Command that produces this log: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
----------------------------------------------------------------------------------------------------
> trainable params:
>>> 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])
>>> type_embedding.weight: torch.Size([123, 100])
>>> trans_rep.weight: torch.Size([1024, 1124])
>>> trans_rep.bias: torch.Size([1024])
>>> coref_type_ffn.weight: torch.Size([3, 4096])
>>> coref_type_ffn.bias: torch.Size([3])
n_trainable_params: 561067023, n_nontrainable_params: 0
----------------------------------------------------------------------------------------------------
******************************
Epoch: 0
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:12:11.296358: step: 4/529, loss: 0.020952977240085602
2023-01-22 17:12:12.399531: step: 8/529, loss: 0.021386858075857162
2023-01-22 17:12:13.505435: step: 12/529, loss: 0.10582775622606277
2023-01-22 17:12:14.618119: step: 16/529, loss: 0.015845540910959244
2023-01-22 17:12:15.717919: step: 20/529, loss: 0.020487669855356216
2023-01-22 17:12:16.803270: step: 24/529, loss: 0.01992269977927208
2023-01-22 17:12:17.901363: step: 28/529, loss: 0.021042712032794952
2023-01-22 17:12:18.999697: step: 32/529, loss: 0.015479862689971924
2023-01-22 17:12:20.113075: step: 36/529, loss: 0.01939421147108078
2023-01-22 17:12:21.199983: step: 40/529, loss: 0.024981655180454254
2023-01-22 17:12:22.284440: step: 44/529, loss: 0.05722786486148834
2023-01-22 17:12:23.387398: step: 48/529, loss: 0.017989467829465866
2023-01-22 17:12:24.475759: step: 52/529, loss: 0.020983770489692688
2023-01-22 17:12:25.580833: step: 56/529, loss: 0.06493190675973892
2023-01-22 17:12:26.695931: step: 60/529, loss: 0.017172398045659065
2023-01-22 17:12:27.785673: step: 64/529, loss: 0.01399940811097622
2023-01-22 17:12:28.915919: step: 68/529, loss: 0.005797416903078556
2023-01-22 17:12:30.017625: step: 72/529, loss: 0.057554345577955246
2023-01-22 17:12:31.138106: step: 76/529, loss: 0.016582118347287178
2023-01-22 17:12:32.219429: step: 80/529, loss: 0.01060114149004221
2023-01-22 17:12:33.334459: step: 84/529, loss: 0.016607947647571564
2023-01-22 17:12:34.439029: step: 88/529, loss: 0.04210435226559639
2023-01-22 17:12:35.540518: step: 92/529, loss: 0.015180429443717003
2023-01-22 17:12:36.659127: step: 96/529, loss: 0.019517146050930023
2023-01-22 17:12:37.751085: step: 100/529, loss: 0.05744655430316925
2023-01-22 17:12:38.886803: step: 104/529, loss: 0.023722369223833084
2023-01-22 17:12:39.989674: step: 108/529, loss: 0.016381805762648582
2023-01-22 17:12:41.076908: step: 112/529, loss: 0.01025377493351698
2023-01-22 17:12:42.173732: step: 116/529, loss: 0.014802636578679085
2023-01-22 17:12:43.271688: step: 120/529, loss: 0.014737598598003387
2023-01-22 17:12:44.384007: step: 124/529, loss: 0.011493614874780178
2023-01-22 17:12:45.491648: step: 128/529, loss: 0.019774504005908966
2023-01-22 17:12:46.621844: step: 132/529, loss: 0.009261373430490494
2023-01-22 17:12:47.722417: step: 136/529, loss: 0.020293032750487328
2023-01-22 17:12:48.813162: step: 140/529, loss: 0.020239634439349174
2023-01-22 17:12:49.932423: step: 144/529, loss: 0.01102185808122158
2023-01-22 17:12:51.035725: step: 148/529, loss: 0.011839834973216057
2023-01-22 17:12:52.138212: step: 152/529, loss: 0.01189011987298727
2023-01-22 17:12:53.234845: step: 156/529, loss: 0.010195641778409481
2023-01-22 17:12:54.366490: step: 160/529, loss: 0.011982514522969723
2023-01-22 17:12:55.476193: step: 164/529, loss: 0.03768981620669365
2023-01-22 17:12:56.599191: step: 168/529, loss: 0.057141996920108795
2023-01-22 17:12:57.689773: step: 172/529, loss: 0.06138473376631737
2023-01-22 17:12:58.827120: step: 176/529, loss: 0.02281174063682556
2023-01-22 17:12:59.935384: step: 180/529, loss: 0.0857110396027565
2023-01-22 17:13:01.067088: step: 184/529, loss: 0.02645503729581833
2023-01-22 17:13:02.232349: step: 188/529, loss: 0.009832601994276047
2023-01-22 17:13:03.333185: step: 192/529, loss: 0.015928616747260094
2023-01-22 17:13:04.427094: step: 196/529, loss: 0.07065419852733612
2023-01-22 17:13:05.566175: step: 200/529, loss: 0.05971941351890564
2023-01-22 17:13:06.667208: step: 204/529, loss: 0.046089768409729004
2023-01-22 17:13:07.781986: step: 208/529, loss: 0.07824447005987167
2023-01-22 17:13:08.888075: step: 212/529, loss: 0.08715863525867462
2023-01-22 17:13:10.005086: step: 216/529, loss: 0.020826468244194984
2023-01-22 17:13:11.113918: step: 220/529, loss: 0.01940343715250492
2023-01-22 17:13:12.232489: step: 224/529, loss: 0.012001829221844673
2023-01-22 17:13:13.333873: step: 228/529, loss: 0.014780465513467789
2023-01-22 17:13:14.456421: step: 232/529, loss: 0.024281956255435944
2023-01-22 17:13:15.547179: step: 236/529, loss: 0.029330244287848473
2023-01-22 17:13:16.672431: step: 240/529, loss: 0.024107133969664574
2023-01-22 17:13:17.785458: step: 244/529, loss: 0.042314548045396805
2023-01-22 17:13:18.904724: step: 248/529, loss: 0.05584156513214111
2023-01-22 17:13:19.990762: step: 252/529, loss: 0.011207744479179382
2023-01-22 17:13:21.088704: step: 256/529, loss: 0.008659057319164276
2023-01-22 17:13:22.179014: step: 260/529, loss: 0.0022084370721131563
2023-01-22 17:13:23.329033: step: 264/529, loss: 0.03535834699869156
2023-01-22 17:13:24.434905: step: 268/529, loss: 0.04234807565808296
2023-01-22 17:13:25.583233: step: 272/529, loss: 0.014030973426997662
2023-01-22 17:13:26.695629: step: 276/529, loss: 0.01415281742811203
2023-01-22 17:13:27.793092: step: 280/529, loss: 0.07230215519666672
2023-01-22 17:13:28.904914: step: 284/529, loss: 0.03130822256207466
2023-01-22 17:13:30.005540: step: 288/529, loss: 0.014295052736997604
2023-01-22 17:13:31.114199: step: 292/529, loss: 0.007630824111402035
2023-01-22 17:13:32.211724: step: 296/529, loss: 0.016019055619835854
2023-01-22 17:13:33.305664: step: 300/529, loss: 0.010471394285559654
2023-01-22 17:13:34.422931: step: 304/529, loss: 0.04447510093450546
2023-01-22 17:13:35.514051: step: 308/529, loss: 0.044086236506700516
2023-01-22 17:13:36.606154: step: 312/529, loss: 0.012051809579133987
2023-01-22 17:13:37.714620: step: 316/529, loss: 0.02167813666164875
2023-01-22 17:13:38.821495: step: 320/529, loss: 0.015795966610312462
2023-01-22 17:13:39.953421: step: 324/529, loss: 0.04795869067311287
2023-01-22 17:13:41.071954: step: 328/529, loss: 0.010937169194221497
2023-01-22 17:13:42.195168: step: 332/529, loss: 0.0289393849670887
2023-01-22 17:13:43.316801: step: 336/529, loss: 0.017226209864020348
2023-01-22 17:13:44.441954: step: 340/529, loss: 0.0026177058462053537
2023-01-22 17:13:45.543339: step: 344/529, loss: 0.061795152723789215
2023-01-22 17:13:46.666192: step: 348/529, loss: 0.04654068872332573
2023-01-22 17:13:47.755920: step: 352/529, loss: 0.013378329575061798
2023-01-22 17:13:48.855882: step: 356/529, loss: 0.01938771642744541
2023-01-22 17:13:49.959703: step: 360/529, loss: 0.06321952491998672
2023-01-22 17:13:51.072328: step: 364/529, loss: 0.01659737154841423
2023-01-22 17:13:52.189598: step: 368/529, loss: 0.0530363991856575
2023-01-22 17:13:53.311533: step: 372/529, loss: 0.009072350338101387
2023-01-22 17:13:54.427651: step: 376/529, loss: 0.021112382411956787
2023-01-22 17:13:55.563454: step: 380/529, loss: 0.01962769217789173
2023-01-22 17:13:56.647631: step: 384/529, loss: 0.010405797511339188
2023-01-22 17:13:57.744201: step: 388/529, loss: 0.014076856896281242
2023-01-22 17:13:58.854900: step: 392/529, loss: 0.030933909118175507
2023-01-22 17:13:59.959622: step: 396/529, loss: 0.008482190780341625
2023-01-22 17:14:01.125966: step: 400/529, loss: 0.06148520112037659
2023-01-22 17:14:02.225247: step: 404/529, loss: 0.01498035155236721
2023-01-22 17:14:03.313771: step: 408/529, loss: 0.03137366846203804
2023-01-22 17:14:04.428613: step: 412/529, loss: 0.02093784138560295
2023-01-22 17:14:05.543048: step: 416/529, loss: 0.04966895282268524
2023-01-22 17:14:06.659141: step: 420/529, loss: 0.015933359041810036
2023-01-22 17:14:07.759931: step: 424/529, loss: 0.010265989229083061
2023-01-22 17:14:08.862404: step: 428/529, loss: 0.0232231467962265
2023-01-22 17:14:09.961355: step: 432/529, loss: 0.007650516927242279
2023-01-22 17:14:11.093160: step: 436/529, loss: 0.04336594417691231
2023-01-22 17:14:12.208762: step: 440/529, loss: 0.01494787260890007
2023-01-22 17:14:13.322245: step: 444/529, loss: 0.011679081246256828
2023-01-22 17:14:14.439233: step: 448/529, loss: 0.009621374309062958
2023-01-22 17:14:15.567740: step: 452/529, loss: 0.0628841444849968
2023-01-22 17:14:16.671884: step: 456/529, loss: 0.055795762687921524
2023-01-22 17:14:17.784875: step: 460/529, loss: 0.01230174582451582
2023-01-22 17:14:18.921862: step: 464/529, loss: 0.014860456809401512
2023-01-22 17:14:20.030031: step: 468/529, loss: 0.016787512227892876
2023-01-22 17:14:21.148888: step: 472/529, loss: 0.009318117052316666
2023-01-22 17:14:22.262301: step: 476/529, loss: 0.05141838267445564
2023-01-22 17:14:23.370190: step: 480/529, loss: 0.05433141067624092
2023-01-22 17:14:24.479610: step: 484/529, loss: 0.013388474471867085
2023-01-22 17:14:25.586869: step: 488/529, loss: 0.021288836374878883
2023-01-22 17:14:26.700890: step: 492/529, loss: 0.007459423039108515
2023-01-22 17:14:27.815324: step: 496/529, loss: 0.018024513497948647
2023-01-22 17:14:28.922584: step: 500/529, loss: 0.04020198434591293
2023-01-22 17:14:30.043602: step: 504/529, loss: 0.011004272848367691
2023-01-22 17:14:31.152646: step: 508/529, loss: 0.019049495458602905
2023-01-22 17:14:32.245414: step: 512/529, loss: 0.011073805391788483
2023-01-22 17:14:33.344896: step: 516/529, loss: 0.012309662997722626
2023-01-22 17:14:34.450418: step: 520/529, loss: 0.019298497587442398
2023-01-22 17:14:35.574481: step: 524/529, loss: 0.009093203581869602
2023-01-22 17:14:36.693840: step: 528/529, loss: 0.049984339624643326
2023-01-22 17:14:37.792696: step: 532/529, loss: 0.0069755008444190025
2023-01-22 17:14:38.899771: step: 536/529, loss: 0.03837039694190025
2023-01-22 17:14:40.010258: step: 540/529, loss: 0.019973745569586754
2023-01-22 17:14:41.137718: step: 544/529, loss: 0.006918622180819511
2023-01-22 17:14:42.251998: step: 548/529, loss: 0.07209032773971558
2023-01-22 17:14:43.389266: step: 552/529, loss: 0.025990018621087074
2023-01-22 17:14:44.510204: step: 556/529, loss: 0.035474564880132675
2023-01-22 17:14:45.633487: step: 560/529, loss: 0.005015677306801081
2023-01-22 17:14:46.754883: step: 564/529, loss: 0.039763789623975754
2023-01-22 17:14:47.890066: step: 568/529, loss: 0.01683920808136463
2023-01-22 17:14:49.010128: step: 572/529, loss: 0.00900550652295351
2023-01-22 17:14:50.141811: step: 576/529, loss: 0.010347955860197544
2023-01-22 17:14:51.244874: step: 580/529, loss: 0.034257613122463226
2023-01-22 17:14:52.386311: step: 584/529, loss: 0.05989512428641319
2023-01-22 17:14:53.497358: step: 588/529, loss: 0.005079173948615789
2023-01-22 17:14:54.625154: step: 592/529, loss: 0.01228341180831194
2023-01-22 17:14:55.757173: step: 596/529, loss: 0.01969623938202858
2023-01-22 17:14:56.874381: step: 600/529, loss: 0.007306233048439026
2023-01-22 17:14:57.985241: step: 604/529, loss: 0.04246971383690834
2023-01-22 17:14:59.071113: step: 608/529, loss: 0.007234849035739899
2023-01-22 17:15:00.186602: step: 612/529, loss: 0.017757266759872437
2023-01-22 17:15:01.290413: step: 616/529, loss: 0.025516996160149574
2023-01-22 17:15:02.414083: step: 620/529, loss: 0.009780902415513992
2023-01-22 17:15:03.505259: step: 624/529, loss: 0.008429944515228271
2023-01-22 17:15:04.613753: step: 628/529, loss: 0.014212721027433872
2023-01-22 17:15:05.751866: step: 632/529, loss: 0.02208278514444828
2023-01-22 17:15:06.869507: step: 636/529, loss: 0.011896387673914433
2023-01-22 17:15:07.967206: step: 640/529, loss: 0.03608326613903046
2023-01-22 17:15:09.083381: step: 644/529, loss: 0.028295794501900673
2023-01-22 17:15:10.212059: step: 648/529, loss: 0.01289941743016243
2023-01-22 17:15:11.332844: step: 652/529, loss: 0.013526106253266335
2023-01-22 17:15:12.420594: step: 656/529, loss: 0.009791851975023746
2023-01-22 17:15:13.502346: step: 660/529, loss: 0.03181343525648117
2023-01-22 17:15:14.616855: step: 664/529, loss: 0.005321584176272154
2023-01-22 17:15:15.746840: step: 668/529, loss: 0.024067873135209084
2023-01-22 17:15:16.848965: step: 672/529, loss: 0.009189567528665066
2023-01-22 17:15:17.938048: step: 676/529, loss: 0.01442819181829691
2023-01-22 17:15:19.057338: step: 680/529, loss: 0.06329543888568878
2023-01-22 17:15:20.166001: step: 684/529, loss: 0.012628337368369102
2023-01-22 17:15:21.278459: step: 688/529, loss: 0.041375380009412766
2023-01-22 17:15:22.389282: step: 692/529, loss: 0.06202450767159462
2023-01-22 17:15:23.512781: step: 696/529, loss: 0.012929446995258331
2023-01-22 17:15:24.611806: step: 700/529, loss: 0.01191332470625639
2023-01-22 17:15:25.726091: step: 704/529, loss: 0.007510307244956493
2023-01-22 17:15:26.829777: step: 708/529, loss: 0.011398904025554657
2023-01-22 17:15:27.934096: step: 712/529, loss: 0.06264317780733109
2023-01-22 17:15:29.046874: step: 716/529, loss: 0.00883929431438446
2023-01-22 17:15:30.135259: step: 720/529, loss: 0.0035735294222831726
2023-01-22 17:15:31.232582: step: 724/529, loss: 0.01408221386373043
2023-01-22 17:15:32.391232: step: 728/529, loss: 0.009267706423997879
2023-01-22 17:15:33.488785: step: 732/529, loss: 0.05647723749279976
2023-01-22 17:15:34.596809: step: 736/529, loss: 0.03602517023682594
2023-01-22 17:15:35.708939: step: 740/529, loss: 0.027513524517416954
2023-01-22 17:15:36.829271: step: 744/529, loss: 0.00937287975102663
2023-01-22 17:15:37.921281: step: 748/529, loss: 0.009648159146308899
2023-01-22 17:15:39.009950: step: 752/529, loss: 0.028540313243865967
2023-01-22 17:15:40.135780: step: 756/529, loss: 0.012167789973318577
2023-01-22 17:15:41.219975: step: 760/529, loss: 0.011136372573673725
2023-01-22 17:15:42.336374: step: 764/529, loss: 0.0290359053760767
2023-01-22 17:15:43.444199: step: 768/529, loss: 0.042235083878040314
2023-01-22 17:15:44.535771: step: 772/529, loss: 0.001173180527985096
2023-01-22 17:15:45.627491: step: 776/529, loss: 0.024135831743478775
2023-01-22 17:15:46.741389: step: 780/529, loss: 0.027562784031033516
2023-01-22 17:15:47.837316: step: 784/529, loss: 0.00653240317478776
2023-01-22 17:15:48.963442: step: 788/529, loss: 0.0821525901556015
2023-01-22 17:15:50.072855: step: 792/529, loss: 0.032976217567920685
2023-01-22 17:15:51.173197: step: 796/529, loss: 0.012385495007038116
2023-01-22 17:15:52.288845: step: 800/529, loss: 0.010210997425019741
2023-01-22 17:15:53.409292: step: 804/529, loss: 0.011432819068431854
2023-01-22 17:15:54.504273: step: 808/529, loss: 0.008386366069316864
2023-01-22 17:15:55.603772: step: 812/529, loss: 0.012356234714388847
2023-01-22 17:15:56.711993: step: 816/529, loss: 0.0057090348564088345
2023-01-22 17:15:57.854834: step: 820/529, loss: 0.037322089076042175
2023-01-22 17:15:58.960314: step: 824/529, loss: 0.06033607944846153
2023-01-22 17:16:00.067934: step: 828/529, loss: 0.008338105864822865
2023-01-22 17:16:01.193360: step: 832/529, loss: 0.060262203216552734
2023-01-22 17:16:02.285385: step: 836/529, loss: 0.006627920549362898
2023-01-22 17:16:03.389911: step: 840/529, loss: 0.01432175561785698
2023-01-22 17:16:04.477883: step: 844/529, loss: 0.04478072747588158
2023-01-22 17:16:05.569999: step: 848/529, loss: 0.021244077011942863
2023-01-22 17:16:06.689226: step: 852/529, loss: 0.014454500749707222
2023-01-22 17:16:07.802845: step: 856/529, loss: 0.017993612214922905
2023-01-22 17:16:08.908036: step: 860/529, loss: 0.016988826915621758
2023-01-22 17:16:10.018625: step: 864/529, loss: 0.0051475767977535725
2023-01-22 17:16:11.111647: step: 868/529, loss: 0.016883045434951782
2023-01-22 17:16:12.201838: step: 872/529, loss: 0.0372672975063324
2023-01-22 17:16:13.294222: step: 876/529, loss: 0.010639122687280178
2023-01-22 17:16:14.404634: step: 880/529, loss: 0.0074227373115718365
2023-01-22 17:16:15.505642: step: 884/529, loss: 0.00881099235266447
2023-01-22 17:16:16.620621: step: 888/529, loss: 0.013152114115655422
2023-01-22 17:16:17.755437: step: 892/529, loss: 0.015497894026339054
2023-01-22 17:16:18.842932: step: 896/529, loss: 0.006738824304193258
2023-01-22 17:16:19.940170: step: 900/529, loss: 0.04644390568137169
2023-01-22 17:16:21.093020: step: 904/529, loss: 0.014287744648754597
2023-01-22 17:16:22.210618: step: 908/529, loss: 0.02299402467906475
2023-01-22 17:16:23.303526: step: 912/529, loss: 0.015505899675190449
2023-01-22 17:16:24.441904: step: 916/529, loss: 0.007542851381003857
2023-01-22 17:16:25.559375: step: 920/529, loss: 0.05951913446187973
2023-01-22 17:16:26.669842: step: 924/529, loss: 0.015890389680862427
2023-01-22 17:16:27.783259: step: 928/529, loss: 0.03368136286735535
2023-01-22 17:16:28.905615: step: 932/529, loss: 0.01791762188076973
2023-01-22 17:16:30.003116: step: 936/529, loss: 0.0779389888048172
2023-01-22 17:16:31.102517: step: 940/529, loss: 0.005780879873782396
2023-01-22 17:16:32.227939: step: 944/529, loss: 0.05669904500246048
2023-01-22 17:16:33.334683: step: 948/529, loss: 0.007478095591068268
2023-01-22 17:16:34.456868: step: 952/529, loss: 0.015467693097889423
2023-01-22 17:16:35.561902: step: 956/529, loss: 0.04223593324422836
2023-01-22 17:16:36.661769: step: 960/529, loss: 0.00645859818905592
2023-01-22 17:16:37.780444: step: 964/529, loss: 0.009627575054764748
2023-01-22 17:16:38.894174: step: 968/529, loss: 0.007642344105988741
2023-01-22 17:16:40.005371: step: 972/529, loss: 0.0061698853969573975
2023-01-22 17:16:41.117091: step: 976/529, loss: 0.020721925422549248
2023-01-22 17:16:42.222798: step: 980/529, loss: 0.023703668266534805
2023-01-22 17:16:43.327210: step: 984/529, loss: 0.01573798805475235
2023-01-22 17:16:44.445127: step: 988/529, loss: 0.009059869684278965
2023-01-22 17:16:45.553153: step: 992/529, loss: 0.030040360987186432
2023-01-22 17:16:46.644126: step: 996/529, loss: 0.02443655952811241
2023-01-22 17:16:47.751927: step: 1000/529, loss: 0.007026128005236387
2023-01-22 17:16:48.868511: step: 1004/529, loss: 0.005020439624786377
2023-01-22 17:16:49.979308: step: 1008/529, loss: 0.028834665194153786
2023-01-22 17:16:51.091186: step: 1012/529, loss: 0.006580329034477472
2023-01-22 17:16:52.196341: step: 1016/529, loss: 0.008372098207473755
2023-01-22 17:16:53.320646: step: 1020/529, loss: 0.03315599262714386
2023-01-22 17:16:54.413001: step: 1024/529, loss: 0.009761552326381207
2023-01-22 17:16:55.517639: step: 1028/529, loss: 0.00852805282920599
2023-01-22 17:16:56.618307: step: 1032/529, loss: 0.025692827999591827
2023-01-22 17:16:57.723231: step: 1036/529, loss: 0.01296450849622488
2023-01-22 17:16:58.807015: step: 1040/529, loss: 0.02006562426686287
2023-01-22 17:16:59.902340: step: 1044/529, loss: 0.00819639302790165
2023-01-22 17:17:00.992113: step: 1048/529, loss: 0.0060485126450657845
2023-01-22 17:17:02.104883: step: 1052/529, loss: 0.010531513020396233
2023-01-22 17:17:03.247142: step: 1056/529, loss: 0.03217656910419464
2023-01-22 17:17:04.351533: step: 1060/529, loss: 0.01268327422440052
2023-01-22 17:17:05.503772: step: 1064/529, loss: 0.05135943740606308
2023-01-22 17:17:06.614892: step: 1068/529, loss: 0.019594566896557808
2023-01-22 17:17:07.738023: step: 1072/529, loss: 0.012082871980965137
2023-01-22 17:17:08.843233: step: 1076/529, loss: 0.07165084034204483
2023-01-22 17:17:09.971117: step: 1080/529, loss: 0.00775414053350687
2023-01-22 17:17:11.083657: step: 1084/529, loss: 0.019090984016656876
2023-01-22 17:17:12.171975: step: 1088/529, loss: 0.015492795035243034
2023-01-22 17:17:13.289723: step: 1092/529, loss: 0.009958931244909763
2023-01-22 17:17:14.391234: step: 1096/529, loss: 0.005504067987203598
2023-01-22 17:17:15.494399: step: 1100/529, loss: 0.01356101781129837
2023-01-22 17:17:16.599828: step: 1104/529, loss: 0.02976878546178341
2023-01-22 17:17:17.698034: step: 1108/529, loss: 0.009017725475132465
2023-01-22 17:17:18.800803: step: 1112/529, loss: 0.031317565590143204
2023-01-22 17:17:19.906024: step: 1116/529, loss: 0.04354654252529144
2023-01-22 17:17:21.034830: step: 1120/529, loss: 0.04566562920808792
2023-01-22 17:17:22.157541: step: 1124/529, loss: 0.02474207431077957
2023-01-22 17:17:23.287585: step: 1128/529, loss: 0.025392092764377594
2023-01-22 17:17:24.388126: step: 1132/529, loss: 0.008057104423642159
2023-01-22 17:17:25.488117: step: 1136/529, loss: 0.009960835799574852
2023-01-22 17:17:26.587882: step: 1140/529, loss: 0.06002819910645485
2023-01-22 17:17:27.693750: step: 1144/529, loss: 0.0075718313455581665
2023-01-22 17:17:28.769686: step: 1148/529, loss: 0.011741343885660172
2023-01-22 17:17:29.871264: step: 1152/529, loss: 0.010663824155926704
2023-01-22 17:17:30.990952: step: 1156/529, loss: 0.01787198893725872
2023-01-22 17:17:32.128357: step: 1160/529, loss: 0.029899438843131065
2023-01-22 17:17:33.215653: step: 1164/529, loss: 0.008893690072000027
2023-01-22 17:17:34.329777: step: 1168/529, loss: 0.012354403734207153
2023-01-22 17:17:35.424188: step: 1172/529, loss: 0.012204738333821297
2023-01-22 17:17:36.530500: step: 1176/529, loss: 0.03429974615573883
2023-01-22 17:17:37.658904: step: 1180/529, loss: 0.021606411784887314
2023-01-22 17:17:38.774798: step: 1184/529, loss: 0.011130974628031254
2023-01-22 17:17:39.890997: step: 1188/529, loss: 0.00621484499424696
2023-01-22 17:17:40.994551: step: 1192/529, loss: 0.014379750937223434
2023-01-22 17:17:42.119167: step: 1196/529, loss: 0.007328517735004425
2023-01-22 17:17:43.218028: step: 1200/529, loss: 0.0319802463054657
2023-01-22 17:17:44.316300: step: 1204/529, loss: 0.009026180021464825
2023-01-22 17:17:45.401618: step: 1208/529, loss: 0.009286165237426758
2023-01-22 17:17:46.527268: step: 1212/529, loss: 0.023003151640295982
2023-01-22 17:17:47.648340: step: 1216/529, loss: 0.05612075328826904
2023-01-22 17:17:48.738889: step: 1220/529, loss: 0.011093712411820889
2023-01-22 17:17:49.833913: step: 1224/529, loss: 0.020905502140522003
2023-01-22 17:17:50.950982: step: 1228/529, loss: 0.012027262710034847
2023-01-22 17:17:52.061773: step: 1232/529, loss: 0.036563143134117126
2023-01-22 17:17:53.151854: step: 1236/529, loss: 0.006464777514338493
2023-01-22 17:17:54.252470: step: 1240/529, loss: 0.008525123819708824
2023-01-22 17:17:55.327687: step: 1244/529, loss: 0.007257360499352217
2023-01-22 17:17:56.452508: step: 1248/529, loss: 0.009333458729088306
2023-01-22 17:17:57.558767: step: 1252/529, loss: 0.018762996420264244
2023-01-22 17:17:58.666295: step: 1256/529, loss: 0.028781188651919365
2023-01-22 17:17:59.785710: step: 1260/529, loss: 0.017822491005063057
2023-01-22 17:18:00.917954: step: 1264/529, loss: 0.005475801881402731
2023-01-22 17:18:02.038115: step: 1268/529, loss: 0.00771291321143508
2023-01-22 17:18:03.128582: step: 1272/529, loss: 0.013042115606367588
2023-01-22 17:18:04.261756: step: 1276/529, loss: 0.01129109039902687
2023-01-22 17:18:05.356272: step: 1280/529, loss: 0.002599012339487672
2023-01-22 17:18:06.464564: step: 1284/529, loss: 0.007883195765316486
2023-01-22 17:18:07.579950: step: 1288/529, loss: 0.018795518204569817
2023-01-22 17:18:08.689560: step: 1292/529, loss: 0.01176285371184349
2023-01-22 17:18:09.805172: step: 1296/529, loss: 0.020236041396856308
2023-01-22 17:18:10.943169: step: 1300/529, loss: 0.0050763231702148914
2023-01-22 17:18:12.038191: step: 1304/529, loss: 0.03246217966079712
2023-01-22 17:18:13.149535: step: 1308/529, loss: 0.04050830379128456
2023-01-22 17:18:14.253937: step: 1312/529, loss: 0.013893981464207172
2023-01-22 17:18:15.342302: step: 1316/529, loss: 0.005745646543800831
2023-01-22 17:18:16.452077: step: 1320/529, loss: 0.03940330818295479
2023-01-22 17:18:17.554277: step: 1324/529, loss: 0.043045010417699814
2023-01-22 17:18:18.657905: step: 1328/529, loss: 0.011276856996119022
2023-01-22 17:18:19.780776: step: 1332/529, loss: 0.008583548478782177
2023-01-22 17:18:20.891082: step: 1336/529, loss: 0.024562150239944458
2023-01-22 17:18:22.008905: step: 1340/529, loss: 0.030079036951065063
2023-01-22 17:18:23.105263: step: 1344/529, loss: 0.015479600988328457
2023-01-22 17:18:24.200527: step: 1348/529, loss: 0.0029222567100077868
2023-01-22 17:18:25.298295: step: 1352/529, loss: 0.003567111911252141
2023-01-22 17:18:26.414936: step: 1356/529, loss: 0.028687715530395508
2023-01-22 17:18:27.527042: step: 1360/529, loss: 0.014020870439708233
2023-01-22 17:18:28.663437: step: 1364/529, loss: 0.010144067928195
2023-01-22 17:18:29.761204: step: 1368/529, loss: 0.06696517020463943
2023-01-22 17:18:30.839328: step: 1372/529, loss: 0.009632857516407967
2023-01-22 17:18:31.948934: step: 1376/529, loss: 0.01684681512415409
2023-01-22 17:18:33.042688: step: 1380/529, loss: 0.03911769762635231
2023-01-22 17:18:34.139698: step: 1384/529, loss: 0.042949378490448
2023-01-22 17:18:35.240002: step: 1388/529, loss: 0.012359624728560448
2023-01-22 17:18:36.347013: step: 1392/529, loss: 0.02868887409567833
2023-01-22 17:18:37.466496: step: 1396/529, loss: 0.013364430516958237
2023-01-22 17:18:38.568961: step: 1400/529, loss: 0.021869942545890808
2023-01-22 17:18:39.678746: step: 1404/529, loss: 0.01448669284582138
2023-01-22 17:18:40.806475: step: 1408/529, loss: 0.01271969173103571
2023-01-22 17:18:41.907746: step: 1412/529, loss: 0.020677125081419945
2023-01-22 17:18:43.045834: step: 1416/529, loss: 0.011627142317593098
2023-01-22 17:18:44.134012: step: 1420/529, loss: 0.013595512136816978
2023-01-22 17:18:45.227311: step: 1424/529, loss: 0.023199519142508507
2023-01-22 17:18:46.329597: step: 1428/529, loss: 0.01161238644272089
2023-01-22 17:18:47.433001: step: 1432/529, loss: 0.010114002972841263
2023-01-22 17:18:48.536887: step: 1436/529, loss: 0.0066328695975244045
2023-01-22 17:18:49.627169: step: 1440/529, loss: 0.014511281624436378
2023-01-22 17:18:50.744200: step: 1444/529, loss: 0.016472142189741135
2023-01-22 17:18:51.852268: step: 1448/529, loss: 0.0473119392991066
2023-01-22 17:18:52.994078: step: 1452/529, loss: 0.008408170193433762
2023-01-22 17:18:54.100260: step: 1456/529, loss: 0.0062958537600934505
2023-01-22 17:18:55.221446: step: 1460/529, loss: 0.013939841650426388
2023-01-22 17:18:56.314573: step: 1464/529, loss: 0.01662561669945717
2023-01-22 17:18:57.426975: step: 1468/529, loss: 0.0005799630889669061
2023-01-22 17:18:58.509365: step: 1472/529, loss: 0.02928600087761879
2023-01-22 17:18:59.625312: step: 1476/529, loss: 0.004867796786129475
2023-01-22 17:19:00.738237: step: 1480/529, loss: 0.018991462886333466
2023-01-22 17:19:01.824585: step: 1484/529, loss: 0.011524781584739685
2023-01-22 17:19:02.953516: step: 1488/529, loss: 0.03889041393995285
2023-01-22 17:19:04.068075: step: 1492/529, loss: 0.013699166476726532
2023-01-22 17:19:05.178884: step: 1496/529, loss: 0.004785880912095308
2023-01-22 17:19:06.285173: step: 1500/529, loss: 0.0132296746596694
2023-01-22 17:19:07.384769: step: 1504/529, loss: 0.004941858351230621
2023-01-22 17:19:08.502663: step: 1508/529, loss: 0.01335514709353447
2023-01-22 17:19:09.605918: step: 1512/529, loss: 0.010904469527304173
2023-01-22 17:19:10.715693: step: 1516/529, loss: 0.009224246256053448
2023-01-22 17:19:11.821177: step: 1520/529, loss: 0.004448066931217909
2023-01-22 17:19:12.905269: step: 1524/529, loss: 0.009903236292302608
2023-01-22 17:19:14.016364: step: 1528/529, loss: 0.013837488368153572
2023-01-22 17:19:15.140221: step: 1532/529, loss: 0.034371789544820786
2023-01-22 17:19:16.268431: step: 1536/529, loss: 0.01723404787480831
2023-01-22 17:19:17.378181: step: 1540/529, loss: 0.01081811636686325
2023-01-22 17:19:18.504013: step: 1544/529, loss: 0.006913135293871164
2023-01-22 17:19:19.594661: step: 1548/529, loss: 0.004861879628151655
2023-01-22 17:19:20.708874: step: 1552/529, loss: 0.022660069167613983
2023-01-22 17:19:21.837995: step: 1556/529, loss: 0.024209827184677124
2023-01-22 17:19:22.956981: step: 1560/529, loss: 0.005939995404332876
2023-01-22 17:19:24.070417: step: 1564/529, loss: 0.010164082050323486
2023-01-22 17:19:25.190822: step: 1568/529, loss: 0.05731247738003731
2023-01-22 17:19:26.294002: step: 1572/529, loss: 0.03543375805020332
2023-01-22 17:19:27.410898: step: 1576/529, loss: 0.008039611391723156
2023-01-22 17:19:28.521019: step: 1580/529, loss: 0.018727675080299377
2023-01-22 17:19:29.631901: step: 1584/529, loss: 0.020055225118994713
2023-01-22 17:19:30.750612: step: 1588/529, loss: 0.0066964756697416306
2023-01-22 17:19:31.874947: step: 1592/529, loss: 0.006271496415138245
2023-01-22 17:19:32.989983: step: 1596/529, loss: 0.016917379572987556
2023-01-22 17:19:34.100006: step: 1600/529, loss: 0.01939815655350685
2023-01-22 17:19:35.210972: step: 1604/529, loss: 0.024073787033557892
2023-01-22 17:19:36.326646: step: 1608/529, loss: 0.029335562139749527
2023-01-22 17:19:37.456123: step: 1612/529, loss: 0.00727007444947958
2023-01-22 17:19:38.562923: step: 1616/529, loss: 0.010016110725700855
2023-01-22 17:19:39.665002: step: 1620/529, loss: 0.013527818955481052
2023-01-22 17:19:40.777585: step: 1624/529, loss: 0.015339715406298637
2023-01-22 17:19:41.888023: step: 1628/529, loss: 0.03363961726427078
2023-01-22 17:19:42.978595: step: 1632/529, loss: 0.035570330917835236
2023-01-22 17:19:44.089468: step: 1636/529, loss: 0.007140653673559427
2023-01-22 17:19:45.210826: step: 1640/529, loss: 0.042375851422548294
2023-01-22 17:19:46.313231: step: 1644/529, loss: 0.009680777788162231
2023-01-22 17:19:47.405625: step: 1648/529, loss: 0.031028874218463898
2023-01-22 17:19:48.524618: step: 1652/529, loss: 0.01726185716688633
2023-01-22 17:19:49.605065: step: 1656/529, loss: 0.023695921525359154
2023-01-22 17:19:50.702183: step: 1660/529, loss: 0.06343021988868713
2023-01-22 17:19:51.836738: step: 1664/529, loss: 0.011768014170229435
2023-01-22 17:19:52.931575: step: 1668/529, loss: 0.007082835771143436
2023-01-22 17:19:54.022391: step: 1672/529, loss: 0.01287764124572277
2023-01-22 17:19:55.124650: step: 1676/529, loss: 0.04795419052243233
2023-01-22 17:19:56.235680: step: 1680/529, loss: 0.004884667694568634
2023-01-22 17:19:57.336409: step: 1684/529, loss: 0.009261339902877808
2023-01-22 17:19:58.449847: step: 1688/529, loss: 0.016716046258807182
2023-01-22 17:19:59.563812: step: 1692/529, loss: 0.005059296730905771
2023-01-22 17:20:00.672159: step: 1696/529, loss: 0.05374990403652191
2023-01-22 17:20:01.767220: step: 1700/529, loss: 0.04184979200363159
2023-01-22 17:20:02.894568: step: 1704/529, loss: 0.006443860474973917
2023-01-22 17:20:04.001057: step: 1708/529, loss: 0.016054097563028336
2023-01-22 17:20:05.108646: step: 1712/529, loss: 0.012395386584103107
2023-01-22 17:20:06.216638: step: 1716/529, loss: 0.03141835704445839
2023-01-22 17:20:07.316716: step: 1720/529, loss: 0.012311109341681004
2023-01-22 17:20:08.407068: step: 1724/529, loss: 0.05921533331274986
2023-01-22 17:20:09.528502: step: 1728/529, loss: 0.009985635988414288
2023-01-22 17:20:10.624091: step: 1732/529, loss: 0.025756413117051125
2023-01-22 17:20:11.731275: step: 1736/529, loss: 0.040602754801511765
2023-01-22 17:20:12.824074: step: 1740/529, loss: 0.03853137791156769
2023-01-22 17:20:13.942028: step: 1744/529, loss: 0.009843072853982449
2023-01-22 17:20:15.039286: step: 1748/529, loss: 0.012607881799340248
2023-01-22 17:20:16.141153: step: 1752/529, loss: 0.004900872707366943
2023-01-22 17:20:17.262219: step: 1756/529, loss: 0.010372872464358807
2023-01-22 17:20:18.353650: step: 1760/529, loss: 0.00687371427193284
2023-01-22 17:20:19.452324: step: 1764/529, loss: 0.033669162541627884
2023-01-22 17:20:20.572029: step: 1768/529, loss: 0.012714053504168987
2023-01-22 17:20:21.670086: step: 1772/529, loss: 0.04491034895181656
2023-01-22 17:20:22.784160: step: 1776/529, loss: 0.011299021542072296
2023-01-22 17:20:23.920317: step: 1780/529, loss: 0.029356691986322403
2023-01-22 17:20:25.025764: step: 1784/529, loss: 0.0052626049146056175
2023-01-22 17:20:26.121734: step: 1788/529, loss: 0.00784127414226532
2023-01-22 17:20:27.218932: step: 1792/529, loss: 0.009773041121661663
2023-01-22 17:20:28.338197: step: 1796/529, loss: 0.005785140208899975
2023-01-22 17:20:29.433655: step: 1800/529, loss: 0.007336001843214035
2023-01-22 17:20:30.539425: step: 1804/529, loss: 0.00700216693803668
2023-01-22 17:20:31.630742: step: 1808/529, loss: 0.004095433745533228
2023-01-22 17:20:32.717457: step: 1812/529, loss: 0.009905686601996422
2023-01-22 17:20:33.826090: step: 1816/529, loss: 0.0322563536465168
2023-01-22 17:20:34.961847: step: 1820/529, loss: 0.035683341324329376
2023-01-22 17:20:36.080416: step: 1824/529, loss: 0.0065209995955228806
2023-01-22 17:20:37.194938: step: 1828/529, loss: 0.011323463171720505
2023-01-22 17:20:38.296887: step: 1832/529, loss: 0.004791976418346167
2023-01-22 17:20:39.428813: step: 1836/529, loss: 0.0074640363454818726
2023-01-22 17:20:40.541269: step: 1840/529, loss: 0.008063922636210918
2023-01-22 17:20:41.659780: step: 1844/529, loss: 0.02339182235300541
2023-01-22 17:20:42.775158: step: 1848/529, loss: 0.01143765076994896
2023-01-22 17:20:43.890622: step: 1852/529, loss: 0.02925294078886509
2023-01-22 17:20:44.983960: step: 1856/529, loss: 0.00841628760099411
2023-01-22 17:20:46.090455: step: 1860/529, loss: 0.09265927970409393
2023-01-22 17:20:47.197581: step: 1864/529, loss: 0.009392473846673965
2023-01-22 17:20:48.306653: step: 1868/529, loss: 0.009746620431542397
2023-01-22 17:20:49.403167: step: 1872/529, loss: 0.00464861374348402
2023-01-22 17:20:50.477880: step: 1876/529, loss: 0.002670533489435911
2023-01-22 17:20:51.595167: step: 1880/529, loss: 0.015554034151136875
2023-01-22 17:20:52.694028: step: 1884/529, loss: 0.07675477862358093
2023-01-22 17:20:53.805140: step: 1888/529, loss: 0.006999322213232517
2023-01-22 17:20:54.907219: step: 1892/529, loss: 0.006108852569013834
2023-01-22 17:20:56.029095: step: 1896/529, loss: 0.012979681603610516
2023-01-22 17:20:57.138998: step: 1900/529, loss: 0.012842020951211452
2023-01-22 17:20:58.245616: step: 1904/529, loss: 0.07957916706800461
2023-01-22 17:20:59.330255: step: 1908/529, loss: 0.011200874112546444
2023-01-22 17:21:00.439138: step: 1912/529, loss: 0.03606186434626579
2023-01-22 17:21:01.545224: step: 1916/529, loss: 0.0678335428237915
2023-01-22 17:21:02.649054: step: 1920/529, loss: 0.03621261194348335
2023-01-22 17:21:03.757949: step: 1924/529, loss: 0.042195264250040054
2023-01-22 17:21:04.860277: step: 1928/529, loss: 0.01831630803644657
2023-01-22 17:21:05.994443: step: 1932/529, loss: 0.006913109216839075
2023-01-22 17:21:07.120043: step: 1936/529, loss: 0.007291656453162432
2023-01-22 17:21:08.208568: step: 1940/529, loss: 0.009371194988489151
2023-01-22 17:21:09.306228: step: 1944/529, loss: 0.051772184669971466
2023-01-22 17:21:10.417308: step: 1948/529, loss: 0.009605119936168194
2023-01-22 17:21:11.528174: step: 1952/529, loss: 0.007756783626973629
2023-01-22 17:21:12.645364: step: 1956/529, loss: 0.049256373196840286
2023-01-22 17:21:13.752428: step: 1960/529, loss: 0.01514006033539772
2023-01-22 17:21:14.858411: step: 1964/529, loss: 0.021082337945699692
2023-01-22 17:21:15.982071: step: 1968/529, loss: 0.011226071044802666
2023-01-22 17:21:17.087180: step: 1972/529, loss: 0.03969605267047882
2023-01-22 17:21:18.178749: step: 1976/529, loss: 0.005889580585062504
2023-01-22 17:21:19.296543: step: 1980/529, loss: 0.011329768225550652
2023-01-22 17:21:20.377103: step: 1984/529, loss: 0.01765243336558342
2023-01-22 17:21:21.490458: step: 1988/529, loss: 0.04848553612828255
2023-01-22 17:21:22.594630: step: 1992/529, loss: 0.025547156110405922
2023-01-22 17:21:23.736196: step: 1996/529, loss: 0.030630121007561684
2023-01-22 17:21:24.812313: step: 2000/529, loss: 0.02028278447687626
2023-01-22 17:21:25.912550: step: 2004/529, loss: 0.00895814411342144
2023-01-22 17:21:27.012049: step: 2008/529, loss: 0.010160822421312332
2023-01-22 17:21:28.133563: step: 2012/529, loss: 0.007527889683842659
2023-01-22 17:21:29.242834: step: 2016/529, loss: 0.011715550906956196
2023-01-22 17:21:30.357120: step: 2020/529, loss: 0.009545152075588703
2023-01-22 17:21:31.480379: step: 2024/529, loss: 0.008271112106740475
2023-01-22 17:21:32.617048: step: 2028/529, loss: 0.038071177899837494
2023-01-22 17:21:33.731213: step: 2032/529, loss: 0.013420408591628075
2023-01-22 17:21:34.825035: step: 2036/529, loss: 0.05669183284044266
2023-01-22 17:21:35.923591: step: 2040/529, loss: 0.005937928333878517
2023-01-22 17:21:37.034822: step: 2044/529, loss: 0.005604805890470743
2023-01-22 17:21:38.140018: step: 2048/529, loss: 0.008186708204448223
2023-01-22 17:21:39.279181: step: 2052/529, loss: 0.006400682032108307
2023-01-22 17:21:40.373303: step: 2056/529, loss: 0.010630583390593529
2023-01-22 17:21:41.466722: step: 2060/529, loss: 0.013762875460088253
2023-01-22 17:21:42.585894: step: 2064/529, loss: 0.0062905061058700085
2023-01-22 17:21:43.696449: step: 2068/529, loss: 0.01811828650534153
2023-01-22 17:21:44.786048: step: 2072/529, loss: 0.00411311024799943
2023-01-22 17:21:45.901927: step: 2076/529, loss: 0.012253466062247753
2023-01-22 17:21:47.010313: step: 2080/529, loss: 0.02685640938580036
2023-01-22 17:21:48.129493: step: 2084/529, loss: 0.05459235608577728
2023-01-22 17:21:49.255159: step: 2088/529, loss: 0.0383254699409008
2023-01-22 17:21:50.369602: step: 2092/529, loss: 0.011927919462323189
2023-01-22 17:21:51.463347: step: 2096/529, loss: 0.0065722474828362465
2023-01-22 17:21:52.587394: step: 2100/529, loss: 0.024399179965257645
2023-01-22 17:21:53.690618: step: 2104/529, loss: 0.012021117843687534
2023-01-22 17:21:54.791725: step: 2108/529, loss: 0.008413835428655148
2023-01-22 17:21:55.917399: step: 2112/529, loss: 0.0459437295794487
2023-01-22 17:21:57.017841: step: 2116/529, loss: 0.007205226458609104
==================================================
Loss: 0.022
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3224434858212948, 'r': 0.32672641637300076, 'f1': 0.32457082267402715}, 'combined': 0.23915744828612526, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.36397754341327815, 'r': 0.3003208648249819, 'f1': 0.3290992399173188}, 'combined': 0.2022756303882057, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31645819358785643, 'r': 0.3446812203404736, 'f1': 0.3299673081188549}, 'combined': 0.2431338059823141, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34316363525288474, 'r': 0.3131293829473896, 'f1': 0.327459273150238}, 'combined': 0.2012676508142926, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33081577134986223, 'r': 0.34525365131389796, 'f1': 0.33788054641118703}, 'combined': 0.24896461314508517, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.35566304226006107, 'r': 0.2999271023041554, 'f1': 0.325425836694504}, 'combined': 0.20099831089954662, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 0}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3224434858212948, 'r': 0.32672641637300076, 'f1': 0.32457082267402715}, 'combined': 0.23915744828612526, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.36397754341327815, 'r': 0.3003208648249819, 'f1': 0.3290992399173188}, 'combined': 0.2022756303882057, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31645819358785643, 'r': 0.3446812203404736, 'f1': 0.3299673081188549}, 'combined': 0.2431338059823141, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34316363525288474, 'r': 0.3131293829473896, 'f1': 0.327459273150238}, 'combined': 0.2012676508142926, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3548387096774194, 'r': 0.4782608695652174, 'f1': 0.40740740740740744}, 'combined': 0.20370370370370372, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33081577134986223, 'r': 0.34525365131389796, 'f1': 0.33788054641118703}, 'combined': 0.24896461314508517, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.35566304226006107, 'r': 0.2999271023041554, 'f1': 0.325425836694504}, 'combined': 0.20099831089954662, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 0}
******************************
Epoch: 1
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:24:43.972498: step: 4/529, loss: 0.021916856989264488
2023-01-22 17:24:45.075223: step: 8/529, loss: 0.011044525541365147
2023-01-22 17:24:46.216349: step: 12/529, loss: 0.005311714950948954
2023-01-22 17:24:47.350033: step: 16/529, loss: 0.004606260918080807
2023-01-22 17:24:48.448304: step: 20/529, loss: 0.004426587838679552
2023-01-22 17:24:49.525311: step: 24/529, loss: 0.03157786652445793
2023-01-22 17:24:50.643363: step: 28/529, loss: 0.019223518669605255
2023-01-22 17:24:51.746209: step: 32/529, loss: 0.02830389514565468
2023-01-22 17:24:52.860125: step: 36/529, loss: 0.0038713307585567236
2023-01-22 17:24:53.960794: step: 40/529, loss: 0.006225733086466789
2023-01-22 17:24:55.033038: step: 44/529, loss: 0.0046651423908770084
2023-01-22 17:24:56.124771: step: 48/529, loss: 0.039311476051807404
2023-01-22 17:24:57.212598: step: 52/529, loss: 0.010235447436571121
2023-01-22 17:24:58.317296: step: 56/529, loss: 0.01629253849387169
2023-01-22 17:24:59.452695: step: 60/529, loss: 0.011247687041759491
2023-01-22 17:25:00.567733: step: 64/529, loss: 0.009514960460364819
2023-01-22 17:25:01.695721: step: 68/529, loss: 0.028238818049430847
2023-01-22 17:25:02.800423: step: 72/529, loss: 0.005100684706121683
2023-01-22 17:25:03.957437: step: 76/529, loss: 0.011901361867785454
2023-01-22 17:25:05.057498: step: 80/529, loss: 0.024363839998841286
2023-01-22 17:25:06.185002: step: 84/529, loss: 0.02609892748296261
2023-01-22 17:25:07.273500: step: 88/529, loss: 0.017716793343424797
2023-01-22 17:25:08.398373: step: 92/529, loss: 0.00783140491694212
2023-01-22 17:25:09.499965: step: 96/529, loss: 0.007628799416124821
2023-01-22 17:25:10.600339: step: 100/529, loss: 0.0015609943075105548
2023-01-22 17:25:11.708304: step: 104/529, loss: 0.025129221379756927
2023-01-22 17:25:12.815392: step: 108/529, loss: 0.00945216417312622
2023-01-22 17:25:13.925357: step: 112/529, loss: 0.0084123145788908
2023-01-22 17:25:15.019121: step: 116/529, loss: 0.00691334018483758
2023-01-22 17:25:16.120059: step: 120/529, loss: 0.006969493348151445
2023-01-22 17:25:17.213290: step: 124/529, loss: 0.004777539521455765
2023-01-22 17:25:18.334798: step: 128/529, loss: 0.049693766981363297
2023-01-22 17:25:19.453694: step: 132/529, loss: 0.000980474054813385
2023-01-22 17:25:20.545078: step: 136/529, loss: 0.008576666936278343
2023-01-22 17:25:21.683706: step: 140/529, loss: 0.0054633659310638905
2023-01-22 17:25:22.785890: step: 144/529, loss: 0.022170914337038994
2023-01-22 17:25:23.896664: step: 148/529, loss: 0.021785352379083633
2023-01-22 17:25:25.004281: step: 152/529, loss: 0.008628305979073048
2023-01-22 17:25:26.120830: step: 156/529, loss: 0.01366341020911932
2023-01-22 17:25:27.242553: step: 160/529, loss: 0.009315998293459415
2023-01-22 17:25:28.377154: step: 164/529, loss: 0.015487903729081154
2023-01-22 17:25:29.492256: step: 168/529, loss: 0.0075741903856396675
2023-01-22 17:25:30.598313: step: 172/529, loss: 0.005317441653460264
2023-01-22 17:25:31.704096: step: 176/529, loss: 0.012066704221069813
2023-01-22 17:25:32.804603: step: 180/529, loss: 0.10282935202121735
2023-01-22 17:25:33.898827: step: 184/529, loss: 0.021517092362046242
2023-01-22 17:25:34.996328: step: 188/529, loss: 0.007219498977065086
2023-01-22 17:25:36.123674: step: 192/529, loss: 0.022852858528494835
2023-01-22 17:25:37.219593: step: 196/529, loss: 0.010436865501105785
2023-01-22 17:25:38.335434: step: 200/529, loss: 0.010775558650493622
2023-01-22 17:25:39.438921: step: 204/529, loss: 0.07135234028100967
2023-01-22 17:25:40.557410: step: 208/529, loss: 0.007811805699020624
2023-01-22 17:25:41.657694: step: 212/529, loss: 0.01022158283740282
2023-01-22 17:25:42.752975: step: 216/529, loss: 0.018166281282901764
2023-01-22 17:25:43.844158: step: 220/529, loss: 0.010322998277842999
2023-01-22 17:25:44.963803: step: 224/529, loss: 0.04177597537636757
2023-01-22 17:25:46.077545: step: 228/529, loss: 0.02162901870906353
2023-01-22 17:25:47.189518: step: 232/529, loss: 0.004620315972715616
2023-01-22 17:25:48.295834: step: 236/529, loss: 0.014923829585313797
2023-01-22 17:25:49.416506: step: 240/529, loss: 0.006562465336173773
2023-01-22 17:25:50.519972: step: 244/529, loss: 0.007545576896518469
2023-01-22 17:25:51.613762: step: 248/529, loss: 0.003948131110519171
2023-01-22 17:25:52.715472: step: 252/529, loss: 0.011165970005095005
2023-01-22 17:25:53.832228: step: 256/529, loss: 0.017482131719589233
2023-01-22 17:25:54.929545: step: 260/529, loss: 0.014062904752790928
2023-01-22 17:25:56.032703: step: 264/529, loss: 0.020463835448026657
2023-01-22 17:25:57.147014: step: 268/529, loss: 0.007404504809528589
2023-01-22 17:25:58.254019: step: 272/529, loss: 0.0030040584970265627
2023-01-22 17:25:59.350722: step: 276/529, loss: 0.0
2023-01-22 17:26:00.469485: step: 280/529, loss: 0.06010463461279869
2023-01-22 17:26:01.598785: step: 284/529, loss: 0.016965633258223534
2023-01-22 17:26:02.704705: step: 288/529, loss: 0.006219563074409962
2023-01-22 17:26:03.824074: step: 292/529, loss: 0.004653458949178457
2023-01-22 17:26:04.929237: step: 296/529, loss: 0.008565942756831646
2023-01-22 17:26:06.018376: step: 300/529, loss: 0.012844175100326538
2023-01-22 17:26:07.127967: step: 304/529, loss: 0.008220589719712734
2023-01-22 17:26:08.236703: step: 308/529, loss: 0.04331209510564804
2023-01-22 17:26:09.349018: step: 312/529, loss: 0.0030146182980388403
2023-01-22 17:26:10.464675: step: 316/529, loss: 0.0468660406768322
2023-01-22 17:26:11.553887: step: 320/529, loss: 0.016729986295104027
2023-01-22 17:26:12.681751: step: 324/529, loss: 0.004962988197803497
2023-01-22 17:26:13.791179: step: 328/529, loss: 0.024184400215744972
2023-01-22 17:26:14.898066: step: 332/529, loss: 0.022226804867386818
2023-01-22 17:26:15.995369: step: 336/529, loss: 0.010644815862178802
2023-01-22 17:26:17.118338: step: 340/529, loss: 0.004353120923042297
2023-01-22 17:26:18.249383: step: 344/529, loss: 0.040854379534721375
2023-01-22 17:26:19.380543: step: 348/529, loss: 0.04305291920900345
2023-01-22 17:26:20.483606: step: 352/529, loss: 0.013636622577905655
2023-01-22 17:26:21.563922: step: 356/529, loss: 0.0040465048514306545
2023-01-22 17:26:22.671787: step: 360/529, loss: 0.012581290677189827
2023-01-22 17:26:23.776503: step: 364/529, loss: 0.004859903361648321
2023-01-22 17:26:24.897621: step: 368/529, loss: 0.015072670765221119
2023-01-22 17:26:26.005697: step: 372/529, loss: 0.00809277594089508
2023-01-22 17:26:27.083880: step: 376/529, loss: 0.009031995199620724
2023-01-22 17:26:28.197219: step: 380/529, loss: 0.00619395449757576
2023-01-22 17:26:29.293092: step: 384/529, loss: 0.02816014178097248
2023-01-22 17:26:30.409636: step: 388/529, loss: 0.03250144422054291
2023-01-22 17:26:31.504956: step: 392/529, loss: 0.009218337014317513
2023-01-22 17:26:32.620603: step: 396/529, loss: 0.006811859551817179
2023-01-22 17:26:33.711928: step: 400/529, loss: 0.030372116714715958
2023-01-22 17:26:34.839153: step: 404/529, loss: 0.011055875569581985
2023-01-22 17:26:35.955958: step: 408/529, loss: 0.009250106289982796
2023-01-22 17:26:37.054095: step: 412/529, loss: 0.01222851313650608
2023-01-22 17:26:38.180998: step: 416/529, loss: 0.009741735644638538
2023-01-22 17:26:39.294505: step: 420/529, loss: 0.00820836890488863
2023-01-22 17:26:40.393412: step: 424/529, loss: 0.009705927222967148
2023-01-22 17:26:41.508321: step: 428/529, loss: 0.004971783608198166
2023-01-22 17:26:42.617163: step: 432/529, loss: 0.009303607977926731
2023-01-22 17:26:43.742864: step: 436/529, loss: 0.026462413370609283
2023-01-22 17:26:44.851614: step: 440/529, loss: 0.003007612656801939
2023-01-22 17:26:45.961969: step: 444/529, loss: 0.007574520073831081
2023-01-22 17:26:47.107246: step: 448/529, loss: 0.0124023063108325
2023-01-22 17:26:48.223251: step: 452/529, loss: 0.012094407342374325
2023-01-22 17:26:49.333380: step: 456/529, loss: 0.010857230052351952
2023-01-22 17:26:50.445327: step: 460/529, loss: 0.009426238015294075
2023-01-22 17:26:51.566803: step: 464/529, loss: 0.00946289487183094
2023-01-22 17:26:52.686357: step: 468/529, loss: 0.04993095621466637
2023-01-22 17:26:53.832730: step: 472/529, loss: 0.008180856704711914
2023-01-22 17:26:54.948878: step: 476/529, loss: 0.007782386150211096
2023-01-22 17:26:56.074527: step: 480/529, loss: 0.012876303866505623
2023-01-22 17:26:57.193818: step: 484/529, loss: 0.0029120012186467648
2023-01-22 17:26:58.293682: step: 488/529, loss: 0.008031805977225304
2023-01-22 17:26:59.421383: step: 492/529, loss: 0.016908133402466774
2023-01-22 17:27:00.526400: step: 496/529, loss: 0.007961700670421124
2023-01-22 17:27:01.644011: step: 500/529, loss: 0.00820307619869709
2023-01-22 17:27:02.744662: step: 504/529, loss: 0.006375925615429878
2023-01-22 17:27:03.842253: step: 508/529, loss: 0.005103034898638725
2023-01-22 17:27:04.957089: step: 512/529, loss: 0.03152255341410637
2023-01-22 17:27:06.077891: step: 516/529, loss: 0.028367677703499794
2023-01-22 17:27:07.197849: step: 520/529, loss: 0.006421062164008617
2023-01-22 17:27:08.311673: step: 524/529, loss: 0.005070759914815426
2023-01-22 17:27:09.411579: step: 528/529, loss: 0.0734584778547287
2023-01-22 17:27:10.527363: step: 532/529, loss: 0.006186713930219412
2023-01-22 17:27:11.639745: step: 536/529, loss: 0.00510924868285656
2023-01-22 17:27:12.750388: step: 540/529, loss: 0.0038213462103158236
2023-01-22 17:27:13.855145: step: 544/529, loss: 0.025778640061616898
2023-01-22 17:27:14.961059: step: 548/529, loss: 0.059537455439567566
2023-01-22 17:27:16.068504: step: 552/529, loss: 0.04153849929571152
2023-01-22 17:27:17.166967: step: 556/529, loss: 0.006779353599995375
2023-01-22 17:27:18.252312: step: 560/529, loss: 0.0036809067241847515
2023-01-22 17:27:19.369651: step: 564/529, loss: 0.03398386016488075
2023-01-22 17:27:20.500250: step: 568/529, loss: 0.005276466719806194
2023-01-22 17:27:21.601073: step: 572/529, loss: 0.0028425143100321293
2023-01-22 17:27:22.701077: step: 576/529, loss: 0.009706833399832249
2023-01-22 17:27:23.801891: step: 580/529, loss: 0.010437401942908764
2023-01-22 17:27:24.910634: step: 584/529, loss: 0.00651808176189661
2023-01-22 17:27:26.004759: step: 588/529, loss: 0.012304767034947872
2023-01-22 17:27:27.110576: step: 592/529, loss: 0.0046713827177882195
2023-01-22 17:27:28.208361: step: 596/529, loss: 0.02026529423892498
2023-01-22 17:27:29.312385: step: 600/529, loss: 0.015400368720293045
2023-01-22 17:27:30.416436: step: 604/529, loss: 0.0
2023-01-22 17:27:31.558239: step: 608/529, loss: 0.0044232867658138275
2023-01-22 17:27:32.655492: step: 612/529, loss: 0.0017095786752179265
2023-01-22 17:27:33.781669: step: 616/529, loss: 0.007761573418974876
2023-01-22 17:27:34.873113: step: 620/529, loss: 0.011994373984634876
2023-01-22 17:27:35.999034: step: 624/529, loss: 0.00995255634188652
2023-01-22 17:27:37.135559: step: 628/529, loss: 0.010592106729745865
2023-01-22 17:27:38.228194: step: 632/529, loss: 0.013124264776706696
2023-01-22 17:27:39.323563: step: 636/529, loss: 0.01579657942056656
2023-01-22 17:27:40.422329: step: 640/529, loss: 0.007024318911135197
2023-01-22 17:27:41.513701: step: 644/529, loss: 0.013561829924583435
2023-01-22 17:27:42.623908: step: 648/529, loss: 0.007875878363847733
2023-01-22 17:27:43.744230: step: 652/529, loss: 0.006561497692018747
2023-01-22 17:27:44.867337: step: 656/529, loss: 0.020171910524368286
2023-01-22 17:27:45.980323: step: 660/529, loss: 0.026801681146025658
2023-01-22 17:27:47.081154: step: 664/529, loss: 0.0040346658788621426
2023-01-22 17:27:48.191997: step: 668/529, loss: 0.010607567615807056
2023-01-22 17:27:49.301307: step: 672/529, loss: 0.00720202038064599
2023-01-22 17:27:50.394986: step: 676/529, loss: 0.007663401775062084
2023-01-22 17:27:51.514316: step: 680/529, loss: 0.00843114499002695
2023-01-22 17:27:52.633119: step: 684/529, loss: 0.028987901285290718
2023-01-22 17:27:53.736990: step: 688/529, loss: 0.021602654829621315
2023-01-22 17:27:54.834135: step: 692/529, loss: 0.00838488806039095
2023-01-22 17:27:55.921169: step: 696/529, loss: 0.005438137799501419
2023-01-22 17:27:57.048481: step: 700/529, loss: 0.02256591059267521
2023-01-22 17:27:58.142865: step: 704/529, loss: 0.01812754012644291
2023-01-22 17:27:59.257966: step: 708/529, loss: 0.006764445919543505
2023-01-22 17:28:00.362718: step: 712/529, loss: 0.04464699700474739
2023-01-22 17:28:01.459536: step: 716/529, loss: 0.020541075617074966
2023-01-22 17:28:02.570702: step: 720/529, loss: 0.0046661836095154285
2023-01-22 17:28:03.683478: step: 724/529, loss: 0.006169058848172426
2023-01-22 17:28:04.770270: step: 728/529, loss: 0.0071898698806762695
2023-01-22 17:28:05.872542: step: 732/529, loss: 0.03490616753697395
2023-01-22 17:28:06.988527: step: 736/529, loss: 0.003926218021661043
2023-01-22 17:28:08.090991: step: 740/529, loss: 0.010022901929914951
2023-01-22 17:28:09.199019: step: 744/529, loss: 0.022787563502788544
2023-01-22 17:28:10.293197: step: 748/529, loss: 0.005251681432127953
2023-01-22 17:28:11.398472: step: 752/529, loss: 0.006961153354495764
2023-01-22 17:28:12.489673: step: 756/529, loss: 0.006728820037096739
2023-01-22 17:28:13.617231: step: 760/529, loss: 0.02350759692490101
2023-01-22 17:28:14.722085: step: 764/529, loss: 0.030634228140115738
2023-01-22 17:28:15.852289: step: 768/529, loss: 0.005208211950957775
2023-01-22 17:28:16.962795: step: 772/529, loss: 0.009751081466674805
2023-01-22 17:28:18.074500: step: 776/529, loss: 0.00818828959017992
2023-01-22 17:28:19.180570: step: 780/529, loss: 0.016989491879940033
2023-01-22 17:28:20.290559: step: 784/529, loss: 0.006734752561897039
2023-01-22 17:28:21.418299: step: 788/529, loss: 0.004802794195711613
2023-01-22 17:28:22.526901: step: 792/529, loss: 0.030767805874347687
2023-01-22 17:28:23.622249: step: 796/529, loss: 0.008174249902367592
2023-01-22 17:28:24.727579: step: 800/529, loss: 0.03600287437438965
2023-01-22 17:28:25.837086: step: 804/529, loss: 0.015916625037789345
2023-01-22 17:28:26.962165: step: 808/529, loss: 0.03856165334582329
2023-01-22 17:28:28.093003: step: 812/529, loss: 0.005122302565723658
2023-01-22 17:28:29.184832: step: 816/529, loss: 0.01365729235112667
2023-01-22 17:28:30.288344: step: 820/529, loss: 0.0024407037999480963
2023-01-22 17:28:31.413376: step: 824/529, loss: 0.01446897815912962
2023-01-22 17:28:32.536085: step: 828/529, loss: 0.01769627258181572
2023-01-22 17:28:33.648987: step: 832/529, loss: 0.024822115898132324
2023-01-22 17:28:34.745085: step: 836/529, loss: 0.03964380547404289
2023-01-22 17:28:35.863256: step: 840/529, loss: 0.025744302198290825
2023-01-22 17:28:36.978781: step: 844/529, loss: 0.03316003084182739
2023-01-22 17:28:38.081225: step: 848/529, loss: 0.0027758243959397078
2023-01-22 17:28:39.199965: step: 852/529, loss: 0.038947537541389465
2023-01-22 17:28:40.316222: step: 856/529, loss: 0.03559670224785805
2023-01-22 17:28:41.428651: step: 860/529, loss: 0.004581565503031015
2023-01-22 17:28:42.542815: step: 864/529, loss: 0.009412151761353016
2023-01-22 17:28:43.645252: step: 868/529, loss: 0.006614048499614
2023-01-22 17:28:44.746814: step: 872/529, loss: 0.0059139481745660305
2023-01-22 17:28:45.862768: step: 876/529, loss: 0.03860270977020264
2023-01-22 17:28:46.979062: step: 880/529, loss: 0.005993709899485111
2023-01-22 17:28:48.101997: step: 884/529, loss: 0.004429427906870842
2023-01-22 17:28:49.215946: step: 888/529, loss: 0.06381593644618988
2023-01-22 17:28:50.329245: step: 892/529, loss: 0.05742922052741051
2023-01-22 17:28:51.427758: step: 896/529, loss: 0.004541744943708181
2023-01-22 17:28:52.541348: step: 900/529, loss: 0.01731082610785961
2023-01-22 17:28:53.674955: step: 904/529, loss: 0.003912780433893204
2023-01-22 17:28:54.778319: step: 908/529, loss: 0.015212543308734894
2023-01-22 17:28:55.901336: step: 912/529, loss: 0.028064537793397903
2023-01-22 17:28:57.013403: step: 916/529, loss: 0.004164090845733881
2023-01-22 17:28:58.113007: step: 920/529, loss: 0.024902500212192535
2023-01-22 17:28:59.229758: step: 924/529, loss: 0.007549820467829704
2023-01-22 17:29:00.339204: step: 928/529, loss: 0.01531895436346531
2023-01-22 17:29:01.468110: step: 932/529, loss: 0.01943441480398178
2023-01-22 17:29:02.620325: step: 936/529, loss: 0.008244885131716728
2023-01-22 17:29:03.714726: step: 940/529, loss: 0.01422719657421112
2023-01-22 17:29:04.820683: step: 944/529, loss: 0.00490589952096343
2023-01-22 17:29:05.963572: step: 948/529, loss: 0.014141133986413479
2023-01-22 17:29:07.105084: step: 952/529, loss: 0.043286994099617004
2023-01-22 17:29:08.231348: step: 956/529, loss: 0.03698762506246567
2023-01-22 17:29:09.329647: step: 960/529, loss: 0.0031352443620562553
2023-01-22 17:29:10.421149: step: 964/529, loss: 0.022375736385583878
2023-01-22 17:29:11.507885: step: 968/529, loss: 0.010876361280679703
2023-01-22 17:29:12.613350: step: 972/529, loss: 0.00666898675262928
2023-01-22 17:29:13.717469: step: 976/529, loss: 0.0071960752829909325
2023-01-22 17:29:14.815650: step: 980/529, loss: 0.006525927688926458
2023-01-22 17:29:15.912584: step: 984/529, loss: 0.030511315912008286
2023-01-22 17:29:17.002985: step: 988/529, loss: 0.012112803757190704
2023-01-22 17:29:18.134306: step: 992/529, loss: 0.07843738049268723
2023-01-22 17:29:19.255628: step: 996/529, loss: 0.016512110829353333
2023-01-22 17:29:20.354499: step: 1000/529, loss: 0.003049770137295127
2023-01-22 17:29:21.495883: step: 1004/529, loss: 0.04512205719947815
2023-01-22 17:29:22.606186: step: 1008/529, loss: 0.007197485771030188
2023-01-22 17:29:23.711574: step: 1012/529, loss: 0.05175314098596573
2023-01-22 17:29:24.818968: step: 1016/529, loss: 0.024995850399136543
2023-01-22 17:29:25.924333: step: 1020/529, loss: 0.019134696573019028
2023-01-22 17:29:27.018605: step: 1024/529, loss: 0.003969466779381037
2023-01-22 17:29:28.119695: step: 1028/529, loss: 0.016748148947954178
2023-01-22 17:29:29.218791: step: 1032/529, loss: 0.010121073573827744
2023-01-22 17:29:30.307636: step: 1036/529, loss: 0.003607254009693861
2023-01-22 17:29:31.424792: step: 1040/529, loss: 0.0025053697172552347
2023-01-22 17:29:32.514586: step: 1044/529, loss: 0.1172996312379837
2023-01-22 17:29:33.631810: step: 1048/529, loss: 0.015168258920311928
2023-01-22 17:29:34.727070: step: 1052/529, loss: 0.00747688626870513
2023-01-22 17:29:35.860443: step: 1056/529, loss: 0.013755887746810913
2023-01-22 17:29:36.997648: step: 1060/529, loss: 0.011706928722560406
2023-01-22 17:29:38.072951: step: 1064/529, loss: 0.010267854668200016
2023-01-22 17:29:39.177255: step: 1068/529, loss: 0.021065551787614822
2023-01-22 17:29:40.272096: step: 1072/529, loss: 0.008091267198324203
2023-01-22 17:29:41.366120: step: 1076/529, loss: 0.009658264927566051
2023-01-22 17:29:42.466815: step: 1080/529, loss: 0.0066797793842852116
2023-01-22 17:29:43.564889: step: 1084/529, loss: 0.006737333722412586
2023-01-22 17:29:44.690711: step: 1088/529, loss: 0.0060395351611077785
2023-01-22 17:29:45.797890: step: 1092/529, loss: 0.02207772620022297
2023-01-22 17:29:46.938067: step: 1096/529, loss: 0.028347786515951157
2023-01-22 17:29:48.043287: step: 1100/529, loss: 0.01743381842970848
2023-01-22 17:29:49.152302: step: 1104/529, loss: 0.006190153304487467
2023-01-22 17:29:50.260352: step: 1108/529, loss: 0.005800239741802216
2023-01-22 17:29:51.397505: step: 1112/529, loss: 0.005582496523857117
2023-01-22 17:29:52.520194: step: 1116/529, loss: 0.007586284540593624
2023-01-22 17:29:53.625094: step: 1120/529, loss: 0.00489607872441411
2023-01-22 17:29:54.741100: step: 1124/529, loss: 0.009180678054690361
2023-01-22 17:29:55.854873: step: 1128/529, loss: 0.01565048284828663
2023-01-22 17:29:56.964335: step: 1132/529, loss: 0.01631510630249977
2023-01-22 17:29:58.065226: step: 1136/529, loss: 0.004433012567460537
2023-01-22 17:29:59.168528: step: 1140/529, loss: 0.037556763738393784
2023-01-22 17:30:00.286543: step: 1144/529, loss: 0.003132070880383253
2023-01-22 17:30:01.400826: step: 1148/529, loss: 0.008190575987100601
2023-01-22 17:30:02.514138: step: 1152/529, loss: 0.026660114526748657
2023-01-22 17:30:03.615725: step: 1156/529, loss: 0.029099665582180023
2023-01-22 17:30:04.710798: step: 1160/529, loss: 0.004278501961380243
2023-01-22 17:30:05.818912: step: 1164/529, loss: 0.004865444730967283
2023-01-22 17:30:06.942650: step: 1168/529, loss: 0.0708141028881073
2023-01-22 17:30:08.031097: step: 1172/529, loss: 0.006155682262033224
2023-01-22 17:30:09.135594: step: 1176/529, loss: 0.03570152074098587
2023-01-22 17:30:10.239601: step: 1180/529, loss: 0.006735211703926325
2023-01-22 17:30:11.334846: step: 1184/529, loss: 0.010107604786753654
2023-01-22 17:30:12.449011: step: 1188/529, loss: 0.0065239532850682735
2023-01-22 17:30:13.560793: step: 1192/529, loss: 0.009267025627195835
2023-01-22 17:30:14.667698: step: 1196/529, loss: 0.04032520949840546
2023-01-22 17:30:15.764392: step: 1200/529, loss: 0.007525768131017685
2023-01-22 17:30:16.874096: step: 1204/529, loss: 0.008084542118012905
2023-01-22 17:30:17.958996: step: 1208/529, loss: 0.03704090416431427
2023-01-22 17:30:19.071161: step: 1212/529, loss: 0.01188336405903101
2023-01-22 17:30:20.187946: step: 1216/529, loss: 0.009477616287767887
2023-01-22 17:30:21.291189: step: 1220/529, loss: 0.006158227566629648
2023-01-22 17:30:22.367989: step: 1224/529, loss: 0.009339524433016777
2023-01-22 17:30:23.465712: step: 1228/529, loss: 0.0031968860421329737
2023-01-22 17:30:24.570133: step: 1232/529, loss: 0.0013618320226669312
2023-01-22 17:30:25.672641: step: 1236/529, loss: 0.008826510049402714
2023-01-22 17:30:26.791904: step: 1240/529, loss: 0.004346330184489489
2023-01-22 17:30:27.899308: step: 1244/529, loss: 0.0046552191488444805
2023-01-22 17:30:29.010627: step: 1248/529, loss: 0.021449366584420204
2023-01-22 17:30:30.121312: step: 1252/529, loss: 0.0045154886320233345
2023-01-22 17:30:31.228003: step: 1256/529, loss: 0.0041392166167497635
2023-01-22 17:30:32.392282: step: 1260/529, loss: 0.0197648573666811
2023-01-22 17:30:33.508120: step: 1264/529, loss: 0.006410130765289068
2023-01-22 17:30:34.620278: step: 1268/529, loss: 0.05202331766486168
2023-01-22 17:30:35.758363: step: 1272/529, loss: 0.010371005162596703
2023-01-22 17:30:36.858262: step: 1276/529, loss: 0.00724055664613843
2023-01-22 17:30:37.969411: step: 1280/529, loss: 0.005425448529422283
2023-01-22 17:30:39.072476: step: 1284/529, loss: 0.022026075050234795
2023-01-22 17:30:40.169060: step: 1288/529, loss: 0.009289804846048355
2023-01-22 17:30:41.254970: step: 1292/529, loss: 0.031058356165885925
2023-01-22 17:30:42.363575: step: 1296/529, loss: 0.04024272412061691
2023-01-22 17:30:43.476636: step: 1300/529, loss: 0.012366924434900284
2023-01-22 17:30:44.579443: step: 1304/529, loss: 0.00781036913394928
2023-01-22 17:30:45.674334: step: 1308/529, loss: 0.022240594029426575
2023-01-22 17:30:46.773347: step: 1312/529, loss: 0.01822182536125183
2023-01-22 17:30:47.888318: step: 1316/529, loss: 0.012602580711245537
2023-01-22 17:30:48.970115: step: 1320/529, loss: 0.007978048175573349
2023-01-22 17:30:50.056316: step: 1324/529, loss: 0.020835481584072113
2023-01-22 17:30:51.150629: step: 1328/529, loss: 0.009168798103928566
2023-01-22 17:30:52.243649: step: 1332/529, loss: 0.008838258683681488
2023-01-22 17:30:53.356346: step: 1336/529, loss: 0.009219838306307793
2023-01-22 17:30:54.463847: step: 1340/529, loss: 0.028161942958831787
2023-01-22 17:30:55.572134: step: 1344/529, loss: 0.01361114252358675
2023-01-22 17:30:56.709620: step: 1348/529, loss: 0.001649112906306982
2023-01-22 17:30:57.841701: step: 1352/529, loss: 0.01526301447302103
2023-01-22 17:30:58.955056: step: 1356/529, loss: 0.005494388286024332
2023-01-22 17:31:00.068669: step: 1360/529, loss: 0.01168822031468153
2023-01-22 17:31:01.172275: step: 1364/529, loss: 0.05306252837181091
2023-01-22 17:31:02.316147: step: 1368/529, loss: 0.07980557531118393
2023-01-22 17:31:03.417613: step: 1372/529, loss: 0.0138575229793787
2023-01-22 17:31:04.527580: step: 1376/529, loss: 0.0192241370677948
2023-01-22 17:31:05.641803: step: 1380/529, loss: 0.005999465007334948
2023-01-22 17:31:06.745325: step: 1384/529, loss: 0.00927741639316082
2023-01-22 17:31:07.866912: step: 1388/529, loss: 0.023513052612543106
2023-01-22 17:31:08.957791: step: 1392/529, loss: 0.005822577513754368
2023-01-22 17:31:10.051418: step: 1396/529, loss: 0.00830264762043953
2023-01-22 17:31:11.160144: step: 1400/529, loss: 0.037708207964897156
2023-01-22 17:31:12.281236: step: 1404/529, loss: 0.006134921219199896
2023-01-22 17:31:13.383415: step: 1408/529, loss: 0.009257950820028782
2023-01-22 17:31:14.476354: step: 1412/529, loss: 0.032635655254125595
2023-01-22 17:31:15.577220: step: 1416/529, loss: 0.016022369265556335
2023-01-22 17:31:16.682683: step: 1420/529, loss: 0.0049875951372087
2023-01-22 17:31:17.775350: step: 1424/529, loss: 0.0034779945854097605
2023-01-22 17:31:18.878764: step: 1428/529, loss: 0.004835793748497963
2023-01-22 17:31:19.986004: step: 1432/529, loss: 0.005195547826588154
2023-01-22 17:31:21.088813: step: 1436/529, loss: 0.009680205024778843
2023-01-22 17:31:22.190392: step: 1440/529, loss: 0.01889902912080288
2023-01-22 17:31:23.314829: step: 1444/529, loss: 0.012766159139573574
2023-01-22 17:31:24.436122: step: 1448/529, loss: 0.009224303998053074
2023-01-22 17:31:25.523701: step: 1452/529, loss: 0.003969091456383467
2023-01-22 17:31:26.628099: step: 1456/529, loss: 0.009867843240499496
2023-01-22 17:31:27.749980: step: 1460/529, loss: 0.021405458450317383
2023-01-22 17:31:28.863329: step: 1464/529, loss: 0.02739710360765457
2023-01-22 17:31:29.966023: step: 1468/529, loss: 0.00500906677916646
2023-01-22 17:31:31.082928: step: 1472/529, loss: 0.016404489055275917
2023-01-22 17:31:32.202328: step: 1476/529, loss: 0.007989022880792618
2023-01-22 17:31:33.298375: step: 1480/529, loss: 0.004829435609281063
2023-01-22 17:31:34.418333: step: 1484/529, loss: 0.02073470689356327
2023-01-22 17:31:35.533481: step: 1488/529, loss: 0.09473828971385956
2023-01-22 17:31:36.650538: step: 1492/529, loss: 0.0077597894705832005
2023-01-22 17:31:37.784565: step: 1496/529, loss: 0.007753786165267229
2023-01-22 17:31:38.881530: step: 1500/529, loss: 0.011193129234015942
2023-01-22 17:31:40.001138: step: 1504/529, loss: 0.006865547504276037
2023-01-22 17:31:41.103698: step: 1508/529, loss: 0.008532942272722721
2023-01-22 17:31:42.206260: step: 1512/529, loss: 0.0017727493541315198
2023-01-22 17:31:43.320453: step: 1516/529, loss: 0.008294845931231976
2023-01-22 17:31:44.401179: step: 1520/529, loss: 0.0044218674302101135
2023-01-22 17:31:45.523466: step: 1524/529, loss: 0.06720639765262604
2023-01-22 17:31:46.626345: step: 1528/529, loss: 0.07407580316066742
2023-01-22 17:31:47.754501: step: 1532/529, loss: 0.009495191276073456
2023-01-22 17:31:48.867097: step: 1536/529, loss: 0.00949164293706417
2023-01-22 17:31:49.978565: step: 1540/529, loss: 0.008992256596684456
2023-01-22 17:31:51.103436: step: 1544/529, loss: 0.00832844153046608
2023-01-22 17:31:52.234202: step: 1548/529, loss: 0.01784440129995346
2023-01-22 17:31:53.338792: step: 1552/529, loss: 0.009815354831516743
2023-01-22 17:31:54.460978: step: 1556/529, loss: 0.03531704470515251
2023-01-22 17:31:55.564216: step: 1560/529, loss: 0.024419886991381645
2023-01-22 17:31:56.670608: step: 1564/529, loss: 0.011316888965666294
2023-01-22 17:31:57.782497: step: 1568/529, loss: 0.008468734100461006
2023-01-22 17:31:58.923357: step: 1572/529, loss: 0.018856732174754143
2023-01-22 17:32:00.032118: step: 1576/529, loss: 0.010021758265793324
2023-01-22 17:32:01.142237: step: 1580/529, loss: 0.006564375013113022
2023-01-22 17:32:02.243748: step: 1584/529, loss: 0.009300853125751019
2023-01-22 17:32:03.336370: step: 1588/529, loss: 0.03209228813648224
2023-01-22 17:32:04.447693: step: 1592/529, loss: 0.011788084171712399
2023-01-22 17:32:05.558972: step: 1596/529, loss: 0.007834677584469318
2023-01-22 17:32:06.647743: step: 1600/529, loss: 0.0005344073288142681
2023-01-22 17:32:07.758065: step: 1604/529, loss: 0.009042621590197086
2023-01-22 17:32:08.868413: step: 1608/529, loss: 0.011133428663015366
2023-01-22 17:32:09.971918: step: 1612/529, loss: 0.011527447029948235
2023-01-22 17:32:11.084639: step: 1616/529, loss: 0.0632004514336586
2023-01-22 17:32:12.202016: step: 1620/529, loss: 0.0006157772149890661
2023-01-22 17:32:13.287383: step: 1624/529, loss: 0.005812895484268665
2023-01-22 17:32:14.414623: step: 1628/529, loss: 0.05044638738036156
2023-01-22 17:32:15.517547: step: 1632/529, loss: 0.025022072717547417
2023-01-22 17:32:16.596329: step: 1636/529, loss: 0.025674128904938698
2023-01-22 17:32:17.707981: step: 1640/529, loss: 0.00849166139960289
2023-01-22 17:32:18.817369: step: 1644/529, loss: 0.008506173267960548
2023-01-22 17:32:19.934868: step: 1648/529, loss: 0.005333370994776487
2023-01-22 17:32:21.046545: step: 1652/529, loss: 0.002690615365281701
2023-01-22 17:32:22.146980: step: 1656/529, loss: 0.022898681461811066
2023-01-22 17:32:23.267823: step: 1660/529, loss: 0.006212149281054735
2023-01-22 17:32:24.381302: step: 1664/529, loss: 0.007051804102957249
2023-01-22 17:32:25.490808: step: 1668/529, loss: 0.0026209489442408085
2023-01-22 17:32:26.581936: step: 1672/529, loss: 0.011211784556508064
2023-01-22 17:32:27.697789: step: 1676/529, loss: 0.008433562703430653
2023-01-22 17:32:28.815463: step: 1680/529, loss: 0.025189196690917015
2023-01-22 17:32:29.904431: step: 1684/529, loss: 0.003636155743151903
2023-01-22 17:32:31.033357: step: 1688/529, loss: 0.009845258668065071
2023-01-22 17:32:32.122930: step: 1692/529, loss: 0.03183900937438011
2023-01-22 17:32:33.230612: step: 1696/529, loss: 0.003094209125265479
2023-01-22 17:32:34.330132: step: 1700/529, loss: 0.02190120331943035
2023-01-22 17:32:35.448577: step: 1704/529, loss: 0.002687569009140134
2023-01-22 17:32:36.549417: step: 1708/529, loss: 0.009060143493115902
2023-01-22 17:32:37.655764: step: 1712/529, loss: 0.02194773405790329
2023-01-22 17:32:38.752073: step: 1716/529, loss: 0.034944772720336914
2023-01-22 17:32:39.869266: step: 1720/529, loss: 0.009142527356743813
2023-01-22 17:32:40.998394: step: 1724/529, loss: 0.01273645181208849
2023-01-22 17:32:42.107477: step: 1728/529, loss: 0.007472269237041473
2023-01-22 17:32:43.212882: step: 1732/529, loss: 0.009180750697851181
2023-01-22 17:32:44.303735: step: 1736/529, loss: 0.004138650372624397
2023-01-22 17:32:45.404188: step: 1740/529, loss: 0.004630414303392172
2023-01-22 17:32:46.496879: step: 1744/529, loss: 0.0065904478542506695
2023-01-22 17:32:47.612618: step: 1748/529, loss: 0.010466614738106728
2023-01-22 17:32:48.727104: step: 1752/529, loss: 0.04151769354939461
2023-01-22 17:32:49.816003: step: 1756/529, loss: 0.02589283511042595
2023-01-22 17:32:50.933984: step: 1760/529, loss: 0.01761699840426445
2023-01-22 17:32:52.028572: step: 1764/529, loss: 0.03993140161037445
2023-01-22 17:32:53.134618: step: 1768/529, loss: 0.006331652402877808
2023-01-22 17:32:54.241960: step: 1772/529, loss: 0.018918009474873543
2023-01-22 17:32:55.358514: step: 1776/529, loss: 0.02306489273905754
2023-01-22 17:32:56.470869: step: 1780/529, loss: 0.006211545318365097
2023-01-22 17:32:57.574016: step: 1784/529, loss: 0.003728611394762993
2023-01-22 17:32:58.685660: step: 1788/529, loss: 0.005016469396650791
2023-01-22 17:32:59.782866: step: 1792/529, loss: 0.004680269863456488
2023-01-22 17:33:00.895772: step: 1796/529, loss: 0.007269581779837608
2023-01-22 17:33:01.997969: step: 1800/529, loss: 0.022171501070261
2023-01-22 17:33:03.122579: step: 1804/529, loss: 0.009929131716489792
2023-01-22 17:33:04.238318: step: 1808/529, loss: 0.057336192578077316
2023-01-22 17:33:05.336678: step: 1812/529, loss: 0.008408146910369396
2023-01-22 17:33:06.459235: step: 1816/529, loss: 0.0034600687213242054
2023-01-22 17:33:07.569421: step: 1820/529, loss: 0.010800952091813087
2023-01-22 17:33:08.661084: step: 1824/529, loss: 0.005716582294553518
2023-01-22 17:33:09.777862: step: 1828/529, loss: 0.00797891803085804
2023-01-22 17:33:10.867577: step: 1832/529, loss: 0.02174191176891327
2023-01-22 17:33:11.968405: step: 1836/529, loss: 0.006099015474319458
2023-01-22 17:33:13.071709: step: 1840/529, loss: 0.0033705770038068295
2023-01-22 17:33:14.172660: step: 1844/529, loss: 0.002841704525053501
2023-01-22 17:33:15.276207: step: 1848/529, loss: 0.014144199900329113
2023-01-22 17:33:16.395491: step: 1852/529, loss: 0.008648702874779701
2023-01-22 17:33:17.518051: step: 1856/529, loss: 0.0062553295865654945
2023-01-22 17:33:18.626163: step: 1860/529, loss: 0.004111865069717169
2023-01-22 17:33:19.725987: step: 1864/529, loss: 0.004711200017482042
2023-01-22 17:33:20.836573: step: 1868/529, loss: 0.005292634945362806
2023-01-22 17:33:21.934012: step: 1872/529, loss: 5.4861877288203686e-05
2023-01-22 17:33:23.025927: step: 1876/529, loss: 0.00027760709053836763
2023-01-22 17:33:24.126692: step: 1880/529, loss: 0.01562339998781681
2023-01-22 17:33:25.226831: step: 1884/529, loss: 0.014251288957893848
2023-01-22 17:33:26.345378: step: 1888/529, loss: 0.02519753947854042
2023-01-22 17:33:27.478049: step: 1892/529, loss: 0.02733030542731285
2023-01-22 17:33:28.581374: step: 1896/529, loss: 0.005994006525725126
2023-01-22 17:33:29.695832: step: 1900/529, loss: 0.005048609338700771
2023-01-22 17:33:30.800487: step: 1904/529, loss: 0.003010928863659501
2023-01-22 17:33:31.933883: step: 1908/529, loss: 0.009821907617151737
2023-01-22 17:33:33.034857: step: 1912/529, loss: 0.02399621158838272
2023-01-22 17:33:34.116946: step: 1916/529, loss: 0.01810375601053238
2023-01-22 17:33:35.221587: step: 1920/529, loss: 0.012408771552145481
2023-01-22 17:33:36.321723: step: 1924/529, loss: 0.004833292681723833
2023-01-22 17:33:37.415402: step: 1928/529, loss: 0.007213070057332516
2023-01-22 17:33:38.509548: step: 1932/529, loss: 0.00512283481657505
2023-01-22 17:33:39.616469: step: 1936/529, loss: 0.029104046523571014
2023-01-22 17:33:40.724503: step: 1940/529, loss: 0.008731608279049397
2023-01-22 17:33:41.809536: step: 1944/529, loss: 0.0018308151047676802
2023-01-22 17:33:42.908031: step: 1948/529, loss: 0.016262350603938103
2023-01-22 17:33:44.031052: step: 1952/529, loss: 0.0015288363210856915
2023-01-22 17:33:45.147848: step: 1956/529, loss: 0.011807559989392757
2023-01-22 17:33:46.255430: step: 1960/529, loss: 0.002348709851503372
2023-01-22 17:33:47.358230: step: 1964/529, loss: 0.003221815684810281
2023-01-22 17:33:48.476646: step: 1968/529, loss: 0.00016679333930369467
2023-01-22 17:33:49.574613: step: 1972/529, loss: 0.01722387783229351
2023-01-22 17:33:50.683101: step: 1976/529, loss: 0.01304915826767683
2023-01-22 17:33:51.760797: step: 1980/529, loss: 0.008372940123081207
2023-01-22 17:33:52.870519: step: 1984/529, loss: 0.008127515204250813
2023-01-22 17:33:53.981848: step: 1988/529, loss: 0.008517141453921795
2023-01-22 17:33:55.118409: step: 1992/529, loss: 0.026112094521522522
2023-01-22 17:33:56.233093: step: 1996/529, loss: 0.013220422901213169
2023-01-22 17:33:57.321282: step: 2000/529, loss: 0.0030801587272435427
2023-01-22 17:33:58.439884: step: 2004/529, loss: 0.007968481630086899
2023-01-22 17:33:59.532632: step: 2008/529, loss: 0.0016047836979851127
2023-01-22 17:34:00.682254: step: 2012/529, loss: 0.0065104663372039795
2023-01-22 17:34:01.820675: step: 2016/529, loss: 0.00422339141368866
2023-01-22 17:34:02.950256: step: 2020/529, loss: 0.009648089297115803
2023-01-22 17:34:04.039158: step: 2024/529, loss: 0.011106958612799644
2023-01-22 17:34:05.158375: step: 2028/529, loss: 0.007304979022592306
2023-01-22 17:34:06.262923: step: 2032/529, loss: 0.010854221880435944
2023-01-22 17:34:07.390848: step: 2036/529, loss: 0.007544748485088348
2023-01-22 17:34:08.510474: step: 2040/529, loss: 0.006136166863143444
2023-01-22 17:34:09.626023: step: 2044/529, loss: 0.004133906215429306
2023-01-22 17:34:10.746372: step: 2048/529, loss: 0.011073668487370014
2023-01-22 17:34:11.863717: step: 2052/529, loss: 0.005836395546793938
2023-01-22 17:34:12.936946: step: 2056/529, loss: 0.009044923819601536
2023-01-22 17:34:14.038349: step: 2060/529, loss: 0.00556538812816143
2023-01-22 17:34:15.158301: step: 2064/529, loss: 0.014669734053313732
2023-01-22 17:34:16.268787: step: 2068/529, loss: 0.010857461020350456
2023-01-22 17:34:17.384575: step: 2072/529, loss: 0.007249240763485432
2023-01-22 17:34:18.482963: step: 2076/529, loss: 0.007566243410110474
2023-01-22 17:34:19.628287: step: 2080/529, loss: 0.006541979964822531
2023-01-22 17:34:20.745280: step: 2084/529, loss: 0.0038325912319123745
2023-01-22 17:34:21.860604: step: 2088/529, loss: 0.01036426518112421
2023-01-22 17:34:22.961506: step: 2092/529, loss: 0.003651689039543271
2023-01-22 17:34:24.047036: step: 2096/529, loss: 0.015157479792833328
2023-01-22 17:34:25.150118: step: 2100/529, loss: 0.02793698012828827
2023-01-22 17:34:26.253610: step: 2104/529, loss: 0.008867218159139156
2023-01-22 17:34:27.365022: step: 2108/529, loss: 0.027072349563241005
2023-01-22 17:34:28.482644: step: 2112/529, loss: 0.014590988866984844
2023-01-22 17:34:29.556528: step: 2116/529, loss: 0.004477841779589653
==================================================
Loss: 0.015
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33833087822671154, 'r': 0.34667680121902134, 'f1': 0.34245299764278203}, 'combined': 0.2523337877367867, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36213467140284455, 'r': 0.29754614992320305, 'f1': 0.3266785201153037}, 'combined': 0.20177202713004055, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best korean model...
