22:36:09.527331: step: 1984/1545, loss: 0.0706869438290596 2023-01-23 22:36:10.443221: step: 1986/1545, loss: 0.00017642916645854712 2023-01-23 22:36:11.302565: step: 1988/1545, loss: 0.09731045365333557 2023-01-23 22:36:12.163194: step: 1990/1545, loss: 0.002619960578158498 2023-01-23 22:36:13.054620: step: 1992/1545, loss: 0.012482116930186749 2023-01-23 22:36:13.946858: step: 1994/1545, loss: 0.0002752254658844322 2023-01-23 22:36:14.799094: step: 1996/1545, loss: 0.00046951640979386866 2023-01-23 22:36:15.696972: step: 1998/1545, loss: 8.463759877486154e-05 2023-01-23 22:36:16.583244: step: 2000/1545, loss: 0.21430623531341553 2023-01-23 22:36:17.453296: step: 2002/1545, loss: 0.06224345415830612 2023-01-23 22:36:18.318352: step: 2004/1545, loss: 0.08058056235313416 2023-01-23 22:36:19.240520: step: 2006/1545, loss: 9.516304271528497e-05 2023-01-23 22:36:20.112877: step: 2008/1545, loss: 6.891421071486548e-05 2023-01-23 22:36:20.990707: step: 2010/1545, loss: 0.004653213545680046 2023-01-23 22:36:21.857427: step: 2012/1545, loss: -2.156816663045902e-06 2023-01-23 22:36:22.716530: step: 2014/1545, loss: 0.0005941777490079403 2023-01-23 22:36:23.594019: step: 2016/1545, loss: 0.17234690487384796 2023-01-23 22:36:24.456350: step: 2018/1545, loss: 0.0006252400926314294 2023-01-23 22:36:25.349609: step: 2020/1545, loss: 2.144022801076062e-05 2023-01-23 22:36:26.223514: step: 2022/1545, loss: 0.0592040978372097 2023-01-23 22:36:27.135288: step: 2024/1545, loss: 0.001675598556175828 2023-01-23 22:36:28.019249: step: 2026/1545, loss: 0.012918228283524513 2023-01-23 22:36:28.849582: step: 2028/1545, loss: 0.00024044513702392578 2023-01-23 22:36:29.757588: step: 2030/1545, loss: 6.932516043889336e-06 2023-01-23 22:36:30.709268: step: 2032/1545, loss: 0.00011952296335948631 2023-01-23 22:36:31.604998: step: 2034/1545, loss: 0.07238505780696869 2023-01-23 22:36:32.457186: step: 2036/1545, loss: 0.030689198523759842 2023-01-23 22:36:33.302538: step: 2038/1545, loss: 0.18750505149364471 2023-01-23 22:36:34.196476: step: 2040/1545, loss: 0.00055175821762532 2023-01-23 22:36:35.068571: step: 2042/1545, loss: 9.509577648714185e-05 2023-01-23 22:36:35.928238: step: 2044/1545, loss: 0.0004883631481789052 2023-01-23 22:36:36.788911: step: 2046/1545, loss: 0.0005171807715669274 2023-01-23 22:36:37.650564: step: 2048/1545, loss: 0.0004853254067711532 2023-01-23 22:36:38.523152: step: 2050/1545, loss: 0.00038540095556527376 2023-01-23 22:36:39.449715: step: 2052/1545, loss: 1.4389803409576416 2023-01-23 22:36:40.315904: step: 2054/1545, loss: 0.9426289200782776 2023-01-23 22:36:41.201319: step: 2056/1545, loss: 0.0013538816710934043 2023-01-23 22:36:42.065694: step: 2058/1545, loss: 0.23275525867938995 2023-01-23 22:36:42.957455: step: 2060/1545, loss: 0.0028579197824001312 2023-01-23 22:36:43.815908: step: 2062/1545, loss: 0.00023657041310798377 2023-01-23 22:36:44.665261: step: 2064/1545, loss: 0.015502224676311016 2023-01-23 22:36:45.611622: step: 2066/1545, loss: 0.08503462374210358 2023-01-23 22:36:46.505427: step: 2068/1545, loss: 0.0010401742765679955 2023-01-23 22:36:47.374384: step: 2070/1545, loss: 0.003624606877565384 2023-01-23 22:36:48.233601: step: 2072/1545, loss: 0.16239500045776367 2023-01-23 22:36:49.143098: step: 2074/1545, loss: 0.057876620441675186 2023-01-23 22:36:50.003139: step: 2076/1545, loss: 0.0001384930219501257 2023-01-23 22:36:50.858894: step: 2078/1545, loss: 0.02558942325413227 2023-01-23 22:36:51.732719: step: 2080/1545, loss: 0.017746923491358757 2023-01-23 22:36:52.642706: step: 2082/1545, loss: 0.6596799492835999 2023-01-23 22:36:53.507414: step: 2084/1545, loss: 0.02322039008140564 2023-01-23 22:36:54.439197: step: 2086/1545, loss: 0.0005109205958433449 2023-01-23 22:36:55.293944: step: 2088/1545, loss: 0.00011832609015982598 2023-01-23 22:36:56.158533: step: 2090/1545, loss: 6.643532833550125e-05 2023-01-23 22:36:57.029854: step: 2092/1545, loss: 0.0031169913709163666 2023-01-23 22:36:57.944331: step: 2094/1545, loss: 0.061584580689668655 2023-01-23 22:36:58.864932: step: 2096/1545, loss: 0.009531700983643532 2023-01-23 22:36:59.735340: step: 2098/1545, loss: 0.1497322916984558 2023-01-23 22:37:00.611283: step: 2100/1545, loss: 0.0005866533610969782 2023-01-23 22:37:01.512144: step: 2102/1545, loss: 0.0002819733344949782 2023-01-23 22:37:02.371547: step: 2104/1545, loss: 0.11717362701892853 2023-01-23 22:37:03.225142: step: 2106/1545, loss: 0.00021779470262117684 2023-01-23 22:37:04.070582: step: 2108/1545, loss: 0.00018733323668129742 2023-01-23 22:37:04.935381: step: 2110/1545, loss: 0.0004478302726056427 2023-01-23 22:37:05.784860: step: 2112/1545, loss: 0.0012541803298518062 2023-01-23 22:37:06.661165: step: 2114/1545, loss: 0.13227488100528717 2023-01-23 22:37:07.506006: step: 2116/1545, loss: 0.0001637639506952837 2023-01-23 22:37:08.408276: step: 2118/1545, loss: 0.0012177075259387493 2023-01-23 22:37:09.319436: step: 2120/1545, loss: 0.34188491106033325 2023-01-23 22:37:10.224241: step: 2122/1545, loss: 0.0004326603375375271 2023-01-23 22:37:11.113324: step: 2124/1545, loss: 0.0007997058564797044 2023-01-23 22:37:12.050271: step: 2126/1545, loss: 0.41328737139701843 2023-01-23 22:37:12.924869: step: 2128/1545, loss: 0.0009873162489384413 2023-01-23 22:37:13.787990: step: 2130/1545, loss: 0.002947867615148425 2023-01-23 22:37:14.627703: step: 2132/1545, loss: 0.0021965426858514547 2023-01-23 22:37:15.492362: step: 2134/1545, loss: 0.08148552477359772 2023-01-23 22:37:16.389411: step: 2136/1545, loss: 0.0029682423919439316 2023-01-23 22:37:17.299745: step: 2138/1545, loss: 0.0696929544210434 2023-01-23 22:37:18.207824: step: 2140/1545, loss: 0.00018038135021924973 2023-01-23 22:37:19.106675: step: 2142/1545, loss: 0.0017941789701581001 2023-01-23 22:37:19.950021: step: 2144/1545, loss: 0.004166846629232168 2023-01-23 22:37:20.790083: step: 2146/1545, loss: 0.023579513654112816 2023-01-23 22:37:21.675293: step: 2148/1545, loss: 0.0007703455630689859 2023-01-23 22:37:22.600319: step: 2150/1545, loss: 0.001508733257651329 2023-01-23 22:37:23.493812: step: 2152/1545, loss: 2.3472588509321213e-05 2023-01-23 22:37:24.421106: step: 2154/1545, loss: 0.0033874802757054567 2023-01-23 22:37:25.293239: step: 2156/1545, loss: 7.691160135436803e-05 2023-01-23 22:37:26.178221: step: 2158/1545, loss: 0.00024265042156912386 2023-01-23 22:37:27.062529: step: 2160/1545, loss: 0.0034524265211075544 2023-01-23 22:37:27.993049: step: 2162/1545, loss: 0.019009267911314964 2023-01-23 22:37:28.881700: step: 2164/1545, loss: 0.0010493643349036574 2023-01-23 22:37:29.750997: step: 2166/1545, loss: 0.00036373623879626393 2023-01-23 22:37:30.663458: step: 2168/1545, loss: 0.12337472289800644 2023-01-23 22:37:31.507942: step: 2170/1545, loss: 0.00011110474588349462 2023-01-23 22:37:32.437164: step: 2172/1545, loss: 0.0001850925327744335 2023-01-23 22:37:33.294018: step: 2174/1545, loss: 0.0003241662634536624 2023-01-23 22:37:34.132330: step: 2176/1545, loss: 0.00041498770588077605 2023-01-23 22:37:35.013876: step: 2178/1545, loss: 0.15305811166763306 2023-01-23 22:37:35.900587: step: 2180/1545, loss: 0.0004766920756082982 2023-01-23 22:37:36.788103: step: 2182/1545, loss: 0.005627399310469627 2023-01-23 22:37:37.641486: step: 2184/1545, loss: 0.0007315233233384788 2023-01-23 22:37:38.516540: step: 2186/1545, loss: 0.0019178746733814478 2023-01-23 22:37:39.392751: step: 2188/1545, loss: 0.35913607478141785 2023-01-23 22:37:40.353394: step: 2190/1545, loss: 0.0007329994114115834 2023-01-23 22:37:41.232339: step: 2192/1545, loss: 0.0020971521735191345 2023-01-23 22:37:42.112856: step: 2194/1545, loss: 0.0005995408282615244 2023-01-23 22:37:42.989062: step: 2196/1545, loss: 0.006834546569734812 2023-01-23 22:37:43.856446: step: 2198/1545, loss: 0.0006270431913435459 2023-01-23 22:37:44.746904: step: 2200/1545, loss: 0.0014687161892652512 2023-01-23 22:37:45.621990: step: 2202/1545, loss: 0.01638469658792019 2023-01-23 22:37:46.438581: step: 2204/1545, loss: 0.0005660118767991662 2023-01-23 22:37:47.285351: step: 2206/1545, loss: 0.0007324559846892953 2023-01-23 22:37:48.153485: step: 2208/1545, loss: 0.0032113732304424047 2023-01-23 22:37:48.985685: step: 2210/1545, loss: 0.019556794315576553 2023-01-23 22:37:49.855033: step: 2212/1545, loss: 0.00026183307636529207 2023-01-23 22:37:50.689544: step: 2214/1545, loss: 0.0010860689217224717 2023-01-23 22:37:51.545324: step: 2216/1545, loss: 0.00011892478505615145 2023-01-23 22:37:52.406329: step: 2218/1545, loss: 0.020358601585030556 2023-01-23 22:37:53.303505: step: 2220/1545, loss: 0.0012297844514250755 2023-01-23 22:37:54.182017: step: 2222/1545, loss: 0.004217019770294428 2023-01-23 22:37:55.034396: step: 2224/1545, loss: 0.06862669438123703 2023-01-23 22:37:55.944097: step: 2226/1545, loss: 0.004452800843864679 2023-01-23 22:37:56.812291: step: 2228/1545, loss: 0.05252499505877495 2023-01-23 22:37:57.658645: step: 2230/1545, loss: 0.09281493723392487 2023-01-23 22:37:58.551496: step: 2232/1545, loss: 0.03337705507874489 2023-01-23 22:37:59.425305: step: 2234/1545, loss: 0.011332569643855095 2023-01-23 22:38:00.334125: step: 2236/1545, loss: 0.006779253948479891 2023-01-23 22:38:01.196902: step: 2238/1545, loss: 0.0010366322239860892 2023-01-23 22:38:02.096752: step: 2240/1545, loss: 0.06916503608226776 2023-01-23 22:38:02.908802: step: 2242/1545, loss: 0.00020780638442374766 2023-01-23 22:38:03.792747: step: 2244/1545, loss: 0.15832817554473877 2023-01-23 22:38:04.648968: step: 2246/1545, loss: 0.03785973787307739 2023-01-23 22:38:05.470906: step: 2248/1545, loss: 1.0618717169563752e-05 2023-01-23 22:38:06.308524: step: 2250/1545, loss: 0.0005391755839809775 2023-01-23 22:38:07.191307: step: 2252/1545, loss: 0.013576728291809559 2023-01-23 22:38:08.124322: step: 2254/1545, loss: 0.15866921842098236 2023-01-23 22:38:08.989301: step: 2256/1545, loss: 0.16612224280834198 2023-01-23 22:38:09.850837: step: 2258/1545, loss: 8.4671177319251e-05 2023-01-23 22:38:10.704749: step: 2260/1545, loss: 1.024355151457712e-05 2023-01-23 22:38:11.592560: step: 2262/1545, loss: 0.00022334863024298102 2023-01-23 22:38:12.441812: step: 2264/1545, loss: 0.00041974789928644896 2023-01-23 22:38:13.290081: step: 2266/1545, loss: 0.0029406475368887186 2023-01-23 22:38:14.169323: step: 2268/1545, loss: 0.04304321110248566 2023-01-23 22:38:15.043172: step: 2270/1545, loss: 6.409213528968394e-05 2023-01-23 22:38:15.961581: step: 2272/1545, loss: 0.000519563676789403 2023-01-23 22:38:16.820225: step: 2274/1545, loss: 3.478857615846209e-05 2023-01-23 22:38:17.674634: step: 2276/1545, loss: 0.016153642907738686 2023-01-23 22:38:18.599643: step: 2278/1545, loss: 0.010247687809169292 2023-01-23 22:38:19.557952: step: 2280/1545, loss: 0.003168200608342886 2023-01-23 22:38:20.416550: step: 2282/1545, loss: 7.854770228732377e-05 2023-01-23 22:38:21.292258: step: 2284/1545, loss: 0.0007951920852065086 2023-01-23 22:38:22.223679: step: 2286/1545, loss: 0.070485420525074 2023-01-23 22:38:23.105218: step: 2288/1545, loss: 0.0008056397782638669 2023-01-23 22:38:23.943913: step: 2290/1545, loss: 0.2705951929092407 2023-01-23 22:38:24.827372: step: 2292/1545, loss: 0.052453041076660156 2023-01-23 22:38:25.667776: step: 2294/1545, loss: 0.015812795609235764 2023-01-23 22:38:26.590168: step: 2296/1545, loss: 0.0498012937605381 2023-01-23 22:38:27.441210: step: 2298/1545, loss: 4.3748914322350174e-05 2023-01-23 22:38:28.283799: step: 2300/1545, loss: 0.0011595974210649729 2023-01-23 22:38:29.150307: step: 2302/1545, loss: 0.051561567932367325 2023-01-23 22:38:30.004285: step: 2304/1545, loss: 0.001131874625571072 2023-01-23 22:38:30.893031: step: 2306/1545, loss: 0.021461548283696175 2023-01-23 22:38:31.790836: step: 2308/1545, loss: 0.016538113355636597 2023-01-23 22:38:32.681645: step: 2310/1545, loss: 6.379907426889986e-05 2023-01-23 22:38:33.514131: step: 2312/1545, loss: 0.00286495266482234 2023-01-23 22:38:34.382863: step: 2314/1545, loss: 0.0001571688480908051 2023-01-23 22:38:35.255183: step: 2316/1545, loss: 0.0031684204004704952 2023-01-23 22:38:36.118533: step: 2318/1545, loss: 0.0009336876682937145 2023-01-23 22:38:36.962206: step: 2320/1545, loss: 0.0003277177456766367 2023-01-23 22:38:37.819484: step: 2322/1545, loss: 0.010013049468398094 2023-01-23 22:38:38.772917: step: 2324/1545, loss: 0.0009854770032688975 2023-01-23 22:38:39.653862: step: 2326/1545, loss: 0.0025429008528590202 2023-01-23 22:38:40.528704: step: 2328/1545, loss: 0.007715224754065275 2023-01-23 22:38:41.396645: step: 2330/1545, loss: 0.0005116909742355347 2023-01-23 22:38:42.257582: step: 2332/1545, loss: 0.004587636329233646 2023-01-23 22:38:43.104766: step: 2334/1545, loss: 3.566437226254493e-05 2023-01-23 22:38:43.969861: step: 2336/1545, loss: 8.427057764492929e-05 2023-01-23 22:38:44.873870: step: 2338/1545, loss: 4.534941035672091e-05 2023-01-23 22:38:45.736667: step: 2340/1545, loss: 4.7470042773056775e-05 2023-01-23 22:38:46.577348: step: 2342/1545, loss: 0.00033991324016824365 2023-01-23 22:38:47.417567: step: 2344/1545, loss: 0.03740105777978897 2023-01-23 22:38:48.264555: step: 2346/1545, loss: 0.008942114189267159 2023-01-23 22:38:49.127711: step: 2348/1545, loss: 0.0001334231492364779 2023-01-23 22:38:50.014524: step: 2350/1545, loss: 0.00889655016362667 2023-01-23 22:38:50.844590: step: 2352/1545, loss: 0.00021490092331077904 2023-01-23 22:38:51.691932: step: 2354/1545, loss: 0.0008253413252532482 2023-01-23 22:38:52.574071: step: 2356/1545, loss: 0.00261210510507226 2023-01-23 22:38:53.505226: step: 2358/1545, loss: 0.17567656934261322 2023-01-23 22:38:54.362339: step: 2360/1545, loss: 0.0034747545141726732 2023-01-23 22:38:55.214969: step: 2362/1545, loss: 0.001163303037174046 2023-01-23 22:38:56.096454: step: 2364/1545, loss: 0.00010605763964122161 2023-01-23 22:38:57.022625: step: 2366/1545, loss: 0.01645965874195099 2023-01-23 22:38:57.920975: step: 2368/1545, loss: 0.005682328715920448 2023-01-23 22:38:58.747020: step: 2370/1545, loss: 0.0005642730975523591 2023-01-23 22:38:59.578392: step: 2372/1545, loss: 6.517655947391177e-06 2023-01-23 22:39:00.429233: step: 2374/1545, loss: 0.02305678464472294 2023-01-23 22:39:01.313578: step: 2376/1545, loss: 0.18014289438724518 2023-01-23 22:39:02.218862: step: 2378/1545, loss: 0.0018231020076200366 2023-01-23 22:39:03.083958: step: 2380/1545, loss: 0.00031643841066397727 2023-01-23 22:39:03.958031: step: 2382/1545, loss: 0.00013131005107425153 2023-01-23 22:39:04.883519: step: 2384/1545, loss: 0.0005936716333962977 2023-01-23 22:39:05.751000: step: 2386/1545, loss: 0.0001213304785778746 2023-01-23 22:39:06.630496: step: 2388/1545, loss: 0.0006766655133105814 2023-01-23 22:39:07.483159: step: 2390/1545, loss: 0.17732374370098114 2023-01-23 22:39:08.399571: step: 2392/1545, loss: 3.527983062667772e-05 2023-01-23 22:39:09.289121: step: 2394/1545, loss: 9.220927313435823e-05 2023-01-23 22:39:10.254928: step: 2396/1545, loss: 0.01787504553794861 2023-01-23 22:39:11.237856: step: 2398/1545, loss: 0.0012009839992970228 2023-01-23 22:39:12.082400: step: 2400/1545, loss: 0.0012549360981211066 2023-01-23 22:39:13.042632: step: 2402/1545, loss: 0.0008042611880227923 2023-01-23 22:39:13.914706: step: 2404/1545, loss: 2.146588303730823e-05 2023-01-23 22:39:14.783648: step: 2406/1545, loss: 6.369260518113151e-05 2023-01-23 22:39:15.638857: step: 2408/1545, loss: 0.0011117288377135992 2023-01-23 22:39:16.502923: step: 2410/1545, loss: 0.00021652028954122216 2023-01-23 22:39:17.348449: step: 2412/1545, loss: 0.004865236114710569 2023-01-23 22:39:18.199844: step: 2414/1545, loss: 0.011882668361067772 2023-01-23 22:39:19.041374: step: 2416/1545, loss: -1.1808672752522398e-05 2023-01-23 22:39:19.914301: step: 2418/1545, loss: 0.002071787603199482 2023-01-23 22:39:20.762817: step: 2420/1545, loss: 0.004554730840027332 2023-01-23 22:39:21.620284: step: 2422/1545, loss: 8.689671813044697e-05 2023-01-23 22:39:22.464663: step: 2424/1545, loss: 0.0007546215201728046 2023-01-23 22:39:23.320213: step: 2426/1545, loss: 0.0022246278822422028 2023-01-23 22:39:24.214195: step: 2428/1545, loss: 5.5087104556150734e-05 2023-01-23 22:39:25.107507: step: 2430/1545, loss: 0.00022877156152389944 2023-01-23 22:39:26.016832: step: 2432/1545, loss: 2.1873587684240192e-05 2023-01-23 22:39:26.870946: step: 2434/1545, loss: 0.0003808156179729849 2023-01-23 22:39:27.744055: step: 2436/1545, loss: 0.00020648492500185966 2023-01-23 22:39:28.625037: step: 2438/1545, loss: 0.027292311191558838 2023-01-23 22:39:29.543792: step: 2440/1545, loss: 0.6466667652130127 2023-01-23 22:39:30.471233: step: 2442/1545, loss: 0.2093152105808258 2023-01-23 22:39:31.315085: step: 2444/1545, loss: 0.03639601171016693 2023-01-23 22:39:32.183340: step: 2446/1545, loss: 4.627992893802002e-05 2023-01-23 22:39:33.060516: step: 2448/1545, loss: 0.0003963645431213081 2023-01-23 22:39:33.907710: step: 2450/1545, loss: 0.06595964729785919 2023-01-23 22:39:34.783713: step: 2452/1545, loss: -1.0264514457958285e-05 2023-01-23 22:39:35.718468: step: 2454/1545, loss: 0.00016638915985822678 2023-01-23 22:39:36.533783: step: 2456/1545, loss: 3.781761915888637e-05 2023-01-23 22:39:37.460186: step: 2458/1545, loss: 0.01739056594669819 2023-01-23 22:39:38.424789: step: 2460/1545, loss: 0.17647510766983032 2023-01-23 22:39:39.350479: step: 2462/1545, loss: 0.007196294609457254 2023-01-23 22:39:40.209690: step: 2464/1545, loss: 0.014009376056492329 2023-01-23 22:39:41.112474: step: 2466/1545, loss: 0.00434951763600111 2023-01-23 22:39:41.985030: step: 2468/1545, loss: 0.0005892593180760741 2023-01-23 22:39:42.857530: step: 2470/1545, loss: 0.013147441670298576 2023-01-23 22:39:43.711080: step: 2472/1545, loss: 0.00046965465298853815 2023-01-23 22:39:44.631360: step: 2474/1545, loss: 7.069431740092114e-05 2023-01-23 22:39:45.550079: step: 2476/1545, loss: 1.5254070603987202e-05 2023-01-23 22:39:46.455663: step: 2478/1545, loss: 0.37968355417251587 2023-01-23 22:39:47.372761: step: 2480/1545, loss: 0.014384284615516663 2023-01-23 22:39:48.235479: step: 2482/1545, loss: 0.7052217721939087 2023-01-23 22:39:49.098888: step: 2484/1545, loss: 0.001939280773513019 2023-01-23 22:39:50.094244: step: 2486/1545, loss: 6.580947956535965e-05 2023-01-23 22:39:50.944770: step: 2488/1545, loss: 6.982966442592442e-05 2023-01-23 22:39:51.796357: step: 2490/1545, loss: 1.0139867299585603e-05 2023-01-23 22:39:52.676071: step: 2492/1545, loss: 0.0010828220983967185 2023-01-23 22:39:53.536055: step: 2494/1545, loss: 0.00019631543545983732 2023-01-23 22:39:54.466843: step: 2496/1545, loss: 0.005139811895787716 2023-01-23 22:39:55.368253: step: 2498/1545, loss: 0.0024684348609298468 2023-01-23 22:39:56.226654: step: 2500/1545, loss: 0.408187597990036 2023-01-23 22:39:57.083744: step: 2502/1545, loss: 0.018016979098320007 2023-01-23 22:39:57.999477: step: 2504/1545, loss: 0.03168454393744469 2023-01-23 22:39:58.863032: step: 2506/1545, loss: 0.00013429202954284847 2023-01-23 22:39:59.797098: step: 2508/1545, loss: 0.061261944472789764 2023-01-23 22:40:00.677352: step: 2510/1545, loss: 0.49050837755203247 2023-01-23 22:40:01.581691: step: 2512/1545, loss: 0.051705971360206604 2023-01-23 22:40:02.475643: step: 2514/1545, loss: 0.009291434660553932 2023-01-23 22:40:03.415581: step: 2516/1545, loss: 7.811064278939739e-05 2023-01-23 22:40:04.276594: step: 2518/1545, loss: 0.0006086325738579035 2023-01-23 22:40:05.188810: step: 2520/1545, loss: 0.0017924720887094736 2023-01-23 22:40:06.119767: step: 2522/1545, loss: 0.0015897173434495926 2023-01-23 22:40:06.969663: step: 2524/1545, loss: 0.10355474799871445 2023-01-23 22:40:07.857811: step: 2526/1545, loss: 4.7900353820296004e-05 2023-01-23 22:40:08.736055: step: 2528/1545, loss: 0.003066493198275566 2023-01-23 22:40:09.655339: step: 2530/1545, loss: 2.2172898752614856e-06 2023-01-23 22:40:10.520201: step: 2532/1545, loss: -1.7646723335928982e-06 2023-01-23 22:40:11.381499: step: 2534/1545, loss: 0.0002503684372641146 2023-01-23 22:40:12.235170: step: 2536/1545, loss: 0.06176723539829254 2023-01-23 22:40:13.091763: step: 2538/1545, loss: 0.0001913893938763067 2023-01-23 22:40:13.973205: step: 2540/1545, loss: -4.460483978618868e-05 2023-01-23 22:40:14.827794: step: 2542/1545, loss: 0.00014747884415555745 2023-01-23 22:40:15.666667: step: 2544/1545, loss: 0.00014630059013143182 2023-01-23 22:40:16.525441: step: 2546/1545, loss: 0.3077895939350128 2023-01-23 22:40:17.406656: step: 2548/1545, loss: 9.878493438009173e-05 2023-01-23 22:40:18.287330: step: 2550/1545, loss: 0.0015407687751576304 2023-01-23 22:40:19.139666: step: 2552/1545, loss: 0.0013143836986273527 2023-01-23 22:40:19.991737: step: 2554/1545, loss: 0.0017690279055386782 2023-01-23 22:40:20.873526: step: 2556/1545, loss: 0.011659741401672363 2023-01-23 22:40:21.723334: step: 2558/1545, loss: 0.0003254076582379639 2023-01-23 22:40:22.573707: step: 2560/1545, loss: 0.0015881103463470936 2023-01-23 22:40:23.471134: step: 2562/1545, loss: 0.00015621064812876284 2023-01-23 22:40:24.331686: step: 2564/1545, loss: 0.03368764370679855 2023-01-23 22:40:25.229155: step: 2566/1545, loss: 0.02125694416463375 2023-01-23 22:40:26.123637: step: 2568/1545, loss: 0.12556910514831543 2023-01-23 22:40:27.009625: step: 2570/1545, loss: 0.0007299361168406904 2023-01-23 22:40:27.862878: step: 2572/1545, loss: 2.8398259019013494e-05 2023-01-23 22:40:28.716144: step: 2574/1545, loss: 0.0009839138947427273 2023-01-23 22:40:29.603858: step: 2576/1545, loss: 0.33052822947502136 2023-01-23 22:40:30.491305: step: 2578/1545, loss: 0.49887576699256897 2023-01-23 22:40:31.378405: step: 2580/1545, loss: 0.011100776493549347 2023-01-23 22:40:32.245088: step: 2582/1545, loss: 0.0001401582412654534 2023-01-23 22:40:33.144764: step: 2584/1545, loss: 1.5864521628827788e-05 2023-01-23 22:40:34.030070: step: 2586/1545, loss: 9.624650374462362e-06 2023-01-23 22:40:34.924037: step: 2588/1545, loss: 2.0395937099237926e-05 2023-01-23 22:40:35.811034: step: 2590/1545, loss: 0.41530168056488037 2023-01-23 22:40:36.798416: step: 2592/1545, loss: 0.003237067721784115 2023-01-23 22:40:37.688633: step: 2594/1545, loss: 0.000296382320811972 2023-01-23 22:40:38.556294: step: 2596/1545, loss: -2.6378305847174488e-05 2023-01-23 22:40:39.432450: step: 2598/1545, loss: 3.8428257539635524e-05 2023-01-23 22:40:40.353748: step: 2600/1545, loss: 0.30112773180007935 2023-01-23 22:40:41.295829: step: 2602/1545, loss: 0.011394193395972252 2023-01-23 22:40:42.182524: step: 2604/1545, loss: 1.6349553334293887e-05 2023-01-23 22:40:43.099483: step: 2606/1545, loss: 3.166745227645151e-05 2023-01-23 22:40:43.974670: step: 2608/1545, loss: 0.010819921270012856 2023-01-23 22:40:44.879232: step: 2610/1545, loss: 0.00023703568149358034 2023-01-23 22:40:45.789099: step: 2612/1545, loss: 8.346745744347572e-06 2023-01-23 22:40:46.675720: step: 2614/1545, loss: 0.023701105266809464 2023-01-23 22:40:47.577473: step: 2616/1545, loss: 0.042755305767059326 2023-01-23 22:40:48.437577: step: 2618/1545, loss: 2.877384758903645e-05 2023-01-23 22:40:49.308648: step: 2620/1545, loss: 0.004936045501381159 2023-01-23 22:40:50.224012: step: 2622/1545, loss: 0.00022447173250839114 2023-01-23 22:40:51.139566: step: 2624/1545, loss: 0.0057120556011796 2023-01-23 22:40:52.025129: step: 2626/1545, loss: 0.04220857098698616 2023-01-23 22:40:52.895707: step: 2628/1545, loss: 0.00023676452110521495 2023-01-23 22:40:53.804579: step: 2630/1545, loss: 0.005208027083426714 2023-01-23 22:40:54.728381: step: 2632/1545, loss: 0.17234107851982117 2023-01-23 22:40:55.604467: step: 2634/1545, loss: 0.0024967656936496496 2023-01-23 22:40:56.488145: step: 2636/1545, loss: 0.0006296626524999738 2023-01-23 22:40:57.347974: step: 2638/1545, loss: 0.0029562076088041067 2023-01-23 22:40:58.248044: step: 2640/1545, loss: 0.05930773541331291 2023-01-23 22:40:59.172362: step: 2642/1545, loss: 0.0005861519020982087 2023-01-23 22:41:00.022194: step: 2644/1545, loss: 5.41078406968154e-05 2023-01-23 22:41:00.933679: step: 2646/1545, loss: 0.027045389637351036 2023-01-23 22:41:01.821730: step: 2648/1545, loss: 0.01014282088726759 2023-01-23 22:41:02.669272: step: 2650/1545, loss: 0.00027090965886600316 2023-01-23 22:41:03.538762: step: 2652/1545, loss: 0.004917195998132229 2023-01-23 22:41:04.400344: step: 2654/1545, loss: 0.03462199866771698 2023-01-23 22:41:05.256187: step: 2656/1545, loss: 0.0009026674670167267 2023-01-23 22:41:06.124817: step: 2658/1545, loss: 0.7267067432403564 2023-01-23 22:41:07.030185: step: 2660/1545, loss: 0.013738729059696198 2023-01-23 22:41:07.888460: step: 2662/1545, loss: 0.040671057999134064 2023-01-23 22:41:08.813776: step: 2664/1545, loss: 0.0004949274007230997 2023-01-23 22:41:09.675890: step: 2666/1545, loss: 0.001076522166840732 2023-01-23 22:41:10.659433: step: 2668/1545, loss: 0.004504207521677017 2023-01-23 22:41:11.556577: step: 2670/1545, loss: 0.001445417059585452 2023-01-23 22:41:12.397608: step: 2672/1545, loss: 0.001156614045612514 2023-01-23 22:41:13.246711: step: 2674/1545, loss: 9.249195863958448e-05 2023-01-23 22:41:14.119914: step: 2676/1545, loss: 0.1623072624206543 2023-01-23 22:41:14.978239: step: 2678/1545, loss: 0.004133694339543581 2023-01-23 22:41:15.831507: step: 2680/1545, loss: 0.021748164668679237 2023-01-23 22:41:16.738082: step: 2682/1545, loss: 0.01024982426315546 2023-01-23 22:41:17.622203: step: 2684/1545, loss: 0.00013855040015187114 2023-01-23 22:41:18.503163: step: 2686/1545, loss: 0.05219201743602753 2023-01-23 22:41:19.407914: step: 2688/1545, loss: 0.00015354664355982095 2023-01-23 22:41:20.336378: step: 2690/1545, loss: 0.055399246513843536 2023-01-23 22:41:21.179679: step: 2692/1545, loss: 0.0002027730515692383 2023-01-23 22:41:22.073128: step: 2694/1545, loss: 4.662135124206543 2023-01-23 22:41:22.950049: step: 2696/1545, loss: 0.0004816168802790344 2023-01-23 22:41:23.885705: step: 2698/1545, loss: 0.046013399958610535 2023-01-23 22:41:24.764447: step: 2700/1545, loss: 0.0001910572755150497 2023-01-23 22:41:25.671832: step: 2702/1545, loss: 0.0019763661548495293 2023-01-23 22:41:26.592900: step: 2704/1545, loss: 0.1811595857143402 2023-01-23 22:41:27.476555: step: 2706/1545, loss: 0.0003632497100625187 2023-01-23 22:41:28.431880: step: 2708/1545, loss: 0.0038172092754393816 2023-01-23 22:41:29.306911: step: 2710/1545, loss: 0.0034846188500523567 2023-01-23 22:41:30.225628: step: 2712/1545, loss: 0.08810053765773773 2023-01-23 22:41:31.074642: step: 2714/1545, loss: 0.0008295822772197425 2023-01-23 22:41:31.907870: step: 2716/1545, loss: 0.004743796773254871 2023-01-23 22:41:32.800016: step: 2718/1545, loss: 0.005189391318708658 2023-01-23 22:41:33.657198: step: 2720/1545, loss: 3.7361111640930176 2023-01-23 22:41:34.504117: step: 2722/1545, loss: 0.3947332203388214 2023-01-23 22:41:35.389297: step: 2724/1545, loss: 0.0004280954890418798 2023-01-23 22:41:36.321565: step: 2726/1545, loss: 0.6041664481163025 2023-01-23 22:41:37.185350: step: 2728/1545, loss: 0.0011600033612921834 2023-01-23 22:41:38.049457: step: 2730/1545, loss: 0.0010688338661566377 2023-01-23 22:41:38.964061: step: 2732/1545, loss: 0.14814545214176178 2023-01-23 22:41:39.831033: step: 2734/1545, loss: 0.07551261782646179 2023-01-23 22:41:40.744644: step: 2736/1545, loss: 0.0001648180914344266 2023-01-23 22:41:41.629270: step: 2738/1545, loss: 0.03923580422997475 2023-01-23 22:41:42.473547: step: 2740/1545, loss: 4.645123772206716e-05 2023-01-23 22:41:43.323312: step: 2742/1545, loss: 0.002466089790686965 2023-01-23 22:41:44.227591: step: 2744/1545, loss: 0.4912368655204773 2023-01-23 22:41:45.086187: step: 2746/1545, loss: 0.00037346823955886066 2023-01-23 22:41:45.933625: step: 2748/1545, loss: 0.024416202679276466 2023-01-23 22:41:46.817251: step: 2750/1545, loss: 0.00041508255526423454 2023-01-23 22:41:47.711005: step: 2752/1545, loss: 0.07568762451410294 2023-01-23 22:41:48.582417: step: 2754/1545, loss: 0.0006160101620480418 2023-01-23 22:41:49.461983: step: 2756/1545, loss: 0.0008147298358380795 2023-01-23 22:41:50.354738: step: 2758/1545, loss: 0.0036150484811514616 2023-01-23 22:41:51.222301: step: 2760/1545, loss: 0.7621772885322571 2023-01-23 22:41:52.086001: step: 2762/1545, loss: 0.005425491835922003 2023-01-23 22:41:52.990529: step: 2764/1545, loss: 0.000301132386084646 2023-01-23 22:41:53.895304: step: 2766/1545, loss: 0.0015195184387266636 2023-01-23 22:41:54.776776: step: 2768/1545, loss: 0.0003007042105309665 2023-01-23 22:41:55.621034: step: 2770/1545, loss: 0.00233419518917799 2023-01-23 22:41:56.522652: step: 2772/1545, loss: 0.11832599341869354 2023-01-23 22:41:57.403523: step: 2774/1545, loss: 0.0009593817521817982 2023-01-23 22:41:58.267223: step: 2776/1545, loss: 0.0030795650091022253 2023-01-23 22:41:59.145967: step: 2778/1545, loss: 0.0007316278060898185 2023-01-23 22:42:00.046396: step: 2780/1545, loss: 8.643718319945037e-05 2023-01-23 22:42:00.928559: step: 2782/1545, loss: 0.0007842902559787035 2023-01-23 22:42:01.886431: step: 2784/1545, loss: 0.00011042561527574435 2023-01-23 22:42:02.718352: step: 2786/1545, loss: 0.003935249987989664 2023-01-23 22:42:03.590105: step: 2788/1545, loss: 0.000352130678948015 2023-01-23 22:42:04.483169: step: 2790/1545, loss: 0.9689169526100159 2023-01-23 22:42:05.383794: step: 2792/1545, loss: 0.7287375330924988 2023-01-23 22:42:06.252958: step: 2794/1545, loss: 0.027574943378567696 2023-01-23 22:42:07.113608: step: 2796/1545, loss: 0.0005358622292988002 2023-01-23 22:42:07.946657: step: 2798/1545, loss: 0.0015219295164570212 2023-01-23 22:42:08.837328: step: 2800/1545, loss: 0.023883620277047157 2023-01-23 22:42:09.747774: step: 2802/1545, loss: 0.005665324628353119 2023-01-23 22:42:10.634926: step: 2804/1545, loss: 0.30638813972473145 2023-01-23 22:42:11.513775: step: 2806/1545, loss: 0.0014077621744945645 2023-01-23 22:42:12.432345: step: 2808/1545, loss: 0.00012133889686083421 2023-01-23 22:42:13.299717: step: 2810/1545, loss: 0.015386468730866909 2023-01-23 22:42:14.246109: step: 2812/1545, loss: 0.00017251318786293268 2023-01-23 22:42:15.175233: step: 2814/1545, loss: 0.0004367269284557551 2023-01-23 22:42:16.036462: step: 2816/1545, loss: 3.0102228265604936e-05 2023-01-23 22:42:16.959996: step: 2818/1545, loss: 0.0008878529188223183 2023-01-23 22:42:17.832005: step: 2820/1545, loss: 0.004910486750304699 2023-01-23 22:42:18.683346: step: 2822/1545, loss: 0.0001123769034165889 2023-01-23 22:42:19.658344: step: 2824/1545, loss: 5.687049269909039e-05 2023-01-23 22:42:20.542709: step: 2826/1545, loss: 0.005804933607578278 2023-01-23 22:42:21.480868: step: 2828/1545, loss: 2.8447590011637658e-05 2023-01-23 22:42:22.318480: step: 2830/1545, loss: 0.01822466403245926 2023-01-23 22:42:23.225989: step: 2832/1545, loss: 0.09458844363689423 2023-01-23 22:42:24.116146: step: 2834/1545, loss: 9.231106378138065e-05 2023-01-23 22:42:25.081020: step: 2836/1545, loss: 0.1423730105161667 2023-01-23 22:42:25.959348: step: 2838/1545, loss: 0.00017755175940692425 2023-01-23 22:42:26.845076: step: 2840/1545, loss: 0.0011514498619362712 2023-01-23 22:42:27.754889: step: 2842/1545, loss: 0.004039203282445669 2023-01-23 22:42:28.644610: step: 2844/1545, loss: 0.024362200871109962 2023-01-23 22:42:29.536093: step: 2846/1545, loss: 0.0002985247119795531 2023-01-23 22:42:30.394107: step: 2848/1545, loss: 7.754034595564008e-05 2023-01-23 22:42:31.289659: step: 2850/1545, loss: 0.0005488407332450151 2023-01-23 22:42:32.155445: step: 2852/1545, loss: 2.7157793738297187e-05 2023-01-23 22:42:33.075583: step: 2854/1545, loss: 0.002821563510224223 2023-01-23 22:42:33.964896: step: 2856/1545, loss: 0.006332154385745525 2023-01-23 22:42:34.824698: step: 2858/1545, loss: 0.0012925553601235151 2023-01-23 22:42:35.733623: step: 2860/1545, loss: 4.7685487515991554e-05 2023-01-23 22:42:36.582332: step: 2862/1545, loss: 8.631013770354912e-06 2023-01-23 22:42:37.522587: step: 2864/1545, loss: 0.00023896545462775975 2023-01-23 22:42:38.387197: step: 2866/1545, loss: 0.00016367691569030285 2023-01-23 22:42:39.250830: step: 2868/1545, loss: 0.00026190606877207756 2023-01-23 22:42:40.173447: step: 2870/1545, loss: 0.00015379476826637983 2023-01-23 22:42:41.043320: step: 2872/1545, loss: 0.16281819343566895 2023-01-23 22:42:41.914236: step: 2874/1545, loss: 1.124724713008618e-05 2023-01-23 22:42:42.805413: step: 2876/1545, loss: -1.5414495919685578e-06 2023-01-23 22:42:43.669236: step: 2878/1545, loss: 0.002329634502530098 2023-01-23 22:42:44.536827: step: 2880/1545, loss: 0.0018401633715257049 2023-01-23 22:42:45.385350: step: 2882/1545, loss: 0.32913342118263245 2023-01-23 22:42:46.247980: step: 2884/1545, loss: 0.0003624240343924612 2023-01-23 22:42:47.156310: step: 2886/1545, loss: 0.04445022717118263 2023-01-23 22:42:48.038754: step: 2888/1545, loss: 0.00403017969802022 2023-01-23 22:42:48.907746: step: 2890/1545, loss: 0.00699642114341259 2023-01-23 22:42:49.844061: step: 2892/1545, loss: 3.27423149428796e-05 2023-01-23 22:42:50.702532: step: 2894/1545, loss: 0.000384899671189487 2023-01-23 22:42:51.557024: step: 2896/1545, loss: 0.001054772874340415 2023-01-23 22:42:52.416861: step: 2898/1545, loss: 0.0004820665344595909 2023-01-23 22:42:53.281696: step: 2900/1545, loss: 0.026267725974321365 2023-01-23 22:42:54.135121: step: 2902/1545, loss: 6.828408368164673e-05 2023-01-23 22:42:54.990717: step: 2904/1545, loss: 0.020376136526465416 2023-01-23 22:42:55.850087: step: 2906/1545, loss: 0.016461655497550964 2023-01-23 22:42:56.770805: step: 2908/1545, loss: 0.24598079919815063 2023-01-23 22:42:57.670239: step: 2910/1545, loss: 0.16127081215381622 2023-01-23 22:42:58.581652: step: 2912/1545, loss: 0.04060487821698189 2023-01-23 22:42:59.438468: step: 2914/1545, loss: 0.04108165577054024 2023-01-23 22:43:00.315370: step: 2916/1545, loss: 0.04486465826630592 2023-01-23 22:43:01.156914: step: 2918/1545, loss: -1.6237312365774415e-06 2023-01-23 22:43:02.071726: step: 2920/1545, loss: 6.880164619360585e-06 2023-01-23 22:43:02.909786: step: 2922/1545, loss: 4.944120883010328e-05 2023-01-23 22:43:03.783223: step: 2924/1545, loss: 0.1267004907131195 2023-01-23 22:43:04.644793: step: 2926/1545, loss: 0.00026493999757803977 2023-01-23 22:43:05.504707: step: 2928/1545, loss: 0.0011348789557814598 2023-01-23 22:43:06.406302: step: 2930/1545, loss: 0.0235458854585886 2023-01-23 22:43:07.251028: step: 2932/1545, loss: -1.235115087183658e-05 2023-01-23 22:43:08.081456: step: 2934/1545, loss: 2.1613635908579454e-05 2023-01-23 22:43:08.968126: step: 2936/1545, loss: 0.17871910333633423 2023-01-23 22:43:09.864746: step: 2938/1545, loss: 0.0017642956227064133 2023-01-23 22:43:10.706098: step: 2940/1545, loss: 7.07112267264165e-05 2023-01-23 22:43:11.670333: step: 2942/1545, loss: 0.038980867713689804 2023-01-23 22:43:12.565824: step: 2944/1545, loss: 0.11828289180994034 2023-01-23 22:43:13.452008: step: 2946/1545, loss: 0.01213597971946001 2023-01-23 22:43:14.304569: step: 2948/1545, loss: 0.0045628733932971954 2023-01-23 22:43:15.138646: step: 2950/1545, loss: 0.08072863519191742 2023-01-23 22:43:15.999399: step: 2952/1545, loss: 5.7659482990857214e-05 2023-01-23 22:43:16.878543: step: 2954/1545, loss: 0.6021317839622498 2023-01-23 22:43:17.754316: step: 2956/1545, loss: 0.0014176316326484084 2023-01-23 22:43:18.681004: step: 2958/1545, loss: 3.5315253626322374e-05 2023-01-23 22:43:19.575790: step: 2960/1545, loss: 0.00021903224114794284 2023-01-23 22:43:20.444825: step: 2962/1545, loss: 0.00033911256468854845 2023-01-23 22:43:21.327040: step: 2964/1545, loss: 0.10783643275499344 2023-01-23 22:43:22.198879: step: 2966/1545, loss: 7.132328755687922e-05 2023-01-23 22:43:23.045085: step: 2968/1545, loss: 0.00026502818218432367 2023-01-23 22:43:23.890675: step: 2970/1545, loss: 0.6021389365196228 2023-01-23 22:43:24.716743: step: 2972/1545, loss: 0.0002278929896419868 2023-01-23 22:43:25.651827: step: 2974/1545, loss: 0.001378726796247065 2023-01-23 22:43:26.548900: step: 2976/1545, loss: 0.0005596116534434259 2023-01-23 22:43:27.467673: step: 2978/1545, loss: 0.02106545679271221 2023-01-23 22:43:28.346463: step: 2980/1545, loss: 0.00042164011392742395 2023-01-23 22:43:29.237865: step: 2982/1545, loss: 0.000244871829636395 2023-01-23 22:43:30.125178: step: 2984/1545, loss: 0.05617409572005272 2023-01-23 22:43:31.051314: step: 2986/1545, loss: 0.1306786835193634 2023-01-23 22:43:31.960900: step: 2988/1545, loss: 0.0001133812329499051 2023-01-23 22:43:32.818669: step: 2990/1545, loss: 0.0037252879701554775 2023-01-23 22:43:33.700614: step: 2992/1545, loss: 0.00021883756562601775 2023-01-23 22:43:34.622422: step: 2994/1545, loss: 0.003589069237932563 2023-01-23 22:43:35.489285: step: 2996/1545, loss: 0.0018266042461618781 2023-01-23 22:43:36.370057: step: 2998/1545, loss: 0.008376928977668285 2023-01-23 22:43:37.223577: step: 3000/1545, loss: 0.008955845609307289 2023-01-23 22:43:38.052680: step: 3002/1545, loss: 0.00025349410134367645 2023-01-23 22:43:38.918765: step: 3004/1545, loss: 5.2447277994360775e-05 2023-01-23 22:43:39.789118: step: 3006/1545, loss: 0.009966154582798481 2023-01-23 22:43:40.713969: step: 3008/1545, loss: 0.005903975572437048 2023-01-23 22:43:41.592382: step: 3010/1545, loss: 0.19304785132408142 2023-01-23 22:43:42.458913: step: 3012/1545, loss: 0.05162109062075615 2023-01-23 22:43:43.377907: step: 3014/1545, loss: 0.00012978653830941767 2023-01-23 22:43:44.287198: step: 3016/1545, loss: 0.015434712171554565 2023-01-23 22:43:45.155946: step: 3018/1545, loss: 0.000961941434070468 2023-01-23 22:43:46.043228: step: 3020/1545, loss: 0.0038122343830764294 2023-01-23 22:43:46.906759: step: 3022/1545, loss: 0.00011693834676407278 2023-01-23 22:43:47.757177: step: 3024/1545, loss: 0.00017311240662820637 2023-01-23 22:43:48.619704: step: 3026/1545, loss: 0.11636622995138168 2023-01-23 22:43:49.484031: step: 3028/1545, loss: 0.002951609203591943 2023-01-23 22:43:50.418333: step: 3030/1545, loss: 0.025728296488523483 2023-01-23 22:43:51.266645: step: 3032/1545, loss: 0.000556778279133141 2023-01-23 22:43:52.140568: step: 3034/1545, loss: 0.009560979902744293 2023-01-23 22:43:53.019809: step: 3036/1545, loss: 6.187891267472878e-05 2023-01-23 22:43:53.889953: step: 3038/1545, loss: 5.8725272538140416e-05 2023-01-23 22:43:54.790483: step: 3040/1545, loss: 0.016367236152291298 2023-01-23 22:43:55.622525: step: 3042/1545, loss: 0.037528835237026215 2023-01-23 22:43:56.486313: step: 3044/1545, loss: -5.57526936972863e-06 2023-01-23 22:43:57.376724: step: 3046/1545, loss: 0.003384311916306615 2023-01-23 22:43:58.246916: step: 3048/1545, loss: 0.007338333874940872 2023-01-23 22:43:59.167763: step: 3050/1545, loss: 4.922076914226636e-05 2023-01-23 22:44:00.098291: step: 3052/1545, loss: 0.002700893674045801 2023-01-23 22:44:00.970940: step: 3054/1545, loss: 0.0001590454048709944 2023-01-23 22:44:01.865844: step: 3056/1545, loss: 0.00459503335878253 2023-01-23 22:44:02.818715: step: 3058/1545, loss: 0.05685363709926605 2023-01-23 22:44:03.730922: step: 3060/1545, loss: 0.0015363269485533237 2023-01-23 22:44:04.638320: step: 3062/1545, loss: 0.36015692353248596 2023-01-23 22:44:05.566179: step: 3064/1545, loss: 6.59589350107126e-05 2023-01-23 22:44:06.459285: step: 3066/1545, loss: 0.4177294671535492 2023-01-23 22:44:07.312817: step: 3068/1545, loss: 0.0004195085493847728 2023-01-23 22:44:08.158202: step: 3070/1545, loss: 0.033149197697639465 2023-01-23 22:44:08.985231: step: 3072/1545, loss: 5.239744859864004e-05 2023-01-23 22:44:09.874976: step: 3074/1545, loss: 0.033386118710041046 2023-01-23 22:44:10.726654: step: 3076/1545, loss: 0.31607162952423096 2023-01-23 22:44:11.688200: step: 3078/1545, loss: 5.76873826503288e-05 2023-01-23 22:44:12.582987: step: 3080/1545, loss: -1.6951298675849102e-05 2023-01-23 22:44:13.452571: step: 3082/1545, loss: 7.291387009900063e-05 2023-01-23 22:44:14.295423: step: 3084/1545, loss: 0.0387667641043663 2023-01-23 22:44:15.151793: step: 3086/1545, loss: 0.0001417967287125066 2023-01-23 22:44:16.003961: step: 3088/1545, loss: 0.0003960269968956709 2023-01-23 22:44:16.910137: step: 3090/1545, loss: 0.117294080555439 ================================================== Loss: 0.054 -------------------- Dev Chinese: {'event': {'p': 0.6008724100327154, 'r': 0.7336884154460719, 'f1': 0.6606714628297362}, 'argument': {'p': 0.6853368328247768, 'r': 0.6360541841722085, 'f1': 0.6597764847473957}, 'combined': 0.43589549531872307, 'epoch': 37} Test Chinese: {'event': {'p': 0.6419423692636073, 'r': 0.7691815856777494, 'f1': 0.6998254799301921}, 'argument': {'p': 0.7281808458432854, 'r': 0.7117640824100587, 'f1': 0.7198788806442992}, 'combined': 0.5037895831385061, 'epoch': 37} Dev Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.6921142718794929, 'r': 0.6343947495815037, 'f1': 0.6619987547573354}, 'combined': 0.4413325031715569, 'epoch': 37} Test Korean: {'event': {'p': 0.6322751322751323, 'r': 0.7640664961636828, 'f1': 0.6919513607411696}, 'argument': {'p': 0.7237467474202179, 'r': 0.7065674601537351, 'f1': 0.7150539348785571}, 'combined': 0.4947825432425452, 'epoch': 37} Dev Russian: {'event': {'p': 0.5688976377952756, 'r': 0.7696404793608522, 'f1': 0.6542161856253538}, 'argument': {'p': 0.6844853539606232, 'r': 0.642438396503042, 'f1': 0.6627956927813256}, 'combined': 0.43361166998031264, 'epoch': 37} Test Russian: {'event': {'p': 0.6263079222720478, 'r': 0.8037084398976982, 'f1': 0.7040044805376645}, 'argument': {'p': 0.7338946921670021, 'r': 0.72096141487722, 'f1': 0.7273705668536204}, 'combined': 0.5120721380761697, 'epoch': 37} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7135076252723311, 'r': 0.6014692378328741, 'f1': 0.6527154957648231}, 'combined': 0.4648125500143437, 'epoch': 37} Korean: {'event': {'p': 0.7058823529411765, 'r': 0.5714285714285714, 'f1': 0.6315789473684211}, 'argument': {'p': 0.6593073593073593, 'r': 0.4967384213959556, 'f1': 0.5665922619047619}, 'combined': 0.3578477443609023, 'epoch': 37} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5823017333543649, 'r': 0.5719034881158941, 'f1': 0.5770557717926139}, 'combined': 0.3213981513781647, 'epoch': 37} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6758987924276707, 'r': 0.6414709887684336, 'f1': 0.6582350269068861}, 'combined': 0.43408784748056034, 'epoch': 33} Test for Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7201409239897084, 'r': 0.7110669833666995, 'f1': 0.7155751890249322}, 'combined': 0.49952892776609586, 'epoch': 33} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7175290642271774, 'r': 0.6285791802320727, 'f1': 0.6701152494104036}, 'combined': 0.4772032836710449, 'epoch': 33} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 38 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 22:49:27.649002: step: 2/1545, loss: 0.09286477416753769 2023-01-23 22:49:28.621805: step: 4/1545, loss: 0.008245022967457771 2023-01-23 22:49:29.474452: step: 6/1545, loss: 8.164346218109131e-05 2023-01-23 22:49:30.358885: step: 8/1545, loss: 0.03142740577459335 2023-01-23 22:49:31.264862: step: 10/1545, loss: 0.0002228230150649324 2023-01-23 22:49:32.122750: step: 12/1545, loss: 0.015345937572419643 2023-01-23 22:49:33.036979: step: 14/1545, loss: 0.006820057984441519 2023-01-23 22:49:33.880871: step: 16/1545, loss: 0.0015551120741292834 2023-01-23 22:49:34.731675: step: 18/1545, loss: 0.0013957974733784795 2023-01-23 22:49:35.607186: step: 20/1545, loss: 0.01253477856516838 2023-01-23 22:49:36.476349: step: 22/1545, loss: 6.25296015641652e-05 2023-01-23 22:49:37.329868: step: 24/1545, loss: 0.0012012507067993283 2023-01-23 22:49:38.172842: step: 26/1545, loss: 0.00138578109908849 2023-01-23 22:49:39.049125: step: 28/1545, loss: 0.0002087798493448645 2023-01-23 22:49:39.992571: step: 30/1545, loss: 0.21803146600723267 2023-01-23 22:49:40.874127: step: 32/1545, loss: 0.14085333049297333 2023-01-23 22:49:41.719771: step: 34/1545, loss: 0.1062820553779602 2023-01-23 22:49:42.591069: step: 36/1545, loss: 0.0626392737030983 2023-01-23 22:49:43.457120: step: 38/1545, loss: 5.8840956626227126e-05 2023-01-23 22:49:44.409574: step: 40/1545, loss: 0.4054024815559387 2023-01-23 22:49:45.282104: step: 42/1545, loss: 0.0019097297918051481 2023-01-23 22:49:46.156265: step: 44/1545, loss: 0.00011517789971549064 2023-01-23 22:49:46.997330: step: 46/1545, loss: 9.730039892019704e-05 2023-01-23 22:49:47.843728: step: 48/1545, loss: 0.0016893417341634631 2023-01-23 22:49:48.832770: step: 50/1545, loss: 0.3344082832336426 2023-01-23 22:49:49.696929: step: 52/1545, loss: -1.0880216905206908e-05 2023-01-23 22:49:50.573755: step: 54/1545, loss: 0.030732810497283936 2023-01-23 22:49:51.466103: step: 56/1545, loss: 0.004157086368650198 2023-01-23 22:49:52.348420: step: 58/1545, loss: 9.92163986666128e-05 2023-01-23 22:49:53.233935: step: 60/1545, loss: 0.0014327343087643385 2023-01-23 22:49:54.116782: step: 62/1545, loss: 0.00018700421787798405 2023-01-23 22:49:54.994885: step: 64/1545, loss: 0.004468420520424843 2023-01-23 22:49:55.839484: step: 66/1545, loss: 0.0006226047407835722 2023-01-23 22:49:56.679860: step: 68/1545, loss: 0.00012847421749029309 2023-01-23 22:49:57.590138: step: 70/1545, loss: 0.04060520604252815 2023-01-23 22:49:58.457388: step: 72/1545, loss: 0.1999790072441101 2023-01-23 22:49:59.444833: step: 74/1545, loss: 0.0003891875094268471 2023-01-23 22:50:00.322594: step: 76/1545, loss: 0.00028181824018247426 2023-01-23 22:50:01.238712: step: 78/1545, loss: 0.27394866943359375 2023-01-23 22:50:02.164969: step: 80/1545, loss: 3.934105552616529e-05 2023-01-23 22:50:03.025494: step: 82/1545, loss: 0.00015968143998179585 2023-01-23 22:50:03.893366: step: 84/1545, loss: 0.08155141025781631 2023-01-23 22:50:04.812208: step: 86/1545, loss: 0.008980895392596722 2023-01-23 22:50:05.691545: step: 88/1545, loss: 0.0037074328865855932 2023-01-23 22:50:06.596892: step: 90/1545, loss: 0.00011475744395283982 2023-01-23 22:50:07.470603: step: 92/1545, loss: 8.274403080577031e-05 2023-01-23 22:50:08.349024: step: 94/1545, loss: 0.03664872795343399 2023-01-23 22:50:09.203743: step: 96/1545, loss: 0.00013818586012348533 2023-01-23 22:50:10.042429: step: 98/1545, loss: 0.0028150291182100773 2023-01-23 22:50:10.921064: step: 100/1545, loss: 0.1376764476299286 2023-01-23 22:50:11.804512: step: 102/1545, loss: 0.02478085085749626 2023-01-23 22:50:12.669778: step: 104/1545, loss: 0.0007781019085086882 2023-01-23 22:50:13.605654: step: 106/1545, loss: 9.08818983589299e-05 2023-01-23 22:50:14.538858: step: 108/1545, loss: 0.14075259864330292 2023-01-23 22:50:15.445841: step: 110/1545, loss: 0.022039564326405525 2023-01-23 22:50:16.371379: step: 112/1545, loss: 2.2421776520786807e-05 2023-01-23 22:50:17.227321: step: 114/1545, loss: 0.00025828974321484566 2023-01-23 22:50:18.072323: step: 116/1545, loss: 0.003944999072700739 2023-01-23 22:50:19.060994: step: 118/1545, loss: 3.601844946388155e-05 2023-01-23 22:50:19.943052: step: 120/1545, loss: 0.0001384882052661851 2023-01-23 22:50:20.790672: step: 122/1545, loss: 0.00047226648894138634 2023-01-23 22:50:21.633143: step: 124/1545, loss: 3.990530240116641e-05 2023-01-23 22:50:22.539335: step: 126/1545, loss: 0.0005034153582528234 2023-01-23 22:50:23.409832: step: 128/1545, loss: 0.0069167036563158035 2023-01-23 22:50:24.284270: step: 130/1545, loss: 0.00010276345710735768 2023-01-23 22:50:25.132117: step: 132/1545, loss: -6.808868874941254e-06 2023-01-23 22:50:26.023901: step: 134/1545, loss: 0.1093740165233612 2023-01-23 22:50:26.861627: step: 136/1545, loss: 0.0005072756903246045 2023-01-23 22:50:27.710626: step: 138/1545, loss: 0.01318230852484703 2023-01-23 22:50:28.618916: step: 140/1545, loss: 0.04285785183310509 2023-01-23 22:50:29.490823: step: 142/1545, loss: 0.0022751183714717627 2023-01-23 22:50:30.374347: step: 144/1545, loss: 0.04098394513130188 2023-01-23 22:50:31.239083: step: 146/1545, loss: 0.0021475625690072775 2023-01-23 22:50:32.078347: step: 148/1545, loss: 9.472923557041213e-05 2023-01-23 22:50:33.002539: step: 150/1545, loss: 0.00032730348175391555 2023-01-23 22:50:33.919300: step: 152/1545, loss: 0.12219966948032379 2023-01-23 22:50:34.801207: step: 154/1545, loss: 0.4095503091812134 2023-01-23 22:50:35.677490: step: 156/1545, loss: 1.2960864305496216 2023-01-23 22:50:36.669543: step: 158/1545, loss: 7.502939115511253e-05 2023-01-23 22:50:37.521826: step: 160/1545, loss: 2.9208182240836322e-05 2023-01-23 22:50:38.371360: step: 162/1545, loss: 0.03488169237971306 2023-01-23 22:50:39.283019: step: 164/1545, loss: 0.0028646395076066256 2023-01-23 22:50:40.216606: step: 166/1545, loss: 0.00015075798728503287 2023-01-23 22:50:41.092411: step: 168/1545, loss: 0.0009954378474503756 2023-01-23 22:50:41.953743: step: 170/1545, loss: 0.0002479642571415752 2023-01-23 22:50:42.822810: step: 172/1545, loss: 0.028630660846829414 2023-01-23 22:50:43.709676: step: 174/1545, loss: 0.0016495815943926573 2023-01-23 22:50:44.604825: step: 176/1545, loss: 0.00031385646434500813 2023-01-23 22:50:45.472908: step: 178/1545, loss: 0.00036241672933101654 2023-01-23 22:50:46.328338: step: 180/1545, loss: 0.03864859417080879 2023-01-23 22:50:47.198012: step: 182/1545, loss: 0.009660371579229832 2023-01-23 22:50:48.059028: step: 184/1545, loss: 0.00024494348326697946 2023-01-23 22:50:48.978411: step: 186/1545, loss: 0.0017494410276412964 2023-01-23 22:50:49.856240: step: 188/1545, loss: 0.005458784755319357 2023-01-23 22:50:50.734251: step: 190/1545, loss: 0.0033450659830123186 2023-01-23 22:50:51.569826: step: 192/1545, loss: 0.0002979733108077198 2023-01-23 22:50:52.506085: step: 194/1545, loss: 0.00016252337081823498 2023-01-23 22:50:53.402060: step: 196/1545, loss: 0.0177888385951519 2023-01-23 22:50:54.328733: step: 198/1545, loss: 0.0008818848291411996 2023-01-23 22:50:55.213113: step: 200/1545, loss: 0.0008187750936485827 2023-01-23 22:50:56.151176: step: 202/1545, loss: 0.011969991959631443 2023-01-23 22:50:57.048854: step: 204/1545, loss: 0.0011430642334744334 2023-01-23 22:50:57.901261: step: 206/1545, loss: 0.0061893826350569725 2023-01-23 22:50:58.751537: step: 208/1545, loss: 0.001376130385324359 2023-01-23 22:50:59.645245: step: 210/1545, loss: 0.017487742006778717 2023-01-23 22:51:00.503120: step: 212/1545, loss: 4.0935250581242144e-05 2023-01-23 22:51:01.387387: step: 214/1545, loss: 0.0007707455661147833 2023-01-23 22:51:02.235221: step: 216/1545, loss: 0.04791583865880966 2023-01-23 22:51:03.123258: step: 218/1545, loss: 8.872806938597932e-05 2023-01-23 22:51:04.003448: step: 220/1545, loss: 0.00011254311539232731 2023-01-23 22:51:04.939240: step: 222/1545, loss: 0.0023914624471217394 2023-01-23 22:51:05.849099: step: 224/1545, loss: 0.002657064702361822 2023-01-23 22:51:06.690211: step: 226/1545, loss: 1.8130987882614136e-05 2023-01-23 22:51:07.540950: step: 228/1545, loss: 0.00034966468228958547 2023-01-23 22:51:08.523528: step: 230/1545, loss: 1.6130803487612866e-05 2023-01-23 22:51:09.404614: step: 232/1545, loss: 0.016402309760451317 2023-01-23 