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33833087822671154, 'r': 0.34667680121902134, 'f1': 0.34245299764278203}, 'combined': 0.2523337877367867, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36213467140284455, 'r': 0.29754614992320305, 'f1': 0.3266785201153037}, 'combined': 0.20177202713004055, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 2
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:37:20.502679: step: 4/529, loss: 0.009641360491514206
2023-01-22 17:37:21.597200: step: 8/529, loss: 0.004441812634468079
2023-01-22 17:37:22.697394: step: 12/529, loss: 0.009472782723605633
2023-01-22 17:37:23.795919: step: 16/529, loss: 0.013659856282174587
2023-01-22 17:37:24.886255: step: 20/529, loss: 0.07212577760219574
2023-01-22 17:37:25.980248: step: 24/529, loss: 0.008560748770833015
2023-01-22 17:37:27.067793: step: 28/529, loss: 0.018241802230477333
2023-01-22 17:37:28.158261: step: 32/529, loss: 0.015703311190009117
2023-01-22 17:37:29.243055: step: 36/529, loss: 0.026424825191497803
2023-01-22 17:37:30.333209: step: 40/529, loss: 0.005716434679925442
2023-01-22 17:37:31.448793: step: 44/529, loss: 0.007539636921137571
2023-01-22 17:37:32.595125: step: 48/529, loss: 0.00743406405672431
2023-01-22 17:37:33.707211: step: 52/529, loss: 0.029411813244223595
2023-01-22 17:37:34.801323: step: 56/529, loss: 0.015271333046257496
2023-01-22 17:37:35.900498: step: 60/529, loss: 0.02746458165347576
2023-01-22 17:37:36.999586: step: 64/529, loss: 0.025568468496203423
2023-01-22 17:37:38.104575: step: 68/529, loss: 0.011672289110720158
2023-01-22 17:37:39.200591: step: 72/529, loss: 0.010656093247234821
2023-01-22 17:37:40.321411: step: 76/529, loss: 0.0061738379299640656
2023-01-22 17:37:41.417954: step: 80/529, loss: 0.0052688331343233585
2023-01-22 17:37:42.531697: step: 84/529, loss: 0.007690116297453642
2023-01-22 17:37:43.648441: step: 88/529, loss: 0.010369677096605301
2023-01-22 17:37:44.762922: step: 92/529, loss: 0.004477673210203648
2023-01-22 17:37:45.875478: step: 96/529, loss: 0.02245650812983513
2023-01-22 17:37:46.980449: step: 100/529, loss: 0.02555593103170395
2023-01-22 17:37:48.116233: step: 104/529, loss: 0.0033164224587380886
2023-01-22 17:37:49.205914: step: 108/529, loss: 0.005291598383337259
2023-01-22 17:37:50.339907: step: 112/529, loss: 0.015692410990595818
2023-01-22 17:37:51.422878: step: 116/529, loss: 0.006268255412578583
2023-01-22 17:37:52.529741: step: 120/529, loss: 0.00944138877093792
2023-01-22 17:37:53.640014: step: 124/529, loss: 0.005227590445429087
2023-01-22 17:37:54.747245: step: 128/529, loss: 0.03279861807823181
2023-01-22 17:37:55.843474: step: 132/529, loss: 0.002848308067768812
2023-01-22 17:37:56.936055: step: 136/529, loss: 0.00799502246081829
2023-01-22 17:37:58.034297: step: 140/529, loss: 0.0037851601373404264
2023-01-22 17:37:59.142954: step: 144/529, loss: 0.005079436115920544
2023-01-22 17:38:00.262229: step: 148/529, loss: 0.008446757681667805
2023-01-22 17:38:01.382379: step: 152/529, loss: 0.0068071456626057625
2023-01-22 17:38:02.485307: step: 156/529, loss: 0.005443734582513571
2023-01-22 17:38:03.580322: step: 160/529, loss: 0.006948627065867186
2023-01-22 17:38:04.712426: step: 164/529, loss: 0.02039605751633644
2023-01-22 17:38:05.812695: step: 168/529, loss: 0.002671348163858056
2023-01-22 17:38:06.926925: step: 172/529, loss: 0.03272193297743797
2023-01-22 17:38:08.041790: step: 176/529, loss: 0.014596843160688877
2023-01-22 17:38:09.177685: step: 180/529, loss: 0.0107597466558218
2023-01-22 17:38:10.265619: step: 184/529, loss: 0.02122785523533821
2023-01-22 17:38:11.359448: step: 188/529, loss: 0.0005063194548711181
2023-01-22 17:38:12.466019: step: 192/529, loss: 0.028680510818958282
2023-01-22 17:38:13.579616: step: 196/529, loss: 0.004366212524473667
2023-01-22 17:38:14.682210: step: 200/529, loss: 0.006697970442473888
2023-01-22 17:38:15.754038: step: 204/529, loss: 0.00811207015067339
2023-01-22 17:38:16.889636: step: 208/529, loss: 0.006754192523658276
2023-01-22 17:38:17.995165: step: 212/529, loss: 0.0032824159134179354
2023-01-22 17:38:19.105331: step: 216/529, loss: 0.02449607476592064
2023-01-22 17:38:20.216488: step: 220/529, loss: 0.005415010266005993
2023-01-22 17:38:21.309841: step: 224/529, loss: 0.014032186940312386
2023-01-22 17:38:22.417581: step: 228/529, loss: 0.013815222308039665
2023-01-22 17:38:23.528576: step: 232/529, loss: 0.005068039521574974
2023-01-22 17:38:24.662286: step: 236/529, loss: 0.003798120655119419
2023-01-22 17:38:25.779372: step: 240/529, loss: 0.01475275494158268
2023-01-22 17:38:26.885461: step: 244/529, loss: 0.004754318855702877
2023-01-22 17:38:27.993273: step: 248/529, loss: 0.014115816913545132
2023-01-22 17:38:29.131343: step: 252/529, loss: 0.0043961177580058575
2023-01-22 17:38:30.229212: step: 256/529, loss: 0.05555802583694458
2023-01-22 17:38:31.339920: step: 260/529, loss: 0.005500257946550846
2023-01-22 17:38:32.461915: step: 264/529, loss: 0.00768198212608695
2023-01-22 17:38:33.566847: step: 268/529, loss: 0.0022405358031392097
2023-01-22 17:38:34.695172: step: 272/529, loss: 0.0062119620852172375
2023-01-22 17:38:35.804118: step: 276/529, loss: 0.008880898356437683
2023-01-22 17:38:36.936963: step: 280/529, loss: 0.0029047697316855192
2023-01-22 17:38:38.027122: step: 284/529, loss: 0.001257889554835856
2023-01-22 17:38:39.128999: step: 288/529, loss: 0.008901875466108322
2023-01-22 17:38:40.254434: step: 292/529, loss: 0.00875263661146164
2023-01-22 17:38:41.376491: step: 296/529, loss: 0.003783109365031123
2023-01-22 17:38:42.496252: step: 300/529, loss: 0.01430480182170868
2023-01-22 17:38:43.585803: step: 304/529, loss: 0.014848808757960796
2023-01-22 17:38:44.718865: step: 308/529, loss: 0.04041906073689461
2023-01-22 17:38:45.809589: step: 312/529, loss: 0.005450076889246702
2023-01-22 17:38:46.920656: step: 316/529, loss: 0.00969383679330349
2023-01-22 17:38:48.008993: step: 320/529, loss: 0.017713718116283417
2023-01-22 17:38:49.120479: step: 324/529, loss: 0.0012562504271045327
2023-01-22 17:38:50.245958: step: 328/529, loss: 0.004226832650601864
2023-01-22 17:38:51.362742: step: 332/529, loss: 0.0089768311008811
2023-01-22 17:38:52.454816: step: 336/529, loss: 0.008501342497766018
2023-01-22 17:38:53.583778: step: 340/529, loss: 0.006809744518250227
2023-01-22 17:38:54.711750: step: 344/529, loss: 0.02093273214995861
2023-01-22 17:38:55.820071: step: 348/529, loss: 0.004513650666922331
2023-01-22 17:38:56.924484: step: 352/529, loss: 0.047725610435009
2023-01-22 17:38:58.043235: step: 356/529, loss: 0.012137938290834427
2023-01-22 17:38:59.159887: step: 360/529, loss: 0.05070371925830841
2023-01-22 17:39:00.263773: step: 364/529, loss: 0.006101368926465511
2023-01-22 17:39:01.371118: step: 368/529, loss: 0.008855664171278477
2023-01-22 17:39:02.477511: step: 372/529, loss: 0.013434840366244316
2023-01-22 17:39:03.584961: step: 376/529, loss: 0.011459002271294594
2023-01-22 17:39:04.696998: step: 380/529, loss: 0.008011535741388798
2023-01-22 17:39:05.798570: step: 384/529, loss: 0.0021826692391186953
2023-01-22 17:39:06.919041: step: 388/529, loss: 0.01060234010219574
2023-01-22 17:39:08.036697: step: 392/529, loss: 0.012082225643098354
2023-01-22 17:39:09.158584: step: 396/529, loss: 0.00652723666280508
2023-01-22 17:39:10.279745: step: 400/529, loss: 0.008234438486397266
2023-01-22 17:39:11.403412: step: 404/529, loss: 0.009681366384029388
2023-01-22 17:39:12.512169: step: 408/529, loss: 0.014691675081849098
2023-01-22 17:39:13.612849: step: 412/529, loss: 0.007199740037322044
2023-01-22 17:39:14.715884: step: 416/529, loss: 0.009227920323610306
2023-01-22 17:39:15.804929: step: 420/529, loss: 0.0388481430709362
2023-01-22 17:39:16.945557: step: 424/529, loss: 0.004231669940054417
2023-01-22 17:39:18.052055: step: 428/529, loss: 0.013324777595698833
2023-01-22 17:39:19.153469: step: 432/529, loss: 0.007496025413274765
2023-01-22 17:39:20.250188: step: 436/529, loss: 0.008432712405920029
2023-01-22 17:39:21.370746: step: 440/529, loss: 0.007808873429894447
2023-01-22 17:39:22.471442: step: 444/529, loss: 0.0038969856686890125
2023-01-22 17:39:23.604249: step: 448/529, loss: 0.004537766333669424
2023-01-22 17:39:24.738201: step: 452/529, loss: 0.009573286399245262
2023-01-22 17:39:25.829052: step: 456/529, loss: 0.0009919755393639207
2023-01-22 17:39:26.943060: step: 460/529, loss: 0.025337519124150276
2023-01-22 17:39:28.046695: step: 464/529, loss: 0.0064736115746200085
2023-01-22 17:39:29.153121: step: 468/529, loss: 0.0006390097551047802
2023-01-22 17:39:30.266201: step: 472/529, loss: 0.009323996491730213
2023-01-22 17:39:31.367001: step: 476/529, loss: 0.015452204272150993
2023-01-22 17:39:32.493597: step: 480/529, loss: 0.009421534836292267
2023-01-22 17:39:33.604258: step: 484/529, loss: 0.013899240642786026
2023-01-22 17:39:34.721513: step: 488/529, loss: 0.011518577113747597
2023-01-22 17:39:35.828497: step: 492/529, loss: 0.003829505294561386
2023-01-22 17:39:36.944054: step: 496/529, loss: 0.013258215971291065
2023-01-22 17:39:38.051771: step: 500/529, loss: 0.005263965111225843
2023-01-22 17:39:39.167826: step: 504/529, loss: 0.004052682314068079
2023-01-22 17:39:40.279474: step: 508/529, loss: 0.0056071230210363865
2023-01-22 17:39:41.426192: step: 512/529, loss: 0.004304805770516396
2023-01-22 17:39:42.539567: step: 516/529, loss: 0.0063183666206896305
2023-01-22 17:39:43.659991: step: 520/529, loss: 0.002637613797560334
2023-01-22 17:39:44.783229: step: 524/529, loss: 0.059482354670763016
2023-01-22 17:39:45.886291: step: 528/529, loss: 0.006300800479948521
2023-01-22 17:39:47.001809: step: 532/529, loss: 0.007320732809603214
2023-01-22 17:39:48.082461: step: 536/529, loss: 0.005531124770641327
2023-01-22 17:39:49.212178: step: 540/529, loss: 0.0034939455799758434
2023-01-22 17:39:50.334118: step: 544/529, loss: 0.015622791834175587
2023-01-22 17:39:51.429953: step: 548/529, loss: 0.005549120716750622
2023-01-22 17:39:52.521211: step: 552/529, loss: 0.016137877479195595
2023-01-22 17:39:53.620030: step: 556/529, loss: 0.0037536765448749065
2023-01-22 17:39:54.717359: step: 560/529, loss: 0.045435480773448944
2023-01-22 17:39:55.814068: step: 564/529, loss: 0.0032697119750082493
2023-01-22 17:39:56.927094: step: 568/529, loss: 0.0029958945233374834
2023-01-22 17:39:58.050880: step: 572/529, loss: 0.006128557026386261
2023-01-22 17:39:59.196319: step: 576/529, loss: 0.01146414503455162
2023-01-22 17:40:00.310032: step: 580/529, loss: 0.011514389887452126
2023-01-22 17:40:01.428735: step: 584/529, loss: 0.010104053653776646
2023-01-22 17:40:02.529614: step: 588/529, loss: 0.0045713214203715324
2023-01-22 17:40:03.642596: step: 592/529, loss: 0.0031343260779976845
2023-01-22 17:40:04.735608: step: 596/529, loss: 0.0013217005180194974
2023-01-22 17:40:05.844933: step: 600/529, loss: 0.0084649957716465
2023-01-22 17:40:06.958836: step: 604/529, loss: 0.002616363810375333
2023-01-22 17:40:08.065682: step: 608/529, loss: 0.006268291734158993
2023-01-22 17:40:09.178769: step: 612/529, loss: 0.01747487485408783
2023-01-22 17:40:10.287335: step: 616/529, loss: 0.003503649728372693
2023-01-22 17:40:11.386289: step: 620/529, loss: 0.008101007901132107
2023-01-22 17:40:12.489178: step: 624/529, loss: 0.004939237143844366
2023-01-22 17:40:13.577482: step: 628/529, loss: 0.0021369410678744316
2023-01-22 17:40:14.673569: step: 632/529, loss: 0.011247859336435795
2023-01-22 17:40:15.794599: step: 636/529, loss: 0.0004374111595097929
2023-01-22 17:40:16.933567: step: 640/529, loss: 0.010549647733569145
2023-01-22 17:40:18.032547: step: 644/529, loss: 0.015212802216410637
2023-01-22 17:40:19.143765: step: 648/529, loss: 0.006264748051762581
2023-01-22 17:40:20.265910: step: 652/529, loss: 0.02324860729277134
2023-01-22 17:40:21.372773: step: 656/529, loss: 0.038062259554862976
2023-01-22 17:40:22.488947: step: 660/529, loss: 0.0011836693156510592
2023-01-22 17:40:23.614778: step: 664/529, loss: 0.024853048846125603
2023-01-22 17:40:24.715801: step: 668/529, loss: 0.005200129467993975
2023-01-22 17:40:25.827579: step: 672/529, loss: 0.034896500408649445
2023-01-22 17:40:26.931720: step: 676/529, loss: 0.007174786180257797
2023-01-22 17:40:28.032381: step: 680/529, loss: 0.010199270211160183
2023-01-22 17:40:29.131224: step: 684/529, loss: 0.01871129311621189
2023-01-22 17:40:30.235495: step: 688/529, loss: 0.003652912098914385
2023-01-22 17:40:31.351657: step: 692/529, loss: 0.002312375232577324
2023-01-22 17:40:32.463417: step: 696/529, loss: 0.004668534733355045
2023-01-22 17:40:33.586776: step: 700/529, loss: 0.004981716629117727
2023-01-22 17:40:34.676751: step: 704/529, loss: 0.005026285070925951
2023-01-22 17:40:35.772198: step: 708/529, loss: 0.009788201190531254
2023-01-22 17:40:36.912010: step: 712/529, loss: 0.00438581220805645
2023-01-22 17:40:38.025795: step: 716/529, loss: 0.011837158352136612
2023-01-22 17:40:39.132310: step: 720/529, loss: 0.007928390987217426
2023-01-22 17:40:40.256113: step: 724/529, loss: 0.00782644934952259
2023-01-22 17:40:41.354439: step: 728/529, loss: 0.002891362411901355
2023-01-22 17:40:42.458801: step: 732/529, loss: 0.006322226021438837
2023-01-22 17:40:43.567538: step: 736/529, loss: 0.009860877878963947
2023-01-22 17:40:44.690110: step: 740/529, loss: 0.006312456447631121
2023-01-22 17:40:45.812823: step: 744/529, loss: 0.00543206324800849
2023-01-22 17:40:46.914855: step: 748/529, loss: 0.006809452082961798
2023-01-22 17:40:48.011022: step: 752/529, loss: 0.0028538559563457966
2023-01-22 17:40:49.142154: step: 756/529, loss: 0.046533554792404175
2023-01-22 17:40:50.249272: step: 760/529, loss: 0.025042230263352394
2023-01-22 17:40:51.359189: step: 764/529, loss: 0.00444047013297677
2023-01-22 17:40:52.457648: step: 768/529, loss: 0.061612099409103394
2023-01-22 17:40:53.571860: step: 772/529, loss: 0.03046591766178608
2023-01-22 17:40:54.712005: step: 776/529, loss: 0.010338617488741875
2023-01-22 17:40:55.835236: step: 780/529, loss: 0.0014948428142815828
2023-01-22 17:40:56.928058: step: 784/529, loss: 0.01369453314691782
2023-01-22 17:40:58.051524: step: 788/529, loss: 0.015225487761199474
2023-01-22 17:40:59.161076: step: 792/529, loss: 0.013376264832913876
2023-01-22 17:41:00.291421: step: 796/529, loss: 0.00604973454028368
2023-01-22 17:41:01.423017: step: 800/529, loss: 0.00472157122567296
2023-01-22 17:41:02.513765: step: 804/529, loss: 0.006451881490647793
2023-01-22 17:41:03.617467: step: 808/529, loss: 0.005709907505661249
2023-01-22 17:41:04.716602: step: 812/529, loss: 0.018158137798309326
2023-01-22 17:41:05.797513: step: 816/529, loss: 0.011198919266462326
2023-01-22 17:41:06.901356: step: 820/529, loss: 0.004058819729834795
2023-01-22 17:41:08.012277: step: 824/529, loss: 0.004995932802557945
2023-01-22 17:41:09.139577: step: 828/529, loss: 0.009096013382077217
2023-01-22 17:41:10.230964: step: 832/529, loss: 0.007504155859351158
2023-01-22 17:41:11.335266: step: 836/529, loss: 0.025504272431135178
2023-01-22 17:41:12.452542: step: 840/529, loss: 0.09928291290998459
2023-01-22 17:41:13.536122: step: 844/529, loss: 0.007400807924568653
2023-01-22 17:41:14.663439: step: 848/529, loss: 0.006773261819034815
2023-01-22 17:41:15.772633: step: 852/529, loss: 0.003998809959739447
2023-01-22 17:41:16.879920: step: 856/529, loss: 0.015541048720479012
2023-01-22 17:41:17.992598: step: 860/529, loss: 0.007549144793301821
2023-01-22 17:41:19.093032: step: 864/529, loss: 0.008947948925197124
2023-01-22 17:41:20.171557: step: 868/529, loss: 0.005314873997122049
2023-01-22 17:41:21.259478: step: 872/529, loss: 0.00538831390440464
2023-01-22 17:41:22.373202: step: 876/529, loss: 0.007756073493510485
2023-01-22 17:41:23.482178: step: 880/529, loss: 0.009078223258256912
2023-01-22 17:41:24.593109: step: 884/529, loss: 0.0029895331244915724
2023-01-22 17:41:25.682877: step: 888/529, loss: 0.008503108285367489
2023-01-22 17:41:26.800067: step: 892/529, loss: 0.022897157818078995
2023-01-22 17:41:27.881200: step: 896/529, loss: 0.004998879972845316
2023-01-22 17:41:28.981858: step: 900/529, loss: 0.0013441942865028977
2023-01-22 17:41:30.090520: step: 904/529, loss: 0.004468087572604418
2023-01-22 17:41:31.218250: step: 908/529, loss: 0.026423035189509392
2023-01-22 17:41:32.349174: step: 912/529, loss: 0.02764108218252659
2023-01-22 17:41:33.443918: step: 916/529, loss: 0.005134744103997946
2023-01-22 17:41:34.573810: step: 920/529, loss: 0.013258428312838078
2023-01-22 17:41:35.686322: step: 924/529, loss: 0.027975497767329216
2023-01-22 17:41:36.809186: step: 928/529, loss: 0.007095934823155403
2023-01-22 17:41:37.915875: step: 932/529, loss: 0.03519057482481003
2023-01-22 17:41:39.047612: step: 936/529, loss: 0.009730612859129906
2023-01-22 17:41:40.152616: step: 940/529, loss: 0.007331518922001123
2023-01-22 17:41:41.255875: step: 944/529, loss: 0.011907260864973068
2023-01-22 17:41:42.378556: step: 948/529, loss: 0.01262362115085125
2023-01-22 17:41:43.465349: step: 952/529, loss: 0.018554141744971275
2023-01-22 17:41:44.563503: step: 956/529, loss: 0.00550667941570282
2023-01-22 17:41:45.700510: step: 960/529, loss: 0.003585243131965399
2023-01-22 17:41:46.824609: step: 964/529, loss: 0.005864799953997135
2023-01-22 17:41:47.930462: step: 968/529, loss: 0.025149207562208176
2023-01-22 17:41:49.031390: step: 972/529, loss: 0.02100159041583538
2023-01-22 17:41:50.149545: step: 976/529, loss: 0.019026894122362137
2023-01-22 17:41:51.268066: step: 980/529, loss: 0.008776872418820858
2023-01-22 17:41:52.374696: step: 984/529, loss: 0.013381061144173145
2023-01-22 17:41:53.492970: step: 988/529, loss: 0.06794261187314987
2023-01-22 17:41:54.581744: step: 992/529, loss: 0.01260827761143446
2023-01-22 17:41:55.671600: step: 996/529, loss: 0.023017434403300285
2023-01-22 17:41:56.776147: step: 1000/529, loss: 0.012222422286868095
2023-01-22 17:41:57.886779: step: 1004/529, loss: 0.016505379229784012
2023-01-22 17:41:58.987400: step: 1008/529, loss: 0.006892653647810221
2023-01-22 17:42:00.080762: step: 1012/529, loss: 0.00251356465741992
2023-01-22 17:42:01.180461: step: 1016/529, loss: 0.004167493432760239
2023-01-22 17:42:02.306792: step: 1020/529, loss: 0.0063850898295640945
2023-01-22 17:42:03.426331: step: 1024/529, loss: 0.007139180321246386
2023-01-22 17:42:04.531898: step: 1028/529, loss: 0.017031438648700714
2023-01-22 17:42:05.633068: step: 1032/529, loss: 0.014146663248538971
2023-01-22 17:42:06.766754: step: 1036/529, loss: 0.008736012503504753
2023-01-22 17:42:07.877493: step: 1040/529, loss: 0.007704694755375385
2023-01-22 17:42:08.976277: step: 1044/529, loss: 0.004681042395532131
2023-01-22 17:42:10.077933: step: 1048/529, loss: 0.021567480638623238
2023-01-22 17:42:11.180355: step: 1052/529, loss: 0.007028264459222555
2023-01-22 17:42:12.284769: step: 1056/529, loss: 0.011092476546764374
2023-01-22 17:42:13.390478: step: 1060/529, loss: 0.0042023384012281895
2023-01-22 17:42:14.496580: step: 1064/529, loss: 0.0019346660701557994
2023-01-22 17:42:15.579568: step: 1068/529, loss: 0.008626299910247326
2023-01-22 17:42:16.694802: step: 1072/529, loss: 0.016826190054416656
2023-01-22 17:42:17.782573: step: 1076/529, loss: 0.0037418168503791094
2023-01-22 17:42:18.902760: step: 1080/529, loss: 0.005875915288925171
2023-01-22 17:42:20.011787: step: 1084/529, loss: 0.01041338685899973
2023-01-22 17:42:21.132190: step: 1088/529, loss: 0.014791525900363922
2023-01-22 17:42:22.247749: step: 1092/529, loss: 0.010074746794998646
2023-01-22 17:42:23.369106: step: 1096/529, loss: 0.019177494570612907
2023-01-22 17:42:24.473714: step: 1100/529, loss: 0.0068747433833777905
2023-01-22 17:42:25.602056: step: 1104/529, loss: 0.012249616906046867
2023-01-22 17:42:26.723546: step: 1108/529, loss: 0.033043939620256424
2023-01-22 17:42:27.808592: step: 1112/529, loss: 0.010264253243803978
2023-01-22 17:42:28.910790: step: 1116/529, loss: 0.012172569520771503
2023-01-22 17:42:30.015991: step: 1120/529, loss: 0.0053809951059520245
2023-01-22 17:42:31.126060: step: 1124/529, loss: 0.01343944389373064
2023-01-22 17:42:32.271533: step: 1128/529, loss: 0.0034981858916580677
2023-01-22 17:42:33.375148: step: 1132/529, loss: 0.010491401888430119
2023-01-22 17:42:34.506646: step: 1136/529, loss: 0.008148564957082272
2023-01-22 17:42:35.637904: step: 1140/529, loss: 0.07247122377157211
2023-01-22 17:42:36.732278: step: 1144/529, loss: 0.08388296514749527
2023-01-22 17:42:37.835780: step: 1148/529, loss: 0.0010937309125438333
2023-01-22 17:42:38.961803: step: 1152/529, loss: 0.008527462370693684
2023-01-22 17:42:40.090610: step: 1156/529, loss: 0.008171889930963516
2023-01-22 17:42:41.209231: step: 1160/529, loss: 0.029753003269433975
2023-01-22 17:42:42.326925: step: 1164/529, loss: 0.03420832380652428
2023-01-22 17:42:43.442605: step: 1168/529, loss: 0.00933653861284256
2023-01-22 17:42:44.549607: step: 1172/529, loss: 0.008758390322327614
2023-01-22 17:42:45.688141: step: 1176/529, loss: 0.026053432375192642
2023-01-22 17:42:46.782991: step: 1180/529, loss: 0.004718575160950422
2023-01-22 17:42:47.893423: step: 1184/529, loss: 0.0029533659107983112
2023-01-22 17:42:49.003960: step: 1188/529, loss: 0.01955961436033249
2023-01-22 17:42:50.100925: step: 1192/529, loss: 0.006807827390730381
2023-01-22 17:42:51.222412: step: 1196/529, loss: 0.004869374912232161
2023-01-22 17:42:52.315434: step: 1200/529, loss: 0.008376733399927616
2023-01-22 17:42:53.440614: step: 1204/529, loss: 0.02058805711567402
2023-01-22 17:42:54.535579: step: 1208/529, loss: 0.008160156197845936
2023-01-22 17:42:55.670810: step: 1212/529, loss: 0.027654292061924934
2023-01-22 17:42:56.760107: step: 1216/529, loss: 0.04118898883461952
2023-01-22 17:42:57.865172: step: 1220/529, loss: 0.05720268562436104
2023-01-22 17:42:58.995448: step: 1224/529, loss: 0.021895918995141983
2023-01-22 17:43:00.095202: step: 1228/529, loss: 0.017520206049084663
2023-01-22 17:43:01.211380: step: 1232/529, loss: 0.005347408354282379
2023-01-22 17:43:02.300547: step: 1236/529, loss: 0.004857045132666826
2023-01-22 17:43:03.386976: step: 1240/529, loss: 0.0069295079447329044
2023-01-22 17:43:04.496740: step: 1244/529, loss: 0.008177652023732662
2023-01-22 17:43:05.588279: step: 1248/529, loss: 0.006703739985823631
2023-01-22 17:43:06.668620: step: 1252/529, loss: 0.006869058590382338
2023-01-22 17:43:07.771757: step: 1256/529, loss: 0.0031312317587435246
2023-01-22 17:43:08.866008: step: 1260/529, loss: 0.013160737231373787
2023-01-22 17:43:09.968597: step: 1264/529, loss: 0.014743266627192497
2023-01-22 17:43:11.092639: step: 1268/529, loss: 0.006623721681535244
2023-01-22 17:43:12.205286: step: 1272/529, loss: 0.004435283597558737
2023-01-22 17:43:13.305920: step: 1276/529, loss: 0.012515711598098278
2023-01-22 17:43:14.395171: step: 1280/529, loss: 0.006792957428842783
2023-01-22 17:43:15.510216: step: 1284/529, loss: 0.00042178278090432286
2023-01-22 17:43:16.632275: step: 1288/529, loss: 0.0008767183753661811
2023-01-22 17:43:17.745597: step: 1292/529, loss: 0.0032390186097472906
2023-01-22 17:43:18.843472: step: 1296/529, loss: 0.007119619753211737
2023-01-22 17:43:19.958251: step: 1300/529, loss: 0.013750935904681683
2023-01-22 17:43:21.089457: step: 1304/529, loss: 0.01803460158407688
2023-01-22 17:43:22.181174: step: 1308/529, loss: 0.0052917650900781155
2023-01-22 17:43:23.271723: step: 1312/529, loss: 0.0075826882384717464
2023-01-22 17:43:24.409526: step: 1316/529, loss: 0.000660874240566045
2023-01-22 17:43:25.516632: step: 1320/529, loss: 0.008228098042309284
2023-01-22 17:43:26.622840: step: 1324/529, loss: 0.0008065270376391709
2023-01-22 17:43:27.720713: step: 1328/529, loss: 0.002440697979182005
2023-01-22 17:43:28.824899: step: 1332/529, loss: 0.03231841325759888
2023-01-22 17:43:29.940195: step: 1336/529, loss: 0.0051038372330367565
2023-01-22 17:43:31.027826: step: 1340/529, loss: 0.014039299450814724
2023-01-22 17:43:32.120909: step: 1344/529, loss: 0.004389962647110224
2023-01-22 17:43:33.239073: step: 1348/529, loss: 0.04818470776081085
2023-01-22 17:43:34.332313: step: 1352/529, loss: 0.024557804688811302
2023-01-22 17:43:35.417000: step: 1356/529, loss: 0.0022025639191269875
2023-01-22 17:43:36.533549: step: 1360/529, loss: 0.005134823266416788
2023-01-22 17:43:37.630359: step: 1364/529, loss: 0.002588310744613409
2023-01-22 17:43:38.730072: step: 1368/529, loss: 0.008885812014341354
2023-01-22 17:43:39.838563: step: 1372/529, loss: 0.012739752419292927
2023-01-22 17:43:40.960337: step: 1376/529, loss: 0.013755069114267826
2023-01-22 17:43:42.072786: step: 1380/529, loss: 0.005059142131358385
2023-01-22 17:43:43.189288: step: 1384/529, loss: 0.011433500796556473
2023-01-22 17:43:44.303912: step: 1388/529, loss: 0.016240177676081657
2023-01-22 17:43:45.417810: step: 1392/529, loss: 0.005287688225507736
2023-01-22 17:43:46.517016: step: 1396/529, loss: 0.011790314689278603
2023-01-22 17:43:47.636293: step: 1400/529, loss: 0.008412167429924011
2023-01-22 17:43:48.750967: step: 1404/529, loss: 0.02273290604352951
2023-01-22 17:43:49.859314: step: 1408/529, loss: 0.011153369210660458
2023-01-22 17:43:50.959077: step: 1412/529, loss: 0.0152726536616683
2023-01-22 17:43:52.035820: step: 1416/529, loss: 0.017236515879631042
2023-01-22 17:43:53.152987: step: 1420/529, loss: 0.04717542231082916
2023-01-22 17:43:54.261898: step: 1424/529, loss: 0.00706536415964365
2023-01-22 17:43:55.356199: step: 1428/529, loss: 0.02329491265118122
2023-01-22 17:43:56.455309: step: 1432/529, loss: 0.061748966574668884
2023-01-22 17:43:57.580640: step: 1436/529, loss: 0.0029622793663293123
2023-01-22 17:43:58.676754: step: 1440/529, loss: 0.007936941459774971
2023-01-22 17:43:59.801004: step: 1444/529, loss: 0.009801620617508888
2023-01-22 17:44:00.895179: step: 1448/529, loss: 0.0049109929241240025
2023-01-22 17:44:02.001228: step: 1452/529, loss: 0.00910202506929636
2023-01-22 17:44:03.116510: step: 1456/529, loss: 0.058633070439100266
2023-01-22 17:44:04.216676: step: 1460/529, loss: 0.04007187858223915
2023-01-22 17:44:05.348210: step: 1464/529, loss: 0.02339683473110199
2023-01-22 17:44:06.453429: step: 1468/529, loss: 0.00334138423204422
2023-01-22 17:44:07.559923: step: 1472/529, loss: 0.019261814653873444
2023-01-22 17:44:08.699156: step: 1476/529, loss: 0.014432044699788094
2023-01-22 17:44:09.790226: step: 1480/529, loss: 0.007782378233969212
2023-01-22 17:44:10.893511: step: 1484/529, loss: 0.03022390976548195
2023-01-22 17:44:12.005579: step: 1488/529, loss: 0.05246228724718094
2023-01-22 17:44:13.117177: step: 1492/529, loss: 0.004392694216221571
2023-01-22 17:44:14.195710: step: 1496/529, loss: 0.02190680056810379
2023-01-22 17:44:15.298955: step: 1500/529, loss: 0.0034517559688538313
2023-01-22 17:44:16.419601: step: 1504/529, loss: 0.027647580951452255
2023-01-22 17:44:17.544122: step: 1508/529, loss: 0.009321940131485462
2023-01-22 17:44:18.654705: step: 1512/529, loss: 0.0009504520567134023
2023-01-22 17:44:19.799577: step: 1516/529, loss: 0.009871454909443855
2023-01-22 17:44:20.903795: step: 1520/529, loss: 0.005512171890586615
2023-01-22 17:44:22.008126: step: 1524/529, loss: 0.008579273708164692
2023-01-22 17:44:23.117165: step: 1528/529, loss: 0.0034248565789312124
2023-01-22 17:44:24.244446: step: 1532/529, loss: 0.01708158291876316
2023-01-22 17:44:25.342726: step: 1536/529, loss: 0.007246970199048519
2023-01-22 17:44:26.430117: step: 1540/529, loss: 0.04061109572649002
2023-01-22 17:44:27.543402: step: 1544/529, loss: 0.023712685331702232
2023-01-22 17:44:28.666855: step: 1548/529, loss: 0.004205163102596998
2023-01-22 17:44:29.786138: step: 1552/529, loss: 0.003635575994849205
2023-01-22 17:44:30.893159: step: 1556/529, loss: 0.010479738935828209
2023-01-22 17:44:32.014186: step: 1560/529, loss: 0.007649003528058529
2023-01-22 17:44:33.114356: step: 1564/529, loss: 0.0029864495154470205
2023-01-22 17:44:34.260518: step: 1568/529, loss: 0.006535951513797045
2023-01-22 17:44:35.378109: step: 1572/529, loss: 0.032627858221530914
2023-01-22 17:44:36.497437: step: 1576/529, loss: 0.012394534423947334
2023-01-22 17:44:37.610902: step: 1580/529, loss: 0.003876542439684272
2023-01-22 17:44:38.712062: step: 1584/529, loss: 0.005604331381618977
2023-01-22 17:44:39.810945: step: 1588/529, loss: 0.008362029679119587
2023-01-22 17:44:40.902405: step: 1592/529, loss: 0.0012405200395733118
2023-01-22 17:44:42.005448: step: 1596/529, loss: 0.0321798212826252
2023-01-22 17:44:43.101847: step: 1600/529, loss: 0.0382835790514946
2023-01-22 17:44:44.208974: step: 1604/529, loss: 0.007573469076305628
2023-01-22 17:44:45.314659: step: 1608/529, loss: 0.0048532807268202305
2023-01-22 17:44:46.435743: step: 1612/529, loss: 0.008612043224275112
2023-01-22 17:44:47.541062: step: 1616/529, loss: 0.004876828286796808
2023-01-22 17:44:48.627357: step: 1620/529, loss: 0.00716797448694706
2023-01-22 17:44:49.747454: step: 1624/529, loss: 0.01805017702281475
2023-01-22 17:44:50.859075: step: 1628/529, loss: 0.00673112366348505
2023-01-22 17:44:51.969500: step: 1632/529, loss: 0.010313460603356361
2023-01-22 17:44:53.078486: step: 1636/529, loss: 0.006847405340522528
2023-01-22 17:44:54.202792: step: 1640/529, loss: 0.007045113481581211
2023-01-22 17:44:55.325467: step: 1644/529, loss: 0.0062449024990201
2023-01-22 17:44:56.450123: step: 1648/529, loss: 0.006150367669761181
2023-01-22 17:44:57.560263: step: 1652/529, loss: 0.0369860902428627
2023-01-22 17:44:58.656504: step: 1656/529, loss: 0.009792941622436047
2023-01-22 17:44:59.762317: step: 1660/529, loss: 0.002108693588525057
2023-01-22 17:45:00.877387: step: 1664/529, loss: 0.0040407944470644
2023-01-22 17:45:01.977589: step: 1668/529, loss: 0.0072971126064658165
2023-01-22 17:45:03.093314: step: 1672/529, loss: 0.006971732713282108
2023-01-22 17:45:04.200443: step: 1676/529, loss: 0.004379850812256336
2023-01-22 17:45:05.308543: step: 1680/529, loss: 0.04694787412881851
2023-01-22 17:45:06.411072: step: 1684/529, loss: 0.017130527645349503
2023-01-22 17:45:07.541425: step: 1688/529, loss: 0.022409014403820038
2023-01-22 17:45:08.654623: step: 1692/529, loss: 0.00207091448828578
2023-01-22 17:45:09.759552: step: 1696/529, loss: 0.003941686823964119
2023-01-22 17:45:10.873999: step: 1700/529, loss: 0.008076979778707027
2023-01-22 17:45:11.964862: step: 1704/529, loss: 0.005978000350296497
2023-01-22 17:45:13.047362: step: 1708/529, loss: 0.009553679265081882
2023-01-22 17:45:14.149626: step: 1712/529, loss: 0.0050934068858623505
2023-01-22 17:45:15.266289: step: 1716/529, loss: 0.02730417251586914
2023-01-22 17:45:16.386457: step: 1720/529, loss: 0.02408521994948387
2023-01-22 17:45:17.521050: step: 1724/529, loss: 0.02619338408112526
2023-01-22 17:45:18.631422: step: 1728/529, loss: 0.00833680760115385
2023-01-22 17:45:19.732002: step: 1732/529, loss: 0.06240164116024971
2023-01-22 17:45:20.852750: step: 1736/529, loss: 0.006684586405754089
2023-01-22 17:45:21.985066: step: 1740/529, loss: 0.017560744658112526
2023-01-22 17:45:23.087059: step: 1744/529, loss: 0.030718432739377022
2023-01-22 17:45:24.216982: step: 1748/529, loss: 0.00947144441306591
2023-01-22 17:45:25.307099: step: 1752/529, loss: 0.004039314109832048
2023-01-22 17:45:26.407597: step: 1756/529, loss: 0.00732135446742177
2023-01-22 17:45:27.529973: step: 1760/529, loss: 0.005373631604015827
2023-01-22 17:45:28.665305: step: 1764/529, loss: 0.028778599575161934
2023-01-22 17:45:29.751659: step: 1768/529, loss: 0.03334533050656319
2023-01-22 17:45:30.854165: step: 1772/529, loss: 0.05198327824473381
2023-01-22 17:45:31.952943: step: 1776/529, loss: 0.014782276935875416
2023-01-22 17:45:33.056261: step: 1780/529, loss: 0.014527741819620132
2023-01-22 17:45:34.169881: step: 1784/529, loss: 0.003307939739897847
2023-01-22 17:45:35.297517: step: 1788/529, loss: 0.002842556219547987
2023-01-22 17:45:36.405420: step: 1792/529, loss: 0.04601949453353882
2023-01-22 17:45:37.496894: step: 1796/529, loss: 0.004989521577954292
2023-01-22 17:45:38.592540: step: 1800/529, loss: 0.001036455505527556
2023-01-22 17:45:39.685283: step: 1804/529, loss: 0.005468796472996473
2023-01-22 17:45:40.772254: step: 1808/529, loss: 0.007337305229157209
2023-01-22 17:45:41.868947: step: 1812/529, loss: 0.0070394789800047874
2023-01-22 17:45:42.979775: step: 1816/529, loss: 0.02285398729145527
2023-01-22 17:45:44.088884: step: 1820/529, loss: 0.006979189347475767
2023-01-22 17:45:45.220849: step: 1824/529, loss: 0.0027024359442293644
2023-01-22 17:45:46.336945: step: 1828/529, loss: 0.005601800978183746
2023-01-22 17:45:47.434669: step: 1832/529, loss: 0.003892092499881983
2023-01-22 17:45:48.539760: step: 1836/529, loss: 0.003860777011141181
2023-01-22 17:45:49.651904: step: 1840/529, loss: 0.011268729344010353
2023-01-22 17:45:50.761323: step: 1844/529, loss: 0.0013628269080072641
2023-01-22 17:45:51.875193: step: 1848/529, loss: 0.003899089526385069
2023-01-22 17:45:52.987864: step: 1852/529, loss: 0.017781587317585945
2023-01-22 17:45:54.086340: step: 1856/529, loss: 0.0024549432564526796
2023-01-22 17:45:55.200939: step: 1860/529, loss: 0.0070040058344602585
2023-01-22 17:45:56.338499: step: 1864/529, loss: 0.01735086180269718
2023-01-22 17:45:57.448857: step: 1868/529, loss: 0.010106250643730164
2023-01-22 17:45:58.570639: step: 1872/529, loss: 0.009298549965023994
2023-01-22 17:45:59.675976: step: 1876/529, loss: 0.004831044003367424
2023-01-22 17:46:00.805152: step: 1880/529, loss: 0.0043725017458200455
2023-01-22 17:46:01.924841: step: 1884/529, loss: 0.004446262493729591
2023-01-22 17:46:03.045933: step: 1888/529, loss: 0.011983290314674377
2023-01-22 17:46:04.129311: step: 1892/529, loss: 0.026223337277770042
2023-01-22 17:46:05.247649: step: 1896/529, loss: 0.010880104266107082
2023-01-22 17:46:06.364169: step: 1900/529, loss: 0.010207395069301128
2023-01-22 17:46:07.473778: step: 1904/529, loss: 0.010739650577306747
2023-01-22 17:46:08.634623: step: 1908/529, loss: 0.006706821732223034
2023-01-22 17:46:09.753526: step: 1912/529, loss: 0.03068714588880539
2023-01-22 17:46:10.868353: step: 1916/529, loss: 0.020680204033851624
2023-01-22 17:46:11.956739: step: 1920/529, loss: 0.004508965648710728
2023-01-22 17:46:13.065689: step: 1924/529, loss: 0.011241476982831955
2023-01-22 17:46:14.169126: step: 1928/529, loss: 0.01198605727404356
2023-01-22 17:46:15.271405: step: 1932/529, loss: 0.005279011093080044
2023-01-22 17:46:16.386883: step: 1936/529, loss: 0.0047566844150424
2023-01-22 17:46:17.503631: step: 1940/529, loss: 0.0025826264172792435
2023-01-22 17:46:18.605495: step: 1944/529, loss: 0.02051517367362976
2023-01-22 17:46:19.720858: step: 1948/529, loss: 0.020873727276921272
2023-01-22 17:46:20.844264: step: 1952/529, loss: 0.010530680418014526
2023-01-22 17:46:21.953689: step: 1956/529, loss: 0.008664194494485855
2023-01-22 17:46:23.051669: step: 1960/529, loss: 0.003982482943683863
2023-01-22 17:46:24.173987: step: 1964/529, loss: 0.0030286768451333046
2023-01-22 17:46:25.276694: step: 1968/529, loss: 0.004773780237883329
2023-01-22 17:46:26.395460: step: 1972/529, loss: 0.028166964650154114
2023-01-22 17:46:27.504403: step: 1976/529, loss: 0.005442872177809477
2023-01-22 17:46:28.633337: step: 1980/529, loss: 0.014951172284781933
2023-01-22 17:46:29.750908: step: 1984/529, loss: 0.012404645793139935
2023-01-22 17:46:30.868462: step: 1988/529, loss: 0.002578714629635215
2023-01-22 17:46:31.983323: step: 1992/529, loss: 0.015002608299255371
2023-01-22 17:46:33.076535: step: 1996/529, loss: 0.04005063325166702
2023-01-22 17:46:34.173823: step: 2000/529, loss: 0.026735400781035423
2023-01-22 17:46:35.269877: step: 2004/529, loss: 0.002559252083301544
2023-01-22 17:46:36.355939: step: 2008/529, loss: 0.00400884822010994
2023-01-22 17:46:37.460382: step: 2012/529, loss: 0.004970897920429707
2023-01-22 17:46:38.550185: step: 2016/529, loss: 0.004061634186655283
2023-01-22 17:46:39.665707: step: 2020/529, loss: 0.025842580944299698
2023-01-22 17:46:40.791841: step: 2024/529, loss: 0.017473995685577393
2023-01-22 17:46:41.905097: step: 2028/529, loss: 0.006059217732399702
2023-01-22 17:46:43.001336: step: 2032/529, loss: 0.001296793925575912
2023-01-22 17:46:44.095101: step: 2036/529, loss: 0.010043682530522346
2023-01-22 17:46:45.234180: step: 2040/529, loss: 0.04651513323187828
2023-01-22 17:46:46.321429: step: 2044/529, loss: 0.014005985110998154
2023-01-22 17:46:47.438197: step: 2048/529, loss: 0.025531034916639328
2023-01-22 17:46:48.562209: step: 2052/529, loss: 0.007653862237930298
2023-01-22 17:46:49.688383: step: 2056/529, loss: 0.00987324956804514
2023-01-22 17:46:50.802893: step: 2060/529, loss: 0.007379939779639244
2023-01-22 17:46:51.930483: step: 2064/529, loss: 0.045019522309303284
2023-01-22 17:46:53.031509: step: 2068/529, loss: 0.013427437283098698
2023-01-22 17:46:54.148904: step: 2072/529, loss: 0.0011129326885566115
2023-01-22 17:46:55.306335: step: 2076/529, loss: 0.008066978305578232
2023-01-22 17:46:56.406064: step: 2080/529, loss: 0.002326990244910121
2023-01-22 17:46:57.517007: step: 2084/529, loss: 0.021870005875825882
2023-01-22 17:46:58.624148: step: 2088/529, loss: 0.005908648017793894
2023-01-22 17:46:59.715364: step: 2092/529, loss: 0.014179644174873829
2023-01-22 17:47:00.856316: step: 2096/529, loss: 0.002904726890847087
2023-01-22 17:47:01.963942: step: 2100/529, loss: 0.013198090717196465
2023-01-22 17:47:03.092972: step: 2104/529, loss: 0.003708828240633011
2023-01-22 17:47:04.213754: step: 2108/529, loss: 0.002924456726759672
2023-01-22 17:47:05.311294: step: 2112/529, loss: 0.0072814770974218845
2023-01-22 17:47:06.423583: step: 2116/529, loss: 0.004571731202304363
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3324190159934942, 'r': 0.3324190159934942, 'f1': 0.3324190159934942}, 'combined': 0.24494032757415363, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3758148621561247, 'r': 0.2977234622275793, 'f1': 0.33224212451483487}, 'combined': 0.20420735457984973, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3349672187967752, 'r': 0.3489506700558436, 'f1': 0.3418159909283078}, 'combined': 0.25186441436822676, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3571370338535805, 'r': 0.310096454004582, 'f1': 0.3319585416709533}, 'combined': 0.2040330548806835, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3377545312942509, 'r': 0.34288173480535905, 'f1': 0.3402988215488216}, 'combined': 0.25074650008860533, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.37008133386405523, 'r': 0.2986284010054541, 'f1': 0.3305374251665544}, 'combined': 0.2041554684852248, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35344827586206895, 'r': 0.44565217391304346, 'f1': 0.3942307692307692}, 'combined': 0.1971153846153846, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 2}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33833087822671154, 'r': 0.34667680121902134, 'f1': 0.34245299764278203}, 'combined': 0.2523337877367867, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36213467140284455, 'r': 0.29754614992320305, 'f1': 0.3266785201153037}, 'combined': 0.20177202713004055, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 3
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 17:49:35.019414: step: 4/529, loss: 0.0059234509244561195
2023-01-22 17:49:36.143947: step: 8/529, loss: 0.047783784568309784
2023-01-22 17:49:37.245422: step: 12/529, loss: 0.004723140504211187
2023-01-22 17:49:38.328844: step: 16/529, loss: 0.00337740289978683
2023-01-22 17:49:39.412952: step: 20/529, loss: 0.00963030755519867
2023-01-22 17:49:40.512542: step: 24/529, loss: 0.010311869904398918
2023-01-22 17:49:41.596192: step: 28/529, loss: 0.002681407844647765
2023-01-22 17:49:42.723248: step: 32/529, loss: 0.0065170335583388805
2023-01-22 17:49:43.825935: step: 36/529, loss: 0.06748323887586594
2023-01-22 17:49:44.939836: step: 40/529, loss: 0.004744097124785185
2023-01-22 17:49:46.052518: step: 44/529, loss: 0.006203114055097103
2023-01-22 17:49:47.150302: step: 48/529, loss: 0.029021665453910828
2023-01-22 17:49:48.243699: step: 52/529, loss: 0.007526801899075508
2023-01-22 17:49:49.360430: step: 56/529, loss: 0.009098030626773834
2023-01-22 17:49:50.469180: step: 60/529, loss: 0.006834360305219889
2023-01-22 17:49:51.607577: step: 64/529, loss: 0.003728195559233427
2023-01-22 17:49:52.708058: step: 68/529, loss: 0.04285121709108353
2023-01-22 17:49:53.817433: step: 72/529, loss: 0.010816344991326332
2023-01-22 17:49:54.916081: step: 76/529, loss: 0.00485533382743597
2023-01-22 17:49:56.014213: step: 80/529, loss: 0.004176477901637554
2023-01-22 17:49:57.136180: step: 84/529, loss: 0.01737510971724987
2023-01-22 17:49:58.245589: step: 88/529, loss: 0.019195539876818657
2023-01-22 17:49:59.359984: step: 92/529, loss: 0.0071071540005505085
2023-01-22 17:50:00.494807: step: 96/529, loss: 0.0227601770311594
2023-01-22 17:50:01.585915: step: 100/529, loss: 0.009289607405662537
2023-01-22 17:50:02.695891: step: 104/529, loss: 0.0017559470143169165
2023-01-22 17:50:03.796283: step: 108/529, loss: 0.005618312396109104
2023-01-22 17:50:04.895868: step: 112/529, loss: 0.001144988345913589
2023-01-22 17:50:05.994024: step: 116/529, loss: 0.01226304192095995
2023-01-22 17:50:07.100654: step: 120/529, loss: 0.029561394825577736
2023-01-22 17:50:08.247226: step: 124/529, loss: 0.009273933246731758
2023-01-22 17:50:09.367946: step: 128/529, loss: 0.010077221319079399
2023-01-22 17:50:10.478963: step: 132/529, loss: 0.026895513758063316
2023-01-22 17:50:11.584568: step: 136/529, loss: 0.006875411607325077
2023-01-22 17:50:12.701615: step: 140/529, loss: 0.003585230093449354
2023-01-22 17:50:13.812991: step: 144/529, loss: 0.006437341682612896
2023-01-22 17:50:14.937112: step: 148/529, loss: 0.0018976558931171894
2023-01-22 17:50:16.059596: step: 152/529, loss: 0.007295002229511738
2023-01-22 17:50:17.159765: step: 156/529, loss: 0.008417168632149696
2023-01-22 17:50:18.274804: step: 160/529, loss: 0.009102290496230125
2023-01-22 17:50:19.397343: step: 164/529, loss: 0.035625748336315155
2023-01-22 17:50:20.507217: step: 168/529, loss: 0.004699665121734142
2023-01-22 17:50:21.625043: step: 172/529, loss: 0.0003505774075165391
2023-01-22 17:50:22.727734: step: 176/529, loss: 0.0005696056759916246
2023-01-22 17:50:23.862191: step: 180/529, loss: 0.03324306011199951
2023-01-22 17:50:24.978549: step: 184/529, loss: 0.0051491158083081245
2023-01-22 17:50:26.075684: step: 188/529, loss: 0.00684776296839118
2023-01-22 17:50:27.176658: step: 192/529, loss: 0.009571096859872341
2023-01-22 17:50:28.283145: step: 196/529, loss: 0.004485643468797207
2023-01-22 17:50:29.378845: step: 200/529, loss: 0.011714925058186054
2023-01-22 17:50:30.476585: step: 204/529, loss: 0.022249605506658554
2023-01-22 17:50:31.571125: step: 208/529, loss: 0.023388579487800598
2023-01-22 17:50:32.690288: step: 212/529, loss: 0.001695031300187111
2023-01-22 17:50:33.775657: step: 216/529, loss: 0.006146294996142387
2023-01-22 17:50:34.875826: step: 220/529, loss: 0.007970155216753483
2023-01-22 17:50:35.990041: step: 224/529, loss: 0.006544598378241062
2023-01-22 17:50:37.102447: step: 228/529, loss: 0.024190906435251236
2023-01-22 17:50:38.191797: step: 232/529, loss: 0.007148230914026499
2023-01-22 17:50:39.299009: step: 236/529, loss: 0.006680634804069996
2023-01-22 17:50:40.411679: step: 240/529, loss: 0.008441604673862457
2023-01-22 17:50:41.513554: step: 244/529, loss: 0.0035221076104789972
2023-01-22 17:50:42.609404: step: 248/529, loss: 0.002338084625080228
2023-01-22 17:50:43.735115: step: 252/529, loss: 0.0025429283268749714
2023-01-22 17:50:44.860401: step: 256/529, loss: 0.0032992931082844734
2023-01-22 17:50:45.997632: step: 260/529, loss: 0.00871511921286583
2023-01-22 17:50:47.093965: step: 264/529, loss: 0.00823371671140194
2023-01-22 17:50:48.200419: step: 268/529, loss: 0.027829378843307495
2023-01-22 17:50:49.295969: step: 272/529, loss: 0.010504011996090412
2023-01-22 17:50:50.387185: step: 276/529, loss: 0.0091888178139925
2023-01-22 17:50:51.517888: step: 280/529, loss: 0.019369134679436684
2023-01-22 17:50:52.606782: step: 284/529, loss: 0.020222444087266922
2023-01-22 17:50:53.704729: step: 288/529, loss: 0.009242132306098938
2023-01-22 17:50:54.817974: step: 292/529, loss: 0.0031274028588086367
2023-01-22 17:50:55.907331: step: 296/529, loss: 0.0022235142532736063
2023-01-22 17:50:57.025398: step: 300/529, loss: 0.01660131849348545
2023-01-22 17:50:58.151411: step: 304/529, loss: 0.0023003313690423965
2023-01-22 17:50:59.255586: step: 308/529, loss: 0.006474396679550409
2023-01-22 17:51:00.373260: step: 312/529, loss: 0.0065093738958239555
2023-01-22 17:51:01.471214: step: 316/529, loss: 0.007061909418553114
2023-01-22 17:51:02.645938: step: 320/529, loss: 0.04676046967506409
2023-01-22 17:51:03.782672: step: 324/529, loss: 0.009776496328413486
2023-01-22 17:51:04.867389: step: 328/529, loss: 0.001634639105759561
2023-01-22 17:51:05.978336: step: 332/529, loss: 0.008967863395810127
2023-01-22 17:51:07.093724: step: 336/529, loss: 0.01077272742986679
2023-01-22 17:51:08.188498: step: 340/529, loss: 0.010361066088080406
2023-01-22 17:51:09.284499: step: 344/529, loss: 0.006212722044438124
2023-01-22 17:51:10.394655: step: 348/529, loss: 0.0037770308554172516
2023-01-22 17:51:11.519827: step: 352/529, loss: 0.003101285081356764
2023-01-22 17:51:12.619793: step: 356/529, loss: 0.007602039258927107
2023-01-22 17:51:13.742052: step: 360/529, loss: 0.002098478376865387
2023-01-22 17:51:14.868066: step: 364/529, loss: 0.014492744579911232
2023-01-22 17:51:16.019114: step: 368/529, loss: 0.017801519483327866
2023-01-22 17:51:17.120688: step: 372/529, loss: 0.01312556304037571
2023-01-22 17:51:18.236531: step: 376/529, loss: 0.007660937495529652
2023-01-22 17:51:19.320863: step: 380/529, loss: 0.012426088564097881
2023-01-22 17:51:20.449836: step: 384/529, loss: 0.0033366484567523003
2023-01-22 17:51:21.560480: step: 388/529, loss: 0.0269781481474638
2023-01-22 17:51:22.692666: step: 392/529, loss: 0.011076470836997032
2023-01-22 17:51:23.798196: step: 396/529, loss: 0.0033511200454086065
2023-01-22 17:51:24.912765: step: 400/529, loss: 0.02930506132543087
2023-01-22 17:51:26.054346: step: 404/529, loss: 0.011032543145120144
2023-01-22 17:51:27.160362: step: 408/529, loss: 0.004598382860422134
2023-01-22 17:51:28.285527: step: 412/529, loss: 0.006473167799413204
2023-01-22 17:51:29.385791: step: 416/529, loss: 0.005065383855253458
2023-01-22 17:51:30.492037: step: 420/529, loss: 0.017824824899435043
2023-01-22 17:51:31.591442: step: 424/529, loss: 0.029513027518987656
2023-01-22 17:51:32.693767: step: 428/529, loss: 0.011568554677069187
2023-01-22 17:51:33.795281: step: 432/529, loss: 0.01351325772702694
2023-01-22 17:51:34.915653: step: 436/529, loss: 0.011314324103295803
2023-01-22 17:51:36.040772: step: 440/529, loss: 0.0018535078270360827
2023-01-22 17:51:37.142235: step: 444/529, loss: 0.00917566753923893
2023-01-22 17:51:38.251448: step: 448/529, loss: 0.004006459377706051
2023-01-22 17:51:39.353732: step: 452/529, loss: 0.007178399711847305
2023-01-22 17:51:40.467124: step: 456/529, loss: 0.018362870439887047
2023-01-22 17:51:41.573703: step: 460/529, loss: 0.0007383043994195759
2023-01-22 17:51:42.666288: step: 464/529, loss: 0.016009826213121414
2023-01-22 17:51:43.815426: step: 468/529, loss: 0.10536003112792969
2023-01-22 17:51:44.928327: step: 472/529, loss: 0.02493038773536682
2023-01-22 17:51:46.044607: step: 476/529, loss: 0.01624736562371254
2023-01-22 17:51:47.142411: step: 480/529, loss: 0.009674545377492905
2023-01-22 17:51:48.247979: step: 484/529, loss: 0.008204970508813858
2023-01-22 17:51:49.364517: step: 488/529, loss: 0.026262089610099792
2023-01-22 17:51:50.483514: step: 492/529, loss: 0.017736749723553658
2023-01-22 17:51:51.597906: step: 496/529, loss: 0.009284062311053276
2023-01-22 17:51:52.729719: step: 500/529, loss: 0.0026390322018414736
2023-01-22 17:51:53.839972: step: 504/529, loss: 0.009106617420911789
2023-01-22 17:51:54.944208: step: 508/529, loss: 0.005013694055378437
2023-01-22 17:51:56.058818: step: 512/529, loss: 0.003496789839118719
2023-01-22 17:51:57.171602: step: 516/529, loss: 0.014424193650484085
2023-01-22 17:51:58.280184: step: 520/529, loss: 0.005190179217606783
2023-01-22 17:51:59.401103: step: 524/529, loss: 0.004365604370832443
2023-01-22 17:52:00.503916: step: 528/529, loss: 0.030612310394644737
2023-01-22 17:52:01.628294: step: 532/529, loss: 0.009976319968700409
2023-01-22 17:52:02.731056: step: 536/529, loss: 0.005136997438967228
2023-01-22 17:52:03.835901: step: 540/529, loss: 0.0431562103331089
2023-01-22 17:52:04.961794: step: 544/529, loss: 0.016987593844532967
2023-01-22 17:52:06.055508: step: 548/529, loss: 0.006357799284160137
2023-01-22 17:52:07.149211: step: 552/529, loss: 0.02931724302470684
2023-01-22 17:52:08.268451: step: 556/529, loss: 0.0063680848106741905
2023-01-22 17:52:09.373341: step: 560/529, loss: 0.07104165852069855
2023-01-22 17:52:10.486517: step: 564/529, loss: 0.007566351443529129
2023-01-22 17:52:11.575117: step: 568/529, loss: 0.005318984389305115
2023-01-22 17:52:12.683228: step: 572/529, loss: 0.0033264204394072294
2023-01-22 17:52:13.778352: step: 576/529, loss: 0.0061906673945486546
2023-01-22 17:52:14.889519: step: 580/529, loss: 0.0015148785896599293
2023-01-22 17:52:15.989276: step: 584/529, loss: 0.005580266937613487
2023-01-22 17:52:17.119086: step: 588/529, loss: 0.005269291810691357
2023-01-22 17:52:18.229700: step: 592/529, loss: 0.010836911387741566
2023-01-22 17:52:19.331979: step: 596/529, loss: 0.007093312684446573
2023-01-22 17:52:20.439946: step: 600/529, loss: 0.00394090823829174
2023-01-22 17:52:21.561480: step: 604/529, loss: 0.025229722261428833
2023-01-22 17:52:22.658470: step: 608/529, loss: 0.007404191419482231
2023-01-22 17:52:23.774031: step: 612/529, loss: 0.006746270693838596
2023-01-22 17:52:24.854052: step: 616/529, loss: 0.004486020654439926
2023-01-22 17:52:25.959939: step: 620/529, loss: 0.006292097270488739
2023-01-22 17:52:27.066286: step: 624/529, loss: 0.003894990775734186
2023-01-22 17:52:28.194842: step: 628/529, loss: 0.003883993485942483
2023-01-22 17:52:29.321125: step: 632/529, loss: 0.010636607185006142
2023-01-22 17:52:30.428603: step: 636/529, loss: 0.003698068903759122
2023-01-22 17:52:31.530392: step: 640/529, loss: 0.0007454185979440808
2023-01-22 17:52:32.631420: step: 644/529, loss: 0.006561399903148413
2023-01-22 17:52:33.727513: step: 648/529, loss: 0.002798452042043209
2023-01-22 17:52:34.858721: step: 652/529, loss: 0.01471537072211504
2023-01-22 17:52:35.969847: step: 656/529, loss: 0.0004220718110445887
2023-01-22 17:52:37.070922: step: 660/529, loss: 0.013086855411529541
2023-01-22 17:52:38.193714: step: 664/529, loss: 0.010682719759643078
2023-01-22 17:52:39.297356: step: 668/529, loss: 0.003999470267444849
2023-01-22 17:52:40.400141: step: 672/529, loss: 0.010561957955360413
2023-01-22 17:52:41.512622: step: 676/529, loss: 0.00589521462097764
2023-01-22 17:52:42.626630: step: 680/529, loss: 0.007122252136468887
2023-01-22 17:52:43.740888: step: 684/529, loss: 0.012555491179227829
2023-01-22 17:52:44.840446: step: 688/529, loss: 0.02013995870947838
2023-01-22 17:52:45.946371: step: 692/529, loss: 0.015481523238122463
2023-01-22 17:52:47.060942: step: 696/529, loss: 0.007118125446140766
2023-01-22 17:52:48.170677: step: 700/529, loss: 0.005167075898498297
2023-01-22 17:52:49.280986: step: 704/529, loss: 0.047261595726013184
2023-01-22 17:52:50.356675: step: 708/529, loss: 0.007963101379573345
2023-01-22 17:52:51.488013: step: 712/529, loss: 0.0034525517839938402
2023-01-22 17:52:52.595558: step: 716/529, loss: 0.0016437385929748416
2023-01-22 17:52:53.716645: step: 720/529, loss: 0.009101164527237415
2023-01-22 17:52:54.818020: step: 724/529, loss: 0.005738244391977787
2023-01-22 17:52:55.948336: step: 728/529, loss: 0.018488379195332527
2023-01-22 17:52:57.099314: step: 732/529, loss: 0.007038819137960672
2023-01-22 17:52:58.197684: step: 736/529, loss: 0.006071228533983231
2023-01-22 17:52:59.310792: step: 740/529, loss: 0.005023562349379063
2023-01-22 17:53:00.411373: step: 744/529, loss: 0.004617659375071526
2023-01-22 17:53:01.524508: step: 748/529, loss: 0.007815138436853886
2023-01-22 17:53:02.612169: step: 752/529, loss: 0.01970025524497032
2023-01-22 17:53:03.735409: step: 756/529, loss: 0.006991046480834484
2023-01-22 17:53:04.861293: step: 760/529, loss: 0.011613264679908752
2023-01-22 17:53:05.965291: step: 764/529, loss: 0.0006045643822290003
2023-01-22 17:53:07.068590: step: 768/529, loss: 0.027163978666067123
2023-01-22 17:53:08.182353: step: 772/529, loss: 0.01495275367051363
2023-01-22 17:53:09.295546: step: 776/529, loss: 0.02189851738512516
2023-01-22 17:53:10.407078: step: 780/529, loss: 0.007105804048478603
2023-01-22 17:53:11.516856: step: 784/529, loss: 0.0036675743758678436
2023-01-22 17:53:12.611325: step: 788/529, loss: 0.013794896192848682
2023-01-22 17:53:13.701843: step: 792/529, loss: 0.0014850583393126726
2023-01-22 17:53:14.802829: step: 796/529, loss: 0.0075757154263556
2023-01-22 17:53:15.902831: step: 800/529, loss: 0.011147506535053253
2023-01-22 17:53:17.023530: step: 804/529, loss: 0.032947223633527756
2023-01-22 17:53:18.140685: step: 808/529, loss: 0.005446398630738258
2023-01-22 17:53:19.235868: step: 812/529, loss: 0.0034685619175434113
2023-01-22 17:53:20.358277: step: 816/529, loss: 0.007180335465818644
2023-01-22 17:53:21.453738: step: 820/529, loss: 0.024265587329864502
2023-01-22 17:53:22.562683: step: 824/529, loss: 0.008386551402509212
2023-01-22 17:53:23.699035: step: 828/529, loss: 0.007402473594993353
2023-01-22 17:53:24.800769: step: 832/529, loss: 0.01185094565153122
2023-01-22 17:53:25.877896: step: 836/529, loss: 0.012170891277492046
2023-01-22 17:53:27.002757: step: 840/529, loss: 0.010631968267261982
2023-01-22 17:53:28.116024: step: 844/529, loss: 0.003322591306641698
2023-01-22 17:53:29.217459: step: 848/529, loss: 0.033631227910518646
2023-01-22 17:53:30.361573: step: 852/529, loss: 0.0030285348184406757
2023-01-22 17:53:31.457906: step: 856/529, loss: 0.02448822371661663
2023-01-22 17:53:32.575926: step: 860/529, loss: 0.0011358704650774598
2023-01-22 17:53:33.683743: step: 864/529, loss: 0.0034448835067451
2023-01-22 17:53:34.784873: step: 868/529, loss: 0.004241591785103083
2023-01-22 17:53:35.882877: step: 872/529, loss: 0.005275551229715347
2023-01-22 17:53:36.990257: step: 876/529, loss: 0.02770281955599785
2023-01-22 17:53:38.102246: step: 880/529, loss: 0.011750437319278717
2023-01-22 17:53:39.221838: step: 884/529, loss: 0.02568661794066429
2023-01-22 17:53:40.317653: step: 888/529, loss: 0.004655956290662289
2023-01-22 17:53:41.413071: step: 892/529, loss: 0.006035744212567806
2023-01-22 17:53:42.521513: step: 896/529, loss: 0.008791065774857998
2023-01-22 17:53:43.632380: step: 900/529, loss: 0.010015271604061127
2023-01-22 17:53:44.711591: step: 904/529, loss: 0.0024109173100441694
2023-01-22 17:53:45.811747: step: 908/529, loss: 0.019569136202335358
2023-01-22 17:53:46.930403: step: 912/529, loss: 0.004561732057482004
2023-01-22 17:53:48.033796: step: 916/529, loss: 0.0037367860786616802
2023-01-22 17:53:49.124473: step: 920/529, loss: 0.010635183192789555
2023-01-22 17:53:50.223235: step: 924/529, loss: 0.008983165957033634
2023-01-22 17:53:51.341426: step: 928/529, loss: 0.007565532345324755
2023-01-22 17:53:52.454467: step: 932/529, loss: 0.0017121994169428945
2023-01-22 17:53:53.573657: step: 936/529, loss: 0.0076131694950163364
2023-01-22 17:53:54.680186: step: 940/529, loss: 0.011468220502138138
2023-01-22 17:53:55.781256: step: 944/529, loss: 0.036546703428030014
2023-01-22 17:53:56.874704: step: 948/529, loss: 0.00682549923658371
2023-01-22 17:53:57.965977: step: 952/529, loss: 0.0024943973403424025
2023-01-22 17:53:59.077026: step: 956/529, loss: 0.002746598096564412
2023-01-22 17:54:00.199487: step: 960/529, loss: 0.009136325679719448
2023-01-22 17:54:01.298707: step: 964/529, loss: 0.009686806239187717
2023-01-22 17:54:02.423737: step: 968/529, loss: 0.009747578762471676
2023-01-22 17:54:03.554712: step: 972/529, loss: 0.002793676685541868
2023-01-22 17:54:04.691428: step: 976/529, loss: 0.006567907985299826
2023-01-22 17:54:05.780801: step: 980/529, loss: 0.0014695754507556558
2023-01-22 17:54:06.876502: step: 984/529, loss: 0.008628619834780693
2023-01-22 17:54:07.985571: step: 988/529, loss: 0.011440317146480083
2023-01-22 17:54:09.086188: step: 992/529, loss: 0.031265582889318466
2023-01-22 17:54:10.185670: step: 996/529, loss: 0.049090299755334854
2023-01-22 17:54:11.300430: step: 1000/529, loss: 0.00949549488723278
2023-01-22 17:54:12.433992: step: 1004/529, loss: 0.005003900267183781
2023-01-22 17:54:13.553913: step: 1008/529, loss: 0.014957522973418236
2023-01-22 17:54:14.669180: step: 1012/529, loss: 0.006984794978052378
2023-01-22 17:54:15.737945: step: 1016/529, loss: 0.006630700081586838
2023-01-22 17:54:16.829495: step: 1020/529, loss: 0.008829296566545963
2023-01-22 17:54:17.942373: step: 1024/529, loss: 0.013563680462539196
2023-01-22 17:54:19.069448: step: 1028/529, loss: 0.013646767474710941
2023-01-22 17:54:20.186375: step: 1032/529, loss: 0.017026502639055252
2023-01-22 17:54:21.273473: step: 1036/529, loss: 0.005695422179996967
2023-01-22 17:54:22.381438: step: 1040/529, loss: 0.07065655291080475
2023-01-22 17:54:23.462649: step: 1044/529, loss: 0.008288687095046043
2023-01-22 17:54:24.574199: step: 1048/529, loss: 0.02265295386314392
2023-01-22 17:54:25.670228: step: 1052/529, loss: 0.011016628704965115
2023-01-22 17:54:26.777448: step: 1056/529, loss: 0.0072325230576097965
2023-01-22 17:54:27.891326: step: 1060/529, loss: 0.03593211621046066
2023-01-22 17:54:29.012445: step: 1064/529, loss: 0.02738920785486698
2023-01-22 17:54:30.153990: step: 1068/529, loss: 0.022856106981635094
2023-01-22 17:54:31.275584: step: 1072/529, loss: 0.0017097165109589696
2023-01-22 17:54:32.371830: step: 1076/529, loss: 0.01007858943194151
2023-01-22 17:54:33.469449: step: 1080/529, loss: 0.016430934891104698
2023-01-22 17:54:34.571388: step: 1084/529, loss: 0.02392333745956421
2023-01-22 17:54:35.685981: step: 1088/529, loss: 0.003210279857739806
2023-01-22 17:54:36.776717: step: 1092/529, loss: 0.03804733231663704
2023-01-22 17:54:37.892443: step: 1096/529, loss: 0.006736402865499258
2023-01-22 17:54:39.007318: step: 1100/529, loss: 0.00113061279989779
2023-01-22 17:54:40.105621: step: 1104/529, loss: 0.009493349120020866
2023-01-22 17:54:41.224531: step: 1108/529, loss: 0.005395055748522282
2023-01-22 17:54:42.339264: step: 1112/529, loss: 0.0
2023-01-22 17:54:43.460784: step: 1116/529, loss: 0.003971834667026997
2023-01-22 17:54:44.551249: step: 1120/529, loss: 0.006149261724203825
2023-01-22 17:54:45.674938: step: 1124/529, loss: 0.0067004370503127575
2023-01-22 17:54:46.816463: step: 1128/529, loss: 0.008645967580378056
2023-01-22 17:54:47.922994: step: 1132/529, loss: 0.007671167608350515
2023-01-22 17:54:48.997163: step: 1136/529, loss: 0.004762822762131691
2023-01-22 17:54:50.095900: step: 1140/529, loss: 0.004212038591504097
2023-01-22 17:54:51.203576: step: 1144/529, loss: 0.0052347611635923386
2023-01-22 17:54:52.286141: step: 1148/529, loss: 0.003539025317877531
2023-01-22 17:54:53.372323: step: 1152/529, loss: 0.03307104855775833
2023-01-22 17:54:54.486233: step: 1156/529, loss: 0.0350826270878315
2023-01-22 17:54:55.591910: step: 1160/529, loss: 0.006120604462921619
2023-01-22 17:54:56.678699: step: 1164/529, loss: 0.010355891659855843
2023-01-22 17:54:57.784826: step: 1168/529, loss: 0.0020980248227715492
2023-01-22 17:54:58.913626: step: 1172/529, loss: 0.0010193908819928765
2023-01-22 17:55:00.037731: step: 1176/529, loss: 0.007296436931937933
2023-01-22 17:55:01.131403: step: 1180/529, loss: 0.01590452715754509
2023-01-22 17:55:02.248159: step: 1184/529, loss: 0.01501762680709362
2023-01-22 17:55:03.355194: step: 1188/529, loss: 0.006405299063771963
2023-01-22 17:55:04.459943: step: 1192/529, loss: 0.034896738827228546
2023-01-22 17:55:05.572857: step: 1196/529, loss: 0.00830760132521391
2023-01-22 17:55:06.681533: step: 1200/529, loss: 0.003155040554702282
2023-01-22 17:55:07.789421: step: 1204/529, loss: 0.015755338594317436
2023-01-22 17:55:08.889303: step: 1208/529, loss: 0.009930795058608055
2023-01-22 17:55:09.990937: step: 1212/529, loss: 0.007268515881150961
2023-01-22 17:55:11.108805: step: 1216/529, loss: 0.014256534166634083
2023-01-22 17:55:12.226812: step: 1220/529, loss: 0.0023033777251839638
2023-01-22 17:55:13.326252: step: 1224/529, loss: 0.00286106183193624
2023-01-22 17:55:14.447948: step: 1228/529, loss: 0.009225982241332531
2023-01-22 17:55:15.548024: step: 1232/529, loss: 0.02584785781800747
2023-01-22 17:55:16.640608: step: 1236/529, loss: 0.0029287950601428747
2023-01-22 17:55:17.763979: step: 1240/529, loss: 0.008580446243286133
2023-01-22 17:55:18.843751: step: 1244/529, loss: 0.0029004202224314213
2023-01-22 17:55:19.976823: step: 1248/529, loss: 0.00072190206265077
2023-01-22 17:55:21.076425: step: 1252/529, loss: 0.008647261187434196
2023-01-22 17:55:22.186186: step: 1256/529, loss: 0.0038553958293050528
2023-01-22 17:55:23.276084: step: 1260/529, loss: 0.0035050292499363422
2023-01-22 17:55:24.410063: step: 1264/529, loss: 0.004807660356163979
2023-01-22 17:55:25.524277: step: 1268/529, loss: 0.013294756412506104
2023-01-22 17:55:26.639006: step: 1272/529, loss: 0.02997460588812828
2023-01-22 17:55:27.763632: step: 1276/529, loss: 0.006026304326951504
2023-01-22 17:55:28.858567: step: 1280/529, loss: 0.009825173765420914
2023-01-22 17:55:29.945113: step: 1284/529, loss: 0.003956271335482597
2023-01-22 17:55:31.055445: step: 1288/529, loss: 0.009954909794032574
2023-01-22 17:55:32.143168: step: 1292/529, loss: 0.0039692954160273075
2023-01-22 17:55:33.242395: step: 1296/529, loss: 0.00824042409658432
2023-01-22 17:55:34.355723: step: 1300/529, loss: 0.006427253130823374
2023-01-22 17:55:35.433988: step: 1304/529, loss: 0.0066772447898983955
2023-01-22 17:55:36.536804: step: 1308/529, loss: 0.01631542108952999
2023-01-22 17:55:37.696125: step: 1312/529, loss: 0.008065924048423767
2023-01-22 17:55:38.799375: step: 1316/529, loss: 0.009312838315963745
2023-01-22 17:55:39.913128: step: 1320/529, loss: 0.05190780758857727
2023-01-22 17:55:41.009050: step: 1324/529, loss: 0.005823833867907524
2023-01-22 17:55:42.120907: step: 1328/529, loss: 0.007591616362333298
2023-01-22 17:55:43.250269: step: 1332/529, loss: 0.006703960243612528
2023-01-22 17:55:44.368970: step: 1336/529, loss: 0.018768370151519775
2023-01-22 17:55:45.448038: step: 1340/529, loss: 0.024526676163077354
2023-01-22 17:55:46.567748: step: 1344/529, loss: 0.006300970911979675
2023-01-22 17:55:47.674752: step: 1348/529, loss: 0.010336175560951233
2023-01-22 17:55:48.806736: step: 1352/529, loss: 0.02772681973874569
2023-01-22 17:55:49.896086: step: 1356/529, loss: 0.03407607972621918
2023-01-22 17:55:50.985897: step: 1360/529, loss: 0.014773945324122906
2023-01-22 17:55:52.115412: step: 1364/529, loss: 0.1562815010547638
2023-01-22 17:55:53.209450: step: 1368/529, loss: 0.028557730838656425
2023-01-22 17:55:54.325622: step: 1372/529, loss: 0.01858489215373993
2023-01-22 17:55:55.404942: step: 1376/529, loss: 0.009563828818500042
2023-01-22 17:55:56.504844: step: 1380/529, loss: 0.01983632519841194
2023-01-22 17:55:57.642703: step: 1384/529, loss: 0.007155098021030426
2023-01-22 17:55:58.752269: step: 1388/529, loss: 0.026392385363578796
2023-01-22 17:55:59.887226: step: 1392/529, loss: 0.004741833079606295
2023-01-22 17:56:01.021663: step: 1396/529, loss: 0.0076646204106509686
2023-01-22 17:56:02.141523: step: 1400/529, loss: 0.008497913368046284
2023-01-22 17:56:03.235240: step: 1404/529, loss: 0.00710978964343667
2023-01-22 17:56:04.336886: step: 1408/529, loss: 0.002102840691804886
2023-01-22 17:56:05.422484: step: 1412/529, loss: 0.04014722257852554
2023-01-22 17:56:06.513279: step: 1416/529, loss: 0.017644071951508522
2023-01-22 17:56:07.597966: step: 1420/529, loss: 0.0036111820954829454
2023-01-22 17:56:08.711104: step: 1424/529, loss: 0.008191789500415325
2023-01-22 17:56:09.825104: step: 1428/529, loss: 0.007937217131257057
2023-01-22 17:56:10.922694: step: 1432/529, loss: 0.00306039210408926
2023-01-22 17:56:12.046249: step: 1436/529, loss: 0.011342877522110939
2023-01-22 17:56:13.161075: step: 1440/529, loss: 0.0025729602202773094
2023-01-22 17:56:14.271237: step: 1444/529, loss: 0.0063449786975979805
2023-01-22 17:56:15.376518: step: 1448/529, loss: 0.004742337390780449
2023-01-22 17:56:16.466445: step: 1452/529, loss: 0.028842899948358536
2023-01-22 17:56:17.554744: step: 1456/529, loss: 0.010683379136025906
2023-01-22 17:56:18.644898: step: 1460/529, loss: 0.009811916388571262
2023-01-22 17:56:19.766711: step: 1464/529, loss: 0.013648955151438713
2023-01-22 17:56:20.861541: step: 1468/529, loss: 0.009029221720993519
2023-01-22 17:56:21.962511: step: 1472/529, loss: 0.009125969372689724
2023-01-22 17:56:23.063272: step: 1476/529, loss: 0.005447356030344963
2023-01-22 17:56:24.160456: step: 1480/529, loss: 0.00017932680202648044
2023-01-22 17:56:25.260750: step: 1484/529, loss: 0.016321277245879173
2023-01-22 17:56:26.342340: step: 1488/529, loss: 0.015126307494938374
2023-01-22 17:56:27.445812: step: 1492/529, loss: 0.020544061437249184
2023-01-22 17:56:28.587213: step: 1496/529, loss: 0.007624355610460043
2023-01-22 17:56:29.690919: step: 1500/529, loss: 0.010923942551016808
2023-01-22 17:56:30.796138: step: 1504/529, loss: 0.008334414102137089
2023-01-22 17:56:31.887956: step: 1508/529, loss: 0.005844576749950647
2023-01-22 17:56:33.002123: step: 1512/529, loss: 0.004947004374116659
2023-01-22 17:56:34.097710: step: 1516/529, loss: 0.012654013931751251
2023-01-22 17:56:35.210494: step: 1520/529, loss: 0.007389873266220093
2023-01-22 17:56:36.337493: step: 1524/529, loss: 0.008271020837128162
2023-01-22 17:56:37.447950: step: 1528/529, loss: 0.006278053391724825
2023-01-22 17:56:38.560980: step: 1532/529, loss: 0.00804481003433466
2023-01-22 17:56:39.682754: step: 1536/529, loss: 0.00594293512403965
2023-01-22 17:56:40.773970: step: 1540/529, loss: 0.0064170872792601585
2023-01-22 17:56:41.888598: step: 1544/529, loss: 0.0012547632213681936
2023-01-22 17:56:42.979216: step: 1548/529, loss: 0.016787130385637283
2023-01-22 17:56:44.070312: step: 1552/529, loss: 0.014671772718429565
2023-01-22 17:56:45.175245: step: 1556/529, loss: 0.01921709254384041
2023-01-22 17:56:46.283882: step: 1560/529, loss: 0.011923871003091335
2023-01-22 17:56:47.381236: step: 1564/529, loss: 0.0192636139690876
2023-01-22 17:56:48.484527: step: 1568/529, loss: 0.002478834008798003
2023-01-22 17:56:49.590737: step: 1572/529, loss: 0.030554722994565964
2023-01-22 17:56:50.674213: step: 1576/529, loss: 0.0007834086427465081
2023-01-22 17:56:51.771085: step: 1580/529, loss: 0.0061339400708675385
2023-01-22 17:56:52.865761: step: 1584/529, loss: 0.011207625269889832
2023-01-22 17:56:53.959546: step: 1588/529, loss: 0.010608324781060219
2023-01-22 17:56:55.126973: step: 1592/529, loss: 0.014916323125362396
2023-01-22 17:56:56.228173: step: 1596/529, loss: 0.005108105484396219
2023-01-22 17:56:57.339815: step: 1600/529, loss: 0.00430460786446929