22:51:10.321641: step: 234/1545, loss: 0.028725923970341682 2023-01-23 22:51:11.207677: step: 236/1545, loss: 0.021333569660782814 2023-01-23 22:51:12.121672: step: 238/1545, loss: 0.00013468116230797023 2023-01-23 22:51:13.016782: step: 240/1545, loss: 0.001714356243610382 2023-01-23 22:51:13.959685: step: 242/1545, loss: 0.0020332501735538244 2023-01-23 22:51:14.805392: step: 244/1545, loss: -1.0849535101442598e-05 2023-01-23 22:51:15.688867: step: 246/1545, loss: 0.00011239322338951752 2023-01-23 22:51:16.586728: step: 248/1545, loss: 0.14193594455718994 2023-01-23 22:51:17.506306: step: 250/1545, loss: 0.037825699895620346 2023-01-23 22:51:18.368112: step: 252/1545, loss: 0.22674110531806946 2023-01-23 22:51:19.235025: step: 254/1545, loss: 0.00876200757920742 2023-01-23 22:51:20.067768: step: 256/1545, loss: 4.731317676487379e-05 2023-01-23 22:51:21.006561: step: 258/1545, loss: 9.402621117260423e-07 2023-01-23 22:51:21.901236: step: 260/1545, loss: 0.008299573324620724 2023-01-23 22:51:22.783469: step: 262/1545, loss: 3.585900049074553e-05 2023-01-23 22:51:23.676649: step: 264/1545, loss: 2.6586649255477823e-05 2023-01-23 22:51:24.514748: step: 266/1545, loss: 1.488268480898114e-05 2023-01-23 22:51:25.432250: step: 268/1545, loss: 0.6145203709602356 2023-01-23 22:51:26.298099: step: 270/1545, loss: 0.0021298450883477926 2023-01-23 22:51:27.137921: step: 272/1545, loss: 0.0013286954490467906 2023-01-23 22:51:27.979655: step: 274/1545, loss: -1.0597706932458095e-05 2023-01-23 22:51:28.887789: step: 276/1545, loss: -2.0096293155802414e-05 2023-01-23 22:51:29.806801: step: 278/1545, loss: 1.666844036662951e-05 2023-01-23 22:51:30.742578: step: 280/1545, loss: 1.877605973277241e-05 2023-01-23 22:51:31.636981: step: 282/1545, loss: 0.001203989959321916 2023-01-23 22:51:32.505809: step: 284/1545, loss: 3.635525717982091e-05 2023-01-23 22:51:33.373386: step: 286/1545, loss: 2.4723258320591412e-05 2023-01-23 22:51:34.269237: step: 288/1545, loss: 2.118901647918392e-05 2023-01-23 22:51:35.151380: step: 290/1545, loss: 0.00039285191451199353 2023-01-23 22:51:35.988571: step: 292/1545, loss: 0.00018561467004474252 2023-01-23 22:51:36.823931: step: 294/1545, loss: 0.0003472572425380349 2023-01-23 22:51:37.741712: step: 296/1545, loss: 6.128003587946296e-05 2023-01-23 22:51:38.601952: step: 298/1545, loss: 8.404105028603226e-05 2023-01-23 22:51:39.505257: step: 300/1545, loss: 0.346867173910141 2023-01-23 22:51:40.347042: step: 302/1545, loss: 0.09892917424440384 2023-01-23 22:51:41.182425: step: 304/1545, loss: 0.0006872612866573036 2023-01-23 22:51:42.083497: step: 306/1545, loss: 0.000406590843340382 2023-01-23 22:51:42.965556: step: 308/1545, loss: 0.00113432586658746 2023-01-23 22:51:43.835426: step: 310/1545, loss: 0.00033734433236531913 2023-01-23 22:51:44.785804: step: 312/1545, loss: 7.518643542425707e-05 2023-01-23 22:51:45.685430: step: 314/1545, loss: 0.05334608629345894 2023-01-23 22:51:46.571021: step: 316/1545, loss: -2.136230432370212e-05 2023-01-23 22:51:47.438360: step: 318/1545, loss: -3.2203399314312264e-05 2023-01-23 22:51:48.396920: step: 320/1545, loss: -4.0411949157714844e-05 2023-01-23 22:51:49.294912: step: 322/1545, loss: 5.473432975122705e-05 2023-01-23 22:51:50.196918: step: 324/1545, loss: -3.471374657237902e-05 2023-01-23 22:51:51.068997: step: 326/1545, loss: 0.0005086641758680344 2023-01-23 22:51:51.956561: step: 328/1545, loss: 1.221199727297062e-05 2023-01-23 22:51:52.859128: step: 330/1545, loss: 3.010430737049319e-05 2023-01-23 22:51:53.745004: step: 332/1545, loss: 0.17159399390220642 2023-01-23 22:51:54.630805: step: 334/1545, loss: 8.972203431767412e-06 2023-01-23 22:51:55.543108: step: 336/1545, loss: 0.000699349504429847 2023-01-23 22:51:56.504278: step: 338/1545, loss: 0.0011661127209663391 2023-01-23 22:51:57.375697: step: 340/1545, loss: 0.21508213877677917 2023-01-23 22:51:58.232925: step: 342/1545, loss: 0.00022528257977683097 2023-01-23 22:51:59.131429: step: 344/1545, loss: 6.027448762324639e-05 2023-01-23 22:52:00.038974: step: 346/1545, loss: 0.06215444207191467 2023-01-23 22:52:00.897918: step: 348/1545, loss: 0.1058834046125412 2023-01-23 22:52:01.758214: step: 350/1545, loss: 0.00031832122476771474 2023-01-23 22:52:02.674802: step: 352/1545, loss: 0.0028988230042159557 2023-01-23 22:52:03.546547: step: 354/1545, loss: 0.0001868516264948994 2023-01-23 22:52:04.464312: step: 356/1545, loss: 0.0008622920140624046 2023-01-23 22:52:05.342815: step: 358/1545, loss: 0.00019021831394638866 2023-01-23 22:52:06.196899: step: 360/1545, loss: 0.0002484506112523377 2023-01-23 22:52:07.080407: step: 362/1545, loss: 8.112718933261931e-05 2023-01-23 22:52:07.994936: step: 364/1545, loss: -2.4870094421203248e-05 2023-01-23 22:52:08.917501: step: 366/1545, loss: 0.00046326377196237445 2023-01-23 22:52:09.752405: step: 368/1545, loss: 0.08520511537790298 2023-01-23 22:52:10.618527: step: 370/1545, loss: 0.00031237280927598476 2023-01-23 22:52:11.477239: step: 372/1545, loss: 0.09162569046020508 2023-01-23 22:52:12.356281: step: 374/1545, loss: 0.0027292321901768446 2023-01-23 22:52:13.195508: step: 376/1545, loss: -3.6819023080170155e-05 2023-01-23 22:52:14.068571: step: 378/1545, loss: 0.00012692176096607 2023-01-23 22:52:14.916965: step: 380/1545, loss: 0.00011965379235334694 2023-01-23 22:52:15.767428: step: 382/1545, loss: 0.10395608097314835 2023-01-23 22:52:16.620188: step: 384/1545, loss: 1.983751826628577e-05 2023-01-23 22:52:17.493232: step: 386/1545, loss: 2.9593704311992042e-05 2023-01-23 22:52:18.406052: step: 388/1545, loss: 0.23407793045043945 2023-01-23 22:52:19.310795: step: 390/1545, loss: 0.21300780773162842 2023-01-23 22:52:20.201964: step: 392/1545, loss: 0.0016896434826776385 2023-01-23 22:52:21.081873: step: 394/1545, loss: 0.021076975390315056 2023-01-23 22:52:21.927575: step: 396/1545, loss: -1.4618042314396007e-06 2023-01-23 22:52:22.812858: step: 398/1545, loss: 4.1436396713834256e-05 2023-01-23 22:52:23.706528: step: 400/1545, loss: 0.21907982230186462 2023-01-23 22:52:24.619881: step: 402/1545, loss: 0.0006106191431172192 2023-01-23 22:52:25.502333: step: 404/1545, loss: 9.074583067558706e-05 2023-01-23 22:52:26.409318: step: 406/1545, loss: 0.0007925046375021338 2023-01-23 22:52:27.232353: step: 408/1545, loss: 3.394821032998152e-05 2023-01-23 22:52:28.135838: step: 410/1545, loss: 0.00010653082426870242 2023-01-23 22:52:28.992098: step: 412/1545, loss: 0.00013618430239148438 2023-01-23 22:52:29.890856: step: 414/1545, loss: -4.1160361433867365e-05 2023-01-23 22:52:30.822772: step: 416/1545, loss: -3.3840038668131456e-05 2023-01-23 22:52:31.708641: step: 418/1545, loss: 1.5463232557522133e-05 2023-01-23 22:52:32.532871: step: 420/1545, loss: 1.679323577263858e-05 2023-01-23 22:52:33.398752: step: 422/1545, loss: 0.12532442808151245 2023-01-23 22:52:34.268677: step: 424/1545, loss: 0.004510423168540001 2023-01-23 22:52:35.119736: step: 426/1545, loss: 0.0005237912409938872 2023-01-23 22:52:36.014770: step: 428/1545, loss: 0.05307918041944504 2023-01-23 22:52:36.885256: step: 430/1545, loss: 0.04234500229358673 2023-01-23 22:52:37.843842: step: 432/1545, loss: 0.0009773041820153594 2023-01-23 22:52:38.788423: step: 434/1545, loss: 0.12731362879276276 2023-01-23 22:52:39.670584: step: 436/1545, loss: -1.4805929822614416e-05 2023-01-23 22:52:40.540185: step: 438/1545, loss: 2.4509261493221857e-05 2023-01-23 22:52:41.394643: step: 440/1545, loss: 0.3058044910430908 2023-01-23 22:52:42.256156: step: 442/1545, loss: 0.0014293038984760642 2023-01-23 22:52:43.160703: step: 444/1545, loss: 2.3438988137058914e-05 2023-01-23 22:52:44.054776: step: 446/1545, loss: -6.908477371325716e-05 2023-01-23 22:52:44.969113: step: 448/1545, loss: 0.009160851128399372 2023-01-23 22:52:45.840171: step: 450/1545, loss: 9.62465946940938e-06 2023-01-23 22:52:46.741410: step: 452/1545, loss: -3.0824543500784785e-05 2023-01-23 22:52:47.635566: step: 454/1545, loss: 0.07193814963102341 2023-01-23 22:52:48.527975: step: 456/1545, loss: 1.662682007008698e-05 2023-01-23 22:52:49.386031: step: 458/1545, loss: -6.172427674755454e-05 2023-01-23 22:52:50.244071: step: 460/1545, loss: 0.03459778055548668 2023-01-23 22:52:51.132019: step: 462/1545, loss: 5.851194873685017e-05 2023-01-23 22:52:51.998440: step: 464/1545, loss: 0.0035363617353141308 2023-01-23 22:52:52.834490: step: 466/1545, loss: -2.4011731511563994e-05 2023-01-23 22:52:53.762941: step: 468/1545, loss: 8.60333238961175e-06 2023-01-23 22:52:54.641394: step: 470/1545, loss: 0.009293044917285442 2023-01-23 22:52:55.501028: step: 472/1545, loss: 7.310135697480291e-05 2023-01-23 22:52:56.387738: step: 474/1545, loss: 0.020967725664377213 2023-01-23 22:52:57.264045: step: 476/1545, loss: 0.23711879551410675 2023-01-23 22:52:58.092786: step: 478/1545, loss: -3.3266765967709944e-05 2023-01-23 22:52:58.998410: step: 480/1545, loss: 0.13036984205245972 2023-01-23 22:52:59.879180: step: 482/1545, loss: -1.1528285540407524e-05 2023-01-23 22:53:00.761452: step: 484/1545, loss: 0.5049383044242859 2023-01-23 22:53:01.646079: step: 486/1545, loss: 0.01818479225039482 2023-01-23 22:53:02.533388: step: 488/1545, loss: 0.012036876752972603 2023-01-23 22:53:03.398261: step: 490/1545, loss: 1.2208023690618575e-05 2023-01-23 22:53:04.330646: step: 492/1545, loss: 0.0015024710446596146 2023-01-23 22:53:05.223709: step: 494/1545, loss: -6.467103958129883e-06 2023-01-23 22:53:06.093993: step: 496/1545, loss: 0.00015726499259471893 2023-01-23 22:53:06.963712: step: 498/1545, loss: -3.546774314600043e-05 2023-01-23 22:53:07.807320: step: 500/1545, loss: -5.918880560784601e-06 2023-01-23 22:53:08.632661: step: 502/1545, loss: 0.0008082481799647212 2023-01-23 22:53:09.483076: step: 504/1545, loss: 5.712408892577514e-07 2023-01-23 22:53:10.378236: step: 506/1545, loss: 3.743546403711662e-05 2023-01-23 22:53:11.222252: step: 508/1545, loss: 0.010083138011395931 2023-01-23 22:53:12.126143: step: 510/1545, loss: -3.2815340091474354e-05 2023-01-23 22:53:13.021760: step: 512/1545, loss: 1.1288375389995053e-05 2023-01-23 22:53:13.860892: step: 514/1545, loss: 0.00037394039100036025 2023-01-23 22:53:14.792791: step: 516/1545, loss: 0.6557186841964722 2023-01-23 22:53:15.732143: step: 518/1545, loss: 0.7519674897193909 2023-01-23 22:53:16.588011: step: 520/1545, loss: 0.00012779356620740145 2023-01-23 22:53:17.518592: step: 522/1545, loss: -3.4318120015086606e-05 2023-01-23 22:53:18.417452: step: 524/1545, loss: 0.00046759782708249986 2023-01-23 22:53:19.324047: step: 526/1545, loss: 0.0005047625163570046 2023-01-23 22:53:20.244735: step: 528/1545, loss: 2.9976779842399992e-05 2023-01-23 22:53:21.095621: step: 530/1545, loss: 4.773447926709196e-06 2023-01-23 22:53:21.966961: step: 532/1545, loss: 9.871927613858134e-05 2023-01-23 22:53:22.839326: step: 534/1545, loss: 1.4769034351047594e-05 2023-01-23 22:53:23.748519: step: 536/1545, loss: 0.022032292559742928 2023-01-23 22:53:24.589128: step: 538/1545, loss: -1.1024376362911426e-05 2023-01-23 22:53:25.490236: step: 540/1545, loss: 0.0032473879400640726 2023-01-23 22:53:26.354304: step: 542/1545, loss: 0.00730747589841485 2023-01-23 22:53:27.233410: step: 544/1545, loss: 0.017357707023620605 2023-01-23 22:53:28.121438: step: 546/1545, loss: 3.0270120987552218e-05 2023-01-23 22:53:29.046611: step: 548/1545, loss: 0.004443494603037834 2023-01-23 22:53:29.898815: step: 550/1545, loss: 6.683100218651816e-05 2023-01-23 22:53:30.822414: step: 552/1545, loss: 0.0026749339886009693 2023-01-23 22:53:31.714803: step: 554/1545, loss: 7.866797386668622e-05 2023-01-23 22:53:32.643914: step: 556/1545, loss: 0.0005362886586226523 2023-01-23 22:53:33.510687: step: 558/1545, loss: 0.02515464276075363 2023-01-23 22:53:34.374199: step: 560/1545, loss: 0.0010422092163935304 2023-01-23 22:53:35.251327: step: 562/1545, loss: 6.349614704959095e-05 2023-01-23 22:53:36.132131: step: 564/1545, loss: 7.818300218787044e-05 2023-01-23 22:53:37.042238: step: 566/1545, loss: 0.20815768837928772 2023-01-23 22:53:37.912224: step: 568/1545, loss: 5.345093450159766e-05 2023-01-23 22:53:38.756391: step: 570/1545, loss: 3.319256938993931e-05 2023-01-23 22:53:39.625151: step: 572/1545, loss: 0.07386358082294464 2023-01-23 22:53:40.521419: step: 574/1545, loss: 0.0002377192140556872 2023-01-23 22:53:41.447391: step: 576/1545, loss: 1.679145498201251e-05 2023-01-23 22:53:42.338063: step: 578/1545, loss: -3.0084622267168015e-05 2023-01-23 22:53:43.261098: step: 580/1545, loss: 0.07457469403743744 2023-01-23 22:53:44.122497: step: 582/1545, loss: 0.06505895406007767 2023-01-23 22:53:45.013491: step: 584/1545, loss: 0.06414644420146942 2023-01-23 22:53:45.862915: step: 586/1545, loss: 0.001338569214567542 2023-01-23 22:53:46.698141: step: 588/1545, loss: 0.003371956292539835 2023-01-23 22:53:47.553057: step: 590/1545, loss: 0.000307829468511045 2023-01-23 22:53:48.436451: step: 592/1545, loss: 0.04106047376990318 2023-01-23 22:53:49.399153: step: 594/1545, loss: 3.2278891012538224e-05 2023-01-23 22:53:50.292847: step: 596/1545, loss: 0.00013401219621300697 2023-01-23 22:53:51.186309: step: 598/1545, loss: 0.0003212339652236551 2023-01-23 22:53:52.129232: step: 600/1545, loss: 0.39333242177963257 2023-01-23 22:53:52.999475: step: 602/1545, loss: 0.0008503628196194768 2023-01-23 22:53:53.890803: step: 604/1545, loss: 0.045038849115371704 2023-01-23 22:53:54.770190: step: 606/1545, loss: 0.0001432623394066468 2023-01-23 22:53:55.628956: step: 608/1545, loss: 0.002273389371111989 2023-01-23 22:53:56.486307: step: 610/1545, loss: -1.293024979531765e-05 2023-01-23 22:53:57.369847: step: 612/1545, loss: 0.20284345746040344 2023-01-23 22:53:58.229648: step: 614/1545, loss: 0.8214347958564758 2023-01-23 22:53:59.097962: step: 616/1545, loss: 2.0171908545307815e-05 2023-01-23 22:53:59.971749: step: 618/1545, loss: 0.0012912920210510492 2023-01-23 22:54:00.828097: step: 620/1545, loss: 0.0011256502475589514 2023-01-23 22:54:01.719535: step: 622/1545, loss: 5.906893784413114e-05 2023-01-23 22:54:02.610019: step: 624/1545, loss: 0.21518300473690033 2023-01-23 22:54:03.510851: step: 626/1545, loss: 0.004414222203195095 2023-01-23 22:54:04.403920: step: 628/1545, loss: 0.011162957176566124 2023-01-23 22:54:05.275498: step: 630/1545, loss: 2.1412246227264404 2023-01-23 22:54:06.208884: step: 632/1545, loss: 0.18818442523479462 2023-01-23 22:54:07.120333: step: 634/1545, loss: 0.011625838465988636 2023-01-23 22:54:08.009977: step: 636/1545, loss: 0.0032913375180214643 2023-01-23 22:54:08.855039: step: 638/1545, loss: 0.5961415767669678 2023-01-23 22:54:09.732715: step: 640/1545, loss: 9.264636901207268e-05 2023-01-23 22:54:10.632055: step: 642/1545, loss: 0.0004343550535850227 2023-01-23 22:54:11.593826: step: 644/1545, loss: 0.00012438550766091794 2023-01-23 22:54:12.468423: step: 646/1545, loss: 0.00030891693313606083 2023-01-23 22:54:13.319460: step: 648/1545, loss: 0.0003016257251147181 2023-01-23 22:54:14.203317: step: 650/1545, loss: 0.004366012290120125 2023-01-23 22:54:15.042557: step: 652/1545, loss: 4.3629603169392794e-05 2023-01-23 22:54:15.891096: step: 654/1545, loss: 9.156185842584819e-05 2023-01-23 22:54:16.742805: step: 656/1545, loss: 0.0021697492338716984 2023-01-23 22:54:17.609873: step: 658/1545, loss: 0.26082825660705566 2023-01-23 22:54:18.465108: step: 660/1545, loss: 0.00011348292900947854 2023-01-23 22:54:19.384519: step: 662/1545, loss: 0.5926402807235718 2023-01-23 22:54:20.273298: step: 664/1545, loss: 4.5222463086247444e-05 2023-01-23 22:54:21.154396: step: 666/1545, loss: 7.35629364498891e-05 2023-01-23 22:54:22.059735: step: 668/1545, loss: 4.822980554308742e-05 2023-01-23 22:54:22.907295: step: 670/1545, loss: 2.3234348191181198e-05 2023-01-23 22:54:23.738257: step: 672/1545, loss: 0.00012630918354261667 2023-01-23 22:54:24.630969: step: 674/1545, loss: 0.006503380369395018 2023-01-23 22:54:25.486481: step: 676/1545, loss: 0.0003829397610388696 2023-01-23 22:54:26.359337: step: 678/1545, loss: 0.00010489705164218321 2023-01-23 22:54:27.198791: step: 680/1545, loss: 0.00046773310168646276 2023-01-23 22:54:28.104212: step: 682/1545, loss: 0.0045467037707567215 2023-01-23 22:54:29.033001: step: 684/1545, loss: 7.030383858364075e-05 2023-01-23 22:54:29.869416: step: 686/1545, loss: 8.070915646385401e-05 2023-01-23 22:54:30.721043: step: 688/1545, loss: 0.0012621430214494467 2023-01-23 22:54:31.636295: step: 690/1545, loss: 0.00010414422285975888 2023-01-23 22:54:32.537089: step: 692/1545, loss: 0.366082102060318 2023-01-23 22:54:33.389626: step: 694/1545, loss: 0.00010190013563260436 2023-01-23 22:54:34.309929: step: 696/1545, loss: 0.25955864787101746 2023-01-23 22:54:35.160690: step: 698/1545, loss: 0.028904352337121964 2023-01-23 22:54:36.032399: step: 700/1545, loss: 0.00040833355160430074 2023-01-23 22:54:36.876340: step: 702/1545, loss: 1.0753626156656537e-05 2023-01-23 22:54:37.724910: step: 704/1545, loss: -4.7137569936239743e-07 2023-01-23 22:54:38.554921: step: 706/1545, loss: 0.000983540085144341 2023-01-23 22:54:39.414326: step: 708/1545, loss: 0.0014427709393203259 2023-01-23 22:54:40.280307: step: 710/1545, loss: 0.0010762503370642662 2023-01-23 22:54:41.152268: step: 712/1545, loss: 0.14097757637500763 2023-01-23 22:54:41.991613: step: 714/1545, loss: 0.0054880171082913876 2023-01-23 22:54:42.900146: step: 716/1545, loss: 0.0002330150455236435 2023-01-23 22:54:43.803387: step: 718/1545, loss: 0.02922697365283966 2023-01-23 22:54:44.706988: step: 720/1545, loss: 1.4854100299999118e-05 2023-01-23 22:54:45.591412: step: 722/1545, loss: -9.617167961550876e-06 2023-01-23 22:54:46.492743: step: 724/1545, loss: 0.00010223388380836695 2023-01-23 22:54:47.371632: step: 726/1545, loss: 0.0015329808229580522 2023-01-23 22:54:48.226509: step: 728/1545, loss: 0.11389866471290588 2023-01-23 22:54:49.133580: step: 730/1545, loss: 0.0014004004187881947 2023-01-23 22:54:49.972960: step: 732/1545, loss: 0.2049533873796463 2023-01-23 22:54:50.826680: step: 734/1545, loss: 0.0021543793845921755 2023-01-23 22:54:51.755310: step: 736/1545, loss: 0.08497058600187302 2023-01-23 22:54:52.745918: step: 738/1545, loss: 0.00226513366214931 2023-01-23 22:54:53.748946: step: 740/1545, loss: -2.244200004497543e-05 2023-01-23 22:54:54.663900: step: 742/1545, loss: 0.038614340126514435 2023-01-23 22:54:55.649756: step: 744/1545, loss: 0.16663525998592377 2023-01-23 22:54:56.531638: step: 746/1545, loss: 0.4891749918460846 2023-01-23 22:54:57.371361: step: 748/1545, loss: 0.0023916601203382015 2023-01-23 22:54:58.229493: step: 750/1545, loss: 0.00030589100788347423 2023-01-23 22:54:59.071621: step: 752/1545, loss: -1.5791854821145535e-05 2023-01-23 22:54:59.916315: step: 754/1545, loss: 1.7531507182866335e-05 2023-01-23 22:55:00.815747: step: 756/1545, loss: 0.018375659361481667 2023-01-23 22:55:01.721653: step: 758/1545, loss: 0.0007747066556476057 2023-01-23 22:55:02.585458: step: 760/1545, loss: 0.005564122460782528 2023-01-23 22:55:03.467516: step: 762/1545, loss: -8.002824324648827e-05 2023-01-23 22:55:04.326765: step: 764/1545, loss: 0.0007944109383970499 2023-01-23 22:55:05.276961: step: 766/1545, loss: 0.0004697452823165804 2023-01-23 22:55:06.158961: step: 768/1545, loss: 0.00028720765840262175 2023-01-23 22:55:07.053928: step: 770/1545, loss: 0.0016831336542963982 2023-01-23 22:55:07.929035: step: 772/1545, loss: 0.56636643409729 2023-01-23 22:55:08.834545: step: 774/1545, loss: 0.00010494673915673047 2023-01-23 22:55:09.702753: step: 776/1545, loss: 0.0006094485288485885 2023-01-23 22:55:10.545983: step: 778/1545, loss: 0.121507927775383 2023-01-23 22:55:11.415441: step: 780/1545, loss: 0.0032517018262296915 2023-01-23 22:55:12.266475: step: 782/1545, loss: 4.194170469418168e-05 2023-01-23 22:55:13.144693: step: 784/1545, loss: 0.0009293427574448287 2023-01-23 22:55:14.039746: step: 786/1545, loss: 0.178207665681839 2023-01-23 22:55:14.893771: step: 788/1545, loss: 0.00014943425776436925 2023-01-23 22:55:15.755548: step: 790/1545, loss: 0.08675356209278107 2023-01-23 22:55:16.623893: step: 792/1545, loss: 3.225371256121434e-05 2023-01-23 22:55:17.469113: step: 794/1545, loss: 1.8931719750980847e-05 2023-01-23 22:55:18.350294: step: 796/1545, loss: 0.0019096373580396175 2023-01-23 22:55:19.249058: step: 798/1545, loss: 8.393327334488276e-06 2023-01-23 22:55:20.151752: step: 800/1545, loss: 4.1881681681843475e-05 2023-01-23 22:55:21.077325: step: 802/1545, loss: 3.418277992750518e-05 2023-01-23 22:55:21.954326: step: 804/1545, loss: 3.389576158951968e-05 2023-01-23 22:55:22.819358: step: 806/1545, loss: 0.002273775637149811 2023-01-23 22:55:23.667533: step: 808/1545, loss: 0.027140434831380844 2023-01-23 22:55:24.601265: step: 810/1545, loss: 0.0003439848660491407 2023-01-23 22:55:25.503972: step: 812/1545, loss: 0.0003986075462307781 2023-01-23 22:55:26.448162: step: 814/1545, loss: 3.759911851375364e-05 2023-01-23 22:55:27.311635: step: 816/1545, loss: 0.017448527738451958 2023-01-23 22:55:28.148455: step: 818/1545, loss: 0.0011807458940893412 2023-01-23 22:55:29.022478: step: 820/1545, loss: 0.008726190775632858 2023-01-23 22:55:29.860583: step: 822/1545, loss: 0.0167700182646513 2023-01-23 22:55:30.786959: step: 824/1545, loss: 0.0003777618985623121 2023-01-23 22:55:31.696035: step: 826/1545, loss: -3.5545688206184423e-06 2023-01-23 22:55:32.557555: step: 828/1545, loss: -1.442753000446828e-05 2023-01-23 22:55:33.464498: step: 830/1545, loss: 0.0005674249259755015 2023-01-23 22:55:34.372471: step: 832/1545, loss: 9.461235094931908e-06 2023-01-23 22:55:35.244235: step: 834/1545, loss: 0.011543822474777699 2023-01-23 22:55:36.129782: step: 836/1545, loss: 0.6853762865066528 2023-01-23 22:55:36.985366: step: 838/1545, loss: 0.00011300733604002744 2023-01-23 22:55:37.909557: step: 840/1545, loss: 4.1999817767646164e-05 2023-01-23 22:55:38.739078: step: 842/1545, loss: 0.0009868494234979153 2023-01-23 22:55:39.615925: step: 844/1545, loss: 0.002494711661711335 2023-01-23 22:55:40.515493: step: 846/1545, loss: 6.0533187934197485e-05 2023-01-23 22:55:41.405988: step: 848/1545, loss: 0.0035606531891971827 2023-01-23 22:55:42.298670: step: 850/1545, loss: 0.0026658792048692703 2023-01-23 22:55:43.231547: step: 852/1545, loss: 0.6259492039680481 2023-01-23 22:55:44.100262: step: 854/1545, loss: 0.0014710426330566406 2023-01-23 22:55:45.006298: step: 856/1545, loss: 5.800843064207584e-05 2023-01-23 22:55:45.906825: step: 858/1545, loss: 0.15482230484485626 2023-01-23 22:55:46.780853: step: 860/1545, loss: 4.861201887251809e-05 2023-01-23 22:55:47.680120: step: 862/1545, loss: 0.00010304972238373011 2023-01-23 22:55:48.568512: step: 864/1545, loss: 4.480329153011553e-05 2023-01-23 22:55:49.499073: step: 866/1545, loss: 7.120371265045833e-06 2023-01-23 22:55:50.442507: step: 868/1545, loss: 0.003414321690797806 2023-01-23 22:55:51.328852: step: 870/1545, loss: 1.0640771389007568 2023-01-23 22:55:52.229723: step: 872/1545, loss: 0.0030826914589852095 2023-01-23 22:55:53.122393: step: 874/1545, loss: 0.002184733748435974 2023-01-23 22:55:54.004100: step: 876/1545, loss: 0.003868160303682089 2023-01-23 22:55:54.910008: step: 878/1545, loss: 0.0012709106085821986 2023-01-23 22:55:55.789285: step: 880/1545, loss: 0.0001435067388229072 2023-01-23 22:55:56.650754: step: 882/1545, loss: 0.00033744648681022227 2023-01-23 22:55:57.520279: step: 884/1545, loss: 0.002825002418830991 2023-01-23 22:55:58.376059: step: 886/1545, loss: 0.017980987206101418 2023-01-23 22:55:59.255529: step: 888/1545, loss: 0.004624843131750822 2023-01-23 22:56:00.136738: step: 890/1545, loss: 0.0007413086714223027 2023-01-23 22:56:01.019711: step: 892/1545, loss: 0.004158888012170792 2023-01-23 22:56:01.904948: step: 894/1545, loss: 0.0012700532097369432 2023-01-23 22:56:02.745681: step: 896/1545, loss: 0.0009820277336984873 2023-01-23 22:56:03.688081: step: 898/1545, loss: 0.01528716180473566 2023-01-23 22:56:04.582579: step: 900/1545, loss: -2.0867020793957636e-05 2023-01-23 22:56:05.465020: step: 902/1545, loss: -2.911837691499386e-05 2023-01-23 22:56:06.316565: step: 904/1545, loss: 1.7176225810544565e-05 2023-01-23 22:56:07.240407: step: 906/1545, loss: 0.575721263885498 2023-01-23 22:56:08.125823: step: 908/1545, loss: -3.9614737033843994e-05 2023-01-23 22:56:08.997486: step: 910/1545, loss: 0.0008661175961606205 2023-01-23 22:56:09.873971: step: 912/1545, loss: 1.2074187907273881e-05 2023-01-23 22:56:10.717302: step: 914/1545, loss: 0.01702522672712803 2023-01-23 22:56:11.607146: step: 916/1545, loss: 0.5391662120819092 2023-01-23 22:56:12.556471: step: 918/1545, loss: 0.029921695590019226 2023-01-23 22:56:13.422937: step: 920/1545, loss: 3.148346513626166e-05 2023-01-23 22:56:14.284696: step: 922/1545, loss: 0.0010747992200776935 2023-01-23 22:56:15.139430: step: 924/1545, loss: -2.770513492578175e-05 2023-01-23 22:56:16.055521: step: 926/1545, loss: -3.356263187015429e-05 2023-01-23 22:56:16.992484: step: 928/1545, loss: 0.1805018186569214 2023-01-23 22:56:17.881088: step: 930/1545, loss: 0.00016061619680840522 2023-01-23 22:56:18.743494: step: 932/1545, loss: 3.300085154478438e-05 2023-01-23 22:56:19.649037: step: 934/1545, loss: 0.00013638523523695767 2023-01-23 22:56:20.523365: step: 936/1545, loss: 0.0190401803702116 2023-01-23 22:56:21.432159: step: 938/1545, loss: 0.4997352659702301 2023-01-23 22:56:22.280729: step: 940/1545, loss: 0.00014004310651216656 2023-01-23 22:56:23.180939: step: 942/1545, loss: 0.040050581097602844 2023-01-23 22:56:24.020261: step: 