2023-01-22 17:56:58.465709: step: 1604/529, loss: 0.007633857429027557
2023-01-22 17:56:59.565405: step: 1608/529, loss: 0.004318347666412592
2023-01-22 17:57:00.691073: step: 1612/529, loss: 0.0016345756594091654
2023-01-22 17:57:01.794742: step: 1616/529, loss: 0.00565393315628171
2023-01-22 17:57:02.904791: step: 1620/529, loss: 0.03454332426190376
2023-01-22 17:57:04.008148: step: 1624/529, loss: 0.01870276778936386
2023-01-22 17:57:05.126269: step: 1628/529, loss: 0.0046154349111020565
2023-01-22 17:57:06.220684: step: 1632/529, loss: 0.018332835286855698
2023-01-22 17:57:07.331050: step: 1636/529, loss: 0.020688025280833244
2023-01-22 17:57:08.433057: step: 1640/529, loss: 0.01965653896331787
2023-01-22 17:57:09.544830: step: 1644/529, loss: 0.008216667920351028
2023-01-22 17:57:10.666755: step: 1648/529, loss: 0.0105309272184968
2023-01-22 17:57:11.791779: step: 1652/529, loss: 0.013985680416226387
2023-01-22 17:57:12.880776: step: 1656/529, loss: 0.0044655888341367245
2023-01-22 17:57:13.976565: step: 1660/529, loss: 0.004166341852396727
2023-01-22 17:57:15.086267: step: 1664/529, loss: 0.0057730115950107574
2023-01-22 17:57:16.201902: step: 1668/529, loss: 0.03798156604170799
2023-01-22 17:57:17.315019: step: 1672/529, loss: 0.010853929445147514
2023-01-22 17:57:18.402730: step: 1676/529, loss: 0.0026412634178996086
2023-01-22 17:57:19.520866: step: 1680/529, loss: 0.007113948464393616
2023-01-22 17:57:20.611052: step: 1684/529, loss: 0.011505438014864922
2023-01-22 17:57:21.749408: step: 1688/529, loss: 0.06450343132019043
2023-01-22 17:57:22.845029: step: 1692/529, loss: 0.0046125007793307304
2023-01-22 17:57:23.967186: step: 1696/529, loss: 0.006554285064339638
2023-01-22 17:57:25.066017: step: 1700/529, loss: 0.01852637156844139
2023-01-22 17:57:26.175474: step: 1704/529, loss: 0.0076111555099487305
2023-01-22 17:57:27.289302: step: 1708/529, loss: 0.033805493265390396
2023-01-22 17:57:28.398251: step: 1712/529, loss: 0.006822461262345314
2023-01-22 17:57:29.499384: step: 1716/529, loss: 0.0046230158768594265
2023-01-22 17:57:30.608712: step: 1720/529, loss: 0.004459755960851908
2023-01-22 17:57:31.700819: step: 1724/529, loss: 0.004157426301389933
2023-01-22 17:57:32.813826: step: 1728/529, loss: 0.0014901006361469626
2023-01-22 17:57:33.906807: step: 1732/529, loss: 0.005487402435392141
2023-01-22 17:57:35.016119: step: 1736/529, loss: 0.009611217305064201
2023-01-22 17:57:36.132962: step: 1740/529, loss: 0.010116838850080967
2023-01-22 17:57:37.228689: step: 1744/529, loss: 0.005602534860372543
2023-01-22 17:57:38.340233: step: 1748/529, loss: 0.0036284972447901964
2023-01-22 17:57:39.482310: step: 1752/529, loss: 0.01792565919458866
2023-01-22 17:57:40.605513: step: 1756/529, loss: 0.00588710093870759
2023-01-22 17:57:41.754762: step: 1760/529, loss: 0.0032751059625297785
2023-01-22 17:57:42.838458: step: 1764/529, loss: 0.007404741831123829
2023-01-22 17:57:43.941070: step: 1768/529, loss: 0.0009137190645560622
2023-01-22 17:57:45.051693: step: 1772/529, loss: 0.009999031201004982
2023-01-22 17:57:46.149995: step: 1776/529, loss: 0.02776346169412136
2023-01-22 17:57:47.280766: step: 1780/529, loss: 0.02876080758869648
2023-01-22 17:57:48.400257: step: 1784/529, loss: 0.11931665986776352
2023-01-22 17:57:49.495798: step: 1788/529, loss: 0.00244296551682055
2023-01-22 17:57:50.587959: step: 1792/529, loss: 0.003958273213356733
2023-01-22 17:57:51.721376: step: 1796/529, loss: 0.0045238640159368515
2023-01-22 17:57:52.823546: step: 1800/529, loss: 0.028285330161452293
2023-01-22 17:57:53.924901: step: 1804/529, loss: 0.009077048860490322
2023-01-22 17:57:55.042214: step: 1808/529, loss: 0.04064033925533295
2023-01-22 17:57:56.157439: step: 1812/529, loss: 0.006792752537876368
2023-01-22 17:57:57.253747: step: 1816/529, loss: 0.003269175998866558
2023-01-22 17:57:58.352427: step: 1820/529, loss: 0.006556231994181871
2023-01-22 17:57:59.461732: step: 1824/529, loss: 0.0054048895835876465
2023-01-22 17:58:00.570813: step: 1828/529, loss: 0.007066300604492426
2023-01-22 17:58:01.648649: step: 1832/529, loss: 0.036295562982559204
2023-01-22 17:58:02.773156: step: 1836/529, loss: 0.006278666201978922
2023-01-22 17:58:03.880174: step: 1840/529, loss: 0.01597563736140728
2023-01-22 17:58:05.011842: step: 1844/529, loss: 0.0073672104626894
2023-01-22 17:58:06.105334: step: 1848/529, loss: 0.011774738319218159
2023-01-22 17:58:07.203087: step: 1852/529, loss: 0.0035159094259142876
2023-01-22 17:58:08.329618: step: 1856/529, loss: 0.004620057996362448
2023-01-22 17:58:09.440590: step: 1860/529, loss: 0.0062436931766569614
2023-01-22 17:58:10.561026: step: 1864/529, loss: 0.007321196608245373
2023-01-22 17:58:11.679011: step: 1868/529, loss: 0.006461309734731913
2023-01-22 17:58:12.782495: step: 1872/529, loss: 0.04484855756163597
2023-01-22 17:58:13.869452: step: 1876/529, loss: 0.005174992606043816
2023-01-22 17:58:15.002930: step: 1880/529, loss: 0.003563453909009695
2023-01-22 17:58:16.105269: step: 1884/529, loss: 0.0046882592141628265
2023-01-22 17:58:17.210430: step: 1888/529, loss: 0.01261555589735508
2023-01-22 17:58:18.311944: step: 1892/529, loss: 0.0034093556459993124
2023-01-22 17:58:19.425968: step: 1896/529, loss: 0.010241791605949402
2023-01-22 17:58:20.524971: step: 1900/529, loss: 0.0015312704490497708
2023-01-22 17:58:21.637477: step: 1904/529, loss: 0.025107678025960922
2023-01-22 17:58:22.756430: step: 1908/529, loss: 0.007371546234935522
2023-01-22 17:58:23.856142: step: 1912/529, loss: 0.0
2023-01-22 17:58:24.961234: step: 1916/529, loss: 0.0038481811061501503
2023-01-22 17:58:26.084373: step: 1920/529, loss: 0.008993173949420452
2023-01-22 17:58:27.182013: step: 1924/529, loss: 0.0033240830525755882
2023-01-22 17:58:28.306376: step: 1928/529, loss: 0.008125894702970982
2023-01-22 17:58:29.434601: step: 1932/529, loss: 0.001147898961789906
2023-01-22 17:58:30.559725: step: 1936/529, loss: 0.0077410549856722355
2023-01-22 17:58:31.681568: step: 1940/529, loss: 0.009782909415662289
2023-01-22 17:58:32.766103: step: 1944/529, loss: 0.025076620280742645
2023-01-22 17:58:33.859116: step: 1948/529, loss: 0.01597674936056137
2023-01-22 17:58:34.974576: step: 1952/529, loss: 0.0004735524416901171
2023-01-22 17:58:36.087486: step: 1956/529, loss: 0.0005445539718493819
2023-01-22 17:58:37.208736: step: 1960/529, loss: 0.006779307499527931
2023-01-22 17:58:38.285195: step: 1964/529, loss: 0.0014635936822742224
2023-01-22 17:58:39.371928: step: 1968/529, loss: 0.003631761996075511
2023-01-22 17:58:40.481024: step: 1972/529, loss: 0.008415826596319675
2023-01-22 17:58:41.607853: step: 1976/529, loss: 0.007191472686827183
2023-01-22 17:58:42.711303: step: 1980/529, loss: 0.008011182770133018
2023-01-22 17:58:43.820613: step: 1984/529, loss: 0.011564129032194614
2023-01-22 17:58:44.917095: step: 1988/529, loss: 4.088526839041151e-05
2023-01-22 17:58:46.033226: step: 1992/529, loss: 0.0044421181082725525
2023-01-22 17:58:47.152013: step: 1996/529, loss: 0.00152040075045079
2023-01-22 17:58:48.252293: step: 2000/529, loss: 0.0023216786794364452
2023-01-22 17:58:49.350009: step: 2004/529, loss: 0.0036217004526406527
2023-01-22 17:58:50.465593: step: 2008/529, loss: 0.009130951948463917
2023-01-22 17:58:51.565173: step: 2012/529, loss: 0.009823904372751713
2023-01-22 17:58:52.672854: step: 2016/529, loss: 0.0022416035644710064
2023-01-22 17:58:53.771328: step: 2020/529, loss: 0.0052179298363626
2023-01-22 17:58:54.895522: step: 2024/529, loss: 0.004806553013622761
2023-01-22 17:58:55.979864: step: 2028/529, loss: 0.007773983757942915
2023-01-22 17:58:57.079770: step: 2032/529, loss: 0.006831275764852762
2023-01-22 17:58:58.182405: step: 2036/529, loss: 0.007376746274530888
2023-01-22 17:58:59.300409: step: 2040/529, loss: 0.024378931149840355
2023-01-22 17:59:00.390734: step: 2044/529, loss: 0.0035203720908612013
2023-01-22 17:59:01.517171: step: 2048/529, loss: 0.0027153335977345705
2023-01-22 17:59:02.633110: step: 2052/529, loss: 0.014825323596596718
2023-01-22 17:59:03.750891: step: 2056/529, loss: 0.003668862860649824
2023-01-22 17:59:04.845220: step: 2060/529, loss: 0.00796460174024105
2023-01-22 17:59:05.961102: step: 2064/529, loss: 0.027771560475230217
2023-01-22 17:59:07.070378: step: 2068/529, loss: 0.03683504834771156
2023-01-22 17:59:08.210349: step: 2072/529, loss: 0.00495346961542964
2023-01-22 17:59:09.313718: step: 2076/529, loss: 0.010131757706403732
2023-01-22 17:59:10.421323: step: 2080/529, loss: 0.02494375966489315
2023-01-22 17:59:11.557001: step: 2084/529, loss: 0.0012241617077961564
2023-01-22 17:59:12.655923: step: 2088/529, loss: 0.023943539708852768
2023-01-22 17:59:13.746166: step: 2092/529, loss: 0.0031378851272165775
2023-01-22 17:59:14.875542: step: 2096/529, loss: 0.004842622671276331
2023-01-22 17:59:15.975846: step: 2100/529, loss: 0.005990363657474518
2023-01-22 17:59:17.088076: step: 2104/529, loss: 0.005425291135907173
2023-01-22 17:59:18.187661: step: 2108/529, loss: 0.004704763647168875
2023-01-22 17:59:19.294365: step: 2112/529, loss: 0.004776051267981529
2023-01-22 17:59:20.420931: step: 2116/529, loss: 0.0035173268988728523
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3351450027685493, 'r': 0.3281495662781242, 'f1': 0.33161039583618684}, 'combined': 0.24434450219508502, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37485811279918213, 'r': 0.2962483525761301, 'f1': 0.33094927286820336}, 'combined': 0.20341272381167622, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.342851509622988, 'r': 0.346104370245597, 'f1': 0.34447026084878113}, 'combined': 0.253820192204365, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35261437982038957, 'r': 0.30403059611896677, 'f1': 0.3265251818718359}, 'combined': 0.20069352641878693, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34158539554333506, 'r': 0.34288173480535905, 'f1': 0.34223233758034893}, 'combined': 0.252171196111836, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36645091639237326, 'r': 0.29538164775870085, 'f1': 0.3271004824173533}, 'combined': 0.2020326509048359, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35185185185185186, 'r': 0.41304347826086957, 'f1': 0.38}, 'combined': 0.19, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 3}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33833087822671154, 'r': 0.34667680121902134, 'f1': 0.34245299764278203}, 'combined': 0.2523337877367867, 'stategy': 1, 'epoch': 1}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36213467140284455, 'r': 0.29754614992320305, 'f1': 0.3266785201153037}, 'combined': 0.20177202713004055, 'stategy': 1, 'epoch': 1}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 1}
******************************
Epoch: 4
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 18:01:46.924201: step: 4/529, loss: 0.0010277761612087488
2023-01-22 18:01:48.041182: step: 8/529, loss: 0.010806041769683361
2023-01-22 18:01:49.147210: step: 12/529, loss: 0.004061661195009947
2023-01-22 18:01:50.233412: step: 16/529, loss: 0.007979325950145721
2023-01-22 18:01:51.359906: step: 20/529, loss: 0.0207815021276474
2023-01-22 18:01:52.440903: step: 24/529, loss: 0.002433926332741976
2023-01-22 18:01:53.548785: step: 28/529, loss: 0.0009482248569838703
2023-01-22 18:01:54.642031: step: 32/529, loss: 0.004135242663323879
2023-01-22 18:01:55.744375: step: 36/529, loss: 0.011053194291889668
2023-01-22 18:01:56.848579: step: 40/529, loss: 0.007244446314871311
2023-01-22 18:01:57.955091: step: 44/529, loss: 0.039158716797828674
2023-01-22 18:01:59.038632: step: 48/529, loss: 0.018788348883390427
2023-01-22 18:02:00.138843: step: 52/529, loss: 0.0009543916676193476
2023-01-22 18:02:01.239316: step: 56/529, loss: 0.00402290653437376
2023-01-22 18:02:02.386643: step: 60/529, loss: 0.004691957496106625
2023-01-22 18:02:03.482350: step: 64/529, loss: 0.014238426461815834
2023-01-22 18:02:04.584928: step: 68/529, loss: 0.01219252310693264
2023-01-22 18:02:05.680027: step: 72/529, loss: 0.010191323235630989
2023-01-22 18:02:06.791204: step: 76/529, loss: 0.017158569768071175
2023-01-22 18:02:07.867482: step: 80/529, loss: 0.005863894708454609
2023-01-22 18:02:08.955500: step: 84/529, loss: 0.014999204315245152
2023-01-22 18:02:10.070795: step: 88/529, loss: 0.009794222190976143
2023-01-22 18:02:11.167551: step: 92/529, loss: 0.00871590618044138
2023-01-22 18:02:12.276666: step: 96/529, loss: 0.014467458240687847
2023-01-22 18:02:13.396851: step: 100/529, loss: 0.01966398023068905
2023-01-22 18:02:14.497777: step: 104/529, loss: 0.004165752325206995
2023-01-22 18:02:15.604461: step: 108/529, loss: 0.00027261098148301244
2023-01-22 18:02:16.724209: step: 112/529, loss: 0.017045212909579277
2023-01-22 18:02:17.864872: step: 116/529, loss: 0.011953402310609818
2023-01-22 18:02:18.979778: step: 120/529, loss: 0.02382500097155571
2023-01-22 18:02:20.088844: step: 124/529, loss: 0.009406017139554024
2023-01-22 18:02:21.203539: step: 128/529, loss: 0.026710592210292816
2023-01-22 18:02:22.332233: step: 132/529, loss: 0.01230623759329319
2023-01-22 18:02:23.426357: step: 136/529, loss: 0.006661921739578247
2023-01-22 18:02:24.549242: step: 140/529, loss: 0.016752805560827255
2023-01-22 18:02:25.651800: step: 144/529, loss: 0.005688263103365898
2023-01-22 18:02:26.751807: step: 148/529, loss: 0.017508279532194138
2023-01-22 18:02:27.844908: step: 152/529, loss: 0.018228985369205475
2023-01-22 18:02:28.950576: step: 156/529, loss: 0.0026795410085469484
2023-01-22 18:02:30.075857: step: 160/529, loss: 0.0034972375724464655
2023-01-22 18:02:31.205558: step: 164/529, loss: 0.005714005324989557
2023-01-22 18:02:32.345082: step: 168/529, loss: 0.0073775555938482285
2023-01-22 18:02:33.441032: step: 172/529, loss: 0.0023705316707491875
2023-01-22 18:02:34.523778: step: 176/529, loss: 0.005095466505736113
2023-01-22 18:02:35.623664: step: 180/529, loss: 0.0193537138402462
2023-01-22 18:02:36.732966: step: 184/529, loss: 0.029033103957772255
2023-01-22 18:02:37.820418: step: 188/529, loss: 0.021615667268633842
2023-01-22 18:02:38.915668: step: 192/529, loss: 0.010073946788907051
2023-01-22 18:02:40.014288: step: 196/529, loss: 0.005494964774698019
2023-01-22 18:02:41.120896: step: 200/529, loss: 0.005054249428212643
2023-01-22 18:02:42.224998: step: 204/529, loss: 0.0051721613854169846
2023-01-22 18:02:43.328319: step: 208/529, loss: 0.008345655165612698
2023-01-22 18:02:44.438504: step: 212/529, loss: 0.023853175342082977
2023-01-22 18:02:45.536419: step: 216/529, loss: 0.005570420064032078
2023-01-22 18:02:46.648071: step: 220/529, loss: 5.236471406533383e-05
2023-01-22 18:02:47.757194: step: 224/529, loss: 0.001574378926306963
2023-01-22 18:02:48.873030: step: 228/529, loss: 0.008779872208833694
2023-01-22 18:02:49.982559: step: 232/529, loss: 0.008622650057077408
2023-01-22 18:02:51.083843: step: 236/529, loss: 0.0014193839160725474
2023-01-22 18:02:52.193267: step: 240/529, loss: 0.01752307079732418
2023-01-22 18:02:53.304685: step: 244/529, loss: 0.011145064607262611
2023-01-22 18:02:54.399387: step: 248/529, loss: 0.01546645350754261
2023-01-22 18:02:55.516165: step: 252/529, loss: 0.008975861594080925
2023-01-22 18:02:56.624957: step: 256/529, loss: 0.0033201894257217646
2023-01-22 18:02:57.741034: step: 260/529, loss: 0.005528888665139675
2023-01-22 18:02:58.840041: step: 264/529, loss: 0.004674576688557863
2023-01-22 18:02:59.957466: step: 268/529, loss: 0.009894490242004395
2023-01-22 18:03:01.058323: step: 272/529, loss: 0.007337674964219332
2023-01-22 18:03:02.192562: step: 276/529, loss: 0.009367755614221096
2023-01-22 18:03:03.294549: step: 280/529, loss: 0.0014483543345704675
2023-01-22 18:03:04.404100: step: 284/529, loss: 0.010304666124284267
2023-01-22 18:03:05.485522: step: 288/529, loss: 0.005490402691066265
2023-01-22 18:03:06.581211: step: 292/529, loss: 0.029745591804385185
2023-01-22 18:03:07.675636: step: 296/529, loss: 0.0025941135827451944
2023-01-22 18:03:08.801889: step: 300/529, loss: 0.012264592573046684
2023-01-22 18:03:09.943819: step: 304/529, loss: 0.004538606386631727
2023-01-22 18:03:11.064039: step: 308/529, loss: 0.020474176853895187
2023-01-22 18:03:12.138013: step: 312/529, loss: 0.0010937289334833622
2023-01-22 18:03:13.230118: step: 316/529, loss: 0.03347092494368553
2023-01-22 18:03:14.319982: step: 320/529, loss: 0.002895524725317955
2023-01-22 18:03:15.450594: step: 324/529, loss: 0.008518103510141373
2023-01-22 18:03:16.563197: step: 328/529, loss: 0.020794207230210304
2023-01-22 18:03:17.691808: step: 332/529, loss: 0.03317151591181755
2023-01-22 18:03:18.817407: step: 336/529, loss: 0.02144635282456875
2023-01-22 18:03:19.932026: step: 340/529, loss: 0.010164160281419754
2023-01-22 18:03:21.034651: step: 344/529, loss: 0.00684781838208437
2023-01-22 18:03:22.156114: step: 348/529, loss: 0.02203591726720333
2023-01-22 18:03:23.264921: step: 352/529, loss: 0.005991616286337376
2023-01-22 18:03:24.373058: step: 356/529, loss: 0.0473276823759079
2023-01-22 18:03:25.477211: step: 360/529, loss: 0.01721019484102726
2023-01-22 18:03:26.576455: step: 364/529, loss: 0.008875301107764244
2023-01-22 18:03:27.679314: step: 368/529, loss: 0.006471844855695963
2023-01-22 18:03:28.790904: step: 372/529, loss: 0.017932103946805
2023-01-22 18:03:29.886169: step: 376/529, loss: 0.03158516436815262
2023-01-22 18:03:30.989488: step: 380/529, loss: 0.010447031818330288
2023-01-22 18:03:32.123356: step: 384/529, loss: 0.0077856131829321384
2023-01-22 18:03:33.222111: step: 388/529, loss: 0.007280371617525816
2023-01-22 18:03:34.327991: step: 392/529, loss: 0.019415080547332764
2023-01-22 18:03:35.434899: step: 396/529, loss: 0.006431635934859514
2023-01-22 18:03:36.550980: step: 400/529, loss: 0.0004165937134530395
2023-01-22 18:03:37.688570: step: 404/529, loss: 0.023850802332162857
2023-01-22 18:03:38.805669: step: 408/529, loss: 0.022242402657866478
2023-01-22 18:03:39.899263: step: 412/529, loss: 0.0005607185303233564
2023-01-22 18:03:40.980582: step: 416/529, loss: 0.0031985067762434483
2023-01-22 18:03:42.079325: step: 420/529, loss: 0.0014394099125638604
2023-01-22 18:03:43.180640: step: 424/529, loss: 0.0044053951278328896
2023-01-22 18:03:44.284176: step: 428/529, loss: 0.007118708454072475
2023-01-22 18:03:45.363040: step: 432/529, loss: 0.016993161290884018
2023-01-22 18:03:46.451005: step: 436/529, loss: 0.009401665069162846
2023-01-22 18:03:47.542078: step: 440/529, loss: 0.0011328529799357057
2023-01-22 18:03:48.658630: step: 444/529, loss: 0.0026023162063211203
2023-01-22 18:03:49.781889: step: 448/529, loss: 0.016223173588514328
2023-01-22 18:03:50.894051: step: 452/529, loss: 0.009850227274000645
2023-01-22 18:03:52.018231: step: 456/529, loss: 0.007447805255651474
2023-01-22 18:03:53.136666: step: 460/529, loss: 0.0026509473100304604
2023-01-22 18:03:54.260295: step: 464/529, loss: 0.002980706049129367
2023-01-22 18:03:55.349104: step: 468/529, loss: 0.002533161547034979
2023-01-22 18:03:56.458732: step: 472/529, loss: 0.0053563425317406654
2023-01-22 18:03:57.551913: step: 476/529, loss: 0.0109642893075943
2023-01-22 18:03:58.665387: step: 480/529, loss: 0.040974292904138565
2023-01-22 18:03:59.766920: step: 484/529, loss: 0.006244489923119545
2023-01-22 18:04:00.884292: step: 488/529, loss: 0.0022297760006040335
2023-01-22 18:04:01.998214: step: 492/529, loss: 0.026245882734656334
2023-01-22 18:04:03.110798: step: 496/529, loss: 0.002393545815721154
2023-01-22 18:04:04.215457: step: 500/529, loss: 0.0007777800783514977
2023-01-22 18:04:05.339380: step: 504/529, loss: 0.00473775016143918
2023-01-22 18:04:06.462093: step: 508/529, loss: 0.026044726371765137
2023-01-22 18:04:07.582247: step: 512/529, loss: 0.01604190282523632
2023-01-22 18:04:08.662617: step: 516/529, loss: 0.0012831779895350337
2023-01-22 18:04:09.770419: step: 520/529, loss: 0.006340454798191786
2023-01-22 18:04:10.884308: step: 524/529, loss: 0.01106035802513361
2023-01-22 18:04:12.005863: step: 528/529, loss: 0.001452543423511088
2023-01-22 18:04:13.119651: step: 532/529, loss: 0.015412398613989353
2023-01-22 18:04:14.226556: step: 536/529, loss: 0.004751899279654026
2023-01-22 18:04:15.332772: step: 540/529, loss: 0.0032661445438861847
2023-01-22 18:04:16.443100: step: 544/529, loss: 0.0005853670882061124
2023-01-22 18:04:17.540081: step: 548/529, loss: 0.006554052233695984
2023-01-22 18:04:18.637565: step: 552/529, loss: 0.00837355200201273
2023-01-22 18:04:19.719869: step: 556/529, loss: 0.008125251159071922
2023-01-22 18:04:20.822288: step: 560/529, loss: 0.0009894382674247026
2023-01-22 18:04:21.947035: step: 564/529, loss: 0.04186941683292389
2023-01-22 18:04:23.094410: step: 568/529, loss: 0.009356123395264149
2023-01-22 18:04:24.192385: step: 572/529, loss: 0.0006051416276022792
2023-01-22 18:04:25.310877: step: 576/529, loss: 0.21576407551765442
2023-01-22 18:04:26.425054: step: 580/529, loss: 0.011934589594602585
2023-01-22 18:04:27.524209: step: 584/529, loss: 0.009236830286681652
2023-01-22 18:04:28.644377: step: 588/529, loss: 0.00466415099799633
2023-01-22 18:04:29.756588: step: 592/529, loss: 0.0016343441093340516
2023-01-22 18:04:30.879164: step: 596/529, loss: 0.026625338941812515
2023-01-22 18:04:31.976690: step: 600/529, loss: 0.004493574611842632
2023-01-22 18:04:33.090069: step: 604/529, loss: 0.006767883896827698
2023-01-22 18:04:34.238319: step: 608/529, loss: 0.011909508146345615
2023-01-22 18:04:35.341188: step: 612/529, loss: 0.001967308111488819
2023-01-22 18:04:36.440421: step: 616/529, loss: 0.0036473397631198168
2023-01-22 18:04:37.554190: step: 620/529, loss: 0.010080767795443535
2023-01-22 18:04:38.672990: step: 624/529, loss: 0.0036771828308701515
2023-01-22 18:04:39.800196: step: 628/529, loss: 0.014914165250957012
2023-01-22 18:04:40.917111: step: 632/529, loss: 0.014681203290820122
2023-01-22 18:04:42.041423: step: 636/529, loss: 0.004522932693362236
2023-01-22 18:04:43.144629: step: 640/529, loss: 0.004725313279777765
2023-01-22 18:04:44.256095: step: 644/529, loss: 0.019719386473298073
2023-01-22 18:04:45.363978: step: 648/529, loss: 0.015340156853199005
2023-01-22 18:04:46.454998: step: 652/529, loss: 0.0007406998774968088
2023-01-22 18:04:47.581285: step: 656/529, loss: 0.02902970276772976
2023-01-22 18:04:48.683879: step: 660/529, loss: 0.007650643587112427
2023-01-22 18:04:49.784950: step: 664/529, loss: 0.00830087997019291
2023-01-22 18:04:50.900288: step: 668/529, loss: 0.015173443593084812
2023-01-22 18:04:52.007076: step: 672/529, loss: 0.012100734747946262
2023-01-22 18:04:53.124300: step: 676/529, loss: 0.006625749170780182
2023-01-22 18:04:54.233520: step: 680/529, loss: 0.006128285545855761
2023-01-22 18:04:55.324521: step: 684/529, loss: 0.013691570609807968
2023-01-22 18:04:56.425858: step: 688/529, loss: 0.0033774354960769415
2023-01-22 18:04:57.545294: step: 692/529, loss: 0.007560168858617544
2023-01-22 18:04:58.635878: step: 696/529, loss: 0.001372764934785664
2023-01-22 18:04:59.780290: step: 700/529, loss: 0.0024722497910261154
2023-01-22 18:05:00.912734: step: 704/529, loss: 0.005930012557655573
2023-01-22 18:05:02.033806: step: 708/529, loss: 0.012372095137834549
2023-01-22 18:05:03.146622: step: 712/529, loss: 0.01303862128406763
2023-01-22 18:05:04.263961: step: 716/529, loss: 0.004747738596051931
2023-01-22 18:05:05.362695: step: 720/529, loss: 0.009267057292163372
2023-01-22 18:05:06.464563: step: 724/529, loss: 0.01605737954378128
2023-01-22 18:05:07.584680: step: 728/529, loss: 0.038729555904865265
2023-01-22 18:05:08.710578: step: 732/529, loss: 0.008422422222793102
2023-01-22 18:05:09.861030: step: 736/529, loss: 0.03169281408190727
2023-01-22 18:05:10.957153: step: 740/529, loss: 0.00846653152257204
2023-01-22 18:05:12.052500: step: 744/529, loss: 0.015459591522812843
2023-01-22 18:05:13.143032: step: 748/529, loss: 0.004907554015517235
2023-01-22 18:05:14.253939: step: 752/529, loss: 0.015004247426986694
2023-01-22 18:05:15.337394: step: 756/529, loss: 0.012084837071597576
2023-01-22 18:05:16.433417: step: 760/529, loss: 0.005137275438755751
2023-01-22 18:05:17.558588: step: 764/529, loss: 0.004976230673491955
2023-01-22 18:05:18.669526: step: 768/529, loss: 0.005279588047415018
2023-01-22 18:05:19.768028: step: 772/529, loss: 0.018384218215942383
2023-01-22 18:05:20.889794: step: 776/529, loss: 0.007088427897542715
2023-01-22 18:05:22.007080: step: 780/529, loss: 0.02659505233168602
2023-01-22 18:05:23.107096: step: 784/529, loss: 0.008689891546964645
2023-01-22 18:05:24.223534: step: 788/529, loss: 0.014384131878614426
2023-01-22 18:05:25.337144: step: 792/529, loss: 0.014415809884667397
2023-01-22 18:05:26.450675: step: 796/529, loss: 0.007281031459569931
2023-01-22 18:05:27.553883: step: 800/529, loss: 0.0013218119274824858
2023-01-22 18:05:28.660327: step: 804/529, loss: 0.004758133087307215
2023-01-22 18:05:29.767166: step: 808/529, loss: 0.004000222310423851
2023-01-22 18:05:30.887775: step: 812/529, loss: 0.0016594043700024486
2023-01-22 18:05:31.992422: step: 816/529, loss: 0.005027247127145529
2023-01-22 18:05:33.098220: step: 820/529, loss: 0.0020168223418295383
2023-01-22 18:05:34.233832: step: 824/529, loss: 0.0061863805167376995
2023-01-22 18:05:35.366764: step: 828/529, loss: 0.0468766875565052
2023-01-22 18:05:36.479598: step: 832/529, loss: 0.01615077815949917
2023-01-22 18:05:37.582355: step: 836/529, loss: 0.0018825752194970846
2023-01-22 18:05:38.699015: step: 840/529, loss: 0.007199371699243784
2023-01-22 18:05:39.801995: step: 844/529, loss: 0.023867301642894745
2023-01-22 18:05:40.934824: step: 848/529, loss: 0.0033928307238966227
2023-01-22 18:05:42.029215: step: 852/529, loss: 0.007349400315433741
2023-01-22 18:05:43.125668: step: 856/529, loss: 0.0052449582144618034
2023-01-22 18:05:44.264492: step: 860/529, loss: 0.047246553003787994
2023-01-22 18:05:45.385307: step: 864/529, loss: 0.016368074342608452
2023-01-22 18:05:46.474596: step: 868/529, loss: 0.0006732017500326037
2023-01-22 18:05:47.591752: step: 872/529, loss: 0.0006092994590289891
2023-01-22 18:05:48.696539: step: 876/529, loss: 0.007539412006735802
2023-01-22 18:05:49.802126: step: 880/529, loss: 0.00515257753431797
2023-01-22 18:05:50.906155: step: 884/529, loss: 0.006033609621226788
2023-01-22 18:05:52.027252: step: 888/529, loss: 0.02253161370754242
2023-01-22 18:05:53.126568: step: 892/529, loss: 0.011741726659238338
2023-01-22 18:05:54.253734: step: 896/529, loss: 0.023104097694158554
2023-01-22 18:05:55.376852: step: 900/529, loss: 0.001843949081376195
2023-01-22 18:05:56.494885: step: 904/529, loss: 0.011249789968132973
2023-01-22 18:05:57.609193: step: 908/529, loss: 0.011782222427427769
2023-01-22 18:05:58.709996: step: 912/529, loss: 0.0015654019080102444
2023-01-22 18:05:59.826407: step: 916/529, loss: 0.0006320729153230786
2023-01-22 18:06:00.951549: step: 920/529, loss: 0.0006103994674049318
2023-01-22 18:06:02.072086: step: 924/529, loss: 0.0006619783816859126
2023-01-22 18:06:03.208124: step: 928/529, loss: 0.04173458367586136
2023-01-22 18:06:04.304634: step: 932/529, loss: 0.0018200431950390339
2023-01-22 18:06:05.406211: step: 936/529, loss: 0.003070810344070196
2023-01-22 18:06:06.537816: step: 940/529, loss: 0.027826832607388496
2023-01-22 18:06:07.638511: step: 944/529, loss: 0.004700905177742243
2023-01-22 18:06:08.736229: step: 948/529, loss: 0.003204314038157463
2023-01-22 18:06:09.819761: step: 952/529, loss: 0.007695063482969999
2023-01-22 18:06:10.913044: step: 956/529, loss: 0.015621177852153778
2023-01-22 18:06:12.017430: step: 960/529, loss: 0.0019094145391136408
2023-01-22 18:06:13.153571: step: 964/529, loss: 0.009083282202482224
2023-01-22 18:06:14.259301: step: 968/529, loss: 0.043462857604026794
2023-01-22 18:06:15.370977: step: 972/529, loss: 0.009487127885222435
2023-01-22 18:06:16.489674: step: 976/529, loss: 0.006757418625056744
2023-01-22 18:06:17.596975: step: 980/529, loss: 0.002615052741020918
2023-01-22 18:06:18.712262: step: 984/529, loss: 0.027554383501410484
2023-01-22 18:06:19.812380: step: 988/529, loss: 0.006075514946132898
2023-01-22 18:06:20.918591: step: 992/529, loss: 0.0023503857664763927
2023-01-22 18:06:22.068054: step: 996/529, loss: 0.011985625140368938
2023-01-22 18:06:23.185922: step: 1000/529, loss: 0.002787108300253749
2023-01-22 18:06:24.273212: step: 1004/529, loss: 0.002494698390364647
2023-01-22 18:06:25.377356: step: 1008/529, loss: 0.011006790213286877
2023-01-22 18:06:26.497030: step: 1012/529, loss: 0.009234877303242683
2023-01-22 18:06:27.608021: step: 1016/529, loss: 0.017534397542476654
2023-01-22 18:06:28.702527: step: 1020/529, loss: 0.0049636405892670155
2023-01-22 18:06:29.794713: step: 1024/529, loss: 0.014070157893002033
2023-01-22 18:06:30.881255: step: 1028/529, loss: 0.004322945140302181
2023-01-22 18:06:31.965216: step: 1032/529, loss: 0.005822870414704084
2023-01-22 18:06:33.074505: step: 1036/529, loss: 0.0006528922822326422
2023-01-22 18:06:34.201057: step: 1040/529, loss: 0.012215661816298962
2023-01-22 18:06:35.335053: step: 1044/529, loss: 0.0034096734598279
2023-01-22 18:06:36.417992: step: 1048/529, loss: 0.029845722019672394
2023-01-22 18:06:37.555143: step: 1052/529, loss: 0.0019420747412368655
2023-01-22 18:06:38.667060: step: 1056/529, loss: 0.004109000787138939
2023-01-22 18:06:39.788643: step: 1060/529, loss: 0.0018830562476068735
2023-01-22 18:06:40.922621: step: 1064/529, loss: 0.010879752226173878
2023-01-22 18:06:42.025933: step: 1068/529, loss: 0.004755171947181225
2023-01-22 18:06:43.131204: step: 1072/529, loss: 0.003979586996138096
2023-01-22 18:06:44.239549: step: 1076/529, loss: 0.0029039925429970026
2023-01-22 18:06:45.331479: step: 1080/529, loss: 0.023646049201488495
2023-01-22 18:06:46.413705: step: 1084/529, loss: 0.005364066921174526
2023-01-22 18:06:47.531085: step: 1088/529, loss: 0.022765837609767914
2023-01-22 18:06:48.642168: step: 1092/529, loss: 0.003873299341648817
2023-01-22 18:06:49.746271: step: 1096/529, loss: 0.07777158170938492
2023-01-22 18:06:50.865069: step: 1100/529, loss: 0.004754194524139166
2023-01-22 18:06:51.959592: step: 1104/529, loss: 0.003386830212548375
2023-01-22 18:06:53.078070: step: 1108/529, loss: 0.004941062536090612
2023-01-22 18:06:54.166037: step: 1112/529, loss: 0.0022608221042901278
2023-01-22 18:06:55.253930: step: 1116/529, loss: 0.00821454543620348
2023-01-22 18:06:56.355741: step: 1120/529, loss: 0.0009982504416257143
2023-01-22 18:06:57.458539: step: 1124/529, loss: 0.010671604424715042
2023-01-22 18:06:58.554627: step: 1128/529, loss: 0.008055897429585457
2023-01-22 18:06:59.657876: step: 1132/529, loss: 0.003617270849645138
2023-01-22 18:07:00.778857: step: 1136/529, loss: 0.005921605974435806
2023-01-22 18:07:01.896546: step: 1140/529, loss: 0.009792027063667774
2023-01-22 18:07:03.001960: step: 1144/529, loss: 0.00025737128453329206
2023-01-22 18:07:04.111493: step: 1148/529, loss: 0.018879905343055725
2023-01-22 18:07:05.214928: step: 1152/529, loss: 0.0023168388288468122
2023-01-22 18:07:06.334257: step: 1156/529, loss: 0.00943329930305481
2023-01-22 18:07:07.428074: step: 1160/529, loss: 0.004371060524135828
2023-01-22 18:07:08.533715: step: 1164/529, loss: 0.029411058872938156
2023-01-22 18:07:09.663691: step: 1168/529, loss: 0.006453365087509155
2023-01-22 18:07:10.777453: step: 1172/529, loss: 0.0024740700609982014
2023-01-22 18:07:11.881753: step: 1176/529, loss: 0.0055062188766896725
2023-01-22 18:07:13.010965: step: 1180/529, loss: 0.003045261837542057
2023-01-22 18:07:14.107080: step: 1184/529, loss: 0.009807714261114597
2023-01-22 18:07:15.219025: step: 1188/529, loss: 0.0062722801230847836
2023-01-22 18:07:16.330294: step: 1192/529, loss: 0.01675247959792614
2023-01-22 18:07:17.459242: step: 1196/529, loss: 0.012035599909722805
2023-01-22 18:07:18.551509: step: 1200/529, loss: 0.005240924656391144
2023-01-22 18:07:19.658404: step: 1204/529, loss: 0.0027321672532707453
2023-01-22 18:07:20.769513: step: 1208/529, loss: 0.01981533132493496
2023-01-22 18:07:21.893300: step: 1212/529, loss: 0.00643549719825387
2023-01-22 18:07:22.992758: step: 1216/529, loss: 0.00613400200381875
2023-01-22 18:07:24.110990: step: 1220/529, loss: 0.03553798794746399
2023-01-22 18:07:25.215827: step: 1224/529, loss: 0.005869312211871147
2023-01-22 18:07:26.325295: step: 1228/529, loss: 0.005721408873796463
2023-01-22 18:07:27.453492: step: 1232/529, loss: 0.0073846555314958096
2023-01-22 18:07:28.550109: step: 1236/529, loss: 0.005948214791715145
2023-01-22 18:07:29.659366: step: 1240/529, loss: 0.01719503290951252
2023-01-22 18:07:30.756187: step: 1244/529, loss: 0.003266494255512953
2023-01-22 18:07:31.870914: step: 1248/529, loss: 0.005929171573370695
2023-01-22 18:07:32.978234: step: 1252/529, loss: 0.012173418886959553
2023-01-22 18:07:34.078143: step: 1256/529, loss: 0.0011466162977740169
2023-01-22 18:07:35.197279: step: 1260/529, loss: 0.03339709714055061
2023-01-22 18:07:36.293916: step: 1264/529, loss: 0.0028979526832699776
2023-01-22 18:07:37.412583: step: 1268/529, loss: 0.0034387765917927027
2023-01-22 18:07:38.533363: step: 1272/529, loss: 0.007735791150480509
2023-01-22 18:07:39.628677: step: 1276/529, loss: 0.0007798764854669571
2023-01-22 18:07:40.726967: step: 1280/529, loss: 0.0102445799857378
2023-01-22 18:07:41.854700: step: 1284/529, loss: 0.024405132979154587
2023-01-22 18:07:42.955077: step: 1288/529, loss: 0.02438303641974926
2023-01-22 18:07:44.071165: step: 1292/529, loss: 0.005531249567866325
2023-01-22 18:07:45.178535: step: 1296/529, loss: 0.009823341853916645
2023-01-22 18:07:46.295298: step: 1300/529, loss: 0.013877890072762966
2023-01-22 18:07:47.397341: step: 1304/529, loss: 0.013430802151560783
2023-01-22 18:07:48.528127: step: 1308/529, loss: 0.001124147092923522
2023-01-22 18:07:49.632321: step: 1312/529, loss: 0.005993430502712727
2023-01-22 18:07:50.737110: step: 1316/529, loss: 0.008682730607688427
2023-01-22 18:07:51.845785: step: 1320/529, loss: 0.007739542983472347
2023-01-22 18:07:52.972795: step: 1324/529, loss: 0.014505354687571526
2023-01-22 18:07:54.088297: step: 1328/529, loss: 0.01330857165157795
2023-01-22 18:07:55.184888: step: 1332/529, loss: 0.005377857945859432
2023-01-22 18:07:56.323967: step: 1336/529, loss: 0.00721074640750885
2023-01-22 18:07:57.419990: step: 1340/529, loss: 0.010000079870223999
2023-01-22 18:07:58.543440: step: 1344/529, loss: 0.0793629065155983
2023-01-22 18:07:59.665499: step: 1348/529, loss: 0.01986638642847538
2023-01-22 18:08:00.792404: step: 1352/529, loss: 0.009433782659471035
2023-01-22 18:08:01.932573: step: 1356/529, loss: 0.013776114210486412
2023-01-22 18:08:03.032647: step: 1360/529, loss: 0.008588962256908417
2023-01-22 18:08:04.127412: step: 1364/529, loss: 0.01841878890991211
2023-01-22 18:08:05.251120: step: 1368/529, loss: 0.011485453695058823
2023-01-22 18:08:06.376480: step: 1372/529, loss: 0.006351157557219267
2023-01-22 18:08:07.499182: step: 1376/529, loss: 0.004423793870955706
2023-01-22 18:08:08.617412: step: 1380/529, loss: 0.0011480154935270548
2023-01-22 18:08:09.736081: step: 1384/529, loss: 0.0015239579370245337
2023-01-22 18:08:10.847660: step: 1388/529, loss: 0.00700216693803668
2023-01-22 18:08:11.969695: step: 1392/529, loss: 0.0028549358248710632
2023-01-22 18:08:13.119880: step: 1396/529, loss: 0.0052362107671797276
2023-01-22 18:08:14.208856: step: 1400/529, loss: 0.013613940216600895
2023-01-22 18:08:15.331424: step: 1404/529, loss: 0.00564269395545125
2023-01-22 18:08:16.423734: step: 1408/529, loss: 0.0034030135720968246
2023-01-22 18:08:17.533039: step: 1412/529, loss: 0.037433601915836334
2023-01-22 18:08:18.615670: step: 1416/529, loss: 0.007563753519207239
2023-01-22 18:08:19.713682: step: 1420/529, loss: 0.010072696954011917
2023-01-22 18:08:20.818004: step: 1424/529, loss: 0.05938692390918732
2023-01-22 18:08:21.915635: step: 1428/529, loss: 0.003408244112506509
2023-01-22 18:08:23.076646: step: 1432/529, loss: 0.0016683181747794151
2023-01-22 18:08:24.196631: step: 1436/529, loss: 0.025166237726807594
2023-01-22 18:08:25.322498: step: 1440/529, loss: 0.011587515473365784
2023-01-22 18:08:26.420745: step: 1444/529, loss: 0.0030882249120622873
2023-01-22 18:08:27.555274: step: 1448/529, loss: 0.01331456657499075
2023-01-22 18:08:28.665174: step: 1452/529, loss: 0.004248378798365593
2023-01-22 18:08:29.777918: step: 1456/529, loss: 0.009153674356639385
2023-01-22 18:08:30.881874: step: 1460/529, loss: 0.0015225185779854655
2023-01-22 18:08:31.973255: step: 1464/529, loss: 0.0013907576212659478
2023-01-22 18:08:33.082119: step: 1468/529, loss: 0.021544748917222023
2023-01-22 18:08:34.168860: step: 1472/529, loss: 0.006420893594622612
2023-01-22 18:08:35.295382: step: 1476/529, loss: 0.026873959228396416
2023-01-22 18:08:36.410333: step: 1480/529, loss: 0.007260599639266729
2023-01-22 18:08:37.522989: step: 1484/529, loss: 0.008032262325286865
2023-01-22 18:08:38.625437: step: 1488/529, loss: 0.012603539042174816
2023-01-22 18:08:39.712868: step: 1492/529, loss: 0.02796679362654686
2023-01-22 18:08:40.815804: step: 1496/529, loss: 0.04258495196700096
2023-01-22 18:08:41.900830: step: 1500/529, loss: 0.002948765642940998
2023-01-22 18:08:42.992738: step: 1504/529, loss: 0.010979026556015015
2023-01-22 18:08:44.097988: step: 1508/529, loss: 0.02838038094341755
2023-01-22 18:08:45.211502: step: 1512/529, loss: 0.0045903087593615055
2023-01-22 18:08:46.353321: step: 1516/529, loss: 0.0034501003101468086
2023-01-22 18:08:47.472631: step: 1520/529, loss: 0.009295562282204628
2023-01-22 18:08:48.556420: step: 1524/529, loss: 0.007982209324836731
2023-01-22 18:08:49.692399: step: 1528/529, loss: 0.009216131642460823
2023-01-22 18:08:50.790362: step: 1532/529, loss: 0.0062230974435806274
2023-01-22 18:08:51.889564: step: 1536/529, loss: 0.007723563816398382
2023-01-22 18:08:52.981898: step: 1540/529, loss: 0.02216295152902603
2023-01-22 18:08:54.107638: step: 1544/529, loss: 0.012259969487786293
2023-01-22 18:08:55.229873: step: 1548/529, loss: 0.006923162844032049
2023-01-22 18:08:56.334371: step: 1552/529, loss: 0.0070540281012654305
2023-01-22 18:08:57.444912: step: 1556/529, loss: 0.007882323116064072
2023-01-22 18:08:58.569209: step: 1560/529, loss: 0.011779258027672768
2023-01-22 18:08:59.698337: step: 1564/529, loss: 0.01809048093855381
2023-01-22 18:09:00.805666: step: 1568/529, loss: 0.006148052867501974
2023-01-22 18:09:01.931093: step: 1572/529, loss: 0.008603012189269066
2023-01-22 18:09:03.059226: step: 1576/529, loss: 0.013636457733809948
2023-01-22 18:09:04.165424: step: 1580/529, loss: 0.011089447885751724
2023-01-22 18:09:05.312468: step: 1584/529, loss: 0.0035017789341509342
2023-01-22 18:09:06.441100: step: 1588/529, loss: 0.005013898015022278
2023-01-22 18:09:07.565664: step: 1592/529, loss: 0.02697349712252617
2023-01-22 18:09:08.679579: step: 1596/529, loss: 0.00529640493914485
2023-01-22 18:09:09.780515: step: 1600/529, loss: 0.0013109358260408044
2023-01-22 18:09:10.870940: step: 1604/529, loss: 0.016566354781389236
2023-01-22 18:09:11.988411: step: 1608/529, loss: 0.0010960629442706704
2023-01-22 18:09:13.098392: step: 1612/529, loss: 0.023096466436982155
2023-01-22 18:09:14.193621: step: 1616/529, loss: 0.010913442820310593
2023-01-22 18:09:15.320624: step: 1620/529, loss: 0.003063932992517948
2023-01-22 18:09:16.413119: step: 1624/529, loss: 0.025128396227955818
2023-01-22 18:09:17.509642: step: 1628/529, loss: 0.002802146365866065
2023-01-22 18:09:18.641129: step: 1632/529, loss: 0.005906732752919197
2023-01-22 18:09:19.738683: step: 1636/529, loss: 0.00568888895213604
2023-01-22 18:09:20.830263: step: 1640/529, loss: 0.004543485585600138
2023-01-22 18:09:21.946002: step: 1644/529, loss: 0.008256948553025723
2023-01-22 18:09:23.081859: step: 1648/529, loss: 0.007747428957372904
2023-01-22 18:09:24.184585: step: 1652/529, loss: 0.10541478544473648
2023-01-22 18:09:25.295710: step: 1656/529, loss: 0.006871631368994713
2023-01-22 18:09:26.413511: step: 1660/529, loss: 0.025203751400113106
2023-01-22 18:09:27.534006: step: 1664/529, loss: 0.007733407896012068
2023-01-22 18:09:28.650122: step: 1668/529, loss: 0.04675344377756119
2023-01-22 18:09:29.757011: step: 1672/529, loss: 0.005513573531061411
2023-01-22 18:09:30.881466: step: 1676/529, loss: 0.07805713266134262
2023-01-22 18:09:32.006689: step: 1680/529, loss: 0.003588608233258128
2023-01-22 18:09:33.143850: step: 1684/529, loss: 0.012582805007696152
2023-01-22 18:09:34.233656: step: 1688/529, loss: 0.013945032842457294
2023-01-22 18:09:35.414989: step: 1692/529, loss: 0.009176121093332767
2023-01-22 18:09:36.510732: step: 1696/529, loss: 0.0031222852412611246
2023-01-22 18:09:37.643535: step: 1700/529, loss: 0.00455207284539938
2023-01-22 18:09:38.747688: step: 1704/529, loss: 0.020229320973157883
2023-01-22 18:09:39.849387: step: 1708/529, loss: 0.019096320495009422
2023-01-22 18:09:40.965879: step: 1712/529, loss: 0.002913964679464698
2023-01-22 18:09:42.091755: step: 1716/529, loss: 0.004774861503392458
2023-01-22 18:09:43.228179: step: 1720/529, loss: 0.01010191347450018
2023-01-22 18:09:44.333162: step: 1724/529, loss: 0.006422301754355431
2023-01-22 18:09:45.418407: step: 1728/529, loss: 0.0012197574833407998
2023-01-22 18:09:46.528947: step: 1732/529, loss: 0.03624510392546654
2023-01-22 18:09:47.635154: step: 1736/529, loss: 0.0015528395306318998
2023-01-22 18:09:48.747908: step: 1740/529, loss: 0.030464252457022667
2023-01-22 18:09:49.857545: step: 1744/529, loss: 0.007331118918955326
2023-01-22 18:09:50.968204: step: 1748/529, loss: 0.004446009639650583
2023-01-22 18:09:52.070100: step: 1752/529, loss: 0.013871542178094387
2023-01-22 18:09:53.162358: step: 1756/529, loss: 0.00801624171435833
2023-01-22 18:09:54.288832: step: 1760/529, loss: 0.009121090173721313
2023-01-22 18:09:55.405824: step: 1764/529, loss: 0.013125907629728317
2023-01-22 18:09:56.504776: step: 1768/529, loss: 0.003242954146116972
2023-01-22 18:09:57.595371: step: 1772/529, loss: 0.00848349928855896
2023-01-22 18:09:58.715543: step: 1776/529, loss: 0.0009747439180500805
2023-01-22 18:09:59.824245: step: 1780/529, loss: 0.005255571566522121
2023-01-22 18:10:00.925969: step: 1784/529, loss: 0.010217031463980675
2023-01-22 18:10:02.047534: step: 1788/529, loss: 0.004849220160394907
2023-01-22 18:10:03.155153: step: 1792/529, loss: 0.008044778369367123
2023-01-22 18:10:04.268757: step: 1796/529, loss: 0.004802039358764887
2023-01-22 18:10:05.369814: step: 1800/529, loss: 0.00802613515406847
2023-01-22 18:10:06.489797: step: 1804/529, loss: 0.024547182023525238
2023-01-22 18:10:07.623948: step: 1808/529, loss: 0.002114079426974058
2023-01-22 18:10:08.710310: step: 1812/529, loss: 0.0035180984996259212
2023-01-22 18:10:09.881995: step: 1816/529, loss: 0.004937905818223953
2023-01-22 18:10:11.012374: step: 1820/529, loss: 0.0801788792014122
2023-01-22 18:10:12.122567: step: 1824/529, loss: 0.006303454749286175
2023-01-22 18:10:13.224743: step: 1828/529, loss: 0.01919054053723812
2023-01-22 18:10:14.333903: step: 1832/529, loss: 0.010505234822630882
2023-01-22 18:10:15.436421: step: 1836/529, loss: 0.007829022593796253
2023-01-22 18:10:16.543262: step: 1840/529, loss: 0.004391024820506573
2023-01-22 18:10:17.692364: step: 1844/529, loss: 0.009637479670345783
2023-01-22 18:10:18.783244: step: 1848/529, loss: 0.004310734570026398
2023-01-22 18:10:19.896367: step: 1852/529, loss: 0.004676748067140579
2023-01-22 18:10:21.019445: step: 1856/529, loss: 0.011473938822746277
2023-01-22 18:10:22.149055: step: 1860/529, loss: 0.036824990063905716
2023-01-22 18:10:23.261765: step: 1864/529, loss: 0.04672694578766823
2023-01-22 18:10:24.357169: step: 1868/529, loss: 0.006650257855653763
2023-01-22 18:10:25.473796: step: 1872/529, loss: 0.008425585925579071
2023-01-22 18:10:26.572912: step: 1876/529, loss: 0.01584876887500286
2023-01-22 18:10:27.671006: step: 1880/529, loss: 0.01270376332104206
2023-01-22 18:10:28.802580: step: 1884/529, loss: 0.03829373046755791
2023-01-22 18:10:29.905333: step: 1888/529, loss: 0.007096637040376663
2023-01-22 18:10:31.010353: step: 1892/529, loss: 0.0025302814319729805
2023-01-22 18:10:32.131554: step: 1896/529, loss: 0.00885958131402731
2023-01-22 18:10:33.247968: step: 1900/529, loss: 0.00826589297503233
2023-01-22 18:10:34.386377: step: 1904/529, loss: 0.004876809194684029
2023-01-22 18:10:35.519833: step: 1908/529, loss: 0.009124829433858395
2023-01-22 18:10:36.657255: step: 1912/529, loss: 0.02632630430161953
2023-01-22 18:10:37.771473: step: 1916/529, loss: 0.026951950043439865
2023-01-22 18:10:38.883066: step: 1920/529, loss: 0.0031709198374301195
2023-01-22 18:10:39.970528: step: 1924/529, loss: 0.01729685068130493
2023-01-22 18:10:41.076960: step: 1928/529, loss: 0.012684958055615425
2023-01-22 18:10:42.173522: step: 1932/529, loss: 0.023566385731101036
2023-01-22 18:10:43.270932: step: 1936/529, loss: 0.0077592674642801285
2023-01-22 18:10:44.399449: step: 1940/529, loss: 0.00289820390753448
2023-01-22 18:10:45.514742: step: 1944/529, loss: 0.006311857141554356
2023-01-22 18:10:46.620014: step: 1948/529, loss: 0.011788878589868546
2023-01-22 18:10:47.717978: step: 1952/529, loss: 0.01812565326690674
2023-01-22 18:10:48.813131: step: 1956/529, loss: 0.006139983888715506
2023-01-22 18:10:49.946569: step: 1960/529, loss: 0.018636690452694893
2023-01-22 18:10:51.058230: step: 1964/529, loss: 0.01315061654895544
2023-01-22 18:10:52.160965: step: 1968/529, loss: 0.021629182621836662
2023-01-22 18:10:53.283367: step: 1972/529, loss: 0.008680710569024086
2023-01-22 18:10:54.399566: step: 1976/529, loss: 0.017384130507707596
2023-01-22 18:10:55.516531: step: 1980/529, loss: 0.010095778852701187
2023-01-22 18:10:56.616085: step: 1984/529, loss: 0.007660235278308392
2023-01-22 18:10:57.732017: step: 1988/529, loss: 0.0465189553797245
2023-01-22 18:10:58.851671: step: 1992/529, loss: 0.01181329507380724
2023-01-22 18:10:59.951909: step: 1996/529, loss: 0.016556112095713615
2023-01-22 18:11:01.070264: step: 2000/529, loss: 0.011529793031513691
2023-01-22 18:11:02.189375: step: 2004/529, loss: 0.007618979085236788
2023-01-22 18:11:03.315392: step: 2008/529, loss: 0.0010885146912187338
2023-01-22 18:11:04.425646: step: 2012/529, loss: 0.004776259884238243
2023-01-22 18:11:05.554725: step: 2016/529, loss: 0.008826421573758125
2023-01-22 18:11:06.674321: step: 2020/529, loss: 0.008537566289305687
2023-01-22 18:11:07.749134: step: 2024/529, loss: 0.005056292749941349
2023-01-22 18:11:08.858635: step: 2028/529, loss: 0.051317837089300156
2023-01-22 18:11:09.971593: step: 2032/529, loss: 0.003719034604728222
2023-01-22 18:11:11.093443: step: 2036/529, loss: 0.00966801866889
2023-01-22 18:11:12.218721: step: 2040/529, loss: 0.027603691443800926
2023-01-22 18:11:13.332712: step: 2044/529, loss: 0.003011699067428708
2023-01-22 18:11:14.440846: step: 2048/529, loss: 0.004103096202015877
2023-01-22 18:11:15.554174: step: 2052/529, loss: 0.023153744637966156
2023-01-22 18:11:16.658898: step: 2056/529, loss: 0.004259122535586357
2023-01-22 18:11:17.781787: step: 2060/529, loss: 0.009866988286376
2023-01-22 18:11:18.884481: step: 2064/529, loss: 0.042463310062885284
2023-01-22 18:11:20.012189: step: 2068/529, loss: 0.01186918094754219
2023-01-22 18:11:21.129324: step: 2072/529, loss: 0.007165533024817705
2023-01-22 18:11:22.253308: step: 2076/529, loss: 0.005914414767175913
2023-01-22 18:11:23.358209: step: 2080/529, loss: 0.042310621589422226
2023-01-22 18:11:24.455415: step: 2084/529, loss: 0.018507735803723335
2023-01-22 18:11:25.575645: step: 2088/529, loss: 0.004264832008630037
2023-01-22 18:11:26.683779: step: 2092/529, loss: 0.0018066433258354664
2023-01-22 18:11:27.773536: step: 2096/529, loss: 0.004704984836280346
2023-01-22 18:11:28.888549: step: 2100/529, loss: 0.0033289070706814528
2023-01-22 18:11:29.987863: step: 2104/529, loss: 0.010304669849574566
2023-01-22 18:11:31.092239: step: 2108/529, loss: 0.0009273941395804286
2023-01-22 18:11:32.192577: step: 2112/529, loss: 0.031020477414131165
2023-01-22 18:11:33.316569: step: 2116/529, loss: 0.006843178067356348
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33112561341330427, 'r': 0.32924064787205204, 'f1': 0.3301804403969009}, 'combined': 0.24329085081876908, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3733486266441867, 'r': 0.2947318881047262, 'f1': 0.3294146236056698}, 'combined': 0.20246947597226533, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33287760034083563, 'r': 0.3448788800495185, 'f1': 0.33877198468983455}, 'combined': 0.24962146240303598, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3536865616745893, 'r': 0.3077134384066617, 'f1': 0.32910223162306546}, 'combined': 0.2022774691927134, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35185185185185186, 'r': 0.41304347826086957, 'f1': 0.38}, 'combined': 0.19, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 5
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 18:14:10.498947: step: 4/529, loss: 0.005944020580500364
2023-01-22 18:14:11.574844: step: 8/529, loss: 0.011787398718297482
2023-01-22 18:14:12.699429: step: 12/529, loss: 0.019872264936566353
2023-01-22 18:14:13.783563: step: 16/529, loss: 0.006311553996056318
2023-01-22 18:14:14.895281: step: 20/529, loss: 0.008970057591795921
2023-01-22 18:14:16.013014: step: 24/529, loss: 0.008300280198454857
2023-01-22 18:14:17.110761: step: 28/529, loss: 0.06833744049072266
2023-01-22 18:14:18.215858: step: 32/529, loss: 0.007676275447010994
2023-01-22 18:14:19.319237: step: 36/529, loss: 0.003142870496958494
2023-01-22 18:14:20.441906: step: 40/529, loss: 0.0048203133046627045
2023-01-22 18:14:21.569534: step: 44/529, loss: 0.02962135709822178
2023-01-22 18:14:22.680691: step: 48/529, loss: 0.005699853878468275
2023-01-22 18:14:23.805472: step: 52/529, loss: 0.004656209610402584
2023-01-22 18:14:24.893829: step: 56/529, loss: 0.0052919150330126286
2023-01-22 18:14:25.995613: step: 60/529, loss: 0.0022464075591415167
2023-01-22 18:14:27.081697: step: 64/529, loss: 0.01805340126156807
2023-01-22 18:14:28.168693: step: 68/529, loss: 0.002308015478774905
2023-01-22 18:14:29.252411: step: 72/529, loss: 0.010844535194337368
2023-01-22 18:14:30.364431: step: 76/529, loss: 0.0033897694665938616
2023-01-22 18:14:31.476234: step: 80/529, loss: 0.0011145416647195816
2023-01-22 18:14:32.597251: step: 84/529, loss: 0.003024139441549778
2023-01-22 18:14:33.713348: step: 88/529, loss: 0.004455516114830971
2023-01-22 18:14:34.795208: step: 92/529, loss: 0.00550863379612565
2023-01-22 18:14:35.913686: step: 96/529, loss: 0.02512248605489731
2023-01-22 18:14:37.032365: step: 100/529, loss: 0.000620989827439189
2023-01-22 18:14:38.144869: step: 104/529, loss: 0.002236340194940567
2023-01-22 18:14:39.237810: step: 108/529, loss: 0.004120348487049341
2023-01-22 18:14:40.343246: step: 112/529, loss: 0.005151495337486267
2023-01-22 18:14:41.440246: step: 116/529, loss: 0.013392942026257515
2023-01-22 18:14:42.551288: step: 120/529, loss: 0.009640827775001526
2023-01-22 18:14:43.641824: step: 124/529, loss: 0.009736905805766582
2023-01-22 18:14:44.758406: step: 128/529, loss: 0.002396953059360385
2023-01-22 18:14:45.861253: step: 132/529, loss: 0.007673532702028751
2023-01-22 18:14:46.978007: step: 136/529, loss: 0.013402070850133896
2023-01-22 18:14:48.086909: step: 140/529, loss: 0.01039112638682127
2023-01-22 18:14:49.208826: step: 144/529, loss: 0.002605579560622573
2023-01-22 18:14:50.307646: step: 148/529, loss: 0.0053550610318779945
2023-01-22 18:14:51.394930: step: 152/529, loss: 0.012103062123060226
2023-01-22 18:14:52.506329: step: 156/529, loss: 0.005834732670336962
2023-01-22 18:14:53.612799: step: 160/529, loss: 0.0028534966986626387
2023-01-22 18:14:54.709429: step: 164/529, loss: 0.0037074636202305555
2023-01-22 18:14:55.817829: step: 168/529, loss: 0.014147473499178886
2023-01-22 18:14:56.920339: step: 172/529, loss: 0.0016528520500287414
2023-01-22 18:14:58.040635: step: 176/529, loss: 0.003087915712967515
2023-01-22 18:14:59.151950: step: 180/529, loss: 0.006248785182833672
2023-01-22 18:15:00.266296: step: 184/529, loss: 0.0022147647105157375
2023-01-22 18:15:01.372280: step: 188/529, loss: 0.004827729891985655
2023-01-22 18:15:02.485068: step: 192/529, loss: 0.004445627331733704
2023-01-22 18:15:03.571461: step: 196/529, loss: 0.01315377838909626
2023-01-22 18:15:04.704482: step: 200/529, loss: 0.012174738571047783
2023-01-22 18:15:05.782444: step: 204/529, loss: 0.017549565061926842
2023-01-22 18:15:06.918250: step: 208/529, loss: 0.025793110951781273
2023-01-22 18:15:08.039770: step: 212/529, loss: 0.029153136536478996
2023-01-22 18:15:09.166822: step: 216/529, loss: 0.011854974552989006
2023-01-22 18:15:10.278788: step: 220/529, loss: 0.009827900677919388
2023-01-22 18:15:11.388811: step: 224/529, loss: 0.005242019891738892
2023-01-22 18:15:12.508998: step: 228/529, loss: 0.003118621651083231
2023-01-22 18:15:13.643429: step: 232/529, loss: 0.030991079285740852
2023-01-22 18:15:14.770925: step: 236/529, loss: 0.012195030227303505
2023-01-22 18:15:15.866893: step: 240/529, loss: 0.0043490249663591385
2023-01-22 18:15:16.989219: step: 244/529, loss: 0.0078894617035985
2023-01-22 18:15:18.099696: step: 248/529, loss: 0.011463350616395473
2023-01-22 18:15:19.231008: step: 252/529, loss: 0.007622966542840004
2023-01-22 18:15:20.342400: step: 256/529, loss: 0.006223446689546108
2023-01-22 18:15:21.445788: step: 260/529, loss: 0.015137385576963425
2023-01-22 18:15:22.541012: step: 264/529, loss: 0.00604736665263772
2023-01-22 18:15:23.670852: step: 268/529, loss: 0.00420906487852335
2023-01-22 18:15:24.754415: step: 272/529, loss: 0.0071423714980483055
2023-01-22 18:15:25.843279: step: 276/529, loss: 0.0020656504202634096
2023-01-22 18:15:26.943476: step: 280/529, loss: 0.008240027353167534
2023-01-22 18:15:28.040925: step: 284/529, loss: 0.021565720438957214
2023-01-22 18:15:29.185199: step: 288/529, loss: 0.019359055906534195
2023-01-22 18:15:30.309027: step: 292/529, loss: 0.007886834442615509
2023-01-22 18:15:31.397321: step: 296/529, loss: 0.0012284136610105634
2023-01-22 18:15:32.504831: step: 300/529, loss: 0.005962691735476255
2023-01-22 18:15:33.613463: step: 304/529, loss: 0.0025677671656012535
2023-01-22 18:15:34.731824: step: 308/529, loss: 0.010364501737058163
2023-01-22 18:15:35.850664: step: 312/529, loss: 0.019816305488348007
2023-01-22 18:15:36.959200: step: 316/529, loss: 0.011486060917377472
2023-01-22 18:15:38.064183: step: 320/529, loss: 0.00010884933726629242
2023-01-22 18:15:39.169792: step: 324/529, loss: 0.008167089894413948
2023-01-22 18:15:40.269632: step: 328/529, loss: 0.004088517278432846
2023-01-22 18:15:41.367299: step: 332/529, loss: 0.010634136386215687
2023-01-22 18:15:42.484299: step: 336/529, loss: 0.003961325157433748
2023-01-22 18:15:43.582910: step: 340/529, loss: 0.0021540720481425524
2023-01-22 18:15:44.692006: step: 344/529, loss: 0.0035539381206035614
2023-01-22 18:15:45.798001: step: 348/529, loss: 0.0037011802196502686
2023-01-22 18:15:46.900641: step: 352/529, loss: 0.006871826481074095
2023-01-22 18:15:48.015452: step: 356/529, loss: 0.004165771417319775
2023-01-22 18:15:49.135405: step: 360/529, loss: 0.008932098746299744
2023-01-22 18:15:50.221619: step: 364/529, loss: 0.011896781623363495
2023-01-22 18:15:51.320532: step: 368/529, loss: 0.0013712149811908603
2023-01-22 18:15:52.432324: step: 372/529, loss: 0.008989798836410046
2023-01-22 18:15:53.549615: step: 376/529, loss: 0.00463844882324338
2023-01-22 18:15:54.667239: step: 380/529, loss: 0.005348381120711565
2023-01-22 18:15:55.792468: step: 384/529, loss: 0.0030955979600548744
2023-01-22 18:15:56.884043: step: 388/529, loss: 0.004573538433760405
2023-01-22 18:15:57.991429: step: 392/529, loss: 0.0
2023-01-22 18:15:59.097403: step: 396/529, loss: 0.0076035400852561
2023-01-22 18:16:00.222292: step: 400/529, loss: 0.0024134861305356026
2023-01-22 18:16:01.346104: step: 404/529, loss: 0.006922394968569279
2023-01-22 18:16:02.450000: step: 408/529, loss: 0.0057018413208425045
2023-01-22 18:16:03.554756: step: 412/529, loss: 0.017347754910588264
2023-01-22 18:16:04.661429: step: 416/529, loss: 0.04166816920042038
2023-01-22 18:16:05.777972: step: 420/529, loss: 0.0021120202727615833
2023-01-22 18:16:06.879436: step: 424/529, loss: 0.0009686889825388789
2023-01-22 18:16:07.997684: step: 428/529, loss: 0.02227970026433468
2023-01-22 18:16:09.088064: step: 432/529, loss: 0.012530308216810226
2023-01-22 18:16:10.175513: step: 436/529, loss: 0.0006451040389947593
2023-01-22 18:16:11.299452: step: 440/529, loss: 0.01064095925539732
2023-01-22 18:16:12.378308: step: 444/529, loss: 0.0058979131281375885
2023-01-22 18:16:13.487394: step: 448/529, loss: 0.008687878027558327
2023-01-22 18:16:14.618939: step: 452/529, loss: 0.0018891702638939023
2023-01-22 18:16:15.729704: step: 456/529, loss: 0.0035672204103320837
2023-01-22 18:16:16.843555: step: 460/529, loss: 0.014552082866430283
2023-01-22 18:16:17.944035: step: 464/529, loss: 0.03941059112548828
2023-01-22 18:16:19.035521: step: 468/529, loss: 0.006344751454889774
2023-01-22 18:16:20.132013: step: 472/529, loss: 0.012980048544704914
2023-01-22 18:16:21.262110: step: 476/529, loss: 0.00494886701926589
2023-01-22 18:16:22.404459: step: 480/529, loss: 0.020085686817765236
2023-01-22 18:16:23.514350: step: 484/529, loss: 0.002725489903241396
2023-01-22 18:16:24.612847: step: 488/529, loss: 0.01815321296453476
2023-01-22 18:16:25.718044: step: 492/529, loss: 0.002221002709120512
2023-01-22 18:16:26.812411: step: 496/529, loss: 8.186974446289241e-05
2023-01-22 18:16:27.935190: step: 500/529, loss: 0.03334472328424454
2023-01-22 18:16:29.040383: step: 504/529, loss: 0.01682993210852146
2023-01-22 18:16:30.143132: step: 508/529, loss: 0.004078906495124102
2023-01-22 18:16:31.226875: step: 512/529, loss: 0.039665382355451584
2023-01-22 18:16:32.356927: step: 516/529, loss: 0.028239037841558456
2023-01-22 18:16:33.471437: step: 520/529, loss: 0.020282002165913582
2023-01-22 18:16:34.587720: step: 524/529, loss: 0.0018099588342010975
2023-01-22 18:16:35.682355: step: 528/529, loss: 0.002890066709369421
2023-01-22 18:16:36.773279: step: 532/529, loss: 0.005001302808523178
2023-01-22 18:16:37.884539: step: 536/529, loss: 0.004335480742156506
2023-01-22 18:16:38.995118: step: 540/529, loss: 0.010238793678581715
2023-01-22 18:16:40.108533: step: 544/529, loss: 0.0036698170006275177
2023-01-22 18:16:41.217579: step: 548/529, loss: 0.010645860806107521
2023-01-22 18:16:42.333459: step: 552/529, loss: 0.039910122752189636
2023-01-22 18:16:43.424287: step: 556/529, loss: 0.0036725865211337805
2023-01-22 18:16:44.518229: step: 560/529, loss: 0.03352321311831474
2023-01-22 18:16:45.637110: step: 564/529, loss: 0.01813039928674698
2023-01-22 18:16:46.740692: step: 568/529, loss: 0.01357536856085062
2023-01-22 18:16:47.832555: step: 572/529, loss: 0.006745693739503622
2023-01-22 18:16:48.944103: step: 576/529, loss: 0.0040192389860749245
2023-01-22 18:16:50.047428: step: 580/529, loss: 0.007827007211744785
2023-01-22 18:16:51.165501: step: 584/529, loss: 0.0016290126368403435
2023-01-22 18:16:52.276306: step: 588/529, loss: 0.02934255823493004
2023-01-22 18:16:53.370054: step: 592/529, loss: 0.03686949983239174
2023-01-22 18:16:54.479577: step: 596/529, loss: 0.011240099556744099
2023-01-22 18:16:55.593802: step: 600/529, loss: 0.0019065714441239834
2023-01-22 18:16:56.694119: step: 604/529, loss: 0.004999896045774221
2023-01-22 18:16:57.811847: step: 608/529, loss: 0.04072859510779381
2023-01-22 18:16:58.932943: step: 612/529, loss: 0.0171133391559124
2023-01-22 18:17:00.038518: step: 616/529, loss: 0.006937309168279171
2023-01-22 18:17:01.136179: step: 620/529, loss: 0.014709793031215668
2023-01-22 18:17:02.241937: step: 624/529, loss: 0.00959252379834652
2023-01-22 18:17:03.382333: step: 628/529, loss: 0.02299790270626545
2023-01-22 18:17:04.490390: step: 632/529, loss: 0.0024731531739234924
2023-01-22 18:17:05.608583: step: 636/529, loss: 0.012275369837880135
2023-01-22 18:17:06.723333: step: 640/529, loss: 0.006461271550506353
2023-01-22 18:17:07.850191: step: 644/529, loss: 0.007846472784876823
2023-01-22 18:17:08.953835: step: 648/529, loss: 0.007151693105697632
2023-01-22 18:17:10.049272: step: 652/529, loss: 0.002280886285007
2023-01-22 18:17:11.152597: step: 656/529, loss: 0.0048790681175887585
2023-01-22 18:17:12.262765: step: 660/529, loss: 0.06166310980916023
2023-01-22 18:17:13.379386: step: 664/529, loss: 0.012223022058606148
2023-01-22 18:17:14.491112: step: 668/529, loss: 0.004073896445333958
2023-01-22 18:17:15.608236: step: 672/529, loss: 0.04534912109375
2023-01-22 18:17:16.706137: step: 676/529, loss: 0.00784063246101141
2023-01-22 18:17:17.802012: step: 680/529, loss: 0.00543764466419816
2023-01-22 18:17:18.925883: step: 684/529, loss: 0.017082558944821358
2023-01-22 18:17:20.013322: step: 688/529, loss: 0.0033302265219390392
2023-01-22 18:17:21.142499: step: 692/529, loss: 0.01859324239194393
2023-01-22 18:17:22.274203: step: 696/529, loss: 0.005464591085910797
2023-01-22 18:17:23.361907: step: 700/529, loss: 0.004670901224017143
2023-01-22 18:17:24.477402: step: 704/529, loss: 0.019552048295736313
2023-01-22 18:17:25.587788: step: 708/529, loss: 0.01808786392211914
2023-01-22 18:17:26.713210: step: 712/529, loss: 0.002900754800066352
2023-01-22 18:17:27.805382: step: 716/529, loss: 0.0007903499063104391
2023-01-22 18:17:28.930085: step: 720/529, loss: 0.012239975854754448
2023-01-22 18:17:30.026859: step: 724/529, loss: 0.008969036862254143
2023-01-22 18:17:31.129398: step: 728/529, loss: 0.0053934622555971146
2023-01-22 18:17:32.237554: step: 732/529, loss: 0.019142204895615578
2023-01-22 18:17:33.335713: step: 736/529, loss: 0.007520847953855991
2023-01-22 18:17:34.470321: step: 740/529, loss: 0.011696289293467999
2023-01-22 18:17:35.568855: step: 744/529, loss: 0.04023462533950806
2023-01-22 18:17:36.705575: step: 748/529, loss: 0.005143493413925171
2023-01-22 18:17:37.811543: step: 752/529, loss: 0.012811396270990372
2023-01-22 18:17:38.938222: step: 756/529, loss: 0.0027981214225292206
2023-01-22 18:17:40.065562: step: 760/529, loss: 1.410916775057558e-05
2023-01-22 18:17:41.170233: step: 764/529, loss: 0.02011924237012863
2023-01-22 18:17:42.272439: step: 768/529, loss: 0.001113583450205624
2023-01-22 18:17:43.408698: step: 772/529, loss: 0.0010251770727336407
2023-01-22 18:17:44.529353: step: 776/529, loss: 0.03435317799448967
2023-01-22 18:17:45.644814: step: 780/529, loss: 0.020054392516613007
2023-01-22 18:17:46.734887: step: 784/529, loss: 0.0007251350907608867
2023-01-22 18:17:47.838518: step: 788/529, loss: 0.004094707313925028
2023-01-22 18:17:48.939329: step: 792/529, loss: 0.0008153258240781724
2023-01-22 18:17:50.067034: step: 796/529, loss: 0.03480057045817375
2023-01-22 18:17:51.174171: step: 800/529, loss: 0.01276328694075346
2023-01-22 18:17:52.291170: step: 804/529, loss: 0.0058260331861674786
2023-01-22 18:17:53.384583: step: 808/529, loss: 0.014401491731405258
2023-01-22 18:17:54.478862: step: 812/529, loss: 0.0006542746559716761
2023-01-22 18:17:55.564852: step: 816/529, loss: 0.006432477850466967
2023-01-22 18:17:56.657317: step: 820/529, loss: 0.00623157387599349
2023-01-22 18:17:57.762780: step: 824/529, loss: 0.09228091686964035
2023-01-22 18:17:58.874476: step: 828/529, loss: 0.011270182207226753
2023-01-22 18:17:59.976632: step: 832/529, loss: 0.012300697155296803
2023-01-22 18:18:01.092814: step: 836/529, loss: 0.0032369368709623814
2023-01-22 18:18:02.193231: step: 840/529, loss: 0.015315155498683453
2023-01-22 18:18:03.305935: step: 844/529, loss: 0.0059449211694300175
2023-01-22 18:18:04.405581: step: 848/529, loss: 0.004831463564187288
2023-01-22 18:18:05.522635: step: 852/529, loss: 0.007845873013138771
2023-01-22 18:18:06.634084: step: 856/529, loss: 0.0031097382307052612
2023-01-22 18:18:07.754345: step: 860/529, loss: 0.009619108401238918
2023-01-22 18:18:08.865236: step: 864/529, loss: 0.00813919585198164
2023-01-22 18:18:09.995025: step: 868/529, loss: 0.0012072770623490214
2023-01-22 18:18:11.107021: step: 872/529, loss: 0.0077570960856974125
2023-01-22 18:18:12.240069: step: 876/529, loss: 0.01115875132381916
2023-01-22 18:18:13.364041: step: 880/529, loss: 0.04828742891550064
2023-01-22 18:18:14.504134: step: 884/529, loss: 0.00378294731490314
2023-01-22 18:18:15.628808: step: 888/529, loss: 0.005132909864187241
2023-01-22 18:18:16.737153: step: 892/529, loss: 0.021029513329267502
2023-01-22 18:18:17.855685: step: 896/529, loss: 0.00169015780556947
2023-01-22 18:18:18.950488: step: 900/529, loss: 0.01202309038490057
2023-01-22 18:18:20.038019: step: 904/529, loss: 0.027538206428289413
2023-01-22 18:18:21.130157: step: 908/529, loss: 0.007902281358838081
2023-01-22 18:18:22.238504: step: 912/529, loss: 0.0072731212712824345
2023-01-22 18:18:23.356388: step: 916/529, loss: 0.0025516508612781763
2023-01-22 18:18:24.456691: step: 920/529, loss: 0.009487972594797611
2023-01-22 18:18:25.555017: step: 924/529, loss: 0.0033455428201705217
2023-01-22 18:18:26.643717: step: 928/529, loss: 0.005422177724540234
2023-01-22 18:18:27.789131: step: 932/529, loss: 0.016131406649947166
2023-01-22 18:18:28.886443: step: 936/529, loss: 0.046241506934165955
2023-01-22 18:18:29.999801: step: 940/529, loss: 0.0024307575076818466
2023-01-22 18:18:31.113713: step: 944/529, loss: 0.0016261221608147025
2023-01-22 18:18:32.216364: step: 948/529, loss: 0.032790955156087875
2023-01-22 18:18:33.303293: step: 952/529, loss: 0.011490444652736187
2023-01-22 18:18:34.435631: step: 956/529, loss: 0.014561083167791367
2023-01-22 18:18:35.546697: step: 960/529, loss: 0.025195373222231865
2023-01-22 18:18:36.677122: step: 964/529, loss: 0.003199903294444084
2023-01-22 18:18:37.767887: step: 968/529, loss: 0.004980687517672777
2023-01-22 18:18:38.863005: step: 972/529, loss: 0.004482956137508154
2023-01-22 18:18:39.976833: step: 976/529, loss: 0.004602277185767889
2023-01-22 18:18:41.117190: step: 980/529, loss: 0.012132798321545124
2023-01-22 18:18:42.231876: step: 984/529, loss: 0.023986024782061577
2023-01-22 18:18:43.370544: step: 988/529, loss: 0.005697285756468773
2023-01-22 18:18:44.460977: step: 992/529, loss: 0.0015940701123327017
2023-01-22 18:18:45.569548: step: 996/529, loss: 0.006752361543476582
2023-01-22 18:18:46.699929: step: 1000/529, loss: 0.007739895489066839
2023-01-22 18:18:47.811723: step: 1004/529, loss: 0.015170280821621418
2023-01-22 18:18:48.920681: step: 1008/529, loss: 0.003680730937048793
2023-01-22 18:18:50.049590: step: 1012/529, loss: 0.005778642371296883
2023-01-22 18:18:51.154664: step: 1016/529, loss: 0.007206473033875227
2023-01-22 18:18:52.259409: step: 1020/529, loss: 0.0047554741613566875
2023-01-22 18:18:53.349702: step: 1024/529, loss: 0.03196348622441292
2023-01-22 18:18:54.453240: step: 1028/529, loss: 0.011443670839071274
2023-01-22 18:18:55.571224: step: 1032/529, loss: 0.012728915549814701
2023-01-22 18:18:56.667194: step: 1036/529, loss: 0.00030084195896051824
2023-01-22 18:18:57.767795: step: 1040/529, loss: 0.0028281589038670063
2023-01-22 18:18:58.897509: step: 1044/529, loss: 0.007238818798214197
2023-01-22 18:19:00.007636: step: 1048/529, loss: 0.008840660564601421