944/1545, loss: 1.4884770280332305e-05 2023-01-23 22:56:24.894114: step: 946/1545, loss: 0.0016372876707464457 2023-01-23 22:56:25.753579: step: 948/1545, loss: 0.003995271399617195 2023-01-23 22:56:26.662872: step: 950/1545, loss: 0.018612906336784363 2023-01-23 22:56:27.502209: step: 952/1545, loss: 6.728285370627418e-05 2023-01-23 22:56:28.442951: step: 954/1545, loss: 5.030677129980177e-05 2023-01-23 22:56:29.307396: step: 956/1545, loss: 0.00043020621524192393 2023-01-23 22:56:30.171929: step: 958/1545, loss: 3.6424837162485346e-05 2023-01-23 22:56:31.048612: step: 960/1545, loss: 6.281708920141682e-06 2023-01-23 22:56:31.945595: step: 962/1545, loss: 6.909395779075567e-06 2023-01-23 22:56:32.781399: step: 964/1545, loss: 5.3106265113456175e-05 2023-01-23 22:56:33.672531: step: 966/1545, loss: 0.008594844490289688 2023-01-23 22:56:34.537876: step: 968/1545, loss: 0.023920636624097824 2023-01-23 22:56:35.370500: step: 970/1545, loss: 0.003207168309018016 2023-01-23 22:56:36.221414: step: 972/1545, loss: 3.062039832002483e-05 2023-01-23 22:56:37.091604: step: 974/1545, loss: 0.10890523344278336 2023-01-23 22:56:37.985987: step: 976/1545, loss: 0.0001379642344545573 2023-01-23 22:56:38.907999: step: 978/1545, loss: 0.023342091590166092 2023-01-23 22:56:39.823909: step: 980/1545, loss: 0.0010187869193032384 2023-01-23 22:56:40.678741: step: 982/1545, loss: 1.1133970474475063e-05 2023-01-23 22:56:41.565029: step: 984/1545, loss: 4.611571421264671e-05 2023-01-23 22:56:42.485357: step: 986/1545, loss: 0.006444892846047878 2023-01-23 22:56:43.309921: step: 988/1545, loss: 0.0002655824937392026 2023-01-23 22:56:44.154161: step: 990/1545, loss: 8.69870200403966e-05 2023-01-23 22:56:45.029066: step: 992/1545, loss: 0.0010378769366070628 2023-01-23 22:56:45.886675: step: 994/1545, loss: 0.014001196250319481 2023-01-23 22:56:46.818593: step: 996/1545, loss: 0.09493575245141983 2023-01-23 22:56:47.718855: step: 998/1545, loss: 0.07515399903059006 2023-01-23 22:56:48.596318: step: 1000/1545, loss: 0.008288117125630379 2023-01-23 22:56:49.519044: step: 1002/1545, loss: 0.0029959154780954123 2023-01-23 22:56:50.415923: step: 1004/1545, loss: 0.0009667605045251548 2023-01-23 22:56:51.385618: step: 1006/1545, loss: -2.9629967684741132e-05 2023-01-23 22:56:52.274267: step: 1008/1545, loss: 0.0029506117571145296 2023-01-23 22:56:53.122585: step: 1010/1545, loss: 2.8862657927675173e-05 2023-01-23 22:56:54.019060: step: 1012/1545, loss: 1.7666248083114624 2023-01-23 22:56:54.880869: step: 1014/1545, loss: 0.0001556471106596291 2023-01-23 22:56:55.756924: step: 1016/1545, loss: 0.0029998747631907463 2023-01-23 22:56:56.643388: step: 1018/1545, loss: 0.24258331954479218 2023-01-23 22:56:57.494210: step: 1020/1545, loss: 0.001499064965173602 2023-01-23 22:56:58.385928: step: 1022/1545, loss: 0.00015172836720012128 2023-01-23 22:56:59.253123: step: 1024/1545, loss: 3.967370139434934e-05 2023-01-23 22:57:00.108238: step: 1026/1545, loss: 2.5574105166015215e-05 2023-01-23 22:57:00.988656: step: 1028/1545, loss: 1.8961354726343416e-05 2023-01-23 22:57:01.866662: step: 1030/1545, loss: 0.00028787669725716114 2023-01-23 22:57:02.739243: step: 1032/1545, loss: 0.010453769937157631 2023-01-23 22:57:03.634238: step: 1034/1545, loss: 1.5258792700478807e-06 2023-01-23 22:57:04.517095: step: 1036/1545, loss: -6.821018814662239e-06 2023-01-23 22:57:05.379406: step: 1038/1545, loss: 0.11219961196184158 2023-01-23 22:57:06.319653: step: 1040/1545, loss: 0.028040144592523575 2023-01-23 22:57:07.257397: step: 1042/1545, loss: -3.1129664421314374e-05 2023-01-23 22:57:08.120153: step: 1044/1545, loss: 0.00585025642067194 2023-01-23 22:57:08.967032: step: 1046/1545, loss: 0.00031701679108664393 2023-01-23 22:57:09.816982: step: 1048/1545, loss: 6.489099905593321e-05 2023-01-23 22:57:10.757257: step: 1050/1545, loss: 0.020913705229759216 2023-01-23 22:57:11.685674: step: 1052/1545, loss: 0.21817725896835327 2023-01-23 22:57:12.592179: step: 1054/1545, loss: 0.016400374472141266 2023-01-23 22:57:13.468091: step: 1056/1545, loss: 0.02204727940261364 2023-01-23 22:57:14.368719: step: 1058/1545, loss: 0.8403633832931519 2023-01-23 22:57:15.331246: step: 1060/1545, loss: 0.00032056166674010456 2023-01-23 22:57:16.166516: step: 1062/1545, loss: 1.2328202956268797e-06 2023-01-23 22:57:16.986824: step: 1064/1545, loss: 0.000907838752027601 2023-01-23 22:57:17.873579: step: 1066/1545, loss: 0.0015777562512084842 2023-01-23 22:57:18.710588: step: 1068/1545, loss: 0.0006113460403867066 2023-01-23 22:57:19.547404: step: 1070/1545, loss: 0.0031012760009616613 2023-01-23 22:57:20.427500: step: 1072/1545, loss: 4.5997869165148586e-05 2023-01-23 22:57:21.350904: step: 1074/1545, loss: -4.525758868112462e-06 2023-01-23 22:57:22.227973: step: 1076/1545, loss: 0.000762993935495615 2023-01-23 22:57:23.092891: step: 1078/1545, loss: 0.00019154668552801013 2023-01-23 22:57:23.943199: step: 1080/1545, loss: 9.728939039632678e-05 2023-01-23 22:57:24.795581: step: 1082/1545, loss: 0.0006619017804041505 2023-01-23 22:57:25.707138: step: 1084/1545, loss: 0.061040110886096954 2023-01-23 22:57:26.604866: step: 1086/1545, loss: 0.000799870234914124 2023-01-23 22:57:27.497121: step: 1088/1545, loss: 0.0002992227382492274 2023-01-23 22:57:28.381842: step: 1090/1545, loss: 0.004463359713554382 2023-01-23 22:57:29.303880: step: 1092/1545, loss: 0.00011417327186791226 2023-01-23 22:57:30.163367: step: 1094/1545, loss: -4.573166734189726e-06 2023-01-23 22:57:31.068014: step: 1096/1545, loss: 0.002682120306417346 2023-01-23 22:57:31.984960: step: 1098/1545, loss: 0.0001933569146785885 2023-01-23 22:57:32.853097: step: 1100/1545, loss: 4.300464153289795 2023-01-23 22:57:33.827539: step: 1102/1545, loss: 1.630545375519432e-05 2023-01-23 22:57:34.702308: step: 1104/1545, loss: 0.020273365080356598 2023-01-23 22:57:35.571909: step: 1106/1545, loss: 0.000979009666480124 2023-01-23 22:57:36.439340: step: 1108/1545, loss: 0.00047133120824582875 2023-01-23 22:57:37.273676: step: 1110/1545, loss: 4.707870539277792e-05 2023-01-23 22:57:38.148601: step: 1112/1545, loss: 2.42402211370063e-06 2023-01-23 22:57:39.020051: step: 1114/1545, loss: 7.433330756612122e-05 2023-01-23 22:57:39.867744: step: 1116/1545, loss: 0.000261272449279204 2023-01-23 22:57:40.749006: step: 1118/1545, loss: 0.015261661261320114 2023-01-23 22:57:41.611643: step: 1120/1545, loss: 0.03212878853082657 2023-01-23 22:57:42.498759: step: 1122/1545, loss: 0.042673733085393906 2023-01-23 22:57:43.372997: step: 1124/1545, loss: 0.0001557874638820067 2023-01-23 22:57:44.257933: step: 1126/1545, loss: 0.0022957446053624153 2023-01-23 22:57:45.129498: step: 1128/1545, loss: 0.0027647707611322403 2023-01-23 22:57:45.989643: step: 1130/1545, loss: 3.723412373801693e-05 2023-01-23 22:57:46.871237: step: 1132/1545, loss: 0.005104892887175083 2023-01-23 22:57:47.792983: step: 1134/1545, loss: 0.002293366938829422 2023-01-23 22:57:48.687874: step: 1136/1545, loss: 0.030507687479257584 2023-01-23 22:57:49.582503: step: 1138/1545, loss: 0.002170159947127104 2023-01-23 22:57:50.491889: step: 1140/1545, loss: 0.16922399401664734 2023-01-23 22:57:51.383856: step: 1142/1545, loss: 5.3352843679022044e-05 2023-01-23 22:57:52.228746: step: 1144/1545, loss: 0.00058488838840276 2023-01-23 22:57:53.136004: step: 1146/1545, loss: 0.0929226502776146 2023-01-23 22:57:54.038719: step: 1148/1545, loss: 0.0010168601293116808 2023-01-23 22:57:54.891178: step: 1150/1545, loss: 0.015627684071660042 2023-01-23 22:57:55.775938: step: 1152/1545, loss: 0.0001399983448209241 2023-01-23 22:57:56.641286: step: 1154/1545, loss: 0.027615554630756378 2023-01-23 22:57:57.514323: step: 1156/1545, loss: 0.033217914402484894 2023-01-23 22:57:58.365886: step: 1158/1545, loss: 0.026191681623458862 2023-01-23 22:57:59.252703: step: 1160/1545, loss: 0.09540122747421265 2023-01-23 22:58:00.140948: step: 1162/1545, loss: 0.0564270056784153 2023-01-23 22:58:00.980636: step: 1164/1545, loss: 0.00038582770503126085 2023-01-23 22:58:01.864557: step: 1166/1545, loss: 5.7992820075014606e-05 2023-01-23 22:58:02.718690: step: 1168/1545, loss: 0.20738154649734497 2023-01-23 22:58:03.647345: step: 1170/1545, loss: 0.003410887438803911 2023-01-23 22:58:04.498346: step: 1172/1545, loss: 0.0015319861704483628 2023-01-23 22:58:05.351246: step: 1174/1545, loss: 0.0018612671410664916 2023-01-23 22:58:06.205843: step: 1176/1545, loss: 0.0008255494176410139 2023-01-23 22:58:07.094279: step: 1178/1545, loss: 0.0003185620007570833 2023-01-23 22:58:07.971897: step: 1180/1545, loss: 0.00015987110964488238 2023-01-23 22:58:08.853640: step: 1182/1545, loss: 1.4628171811637003e-05 2023-01-23 22:58:09.711955: step: 1184/1545, loss: 0.0018078836146742105 2023-01-23 22:58:10.568594: step: 1186/1545, loss: 0.003602567594498396 2023-01-23 22:58:11.461283: step: 1188/1545, loss: 0.00010232575004920363 2023-01-23 22:58:12.335576: step: 1190/1545, loss: 0.001981135457754135 2023-01-23 22:58:13.202313: step: 1192/1545, loss: 0.2126387655735016 2023-01-23 22:58:14.155749: step: 1194/1545, loss: 0.0007076075999066234 2023-01-23 22:58:15.070497: step: 1196/1545, loss: 0.43800148367881775 2023-01-23 22:58:15.981017: step: 1198/1545, loss: 0.2148125022649765 2023-01-23 22:58:16.857346: step: 1200/1545, loss: 0.0006362822605296969 2023-01-23 22:58:17.703227: step: 1202/1545, loss: 0.000577898696064949 2023-01-23 22:58:18.548938: step: 1204/1545, loss: 0.0003173953737132251 2023-01-23 22:58:19.421685: step: 1206/1545, loss: 6.591793498955667e-05 2023-01-23 22:58:20.321506: step: 1208/1545, loss: 0.00048135887482203543 2023-01-23 22:58:21.234905: step: 1210/1545, loss: 0.00021450346685014665 2023-01-23 22:58:22.077273: step: 1212/1545, loss: 3.907829523086548e-06 2023-01-23 22:58:23.009049: step: 1214/1545, loss: 0.4151626229286194 2023-01-23 22:58:23.842469: step: 1216/1545, loss: 0.000394257134757936 2023-01-23 22:58:24.718318: step: 1218/1545, loss: 0.0026357206515967846 2023-01-23 22:58:25.575583: step: 1220/1545, loss: 0.0006572081474587321 2023-01-23 22:58:26.498186: step: 1222/1545, loss: 0.024688202887773514 2023-01-23 22:58:27.352015: step: 1224/1545, loss: 0.007962376810610294 2023-01-23 22:58:28.252662: step: 1226/1545, loss: 0.24920818209648132 2023-01-23 22:58:29.117856: step: 1228/1545, loss: 0.004152090288698673 2023-01-23 22:58:30.026710: step: 1230/1545, loss: 0.17317600548267365 2023-01-23 22:58:30.938940: step: 1232/1545, loss: 0.034474894404411316 2023-01-23 22:58:31.790467: step: 1234/1545, loss: 0.008994895964860916 2023-01-23 22:58:32.689516: step: 1236/1545, loss: 0.00654528709128499 2023-01-23 22:58:33.659040: step: 1238/1545, loss: 0.00012782747216988355 2023-01-23 22:58:34.505424: step: 1240/1545, loss: 0.007654949557036161 2023-01-23 22:58:35.376634: step: 1242/1545, loss: 0.19226248562335968 2023-01-23 22:58:36.299497: step: 1244/1545, loss: 0.07412101328372955 2023-01-23 22:58:37.125870: step: 1246/1545, loss: 0.13490401208400726 2023-01-23 22:58:37.982375: step: 1248/1545, loss: 0.0003223538224119693 2023-01-23 22:58:38.864852: step: 1250/1545, loss: 0.0002548962947912514 2023-01-23 22:58:39.739139: step: 1252/1545, loss: 0.16687270998954773 2023-01-23 22:58:40.628354: step: 1254/1545, loss: 1.1586403161345515e-05 2023-01-23 22:58:41.515914: step: 1256/1545, loss: 0.00012245179095771164 2023-01-23 22:58:42.405506: step: 1258/1545, loss: 0.022420009598135948 2023-01-23 22:58:43.283158: step: 1260/1545, loss: 0.0007092992891557515 2023-01-23 22:58:44.120388: step: 1262/1545, loss: 0.00020646002667490393 2023-01-23 22:58:45.091354: step: 1264/1545, loss: 0.00024137244326993823 2023-01-23 22:58:45.992345: step: 1266/1545, loss: 0.2985396981239319 2023-01-23 22:58:46.884456: step: 1268/1545, loss: 0.00021637266036123037 2023-01-23 22:58:47.850722: step: 1270/1545, loss: 0.05122282728552818 2023-01-23 22:58:48.754210: step: 1272/1545, loss: 0.01734357513487339 2023-01-23 22:58:49.651117: step: 1274/1545, loss: 0.004853013902902603 2023-01-23 22:58:50.499720: step: 1276/1545, loss: 0.00019092965521849692 2023-01-23 22:58:51.381088: step: 1278/1545, loss: 0.005215450655668974 2023-01-23 22:58:52.236199: step: 1280/1545, loss: 0.0005673148552887142 2023-01-23 22:58:53.141450: step: 1282/1545, loss: 0.00010120961087523028 2023-01-23 22:58:54.021020: step: 1284/1545, loss: 0.5494915843009949 2023-01-23 22:58:54.882507: step: 1286/1545, loss: 0.0005775520694442093 2023-01-23 22:58:55.722526: step: 1288/1545, loss: 0.34395265579223633 2023-01-23 22:58:56.640466: step: 1290/1545, loss: 0.0005789730930700898 2023-01-23 22:58:57.499306: step: 1292/1545, loss: -9.565343134454452e-06 2023-01-23 22:58:58.394158: step: 1294/1545, loss: 0.18163470923900604 2023-01-23 22:58:59.228377: step: 1296/1545, loss: 7.0325200795196e-05 2023-01-23 22:59:00.109191: step: 1298/1545, loss: 0.00039063446456566453 2023-01-23 22:59:01.006036: step: 1300/1545, loss: 0.05007186532020569 2023-01-23 22:59:01.868865: step: 1302/1545, loss: 0.0023013115860521793 2023-01-23 22:59:02.742691: step: 1304/1545, loss: 0.016349637880921364 2023-01-23 22:59:03.616618: step: 1306/1545, loss: 0.004573100246489048 2023-01-23 22:59:04.505834: step: 1308/1545, loss: 0.0006760249380022287 2023-01-23 22:59:05.379439: step: 1310/1545, loss: 0.001179275568574667 2023-01-23 22:59:06.230170: step: 1312/1545, loss: 0.01672567054629326 2023-01-23 22:59:07.088434: step: 1314/1545, loss: 0.002499915659427643 2023-01-23 22:59:07.960409: step: 1316/1545, loss: 7.20969692338258e-05 2023-01-23 22:59:08.826753: step: 1318/1545, loss: 0.32236936688423157 2023-01-23 22:59:09.678122: step: 1320/1545, loss: 0.006215665023773909 2023-01-23 22:59:10.542869: step: 1322/1545, loss: 0.10512494295835495 2023-01-23 22:59:11.393481: step: 1324/1545, loss: 0.0006500156596302986 2023-01-23 22:59:12.278458: step: 1326/1545, loss: 0.059817664325237274 2023-01-23 22:59:13.183300: step: 1328/1545, loss: 1.1188534699613228e-05 2023-01-23 22:59:14.075980: step: 1330/1545, loss: 0.0006514814449474216 2023-01-23 22:59:14.945121: step: 1332/1545, loss: 4.9015045078704134e-05 2023-01-23 22:59:15.818905: step: 1334/1545, loss: 0.0006708201253786683 2023-01-23 22:59:16.708301: step: 1336/1545, loss: 0.003909353632479906 2023-01-23 22:59:17.571454: step: 1338/1545, loss: 0.029993047937750816 2023-01-23 22:59:18.461883: step: 1340/1545, loss: 0.29494306445121765 2023-01-23 22:59:19.359838: step: 1342/1545, loss: 0.011178645305335522 2023-01-23 22:59:20.255957: step: 1344/1545, loss: 0.0008347961120307446 2023-01-23 22:59:21.115460: step: 1346/1545, loss: 5.142633381183259e-05 2023-01-23 22:59:22.020598: step: 1348/1545, loss: 0.05618519335985184 2023-01-23 22:59:22.929166: step: 1350/1545, loss: 0.15651743113994598 2023-01-23 22:59:23.799080: step: 1352/1545, loss: 7.404722418868914e-05 2023-01-23 22:59:24.672136: step: 1354/1545, loss: 8.77844140632078e-05 2023-01-23 22:59:25.598010: step: 1356/1545, loss: 0.0003465781919658184 2023-01-23 22:59:26.449847: step: 1358/1545, loss: 6.968102388782427e-05 2023-01-23 22:59:27.319750: step: 1360/1545, loss: 0.013910218141973019 2023-01-23 22:59:28.217962: step: 1362/1545, loss: 0.0022010947577655315 2023-01-23 22:59:29.084490: step: 1364/1545, loss: 7.394177373498678e-05 2023-01-23 22:59:29.980270: step: 1366/1545, loss: 0.2462068349123001 2023-01-23 22:59:30.882514: step: 1368/1545, loss: 0.0028744072187691927 2023-01-23 22:59:31.760549: step: 1370/1545, loss: 0.007010797504335642 2023-01-23 22:59:32.620865: step: 1372/1545, loss: 0.06624588370323181 2023-01-23 22:59:33.548539: step: 1374/1545, loss: 0.00029694795375689864 2023-01-23 22:59:34.436433: step: 1376/1545, loss: 0.0005403312970884144 2023-01-23 22:59:35.321492: step: 1378/1545, loss: 9.546647197566926e-05 2023-01-23 22:59:36.196171: step: 1380/1545, loss: 0.0020060802344232798 2023-01-23 22:59:37.080393: step: 1382/1545, loss: 0.08422045409679413 2023-01-23 22:59:37.908853: step: 1384/1545, loss: 0.0015562506159767509 2023-01-23 22:59:38.767068: step: 1386/1545, loss: 0.0004516539629548788 2023-01-23 22:59:39.736360: step: 1388/1545, loss: 0.0015595128061249852 2023-01-23 22:59:40.625039: step: 1390/1545, loss: 0.0011075333459302783 2023-01-23 22:59:41.522509: step: 1392/1545, loss: 0.25713855028152466 2023-01-23 22:59:42.359105: step: 1394/1545, loss: 0.1258804351091385 2023-01-23 22:59:43.191958: step: 1396/1545, loss: 2.0425766706466675e-05 2023-01-23 22:59:44.086010: step: 1398/1545, loss: -7.012245987425558e-06 2023-01-23 22:59:44.956916: step: 1400/1545, loss: 0.0036616739816963673 2023-01-23 22:59:45.825858: step: 1402/1545, loss: 0.0023978326935321093 2023-01-23 22:59:46.735955: step: 1404/1545, loss: 0.00016077791224233806 2023-01-23 22:59:47.573487: step: 1406/1545, loss: -1.1308119610475842e-05 2023-01-23 22:59:48.449205: step: 1408/1545, loss: 0.10654458403587341 2023-01-23 22:59:49.302840: step: 1410/1545, loss: 6.700752419419587e-05 2023-01-23 22:59:50.152707: step: 1412/1545, loss: 2.504115343093872 2023-01-23 22:59:51.059713: step: 1414/1545, loss: 0.0019597187638282776 2023-01-23 22:59:51.940058: step: 1416/1545, loss: 5.795580364065245e-05 2023-01-23 22:59:52.785514: step: 1418/1545, loss: 0.005791238509118557 2023-01-23 22:59:53.668991: step: 1420/1545, loss: 0.002029141178354621 2023-01-23 22:59:54.544147: step: 1422/1545, loss: 0.003897362854331732 2023-01-23 22:59:55.476205: step: 1424/1545, loss: 0.004200880415737629 2023-01-23 22:59:56.360409: step: 1426/1545, loss: 0.009822606109082699 2023-01-23 22:59:57.286733: step: 1428/1545, loss: 0.006099240388721228 2023-01-23 22:59:58.192599: step: 1430/1545, loss: 0.009478546679019928 2023-01-23 22:59:59.054690: step: 1432/1545, loss: 0.03751599043607712 2023-01-23 22:59:59.892092: step: 1434/1545, loss: 0.0007705342723056674 2023-01-23 23:00:00.839309: step: 1436/1545, loss: 0.003514599986374378 2023-01-23 23:00:01.683270: step: 1438/1545, loss: 0.04767953231930733 2023-01-23 23:00:02.528676: step: 1440/1545, loss: 0.022886838763952255 2023-01-23 23:00:03.446632: step: 1442/1545, loss: 0.00012668893032241613 2023-01-23 23:00:04.309202: step: 1444/1545, loss: 0.0008665099740028381 2023-01-23 23:00:05.167543: step: 1446/1545, loss: -2.1408661268651485e-05 2023-01-23 23:00:06.022883: step: 1448/1545, loss: 0.08229639381170273 2023-01-23 23:00:06.863505: step: 1450/1545, loss: 0.002128775930032134 2023-01-23 23:00:07.725306: step: 1452/1545, loss: 0.001393536222167313 2023-01-23 23:00:08.584949: step: 1454/1545, loss: 2.3341781343333423e-05 2023-01-23 23:00:09.487925: step: 1456/1545, loss: 0.0006373816868290305 2023-01-23 23:00:10.411056: step: 1458/1545, loss: 0.009888880886137486 2023-01-23 23:00:11.252713: step: 1460/1545, loss: 0.0005124374874867499 2023-01-23 23:00:12.133863: step: 1462/1545, loss: 0.0038387198001146317 2023-01-23 23:00:13.009433: step: 1464/1545, loss: 4.009004896943225e-06 2023-01-23 23:00:13.893302: step: 1466/1545, loss: 0.007811198942363262 2023-01-23 23:00:14.774713: step: 1468/1545, loss: -4.975429328624159e-05 2023-01-23 23:00:15.673885: step: 1470/1545, loss: 0.007864684797823429 2023-01-23 23:00:16.531274: step: 1472/1545, loss: 0.00014915765495970845 2023-01-23 23:00:17.430683: step: 1474/1545, loss: 8.411556336795911e-05 2023-01-23 23:00:18.265910: step: 1476/1545, loss: -2.7360024432709906e-06 2023-01-23 23:00:19.128263: step: 1478/1545, loss: -1.6695883459760807e-05 2023-01-23 23:00:20.012639: step: 1480/1545, loss: 0.00017728208331391215 2023-01-23 23:00:20.844521: step: 1482/1545, loss: 3.9165613998193294e-05 2023-01-23 23:00:21.673089: step: 1484/1545, loss: 5.157060513738543e-05 2023-01-23 23:00:22.526183: step: 1486/1545, loss: 2.8339025448076427e-05 2023-01-23 23:00:23.458226: step: 1488/1545, loss: 0.00850769504904747 2023-01-23 23:00:24.326677: step: 1490/1545, loss: 7.098612695699558e-05 2023-01-23 23:00:25.226258: step: 1492/1545, loss: 0.029618648812174797 2023-01-23 23:00:26.120276: step: 1494/1545, loss: -7.2170050771092065e-06 2023-01-23 23:00:27.007572: step: 1496/1545, loss: 0.05919034779071808 2023-01-23 23:00:27.928310: step: 1498/1545, loss: 0.11588780581951141 2023-01-23 23:00:28.780392: step: 1500/1545, loss: 5.208849688642658e-05 2023-01-23 23:00:29.673407: step: 1502/1545, loss: 1.8322096366318874e-05 2023-01-23 23:00:30.553349: step: 1504/1545, loss: 0.23845133185386658 2023-01-23 23:00:31.441032: step: 1506/1545, loss: 0.0004213445645291358 2023-01-23 23:00:32.293096: step: 1508/1545, loss: 0.0002487212186679244 2023-01-23 23:00:33.166179: step: 1510/1545, loss: 8.50826472742483e-05 2023-01-23 23:00:34.042386: step: 1512/1545, loss: 0.00017052378098014742 2023-01-23 23:00:34.922526: step: 1514/1545, loss: 6.0843438404845074e-05 2023-01-23 23:00:35.792861: step: 1516/1545, loss: 4.7934940084815025e-05 2023-01-23 23:00:36.724749: step: 1518/1545, loss: 0.000493385421577841 2023-01-23 23:00:37.594176: step: 1520/1545, loss: 4.809200981981121e-05 2023-01-23 23:00:38.506194: step: 1522/1545, loss: 0.18298836052417755 2023-01-23 23:00:39.396440: step: 1524/1545, loss: 0.018880624324083328 2023-01-23 23:00:40.237208: step: 1526/1545, loss: 9.19919057196239e-06 2023-01-23 23:00:41.085527: step: 1528/1545, loss: 8.395053737331182e-05 2023-01-23 23:00:41.941445: step: 1530/1545, loss: 1.2461895942687988 2023-01-23 23:00:42.828629: step: 1532/1545, loss: 0.001957704545930028 2023-01-23 23:00:43.677818: step: 1534/1545, loss: 0.09808581322431564 2023-01-23 23:00:44.562861: step: 1536/1545, loss: 0.06354983896017075 2023-01-23 23:00:45.396835: step: 1538/1545, loss: 0.0033241277560591698 2023-01-23 23:00:46.268799: step: 1540/1545, loss: -1.8299619114259258e-05 2023-01-23 23:00:47.212683: step: 1542/1545, loss: -2.2104753952589817e-05 2023-01-23 23:00:48.207310: step: 1544/1545, loss: 0.015749577432870865 2023-01-23 23:00:49.073402: step: 1546/1545, loss: 0.15230321884155273 2023-01-23 23:00:49.915741: step: 1548/1545, loss: 2.922416024375707e-05 2023-01-23 23:00:50.795325: step: 1550/1545, loss: 7.134414772735909e-05 2023-01-23 23:00:51.686988: step: 1552/1545, loss: 1.9968389096902683e-05 2023-01-23 23:00:52.624505: step: 1554/1545, loss: 2.9005484975641593e-05 2023-01-23 23:00:53.515385: step: 1556/1545, loss: 0.0001197100937133655 2023-01-23 23:00:54.411050: step: 1558/1545, loss: 0.027451323345303535 2023-01-23 23:00:55.265817: step: 1560/1545, loss: 0.002400314435362816 2023-01-23 23:00:56.113522: step: 1562/1545, loss: 0.0008607019553892314 2023-01-23 23:00:56.983753: step: 1564/1545, loss: 0.017045270651578903 2023-01-23 23:00:57.828678: step: 1566/1545, loss: 2.6963070922647603e-06 2023-01-23 23:00:58.743813: step: 1568/1545, loss: 0.0012909143697470427 2023-01-23 23:00:59.590941: step: 1570/1545, loss: 0.02154182828962803 2023-01-23 23:01:00.474528: step: 1572/1545, loss: 0.00035265745827928185 2023-01-23 23:01:01.341133: step: 1574/1545, loss: 0.003696443745866418 2023-01-23 23:01:02.239256: step: 1576/1545, loss: 0.0038976608775556087 2023-01-23 23:01:03.130604: step: 1578/1545, loss: 0.0501975417137146 2023-01-23 23:01:04.008944: step: 1580/1545, loss: 2.5762119548744522e-05 2023-01-23 23:01:04.879355: step: 1582/1545, loss: 8.599534339737147e-05 2023-01-23 23:01:05.729578: step: 1584/1545, loss: 2.56717194133671e-05 2023-01-23 23:01:06.570659: step: 1586/1545, loss: 1.4496274161501788e-05 2023-01-23 23:01:07.480216: step: 1588/1545, loss: 1.3811830285703763e-05 2023-01-23 23:01:08.336046: step: 1590/1545, loss: 2.3462996978196315e-05 2023-01-23 23:01:09.235797: step: 1592/1545, loss: 0.0004650473711080849 2023-01-23 23:01:10.141974: step: 1594/1545, loss: 2.467334343236871e-05 2023-01-23 23:01:11.004594: step: 1596/1545, loss: 0.07807048410177231 2023-01-23 23:01:12.016867: step: 1598/1545, loss: 0.31419870257377625 2023-01-23 23:01:12.894252: step: 1600/1545, loss: 0.0011154025560244918 2023-01-23 23:01:13.777497: step: 1602/1545, loss: -7.303060556296259e-06 2023-01-23 23:01:14.666986: step: 1604/1545, loss: 0.012384381145238876 2023-01-23 23:01:15.519885: step: 1606/1545, loss: 2.535432213335298e-05 2023-01-23 23:01:16.355110: step: 1608/1545, loss: 0.0014917857479304075 2023-01-23 23:01:17.247956: step: 1610/1545, loss: 0.0026125358417630196 2023-01-23 23:01:18.129648: step: 1612/1545, loss: 0.050797343254089355 2023-01-23 23:01:19.026040: step: 1614/1545, loss: 6.423755257856101e-05 2023-01-23 23:01:19.881052: step: 1616/1545, loss: -9.405620403413195e-06 2023-01-23 23:01:20.763117: step: 1618/1545, loss: 0.00041523875552229583 2023-01-23 23:01:21.641302: step: 1620/1545, loss: 0.0012752293841913342 2023-01-23 23:01:22.553282: step: 1622/1545, loss: -3.051758767469437e-06 2023-01-23 23:01:23.428202: step: 1624/1545, loss: 1.030613566399552e-05 2023-01-23 23:01:24.335230: step: 1626/1545, loss: 4.6230386942625046e-05 2023-01-23 23:01:25.172850: step: 1628/1545, loss: -1.805305691959802e-05 2023-01-23 23:01:26.097781: step: 1630/1545, loss: 0.0010499369818717241 2023-01-23 23:01:26.947167: step: 1632/1545, loss: 3.1822837627260014e-05 2023-01-23 23:01:27.836500: step: 1634/1545, loss: 0.0010040700435638428 2023-01-23 23:01:28.796775: step: 1636/1545, loss: 0.00764580350369215 2023-01-23 23:01:29.674675: step: 1638/1545, loss: 6.954055425012484e-05 2023-01-23 23:01:30.614812: step: 1640/1545, loss: 6.568066601175815e-05 2023-01-23 23:01:31.498035: step: 1642/1545, loss: 0.00042956831748597324 2023-01-23 23:01:32.381762: step: 1644/1545, loss: 0.2580532431602478 2023-01-23 23:01:33.250564: step: 1646/1545, loss: 0.008852895349264145 