2023-01-22 18:19:01.142037: step: 1052/529, loss: 0.01645452156662941
2023-01-22 18:19:02.233797: step: 1056/529, loss: 0.010672023519873619
2023-01-22 18:19:03.351101: step: 1060/529, loss: 0.08599682152271271
2023-01-22 18:19:04.443972: step: 1064/529, loss: 0.014405096881091595
2023-01-22 18:19:05.561568: step: 1068/529, loss: 0.008899947628378868
2023-01-22 18:19:06.677584: step: 1072/529, loss: 0.008222026750445366
2023-01-22 18:19:07.779935: step: 1076/529, loss: 0.00418322067707777
2023-01-22 18:19:08.884638: step: 1080/529, loss: 0.009708245284855366
2023-01-22 18:19:09.976855: step: 1084/529, loss: 0.028555525466799736
2023-01-22 18:19:11.083806: step: 1088/529, loss: 0.0147315738722682
2023-01-22 18:19:12.193560: step: 1092/529, loss: 0.007116028107702732
2023-01-22 18:19:13.324750: step: 1096/529, loss: 0.02818264439702034
2023-01-22 18:19:14.446027: step: 1100/529, loss: 0.0023795946035534143
2023-01-22 18:19:15.582580: step: 1104/529, loss: 0.011722657829523087
2023-01-22 18:19:16.667709: step: 1108/529, loss: 0.010309661738574505
2023-01-22 18:19:17.760047: step: 1112/529, loss: 0.015570037066936493
2023-01-22 18:19:18.865655: step: 1116/529, loss: 0.00650654174387455
2023-01-22 18:19:19.978712: step: 1120/529, loss: 0.007435745093971491
2023-01-22 18:19:21.080330: step: 1124/529, loss: 0.05043143406510353
2023-01-22 18:19:22.175748: step: 1128/529, loss: 0.02381957322359085
2023-01-22 18:19:23.295680: step: 1132/529, loss: 0.015333091840147972
2023-01-22 18:19:24.393665: step: 1136/529, loss: 0.007082587573677301
2023-01-22 18:19:25.510596: step: 1140/529, loss: 0.01254449225962162
2023-01-22 18:19:26.613523: step: 1144/529, loss: 0.009702915325760841
2023-01-22 18:19:27.721574: step: 1148/529, loss: 0.011501430533826351
2023-01-22 18:19:28.816204: step: 1152/529, loss: 0.008191782981157303
2023-01-22 18:19:29.916671: step: 1156/529, loss: 0.007531412877142429
2023-01-22 18:19:31.042390: step: 1160/529, loss: 0.036406949162483215
2023-01-22 18:19:32.151443: step: 1164/529, loss: 0.01686202920973301
2023-01-22 18:19:33.256532: step: 1168/529, loss: 0.08043814450502396
2023-01-22 18:19:34.384809: step: 1172/529, loss: 0.002022986300289631
2023-01-22 18:19:35.486447: step: 1176/529, loss: 0.0037562139332294464
2023-01-22 18:19:36.570195: step: 1180/529, loss: 0.001928901532664895
2023-01-22 18:19:37.671350: step: 1184/529, loss: 0.0026344051584601402
2023-01-22 18:19:38.827721: step: 1188/529, loss: 0.012846373952925205
2023-01-22 18:19:39.931398: step: 1192/529, loss: 0.0033279662020504475
2023-01-22 18:19:41.055498: step: 1196/529, loss: 0.005176838953047991
2023-01-22 18:19:42.165768: step: 1200/529, loss: 0.007989929988980293
2023-01-22 18:19:43.278661: step: 1204/529, loss: 0.00819362886250019
2023-01-22 18:19:44.389606: step: 1208/529, loss: 0.005794148426502943
2023-01-22 18:19:45.513570: step: 1212/529, loss: 0.015545502305030823
2023-01-22 18:19:46.645042: step: 1216/529, loss: 0.002302897395566106
2023-01-22 18:19:47.757284: step: 1220/529, loss: 0.002769102808088064
2023-01-22 18:19:48.874028: step: 1224/529, loss: 0.007388010621070862
2023-01-22 18:19:49.977200: step: 1228/529, loss: 0.03529055789113045
2023-01-22 18:19:51.115063: step: 1232/529, loss: 0.018408609554171562
2023-01-22 18:19:52.236239: step: 1236/529, loss: 0.010375368408858776
2023-01-22 18:19:53.339499: step: 1240/529, loss: 0.006846352480351925
2023-01-22 18:19:54.436082: step: 1244/529, loss: 0.010709736496210098
2023-01-22 18:19:55.540979: step: 1248/529, loss: 0.005159872584044933
2023-01-22 18:19:56.646712: step: 1252/529, loss: 0.004337864462286234
2023-01-22 18:19:57.748961: step: 1256/529, loss: 0.040999140590429306
2023-01-22 18:19:58.871363: step: 1260/529, loss: 0.0399836003780365
2023-01-22 18:20:00.011298: step: 1264/529, loss: 0.033606402575969696
2023-01-22 18:20:01.105367: step: 1268/529, loss: 0.003775114892050624
2023-01-22 18:20:02.219903: step: 1272/529, loss: 0.002228394616395235
2023-01-22 18:20:03.335703: step: 1276/529, loss: 0.007961426861584187
2023-01-22 18:20:04.437573: step: 1280/529, loss: 0.006111622788012028
2023-01-22 18:20:05.548208: step: 1284/529, loss: 0.004772203974425793
2023-01-22 18:20:06.645856: step: 1288/529, loss: 0.021087775006890297
2023-01-22 18:20:07.774808: step: 1292/529, loss: 0.02013617940247059
2023-01-22 18:20:08.888764: step: 1296/529, loss: 0.0033751027658581734
2023-01-22 18:20:09.991913: step: 1300/529, loss: 0.0056016636081039906
2023-01-22 18:20:11.115475: step: 1304/529, loss: 0.004481578711420298
2023-01-22 18:20:12.237030: step: 1308/529, loss: 0.047987911850214005
2023-01-22 18:20:13.341184: step: 1312/529, loss: 0.005470435135066509
2023-01-22 18:20:14.441680: step: 1316/529, loss: 0.0074748448096215725
2023-01-22 18:20:15.564941: step: 1320/529, loss: 0.01324130967259407
2023-01-22 18:20:16.688081: step: 1324/529, loss: 0.0027180227916687727
2023-01-22 18:20:17.795533: step: 1328/529, loss: 0.0033113453537225723
2023-01-22 18:20:18.907200: step: 1332/529, loss: 0.005601783748716116
2023-01-22 18:20:20.017129: step: 1336/529, loss: 0.06927123665809631
2023-01-22 18:20:21.138407: step: 1340/529, loss: 0.003348682541400194
2023-01-22 18:20:22.235746: step: 1344/529, loss: 0.007403103169053793
2023-01-22 18:20:23.378562: step: 1348/529, loss: 0.0058478242717683315
2023-01-22 18:20:24.492740: step: 1352/529, loss: 0.007413605228066444
2023-01-22 18:20:25.616280: step: 1356/529, loss: 0.004356472287327051
2023-01-22 18:20:26.715992: step: 1360/529, loss: 0.0012251229491084814
2023-01-22 18:20:27.825463: step: 1364/529, loss: 0.009137889370322227
2023-01-22 18:20:28.931056: step: 1368/529, loss: 0.00401352858170867
2023-01-22 18:20:30.035348: step: 1372/529, loss: 0.01571653038263321
2023-01-22 18:20:31.151302: step: 1376/529, loss: 0.006919472478330135
2023-01-22 18:20:32.258682: step: 1380/529, loss: 0.009047403931617737
2023-01-22 18:20:33.382672: step: 1384/529, loss: 0.004000944551080465
2023-01-22 18:20:34.484776: step: 1388/529, loss: 0.0016980344662442803
2023-01-22 18:20:35.612323: step: 1392/529, loss: 0.004459714982658625
2023-01-22 18:20:36.717096: step: 1396/529, loss: 0.0028377303387969732
2023-01-22 18:20:37.830244: step: 1400/529, loss: 0.0
2023-01-22 18:20:38.934363: step: 1404/529, loss: 0.005838384386152029
2023-01-22 18:20:40.037290: step: 1408/529, loss: 0.004882547073066235
2023-01-22 18:20:41.151723: step: 1412/529, loss: 0.006299017928540707
2023-01-22 18:20:42.256513: step: 1416/529, loss: 0.006627513561397791
2023-01-22 18:20:43.360685: step: 1420/529, loss: 0.0
2023-01-22 18:20:44.476904: step: 1424/529, loss: 0.0052241915836930275
2023-01-22 18:20:45.568562: step: 1428/529, loss: 0.0
2023-01-22 18:20:46.692006: step: 1432/529, loss: 0.006132422015070915
2023-01-22 18:20:47.830656: step: 1436/529, loss: 0.00824801716953516
2023-01-22 18:20:48.949274: step: 1440/529, loss: 0.01043170690536499
2023-01-22 18:20:50.050716: step: 1444/529, loss: 0.011481354013085365
2023-01-22 18:20:51.159726: step: 1448/529, loss: 0.009087396785616875
2023-01-22 18:20:52.254708: step: 1452/529, loss: 0.0005475827492773533
2023-01-22 18:20:53.360523: step: 1456/529, loss: 0.021182693541049957
2023-01-22 18:20:54.453258: step: 1460/529, loss: 0.0019548223353922367
2023-01-22 18:20:55.590351: step: 1464/529, loss: 0.06760632991790771
2023-01-22 18:20:56.689339: step: 1468/529, loss: 0.010388791561126709
2023-01-22 18:20:57.795255: step: 1472/529, loss: 0.006924397777765989
2023-01-22 18:20:58.904366: step: 1476/529, loss: 0.01615745760500431
2023-01-22 18:20:59.982870: step: 1480/529, loss: 0.0034435386769473553
2023-01-22 18:21:01.087095: step: 1484/529, loss: 0.005169328302145004
2023-01-22 18:21:02.199400: step: 1488/529, loss: 0.0073610697872936726
2023-01-22 18:21:03.329856: step: 1492/529, loss: 0.020026110112667084
2023-01-22 18:21:04.421285: step: 1496/529, loss: 0.012640643864870071
2023-01-22 18:21:05.516898: step: 1500/529, loss: 0.004735766910016537
2023-01-22 18:21:06.669669: step: 1504/529, loss: 0.005756611004471779
2023-01-22 18:21:07.806945: step: 1508/529, loss: 0.0024541865568608046
2023-01-22 18:21:08.904520: step: 1512/529, loss: 0.005774150602519512
2023-01-22 18:21:10.023373: step: 1516/529, loss: 0.03664577379822731
2023-01-22 18:21:11.132694: step: 1520/529, loss: 0.010698582977056503
2023-01-22 18:21:12.219581: step: 1524/529, loss: 0.0069966986775398254
2023-01-22 18:21:13.354263: step: 1528/529, loss: 0.03440531715750694
2023-01-22 18:21:14.474651: step: 1532/529, loss: 0.01456489972770214
2023-01-22 18:21:15.564394: step: 1536/529, loss: 0.018541404977440834
2023-01-22 18:21:16.656730: step: 1540/529, loss: 0.018075400963425636
2023-01-22 18:21:17.792982: step: 1544/529, loss: 0.005095444619655609
2023-01-22 18:21:18.897589: step: 1548/529, loss: 0.003705532755702734
2023-01-22 18:21:20.033530: step: 1552/529, loss: 0.002478782320395112
2023-01-22 18:21:21.147043: step: 1556/529, loss: 0.005461443215608597
2023-01-22 18:21:22.245528: step: 1560/529, loss: 0.1274636834859848
2023-01-22 18:21:23.344437: step: 1564/529, loss: 0.003411645768210292
2023-01-22 18:21:24.441243: step: 1568/529, loss: 0.009192973375320435
2023-01-22 18:21:25.553461: step: 1572/529, loss: 0.008603168651461601
2023-01-22 18:21:26.659005: step: 1576/529, loss: 0.005672864615917206
2023-01-22 18:21:27.794234: step: 1580/529, loss: 0.013235931284725666
2023-01-22 18:21:28.896477: step: 1584/529, loss: 0.006756671238690615
2023-01-22 18:21:29.991006: step: 1588/529, loss: 0.00015990881365723908
2023-01-22 18:21:31.080196: step: 1592/529, loss: 0.009757466614246368
2023-01-22 18:21:32.199674: step: 1596/529, loss: 0.004599540028721094
2023-01-22 18:21:33.291930: step: 1600/529, loss: 0.0033793197944760323
2023-01-22 18:21:34.401090: step: 1604/529, loss: 0.0013420956674963236
2023-01-22 18:21:35.488461: step: 1608/529, loss: 0.01148051768541336
2023-01-22 18:21:36.631056: step: 1612/529, loss: 0.0010839785682037473
2023-01-22 18:21:37.730747: step: 1616/529, loss: 0.006117976736277342
2023-01-22 18:21:38.853805: step: 1620/529, loss: 0.006065054796636105
2023-01-22 18:21:39.958741: step: 1624/529, loss: 0.01303850393742323
2023-01-22 18:21:41.074747: step: 1628/529, loss: 0.006825159303843975
2023-01-22 18:21:42.162055: step: 1632/529, loss: 0.039214178919792175
2023-01-22 18:21:43.241717: step: 1636/529, loss: 0.02118976041674614
2023-01-22 18:21:44.352297: step: 1640/529, loss: 0.004901760257780552
2023-01-22 18:21:45.452848: step: 1644/529, loss: 0.017291145399212837
2023-01-22 18:21:46.547467: step: 1648/529, loss: 0.013679240830242634
2023-01-22 18:21:47.651671: step: 1652/529, loss: 0.005540389567613602
2023-01-22 18:21:48.753879: step: 1656/529, loss: 0.0013256166130304337
2023-01-22 18:21:49.863731: step: 1660/529, loss: 0.07681383192539215
2023-01-22 18:21:50.969196: step: 1664/529, loss: 0.02331751212477684
2023-01-22 18:21:52.075412: step: 1668/529, loss: 0.0029005850665271282
2023-01-22 18:21:53.195189: step: 1672/529, loss: 0.0011654160916805267
2023-01-22 18:21:54.333351: step: 1676/529, loss: 0.0011839760700240731
2023-01-22 18:21:55.470328: step: 1680/529, loss: 0.028308244422078133
2023-01-22 18:21:56.582079: step: 1684/529, loss: 0.0032881482038646936
2023-01-22 18:21:57.680940: step: 1688/529, loss: 0.0014153735246509314
2023-01-22 18:21:58.793826: step: 1692/529, loss: 0.011508672498166561
2023-01-22 18:21:59.914210: step: 1696/529, loss: 0.008085059002041817
2023-01-22 18:22:01.011844: step: 1700/529, loss: 0.011574369855225086
2023-01-22 18:22:02.136215: step: 1704/529, loss: 0.03143833950161934
2023-01-22 18:22:03.251339: step: 1708/529, loss: 0.004696979187428951
2023-01-22 18:22:04.378609: step: 1712/529, loss: 0.006900436244904995
2023-01-22 18:22:05.513450: step: 1716/529, loss: 0.0028517390601336956
2023-01-22 18:22:06.628976: step: 1720/529, loss: 0.0016723640728741884
2023-01-22 18:22:07.726644: step: 1724/529, loss: 0.0006003755843266845
2023-01-22 18:22:08.811621: step: 1728/529, loss: 0.001794571871869266
2023-01-22 18:22:09.922853: step: 1732/529, loss: 0.004456062335520983
2023-01-22 18:22:11.031085: step: 1736/529, loss: 0.016209375113248825
2023-01-22 18:22:12.156821: step: 1740/529, loss: 0.010823754593729973
2023-01-22 18:22:13.293569: step: 1744/529, loss: 0.011083311401307583
2023-01-22 18:22:14.413951: step: 1748/529, loss: 0.00016748525376897305
2023-01-22 18:22:15.541290: step: 1752/529, loss: 0.01249956525862217
2023-01-22 18:22:16.678606: step: 1756/529, loss: 0.0006623414810746908
2023-01-22 18:22:17.770756: step: 1760/529, loss: 0.00020094467618037015
2023-01-22 18:22:18.859949: step: 1764/529, loss: 0.0019419906893745065
2023-01-22 18:22:19.977807: step: 1768/529, loss: 0.06702131778001785
2023-01-22 18:22:21.093128: step: 1772/529, loss: 0.01007301639765501
2023-01-22 18:22:22.218100: step: 1776/529, loss: 0.04495028406381607
2023-01-22 18:22:23.333116: step: 1780/529, loss: 0.001488852663896978
2023-01-22 18:22:24.457611: step: 1784/529, loss: 0.004896989557892084
2023-01-22 18:22:25.567922: step: 1788/529, loss: 0.003095545805990696
2023-01-22 18:22:26.645191: step: 1792/529, loss: 0.002195939887315035
2023-01-22 18:22:27.736108: step: 1796/529, loss: 0.0036110514774918556
2023-01-22 18:22:28.890397: step: 1800/529, loss: 0.0278365109115839
2023-01-22 18:22:30.009167: step: 1804/529, loss: 0.00488294055685401
2023-01-22 18:22:31.110356: step: 1808/529, loss: 0.08174276351928711
2023-01-22 18:22:32.206663: step: 1812/529, loss: 0.0004541809903457761
2023-01-22 18:22:33.366898: step: 1816/529, loss: 0.007615325972437859
2023-01-22 18:22:34.471511: step: 1820/529, loss: 0.04389224573969841
2023-01-22 18:22:35.574268: step: 1824/529, loss: 0.021634459495544434
2023-01-22 18:22:36.700308: step: 1828/529, loss: 0.00733558926731348
2023-01-22 18:22:37.811683: step: 1832/529, loss: 0.020841460675001144
2023-01-22 18:22:38.923444: step: 1836/529, loss: 0.0019189510494470596
2023-01-22 18:22:40.048228: step: 1840/529, loss: 0.02001775987446308
2023-01-22 18:22:41.144022: step: 1844/529, loss: 0.008444736711680889
2023-01-22 18:22:42.255810: step: 1848/529, loss: 0.0018344405107200146
2023-01-22 18:22:43.327484: step: 1852/529, loss: 0.015778839588165283
2023-01-22 18:22:44.438833: step: 1856/529, loss: 0.0066888462752103806
2023-01-22 18:22:45.556833: step: 1860/529, loss: 0.02231615222990513
2023-01-22 18:22:46.646788: step: 1864/529, loss: 0.00994773581624031
2023-01-22 18:22:47.755597: step: 1868/529, loss: 0.0008641586755402386
2023-01-22 18:22:48.866794: step: 1872/529, loss: 0.006874522659927607
2023-01-22 18:22:49.964381: step: 1876/529, loss: 0.0026030277367681265
2023-01-22 18:22:51.109339: step: 1880/529, loss: 0.06523173302412033
2023-01-22 18:22:52.221240: step: 1884/529, loss: 0.002486263168975711
2023-01-22 18:22:53.327995: step: 1888/529, loss: 0.018967991694808006
2023-01-22 18:22:54.421226: step: 1892/529, loss: 0.005981970578432083
2023-01-22 18:22:55.550374: step: 1896/529, loss: 0.01120185200124979
2023-01-22 18:22:56.651724: step: 1900/529, loss: 0.004858768079429865
2023-01-22 18:22:57.751556: step: 1904/529, loss: 0.036857277154922485
2023-01-22 18:22:58.858776: step: 1908/529, loss: 0.01874036341905594
2023-01-22 18:22:59.953901: step: 1912/529, loss: 0.00855395570397377
2023-01-22 18:23:01.065815: step: 1916/529, loss: 0.005791983101516962
2023-01-22 18:23:02.187855: step: 1920/529, loss: 0.005590052343904972
2023-01-22 18:23:03.328593: step: 1924/529, loss: 0.0035764267668128014
2023-01-22 18:23:04.431153: step: 1928/529, loss: 0.0007121971575543284
2023-01-22 18:23:05.548937: step: 1932/529, loss: 0.006333343684673309
2023-01-22 18:23:06.673393: step: 1936/529, loss: 0.0018290726002305746
2023-01-22 18:23:07.767807: step: 1940/529, loss: 0.020614778622984886
2023-01-22 18:23:08.884117: step: 1944/529, loss: 0.015153782442212105
2023-01-22 18:23:09.965385: step: 1948/529, loss: 0.007827503606677055
2023-01-22 18:23:11.052657: step: 1952/529, loss: 0.004643795546144247
2023-01-22 18:23:12.157561: step: 1956/529, loss: 0.045869313180446625
2023-01-22 18:23:13.261880: step: 1960/529, loss: 0.0068098013289272785
2023-01-22 18:23:14.361444: step: 1964/529, loss: 0.002404472790658474
2023-01-22 18:23:15.475572: step: 1968/529, loss: 0.001679004984907806
2023-01-22 18:23:16.588180: step: 1972/529, loss: 0.003071703715249896
2023-01-22 18:23:17.706328: step: 1976/529, loss: 0.006801737006753683
2023-01-22 18:23:18.802210: step: 1980/529, loss: 0.004793296102434397
2023-01-22 18:23:19.910375: step: 1984/529, loss: 0.009354254230856895
2023-01-22 18:23:21.009326: step: 1988/529, loss: 0.01072611566632986
2023-01-22 18:23:22.115071: step: 1992/529, loss: 0.0031407487113028765
2023-01-22 18:23:23.239736: step: 1996/529, loss: 0.005848722532391548
2023-01-22 18:23:24.367901: step: 2000/529, loss: 0.010853058658540249
2023-01-22 18:23:25.486548: step: 2004/529, loss: 0.005025187041610479
2023-01-22 18:23:26.574147: step: 2008/529, loss: 0.0029536725487560034
2023-01-22 18:23:27.679384: step: 2012/529, loss: 0.05910155177116394
2023-01-22 18:23:28.774565: step: 2016/529, loss: 0.010073854587972164
2023-01-22 18:23:29.870878: step: 2020/529, loss: 0.003368824953213334
2023-01-22 18:23:31.003335: step: 2024/529, loss: 0.0011643996695056558
2023-01-22 18:23:32.117368: step: 2028/529, loss: 0.0022635748609900475
2023-01-22 18:23:33.228242: step: 2032/529, loss: 0.008298167027533054
2023-01-22 18:23:34.324057: step: 2036/529, loss: 0.0030539599247276783
2023-01-22 18:23:35.420167: step: 2040/529, loss: 0.020333029329776764
2023-01-22 18:23:36.524521: step: 2044/529, loss: 0.0022788713686168194
2023-01-22 18:23:37.632617: step: 2048/529, loss: 0.025013364851474762
2023-01-22 18:23:38.732082: step: 2052/529, loss: 0.005531164351850748
2023-01-22 18:23:39.838464: step: 2056/529, loss: 0.005339278373867273
2023-01-22 18:23:40.933361: step: 2060/529, loss: 0.010453582741320133
2023-01-22 18:23:42.080768: step: 2064/529, loss: 0.053581543266773224
2023-01-22 18:23:43.218691: step: 2068/529, loss: 0.010096881538629532
2023-01-22 18:23:44.314810: step: 2072/529, loss: 0.01938735507428646
2023-01-22 18:23:45.452203: step: 2076/529, loss: 0.00021988751541357487
2023-01-22 18:23:46.568768: step: 2080/529, loss: 0.004157444927841425
2023-01-22 18:23:47.686998: step: 2084/529, loss: 0.003393003484234214
2023-01-22 18:23:48.790118: step: 2088/529, loss: 0.0045474013313651085
2023-01-22 18:23:49.894670: step: 2092/529, loss: 0.033529434353113174
2023-01-22 18:23:50.986351: step: 2096/529, loss: 0.0008140570134855807
2023-01-22 18:23:52.093234: step: 2100/529, loss: 0.006187839899212122
2023-01-22 18:23:53.226148: step: 2104/529, loss: 0.004368227906525135
2023-01-22 18:23:54.346588: step: 2108/529, loss: 0.012259622104465961
2023-01-22 18:23:55.483453: step: 2112/529, loss: 0.027089525014162064
2023-01-22 18:23:56.604070: step: 2116/529, loss: 0.05032616853713989
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3306438873626374, 'r': 0.3262520330712931, 'f1': 0.3284332787556284}, 'combined': 0.2420034685567788, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3703605222168529, 'r': 0.294298612541468, 'f1': 0.32797740113264523}, 'combined': 0.2015861099644551, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33670446676473903, 'r': 0.3437324537370581, 'f1': 0.3401821654824969}, 'combined': 0.250660542987103, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3549160560895563, 'r': 0.30663024949851614, 'f1': 0.32901097900631116}, 'combined': 0.20222138221851318, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.339090119949495, 'r': 0.3397335547122075, 'f1': 0.3394115323854661}, 'combined': 0.2500927080735013, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36102115722361056, 'r': 0.292567794944848, 'f1': 0.3232097591212812}, 'combined': 0.1996295571043208, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3269230769230769, 'r': 0.36428571428571427, 'f1': 0.34459459459459457}, 'combined': 0.22972972972972971, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35185185185185186, 'r': 0.41304347826086957, 'f1': 0.38}, 'combined': 0.19, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 6
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 18:26:22.026215: step: 4/529, loss: 0.005305708386003971
2023-01-22 18:26:23.156395: step: 8/529, loss: 0.006093189120292664
2023-01-22 18:26:24.266791: step: 12/529, loss: 0.007629713974893093
2023-01-22 18:26:25.364254: step: 16/529, loss: 0.005305420607328415
2023-01-22 18:26:26.453125: step: 20/529, loss: 0.01621827483177185
2023-01-22 18:26:27.538941: step: 24/529, loss: 0.012369094416499138
2023-01-22 18:26:28.663398: step: 28/529, loss: 0.0037875082343816757
2023-01-22 18:26:29.754996: step: 32/529, loss: 0.006324531510472298
2023-01-22 18:26:30.863353: step: 36/529, loss: 0.0042244186624884605
2023-01-22 18:26:31.961919: step: 40/529, loss: 0.006109151057898998
2023-01-22 18:26:33.076136: step: 44/529, loss: 0.0071633318439126015
2023-01-22 18:26:34.187619: step: 48/529, loss: 0.009522320702672005
2023-01-22 18:26:35.274236: step: 52/529, loss: 0.006063740700483322
2023-01-22 18:26:36.371593: step: 56/529, loss: 0.0026602260768413544
2023-01-22 18:26:37.469650: step: 60/529, loss: 0.004821986425668001
2023-01-22 18:26:38.590748: step: 64/529, loss: 0.005420095287263393
2023-01-22 18:26:39.684359: step: 68/529, loss: 0.009220386855304241
2023-01-22 18:26:40.799855: step: 72/529, loss: 0.004033449571579695
2023-01-22 18:26:41.912292: step: 76/529, loss: 0.028109779581427574
2023-01-22 18:26:42.988556: step: 80/529, loss: 0.0012292263563722372
2023-01-22 18:26:44.087191: step: 84/529, loss: 0.001076428801752627
2023-01-22 18:26:45.167142: step: 88/529, loss: 0.0036951242946088314
2023-01-22 18:26:46.249422: step: 92/529, loss: 0.009567310102283955
2023-01-22 18:26:47.328205: step: 96/529, loss: 0.009079602546989918
2023-01-22 18:26:48.439775: step: 100/529, loss: 0.011921736411750317
2023-01-22 18:26:49.565802: step: 104/529, loss: 0.005667198449373245
2023-01-22 18:26:50.677005: step: 108/529, loss: 0.005825122818350792
2023-01-22 18:26:51.798589: step: 112/529, loss: 0.00235575158149004
2023-01-22 18:26:52.890270: step: 116/529, loss: 0.04373656585812569
2023-01-22 18:26:54.002612: step: 120/529, loss: 0.012989873997867107
2023-01-22 18:26:55.120564: step: 124/529, loss: 0.007287052925676107
2023-01-22 18:26:56.225835: step: 128/529, loss: 0.006580047309398651
2023-01-22 18:26:57.338137: step: 132/529, loss: 0.011693893000483513
2023-01-22 18:26:58.436585: step: 136/529, loss: 0.007187485229223967
2023-01-22 18:26:59.547786: step: 140/529, loss: 0.007349448278546333
2023-01-22 18:27:00.653112: step: 144/529, loss: 0.009007965214550495
2023-01-22 18:27:01.760449: step: 148/529, loss: 0.045606840401887894
2023-01-22 18:27:02.885638: step: 152/529, loss: 0.010001951828598976
2023-01-22 18:27:03.999125: step: 156/529, loss: 0.006817980203777552
2023-01-22 18:27:05.108931: step: 160/529, loss: 0.003874080488458276
2023-01-22 18:27:06.243085: step: 164/529, loss: 0.007783068343997002
2023-01-22 18:27:07.346694: step: 168/529, loss: 0.005335921887308359
2023-01-22 18:27:08.452387: step: 172/529, loss: 0.0020430851727724075
2023-01-22 18:27:09.573918: step: 176/529, loss: 0.04033869504928589
2023-01-22 18:27:10.681175: step: 180/529, loss: 0.0034851818345487118
2023-01-22 18:27:11.788296: step: 184/529, loss: 0.007983280345797539
2023-01-22 18:27:12.911076: step: 188/529, loss: 0.0017792755970731378
2023-01-22 18:27:14.022150: step: 192/529, loss: 0.001871102605946362
2023-01-22 18:27:15.120902: step: 196/529, loss: 0.02657787688076496
2023-01-22 18:27:16.248169: step: 200/529, loss: 0.006426504347473383
2023-01-22 18:27:17.360713: step: 204/529, loss: 0.006066290196031332
2023-01-22 18:27:18.464753: step: 208/529, loss: 0.0011546644382178783
2023-01-22 18:27:19.591972: step: 212/529, loss: 0.006882756017148495
2023-01-22 18:27:20.705497: step: 216/529, loss: 0.007010776083916426
2023-01-22 18:27:21.821150: step: 220/529, loss: 0.007206588983535767
2023-01-22 18:27:22.919649: step: 224/529, loss: 0.006268988363444805
2023-01-22 18:27:24.027715: step: 228/529, loss: 0.019737256690859795
2023-01-22 18:27:25.152353: step: 232/529, loss: 0.00629029655829072
2023-01-22 18:27:26.228642: step: 236/529, loss: 0.006087011191993952
2023-01-22 18:27:27.351949: step: 240/529, loss: 0.003464686218649149
2023-01-22 18:27:28.444912: step: 244/529, loss: 0.0019196582725271583
2023-01-22 18:27:29.582119: step: 248/529, loss: 0.008158623240888119
2023-01-22 18:27:30.715473: step: 252/529, loss: 0.007937573827803135
2023-01-22 18:27:31.868457: step: 256/529, loss: 0.006093911826610565
2023-01-22 18:27:32.973333: step: 260/529, loss: 0.011993014253675938
2023-01-22 18:27:34.072189: step: 264/529, loss: 0.0046798307448625565
2023-01-22 18:27:35.174866: step: 268/529, loss: 0.004838019609451294
2023-01-22 18:27:36.289221: step: 272/529, loss: 0.005612580105662346
2023-01-22 18:27:37.403349: step: 276/529, loss: 0.003289461135864258
2023-01-22 18:27:38.486228: step: 280/529, loss: 0.0008001339738257229
2023-01-22 18:27:39.619683: step: 284/529, loss: 0.010058913379907608
2023-01-22 18:27:40.742017: step: 288/529, loss: 0.027089452371001244
2023-01-22 18:27:41.844517: step: 292/529, loss: 0.0019319587154313922
2023-01-22 18:27:42.964545: step: 296/529, loss: 0.02260185033082962
2023-01-22 18:27:44.090536: step: 300/529, loss: 0.016764825209975243
2023-01-22 18:27:45.205592: step: 304/529, loss: 0.015785498544573784
2023-01-22 18:27:46.325801: step: 308/529, loss: 0.027940809726715088
2023-01-22 18:27:47.437402: step: 312/529, loss: 0.007339327596127987
2023-01-22 18:27:48.563453: step: 316/529, loss: 0.009754262864589691
2023-01-22 18:27:49.668355: step: 320/529, loss: 0.009043138474225998
2023-01-22 18:27:50.775964: step: 324/529, loss: 0.014477244578301907
2023-01-22 18:27:51.907932: step: 328/529, loss: 0.006711823400110006
2023-01-22 18:27:53.010871: step: 332/529, loss: 0.0010740314610302448
2023-01-22 18:27:54.091797: step: 336/529, loss: 0.011390362866222858
2023-01-22 18:27:55.199286: step: 340/529, loss: 0.00804499164223671
2023-01-22 18:27:56.318157: step: 344/529, loss: 0.001907942583784461
2023-01-22 18:27:57.427436: step: 348/529, loss: 0.013106828555464745
2023-01-22 18:27:58.562529: step: 352/529, loss: 0.0017678738804534078
2023-01-22 18:27:59.667881: step: 356/529, loss: 0.005667952820658684
2023-01-22 18:28:00.793555: step: 360/529, loss: 0.0069861216470599174
2023-01-22 18:28:01.914428: step: 364/529, loss: 0.011109267361462116
2023-01-22 18:28:03.041622: step: 368/529, loss: 0.005532680079340935
2023-01-22 18:28:04.170069: step: 372/529, loss: 0.00781653355807066
2023-01-22 18:28:05.290212: step: 376/529, loss: 0.012174945324659348
2023-01-22 18:28:06.398533: step: 380/529, loss: 0.0015434130327776074
2023-01-22 18:28:07.521197: step: 384/529, loss: 0.02806060202419758
2023-01-22 18:28:08.633088: step: 388/529, loss: 0.0021952311508357525
2023-01-22 18:28:09.750789: step: 392/529, loss: 0.009764987975358963
2023-01-22 18:28:10.857532: step: 396/529, loss: 0.007892412133514881
2023-01-22 18:28:11.971862: step: 400/529, loss: 0.002366431523114443
2023-01-22 18:28:13.091332: step: 404/529, loss: 0.012028719298541546
2023-01-22 18:28:14.186849: step: 408/529, loss: 0.00608090590685606
2023-01-22 18:28:15.308569: step: 412/529, loss: 0.014038904570043087
2023-01-22 18:28:16.419083: step: 416/529, loss: 0.011369108222424984
2023-01-22 18:28:17.511657: step: 420/529, loss: 0.011203082278370857
2023-01-22 18:28:18.636471: step: 424/529, loss: 0.06550873816013336
2023-01-22 18:28:19.727157: step: 428/529, loss: 0.0039025964215397835
2023-01-22 18:28:20.820650: step: 432/529, loss: 0.0033832304179668427
2023-01-22 18:28:21.938828: step: 436/529, loss: 0.0053379652090370655
2023-01-22 18:28:23.053350: step: 440/529, loss: 0.02753600664436817
2023-01-22 18:28:24.185219: step: 444/529, loss: 0.008254663087427616
2023-01-22 18:28:25.286807: step: 448/529, loss: 0.002607951872050762
2023-01-22 18:28:26.439534: step: 452/529, loss: 0.014489099383354187
2023-01-22 18:28:27.558537: step: 456/529, loss: 0.023807143792510033
2023-01-22 18:28:28.666168: step: 460/529, loss: 0.002194441156461835
2023-01-22 18:28:29.770223: step: 464/529, loss: 0.007039714138954878
2023-01-22 18:28:30.871897: step: 468/529, loss: 0.010733935981988907
2023-01-22 18:28:31.955149: step: 472/529, loss: 0.02351614274084568
2023-01-22 18:28:33.030357: step: 476/529, loss: 0.004978803917765617
2023-01-22 18:28:34.154872: step: 480/529, loss: 0.006381789688020945
2023-01-22 18:28:35.253800: step: 484/529, loss: 0.014700474217534065
2023-01-22 18:28:36.383899: step: 488/529, loss: 0.012882917188107967
2023-01-22 18:28:37.504511: step: 492/529, loss: 0.012605691328644753
2023-01-22 18:28:38.619744: step: 496/529, loss: 0.007123208604753017
2023-01-22 18:28:39.724150: step: 500/529, loss: 0.002348636044189334
2023-01-22 18:28:40.866702: step: 504/529, loss: 0.0015904400497674942
2023-01-22 18:28:41.987284: step: 508/529, loss: 0.0019640130922198296
2023-01-22 18:28:43.086140: step: 512/529, loss: 0.01146282721310854
2023-01-22 18:28:44.174841: step: 516/529, loss: 0.010517077520489693
2023-01-22 18:28:45.283341: step: 520/529, loss: 0.008044732734560966
2023-01-22 18:28:46.405147: step: 524/529, loss: 0.005586392246186733
2023-01-22 18:28:47.511116: step: 528/529, loss: 0.010143124498426914
2023-01-22 18:28:48.647336: step: 532/529, loss: 0.00445580156520009
2023-01-22 18:28:49.744309: step: 536/529, loss: 0.002814148785546422
2023-01-22 18:28:50.847591: step: 540/529, loss: 0.007910819724202156
2023-01-22 18:28:51.947219: step: 544/529, loss: 0.004795929882675409
2023-01-22 18:28:53.047266: step: 548/529, loss: 0.003995841834694147
2023-01-22 18:28:54.157755: step: 552/529, loss: 0.005644669756293297
2023-01-22 18:28:55.273373: step: 556/529, loss: 0.0033773272298276424
2023-01-22 18:28:56.393135: step: 560/529, loss: 8.530495688319206e-05
2023-01-22 18:28:57.496069: step: 564/529, loss: 0.0038765519857406616
2023-01-22 18:28:58.600078: step: 568/529, loss: 0.0009553500567562878
2023-01-22 18:28:59.701600: step: 572/529, loss: 0.006487762089818716
2023-01-22 18:29:00.797822: step: 576/529, loss: 0.0039129070937633514
2023-01-22 18:29:01.916162: step: 580/529, loss: 0.00626823864877224
2023-01-22 18:29:03.004568: step: 584/529, loss: 0.01893220655620098
2023-01-22 18:29:04.108152: step: 588/529, loss: 0.0023820495698601007
2023-01-22 18:29:05.206679: step: 592/529, loss: 0.004280897788703442
2023-01-22 18:29:06.334533: step: 596/529, loss: 0.004197548609226942
2023-01-22 18:29:07.417652: step: 600/529, loss: 0.003984412178397179
2023-01-22 18:29:08.523310: step: 604/529, loss: 0.004340028390288353
2023-01-22 18:29:09.633531: step: 608/529, loss: 0.0048962910659611225
2023-01-22 18:29:10.745693: step: 612/529, loss: 0.024945199489593506
2023-01-22 18:29:11.854772: step: 616/529, loss: 0.0054998514242470264
2023-01-22 18:29:12.978199: step: 620/529, loss: 0.002281581051647663
2023-01-22 18:29:14.068211: step: 624/529, loss: 0.008889270015060902
2023-01-22 18:29:15.188259: step: 628/529, loss: 0.026520676910877228
2023-01-22 18:29:16.294754: step: 632/529, loss: 0.0068703144788742065
2023-01-22 18:29:17.419112: step: 636/529, loss: 0.006307255011051893
2023-01-22 18:29:18.550101: step: 640/529, loss: 0.0048749265260994434
2023-01-22 18:29:19.655780: step: 644/529, loss: 0.0028190717566758394
2023-01-22 18:29:20.763833: step: 648/529, loss: 0.014694026671350002
2023-01-22 18:29:21.864313: step: 652/529, loss: 0.0014744563959538937
2023-01-22 18:29:22.978000: step: 656/529, loss: 0.003851824440062046
2023-01-22 18:29:24.123069: step: 660/529, loss: 0.0055006761103868484
2023-01-22 18:29:25.246348: step: 664/529, loss: 0.0433463454246521
2023-01-22 18:29:26.351792: step: 668/529, loss: 0.005329366773366928
2023-01-22 18:29:27.492249: step: 672/529, loss: 0.005724288523197174
2023-01-22 18:29:28.593105: step: 676/529, loss: 0.002345007611438632
2023-01-22 18:29:29.696275: step: 680/529, loss: 0.003112499602138996
2023-01-22 18:29:30.838959: step: 684/529, loss: 0.00028195566846989095
2023-01-22 18:29:31.938333: step: 688/529, loss: 0.002822271781042218
2023-01-22 18:29:33.051522: step: 692/529, loss: 0.005992645863443613
2023-01-22 18:29:34.190246: step: 696/529, loss: 0.0057897260412573814
2023-01-22 18:29:35.324164: step: 700/529, loss: 0.012225686572492123
2023-01-22 18:29:36.424854: step: 704/529, loss: 0.0027927816845476627
2023-01-22 18:29:37.540010: step: 708/529, loss: 0.017846500501036644
2023-01-22 18:29:38.698153: step: 712/529, loss: 0.05046258866786957
2023-01-22 18:29:39.831037: step: 716/529, loss: 0.0012455973774194717
2023-01-22 18:29:40.923314: step: 720/529, loss: 0.0068160658702254295
2023-01-22 18:29:42.034557: step: 724/529, loss: 0.005377395078539848
2023-01-22 18:29:43.164011: step: 728/529, loss: 0.006648749113082886
2023-01-22 18:29:44.252254: step: 732/529, loss: 0.023196039721369743
2023-01-22 18:29:45.373595: step: 736/529, loss: 0.021718859672546387
2023-01-22 18:29:46.460024: step: 740/529, loss: 0.007760044187307358
2023-01-22 18:29:47.587568: step: 744/529, loss: 0.0010392244439572096
2023-01-22 18:29:48.689183: step: 748/529, loss: 0.006531145423650742
2023-01-22 18:29:49.784511: step: 752/529, loss: 0.008210964500904083
2023-01-22 18:29:50.894368: step: 756/529, loss: 0.036858491599559784
2023-01-22 18:29:51.997093: step: 760/529, loss: 0.0012899063294753432
2023-01-22 18:29:53.099564: step: 764/529, loss: 0.00021576260041911155
2023-01-22 18:29:54.182959: step: 768/529, loss: 0.0008020169334486127
2023-01-22 18:29:55.294834: step: 772/529, loss: 0.0072806584648787975
2023-01-22 18:29:56.392248: step: 776/529, loss: 0.0036610804963856936
2023-01-22 18:29:57.495718: step: 780/529, loss: 0.005994501058012247
2023-01-22 18:29:58.606233: step: 784/529, loss: 0.0062747919000685215
2023-01-22 18:29:59.714190: step: 788/529, loss: 0.006858598906546831
2023-01-22 18:30:00.817512: step: 792/529, loss: 0.007317975163459778
2023-01-22 18:30:01.932992: step: 796/529, loss: 0.018855173140764236
2023-01-22 18:30:03.038002: step: 800/529, loss: 0.003291010158136487
2023-01-22 18:30:04.153445: step: 804/529, loss: 0.026685452088713646
2023-01-22 18:30:05.254169: step: 808/529, loss: 0.004708230495452881
2023-01-22 18:30:06.361624: step: 812/529, loss: 0.05527876317501068
2023-01-22 18:30:07.466158: step: 816/529, loss: 0.006717084441334009
2023-01-22 18:30:08.581133: step: 820/529, loss: 0.038744643330574036
2023-01-22 18:30:09.701006: step: 824/529, loss: 0.046610649675130844
2023-01-22 18:30:10.830960: step: 828/529, loss: 0.0054276264272630215
2023-01-22 18:30:11.957255: step: 832/529, loss: 0.031156649813055992
2023-01-22 18:30:13.046368: step: 836/529, loss: 0.007855386473238468
2023-01-22 18:30:14.150551: step: 840/529, loss: 0.0017032561590895057
2023-01-22 18:30:15.279370: step: 844/529, loss: 0.008952956646680832
2023-01-22 18:30:16.404210: step: 848/529, loss: 0.002339595463126898
2023-01-22 18:30:17.513990: step: 852/529, loss: 0.0059345318004488945
2023-01-22 18:30:18.615563: step: 856/529, loss: 0.006251884624361992
2023-01-22 18:30:19.711314: step: 860/529, loss: 0.00011411734885768965
2023-01-22 18:30:20.794791: step: 864/529, loss: 0.062095288187265396
2023-01-22 18:30:21.928761: step: 868/529, loss: 0.009423395618796349
2023-01-22 18:30:23.053502: step: 872/529, loss: 0.038906171917915344
2023-01-22 18:30:24.155627: step: 876/529, loss: 0.02318127453327179
2023-01-22 18:30:25.266499: step: 880/529, loss: 0.0064411889761686325
2023-01-22 18:30:26.361056: step: 884/529, loss: 0.02866014838218689
2023-01-22 18:30:27.465051: step: 888/529, loss: 0.009514992125332355
2023-01-22 18:30:28.577781: step: 892/529, loss: 0.006461628712713718
2023-01-22 18:30:29.679888: step: 896/529, loss: 0.003239220008254051
2023-01-22 18:30:30.817033: step: 900/529, loss: 0.021247822791337967
2023-01-22 18:30:31.950685: step: 904/529, loss: 0.0050697955302894115
2023-01-22 18:30:33.071418: step: 908/529, loss: 0.0012252520537003875
2023-01-22 18:30:34.166447: step: 912/529, loss: 0.006530306302011013
2023-01-22 18:30:35.286745: step: 916/529, loss: 0.009525244124233723
2023-01-22 18:30:36.395206: step: 920/529, loss: 0.003942673560231924
2023-01-22 18:30:37.515109: step: 924/529, loss: 0.029574938118457794
2023-01-22 18:30:38.644149: step: 928/529, loss: 0.0008766837418079376
2023-01-22 18:30:39.746571: step: 932/529, loss: 0.010835814289748669
2023-01-22 18:30:40.853261: step: 936/529, loss: 0.0033007157035171986
2023-01-22 18:30:41.960557: step: 940/529, loss: 0.00879733171314001
2023-01-22 18:30:43.057832: step: 944/529, loss: 0.02690090425312519
2023-01-22 18:30:44.156448: step: 948/529, loss: 0.010351556353271008
2023-01-22 18:30:45.283886: step: 952/529, loss: 0.00414371769875288
2023-01-22 18:30:46.377104: step: 956/529, loss: 0.004672827199101448
2023-01-22 18:30:47.482115: step: 960/529, loss: 0.005142142064869404
2023-01-22 18:30:48.579875: step: 964/529, loss: 0.007731347344815731
2023-01-22 18:30:49.688619: step: 968/529, loss: 0.0029873691964894533
2023-01-22 18:30:50.810186: step: 972/529, loss: 0.0059210131876170635
2023-01-22 18:30:51.911649: step: 976/529, loss: 0.013368169777095318
2023-01-22 18:30:53.027907: step: 980/529, loss: 0.026535727083683014
2023-01-22 18:30:54.136159: step: 984/529, loss: 0.009639458730816841
2023-01-22 18:30:55.252059: step: 988/529, loss: 0.015243644826114178
2023-01-22 18:30:56.367168: step: 992/529, loss: 0.004069318063557148
2023-01-22 18:30:57.474201: step: 996/529, loss: 0.006744795944541693
2023-01-22 18:30:58.597283: step: 1000/529, loss: 0.0044373259879648685
2023-01-22 18:30:59.697832: step: 1004/529, loss: 0.006861021742224693
2023-01-22 18:31:00.831200: step: 1008/529, loss: 0.009816762991249561
2023-01-22 18:31:01.932756: step: 1012/529, loss: 0.0045770020224153996
2023-01-22 18:31:03.015220: step: 1016/529, loss: 0.0018444191664457321
2023-01-22 18:31:04.112965: step: 1020/529, loss: 0.0036486079916357994
2023-01-22 18:31:05.214515: step: 1024/529, loss: 0.006663595791906118
2023-01-22 18:31:06.336650: step: 1028/529, loss: 0.0068853083066642284
2023-01-22 18:31:07.436011: step: 1032/529, loss: 0.016710858792066574
2023-01-22 18:31:08.562300: step: 1036/529, loss: 0.01309026125818491
2023-01-22 18:31:09.654421: step: 1040/529, loss: 0.047220248728990555
2023-01-22 18:31:10.752647: step: 1044/529, loss: 0.00925512332469225
2023-01-22 18:31:11.888023: step: 1048/529, loss: 0.03308819234371185
2023-01-22 18:31:12.983869: step: 1052/529, loss: 0.0033879652619361877
2023-01-22 18:31:14.091597: step: 1056/529, loss: 0.00047140775131992996
2023-01-22 18:31:15.217801: step: 1060/529, loss: 0.007818601094186306
2023-01-22 18:31:16.319866: step: 1064/529, loss: 0.0001789512170944363
2023-01-22 18:31:17.414398: step: 1068/529, loss: 0.003873070701956749
2023-01-22 18:31:18.524371: step: 1072/529, loss: 0.029652584344148636
2023-01-22 18:31:19.630538: step: 1076/529, loss: 0.02211040072143078
2023-01-22 18:31:20.737981: step: 1080/529, loss: 0.005249269772320986
2023-01-22 18:31:21.843294: step: 1084/529, loss: 0.01418808102607727
2023-01-22 18:31:22.948635: step: 1088/529, loss: 0.018592024222016335
2023-01-22 18:31:24.068132: step: 1092/529, loss: 0.008901447989046574
2023-01-22 18:31:25.163170: step: 1096/529, loss: 0.04650983586907387
2023-01-22 18:31:26.249245: step: 1100/529, loss: 0.01016843318939209
2023-01-22 18:31:27.360037: step: 1104/529, loss: 0.0009103661868721247
2023-01-22 18:31:28.483170: step: 1108/529, loss: 0.015927115455269814
2023-01-22 18:31:29.599038: step: 1112/529, loss: 0.003786415560171008
2023-01-22 18:31:30.714533: step: 1116/529, loss: 0.005481277592480183
2023-01-22 18:31:31.821806: step: 1120/529, loss: 0.019856378436088562
2023-01-22 18:31:32.926336: step: 1124/529, loss: 0.06672421842813492
2023-01-22 18:31:34.020101: step: 1128/529, loss: 0.004589391406625509
2023-01-22 18:31:35.126534: step: 1132/529, loss: 0.04602415859699249
2023-01-22 18:31:36.231097: step: 1136/529, loss: 0.012788642197847366
2023-01-22 18:31:37.368736: step: 1140/529, loss: 0.030948707833886147
2023-01-22 18:31:38.459980: step: 1144/529, loss: 0.019195549190044403
2023-01-22 18:31:39.553130: step: 1148/529, loss: 0.057643767446279526
2023-01-22 18:31:40.644687: step: 1152/529, loss: 0.005220762453973293
2023-01-22 18:31:41.779545: step: 1156/529, loss: 0.011224639602005482
2023-01-22 18:31:42.883460: step: 1160/529, loss: 0.0016792897367849946
2023-01-22 18:31:43.989080: step: 1164/529, loss: 0.01700332574546337
2023-01-22 18:31:45.104782: step: 1168/529, loss: 0.004716961644589901
2023-01-22 18:31:46.213756: step: 1172/529, loss: 0.0006620117928832769
2023-01-22 18:31:47.312473: step: 1176/529, loss: 0.002469106810167432
2023-01-22 18:31:48.431139: step: 1180/529, loss: 0.023486923426389694
2023-01-22 18:31:49.540798: step: 1184/529, loss: 0.03730182722210884
2023-01-22 18:31:50.658311: step: 1188/529, loss: 0.005834262818098068
2023-01-22 18:31:51.759053: step: 1192/529, loss: 0.0055563002824783325
2023-01-22 18:31:52.874850: step: 1196/529, loss: 0.0059983497485518456
2023-01-22 18:31:53.976567: step: 1200/529, loss: 0.031246904283761978
2023-01-22 18:31:55.091293: step: 1204/529, loss: 0.0033794923219829798
2023-01-22 18:31:56.198484: step: 1208/529, loss: 0.002044606488198042
2023-01-22 18:31:57.328614: step: 1212/529, loss: 0.01928640343248844
2023-01-22 18:31:58.438893: step: 1216/529, loss: 0.009126346558332443
2023-01-22 18:31:59.536833: step: 1220/529, loss: 0.024784620851278305
2023-01-22 18:32:00.655137: step: 1224/529, loss: 0.00625180546194315
2023-01-22 18:32:01.761418: step: 1228/529, loss: 0.019677041098475456
2023-01-22 18:32:02.897495: step: 1232/529, loss: 0.008510519750416279
2023-01-22 18:32:04.025037: step: 1236/529, loss: 0.014463532716035843
2023-01-22 18:32:05.136191: step: 1240/529, loss: 0.0019503699149936438
2023-01-22 18:32:06.255413: step: 1244/529, loss: 0.008476648479700089
2023-01-22 18:32:07.385075: step: 1248/529, loss: 0.0016467832028865814
2023-01-22 18:32:08.501134: step: 1252/529, loss: 0.011762903071939945
2023-01-22 18:32:09.606211: step: 1256/529, loss: 0.022418145090341568
2023-01-22 18:32:10.724969: step: 1260/529, loss: 0.03791734576225281
2023-01-22 18:32:11.873307: step: 1264/529, loss: 0.0024281104560941458
2023-01-22 18:32:12.982437: step: 1268/529, loss: 0.003130145836621523
2023-01-22 18:32:14.098158: step: 1272/529, loss: 0.005850307643413544
2023-01-22 18:32:15.208837: step: 1276/529, loss: 0.010025348514318466
2023-01-22 18:32:16.337399: step: 1280/529, loss: 0.0015392365166917443
2023-01-22 18:32:17.456370: step: 1284/529, loss: 0.09602412581443787
2023-01-22 18:32:18.576928: step: 1288/529, loss: 0.004956912714987993
2023-01-22 18:32:19.677151: step: 1292/529, loss: 0.01091617438942194
2023-01-22 18:32:20.776999: step: 1296/529, loss: 0.004811576101928949
2023-01-22 18:32:21.906248: step: 1300/529, loss: 0.0041037858463823795
2023-01-22 18:32:23.005637: step: 1304/529, loss: 0.005641773343086243
2023-01-22 18:32:24.146495: step: 1308/529, loss: 0.006840884685516357
2023-01-22 18:32:25.263500: step: 1312/529, loss: 0.02102852612733841
2023-01-22 18:32:26.380666: step: 1316/529, loss: 0.013571326620876789
2023-01-22 18:32:27.497312: step: 1320/529, loss: 0.01271682046353817
2023-01-22 18:32:28.613631: step: 1324/529, loss: 0.008418488316237926
2023-01-22 18:32:29.722547: step: 1328/529, loss: 0.021897785365581512
2023-01-22 18:32:30.822658: step: 1332/529, loss: 0.006459553726017475
2023-01-22 18:32:31.936206: step: 1336/529, loss: 0.0351315401494503
2023-01-22 18:32:33.039871: step: 1340/529, loss: 0.01350568700581789
2023-01-22 18:32:34.140193: step: 1344/529, loss: 0.0046593365259468555
2023-01-22 18:32:35.252529: step: 1348/529, loss: 0.016990235075354576
2023-01-22 18:32:36.361093: step: 1352/529, loss: 0.001244245795533061
2023-01-22 18:32:37.471653: step: 1356/529, loss: 0.0010579493828117847
2023-01-22 18:32:38.579906: step: 1360/529, loss: 0.0009354364592581987
2023-01-22 18:32:39.698150: step: 1364/529, loss: 0.013501330278813839
2023-01-22 18:32:40.803719: step: 1368/529, loss: 0.011196371167898178
2023-01-22 18:32:41.915352: step: 1372/529, loss: 0.010294260457158089
2023-01-22 18:32:43.033203: step: 1376/529, loss: 0.010214634239673615
2023-01-22 18:32:44.145773: step: 1380/529, loss: 0.006198344752192497
2023-01-22 18:32:45.244616: step: 1384/529, loss: 0.008807285688817501
2023-01-22 18:32:46.361469: step: 1388/529, loss: 0.006719553377479315
2023-01-22 18:32:47.462365: step: 1392/529, loss: 0.005882189143449068
2023-01-22 18:32:48.559206: step: 1396/529, loss: 0.005123903043568134
2023-01-22 18:32:49.659189: step: 1400/529, loss: 8.376445475732908e-05
2023-01-22 18:32:50.782956: step: 1404/529, loss: 0.002987247658893466
2023-01-22 18:32:51.906906: step: 1408/529, loss: 0.005623606964945793
2023-01-22 18:32:53.011949: step: 1412/529, loss: 0.008316478691995144
2023-01-22 18:32:54.136191: step: 1416/529, loss: 0.0110525693744421
2023-01-22 18:32:55.233195: step: 1420/529, loss: 0.014707077294588089
2023-01-22 18:32:56.366012: step: 1424/529, loss: 0.009544271975755692
2023-01-22 18:32:57.475171: step: 1428/529, loss: 0.010115514509379864
2023-01-22 18:32:58.577987: step: 1432/529, loss: 0.037536054849624634
2023-01-22 18:32:59.692127: step: 1436/529, loss: 0.005475954618304968
2023-01-22 18:33:00.783300: step: 1440/529, loss: 0.007395019289106131
2023-01-22 18:33:01.930664: step: 1444/529, loss: 0.02025020122528076
2023-01-22 18:33:03.059135: step: 1448/529, loss: 0.015663426369428635
2023-01-22 18:33:04.158006: step: 1452/529, loss: 0.0006771829794161022
2023-01-22 18:33:05.263134: step: 1456/529, loss: 0.009414381347596645
2023-01-22 18:33:06.357362: step: 1460/529, loss: 0.0007117522764019668
2023-01-22 18:33:07.483181: step: 1464/529, loss: 0.015193939208984375
2023-01-22 18:33:08.633974: step: 1468/529, loss: 0.023331169039011
2023-01-22 18:33:09.757880: step: 1472/529, loss: 0.013729014433920383
2023-01-22 18:33:10.870315: step: 1476/529, loss: 0.10108592361211777
2023-01-22 18:33:11.991604: step: 1480/529, loss: 0.006191513501107693
2023-01-22 18:33:13.101971: step: 1484/529, loss: 0.0033932547084987164
2023-01-22 18:33:14.206934: step: 1488/529, loss: 0.0005136637482792139
2023-01-22 18:33:15.307701: step: 1492/529, loss: 0.001695052022114396
2023-01-22 18:33:16.437582: step: 1496/529, loss: 0.0025329450145363808
2023-01-22 18:33:17.531901: step: 1500/529, loss: 0.06505904346704483
2023-01-22 18:33:18.629977: step: 1504/529, loss: 0.0009990466060116887
2023-01-22 18:33:19.721932: step: 1508/529, loss: 0.001257079653441906
2023-01-22 18:33:20.839104: step: 1512/529, loss: 0.010051651857793331
2023-01-22 18:33:21.970311: step: 1516/529, loss: 0.005372804589569569
2023-01-22 18:33:23.084075: step: 1520/529, loss: 0.0012749641900882125
2023-01-22 18:33:24.184357: step: 1524/529, loss: 0.0033251801505684853
2023-01-22 18:33:25.287210: step: 1528/529, loss: 0.03823993727564812
2023-01-22 18:33:26.408031: step: 1532/529, loss: 0.00402421411126852
2023-01-22 18:33:27.549057: step: 1536/529, loss: 0.001792093156836927
2023-01-22 18:33:28.658644: step: 1540/529, loss: 0.01689228042960167
2023-01-22 18:33:29.750428: step: 1544/529, loss: 0.01427196990698576
2023-01-22 18:33:30.860444: step: 1548/529, loss: 0.011329120956361294
2023-01-22 18:33:31.988348: step: 1552/529, loss: 0.0033109106589108706
2023-01-22 18:33:33.133839: step: 1556/529, loss: 0.0016857982845976949
2023-01-22 18:33:34.241505: step: 1560/529, loss: 0.0032844559755176306
2023-01-22 18:33:35.349794: step: 1564/529, loss: 0.005794933997094631
2023-01-22 18:33:36.455023: step: 1568/529, loss: 0.003992067649960518
2023-01-22 18:33:37.569886: step: 1572/529, loss: 0.009744444862008095
2023-01-22 18:33:38.689475: step: 1576/529, loss: 0.006623596418648958
2023-01-22 18:33:39.813638: step: 1580/529, loss: 0.016973726451396942
2023-01-22 18:33:40.919254: step: 1584/529, loss: 0.002122956793755293
2023-01-22 18:33:42.020494: step: 1588/529, loss: 0.003243247279897332
2023-01-22 18:33:43.168268: step: 1592/529, loss: 0.001763826236128807
2023-01-22 18:33:44.275745: step: 1596/529, loss: 0.0013744751922786236
2023-01-22 18:33:45.369344: step: 1600/529, loss: 0.008129049092531204
2023-01-22 18:33:46.470195: step: 1604/529, loss: 0.04044123366475105
2023-01-22 18:33:47.582139: step: 1608/529, loss: 0.015696074813604355
2023-01-22 18:33:48.708819: step: 1612/529, loss: 0.016748961061239243
2023-01-22 18:33:49.828558: step: 1616/529, loss: 0.04168316349387169
2023-01-22 18:33:50.933562: step: 1620/529, loss: 0.024754514917731285
2023-01-22 18:33:52.048828: step: 1624/529, loss: 0.009901798330247402
2023-01-22 18:33:53.170066: step: 1628/529, loss: 0.0010433894349262118
2023-01-22 18:33:54.259329: step: 1632/529, loss: 0.0022630058228969574
2023-01-22 18:33:55.362449: step: 1636/529, loss: 0.005433759652078152
2023-01-22 18:33:56.464410: step: 1640/529, loss: 0.004507997073233128
2023-01-22 18:33:57.564670: step: 1644/529, loss: 0.0015100986929610372
2023-01-22 18:33:58.709024: step: 1648/529, loss: 0.011910167522728443
2023-01-22 18:33:59.814127: step: 1652/529, loss: 0.004427351988852024
2023-01-22 18:34:00.926446: step: 1656/529, loss: 0.005018251948058605
2023-01-22 18:34:02.025254: step: 1660/529, loss: 0.005804268177598715
2023-01-22 18:34:03.096431: step: 1664/529, loss: 0.02130913734436035
2023-01-22 18:34:04.190575: step: 1668/529, loss: 0.0015406433958560228
2023-01-22 18:34:05.293420: step: 1672/529, loss: 0.003071944694966078
2023-01-22 18:34:06.412686: step: 1676/529, loss: 0.001010268577374518
2023-01-22 18:34:07.545972: step: 1680/529, loss: 0.00027104635955765843
2023-01-22 18:34:08.670895: step: 1684/529, loss: 0.012311664409935474
2023-01-22 18:34:09.754698: step: 1688/529, loss: 0.0005201937165111303
2023-01-22 18:34:10.869494: step: 1692/529, loss: 0.010430201888084412
2023-01-22 18:34:11.992976: step: 1696/529, loss: 0.009044974111020565
2023-01-22 18:34:13.107353: step: 1700/529, loss: 0.02239764668047428
2023-01-22 18:34:14.213364: step: 1704/529, loss: 0.02251269854605198
2023-01-22 18:34:15.329505: step: 1708/529, loss: 0.005508198402822018
2023-01-22 18:34:16.444784: step: 1712/529, loss: 0.014079774729907513
2023-01-22 18:34:17.570080: step: 1716/529, loss: 0.023932337760925293
2023-01-22 18:34:18.703647: step: 1720/529, loss: 0.0025198282673954964
2023-01-22 18:34:19.821256: step: 1724/529, loss: 0.0054346430115401745
2023-01-22 18:34:20.970455: step: 1728/529, loss: 0.016678204759955406
2023-01-22 18:34:22.056331: step: 1732/529, loss: 0.005527746398001909
2023-01-22 18:34:23.164334: step: 1736/529, loss: 0.024834997951984406
2023-01-22 18:34:24.271213: step: 1740/529, loss: 0.027903374284505844
2023-01-22 18:34:25.361427: step: 1744/529, loss: 0.0011577687691897154
2023-01-22 18:34:26.449344: step: 1748/529, loss: 0.017095379531383514
2023-01-22 18:34:27.560243: step: 1752/529, loss: 0.003511288436129689
2023-01-22 18:34:28.674772: step: 1756/529, loss: 0.0049431780353188515
2023-01-22 18:34:29.785690: step: 1760/529, loss: 0.00928831472992897
2023-01-22 18:34:30.880505: step: 1764/529, loss: 0.005988477263599634
2023-01-22 18:34:31.962874: step: 1768/529, loss: 0.010179761797189713
2023-01-22 18:34:33.059581: step: 1772/529, loss: 0.010879379697144032
2023-01-22 18:34:34.166935: step: 1776/529, loss: 0.006690423935651779
2023-01-22 18:34:35.277355: step: 1780/529, loss: 0.007379619404673576
2023-01-22 18:34:36.384848: step: 1784/529, loss: 0.014838037081062794
2023-01-22 18:34:37.493103: step: 1788/529, loss: 0.007637612521648407
2023-01-22 18:34:38.611279: step: 1792/529, loss: 0.003951916936784983
2023-01-22 18:34:39.710501: step: 1796/529, loss: 0.007001466117799282
2023-01-22 18:34:40.824268: step: 1800/529, loss: 0.0009166442323476076
2023-01-22 18:34:41.912948: step: 1804/529, loss: 0.0013012280687689781
2023-01-22 18:34:43.020943: step: 1808/529, loss: 0.002779993461444974
2023-01-22 18:34:44.120313: step: 1812/529, loss: 0.015612097457051277
2023-01-22 18:34:45.237983: step: 1816/529, loss: 0.0012944986810907722
2023-01-22 18:34:46.363182: step: 1820/529, loss: 0.012227851897478104
2023-01-22 18:34:47.474288: step: 1824/529, loss: 0.013243754394352436
2023-01-22 18:34:48.594512: step: 1828/529, loss: 0.004501806106418371
2023-01-22 18:34:49.697063: step: 1832/529, loss: 0.003766302252188325
2023-01-22 18:34:50.833230: step: 1836/529, loss: 0.01177501492202282
2023-01-22 18:34:51.949479: step: 1840/529, loss: 0.004233608953654766
2023-01-22 18:34:53.054314: step: 1844/529, loss: 0.012065853923559189
2023-01-22 18:34:54.151013: step: 1848/529, loss: 0.01186690665781498
2023-01-22 18:34:55.255621: step: 1852/529, loss: 0.007836073637008667
2023-01-22 18:34:56.351419: step: 1856/529, loss: 0.0040960488840937614
2023-01-22 18:34:57.466565: step: 1860/529, loss: 0.0016701840795576572
2023-01-22 18:34:58.605153: step: 1864/529, loss: 0.007522040046751499
2023-01-22 18:34:59.726367: step: 1868/529, loss: 0.007356657646596432
2023-01-22 18:35:00.850999: step: 1872/529, loss: 0.01644561067223549
2023-01-22 18:35:01.940163: step: 1876/529, loss: 0.0
2023-01-22 18:35:03.017487: step: 1880/529, loss: 0.0005244215135462582
2023-01-22 18:35:04.145044: step: 1884/529, loss: 0.02792527712881565
2023-01-22 18:35:05.272926: step: 1888/529, loss: 0.020295726135373116
2023-01-22 18:35:06.370617: step: 1892/529, loss: 0.007545561529695988
2023-01-22 18:35:07.481904: step: 1896/529, loss: 0.007613576017320156
2023-01-22 18:35:08.571442: step: 1900/529, loss: 0.006284275557845831
2023-01-22 18:35:09.667074: step: 1904/529, loss: 0.003373147686943412
2023-01-22 18:35:10.765034: step: 1908/529, loss: 0.008601627312600613
2023-01-22 18:35:11.844700: step: 1912/529, loss: 0.005692754406481981
2023-01-22 18:35:12.936252: step: 1916/529, loss: 0.007508687674999237
2023-01-22 18:35:14.075805: step: 1920/529, loss: 0.010715275071561337
2023-01-22 18:35:15.182054: step: 1924/529, loss: 0.014799711294472218
2023-01-22 18:35:16.292163: step: 1928/529, loss: 0.03008132614195347
2023-01-22 18:35:17.425131: step: 1932/529, loss: 0.0021488473284989595
2023-01-22 18:35:18.537086: step: 1936/529, loss: 0.00580828869715333
2023-01-22 18:35:19.648549: step: 1940/529, loss: 0.0005442879046313465
2023-01-22 18:35:20.752947: step: 1944/529, loss: 0.0023842223454266787
2023-01-22 18:35:21.872179: step: 1948/529, loss: 0.010349349118769169
2023-01-22 18:35:22.979904: step: 1952/529, loss: 0.005742854438722134
2023-01-22 18:35:24.088945: step: 1956/529, loss: 0.005746699869632721
2023-01-22 18:35:25.176394: step: 1960/529, loss: 0.0030572963878512383
2023-01-22 18:35:26.271015: step: 1964/529, loss: 0.002705326536670327
2023-01-22 18:35:27.415049: step: 1968/529, loss: 0.0017700176686048508
2023-01-22 18:35:28.506992: step: 1972/529, loss: 0.0073394086211919785
2023-01-22 18:35:29.618365: step: 1976/529, loss: 0.006702421233057976
2023-01-22 18:35:30.693305: step: 1980/529, loss: 0.00996773038059473
2023-01-22 18:35:31.786198: step: 1984/529, loss: 0.0006468212814070284
2023-01-22 18:35:32.893814: step: 1988/529, loss: 0.010966029949486256
2023-01-22 18:35:33.987618: step: 1992/529, loss: 0.017896467819809914
2023-01-22 18:35:35.099171: step: 1996/529, loss: 0.005553707480430603
2023-01-22 18:35:36.210597: step: 2000/529, loss: 0.001417280058376491
2023-01-22 18:35:37.308318: step: 2004/529, loss: 0.002545019146054983
2023-01-22 18:35:38.412503: step: 2008/529, loss: 0.008214138448238373
2023-01-22 18:35:39.518319: step: 2012/529, loss: 0.004287917632609606
2023-01-22 18:35:40.628257: step: 2016/529, loss: 0.001959157409146428
2023-01-22 18:35:41.730678: step: 2020/529, loss: 0.009076257236301899
2023-01-22 18:35:42.828854: step: 2024/529, loss: 0.0019160517258569598
2023-01-22 18:35:43.941057: step: 2028/529, loss: 0.0029994845390319824
2023-01-22 18:35:45.083157: step: 2032/529, loss: 0.019224248826503754
2023-01-22 18:35:46.213307: step: 2036/529, loss: 0.0018323797266930342
2023-01-22 18:35:47.320871: step: 2040/529, loss: 0.008813927881419659
2023-01-22 18:35:48.422786: step: 2044/529, loss: 0.0007864231592975557
2023-01-22 18:35:49.528358: step: 2048/529, loss: 0.009530700743198395
2023-01-22 18:35:50.628692: step: 2052/529, loss: 0.005855603143572807
2023-01-22 18:35:51.735999: step: 2056/529, loss: 0.0010591085301712155
2023-01-22 18:35:52.833994: step: 2060/529, loss: 0.015139475464820862
2023-01-22 18:35:53.951096: step: 2064/529, loss: 0.014226407743990421
2023-01-22 18:35:55.065429: step: 2068/529, loss: 0.005667650606483221
2023-01-22 18:35:56.175827: step: 2072/529, loss: 0.008938327431678772
2023-01-22 18:35:57.288932: step: 2076/529, loss: 0.059929583221673965
2023-01-22 18:35:58.394405: step: 2080/529, loss: 0.01760035566985607
2023-01-22 18:35:59.519502: step: 2084/529, loss: 0.004652060568332672
2023-01-22 18:36:00.607159: step: 2088/529, loss: 0.0022942896466702223
2023-01-22 18:36:01.721661: step: 2092/529, loss: 0.009372753091156483
2023-01-22 18:36:02.837024: step: 2096/529, loss: 0.011929132975637913
2023-01-22 18:36:03.939312: step: 2100/529, loss: 0.003926228266209364
2023-01-22 18:36:05.070294: step: 2104/529, loss: 0.03250231221318245
2023-01-22 18:36:06.173785: step: 2108/529, loss: 0.021480895578861237
2023-01-22 18:36:07.260958: step: 2112/529, loss: 0.0008534525986760855
2023-01-22 18:36:08.365483: step: 2116/529, loss: 0.002471882151439786
==================================================
Loss: 0.011
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32999000275785995, 'r': 0.3243544998644619, 'f1': 0.327147983595352}, 'combined': 0.24105640896499622, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3745858066297534, 'r': 0.29707411157822866, 'f1': 0.3313574107898156}, 'combined': 0.20366357931471593, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328357991133387, 'r': 0.3423093038319347, 'f1': 0.33750608628518164}, 'combined': 0.24868869515750225, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3550112181758806, 'r': 0.310096454004582, 'f1': 0.3310372876237629}, 'combined': 0.203466820685825, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34230520495764394, 'r': 0.34620241791731354, 'f1': 0.3442427815894797}, 'combined': 0.25365257590803764, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3670222493703738, 'r': 0.2971132494903026, 'f1': 0.32838832838401866}, 'combined': 0.2028280851783645, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35185185185185186, 'r': 0.41304347826086957, 'f1': 0.38}, 'combined': 0.19, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 7
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 18:38:37.338330: step: 4/529, loss: 0.0030545054469257593
2023-01-22 18:38:38.450531: step: 8/529, loss: 3.35619188263081e-05
2023-01-22 18:38:39.515531: step: 12/529, loss: 0.0008464528946205974
2023-01-22 18:38:40.672994: step: 16/529, loss: 0.0038379754405468702
2023-01-22 18:38:41.782326: step: 20/529, loss: 0.021549325436353683
2023-01-22 18:38:42.905198: step: 24/529, loss: 0.0104114580899477
2023-01-22 18:38:44.031390: step: 28/529, loss: 0.011546680703759193
2023-01-22 18:38:45.124119: step: 32/529, loss: 0.0034092096611857414
2023-01-22 18:38:46.224139: step: 36/529, loss: 0.002887334441766143
2023-01-22 18:38:47.344130: step: 40/529, loss: 0.0013238664250820875
2023-01-22 18:38:48.471228: step: 44/529, loss: 0.00871653389185667
2023-01-22 18:38:49.601616: step: 48/529, loss: 0.008016478270292282
2023-01-22 18:38:50.714359: step: 52/529, loss: 0.009020499885082245
2023-01-22 18:38:51.815695: step: 56/529, loss: 0.007172887679189444
2023-01-22 18:38:52.912416: step: 60/529, loss: 0.007009623106569052
2023-01-22 18:38:54.016007: step: 64/529, loss: 0.0005968121695332229
2023-01-22 18:38:55.126735: step: 68/529, loss: 0.0018050582148134708
2023-01-22 18:38:56.229723: step: 72/529, loss: 0.0016797339776530862
2023-01-22 18:38:57.325349: step: 76/529, loss: 0.007626965641975403
2023-01-22 18:38:58.429070: step: 80/529, loss: 0.010014185681939125
2023-01-22 18:38:59.542340: step: 84/529, loss: 0.003433970967307687
2023-01-22 18:39:00.643779: step: 88/529, loss: 0.004399940371513367
2023-01-22 18:39:01.716076: step: 92/529, loss: 0.0033530103974044323
2023-01-22 18:39:02.817739: step: 96/529, loss: 0.00021855183877050877
2023-01-22 18:39:03.920333: step: 100/529, loss: 0.0024746328126639128
2023-01-22 18:39:04.999338: step: 104/529, loss: 4.1829844121821225e-05
2023-01-22 18:39:06.083113: step: 108/529, loss: 0.0035631083883345127
2023-01-22 18:39:07.194348: step: 112/529, loss: 0.05124026536941528
2023-01-22 18:39:08.312404: step: 116/529, loss: 0.010831589810550213
2023-01-22 18:39:09.433508: step: 120/529, loss: 0.022203927859663963
2023-01-22 18:39:10.555608: step: 124/529, loss: 0.0019304860616102815
2023-01-22 18:39:11.657104: step: 128/529, loss: 0.0015121285105124116
2023-01-22 18:39:12.764504: step: 132/529, loss: 0.0012433846713975072
2023-01-22 18:39:13.863974: step: 136/529, loss: 0.007195828948169947
2023-01-22 18:39:14.991955: step: 140/529, loss: 0.051155611872673035
2023-01-22 18:39:16.113760: step: 144/529, loss: 0.022610561922192574
2023-01-22 18:39:17.222983: step: 148/529, loss: 0.015706732869148254
2023-01-22 18:39:18.347405: step: 152/529, loss: 0.009368144907057285
2023-01-22 18:39:19.478958: step: 156/529, loss: 0.021543605253100395
2023-01-22 18:39:20.598054: step: 160/529, loss: 0.007966682314872742
2023-01-22 18:39:21.706946: step: 164/529, loss: 0.0033177065197378397
2023-01-22 18:39:22.826915: step: 168/529, loss: 0.0019967108964920044
2023-01-22 18:39:23.932593: step: 172/529, loss: 0.007210269570350647
2023-01-22 18:39:25.049656: step: 176/529, loss: 0.004201869014650583
2023-01-22 18:39:26.190713: step: 180/529, loss: 0.003667253302410245
2023-01-22 18:39:27.305037: step: 184/529, loss: 0.015110588632524014
2023-01-22 18:39:28.413643: step: 188/529, loss: 0.006328313611447811
2023-01-22 18:39:29.511184: step: 192/529, loss: 0.00014509470202028751
2023-01-22 18:39:30.623517: step: 196/529, loss: 0.006437382660806179
2023-01-22 18:39:31.735374: step: 200/529, loss: 0.01717740297317505
2023-01-22 18:39:32.874403: step: 204/529, loss: 0.016561701893806458
2023-01-22 18:39:33.996767: step: 208/529, loss: 0.004435568116605282
2023-01-22 18:39:35.108892: step: 212/529, loss: 0.0149191003292799
2023-01-22 18:39:36.215592: step: 216/529, loss: 0.012894520536065102
2023-01-22 18:39:37.329262: step: 220/529, loss: 0.0027414702344685793
2023-01-22 18:39:38.436631: step: 224/529, loss: 0.0025472422130405903
2023-01-22 18:39:39.528347: step: 228/529, loss: 0.020510386675596237
2023-01-22 18:39:40.628741: step: 232/529, loss: 0.00802549161016941
2023-01-22 18:39:41.731310: step: 236/529, loss: 0.015726827085018158
2023-01-22 18:39:42.839542: step: 240/529, loss: 0.010865849442780018
2023-01-22 18:39:43.938035: step: 244/529, loss: 0.008605439215898514
2023-01-22 18:39:45.040592: step: 248/529, loss: 0.009382029995322227
2023-01-22 18:39:46.159940: step: 252/529, loss: 0.007287350948899984
2023-01-22 18:39:47.253658: step: 256/529, loss: 0.007945645600557327
2023-01-22 18:39:48.353837: step: 260/529, loss: 0.0009632874862290919
2023-01-22 18:39:49.467232: step: 264/529, loss: 0.005275438539683819
2023-01-22 18:39:50.578596: step: 268/529, loss: 0.0007581347017548978
2023-01-22 18:39:51.689036: step: 272/529, loss: 0.015828052535653114
2023-01-22 18:39:52.787854: step: 276/529, loss: 0.006983165629208088
2023-01-22 18:39:53.904061: step: 280/529, loss: 0.010498067364096642
2023-01-22 18:39:55.005324: step: 284/529, loss: 0.007609185762703419
2023-01-22 18:39:56.110830: step: 288/529, loss: 0.007381083443760872
2023-01-22 18:39:57.208437: step: 292/529, loss: 0.0025392977986484766
2023-01-22 18:39:58.316967: step: 296/529, loss: 0.0058061471208930016
2023-01-22 18:39:59.431599: step: 300/529, loss: 0.022824106737971306
2023-01-22 18:40:00.557310: step: 304/529, loss: 0.004457931034266949
2023-01-22 18:40:01.667839: step: 308/529, loss: 0.007100955583155155
2023-01-22 18:40:02.792365: step: 312/529, loss: 0.009412058629095554
2023-01-22 18:40:03.911924: step: 316/529, loss: 0.013740717433393002
2023-01-22 18:40:05.036949: step: 320/529, loss: 0.0007836969452910125
2023-01-22 18:40:06.148698: step: 324/529, loss: 0.0025598241481930017
2023-01-22 18:40:07.252541: step: 328/529, loss: 0.00013891237904317677
2023-01-22 18:40:08.358025: step: 332/529, loss: 0.029512524604797363
2023-01-22 18:40:09.459353: step: 336/529, loss: 0.0036302239168435335
2023-01-22 18:40:10.552200: step: 340/529, loss: 0.0012657804181799293
2023-01-22 18:40:11.674690: step: 344/529, loss: 0.006451549474149942
2023-01-22 18:40:12.783400: step: 348/529, loss: 0.0017815489554777741
2023-01-22 18:40:13.885693: step: 352/529, loss: 0.0008167997002601624
2023-01-22 18:40:14.982333: step: 356/529, loss: 0.0016680710250511765
2023-01-22 18:40:16.129202: step: 360/529, loss: 0.006359196733683348
2023-01-22 18:40:17.226766: step: 364/529, loss: 0.003547897795215249
2023-01-22 18:40:18.361048: step: 368/529, loss: 0.018223920837044716
2023-01-22 18:40:19.477322: step: 372/529, loss: 0.0040784962475299835
2023-01-22 18:40:20.605076: step: 376/529, loss: 0.002145932288840413
2023-01-22 18:40:21.721856: step: 380/529, loss: 0.009615127928555012
2023-01-22 18:40:22.849446: step: 384/529, loss: 0.022602489218115807
2023-01-22 18:40:23.956882: step: 388/529, loss: 0.005098290741443634
2023-01-22 18:40:25.081844: step: 392/529, loss: 0.010976966470479965
2023-01-22 18:40:26.185718: step: 396/529, loss: 0.013189560733735561
2023-01-22 18:40:27.277935: step: 400/529, loss: 0.007032593712210655
2023-01-22 18:40:28.382414: step: 404/529, loss: 0.019586682319641113
2023-01-22 18:40:29.489184: step: 408/529, loss: 0.006527661345899105
2023-01-22 18:40:30.604885: step: 412/529, loss: 0.013549278490245342
2023-01-22 18:40:31.713143: step: 416/529, loss: 0.025871869176626205
2023-01-22 18:40:32.830054: step: 420/529, loss: 0.0035328990779817104
2023-01-22 18:40:33.955999: step: 424/529, loss: 0.013496090658009052
2023-01-22 18:40:35.067345: step: 428/529, loss: 0.04311005398631096
2023-01-22 18:40:36.185853: step: 432/529, loss: 0.004175006877630949
2023-01-22 18:40:37.289138: step: 436/529, loss: 0.011185020208358765
2023-01-22 18:40:38.403646: step: 440/529, loss: 0.022860603407025337
2023-01-22 18:40:39.492736: step: 444/529, loss: 0.00024456216488033533
2023-01-22 18:40:40.581357: step: 448/529, loss: 0.0033862697891891003
2023-01-22 18:40:41.706873: step: 452/529, loss: 0.0021403245627880096
2023-01-22 18:40:42.821588: step: 456/529, loss: 0.003632894018664956
2023-01-22 18:40:43.927354: step: 460/529, loss: 0.016885651275515556
2023-01-22 18:40:45.039674: step: 464/529, loss: 0.0039877681992948055
2023-01-22 18:40:46.168599: step: 468/529, loss: 0.004039587918668985
2023-01-22 18:40:47.276669: step: 472/529, loss: 0.003896596608683467
2023-01-22 18:40:48.423644: step: 476/529, loss: 0.0023756225127726793
2023-01-22 18:40:49.542299: step: 480/529, loss: 0.018946556374430656
2023-01-22 18:40:50.638600: step: 484/529, loss: 0.0030556556303054094
2023-01-22 18:40:51.763343: step: 488/529, loss: 0.012143340893089771
2023-01-22 18:40:52.892127: step: 492/529, loss: 0.014629404060542583
2023-01-22 18:40:54.005818: step: 496/529, loss: 0.003899217117577791
2023-01-22 18:40:55.095514: step: 500/529, loss: 0.0001421123306499794
2023-01-22 18:40:56.222155: step: 504/529, loss: 0.0795435756444931
2023-01-22 18:40:57.326358: step: 508/529, loss: 0.0029668051283806562
2023-01-22 18:40:58.414794: step: 512/529, loss: 0.006415557116270065
2023-01-22 18:40:59.533785: step: 516/529, loss: 0.0025698819663375616
2023-01-22 18:41:00.646599: step: 520/529, loss: 0.05516723170876503
2023-01-22 18:41:01.740924: step: 524/529, loss: 0.005604919046163559
2023-01-22 18:41:02.878606: step: 528/529, loss: 0.002612817334011197
2023-01-22 18:41:03.981292: step: 532/529, loss: 0.003561482299119234
2023-01-22 18:41:05.052879: step: 536/529, loss: 0.018908070400357246
2023-01-22 18:41:06.163740: step: 540/529, loss: 0.00021792951156385243
2023-01-22 18:41:07.301948: step: 544/529, loss: 0.006110842805355787
2023-01-22 18:41:08.418271: step: 548/529, loss: 0.03918713703751564
2023-01-22 18:41:09.535329: step: 552/529, loss: 0.050406988710165024
2023-01-22 18:41:10.655786: step: 556/529, loss: 0.0017296071164309978
2023-01-22 18:41:11.754873: step: 560/529, loss: 0.00035165162989869714
2023-01-22 18:41:12.907099: step: 564/529, loss: 0.008679358288645744
2023-01-22 18:41:14.023188: step: 568/529, loss: 0.007770695257931948
2023-01-22 18:41:15.117247: step: 572/529, loss: 0.0034984855446964502
2023-01-22 18:41:16.230518: step: 576/529, loss: 0.0037792366929352283
2023-01-22 18:41:17.379683: step: 580/529, loss: 0.008669867180287838
2023-01-22 18:41:18.483209: step: 584/529, loss: 0.007455957587808371
2023-01-22 18:41:19.592594: step: 588/529, loss: 0.003013304201886058
2023-01-22 18:41:20.680958: step: 592/529, loss: 0.007323120720684528
2023-01-22 18:41:21.783604: step: 596/529, loss: 0.031962260603904724
2023-01-22 18:41:22.896643: step: 600/529, loss: 0.01004704274237156
2023-01-22 18:41:24.013880: step: 604/529, loss: 0.0027537778951227665
2023-01-22 18:41:25.104734: step: 608/529, loss: 0.002929972717538476
2023-01-22 18:41:26.208545: step: 612/529, loss: 0.005249975249171257
2023-01-22 18:41:27.300867: step: 616/529, loss: 0.009610047563910484
2023-01-22 18:41:28.408585: step: 620/529, loss: 0.007955987937748432
2023-01-22 18:41:29.523448: step: 624/529, loss: 0.03379003331065178
2023-01-22 18:41:30.626850: step: 628/529, loss: 0.002837971318513155
2023-01-22 18:41:31.740114: step: 632/529, loss: 0.0021671061404049397
2023-01-22 18:41:32.866662: step: 636/529, loss: 0.004177336115390062
2023-01-22 18:41:33.994707: step: 640/529, loss: 0.0038862500805407763
2023-01-22 18:41:35.102633: step: 644/529, loss: 0.02319229766726494
2023-01-22 18:41:36.205639: step: 648/529, loss: 0.017669769003987312
2023-01-22 18:41:37.308348: step: 652/529, loss: 0.0007057110778987408
2023-01-22 18:41:38.424634: step: 656/529, loss: 0.0055283447727561
2023-01-22 18:41:39.527175: step: 660/529, loss: 0.006416219752281904
2023-01-22 18:41:40.636273: step: 664/529, loss: 0.005335769150406122
2023-01-22 18:41:41.747146: step: 668/529, loss: 0.004108957014977932
2023-01-22 18:41:42.847190: step: 672/529, loss: 0.03745479881763458
2023-01-22 18:41:43.949442: step: 676/529, loss: 0.0017263751942664385
2023-01-22 18:41:45.052121: step: 680/529, loss: 0.017309946939349174
2023-01-22 18:41:46.169073: step: 684/529, loss: 0.0035648455377668142
2023-01-22 18:41:47.271541: step: 688/529, loss: 0.0004801817412953824
2023-01-22 18:41:48.366215: step: 692/529, loss: 0.006715321913361549
2023-01-22 18:41:49.471570: step: 696/529, loss: 0.014194621704518795
2023-01-22 18:41:50.587538: step: 700/529, loss: 0.0041891890577971935
2023-01-22 18:41:51.694133: step: 704/529, loss: 0.018518999218940735
2023-01-22 18:41:52.811822: step: 708/529, loss: 0.0025279333349317312
2023-01-22 18:41:53.911401: step: 712/529, loss: 0.0013000944163650274
2023-01-22 18:41:55.025489: step: 716/529, loss: 0.017144083976745605
2023-01-22 18:41:56.158523: step: 720/529, loss: 0.00548380333930254
2023-01-22 18:41:57.255432: step: 724/529, loss: 0.02012791484594345
2023-01-22 18:41:58.362037: step: 728/529, loss: 0.0026749796234071255
2023-01-22 18:41:59.492418: step: 732/529, loss: 0.06688763201236725
2023-01-22 18:42:00.597119: step: 736/529, loss: 0.0020136148668825626
2023-01-22 18:42:01.704821: step: 740/529, loss: 0.006192317232489586
2023-01-22 18:42:02.825691: step: 744/529, loss: 0.0007998402579687536
2023-01-22 18:42:03.934411: step: 748/529, loss: 0.0008538974216207862
2023-01-22 18:42:05.036567: step: 752/529, loss: 0.01586047187447548
2023-01-22 18:42:06.145936: step: 756/529, loss: 0.005411903373897076
2023-01-22 18:42:07.265625: step: 760/529, loss: 0.014611969701945782
2023-01-22 18:42:08.387288: step: 764/529, loss: 0.00531504862010479
2023-01-22 18:42:09.484359: step: 768/529, loss: 0.008997040800750256
2023-01-22 18:42:10.594317: step: 772/529, loss: 0.007737362757325172
2023-01-22 18:42:11.697010: step: 776/529, loss: 0.01996825635433197
2023-01-22 18:42:12.805037: step: 780/529, loss: 0.006075692363083363
2023-01-22 18:42:13.919411: step: 784/529, loss: 0.007126900367438793
2023-01-22 18:42:15.014164: step: 788/529, loss: 0.006055962294340134
2023-01-22 18:42:16.130218: step: 792/529, loss: 0.00789804756641388
2023-01-22 18:42:17.236682: step: 796/529, loss: 0.006226102355867624
2023-01-22 18:42:18.364291: step: 800/529, loss: 0.008890541270375252
2023-01-22 18:42:19.452822: step: 804/529, loss: 0.0018181040650233626
2023-01-22 18:42:20.573923: step: 808/529, loss: 0.03955285623669624
2023-01-22 18:42:21.698618: step: 812/529, loss: 0.0028145357500761747
2023-01-22 18:42:22.800347: step: 816/529, loss: 0.0006396938697434962
2023-01-22 18:42:23.905324: step: 820/529, loss: 0.001901389448903501
2023-01-22 18:42:25.019471: step: 824/529, loss: 0.0016176918288692832
2023-01-22 18:42:26.135919: step: 828/529, loss: 0.003536874894052744
2023-01-22 18:42:27.238025: step: 832/529, loss: 0.015310823917388916
2023-01-22 18:42:28.316688: step: 836/529, loss: 0.0036519435234367847
2023-01-22 18:42:29.392733: step: 840/529, loss: 0.0005294833099469543
2023-01-22 18:42:30.494648: step: 844/529, loss: 0.0041089183650910854
2023-01-22 18:42:31.598901: step: 848/529, loss: 0.008666718378663063
2023-01-22 18:42:32.696332: step: 852/529, loss: 0.003968899138271809
2023-01-22 18:42:33.799791: step: 856/529, loss: 0.012749884277582169
2023-01-22 18:42:34.891052: step: 860/529, loss: 0.008709506131708622
2023-01-22 18:42:36.002007: step: 864/529, loss: 0.041848987340927124
2023-01-22 18:42:37.079258: step: 868/529, loss: 0.0026900023221969604
2023-01-22 18:42:38.198964: step: 872/529, loss: 0.037015657871961594
2023-01-22 18:42:39.311521: step: 876/529, loss: 0.004798011854290962
2023-01-22 18:42:40.427031: step: 880/529, loss: 0.0014959161635488272
2023-01-22 18:42:41.538116: step: 884/529, loss: 0.006169901229441166
2023-01-22 18:42:42.659749: step: 888/529, loss: 0.011533129960298538
2023-01-22 18:42:43.773166: step: 892/529, loss: 0.01700163260102272
2023-01-22 18:42:44.876206: step: 896/529, loss: 0.0006934865959919989
2023-01-22 18:42:46.011646: step: 900/529, loss: 0.049045197665691376
2023-01-22 18:42:47.119907: step: 904/529, loss: 0.009306986816227436
2023-01-22 18:42:48.262528: step: 908/529, loss: 0.0069193728268146515
2023-01-22 18:42:49.376732: step: 912/529, loss: 0.004257889464497566
2023-01-22 18:42:50.486077: step: 916/529, loss: 0.0010051759891211987
2023-01-22 18:42:51.586992: step: 920/529, loss: 0.006709117908030748
2023-01-22 18:42:52.714684: step: 924/529, loss: 0.00445249117910862
2023-01-22 18:42:53.833574: step: 928/529, loss: 0.003797889454290271
2023-01-22 18:42:54.950699: step: 932/529, loss: 0.01634194888174534
2023-01-22 18:42:56.058153: step: 936/529, loss: 0.006429014727473259
2023-01-22 18:42:57.165374: step: 940/529, loss: 0.000796058913692832
2023-01-22 18:42:58.276381: step: 944/529, loss: 0.012223836965858936
2023-01-22 18:42:59.390738: step: 948/529, loss: 0.0038601565174758434
2023-01-22 18:43:00.506464: step: 952/529, loss: 0.010627320036292076
2023-01-22 18:43:01.640092: step: 956/529, loss: 0.005791979841887951
2023-01-22 18:43:02.746387: step: 960/529, loss: 0.0020676245912909508
2023-01-22 18:43:03.856010: step: 964/529, loss: 0.002595597179606557
2023-01-22 18:43:04.947414: step: 968/529, loss: 0.011650782078504562
2023-01-22 18:43:06.046856: step: 972/529, loss: 0.023557884618639946
2023-01-22 18:43:07.140511: step: 976/529, loss: 0.0024959726724773645
2023-01-22 18:43:08.271532: step: 980/529, loss: 0.009766514413058758
2023-01-22 18:43:09.398517: step: 984/529, loss: 0.008665000088512897
2023-01-22 18:43:10.510569: step: 988/529, loss: 0.012160072103142738
2023-01-22 18:43:11.634788: step: 992/529, loss: 0.003717874875292182
2023-01-22 18:43:12.761541: step: 996/529, loss: 0.0007553992327302694
2023-01-22 18:43:13.879260: step: 1000/529, loss: 0.0009899020660668612
2023-01-22 18:43:14.984824: step: 1004/529, loss: 0.00651220278814435
2023-01-22 18:43:16.096710: step: 1008/529, loss: 0.004271156154572964
2023-01-22 18:43:17.202707: step: 1012/529, loss: 0.0027377386577427387
2023-01-22 18:43:18.319586: step: 1016/529, loss: 0.0012419747654348612
2023-01-22 18:43:19.419197: step: 1020/529, loss: 0.005044716876000166
2023-01-22 18:43:20.534382: step: 1024/529, loss: 0.003990651108324528
2023-01-22 18:43:21.662473: step: 1028/529, loss: 0.004522216971963644
2023-01-22 18:43:22.780254: step: 1032/529, loss: 0.010923494584858418
2023-01-22 18:43:23.877367: step: 1036/529, loss: 0.0027218852192163467
2023-01-22 18:43:24.979351: step: 1040/529, loss: 0.001818226301111281
2023-01-22 18:43:26.079709: step: 1044/529, loss: 0.021147651597857475
2023-01-22 18:43:27.191273: step: 1048/529, loss: 0.008560696616768837
2023-01-22 18:43:28.287261: step: 1052/529, loss: 0.00042288025724701583
2023-01-22 18:43:29.386288: step: 1056/529, loss: 0.003587961196899414
2023-01-22 18:43:30.504315: step: 1060/529, loss: 0.004614383447915316
2023-01-22 18:43:31.612122: step: 1064/529, loss: 0.001856955816037953
2023-01-22 18:43:32.694290: step: 1068/529, loss: 0.0
2023-01-22 18:43:33.819412: step: 1072/529, loss: 0.022344503551721573
2023-01-22 18:43:34.955734: step: 1076/529, loss: 0.00451620202511549
2023-01-22 18:43:36.083747: step: 1080/529, loss: 0.020677490159869194
2023-01-22 18:43:37.203401: step: 1084/529, loss: 0.021734872832894325
2023-01-22 18:43:38.293712: step: 1088/529, loss: 0.01625116914510727
2023-01-22 18:43:39.422828: step: 1092/529, loss: 0.002873418852686882
2023-01-22 18:43:40.536338: step: 1096/529, loss: 0.003447467228397727
2023-01-22 18:43:41.652105: step: 1100/529, loss: 0.00568568566814065
2023-01-22 18:43:42.746087: step: 1104/529, loss: 0.013935388997197151
2023-01-22 18:43:43.846076: step: 1108/529, loss: 0.0036689352709800005
2023-01-22 18:43:44.979543: step: 1112/529, loss: 0.008914774283766747
2023-01-22 18:43:46.082063: step: 1116/529, loss: 0.0038859290070831776
2023-01-22 18:43:47.194039: step: 1120/529, loss: 0.005843544378876686
2023-01-22 18:43:48.310624: step: 1124/529, loss: 0.0038129333406686783
2023-01-22 18:43:49.414766: step: 1128/529, loss: 0.018381819128990173
2023-01-22 18:43:50.516506: step: 1132/529, loss: 0.0043317642994225025
2023-01-22 18:43:51.632386: step: 1136/529, loss: 0.0008181605953723192
2023-01-22 18:43:52.729808: step: 1140/529, loss: 0.033095523715019226
2023-01-22 18:43:53.838052: step: 1144/529, loss: 0.008096587844192982
2023-01-22 18:43:54.940455: step: 1148/529, loss: 0.010569499805569649
2023-01-22 18:43:56.032203: step: 1152/529, loss: 0.005974179599434137
2023-01-22 18:43:57.143545: step: 1156/529, loss: 0.0011172093218192458
2023-01-22 18:43:58.231440: step: 1160/529, loss: 0.0009726683492772281
2023-01-22 18:43:59.334180: step: 1164/529, loss: 0.007001920137554407
2023-01-22 18:44:00.448064: step: 1168/529, loss: 0.018469376489520073
2023-01-22 18:44:01.558916: step: 1172/529, loss: 0.004775014240294695
2023-01-22 18:44:02.649671: step: 1176/529, loss: 0.0003716326900757849
2023-01-22 18:44:03.799498: step: 1180/529, loss: 0.009061123244464397
2023-01-22 18:44:04.906870: step: 1184/529, loss: 0.007884989492595196
2023-01-22 18:44:05.992411: step: 1188/529, loss: 0.005078867077827454
2023-01-22 18:44:07.103159: step: 1192/529, loss: 0.003576371818780899
2023-01-22 18:44:08.206360: step: 1196/529, loss: 0.002088880632072687
2023-01-22 18:44:09.319674: step: 1200/529, loss: 0.0030322414822876453
2023-01-22 18:44:10.414607: step: 1204/529, loss: 0.004681067541241646
2023-01-22 18:44:11.504688: step: 1208/529, loss: 0.0013306960463523865
2023-01-22 18:44:12.599349: step: 1212/529, loss: 0.004194363951683044
2023-01-22 18:44:13.709703: step: 1216/529, loss: 0.016724074259400368
2023-01-22 18:44:14.810106: step: 1220/529, loss: 0.013624606654047966
2023-01-22 18:44:15.930420: step: 1224/529, loss: 0.002238082466647029
2023-01-22 18:44:17.024832: step: 1228/529, loss: 0.012839583680033684
2023-01-22 18:44:18.131137: step: 1232/529, loss: 0.0002458159578964114
2023-01-22 18:44:19.255747: step: 1236/529, loss: 0.038128044456243515
2023-01-22 18:44:20.351457: step: 1240/529, loss: 0.0018575232243165374
2023-01-22 18:44:21.463940: step: 1244/529, loss: 0.010543646290898323
2023-01-22 18:44:22.593719: step: 1248/529, loss: 0.00048154941760003567
2023-01-22 18:44:23.686683: step: 1252/529, loss: 0.03804149478673935
2023-01-22 18:44:24.791486: step: 1256/529, loss: 0.00981319323182106
2023-01-22 18:44:25.897887: step: 1260/529, loss: 0.00769336661323905
2023-01-22 18:44:27.016947: step: 1264/529, loss: 0.010434003546833992
2023-01-22 18:44:28.117756: step: 1268/529, loss: 0.016274206340312958
2023-01-22 18:44:29.228217: step: 1272/529, loss: 0.006919366307556629
2023-01-22 18:44:30.324915: step: 1276/529, loss: 0.0007365404744632542
2023-01-22 18:44:31.426682: step: 1280/529, loss: 0.006953903939574957
2023-01-22 18:44:32.543497: step: 1284/529, loss: 0.004470301792025566
2023-01-22 18:44:33.683686: step: 1288/529, loss: 0.005321430508047342
2023-01-22 18:44:34.774413: step: 1292/529, loss: 0.01020444743335247
2023-01-22 18:44:35.855258: step: 1296/529, loss: 0.00046618375927209854
2023-01-22 18:44:36.984264: step: 1300/529, loss: 0.003094441257417202
2023-01-22 18:44:38.081866: step: 1304/529, loss: 0.015473908744752407
2023-01-22 18:44:39.207086: step: 1308/529, loss: 0.006819084752351046
2023-01-22 18:44:40.352062: step: 1312/529, loss: 0.008944142609834671
2023-01-22 18:44:41.475002: step: 1316/529, loss: 0.00334442057646811
2023-01-22 18:44:42.581704: step: 1320/529, loss: 0.005131879821419716
2023-01-22 18:44:43.688708: step: 1324/529, loss: 0.011224307119846344
2023-01-22 18:44:44.813208: step: 1328/529, loss: 0.0012206730898469687
2023-01-22 18:44:45.922285: step: 1332/529, loss: 0.00507092522457242
2023-01-22 18:44:47.033652: step: 1336/529, loss: 0.0077430796809494495
2023-01-22 18:44:48.143014: step: 1340/529, loss: 0.02381853014230728
2023-01-22 18:44:49.260866: step: 1344/529, loss: 0.003044499782845378
2023-01-22 18:44:50.361221: step: 1348/529, loss: 0.008158575743436813
2023-01-22 18:44:51.475749: step: 1352/529, loss: 0.006804183125495911
2023-01-22 18:44:52.581909: step: 1356/529, loss: 0.008868962526321411
2023-01-22 18:44:53.693624: step: 1360/529, loss: 0.0007548411376774311
2023-01-22 18:44:54.822177: step: 1364/529, loss: 0.0022392296232283115
2023-01-22 18:44:55.939513: step: 1368/529, loss: 0.0010228336323052645
2023-01-22 18:44:57.042158: step: 1372/529, loss: 0.0018546622013673186
2023-01-22 18:44:58.150538: step: 1376/529, loss: 0.0013475528685376048
2023-01-22 18:44:59.246113: step: 1380/529, loss: 0.02138546295464039
2023-01-22 18:45:00.343532: step: 1384/529, loss: 0.01893160119652748
2023-01-22 18:45:01.455045: step: 1388/529, loss: 0.004333828575909138
2023-01-22 18:45:02.573993: step: 1392/529, loss: 0.0010282692965120077
2023-01-22 18:45:03.706932: step: 1396/529, loss: 0.005786009132862091
2023-01-22 18:45:04.804091: step: 1400/529, loss: 0.01035977154970169
2023-01-22 18:45:05.921293: step: 1404/529, loss: 0.003354752669110894
2023-01-22 18:45:07.021911: step: 1408/529, loss: 0.0026946559082716703
2023-01-22 18:45:08.114811: step: 1412/529, loss: 0.006450484041124582
2023-01-22 18:45:09.226119: step: 1416/529, loss: 0.011759447865188122
2023-01-22 18:45:10.360860: step: 1420/529, loss: 0.041142694652080536
2023-01-22 18:45:11.507266: step: 1424/529, loss: 0.050200410187244415
2023-01-22 18:45:12.612711: step: 1428/529, loss: 0.002981449943035841
2023-01-22 18:45:13.772129: step: 1432/529, loss: 0.0008520122501067817
2023-01-22 18:45:14.917631: step: 1436/529, loss: 0.013236681930720806
2023-01-22 18:45:16.025947: step: 1440/529, loss: 0.005776203237473965
2023-01-22 18:45:17.122517: step: 1444/529, loss: 0.0004227413155604154
2023-01-22 18:45:18.254529: step: 1448/529, loss: 0.010980979539453983
2023-01-22 18:45:19.405112: step: 1452/529, loss: 0.0011604557512328029
2023-01-22 18:45:20.506557: step: 1456/529, loss: 0.0015585614601150155
2023-01-22 18:45:21.616084: step: 1460/529, loss: 0.004838043358176947
2023-01-22 18:45:22.738806: step: 1464/529, loss: 0.013198030181229115
2023-01-22 18:45:23.836629: step: 1468/529, loss: 0.0022277210373431444
2023-01-22 18:45:24.943228: step: 1472/529, loss: 0.06916091591119766
2023-01-22 18:45:26.052622: step: 1476/529, loss: 0.008894179947674274
2023-01-22 18:45:27.183085: step: 1480/529, loss: 0.0009989392710849643
2023-01-22 18:45:28.280388: step: 1484/529, loss: 0.004288040567189455
2023-01-22 18:45:29.413869: step: 1488/529, loss: 0.005061854142695665
2023-01-22 18:45:30.523389: step: 1492/529, loss: 0.008063099347054958
2023-01-22 18:45:31.639360: step: 1496/529, loss: 0.00906107947230339
2023-01-22 18:45:32.741497: step: 1500/529, loss: 0.0030321567319333553
2023-01-22 18:45:33.845305: step: 1504/529, loss: 0.02668239176273346
2023-01-22 18:45:34.969827: step: 1508/529, loss: 0.0029460571240633726
2023-01-22 18:45:36.078138: step: 1512/529, loss: 0.00484667532145977
2023-01-22 18:45:37.180213: step: 1516/529, loss: 0.011024574749171734
2023-01-22 18:45:38.309285: step: 1520/529, loss: 0.007701247930526733
2023-01-22 18:45:39.427003: step: 1524/529, loss: 0.027079027146100998
2023-01-22 18:45:40.570054: step: 1528/529, loss: 0.002607388189062476
2023-01-22 18:45:41.665562: step: 1532/529, loss: 0.000754452426917851
2023-01-22 18:45:42.775665: step: 1536/529, loss: 0.002925124019384384
2023-01-22 18:45:43.865359: step: 1540/529, loss: 0.00450309831649065
2023-01-22 18:45:44.991412: step: 1544/529, loss: 0.003333688247948885
2023-01-22 18:45:46.089211: step: 1548/529, loss: 0.005743012297898531
2023-01-22 18:45:47.209337: step: 1552/529, loss: 0.012968389317393303
2023-01-22 18:45:48.337139: step: 1556/529, loss: 0.00378986494615674
2023-01-22 18:45:49.467170: step: 1560/529, loss: 0.0026724375784397125
2023-01-22 18:45:50.558474: step: 1564/529, loss: 0.0018774084746837616
2023-01-22 18:45:51.675819: step: 1568/529, loss: 0.015226670540869236
2023-01-22 18:45:52.754082: step: 1572/529, loss: 0.003603462828323245
2023-01-22 18:45:53.861198: step: 1576/529, loss: 0.01170405838638544
2023-01-22 18:45:55.008737: step: 1580/529, loss: 0.00882007461041212
2023-01-22 18:45:56.131938: step: 1584/529, loss: 0.0019141166703775525
2023-01-22 18:45:57.259176: step: 1588/529, loss: 0.016407420858740807
2023-01-22 18:45:58.365103: step: 1592/529, loss: 0.001737741520628333
2023-01-22 18:45:59.493938: step: 1596/529, loss: 0.0017130805645138025
2023-01-22 18:46:00.610334: step: 1600/529, loss: 0.006675695069134235
2023-01-22 18:46:01.729338: step: 1604/529, loss: 0.0036178254522383213
2023-01-22 18:46:02.849477: step: 1608/529, loss: 0.004487319383770227
2023-01-22 18:46:03.997773: step: 1612/529, loss: 0.005593766923993826
2023-01-22 18:46:05.114603: step: 1616/529, loss: 0.002983157057315111
2023-01-22 18:46:06.239593: step: 1620/529, loss: 0.01660698466002941
2023-01-22 18:46:07.345569: step: 1624/529, loss: 0.006098631769418716
2023-01-22 18:46:08.443089: step: 1628/529, loss: 0.06224154308438301
2023-01-22 18:46:09.558946: step: 1632/529, loss: 0.012845651246607304
2023-01-22 18:46:10.664435: step: 1636/529, loss: 0.0028631037566810846
2023-01-22 18:46:11.794019: step: 1640/529, loss: 0.0020831632427871227
2023-01-22 18:46:12.904775: step: 1644/529, loss: 0.007122849114239216
2023-01-22 18:46:14.029805: step: 1648/529, loss: 0.029846210032701492
2023-01-22 18:46:15.139109: step: 1652/529, loss: 0.012220275588333607
2023-01-22 18:46:16.263670: step: 1656/529, loss: 0.010339400731027126
2023-01-22 18:46:17.399235: step: 1660/529, loss: 0.004446351435035467
2023-01-22 18:46:18.490830: step: 1664/529, loss: 3.9849554013926536e-05
2023-01-22 18:46:19.611367: step: 1668/529, loss: 0.010926641523838043
2023-01-22 18:46:20.718413: step: 1672/529, loss: 0.009528790600597858
2023-01-22 18:46:21.819926: step: 1676/529, loss: 0.0038331919349730015
2023-01-22 18:46:22.940805: step: 1680/529, loss: 0.0112329525873065
2023-01-22 18:46:24.042840: step: 1684/529, loss: 0.0011112805223092437
2023-01-22 18:46:25.146311: step: 1688/529, loss: 0.005715968552976847
2023-01-22 18:46:26.253199: step: 1692/529, loss: 0.006637838669121265
2023-01-22 18:46:27.370841: step: 1696/529, loss: 0.01248794887214899
2023-01-22 18:46:28.470719: step: 1700/529, loss: 0.0009806236485019326
2023-01-22 18:46:29.598993: step: 1704/529, loss: 0.0025035240687429905
2023-01-22 18:46:30.704739: step: 1708/529, loss: 0.023603204637765884
2023-01-22 18:46:31.859257: step: 1712/529, loss: 0.0027091698721051216
2023-01-22 18:46:32.979590: step: 1716/529, loss: 0.015486306510865688
2023-01-22 18:46:34.101914: step: 1720/529, loss: 0.005725586786866188
2023-01-22 18:46:35.222478: step: 1724/529, loss: 0.003215622389689088
2023-01-22 18:46:36.331906: step: 1728/529, loss: 0.0015625227242708206
2023-01-22 18:46:37.427035: step: 1732/529, loss: 0.00022542999067809433
2023-01-22 18:46:38.549776: step: 1736/529, loss: 0.0006033622776158154
2023-01-22 18:46:39.645995: step: 1740/529, loss: 0.0012999210739508271
2023-01-22 18:46:40.759079: step: 1744/529, loss: 0.007129587698727846
2023-01-22 18:46:41.899974: step: 1748/529, loss: 0.004076377488672733
2023-01-22 18:46:43.007169: step: 1752/529, loss: 0.004623218439519405
2023-01-22 18:46:44.133869: step: 1756/529, loss: 0.0037794874515384436
2023-01-22 18:46:45.269406: step: 1760/529, loss: 0.0014138724654912949
2023-01-22 18:46:46.377006: step: 1764/529, loss: 0.00626613013446331
2023-01-22 18:46:47.499585: step: 1768/529, loss: 0.009518090635538101
2023-01-22 18:46:48.617327: step: 1772/529, loss: 0.0045984480530023575
2023-01-22 18:46:49.718258: step: 1776/529, loss: 0.004752174485474825
2023-01-22 18:46:50.829939: step: 1780/529, loss: 0.027641193941235542
2023-01-22 18:46:51.939951: step: 1784/529, loss: 0.019016485661268234
2023-01-22 18:46:53.053750: step: 1788/529, loss: 0.027889788150787354
2023-01-22 18:46:54.169250: step: 1792/529, loss: 0.0035197893157601357
2023-01-22 18:46:55.308981: step: 1796/529, loss: 0.006892375648021698
2023-01-22 18:46:56.435799: step: 1800/529, loss: 0.0014207635540515184
2023-01-22 18:46:57.537535: step: 1804/529, loss: 0.0018155979923903942
2023-01-22 18:46:58.655777: step: 1808/529, loss: 0.003822892904281616
2023-01-22 18:46:59.761200: step: 1812/529, loss: 0.026996824890375137
2023-01-22 18:47:00.875353: step: 1816/529, loss: 0.007372335530817509
2023-01-22 18:47:02.054611: step: 1820/529, loss: 0.011459797620773315
2023-01-22 18:47:03.162971: step: 1824/529, loss: 0.0035965193528681993
2023-01-22 18:47:04.271111: step: 1828/529, loss: 0.005146507173776627
2023-01-22 18:47:05.374859: step: 1832/529, loss: 0.0039470563642680645
2023-01-22 18:47:06.501850: step: 1836/529, loss: 0.006077685859054327
2023-01-22 18:47:07.622840: step: 1840/529, loss: 0.010810391046106815
2023-01-22 18:47:08.725547: step: 1844/529, loss: 0.007124264724552631
2023-01-22 18:47:09.840709: step: 1848/529, loss: 0.002527458593249321
2023-01-22 18:47:10.948536: step: 1852/529, loss: 0.031402889639139175
2023-01-22 18:47:12.070315: step: 1856/529, loss: 0.00225332984700799
2023-01-22 18:47:13.167206: step: 1860/529, loss: 0.00868365727365017
2023-01-22 18:47:14.274797: step: 1864/529, loss: 0.010610532015562057
2023-01-22 18:47:15.394813: step: 1868/529, loss: 0.006207606755197048
2023-01-22 18:47:16.507650: step: 1872/529, loss: 0.008675008080899715
2023-01-22 18:47:17.614406: step: 1876/529, loss: 0.0021586900111287832
2023-01-22 18:47:18.714670: step: 1880/529, loss: 0.005463351029902697
2023-01-22 18:47:19.837551: step: 1884/529, loss: 0.00015167509263847023
2023-01-22 18:47:20.963233: step: 1888/529, loss: 0.01060989685356617
2023-01-22 18:47:22.059126: step: 1892/529, loss: 0.0019999961368739605
2023-01-22 18:47:23.176287: step: 1896/529, loss: 0.017775509506464005
2023-01-22 18:47:24.306610: step: 1900/529, loss: 0.003965908195823431
2023-01-22 18:47:25.394300: step: 1904/529, loss: 0.0018829237669706345
2023-01-22 18:47:26.497596: step: 1908/529, loss: 0.0032470521982759237
2023-01-22 18:47:27.610585: step: 1912/529, loss: 0.021635238081216812
2023-01-22 18:47:28.729259: step: 1916/529, loss: 0.0054940590634942055
2023-01-22 18:47:29.850238: step: 1920/529, loss: 0.006706266663968563
2023-01-22 18:47:30.958799: step: 1924/529, loss: 0.00026026403065770864
2023-01-22 18:47:32.075101: step: 1928/529, loss: 0.0032187732867896557
2023-01-22 18:47:33.194359: step: 1932/529, loss: 0.005245766136795282
2023-01-22 18:47:34.296406: step: 1936/529, loss: 0.0030085307080298662
2023-01-22 18:47:35.423104: step: 1940/529, loss: 0.00255844509229064
2023-01-22 18:47:36.545377: step: 1944/529, loss: 0.0038450192660093307
2023-01-22 18:47:37.669175: step: 1948/529, loss: 0.05609880015254021
2023-01-22 18:47:38.770801: step: 1952/529, loss: 0.017728636041283607
2023-01-22 18:47:39.891379: step: 1956/529, loss: 0.010679494589567184
2023-01-22 18:47:40.978240: step: 1960/529, loss: 0.003283848287537694
2023-01-22 18:47:42.092996: step: 1964/529, loss: 0.006431478075683117
2023-01-22 18:47:43.191837: step: 1968/529, loss: 0.008664300665259361
2023-01-22 18:47:44.304837: step: 1972/529, loss: 0.0038368417881429195
2023-01-22 18:47:45.422807: step: 1976/529, loss: 0.007292424328625202
2023-01-22 18:47:46.524901: step: 1980/529, loss: 0.0028334050439298153
2023-01-22 18:47:47.632869: step: 1984/529, loss: 0.008170985616743565
2023-01-22 18:47:48.752426: step: 1988/529, loss: 0.04894591495394707
2023-01-22 18:47:49.878273: step: 1992/529, loss: 0.019697679206728935
2023-01-22 18:47:50.998249: step: 1996/529, loss: 0.0083999615162611
2023-01-22 18:47:52.113801: step: 2000/529, loss: 0.008980633690953255
2023-01-22 18:47:53.229893: step: 2004/529, loss: 0.009917245246469975
2023-01-22 18:47:54.333558: step: 2008/529, loss: 0.013036241754889488
2023-01-22 18:47:55.463139: step: 2012/529, loss: 0.009323484264314175
2023-01-22 18:47:56.583756: step: 2016/529, loss: 0.02634882926940918
2023-01-22 18:47:57.715112: step: 2020/529, loss: 0.012787842191755772
2023-01-22 18:47:58.818824: step: 2024/529, loss: 0.0032681659795343876
2023-01-22 18:47:59.937100: step: 2028/529, loss: 0.010101065039634705
2023-01-22 18:48:01.047759: step: 2032/529, loss: 0.0034691786859184504
2023-01-22 18:48:02.151723: step: 2036/529, loss: 0.035090502351522446
2023-01-22 18:48:03.268545: step: 2040/529, loss: 0.009759358130395412
2023-01-22 18:48:04.404554: step: 2044/529, loss: 0.010804848745465279
2023-01-22 18:48:05.501129: step: 2048/529, loss: 0.01250616554170847
2023-01-22 18:48:06.590259: step: 2052/529, loss: 0.004521224647760391
2023-01-22 18:48:07.683319: step: 2056/529, loss: 0.004803786985576153
2023-01-22 18:48:08.783289: step: 2060/529, loss: 0.006789981387555599
2023-01-22 18:48:09.866683: step: 2064/529, loss: 0.06477535516023636
2023-01-22 18:48:10.960251: step: 2068/529, loss: 0.004640466999262571
2023-01-22 18:48:12.047949: step: 2072/529, loss: 0.009149201214313507
2023-01-22 18:48:13.150311: step: 2076/529, loss: 0.009796473197638988
2023-01-22 18:48:14.253808: step: 2080/529, loss: 0.012918299064040184
2023-01-22 18:48:15.362555: step: 2084/529, loss: 0.007878929376602173
2023-01-22 18:48:16.469191: step: 2088/529, loss: 0.005031415726989508
2023-01-22 18:48:17.582282: step: 2092/529, loss: 4.6794557420071214e-05
2023-01-22 18:48:18.681414: step: 2096/529, loss: 0.005519380327314138
2023-01-22 18:48:19.782233: step: 2100/529, loss: 0.001372506027109921
2023-01-22 18:48:20.878413: step: 2104/529, loss: 0.012617439031600952
2023-01-22 18:48:21.986721: step: 2108/529, loss: 0.011319011449813843
2023-01-22 18:48:23.098434: step: 2112/529, loss: 0.0026188690681010485
2023-01-22 18:48:24.213296: step: 2116/529, loss: 0.002033472992479801
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3306330545653962, 'r': 0.32686873136351313, 'f1': 0.3287401172300981}, 'combined': 0.2422295600642828, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3726854335574501, 'r': 0.29711490370264654, 'f1': 0.33063702880699525}, 'combined': 0.20322080794966538, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3331822974009122, 'r': 0.34393011344610297, 'f1': 0.3384709052961648}, 'combined': 0.249399614428753, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3564256054992905, 'r': 0.310096454004582, 'f1': 0.3316508877861794}, 'combined': 0.20384396029784685, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33852364597467205, 'r': 0.34430488471048243, 'f1': 0.34138979161321586}, 'combined': 0.2515503727676327, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3682757995342882, 'r': 0.3003600027370558, 'f1': 0.33086867254296565}, 'combined': 0.20436006245300825, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3269230769230769, 'r': 0.36428571428571427, 'f1': 0.34459459459459457}, 'combined': 0.22972972972972971, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3416666666666667, 'r': 0.44565217391304346, 'f1': 0.3867924528301887}, 'combined': 0.19339622641509435, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 8
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 18:50:48.612209: step: 4/529, loss: 0.010119680315256119
2023-01-22 18:50:49.711349: step: 8/529, loss: 0.005893799476325512
2023-01-22 18:50:50.804533: step: 12/529, loss: 0.004199305549263954
2023-01-22 18:50:51.921826: step: 16/529, loss: 0.005066265352070332
2023-01-22 18:50:53.003093: step: 20/529, loss: 0.004055889323353767
2023-01-22 18:50:54.088332: step: 24/529, loss: 0.0013050538254901767
2023-01-22 18:50:55.205937: step: 28/529, loss: 0.0009191795834340155
2023-01-22 18:50:56.285606: step: 32/529, loss: 0.012659515254199505
2023-01-22 18:50:57.382150: step: 36/529, loss: 0.00026151465135626495
2023-01-22 18:50:58.487090: step: 40/529, loss: 0.004720237571746111
2023-01-22 18:50:59.588864: step: 44/529, loss: 0.00812650378793478
2023-01-22 18:51:00.686083: step: 48/529, loss: 0.001217373413965106
2023-01-22 18:51:01.783541: step: 52/529, loss: 0.0032107161823660135
2023-01-22 18:51:02.875735: step: 56/529, loss: 0.0020576557144522667
2023-01-22 18:51:03.977067: step: 60/529, loss: 0.006836101412773132
2023-01-22 18:51:05.080865: step: 64/529, loss: 0.0418306328356266
2023-01-22 18:51:06.173913: step: 68/529, loss: 0.0013350642984732985
2023-01-22 18:51:07.259056: step: 72/529, loss: 0.0017905108397826552
2023-01-22 18:51:08.375067: step: 76/529, loss: 0.0018587341764941812
2023-01-22 18:51:09.475569: step: 80/529, loss: 0.0032744163181632757
2023-01-22 18:51:10.553556: step: 84/529, loss: 0.002595275640487671
2023-01-22 18:51:11.646415: step: 88/529, loss: 0.012285172939300537
2023-01-22 18:51:12.777926: step: 92/529, loss: 0.00601964583620429
2023-01-22 18:51:13.867069: step: 96/529, loss: 0.011044785380363464
2023-01-22 18:51:14.981215: step: 100/529, loss: 0.01676752045750618
2023-01-22 18:51:16.102646: step: 104/529, loss: 0.010028683580458164
2023-01-22 18:51:17.243854: step: 108/529, loss: 0.007332808803766966
2023-01-22 18:51:18.334953: step: 112/529, loss: 0.004588474985212088
2023-01-22 18:51:19.423274: step: 116/529, loss: 0.001440213294699788
2023-01-22 18:51:20.514916: step: 120/529, loss: 0.010107388719916344
2023-01-22 18:51:21.604887: step: 124/529, loss: 0.014141440391540527
2023-01-22 18:51:22.691595: step: 128/529, loss: 0.0010853768326342106
2023-01-22 18:51:23.780623: step: 132/529, loss: 0.0005682872142642736
2023-01-22 18:51:24.865178: step: 136/529, loss: 0.002661020727828145
2023-01-22 18:51:25.965379: step: 140/529, loss: 0.0005171256489120424
2023-01-22 18:51:27.071797: step: 144/529, loss: 0.005109234247356653
2023-01-22 18:51:28.166866: step: 148/529, loss: 0.018681224435567856
2023-01-22 18:51:29.252137: step: 152/529, loss: 0.00661963177844882
2023-01-22 18:51:30.377414: step: 156/529, loss: 0.0007853424758650362
2023-01-22 18:51:31.486581: step: 160/529, loss: 0.006194726563990116
2023-01-22 18:51:32.621122: step: 164/529, loss: 0.009804238565266132
2023-01-22 18:51:33.723038: step: 168/529, loss: 0.009070285595953465
2023-01-22 18:51:34.825717: step: 172/529, loss: 0.006323863286525011
2023-01-22 18:51:35.938566: step: 176/529, loss: 0.005981122609227896
2023-01-22 18:51:37.049861: step: 180/529, loss: 0.0038628876209259033
2023-01-22 18:51:38.148848: step: 184/529, loss: 0.001554613932967186
2023-01-22 18:51:39.230114: step: 188/529, loss: 0.00015930060180835426
2023-01-22 18:51:40.352277: step: 192/529, loss: 0.004268538672477007
2023-01-22 18:51:41.444096: step: 196/529, loss: 0.009430995211005211
2023-01-22 18:51:42.521069: step: 200/529, loss: 0.008636308833956718
2023-01-22 18:51:43.623684: step: 204/529, loss: 0.004446480888873339
2023-01-22 18:51:44.735674: step: 208/529, loss: 0.009354028850793839
2023-01-22 18:51:45.857092: step: 212/529, loss: 0.00013394693087320775
2023-01-22 18:51:46.949608: step: 216/529, loss: 0.0018775715725496411
2023-01-22 18:51:48.060694: step: 220/529, loss: 0.005348735488951206
2023-01-22 18:51:49.183506: step: 224/529, loss: 0.002338995458558202
2023-01-22 18:51:50.264427: step: 228/529, loss: 0.0
2023-01-22 18:51:51.345517: step: 232/529, loss: 0.007684392388910055
2023-01-22 18:51:52.437152: step: 236/529, loss: 0.000983944395557046
2023-01-22 18:51:53.534820: step: 240/529, loss: 0.005075910594314337
2023-01-22 18:51:54.652886: step: 244/529, loss: 0.007581962738186121
2023-01-22 18:51:55.740867: step: 248/529, loss: 0.007029070518910885
2023-01-22 18:51:56.829720: step: 252/529, loss: 0.012074478901922703
2023-01-22 18:51:57.952312: step: 256/529, loss: 0.006531259045004845
2023-01-22 18:51:59.065053: step: 260/529, loss: 0.002120832446962595
2023-01-22 18:52:00.176878: step: 264/529, loss: 0.0016957768239080906
2023-01-22 18:52:01.265822: step: 268/529, loss: 0.0282749030739069
2023-01-22 18:52:02.359157: step: 272/529, loss: 0.0012005006428807974
2023-01-22 18:52:03.441872: step: 276/529, loss: 0.0022363727912306786
2023-01-22 18:52:04.552682: step: 280/529, loss: 0.012153119780123234
2023-01-22 18:52:05.663631: step: 284/529, loss: 0.008582841604948044
2023-01-22 18:52:06.768691: step: 288/529, loss: 0.010345152579247952
2023-01-22 18:52:07.864994: step: 292/529, loss: 0.0053466204553842545
2023-01-22 18:52:08.964958: step: 296/529, loss: 0.003791054943576455
2023-01-22 18:52:10.055472: step: 300/529, loss: 0.004288640804588795
2023-01-22 18:52:11.165281: step: 304/529, loss: 0.012499445118010044
2023-01-22 18:52:12.267850: step: 308/529, loss: 0.008475806564092636
2023-01-22 18:52:13.355875: step: 312/529, loss: 0.0037184483371675014
2023-01-22 18:52:14.456097: step: 316/529, loss: 0.004467348102480173
2023-01-22 18:52:15.559383: step: 320/529, loss: 0.006024380214512348
2023-01-22 18:52:16.669965: step: 324/529, loss: 0.004249947145581245
2023-01-22 18:52:17.779185: step: 328/529, loss: 0.04182042181491852
2023-01-22 18:52:18.891780: step: 332/529, loss: 0.005245944485068321
2023-01-22 18:52:20.002173: step: 336/529, loss: 0.0010759185533970594
2023-01-22 18:52:21.115382: step: 340/529, loss: 0.009408141486346722
2023-01-22 18:52:22.202025: step: 344/529, loss: 0.0018801884725689888
2023-01-22 18:52:23.330895: step: 348/529, loss: 0.020278364419937134
2023-01-22 18:52:24.433239: step: 352/529, loss: 0.00014065821596886963
2023-01-22 18:52:25.528926: step: 356/529, loss: 0.0013568383874371648
2023-01-22 18:52:26.626942: step: 360/529, loss: 3.261092570028268e-05
2023-01-22 18:52:27.715859: step: 364/529, loss: 0.00794623326510191
2023-01-22 18:52:28.882546: step: 368/529, loss: 0.010475981049239635
2023-01-22 18:52:29.993965: step: 372/529, loss: 0.006949152797460556
2023-01-22 18:52:31.094113: step: 376/529, loss: 0.0028570599388331175
2023-01-22 18:52:32.193598: step: 380/529, loss: 0.008676288649439812
2023-01-22 18:52:33.290972: step: 384/529, loss: 0.008295878767967224
2023-01-22 18:52:34.396817: step: 388/529, loss: 0.00838957168161869
2023-01-22 18:52:35.498862: step: 392/529, loss: 0.003047575941309333
2023-01-22 18:52:36.590884: step: 396/529, loss: 0.0005909263854846358
2023-01-22 18:52:37.715847: step: 400/529, loss: 0.002323870314285159
2023-01-22 18:52:38.814871: step: 404/529, loss: 0.04494519904255867
2023-01-22 18:52:39.931904: step: 408/529, loss: 0.012526496313512325
2023-01-22 18:52:41.032273: step: 412/529, loss: 0.00234247581101954
2023-01-22 18:52:42.154368: step: 416/529, loss: 0.00038808339741081
2023-01-22 18:52:43.291180: step: 420/529, loss: 0.005925024393945932
2023-01-22 18:52:44.396164: step: 424/529, loss: 0.005720778834074736
2023-01-22 18:52:45.506907: step: 428/529, loss: 0.0039130826480686665
2023-01-22 18:52:46.615858: step: 432/529, loss: 0.001470521790906787
2023-01-22 18:52:47.759848: step: 436/529, loss: 0.002171593252569437
2023-01-22 18:52:48.872188: step: 440/529, loss: 0.008871885016560555
2023-01-22 18:52:49.963680: step: 444/529, loss: 7.68634636187926e-05
2023-01-22 18:52:51.059088: step: 448/529, loss: 0.002398934680968523
2023-01-22 18:52:52.150715: step: 452/529, loss: 0.00535996537655592
2023-01-22 18:52:53.280377: step: 456/529, loss: 0.009155374951660633
2023-01-22 18:52:54.380155: step: 460/529, loss: 0.008391357026994228
2023-01-22 18:52:55.468888: step: 464/529, loss: 0.014014866203069687
2023-01-22 18:52:56.588689: step: 468/529, loss: 0.005233097355812788
2023-01-22 18:52:57.686129: step: 472/529, loss: 0.00426349276676774
2023-01-22 18:52:58.791173: step: 476/529, loss: 0.007027878891676664
2023-01-22 18:52:59.895159: step: 480/529, loss: 0.011404664255678654
2023-01-22 18:53:01.015409: step: 484/529, loss: 0.030552171170711517
2023-01-22 18:53:02.119653: step: 488/529, loss: 0.01040281355381012
2023-01-22 18:53:03.227182: step: 492/529, loss: 0.010576466098427773
2023-01-22 18:53:04.318611: step: 496/529, loss: 0.011815064586699009
2023-01-22 18:53:05.430013: step: 500/529, loss: 0.0030642158817499876
2023-01-22 18:53:06.532188: step: 504/529, loss: 0.003776549594476819
2023-01-22 18:53:07.629848: step: 508/529, loss: 0.0048186518251895905
2023-01-22 18:53:08.757339: step: 512/529, loss: 0.013100002892315388
2023-01-22 18:53:09.850883: step: 516/529, loss: 0.003193611279129982
2023-01-22 18:53:10.965862: step: 520/529, loss: 5.077326477476163e-06
2023-01-22 18:53:12.076508: step: 524/529, loss: 0.011406700126826763
2023-01-22 18:53:13.185287: step: 528/529, loss: 0.011409236118197441
2023-01-22 18:53:14.303773: step: 532/529, loss: 0.002291899174451828
2023-01-22 18:53:15.408062: step: 536/529, loss: 0.001981314504519105
2023-01-22 18:53:16.504401: step: 540/529, loss: 0.0023756574373692274
2023-01-22 18:53:17.627943: step: 544/529, loss: 0.0034676450304687023
2023-01-22 18:53:18.747472: step: 548/529, loss: 0.0017041319515556097
2023-01-22 18:53:19.857527: step: 552/529, loss: 0.005051422398537397
2023-01-22 18:53:20.969817: step: 556/529, loss: 0.028502410277724266
2023-01-22 18:53:22.104410: step: 560/529, loss: 0.018700528889894485
2023-01-22 18:53:23.196301: step: 564/529, loss: 0.0024653091095387936
2023-01-22 18:53:24.302482: step: 568/529, loss: 0.003245433559641242
2023-01-22 18:53:25.410559: step: 572/529, loss: 0.00032193041988648474
2023-01-22 18:53:26.521963: step: 576/529, loss: 0.004998068790882826
2023-01-22 18:53:27.611961: step: 580/529, loss: 0.005314449314028025
2023-01-22 18:53:28.716414: step: 584/529, loss: 0.0021088221110403538
2023-01-22 18:53:29.821666: step: 588/529, loss: 0.0008396217599511147
2023-01-22 18:53:30.951415: step: 592/529, loss: 0.0019381141755729914
2023-01-22 18:53:32.095877: step: 596/529, loss: 0.00046278350055217743
2023-01-22 18:53:33.186778: step: 600/529, loss: 0.0039575002156198025
2023-01-22 18:53:34.300748: step: 604/529, loss: 0.007890153676271439
2023-01-22 18:53:35.410350: step: 608/529, loss: 0.016897959634661674
2023-01-22 18:53:36.511892: step: 612/529, loss: 0.03406417369842529
2023-01-22 18:53:37.603145: step: 616/529, loss: 0.0012760208919644356
2023-01-22 18:53:38.712534: step: 620/529, loss: 0.026287732645869255
2023-01-22 18:53:39.812474: step: 624/529, loss: 0.015432106330990791
2023-01-22 18:53:40.913534: step: 628/529, loss: 0.005200305953621864
2023-01-22 18:53:42.036474: step: 632/529, loss: 0.021572012454271317
2023-01-22 18:53:43.145236: step: 636/529, loss: 0.005489361472427845
2023-01-22 18:53:44.232709: step: 640/529, loss: 0.012023410759866238
2023-01-22 18:53:45.329064: step: 644/529, loss: 0.007949097082018852
2023-01-22 18:53:46.446959: step: 648/529, loss: 0.0016418035374954343
2023-01-22 18:53:47.561505: step: 652/529, loss: 0.0005466703441925347
2023-01-22 18:53:48.665016: step: 656/529, loss: 0.001666917116381228
2023-01-22 18:53:49.758045: step: 660/529, loss: 0.005398231092840433
2023-01-22 18:53:50.871788: step: 664/529, loss: 0.002538684755563736
2023-01-22 18:53:51.952875: step: 668/529, loss: 0.00783788412809372
2023-01-22 18:53:53.037275: step: 672/529, loss: 0.0008194351685233414
2023-01-22 18:53:54.145476: step: 676/529, loss: 0.005514910910278559
2023-01-22 18:53:55.253094: step: 680/529, loss: 0.0030528572387993336
2023-01-22 18:53:56.378865: step: 684/529, loss: 0.004789189901202917
2023-01-22 18:53:57.489019: step: 688/529, loss: 0.008657111786305904
2023-01-22 18:53:58.607044: step: 692/529, loss: 0.0079760467633605
2023-01-22 18:53:59.742265: step: 696/529, loss: 0.07318770885467529
2023-01-22 18:54:00.849790: step: 700/529, loss: 0.004092132207006216
2023-01-22 18:54:01.942575: step: 704/529, loss: 0.0018960719462484121
2023-01-22 18:54:03.050973: step: 708/529, loss: 0.006012339610606432
2023-01-22 18:54:04.166384: step: 712/529, loss: 0.002216975437477231
2023-01-22 18:54:05.277690: step: 716/529, loss: 0.00660129776224494
2023-01-22 18:54:06.374521: step: 720/529, loss: 0.003538223449140787
2023-01-22 18:54:07.470862: step: 724/529, loss: 0.006321675609797239
2023-01-22 18:54:08.576046: step: 728/529, loss: 0.00013304193271324039
2023-01-22 18:54:09.645664: step: 732/529, loss: 6.925478373887017e-05
2023-01-22 18:54:10.779624: step: 736/529, loss: 0.006495039444416761
2023-01-22 18:54:11.864567: step: 740/529, loss: 0.006380516570061445
2023-01-22 18:54:12.957027: step: 744/529, loss: 0.013447131030261517
2023-01-22 18:54:14.056312: step: 748/529, loss: 0.00013909900735598058
2023-01-22 18:54:15.144202: step: 752/529, loss: 0.0011064481223002076
2023-01-22 18:54:16.260645: step: 756/529, loss: 0.007094236556440592
2023-01-22 18:54:17.378310: step: 760/529, loss: 0.002531299600377679
2023-01-22 18:54:18.473199: step: 764/529, loss: 0.004947530571371317
2023-01-22 18:54:19.606862: step: 768/529, loss: 0.00331061240285635
2023-01-22 18:54:20.687135: step: 772/529, loss: 0.0004600965476129204
2023-01-22 18:54:21.770919: step: 776/529, loss: 0.005410581827163696
2023-01-22 18:54:22.856005: step: 780/529, loss: 0.00030218143365345895
2023-01-22 18:54:23.943050: step: 784/529, loss: 0.005493725184351206
2023-01-22 18:54:25.055986: step: 788/529, loss: 0.003168599447235465
2023-01-22 18:54:26.164593: step: 792/529, loss: 0.005202501080930233
2023-01-22 18:54:27.252643: step: 796/529, loss: 0.005630144849419594
2023-01-22 18:54:28.350194: step: 800/529, loss: 0.0019438144518062472
2023-01-22 18:54:29.467467: step: 804/529, loss: 0.002969382330775261
2023-01-22 18:54:30.572685: step: 808/529, loss: 0.0007965315016917884
2023-01-22 18:54:31.693370: step: 812/529, loss: 0.0021448356565088034
2023-01-22 18:54:32.784116: step: 816/529, loss: 0.0044776624999940395
2023-01-22 18:54:33.889234: step: 820/529, loss: 0.008589869365096092
2023-01-22 18:54:35.004538: step: 824/529, loss: 0.0013891683192923665
2023-01-22 18:54:36.106341: step: 828/529, loss: 0.003999660257250071
2023-01-22 18:54:37.216097: step: 832/529, loss: 3.5043980460613966e-05
2023-01-22 18:54:38.337742: step: 836/529, loss: 0.009071200154721737
2023-01-22 18:54:39.438068: step: 840/529, loss: 0.004447650630027056
2023-01-22 18:54:40.550106: step: 844/529, loss: 0.002736475318670273
2023-01-22 18:54:41.630674: step: 848/529, loss: 0.002411683788523078
2023-01-22 18:54:42.745742: step: 852/529, loss: 0.00021431082859635353
2023-01-22 18:54:43.839236: step: 856/529, loss: 0.014097589999437332
2023-01-22 18:54:44.926889: step: 860/529, loss: 0.006544869858771563
2023-01-22 18:54:46.016588: step: 864/529, loss: 0.0072073000483214855
2023-01-22 18:54:47.128252: step: 868/529, loss: 0.01216262299567461
2023-01-22 18:54:48.211491: step: 872/529, loss: 0.004361768718808889
2023-01-22 18:54:49.326373: step: 876/529, loss: 0.0006993083516135812
2023-01-22 18:54:50.448768: step: 880/529, loss: 0.0013722070725634694
2023-01-22 18:54:51.546164: step: 884/529, loss: 0.010257489047944546
2023-01-22 18:54:52.647129: step: 888/529, loss: 0.00771905155852437
2023-01-22 18:54:53.761107: step: 892/529, loss: 0.0034532530698925257
2023-01-22 18:54:54.876029: step: 896/529, loss: 0.003750961972400546
2023-01-22 18:54:56.007442: step: 900/529, loss: 0.004235539119690657
2023-01-22 18:54:57.121145: step: 904/529, loss: 0.01876828633248806
2023-01-22 18:54:58.228837: step: 908/529, loss: 0.01389996986836195
2023-01-22 18:54:59.340861: step: 912/529, loss: 0.004842726048082113
2023-01-22 18:55:00.443029: step: 916/529, loss: 0.026237189769744873
2023-01-22 18:55:01.547179: step: 920/529, loss: 0.007675171829760075
2023-01-22 18:55:02.682034: step: 924/529, loss: 0.004274559672921896
2023-01-22 18:55:03.775923: step: 928/529, loss: 0.0020656881388276815
2023-01-22 18:55:04.869059: step: 932/529, loss: 5.031748059991514e-06
2023-01-22 18:55:05.973182: step: 936/529, loss: 0.004031971096992493
2023-01-22 18:55:07.077825: step: 940/529, loss: 0.0024676888715475798
2023-01-22 18:55:08.167169: step: 944/529, loss: 0.019141731783747673
2023-01-22 18:55:09.285892: step: 948/529, loss: 0.0019298330880701542
2023-01-22 18:55:10.377830: step: 952/529, loss: 0.0012369854375720024
2023-01-22 18:55:11.492018: step: 956/529, loss: 0.01196899265050888
2023-01-22 18:55:12.592120: step: 960/529, loss: 0.0028338537085801363
2023-01-22 18:55:13.683357: step: 964/529, loss: 0.0011622555321082473
2023-01-22 18:55:14.811754: step: 968/529, loss: 0.0030543047469109297
2023-01-22 18:55:15.905206: step: 972/529, loss: 0.002496180823072791
2023-01-22 18:55:17.008240: step: 976/529, loss: 0.01589144580066204
2023-01-22 18:55:18.120841: step: 980/529, loss: 0.0027341567911207676
2023-01-22 18:55:19.215529: step: 984/529, loss: 0.007058282848447561
2023-01-22 18:55:20.327464: step: 988/529, loss: 0.012735437601804733
2023-01-22 18:55:21.449235: step: 992/529, loss: 0.005443592555820942
2023-01-22 18:55:22.575141: step: 996/529, loss: 0.012711774557828903
2023-01-22 18:55:23.682042: step: 1000/529, loss: 0.0022652146872133017
2023-01-22 18:55:24.801042: step: 1004/529, loss: 0.0033271366264671087
2023-01-22 18:55:25.885294: step: 1008/529, loss: 0.0035942820832133293
2023-01-22 18:55:26.979598: step: 1012/529, loss: 0.0007693001534789801
2023-01-22 18:55:28.101341: step: 1016/529, loss: 0.0026533822529017925
2023-01-22 18:55:29.210736: step: 1020/529, loss: 0.004491900093853474
2023-01-22 18:55:30.310012: step: 1024/529, loss: 0.005299916956573725
2023-01-22 18:55:31.414193: step: 1028/529, loss: 0.005103908479213715
2023-01-22 18:55:32.534177: step: 1032/529, loss: 0.0008068275637924671
2023-01-22 18:55:33.640040: step: 1036/529, loss: 0.0026617106050252914
2023-01-22 18:55:34.737831: step: 1040/529, loss: 0.002513264771550894
2023-01-22 18:55:35.830951: step: 1044/529, loss: 0.004923961125314236
2023-01-22 18:55:36.952937: step: 1048/529, loss: 0.01862596906721592
2023-01-22 18:55:38.069508: step: 1052/529, loss: 0.011417374014854431
2023-01-22 18:55:39.169511: step: 1056/529, loss: 0.01099475659430027
2023-01-22 18:55:40.266682: step: 1060/529, loss: 0.004778279922902584
2023-01-22 18:55:41.361783: step: 1064/529, loss: 0.011101208627223969
2023-01-22 18:55:42.455757: step: 1068/529, loss: 0.014456914737820625
2023-01-22 18:55:43.570284: step: 1072/529, loss: 0.0037627792917191982
2023-01-22 18:55:44.698443: step: 1076/529, loss: 0.002306982409209013
2023-01-22 18:55:45.812726: step: 1080/529, loss: 0.005412676837295294
2023-01-22 18:55:46.888955: step: 1084/529, loss: 0.008773085661232471
2023-01-22 18:55:47.997418: step: 1088/529, loss: 0.012251120992004871
2023-01-22 18:55:49.117251: step: 1092/529, loss: 0.006224720738828182
2023-01-22 18:55:50.205972: step: 1096/529, loss: 0.009956118650734425
2023-01-22 18:55:51.329981: step: 1100/529, loss: 0.021415360271930695
2023-01-22 18:55:52.457270: step: 1104/529, loss: 0.0013100974028930068
2023-01-22 18:55:53.549608: step: 1108/529, loss: 0.00012982427142560482
2023-01-22 18:55:54.669511: step: 1112/529, loss: 0.009698528796434402
2023-01-22 18:55:55.782597: step: 1116/529, loss: 0.0028295607771724463
2023-01-22 18:55:56.892206: step: 1120/529, loss: 0.005183225963264704
2023-01-22 18:55:57.993685: step: 1124/529, loss: 0.007370187900960445
2023-01-22 18:55:59.104346: step: 1128/529, loss: 0.0038984548300504684
2023-01-22 18:56:00.216817: step: 1132/529, loss: 0.016510816290974617
2023-01-22 18:56:01.337286: step: 1136/529, loss: 0.04182136058807373
2023-01-22 18:56:02.435777: step: 1140/529, loss: 0.011409271508455276
2023-01-22 18:56:03.510667: step: 1144/529, loss: 7.113488209142815e-06
2023-01-22 18:56:04.612217: step: 1148/529, loss: 0.0065594385378062725
2023-01-22 18:56:05.718766: step: 1152/529, loss: 0.007482252549380064
2023-01-22 18:56:06.832752: step: 1156/529, loss: 0.0004910477437078953
2023-01-22 18:56:07.955716: step: 1160/529, loss: 0.001266395440325141
2023-01-22 18:56:09.046837: step: 1164/529, loss: 0.0022375599946826696
2023-01-22 18:56:10.148849: step: 1168/529, loss: 0.0012515420094132423
2023-01-22 18:56:11.274823: step: 1172/529, loss: 0.016432879492640495
2023-01-22 18:56:12.376401: step: 1176/529, loss: 0.0018286400008946657
2023-01-22 18:56:13.478710: step: 1180/529, loss: 0.004006275441497564
2023-01-22 18:56:14.578310: step: 1184/529, loss: 0.015635188668966293
2023-01-22 18:56:15.682430: step: 1188/529, loss: 0.013672055676579475
2023-01-22 18:56:16.794527: step: 1192/529, loss: 0.006033264100551605
2023-01-22 18:56:17.906047: step: 1196/529, loss: 0.000723105447832495
2023-01-22 18:56:19.024733: step: 1200/529, loss: 0.0071470164693892
2023-01-22 18:56:20.122767: step: 1204/529, loss: 0.0019975490868091583
2023-01-22 18:56:21.235886: step: 1208/529, loss: 0.045328289270401
2023-01-22 18:56:22.342718: step: 1212/529, loss: 0.0010167284635826945
2023-01-22 18:56:23.458312: step: 1216/529, loss: 0.004742552060633898
2023-01-22 18:56:24.577472: step: 1220/529, loss: 0.02452757954597473
2023-01-22 18:56:25.662735: step: 1224/529, loss: 0.0064271967858076096
2023-01-22 18:56:26.788500: step: 1228/529, loss: 0.00568555248901248
2023-01-22 18:56:27.888658: step: 1232/529, loss: 0.012515513226389885
2023-01-22 18:56:28.989868: step: 1236/529, loss: 0.00309370388276875
2023-01-22 18:56:30.105858: step: 1240/529, loss: 0.01939237490296364
2023-01-22 18:56:31.204380: step: 1244/529, loss: 0.007814579643309116
2023-01-22 18:56:32.320272: step: 1248/529, loss: 0.006513823289424181
2023-01-22 18:56:33.459524: step: 1252/529, loss: 0.004988866858184338
2023-01-22 18:56:34.582677: step: 1256/529, loss: 0.005829906091094017
2023-01-22 18:56:35.689109: step: 1260/529, loss: 0.04851846769452095
2023-01-22 18:56:36.796099: step: 1264/529, loss: 0.000664384919218719
2023-01-22 18:56:37.904739: step: 1268/529, loss: 0.0003752862976398319
2023-01-22 18:56:38.992394: step: 1272/529, loss: 0.015612095594406128
2023-01-22 18:56:40.080528: step: 1276/529, loss: 9.446031981497072e-06
2023-01-22 18:56:41.194961: step: 1280/529, loss: 0.003517782548442483
2023-01-22 18:56:42.298813: step: 1284/529, loss: 0.001117116305977106
2023-01-22 18:56:43.402491: step: 1288/529, loss: 0.0030756795313209295
2023-01-22 18:56:44.504475: step: 1292/529, loss: 0.004678931552916765
2023-01-22 18:56:45.621527: step: 1296/529, loss: 0.0003312908811494708
2023-01-22 18:56:46.716170: step: 1300/529, loss: 0.01911284774541855
2023-01-22 18:56:47.815774: step: 1304/529, loss: 0.0010765891056507826
2023-01-22 18:56:48.946652: step: 1308/529, loss: 0.0017226110212504864
2023-01-22 18:56:50.042981: step: 1312/529, loss: 0.01661721058189869
2023-01-22 18:56:51.165745: step: 1316/529, loss: 0.014970474876463413
2023-01-22 18:56:52.261383: step: 1320/529, loss: 0.00523312296718359
2023-01-22 18:56:53.353886: step: 1324/529, loss: 0.014798336662352085
2023-01-22 18:56:54.473215: step: 1328/529, loss: 0.006073483265936375
2023-01-22 18:56:55.600051: step: 1332/529, loss: 0.013157440349459648
2023-01-22 18:56:56.735259: step: 1336/529, loss: 0.0037649902515113354
2023-01-22 18:56:57.838195: step: 1340/529, loss: 0.003918703645467758
2023-01-22 18:56:58.961267: step: 1344/529, loss: 0.015555571764707565
2023-01-22 18:57:00.082847: step: 1348/529, loss: 0.025919701904058456
2023-01-22 18:57:01.203841: step: 1352/529, loss: 0.008317217230796814
2023-01-22 18:57:02.345691: step: 1356/529, loss: 0.015770718455314636
2023-01-22 18:57:03.445771: step: 1360/529, loss: 0.016272801905870438
2023-01-22 18:57:04.548342: step: 1364/529, loss: 0.01836567558348179
2023-01-22 18:57:05.643030: step: 1368/529, loss: 0.015131909400224686
2023-01-22 18:57:06.743058: step: 1372/529, loss: 0.0033577620051801205
2023-01-22 18:57:07.834851: step: 1376/529, loss: 0.00923423282802105
2023-01-22 18:57:08.931057: step: 1380/529, loss: 0.004627783317118883
2023-01-22 18:57:10.037743: step: 1384/529, loss: 0.0006984298233874142
2023-01-22 18:57:11.167043: step: 1388/529, loss: 0.001548895612359047
2023-01-22 18:57:12.268967: step: 1392/529, loss: 0.03049153834581375
2023-01-22 18:57:13.381361: step: 1396/529, loss: 0.0013241315027698874
2023-01-22 18:57:14.479433: step: 1400/529, loss: 0.002538112923502922
2023-01-22 18:57:15.609788: step: 1404/529, loss: 0.0011562154395505786
2023-01-22 18:57:16.688295: step: 1408/529, loss: 0.003173451405018568
2023-01-22 18:57:17.797112: step: 1412/529, loss: 0.004766612313687801
2023-01-22 18:57:18.893385: step: 1416/529, loss: 0.0015264734392985702
2023-01-22 18:57:20.022774: step: 1420/529, loss: 0.004329460673034191
2023-01-22 18:57:21.136308: step: 1424/529, loss: 0.014855623245239258
2023-01-22 18:57:22.236184: step: 1428/529, loss: 0.031332649290561676
2023-01-22 18:57:23.347021: step: 1432/529, loss: 0.006972219329327345
2023-01-22 18:57:24.439589: step: 1436/529, loss: 0.023841822519898415
2023-01-22 18:57:25.531857: step: 1440/529, loss: 0.004149661399424076
2023-01-22 18:57:26.666144: step: 1444/529, loss: 0.005571763031184673
2023-01-22 18:57:27.753701: step: 1448/529, loss: 0.003978666849434376
2023-01-22 18:57:28.861192: step: 1452/529, loss: 0.0069182622246444225
2023-01-22 18:57:29.948048: step: 1456/529, loss: 0.0008632629178464413
2023-01-22 18:57:31.050594: step: 1460/529, loss: 0.003161513712257147
2023-01-22 18:57:32.184874: step: 1464/529, loss: 0.0020406313706189394
2023-01-22 18:57:33.295836: step: 1468/529, loss: 0.0010959033388644457
2023-01-22 18:57:34.425116: step: 1472/529, loss: 0.0032862797379493713
2023-01-22 18:57:35.523906: step: 1476/529, loss: 0.0025266262236982584
2023-01-22 18:57:36.628390: step: 1480/529, loss: 0.003277143696323037
2023-01-22 18:57:37.731851: step: 1484/529, loss: 0.004762754775583744
2023-01-22 18:57:38.857513: step: 1488/529, loss: 0.0004464202211238444
2023-01-22 18:57:39.997190: step: 1492/529, loss: 0.0007594140479341149
2023-01-22 18:57:41.132654: step: 1496/529, loss: 0.00411064550280571
2023-01-22 18:57:42.225842: step: 1500/529, loss: 9.792173659661785e-05
2023-01-22 18:57:43.326241: step: 1504/529, loss: 0.0042410958558321
2023-01-22 18:57:44.463275: step: 1508/529, loss: 0.008341701701283455
2023-01-22 18:57:45.541411: step: 1512/529, loss: 0.00592674408107996
2023-01-22 18:57:46.645159: step: 1516/529, loss: 0.014140663668513298
2023-01-22 18:57:47.771489: step: 1520/529, loss: 0.0008491849876008928
2023-01-22 18:57:48.869125: step: 1524/529, loss: 0.007004720624536276
2023-01-22 18:57:49.987365: step: 1528/529, loss: 0.0004268204793334007
2023-01-22 18:57:51.108663: step: 1532/529, loss: 0.03574948385357857
2023-01-22 18:57:52.205705: step: 1536/529, loss: 0.006179031915962696
2023-01-22 18:57:53.332481: step: 1540/529, loss: 0.007838006131350994
2023-01-22 18:57:54.437207: step: 1544/529, loss: 0.008983041159808636
2023-01-22 18:57:55.540198: step: 1548/529, loss: 0.00875949952751398
2023-01-22 18:57:56.657410: step: 1552/529, loss: 0.005664760712534189
2023-01-22 18:57:57.757474: step: 1556/529, loss: 0.022366249933838844
2023-01-22 18:57:58.839872: step: 1560/529, loss: 0.0013862333726137877
2023-01-22 18:57:59.945567: step: 1564/529, loss: 0.0022592064924538136
2023-01-22 18:58:01.051593: step: 1568/529, loss: 0.01212913915514946
2023-01-22 18:58:02.180768: step: 1572/529, loss: 0.008453449234366417
2023-01-22 18:58:03.279749: step: 1576/529, loss: 0.0037377227563410997
2023-01-22 18:58:04.368970: step: 1580/529, loss: 0.0001311369560426101
2023-01-22 18:58:05.464367: step: 1584/529, loss: 0.0007882571080699563
2023-01-22 18:58:06.549640: step: 1588/529, loss: 0.00010435284639243037
2023-01-22 18:58:07.644354: step: 1592/529, loss: 0.00039552515954710543
2023-01-22 18:58:08.731233: step: 1596/529, loss: 0.004523188807070255
2023-01-22 18:58:09.861364: step: 1600/529, loss: 0.0017764779040589929
2023-01-22 18:58:10.968681: step: 1604/529, loss: 0.0060484642162919044
2023-01-22 18:58:12.078809: step: 1608/529, loss: 0.008821922354400158
2023-01-22 18:58:13.195917: step: 1612/529, loss: 0.004837465472519398
2023-01-22 18:58:14.290703: step: 1616/529, loss: 0.003824402578175068
2023-01-22 18:58:15.405021: step: 1620/529, loss: 0.013101443648338318
2023-01-22 18:58:16.498516: step: 1624/529, loss: 0.008894307538866997
2023-01-22 18:58:17.603672: step: 1628/529, loss: 0.0024431536439806223
2023-01-22 18:58:18.710671: step: 1632/529, loss: 0.008759829215705395
2023-01-22 18:58:19.798979: step: 1636/529, loss: 0.004570564720779657
2023-01-22 18:58:20.885006: step: 1640/529, loss: 0.01350428257137537
2023-01-22 18:58:21.992274: step: 1644/529, loss: 0.006743482779711485
2023-01-22 18:58:23.101327: step: 1648/529, loss: 0.0009088098886422813
2023-01-22 18:58:24.211146: step: 1652/529, loss: 0.0013909143162891269
2023-01-22 18:58:25.319863: step: 1656/529, loss: 0.006951337214559317
2023-01-22 18:58:26.430517: step: 1660/529, loss: 0.011399917304515839
2023-01-22 18:58:27.528812: step: 1664/529, loss: 0.0023579145781695843
2023-01-22 18:58:28.633699: step: 1668/529, loss: 0.008432172238826752
2023-01-22 18:58:29.713983: step: 1672/529, loss: 0.0033959040883928537
2023-01-22 18:58:30.804099: step: 1676/529, loss: 0.006625001784414053
2023-01-22 18:58:31.936180: step: 1680/529, loss: 0.006230037193745375
2023-01-22 18:58:33.037823: step: 1684/529, loss: 0.004751909989863634
2023-01-22 18:58:34.169855: step: 1688/529, loss: 0.007471776567399502
2023-01-22 18:58:35.280041: step: 1692/529, loss: 0.003270291956141591
2023-01-22 18:58:36.401133: step: 1696/529, loss: 0.00880468264222145
2023-01-22 18:58:37.484706: step: 1700/529, loss: 0.011734520085155964
2023-01-22 18:58:38.612848: step: 1704/529, loss: 0.002255986910313368
2023-01-22 18:58:39.733523: step: 1708/529, loss: 0.004465277306735516
2023-01-22 18:58:40.823170: step: 1712/529, loss: 0.0020688881631940603
2023-01-22 18:58:41.922218: step: 1716/529, loss: 0.0008904458954930305
2023-01-22 18:58:43.016557: step: 1720/529, loss: 0.002547086915001273
2023-01-22 18:58:44.108766: step: 1724/529, loss: 0.005983465816825628
2023-01-22 18:58:45.243842: step: 1728/529, loss: 0.030051473528146744
2023-01-22 18:58:46.357324: step: 1732/529, loss: 0.012958361767232418
2023-01-22 18:58:47.451252: step: 1736/529, loss: 0.003839613404124975
2023-01-22 18:58:48.556494: step: 1740/529, loss: 0.008171058259904385
2023-01-22 18:58:49.671239: step: 1744/529, loss: 0.005781652871519327
2023-01-22 18:58:50.781402: step: 1748/529, loss: 0.0033688365947455168
2023-01-22 18:58:51.879944: step: 1752/529, loss: 0.0029633932281285524
2023-01-22 18:58:52.992253: step: 1756/529, loss: 0.008164803497493267
2023-01-22 18:58:54.074305: step: 1760/529, loss: 0.000297634833259508
2023-01-22 18:58:55.193132: step: 1764/529, loss: 0.00467092078179121
2023-01-22 18:58:56.304382: step: 1768/529, loss: 0.006810002028942108
2023-01-22 18:58:57.418044: step: 1772/529, loss: 0.0042831869795918465
2023-01-22 18:58:58.532484: step: 1776/529, loss: 0.013637793250381947
2023-01-22 18:58:59.642432: step: 1780/529, loss: 0.002816260326653719
2023-01-22 18:59:00.750233: step: 1784/529, loss: 0.0038292035460472107
2023-01-22 18:59:01.871611: step: 1788/529, loss: 0.007115884218364954
2023-01-22 18:59:02.977740: step: 1792/529, loss: 0.009606112726032734
2023-01-22 18:59:04.092606: step: 1796/529, loss: 0.005211938638240099
2023-01-22 18:59:05.179566: step: 1800/529, loss: 0.023559128865599632
2023-01-22 18:59:06.272987: step: 1804/529, loss: 0.0031590706203132868
2023-01-22 18:59:07.365126: step: 1808/529, loss: 0.011790262535214424
2023-01-22 18:59:08.460326: step: 1812/529, loss: 0.0020895814523100853
2023-01-22 18:59:09.560774: step: 1816/529, loss: 0.010864565148949623
2023-01-22 18:59:10.663209: step: 1820/529, loss: 0.008166816085577011
2023-01-22 18:59:11.789474: step: 1824/529, loss: 0.019291039556264877
2023-01-22 18:59:12.876339: step: 1828/529, loss: 0.0005839415825903416
2023-01-22 18:59:14.001512: step: 1832/529, loss: 0.013008509762585163
2023-01-22 18:59:15.116946: step: 1836/529, loss: 0.0059598283842206
2023-01-22 18:59:16.226717: step: 1840/529, loss: 0.02035428211092949
2023-01-22 18:59:17.342550: step: 1844/529, loss: 0.0016842653276398778
2023-01-22 18:59:18.451492: step: 1848/529, loss: 0.0023054194170981646
2023-01-22 18:59:19.540019: step: 1852/529, loss: 0.000536528299562633
2023-01-22 18:59:20.649931: step: 1856/529, loss: 0.00028577970806509256
2023-01-22 18:59:21.755047: step: 1860/529, loss: 0.021707382053136826
2023-01-22 18:59:22.858143: step: 1864/529, loss: 0.004447434563189745
2023-01-22 18:59:23.969921: step: 1868/529, loss: 0.017727050930261612
2023-01-22 18:59:25.060362: step: 1872/529, loss: 0.0029900369700044394
2023-01-22 18:59:26.168616: step: 1876/529, loss: 0.012091061100363731
2023-01-22 18:59:27.269129: step: 1880/529, loss: 0.007277886848896742
2023-01-22 18:59:28.347635: step: 1884/529, loss: 0.006311463657766581
2023-01-22 18:59:29.462538: step: 1888/529, loss: 0.011168006807565689
2023-01-22 18:59:30.605210: step: 1892/529, loss: 0.046983376145362854
2023-01-22 18:59:31.708079: step: 1896/529, loss: 0.011099531315267086
2023-01-22 18:59:32.828578: step: 1900/529, loss: 0.009420022368431091
2023-01-22 18:59:33.934472: step: 1904/529, loss: 0.005504069849848747
2023-01-22 18:59:35.066267: step: 1908/529, loss: 0.0008501311531290412
2023-01-22 18:59:36.190564: step: 1912/529, loss: 0.0037150210700929165
2023-01-22 18:59:37.302920: step: 1916/529, loss: 0.011345190927386284
2023-01-22 18:59:38.412583: step: 1920/529, loss: 0.009494204074144363
2023-01-22 18:59:39.536171: step: 1924/529, loss: 0.00693238852545619
2023-01-22 18:59:40.629660: step: 1928/529, loss: 0.0013735938118770719
2023-01-22 18:59:41.739935: step: 1932/529, loss: 0.0016123269451782107
2023-01-22 18:59:42.842081: step: 1936/529, loss: 0.003117071697488427
2023-01-22 18:59:43.962505: step: 1940/529, loss: 0.022922208532691002
2023-01-22 18:59:45.072852: step: 1944/529, loss: 0.002638646401464939
2023-01-22 18:59:46.167460: step: 1948/529, loss: 0.00040953143616206944
2023-01-22 18:59:47.269204: step: 1952/529, loss: 0.001016639405861497
2023-01-22 18:59:48.386822: step: 1956/529, loss: 0.003975257743149996
2023-01-22 18:59:49.552029: step: 1960/529, loss: 0.006373354699462652
2023-01-22 18:59:50.651918: step: 1964/529, loss: 0.0010295009706169367
2023-01-22 18:59:51.784805: step: 1968/529, loss: 0.007885849103331566
2023-01-22 18:59:52.891999: step: 1972/529, loss: 0.0020311139523983
2023-01-22 18:59:53.998312: step: 1976/529, loss: 0.01220087893307209
2023-01-22 18:59:55.113050: step: 1980/529, loss: 0.007413088344037533
2023-01-22 18:59:56.230509: step: 1984/529, loss: 0.004888553638011217
2023-01-22 18:59:57.339654: step: 1988/529, loss: 0.014558098278939724
2023-01-22 18:59:58.447586: step: 1992/529, loss: 0.009451298043131828
2023-01-22 18:59:59.541056: step: 1996/529, loss: 0.005956432782113552
2023-01-22 19:00:00.645360: step: 2000/529, loss: 0.004337357357144356
2023-01-22 19:00:01.734899: step: 2004/529, loss: 0.002232165774330497
2023-01-22 19:00:02.882857: step: 2008/529, loss: 0.0025686766020953655
2023-01-22 19:00:03.981142: step: 2012/529, loss: 0.0014873025938868523
2023-01-22 19:00:05.072093: step: 2016/529, loss: 0.005499100778251886
2023-01-22 19:00:06.181226: step: 2020/529, loss: 0.038545068353414536
2023-01-22 19:00:07.271205: step: 2024/529, loss: 0.023336559534072876
2023-01-22 19:00:08.370539: step: 2028/529, loss: 0.005675704218447208
2023-01-22 19:00:09.480899: step: 2032/529, loss: 0.004638324957340956
2023-01-22 19:00:10.579621: step: 2036/529, loss: 0.006674089003354311
2023-01-22 19:00:11.681255: step: 2040/529, loss: 0.00048447161680087447
2023-01-22 19:00:12.818593: step: 2044/529, loss: 0.0025183423422276974
2023-01-22 19:00:13.917368: step: 2048/529, loss: 0.005090930499136448
2023-01-22 19:00:15.021255: step: 2052/529, loss: 0.0075054531916975975
2023-01-22 19:00:16.134194: step: 2056/529, loss: 0.0031944126822054386
2023-01-22 19:00:17.267730: step: 2060/529, loss: 0.023951824754476547
2023-01-22 19:00:18.392498: step: 2064/529, loss: 0.005172196310013533
2023-01-22 19:00:19.479974: step: 2068/529, loss: 0.005661047529429197
2023-01-22 19:00:20.605248: step: 2072/529, loss: 0.0016060305060818791
2023-01-22 19:00:21.718323: step: 2076/529, loss: 0.005676075350493193
2023-01-22 19:00:22.805854: step: 2080/529, loss: 0.007122858427464962
2023-01-22 19:00:23.910911: step: 2084/529, loss: 0.01702049747109413
2023-01-22 19:00:24.999193: step: 2088/529, loss: 0.020898722112178802
2023-01-22 19:00:26.078620: step: 2092/529, loss: 0.04448986053466797
2023-01-22 19:00:27.205921: step: 2096/529, loss: 0.0036965468898415565
2023-01-22 19:00:28.308042: step: 2100/529, loss: 0.0017909681191667914