2023-01-23 23:01:34.115466: step: 1648/1545, loss: 7.791876851115376e-05 2023-01-23 23:01:35.015392: step: 1650/1545, loss: 0.0027232635766267776 2023-01-23 23:01:35.877314: step: 1652/1545, loss: 0.025997614488005638 2023-01-23 23:01:36.758887: step: 1654/1545, loss: 0.01498459093272686 2023-01-23 23:01:37.616243: step: 1656/1545, loss: 0.01896747574210167 2023-01-23 23:01:38.485371: step: 1658/1545, loss: 5.799196878797375e-05 2023-01-23 23:01:39.407226: step: 1660/1545, loss: 0.114339679479599 2023-01-23 23:01:40.275294: step: 1662/1545, loss: 8.941352280089632e-05 2023-01-23 23:01:41.136489: step: 1664/1545, loss: 2.4943521566456184e-05 2023-01-23 23:01:42.029067: step: 1666/1545, loss: 0.015066329389810562 2023-01-23 23:01:42.894161: step: 1668/1545, loss: 0.06075667962431908 2023-01-23 23:01:43.748557: step: 1670/1545, loss: 0.0037729586474597454 2023-01-23 23:01:44.599430: step: 1672/1545, loss: 3.3596137654967606e-05 2023-01-23 23:01:45.466885: step: 1674/1545, loss: 0.029827741906046867 2023-01-23 23:01:46.346289: step: 1676/1545, loss: 0.0003875953843817115 2023-01-23 23:01:47.179059: step: 1678/1545, loss: 0.00032693298999220133 2023-01-23 23:01:48.046136: step: 1680/1545, loss: 0.0005499111139215529 2023-01-23 23:01:49.012186: step: 1682/1545, loss: -1.2851656720158644e-05 2023-01-23 23:01:49.853602: step: 1684/1545, loss: 2.4908285922720097e-05 2023-01-23 23:01:50.731495: step: 1686/1545, loss: 0.6176882386207581 2023-01-23 23:01:51.586171: step: 1688/1545, loss: 0.07609941065311432 2023-01-23 23:01:52.472983: step: 1690/1545, loss: 0.2862013876438141 2023-01-23 23:01:53.349707: step: 1692/1545, loss: 0.0026292335242033005 2023-01-23 23:01:54.265334: step: 1694/1545, loss: 0.02141251228749752 2023-01-23 23:01:55.138385: step: 1696/1545, loss: 0.0001876837050076574 2023-01-23 23:01:56.060777: step: 1698/1545, loss: 0.00027564517222344875 2023-01-23 23:01:56.945110: step: 1700/1545, loss: 0.02747129090130329 2023-01-23 23:01:57.806881: step: 1702/1545, loss: 0.002193177118897438 2023-01-23 23:01:58.686420: step: 1704/1545, loss: 0.09965656697750092 2023-01-23 23:01:59.573028: step: 1706/1545, loss: 0.14386941492557526 2023-01-23 23:02:00.463253: step: 1708/1545, loss: 0.004553431179374456 2023-01-23 23:02:01.367628: step: 1710/1545, loss: 0.2956240475177765 2023-01-23 23:02:02.212349: step: 1712/1545, loss: 0.0073300073854625225 2023-01-23 23:02:03.122245: step: 1714/1545, loss: 0.00032326774089597166 2023-01-23 23:02:03.997458: step: 1716/1545, loss: 0.006958375219255686 2023-01-23 23:02:04.943764: step: 1718/1545, loss: 0.041186098009347916 2023-01-23 23:02:05.882079: step: 1720/1545, loss: 0.00016251146735157818 2023-01-23 23:02:06.788058: step: 1722/1545, loss: 0.0035851006396114826 2023-01-23 23:02:07.680506: step: 1724/1545, loss: 0.0006777687813155353 2023-01-23 23:02:08.579788: step: 1726/1545, loss: 0.0013152817264199257 2023-01-23 23:02:09.463281: step: 1728/1545, loss: 0.00021112860122229904 2023-01-23 23:02:10.376293: step: 1730/1545, loss: 0.10928647220134735 2023-01-23 23:02:11.270416: step: 1732/1545, loss: 0.236345574259758 2023-01-23 23:02:12.090821: step: 1734/1545, loss: 3.4648172004381195e-05 2023-01-23 23:02:12.949020: step: 1736/1545, loss: 0.0001510725123807788 2023-01-23 23:02:13.828279: step: 1738/1545, loss: 0.00025144778192043304 2023-01-23 23:02:14.677653: step: 1740/1545, loss: 0.00011318919132463634 2023-01-23 23:02:15.575204: step: 1742/1545, loss: 6.104856583988294e-05 2023-01-23 23:02:16.483223: step: 1744/1545, loss: 7.977087807375938e-05 2023-01-23 23:02:17.336862: step: 1746/1545, loss: 0.001155163859948516 2023-01-23 23:02:18.206782: step: 1748/1545, loss: 0.4928648769855499 2023-01-23 23:02:19.077193: step: 1750/1545, loss: 0.6743053197860718 2023-01-23 23:02:19.939020: step: 1752/1545, loss: 3.2424923119833693e-06 2023-01-23 23:02:20.848714: step: 1754/1545, loss: 0.04832610860466957 2023-01-23 23:02:21.716579: step: 1756/1545, loss: 9.894924005493522e-05 2023-01-23 23:02:22.570460: step: 1758/1545, loss: 0.00025465089129284024 2023-01-23 23:02:23.446525: step: 1760/1545, loss: 5.191058153286576e-05 2023-01-23 23:02:24.338862: step: 1762/1545, loss: 0.29694291949272156 2023-01-23 23:02:25.203803: step: 1764/1545, loss: 3.896987618645653e-05 2023-01-23 23:02:26.110662: step: 1766/1545, loss: 0.25098344683647156 2023-01-23 23:02:27.039517: step: 1768/1545, loss: 0.00027465372113510966 2023-01-23 23:02:27.912941: step: 1770/1545, loss: 0.0023468949366360903 2023-01-23 23:02:28.795773: step: 1772/1545, loss: 0.0007188932504504919 2023-01-23 23:02:29.677795: step: 1774/1545, loss: -2.47955322265625e-05 2023-01-23 23:02:30.531492: step: 1776/1545, loss: 0.002653103321790695 2023-01-23 23:02:31.394731: step: 1778/1545, loss: 0.0007666315650567412 2023-01-23 23:02:32.243765: step: 1780/1545, loss: 0.06553630530834198 2023-01-23 23:02:33.142143: step: 1782/1545, loss: 0.0009975720895454288 2023-01-23 23:02:34.057141: step: 1784/1545, loss: 0.00022093651932664216 2023-01-23 23:02:34.898923: step: 1786/1545, loss: 0.0026986896991729736 2023-01-23 23:02:35.760610: step: 1788/1545, loss: 0.02814740687608719 2023-01-23 23:02:36.633460: step: 1790/1545, loss: 0.15363237261772156 2023-01-23 23:02:37.539279: step: 1792/1545, loss: 0.06492727249860764 2023-01-23 23:02:38.417201: step: 1794/1545, loss: 0.002101224847137928 2023-01-23 23:02:39.395396: step: 1796/1545, loss: 0.18321602046489716 2023-01-23 23:02:40.235051: step: 1798/1545, loss: 0.07699776440858841 2023-01-23 23:02:41.061489: step: 1800/1545, loss: 0.00027314870385453105 2023-01-23 23:02:42.042156: step: 1802/1545, loss: 8.867497672326863e-05 2023-01-23 23:02:42.912493: step: 1804/1545, loss: 0.000538374821189791 2023-01-23 23:02:43.798427: step: 1806/1545, loss: 0.004375883843749762 2023-01-23 23:02:44.687899: step: 1808/1545, loss: 0.010942860506474972 2023-01-23 23:02:45.588966: step: 1810/1545, loss: 0.00015984238416422158 2023-01-23 23:02:46.475785: step: 1812/1545, loss: 0.00014265051868278533 2023-01-23 23:02:47.384220: step: 1814/1545, loss: 0.0021876369137316942 2023-01-23 23:02:48.302644: step: 1816/1545, loss: 4.930197974317707e-05 2023-01-23 23:02:49.175587: step: 1818/1545, loss: 0.22855541110038757 2023-01-23 23:02:50.022045: step: 1820/1545, loss: 0.003321751020848751 2023-01-23 23:02:50.878398: step: 1822/1545, loss: 0.0015055942349135876 2023-01-23 23:02:51.798472: step: 1824/1545, loss: 0.001285269041545689 2023-01-23 23:02:52.715100: step: 1826/1545, loss: 3.248072971473448e-05 2023-01-23 23:02:53.547759: step: 1828/1545, loss: 0.0006526410579681396 2023-01-23 23:02:54.388791: step: 1830/1545, loss: 0.00011770959827117622 2023-01-23 23:02:55.230356: step: 1832/1545, loss: 7.160534005379304e-05 2023-01-23 23:02:56.194365: step: 1834/1545, loss: 0.00022202347463462502 2023-01-23 23:02:57.077496: step: 1836/1545, loss: 5.832967144669965e-05 2023-01-23 23:02:57.966422: step: 1838/1545, loss: 0.010456438176333904 2023-01-23 23:02:58.848948: step: 1840/1545, loss: 0.002901825588196516 2023-01-23 23:02:59.712909: step: 1842/1545, loss: 2.86102294921875e-05 2023-01-23 23:03:00.608735: step: 1844/1545, loss: 7.171929610194638e-05 2023-01-23 23:03:01.500701: step: 1846/1545, loss: 0.00012323555711191148 2023-01-23 23:03:02.341074: step: 1848/1545, loss: 0.0001301707816310227 2023-01-23 23:03:03.205859: step: 1850/1545, loss: 1.971332312677987e-05 2023-01-23 23:03:04.062890: step: 1852/1545, loss: 0.2673368752002716 2023-01-23 23:03:04.950875: step: 1854/1545, loss: 9.97554961941205e-05 2023-01-23 23:03:05.804019: step: 1856/1545, loss: 6.99088050168939e-05 2023-01-23 23:03:06.656058: step: 1858/1545, loss: 0.002261352725327015 2023-01-23 23:03:07.519775: step: 1860/1545, loss: 0.008692914620041847 2023-01-23 23:03:08.400931: step: 1862/1545, loss: 0.10025549679994583 2023-01-23 23:03:09.273019: step: 1864/1545, loss: 0.07706001400947571 2023-01-23 23:03:10.152723: step: 1866/1545, loss: 5.057992530055344e-05 2023-01-23 23:03:11.010299: step: 1868/1545, loss: 3.840241902253183e-07 2023-01-23 23:03:11.876169: step: 1870/1545, loss: 3.5837285395246e-05 2023-01-23 23:03:12.768470: step: 1872/1545, loss: 0.03694997355341911 2023-01-23 23:03:13.644082: step: 1874/1545, loss: 0.00014840680523775518 2023-01-23 23:03:14.480831: step: 1876/1545, loss: 0.0024517287965863943 2023-01-23 23:03:15.344309: step: 1878/1545, loss: 0.0004781864699907601 2023-01-23 23:03:16.209757: step: 1880/1545, loss: 0.0008026162977330387 2023-01-23 23:03:17.100876: step: 1882/1545, loss: 0.000551362696569413 2023-01-23 23:03:17.961425: step: 1884/1545, loss: 0.00046268373262137175 2023-01-23 23:03:18.807327: step: 1886/1545, loss: 0.00017857432249002159 2023-01-23 23:03:19.715857: step: 1888/1545, loss: 0.0015181559138000011 2023-01-23 23:03:20.593812: step: 1890/1545, loss: 7.934918539831415e-05 2023-01-23 23:03:21.433057: step: 1892/1545, loss: 8.316040475619957e-05 2023-01-23 23:03:22.286379: step: 1894/1545, loss: -4.190258550806902e-06 2023-01-23 23:03:23.191990: step: 1896/1545, loss: 0.003131115809082985 2023-01-23 23:03:24.076598: step: 1898/1545, loss: 0.0020239900331944227 2023-01-23 23:03:24.923912: step: 1900/1545, loss: 0.00013924340601079166 2023-01-23 23:03:25.828068: step: 1902/1545, loss: 0.5605800747871399 2023-01-23 23:03:26.700520: step: 1904/1545, loss: 0.0006558902678079903 2023-01-23 23:03:27.580873: step: 1906/1545, loss: 8.705854997970164e-05 2023-01-23 23:03:28.461618: step: 1908/1545, loss: 0.1238350048661232 2023-01-23 23:03:29.385254: step: 1910/1545, loss: 0.002163128461688757 2023-01-23 23:03:30.251201: step: 1912/1545, loss: 0.005451929289847612 2023-01-23 23:03:31.127215: step: 1914/1545, loss: 7.439478940796107e-05 2023-01-23 23:03:32.017618: step: 1916/1545, loss: 0.003997312858700752 2023-01-23 23:03:32.892827: step: 1918/1545, loss: 6.25523243797943e-05 2023-01-23 23:03:33.875389: step: 1920/1545, loss: 0.00023282752954401076 2023-01-23 23:03:34.745159: step: 1922/1545, loss: 0.1310247927904129 2023-01-23 23:03:35.625265: step: 1924/1545, loss: 0.001112844329327345 2023-01-23 23:03:36.485161: step: 1926/1545, loss: 0.0015692629385739565 2023-01-23 23:03:37.351969: step: 1928/1545, loss: 0.0009780136169865727 2023-01-23 23:03:38.359232: step: 1930/1545, loss: 0.0005828863359056413 2023-01-23 23:03:39.239063: step: 1932/1545, loss: 3.8544538256246597e-05 2023-01-23 23:03:40.148749: step: 1934/1545, loss: 0.07485560327768326 2023-01-23 23:03:41.029652: step: 1936/1545, loss: 0.05094187706708908 2023-01-23 23:03:41.895354: step: 1938/1545, loss: 0.019301218912005424 2023-01-23 23:03:42.726539: step: 1940/1545, loss: 0.00011331214773235843 2023-01-23 23:03:43.613085: step: 1942/1545, loss: 0.00029380759224295616 2023-01-23 23:03:44.503314: step: 1944/1545, loss: 0.0002869360032491386 2023-01-23 23:03:45.391955: step: 1946/1545, loss: 0.00028854317497462034 2023-01-23 23:03:46.273460: step: 1948/1545, loss: 0.33066725730895996 2023-01-23 23:03:47.178440: step: 1950/1545, loss: 0.047904834151268005 2023-01-23 23:03:48.056502: step: 1952/1545, loss: 0.43987712264060974 2023-01-23 23:03:48.947458: step: 1954/1545, loss: 0.5404929518699646 2023-01-23 23:03:49.820420: step: 1956/1545, loss: 0.005826625041663647 2023-01-23 23:03:50.707011: step: 1958/1545, loss: 0.004191151354461908 2023-01-23 23:03:51.604819: step: 1960/1545, loss: 0.00022278845426626503 2023-01-23 23:03:52.566528: step: 1962/1545, loss: 0.00013045669766142964 2023-01-23 23:03:53.493061: step: 1964/1545, loss: 0.1746721714735031 2023-01-23 23:03:54.357111: step: 1966/1545, loss: 0.00024119876616168767 2023-01-23 23:03:55.199483: step: 1968/1545, loss: 0.001773747499100864 2023-01-23 23:03:56.086087: step: 1970/1545, loss: 2.927570130850654e-05 2023-01-23 23:03:56.937199: step: 1972/1545, loss: 0.019043147563934326 2023-01-23 23:03:57.789796: step: 1974/1545, loss: 0.000283371948171407 2023-01-23 23:03:58.656192: step: 1976/1545, loss: 5.576982948696241e-05 2023-01-23 23:03:59.534400: step: 1978/1545, loss: 0.0019569338764995337 2023-01-23 23:04:00.438780: step: 1980/1545, loss: 0.0002718487230595201 2023-01-23 23:04:01.315537: step: 1982/1545, loss: 0.05345971882343292 2023-01-23 23:04:02.212993: step: 1984/1545, loss: 0.002888911170884967 2023-01-23 23:04:03.116420: step: 1986/1545, loss: 0.0001804184284992516 2023-01-23 23:04:04.002471: step: 1988/1545, loss: 0.00010641096741892397 2023-01-23 23:04:04.897804: step: 1990/1545, loss: 0.013441251590847969 2023-01-23 23:04:05.779609: step: 1992/1545, loss: 0.0034119857009500265 2023-01-23 23:04:06.651559: step: 1994/1545, loss: 0.0004198098904453218 2023-01-23 23:04:07.545040: step: 1996/1545, loss: 0.0001257639960385859 2023-01-23 23:04:08.400996: step: 1998/1545, loss: 1.1872749382746406e-05 2023-01-23 23:04:09.309462: step: 2000/1545, loss: 0.0038638992700725794 2023-01-23 23:04:10.180788: step: 2002/1545, loss: 0.00012041826266795397 2023-01-23 23:04:11.078765: step: 2004/1545, loss: 1.5970317690516822e-05 2023-01-23 23:04:11.931086: step: 2006/1545, loss: 0.0005331075517460704 2023-01-23 23:04:12.811645: step: 2008/1545, loss: 0.00011734183499356732 2023-01-23 23:04:13.690839: step: 2010/1545, loss: 5.6155884522013366e-05 2023-01-23 23:04:14.585938: step: 2012/1545, loss: 0.001618111040443182 2023-01-23 23:04:15.430144: step: 2014/1545, loss: 0.05700548365712166 2023-01-23 23:04:16.282249: step: 2016/1545, loss: 0.11547525227069855 2023-01-23 23:04:17.162603: step: 2018/1545, loss: 2.1555504645220935e-05 2023-01-23 23:04:18.041973: step: 2020/1545, loss: 0.00045993097592145205 2023-01-23 23:04:18.947827: step: 2022/1545, loss: 0.01908082142472267 2023-01-23 23:04:19.829422: step: 2024/1545, loss: 5.185728150536306e-05 2023-01-23 23:04:20.703148: step: 2026/1545, loss: 0.019244667142629623 2023-01-23 23:04:21.586263: step: 2028/1545, loss: 0.00016151070303749293 2023-01-23 23:04:22.523854: step: 2030/1545, loss: 0.0317997932434082 2023-01-23 23:04:23.395026: step: 2032/1545, loss: 0.0028587982524186373 2023-01-23 23:04:24.288781: step: 2034/1545, loss: 0.02877691574394703 2023-01-23 23:04:25.148178: step: 2036/1545, loss: 0.00016060471534729004 2023-01-23 23:04:26.000845: step: 2038/1545, loss: 0.5027217864990234 2023-01-23 23:04:26.915824: step: 2040/1545, loss: 0.02153262309730053 2023-01-23 23:04:27.781758: step: 2042/1545, loss: 8.40455322759226e-06 2023-01-23 23:04:28.704340: step: 2044/1545, loss: 0.19366154074668884 2023-01-23 23:04:29.572879: step: 2046/1545, loss: 0.8037251830101013 2023-01-23 23:04:30.441628: step: 2048/1545, loss: 1.2375486221571919e-05 2023-01-23 23:04:31.425696: step: 2050/1545, loss: 8.545816672267392e-05 2023-01-23 23:04:32.301689: step: 2052/1545, loss: 0.026614367961883545 2023-01-23 23:04:33.161098: step: 2054/1545, loss: 0.002483169548213482 2023-01-23 23:04:34.025476: step: 2056/1545, loss: 0.00032416259637102485 2023-01-23 23:04:34.907769: step: 2058/1545, loss: 0.5285202860832214 2023-01-23 23:04:35.752065: step: 2060/1545, loss: 8.832513412926346e-05 2023-01-23 23:04:36.603036: step: 2062/1545, loss: 4.623842323780991e-05 2023-01-23 23:04:37.485708: step: 2064/1545, loss: 0.00018319746595807374 2023-01-23 23:04:38.359650: step: 2066/1545, loss: 4.17910487158224e-05 2023-01-23 23:04:39.224260: step: 2068/1545, loss: 0.000485879834741354 2023-01-23 23:04:40.087469: step: 2070/1545, loss: 2.4893630325095728e-05 2023-01-23 23:04:40.952406: step: 2072/1545, loss: 0.11863213032484055 2023-01-23 23:04:41.817657: step: 2074/1545, loss: 0.00029945370624773204 2023-01-23 23:04:42.703903: step: 2076/1545, loss: 0.382610559463501 2023-01-23 23:04:43.565005: step: 2078/1545, loss: 0.5115116238594055 2023-01-23 23:04:44.494720: step: 2080/1545, loss: 7.48184829717502e-05 2023-01-23 23:04:45.409644: step: 2082/1545, loss: 0.004733708221465349 2023-01-23 23:04:46.283907: step: 2084/1545, loss: 0.0013122871750965714 2023-01-23 23:04:47.129095: step: 2086/1545, loss: 0.0003599695337470621 2023-01-23 23:04:47.990859: step: 2088/1545, loss: 2.3082635379978456e-05 2023-01-23 23:04:48.893913: step: 2090/1545, loss: 0.00011731867562048137 2023-01-23 23:04:49.779301: step: 2092/1545, loss: 0.0007124832482077181 2023-01-23 23:04:50.660370: step: 2094/1545, loss: 0.003976601641625166 2023-01-23 23:04:51.507060: step: 2096/1545, loss: -5.623704055324197e-06 2023-01-23 23:04:52.426952: step: 2098/1545, loss: 0.20962214469909668 2023-01-23 23:04:53.314522: step: 2100/1545, loss: 0.00052977743325755 2023-01-23 23:04:54.195032: step: 2102/1545, loss: 0.51896071434021 2023-01-23 23:04:55.052068: step: 2104/1545, loss: 0.01765213906764984 2023-01-23 23:04:55.899543: step: 2106/1545, loss: 0.0002613818214740604 2023-01-23 23:04:56.782099: step: 2108/1545, loss: 0.051433123648166656 2023-01-23 23:04:57.648272: step: 2110/1545, loss: 0.0028505611699074507 2023-01-23 23:04:58.546150: step: 2112/1545, loss: 0.0021233935840427876 2023-01-23 23:04:59.456078: step: 2114/1545, loss: 0.0048415884375572205 2023-01-23 23:05:00.352650: step: 2116/1545, loss: 0.01792226918041706 2023-01-23 23:05:01.248127: step: 2118/1545, loss: 0.002059497404843569 2023-01-23 23:05:02.146590: step: 2120/1545, loss: 0.30889204144477844 2023-01-23 23:05:03.045805: step: 2122/1545, loss: 0.037820376455783844 2023-01-23 23:05:03.922456: step: 2124/1545, loss: 5.724778020521626e-05 2023-01-23 23:05:04.848927: step: 2126/1545, loss: 0.0800664871931076 2023-01-23 23:05:05.732188: step: 2128/1545, loss: 0.002888247836381197 2023-01-23 23:05:06.631012: step: 2130/1545, loss: 0.0012167916866019368 2023-01-23 23:05:07.554262: step: 2132/1545, loss: 0.010904630646109581 2023-01-23 23:05:08.430307: step: 2134/1545, loss: 0.05465038865804672 2023-01-23 23:05:09.313779: step: 2136/1545, loss: 0.006546488031744957 2023-01-23 23:05:10.184506: step: 2138/1545, loss: 5.64600013603922e-05 2023-01-23 23:05:11.066801: step: 2140/1545, loss: 0.0029995639342814684 2023-01-23 23:05:11.943647: step: 2142/1545, loss: 0.0019668585155159235 2023-01-23 23:05:12.790037: step: 2144/1545, loss: 0.0010403967462480068 2023-01-23 23:05:13.703730: step: 2146/1545, loss: 0.1390688568353653 2023-01-23 23:05:14.706995: step: 2148/1545, loss: 0.042090192437171936 2023-01-23 23:05:15.601606: step: 2150/1545, loss: 0.0004407921223901212 2023-01-23 23:05:16.521976: step: 2152/1545, loss: 0.009825501590967178 2023-01-23 23:05:17.401359: step: 2154/1545, loss: 0.00044741996680386364 2023-01-23 23:05:18.302529: step: 2156/1545, loss: 2.1025396563345566e-05 2023-01-23 23:05:19.165299: step: 2158/1545, loss: 0.00022067292593419552 2023-01-23 23:05:20.014119: step: 2160/1545, loss: 0.0342659056186676 2023-01-23 23:05:20.868017: step: 2162/1545, loss: 0.00016101967776194215 2023-01-23 23:05:21.826443: step: 2164/1545, loss: 0.18551813066005707 2023-01-23 23:05:22.721690: step: 2166/1545, loss: 0.0001488795824116096 2023-01-23 23:05:23.575591: step: 2168/1545, loss: 0.03124578855931759 2023-01-23 23:05:24.447651: step: 2170/1545, loss: 0.004283970687538385 2023-01-23 23:05:25.305859: step: 2172/1545, loss: 0.28084850311279297 2023-01-23 23:05:26.176688: step: 2174/1545, loss: 0.0007581728277727962 2023-01-23 23:05:27.119316: step: 2176/1545, loss: 0.05864439904689789 2023-01-23 23:05:27.949988: step: 2178/1545, loss: 0.07480494678020477 2023-01-23 23:05:28.834050: step: 2180/1545, loss: 0.05435597151517868 2023-01-23 23:05:29.660978: step: 2182/1545, loss: 0.0004082758096046746 2023-01-23 23:05:30.563531: step: 2184/1545, loss: 0.07796373218297958 2023-01-23 23:05:31.458557: step: 2186/1545, loss: 0.0014410954900085926 2023-01-23 23:05:32.291881: step: 2188/1545, loss: 0.00034897192381322384 2023-01-23 23:05:33.178917: step: 2190/1545, loss: 5.829987640026957e-05 2023-01-23 23:05:34.059338: step: 2192/1545, loss: 0.07345034927129745 2023-01-23 23:05:34.876382: step: 2194/1545, loss: 0.00022942321083974093 2023-01-23 23:05:35.776520: step: 2196/1545, loss: 1.3083414160064422e-05 2023-01-23 23:05:36.639451: step: 2198/1545, loss: 0.0002239285095129162 2023-01-23 23:05:37.482843: step: 2200/1545, loss: 0.001823592116124928 2023-01-23 23:05:38.381030: step: 2202/1545, loss: 0.0034271960612386465 2023-01-23 23:05:39.272446: step: 2204/1545, loss: 0.009908600710332394 2023-01-23 23:05:40.159175: step: 2206/1545, loss: 0.05026102438569069 2023-01-23 23:05:41.026303: step: 2208/1545, loss: 0.0001159816310973838 2023-01-23 23:05:41.889354: step: 2210/1545, loss: 0.08133970946073532 2023-01-23 23:05:42.820041: step: 2212/1545, loss: 0.006571777630597353 2023-01-23 23:05:43.658376: step: 2214/1545, loss: 0.009891991503536701 2023-01-23 23:05:44.545629: step: 2216/1545, loss: 0.0006607746472582221 2023-01-23 23:05:45.433945: step: 2218/1545, loss: 3.7095545849297196e-05 2023-01-23 23:05:46.316679: step: 2220/1545, loss: 0.0049943323247134686 2023-01-23 23:05:47.190113: step: 2222/1545, loss: 0.002634945325553417 2023-01-23 23:05:48.110761: step: 2224/1545, loss: 0.17912322282791138 2023-01-23 23:05:48.980389: step: 2226/1545, loss: 0.00047258660197257996 2023-01-23 23:05:49.873308: step: 2228/1545, loss: 0.00027690071146935225 2023-01-23 23:05:50.764922: step: 2230/1545, loss: 0.0004635245131794363 2023-01-23 23:05:51.661333: step: 2232/1545, loss: 0.00031439619488082826 2023-01-23 23:05:52.560354: step: 2234/1545, loss: 0.09098757803440094 2023-01-23 23:05:53.395150: step: 2236/1545, loss: 0.11253711581230164 2023-01-23 23:05:54.257474: step: 2238/1545, loss: 9.778476669453084e-05 2023-01-23 23:05:55.182366: step: 2240/1545, loss: 0.1978142410516739 2023-01-23 23:05:56.138226: step: 2242/1545, loss: 0.0015687927370890975 2023-01-23 23:05:57.055647: step: 2244/1545, loss: 0.0003519781748764217 2023-01-23 23:05:57.937670: step: 2246/1545, loss: 0.000789985409937799 2023-01-23 23:05:58.830059: step: 2248/1545, loss: 0.08161083608865738 2023-01-23 23:05:59.699749: step: 2250/1545, loss: 0.03546348959207535 2023-01-23 23:06:00.554174: step: 2252/1545, loss: 0.00011924803402507678 2023-01-23 23:06:01.424987: step: 2254/1545, loss: 0.00010933249723166227 2023-01-23 23:06:02.270859: step: 2256/1545, loss: 0.023844048380851746 2023-01-23 23:06:03.150086: step: 2258/1545, loss: 0.00166017422452569 2023-01-23 23:06:04.033579: step: 2260/1545, loss: 0.0006983891944400966 2023-01-23 23:06:04.926293: step: 2262/1545, loss: 0.0006613428122363985 2023-01-23 23:06:05.802072: step: 2264/1545, loss: 0.00010834217391675338 2023-01-23 23:06:06.755790: step: 2266/1545, loss: 0.03517847880721092 2023-01-23 23:06:07.638294: step: 2268/1545, loss: 0.00037102893111296 2023-01-23 23:06:08.499293: step: 2270/1545, loss: 0.04098372533917427 2023-01-23 23:06:09.417641: step: 2272/1545, loss: 0.008520436473190784 2023-01-23 23:06:10.344730: step: 2274/1545, loss: 0.020369507372379303 2023-01-23 23:06:11.197879: step: 2276/1545, loss: 0.000963957398198545 2023-01-23 23:06:12.057589: step: 2278/1545, loss: 0.006674203090369701 2023-01-23 23:06:12.912635: step: 2280/1545, loss: 0.00023228001373354346 2023-01-23 23:06:13.805658: step: 2282/1545, loss: 0.0003923762997146696 2023-01-23 23:06:14.715516: step: 2284/1545, loss: 0.04306519031524658 2023-01-23 23:06:15.598601: step: 2286/1545, loss: 0.00017773202853277326 2023-01-23 23:06:16.509145: step: 2288/1545, loss: 0.36209020018577576 2023-01-23 23:06:17.386644: step: 2290/1545, loss: 0.29678359627723694 2023-01-23 23:06:18.282400: step: 2292/1545, loss: 0.0003267649153713137 2023-01-23 23:06:19.182151: step: 2294/1545, loss: 0.16638065874576569 2023-01-23 23:06:20.074685: step: 2296/1545, loss: 0.00032450020080432296 2023-01-23 23:06:20.964393: step: 2298/1545, loss: 0.018685951828956604 2023-01-23 23:06:21.888847: step: 2300/1545, loss: 6.586160452570766e-05 2023-01-23 23:06:22.810529: step: 2302/1545, loss: 0.002326209330931306 2023-01-23 23:06:23.688952: step: 2304/1545, loss: 0.005302465986460447 2023-01-23 23:06:24.581970: step: 2306/1545, loss: 0.08094209432601929 2023-01-23 23:06:25.496761: step: 2308/1545, loss: 0.004682547878473997 2023-01-23 23:06:26.415159: step: 2310/1545, loss: 0.031999994069337845 2023-01-23 23:06:27.251775: step: 2312/1545, loss: 0.00018464856839273125 2023-01-23 23:06:28.121561: step: 2314/1545, loss: 0.003979169763624668 2023-01-23 23:06:29.019254: step: 2316/1545, loss: 0.000416324008256197 2023-01-23 23:06:29.944545: step: 2318/1545, loss: 0.010617459192872047 2023-01-23 23:06:30.791857: step: 2320/1545, loss: 0.00023326653172262013 2023-01-23 23:06:31.677572: step: 2322/1545, loss: 0.0013053400907665491 2023-01-23 23:06:32.579119: step: 2324/1545, loss: 7.353578985203058e-05 2023-01-23 23:06:33.451761: step: 2326/1545, loss: 0.00025234222994185984 2023-01-23 23:06:34.392004: step: 2328/1545, loss: 0.02460797131061554 2023-01-23 23:06:35.284852: step: 2330/1545, loss: 9.783432687981986e-06 2023-01-23 23:06:36.146021: step: 2332/1545, loss: 0.00017460067465435714 2023-01-23 23:06:37.039437: step: 2334/1545, loss: 0.0015147437807172537 2023-01-23 23:06:37.913626: step: 2336/1545, loss: 0.00019534429884515703 2023-01-23 23:06:38.787554: step: 2338/1545, loss: 0.0747571513056755 2023-01-23 23:06:39.703572: step: 2340/1545, loss: 7.974018808454275e-05 2023-01-23 23:06:40.577530: step: 2342/1545, loss: 9.103561751544476e-05 2023-01-23 23:06:41.443781: step: 2344/1545, loss: 0.009079922921955585 2023-01-23 23:06:42.357885: step: 2346/1545, loss: 0.0001287882769247517 2023-01-23 23:06:43.225103: step: 2348/1545, loss: 0.003513412782922387 2023-01-23 23:06:44.085321: step: 2350/1545, loss: 2.8801396183553152e-05 