2023-01-22 19:00:29.408683: step: 2104/529, loss: 0.006705079693347216
2023-01-22 19:00:30.519118: step: 2108/529, loss: 0.011283526197075844
2023-01-22 19:00:31.607622: step: 2112/529, loss: 0.01771441660821438
2023-01-22 19:00:32.710325: step: 2116/529, loss: 0.01893550530076027
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32672314664502167, 'r': 0.3273431146652209, 'f1': 0.32703283683141504}, 'combined': 0.24097156398104264, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3704498383666889, 'r': 0.30014783264545414, 'f1': 0.3316137854215932}, 'combined': 0.20382115591766214, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3267878031894576, 'r': 0.3472507965580574, 'f1': 0.33670868405905474}, 'combined': 0.2481011356224614, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3487829511903388, 'r': 0.310096454004582, 'f1': 0.32830395222136477}, 'combined': 0.20178681941410712, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3352374063513362, 'r': 0.3447792680121902, 'f1': 0.3399413924086515}, 'combined': 0.25048313124848004, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.35757643708164705, 'r': 0.2968967992738524, 'f1': 0.3244236548356665}, 'combined': 0.20037931622202934, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3269230769230769, 'r': 0.36428571428571427, 'f1': 0.34459459459459457}, 'combined': 0.22972972972972971, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36607142857142855, 'r': 0.44565217391304346, 'f1': 0.4019607843137254}, 'combined': 0.2009803921568627, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 9
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 19:03:04.219261: step: 4/529, loss: 0.00414487486705184
2023-01-22 19:03:05.344137: step: 8/529, loss: 0.002066281856968999
2023-01-22 19:03:06.457250: step: 12/529, loss: 0.004331429488956928
2023-01-22 19:03:07.567086: step: 16/529, loss: 0.008557716384530067
2023-01-22 19:03:08.646238: step: 20/529, loss: 0.0053951493464410305
2023-01-22 19:03:09.745938: step: 24/529, loss: 0.014109299518167973
2023-01-22 19:03:10.848465: step: 28/529, loss: 0.01493789441883564
2023-01-22 19:03:11.945402: step: 32/529, loss: 0.0017501991242170334
2023-01-22 19:03:13.038970: step: 36/529, loss: 0.006952761206775904
2023-01-22 19:03:14.136785: step: 40/529, loss: 0.002125214785337448
2023-01-22 19:03:15.245398: step: 44/529, loss: 0.005766458343714476
2023-01-22 19:03:16.362222: step: 48/529, loss: 0.00222352659329772
2023-01-22 19:03:17.462704: step: 52/529, loss: 0.006024430971592665
2023-01-22 19:03:18.554506: step: 56/529, loss: 0.004829976242035627
2023-01-22 19:03:19.663670: step: 60/529, loss: 0.012165335938334465
2023-01-22 19:03:20.766339: step: 64/529, loss: 0.0006877960986457765
2023-01-22 19:03:21.857612: step: 68/529, loss: 0.0019286986207589507
2023-01-22 19:03:22.955818: step: 72/529, loss: 0.0030915564857423306
2023-01-22 19:03:24.075723: step: 76/529, loss: 0.025230253115296364
2023-01-22 19:03:25.172118: step: 80/529, loss: 0.0005667478544637561
2023-01-22 19:03:26.257520: step: 84/529, loss: 0.0013361324090510607
2023-01-22 19:03:27.375341: step: 88/529, loss: 0.02095462754368782
2023-01-22 19:03:28.460413: step: 92/529, loss: 0.009107070043683052
2023-01-22 19:03:29.576453: step: 96/529, loss: 0.004378173034638166
2023-01-22 19:03:30.687786: step: 100/529, loss: 0.0033493824303150177
2023-01-22 19:03:31.773364: step: 104/529, loss: 0.005826561711728573
2023-01-22 19:03:32.860717: step: 108/529, loss: 0.00200914335437119
2023-01-22 19:03:33.966591: step: 112/529, loss: 0.010383873246610165
2023-01-22 19:03:35.121918: step: 116/529, loss: 0.018977833911776543
2023-01-22 19:03:36.209121: step: 120/529, loss: 0.0004841686168219894
2023-01-22 19:03:37.337229: step: 124/529, loss: 0.002106103580445051
2023-01-22 19:03:38.422126: step: 128/529, loss: 0.00032513117184862494
2023-01-22 19:03:39.524467: step: 132/529, loss: 0.005869721528142691
2023-01-22 19:03:40.623199: step: 136/529, loss: 0.006620506290346384
2023-01-22 19:03:41.735576: step: 140/529, loss: 0.0020251385867595673
2023-01-22 19:03:42.838424: step: 144/529, loss: 0.0034202842507511377
2023-01-22 19:03:43.957764: step: 148/529, loss: 0.0014481099788099527
2023-01-22 19:03:45.036836: step: 152/529, loss: 0.0
2023-01-22 19:03:46.138067: step: 156/529, loss: 0.0008477833471260965
2023-01-22 19:03:47.262014: step: 160/529, loss: 0.005983901210129261
2023-01-22 19:03:48.382560: step: 164/529, loss: 0.009541898965835571
2023-01-22 19:03:49.495434: step: 168/529, loss: 0.010809199884533882
2023-01-22 19:03:50.596473: step: 172/529, loss: 0.004650185350328684
2023-01-22 19:03:51.707518: step: 176/529, loss: 0.011558866128325462
2023-01-22 19:03:52.809946: step: 180/529, loss: 0.005416307598352432
2023-01-22 19:03:53.915893: step: 184/529, loss: 0.007540030870586634
2023-01-22 19:03:55.013390: step: 188/529, loss: 0.0005049585015513003
2023-01-22 19:03:56.117497: step: 192/529, loss: 0.0009229168645106256
2023-01-22 19:03:57.228447: step: 196/529, loss: 0.004483763128519058
2023-01-22 19:03:58.322284: step: 200/529, loss: 0.00019230988982599229
2023-01-22 19:03:59.419230: step: 204/529, loss: 0.003221993101760745
2023-01-22 19:04:00.540856: step: 208/529, loss: 0.0013136722845956683
2023-01-22 19:04:01.652059: step: 212/529, loss: 0.00852738693356514
2023-01-22 19:04:02.789822: step: 216/529, loss: 0.0005509539623744786
2023-01-22 19:04:03.903622: step: 220/529, loss: 0.011330599896609783
2023-01-22 19:04:05.013830: step: 224/529, loss: 0.026606164872646332
2023-01-22 19:04:06.132506: step: 228/529, loss: 0.007711793761700392
2023-01-22 19:04:07.239047: step: 232/529, loss: 0.008934825658798218
2023-01-22 19:04:08.343298: step: 236/529, loss: 0.005774942692369223
2023-01-22 19:04:09.472714: step: 240/529, loss: 0.0008422565879300237
2023-01-22 19:04:10.588777: step: 244/529, loss: 0.002665509469807148
2023-01-22 19:04:11.722428: step: 248/529, loss: 0.003581276163458824
2023-01-22 19:04:12.824571: step: 252/529, loss: 0.009856889955699444
2023-01-22 19:04:13.931281: step: 256/529, loss: 0.004116377327591181
2023-01-22 19:04:15.047865: step: 260/529, loss: 0.011990280821919441
2023-01-22 19:04:16.148902: step: 264/529, loss: 0.0026049900334328413
2023-01-22 19:04:17.249735: step: 268/529, loss: 3.9648999518249184e-05
2023-01-22 19:04:18.378490: step: 272/529, loss: 0.0002796795160975307
2023-01-22 19:04:19.530876: step: 276/529, loss: 0.009639749303460121
2023-01-22 19:04:20.632632: step: 280/529, loss: 0.0067772273905575275
2023-01-22 19:04:21.742760: step: 284/529, loss: 0.0005912405904382467
2023-01-22 19:04:22.820208: step: 288/529, loss: 0.00014372813166119158
2023-01-22 19:04:23.928916: step: 292/529, loss: 0.00173787004314363
2023-01-22 19:04:25.030364: step: 296/529, loss: 0.006105820182710886
2023-01-22 19:04:26.133210: step: 300/529, loss: 0.004554436542093754
2023-01-22 19:04:27.248882: step: 304/529, loss: 0.006808524020016193
2023-01-22 19:04:28.379459: step: 308/529, loss: 0.018997371196746826
2023-01-22 19:04:29.479305: step: 312/529, loss: 0.009039481170475483
2023-01-22 19:04:30.577040: step: 316/529, loss: 0.0018510365625843406
2023-01-22 19:04:31.710048: step: 320/529, loss: 0.0039311740547418594
2023-01-22 19:04:32.810425: step: 324/529, loss: 0.0
2023-01-22 19:04:33.910358: step: 328/529, loss: 0.000220126734348014
2023-01-22 19:04:35.042082: step: 332/529, loss: 0.015490574762225151
2023-01-22 19:04:36.147330: step: 336/529, loss: 0.00874862540513277
2023-01-22 19:04:37.239156: step: 340/529, loss: 0.004412591457366943
2023-01-22 19:04:38.353487: step: 344/529, loss: 0.00694803474470973
2023-01-22 19:04:39.462849: step: 348/529, loss: 3.25481996696908e-05
2023-01-22 19:04:40.562341: step: 352/529, loss: 0.0010647244052961469
2023-01-22 19:04:41.665493: step: 356/529, loss: 0.0011962694115936756
2023-01-22 19:04:42.745174: step: 360/529, loss: 0.00199749949388206
2023-01-22 19:04:43.850831: step: 364/529, loss: 0.0052075800485908985
2023-01-22 19:04:44.945941: step: 368/529, loss: 0.005952970124781132
2023-01-22 19:04:46.054624: step: 372/529, loss: 0.002065795473754406
2023-01-22 19:04:47.167864: step: 376/529, loss: 0.04618256539106369
2023-01-22 19:04:48.294103: step: 380/529, loss: 0.0067822812125086784
2023-01-22 19:04:49.426287: step: 384/529, loss: 0.010984989814460278
2023-01-22 19:04:50.513730: step: 388/529, loss: 0.0020203085150569677
2023-01-22 19:04:51.638820: step: 392/529, loss: 0.0024973878171294928
2023-01-22 19:04:52.794847: step: 396/529, loss: 0.007390706334263086
2023-01-22 19:04:53.883567: step: 400/529, loss: 0.026156747713685036
2023-01-22 19:04:54.999627: step: 404/529, loss: 0.010489759035408497
2023-01-22 19:04:56.117597: step: 408/529, loss: 0.007646896410733461
2023-01-22 19:04:57.240511: step: 412/529, loss: 0.012465310283005238
2023-01-22 19:04:58.335624: step: 416/529, loss: 0.000603461405262351
2023-01-22 19:04:59.456202: step: 420/529, loss: 0.0025774831883609295
2023-01-22 19:05:00.565983: step: 424/529, loss: 0.004329221323132515
2023-01-22 19:05:01.680755: step: 428/529, loss: 0.008298619650304317
2023-01-22 19:05:02.792734: step: 432/529, loss: 0.00048650981625542045
2023-01-22 19:05:03.879296: step: 436/529, loss: 0.005668371915817261
2023-01-22 19:05:05.003534: step: 440/529, loss: 0.00552634010091424
2023-01-22 19:05:06.126178: step: 444/529, loss: 0.011496046558022499
2023-01-22 19:05:07.230825: step: 448/529, loss: 0.0002006281865760684
2023-01-22 19:05:08.322830: step: 452/529, loss: 0.0033039164263755083
2023-01-22 19:05:09.456227: step: 456/529, loss: 0.002336034318432212
2023-01-22 19:05:10.556407: step: 460/529, loss: 0.0026862837839871645
2023-01-22 19:05:11.690030: step: 464/529, loss: 0.0040974910371005535
2023-01-22 19:05:12.790248: step: 468/529, loss: 0.00464132335036993
2023-01-22 19:05:13.888850: step: 472/529, loss: 0.000561471504624933
2023-01-22 19:05:14.999171: step: 476/529, loss: 0.00554230622947216
2023-01-22 19:05:16.093452: step: 480/529, loss: 0.005267248954623938
2023-01-22 19:05:17.190272: step: 484/529, loss: 0.007264274638146162
2023-01-22 19:05:18.313575: step: 488/529, loss: 0.0027749843429774046
2023-01-22 19:05:19.402465: step: 492/529, loss: 0.00032936056959442794
2023-01-22 19:05:20.511445: step: 496/529, loss: 0.01107385940849781
2023-01-22 19:05:21.619599: step: 500/529, loss: 0.022173600271344185
2023-01-22 19:05:22.716661: step: 504/529, loss: 0.004900334868580103
2023-01-22 19:05:23.798359: step: 508/529, loss: 0.0056189619936048985
2023-01-22 19:05:24.911339: step: 512/529, loss: 0.007474112324416637
2023-01-22 19:05:26.029122: step: 516/529, loss: 9.483334724791348e-05
2023-01-22 19:05:27.154711: step: 520/529, loss: 0.0020297919400036335
2023-01-22 19:05:28.258398: step: 524/529, loss: 0.008607524447143078
2023-01-22 19:05:29.353988: step: 528/529, loss: 0.01237131841480732
2023-01-22 19:05:30.451834: step: 532/529, loss: 0.0021569342352449894
2023-01-22 19:05:31.539247: step: 536/529, loss: 0.0033774443436414003
2023-01-22 19:05:32.653097: step: 540/529, loss: 0.012475697323679924
2023-01-22 19:05:33.750544: step: 544/529, loss: 0.0007182147237472236
2023-01-22 19:05:34.842936: step: 548/529, loss: 0.0003945502976421267
2023-01-22 19:05:35.946901: step: 552/529, loss: 0.003738230559974909
2023-01-22 19:05:37.064914: step: 556/529, loss: 0.006862856447696686
2023-01-22 19:05:38.170097: step: 560/529, loss: 0.006230687256902456
2023-01-22 19:05:39.263102: step: 564/529, loss: 0.00483669014647603
2023-01-22 19:05:40.350346: step: 568/529, loss: 0.0014557491522282362
2023-01-22 19:05:41.443605: step: 572/529, loss: 0.001094767707400024
2023-01-22 19:05:42.554487: step: 576/529, loss: 0.0032514336053282022
2023-01-22 19:05:43.663152: step: 580/529, loss: 0.001310235122218728
2023-01-22 19:05:44.827165: step: 584/529, loss: 0.021781522780656815
2023-01-22 19:05:45.962564: step: 588/529, loss: 0.0032963836565613747
2023-01-22 19:05:47.067507: step: 592/529, loss: 0.01116613857448101
2023-01-22 19:05:48.176871: step: 596/529, loss: 0.010423549450933933
2023-01-22 19:05:49.295400: step: 600/529, loss: 0.0019972852896898985
2023-01-22 19:05:50.412700: step: 604/529, loss: 0.002582851331681013
2023-01-22 19:05:51.541712: step: 608/529, loss: 0.004633565898984671
2023-01-22 19:05:52.650406: step: 612/529, loss: 0.009637289680540562
2023-01-22 19:05:53.746444: step: 616/529, loss: 0.0003890860825777054
2023-01-22 19:05:54.877367: step: 620/529, loss: 0.0015760910464450717
2023-01-22 19:05:55.959064: step: 624/529, loss: 0.0034791354555636644
2023-01-22 19:05:57.073784: step: 628/529, loss: 0.002584443660452962
2023-01-22 19:05:58.154785: step: 632/529, loss: 0.004601211287081242
2023-01-22 19:05:59.247384: step: 636/529, loss: 0.002178665716201067
2023-01-22 19:06:00.340723: step: 640/529, loss: 0.0008391987648792565
2023-01-22 19:06:01.437427: step: 644/529, loss: 0.005405292846262455
2023-01-22 19:06:02.540737: step: 648/529, loss: 0.0726286843419075
2023-01-22 19:06:03.660882: step: 652/529, loss: 0.0053447457030415535
2023-01-22 19:06:04.772058: step: 656/529, loss: 0.0003974978462792933
2023-01-22 19:06:05.856587: step: 660/529, loss: 0.0037565017119050026
2023-01-22 19:06:06.954316: step: 664/529, loss: 0.003937878645956516
2023-01-22 19:06:08.069375: step: 668/529, loss: 0.01446220837533474
2023-01-22 19:06:09.195090: step: 672/529, loss: 0.0008877164218574762
2023-01-22 19:06:10.326133: step: 676/529, loss: 0.01086584571748972
2023-01-22 19:06:11.427279: step: 680/529, loss: 0.00027775357011705637
2023-01-22 19:06:12.523053: step: 684/529, loss: 0.000326420966302976
2023-01-22 19:06:13.662757: step: 688/529, loss: 0.014666769653558731
2023-01-22 19:06:14.803310: step: 692/529, loss: 0.020226916298270226
2023-01-22 19:06:15.893685: step: 696/529, loss: 0.0022267738822847605
2023-01-22 19:06:17.003378: step: 700/529, loss: 0.002878149040043354
2023-01-22 19:06:18.104476: step: 704/529, loss: 0.0013113577151671052
2023-01-22 19:06:19.222703: step: 708/529, loss: 0.009311271831393242
2023-01-22 19:06:20.324419: step: 712/529, loss: 0.010569063946604729
2023-01-22 19:06:21.433803: step: 716/529, loss: 0.0005601709708571434
2023-01-22 19:06:22.527733: step: 720/529, loss: 1.091440935852006e-05
2023-01-22 19:06:23.634280: step: 724/529, loss: 0.010182461701333523
2023-01-22 19:06:24.723893: step: 728/529, loss: 0.0004533478058874607
2023-01-22 19:06:25.851061: step: 732/529, loss: 0.0013494596350938082
2023-01-22 19:06:26.996791: step: 736/529, loss: 0.005440648645162582
2023-01-22 19:06:28.104951: step: 740/529, loss: 0.00649876007810235
2023-01-22 19:06:29.227143: step: 744/529, loss: 0.009621547535061836
2023-01-22 19:06:30.322417: step: 748/529, loss: 0.013323670253157616
2023-01-22 19:06:31.423504: step: 752/529, loss: 0.003264613915234804
2023-01-22 19:06:32.562049: step: 756/529, loss: 0.004687939770519733
2023-01-22 19:06:33.668192: step: 760/529, loss: 0.0005088684265501797
2023-01-22 19:06:34.771437: step: 764/529, loss: 0.004500416107475758
2023-01-22 19:06:35.898379: step: 768/529, loss: 0.016622252762317657
2023-01-22 19:06:37.013567: step: 772/529, loss: 0.0030898733530193567
2023-01-22 19:06:38.108043: step: 776/529, loss: 0.029359664767980576
2023-01-22 19:06:39.208480: step: 780/529, loss: 0.006753432564437389
2023-01-22 19:06:40.318555: step: 784/529, loss: 0.004939466714859009
2023-01-22 19:06:41.421877: step: 788/529, loss: 0.01325714960694313
2023-01-22 19:06:42.536194: step: 792/529, loss: 0.01342522632330656
2023-01-22 19:06:43.647151: step: 796/529, loss: 0.04887712746858597
2023-01-22 19:06:44.740671: step: 800/529, loss: 1.631297095627815e-06
2023-01-22 19:06:45.834347: step: 804/529, loss: 0.0006498720613308251
2023-01-22 19:06:46.929080: step: 808/529, loss: 0.003923764917999506
2023-01-22 19:06:48.053125: step: 812/529, loss: 0.03379932790994644
2023-01-22 19:06:49.187293: step: 816/529, loss: 0.00025219074450433254
2023-01-22 19:06:50.302317: step: 820/529, loss: 0.0008926524315029383
2023-01-22 19:06:51.427495: step: 824/529, loss: 0.0005559226265177131
2023-01-22 19:06:52.531583: step: 828/529, loss: 0.009458750486373901
2023-01-22 19:06:53.668117: step: 832/529, loss: 0.0012705448316410184
2023-01-22 19:06:54.784961: step: 836/529, loss: 0.0027521993033587933
2023-01-22 19:06:55.922951: step: 840/529, loss: 0.0005377698689699173
2023-01-22 19:06:57.034672: step: 844/529, loss: 0.005243862979114056
2023-01-22 19:06:58.137991: step: 848/529, loss: 0.006307366769760847
2023-01-22 19:06:59.262757: step: 852/529, loss: 0.02259444259107113
2023-01-22 19:07:00.374452: step: 856/529, loss: 0.00029475154587998986
2023-01-22 19:07:01.489468: step: 860/529, loss: 0.018171200528740883
2023-01-22 19:07:02.623829: step: 864/529, loss: 0.014193836599588394
2023-01-22 19:07:03.754159: step: 868/529, loss: 0.017552636563777924
2023-01-22 19:07:04.858512: step: 872/529, loss: 0.005190863739699125
2023-01-22 19:07:05.982244: step: 876/529, loss: 0.011153382249176502
2023-01-22 19:07:07.094543: step: 880/529, loss: 0.004842577967792749
2023-01-22 19:07:08.195906: step: 884/529, loss: 0.0062121800146996975
2023-01-22 19:07:09.340440: step: 888/529, loss: 0.01323642022907734
2023-01-22 19:07:10.452817: step: 892/529, loss: 0.015374289825558662
2023-01-22 19:07:11.546818: step: 896/529, loss: 0.0006335610523819923
2023-01-22 19:07:12.648764: step: 900/529, loss: 0.0008593490347266197
2023-01-22 19:07:13.745320: step: 904/529, loss: 0.0026908060535788536
2023-01-22 19:07:14.894297: step: 908/529, loss: 0.0017181062139570713
2023-01-22 19:07:16.006715: step: 912/529, loss: 0.00039353594183921814
2023-01-22 19:07:17.103245: step: 916/529, loss: 0.011335449293255806
2023-01-22 19:07:18.245222: step: 920/529, loss: 0.0061332546174526215
2023-01-22 19:07:19.381660: step: 924/529, loss: 0.0045195990242064
2023-01-22 19:07:20.492949: step: 928/529, loss: 0.00182430655695498
2023-01-22 19:07:21.596959: step: 932/529, loss: 0.009797133505344391
2023-01-22 19:07:22.722373: step: 936/529, loss: 0.0018056317931041121
2023-01-22 19:07:23.813450: step: 940/529, loss: 0.0021196717862039804
2023-01-22 19:07:24.945051: step: 944/529, loss: 0.038824744522571564
2023-01-22 19:07:26.047660: step: 948/529, loss: 0.016484001651406288
2023-01-22 19:07:27.134054: step: 952/529, loss: 0.0025689927861094475
2023-01-22 19:07:28.233722: step: 956/529, loss: 0.002180657582357526
2023-01-22 19:07:29.327350: step: 960/529, loss: 0.004588786978274584
2023-01-22 19:07:30.466089: step: 964/529, loss: 0.0012917533749714494
2023-01-22 19:07:31.585229: step: 968/529, loss: 0.01603994332253933
2023-01-22 19:07:32.689224: step: 972/529, loss: 0.00025173340691253543
2023-01-22 19:07:33.793693: step: 976/529, loss: 0.003559976350516081
2023-01-22 19:07:34.907571: step: 980/529, loss: 0.011127837002277374
2023-01-22 19:07:36.023771: step: 984/529, loss: 0.002899858169257641
2023-01-22 19:07:37.113052: step: 988/529, loss: 0.0003040945448447019
2023-01-22 19:07:38.225818: step: 992/529, loss: 0.0014891703613102436
2023-01-22 19:07:39.335416: step: 996/529, loss: 0.0091707156971097
2023-01-22 19:07:40.464862: step: 1000/529, loss: 0.00819131638854742
2023-01-22 19:07:41.553115: step: 1004/529, loss: 0.003619322320446372
2023-01-22 19:07:42.666253: step: 1008/529, loss: 0.015467430464923382
2023-01-22 19:07:43.769608: step: 1012/529, loss: 0.0
2023-01-22 19:07:44.861673: step: 1016/529, loss: 0.0004135034396313131
2023-01-22 19:07:45.978277: step: 1020/529, loss: 0.0007961735827848315
2023-01-22 19:07:47.072392: step: 1024/529, loss: 0.0030170453246682882
2023-01-22 19:07:48.201474: step: 1028/529, loss: 0.008891111239790916
2023-01-22 19:07:49.301787: step: 1032/529, loss: 0.028812071308493614
2023-01-22 19:07:50.413880: step: 1036/529, loss: 0.001309006940573454
2023-01-22 19:07:51.520419: step: 1040/529, loss: 0.0021758500952273607
2023-01-22 19:07:52.616447: step: 1044/529, loss: 0.016453970223665237
2023-01-22 19:07:53.720930: step: 1048/529, loss: 0.006567211821675301
2023-01-22 19:07:54.825281: step: 1052/529, loss: 0.00442207045853138
2023-01-22 19:07:55.907587: step: 1056/529, loss: 0.007647641934454441
2023-01-22 19:07:57.014737: step: 1060/529, loss: 0.0018164472421631217
2023-01-22 19:07:58.123271: step: 1064/529, loss: 0.0031214046757668257
2023-01-22 19:07:59.218513: step: 1068/529, loss: 0.0011373583693057299
2023-01-22 19:08:00.327955: step: 1072/529, loss: 2.2035350411897525e-05
2023-01-22 19:08:01.418118: step: 1076/529, loss: 5.894828791497275e-05
2023-01-22 19:08:02.529618: step: 1080/529, loss: 0.0053973328322172165
2023-01-22 19:08:03.640533: step: 1084/529, loss: 0.005806416273117065
2023-01-22 19:08:04.757493: step: 1088/529, loss: 0.003591387765482068
2023-01-22 19:08:05.843766: step: 1092/529, loss: 0.0004339154402259737
2023-01-22 19:08:06.934624: step: 1096/529, loss: 0.010434546507894993
2023-01-22 19:08:08.046079: step: 1100/529, loss: 0.0004758901195600629
2023-01-22 19:08:09.169143: step: 1104/529, loss: 0.004990661516785622
2023-01-22 19:08:10.293952: step: 1108/529, loss: 0.0016362224705517292
2023-01-22 19:08:11.459681: step: 1112/529, loss: 0.0032431031577289104
2023-01-22 19:08:12.577488: step: 1116/529, loss: 0.002160650212317705
2023-01-22 19:08:13.711336: step: 1120/529, loss: 0.008366209454834461
2023-01-22 19:08:14.826713: step: 1124/529, loss: 0.004021232016384602
2023-01-22 19:08:15.940646: step: 1128/529, loss: 0.006672700867056847
2023-01-22 19:08:17.079968: step: 1132/529, loss: 0.008496283553540707
2023-01-22 19:08:18.195945: step: 1136/529, loss: 0.003757246071472764
2023-01-22 19:08:19.314851: step: 1140/529, loss: 0.003016631817445159
2023-01-22 19:08:20.431009: step: 1144/529, loss: 0.004463598132133484
2023-01-22 19:08:21.545116: step: 1148/529, loss: 0.006736485753208399
2023-01-22 19:08:22.652078: step: 1152/529, loss: 0.008964328095316887
2023-01-22 19:08:23.731334: step: 1156/529, loss: 0.0049659074284136295
2023-01-22 19:08:24.858724: step: 1160/529, loss: 0.010895629413425922
2023-01-22 19:08:25.966327: step: 1164/529, loss: 0.010083192028105259
2023-01-22 19:08:27.058212: step: 1168/529, loss: 0.0060403067618608475
2023-01-22 19:08:28.159615: step: 1172/529, loss: 0.0014959246618673205
2023-01-22 19:08:29.275523: step: 1176/529, loss: 0.007001032587140799
2023-01-22 19:08:30.382549: step: 1180/529, loss: 0.02842397801578045
2023-01-22 19:08:31.506471: step: 1184/529, loss: 0.00036816977080889046
2023-01-22 19:08:32.660999: step: 1188/529, loss: 0.005977166350930929
2023-01-22 19:08:33.790545: step: 1192/529, loss: 0.006570525001734495
2023-01-22 19:08:34.900508: step: 1196/529, loss: 0.011007840745151043
2023-01-22 19:08:35.991730: step: 1200/529, loss: 0.01480249222368002
2023-01-22 19:08:37.078352: step: 1204/529, loss: 0.008009331300854683
2023-01-22 19:08:38.185936: step: 1208/529, loss: 0.002041494706645608
2023-01-22 19:08:39.279591: step: 1212/529, loss: 0.008568771183490753
2023-01-22 19:08:40.372651: step: 1216/529, loss: 0.00023385141685139388
2023-01-22 19:08:41.493595: step: 1220/529, loss: 0.0006642532534897327
2023-01-22 19:08:42.583404: step: 1224/529, loss: 0.004000767599791288
2023-01-22 19:08:43.681999: step: 1228/529, loss: 0.004966043867170811
2023-01-22 19:08:44.786675: step: 1232/529, loss: 0.007257959805428982
2023-01-22 19:08:45.897551: step: 1236/529, loss: 0.0028047217056155205
2023-01-22 19:08:46.983075: step: 1240/529, loss: 0.022721443325281143
2023-01-22 19:08:48.128966: step: 1244/529, loss: 0.012151169590651989
2023-01-22 19:08:49.241414: step: 1248/529, loss: 0.009717456065118313
2023-01-22 19:08:50.351481: step: 1252/529, loss: 0.0021035117097198963
2023-01-22 19:08:51.454910: step: 1256/529, loss: 0.0022540895733982325
2023-01-22 19:08:52.556967: step: 1260/529, loss: 0.004127219319343567
2023-01-22 19:08:53.662155: step: 1264/529, loss: 0.00014807403204031289
2023-01-22 19:08:54.767398: step: 1268/529, loss: 0.003077795496210456
2023-01-22 19:08:55.884093: step: 1272/529, loss: 0.004435978829860687
2023-01-22 19:08:56.985324: step: 1276/529, loss: 7.443239155691117e-05
2023-01-22 19:08:58.106076: step: 1280/529, loss: 0.006930656731128693
2023-01-22 19:08:59.197228: step: 1284/529, loss: 0.00949372723698616
2023-01-22 19:09:00.292438: step: 1288/529, loss: 0.008394051343202591
2023-01-22 19:09:01.389011: step: 1292/529, loss: 0.0007678737747482955
2023-01-22 19:09:02.471946: step: 1296/529, loss: 0.00044750425149686635
2023-01-22 19:09:03.590222: step: 1300/529, loss: 0.006408497225493193
2023-01-22 19:09:04.680792: step: 1304/529, loss: 0.005615501664578915
2023-01-22 19:09:05.793286: step: 1308/529, loss: 0.004020937718451023
2023-01-22 19:09:06.895717: step: 1312/529, loss: 0.008426829241216183
2023-01-22 19:09:07.990210: step: 1316/529, loss: 0.00027023834991268814
2023-01-22 19:09:09.103551: step: 1320/529, loss: 0.003480748739093542
2023-01-22 19:09:10.208404: step: 1324/529, loss: 0.013082791119813919
2023-01-22 19:09:11.306866: step: 1328/529, loss: 0.0084109827876091
2023-01-22 19:09:12.402146: step: 1332/529, loss: 0.007231859490275383
2023-01-22 19:09:13.509635: step: 1336/529, loss: 0.006308066193014383
2023-01-22 19:09:14.642988: step: 1340/529, loss: 0.008806136436760426
2023-01-22 19:09:15.757774: step: 1344/529, loss: 0.0019393779803067446
2023-01-22 19:09:16.881191: step: 1348/529, loss: 0.003081943839788437
2023-01-22 19:09:17.996827: step: 1352/529, loss: 0.003209242830052972
2023-01-22 19:09:19.116957: step: 1356/529, loss: 0.006779505871236324
2023-01-22 19:09:20.246338: step: 1360/529, loss: 0.0030315180774778128
2023-01-22 19:09:21.371598: step: 1364/529, loss: 0.005632452201098204
2023-01-22 19:09:22.486033: step: 1368/529, loss: 0.0014330879785120487
2023-01-22 19:09:23.596102: step: 1372/529, loss: 0.003500144463032484
2023-01-22 19:09:24.696923: step: 1376/529, loss: 0.00019482402421999723
2023-01-22 19:09:25.811239: step: 1380/529, loss: 0.0023417675402015448
2023-01-22 19:09:26.922268: step: 1384/529, loss: 0.003628364996984601
2023-01-22 19:09:28.040588: step: 1388/529, loss: 0.0008343298104591668
2023-01-22 19:09:29.163969: step: 1392/529, loss: 0.0007469439296983182
2023-01-22 19:09:30.270737: step: 1396/529, loss: 0.006617559120059013
2023-01-22 19:09:31.384070: step: 1400/529, loss: 0.003707305993884802
2023-01-22 19:09:32.525678: step: 1404/529, loss: 0.011335399001836777
2023-01-22 19:09:33.635391: step: 1408/529, loss: 0.03631199896335602
2023-01-22 19:09:34.743427: step: 1412/529, loss: 0.0039132460951805115
2023-01-22 19:09:35.836422: step: 1416/529, loss: 0.009202838875353336
2023-01-22 19:09:36.970467: step: 1420/529, loss: 0.012749945744872093
2023-01-22 19:09:38.077529: step: 1424/529, loss: 0.0005176840350031853
2023-01-22 19:09:39.186567: step: 1428/529, loss: 0.007134643383324146
2023-01-22 19:09:40.314182: step: 1432/529, loss: 0.015709972009062767
2023-01-22 19:09:41.441939: step: 1436/529, loss: 0.03329239413142204
2023-01-22 19:09:42.538687: step: 1440/529, loss: 0.017335517331957817
2023-01-22 19:09:43.640590: step: 1444/529, loss: 0.008728752844035625
2023-01-22 19:09:44.724521: step: 1448/529, loss: 0.008029668591916561
2023-01-22 19:09:45.830003: step: 1452/529, loss: 0.00221322663128376
2023-01-22 19:09:46.948447: step: 1456/529, loss: 9.519590821582824e-05
2023-01-22 19:09:48.053860: step: 1460/529, loss: 0.0008156742551364005
2023-01-22 19:09:49.164334: step: 1464/529, loss: 0.006727467756718397
2023-01-22 19:09:50.265144: step: 1468/529, loss: 0.027762891724705696
2023-01-22 19:09:51.366608: step: 1472/529, loss: 0.033658042550086975
2023-01-22 19:09:52.482583: step: 1476/529, loss: 0.0025946490932255983
2023-01-22 19:09:53.571496: step: 1480/529, loss: 0.00903841108083725
2023-01-22 19:09:54.667644: step: 1484/529, loss: 0.0021163439378142357
2023-01-22 19:09:55.771096: step: 1488/529, loss: 0.000791509635746479
2023-01-22 19:09:56.867478: step: 1492/529, loss: 0.00154003722127527
2023-01-22 19:09:57.966045: step: 1496/529, loss: 0.003983136732131243
2023-01-22 19:09:59.065134: step: 1500/529, loss: 0.006082726176828146
2023-01-22 19:10:00.180220: step: 1504/529, loss: 0.0028926811646670103
2023-01-22 19:10:01.282779: step: 1508/529, loss: 0.0001696194231044501
2023-01-22 19:10:02.407097: step: 1512/529, loss: 0.0024253271985799074
2023-01-22 19:10:03.539372: step: 1516/529, loss: 0.007770913653075695
2023-01-22 19:10:04.660280: step: 1520/529, loss: 0.012699322775006294
2023-01-22 19:10:05.753946: step: 1524/529, loss: 0.017201188951730728
2023-01-22 19:10:06.845578: step: 1528/529, loss: 0.009002854116261005
2023-01-22 19:10:07.947873: step: 1532/529, loss: 0.008372846059501171
2023-01-22 19:10:09.044368: step: 1536/529, loss: 0.003935167100280523
2023-01-22 19:10:10.149069: step: 1540/529, loss: 0.0019512263825163245
2023-01-22 19:10:11.271782: step: 1544/529, loss: 0.005391594022512436
2023-01-22 19:10:12.373533: step: 1548/529, loss: 0.00509494636207819
2023-01-22 19:10:13.491778: step: 1552/529, loss: 0.003335651708766818
2023-01-22 19:10:14.598956: step: 1556/529, loss: 0.0032638385891914368
2023-01-22 19:10:15.718699: step: 1560/529, loss: 0.007019201293587685
2023-01-22 19:10:16.833021: step: 1564/529, loss: 0.016559820622205734
2023-01-22 19:10:17.931157: step: 1568/529, loss: 0.0037013862747699022
2023-01-22 19:10:19.027653: step: 1572/529, loss: 0.003973239101469517
2023-01-22 19:10:20.133626: step: 1576/529, loss: 0.0024306594859808683
2023-01-22 19:10:21.224887: step: 1580/529, loss: 0.0065403287298977375
2023-01-22 19:10:22.348356: step: 1584/529, loss: 0.004244917072355747
2023-01-22 19:10:23.462931: step: 1588/529, loss: 0.01420369278639555
2023-01-22 19:10:24.564195: step: 1592/529, loss: 0.0041676415130496025
2023-01-22 19:10:25.679346: step: 1596/529, loss: 0.010674137622117996
2023-01-22 19:10:26.769731: step: 1600/529, loss: 0.0014914104249328375
2023-01-22 19:10:27.879552: step: 1604/529, loss: 0.0036897300742566586
2023-01-22 19:10:28.988142: step: 1608/529, loss: 0.007229203823953867
2023-01-22 19:10:30.073737: step: 1612/529, loss: 0.0019751908257603645
2023-01-22 19:10:31.187804: step: 1616/529, loss: 0.009596874006092548
2023-01-22 19:10:32.295093: step: 1620/529, loss: 0.004519632551819086
2023-01-22 19:10:33.408601: step: 1624/529, loss: 0.011144997552037239
2023-01-22 19:10:34.520492: step: 1628/529, loss: 0.005563520826399326
2023-01-22 19:10:35.612529: step: 1632/529, loss: 0.027692407369613647
2023-01-22 19:10:36.716156: step: 1636/529, loss: 0.0023939991369843483
2023-01-22 19:10:37.817104: step: 1640/529, loss: 0.0012472938979044557
2023-01-22 19:10:38.915474: step: 1644/529, loss: 0.011303827166557312
2023-01-22 19:10:40.008898: step: 1648/529, loss: 0.010501573793590069
2023-01-22 19:10:41.123665: step: 1652/529, loss: 0.004100640304386616
2023-01-22 19:10:42.224216: step: 1656/529, loss: 0.008339384570717812
2023-01-22 19:10:43.330223: step: 1660/529, loss: 0.011582618579268456
2023-01-22 19:10:44.449303: step: 1664/529, loss: 0.005339955445379019
2023-01-22 19:10:45.542839: step: 1668/529, loss: 0.0023792346473783255
2023-01-22 19:10:46.650605: step: 1672/529, loss: 0.00461668660864234
2023-01-22 19:10:47.762721: step: 1676/529, loss: 0.03551819920539856
2023-01-22 19:10:48.875008: step: 1680/529, loss: 0.00201983074657619
2023-01-22 19:10:49.961625: step: 1684/529, loss: 0.007052142638713121
2023-01-22 19:10:51.075572: step: 1688/529, loss: 0.007040137890726328
2023-01-22 19:10:52.192151: step: 1692/529, loss: 0.0031473380513489246
2023-01-22 19:10:53.292418: step: 1696/529, loss: 0.014354725368320942
2023-01-22 19:10:54.427549: step: 1700/529, loss: 0.001469269162043929
2023-01-22 19:10:55.526442: step: 1704/529, loss: 0.003306277096271515
2023-01-22 19:10:56.602771: step: 1708/529, loss: 6.649853457929567e-05
2023-01-22 19:10:57.727455: step: 1712/529, loss: 0.0029305091593414545
2023-01-22 19:10:58.822147: step: 1716/529, loss: 0.06696254014968872
2023-01-22 19:10:59.933409: step: 1720/529, loss: 0.0056436811573803425
2023-01-22 19:11:01.042215: step: 1724/529, loss: 0.007862314581871033
2023-01-22 19:11:02.158349: step: 1728/529, loss: 0.001981362234801054
2023-01-22 19:11:03.295519: step: 1732/529, loss: 0.0005357115296646953
2023-01-22 19:11:04.410468: step: 1736/529, loss: 0.0020502007100731134
2023-01-22 19:11:05.512526: step: 1740/529, loss: 0.0066886888816952705
2023-01-22 19:11:06.637529: step: 1744/529, loss: 0.008874895982444286
2023-01-22 19:11:07.776925: step: 1748/529, loss: 0.0013597782235592604
2023-01-22 19:11:08.875843: step: 1752/529, loss: 0.002254927298054099
2023-01-22 19:11:09.985520: step: 1756/529, loss: 0.002668507397174835
2023-01-22 19:11:11.076451: step: 1760/529, loss: 0.004951762966811657
2023-01-22 19:11:12.172873: step: 1764/529, loss: 0.0053134518675506115
2023-01-22 19:11:13.296655: step: 1768/529, loss: 0.008444095030426979
2023-01-22 19:11:14.396661: step: 1772/529, loss: 0.0048981402069330215
2023-01-22 19:11:15.487268: step: 1776/529, loss: 0.002013629302382469
2023-01-22 19:11:16.585348: step: 1780/529, loss: 0.006046490743756294
2023-01-22 19:11:17.698734: step: 1784/529, loss: 0.0023891483433544636
2023-01-22 19:11:18.816553: step: 1788/529, loss: 0.006254952400922775
2023-01-22 19:11:19.916900: step: 1792/529, loss: 0.0017275239806622267
2023-01-22 19:11:21.043357: step: 1796/529, loss: 0.002768761944025755
2023-01-22 19:11:22.150062: step: 1800/529, loss: 0.01100082416087389
2023-01-22 19:11:23.255607: step: 1804/529, loss: 0.0097651407122612
2023-01-22 19:11:24.360205: step: 1808/529, loss: 0.009489976800978184
2023-01-22 19:11:25.475549: step: 1812/529, loss: 0.0043052989058196545
2023-01-22 19:11:26.606035: step: 1816/529, loss: 0.003355396678671241
2023-01-22 19:11:27.718619: step: 1820/529, loss: 0.009334057569503784
2023-01-22 19:11:28.847221: step: 1824/529, loss: 0.009333780035376549
2023-01-22 19:11:29.963597: step: 1828/529, loss: 0.005161263979971409
2023-01-22 19:11:31.055475: step: 1832/529, loss: 0.00623353524133563
2023-01-22 19:11:32.188592: step: 1836/529, loss: 0.014610852114856243
2023-01-22 19:11:33.282565: step: 1840/529, loss: 0.0091658104211092
2023-01-22 19:11:34.410032: step: 1844/529, loss: 0.018840985372662544
2023-01-22 19:11:35.507794: step: 1848/529, loss: 0.006212329957634211
2023-01-22 19:11:36.596071: step: 1852/529, loss: 0.002447352511808276
2023-01-22 19:11:37.695892: step: 1856/529, loss: 0.016949230805039406
2023-01-22 19:11:38.797003: step: 1860/529, loss: 0.005489578004926443
2023-01-22 19:11:39.901673: step: 1864/529, loss: 0.008976762183010578
2023-01-22 19:11:40.985004: step: 1868/529, loss: 0.003297926625236869
2023-01-22 19:11:42.091407: step: 1872/529, loss: 0.005246599670499563
2023-01-22 19:11:43.218017: step: 1876/529, loss: 0.010308386757969856
2023-01-22 19:11:44.313800: step: 1880/529, loss: 0.00042239148751832545
2023-01-22 19:11:45.432293: step: 1884/529, loss: 0.009330831468105316
2023-01-22 19:11:46.542226: step: 1888/529, loss: 0.0014277645386755466
2023-01-22 19:11:47.658151: step: 1892/529, loss: 0.004763399716466665
2023-01-22 19:11:48.776579: step: 1896/529, loss: 0.011139397509396076
2023-01-22 19:11:49.887076: step: 1900/529, loss: 0.005003584083169699
2023-01-22 19:11:50.990685: step: 1904/529, loss: 0.006582403089851141
2023-01-22 19:11:52.102334: step: 1908/529, loss: 0.0018480712315067649
2023-01-22 19:11:53.187511: step: 1912/529, loss: 0.0008753414731472731
2023-01-22 19:11:54.267059: step: 1916/529, loss: 0.0014442336978390813
2023-01-22 19:11:55.374935: step: 1920/529, loss: 0.01727409102022648
2023-01-22 19:11:56.480259: step: 1924/529, loss: 0.011511181481182575
2023-01-22 19:11:57.576885: step: 1928/529, loss: 0.00012517809227574617
2023-01-22 19:11:58.670688: step: 1932/529, loss: 0.004393650684505701
2023-01-22 19:11:59.770471: step: 1936/529, loss: 0.006960937287658453
2023-01-22 19:12:00.894171: step: 1940/529, loss: 0.002801342634484172
2023-01-22 19:12:02.001386: step: 1944/529, loss: 0.005089263431727886
2023-01-22 19:12:03.106373: step: 1948/529, loss: 0.008249325677752495
2023-01-22 19:12:04.211747: step: 1952/529, loss: 0.009227005764842033
2023-01-22 19:12:05.322683: step: 1956/529, loss: 0.003623245283961296
2023-01-22 19:12:06.440067: step: 1960/529, loss: 0.03922535479068756
2023-01-22 19:12:07.559009: step: 1964/529, loss: 0.004454377572983503
2023-01-22 19:12:08.662474: step: 1968/529, loss: 0.047634806483983994
2023-01-22 19:12:09.773041: step: 1972/529, loss: 0.007287457585334778
2023-01-22 19:12:10.879786: step: 1976/529, loss: 0.013993768952786922
2023-01-22 19:12:11.970645: step: 1980/529, loss: 0.0004196054651401937
2023-01-22 19:12:13.069737: step: 1984/529, loss: 0.003994377329945564
2023-01-22 19:12:14.185714: step: 1988/529, loss: 0.013684292323887348
2023-01-22 19:12:15.296258: step: 1992/529, loss: 0.012142702005803585
2023-01-22 19:12:16.400367: step: 1996/529, loss: 0.004128783941268921
2023-01-22 19:12:17.506741: step: 2000/529, loss: 0.006840996909886599
2023-01-22 19:12:18.601480: step: 2004/529, loss: 0.024897616356611252
2023-01-22 19:12:19.720605: step: 2008/529, loss: 0.0038118695374578238
2023-01-22 19:12:20.821670: step: 2012/529, loss: 0.000697502342518419
2023-01-22 19:12:21.925837: step: 2016/529, loss: 0.004093602299690247
2023-01-22 19:12:23.012605: step: 2020/529, loss: 0.0002405818522674963
2023-01-22 19:12:24.112657: step: 2024/529, loss: 0.0002203623007517308
2023-01-22 19:12:25.222703: step: 2028/529, loss: 0.008386366069316864
2023-01-22 19:12:26.328490: step: 2032/529, loss: 0.010255941189825535
2023-01-22 19:12:27.444912: step: 2036/529, loss: 0.001848246669396758
2023-01-22 19:12:28.563939: step: 2040/529, loss: 0.0015120984753593802
2023-01-22 19:12:29.670893: step: 2044/529, loss: 0.0016965073300525546
2023-01-22 19:12:30.780062: step: 2048/529, loss: 0.0006703918916173279
2023-01-22 19:12:31.896505: step: 2052/529, loss: 0.019006190821528435
2023-01-22 19:12:33.001298: step: 2056/529, loss: 0.012485519051551819
2023-01-22 19:12:34.126751: step: 2060/529, loss: 0.0028193420730531216
2023-01-22 19:12:35.235750: step: 2064/529, loss: 0.0033545701298862696
2023-01-22 19:12:36.355291: step: 2068/529, loss: 0.0016799798468127847
2023-01-22 19:12:37.461411: step: 2072/529, loss: 0.0003219117352273315
2023-01-22 19:12:38.576019: step: 2076/529, loss: 0.0012330266181379557
2023-01-22 19:12:39.704191: step: 2080/529, loss: 0.008077512495219707
2023-01-22 19:12:40.813805: step: 2084/529, loss: 0.0036298127379268408
2023-01-22 19:12:41.918985: step: 2088/529, loss: 0.003100254572927952
2023-01-22 19:12:43.009414: step: 2092/529, loss: 0.00027639689506031573
2023-01-22 19:12:44.100451: step: 2096/529, loss: 0.000616960518527776
2023-01-22 19:12:45.209696: step: 2100/529, loss: 0.017584307119250298
2023-01-22 19:12:46.296917: step: 2104/529, loss: 0.0077926889061927795
2023-01-22 19:12:47.396752: step: 2108/529, loss: 0.00510401651263237
2023-01-22 19:12:48.489177: step: 2112/529, loss: 0.06850270181894302
2023-01-22 19:12:49.611370: step: 2116/529, loss: 0.005144988186657429
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33178061224489797, 'r': 0.33052148278666305, 'f1': 0.3311498506246605}, 'combined': 0.2440051530918551, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37472497175443686, 'r': 0.30036447042708325, 'f1': 0.3334493495650352}, 'combined': 0.20494935631802164, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3361919618271108, 'r': 0.3489506700558436, 'f1': 0.3424525197754741}, 'combined': 0.25233343562403354, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35536376159015653, 'r': 0.310096454004582, 'f1': 0.33119047470734625}, 'combined': 0.2035609746981738, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33895857929948836, 'r': 0.34667680121902134, 'f1': 0.34277424810961393}, 'combined': 0.2525704986070839, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3694523995328003, 'r': 0.3003600027370558, 'f1': 0.33134269642913033}, 'combined': 0.20465284191210995, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35185185185185186, 'r': 0.41304347826086957, 'f1': 0.38}, 'combined': 0.19, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 10
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 19:15:17.283875: step: 4/529, loss: 0.00014066699077375233
2023-01-22 19:15:18.378349: step: 8/529, loss: 6.804722215747461e-05
2023-01-22 19:15:19.467484: step: 12/529, loss: 0.007144611328840256
2023-01-22 19:15:20.553668: step: 16/529, loss: 0.0002006435242947191
2023-01-22 19:15:21.671850: step: 20/529, loss: 0.008061826229095459
2023-01-22 19:15:22.771006: step: 24/529, loss: 0.005260359030216932
2023-01-22 19:15:23.887731: step: 28/529, loss: 0.0011097720125690103
2023-01-22 19:15:25.020238: step: 32/529, loss: 0.002329524839296937
2023-01-22 19:15:26.109801: step: 36/529, loss: 4.7850655391812325e-05
2023-01-22 19:15:27.202731: step: 40/529, loss: 0.00406494690105319
2023-01-22 19:15:28.314646: step: 44/529, loss: 0.0009985339129343629
2023-01-22 19:15:29.389380: step: 48/529, loss: 0.006624714005738497
2023-01-22 19:15:30.480445: step: 52/529, loss: 0.00023740004689898342
2023-01-22 19:15:31.579762: step: 56/529, loss: 0.01133043970912695
2023-01-22 19:15:32.706742: step: 60/529, loss: 0.0026419993955641985
2023-01-22 19:15:33.784860: step: 64/529, loss: 0.0002959644771181047
2023-01-22 19:15:34.906398: step: 68/529, loss: 0.002906143432483077
2023-01-22 19:15:36.025255: step: 72/529, loss: 0.0004793589760083705
2023-01-22 19:15:37.122446: step: 76/529, loss: 0.009128259494900703
2023-01-22 19:15:38.262559: step: 80/529, loss: 0.0033187370281666517
2023-01-22 19:15:39.346802: step: 84/529, loss: 0.001691467477940023
2023-01-22 19:15:40.452211: step: 88/529, loss: 0.00849154032766819
2023-01-22 19:15:41.550241: step: 92/529, loss: 0.01052180491387844
2023-01-22 19:15:42.645012: step: 96/529, loss: 0.027855128049850464
2023-01-22 19:15:43.748897: step: 100/529, loss: 0.000742443953640759
2023-01-22 19:15:44.895546: step: 104/529, loss: 0.0006658468046225607
2023-01-22 19:15:46.023554: step: 108/529, loss: 0.008926274254918098
2023-01-22 19:15:47.112430: step: 112/529, loss: 0.0021948402281850576
2023-01-22 19:15:48.234256: step: 116/529, loss: 0.004141767509281635
2023-01-22 19:15:49.342946: step: 120/529, loss: 0.016386695206165314
2023-01-22 19:15:50.432096: step: 124/529, loss: 0.0030487675685435534
2023-01-22 19:15:51.554847: step: 128/529, loss: 0.0036591063253581524
2023-01-22 19:15:52.669897: step: 132/529, loss: 0.006724723614752293
2023-01-22 19:15:53.843270: step: 136/529, loss: 0.0007174345082603395
2023-01-22 19:15:54.954907: step: 140/529, loss: 0.0014685202622786164
2023-01-22 19:15:56.045736: step: 144/529, loss: 0.0004873551370110363
2023-01-22 19:15:57.155890: step: 148/529, loss: 0.0033629818353801966
2023-01-22 19:15:58.295546: step: 152/529, loss: 0.00596148194745183
2023-01-22 19:15:59.401152: step: 156/529, loss: 0.002383374609053135
2023-01-22 19:16:00.496786: step: 160/529, loss: 0.008389468304812908
2023-01-22 19:16:01.615711: step: 164/529, loss: 0.0028305177111178637
2023-01-22 19:16:02.715353: step: 168/529, loss: 0.02574547380208969
2023-01-22 19:16:03.804594: step: 172/529, loss: 4.863203866989352e-05
2023-01-22 19:16:04.888773: step: 176/529, loss: 0.005315895192325115
2023-01-22 19:16:05.994681: step: 180/529, loss: 0.015754589810967445
2023-01-22 19:16:07.117039: step: 184/529, loss: 0.0009819060796871781
2023-01-22 19:16:08.210314: step: 188/529, loss: 0.011542145162820816
2023-01-22 19:16:09.311630: step: 192/529, loss: 0.011502913199365139
2023-01-22 19:16:10.429180: step: 196/529, loss: 0.001410657074302435
2023-01-22 19:16:11.536982: step: 200/529, loss: 0.004170591477304697
2023-01-22 19:16:12.635439: step: 204/529, loss: 0.002422420075163245
2023-01-22 19:16:13.748401: step: 208/529, loss: 0.007114346604794264
2023-01-22 19:16:14.855123: step: 212/529, loss: 0.018315928056836128
2023-01-22 19:16:15.962664: step: 216/529, loss: 0.005528508685529232
2023-01-22 19:16:17.077766: step: 220/529, loss: 0.007643497083336115
2023-01-22 19:16:18.192857: step: 224/529, loss: 0.0023897422943264246
2023-01-22 19:16:19.320195: step: 228/529, loss: 0.0034760087728500366
2023-01-22 19:16:20.419416: step: 232/529, loss: 0.011766092851758003
2023-01-22 19:16:21.506290: step: 236/529, loss: 0.0009508852963335812
2023-01-22 19:16:22.597570: step: 240/529, loss: 0.004056363832205534
2023-01-22 19:16:23.723289: step: 244/529, loss: 0.0011971058556810021
2023-01-22 19:16:24.834013: step: 248/529, loss: 0.011388525366783142
2023-01-22 19:16:25.908135: step: 252/529, loss: 0.0016499351477250457
2023-01-22 19:16:27.022971: step: 256/529, loss: 0.004142810590565205
2023-01-22 19:16:28.134231: step: 260/529, loss: 0.0025163902901113033
2023-01-22 19:16:29.261581: step: 264/529, loss: 0.005788113456219435
2023-01-22 19:16:30.374932: step: 268/529, loss: 0.006758593022823334
2023-01-22 19:16:31.477059: step: 272/529, loss: 0.00033913305378519
2023-01-22 19:16:32.612682: step: 276/529, loss: 0.007300782483071089
2023-01-22 19:16:33.726344: step: 280/529, loss: 0.013562587089836597
2023-01-22 19:16:34.831048: step: 284/529, loss: 0.0014538648538291454
2023-01-22 19:16:35.934431: step: 288/529, loss: 0.0005513126961886883
2023-01-22 19:16:37.035833: step: 292/529, loss: 0.004913745913654566
2023-01-22 19:16:38.160239: step: 296/529, loss: 0.009528543800115585
2023-01-22 19:16:39.239737: step: 300/529, loss: 0.0005764710949733853
2023-01-22 19:16:40.379877: step: 304/529, loss: 0.002948667388409376
2023-01-22 19:16:41.468851: step: 308/529, loss: 0.00105380080640316
2023-01-22 19:16:42.574591: step: 312/529, loss: 0.0009540129103697836
2023-01-22 19:16:43.677055: step: 316/529, loss: 0.005260543432086706
2023-01-22 19:16:44.796325: step: 320/529, loss: 0.003926956094801426
2023-01-22 19:16:45.871073: step: 324/529, loss: 0.0006715389317832887
2023-01-22 19:16:46.964792: step: 328/529, loss: 0.01817171461880207
2023-01-22 19:16:48.076678: step: 332/529, loss: 0.004444970283657312
2023-01-22 19:16:49.207960: step: 336/529, loss: 0.00256772106513381
2023-01-22 19:16:50.322836: step: 340/529, loss: 0.012765337713062763
2023-01-22 19:16:51.400910: step: 344/529, loss: 0.004169865977019072
2023-01-22 19:16:52.477582: step: 348/529, loss: 0.01905876398086548
2023-01-22 19:16:53.589040: step: 352/529, loss: 0.005085855722427368
2023-01-22 19:16:54.692818: step: 356/529, loss: 0.001628398080356419
2023-01-22 19:16:55.811899: step: 360/529, loss: 0.005859238561242819
2023-01-22 19:16:56.928067: step: 364/529, loss: 0.0018615691224113107
2023-01-22 19:16:58.025378: step: 368/529, loss: 0.0006174053996801376
2023-01-22 19:16:59.159705: step: 372/529, loss: 0.00788771454244852
2023-01-22 19:17:00.261699: step: 376/529, loss: 0.0025621491950005293
2023-01-22 19:17:01.362186: step: 380/529, loss: 0.0005735280574299395
2023-01-22 19:17:02.469678: step: 384/529, loss: 0.002404374536126852
2023-01-22 19:17:03.577370: step: 388/529, loss: 0.0036898041144013405
2023-01-22 19:17:04.668688: step: 392/529, loss: 0.00010659175313776359
2023-01-22 19:17:05.782739: step: 396/529, loss: 0.00033455833909101784
2023-01-22 19:17:06.879317: step: 400/529, loss: 0.0048098755069077015
2023-01-22 19:17:08.010784: step: 404/529, loss: 0.001305817742832005
2023-01-22 19:17:09.106956: step: 408/529, loss: 0.003557774471119046
2023-01-22 19:17:10.220978: step: 412/529, loss: 0.0022564949467778206
2023-01-22 19:17:11.338098: step: 416/529, loss: 0.004168667830526829
2023-01-22 19:17:12.433149: step: 420/529, loss: 0.0007751243538223207
2023-01-22 19:17:13.546724: step: 424/529, loss: 0.0010004036594182253
2023-01-22 19:17:14.652148: step: 428/529, loss: 0.000813534832559526
2023-01-22 19:17:15.764240: step: 432/529, loss: 0.010044993832707405
2023-01-22 19:17:16.903573: step: 436/529, loss: 0.0059012179262936115
2023-01-22 19:17:18.004782: step: 440/529, loss: 0.0020030431915074587
2023-01-22 19:17:19.116896: step: 444/529, loss: 0.0006674128817394376
2023-01-22 19:17:20.240046: step: 448/529, loss: 0.0025878131855279207
2023-01-22 19:17:21.361550: step: 452/529, loss: 0.003642268246039748
2023-01-22 19:17:22.480604: step: 456/529, loss: 0.007925009354948997
2023-01-22 19:17:23.610146: step: 460/529, loss: 8.282779162982479e-05
2023-01-22 19:17:24.709803: step: 464/529, loss: 0.006399889476597309
2023-01-22 19:17:25.830075: step: 468/529, loss: 0.002955260220915079
2023-01-22 19:17:26.935179: step: 472/529, loss: 0.0017032220494002104
2023-01-22 19:17:28.043426: step: 476/529, loss: 0.0058366963639855385
2023-01-22 19:17:29.143685: step: 480/529, loss: 0.0066220504231750965
2023-01-22 19:17:30.257821: step: 484/529, loss: 0.0007051354041323066
2023-01-22 19:17:31.369873: step: 488/529, loss: 0.003883779514580965
2023-01-22 19:17:32.508690: step: 492/529, loss: 0.008248812519013882
2023-01-22 19:17:33.616486: step: 496/529, loss: 0.0013648374006152153
2023-01-22 19:17:34.724084: step: 500/529, loss: 0.005969061050564051
2023-01-22 19:17:35.835451: step: 504/529, loss: 0.008295079693198204
2023-01-22 19:17:36.934388: step: 508/529, loss: 0.001758683705702424
2023-01-22 19:17:38.052502: step: 512/529, loss: 0.014007318764925003
2023-01-22 19:17:39.185987: step: 516/529, loss: 0.0018363615963608027
2023-01-22 19:17:40.297422: step: 520/529, loss: 0.005349340848624706
2023-01-22 19:17:41.420290: step: 524/529, loss: 0.0026836220640689135
2023-01-22 19:17:42.519849: step: 528/529, loss: 0.00022390381491277367
2023-01-22 19:17:43.659714: step: 532/529, loss: 0.002677630167454481
2023-01-22 19:17:44.745267: step: 536/529, loss: 0.0013838220620527864
2023-01-22 19:17:45.843179: step: 540/529, loss: 0.0008319858461618423
2023-01-22 19:17:46.950382: step: 544/529, loss: 0.0036801432725042105
2023-01-22 19:17:48.061324: step: 548/529, loss: 0.004043183755129576
2023-01-22 19:17:49.182489: step: 552/529, loss: 0.003895303001627326
2023-01-22 19:17:50.285564: step: 556/529, loss: 0.003321310505270958
2023-01-22 19:17:51.395921: step: 560/529, loss: 0.008743378333747387
2023-01-22 19:17:52.481783: step: 564/529, loss: 0.004023090936243534
2023-01-22 19:17:53.598608: step: 568/529, loss: 0.009847203269600868
2023-01-22 19:17:54.706993: step: 572/529, loss: 0.005047728773206472
2023-01-22 19:17:55.799586: step: 576/529, loss: 0.004513503052294254
2023-01-22 19:17:56.893720: step: 580/529, loss: 0.0016682291170582175
2023-01-22 19:17:58.008729: step: 584/529, loss: 0.001351230894215405
2023-01-22 19:17:59.117744: step: 588/529, loss: 0.0002922937856055796
2023-01-22 19:18:00.216858: step: 592/529, loss: 0.0061531090177595615
2023-01-22 19:18:01.318330: step: 596/529, loss: 0.0029740040190517902
2023-01-22 19:18:02.442522: step: 600/529, loss: 0.0024397841189056635
2023-01-22 19:18:03.546357: step: 604/529, loss: 0.001254424569196999
2023-01-22 19:18:04.648775: step: 608/529, loss: 0.0013636890798807144
2023-01-22 19:18:05.762891: step: 612/529, loss: 0.001084949355572462
2023-01-22 19:18:06.850168: step: 616/529, loss: 2.5542514777043834e-05
2023-01-22 19:18:07.966781: step: 620/529, loss: 0.002615207340568304
2023-01-22 19:18:09.077692: step: 624/529, loss: 0.00659587187692523
2023-01-22 19:18:10.201961: step: 628/529, loss: 0.0029926938004791737
2023-01-22 19:18:11.312331: step: 632/529, loss: 0.006990282330662012
2023-01-22 19:18:12.415885: step: 636/529, loss: 0.009059948846697807
2023-01-22 19:18:13.523678: step: 640/529, loss: 0.007853774353861809
2023-01-22 19:18:14.641851: step: 644/529, loss: 0.003246077336370945
2023-01-22 19:18:15.743112: step: 648/529, loss: 0.0021399124525487423
2023-01-22 19:18:16.860054: step: 652/529, loss: 0.0015789818717166781
2023-01-22 19:18:17.969028: step: 656/529, loss: 0.00551167456433177
2023-01-22 19:18:19.080816: step: 660/529, loss: 0.0038017481565475464
2023-01-22 19:18:20.189214: step: 664/529, loss: 0.015864379703998566
2023-01-22 19:18:21.289702: step: 668/529, loss: 0.02462594583630562
2023-01-22 19:18:22.378761: step: 672/529, loss: 0.0037727653980255127
2023-01-22 19:18:23.478945: step: 676/529, loss: 0.0011074565118178725
2023-01-22 19:18:24.613928: step: 680/529, loss: 0.0018161415355280042
2023-01-22 19:18:25.709969: step: 684/529, loss: 0.0012065795017406344
2023-01-22 19:18:26.803902: step: 688/529, loss: 0.0020751527044922113
2023-01-22 19:18:27.911947: step: 692/529, loss: 0.001213929965160787
2023-01-22 19:18:29.024802: step: 696/529, loss: 0.00249796942807734
2023-01-22 19:18:30.148995: step: 700/529, loss: 0.00019309222989249974
2023-01-22 19:18:31.250020: step: 704/529, loss: 0.0005429618177004158
2023-01-22 19:18:32.374356: step: 708/529, loss: 0.020188502967357635
2023-01-22 19:18:33.474812: step: 712/529, loss: 0.004486955236643553
2023-01-22 19:18:34.577992: step: 716/529, loss: 0.0032540129031986
2023-01-22 19:18:35.693838: step: 720/529, loss: 0.00016577863425482064
2023-01-22 19:18:36.793856: step: 724/529, loss: 0.003164031310006976
2023-01-22 19:18:37.898405: step: 728/529, loss: 0.0058807688765227795
2023-01-22 19:18:39.022125: step: 732/529, loss: 0.0024319204967468977
2023-01-22 19:18:40.116848: step: 736/529, loss: 0.0015095642302185297
2023-01-22 19:18:41.228931: step: 740/529, loss: 0.011623300611972809
2023-01-22 19:18:42.335954: step: 744/529, loss: 0.0029770415276288986
2023-01-22 19:18:43.421107: step: 748/529, loss: 0.0017354115843772888
2023-01-22 19:18:44.519004: step: 752/529, loss: 0.0014948470052331686
2023-01-22 19:18:45.632953: step: 756/529, loss: 0.008451261557638645
2023-01-22 19:18:46.710614: step: 760/529, loss: 0.01382976770401001
2023-01-22 19:18:47.830392: step: 764/529, loss: 0.006939781829714775
2023-01-22 19:18:48.971624: step: 768/529, loss: 0.03109847754240036
2023-01-22 19:18:50.084500: step: 772/529, loss: 0.004628642462193966
2023-01-22 19:18:51.173003: step: 776/529, loss: 0.006465520244091749
2023-01-22 19:18:52.271362: step: 780/529, loss: 0.0008791473228484392
2023-01-22 19:18:53.399161: step: 784/529, loss: 0.031057298183441162
2023-01-22 19:18:54.504831: step: 788/529, loss: 0.003810094902291894
2023-01-22 19:18:55.598740: step: 792/529, loss: 0.0015693034511059523
2023-01-22 19:18:56.708025: step: 796/529, loss: 0.0007189961615949869
2023-01-22 19:18:57.828470: step: 800/529, loss: 0.008132641203701496
2023-01-22 19:18:58.929096: step: 804/529, loss: 0.00201398110948503
2023-01-22 19:19:00.043082: step: 808/529, loss: 0.003772712778300047
2023-01-22 19:19:01.139080: step: 812/529, loss: 0.0010151639580726624
2023-01-22 19:19:02.242658: step: 816/529, loss: 0.00570036331191659
2023-01-22 19:19:03.378735: step: 820/529, loss: 0.0028964008670300245
2023-01-22 19:19:04.467130: step: 824/529, loss: 0.0010831697145476937
2023-01-22 19:19:05.567404: step: 828/529, loss: 0.0027090804651379585
2023-01-22 19:19:06.677364: step: 832/529, loss: 0.004136858507990837
2023-01-22 19:19:07.780669: step: 836/529, loss: 0.0049913739785552025
2023-01-22 19:19:08.881355: step: 840/529, loss: 0.0033293762244284153
2023-01-22 19:19:10.035792: step: 844/529, loss: 0.004989622626453638
2023-01-22 19:19:11.137741: step: 848/529, loss: 0.0046120393089950085
2023-01-22 19:19:12.259841: step: 852/529, loss: 0.00783604010939598
2023-01-22 19:19:13.374897: step: 856/529, loss: 0.008817343972623348
2023-01-22 19:19:14.479879: step: 860/529, loss: 0.0012536334106698632
2023-01-22 19:19:15.605986: step: 864/529, loss: 0.0007285188767127693
2023-01-22 19:19:16.724325: step: 868/529, loss: 0.011100014671683311
2023-01-22 19:19:17.821084: step: 872/529, loss: 0.012568839825689793
2023-01-22 19:19:18.932975: step: 876/529, loss: 0.003599324496462941
2023-01-22 19:19:20.047363: step: 880/529, loss: 0.0023192751687020063
2023-01-22 19:19:21.169432: step: 884/529, loss: 0.003987746778875589
2023-01-22 19:19:22.287461: step: 888/529, loss: 0.006785211153328419
2023-01-22 19:19:23.405837: step: 892/529, loss: 0.005245667416602373
2023-01-22 19:19:24.509966: step: 896/529, loss: 0.001611137529835105
2023-01-22 19:19:25.621973: step: 900/529, loss: 0.0020552293863147497
2023-01-22 19:19:26.707330: step: 904/529, loss: 0.03360049054026604
2023-01-22 19:19:27.826213: step: 908/529, loss: 0.009339140728116035
2023-01-22 19:19:28.923225: step: 912/529, loss: 0.0027816693764179945
2023-01-22 19:19:30.058732: step: 916/529, loss: 0.006510804872959852
2023-01-22 19:19:31.150812: step: 920/529, loss: 0.0011626067571341991
2023-01-22 19:19:32.257206: step: 924/529, loss: 0.006616579368710518
2023-01-22 19:19:33.383559: step: 928/529, loss: 0.001994227059185505
2023-01-22 19:19:34.488398: step: 932/529, loss: 0.004685595631599426
2023-01-22 19:19:35.585151: step: 936/529, loss: 0.00412451708689332
2023-01-22 19:19:36.689137: step: 940/529, loss: 0.0052533987909555435
2023-01-22 19:19:37.803362: step: 944/529, loss: 0.004642639309167862
2023-01-22 19:19:38.923072: step: 948/529, loss: 8.168735075742006e-05
2023-01-22 19:19:40.024060: step: 952/529, loss: 0.00092249148292467
2023-01-22 19:19:41.134791: step: 956/529, loss: 0.00235861842520535
2023-01-22 19:19:42.266909: step: 960/529, loss: 0.030054334551095963
2023-01-22 19:19:43.385197: step: 964/529, loss: 0.0011185595067217946
2023-01-22 19:19:44.493226: step: 968/529, loss: 0.0020445131231099367
2023-01-22 19:19:45.611209: step: 972/529, loss: 0.00395802641287446
2023-01-22 19:19:46.722948: step: 976/529, loss: 0.011483406648039818
2023-01-22 19:19:47.836506: step: 980/529, loss: 0.003362680319696665
2023-01-22 19:19:48.945882: step: 984/529, loss: 0.0029373872093856335
2023-01-22 19:19:50.047695: step: 988/529, loss: 0.0008233357220888138
2023-01-22 19:19:51.167025: step: 992/529, loss: 0.007795578800141811
2023-01-22 19:19:52.262714: step: 996/529, loss: 0.00022003796766512096
2023-01-22 19:19:53.395655: step: 1000/529, loss: 0.003951712045818567
2023-01-22 19:19:54.484157: step: 1004/529, loss: 0.006149396300315857
2023-01-22 19:19:55.591294: step: 1008/529, loss: 0.006995068397372961
2023-01-22 19:19:56.678654: step: 1012/529, loss: 0.009835072793066502
2023-01-22 19:19:57.786015: step: 1016/529, loss: 0.0022883054334670305
2023-01-22 19:19:58.898584: step: 1020/529, loss: 0.005302901845425367
2023-01-22 19:20:00.012725: step: 1024/529, loss: 0.03129454329609871
2023-01-22 19:20:01.111524: step: 1028/529, loss: 0.0014231225941330194
2023-01-22 19:20:02.212856: step: 1032/529, loss: 0.0003283943224232644
2023-01-22 19:20:03.325942: step: 1036/529, loss: 0.006184760015457869
2023-01-22 19:20:04.452568: step: 1040/529, loss: 0.006263521034270525
2023-01-22 19:20:05.555684: step: 1044/529, loss: 0.0016147817950695753
2023-01-22 19:20:06.680150: step: 1048/529, loss: 0.007773539982736111
2023-01-22 19:20:07.771006: step: 1052/529, loss: 0.01164105162024498
2023-01-22 19:20:08.881321: step: 1056/529, loss: 0.0048789698630571365
2023-01-22 19:20:09.972573: step: 1060/529, loss: 0.0010418322635814548
2023-01-22 19:20:11.090394: step: 1064/529, loss: 0.009207838214933872
2023-01-22 19:20:12.182873: step: 1068/529, loss: 0.007035735063254833
2023-01-22 19:20:13.273953: step: 1072/529, loss: 0.003296822775155306
2023-01-22 19:20:14.369915: step: 1076/529, loss: 2.4164819478755817e-05
2023-01-22 19:20:15.482769: step: 1080/529, loss: 0.0007315662805922329
2023-01-22 19:20:16.599096: step: 1084/529, loss: 0.0038923739921301603
2023-01-22 19:20:17.696004: step: 1088/529, loss: 0.006251499056816101
2023-01-22 19:20:18.795836: step: 1092/529, loss: 0.00013339155702851713
2023-01-22 19:20:19.885170: step: 1096/529, loss: 0.00040758305112831295
2023-01-22 19:20:20.997486: step: 1100/529, loss: 0.000778841960709542
2023-01-22 19:20:22.093446: step: 1104/529, loss: 0.008138620294630527
2023-01-22 19:20:23.198997: step: 1108/529, loss: 0.0003479059669189155
2023-01-22 19:20:24.309419: step: 1112/529, loss: 0.0006827504257671535
2023-01-22 19:20:25.383269: step: 1116/529, loss: 0.0015229344135150313
2023-01-22 19:20:26.477212: step: 1120/529, loss: 0.005617843009531498
2023-01-22 19:20:27.583635: step: 1124/529, loss: 0.0029102216940373182
2023-01-22 19:20:28.701100: step: 1128/529, loss: 0.0023615192621946335
2023-01-22 19:20:29.805343: step: 1132/529, loss: 0.003164583118632436
2023-01-22 19:20:30.901263: step: 1136/529, loss: 0.0028596746269613504
2023-01-22 19:20:32.002029: step: 1140/529, loss: 0.004839289467781782
2023-01-22 19:20:33.124982: step: 1144/529, loss: 0.005066284444183111
2023-01-22 19:20:34.230057: step: 1148/529, loss: 0.006997893564403057
2023-01-22 19:20:35.354537: step: 1152/529, loss: 0.0041889953427016735
2023-01-22 19:20:36.462688: step: 1156/529, loss: 0.0067227184772491455
2023-01-22 19:20:37.566539: step: 1160/529, loss: 0.011504698544740677
2023-01-22 19:20:38.662279: step: 1164/529, loss: 0.009526612237095833
2023-01-22 19:20:39.767470: step: 1168/529, loss: 0.0007159090018831193
2023-01-22 19:20:40.862424: step: 1172/529, loss: 0.002992949215695262
2023-01-22 19:20:41.965670: step: 1176/529, loss: 0.00432601198554039
2023-01-22 19:20:43.089736: step: 1180/529, loss: 0.004364124499261379
2023-01-22 19:20:44.201527: step: 1184/529, loss: 0.0006833907100372016
2023-01-22 19:20:45.297173: step: 1188/529, loss: 0.0032942513935267925
2023-01-22 19:20:46.394616: step: 1192/529, loss: 0.0069978623650968075
2023-01-22 19:20:47.516493: step: 1196/529, loss: 0.0009046870400197804
2023-01-22 19:20:48.614877: step: 1200/529, loss: 0.0021494224201887846
2023-01-22 19:20:49.726111: step: 1204/529, loss: 0.06519996374845505
2023-01-22 19:20:50.835626: step: 1208/529, loss: 0.00959350261837244
2023-01-22 19:20:51.929605: step: 1212/529, loss: 0.01464216411113739
2023-01-22 19:20:53.041475: step: 1216/529, loss: 0.011363436467945576
2023-01-22 19:20:54.179465: step: 1220/529, loss: 0.016761422157287598
2023-01-22 19:20:55.286562: step: 1224/529, loss: 0.01099938340485096
2023-01-22 19:20:56.382291: step: 1228/529, loss: 0.0030593248084187508
2023-01-22 19:20:57.492107: step: 1232/529, loss: 0.016539357602596283
2023-01-22 19:20:58.593789: step: 1236/529, loss: 0.05035647749900818
2023-01-22 19:20:59.702367: step: 1240/529, loss: 0.008927545510232449
2023-01-22 19:21:00.804162: step: 1244/529, loss: 0.0019050062401220202
2023-01-22 19:21:01.936933: step: 1248/529, loss: 0.007214971352368593
2023-01-22 19:21:03.048331: step: 1252/529, loss: 0.006051830481737852
2023-01-22 19:21:04.160133: step: 1256/529, loss: 0.0014903438277542591
2023-01-22 19:21:05.277922: step: 1260/529, loss: 0.00043756101513281465
2023-01-22 19:21:06.372011: step: 1264/529, loss: 0.0032073138281702995
2023-01-22 19:21:07.470510: step: 1268/529, loss: 0.0021619040053337812
2023-01-22 19:21:08.558148: step: 1272/529, loss: 7.138351065805182e-05
2023-01-22 19:21:09.675817: step: 1276/529, loss: 0.016567518934607506
2023-01-22 19:21:10.784020: step: 1280/529, loss: 0.0008126603788696229
2023-01-22 19:21:11.899317: step: 1284/529, loss: 0.0022804513573646545
2023-01-22 19:21:12.992195: step: 1288/529, loss: 0.007368456106632948
2023-01-22 19:21:14.118099: step: 1292/529, loss: 0.004361659288406372
2023-01-22 19:21:15.247193: step: 1296/529, loss: 0.0013874147552996874
2023-01-22 19:21:16.357187: step: 1300/529, loss: 0.0015606442466378212
2023-01-22 19:21:17.484679: step: 1304/529, loss: 0.004548514727503061
2023-01-22 19:21:18.601820: step: 1308/529, loss: 0.01393069326877594
2023-01-22 19:21:19.719286: step: 1312/529, loss: 0.00254705804400146
2023-01-22 19:21:20.814706: step: 1316/529, loss: 0.0019660783000290394
2023-01-22 19:21:21.885899: step: 1320/529, loss: 0.002159697934985161
2023-01-22 19:21:22.979137: step: 1324/529, loss: 0.0006825807504355907
2023-01-22 19:21:24.097430: step: 1328/529, loss: 0.0034086888190358877
2023-01-22 19:21:25.200365: step: 1332/529, loss: 0.002815220272168517
2023-01-22 19:21:26.347069: step: 1336/529, loss: 0.005541335325688124
2023-01-22 19:21:27.431501: step: 1340/529, loss: 0.012482447549700737
2023-01-22 19:21:28.554692: step: 1344/529, loss: 0.0077318670228123665
2023-01-22 19:21:29.656941: step: 1348/529, loss: 0.005491401068866253
2023-01-22 19:21:30.802601: step: 1352/529, loss: 0.014446879737079144
2023-01-22 19:21:31.931492: step: 1356/529, loss: 0.0033122741151601076
2023-01-22 19:21:33.030609: step: 1360/529, loss: 0.0002267425152240321
2023-01-22 19:21:34.139320: step: 1364/529, loss: 0.008907677605748177
2023-01-22 19:21:35.234540: step: 1368/529, loss: 0.004636609926819801
2023-01-22 19:21:36.326325: step: 1372/529, loss: 0.004368450026959181
2023-01-22 19:21:37.450146: step: 1376/529, loss: 0.001231278874911368
2023-01-22 19:21:38.565627: step: 1380/529, loss: 0.003768891328945756
2023-01-22 19:21:39.674773: step: 1384/529, loss: 0.005708478856831789
2023-01-22 19:21:40.771349: step: 1388/529, loss: 0.003974672872573137
2023-01-22 19:21:41.899774: step: 1392/529, loss: 0.0020599307026714087
2023-01-22 19:21:43.001916: step: 1396/529, loss: 0.0050084348767995834
2023-01-22 19:21:44.098672: step: 1400/529, loss: 0.004200869705528021
2023-01-22 19:21:45.188887: step: 1404/529, loss: 0.004128196742385626
2023-01-22 19:21:46.300941: step: 1408/529, loss: 0.0002895516809076071
2023-01-22 19:21:47.386531: step: 1412/529, loss: 0.0020509089808911085
2023-01-22 19:21:48.494050: step: 1416/529, loss: 0.005778855178505182
2023-01-22 19:21:49.586177: step: 1420/529, loss: 0.005256418604403734
2023-01-22 19:21:50.733976: step: 1424/529, loss: 0.04043223336338997
2023-01-22 19:21:51.843219: step: 1428/529, loss: 8.14585447983518e-08
2023-01-22 19:21:52.940362: step: 1432/529, loss: 0.005672309547662735
2023-01-22 19:21:54.066668: step: 1436/529, loss: 0.003921144176274538
2023-01-22 19:21:55.188527: step: 1440/529, loss: 0.01918674260377884
2023-01-22 19:21:56.288859: step: 1444/529, loss: 0.01670699007809162
2023-01-22 19:21:57.412075: step: 1448/529, loss: 0.0056404490023851395
2023-01-22 19:21:58.534831: step: 1452/529, loss: 0.006281205918639898
2023-01-22 19:21:59.642980: step: 1456/529, loss: 0.0015719493385404348
2023-01-22 19:22:00.738663: step: 1460/529, loss: 0.0008468436426483095
2023-01-22 19:22:01.886641: step: 1464/529, loss: 0.012255445122718811
2023-01-22 19:22:02.984065: step: 1468/529, loss: 0.012468352913856506
2023-01-22 19:22:04.090462: step: 1472/529, loss: 0.008524143137037754
2023-01-22 19:22:05.183246: step: 1476/529, loss: 0.011128108017146587
2023-01-22 19:22:06.291162: step: 1480/529, loss: 0.0017354199662804604
2023-01-22 19:22:07.383856: step: 1484/529, loss: 0.0018120865570381284
2023-01-22 19:22:08.466544: step: 1488/529, loss: 0.0022514646407216787
2023-01-22 19:22:09.590701: step: 1492/529, loss: 0.004379614256322384
2023-01-22 19:22:10.731458: step: 1496/529, loss: 0.002164768986403942
2023-01-22 19:22:11.829898: step: 1500/529, loss: 0.0024084909819066525
2023-01-22 19:22:12.940844: step: 1504/529, loss: 0.003927608486264944
2023-01-22 19:22:14.086084: step: 1508/529, loss: 0.0009050379740074277
2023-01-22 19:22:15.207182: step: 1512/529, loss: 0.002371875336393714
2023-01-22 19:22:16.316551: step: 1516/529, loss: 0.006972091738134623
2023-01-22 19:22:17.405480: step: 1520/529, loss: 0.015984030440449715
2023-01-22 19:22:18.521557: step: 1524/529, loss: 0.00791555643081665
2023-01-22 19:22:19.606308: step: 1528/529, loss: 3.0780862289248034e-05
2023-01-22 19:22:20.697448: step: 1532/529, loss: 0.005594571121037006
2023-01-22 19:22:21.803219: step: 1536/529, loss: 0.0028753369115293026
2023-01-22 19:22:22.906439: step: 1540/529, loss: 0.0027244416996836662
2023-01-22 19:22:24.007529: step: 1544/529, loss: 0.0006780403782613575
2023-01-22 19:22:25.101811: step: 1548/529, loss: 0.001308053731918335
2023-01-22 19:22:26.204935: step: 1552/529, loss: 0.005350498482584953
2023-01-22 19:22:27.307874: step: 1556/529, loss: 0.00045887118903920054
2023-01-22 19:22:28.410273: step: 1560/529, loss: 0.0008210574160329998
2023-01-22 19:22:29.523918: step: 1564/529, loss: 0.0014283667551353574
2023-01-22 19:22:30.623388: step: 1568/529, loss: 0.0033723702654242516
2023-01-22 19:22:31.727253: step: 1572/529, loss: 0.0003330713661853224
2023-01-22 19:22:32.857131: step: 1576/529, loss: 0.0032891619484871626
2023-01-22 19:22:33.953798: step: 1580/529, loss: 0.0007278310367837548
2023-01-22 19:22:35.047429: step: 1584/529, loss: 0.003239043988287449
2023-01-22 19:22:36.156246: step: 1588/529, loss: 0.0015649964334443212
2023-01-22 19:22:37.245861: step: 1592/529, loss: 0.0017161876894533634
2023-01-22 19:22:38.360622: step: 1596/529, loss: 0.0027427058666944504
2023-01-22 19:22:39.449973: step: 1600/529, loss: 0.000109870896267239
2023-01-22 19:22:40.573683: step: 1604/529, loss: 0.008840505965054035
2023-01-22 19:22:41.688356: step: 1608/529, loss: 0.0043314662761986256
2023-01-22 19:22:42.807809: step: 1612/529, loss: 0.00044054878526367247
2023-01-22 19:22:43.890935: step: 1616/529, loss: 3.8303591281874105e-05
2023-01-22 19:22:45.006904: step: 1620/529, loss: 0.015765313059091568
2023-01-22 19:22:46.094656: step: 1624/529, loss: 0.010190917178988457
2023-01-22 19:22:47.196623: step: 1628/529, loss: 0.003241418395191431
2023-01-22 19:22:48.293977: step: 1632/529, loss: 0.004772573243826628
2023-01-22 19:22:49.413053: step: 1636/529, loss: 0.001373734325170517
2023-01-22 19:22:50.531769: step: 1640/529, loss: 0.0017684214981272817
2023-01-22 19:22:51.636522: step: 1644/529, loss: 0.00039553537499159575
2023-01-22 19:22:52.744879: step: 1648/529, loss: 0.007489887531846762
2023-01-22 19:22:53.856581: step: 1652/529, loss: 0.006042259745299816
2023-01-22 19:22:54.967858: step: 1656/529, loss: 0.0007259639678522944
2023-01-22 19:22:56.071394: step: 1660/529, loss: 0.0008213031105697155
2023-01-22 19:22:57.168634: step: 1664/529, loss: 0.016987815499305725
2023-01-22 19:22:58.277529: step: 1668/529, loss: 0.02598005346953869
2023-01-22 19:22:59.385146: step: 1672/529, loss: 0.011696085333824158
2023-01-22 19:23:00.489794: step: 1676/529, loss: 0.007905970327556133
2023-01-22 19:23:01.622437: step: 1680/529, loss: 0.004529423546046019
2023-01-22 19:23:02.719211: step: 1684/529, loss: 0.003708254313096404
2023-01-22 19:23:03.832216: step: 1688/529, loss: 0.0033165302593261003
2023-01-22 19:23:04.966317: step: 1692/529, loss: 0.0038341544568538666
2023-01-22 19:23:06.112898: step: 1696/529, loss: 0.012603913433849812
2023-01-22 19:23:07.238747: step: 1700/529, loss: 0.0002838079526554793
2023-01-22 19:23:08.350487: step: 1704/529, loss: 0.0024313030298799276
2023-01-22 19:23:09.462063: step: 1708/529, loss: 0.0018001944990828633
2023-01-22 19:23:10.565536: step: 1712/529, loss: 0.013044815510511398
2023-01-22 19:23:11.672470: step: 1716/529, loss: 0.006613976322114468
2023-01-22 19:23:12.794175: step: 1720/529, loss: 0.0006235204637050629
2023-01-22 19:23:13.886574: step: 1724/529, loss: 0.004450184293091297
2023-01-22 19:23:15.004937: step: 1728/529, loss: 0.009699058718979359
2023-01-22 19:23:16.108716: step: 1732/529, loss: 0.015105639584362507
2023-01-22 19:23:17.206708: step: 1736/529, loss: 0.006358313374221325
2023-01-22 19:23:18.286074: step: 1740/529, loss: 0.010097693651914597
2023-01-22 19:23:19.409266: step: 1744/529, loss: 0.000390678527764976
2023-01-22 19:23:20.521583: step: 1748/529, loss: 0.0016387834912166
2023-01-22 19:23:21.631857: step: 1752/529, loss: 0.005541583988815546
2023-01-22 19:23:22.740156: step: 1756/529, loss: 0.0014011363964527845
2023-01-22 19:23:23.845358: step: 1760/529, loss: 0.0023862060625106096
2023-01-22 19:23:24.944543: step: 1764/529, loss: 0.012335315346717834
2023-01-22 19:23:26.063285: step: 1768/529, loss: 0.009803946129977703
2023-01-22 19:23:27.196590: step: 1772/529, loss: 0.0059935241006314754
2023-01-22 19:23:28.307846: step: 1776/529, loss: 0.0031732802744954824
2023-01-22 19:23:29.422978: step: 1780/529, loss: 0.0031303339637815952
2023-01-22 19:23:30.557281: step: 1784/529, loss: 0.013180905021727085
2023-01-22 19:23:31.669703: step: 1788/529, loss: 0.0035919812507927418
2023-01-22 19:23:32.778926: step: 1792/529, loss: 0.006066866219043732
2023-01-22 19:23:33.861799: step: 1796/529, loss: 0.0020214738324284554
2023-01-22 19:23:34.955686: step: 1800/529, loss: 0.004169781226664782
2023-01-22 19:23:36.070553: step: 1804/529, loss: 0.04999531805515289
2023-01-22 19:23:37.179665: step: 1808/529, loss: 0.0022171849850565195
2023-01-22 19:23:38.275732: step: 1812/529, loss: 7.562074461020529e-05
2023-01-22 19:23:39.381165: step: 1816/529, loss: 0.004359940066933632
2023-01-22 19:23:40.497228: step: 1820/529, loss: 0.0041817729361355305
2023-01-22 19:23:41.606666: step: 1824/529, loss: 0.0021923796739429235
2023-01-22 19:23:42.702552: step: 1828/529, loss: 0.0041497633792459965
2023-01-22 19:23:43.815152: step: 1832/529, loss: 0.0009777399245649576
2023-01-22 19:23:44.915282: step: 1836/529, loss: 0.0005270448164083064
2023-01-22 19:23:46.023503: step: 1840/529, loss: 0.009624544531106949
2023-01-22 19:23:47.149116: step: 1844/529, loss: 0.0005393408937379718
2023-01-22 19:23:48.275798: step: 1848/529, loss: 0.008533255197107792
2023-01-22 19:23:49.378867: step: 1852/529, loss: 0.0003352747007738799
2023-01-22 19:23:50.531128: step: 1856/529, loss: 0.0017396059120073915
2023-01-22 19:23:51.668433: step: 1860/529, loss: 0.054066430777311325
2023-01-22 19:23:52.786471: step: 1864/529, loss: 0.028022324666380882
2023-01-22 19:23:53.889425: step: 1868/529, loss: 0.004758719354867935
2023-01-22 19:23:55.016845: step: 1872/529, loss: 0.0066461097449064255
2023-01-22 19:23:56.133633: step: 1876/529, loss: 0.002942661289125681
2023-01-22 19:23:57.267267: step: 1880/529, loss: 0.0049504851922392845
2023-01-22 19:23:58.377164: step: 1884/529, loss: 0.0009159165783785284
2023-01-22 19:23:59.474235: step: 1888/529, loss: 0.010240484029054642
2023-01-22 19:24:00.584757: step: 1892/529, loss: 0.008234058506786823
2023-01-22 19:24:01.675105: step: 1896/529, loss: 0.004558432847261429
2023-01-22 19:24:02.790492: step: 1900/529, loss: 0.0018280777148902416
2023-01-22 19:24:03.909527: step: 1904/529, loss: 0.001706184702925384
2023-01-22 19:24:05.008202: step: 1908/529, loss: 0.0035248363856226206
2023-01-22 19:24:06.111301: step: 1912/529, loss: 0.0002554664679337293
2023-01-22 19:24:07.199409: step: 1916/529, loss: 0.001244658138602972
2023-01-22 19:24:08.313178: step: 1920/529, loss: 0.0012626301031559706
2023-01-22 19:24:09.436132: step: 1924/529, loss: 0.009176721796393394
2023-01-22 19:24:10.569278: step: 1928/529, loss: 0.0240730382502079
2023-01-22 19:24:11.695218: step: 1932/529, loss: 0.008625274524092674
2023-01-22 19:24:12.798891: step: 1936/529, loss: 0.008096283301711082
2023-01-22 19:24:13.908994: step: 1940/529, loss: 4.583534609992057e-05
2023-01-22 19:24:14.986257: step: 1944/529, loss: 0.008541249670088291
2023-01-22 19:24:16.075088: step: 1948/529, loss: 0.005415746942162514
2023-01-22 19:24:17.176512: step: 1952/529, loss: 0.002098322147503495
2023-01-22 19:24:18.275135: step: 1956/529, loss: 0.0053655002266168594
2023-01-22 19:24:19.388724: step: 1960/529, loss: 0.001825091545470059
2023-01-22 19:24:20.510508: step: 1964/529, loss: 0.004083148203790188
2023-01-22 19:24:21.627171: step: 1968/529, loss: 0.0052253492176532745
2023-01-22 19:24:22.738570: step: 1972/529, loss: 0.009055962786078453
2023-01-22 19:24:23.823497: step: 1976/529, loss: 1.0427392226119991e-05
2023-01-22 19:24:24.924879: step: 1980/529, loss: 0.010929914191365242
2023-01-22 19:24:26.004905: step: 1984/529, loss: 0.0027245418168604374
2023-01-22 19:24:27.109271: step: 1988/529, loss: 0.0027202703058719635
2023-01-22 19:24:28.220648: step: 1992/529, loss: 0.0028581772930920124
2023-01-22 19:24:29.335380: step: 1996/529, loss: 0.010418610647320747
2023-01-22 19:24:30.431036: step: 2000/529, loss: 0.001159005449153483
2023-01-22 19:24:31.546277: step: 2004/529, loss: 0.0027979742735624313
2023-01-22 19:24:32.698521: step: 2008/529, loss: 0.00393333425745368
2023-01-22 19:24:33.803354: step: 2012/529, loss: 0.007475843653082848
2023-01-22 19:24:34.891934: step: 2016/529, loss: 0.011700699105858803
2023-01-22 19:24:36.017851: step: 2020/529, loss: 0.002454961882904172
2023-01-22 19:24:37.111584: step: 2024/529, loss: 0.008408984169363976
2023-01-22 19:24:38.210636: step: 2028/529, loss: 0.03319612890481949
2023-01-22 19:24:39.290183: step: 2032/529, loss: 0.006548134610056877
2023-01-22 19:24:40.413606: step: 2036/529, loss: 0.018203601241111755
2023-01-22 19:24:41.519178: step: 2040/529, loss: 0.0025989694986492395
2023-01-22 19:24:42.614057: step: 2044/529, loss: 0.010249124839901924
2023-01-22 19:24:43.725769: step: 2048/529, loss: 0.0030631597619503736
2023-01-22 19:24:44.824370: step: 2052/529, loss: 0.004294148646295071
2023-01-22 19:24:45.931276: step: 2056/529, loss: 0.02513548918068409
2023-01-22 19:24:47.036380: step: 2060/529, loss: 0.0018500180449336767
2023-01-22 19:24:48.173163: step: 2064/529, loss: 0.0019697914831340313
2023-01-22 19:24:49.296941: step: 2068/529, loss: 0.011786270886659622
2023-01-22 19:24:50.390651: step: 2072/529, loss: 0.002880977699533105
2023-01-22 19:24:51.490804: step: 2076/529, loss: 0.0023447556886821985
2023-01-22 19:24:52.628175: step: 2080/529, loss: 0.010426324792206287
2023-01-22 19:24:53.749312: step: 2084/529, loss: 0.0038744681514799595
2023-01-22 19:24:54.846768: step: 2088/529, loss: 0.008821678347885609
2023-01-22 19:24:55.948638: step: 2092/529, loss: 0.0016580615192651749
2023-01-22 19:24:57.057565: step: 2096/529, loss: 0.005616358015686274
2023-01-22 19:24:58.167189: step: 2100/529, loss: 0.0034102166537195444
2023-01-22 19:24:59.276988: step: 2104/529, loss: 0.007788404822349548
2023-01-22 19:25:00.381171: step: 2108/529, loss: 0.0020257786381989717
2023-01-22 19:25:01.486481: step: 2112/529, loss: 0.006368610076606274
2023-01-22 19:25:02.625571: step: 2116/529, loss: 0.0063580297864973545
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32949869254060005, 'r': 0.3244968148549742, 'f1': 0.3269786260584539}, 'combined': 0.240931619200966, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3729660160961624, 'r': 0.29863136817405034, 'f1': 0.33168488823181336}, 'combined': 0.2038648581327243, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33134406210679457, 'r': 0.34203258023927186, 'f1': 0.3366034916640453}, 'combined': 0.24802362543666495, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3569953451600076, 'r': 0.31182955625761494, 'f1': 0.3328874263841699}, 'combined': 0.204603979143441, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33962369017275557, 'r': 0.3447792680121902, 'f1': 0.3421820607201963}, 'combined': 0.25213415000435513, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3675887147617673, 'r': 0.29884485122190435, 'f1': 0.32967125421327553}, 'combined': 0.20362048054349377, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3392857142857143, 'r': 0.41304347826086957, 'f1': 0.3725490196078432}, 'combined': 0.1862745098039216, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 10}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 11
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 19:27:29.650102: step: 4/529, loss: 0.00844115111976862
2023-01-22 19:27:30.760028: step: 8/529, loss: 0.020979363471269608
2023-01-22 19:27:31.884110: step: 12/529, loss: 0.00579110998660326
2023-01-22 19:27:32.981282: step: 16/529, loss: 0.007949178107082844
2023-01-22 19:27:34.084625: step: 20/529, loss: 0.005044217221438885
2023-01-22 19:27:35.189498: step: 24/529, loss: 0.001715436577796936
2023-01-22 19:27:36.281587: step: 28/529, loss: 0.0029960733372718096
2023-01-22 19:27:37.390716: step: 32/529, loss: 0.004749746061861515
2023-01-22 19:27:38.507017: step: 36/529, loss: 0.001871377811767161
2023-01-22 19:27:39.623445: step: 40/529, loss: 0.006074720993638039
2023-01-22 19:27:40.726452: step: 44/529, loss: 0.0026944035198539495
2023-01-22 19:27:41.830184: step: 48/529, loss: 0.0011238680453971028
2023-01-22 19:27:42.904847: step: 52/529, loss: 0.0010088251437991858
2023-01-22 19:27:44.033630: step: 56/529, loss: 0.007105117663741112
2023-01-22 19:27:45.129820: step: 60/529, loss: 0.001084332587197423
2023-01-22 19:27:46.253902: step: 64/529, loss: 0.0013439208269119263
2023-01-22 19:27:47.369154: step: 68/529, loss: 0.0051331473514437675
2023-01-22 19:27:48.469489: step: 72/529, loss: 0.0011121021816506982
2023-01-22 19:27:49.576407: step: 76/529, loss: 0.0029541226103901863
2023-01-22 19:27:50.684735: step: 80/529, loss: 0.00561157101765275
2023-01-22 19:27:51.765301: step: 84/529, loss: 0.0002865288406610489
2023-01-22 19:27:52.844450: step: 88/529, loss: 0.010356693528592587
2023-01-22 19:27:53.932532: step: 92/529, loss: 0.00010010231198975816
2023-01-22 19:27:55.015444: step: 96/529, loss: 0.00020123893045820296
2023-01-22 19:27:56.096899: step: 100/529, loss: 0.0006299946107901633
2023-01-22 19:27:57.206298: step: 104/529, loss: 0.0013150712475180626
2023-01-22 19:27:58.306782: step: 108/529, loss: 0.0059531028382480145
2023-01-22 19:27:59.393374: step: 112/529, loss: 0.008020145818591118
2023-01-22 19:28:00.482547: step: 116/529, loss: 0.007236039265990257
2023-01-22 19:28:01.586262: step: 120/529, loss: 0.012774981558322906
2023-01-22 19:28:02.702340: step: 124/529, loss: 0.011293821968138218
2023-01-22 19:28:03.844686: step: 128/529, loss: 0.0026905222330242395
2023-01-22 19:28:04.944846: step: 132/529, loss: 0.0011036355281248689
2023-01-22 19:28:06.048653: step: 136/529, loss: 0.00019762357987929136
2023-01-22 19:28:07.148897: step: 140/529, loss: 0.01146754901856184
2023-01-22 19:28:08.256423: step: 144/529, loss: 0.005518396385014057
2023-01-22 19:28:09.371862: step: 148/529, loss: 0.0049437787383794785
2023-01-22 19:28:10.477478: step: 152/529, loss: 0.004379387479275465
2023-01-22 19:28:11.569005: step: 156/529, loss: 0.00446859747171402
2023-01-22 19:28:12.694722: step: 160/529, loss: 0.005369523540139198
2023-01-22 19:28:13.795286: step: 164/529, loss: 0.0011135268723592162
2023-01-22 19:28:14.907774: step: 168/529, loss: 0.003364636329934001
2023-01-22 19:28:16.016147: step: 172/529, loss: 0.0016140296356752515
2023-01-22 19:28:17.117330: step: 176/529, loss: 0.0006261312519200146
2023-01-22 19:28:18.233953: step: 180/529, loss: 0.0026179319247603416
2023-01-22 19:28:19.360833: step: 184/529, loss: 0.0022436040453612804
2023-01-22 19:28:20.476937: step: 188/529, loss: 0.0071028852835297585
2023-01-22 19:28:21.596231: step: 192/529, loss: 0.004583127796649933
2023-01-22 19:28:22.692878: step: 196/529, loss: 0.0014352560974657536
2023-01-22 19:28:23.799388: step: 200/529, loss: 0.003546495456248522
2023-01-22 19:28:24.898013: step: 204/529, loss: 0.0055420780554413795
2023-01-22 19:28:26.036779: step: 208/529, loss: 0.019877225160598755
2023-01-22 19:28:27.138545: step: 212/529, loss: 0.021463608369231224
2023-01-22 19:28:28.257427: step: 216/529, loss: 9.85792648862116e-05
2023-01-22 19:28:29.357561: step: 220/529, loss: 0.004329256247729063
2023-01-22 19:28:30.454684: step: 224/529, loss: 0.0010845923097804189
2023-01-22 19:28:31.557878: step: 228/529, loss: 0.0022307466715574265
2023-01-22 19:28:32.640966: step: 232/529, loss: 0.0007933827582746744
2023-01-22 19:28:33.738428: step: 236/529, loss: 0.005464385263621807
2023-01-22 19:28:34.839850: step: 240/529, loss: 4.0545080537413014e-07
2023-01-22 19:28:35.947680: step: 244/529, loss: 0.003553795162588358
2023-01-22 19:28:37.061771: step: 248/529, loss: 0.004247546195983887
2023-01-22 19:28:38.159741: step: 252/529, loss: 0.018267003819346428
2023-01-22 19:28:39.288667: step: 256/529, loss: 0.0031788437627255917
2023-01-22 19:28:40.408589: step: 260/529, loss: 0.01948254369199276
2023-01-22 19:28:41.543247: step: 264/529, loss: 0.004951623734086752
2023-01-22 19:28:42.633240: step: 268/529, loss: 0.0017793672159314156
2023-01-22 19:28:43.726415: step: 272/529, loss: 0.0019417222356423736
2023-01-22 19:28:44.839643: step: 276/529, loss: 1.5217972759273835e-05
2023-01-22 19:28:45.958044: step: 280/529, loss: 0.0020967256277799606
2023-01-22 19:28:47.065400: step: 284/529, loss: 0.003428031224757433
2023-01-22 19:28:48.173423: step: 288/529, loss: 0.001250486820936203
2023-01-22 19:28:49.264728: step: 292/529, loss: 0.006197906564921141
2023-01-22 19:28:50.366478: step: 296/529, loss: 0.007990062236785889
2023-01-22 19:28:51.482565: step: 300/529, loss: 0.008474033325910568
2023-01-22 19:28:52.590023: step: 304/529, loss: 0.014518667943775654
2023-01-22 19:28:53.718013: step: 308/529, loss: 0.00179564137943089
2023-01-22 19:28:54.844481: step: 312/529, loss: 0.004551586229354143
2023-01-22 19:28:55.944203: step: 316/529, loss: 0.022535188123583794
2023-01-22 19:28:57.051304: step: 320/529, loss: 0.022015513852238655
2023-01-22 19:28:58.161202: step: 324/529, loss: 0.014681173488497734
2023-01-22 19:28:59.284491: step: 328/529, loss: 0.0030733528546988964
2023-01-22 19:29:00.393506: step: 332/529, loss: 0.0018407984171062708
2023-01-22 19:29:01.492022: step: 336/529, loss: 0.01389398518949747
2023-01-22 19:29:02.621243: step: 340/529, loss: 0.0007159760571084917
2023-01-22 19:29:03.739666: step: 344/529, loss: 0.006780853029340506
2023-01-22 19:29:04.851703: step: 348/529, loss: 0.011438514105975628
2023-01-22 19:29:05.938697: step: 352/529, loss: 0.006648657843470573
2023-01-22 19:29:07.045567: step: 356/529, loss: 0.012801037169992924
2023-01-22 19:29:08.167203: step: 360/529, loss: 0.001693736296147108
2023-01-22 19:29:09.271639: step: 364/529, loss: 0.0030145260971039534
2023-01-22 19:29:10.400200: step: 368/529, loss: 0.005842269863933325
2023-01-22 19:29:11.497561: step: 372/529, loss: 0.0005585098406299949
2023-01-22 19:29:12.585053: step: 376/529, loss: 0.00034072474227286875
2023-01-22 19:29:13.686252: step: 380/529, loss: 0.0255210492759943
2023-01-22 19:29:14.791104: step: 384/529, loss: 0.00613732123747468
2023-01-22 19:29:15.904620: step: 388/529, loss: 0.007783234119415283
2023-01-22 19:29:17.012208: step: 392/529, loss: 0.004175110254436731
2023-01-22 19:29:18.102664: step: 396/529, loss: 0.004834686405956745
2023-01-22 19:29:19.224150: step: 400/529, loss: 0.007448016200214624
2023-01-22 19:29:20.337605: step: 404/529, loss: 0.00578970555216074
2023-01-22 19:29:21.424409: step: 408/529, loss: 0.0006020013242959976
2023-01-22 19:29:22.533120: step: 412/529, loss: 0.01662960648536682
2023-01-22 19:29:23.658849: step: 416/529, loss: 0.0017585533205419779
2023-01-22 19:29:24.767436: step: 420/529, loss: 0.0007989160949364305
2023-01-22 19:29:25.868000: step: 424/529, loss: 0.00858911219984293
2023-01-22 19:29:26.978030: step: 428/529, loss: 0.002652117982506752
2023-01-22 19:29:28.071681: step: 432/529, loss: 0.015698252245783806
2023-01-22 19:29:29.189537: step: 436/529, loss: 0.04495786130428314
2023-01-22 19:29:30.310458: step: 440/529, loss: 0.016684578731656075
2023-01-22 19:29:31.424924: step: 444/529, loss: 0.011736352927982807
2023-01-22 19:29:32.544193: step: 448/529, loss: 0.0004370490205474198
2023-01-22 19:29:33.632080: step: 452/529, loss: 0.00010130803275387734
2023-01-22 19:29:34.735179: step: 456/529, loss: 0.0010403740452602506
2023-01-22 19:29:35.850503: step: 460/529, loss: 0.01684565283358097
2023-01-22 19:29:36.965458: step: 464/529, loss: 0.00397358275949955
2023-01-22 19:29:38.065518: step: 468/529, loss: 0.006977117154747248
2023-01-22 19:29:39.185306: step: 472/529, loss: 0.00773286446928978
2023-01-22 19:29:40.279108: step: 476/529, loss: 0.004086590372025967
2023-01-22 19:29:41.390142: step: 480/529, loss: 0.0030200290493667126
2023-01-22 19:29:42.498751: step: 484/529, loss: 0.0013680586125701666
2023-01-22 19:29:43.596352: step: 488/529, loss: 0.002889792900532484
2023-01-22 19:29:44.727625: step: 492/529, loss: 0.015945566818118095
2023-01-22 19:29:45.828449: step: 496/529, loss: 0.0011217283317819238
2023-01-22 19:29:46.951384: step: 500/529, loss: 0.0055679152719676495
2023-01-22 19:29:48.070220: step: 504/529, loss: 0.008145378902554512
2023-01-22 19:29:49.186329: step: 508/529, loss: 0.005072348285466433
2023-01-22 19:29:50.311150: step: 512/529, loss: 0.002225040690973401
2023-01-22 19:29:51.417388: step: 516/529, loss: 0.009913398884236813
2023-01-22 19:29:52.522074: step: 520/529, loss: 0.0035862799268215895
2023-01-22 19:29:53.634784: step: 524/529, loss: 0.003490537405014038
2023-01-22 19:29:54.753848: step: 528/529, loss: 0.01014535129070282
2023-01-22 19:29:55.866863: step: 532/529, loss: 0.0011744301300495863
2023-01-22 19:29:56.970953: step: 536/529, loss: 0.0038102632388472557
2023-01-22 19:29:58.111908: step: 540/529, loss: 0.001190882408991456
2023-01-22 19:29:59.223347: step: 544/529, loss: 0.011781220324337482
2023-01-22 19:30:00.335021: step: 548/529, loss: 0.0049925874918699265
2023-01-22 19:30:01.423388: step: 552/529, loss: 0.0030839182436466217
2023-01-22 19:30:02.541618: step: 556/529, loss: 0.017217248678207397
2023-01-22 19:30:03.660099: step: 560/529, loss: 0.004445804748684168
2023-01-22 19:30:04.749043: step: 564/529, loss: 0.0009031649678945541
2023-01-22 19:30:05.876402: step: 568/529, loss: 0.0011117144022136927
2023-01-22 19:30:06.987994: step: 572/529, loss: 0.0021940015722066164
2023-01-22 19:30:08.107685: step: 576/529, loss: 0.003153864061459899
2023-01-22 19:30:09.219358: step: 580/529, loss: 0.0008436269126832485
2023-01-22 19:30:10.319756: step: 584/529, loss: 0.0033403721172362566
2023-01-22 19:30:11.417652: step: 588/529, loss: 0.004300093278288841
2023-01-22 19:30:12.530725: step: 592/529, loss: 0.00236880243755877
2023-01-22 19:30:13.647595: step: 596/529, loss: 0.017922911792993546
2023-01-22 19:30:14.756904: step: 600/529, loss: 0.0012190206907689571
2023-01-22 19:30:15.899321: step: 604/529, loss: 0.01166699081659317
2023-01-22 19:30:17.009190: step: 608/529, loss: 0.00715693598613143
2023-01-22 19:30:18.099479: step: 612/529, loss: 0.0020148113835603
2023-01-22 19:30:19.231596: step: 616/529, loss: 0.0009512178949080408
2023-01-22 19:30:20.330555: step: 620/529, loss: 0.001246428582817316
2023-01-22 19:30:21.470808: step: 624/529, loss: 0.004320949781686068
2023-01-22 19:30:22.559376: step: 628/529, loss: 0.0007918922347016633
2023-01-22 19:30:23.652928: step: 632/529, loss: 0.0016534344758838415
2023-01-22 19:30:24.742258: step: 636/529, loss: 0.0003141536726616323
2023-01-22 19:30:25.839783: step: 640/529, loss: 0.007538760546594858
2023-01-22 19:30:26.963984: step: 644/529, loss: 0.01648290455341339
2023-01-22 19:30:28.062653: step: 648/529, loss: 0.005710061173886061
2023-01-22 19:30:29.180242: step: 652/529, loss: 0.009857021272182465
2023-01-22 19:30:30.310497: step: 656/529, loss: 0.004674674943089485
2023-01-22 19:30:31.429418: step: 660/529, loss: 0.0016565866535529494
2023-01-22 19:30:32.535535: step: 664/529, loss: 0.004142623394727707
2023-01-22 19:30:33.625938: step: 668/529, loss: 0.021623900160193443
2023-01-22 19:30:34.731217: step: 672/529, loss: 0.0017556409584358335
2023-01-22 19:30:35.853230: step: 676/529, loss: 0.00033482073922641575
2023-01-22 19:30:36.953980: step: 680/529, loss: 0.0009201587527059019
2023-01-22 19:30:38.070495: step: 684/529, loss: 0.006340256426483393
2023-01-22 19:30:39.170849: step: 688/529, loss: 0.010735297575592995
2023-01-22 19:30:40.261786: step: 692/529, loss: 0.004740302916616201
2023-01-22 19:30:41.374622: step: 696/529, loss: 0.0018195533193647861
2023-01-22 19:30:42.479884: step: 700/529, loss: 0.0013502421788871288
2023-01-22 19:30:43.587185: step: 704/529, loss: 0.0009792293421924114
2023-01-22 19:30:44.691105: step: 708/529, loss: 0.00033946821349672973
2023-01-22 19:30:45.790409: step: 712/529, loss: 0.0025781760923564434
2023-01-22 19:30:46.905771: step: 716/529, loss: 0.006270202342420816
2023-01-22 19:30:47.992510: step: 720/529, loss: 9.889738521451363e-07
2023-01-22 19:30:49.100954: step: 724/529, loss: 0.005066626239567995
2023-01-22 19:30:50.200416: step: 728/529, loss: 0.0008674657437950373
2023-01-22 19:30:51.281707: step: 732/529, loss: 0.0007751052035018802
2023-01-22 19:30:52.401050: step: 736/529, loss: 0.004346473608165979
2023-01-22 19:30:53.526577: step: 740/529, loss: 0.0033800092060118914
2023-01-22 19:30:54.632895: step: 744/529, loss: 0.0029286060016602278
2023-01-22 19:30:55.741049: step: 748/529, loss: 0.00028459422173909843
2023-01-22 19:30:56.886618: step: 752/529, loss: 0.0024262836668640375
2023-01-22 19:30:58.007572: step: 756/529, loss: 0.0011191107332706451
2023-01-22 19:30:59.140047: step: 760/529, loss: 0.0012898595305159688
2023-01-22 19:31:00.272383: step: 764/529, loss: 0.0026762045454233885
2023-01-22 19:31:01.360085: step: 768/529, loss: 0.00328453560359776
2023-01-22 19:31:02.481084: step: 772/529, loss: 0.003801693907007575
2023-01-22 19:31:03.599438: step: 776/529, loss: 0.0012236833572387695
2023-01-22 19:31:04.723787: step: 780/529, loss: 0.006623003166168928
2023-01-22 19:31:05.847642: step: 784/529, loss: 0.003294985042884946
2023-01-22 19:31:06.955485: step: 788/529, loss: 0.025937139987945557
2023-01-22 19:31:08.052256: step: 792/529, loss: 0.0009773930069059134
2023-01-22 19:31:09.172981: step: 796/529, loss: 0.014964092522859573
2023-01-22 19:31:10.261292: step: 800/529, loss: 0.0012083734618499875
2023-01-22 19:31:11.387108: step: 804/529, loss: 0.0053486586548388
2023-01-22 19:31:12.499110: step: 808/529, loss: 0.01712695322930813
2023-01-22 19:31:13.590876: step: 812/529, loss: 0.0002649268717505038
2023-01-22 19:31:14.702953: step: 816/529, loss: 0.0020419349893927574
2023-01-22 19:31:15.827810: step: 820/529, loss: 0.0011201896704733372
2023-01-22 19:31:16.946278: step: 824/529, loss: 0.007399091497063637
2023-01-22 19:31:18.072001: step: 828/529, loss: 9.503376350039616e-05
2023-01-22 19:31:19.195771: step: 832/529, loss: 0.004010332748293877
2023-01-22 19:31:20.301118: step: 836/529, loss: 0.0012934714322909713
2023-01-22 19:31:21.411344: step: 840/529, loss: 0.003757230006158352
2023-01-22 19:31:22.519022: step: 844/529, loss: 0.017119761556386948
2023-01-22 19:31:23.655606: step: 848/529, loss: 0.004221073351800442
2023-01-22 19:31:24.791917: step: 852/529, loss: 0.00029825398814864457
2023-01-22 19:31:25.907999: step: 856/529, loss: 0.005733921192586422
2023-01-22 19:31:27.012853: step: 860/529, loss: 0.0035247572232037783
2023-01-22 19:31:28.095318: step: 864/529, loss: 0.006842564791440964
2023-01-22 19:31:29.184435: step: 868/529, loss: 3.855265731544932e-06
2023-01-22 19:31:30.285426: step: 872/529, loss: 0.001217746757902205
2023-01-22 19:31:31.372108: step: 876/529, loss: 0.005069629289209843
2023-01-22 19:31:32.472842: step: 880/529, loss: 0.0025810536462813616
2023-01-22 19:31:33.590981: step: 884/529, loss: 0.002445860533043742
2023-01-22 19:31:34.706985: step: 888/529, loss: 0.0017040508100762963
2023-01-22 19:31:35.820318: step: 892/529, loss: 0.006463023833930492
2023-01-22 19:31:36.942564: step: 896/529, loss: 0.0019293962977826595
2023-01-22 19:31:38.072943: step: 900/529, loss: 0.0011861694511026144
2023-01-22 19:31:39.170556: step: 904/529, loss: 0.03439740836620331
2023-01-22 19:31:40.276608: step: 908/529, loss: 0.0009568601381033659
2023-01-22 19:31:41.364935: step: 912/529, loss: 0.0023391391150653362
2023-01-22 19:31:42.480515: step: 916/529, loss: 0.0003876067348755896
2023-01-22 19:31:43.573142: step: 920/529, loss: 0.0018878539558500051
2023-01-22 19:31:44.697393: step: 924/529, loss: 0.003929265309125185
2023-01-22 19:31:45.806199: step: 928/529, loss: 0.002547285985201597
2023-01-22 19:31:46.905379: step: 932/529, loss: 0.05676935240626335
2023-01-22 19:31:48.005568: step: 936/529, loss: 0.0014037369983270764
2023-01-22 19:31:49.120489: step: 940/529, loss: 0.005906595382839441
2023-01-22 19:31:50.252138: step: 944/529, loss: 0.0024180065374821424
2023-01-22 19:31:51.374813: step: 948/529, loss: 0.004414003808051348
2023-01-22 19:31:52.492577: step: 952/529, loss: 0.002302455250173807
2023-01-22 19:31:53.623949: step: 956/529, loss: 0.00012025266914861277
2023-01-22 19:31:54.727324: step: 960/529, loss: 0.008000114932656288
2023-01-22 19:31:55.833458: step: 964/529, loss: 0.010300581343472004
2023-01-22 19:31:56.941594: step: 968/529, loss: 0.005171730183064938
2023-01-22 19:31:58.041372: step: 972/529, loss: 0.002349207177758217
2023-01-22 19:31:59.165232: step: 976/529, loss: 0.002971658017486334
2023-01-22 19:32:00.279308: step: 980/529, loss: 0.00809214822947979
2023-01-22 19:32:01.392410: step: 984/529, loss: 0.0005921954289078712
2023-01-22 19:32:02.490361: step: 988/529, loss: 0.0026468555442988873
2023-01-22 19:32:03.589928: step: 992/529, loss: 0.0002647619985509664
2023-01-22 19:32:04.700455: step: 996/529, loss: 0.005888370331376791
2023-01-22 19:32:05.813076: step: 1000/529, loss: 0.003267069347202778
2023-01-22 19:32:06.915555: step: 1004/529, loss: 7.504592940676957e-05
2023-01-22 19:32:08.052398: step: 1008/529, loss: 0.003062062431126833
2023-01-22 19:32:09.139576: step: 1012/529, loss: 0.0007736250408925116
2023-01-22 19:32:10.243160: step: 1016/529, loss: 0.00655006617307663
2023-01-22 19:32:11.359851: step: 1020/529, loss: 0.01732056960463524
2023-01-22 19:32:12.482427: step: 1024/529, loss: 0.0008451450848951936
2023-01-22 19:32:13.601846: step: 1028/529, loss: 0.0019260543631389737
2023-01-22 19:32:14.703044: step: 1032/529, loss: 0.005653090309351683
2023-01-22 19:32:15.811518: step: 1036/529, loss: 0.005015730392187834
2023-01-22 19:32:16.915683: step: 1040/529, loss: 0.006838577333837748
2023-01-22 19:32:18.027710: step: 1044/529, loss: 0.033377669751644135
2023-01-22 19:32:19.131273: step: 1048/529, loss: 0.0008285798830911517
2023-01-22 19:32:20.239121: step: 1052/529, loss: 0.0040962472558021545
2023-01-22 19:32:21.351802: step: 1056/529, loss: 0.007803542539477348
2023-01-22 19:32:22.444559: step: 1060/529, loss: 0.0013499382184818387
2023-01-22 19:32:23.554661: step: 1064/529, loss: 0.0019406476058065891
2023-01-22 19:32:24.648245: step: 1068/529, loss: 8.576701657148078e-05
2023-01-22 19:32:25.781536: step: 1072/529, loss: 0.004887906368821859
2023-01-22 19:32:26.907770: step: 1076/529, loss: 0.0021051515359431505
2023-01-22 19:32:28.020136: step: 1080/529, loss: 0.004105157684534788
2023-01-22 19:32:29.135165: step: 1084/529, loss: 0.0007092682644724846
2023-01-22 19:32:30.261209: step: 1088/529, loss: 0.005515716038644314
2023-01-22 19:32:31.371319: step: 1092/529, loss: 0.007160830311477184
2023-01-22 19:32:32.463034: step: 1096/529, loss: 0.00030613827402703464
2023-01-22 19:32:33.584820: step: 1100/529, loss: 0.005239086225628853
2023-01-22 19:32:34.698809: step: 1104/529, loss: 0.0023801024071872234
2023-01-22 19:32:35.824324: step: 1108/529, loss: 0.0058539560995996
2023-01-22 19:32:36.923654: step: 1112/529, loss: 0.0009661816875450313
2023-01-22 19:32:38.024306: step: 1116/529, loss: 0.00082486926112324
2023-01-22 19:32:39.113789: step: 1120/529, loss: 0.004162740893661976
2023-01-22 19:32:40.230964: step: 1124/529, loss: 0.0026770695112645626
2023-01-22 19:32:41.329161: step: 1128/529, loss: 0.0032701033633202314
2023-01-22 19:32:42.426287: step: 1132/529, loss: 0.016873609274625778
2023-01-22 19:32:43.552466: step: 1136/529, loss: 0.006976199336349964
2023-01-22 19:32:44.642842: step: 1140/529, loss: 0.008767476305365562
2023-01-22 19:32:45.756432: step: 1144/529, loss: 0.012852507643401623
2023-01-22 19:32:46.892570: step: 1148/529, loss: 0.0007530332659371197
2023-01-22 19:32:47.982233: step: 1152/529, loss: 0.0006995071889832616
2023-01-22 19:32:49.079050: step: 1156/529, loss: 0.007044769357889891
2023-01-22 19:32:50.190340: step: 1160/529, loss: 0.016497166827321053
2023-01-22 19:32:51.288365: step: 1164/529, loss: 0.00271224114112556
2023-01-22 19:32:52.401454: step: 1168/529, loss: 7.165854913182557e-05
2023-01-22 19:32:53.497246: step: 1172/529, loss: 0.0035616715904325247
2023-01-22 19:32:54.610717: step: 1176/529, loss: 0.0023160730488598347
2023-01-22 19:32:55.714185: step: 1180/529, loss: 0.020186278969049454
2023-01-22 19:32:56.823498: step: 1184/529, loss: 0.0025611594319343567
2023-01-22 19:32:57.941776: step: 1188/529, loss: 0.003797759534791112
2023-01-22 19:32:59.057622: step: 1192/529, loss: 0.005366635043174028
2023-01-22 19:33:00.160279: step: 1196/529, loss: 0.006503208074718714
2023-01-22 19:33:01.245452: step: 1200/529, loss: 0.0046144467778503895
2023-01-22 19:33:02.359521: step: 1204/529, loss: 0.0030831072945147753
2023-01-22 19:33:03.487043: step: 1208/529, loss: 0.017920056357979774
2023-01-22 19:33:04.597682: step: 1212/529, loss: 0.002440088428556919
2023-01-22 19:33:05.697708: step: 1216/529, loss: 0.006227685138583183
2023-01-22 19:33:06.800505: step: 1220/529, loss: 0.0028466784860938787
2023-01-22 19:33:07.903174: step: 1224/529, loss: 0.0053274682722985744
2023-01-22 19:33:08.995611: step: 1228/529, loss: 0.0010565445991232991
2023-01-22 19:33:10.097547: step: 1232/529, loss: 0.0015335481148213148
2023-01-22 19:33:11.230311: step: 1236/529, loss: 0.003924991469830275
2023-01-22 19:33:12.330594: step: 1240/529, loss: 0.0004750562075059861
2023-01-22 19:33:13.449150: step: 1244/529, loss: 0.0010517614427953959
2023-01-22 19:33:14.553901: step: 1248/529, loss: 0.0046148705296218395
2023-01-22 19:33:15.671327: step: 1252/529, loss: 0.0003543717903085053
2023-01-22 19:33:16.796688: step: 1256/529, loss: 0.0010193290654569864
2023-01-22 19:33:17.918426: step: 1260/529, loss: 0.012018855661153793
2023-01-22 19:33:19.042254: step: 1264/529, loss: 0.006649521645158529
2023-01-22 19:33:20.160922: step: 1268/529, loss: 5.692885315511376e-05
2023-01-22 19:33:21.267520: step: 1272/529, loss: 0.011772981844842434
2023-01-22 19:33:22.389084: step: 1276/529, loss: 0.009156133979558945
2023-01-22 19:33:23.478498: step: 1280/529, loss: 0.0020698204170912504
2023-01-22 19:33:24.573402: step: 1284/529, loss: 0.004424553830176592
2023-01-22 19:33:25.669554: step: 1288/529, loss: 0.00022289076878223568
2023-01-22 19:33:26.773697: step: 1292/529, loss: 0.007505868095904589
2023-01-22 19:33:27.864739: step: 1296/529, loss: 0.0029971294570714235
2023-01-22 19:33:28.979066: step: 1300/529, loss: 0.00896605383604765
2023-01-22 19:33:30.079536: step: 1304/529, loss: 0.0015668014530092478
2023-01-22 19:33:31.183014: step: 1308/529, loss: 0.0005669065285474062
2023-01-22 19:33:32.302009: step: 1312/529, loss: 0.026423176750540733
2023-01-22 19:33:33.408030: step: 1316/529, loss: 0.004049985203891993
2023-01-22 19:33:34.543782: step: 1320/529, loss: 0.004315638914704323
2023-01-22 19:33:35.678222: step: 1324/529, loss: 0.0035286752972751856
2023-01-22 19:33:36.795734: step: 1328/529, loss: 0.002237678272649646
2023-01-22 19:33:37.934510: step: 1332/529, loss: 0.0014509214088320732
2023-01-22 19:33:39.054171: step: 1336/529, loss: 0.003688718192279339
2023-01-22 19:33:40.157228: step: 1340/529, loss: 0.0017588643822818995
2023-01-22 19:33:41.264324: step: 1344/529, loss: 0.003400132292881608
2023-01-22 19:33:42.380357: step: 1348/529, loss: 0.004457415081560612
2023-01-22 19:33:43.497989: step: 1352/529, loss: 0.0012696267804130912
2023-01-22 19:33:44.612931: step: 1356/529, loss: 0.003029454266652465
2023-01-22 19:33:45.721984: step: 1360/529, loss: 0.005543313920497894
2023-01-22 19:33:46.818124: step: 1364/529, loss: 0.003372120438143611
2023-01-22 19:33:47.960420: step: 1368/529, loss: 0.03488500043749809
2023-01-22 19:33:49.054674: step: 1372/529, loss: 0.0015060494188219309
2023-01-22 19:33:50.174304: step: 1376/529, loss: 0.012768702581524849
2023-01-22 19:33:51.311626: step: 1380/529, loss: 0.0013559150975197554
2023-01-22 19:33:52.431584: step: 1384/529, loss: 0.012266425415873528
2023-01-22 19:33:53.530924: step: 1388/529, loss: 0.01115561556071043
2023-01-22 19:33:54.669925: step: 1392/529, loss: 0.002833722857758403
2023-01-22 19:33:55.819253: step: 1396/529, loss: 0.0012369280448183417
2023-01-22 19:33:56.943467: step: 1400/529, loss: 0.026487652212381363
2023-01-22 19:33:58.043605: step: 1404/529, loss: 0.0036454596556723118
2023-01-22 19:33:59.154771: step: 1408/529, loss: 0.006267383694648743
2023-01-22 19:34:00.278762: step: 1412/529, loss: 0.015909546986222267
2023-01-22 19:34:01.407783: step: 1416/529, loss: 0.011788478121161461
2023-01-22 19:34:02.506855: step: 1420/529, loss: 0.004515159875154495
2023-01-22 19:34:03.628172: step: 1424/529, loss: 0.011597182601690292
2023-01-22 19:34:04.744124: step: 1428/529, loss: 0.0002957967226393521
2023-01-22 19:34:05.858549: step: 1432/529, loss: 0.005916237831115723
2023-01-22 19:34:06.955959: step: 1436/529, loss: 0.002234724350273609
2023-01-22 19:34:08.078937: step: 1440/529, loss: 0.0019734741654247046
2023-01-22 19:34:09.181134: step: 1444/529, loss: 0.00026089372113347054
2023-01-22 19:34:10.285426: step: 1448/529, loss: 0.0071403454057872295
2023-01-22 19:34:11.410421: step: 1452/529, loss: 0.012803579680621624
2023-01-22 19:34:12.543826: step: 1456/529, loss: 0.007361842319369316
2023-01-22 19:34:13.632989: step: 1460/529, loss: 0.0003282254037912935
2023-01-22 19:34:14.729458: step: 1464/529, loss: 0.003516164608299732
2023-01-22 19:34:15.833433: step: 1468/529, loss: 0.0006904699257574975
2023-01-22 19:34:16.943627: step: 1472/529, loss: 0.006863766815513372
2023-01-22 19:34:18.045157: step: 1476/529, loss: 0.003444032510742545
2023-01-22 19:34:19.147595: step: 1480/529, loss: 0.0020606897305697203
2023-01-22 19:34:20.270983: step: 1484/529, loss: 0.006396012380719185
2023-01-22 19:34:21.382988: step: 1488/529, loss: 0.0004291832447052002
2023-01-22 19:34:22.477219: step: 1492/529, loss: 7.820609607733786e-05
2023-01-22 19:34:23.587189: step: 1496/529, loss: 0.0030667679384350777
2023-01-22 19:34:24.683796: step: 1500/529, loss: 0.000850684242323041
2023-01-22 19:34:25.812789: step: 1504/529, loss: 0.004149554762989283
2023-01-22 19:34:26.926857: step: 1508/529, loss: 0.0022297692485153675
2023-01-22 19:34:28.002177: step: 1512/529, loss: 0.0004538490029517561
2023-01-22 19:34:29.135957: step: 1516/529, loss: 0.006826519500464201
2023-01-22 19:34:30.226372: step: 1520/529, loss: 0.00019551030709408224
2023-01-22 19:34:31.337282: step: 1524/529, loss: 0.014934631064534187
2023-01-22 19:34:32.506438: step: 1528/529, loss: 0.014110477641224861
2023-01-22 19:34:33.612193: step: 1532/529, loss: 0.01045110635459423
2023-01-22 19:34:34.710028: step: 1536/529, loss: 0.0066744061186909676
2023-01-22 19:34:35.824107: step: 1540/529, loss: 0.0019012573175132275
2023-01-22 19:34:36.933491: step: 1544/529, loss: 0.003337307134643197
2023-01-22 19:34:38.058932: step: 1548/529, loss: 0.005773071199655533
2023-01-22 19:34:39.146408: step: 1552/529, loss: 0.0022756510879844427
2023-01-22 19:34:40.263346: step: 1556/529, loss: 0.012884018011391163
2023-01-22 19:34:41.386521: step: 1560/529, loss: 0.0054016620852053165
2023-01-22 19:34:42.498750: step: 1564/529, loss: 0.0017216844717040658
2023-01-22 19:34:43.607175: step: 1568/529, loss: 0.013849829323589802
2023-01-22 19:34:44.699993: step: 1572/529, loss: 0.007813731208443642
2023-01-22 19:34:45.804211: step: 1576/529, loss: 0.007207179442048073
2023-01-22 19:34:46.913405: step: 1580/529, loss: 0.004785093944519758
2023-01-22 19:34:47.989731: step: 1584/529, loss: 0.003768039168789983
2023-01-22 19:34:49.089891: step: 1588/529, loss: 0.004621509928256273
2023-01-22 19:34:50.203936: step: 1592/529, loss: 0.014007627964019775
2023-01-22 19:34:51.324830: step: 1596/529, loss: 0.009194851852953434
2023-01-22 19:34:52.437628: step: 1600/529, loss: 0.005072671454399824
2023-01-22 19:34:53.531806: step: 1604/529, loss: 0.00021289379219524562
2023-01-22 19:34:54.667836: step: 1608/529, loss: 0.0031537243630737066
2023-01-22 19:34:55.779868: step: 1612/529, loss: 0.019190721213817596
2023-01-22 19:34:56.886487: step: 1616/529, loss: 0.005900430027395487
2023-01-22 19:34:57.983279: step: 1620/529, loss: 0.007275173906236887
2023-01-22 19:34:59.082912: step: 1624/529, loss: 0.002585094887763262
2023-01-22 19:35:00.201773: step: 1628/529, loss: 0.0019110547145828605
2023-01-22 19:35:01.288628: step: 1632/529, loss: 5.253553536022082e-05
2023-01-22 19:35:02.397888: step: 1636/529, loss: 0.012486271560192108
2023-01-22 19:35:03.513185: step: 1640/529, loss: 0.003716852981597185
2023-01-22 19:35:04.660255: step: 1644/529, loss: 0.004231891594827175
2023-01-22 19:35:05.768616: step: 1648/529, loss: 0.003106782678514719
2023-01-22 19:35:06.862457: step: 1652/529, loss: 0.006548008881509304
2023-01-22 19:35:07.972552: step: 1656/529, loss: 0.007671670988202095
2023-01-22 19:35:09.100497: step: 1660/529, loss: 0.002767820144072175
2023-01-22 19:35:10.210934: step: 1664/529, loss: 0.0008777441107667983
2023-01-22 19:35:11.309976: step: 1668/529, loss: 0.001488186651840806
2023-01-22 19:35:12.413589: step: 1672/529, loss: 0.0011112248757854104
2023-01-22 19:35:13.540266: step: 1676/529, loss: 0.0005050413310527802
2023-01-22 19:35:14.663634: step: 1680/529, loss: 0.0009451690712012351
2023-01-22 19:35:15.766793: step: 1684/529, loss: 0.002810921985656023
2023-01-22 19:35:16.902912: step: 1688/529, loss: 0.001579177100211382
2023-01-22 19:35:18.010382: step: 1692/529, loss: 0.0155815863981843
2023-01-22 19:35:19.118899: step: 1696/529, loss: 0.0025179111398756504
2023-01-22 19:35:20.226344: step: 1700/529, loss: 0.0021014863159507513
2023-01-22 19:35:21.345192: step: 1704/529, loss: 0.0048246257938444614
2023-01-22 19:35:22.449020: step: 1708/529, loss: 0.017451664432883263
2023-01-22 19:35:23.562131: step: 1712/529, loss: 0.006588782649487257
2023-01-22 19:35:24.672162: step: 1716/529, loss: 1.5870620700297877e-05
2023-01-22 19:35:25.765232: step: 1720/529, loss: 0.005207560490816832
2023-01-22 19:35:26.881076: step: 1724/529, loss: 0.0010843047639355063
2023-01-22 19:35:27.984105: step: 1728/529, loss: 0.008674499578773975
2023-01-22 19:35:29.095374: step: 1732/529, loss: 0.0004631158953998238
2023-01-22 19:35:30.182761: step: 1736/529, loss: 0.01776072382926941
2023-01-22 19:35:31.276231: step: 1740/529, loss: 0.0024243418592959642
2023-01-22 19:35:32.419508: step: 1744/529, loss: 0.0016719745472073555
2023-01-22 19:35:33.529370: step: 1748/529, loss: 0.003435152815654874
2023-01-22 19:35:34.646891: step: 1752/529, loss: 0.005865814164280891
2023-01-22 19:35:35.767178: step: 1756/529, loss: 0.00036233774153515697
2023-01-22 19:35:36.886837: step: 1760/529, loss: 0.004737775307148695
2023-01-22 19:35:37.976638: step: 1764/529, loss: 0.005815178155899048
2023-01-22 19:35:39.107903: step: 1768/529, loss: 0.0004244623414706439
2023-01-22 19:35:40.210496: step: 1772/529, loss: 0.01204951573163271
2023-01-22 19:35:41.295258: step: 1776/529, loss: 0.004508337937295437
2023-01-22 19:35:42.390692: step: 1780/529, loss: 0.0009568501263856888
2023-01-22 19:35:43.505721: step: 1784/529, loss: 0.003377004526555538
2023-01-22 19:35:44.603148: step: 1788/529, loss: 0.048388440161943436
2023-01-22 19:35:45.716621: step: 1792/529, loss: 0.001426311326213181
2023-01-22 19:35:46.835721: step: 1796/529, loss: 0.008733781054615974
2023-01-22 19:35:47.934793: step: 1800/529, loss: 0.008310790173709393
2023-01-22 19:35:49.078671: step: 1804/529, loss: 0.004265836905688047
2023-01-22 19:35:50.184792: step: 1808/529, loss: 0.0001271079236175865
2023-01-22 19:35:51.312304: step: 1812/529, loss: 0.008557415567338467
2023-01-22 19:35:52.438710: step: 1816/529, loss: 0.003814536612480879
2023-01-22 19:35:53.531701: step: 1820/529, loss: 0.005167282652109861
2023-01-22 19:35:54.632915: step: 1824/529, loss: 0.004549714736640453
2023-01-22 19:35:55.758451: step: 1828/529, loss: 0.01032494567334652
2023-01-22 19:35:56.871473: step: 1832/529, loss: 0.0038686967454850674
2023-01-22 19:35:57.999106: step: 1836/529, loss: 0.0011009577428922057
2023-01-22 19:35:59.120642: step: 1840/529, loss: 0.0038741272874176502
2023-01-22 19:36:00.249068: step: 1844/529, loss: 0.0007635563379153609
2023-01-22 19:36:01.391181: step: 1848/529, loss: 0.012273360043764114
2023-01-22 19:36:02.484514: step: 1852/529, loss: 0.007692363578826189
2023-01-22 19:36:03.598956: step: 1856/529, loss: 0.00312973209656775
2023-01-22 19:36:04.717810: step: 1860/529, loss: 0.011812441051006317
2023-01-22 19:36:05.827390: step: 1864/529, loss: 0.003971350844949484
2023-01-22 19:36:06.928572: step: 1868/529, loss: 0.005851636175066233
2023-01-22 19:36:08.043363: step: 1872/529, loss: 0.004560678731650114
2023-01-22 19:36:09.138414: step: 1876/529, loss: 0.0021861877758055925
2023-01-22 19:36:10.250054: step: 1880/529, loss: 0.003824198618531227
2023-01-22 19:36:11.366977: step: 1884/529, loss: 0.004318365827202797
2023-01-22 19:36:12.480506: step: 1888/529, loss: 0.005066792480647564
2023-01-22 19:36:13.569209: step: 1892/529, loss: 0.0064278095960617065
2023-01-22 19:36:14.667908: step: 1896/529, loss: 0.006338384468108416
2023-01-22 19:36:15.790168: step: 1900/529, loss: 0.002471103798598051
2023-01-22 19:36:16.912199: step: 1904/529, loss: 0.005269594024866819
2023-01-22 19:36:18.012138: step: 1908/529, loss: 0.013808159157633781
2023-01-22 19:36:19.108006: step: 1912/529, loss: 0.028862416744232178
2023-01-22 19:36:20.211005: step: 1916/529, loss: 0.0035963926929980516
2023-01-22 19:36:21.301763: step: 1920/529, loss: 0.0001030353523674421
2023-01-22 19:36:22.416558: step: 1924/529, loss: 0.004442925099283457
2023-01-22 19:36:23.526978: step: 1928/529, loss: 0.0013091267319396138
2023-01-22 19:36:24.643400: step: 1932/529, loss: 0.0042597330175340176
2023-01-22 19:36:25.742063: step: 1936/529, loss: 0.0005841926904395223
2023-01-22 19:36:26.871541: step: 1940/529, loss: 0.002184335608035326
2023-01-22 19:36:27.974899: step: 1944/529, loss: 0.005775731522589922
2023-01-22 19:36:29.078109: step: 1948/529, loss: 0.0041688294149935246
2023-01-22 19:36:30.172678: step: 1952/529, loss: 0.0010458033066242933
2023-01-22 19:36:31.275194: step: 1956/529, loss: 0.021324271336197853
2023-01-22 19:36:32.386820: step: 1960/529, loss: 0.002240370027720928
2023-01-22 19:36:33.495502: step: 1964/529, loss: 0.0037174688186496496
2023-01-22 19:36:34.585666: step: 1968/529, loss: 0.0014703454216942191
2023-01-22 19:36:35.714031: step: 1972/529, loss: 0.012709921225905418
2023-01-22 19:36:36.796251: step: 1976/529, loss: 0.0007731486111879349
2023-01-22 19:36:37.899331: step: 1980/529, loss: 0.0006906954804435372
2023-01-22 19:36:39.004088: step: 1984/529, loss: 0.009930431842803955
2023-01-22 19:36:40.087934: step: 1988/529, loss: 8.848836296238005e-05
2023-01-22 19:36:41.202028: step: 1992/529, loss: 0.0059011559933424
2023-01-22 19:36:42.299953: step: 1996/529, loss: 0.0005378047353588045
2023-01-22 19:36:43.408873: step: 2000/529, loss: 0.01136679295450449
2023-01-22 19:36:44.513038: step: 2004/529, loss: 0.01261558011174202
2023-01-22 19:36:45.621799: step: 2008/529, loss: 0.00015609461115673184
2023-01-22 19:36:46.756390: step: 2012/529, loss: 0.003131320932880044
2023-01-22 19:36:47.833154: step: 2016/529, loss: 0.0002025125577347353
2023-01-22 19:36:48.939829: step: 2020/529, loss: 0.010645151138305664
2023-01-22 19:36:50.078225: step: 2024/529, loss: 0.002788886893540621
2023-01-22 19:36:51.213369: step: 2028/529, loss: 0.0005681856418959796
2023-01-22 19:36:52.324444: step: 2032/529, loss: 0.05632838234305382
2023-01-22 19:36:53.415136: step: 2036/529, loss: 0.0030708699487149715
2023-01-22 19:36:54.502487: step: 2040/529, loss: 0.002978625474497676
2023-01-22 19:36:55.606914: step: 2044/529, loss: 0.003536547301337123
2023-01-22 19:36:56.710897: step: 2048/529, loss: 0.004249243531376123
2023-01-22 19:36:57.825673: step: 2052/529, loss: 0.0016448420938104391
2023-01-22 19:36:58.924256: step: 2056/529, loss: 0.0033577769063413143
2023-01-22 19:37:00.045158: step: 2060/529, loss: 0.0013673026114702225
2023-01-22 19:37:01.145034: step: 2064/529, loss: 0.0045458669774234295
2023-01-22 19:37:02.249769: step: 2068/529, loss: 0.0006131752743385732
2023-01-22 19:37:03.379296: step: 2072/529, loss: 0.0015062569873407483
2023-01-22 19:37:04.480460: step: 2076/529, loss: 0.004423859063535929
2023-01-22 19:37:05.597692: step: 2080/529, loss: 0.0061938087455928326
2023-01-22 19:37:06.727048: step: 2084/529, loss: 0.0015077540883794427
2023-01-22 19:37:07.815797: step: 2088/529, loss: 0.00013401305477600545
2023-01-22 19:37:08.932479: step: 2092/529, loss: 0.0015274615725502372
2023-01-22 19:37:10.027243: step: 2096/529, loss: 0.00226380187086761
2023-01-22 19:37:11.127503: step: 2100/529, loss: 0.0007622981793247163
2023-01-22 19:37:12.238229: step: 2104/529, loss: 0.003061251249164343
2023-01-22 19:37:13.324137: step: 2108/529, loss: 0.0015172269195318222
2023-01-22 19:37:14.423089: step: 2112/529, loss: 0.001013267901726067
2023-01-22 19:37:15.538652: step: 2116/529, loss: 0.001493466435931623
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33497081043956045, 'r': 0.33052148278666305, 'f1': 0.3327312730249693}, 'combined': 0.24517041170260895, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37218418448261237, 'r': 0.29639277776388284, 'f1': 0.3299925379059535}, 'combined': 0.20282468183487873, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3368268934059477, 'r': 0.3470531368490125, 'f1': 0.34186355723257866}, 'combined': 0.2518994632240053, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35749381410718045, 'r': 0.310096454004582, 'f1': 0.33211258275757555}, 'combined': 0.20412773379246107, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34025968959255476, 'r': 0.3447792680121902, 'f1': 0.3425045697312427}, 'combined': 0.2523717882230209, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36625751135388657, 'r': 0.2977626001396532, 'f1': 0.32847736691623636}, 'combined': 0.20288307956591073, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35185185185185186, 'r': 0.41304347826086957, 'f1': 0.38}, 'combined': 0.19, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 11}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 12
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 19:39:40.179424: step: 4/529, loss: 0.0027762765530496836
2023-01-22 19:39:41.267608: step: 8/529, loss: 0.0010462049394845963
2023-01-22 19:39:42.364821: step: 12/529, loss: 0.003816004376858473
2023-01-22 19:39:43.459857: step: 16/529, loss: 0.0034619285725057125
2023-01-22 19:39:44.533948: step: 20/529, loss: 0.0012335400097072124
2023-01-22 19:39:45.623382: step: 24/529, loss: 0.0009715323685668409
2023-01-22 19:39:46.723068: step: 28/529, loss: 8.888173033483326e-05
2023-01-22 19:39:47.814072: step: 32/529, loss: 9.12934137886623e-06
2023-01-22 19:39:48.909763: step: 36/529, loss: 0.0010657234815880656
2023-01-22 19:39:50.016824: step: 40/529, loss: 0.004928060807287693
2023-01-22 19:39:51.112816: step: 44/529, loss: 1.7358754121232778e-05
2023-01-22 19:39:52.216546: step: 48/529, loss: 0.005204554181545973
2023-01-22 19:39:53.327255: step: 52/529, loss: 0.005520981270819902
2023-01-22 19:39:54.431769: step: 56/529, loss: 0.009502717293798923
2023-01-22 19:39:55.536529: step: 60/529, loss: 0.003339269896969199
2023-01-22 19:39:56.633319: step: 64/529, loss: 0.012243479490280151
2023-01-22 19:39:57.731853: step: 68/529, loss: 0.000890921161044389
2023-01-22 19:39:58.826674: step: 72/529, loss: 5.428383701655548e-06
2023-01-22 19:39:59.916628: step: 76/529, loss: 0.006472372449934483
2023-01-22 19:40:01.030868: step: 80/529, loss: 0.00230636028572917
2023-01-22 19:40:02.141913: step: 84/529, loss: 0.0037265836726874113
2023-01-22 19:40:03.239542: step: 88/529, loss: 0.00020787192624993622
2023-01-22 19:40:04.338296: step: 92/529, loss: 0.0018673932645469904
2023-01-22 19:40:05.453110: step: 96/529, loss: 0.0038730923552066088
2023-01-22 19:40:06.570436: step: 100/529, loss: 0.016526632010936737
2023-01-22 19:40:07.702945: step: 104/529, loss: 0.0035179378464818
2023-01-22 19:40:08.819229: step: 108/529, loss: 0.0024837448727339506
2023-01-22 19:40:09.933986: step: 112/529, loss: 0.011297304183244705
2023-01-22 19:40:11.052248: step: 116/529, loss: 0.002900385297834873
2023-01-22 19:40:12.171878: step: 120/529, loss: 0.0032932006288319826
2023-01-22 19:40:13.258313: step: 124/529, loss: 0.00015768481534905732
2023-01-22 19:40:14.357123: step: 128/529, loss: 0.005349403712898493
2023-01-22 19:40:15.468071: step: 132/529, loss: 0.0018632753053680062
2023-01-22 19:40:16.590981: step: 136/529, loss: 0.014207469299435616
2023-01-22 19:40:17.690902: step: 140/529, loss: 0.0030285371467471123
2023-01-22 19:40:18.801271: step: 144/529, loss: 0.000701298238709569
2023-01-22 19:40:19.910589: step: 148/529, loss: 0.01561272144317627
2023-01-22 19:40:21.037221: step: 152/529, loss: 0.0022973588202148676
2023-01-22 19:40:22.128506: step: 156/529, loss: 0.0008811238221824169
2023-01-22 19:40:23.220395: step: 160/529, loss: 0.0033532651141285896
2023-01-22 19:40:24.323921: step: 164/529, loss: 0.011777253821492195
2023-01-22 19:40:25.418555: step: 168/529, loss: 4.221989868824494e-08
2023-01-22 19:40:26.516412: step: 172/529, loss: 0.0024700488429516554
2023-01-22 19:40:27.607443: step: 176/529, loss: 0.014778150245547295
2023-01-22 19:40:28.708257: step: 180/529, loss: 0.0006405175081454217
2023-01-22 19:40:29.798529: step: 184/529, loss: 0.0039296685717999935
2023-01-22 19:40:30.898842: step: 188/529, loss: 0.006972936913371086
2023-01-22 19:40:32.005098: step: 192/529, loss: 0.0008915242506191134
2023-01-22 19:40:33.110245: step: 196/529, loss: 0.0054492829367518425
2023-01-22 19:40:34.228671: step: 200/529, loss: 5.854661139892414e-05
2023-01-22 19:40:35.325001: step: 204/529, loss: 0.00039613962871953845
2023-01-22 19:40:36.412285: step: 208/529, loss: 0.004649805836379528
2023-01-22 19:40:37.515548: step: 212/529, loss: 0.0004632494237739593
2023-01-22 19:40:38.604165: step: 216/529, loss: 3.7326213941923925e-07
2023-01-22 19:40:39.725000: step: 220/529, loss: 0.001702315523289144
2023-01-22 19:40:40.830975: step: 224/529, loss: 0.0007884991355240345
2023-01-22 19:40:41.924078: step: 228/529, loss: 0.008432826958596706
2023-01-22 19:40:43.014584: step: 232/529, loss: 0.0029229691717773676
2023-01-22 19:40:44.114742: step: 236/529, loss: 0.00044485388207249343
2023-01-22 19:40:45.227452: step: 240/529, loss: 0.0033600148744881153
2023-01-22 19:40:46.351219: step: 244/529, loss: 8.977828110801056e-05
2023-01-22 19:40:47.449610: step: 248/529, loss: 0.00847327895462513
2023-01-22 19:40:48.570613: step: 252/529, loss: 0.0049040899612009525
2023-01-22 19:40:49.678962: step: 256/529, loss: 0.008703096769750118
2023-01-22 19:40:50.781494: step: 260/529, loss: 0.006281276699155569
2023-01-22 19:40:51.890228: step: 264/529, loss: 0.0020060474053025246
2023-01-22 19:40:53.025464: step: 268/529, loss: 0.005718177184462547
2023-01-22 19:40:54.128102: step: 272/529, loss: 0.004087462089955807
2023-01-22 19:40:55.229499: step: 276/529, loss: 0.0018782959086820483
2023-01-22 19:40:56.342967: step: 280/529, loss: 0.004205251578241587
2023-01-22 19:40:57.463341: step: 284/529, loss: 0.007965457625687122
2023-01-22 19:40:58.573809: step: 288/529, loss: 0.005605509039014578
2023-01-22 19:40:59.687159: step: 292/529, loss: 0.006963943596929312
2023-01-22 19:41:00.776530: step: 296/529, loss: 0.0009007885819301009
2023-01-22 19:41:01.893340: step: 300/529, loss: 0.0017291028052568436
2023-01-22 19:41:03.002340: step: 304/529, loss: 0.006150687579065561
2023-01-22 19:41:04.096465: step: 308/529, loss: 0.00046188855776563287
2023-01-22 19:41:05.180062: step: 312/529, loss: 0.002029713010415435
2023-01-22 19:41:06.287160: step: 316/529, loss: 0.0005733241559937596
2023-01-22 19:41:07.390009: step: 320/529, loss: 0.0016295771347358823
2023-01-22 19:41:08.518769: step: 324/529, loss: 0.0064054992981255054
2023-01-22 19:41:09.641942: step: 328/529, loss: 0.006284876260906458
2023-01-22 19:41:10.754046: step: 332/529, loss: 0.0009272422175854445
2023-01-22 19:41:11.867037: step: 336/529, loss: 0.002939266385510564
2023-01-22 19:41:12.965523: step: 340/529, loss: 0.002147701568901539
2023-01-22 19:41:14.083511: step: 344/529, loss: 0.00019012653501704335
2023-01-22 19:41:15.178873: step: 348/529, loss: 0.006655167322605848
2023-01-22 19:41:16.283162: step: 352/529, loss: 0.0004504171956796199
2023-01-22 19:41:17.429514: step: 356/529, loss: 0.007450321689248085
2023-01-22 19:41:18.541891: step: 360/529, loss: 0.06278450042009354
2023-01-22 19:41:19.635686: step: 364/529, loss: 9.735236380947754e-05
2023-01-22 19:41:20.750759: step: 368/529, loss: 0.0072176530957221985
2023-01-22 19:41:21.841515: step: 372/529, loss: 0.010108393616974354
2023-01-22 19:41:22.960283: step: 376/529, loss: 0.0003134808212053031
2023-01-22 19:41:24.066918: step: 380/529, loss: 0.0006017570267431438
2023-01-22 19:41:25.179569: step: 384/529, loss: 0.006629629526287317
2023-01-22 19:41:26.291045: step: 388/529, loss: 0.0012141151819378138
2023-01-22 19:41:27.396087: step: 392/529, loss: 0.006044619716703892
2023-01-22 19:41:28.501271: step: 396/529, loss: 0.0016516806790605187
2023-01-22 19:41:29.623604: step: 400/529, loss: 0.01478307880461216
2023-01-22 19:41:30.717702: step: 404/529, loss: 0.0020569320768117905
2023-01-22 19:41:31.875421: step: 408/529, loss: 0.023637816309928894
2023-01-22 19:41:32.977424: step: 412/529, loss: 0.012432195246219635
2023-01-22 19:41:34.084768: step: 416/529, loss: 0.008101772516965866
2023-01-22 19:41:35.182613: step: 420/529, loss: 0.0018454748205840588
2023-01-22 19:41:36.279853: step: 424/529, loss: 0.0051687536761164665
2023-01-22 19:41:37.389263: step: 428/529, loss: 0.0154078658670187
2023-01-22 19:41:38.497530: step: 432/529, loss: 0.003809664398431778
2023-01-22 19:41:39.589057: step: 436/529, loss: 0.0017395021859556437
2023-01-22 19:41:40.697496: step: 440/529, loss: 0.004277052357792854
2023-01-22 19:41:41.843465: step: 444/529, loss: 0.005925856996327639
2023-01-22 19:41:42.956957: step: 448/529, loss: 0.0009125491487793624
2023-01-22 19:41:44.080579: step: 452/529, loss: 0.002475291956216097
2023-01-22 19:41:45.185871: step: 456/529, loss: 0.002568066818639636
2023-01-22 19:41:46.278925: step: 460/529, loss: 0.010470638051629066
2023-01-22 19:41:47.375389: step: 464/529, loss: 1.4093047866481356e-05
2023-01-22 19:41:48.492043: step: 468/529, loss: 3.222980740247294e-05
2023-01-22 19:41:49.622947: step: 472/529, loss: 0.003734169527888298
2023-01-22 19:41:50.729677: step: 476/529, loss: 0.0018193547148257494
2023-01-22 19:41:51.835857: step: 480/529, loss: 0.014440534636378288
2023-01-22 19:41:52.936856: step: 484/529, loss: 0.001823248341679573
2023-01-22 19:41:54.032716: step: 488/529, loss: 0.004446464125066996
2023-01-22 19:41:55.122197: step: 492/529, loss: 0.0001428972027497366
2023-01-22 19:41:56.238704: step: 496/529, loss: 0.0004731105000246316
2023-01-22 19:41:57.360833: step: 500/529, loss: 0.005937726236879826
2023-01-22 19:41:58.479213: step: 504/529, loss: 0.006876176223158836
2023-01-22 19:41:59.577860: step: 508/529, loss: 0.006428639404475689
2023-01-22 19:42:00.689281: step: 512/529, loss: 0.00403979467228055
2023-01-22 19:42:01.803425: step: 516/529, loss: 0.001402258756570518
2023-01-22 19:42:02.910345: step: 520/529, loss: 0.007169619202613831
2023-01-22 19:42:04.009579: step: 524/529, loss: 0.0021410060580819845
2023-01-22 19:42:05.141281: step: 528/529, loss: 0.010816287249326706
2023-01-22 19:42:06.242590: step: 532/529, loss: 0.005744959227740765
2023-01-22 19:42:07.341921: step: 536/529, loss: 0.006379859521985054
2023-01-22 19:42:08.456248: step: 540/529, loss: 0.000716628332156688
2023-01-22 19:42:09.574769: step: 544/529, loss: 0.008350600488483906
2023-01-22 19:42:10.690843: step: 548/529, loss: 0.0005022928235121071
2023-01-22 19:42:11.817062: step: 552/529, loss: 0.006073886062949896
2023-01-22 19:42:12.917967: step: 556/529, loss: 1.9644396161311306e-05
2023-01-22 19:42:14.035593: step: 560/529, loss: 0.0033455078955739737
2023-01-22 19:42:15.140935: step: 564/529, loss: 0.0031072634737938643
2023-01-22 19:42:16.245999: step: 568/529, loss: 0.0002251608675578609
2023-01-22 19:42:17.340511: step: 572/529, loss: 0.000593160220887512
2023-01-22 19:42:18.440013: step: 576/529, loss: 0.000989574589766562
2023-01-22 19:42:19.559756: step: 580/529, loss: 0.010913743637502193
2023-01-22 19:42:20.661590: step: 584/529, loss: 0.0010446750093251467
2023-01-22 19:42:21.769759: step: 588/529, loss: 0.0008054329082369804
2023-01-22 19:42:22.885875: step: 592/529, loss: 0.005038390401750803
2023-01-22 19:42:23.978852: step: 596/529, loss: 0.0031528063118457794
2023-01-22 19:42:25.085719: step: 600/529, loss: 0.0009920148877426982
2023-01-22 19:42:26.202397: step: 604/529, loss: 0.0004315426049288362
2023-01-22 19:42:27.312107: step: 608/529, loss: 0.0019793694373220205
2023-01-22 19:42:28.429737: step: 612/529, loss: 0.004922003485262394
2023-01-22 19:42:29.550448: step: 616/529, loss: 0.005950198974460363
2023-01-22 19:42:30.648440: step: 620/529, loss: 0.0022428338415920734
2023-01-22 19:42:31.756465: step: 624/529, loss: 0.0020557651296257973
2023-01-22 19:42:32.873687: step: 628/529, loss: 0.0024385626893490553
2023-01-22 19:42:33.992509: step: 632/529, loss: 0.004152493551373482
2023-01-22 19:42:35.102455: step: 636/529, loss: 0.011170807294547558
2023-01-22 19:42:36.201088: step: 640/529, loss: 1.6699037587386556e-05
2023-01-22 19:42:37.316941: step: 644/529, loss: 0.00025188561994582415
2023-01-22 19:42:38.428880: step: 648/529, loss: 0.00864182785153389
2023-01-22 19:42:39.546990: step: 652/529, loss: 0.005259454715996981
2023-01-22 19:42:40.675077: step: 656/529, loss: 0.008205665275454521
2023-01-22 19:42:41.762839: step: 660/529, loss: 0.004176001064479351
2023-01-22 19:42:42.877625: step: 664/529, loss: 0.0049326494336128235
2023-01-22 19:42:43.986588: step: 668/529, loss: 0.0002073399955406785
2023-01-22 19:42:45.104091: step: 672/529, loss: 0.00042785776895470917
2023-01-22 19:42:46.210034: step: 676/529, loss: 0.0007630366017110646
2023-01-22 19:42:47.321483: step: 680/529, loss: 0.0040321857668459415
2023-01-22 19:42:48.426577: step: 684/529, loss: 0.008868553675711155
2023-01-22 19:42:49.507998: step: 688/529, loss: 0.006499852053821087
2023-01-22 19:42:50.629847: step: 692/529, loss: 0.0064085922203958035
2023-01-22 19:42:51.732471: step: 696/529, loss: 0.0006844301242381334
2023-01-22 19:42:52.855405: step: 700/529, loss: 0.005194731056690216
2023-01-22 19:42:53.982843: step: 704/529, loss: 0.0031888349913060665
2023-01-22 19:42:55.092490: step: 708/529, loss: 0.0038050925359129906
2023-01-22 19:42:56.212871: step: 712/529, loss: 0.004980681464076042
2023-01-22 19:42:57.306663: step: 716/529, loss: 0.0008619455038569868
2023-01-22 19:42:58.423542: step: 720/529, loss: 0.009143445640802383
2023-01-22 19:42:59.572011: step: 724/529, loss: 0.002914109267294407
2023-01-22 19:43:00.692408: step: 728/529, loss: 0.01674947515130043
2023-01-22 19:43:01.798679: step: 732/529, loss: 0.0027589236851781607
2023-01-22 19:43:02.926850: step: 736/529, loss: 0.00457782344892621
2023-01-22 19:43:04.053400: step: 740/529, loss: 0.0031165701802819967
2023-01-22 19:43:05.140654: step: 744/529, loss: 1.4442201972997282e-05
2023-01-22 19:43:06.256761: step: 748/529, loss: 0.025098251178860664
2023-01-22 19:43:07.392332: step: 752/529, loss: 0.0007629389874637127
2023-01-22 19:43:08.521579: step: 756/529, loss: 0.005204486660659313
2023-01-22 19:43:09.629945: step: 760/529, loss: 0.006737139075994492
2023-01-22 19:43:10.735275: step: 764/529, loss: 0.005380614660680294
2023-01-22 19:43:11.848307: step: 768/529, loss: 0.0002633388212416321
2023-01-22 19:43:12.964249: step: 772/529, loss: 0.0009019324206747115
2023-01-22 19:43:14.081750: step: 776/529, loss: 0.002258089603856206
2023-01-22 19:43:15.172190: step: 780/529, loss: 0.0011565203312784433
2023-01-22 19:43:16.287708: step: 784/529, loss: 0.0732300654053688
2023-01-22 19:43:17.410048: step: 788/529, loss: 0.003253780771046877
2023-01-22 19:43:18.497165: step: 792/529, loss: 0.002508033998310566
2023-01-22 19:43:19.636545: step: 796/529, loss: 0.004601568914949894
2023-01-22 19:43:20.749553: step: 800/529, loss: 0.0003843796730507165
2023-01-22 19:43:21.828793: step: 804/529, loss: 0.0008514925139024854
2023-01-22 19:43:22.928120: step: 808/529, loss: 0.002466159872710705
2023-01-22 19:43:24.047111: step: 812/529, loss: 0.004014667589217424
2023-01-22 19:43:25.154139: step: 816/529, loss: 0.005253095179796219
2023-01-22 19:43:26.276911: step: 820/529, loss: 0.023806003853678703
2023-01-22 19:43:27.400298: step: 824/529, loss: 0.0177925955504179
2023-01-22 19:43:28.518444: step: 828/529, loss: 0.006049338728189468
2023-01-22 19:43:29.629170: step: 832/529, loss: 7.290684879990295e-05
2023-01-22 19:43:30.731585: step: 836/529, loss: 0.0028248184826225042
2023-01-22 19:43:31.870881: step: 840/529, loss: 0.001416673301719129
2023-01-22 19:43:32.986639: step: 844/529, loss: 0.003167527262121439
2023-01-22 19:43:34.111744: step: 848/529, loss: 0.002980906283482909
2023-01-22 19:43:35.226150: step: 852/529, loss: 0.000622231513261795
2023-01-22 19:43:36.337803: step: 856/529, loss: 6.845410098321736e-05
2023-01-22 19:43:37.451457: step: 860/529, loss: 0.00825956929475069
2023-01-22 19:43:38.575732: step: 864/529, loss: 0.01506503950804472
2023-01-22 19:43:39.708865: step: 868/529, loss: 0.0025807705242186785
2023-01-22 19:43:40.813628: step: 872/529, loss: 0.003535150783136487
2023-01-22 19:43:41.926013: step: 876/529, loss: 0.000918049190659076
2023-01-22 19:43:43.026292: step: 880/529, loss: 0.0010378474835306406
2023-01-22 19:43:44.140592: step: 884/529, loss: 0.005866731982678175
2023-01-22 19:43:45.275123: step: 888/529, loss: 0.005037650465965271
2023-01-22 19:43:46.378882: step: 892/529, loss: 0.0061570582911372185
2023-01-22 19:43:47.516998: step: 896/529, loss: 0.0037480811588466167
2023-01-22 19:43:48.603068: step: 900/529, loss: 0.012541557662189007
2023-01-22 19:43:49.707090: step: 904/529, loss: 0.004607129376381636
2023-01-22 19:43:50.838192: step: 908/529, loss: 0.0018726926064118743
2023-01-22 19:43:51.928281: step: 912/529, loss: 0.02313421294093132
2023-01-22 19:43:53.045706: step: 916/529, loss: 0.0042212773114442825
2023-01-22 19:43:54.163136: step: 920/529, loss: 1.41079981403891e-05
2023-01-22 19:43:55.272007: step: 924/529, loss: 4.5843273710488575e-07
2023-01-22 19:43:56.403865: step: 928/529, loss: 0.0012715106131508946
2023-01-22 19:43:57.491210: step: 932/529, loss: 0.0013334781397134066
2023-01-22 19:43:58.609696: step: 936/529, loss: 0.008069056086242199
2023-01-22 19:43:59.714466: step: 940/529, loss: 0.00025343330344185233
2023-01-22 19:44:00.819376: step: 944/529, loss: 0.0007796770660206676
2023-01-22 19:44:01.925321: step: 948/529, loss: 0.0068210759200155735
2023-01-22 19:44:03.037498: step: 952/529, loss: 0.027938488870859146
2023-01-22 19:44:04.165336: step: 956/529, loss: 0.012449776753783226
2023-01-22 19:44:05.284399: step: 960/529, loss: 0.007851033471524715