2023-01-23 23:06:44.959009: step: 2352/1545, loss: 0.0006990800611674786 2023-01-23 23:06:45.839573: step: 2354/1545, loss: 0.00020485473214648664 2023-01-23 23:06:46.729152: step: 2356/1545, loss: 0.0018934420077130198 2023-01-23 23:06:47.656534: step: 2358/1545, loss: 0.0015443714801222086 2023-01-23 23:06:48.564557: step: 2360/1545, loss: -8.039180102059618e-06 2023-01-23 23:06:49.453289: step: 2362/1545, loss: 2.0687357391580008e-05 2023-01-23 23:06:50.319664: step: 2364/1545, loss: 8.662328764330596e-05 2023-01-23 23:06:51.233345: step: 2366/1545, loss: 0.019854098558425903 2023-01-23 23:06:52.130082: step: 2368/1545, loss: 0.07875171303749084 2023-01-23 23:06:53.093225: step: 2370/1545, loss: 1.394074297422776e-05 2023-01-23 23:06:53.992090: step: 2372/1545, loss: 8.470081229461357e-05 2023-01-23 23:06:54.922336: step: 2374/1545, loss: 0.07317686080932617 2023-01-23 23:06:55.781162: step: 2376/1545, loss: 8.283051283797249e-05 2023-01-23 23:06:56.687016: step: 2378/1545, loss: 0.28052088618278503 2023-01-23 23:06:57.562183: step: 2380/1545, loss: 1.0961283805954736e-05 2023-01-23 23:06:58.445598: step: 2382/1545, loss: 0.01777701824903488 2023-01-23 23:06:59.349601: step: 2384/1545, loss: 0.0003866585320793092 2023-01-23 23:07:00.269206: step: 2386/1545, loss: 0.07331801950931549 2023-01-23 23:07:01.219842: step: 2388/1545, loss: 3.423541784286499e-05 2023-01-23 23:07:02.252353: step: 2390/1545, loss: 3.472268508630805e-05 2023-01-23 23:07:03.171230: step: 2392/1545, loss: 0.18321385979652405 2023-01-23 23:07:04.067490: step: 2394/1545, loss: 0.0004000551416538656 2023-01-23 23:07:04.928501: step: 2396/1545, loss: 0.0014542428543791175 2023-01-23 23:07:05.831423: step: 2398/1545, loss: 0.0012341836700215936 2023-01-23 23:07:06.730733: step: 2400/1545, loss: 2.0794118427147623e-06 2023-01-23 23:07:07.637431: step: 2402/1545, loss: 0.055618613958358765 2023-01-23 23:07:08.500002: step: 2404/1545, loss: 0.0014409985160455108 2023-01-23 23:07:09.347474: step: 2406/1545, loss: 1.30228700072621e-05 2023-01-23 23:07:10.191313: step: 2408/1545, loss: 0.16817207634449005 2023-01-23 23:07:11.073613: step: 2410/1545, loss: 0.0006874113460071385 2023-01-23 23:07:11.927636: step: 2412/1545, loss: 0.00030315632466226816 2023-01-23 23:07:12.799696: step: 2414/1545, loss: 9.783846326172352e-05 2023-01-23 23:07:13.720523: step: 2416/1545, loss: 0.0016172085888683796 2023-01-23 23:07:14.614745: step: 2418/1545, loss: 0.002507888013496995 2023-01-23 23:07:15.463869: step: 2420/1545, loss: 0.1956101804971695 2023-01-23 23:07:16.333480: step: 2422/1545, loss: -2.7385354769648984e-05 2023-01-23 23:07:17.228253: step: 2424/1545, loss: 0.00017748707614373416 2023-01-23 23:07:18.096096: step: 2426/1545, loss: 0.00046627363190054893 2023-01-23 23:07:19.010969: step: 2428/1545, loss: 0.00033951495424844325 2023-01-23 23:07:19.866574: step: 2430/1545, loss: 0.0006698608631268144 2023-01-23 23:07:20.715249: step: 2432/1545, loss: -4.495436769502703e-06 2023-01-23 23:07:21.621112: step: 2434/1545, loss: 0.0001288073544856161 2023-01-23 23:07:22.519384: step: 2436/1545, loss: 0.06785689294338226 2023-01-23 23:07:23.368626: step: 2438/1545, loss: 7.187389564933255e-05 2023-01-23 23:07:24.250047: step: 2440/1545, loss: 0.00030281758517958224 2023-01-23 23:07:25.169287: step: 2442/1545, loss: 3.004073369083926e-05 2023-01-23 23:07:26.036676: step: 2444/1545, loss: 7.41779649615637e-06 2023-01-23 23:07:26.894180: step: 2446/1545, loss: 0.10319939255714417 2023-01-23 23:07:27.756314: step: 2448/1545, loss: 0.021191522479057312 2023-01-23 23:07:28.663007: step: 2450/1545, loss: 6.106274668127298e-05 2023-01-23 23:07:29.539372: step: 2452/1545, loss: 8.716924639884382e-05 2023-01-23 23:07:30.471760: step: 2454/1545, loss: 0.27607661485671997 2023-01-23 23:07:31.310788: step: 2456/1545, loss: 0.05734962224960327 2023-01-23 23:07:32.181567: step: 2458/1545, loss: 0.15682204067707062 2023-01-23 23:07:33.070220: step: 2460/1545, loss: 0.0017021674429997802 2023-01-23 23:07:33.960501: step: 2462/1545, loss: 0.025360461324453354 2023-01-23 23:07:34.847268: step: 2464/1545, loss: 0.0004799643938895315 2023-01-23 23:07:35.713111: step: 2466/1545, loss: 0.023042570799589157 2023-01-23 23:07:36.586445: step: 2468/1545, loss: 0.007925057783722878 2023-01-23 23:07:37.479672: step: 2470/1545, loss: 3.814693627646193e-07 2023-01-23 23:07:38.321704: step: 2472/1545, loss: 1.6839792806422338e-05 2023-01-23 23:07:39.219618: step: 2474/1545, loss: 0.21198812127113342 2023-01-23 23:07:40.105818: step: 2476/1545, loss: 0.00022942732903175056 2023-01-23 23:07:40.965185: step: 2478/1545, loss: 0.006067147944122553 2023-01-23 23:07:41.810143: step: 2480/1545, loss: 6.597071478608996e-05 2023-01-23 23:07:42.745669: step: 2482/1545, loss: 0.005070878192782402 2023-01-23 23:07:43.681060: step: 2484/1545, loss: 0.03396713361144066 2023-01-23 23:07:44.527186: step: 2486/1545, loss: 3.05696994473692e-05 2023-01-23 23:07:45.404837: step: 2488/1545, loss: 7.665348675800487e-05 2023-01-23 23:07:46.268373: step: 2490/1545, loss: 0.092876136302948 2023-01-23 23:07:47.171954: step: 2492/1545, loss: 0.206936314702034 2023-01-23 23:07:48.054508: step: 2494/1545, loss: 0.00028029008535668254 2023-01-23 23:07:48.886762: step: 2496/1545, loss: 6.105005468270974e-06 2023-01-23 23:07:49.724240: step: 2498/1545, loss: 1.2573584172059782e-05 2023-01-23 23:07:50.653369: step: 2500/1545, loss: 0.0021125953644514084 2023-01-23 23:07:51.549409: step: 2502/1545, loss: 0.0007740497821941972 2023-01-23 23:07:52.406560: step: 2504/1545, loss: 0.1363559365272522 2023-01-23 23:07:53.286131: step: 2506/1545, loss: 0.00010299459245288745 2023-01-23 23:07:54.159563: step: 2508/1545, loss: 0.0009613336296752095 2023-01-23 23:07:55.018433: step: 2510/1545, loss: 0.3156276047229767 2023-01-23 23:07:55.868480: step: 2512/1545, loss: 0.0011290842667222023 2023-01-23 23:07:56.699596: step: 2514/1545, loss: 7.659243419766426e-05 2023-01-23 23:07:57.627917: step: 2516/1545, loss: 0.02278292179107666 2023-01-23 23:07:58.480359: step: 2518/1545, loss: 0.000569234776776284 2023-01-23 23:07:59.349849: step: 2520/1545, loss: 0.143762469291687 2023-01-23 23:08:00.210640: step: 2522/1545, loss: 0.0011338780168443918 2023-01-23 23:08:01.109667: step: 2524/1545, loss: 9.531081013847142e-05 2023-01-23 23:08:01.958555: step: 2526/1545, loss: 0.0011499011889100075 2023-01-23 23:08:02.879982: step: 2528/1545, loss: 4.451572385733016e-05 2023-01-23 23:08:03.760851: step: 2530/1545, loss: 7.40882387617603e-05 2023-01-23 23:08:04.651791: step: 2532/1545, loss: 0.00010857016604859382 2023-01-23 23:08:05.530261: step: 2534/1545, loss: 0.0001278628915315494 2023-01-23 23:08:06.394417: step: 2536/1545, loss: 0.08327703922986984 2023-01-23 23:08:07.349274: step: 2538/1545, loss: 0.4342317581176758 2023-01-23 23:08:08.221981: step: 2540/1545, loss: 0.0004387715889606625 2023-01-23 23:08:09.082587: step: 2542/1545, loss: 0.0035558314993977547 2023-01-23 23:08:09.982046: step: 2544/1545, loss: 0.29655054211616516 2023-01-23 23:08:10.845369: step: 2546/1545, loss: 0.15368489921092987 2023-01-23 23:08:11.716961: step: 2548/1545, loss: 0.08070029318332672 2023-01-23 23:08:12.590447: step: 2550/1545, loss: 0.26104652881622314 2023-01-23 23:08:13.467061: step: 2552/1545, loss: 0.22035805881023407 2023-01-23 23:08:14.339385: step: 2554/1545, loss: 0.23040048778057098 2023-01-23 23:08:15.211999: step: 2556/1545, loss: 0.004007377196103334 2023-01-23 23:08:16.126162: step: 2558/1545, loss: 0.003696852596476674 2023-01-23 23:08:17.011437: step: 2560/1545, loss: 7.22467084415257e-05 2023-01-23 23:08:17.869239: step: 2562/1545, loss: 0.016232216730713844 2023-01-23 23:08:18.759764: step: 2564/1545, loss: 0.09643115848302841 2023-01-23 23:08:19.727055: step: 2566/1545, loss: 0.0030134369153529406 2023-01-23 23:08:20.595590: step: 2568/1545, loss: 0.0007324147154577076 2023-01-23 23:08:21.443436: step: 2570/1545, loss: 0.0002457648515701294 2023-01-23 23:08:22.323153: step: 2572/1545, loss: 0.0004130364686716348 2023-01-23 23:08:23.135811: step: 2574/1545, loss: 0.004652659874409437 2023-01-23 23:08:23.964234: step: 2576/1545, loss: 0.0007897243485786021 2023-01-23 23:08:24.844929: step: 2578/1545, loss: 0.0012158968020230532 2023-01-23 23:08:25.784457: step: 2580/1545, loss: 0.20740653574466705 2023-01-23 23:08:26.648395: step: 2582/1545, loss: 0.08741430938243866 2023-01-23 23:08:27.489889: step: 2584/1545, loss: 0.00045708834659308195 2023-01-23 23:08:28.346607: step: 2586/1545, loss: 0.014598682522773743 2023-01-23 23:08:29.254605: step: 2588/1545, loss: 0.0013282130239531398 2023-01-23 23:08:30.114341: step: 2590/1545, loss: 0.002439193893224001 2023-01-23 23:08:31.016018: step: 2592/1545, loss: 0.0001759268925525248 2023-01-23 23:08:31.874430: step: 2594/1545, loss: 0.016051972284913063 2023-01-23 23:08:32.721868: step: 2596/1545, loss: 1.4755121810594574e-05 2023-01-23 23:08:33.633766: step: 2598/1545, loss: 0.00645486731082201 2023-01-23 23:08:34.494993: step: 2600/1545, loss: 0.00018116759019903839 2023-01-23 23:08:35.365968: step: 2602/1545, loss: 0.0003124202194157988 2023-01-23 23:08:36.219569: step: 2604/1545, loss: 4.461999924387783e-05 2023-01-23 23:08:37.030389: step: 2606/1545, loss: 0.0018432221841067076 2023-01-23 23:08:37.931468: step: 2608/1545, loss: 0.0004249765770509839 2023-01-23 23:08:38.804526: step: 2610/1545, loss: 0.00987198669463396 2023-01-23 23:08:39.669216: step: 2612/1545, loss: 0.0006894668331369758 2023-01-23 23:08:40.526801: step: 2614/1545, loss: 0.000407073792302981 2023-01-23 23:08:41.386580: step: 2616/1545, loss: 0.04737293720245361 2023-01-23 23:08:42.279794: step: 2618/1545, loss: 0.09655197709798813 2023-01-23 23:08:43.176021: step: 2620/1545, loss: 0.004948565736413002 2023-01-23 23:08:44.029562: step: 2622/1545, loss: 0.014044729992747307 2023-01-23 23:08:44.913407: step: 2624/1545, loss: 0.03348616510629654 2023-01-23 23:08:45.769028: step: 2626/1545, loss: 0.0005466570146381855 2023-01-23 23:08:46.667128: step: 2628/1545, loss: 0.0003330112958792597 2023-01-23 23:08:47.522274: step: 2630/1545, loss: 0.11197282373905182 2023-01-23 23:08:48.424279: step: 2632/1545, loss: 6.881691660964862e-05 2023-01-23 23:08:49.358438: step: 2634/1545, loss: 0.00021296711929608136 2023-01-23 23:08:50.245735: step: 2636/1545, loss: 0.6935604214668274 2023-01-23 23:08:51.123834: step: 2638/1545, loss: 2.4766795831965283e-05 2023-01-23 23:08:52.043379: step: 2640/1545, loss: 4.421779522090219e-06 2023-01-23 23:08:52.907691: step: 2642/1545, loss: 0.00021176988957449794 2023-01-23 23:08:53.753705: step: 2644/1545, loss: 0.0009084107587113976 2023-01-23 23:08:54.668401: step: 2646/1545, loss: -1.5859874110901728e-05 2023-01-23 23:08:55.551703: step: 2648/1545, loss: 0.006962986662983894 2023-01-23 23:08:56.416308: step: 2650/1545, loss: -2.0955145373591222e-05 2023-01-23 23:08:57.304967: step: 2652/1545, loss: 0.060634784400463104 2023-01-23 23:08:58.179791: step: 2654/1545, loss: 0.0016325716860592365 2023-01-23 23:08:59.041281: step: 2656/1545, loss: 2.82456476270454e-05 2023-01-23 23:08:59.876854: step: 2658/1545, loss: 0.7493739128112793 2023-01-23 23:09:00.733418: step: 2660/1545, loss: 0.024525795131921768 2023-01-23 23:09:01.616731: step: 2662/1545, loss: 0.01573956571519375 2023-01-23 23:09:02.497797: step: 2664/1545, loss: 0.0001493722083978355 2023-01-23 23:09:03.381441: step: 2666/1545, loss: 1.3402224794845097e-05 2023-01-23 23:09:04.259296: step: 2668/1545, loss: 0.00012911764497403055 2023-01-23 23:09:05.215451: step: 2670/1545, loss: 0.00013911073619965464 2023-01-23 23:09:06.121358: step: 2672/1545, loss: 0.3063856065273285 2023-01-23 23:09:06.952379: step: 2674/1545, loss: 0.026236137375235558 2023-01-23 23:09:07.814872: step: 2676/1545, loss: -9.512901669950224e-06 2023-01-23 23:09:08.671757: step: 2678/1545, loss: 0.003124329261481762 2023-01-23 23:09:09.550253: step: 2680/1545, loss: 0.028764769434928894 2023-01-23 23:09:10.425094: step: 2682/1545, loss: 0.0872846469283104 2023-01-23 23:09:11.289962: step: 2684/1545, loss: -6.295755383689539e-07 2023-01-23 23:09:12.161011: step: 2686/1545, loss: 0.00013699331611860543 2023-01-23 23:09:13.002003: step: 2688/1545, loss: 4.6968143578851596e-06 2023-01-23 23:09:13.862076: step: 2690/1545, loss: 3.0181807233020663e-05 2023-01-23 23:09:14.821604: step: 2692/1545, loss: 0.050082169473171234 2023-01-23 23:09:15.710405: step: 2694/1545, loss: -4.527048076852225e-05 2023-01-23 23:09:16.568481: step: 2696/1545, loss: 0.011398493312299252 2023-01-23 23:09:17.409120: step: 2698/1545, loss: 0.007308299653232098 2023-01-23 23:09:18.318915: step: 2700/1545, loss: -1.5147775229706895e-05 2023-01-23 23:09:19.166530: step: 2702/1545, loss: 0.0019360128790140152 2023-01-23 23:09:20.081126: step: 2704/1545, loss: 0.0044822292402386665 2023-01-23 23:09:20.916063: step: 2706/1545, loss: 0.0015867501497268677 2023-01-23 23:09:21.910673: step: 2708/1545, loss: 5.825219341204502e-05 2023-01-23 23:09:22.741495: step: 2710/1545, loss: 0.011154429987072945 2023-01-23 23:09:23.649290: step: 2712/1545, loss: 0.0026055488269776106 2023-01-23 23:09:24.503047: step: 2714/1545, loss: -1.0439795005368069e-05 2023-01-23 23:09:25.374213: step: 2716/1545, loss: 0.00010011947597377002 2023-01-23 23:09:26.279914: step: 2718/1545, loss: 1.144120869867038e-05 2023-01-23 23:09:27.159029: step: 2720/1545, loss: 0.004966341890394688 2023-01-23 23:09:28.020349: step: 2722/1545, loss: 8.334020094480366e-05 2023-01-23 23:09:28.900880: step: 2724/1545, loss: 0.024832503870129585 2023-01-23 23:09:29.814437: step: 2726/1545, loss: 0.0003855004906654358 2023-01-23 23:09:30.666256: step: 2728/1545, loss: 3.937480505555868e-05 2023-01-23 23:09:31.525387: step: 2730/1545, loss: 2.3568745746160857e-05 2023-01-23 23:09:32.433353: step: 2732/1545, loss: 0.001655137399211526 2023-01-23 23:09:33.336163: step: 2734/1545, loss: 9.562706691212952e-05 2023-01-23 23:09:34.205015: step: 2736/1545, loss: 0.005346106365323067 2023-01-23 23:09:35.107531: step: 2738/1545, loss: 0.0002928097383119166 2023-01-23 23:09:35.969116: step: 2740/1545, loss: 0.0008666646317578852 2023-01-23 23:09:36.837831: step: 2742/1545, loss: -1.6275353118544444e-05 2023-01-23 23:09:37.746688: step: 2744/1545, loss: 0.005125813186168671 2023-01-23 23:09:38.626174: step: 2746/1545, loss: 8.330788114108145e-05 2023-01-23 23:09:39.567141: step: 2748/1545, loss: 1.3045203559158836e-05 2023-01-23 23:09:40.474534: step: 2750/1545, loss: 0.188681498169899 2023-01-23 23:09:41.368678: step: 2752/1545, loss: 0.00011476935469545424 2023-01-23 23:09:42.227686: step: 2754/1545, loss: -2.6687980607675854e-06 2023-01-23 23:09:43.116479: step: 2756/1545, loss: 9.157509339274839e-06 2023-01-23 23:09:43.971162: step: 2758/1545, loss: 2.2779729988542385e-05 2023-01-23 23:09:44.907010: step: 2760/1545, loss: 0.0001295017427764833 2023-01-23 23:09:45.871215: step: 2762/1545, loss: 0.00017969799228012562 2023-01-23 23:09:46.730217: step: 2764/1545, loss: 0.00035898745409213006 2023-01-23 23:09:47.588548: step: 2766/1545, loss: 0.000417820003349334 2023-01-23 23:09:48.467774: step: 2768/1545, loss: 0.000579379266127944 2023-01-23 23:09:49.321400: step: 2770/1545, loss: 1.8466076653567143e-05 2023-01-23 23:09:50.189910: step: 2772/1545, loss: 4.123767212149687e-05 2023-01-23 23:09:51.087926: step: 2774/1545, loss: 4.526925476966426e-05 2023-01-23 23:09:51.950161: step: 2776/1545, loss: 0.0015143449418246746 2023-01-23 23:09:52.798148: step: 2778/1545, loss: 0.001350743230432272 2023-01-23 23:09:53.650471: step: 2780/1545, loss: 0.008603149093687534 2023-01-23 23:09:54.555323: step: 2782/1545, loss: 0.1652776449918747 2023-01-23 23:09:55.416426: step: 2784/1545, loss: 0.00018255747272633016 2023-01-23 23:09:56.281975: step: 2786/1545, loss: 0.10383806377649307 2023-01-23 23:09:57.230361: step: 2788/1545, loss: 0.014051070436835289 2023-01-23 23:09:58.159642: step: 2790/1545, loss: 0.0005584288737736642 2023-01-23 23:09:59.049097: step: 2792/1545, loss: 0.0007210289477370679 2023-01-23 23:09:59.924915: step: 2794/1545, loss: 0.0026278444565832615 2023-01-23 23:10:00.833413: step: 2796/1545, loss: 0.015108978375792503 2023-01-23 23:10:01.742339: step: 2798/1545, loss: 0.0001784743508324027 2023-01-23 23:10:02.675928: step: 2800/1545, loss: 3.306537837488577e-05 2023-01-23 23:10:03.542632: step: 2802/1545, loss: 0.0011056505609303713 2023-01-23 23:10:04.442943: step: 2804/1545, loss: 0.017717380076646805 2023-01-23 23:10:05.309954: step: 2806/1545, loss: 0.00014124513836577535 2023-01-23 23:10:06.146504: step: 2808/1545, loss: 2.0603338271030225e-05 2023-01-23 23:10:07.039456: step: 2810/1545, loss: 0.00039439008105546236 2023-01-23 23:10:07.982972: step: 2812/1545, loss: 0.02246193028986454 2023-01-23 23:10:08.844772: step: 2814/1545, loss: 0.08934377878904343 2023-01-23 23:10:09.693543: step: 2816/1545, loss: 3.783046850003302e-05 2023-01-23 23:10:10.622105: step: 2818/1545, loss: 0.004410785157233477 2023-01-23 23:10:11.504978: step: 2820/1545, loss: -1.2877618246420752e-05 2023-01-23 23:10:12.365660: step: 2822/1545, loss: 0.005330936051905155 2023-01-23 23:10:13.234136: step: 2824/1545, loss: 0.11238530278205872 2023-01-23 23:10:14.133043: step: 2826/1545, loss: 7.686039316467941e-05 2023-01-23 23:10:14.962476: step: 2828/1545, loss: 1.8665466996026225e-05 2023-01-23 23:10:15.892560: step: 2830/1545, loss: 0.07413293421268463 2023-01-23 23:10:16.766320: step: 2832/1545, loss: 0.8169718980789185 2023-01-23 23:10:17.658985: step: 2834/1545, loss: 1.9905744920833968e-05 2023-01-23 23:10:18.539229: step: 2836/1545, loss: 0.0005124039598740637 2023-01-23 23:10:19.429849: step: 2838/1545, loss: 0.1874437779188156 2023-01-23 23:10:20.309993: step: 2840/1545, loss: 0.0011481033870950341 2023-01-23 23:10:21.175329: step: 2842/1545, loss: 0.002168850740417838 2023-01-23 23:10:22.013316: step: 2844/1545, loss: 0.01571076363325119 2023-01-23 23:10:22.943544: step: 2846/1545, loss: 0.0916878879070282 2023-01-23 23:10:23.814149: step: 2848/1545, loss: 0.0019245815929025412 2023-01-23 23:10:24.662840: step: 2850/1545, loss: 0.012912950478494167 2023-01-23 23:10:25.537097: step: 2852/1545, loss: 0.0055448436178267 2023-01-23 23:10:26.388211: step: 2854/1545, loss: 0.1139262467622757 2023-01-23 23:10:27.258477: step: 2856/1545, loss: 0.007413654122501612 2023-01-23 23:10:28.147724: step: 2858/1545, loss: 0.011096274480223656 2023-01-23 23:10:29.010226: step: 2860/1545, loss: 0.0009791068732738495 2023-01-23 23:10:29.890757: step: 2862/1545, loss: 0.0021511861123144627 2023-01-23 23:10:30.805314: step: 2864/1545, loss: 0.0010615969076752663 2023-01-23 23:10:31.650629: step: 2866/1545, loss: 1.327293739450397e-05 2023-01-23 23:10:32.490203: step: 2868/1545, loss: 0.0002518206893000752 2023-01-23 23:10:33.346619: step: 2870/1545, loss: 0.000552806886844337 2023-01-23 23:10:34.242498: step: 2872/1545, loss: 0.09830059111118317 2023-01-23 23:10:35.131522: step: 2874/1545, loss: -1.0430070688016713e-05 2023-01-23 23:10:36.022406: step: 2876/1545, loss: 0.00771041726693511 2023-01-23 23:10:36.956621: step: 2878/1545, loss: 0.0017162943258881569 2023-01-23 23:10:37.816812: step: 2880/1545, loss: 0.03561867028474808 2023-01-23 23:10:38.669396: step: 2882/1545, loss: 0.0006087615620344877 2023-01-23 23:10:39.568250: step: 2884/1545, loss: 0.003052005311474204 2023-01-23 23:10:40.429768: step: 2886/1545, loss: 0.48275938630104065 2023-01-23 23:10:41.320855: step: 2888/1545, loss: 0.1984413117170334 2023-01-23 23:10:42.214250: step: 2890/1545, loss: 0.0031085656955838203 2023-01-23 23:10:43.107835: step: 2892/1545, loss: 0.005147450137883425 2023-01-23 23:10:43.966202: step: 2894/1545, loss: -1.9057601093663834e-05 2023-01-23 23:10:44.841706: step: 2896/1545, loss: 2.7118127036374062e-05 2023-01-23 23:10:45.733085: step: 2898/1545, loss: 0.022065365687012672 2023-01-23 23:10:46.629056: step: 2900/1545, loss: 0.373463898897171 2023-01-23 23:10:47.492638: step: 2902/1545, loss: 0.0008996905526146293 2023-01-23 23:10:48.371378: step: 2904/1545, loss: 0.0011975435772910714 2023-01-23 23:10:49.268281: step: 2906/1545, loss: 2.757440415734891e-05 2023-01-23 23:10:50.131377: step: 2908/1545, loss: 9.575395961292088e-05 2023-01-23 23:10:51.047953: step: 2910/1545, loss: 0.2974560856819153 2023-01-23 23:10:51.953382: step: 2912/1545, loss: 0.0006309528835117817 2023-01-23 23:10:52.901763: step: 2914/1545, loss: 0.010097642429172993 2023-01-23 23:10:53.949593: step: 2916/1545, loss: 0.2044754922389984 2023-01-23 23:10:54.889783: step: 2918/1545, loss: 0.00013156891509424895 2023-01-23 23:10:55.711341: step: 2920/1545, loss: 0.00016800661978777498 2023-01-23 23:10:56.569290: step: 2922/1545, loss: 0.0001203811407322064 2023-01-23 23:10:57.423825: step: 2924/1545, loss: 1.2237060218467377e-05 2023-01-23 23:10:58.365209: step: 2926/1545, loss: 0.02595445141196251 2023-01-23 23:10:59.238981: step: 2928/1545, loss: 0.0009901042794808745 2023-01-23 23:11:00.143879: step: 2930/1545, loss: 4.076817276654765e-05 2023-01-23 23:11:00.998038: step: 2932/1545, loss: -8.137525583151728e-06 2023-01-23 23:11:01.868397: step: 2934/1545, loss: 9.076639980776235e-05 2023-01-23 23:11:02.709097: step: 2936/1545, loss: 2.976109681185335e-05 2023-01-23 23:11:03.582183: step: 2938/1545, loss: 7.899694901425391e-05 2023-01-23 23:11:04.505883: step: 2940/1545, loss: 0.0006202342337928712 2023-01-23 23:11:05.378242: step: 2942/1545, loss: 0.00015819403051864356 2023-01-23 23:11:06.271496: step: 2944/1545, loss: 2.8262213163543493e-05 2023-01-23 23:11:07.122427: step: 2946/1545, loss: 0.0007778379367664456 2023-01-23 23:11:08.005627: step: 2948/1545, loss: 0.7958571314811707 2023-01-23 23:11:08.876690: step: 2950/1545, loss: 0.34631770849227905 2023-01-23 23:11:09.738401: step: 2952/1545, loss: 0.00012832146603614092 2023-01-23 23:11:10.609052: step: 2954/1545, loss: 5.607704588328488e-05 2023-01-23 23:11:11.453106: step: 2956/1545, loss: 1.2562860320031177e-05 2023-01-23 23:11:12.342324: step: 2958/1545, loss: 0.15566326677799225 2023-01-23 23:11:13.256686: step: 2960/1545, loss: 0.04709320887923241 2023-01-23 23:11:14.156148: step: 2962/1545, loss: 0.45026955008506775 2023-01-23 23:11:15.050268: step: 2964/1545, loss: 0.0009231693111360073 2023-01-23 23:11:15.948132: step: 2966/1545, loss: 0.0001513001334387809 2023-01-23 23:11:16.822856: step: 2968/1545, loss: 0.0036298087798058987 2023-01-23 23:11:17.715030: step: 2970/1545, loss: 7.473393634427339e-05 2023-01-23 23:11:18.588670: step: 2972/1545, loss: 5.583825259236619e-05 2023-01-23 23:11:19.516962: step: 2974/1545, loss: 5.555986354011111e-05 2023-01-23 23:11:20.367281: step: 2976/1545, loss: 0.0002872660697903484 2023-01-23 23:11:21.242570: step: 2978/1545, loss: 0.08990637212991714 2023-01-23 23:11:22.095313: step: 2980/1545, loss: 0.0009442732552997768 2023-01-23 23:11:23.007864: step: 2982/1545, loss: 0.00029073984478600323 2023-01-23 23:11:23.879531: step: 2984/1545, loss: 0.14687120914459229 2023-01-23 23:11:24.727467: step: 2986/1545, loss: 1.3864968423149548e-05 2023-01-23 23:11:25.602856: step: 2988/1545, loss: 0.0002464823774062097 2023-01-23 23:11:26.471950: step: 2990/1545, loss: 0.0009597777971066535 2023-01-23 23:11:27.320475: step: 2992/1545, loss: 3.669858051580377e-05 2023-01-23 23:11:28.215479: step: 2994/1545, loss: 0.00018491312221158296 2023-01-23 23:11:29.045880: step: 2996/1545, loss: 0.058207813650369644 2023-01-23 23:11:30.073513: step: 2998/1545, loss: 0.05215476453304291 2023-01-23 23:11:30.981509: step: 3000/1545, loss: 0.2977886199951172 2023-01-23 23:11:31.860627: step: 3002/1545, loss: 0.030090339481830597 2023-01-23 23:11:32.707683: step: 3004/1545, loss: 0.0006569107063114643 2023-01-23 23:11:33.574666: step: 3006/1545, loss: 0.0002022025000769645 2023-01-23 23:11:34.419891: step: 3008/1545, loss: 0.0014222413301467896 2023-01-23 23:11:35.293189: step: 3010/1545, loss: 0.05549877882003784 2023-01-23 23:11:36.153567: step: 3012/1545, loss: 0.13902054727077484 2023-01-23 23:11:37.001795: step: 3014/1545, loss: 0.021693721413612366 2023-01-23 23:11:37.975410: step: 3016/1545, loss: 0.05034373700618744 2023-01-23 23:11:38.842380: step: 3018/1545, loss: 0.013922021724283695 2023-01-23 23:11:39.683261: step: 3020/1545, loss: 0.00012417063408065587 2023-01-23 23:11:40.537856: step: 3022/1545, loss: 0.028086192905902863 2023-01-23 23:11:41.482715: step: 3024/1545, loss: 0.11194045841693878 2023-01-23 23:11:42.367129: step: 3026/1545, loss: 9.838655387284234e-05 2023-01-23 23:11:43.252284: step: 3028/1545, loss: 0.00029185862513259053 2023-01-23 23:11:44.124711: step: 3030/1545, loss: 0.0011757948668673635 2023-01-23 23:11:45.023197: step: 3032/1545, loss: 0.00022663080017082393 2023-01-23 23:11:45.911783: step: 3034/1545, loss: 0.00453226687386632 2023-01-23 23:11:46.744557: step: 3036/1545, loss: 0.01759480871260166 2023-01-23 23:11:47.588985: step: 3038/1545, loss: 0.007062563672661781 2023-01-23 23:11:48.462888: step: 3040/1545, loss: 0.0004929829156026244 2023-01-23 23:11:49.373420: step: 3042/1545, loss: 0.04983516037464142 2023-01-23 23:11:50.264550: step: 3044/1545, loss: 0.0002664772910065949 2023-01-23 23:11:51.153501: step: 3046/1545, loss: 0.00017622634186409414 2023-01-23 23:11:52.012857: step: 3048/1545, loss: 3.857810588669963e-05 2023-01-23 23:11:52.875303: step: 3050/1545, loss: 0.0031061815097928047 2023-01-23 23:11:53.819618: step: 3052/1545, loss: 0.18225102126598358 2023-01-23 23:11:54.656565: step: 3054/1545, loss: 0.0012645686510950327 2023-01-23 23:11:55.615986: step: 3056/1545, loss: 0.00024829793255776167 2023-01-23 23:11:56.480002: step: 3058/1545, loss: 0.0001873224973678589 2023-01-23 23:11:57.407154: step: 3060/1545, loss: 0.0005426038987934589 2023-01-23 23:11:58.270187: step: 3062/1545, loss: 0.011891979724168777 2023-01-23 23:11:59.127115: step: 3064/1545, loss: 0.00015937222633510828 2023-01-23 23:11:59.996408: step: 3066/1545, loss: 0.00030783380498178303 2023-01-23 23:12:00.844371: step: 3068/1545, loss: 0.00022476086451206356 2023-01-23 23:12:01.707626: step: 3070/1545, loss: 0.04568184167146683 2023-01-23 23:12:02.564791: step: 3072/1545, loss: 0.037692777812480927 2023-01-23 23:12:03.469348: step: 3074/1545, loss: 0.2654385566711426 2023-01-23 23:12:04.319802: step: 3076/1545, loss: 0.0013552773743867874 2023-01-23 23:12:05.184017: step: 3078/1545, loss: 1.092522144317627 2023-01-23 23:12:06.088432: step: 3080/1545, loss: 0.000102849597169552 2023-01-23 23:12:06.982758: step: 3082/1545, loss: 0.008942573331296444 2023-01-23 23:12:07.838679: step: 3084/1545, loss: 0.0005663189804181457 2023-01-23 23:12:08.705753: step: 3086/1545, loss: 0.5272532105445862 2023-01-23 23:12:09.581279: step: 3088/1545, loss: 0.0008671785471960902 2023-01-23 23:12:10.479562: step: 3090/1545, loss: 0.01255625206977129 ================================================== Loss: 0.051 -------------------- Dev Chinese: {'event': {'p': 0.604143947655398, 'r': 0.7376830892143809, 'f1': 0.6642685851318945}, 'argument': {'p': 0.6547518161109622, 'r': 0.6547518161109622, 'f1': 0.6547518161109622}, 'combined': 0.43493106250056723, 'epoch': 38} Test Chinese: {'event': {'p': 0.6430096051227321, 'r': 0.770460358056266, 'f1': 0.7009889470622455}, 'argument': {'p': 0.6996405349315086, 'r': 0.7063164942342901, 'f1': 0.7029626647270049}, 'combined': 0.49276905817105343, 'epoch': 38} Dev Korean: {'event': {'p': 0.6083150984682714, 'r': 0.7403462050599201, 'f1': 0.667867867867868}, 'argument': {'p': 0.6626196217973507, 'r': 0.6546602269409261, 'f1': 0.6586158778589982}, 'combined': 0.4398683820896133, 'epoch': 38} Test Korean: {'event': {'p': 0.6301587301587301, 'r': 0.7615089514066496, 'f1': 0.6896352055587724}, 'argument': {'p': 0.6924399079547182, 'r': 0.7051452273667315, 'f1': 0.698734816208852}, 'combined': 0.48187212860726275, 'epoch': 38} Dev Russian: {'event': {'p': 0.5757874015748031, 'r': 0.7789613848202397, 'f1': 0.6621392190152802}, 'argument': {'p': 0.6564582780597298, 'r': 0.6606874294573944, 'f1': 0.6585660641826472}, 'combined': 0.4360624194078649, 'epoch': 38} Test Russian: {'event': {'p': 0.6292974588938715, 'r': 0.8075447570332481, 'f1': 0.7073648837860543}, 'argument': {'p': 0.7022199678478288, 'r': 0.7195977398305647, 'f1': 0.7108026563437467}, 'combined': 0.5027968383994131, 'epoch': 38} Chinese: {'event': {'p': 0.5897435897435898, 'r': 0.8518518518518519, 'f1': 0.6969696969696971}, 'argument': {'p': 0.6666457431457431, 'r': 0.5509468951617712, 'f1': 0.603299315064021}, 'combined': 0.42048134080219657, 'epoch': 38} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6619500139236981, 'r': 0.5168650793650793, 'f1': 0.580479242979243}, 'combined': 0.35643462288199135, 'epoch': 38} Russian: {'event': {'p': 0.5116279069767442, 'r': 0.6111111111111112, 'f1': 0.5569620253164557}, 'argument': {'p': 0.5566564116082233, 'r': 0.5765369977370884, 'f1': 0.5664223135662623}, 'combined': 0.31547571894829796, 'epoch': 38} ================================================== Current best result: -------------------- Dev for Chinese: {'event': {'p': 0.5997818974918212, 'r': 0.7323568575233023, 'f1': 0.6594724220623501}, 'argument': {'p': 0.6758987924276707, 'r': 0.6414709887684336, 'f1': 0.6582350269068861}, 'combined': 0.43408784748056034, 'epoch': 33} Test for Chinese: {'event': {'p': 0.6403415154749199, 'r': 0.7672634271099744, 'f1': 0.6980802792321118}, 'argument': {'p': 0.7201409239897084, 'r': 0.7110669833666995, 'f1': 0.7155751890249322}, 'combined': 0.49952892776609586, 'epoch': 33} Chinese: {'event': {'p': 0.6025641025641025, 'r': 0.8703703703703703, 'f1': 0.712121212121212}, 'argument': {'p': 0.7175290642271774, 'r': 0.6285791802320727, 'f1': 0.6701152494104036}, 'combined': 0.4772032836710449, 'epoch': 33} -------------------- Dev for Korean: {'event': {'p': 0.6072210065645515, 'r': 0.7390146471371505, 'f1': 0.6666666666666666}, 'argument': {'p': 0.679479351255927, 'r': 0.6457861602845586, 'f1': 0.6622044524951831}, 'combined': 0.4414696349967887, 'epoch': 21} Test for Korean: {'event': {'p': 0.6349206349206349, 'r': 0.7672634271099744, 'f1': 0.6948465547191662}, 'argument': {'p': 0.7120765802085607, 'r': 0.7036480296218995, 'f1': 0.7078372151256981}, 'combined': 0.4918382502321006, 'epoch': 21} Korean: {'event': {'p': 0.6862745098039216, 'r': 0.5555555555555556, 'f1': 0.6140350877192983}, 'argument': {'p': 0.6946010860484545, 'r': 0.5423597521200261, 'f1': 0.6091117216117216}, 'combined': 0.37401596941070625, 'epoch': 21} -------------------- Dev for Russian: {'event': {'p': 0.5718503937007874, 'r': 0.7736351531291611, 'f1': 0.6576117713638936}, 'argument': {'p': 0.6589821494992243, 'r': 0.6537970252900029, 'f1': 0.656379347472477}, 'combined': 0.4316427853780522, 'epoch': 17} Test for Russian: {'event': {'p': 0.6278026905829597, 'r': 0.8056265984654731, 'f1': 0.7056846821618594}, 'argument': {'p': 0.7071220972103918, 'r': 0.7219364770995731, 'f1': 0.7144525002914325}, 'combined': 0.5041781855879053, 'epoch': 17} Russian: {'event': {'p': 0.5348837209302325, 'r': 0.6388888888888888, 'f1': 0.5822784810126581}, 'argument': {'p': 0.5898371784374884, 'r': 0.610902791953113, 'f1': 0.6001851991118303}, 'combined': 0.3494749260651163, 'epoch': 17} ****************************** Epoch: 39 command: python train.py --model_name arg --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --max_epoch 40 --p1_data_weight 0.4 --event_hidden_num 450 --role_hidden_num 350 --learning_rate 2e-4 2023-01-23 23:17:26.384149: step: 2/1545, loss: 0.0006336256046779454 2023-01-23 23:17:27.313713: step: 4/1545, loss: 0.00010930249118246138 2023-01-23 23:17:28.238098: step: 6/1545, loss: 0.00041379936737939715 2023-01-23 23:17:29.116882: step: 8/1545, loss: 0.013735109008848667 2023-01-23 23:17:30.013041: step: 10/1545, loss: 0.0006209817947819829 2023-01-23 23:17:30.911154: step: 12/1545, loss: 0.00019637418154161423 2023-01-23 23:17:31.774034: step: 14/1545, loss: 0.05743959918618202 2023-01-23 23:17:32.693173: step: 16/1545, loss: 0.0023047379218041897 2023-01-23 23:17:33.555571: step: 18/1545, loss: 0.00015354207425843924 2023-01-23 23:17:34.470925: step: 20/1545, loss: 0.0072355144657194614 2023-01-23 23:17:35.387114: step: 22/1545, loss: 0.0004444106016308069 2023-01-23 23:17:36.253005: step: 24/1545, loss: 0.3765602707862854 2023-01-23 23:17:37.147138: step: 26/1545, loss: 0.00973354559391737 2023-01-23 23:17:38.068472: step: 28/1545, loss: 0.00023864512331783772 2023-01-23 23:17:39.019031: step: 30/1545, loss: 0.00029523298144340515 2023-01-23 23:17:39.887343: step: 32/1545, loss: 0.003405817085877061 2023-01-23 23:17:40.769310: step: 34/1545, loss: 0.00044867797987535596 2023-01-23 23:17:41.658172: step: 36/1545, loss: 0.0029058754444122314 2023-01-23 23:17:42.514054: step: 38/1545, loss: 0.0003544304345268756 2023-01-23 23:17:43.407416: step: 40/1545, loss: 0.00039892829954624176 2023-01-23 23:17:44.303597: step: 42/1545, loss: 0.00045672556734643877 2023-01-23 23:17:45.162871: step: 44/1545, loss: 0.003669008379802108 2023-01-23 23:17:46.054761: step: 46/1545, loss: 0.00023107729793991894 2023-01-23 23:17:46.970912: step: 48/1545, loss: 0.0006867318879812956 2023-01-23 23:17:47.897284: step: 50/1545, loss: 0.0008457467774860561 2023-01-23 23:17:48.756565: step: 52/1545, loss: 0.001241892809048295 2023-01-23 23:17:49.714190: step: 54/1545, loss: 0.0009418821427971125 2023-01-23 23:17:50.573754: step: 56/1545, loss: 0.0001376968575641513 2023-01-23 23:17:51.490657: step: 58/1545, loss: 0.0022992428857833147 2023-01-23 23:17:52.389497: step: 60/1545, loss: 0.0016215427312999964 2023-01-23 23:17:53.272278: step: 62/1545, loss: 9.813223732635379e-05 2023-01-23 23:17:54.229138: step: 64/1545, loss: 0.000351340597262606 2023-01-23 23:17:55.110178: step: 66/1545, loss: 3.87718973797746e-05 2023-01-23 23:17:56.049357: step: 68/1545, loss: 0.005859776400029659 2023-01-23 23:17:56.887860: step: 70/1545, loss: 0.0003783932188525796 2023-01-23 23:17:57.762722: step: 72/1545, loss: 0.0016548638232052326 2023-01-23 23:17:58.618630: step: 74/1545, loss: 0.002637378638610244 2023-01-23 23:17:59.500016: step: 76/1545, loss: 0.14360660314559937 2023-01-23 23:18:00.424301: step: 78/1545, loss: 0.0005696045700460672 2023-01-23 23:18:01.291934: step: 80/1545, loss: 0.004348467569798231 2023-01-23 23:18:02.205390: step: 82/1545, loss: 0.0007091984152793884 2023-01-23 23:18:03.066609: step: 84/1545, loss: 0.005733391735702753 2023-01-23 23:18:03.940348: step: 86/1545, loss: 4.908069604425691e-05 2023-01-23 23:18:04.846374: step: 88/1545, loss: 0.0005276202573440969 2023-01-23 23:18:05.740664: step: 90/1545, loss: 0.0002524035226088017 2023-01-23 23:18:06.658256: step: 92/1545, loss: 0.00022506773530039936 2023-01-23 23:18:07.609659: step: 94/1545, loss: 0.00019196377252228558 2023-01-23 23:18:08.548535: step: 96/1545, loss: 0.00028497132007032633 2023-01-23 23:18:09.415608: step: 98/1545, loss: 0.007216432597488165 2023-01-23 23:18:10.269871: step: 100/1545, loss: 0.5325251221656799 2023-01-23 23:18:11.264187: step: 102/1545, loss: 0.11705146729946136 2023-01-23 23:18:12.132306: step: 104/1545, loss: 0.002159008290618658 2023-01-23 23:18:13.040125: step: 106/1545, loss: 0.0016971564618870616 2023-01-23 23:18:13.952683: step: 108/1545, loss: 0.024569759145379066 2023-01-23 23:18:14.854202: step: 110/1545, loss: 0.00018174051365349442 2023-01-23 23:18:15.675028: step: 112/1545, loss: 3.0517578125e-05 2023-01-23 23:18:16.541680: step: 114/1545, loss: 6.699489313177764e-05 2023-01-23 23:18:17.455354: step: 116/1545, loss: 0.24130332469940186 2023-01-23 23:18:18.360970: step: 118/1545, loss: 0.005400197114795446 2023-01-23 23:18:19.226255: step: 120/1545, loss: 0.1038067564368248 2023-01-23 23:18:20.098788: step: 122/1545, loss: 0.30684009194374084 2023-01-23 23:18:21.009520: step: 124/1545, loss: 1.972650170500856e-05 2023-01-23 23:18:21.913228: step: 126/1545, loss: 0.015410354360938072 2023-01-23 23:18:22.817497: step: 128/1545, loss: -2.139580828952603e-06 2023-01-23 23:18:23.703944: step: 130/1545, loss: 0.3166375458240509 2023-01-23 23:18:24.590404: step: 132/1545, loss: -4.383162831800291e-06 2023-01-23 23:18:25.538950: step: 134/1545, loss: 0.00014308861864265054 2023-01-23 23:18:26.375573: step: 136/1545, loss: 0.000524521863553673 2023-01-23 23:18:27.244214: step: 138/1545, loss: 0.00022866428480483592 2023-01-23 23:18:28.127947: step: 140/1545, loss: 0.0005700822221115232 2023-01-23 23:18:28.975021: step: 142/1545, loss: 3.1357012630905956e-05 2023-01-23 23:18:29.874775: step: 144/1545, loss: 0.00036203546915203333 2023-01-23 23:18:30.717267: step: 146/1545, loss: 0.0014377867337316275 2023-01-23 23:18:31.610940: step: 148/1545, loss: 0.0003775604418478906 2023-01-23 23:18:32.506409: step: 150/1545, loss: 0.0040093171410262585 2023-01-23 23:18:33.422504: step: 152/1545, loss: 5.5724012781865895e-05 2023-01-23 23:18:34.334901: step: 154/1545, loss: 0.001473412849009037 2023-01-23 23:18:35.175362: step: 156/1545, loss: 0.0002601129235699773 2023-01-23 23:18:36.057597: step: 158/1545, loss: -2.4410586775047705e-05 2023-01-23 23:18:36.922375: step: 160/1545, loss: 0.00015223519585561007 2023-01-23 23:18:37.839238: step: 162/1545, loss: 0.004658667836338282 2023-01-23 23:18:38.743883: step: 164/1545, loss: 3.0865761800669134e-05 2023-01-23 23:18:39.621207: step: 166/1545, loss: 0.19104433059692383 2023-01-23 23:18:40.510010: step: 168/1545, loss: 1.4676069440611172e-05 2023-01-23 23:18:41.370177: step: 170/1545, loss: 7.333798566833138e-05 2023-01-23 23:18:42.276241: step: 172/1545, loss: 3.798117904807441e-05 2023-01-23 23:18:43.156570: step: 174/1545, loss: 0.1313641518354416 2023-01-23 23:18:44.031806: step: 176/1545, loss: 9.980798495234922e-06 2023-01-23 23:18:44.875697: step: 178/1545, loss: 0.002776087960228324 2023-01-23 23:18:45.765577: step: 180/1545, loss: 0.000217796114156954 2023-01-23 23:18:46.748435: step: 182/1545, loss: 0.0001395994477206841 2023-01-23 23:18:47.614635: step: 184/1545, loss: 0.0018287337152287364 2023-01-23 23:18:48.553251: step: 186/1545, loss: 0.13615082204341888 2023-01-23 23:18:49.482839: step: 188/1545, loss: 0.002483417047187686 2023-01-23 23:18:50.394427: step: 190/1545, loss: 5.0023383664665744e-05 2023-01-23 23:18:51.262864: step: 192/1545, loss: 9.264995605917647e-05 2023-01-23 23:18:52.160620: step: 194/1545, loss: 3.815964009845629e-05 2023-01-23 23:18:53.060826: step: 196/1545, loss: -4.1947514546336606e-05 2023-01-23 23:18:53.920490: step: 198/1545, loss: 0.00026985365548171103 2023-01-23 23:18:54.830187: step: 200/1545, loss: 0.04890467971563339 2023-01-23 23:18:55.723785: step: 202/1545, loss: 0.21499089896678925 2023-01-23 23:18:56.603419: step: 204/1545, loss: 0.06685010343790054 2023-01-23 23:18:57.494757: step: 206/1545, loss: 7.399929745588452e-05 2023-01-23 23:18:58.368110: step: 208/1545, loss: 0.00034044802305288613 2023-01-23 23:18:59.222483: step: 210/1545, loss: 0.02978495880961418 2023-01-23 23:19:00.105261: step: 212/1545, loss: 2.5563438612152822e-05 2023-01-23 23:19:00.957995: step: 214/1545, loss: 0.00018909573554992676 2023-01-23 23:19:01.885511: step: 216/1545, loss: 0.0007759350119158626 2023-01-23 23:19:02.777750: step: 218/1545, loss: 0.00034879735903814435 2023-01-23 23:19:03.650633: step: 220/1545, loss: 0.0033844406716525555 2023-01-23 23:19:04.551046: step: 222/1545, loss: 0.26152655482292175 2023-01-23 23:19:05.420937: step: 224/1545, loss: 0.0006159722688607872 2023-01-23 23:19:06.273850: step: 226/1545, loss: 2.8149777335784165e-06 2023-01-23 23:19:07.171052: step: 228/1545, loss: 0.0004389658570289612 2023-01-23 23:19:08.044904: step: 230/1545, loss: 4.428327520145103e-05 2023-01-23 23:19:08.884959: step: 232/1545, loss: 3.969371027778834e-05 2023-01-23 23:19:09.758153: step: 234/1545, loss: 0.005187990143895149 2023-01-23 23:19:10.640537: step: 236/1545, loss: 0.00035058657522313297 2023-01-23 23:19:11.556582: step: 238/1545, loss: 0.0007492417353205383 2023-01-23 23:19:12.486539: step: 240/1545, loss: 0.18551890552043915 2023-01-23 23:19:13.351962: step: 242/1545, loss: 0.5049214363098145 2023-01-23 23:19:14.233720: step: 244/1545, loss: 0.0005878700758330524 2023-01-23 23:19:15.090513: step: 246/1545, loss: 2.5985837055486627e-05 2023-01-23 23:19:15.956751: step: 248/1545, loss: 0.0002495482622180134 2023-01-23 23:19:16.879322: step: 250/1545, loss: 0.007205859757959843 2023-01-23 23:19:17.721009: step: 252/1545, loss: 4.5700631744693965e-05 2023-01-23 23:19:18.603854: step: 254/1545, loss: 0.002752714091911912 2023-01-23 23:19:19.494794: step: 256/1545, loss: 0.2850286662578583 2023-01-23 23:19:20.356306: step: 258/1545, loss: 0.004441197961568832 2023-01-23 23:19:21.301408: step: 260/1545, loss: 0.0008395850309170783 2023-01-23 23:19:22.193689: step: 262/1545, loss: 0.009168232791125774 2023-01-23 23:19:23.065710: step: 264/1545, loss: 0.0006440607248805463 2023-01-23 23:19:23.902504: step: 266/1545, loss: 1.0133936484635342e-05 2023-01-23 23:19:24.776240: step: 268/1545, loss: 0.013308720663189888 2023-01-23 23:19:25.662928: step: 270/1545, loss: 0.009956905618309975 2023-01-23 23:19:26.544815: step: 272/1545, loss: 7.61994524509646e-05 2023-01-23 23:19:27.446846: step: 274/1545, loss: 0.06508656591176987 2023-01-23 23:19:28.318630: step: 276/1545, loss: 0.29145267605781555 2023-01-23 23:19:29.194985: step: 278/1545, loss: 0.0001031932988553308 2023-01-23 23:19:30.098172: step: 280/1545, loss: 0.0007393867126666009 2023-01-23 23:19:30.946381: step: 282/1545, loss: 0.13204865157604218 2023-01-23 23:19:31.796877: step: 284/1545, loss: 3.2043459214037284e-05 2023-01-23 23:19:32.751286: step: 286/1545, loss: 5.798787242383696e-05 2023-01-23 23:19:33.605559: step: 288/1545, loss: -1.782133949745912e-05 2023-01-23 23:19:34.496091: step: 290/1545, loss: 0.0024885660968720913 2023-01-23 23:19:35.354408: step: 292/1545, loss: 0.014823057688772678 2023-01-23 23:19:36.206028: step: 294/1545, loss: 2.4045632017077878e-05 2023-01-23 23:19:37.161887: step: 296/1545, loss: 0.0013611463364213705 2023-01-23 23:19:38.075962: step: 298/1545, loss: 0.03079109638929367 2023-01-23 23:19:39.002842: step: 300/1545, loss: 0.0008898860542103648 2023-01-23 23:19:39.865132: step: 302/1545, loss: 4.622931010089815e-05 2023-01-23 23:19:40.772662: step: 304/1545, loss: 3.5038203350268304e-05 2023-01-23 23:19:41.672577: step: 306/1545, loss: 0.0030545475892722607 2023-01-23 23:19:42.557752: step: 308/1545, loss: 0.0008232070249505341 2023-01-23 23:19:43.473668: step: 310/1545, loss: 0.13049285113811493 2023-01-23 23:19:44.460360: step: 312/1545, loss: 0.030278444290161133 2023-01-23 23:19:45.377329: step: 314/1545, loss: 0.00038530179881490767 2023-01-23 23:19:46.225865: step: 316/1545, loss: 0.00012812262866646051 2023-01-23 23:19:47.098338: step: 318/1545, loss: 0.0004508972342591733 2023-01-23 23:19:47.953250: step: 320/1545, loss: 0.043822918087244034 2023-01-23 23:19:48.804270: step: 322/1545, loss: 3.188587288605049e-05 2023-01-23 23:19:49.682749: step: 324/1545, loss: 0.0033924621529877186 2023-01-23 23:19:50.548157: step: 326/1545, loss: 0.1396455615758896 2023-01-23 23:19:51.423743: step: 328/1545, loss: 0.016204625368118286 2023-01-23 23:19:52.322455: step: 330/1545, loss: 0.051465656608343124 2023-01-23 23:19:53.252283: step: 332/1545, loss: 0.00024869179469533265 2023-01-23 23:19:54.117803: step: 334/1545, loss: 4.082843952346593e-05 2023-01-23 23:19:54.992615: step: 336/1545, loss: 0.00048074498772621155 2023-01-23 23:19:55.919824: step: 338/1545, loss: 0.003806911874562502 2023-01-23 23:19:56.794901: step: 340/1545, loss: 0.045271165668964386 2023-01-23 23:19:57.677546: step: 342/1545, loss: 0.00046876075793989 2023-01-23 23:19:58.547516: step: 344/1545, loss: 0.0007978866924531758 2023-01-23 23:19:59.440291: step: 346/1545, loss: 0.0004995878553017974 2023-01-23 23:20:00.363067: step: 348/1545, loss: 0.0016588366124778986 2023-01-23 23:20:01.232321: step: 350/1545, loss: 0.0068027563393116 2023-01-23 23:20:02.102531: step: 352/1545, loss: 0.0004436079179868102 2023-01-23 23:20:03.007681: step: 354/1545, loss: 2.8696400477201678e-05 2023-01-23 23:20:03.920488: step: 356/1545, loss: 0.9006269574165344 2023-01-23 23:20:04.808604: step: 358/1545, loss: 0.004372789990156889 2023-01-23 23:20:05.696343: step: 360/1545, loss: -6.709736226184759e-06 2023-01-23 23:20:06.609714: step: 362/1545, loss: 0.0028230769094079733 2023-01-23 23:20:07.512158: step: 364/1545, loss: 0.00010214120266027749 2023-01-23 23:20:08.356984: step: 366/1545, loss: 0.011982543393969536 2023-01-23 23:20:09.213270: step: 368/1545, loss: 0.00015067041385918856 2023-01-23 23:20:10.102455: step: 370/1545, loss: 0.004073156043887138 2023-01-23 23:20:11.033440: step: 372/1545, loss: 0.011279632337391376 2023-01-23 23:20:11.905326: step: 374/1545, loss: 0.016005920246243477 2023-01-23 23:20:12.817626: step: 376/1545, loss: 0.0007768767536617815 2023-01-23 23:20:13.711524: step: 378/1545, loss: 6.802087591495365e-05 2023-01-23 23:20:14.588386: step: 380/1545, loss: 0.00011750338308047503 2023-01-23 23:20:15.509426: step: 382/1545, loss: 0.0002374151663389057 2023-01-23 23:20:16.439267: step: 384/1545, loss: 0.0005489384057000279 2023-01-23 23:20:17.368527: step: 386/1545, loss: 0.01580391451716423 2023-01-23 23:20:18.284797: step: 388/1545, loss: 0.1389736533164978 2023-01-23 23:20:19.289382: step: 390/1545, loss: 0.004356391727924347 2023-01-23 23:20:20.131850: step: 392/1545, loss: 7.076263864291832e-05 2023-01-23 23:20:21.000511: step: 394/1545, loss: 0.0006594205042347312 2023-01-23 23:20:21.890352: step: 396/1545, loss: 0.00646161288022995 2023-01-23 23:20:22.759191: step: 398/1545, loss: 0.0002239575987914577 2023-01-23 23:20:23.669712: step: 400/1545, loss: 0.0005727190291509032 2023-01-23 23:20:24.576371: step: 402/1545, loss: 0.0005814097821712494 2023-01-23 23:20:25.476684: step: 404/1545, loss: 0.00033689860720187426 2023-01-23 23:20:26.364792: step: 406/1545, loss: 0.000640988175291568 2023-01-23 23:20:27.239346: step: 408/1545, loss: 0.00028954329900443554 2023-01-23 23:20:28.094511: step: 410/1545, loss: 0.08524054288864136 2023-01-23 23:20:28.967759: step: 412/1545, loss: 0.0006850484060123563 2023-01-23 23:20:29.848456: step: 414/1545, loss: 0.00047028777771629393 2023-01-23 23:20:30.785988: step: 416/1545, loss: 0.25019410252571106 2023-01-23 23:20:31.646036: step: 418/1545, loss: 0.0005203423206694424 2023-01-23 23:20:32.521998: step: 420/1545, loss: 0.0029688032809644938 2023-01-23 23:20:33.422944: step: 422/1545, loss: 0.00016060170310083777 2023-01-23 23:20:34.273030: step: 424/1545, loss: 0.06542495638132095 2023-01-23 23:20:35.125123: step: 426/1545, loss: 0.0008527517784386873 2023-01-23 23:20:36.009881: step: 428/1545, loss: 0.1885305941104889 2023-01-23 23:20:36.870089: step: 430/1545, loss: 0.08312416821718216 2023-01-23 23:20:37.782536: step: 432/1545, loss: 0.38434740900993347 2023-01-23 23:20:38.654259: step: 434/1545, loss: 0.00010100374493049458 2023-01-23 23:20:39.549330: step: 436/1545, loss: 0.0001912675506900996 2023-01-23 23:20:40.397234: step: 438/1545, loss: 0.00011207685020053759 2023-01-23 23:20:41.445301: step: 440/1545, loss: 5.2205261454219e-05 2023-01-23 23:20:42.317613: step: 442/1545, loss: 0.001330699073150754 2023-01-23 23:20:43.178729: step: 444/1545, loss: 0.002909502014517784 2023-01-23 23:20:44.054463: step: 446/1545, loss: 0.00299249985255301 2023-01-23 23:20:44.989225: step: 448/1545, loss: 0.0008496735827066004 2023-01-23 23:20:45.871386: step: 450/1545, loss: 0.0005494317156262696 2023-01-23 23:20:46.777325: step: 452/1545, loss: 0.00018428861221764237 2023-01-23 23:20:47.685955: step: 454/1545, loss: 0.0004083095700480044 2023-01-23 23:20:48.649845: step: 456/1545, loss: 0.00017897329234983772 2023-01-23 23:20:49.595271: step: 458/1545, loss: 0.0010192872723564506 2023-01-23 23:20:50.445020: step: 460/1545, loss: 0.0002486029698047787 2023-01-23 23:20:51.319044: step: 462/1545, loss: 0.00034831464290618896 2023-01-23 23:20:52.257183: step: 464/1545, loss: 0.000472658226499334 2023-01-23 23:20:53.165922: step: 466/1545, loss: 0.0001796489377738908 2023-01-23 23:20:54.027053: step: 468/1545, loss: 0.0002279234176967293 2023-01-23 23:20:54.874589: step: 470/1545, loss: 4.272808291716501e-05 2023-01-23 23:20:55.723456: step: 472/1545, loss: 0.21006807684898376 2023-01-23 23:20:56.581403: step: 474/1545, loss: 0.39087846875190735 2023-01-23 23:20:57.391143: step: 476/1545, loss: 0.00056767015485093 2023-01-23 23:20:58.313959: step: 478/1545, loss: 0.007467110175639391 2023-01-23 23:20:59.175262: step: 480/1545, loss: 0.04319965839385986 2023-01-23 23:21:00.045440: step: 482/1545, loss: 0.0028834433760493994 2023-01-23 23:21:00.923350: step: 484/1545, loss: 0.005521468352526426 2023-01-23 23:21:01.832278: step: 486/1545, loss: 0.00022169649309944361 2023-01-23 23:21:02.701853: step: 488/1545, loss: 9.52762711676769e-05 2023-01-23 23:21:03.571814: step: 490/1545, loss: 0.00408172607421875 2023-01-23 23:21:04.474209: step: 492/1545, loss: 0.002711209235712886 2023-01-23 23:21:05.338068: step: 494/1545, loss: 0.0036920621059834957 2023-01-23 23:21:06.270268: step: 496/1545, loss: 0.13668546080589294 2023-01-23 23:21:07.135225: step: 498/1545, loss: 1.0468561413290445e-05 2023-01-23 23:21:07.962823: step: 500/1545, loss: 0.0038117473013699055 2023-01-23 23:21:08.820004: step: 502/1545, loss: 0.05210953950881958 2023-01-23 23:21:09.685848: step: 504/1545, loss: 0.00022819938021712005 2023-01-23 23:21:10.555342: step: 506/1545, loss: 0.0003015432448592037 2023-01-23 23:21:11.469859: step: 508/1545, loss: 0.0007842703489586711 2023-01-23 23:21:12.346902: step: 510/1545, loss: 0.00015184879885055125 2023-01-23 23:21:13.224134: step: 512/1545, loss: 0.11128523200750351 2023-01-23 23:21:14.065341: step: 514/1545, loss: 0.00010052075958810747 2023-01-23 23:21:15.023363: step: 516/1545, loss: 0.002133106580004096 2023-01-23 23:21:15.904733: step: 518/1545, loss: 6.523604679387063e-05 2023-01-23 23:21:16.763410: step: 520/1545, loss: 0.0005912873893976212 2023-01-23 23:21:17.648487: step: 522/1545, loss: 0.00025827091303654015 2023-01-23 23:21:18.540911: step: 524/1545, loss: 0.00023410667199641466 2023-01-23 23:21:19.451100: step: 526/1545, loss: 2.9039380024187267e-05 2023-01-23 23:21:20.348759: step: 528/1545, loss: 0.003201116807758808 2023-01-23 23:21:21.235779: step: 530/1545, loss: 0.00020411511650308967 2023-01-23 23:21:22.069893: step: 532/1545, loss: 5.742967186961323e-05 2023-01-23 23:21:22.940465: step: 534/1545, loss: 0.001270319102331996 2023-01-23 23:21:23.747681: step: 536/1545, loss: 8.730970148462802e-05 2023-01-23 23:21:24.650274: step: 538/1545, loss: 0.421252578496933 2023-01-23 23:21:25.505655: step: 540/1545, loss: 0.0001154484853032045 2023-01-23 23:21:26.344385: step: 542/1545, loss: 0.019663581624627113 2023-01-23 23:21:27.231322: step: 544/1545, loss: 5.8223675296176225e-05 2023-01-23 23:21:28.088616: step: 546/1545, loss: 2.2961943614063784e-05 2023-01-23 23:21:28.941985: step: 548/1545, loss: 0.00012058728316333145 2023-01-23 23:21:29.816894: step: 550/1545, loss: 0.0002584861358627677 2023-01-23 23:21:30.739701: step: 552/1545, loss: 0.00023773462453391403 2023-01-23 23:21:31.699671: step: 554/1545, loss: 0.016206378117203712 2023-01-23 23:21:32.562454: step: 556/1545, loss: 7.462433859473094e-05 2023-01-23 23:21:33.455556: step: 558/1545, loss: 0.006663123145699501 2023-01-23 23:21:34.299076: step: 560/1545, loss: 0.0003488597576506436 2023-01-23 23:21:35.174717: step: 562/1545, loss: 8.708163659321144e-05 2023-01-23 23:21:36.085103: step: 564/1545, loss: 0.001021120697259903 2023-01-23 23:21:36.923966: step: 566/1545, loss: 0.0004319846339058131 2023-01-23 23:21:37.801024: step: 568/1545, loss: 0.05113754794001579 2023-01-23 23:21:38.680663: step: 570/1545, loss: 3.8012858567526564e-05 2023-01-23 23:21:39.565837: step: 572/1545, loss: 0.021103035658597946 2023-01-23 23:21:40.467833: step: 574/1545, loss: 0.006507207173854113 2023-01-23 23:21:41.310283: step: 576/1545, loss: 5.463123306981288e-05 2023-01-23 23:21:42.148722: step: 578/1545, loss: 0.0006062562461011112 2023-01-23 23:21:43.017419: step: 580/1545, loss: 0.19662374258041382 2023-01-23 23:21:43.877844: step: 582/1545, loss: 0.0026964538265019655 2023-01-23 23:21:44.785685: step: 584/1545, loss: 6.0112801293144e-05 2023-01-23 23:21:45.672831: step: 586/1545, loss: 0.0037506723310798407 2023-01-23 23:21:46.533542: step: 588/1545, loss: 0.00014966870367061347 2023-01-23 23:21:47.388676: step: 590/1545, loss: 0.0036919836420565844 2023-01-23 23:21:48.275337: step: 592/1545, loss: 0.00015298226207960397 2023-01-23 23:21:49.156120: step: 594/1545, loss: 4.4705615437123924e-05 2023-01-23 23:21:49.993175: step: 596/1545, loss: 0.008341220207512379 2023-01-23 23:21:50.853953: step: 598/1545, loss: 0.000174976623384282 2023-01-23 23:21:51.795602: step: 600/1545, loss: 0.04708749055862427 2023-01-23 23:21:52.694267: step: 602/1545, loss: 0.026305779814720154 2023-01-23 23:21:53.602680: step: 604/1545, loss: 0.0003608193655963987 2023-01-23 23:21:54.482098: step: 606/1545, loss: 0.1455349624156952 2023-01-23 23:21:55.352128: step: 608/1545, loss: 0.0007727115880697966 2023-01-23 23:21:56.255459: step: 610/1545, loss: 0.005275960545986891 2023-01-23 23:21:57.114973: step: 612/1545, loss: 0.00022390144295059144 2023-01-23 23:21:57.997976: step: 614/1545, loss: 0.00905961450189352 2023-01-23 23:21:58.871416: step: 616/1545, loss: 5.000827513867989e-06 2023-01-23 23:21:59.770364: step: 618/1545, loss: 0.026707667857408524 2023-01-23 23:22:00.650652: step: 620/1545, loss: 0.016524875536561012 2023-01-23 23:22:01.511863: step: 622/1545, loss: 2.0545703591778874e-06 2023-01-23 23:22:02.397557: step: 624/1545, loss: 8.514447108609602e-05 2023-01-23 23:22:03.247996: step: 626/1545, loss: 0.07743550091981888 2023-01-23 23:22:04.125976: step: 628/1545, loss: 0.00029316096333786845 2023-01-23 23:22:05.024225: step: 630/1545, loss: 0.5807744264602661 2023-01-23 23:22:05.893337: step: 632/1545, loss: 0.48518380522727966 2023-01-23 23:22:06.747549: step: 634/1545, loss: 0.23505643010139465 2023-01-23 23:22:07.634541: step: 636/1545, loss: 0.002567322924733162 2023-01-23 23:22:08.520991: step: 638/1545, loss: 0.0015974314883351326 2023-01-23 23:22:09.400456: step: 640/1545, loss: 0.00019983462698291987 2023-01-23 23:22:10.290071: step: 642/1545, loss: 0.00016644517017994076 2023-01-23 23:22:11.225818: step: 644/1545, loss: 0.24443472921848297 2023-01-23 23:22:12.148534: step: 646/1545, loss: 7.027015271887649e-07 2023-01-23 23:22:13.012752: step: 648/1545, loss: 2.4844206564011984e-05 2023-01-23 23:22:13.861871: step: 650/1545, loss: 9.55237919697538e-05 2023-01-23 23:22:14.732615: step: 652/1545, loss: 3.713199112098664e-05 2023-01-23 23:22:15.587360: step: 654/1545, loss: 0.00022499857004731894 2023-01-23 23:22:16.418402: step: 656/1545, loss: 0.0022155132610350847 2023-01-23 23:22:17.318479: step: 658/1545, loss: 9.158409375231713e-05 2023-01-23 23:22:18.193298: step: 660/1545, loss: 0.00011797775368904695 2023-01-23 23:22:19.060336: step: 662/1545, loss: 0.004527532961219549 2023-01-23 23:22:19.899128: step: 664/1545, loss: 0.001512133632786572 2023-01-23 23:22:20.803766: step: 666/1545, loss: 0.0004106542037334293 2023-01-23 23:22:21.724411: step: 668/1545, loss: 6.053224205970764e-05 2023-01-23 23:22:22.632661: step: 670/1545, loss: 0.000354788702679798 2023-01-23 23:22:23.488884: step: 672/1545, loss: 0.0004910965799354017 2023-01-23 23:22:24.342055: step: 674/1545, loss: 0.006889669224619865 2023-01-23 23:22:25.199328: step: 676/1545, loss: 0.296642005443573 2023-01-23 23:22:26.076156: step: 678/1545, loss: 0.02332712709903717 2023-01-23 23:22:26.982850: step: 680/1545, loss: 0.02376594766974449 2023-01-23 23:22:27.848651: step: 682/1545, loss: 0.0018936545820906758 2023-01-23 23:22:28.724820: step: 684/1545, loss: 0.00029576485394500196 2023-01-23 23:22:29.647116: step: 686/1545, loss: 1.9647868612082675e-05 2023-01-23 23:22:30.520985: step: 688/1545, loss: 0.00014209818618837744 2023-01-23 23:22:31.415017: step: 690/1545, loss: 0.00019301174324937165 2023-01-23 23:22:32.287351: step: 692/1545, loss: 0.005170577671378851 2023-01-23 23:22:33.124472: step: 694/1545, loss: 0.00042115600081160665 2023-01-23 23:22:33.974708: step: 696/1545, loss: 0.007931951433420181 2023-01-23 23:22:34.836147: step: 698/1545, loss: 0.010314946062862873 2023-01-23 23:22:35.693878: step: 700/1545, loss: 1.0961413383483887 2023-01-23 23:22:36.535874: step: 702/1545, loss: 0.0005912682972848415 2023-01-23 23:22:37.423370: step: 704/1545, loss: 0.012631259858608246 2023-01-23 23:22:38.291054: step: 706/1545, loss: 6.559252506121993e-05 2023-01-23 23:22:39.169698: step: 708/1545, loss: 0.00029262652969919145 2023-01-23 23:22:40.056369: step: 710/1545, loss: 0.009347686544060707 2023-01-23 23:22:40.908294: step: 712/1545, loss: 0.00039933284278959036 2023-01-23 23:22:41.801694: step: 714/1545, loss: 0.0010711890645325184 2023-01-23 23:22:42.685803: step: 716/1545, loss: 0.3196095824241638 2023-01-23 23:22:43.604373: step: 718/1545, loss: 0.020443834364414215 2023-01-23 23:22:44.497441: step: 720/1545, loss: 0.0010761419543996453 2023-01-23 23:22:45.355834: step: 722/1545, loss: 0.0007172456826083362 2023-01-23 23:22:46.238572: step: 724/1545, loss: 0.012104840949177742 2023-01-23 23:22:47.156754: step: 726/1545, loss: 0.0007179813692346215 2023-01-23 23:22:48.037764: step: 728/1545, loss: 0.0007171406177803874 2023-01-23 23:22:48.941176: step: 730/1545, loss: 0.2293013632297516 2023-01-23 23:22:49.832211: step: 732/1545, loss: 0.0018568929517641664 2023-01-23 23:22:50.704897: step: 734/1545, loss: 0.0005150592769496143 2023-01-23 23:22:51.573108: step: 736/1545, loss: 0.05502378195524216 2023-01-23 23:22:52.434012: step: 738/1545, loss: 0.0009769783355295658 2023-01-23 23:22:53.327794: step: 740/1545, loss: 0.3828091323375702 2023-01-23 23:22:54.165426: step: 742/1545, loss: 0.01407696958631277 2023-01-23 23:22:55.057954: step: 744/1545, loss: 0.03915642574429512 2023-01-23 23:22:55.902752: step: 746/1545, loss: 0.00029363384237512946 2023-01-23 23:22:56.754988: step: 748/1545, loss: 0.0007675901288166642 2023-01-23 23:22:57.616637: step: 750/1545, loss: 0.001567118801176548 2023-01-23 23:22:58.466264: step: 752/1545, loss: 0.003303057048469782 2023-01-23 23:22:59.343845: step: 754/1545, loss: 0.00012011091166641563 2023-01-23 23:23:00.233968: step: 756/1545, loss: 0.0038788816891610622 2023-01-23 23:23:01.085370: step: 758/1545, loss: 0.0003605197125580162 2023-01-23 23:23:01.938244: step: 760/1545, loss: 6.083556581870653e-05 2023-01-23 23:23:02.825707: step: 762/1545, loss: 0.00865943729877472 2023-01-23 23:23:03.708466: step: 764/1545, loss: 0.00021935583208687603 2023-01-23 23:23:04.571840: step: 766/1545, loss: 0.0012275713961571455 2023-01-23 23:23:05.484168: step: 768/1545, loss: 0.005833038594573736 2023-01-23 23:23:06.382414: step: 770/1545, loss: 9.735659841680899e-05 2023-01-23 23:23:07.280171: step: 772/1545, loss: 0.008258320391178131 2023-01-23 23:23:08.146449: step: 774/1545, loss: 0.0006524219643324614 2023-01-23 23:23:08.996505: step: 776/1545, loss: 0.11580822616815567 2023-01-23 23:23:09.860898: step: 778/1545, loss: 0.00025784072931855917 2023-01-23 23:23:10.759040: step: 780/1545, loss: 0.00022291005006991327 2023-01-23 23:23:11.597718: step: 782/1545, loss: 0.00012178942415630445 2023-01-23 23:23:12.486191: step: 784/1545, loss: 0.0010372040560469031 2023-01-23 23:23:13.329074: step: 786/1545, loss: 0.07260226458311081 2023-01-23 23:23:14.195058: step: 788/1545, loss: 7.004540384514257e-05 2023-01-23 23:23:15.053043: step: 790/1545, loss: 0.006157589145004749 2023-01-23 23:23:15.914399: step: 792/1545, loss: 0.0011868870351463556 2023-01-23 23:23:16.774685: step: 794/1545, loss: 0.011729412712156773 2023-01-23 23:23:17.630055: step: 796/1545, loss: 0.0002663393970578909 2023-01-23 23:23:18.506885: step: 798/1545, loss: 0.000431652384577319 2023-01-23 23:23:19.391890: step: 800/1545, loss: 4.168093437328935e-05 2023-01-23 23:23:20.265025: step: 802/1545, loss: 0.001033024163916707 2023-01-23 23:23:21.179608: step: 804/1545, loss: 3.157779428875074e-05 2023-01-23 23:23:22.085246: step: 806/1545, loss: 0.00010156861389987171 2023-01-23 23:23:22.953329: step: 808/1545, loss: 0.0002255072322441265 2023-01-23 23:23:23.786457: step: 810/1545, loss: 0.0232683178037405 2023-01-23 23:23:24.699641: step: 812/1545, loss: 0.028008954599499702 2023-01-23 23:23:25.578890: step: 814/1545, loss: 1.889019949885551e-05 2023-01-23 23:23:26.487950: step: 816/1545, loss: 0.21759319305419922 2023-01-23 23:23:27.332171: step: 818/1545, loss: 9.164214134216309e-06 2023-01-23 23:23:28.304755: step: 820/1545, loss: 3.857215415337123e-05 2023-01-23 23:23:29.204926: step: 822/1545, loss: 0.0007556011551059783 2023-01-23 23:23:30.079035: step: 824/1545, loss: 0.00022261218691710383 2023-01-23 23:23:31.024909: step: 826/1545, loss: 0.13782407343387604 2023-01-23 23:23:31.878023: step: 828/1545, loss: 0.010341438464820385 2023-01-23 23:23:32.750798: step: 830/1545, loss: 0.00017781183123588562 2023-01-23 23:23:33.641694: step: 832/1545, loss: 0.007430093362927437 2023-01-23 23:23:34.539717: step: 834/1545, loss: 0.24486826360225677 2023-01-23 23:23:35.405788: step: 836/1545, loss: 0.004132446832954884 2023-01-23 23:23:36.297979: step: 838/1545, loss: 5.8523542975308374e-05 2023-01-23 23:23:37.163027: step: 840/1545, loss: 0.00398283451795578 2023-01-23 23:23:38.008293: step: 842/1545, loss: 0.00010458280303282663 2023-01-23 23:23:38.889646: step: 844/1545, loss: 0.0005299806362017989 2023-01-23 23:23:39.795260: step: 846/1545, loss: 0.00016011972911655903 2023-01-23 23:23:40.665639: step: 848/1545, loss: 0.000527563039213419 2023-01-23 23:23:41.566047: step: 850/1545, loss: 0.0358862467110157 2023-01-23 23:23:42.422810: step: 852/1545, loss: 7.362564792856574e-05 2023-01-23 23:23:43.264556: step: 854/1545, loss: 3.63007202395238e-05 2023-01-23 23:23:44.144832: step: 856/1545, loss: 6.686199048999697e-05 2023-01-23 23:23:45.042679: step: 858/1545, loss: 0.004420475568622351 2023-01-23 23:23:45.933025: step: 860/1545, loss: 0.00045652358676306903 2023-01-23 23:23:46.831760: step: 862/1545, loss: 0.0020124255679547787 2023-01-23 23:23:47.659508: step: 864/1545, loss: 0.00033112955861724913 2023-01-23 23:23:48.554514: step: 866/1545, loss: 0.0006657827761955559 2023-01-23 23:23:49.455095: step: 868/1545, loss: 0.001945345546118915 2023-01-23 23:23:50.306208: step: 870/1545, loss: 7.783372711855918e-05 2023-01-23 23:23:51.183877: step: 872/1545, loss: -2.7465821403893642e-05 2023-01-23 23:23:52.082311: step: 874/1545, loss: 0.01809169165790081 2023-01-23 23:23:52.939083: step: 876/1545, loss: 0.0006959305610507727 2023-01-23 23:23:53.779565: step: 878/1545, loss: 0.00025124105741269886 2023-01-23 23:23:54.670906: step: 880/1545, loss: 0.008915946818888187 2023-01-23 23:23:55.548296: step: 882/1545, loss: 0.00023698341101408005 2023-01-23 23:23:56.449691: step: 884/1545, loss: 0.19834035634994507 2023-01-23 23:23:57.335667: step: 886/1545, loss: 0.02533305622637272 2023-01-23 23:23:58.235160: step: 888/1545, loss: 0.0016029559774324298 2023-01-23 23:23:59.101130: step: 890/1545, loss: 0.10488893836736679 2023-01-23 23:23:59.951892: step: 892/1545, loss: 5.1262974011478946e-05 2023-01-23 23:24:00.806475: step: 894/1545, loss: 0.0013621676480397582 2023-01-23 23:24:01.720465: step: 896/1545, loss: 0.0007429319666698575 2023-01-23 23:24:02.582687: step: 898/1545, loss: 0.19835463166236877 2023-01-23 23:24:03.431960: step: 900/1545, loss: 7.192490011220798e-05 2023-01-23 23:24:04.332829: step: 902/1545, loss: 0.0005603114259429276 2023-01-23 23:24:05.198298: step: 904/1545, loss: 0.002978699980303645 2023-01-23 23:24:06.052436: step: 906/1545, loss: 0.22664186358451843 2023-01-23 23:24:06.885483: step: 908/1545, loss: 0.22303929924964905 2023-01-23 23:24:07.750478: step: 910/1545, loss: 0.1054026186466217 2023-01-23 23:24:08.612239: step: 912/1545, loss: 0.09055536240339279 2023-01-23 23:24:09.451362: step: 914/1545, loss: 0.0002054735814454034 2023-01-23 23:24:10.318696: step: 916/1545, loss: 0.00457049161195755 2023-01-23 23:24:11.226866: step: 918/1545, loss: 0.05114007741212845 2023-01-23 23:24:12.123915: step: 920/1545, loss: 1.714484453201294 2023-01-23 23:24:13.035547: step: 922/1545, loss: 0.21805523335933685 2023-01-23 23:24:13.890422: step: 924/1545, loss: 0.12920616567134857 2023-01-23 23:24:14.771692: step: 926/1545, loss: 0.0001812960981624201 2023-01-23 23:24:15.637707: step: 928/1545, loss: 0.0015730004524812102 2023-01-23 23:24:16.580712: step: 930/1545, loss: 0.00035101757384836674 2023-01-23 23:24:17.417760: step: 932/1545, loss: 0.001627844525501132 2023-01-23 23:24:18.299886: step: 934/1545, loss: 0.0004262029833626002 2023-01-23 23:24:19.234005: step: 936/1545, loss: 0.000674195121973753 2023-01-23 23:24:20.110115: step: 938/1545, loss: 0.00952270720154047 2023-01-23 23:24:20.989456: step: 940/1545, loss: 0.0002033528871834278 2023-01-23 23:24:21.835655: step: 942/1545, loss: 0.0005944117438048124 2023-01-23 23:24:22.784220: step: 944/1545, loss: 0.004691715352237225 2023-01-23 23:24:23.647112: step: 946/1545, loss: 0.012592068873345852 2023-01-23 23:24:24.557273: step: 948/1545, loss: 0.05209031701087952 2023-01-23 23:24:25.418644: step: 950/1545, loss: 0.0002877918304875493 2023-01-23 23:24:26.317367: step: 952/1545, loss: 0.005877373740077019 2023-01-23 23:24:27.171634: step: 954/1545, loss: 0.000387084495741874 2023-01-23 23:24:28.087601: step: 956/1545, loss: 0.034974414855241776 2023-01-23 23:24:28.962122: step: 958/1545, loss: 0.00034962594509124756 2023-01-23 23:24:29.891491: step: 960/1545, loss: 0.009630120359361172 2023-01-23 23:24:30.800564: step: 962/1545, loss: 0.08242034167051315 2023-01-23 23:24:31.735097: step: 964/1545, loss: 0.07352964580059052 2023-01-23 23:24:32.649639: step: 966/1545, loss: 0.0029228944331407547 2023-01-23 23:24:33.515043: step: 968/1545, loss: 0.014112531207501888 2023-01-23 23:24:34.448911: step: 970/1545, loss: 0.07563161849975586 2023-01-23 23:24:35.314375: step: 972/1545, loss: 0.001993973273783922 2023-01-23 23:24:36.156297: step: 974/1545, loss: 0.005386888049542904 2023-01-23 23:24:37.012734: step: 976/1545, loss: 0.004139584954828024 2023-01-23 23:24:37.875193: step: 978/1545, loss: 0.10594819486141205 2023-01-23 23:24:38.750995: step: 980/1545, loss: 0.0002115880197379738 2023-01-23 23:24:39.745689: step: 982/1545, loss: 0.00012211700959596783 2023-01-23 23:24:40.628193: step: 984/1545, loss: 0.00010889641271205619 2023-01-23 23:24:41.497749: step: 986/1545, loss: 0.045794326812028885 2023-01-23 23:24:42.363810: step: 988/1545, loss: 0.001529703033156693 2023-01-23 23:24:43.271406: step: 990/1545, loss: 0.0020685135386884212 2023-01-23 23:24:44.125609: step: 992/1545, loss: 0.00010566711716819555 2023-01-23 23:24:45.039721: step: 994/1545, loss: 0.01715792529284954 2023-01-23 23:24:45.910062: step: 996/1545, loss: 0.0021224645897746086 2023-01-23 23:24:46.809143: step: 998/1545, loss: 0.004203501157462597 2023-01-23 23:24:47.668065: step: 1000/1545, loss: 1.5341029211413115e-05 2023-01-23 23:24:48.592507: step: 1002/1545, loss: 0.0021003750152885914 2023-01-23 23:24:49.477240: step: 1004/1545, loss: 8.30679782666266e-05 2023-01-23 23:24:50.366974: step: 1006/1545, loss: 0.00020254983974155039 2023-01-23 23:24:51.274479: step: 1008/1545, loss: 0.00018272586748935282 2023-01-23 23:24:52.130095: step: 1010/1545, loss: 0.0005123247392475605 2023-01-23 23:24:52.947734: step: 1012/1545, loss: 0.00010567784920567647 2023-01-23 23:24:53.839037: step: 1014/1545, loss: 0.0035719291772693396 2023-01-23 23:24:54.721114: step: 1016/1545, loss: 0.25512778759002686 2023-01-23 23:24:55.625459: step: 1018/1545, loss: 0.13599951565265656 2023-01-23 23:24:56.500153: step: 1020/1545, loss: 3.971259138779715e-05 2023-01-23 23:24:57.391577: step: 1022/1545, loss: 0.2522158622741699 2023-01-23 23:24:58.252201: step: 1024/1545, loss: 2.7486681574373506e-05 2023-01-23 23:24:59.128491: step: 1026/1545, loss: 3.2137484140548622e-06 2023-01-23 23:24:59.995033: step: 1028/1545, loss: 0.2377643585205078 2023-01-23 23:25:00.868228: step: 1030/1545, loss: 3.929674858227372e-05 2023-01-23 23:25:01.747820: step: 1032/1545, loss: 0.05980721861124039 2023-01-23 23:25:02.697445: step: 1034/1545, loss: 7.595717761432752e-05 2023-01-23 23:25:03.554366: step: 1036/1545, loss: 4.3704192648874596e-05 2023-01-23 23:25:04.461019: step: 1038/1545, loss: 1.739188883220777e-05 2023-01-23 23:25:05.308242: step: 1040/1545, loss: 1.9187828002031893e-05 2023-01-23 23:25:06.191356: step: 1042/1545, loss: 0.01505634281784296 2023-01-23 23:25:07.084904: step: 1044/1545, loss: 0.00011204993643332273 2023-01-23 23:25:07.955112: step: 1046/1545, loss: 0.05299443006515503 2023-01-23 23:25:08.822568: step: 1048/1545, loss: 0.00019495488959364593 2023-01-23 23:25:09.681968: step: 1050/1545, loss: 0.00010200701944995672 2023-01-23 23:25:10.591854: step: 1052/1545, loss: -8.882507245289162e-05 2023-01-23 23:25:11.430975: step: 1054/1545, loss: 0.37070730328559875 2023-01-23 23:25:12.276761: step: 1056/1545, loss: 0.00872697401791811 2023-01-23 23:25:13.155868: step: 1058/1545, loss: 0.0001801080215955153 2023-01-23 23:25:14.055828: step: 1060/1545, loss: 0.1571509838104248 2023-01-23 23:25:14.948736: step: 1062/1545, loss: 8.542639261577278e-05 2023-01-23 23:25:15.838407: step: 1064/1545, loss: -1.0503084922675043e-05 2023-01-23 23:25:16.806429: step: 1066/1545, loss: 6.991681584622711e-05 2023-01-23 23:25:17.743206: step: 1068/1545, loss: -1.3139026123099029e-05 2023-01-23 23:25:18.625273: step: 1070/1545, loss: 0.00014481243852060288 2023-01-23 23:25:19.548676: step: 1072/1545, loss: 4.929597253067186e-06 2023-01-23 23:25:20.453953: step: 1074/1545, loss: 0.00023900880478322506 2023-01-23 23:25:21.345590: step: 1076/1545, loss: 0.1515379399061203 2023-01-23 23:25:22.232597: step: 1078/1545, loss: 0.00010723411105573177 2023-01-23 23:25:23.070407: step: 1080/1545, loss: 0.00019977537158410996 2023-01-23 23:25:23.939497: step: 1082/1545, loss: 0.0005061158444732428 2023-01-23 23:25:24.823660: step: 1084/1545, loss: 0.13457196950912476 2023-01-23 23:25:25.708676: step: 1086/1545, loss: 0.011354749090969563 2023-01-23 23:25:26.620744: step: 1088/1545, loss: 6.625453534070402e-05 2023-01-23 23:25:27.506269: step: 1090/1545, loss: 0.029336396604776382 2023-01-23 23:25:28.467927: step: 1092/1545, loss: 0.00046824998571537435 2023-01-23 23:25:29.309128: step: 1094/1545, loss: 0.03427049145102501 2023-01-23 23:25:30.232098: step: 1096/1545, loss: 4.965592597727664e-05 2023-01-23 23:25:31.107594: step: 1098/1545, loss: 3.397671025595628e-05 2023-01-23 23:25:32.014856: step: 1100/1545, loss: 0.004763252101838589 2023-01-23 23:25:32.856008: step: 1102/1545, loss: 0.00021788083540741354 2023-01-23 23:25:33.690853: step: 1104/1545, loss: 0.0006501168245449662 2023-01-23 23:25:34.613273: step: 1106/1545, loss: 9.080916061066091e-05 2023-01-23 23:25:35.512788: step: 1108/1545, loss: 0.0033731479197740555 2023-01-23 23:25:36.413577: step: 1110/1545, loss: 0.053445830941200256 2023-01-23 23:25:37.329311: step: 1112/1545, loss: 0.00020557692914735526 2023-01-23 23:25:38.218226: step: 1114/1545, loss: 7.304152677534148e-05 2023-01-23 23:25:39.103666: step: 1116/1545, loss: 0.0013262676075100899 2023-01-23 23:25:40.009644: step: 1118/1545, loss: 0.001934959553182125 2023-01-23 23:25:40.907267: step: 1120/1545, loss: 0.00010378311708336696 2023-01-23 23:25:41.810203: step: 1122/1545, loss: 0.00012113632692489773 2023-01-23 23:25:42.701863: step: 1124/1545, loss: 0.00021859505795873702 2023-01-23 23:25:43.620413: step: 1126/1545, loss: 0.00016150395094882697 2023-01-23 23:25:44.526939: step: 1128/1545, loss: 0.00018519163131713867 2023-01-23 23:25:45.482618: step: 1130/1545, loss: 0.00022468715906143188 2023-01-23 23:25:46.362314: step: 1132/1545, loss: 0.00010692398791434243 2023-01-23 23:25:47.192864: step: 1134/1545, loss: 0.00020410674915183336 2023-01-23 23:25:48.120363: step: 1136/1545, loss: 0.023785317316651344 2023-01-23 23:25:49.026042: step: 1138/1545, loss: 0.0003001643344759941 2023-01-23 23:25:49.933194: step: 1140/1545, loss: 7.990746235009283e-05 2023-01-23 23:25:50.812622: step: 1142/1545, loss: 0.024153169244527817 2023-01-23 23:25:51.716523: step: 1144/1545, loss: 0.029637135565280914 2023-01-23 23:25:52.600400: step: 1146/1545, loss: 0.07599419355392456 2023-01-23 23:25:53.483352: step: 1148/1545, loss: 0.00025958791957236826 2023-01-23 23:25:54.345661: step: 1150/1545, loss: 0.0001469248381908983 2023-01-23 23:25:55.245913: step: 1152/1545, loss: 0.0002480665862094611 2023-01-23 23:25:56.120879: step: 1154/1545, loss: 0.008223071694374084 2023-01-23 23:25:56.974202: step: 1156/1545, loss: 0.0020118094980716705 2023-01-23 23:25:57.841403: step: 1158/1545, loss: 0.0035168249160051346 2023-01-23 23:25:58.765483: step: 1160/1545, loss: 1.6717238395358436e-05 2023-01-23 23:25:59.682962: step: 1162/1545, loss: 5.112236976856366e-05 2023-01-23 23:26:00.509103: step: 1164/1545, loss: 6.572881829924881e-05 2023-01-23 23:26:01.382088: step: 1166/1545, loss: 0.0001558065414428711 2023-01-23 23:26:02.235893: step: 1168/1545, loss: 5.9818838053615764e-05 2023-01-23 23:26:03.173191: step: 1170/1545, loss: 7.239675323944539e-05 2023-01-23 23:26:04.072743: step: 1172/1545, loss: 0.0006493526161648333 2023-01-23 23:26:04.965584: step: 1174/1545, loss: 0.04932274669408798 2023-01-23 23:26:05.853782: step: 1176/1545, loss: 0.00010410987306386232 2023-01-23 23:26:06.765450: step: 1178/1545, loss: 1.5276373233064078e-05 2023-01-23 23:26:07.604326: step: 1180/1545, loss: 0.03810007870197296 2023-01-23 23:26:08.512793: step: 1182/1545, loss: -1.0288187695550732e-05 2023-01-23 23:26:09.348194: step: 1184/1545, loss: 0.012810139916837215 2023-01-23 23:26:10.239318: step: 1186/1545, loss: 2.78592124232091e-05 2023-01-23 23:26:11.115540: step: 1188/1545, loss: 3.729154559550807e-05 2023-01-23 23:26:11.969273: step: 1190/1545, loss: 0.001127883791923523 2023-01-23 23:26:12.824815: step: 1192/1545, loss: 0.004285440780222416 2023-01-23 23:26:13.702706: step: 1194/1545, loss: 0.6806120872497559 2023-01-23 23:26:14.566894: step: 1196/1545, loss: 0.11418849229812622 2023-01-23 23:26:15.485364: step: 1198/1545, loss: 0.013844393193721771 2023-01-23 23:26:16.378742: step: 1200/1545, loss: 0.18542401492595673 2023-01-23 23:26:17.253223: step: 1202/1545, loss: 5.913524000789039e-05 2023-01-23 23:26:18.084767: step: 1204/1545, loss: 0.0011834701290354133 2023-01-23 23:26:18.967732: step: 1206/1545, loss: 0.20886604487895966 2023-01-23 23:26:19.839318: step: 1208/1545, loss: 0.00014240840391721576 2023-01-23 23:26:20.795306: step: 1210/1545, loss: 0.0014044562121853232 2023-01-23 23:26:21.622720: step: 1212/1545, loss: 0.00048706107190810144 2023-01-23 23:26:22.504299: step: 1214/1545, loss: 0.0008457189542241395 2023-01-23 23:26:23.396898: step: 1216/1545, loss: -3.5037664929404855e-06 2023-01-23 23:26:24.292925: step: 1218/1545, loss: 0.003956107888370752 2023-01-23 23:26:25.179354: step: 1220/1545, loss: 4.427731619216502e-05 2023-01-23 23:26:26.015468: step: 1222/1545, loss: 0.0013638271484524012 2023-01-23 23:26:26.903434: step: 1224/1545, loss: 1.0623957678035367e-06 2023-01-23 23:26:27.844241: step: 1226/1545, loss: -7.707377335464116e-06 2023-01-23 23:26:28.757912: step: 1228/1545, loss: 0.00033226702362298965 2023-01-23 23:26:29.620965: step: 1230/1545, loss: 0.38719236850738525 2023-01-23 23:26:30.561736: step: 1232/1545, loss: 0.21187232434749603 2023-01-23 23:26:31.409275: step: 1234/1545, loss: 0.003034979570657015 2023-01-23 23:26:32.253959: step: 1236/1545, loss: 0.00014131372154224664 2023-01-23 23:26:33.133171: step: 1238/1545, loss: 0.20522139966487885 2023-01-23 23:26:33.986754: step: 1240/1545, loss: 8.033373887883499e-05 2023-01-23 23:26:34.848560: step: 1242/1545, loss: 0.00208265520632267 2023-01-23 23:26:35.753885: step: 1244/1545, loss: 0.024057818576693535 2023-01-23 23:26:36.670712: step: 1246/1545, loss: 0.0008606227347627282 2023-01-23 23:26:37.544697: step: 1248/1545, loss: 0.0003034931723959744 2023-01-23 23:26:38.399852: step: 1250/1545, loss: 0.010061047971248627 2023-01-23 23:26:39.310436: step: 1252/1545, loss: 0.00021976549760438502 2023-01-23 23:26:40.191797: step: 1254/1545, loss: 0.016826774924993515