2023-01-22 19:44:06.384194: step: 964/529, loss: 0.017245260998606682
2023-01-22 19:44:07.501540: step: 968/529, loss: 0.01738094352185726
2023-01-22 19:44:08.625017: step: 972/529, loss: 0.008785337209701538
2023-01-22 19:44:09.744345: step: 976/529, loss: 0.003211799543350935
2023-01-22 19:44:10.843070: step: 980/529, loss: 0.01256631314754486
2023-01-22 19:44:11.942174: step: 984/529, loss: 7.312333764275536e-05
2023-01-22 19:44:13.048734: step: 988/529, loss: 0.0003245885600335896
2023-01-22 19:44:14.184568: step: 992/529, loss: 0.011345455422997475
2023-01-22 19:44:15.280222: step: 996/529, loss: 0.003959354944527149
2023-01-22 19:44:16.400983: step: 1000/529, loss: 0.009822244755923748
2023-01-22 19:44:17.531354: step: 1004/529, loss: 0.005414898507297039
2023-01-22 19:44:18.635401: step: 1008/529, loss: 0.007246408145874739
2023-01-22 19:44:19.716966: step: 1012/529, loss: 0.00025633323821239173
2023-01-22 19:44:20.824249: step: 1016/529, loss: 0.012919302098453045
2023-01-22 19:44:21.905773: step: 1020/529, loss: 0.002659374149516225
2023-01-22 19:44:23.021919: step: 1024/529, loss: 0.003732177196070552
2023-01-22 19:44:24.131836: step: 1028/529, loss: 0.0009060488664545119
2023-01-22 19:44:25.244534: step: 1032/529, loss: 0.008955580182373524
2023-01-22 19:44:26.337387: step: 1036/529, loss: 0.005297385156154633
2023-01-22 19:44:27.443786: step: 1040/529, loss: 0.0021100337617099285
2023-01-22 19:44:28.556021: step: 1044/529, loss: 0.0015339320525527
2023-01-22 19:44:29.644142: step: 1048/529, loss: 0.0031962525099515915
2023-01-22 19:44:30.745495: step: 1052/529, loss: 0.00037727487506344914
2023-01-22 19:44:31.884257: step: 1056/529, loss: 0.0032557810191065073
2023-01-22 19:44:33.020669: step: 1060/529, loss: 0.0031550107523798943
2023-01-22 19:44:34.108953: step: 1064/529, loss: 0.004502748139202595
2023-01-22 19:44:35.202637: step: 1068/529, loss: 0.0024195455480366945
2023-01-22 19:44:36.333246: step: 1072/529, loss: 0.004258297849446535
2023-01-22 19:44:37.448418: step: 1076/529, loss: 0.00346053927205503
2023-01-22 19:44:38.617418: step: 1080/529, loss: 0.004028636496514082
2023-01-22 19:44:39.725539: step: 1084/529, loss: 0.0013401623582467437
2023-01-22 19:44:40.840581: step: 1088/529, loss: 0.00923909805715084
2023-01-22 19:44:41.953385: step: 1092/529, loss: 0.0016524532111361623
2023-01-22 19:44:43.084416: step: 1096/529, loss: 0.0036014998331665993
2023-01-22 19:44:44.185990: step: 1100/529, loss: 0.006009596865624189
2023-01-22 19:44:45.271315: step: 1104/529, loss: 0.0002660062746144831
2023-01-22 19:44:46.379955: step: 1108/529, loss: 0.01304792333394289
2023-01-22 19:44:47.492501: step: 1112/529, loss: 0.0018842763965949416
2023-01-22 19:44:48.583005: step: 1116/529, loss: 0.014432252384722233
2023-01-22 19:44:49.690634: step: 1120/529, loss: 0.00583024974912405
2023-01-22 19:44:50.830104: step: 1124/529, loss: 0.00019042934582103044
2023-01-22 19:44:51.924999: step: 1128/529, loss: 0.00012445123866200447
2023-01-22 19:44:53.020651: step: 1132/529, loss: 0.009986771270632744
2023-01-22 19:44:54.125244: step: 1136/529, loss: 0.0010908894473686814
2023-01-22 19:44:55.230104: step: 1140/529, loss: 0.0015294832410290837
2023-01-22 19:44:56.346143: step: 1144/529, loss: 0.008392107672989368
2023-01-22 19:44:57.435444: step: 1148/529, loss: 0.0020511711481958628
2023-01-22 19:44:58.540463: step: 1152/529, loss: 0.00610328046604991
2023-01-22 19:44:59.656328: step: 1156/529, loss: 0.0035546545404940844
2023-01-22 19:45:00.764217: step: 1160/529, loss: 0.03642532601952553
2023-01-22 19:45:01.882231: step: 1164/529, loss: 0.0006725058192387223
2023-01-22 19:45:02.979733: step: 1168/529, loss: 0.0018742317333817482
2023-01-22 19:45:04.093649: step: 1172/529, loss: 0.0066394745372235775
2023-01-22 19:45:05.201885: step: 1176/529, loss: 0.007165821734815836
2023-01-22 19:45:06.297553: step: 1180/529, loss: 0.0013178761582821608
2023-01-22 19:45:07.395234: step: 1184/529, loss: 0.0007705226307734847
2023-01-22 19:45:08.496796: step: 1188/529, loss: 2.0272864276194014e-06
2023-01-22 19:45:09.642231: step: 1192/529, loss: 0.002795303473249078
2023-01-22 19:45:10.742987: step: 1196/529, loss: 0.013296723365783691
2023-01-22 19:45:11.831156: step: 1200/529, loss: 8.158142736647278e-05
2023-01-22 19:45:12.925520: step: 1204/529, loss: 0.0009482708992436528
2023-01-22 19:45:14.012962: step: 1208/529, loss: 0.0023630447685718536
2023-01-22 19:45:15.115201: step: 1212/529, loss: 0.0009397470275871456
2023-01-22 19:45:16.244189: step: 1216/529, loss: 0.03506022319197655
2023-01-22 19:45:17.368492: step: 1220/529, loss: 0.0057658851146698
2023-01-22 19:45:18.484073: step: 1224/529, loss: 0.007470401469618082
2023-01-22 19:45:19.587248: step: 1228/529, loss: 0.004173722583800554
2023-01-22 19:45:20.704312: step: 1232/529, loss: 0.06375173479318619
2023-01-22 19:45:21.805370: step: 1236/529, loss: 0.0022007934749126434
2023-01-22 19:45:22.902312: step: 1240/529, loss: 0.001349522382952273
2023-01-22 19:45:24.011951: step: 1244/529, loss: 0.0019629907328635454
2023-01-22 19:45:25.114818: step: 1248/529, loss: 0.002263437258079648
2023-01-22 19:45:26.207059: step: 1252/529, loss: 0.013698682188987732
2023-01-22 19:45:27.327328: step: 1256/529, loss: 0.0009694842738099396
2023-01-22 19:45:28.438492: step: 1260/529, loss: 0.001156351063400507
2023-01-22 19:45:29.538034: step: 1264/529, loss: 0.004087864421308041
2023-01-22 19:45:30.641365: step: 1268/529, loss: 9.240079816663638e-05
2023-01-22 19:45:31.745635: step: 1272/529, loss: 0.0028486757073551416
2023-01-22 19:45:32.860571: step: 1276/529, loss: 0.0068897828459739685
2023-01-22 19:45:33.995158: step: 1280/529, loss: 0.006369309965521097
2023-01-22 19:45:35.080858: step: 1284/529, loss: 0.0010332973906770349
2023-01-22 19:45:36.215852: step: 1288/529, loss: 0.0038308745715767145
2023-01-22 19:45:37.335464: step: 1292/529, loss: 0.005273086950182915
2023-01-22 19:45:38.449595: step: 1296/529, loss: 0.013699567876756191
2023-01-22 19:45:39.550205: step: 1300/529, loss: 0.002056204015389085
2023-01-22 19:45:40.651050: step: 1304/529, loss: 0.006813964806497097
2023-01-22 19:45:41.765250: step: 1308/529, loss: 0.003750395029783249
2023-01-22 19:45:42.875230: step: 1312/529, loss: 0.00574092660099268
2023-01-22 19:45:43.996901: step: 1316/529, loss: 3.545842628227547e-05
2023-01-22 19:45:45.100885: step: 1320/529, loss: 0.008565038442611694
2023-01-22 19:45:46.202710: step: 1324/529, loss: 0.004500707145780325
2023-01-22 19:45:47.307822: step: 1328/529, loss: 0.0008234553970396519
2023-01-22 19:45:48.428126: step: 1332/529, loss: 0.008897936902940273
2023-01-22 19:45:49.559476: step: 1336/529, loss: 0.0039969575591385365
2023-01-22 19:45:50.666146: step: 1340/529, loss: 3.910925079253502e-05
2023-01-22 19:45:51.777512: step: 1344/529, loss: 0.0026806683745235205
2023-01-22 19:45:52.873776: step: 1348/529, loss: 0.003770589828491211
2023-01-22 19:45:53.972087: step: 1352/529, loss: 0.0036758952774107456
2023-01-22 19:45:55.099955: step: 1356/529, loss: 0.006809667218476534
2023-01-22 19:45:56.214189: step: 1360/529, loss: 0.0037387895863503218
2023-01-22 19:45:57.323204: step: 1364/529, loss: 4.5424258132698014e-05
2023-01-22 19:45:58.428240: step: 1368/529, loss: 0.006170026026666164
2023-01-22 19:45:59.534329: step: 1372/529, loss: 0.005843598861247301
2023-01-22 19:46:00.646293: step: 1376/529, loss: 0.006097909528762102
2023-01-22 19:46:01.749411: step: 1380/529, loss: 0.00045167311327531934
2023-01-22 19:46:02.875060: step: 1384/529, loss: 0.0012006715405732393
2023-01-22 19:46:03.981886: step: 1388/529, loss: 0.001215904951095581
2023-01-22 19:46:05.088794: step: 1392/529, loss: 0.00017230652156285942
2023-01-22 19:46:06.182548: step: 1396/529, loss: 3.0342256650328636e-05
2023-01-22 19:46:07.298039: step: 1400/529, loss: 0.002087270375341177
2023-01-22 19:46:08.405359: step: 1404/529, loss: 0.0006398286786861718
2023-01-22 19:46:09.532491: step: 1408/529, loss: 0.004571040626615286
2023-01-22 19:46:10.644493: step: 1412/529, loss: 0.0037977604661136866
2023-01-22 19:46:11.733586: step: 1416/529, loss: 0.0
2023-01-22 19:46:12.830684: step: 1420/529, loss: 0.006175719201564789
2023-01-22 19:46:13.962234: step: 1424/529, loss: 0.00027760930242948234
2023-01-22 19:46:15.091881: step: 1428/529, loss: 0.003787989029660821
2023-01-22 19:46:16.195435: step: 1432/529, loss: 0.0024578107986599207
2023-01-22 19:46:17.304201: step: 1436/529, loss: 0.0030939143616706133
2023-01-22 19:46:18.427950: step: 1440/529, loss: 0.001311361906118691
2023-01-22 19:46:19.535552: step: 1444/529, loss: 0.0023455703631043434
2023-01-22 19:46:20.628624: step: 1448/529, loss: 0.0017849833238869905
2023-01-22 19:46:21.702159: step: 1452/529, loss: 0.0004918168415315449
2023-01-22 19:46:22.854711: step: 1456/529, loss: 6.398432742571458e-05
2023-01-22 19:46:23.960853: step: 1460/529, loss: 0.0005941387498751283
2023-01-22 19:46:25.071468: step: 1464/529, loss: 0.003601847914978862
2023-01-22 19:46:26.174274: step: 1468/529, loss: 0.00023561141279060394
2023-01-22 19:46:27.329440: step: 1472/529, loss: 0.0022896183654665947
2023-01-22 19:46:28.438405: step: 1476/529, loss: 0.0027066089678555727
2023-01-22 19:46:29.545352: step: 1480/529, loss: 0.013704094104468822
2023-01-22 19:46:30.647296: step: 1484/529, loss: 0.003100431989878416
2023-01-22 19:46:31.725127: step: 1488/529, loss: 0.0008488218300044537
2023-01-22 19:46:32.827809: step: 1492/529, loss: 0.0003397142281755805
2023-01-22 19:46:33.916833: step: 1496/529, loss: 0.004243710543960333
2023-01-22 19:46:35.036990: step: 1500/529, loss: 0.002570914104580879
2023-01-22 19:46:36.159900: step: 1504/529, loss: 0.00468383589759469
2023-01-22 19:46:37.247979: step: 1508/529, loss: 0.027202624827623367
2023-01-22 19:46:38.324913: step: 1512/529, loss: 0.0005272456910461187
2023-01-22 19:46:39.441617: step: 1516/529, loss: 0.009197598323225975
2023-01-22 19:46:40.553767: step: 1520/529, loss: 0.0020008489955216646
2023-01-22 19:46:41.658394: step: 1524/529, loss: 0.012477155774831772
2023-01-22 19:46:42.772025: step: 1528/529, loss: 0.0005014143534936011
2023-01-22 19:46:43.875632: step: 1532/529, loss: 0.0012618745677173138
2023-01-22 19:46:45.004991: step: 1536/529, loss: 0.0023072431795299053
2023-01-22 19:46:46.108364: step: 1540/529, loss: 0.001811041496694088
2023-01-22 19:46:47.222239: step: 1544/529, loss: 0.0018031415529549122
2023-01-22 19:46:48.326442: step: 1548/529, loss: 0.003972366917878389
2023-01-22 19:46:49.420534: step: 1552/529, loss: 0.008141478523612022
2023-01-22 19:46:50.546222: step: 1556/529, loss: 0.0010068807750940323
2023-01-22 19:46:51.706136: step: 1560/529, loss: 0.0021519185975193977
2023-01-22 19:46:52.785314: step: 1564/529, loss: 0.0018538638250902295
2023-01-22 19:46:53.877581: step: 1568/529, loss: 0.007912657223641872
2023-01-22 19:46:54.979914: step: 1572/529, loss: 0.003314683912321925
2023-01-22 19:46:56.099939: step: 1576/529, loss: 8.966632594820112e-05
2023-01-22 19:46:57.204973: step: 1580/529, loss: 0.012869778089225292
2023-01-22 19:46:58.320621: step: 1584/529, loss: 0.0020855716429650784
2023-01-22 19:46:59.425896: step: 1588/529, loss: 0.004303572233766317
2023-01-22 19:47:00.541926: step: 1592/529, loss: 0.0006219679489731789
2023-01-22 19:47:01.658546: step: 1596/529, loss: 0.00776786869391799
2023-01-22 19:47:02.764934: step: 1600/529, loss: 0.0009899999713525176
2023-01-22 19:47:03.902887: step: 1604/529, loss: 0.007224968168884516
2023-01-22 19:47:04.986124: step: 1608/529, loss: 0.00024036105605773628
2023-01-22 19:47:06.081545: step: 1612/529, loss: 0.00498131662607193
2023-01-22 19:47:07.205216: step: 1616/529, loss: 0.006104725878685713
2023-01-22 19:47:08.310142: step: 1620/529, loss: 0.005027460400015116
2023-01-22 19:47:09.410380: step: 1624/529, loss: 0.0059813326224684715
2023-01-22 19:47:10.495745: step: 1628/529, loss: 0.004766613710671663
2023-01-22 19:47:11.611126: step: 1632/529, loss: 0.0012144464999437332
2023-01-22 19:47:12.735312: step: 1636/529, loss: 0.0011972025968134403
2023-01-22 19:47:13.839838: step: 1640/529, loss: 0.002710269298404455
2023-01-22 19:47:14.947079: step: 1644/529, loss: 0.0037481330800801516
2023-01-22 19:47:16.045582: step: 1648/529, loss: 0.028278984129428864
2023-01-22 19:47:17.160692: step: 1652/529, loss: 0.003947314340621233
2023-01-22 19:47:18.264102: step: 1656/529, loss: 0.0066324397921562195
2023-01-22 19:47:19.390663: step: 1660/529, loss: 0.004012054763734341
2023-01-22 19:47:20.503499: step: 1664/529, loss: 0.0036920784041285515
2023-01-22 19:47:21.601884: step: 1668/529, loss: 0.004566891118884087
2023-01-22 19:47:22.729757: step: 1672/529, loss: 0.00865353737026453
2023-01-22 19:47:23.827779: step: 1676/529, loss: 0.026723137125372887
2023-01-22 19:47:24.952444: step: 1680/529, loss: 0.0040269517339766026
2023-01-22 19:47:26.083543: step: 1684/529, loss: 0.0004061144427396357
2023-01-22 19:47:27.193788: step: 1688/529, loss: 0.0010386602953076363
2023-01-22 19:47:28.329546: step: 1692/529, loss: 0.0006115996511653066
2023-01-22 19:47:29.446067: step: 1696/529, loss: 0.006431979592889547
2023-01-22 19:47:30.574722: step: 1700/529, loss: 0.0007895925082266331
2023-01-22 19:47:31.700262: step: 1704/529, loss: 0.006763428915292025
2023-01-22 19:47:32.806221: step: 1708/529, loss: 0.004503482487052679
2023-01-22 19:47:33.920677: step: 1712/529, loss: 0.0024288950953632593
2023-01-22 19:47:35.033522: step: 1716/529, loss: 0.0016698454273864627
2023-01-22 19:47:36.148692: step: 1720/529, loss: 0.008600680157542229
2023-01-22 19:47:37.253106: step: 1724/529, loss: 0.009262578561902046
2023-01-22 19:47:38.356184: step: 1728/529, loss: 0.005364392884075642
2023-01-22 19:47:39.441628: step: 1732/529, loss: 0.00012965862697456032
2023-01-22 19:47:40.577476: step: 1736/529, loss: 0.006011847872287035
2023-01-22 19:47:41.687225: step: 1740/529, loss: 0.00032434886088594794
2023-01-22 19:47:42.785030: step: 1744/529, loss: 0.0036722864024341106
2023-01-22 19:47:43.868415: step: 1748/529, loss: 0.00034246567520312965
2023-01-22 19:47:44.961017: step: 1752/529, loss: 0.006833645049482584
2023-01-22 19:47:46.065970: step: 1756/529, loss: 0.008699985221028328
2023-01-22 19:47:47.161260: step: 1760/529, loss: 0.008430399931967258
2023-01-22 19:47:48.291878: step: 1764/529, loss: 0.025292176753282547
2023-01-22 19:47:49.405351: step: 1768/529, loss: 0.0013584656408056617
2023-01-22 19:47:50.512155: step: 1772/529, loss: 0.0020845450926572084
2023-01-22 19:47:51.628002: step: 1776/529, loss: 0.005831795744597912
2023-01-22 19:47:52.750175: step: 1780/529, loss: 0.0007305140607059002
2023-01-22 19:47:53.847397: step: 1784/529, loss: 0.0005277474992908537
2023-01-22 19:47:54.975960: step: 1788/529, loss: 0.0026804453227669
2023-01-22 19:47:56.116449: step: 1792/529, loss: 0.0037544609513133764
2023-01-22 19:47:57.238178: step: 1796/529, loss: 0.002447819337248802
2023-01-22 19:47:58.346001: step: 1800/529, loss: 0.006819633301347494
2023-01-22 19:47:59.462382: step: 1804/529, loss: 0.014861439354717731
2023-01-22 19:48:00.557296: step: 1808/529, loss: 0.01005969475954771
2023-01-22 19:48:01.677385: step: 1812/529, loss: 0.0026143486611545086
2023-01-22 19:48:02.792295: step: 1816/529, loss: 0.0017141166608780622
2023-01-22 19:48:03.913042: step: 1820/529, loss: 0.00028625846607610583
2023-01-22 19:48:05.011622: step: 1824/529, loss: 0.009886933490633965
2023-01-22 19:48:06.126267: step: 1828/529, loss: 0.008462507277727127
2023-01-22 19:48:07.259807: step: 1832/529, loss: 0.002373362658545375
2023-01-22 19:48:08.380430: step: 1836/529, loss: 0.010799266397953033
2023-01-22 19:48:09.472046: step: 1840/529, loss: 0.0023878805804997683
2023-01-22 19:48:10.555678: step: 1844/529, loss: 0.00037746719317510724
2023-01-22 19:48:11.657859: step: 1848/529, loss: 0.002651546848937869
2023-01-22 19:48:12.751331: step: 1852/529, loss: 0.0016376536805182695
2023-01-22 19:48:13.875035: step: 1856/529, loss: 0.00024241811479441822
2023-01-22 19:48:14.979206: step: 1860/529, loss: 0.04234139248728752
2023-01-22 19:48:16.085866: step: 1864/529, loss: 0.012446251697838306
2023-01-22 19:48:17.176393: step: 1868/529, loss: 0.000920478836633265
2023-01-22 19:48:18.308651: step: 1872/529, loss: 0.007537745870649815
2023-01-22 19:48:19.424169: step: 1876/529, loss: 1.1320285011606757e-05
2023-01-22 19:48:20.533800: step: 1880/529, loss: 0.0031365377362817526
2023-01-22 19:48:21.645869: step: 1884/529, loss: 0.003990591503679752
2023-01-22 19:48:22.762612: step: 1888/529, loss: 0.009194576181471348
2023-01-22 19:48:23.871054: step: 1892/529, loss: 0.0014267516089603305
2023-01-22 19:48:24.985054: step: 1896/529, loss: 0.0035343386698514223
2023-01-22 19:48:26.069662: step: 1900/529, loss: 0.0096924202516675
2023-01-22 19:48:27.217476: step: 1904/529, loss: 0.003925623372197151
2023-01-22 19:48:28.330238: step: 1908/529, loss: 0.0009244598331861198
2023-01-22 19:48:29.460376: step: 1912/529, loss: 0.0001163346751127392
2023-01-22 19:48:30.563417: step: 1916/529, loss: 0.009144597686827183
2023-01-22 19:48:31.665298: step: 1920/529, loss: 0.013364441692829132
2023-01-22 19:48:32.763289: step: 1924/529, loss: 0.003969738259911537
2023-01-22 19:48:33.863810: step: 1928/529, loss: 0.006603530142456293
2023-01-22 19:48:34.979581: step: 1932/529, loss: 0.004993661306798458
2023-01-22 19:48:36.091621: step: 1936/529, loss: 0.0001218821998918429
2023-01-22 19:48:37.207647: step: 1940/529, loss: 0.004339583683758974
2023-01-22 19:48:38.310451: step: 1944/529, loss: 0.00029273389372974634
2023-01-22 19:48:39.450520: step: 1948/529, loss: 0.00806443765759468
2023-01-22 19:48:40.579206: step: 1952/529, loss: 0.0008818538044579327
2023-01-22 19:48:41.699619: step: 1956/529, loss: 0.0025958630722016096
2023-01-22 19:48:42.818579: step: 1960/529, loss: 0.0037159130442887545
2023-01-22 19:48:43.957024: step: 1964/529, loss: 0.0017035230994224548
2023-01-22 19:48:45.061763: step: 1968/529, loss: 0.0020899998489767313
2023-01-22 19:48:46.163164: step: 1972/529, loss: 0.0015551656251773238
2023-01-22 19:48:47.263215: step: 1976/529, loss: 0.0018237102776765823
2023-01-22 19:48:48.382000: step: 1980/529, loss: 0.005107039585709572
2023-01-22 19:48:49.484072: step: 1984/529, loss: 0.004629435949027538
2023-01-22 19:48:50.597232: step: 1988/529, loss: 0.006663202308118343
2023-01-22 19:48:51.710878: step: 1992/529, loss: 0.0038683104794472456
2023-01-22 19:48:52.794163: step: 1996/529, loss: 0.0008164198370650411
2023-01-22 19:48:53.893946: step: 2000/529, loss: 0.004791025537997484
2023-01-22 19:48:54.991456: step: 2004/529, loss: 0.004603276029229164
2023-01-22 19:48:56.099513: step: 2008/529, loss: 6.202576332725585e-05
2023-01-22 19:48:57.232425: step: 2012/529, loss: 0.0008024513372220099
2023-01-22 19:48:58.356605: step: 2016/529, loss: 0.0019630303140729666
2023-01-22 19:48:59.464716: step: 2020/529, loss: 0.0017096453811973333
2023-01-22 19:49:00.561621: step: 2024/529, loss: 2.481234332663007e-05
2023-01-22 19:49:01.682049: step: 2028/529, loss: 0.0018272375455126166
2023-01-22 19:49:02.788842: step: 2032/529, loss: 8.301223715534434e-06
2023-01-22 19:49:03.892334: step: 2036/529, loss: 0.002904096618294716
2023-01-22 19:49:05.027853: step: 2040/529, loss: 0.011072534136474133
2023-01-22 19:49:06.144929: step: 2044/529, loss: 0.004040045663714409
2023-01-22 19:49:07.265426: step: 2048/529, loss: 0.003164100693538785
2023-01-22 19:49:08.370149: step: 2052/529, loss: 0.003730867989361286
2023-01-22 19:49:09.475610: step: 2056/529, loss: 0.0008495133952237666
2023-01-22 19:49:10.576770: step: 2060/529, loss: 0.0006894392427057028
2023-01-22 19:49:11.733635: step: 2064/529, loss: 0.004105313681066036
2023-01-22 19:49:12.872622: step: 2068/529, loss: 0.005463628098368645
2023-01-22 19:49:13.970686: step: 2072/529, loss: 0.003398022847250104
2023-01-22 19:49:15.063753: step: 2076/529, loss: 0.012395462952554226
2023-01-22 19:49:16.168061: step: 2080/529, loss: 0.004758353810757399
2023-01-22 19:49:17.302528: step: 2084/529, loss: 0.0029524625279009342
2023-01-22 19:49:18.432057: step: 2088/529, loss: 0.0026175796519964933
2023-01-22 19:49:19.550596: step: 2092/529, loss: 0.0030490770004689693
2023-01-22 19:49:20.662021: step: 2096/529, loss: 0.002107314532622695
2023-01-22 19:49:21.779332: step: 2100/529, loss: 0.0012011931976303458
2023-01-22 19:49:22.879001: step: 2104/529, loss: 0.004759353119879961
2023-01-22 19:49:23.992298: step: 2108/529, loss: 0.002035393612459302
2023-01-22 19:49:25.086141: step: 2112/529, loss: 0.00014560946146957576
2023-01-22 19:49:26.197512: step: 2116/529, loss: 0.0034651432652026415
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3332070182724252, 'r': 0.326252033071293, 'f1': 0.3296928502944802}, 'combined': 0.24293157390119594, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3759483647852441, 'r': 0.29906464373730857, 'f1': 0.3331279911900136}, 'combined': 0.20475183848752054, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33545741318412886, 'r': 0.3437324537370581, 'f1': 0.33954452318543504}, 'combined': 0.2501907012945311, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3578513079212876, 'r': 0.310096454004582, 'f1': 0.33226676687213336}, 'combined': 0.20422250061409172, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33965916210982, 'r': 0.34288173480535905, 'f1': 0.3412628408733224}, 'combined': 0.25145683011718495, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3682182046694855, 'r': 0.2977626001396532, 'f1': 0.32926357411325946}, 'combined': 0.20336867812877796, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36607142857142855, 'r': 0.44565217391304346, 'f1': 0.4019607843137254}, 'combined': 0.2009803921568627, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 12}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 13
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 19:51:51.134392: step: 4/529, loss: 0.0006948032532818615
2023-01-22 19:51:52.229865: step: 8/529, loss: 0.0001499262871220708
2023-01-22 19:51:53.346114: step: 12/529, loss: 0.0006850948557257652
2023-01-22 19:51:54.422040: step: 16/529, loss: 0.007784007582813501
2023-01-22 19:51:55.521083: step: 20/529, loss: 0.0006867876509204507
2023-01-22 19:51:56.618626: step: 24/529, loss: 0.0008491107728332281
2023-01-22 19:51:57.740979: step: 28/529, loss: 0.001975971506908536
2023-01-22 19:51:58.850400: step: 32/529, loss: 0.0033514846581965685
2023-01-22 19:51:59.952398: step: 36/529, loss: 0.0018445549067109823
2023-01-22 19:52:01.067250: step: 40/529, loss: 0.002414599061012268
2023-01-22 19:52:02.190552: step: 44/529, loss: 0.0045388913713395596
2023-01-22 19:52:03.289613: step: 48/529, loss: 0.00047159349196590483
2023-01-22 19:52:04.398341: step: 52/529, loss: 0.0036370062734931707
2023-01-22 19:52:05.498518: step: 56/529, loss: 0.0033063916489481926
2023-01-22 19:52:06.571284: step: 60/529, loss: 0.000929742818698287
2023-01-22 19:52:07.662838: step: 64/529, loss: 0.0016535071190446615
2023-01-22 19:52:08.767100: step: 68/529, loss: 0.0004412627313286066
2023-01-22 19:52:09.874012: step: 72/529, loss: 0.0034161717630922794
2023-01-22 19:52:10.974138: step: 76/529, loss: 0.00904846005141735
2023-01-22 19:52:12.079716: step: 80/529, loss: 0.00037185585824772716
2023-01-22 19:52:13.170975: step: 84/529, loss: 0.0009800201514735818
2023-01-22 19:52:14.280876: step: 88/529, loss: 0.0006961131002753973
2023-01-22 19:52:15.379339: step: 92/529, loss: 0.004999516066163778
2023-01-22 19:52:16.483278: step: 96/529, loss: 0.0010828980011865497
2023-01-22 19:52:17.611602: step: 100/529, loss: 0.0024024604354053736
2023-01-22 19:52:18.713644: step: 104/529, loss: 0.00323964050039649
2023-01-22 19:52:19.814616: step: 108/529, loss: 0.0012623514048755169
2023-01-22 19:52:20.917956: step: 112/529, loss: 0.003003516234457493
2023-01-22 19:52:22.014356: step: 116/529, loss: 0.0013126255944371223
2023-01-22 19:52:23.133523: step: 120/529, loss: 0.0034391535446047783
2023-01-22 19:52:24.244448: step: 124/529, loss: 0.0034552402794361115
2023-01-22 19:52:25.352228: step: 128/529, loss: 0.00046613425365649164
2023-01-22 19:52:26.445989: step: 132/529, loss: 0.003780502825975418
2023-01-22 19:52:27.557515: step: 136/529, loss: 0.000349131238181144
2023-01-22 19:52:28.667731: step: 140/529, loss: 5.621160994451202e-07
2023-01-22 19:52:29.769019: step: 144/529, loss: 0.00248551438562572
2023-01-22 19:52:30.887874: step: 148/529, loss: 0.0037998247426003218
2023-01-22 19:52:31.993057: step: 152/529, loss: 0.05563031882047653
2023-01-22 19:52:33.121524: step: 156/529, loss: 6.327210576273501e-05
2023-01-22 19:52:34.252482: step: 160/529, loss: 0.009362129494547844
2023-01-22 19:52:35.387970: step: 164/529, loss: 0.00032673621899448335
2023-01-22 19:52:36.508526: step: 168/529, loss: 0.008832283318042755
2023-01-22 19:52:37.628007: step: 172/529, loss: 0.0010492218425497413
2023-01-22 19:52:38.718649: step: 176/529, loss: 0.006012359168380499
2023-01-22 19:52:39.832461: step: 180/529, loss: 0.0029631650540977716
2023-01-22 19:52:40.941053: step: 184/529, loss: 0.007308172062039375
2023-01-22 19:52:42.053594: step: 188/529, loss: 0.004614134784787893
2023-01-22 19:52:43.146559: step: 192/529, loss: 2.1989408196532167e-06
2023-01-22 19:52:44.244160: step: 196/529, loss: 0.004140627104789019
2023-01-22 19:52:45.364244: step: 200/529, loss: 0.0024242205545306206
2023-01-22 19:52:46.487682: step: 204/529, loss: 0.0029170934576541185
2023-01-22 19:52:47.622019: step: 208/529, loss: 0.00487776892259717
2023-01-22 19:52:48.725642: step: 212/529, loss: 0.00011802694643847644
2023-01-22 19:52:49.844994: step: 216/529, loss: 0.005051000043749809
2023-01-22 19:52:50.980196: step: 220/529, loss: 0.01882794126868248
2023-01-22 19:52:52.091702: step: 224/529, loss: 0.026438212022185326
2023-01-22 19:52:53.209032: step: 228/529, loss: 0.0018311140593141317
2023-01-22 19:52:54.301193: step: 232/529, loss: 0.004033572040498257
2023-01-22 19:52:55.408486: step: 236/529, loss: 0.006434094626456499
2023-01-22 19:52:56.513516: step: 240/529, loss: 0.00786223541945219
2023-01-22 19:52:57.645706: step: 244/529, loss: 0.0021165211219340563
2023-01-22 19:52:58.738315: step: 248/529, loss: 0.0071181440725922585
2023-01-22 19:52:59.831135: step: 252/529, loss: 5.6450884585501626e-05
2023-01-22 19:53:00.937821: step: 256/529, loss: 0.004464322235435247
2023-01-22 19:53:02.036665: step: 260/529, loss: 0.003140700049698353
2023-01-22 19:53:03.150334: step: 264/529, loss: 0.0061014434322714806
2023-01-22 19:53:04.263687: step: 268/529, loss: 0.0012937269639223814
2023-01-22 19:53:05.369888: step: 272/529, loss: 0.00657568359747529
2023-01-22 19:53:06.465643: step: 276/529, loss: 0.00027721558581106365
2023-01-22 19:53:07.589107: step: 280/529, loss: 0.0029196091927587986
2023-01-22 19:53:08.710307: step: 284/529, loss: 0.0006043731118552387
2023-01-22 19:53:09.824650: step: 288/529, loss: 0.0011730119585990906
2023-01-22 19:53:10.950056: step: 292/529, loss: 0.0007926944526843727
2023-01-22 19:53:12.061605: step: 296/529, loss: 0.0007542414823547006
2023-01-22 19:53:13.238410: step: 300/529, loss: 0.0015026562614366412
2023-01-22 19:53:14.370450: step: 304/529, loss: 0.005537477787584066
2023-01-22 19:53:15.472560: step: 308/529, loss: 0.00019311800133436918
2023-01-22 19:53:16.577111: step: 312/529, loss: 0.0028398402500897646
2023-01-22 19:53:17.697627: step: 316/529, loss: 0.008974147029221058
2023-01-22 19:53:18.827509: step: 320/529, loss: 0.009728076867759228
2023-01-22 19:53:19.965888: step: 324/529, loss: 0.004854380618780851
2023-01-22 19:53:21.082317: step: 328/529, loss: 0.002332303673028946
2023-01-22 19:53:22.186286: step: 332/529, loss: 0.0008780196076259017
2023-01-22 19:53:23.291156: step: 336/529, loss: 0.0008499495452269912
2023-01-22 19:53:24.418149: step: 340/529, loss: 0.019866853952407837
2023-01-22 19:53:25.536255: step: 344/529, loss: 0.003416645573452115
2023-01-22 19:53:26.654269: step: 348/529, loss: 0.002405986189842224
2023-01-22 19:53:27.769899: step: 352/529, loss: 0.001651348895393312
2023-01-22 19:53:28.884550: step: 356/529, loss: 0.0022714484948664904
2023-01-22 19:53:29.997077: step: 360/529, loss: 0.003909091465175152
2023-01-22 19:53:31.109221: step: 364/529, loss: 0.001101157278753817
2023-01-22 19:53:32.229189: step: 368/529, loss: 0.0008100132690742612
2023-01-22 19:53:33.331534: step: 372/529, loss: 0.007777967490255833
2023-01-22 19:53:34.459039: step: 376/529, loss: 0.00048486358718946576
2023-01-22 19:53:35.579622: step: 380/529, loss: 0.0012975268764421344
2023-01-22 19:53:36.708809: step: 384/529, loss: 0.0018789772875607014
2023-01-22 19:53:37.813887: step: 388/529, loss: 0.0035135129000991583
2023-01-22 19:53:38.914466: step: 392/529, loss: 0.0006281780079007149
2023-01-22 19:53:40.014639: step: 396/529, loss: 0.00021168992680031806
2023-01-22 19:53:41.109646: step: 400/529, loss: 8.455010538455099e-05
2023-01-22 19:53:42.215172: step: 404/529, loss: 5.767868788097985e-05
2023-01-22 19:53:43.318689: step: 408/529, loss: 0.0007190883043222129
2023-01-22 19:53:44.427585: step: 412/529, loss: 0.0007240864797495306
2023-01-22 19:53:45.537978: step: 416/529, loss: 0.0005532549694180489
2023-01-22 19:53:46.650332: step: 420/529, loss: 0.0013095646863803267
2023-01-22 19:53:47.777035: step: 424/529, loss: 0.0037706487346440554
2023-01-22 19:53:48.871691: step: 428/529, loss: 0.011104962788522243
2023-01-22 19:53:49.968190: step: 432/529, loss: 0.0020567597821354866
2023-01-22 19:53:51.082861: step: 436/529, loss: 0.0046827602200210094
2023-01-22 19:53:52.179080: step: 440/529, loss: 0.008268962614238262
2023-01-22 19:53:53.274497: step: 444/529, loss: 0.0077894278801977634
2023-01-22 19:53:54.381061: step: 448/529, loss: 0.0022867717780172825
2023-01-22 19:53:55.480911: step: 452/529, loss: 0.00026830582646653056
2023-01-22 19:53:56.594552: step: 456/529, loss: 0.0026021983940154314
2023-01-22 19:53:57.674211: step: 460/529, loss: 0.018371181562542915
2023-01-22 19:53:58.805327: step: 464/529, loss: 0.013064390048384666
2023-01-22 19:53:59.896422: step: 468/529, loss: 0.009543689899146557
2023-01-22 19:54:01.012176: step: 472/529, loss: 0.009290165267884731
2023-01-22 19:54:02.109998: step: 476/529, loss: 0.0010082634398713708
2023-01-22 19:54:03.200054: step: 480/529, loss: 0.000775691878516227
2023-01-22 19:54:04.285963: step: 484/529, loss: 0.012369402684271336
2023-01-22 19:54:05.395651: step: 488/529, loss: 0.018461138010025024
2023-01-22 19:54:06.505650: step: 492/529, loss: 0.004069300834089518
2023-01-22 19:54:07.634195: step: 496/529, loss: 0.001836001523770392
2023-01-22 19:54:08.747341: step: 500/529, loss: 0.014671975746750832
2023-01-22 19:54:09.856094: step: 504/529, loss: 9.197022882290184e-05
2023-01-22 19:54:10.984791: step: 508/529, loss: 6.764496356481686e-05
2023-01-22 19:54:12.112682: step: 512/529, loss: 0.013049319386482239
2023-01-22 19:54:13.238346: step: 516/529, loss: 0.012440884485840797
2023-01-22 19:54:14.347924: step: 520/529, loss: 0.004193383734673262
2023-01-22 19:54:15.481630: step: 524/529, loss: 0.013714454136788845
2023-01-22 19:54:16.591630: step: 528/529, loss: 0.003881119191646576
2023-01-22 19:54:17.704970: step: 532/529, loss: 0.00396935036405921
2023-01-22 19:54:18.805941: step: 536/529, loss: 0.02821853756904602
2023-01-22 19:54:19.900479: step: 540/529, loss: 0.006639223080128431
2023-01-22 19:54:21.008781: step: 544/529, loss: 0.005402149632573128
2023-01-22 19:54:22.110787: step: 548/529, loss: 0.004063083324581385
2023-01-22 19:54:23.231081: step: 552/529, loss: 0.010244485922157764
2023-01-22 19:54:24.325331: step: 556/529, loss: 0.003431206103414297
2023-01-22 19:54:25.421344: step: 560/529, loss: 0.0006999879842624068
2023-01-22 19:54:26.536078: step: 564/529, loss: 0.015978271141648293
2023-01-22 19:54:27.639413: step: 568/529, loss: 0.015868045389652252
2023-01-22 19:54:28.733402: step: 572/529, loss: 0.0075306762009859085
2023-01-22 19:54:29.814099: step: 576/529, loss: 0.004426661413162947
2023-01-22 19:54:30.932580: step: 580/529, loss: 0.002008965704590082
2023-01-22 19:54:32.032051: step: 584/529, loss: 0.020740127190947533
2023-01-22 19:54:33.143535: step: 588/529, loss: 0.007090700324624777
2023-01-22 19:54:34.244400: step: 592/529, loss: 0.00010234750516247004
2023-01-22 19:54:35.337919: step: 596/529, loss: 0.00015524840273428708
2023-01-22 19:54:36.436336: step: 600/529, loss: 0.0001827776723075658
2023-01-22 19:54:37.541175: step: 604/529, loss: 0.003889684798195958
2023-01-22 19:54:38.641086: step: 608/529, loss: 0.0015885920729488134
2023-01-22 19:54:39.774023: step: 612/529, loss: 0.005676168482750654
2023-01-22 19:54:40.895912: step: 616/529, loss: 0.013380931690335274
2023-01-22 19:54:42.003476: step: 620/529, loss: 0.0006388660985976458
2023-01-22 19:54:43.146297: step: 624/529, loss: 0.01510299276560545
2023-01-22 19:54:44.254612: step: 628/529, loss: 0.0030728622805327177
2023-01-22 19:54:45.351230: step: 632/529, loss: 0.0009192724246531725
2023-01-22 19:54:46.445049: step: 636/529, loss: 0.003525824286043644
2023-01-22 19:54:47.527387: step: 640/529, loss: 0.0011931014014407992
2023-01-22 19:54:48.659765: step: 644/529, loss: 0.007567007560282946
2023-01-22 19:54:49.763884: step: 648/529, loss: 0.00481884041801095
2023-01-22 19:54:50.921697: step: 652/529, loss: 0.0004379861056804657
2023-01-22 19:54:52.052813: step: 656/529, loss: 0.00036360116791911423
2023-01-22 19:54:53.168913: step: 660/529, loss: 0.006468756124377251
2023-01-22 19:54:54.271724: step: 664/529, loss: 0.022208135575056076
2023-01-22 19:54:55.390022: step: 668/529, loss: 0.006527363322675228
2023-01-22 19:54:56.475088: step: 672/529, loss: 0.0002511840721126646
2023-01-22 19:54:57.562998: step: 676/529, loss: 0.0011463487753644586
2023-01-22 19:54:58.673197: step: 680/529, loss: 0.007166531402617693
2023-01-22 19:54:59.764000: step: 684/529, loss: 0.005786821246147156
2023-01-22 19:55:00.883348: step: 688/529, loss: 0.00015440903371199965
2023-01-22 19:55:02.012226: step: 692/529, loss: 0.01104927621781826
2023-01-22 19:55:03.134412: step: 696/529, loss: 0.012749074958264828
2023-01-22 19:55:04.240059: step: 700/529, loss: 0.0036831344477832317
2023-01-22 19:55:05.361278: step: 704/529, loss: 0.0009097973816096783
2023-01-22 19:55:06.480864: step: 708/529, loss: 4.9499318265588954e-05
2023-01-22 19:55:07.573931: step: 712/529, loss: 0.0315108560025692
2023-01-22 19:55:08.693472: step: 716/529, loss: 2.919686994573567e-05
2023-01-22 19:55:09.783158: step: 720/529, loss: 0.0025843854527920485
2023-01-22 19:55:10.897445: step: 724/529, loss: 0.004740494303405285
2023-01-22 19:55:12.013073: step: 728/529, loss: 0.010217221453785896
2023-01-22 19:55:13.107739: step: 732/529, loss: 0.0005563810700550675
2023-01-22 19:55:14.252542: step: 736/529, loss: 0.01862388104200363
2023-01-22 19:55:15.359870: step: 740/529, loss: 0.00048288985271938145
2023-01-22 19:55:16.444772: step: 744/529, loss: 0.00038192738429643214
2023-01-22 19:55:17.534743: step: 748/529, loss: 0.007242663763463497
2023-01-22 19:55:18.638744: step: 752/529, loss: 0.002760883653536439
2023-01-22 19:55:19.773050: step: 756/529, loss: 0.005144339520484209
2023-01-22 19:55:20.894206: step: 760/529, loss: 0.006629531271755695
2023-01-22 19:55:21.980758: step: 764/529, loss: 0.006685684900730848
2023-01-22 19:55:23.110254: step: 768/529, loss: 0.022398415952920914
2023-01-22 19:55:24.214423: step: 772/529, loss: 0.0007041774806566536
2023-01-22 19:55:25.316155: step: 776/529, loss: 1.6293995940941386e-05
2023-01-22 19:55:26.423982: step: 780/529, loss: 0.003203638596460223
2023-01-22 19:55:27.530870: step: 784/529, loss: 0.004283823538571596
2023-01-22 19:55:28.643520: step: 788/529, loss: 0.0075381905771791935
2023-01-22 19:55:29.749582: step: 792/529, loss: 0.0066542052663862705
2023-01-22 19:55:30.872140: step: 796/529, loss: 0.03295162320137024
2023-01-22 19:55:31.988512: step: 800/529, loss: 0.00010164460400119424
2023-01-22 19:55:33.100138: step: 804/529, loss: 1.910340870381333e-05
2023-01-22 19:55:34.213721: step: 808/529, loss: 0.004703650251030922
2023-01-22 19:55:35.323209: step: 812/529, loss: 0.0043242513202130795
2023-01-22 19:55:36.413988: step: 816/529, loss: 3.7775909731863067e-05
2023-01-22 19:55:37.524016: step: 820/529, loss: 0.003010609420016408
2023-01-22 19:55:38.628516: step: 824/529, loss: 0.006059859413653612
2023-01-22 19:55:39.767179: step: 828/529, loss: 0.00140922493301332
2023-01-22 19:55:40.892903: step: 832/529, loss: 0.004433562513440847
2023-01-22 19:55:41.999668: step: 836/529, loss: 0.00036265054950490594
2023-01-22 19:55:43.111198: step: 840/529, loss: 0.0013340807054191828
2023-01-22 19:55:44.225271: step: 844/529, loss: 0.0016003873897716403
2023-01-22 19:55:45.342590: step: 848/529, loss: 0.015481779351830482
2023-01-22 19:55:46.444511: step: 852/529, loss: 0.0020873250905424356
2023-01-22 19:55:47.562683: step: 856/529, loss: 0.010177010670304298
2023-01-22 19:55:48.662355: step: 860/529, loss: 0.0022814415860921144
2023-01-22 19:55:49.762794: step: 864/529, loss: 0.00021137519797775894
2023-01-22 19:55:50.881527: step: 868/529, loss: 0.0020440544467419386
2023-01-22 19:55:52.054189: step: 872/529, loss: 0.0017960197292268276
2023-01-22 19:55:53.164097: step: 876/529, loss: 0.00021832113270647824
2023-01-22 19:55:54.257854: step: 880/529, loss: 0.003966952674090862
2023-01-22 19:55:55.361191: step: 884/529, loss: 0.006781257223337889
2023-01-22 19:55:56.455818: step: 888/529, loss: 6.368824415403651e-06
2023-01-22 19:55:57.571843: step: 892/529, loss: 0.0010949590941891074
2023-01-22 19:55:58.678476: step: 896/529, loss: 0.006874303799122572
2023-01-22 19:55:59.784896: step: 900/529, loss: 0.00033875342342071235
2023-01-22 19:56:00.893134: step: 904/529, loss: 0.00014677204308100045
2023-01-22 19:56:01.985487: step: 908/529, loss: 0.00024912384105846286
2023-01-22 19:56:03.086404: step: 912/529, loss: 0.0001998598309000954
2023-01-22 19:56:04.193100: step: 916/529, loss: 0.012555522844195366
2023-01-22 19:56:05.309319: step: 920/529, loss: 0.06372683495283127
2023-01-22 19:56:06.418202: step: 924/529, loss: 0.0012132684933021665
2023-01-22 19:56:07.528168: step: 928/529, loss: 4.712116424343549e-05
2023-01-22 19:56:08.625386: step: 932/529, loss: 0.004622513893991709
2023-01-22 19:56:09.758664: step: 936/529, loss: 0.002345712622627616
2023-01-22 19:56:10.873319: step: 940/529, loss: 0.0024560585152357817
2023-01-22 19:56:11.985310: step: 944/529, loss: 0.008232715539634228
2023-01-22 19:56:13.099643: step: 948/529, loss: 0.01013212464749813
2023-01-22 19:56:14.198317: step: 952/529, loss: 0.005070831160992384
2023-01-22 19:56:15.343784: step: 956/529, loss: 0.008775657042860985
2023-01-22 19:56:16.430549: step: 960/529, loss: 0.008252574130892754
2023-01-22 19:56:17.539349: step: 964/529, loss: 0.007017153315246105
2023-01-22 19:56:18.652144: step: 968/529, loss: 0.0007136272615753114
2023-01-22 19:56:19.773910: step: 972/529, loss: 8.079919643932953e-05
2023-01-22 19:56:20.880793: step: 976/529, loss: 0.010866090655326843
2023-01-22 19:56:21.983516: step: 980/529, loss: 0.004205236677080393
2023-01-22 19:56:23.102282: step: 984/529, loss: 9.855058306129649e-05
2023-01-22 19:56:24.211210: step: 988/529, loss: 0.002479932038113475
2023-01-22 19:56:25.291575: step: 992/529, loss: 0.004178322851657867
2023-01-22 19:56:26.391921: step: 996/529, loss: 1.0259625923936255e-05
2023-01-22 19:56:27.485871: step: 1000/529, loss: 0.001369644422084093
2023-01-22 19:56:28.606818: step: 1004/529, loss: 0.000839556974824518
2023-01-22 19:56:29.711835: step: 1008/529, loss: 0.002839289605617523
2023-01-22 19:56:30.842470: step: 1012/529, loss: 0.005903448909521103
2023-01-22 19:56:31.952410: step: 1016/529, loss: 0.003977745305746794
2023-01-22 19:56:33.052540: step: 1020/529, loss: 0.00040159703348763287
2023-01-22 19:56:34.161916: step: 1024/529, loss: 0.00013529737771023065
2023-01-22 19:56:35.296004: step: 1028/529, loss: 0.003173396922647953
2023-01-22 19:56:36.406819: step: 1032/529, loss: 9.981417679227889e-05
2023-01-22 19:56:37.489771: step: 1036/529, loss: 0.004461656790226698
2023-01-22 19:56:38.585316: step: 1040/529, loss: 0.002025868743658066
2023-01-22 19:56:39.665407: step: 1044/529, loss: 0.00030859134858474135
2023-01-22 19:56:40.775387: step: 1048/529, loss: 0.0038641036953777075
2023-01-22 19:56:41.888483: step: 1052/529, loss: 0.005401624366641045
2023-01-22 19:56:43.007215: step: 1056/529, loss: 0.002669194247573614
2023-01-22 19:56:44.128591: step: 1060/529, loss: 0.00031682837288826704
2023-01-22 19:56:45.230957: step: 1064/529, loss: 0.004601342137902975
2023-01-22 19:56:46.327720: step: 1068/529, loss: 0.00548685435205698
2023-01-22 19:56:47.429335: step: 1072/529, loss: 0.0019524060189723969
2023-01-22 19:56:48.533427: step: 1076/529, loss: 0.0007251353235915303
2023-01-22 19:56:49.632538: step: 1080/529, loss: 0.007719394285231829
2023-01-22 19:56:50.732207: step: 1084/529, loss: 0.0036274902522563934
2023-01-22 19:56:51.817945: step: 1088/529, loss: 0.0010000169277191162
2023-01-22 19:56:52.936731: step: 1092/529, loss: 0.0020134553778916597
2023-01-22 19:56:54.038825: step: 1096/529, loss: 0.004333728924393654
2023-01-22 19:56:55.142979: step: 1100/529, loss: 0.010719121433794498
2023-01-22 19:56:56.240738: step: 1104/529, loss: 0.00137236132286489
2023-01-22 19:56:57.352928: step: 1108/529, loss: 0.005249538458883762
2023-01-22 19:56:58.463841: step: 1112/529, loss: 0.00045455145300365984
2023-01-22 19:56:59.567744: step: 1116/529, loss: 0.0009653582819737494
2023-01-22 19:57:00.657624: step: 1120/529, loss: 0.00039493918302468956
2023-01-22 19:57:01.805823: step: 1124/529, loss: 0.00794602744281292
2023-01-22 19:57:02.893381: step: 1128/529, loss: 0.003449873998761177
2023-01-22 19:57:04.021118: step: 1132/529, loss: 0.0024797539226710796
2023-01-22 19:57:05.133656: step: 1136/529, loss: 0.03432765230536461
2023-01-22 19:57:06.259851: step: 1140/529, loss: 0.007650433573871851
2023-01-22 19:57:07.355823: step: 1144/529, loss: 0.000994968693703413
2023-01-22 19:57:08.476812: step: 1148/529, loss: 0.0015026867622509599
2023-01-22 19:57:09.597983: step: 1152/529, loss: 0.0014761639758944511
2023-01-22 19:57:10.697933: step: 1156/529, loss: 0.004784488584846258
2023-01-22 19:57:11.813134: step: 1160/529, loss: 0.005220495630055666
2023-01-22 19:57:12.919516: step: 1164/529, loss: 3.091091275564395e-05
2023-01-22 19:57:14.035366: step: 1168/529, loss: 0.014425866305828094
2023-01-22 19:57:15.133438: step: 1172/529, loss: 0.00026621806318871677
2023-01-22 19:57:16.232239: step: 1176/529, loss: 0.011068666353821754
2023-01-22 19:57:17.343138: step: 1180/529, loss: 0.00034518170286901295
2023-01-22 19:57:18.447744: step: 1184/529, loss: 0.007991258054971695
2023-01-22 19:57:19.575035: step: 1188/529, loss: 0.004384639207273722
2023-01-22 19:57:20.694008: step: 1192/529, loss: 0.0009908170904964209
2023-01-22 19:57:21.820529: step: 1196/529, loss: 0.00015601824270561337
2023-01-22 19:57:22.918383: step: 1200/529, loss: 0.0038968706503510475
2023-01-22 19:57:24.022124: step: 1204/529, loss: 0.007342000026255846
2023-01-22 19:57:25.146431: step: 1208/529, loss: 0.0006651327712461352
2023-01-22 19:57:26.242109: step: 1212/529, loss: 0.0007706377655267715
2023-01-22 19:57:27.351015: step: 1216/529, loss: 8.94587064976804e-05
2023-01-22 19:57:28.445648: step: 1220/529, loss: 0.02960543893277645
2023-01-22 19:57:29.549439: step: 1224/529, loss: 0.001897280104458332
2023-01-22 19:57:30.646598: step: 1228/529, loss: 0.011684943921864033
2023-01-22 19:57:31.790010: step: 1232/529, loss: 0.001498076831921935
2023-01-22 19:57:32.904175: step: 1236/529, loss: 0.006867724470794201
2023-01-22 19:57:34.008376: step: 1240/529, loss: 0.0002791465085465461
2023-01-22 19:57:35.149906: step: 1244/529, loss: 0.010626512579619884
2023-01-22 19:57:36.241836: step: 1248/529, loss: 0.005484021268785
2023-01-22 19:57:37.365857: step: 1252/529, loss: 0.004931524395942688
2023-01-22 19:57:38.468029: step: 1256/529, loss: 0.02793239988386631
2023-01-22 19:57:39.587170: step: 1260/529, loss: 0.0033209649845957756
2023-01-22 19:57:40.690599: step: 1264/529, loss: 0.008885874412953854
2023-01-22 19:57:41.818594: step: 1268/529, loss: 0.004936038050800562
2023-01-22 19:57:42.921452: step: 1272/529, loss: 0.004901057109236717
2023-01-22 19:57:44.039632: step: 1276/529, loss: 0.001988119212910533
2023-01-22 19:57:45.144781: step: 1280/529, loss: 0.0009802528657019138
2023-01-22 19:57:46.262600: step: 1284/529, loss: 0.0013996611814945936
2023-01-22 19:57:47.362923: step: 1288/529, loss: 0.002583850407972932
2023-01-22 19:57:48.485592: step: 1292/529, loss: 0.006440429948270321
2023-01-22 19:57:49.571968: step: 1296/529, loss: 0.004300088156014681
2023-01-22 19:57:50.695111: step: 1300/529, loss: 0.005393211729824543
2023-01-22 19:57:51.814807: step: 1304/529, loss: 0.0017906812718138099
2023-01-22 19:57:52.925905: step: 1308/529, loss: 0.004659599158912897
2023-01-22 19:57:54.050325: step: 1312/529, loss: 0.005110634956508875
2023-01-22 19:57:55.169864: step: 1316/529, loss: 0.0057045090943574905
2023-01-22 19:57:56.278386: step: 1320/529, loss: 0.0021445073653012514
2023-01-22 19:57:57.386899: step: 1324/529, loss: 0.004785752389580011
2023-01-22 19:57:58.503793: step: 1328/529, loss: 0.0022379099391400814
2023-01-22 19:57:59.607863: step: 1332/529, loss: 0.024793200194835663
2023-01-22 19:58:00.732066: step: 1336/529, loss: 0.027622297406196594
2023-01-22 19:58:01.817292: step: 1340/529, loss: 0.0011838177451863885
2023-01-22 19:58:02.933415: step: 1344/529, loss: 0.007566556334495544
2023-01-22 19:58:04.048305: step: 1348/529, loss: 0.011250466108322144
2023-01-22 19:58:05.168142: step: 1352/529, loss: 0.0006066447240300477
2023-01-22 19:58:06.269265: step: 1356/529, loss: 0.0034677174407988787
2023-01-22 19:58:07.367354: step: 1360/529, loss: 0.011056795716285706
2023-01-22 19:58:08.495366: step: 1364/529, loss: 0.010419712401926517
2023-01-22 19:58:09.600807: step: 1368/529, loss: 3.5082746762782335e-05
2023-01-22 19:58:10.707851: step: 1372/529, loss: 0.0002436417416902259
2023-01-22 19:58:11.813927: step: 1376/529, loss: 0.013517429120838642
2023-01-22 19:58:12.916962: step: 1380/529, loss: 0.008008817210793495
2023-01-22 19:58:14.028021: step: 1384/529, loss: 0.015433688648045063
2023-01-22 19:58:15.133942: step: 1388/529, loss: 0.00700283283367753
2023-01-22 19:58:16.228600: step: 1392/529, loss: 0.00032517960062250495
2023-01-22 19:58:17.391144: step: 1396/529, loss: 0.007295718416571617
2023-01-22 19:58:18.500421: step: 1400/529, loss: 0.0061205471865832806
2023-01-22 19:58:19.625664: step: 1404/529, loss: 0.0005795481847599149
2023-01-22 19:58:20.745430: step: 1408/529, loss: 0.003091163234785199
2023-01-22 19:58:21.873504: step: 1412/529, loss: 0.00026308713131584227
2023-01-22 19:58:22.967068: step: 1416/529, loss: 0.002890215488150716
2023-01-22 19:58:24.086969: step: 1420/529, loss: 0.00016771670198068023
2023-01-22 19:58:25.234943: step: 1424/529, loss: 0.01871509477496147
2023-01-22 19:58:26.339591: step: 1428/529, loss: 0.00030465179588645697
2023-01-22 19:58:27.438306: step: 1432/529, loss: 0.0032001181971281767
2023-01-22 19:58:28.544021: step: 1436/529, loss: 0.002943756990134716
2023-01-22 19:58:29.655480: step: 1440/529, loss: 2.249479621241335e-06
2023-01-22 19:58:30.766624: step: 1444/529, loss: 1.8380209439783357e-05
2023-01-22 19:58:31.877133: step: 1448/529, loss: 0.00759240472689271
2023-01-22 19:58:32.967530: step: 1452/529, loss: 0.0138852559030056
2023-01-22 19:58:34.063016: step: 1456/529, loss: 0.0015683637466281652
2023-01-22 19:58:35.170484: step: 1460/529, loss: 0.02113204635679722
2023-01-22 19:58:36.289471: step: 1464/529, loss: 0.02652093954384327
2023-01-22 19:58:37.411481: step: 1468/529, loss: 0.003285401500761509
2023-01-22 19:58:38.526680: step: 1472/529, loss: 0.0012357857776805758
2023-01-22 19:58:39.631803: step: 1476/529, loss: 0.009123251773416996
2023-01-22 19:58:40.753807: step: 1480/529, loss: 0.00026756885927170515
2023-01-22 19:58:41.858468: step: 1484/529, loss: 0.003258280921727419
2023-01-22 19:58:42.957550: step: 1488/529, loss: 0.0022948661353439093
2023-01-22 19:58:44.069955: step: 1492/529, loss: 5.1069684559479356e-05
2023-01-22 19:58:45.170144: step: 1496/529, loss: 0.0007203823770396411
2023-01-22 19:58:46.277221: step: 1500/529, loss: 0.002969960682094097
2023-01-22 19:58:47.396943: step: 1504/529, loss: 0.0036475860979408026
2023-01-22 19:58:48.493998: step: 1508/529, loss: 0.001101042260415852
2023-01-22 19:58:49.611237: step: 1512/529, loss: 0.003134277882054448
2023-01-22 19:58:50.738412: step: 1516/529, loss: 0.0024678397458046675
2023-01-22 19:58:51.836434: step: 1520/529, loss: 0.006030470132827759
2023-01-22 19:58:52.947282: step: 1524/529, loss: 0.007488882169127464
2023-01-22 19:58:54.060992: step: 1528/529, loss: 0.0006192834116518497
2023-01-22 19:58:55.158617: step: 1532/529, loss: 0.0011881602695211768
2023-01-22 19:58:56.264832: step: 1536/529, loss: 0.0005812318413518369
2023-01-22 19:58:57.382278: step: 1540/529, loss: 0.0012676113983616233
2023-01-22 19:58:58.479480: step: 1544/529, loss: 0.0013949732528999448
2023-01-22 19:58:59.581889: step: 1548/529, loss: 0.008488287217915058
2023-01-22 19:59:00.673290: step: 1552/529, loss: 1.2618501386896241e-05
2023-01-22 19:59:01.775713: step: 1556/529, loss: 0.005794909317046404
2023-01-22 19:59:02.875173: step: 1560/529, loss: 0.0014684823108837008
2023-01-22 19:59:03.973336: step: 1564/529, loss: 0.0057525066658854485
2023-01-22 19:59:05.102107: step: 1568/529, loss: 0.005236676428467035
2023-01-22 19:59:06.219874: step: 1572/529, loss: 0.0036738950293511152
2023-01-22 19:59:07.309480: step: 1576/529, loss: 0.0008385474211536348
2023-01-22 19:59:08.410395: step: 1580/529, loss: 0.001723063993267715
2023-01-22 19:59:09.514166: step: 1584/529, loss: 0.008128863759338856
2023-01-22 19:59:10.613220: step: 1588/529, loss: 0.003797698300331831
2023-01-22 19:59:11.722969: step: 1592/529, loss: 0.008646626025438309
2023-01-22 19:59:12.822453: step: 1596/529, loss: 0.002870364813134074
2023-01-22 19:59:13.937751: step: 1600/529, loss: 0.00034339699777774513
2023-01-22 19:59:15.060831: step: 1604/529, loss: 0.0035608645994216204
2023-01-22 19:59:16.168482: step: 1608/529, loss: 0.007049956824630499
2023-01-22 19:59:17.275786: step: 1612/529, loss: 0.002489047357812524
2023-01-22 19:59:18.387061: step: 1616/529, loss: 0.020995063707232475
2023-01-22 19:59:19.510949: step: 1620/529, loss: 0.018273737281560898
2023-01-22 19:59:20.637240: step: 1624/529, loss: 0.0007087595877237618
2023-01-22 19:59:21.744636: step: 1628/529, loss: 0.008334141224622726
2023-01-22 19:59:22.853930: step: 1632/529, loss: 0.00499467458575964
2023-01-22 19:59:23.961616: step: 1636/529, loss: 0.0026572425849735737
2023-01-22 19:59:25.085510: step: 1640/529, loss: 0.004773653578013182
2023-01-22 19:59:26.192166: step: 1644/529, loss: 0.00435072835534811
2023-01-22 19:59:27.298087: step: 1648/529, loss: 0.00041979688103310764
2023-01-22 19:59:28.401189: step: 1652/529, loss: 0.003310898318886757
2023-01-22 19:59:29.515261: step: 1656/529, loss: 0.01849922351539135
2023-01-22 19:59:30.616285: step: 1660/529, loss: 0.0005802304367534816
2023-01-22 19:59:31.746803: step: 1664/529, loss: 0.003721635788679123
2023-01-22 19:59:32.872508: step: 1668/529, loss: 0.0036931943614035845
2023-01-22 19:59:33.996341: step: 1672/529, loss: 0.0017643123865127563
2023-01-22 19:59:35.094848: step: 1676/529, loss: 0.001096975291147828
2023-01-22 19:59:36.218356: step: 1680/529, loss: 0.027191104367375374
2023-01-22 19:59:37.328016: step: 1684/529, loss: 0.000802180846221745
2023-01-22 19:59:38.432462: step: 1688/529, loss: 0.009118456393480301
2023-01-22 19:59:39.534395: step: 1692/529, loss: 0.00022893202549312264
2023-01-22 19:59:40.652424: step: 1696/529, loss: 0.0023596887476742268
2023-01-22 19:59:41.764075: step: 1700/529, loss: 0.004643856082111597
2023-01-22 19:59:42.856100: step: 1704/529, loss: 0.0035202878061681986
2023-01-22 19:59:43.966958: step: 1708/529, loss: 0.0009159942273981869
2023-01-22 19:59:45.066376: step: 1712/529, loss: 5.7536151871318e-05
2023-01-22 19:59:46.184943: step: 1716/529, loss: 0.00593317486345768
2023-01-22 19:59:47.286279: step: 1720/529, loss: 0.0013714809902012348
2023-01-22 19:59:48.397179: step: 1724/529, loss: 0.009653424844145775
2023-01-22 19:59:49.512886: step: 1728/529, loss: 0.0015635871095582843
2023-01-22 19:59:50.615528: step: 1732/529, loss: 0.00043258399819023907
2023-01-22 19:59:51.735709: step: 1736/529, loss: 0.0036243880167603493
2023-01-22 19:59:52.843830: step: 1740/529, loss: 0.032035134732723236
2023-01-22 19:59:53.931656: step: 1744/529, loss: 0.0016696734819561243
2023-01-22 19:59:55.034739: step: 1748/529, loss: 0.00035671357181854546
2023-01-22 19:59:56.132906: step: 1752/529, loss: 0.0010831819381564856
2023-01-22 19:59:57.223235: step: 1756/529, loss: 0.002690880326554179
2023-01-22 19:59:58.313096: step: 1760/529, loss: 0.00019929495465476066
2023-01-22 19:59:59.443190: step: 1764/529, loss: 0.005031203385442495
2023-01-22 20:00:00.543748: step: 1768/529, loss: 0.006407430395483971
2023-01-22 20:00:01.657055: step: 1772/529, loss: 0.005499716382473707
2023-01-22 20:00:02.786086: step: 1776/529, loss: 0.034918952733278275
2023-01-22 20:00:03.872182: step: 1780/529, loss: 0.007672132924199104
2023-01-22 20:00:04.969644: step: 1784/529, loss: 0.0007506535039283335
2023-01-22 20:00:06.091372: step: 1788/529, loss: 0.002601213753223419
2023-01-22 20:00:07.179261: step: 1792/529, loss: 0.0023681249003857374
2023-01-22 20:00:08.300090: step: 1796/529, loss: 0.010361873544752598
2023-01-22 20:00:09.437332: step: 1800/529, loss: 0.004262631293386221
2023-01-22 20:00:10.557300: step: 1804/529, loss: 0.002712997840717435
2023-01-22 20:00:11.654648: step: 1808/529, loss: 0.002933068433776498
2023-01-22 20:00:12.762670: step: 1812/529, loss: 0.0049403076991438866
2023-01-22 20:00:13.852735: step: 1816/529, loss: 0.00030556172714568675
2023-01-22 20:00:14.986904: step: 1820/529, loss: 0.00022162875393405557
2023-01-22 20:00:16.100048: step: 1824/529, loss: 9.264702384825796e-05
2023-01-22 20:00:17.185229: step: 1828/529, loss: 0.0036450079642236233
2023-01-22 20:00:18.309120: step: 1832/529, loss: 0.004458323121070862
2023-01-22 20:00:19.429745: step: 1836/529, loss: 0.0023477349895983934
2023-01-22 20:00:20.546684: step: 1840/529, loss: 0.008056516759097576
2023-01-22 20:00:21.650732: step: 1844/529, loss: 0.006951354444026947
2023-01-22 20:00:22.768317: step: 1848/529, loss: 0.0019325959729030728
2023-01-22 20:00:23.885435: step: 1852/529, loss: 0.009846577420830727
2023-01-22 20:00:25.039279: step: 1856/529, loss: 0.0029493931215256453
2023-01-22 20:00:26.150314: step: 1860/529, loss: 0.00021619869221467525
2023-01-22 20:00:27.250783: step: 1864/529, loss: 0.000570410571526736
2023-01-22 20:00:28.354234: step: 1868/529, loss: 0.00903247483074665
2023-01-22 20:00:29.469084: step: 1872/529, loss: 0.0001422100467607379
2023-01-22 20:00:30.564287: step: 1876/529, loss: 0.001439129700884223
2023-01-22 20:00:31.676569: step: 1880/529, loss: 0.007189551368355751
2023-01-22 20:00:32.771274: step: 1884/529, loss: 0.0007763136527501047
2023-01-22 20:00:33.887982: step: 1888/529, loss: 0.000886360474396497
2023-01-22 20:00:34.986984: step: 1892/529, loss: 0.0068611567839980125
2023-01-22 20:00:36.103177: step: 1896/529, loss: 0.0014084739377722144
2023-01-22 20:00:37.194974: step: 1900/529, loss: 0.0006912951939739287
2023-01-22 20:00:38.298704: step: 1904/529, loss: 0.004323470406234264
2023-01-22 20:00:39.404330: step: 1908/529, loss: 0.007418234366923571
2023-01-22 20:00:40.493799: step: 1912/529, loss: 0.0005564384628087282
2023-01-22 20:00:41.599403: step: 1916/529, loss: 0.005541039165109396
2023-01-22 20:00:42.701936: step: 1920/529, loss: 0.0001588106097187847
2023-01-22 20:00:43.822117: step: 1924/529, loss: 0.0011011230526492
2023-01-22 20:00:44.943282: step: 1928/529, loss: 4.149424057686701e-06
2023-01-22 20:00:46.020345: step: 1932/529, loss: 0.00012599601177498698
2023-01-22 20:00:47.121677: step: 1936/529, loss: 0.0005975664826110005
2023-01-22 20:00:48.227197: step: 1940/529, loss: 0.010239941067993641
2023-01-22 20:00:49.364021: step: 1944/529, loss: 0.001049767597578466
2023-01-22 20:00:50.481673: step: 1948/529, loss: 0.007149444427341223
2023-01-22 20:00:51.580109: step: 1952/529, loss: 0.005090836901217699
2023-01-22 20:00:52.686030: step: 1956/529, loss: 0.0072985077276825905
2023-01-22 20:00:53.792989: step: 1960/529, loss: 0.006151984911412001
2023-01-22 20:00:54.912509: step: 1964/529, loss: 0.0016086878022179008
2023-01-22 20:00:56.024048: step: 1968/529, loss: 0.006416039075702429
2023-01-22 20:00:57.136308: step: 1972/529, loss: 0.0075052035972476006
2023-01-22 20:00:58.230651: step: 1976/529, loss: 0.0005445227143354714
2023-01-22 20:00:59.330324: step: 1980/529, loss: 0.0035929791629314423
2023-01-22 20:01:00.416422: step: 1984/529, loss: 2.261967892991379e-05
2023-01-22 20:01:01.510140: step: 1988/529, loss: 0.02420150674879551
2023-01-22 20:01:02.613691: step: 1992/529, loss: 0.0
2023-01-22 20:01:03.729352: step: 1996/529, loss: 0.003548518754541874
2023-01-22 20:01:04.866120: step: 2000/529, loss: 0.02597544901072979
2023-01-22 20:01:06.007701: step: 2004/529, loss: 0.002890253672376275
2023-01-22 20:01:07.106150: step: 2008/529, loss: 0.0014319369802251458
2023-01-22 20:01:08.219087: step: 2012/529, loss: 7.815883873263374e-05
2023-01-22 20:01:09.327128: step: 2016/529, loss: 0.001766129513271153
2023-01-22 20:01:10.470568: step: 2020/529, loss: 0.005064873490482569
2023-01-22 20:01:11.550105: step: 2024/529, loss: 0.0001890771818580106
2023-01-22 20:01:12.659438: step: 2028/529, loss: 0.0013856698060408235
2023-01-22 20:01:13.775998: step: 2032/529, loss: 0.0022560851648449898
2023-01-22 20:01:14.869371: step: 2036/529, loss: 0.001329240039922297
2023-01-22 20:01:15.985582: step: 2040/529, loss: 0.001558055286295712
2023-01-22 20:01:17.104235: step: 2044/529, loss: 0.0001524899562355131
2023-01-22 20:01:18.236005: step: 2048/529, loss: 0.006990751251578331
2023-01-22 20:01:19.346687: step: 2052/529, loss: 0.004695339128375053
2023-01-22 20:01:20.473079: step: 2056/529, loss: 0.05430683493614197
2023-01-22 20:01:21.580926: step: 2060/529, loss: 0.009949995204806328
2023-01-22 20:01:22.678595: step: 2064/529, loss: 0.0011440449161455035
2023-01-22 20:01:23.783221: step: 2068/529, loss: 0.0028380993753671646
2023-01-22 20:01:24.902468: step: 2072/529, loss: 0.00656010489910841
2023-01-22 20:01:26.014824: step: 2076/529, loss: 0.0033120117150247097
2023-01-22 20:01:27.096341: step: 2080/529, loss: 0.00010947092960122973
2023-01-22 20:01:28.207327: step: 2084/529, loss: 0.0005642026080749929
2023-01-22 20:01:29.300317: step: 2088/529, loss: 0.008556976914405823
2023-01-22 20:01:30.405362: step: 2092/529, loss: 8.561924187233672e-05
2023-01-22 20:01:31.497651: step: 2096/529, loss: 0.002317034639418125
2023-01-22 20:01:32.616597: step: 2100/529, loss: 0.0016840959433466196
2023-01-22 20:01:33.723162: step: 2104/529, loss: 0.0010007693199440837
2023-01-22 20:01:34.809736: step: 2108/529, loss: 0.002132132649421692
2023-01-22 20:01:35.948917: step: 2112/529, loss: 0.0031894545536488295
2023-01-22 20:01:37.067507: step: 2116/529, loss: 1.4975915291870479e-05
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33433363210148925, 'r': 0.32862394957983193, 'f1': 0.33145420369104583}, 'combined': 0.24422941324603376, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37212319351515766, 'r': 0.2947318881047262, 'f1': 0.3289367493934759}, 'combined': 0.20217575816379493, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3418159909283078, 'r': 0.3489506700558436, 'f1': 0.3453464847313232}, 'combined': 0.2544658308546592, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3561390298615645, 'r': 0.3092299028780655, 'f1': 0.33103089788616663}, 'combined': 0.20346289333491216, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34388848541809064, 'r': 0.3471511845207291, 'f1': 0.345512132658025}, 'combined': 0.2545878872217026, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3659720417943431, 'r': 0.2968967992738524, 'f1': 0.3278353758712232}, 'combined': 0.2024865556851673, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35185185185185186, 'r': 0.41304347826086957, 'f1': 0.38}, 'combined': 0.19, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 14
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 20:04:01.310068: step: 4/529, loss: 0.004017682746052742
2023-01-22 20:04:02.417531: step: 8/529, loss: 0.0009242295636795461
2023-01-22 20:04:03.490364: step: 12/529, loss: 0.006270421668887138
2023-01-22 20:04:04.589977: step: 16/529, loss: 0.0015395382652059197
2023-01-22 20:04:05.694052: step: 20/529, loss: 0.005934928078204393
2023-01-22 20:04:06.765955: step: 24/529, loss: 0.0001630986953387037
2023-01-22 20:04:07.875360: step: 28/529, loss: 0.000970147957559675
2023-01-22 20:04:08.968903: step: 32/529, loss: 0.01720673404633999
2023-01-22 20:04:10.072767: step: 36/529, loss: 0.0018050681101158261
2023-01-22 20:04:11.168333: step: 40/529, loss: 7.151860336307436e-05
2023-01-22 20:04:12.280360: step: 44/529, loss: 0.006344522815197706
2023-01-22 20:04:13.396282: step: 48/529, loss: 0.00037268741289153695
2023-01-22 20:04:14.529595: step: 52/529, loss: 0.01832570508122444
2023-01-22 20:04:15.621166: step: 56/529, loss: 0.0050773825496435165
2023-01-22 20:04:16.731635: step: 60/529, loss: 0.0004603034467436373
2023-01-22 20:04:17.831658: step: 64/529, loss: 0.0024300641380250454
2023-01-22 20:04:18.932053: step: 68/529, loss: 0.003232666989788413
2023-01-22 20:04:20.058719: step: 72/529, loss: 0.0031463447958230972
2023-01-22 20:04:21.169127: step: 76/529, loss: 0.00031368760392069817
2023-01-22 20:04:22.284276: step: 80/529, loss: 0.00574699928984046
2023-01-22 20:04:23.367382: step: 84/529, loss: 0.0033522658050060272
2023-01-22 20:04:24.486738: step: 88/529, loss: 0.012863255105912685
2023-01-22 20:04:25.592312: step: 92/529, loss: 0.0013765029143542051
2023-01-22 20:04:26.696790: step: 96/529, loss: 0.0008481140830554068
2023-01-22 20:04:27.791707: step: 100/529, loss: 0.002638123696669936
2023-01-22 20:04:28.913599: step: 104/529, loss: 0.00043326185550540686
2023-01-22 20:04:30.004625: step: 108/529, loss: 0.0025408542715013027
2023-01-22 20:04:31.132416: step: 112/529, loss: 0.010455128736793995
2023-01-22 20:04:32.227908: step: 116/529, loss: 0.00810779444873333
2023-01-22 20:04:33.310988: step: 120/529, loss: 0.0012793648056685925
2023-01-22 20:04:34.430661: step: 124/529, loss: 0.006055021192878485
2023-01-22 20:04:35.536691: step: 128/529, loss: 0.008519347757101059
2023-01-22 20:04:36.645870: step: 132/529, loss: 0.0017153981607407331
2023-01-22 20:04:37.775180: step: 136/529, loss: 0.011559495702385902
2023-01-22 20:04:38.888723: step: 140/529, loss: 0.007168784271925688
2023-01-22 20:04:39.969741: step: 144/529, loss: 0.0007770570227876306
2023-01-22 20:04:41.079930: step: 148/529, loss: 0.002134120324626565
2023-01-22 20:04:42.199617: step: 152/529, loss: 0.0033081024885177612
2023-01-22 20:04:43.295710: step: 156/529, loss: 0.012740008533000946
2023-01-22 20:04:44.391956: step: 160/529, loss: 0.003394529689103365
2023-01-22 20:04:45.507652: step: 164/529, loss: 0.005497364792972803
2023-01-22 20:04:46.611573: step: 168/529, loss: 0.0025131255388259888
2023-01-22 20:04:47.712205: step: 172/529, loss: 0.0007885585655458272
2023-01-22 20:04:48.813674: step: 176/529, loss: 0.004025578033179045
2023-01-22 20:04:49.918669: step: 180/529, loss: 0.0020649516955018044
2023-01-22 20:04:51.031312: step: 184/529, loss: 0.0015408031176775694
2023-01-22 20:04:52.132016: step: 188/529, loss: 0.0006245877593755722
2023-01-22 20:04:53.226306: step: 192/529, loss: 1.6311241779476404e-05
2023-01-22 20:04:54.316766: step: 196/529, loss: 0.00018585943325888366
2023-01-22 20:04:55.422123: step: 200/529, loss: 0.0026932486798614264
2023-01-22 20:04:56.520052: step: 204/529, loss: 0.004115288611501455
2023-01-22 20:04:57.638988: step: 208/529, loss: 0.0008540253038518131
2023-01-22 20:04:58.774128: step: 212/529, loss: 0.0013984618708491325
2023-01-22 20:04:59.894392: step: 216/529, loss: 0.008898225612938404
2023-01-22 20:05:01.003058: step: 220/529, loss: 0.004957273602485657
2023-01-22 20:05:02.123609: step: 224/529, loss: 0.00038612468051724136
2023-01-22 20:05:03.216959: step: 228/529, loss: 0.0015860882122069597
2023-01-22 20:05:04.326319: step: 232/529, loss: 0.0028882650658488274
2023-01-22 20:05:05.434331: step: 236/529, loss: 0.0007981908274814487
2023-01-22 20:05:06.519473: step: 240/529, loss: 0.012773731723427773
2023-01-22 20:05:07.606286: step: 244/529, loss: 0.0013330148067325354
2023-01-22 20:05:08.710278: step: 248/529, loss: 0.004262182861566544
2023-01-22 20:05:09.864216: step: 252/529, loss: 0.001346705132164061
2023-01-22 20:05:10.968228: step: 256/529, loss: 0.010781573131680489
2023-01-22 20:05:12.067051: step: 260/529, loss: 0.005327738355845213
2023-01-22 20:05:13.190497: step: 264/529, loss: 0.005056611727923155
2023-01-22 20:05:14.299164: step: 268/529, loss: 0.01770065352320671
2023-01-22 20:05:15.439007: step: 272/529, loss: 0.0015972615219652653
2023-01-22 20:05:16.553074: step: 276/529, loss: 0.012061548419296741
2023-01-22 20:05:17.658991: step: 280/529, loss: 0.001330185099504888
2023-01-22 20:05:18.763807: step: 284/529, loss: 0.0001306285266764462
2023-01-22 20:05:19.873250: step: 288/529, loss: 0.004532399587333202
2023-01-22 20:05:20.998466: step: 292/529, loss: 0.0007070941501297057
2023-01-22 20:05:22.105734: step: 296/529, loss: 0.0007744791219010949
2023-01-22 20:05:23.225604: step: 300/529, loss: 1.813436028896831e-05
2023-01-22 20:05:24.333693: step: 304/529, loss: 6.861891597509384e-05
2023-01-22 20:05:25.427663: step: 308/529, loss: 0.005068132653832436
2023-01-22 20:05:26.512212: step: 312/529, loss: 0.0022420270834118128
2023-01-22 20:05:27.609383: step: 316/529, loss: 0.0018985880305990577
2023-01-22 20:05:28.724589: step: 320/529, loss: 0.0017229585209861398
2023-01-22 20:05:29.836558: step: 324/529, loss: 0.006043081171810627
2023-01-22 20:05:30.936480: step: 328/529, loss: 0.0029211172368377447
2023-01-22 20:05:32.041394: step: 332/529, loss: 1.9933515886805253e-06
2023-01-22 20:05:33.155691: step: 336/529, loss: 0.00656077079474926
2023-01-22 20:05:34.256730: step: 340/529, loss: 0.0002971893409267068
2023-01-22 20:05:35.361753: step: 344/529, loss: 0.0012217750772833824
2023-01-22 20:05:36.480314: step: 348/529, loss: 0.003328346647322178
2023-01-22 20:05:37.572437: step: 352/529, loss: 0.0028509267140179873
2023-01-22 20:05:38.695204: step: 356/529, loss: 0.0023718641605228186
2023-01-22 20:05:39.797207: step: 360/529, loss: 0.000895620440132916
2023-01-22 20:05:40.901448: step: 364/529, loss: 0.000947058666497469
2023-01-22 20:05:42.015780: step: 368/529, loss: 0.01822621561586857
2023-01-22 20:05:43.135107: step: 372/529, loss: 0.002414952265098691
2023-01-22 20:05:44.261488: step: 376/529, loss: 0.0064300671219825745
2023-01-22 20:05:45.348804: step: 380/529, loss: 0.002475287299603224
2023-01-22 20:05:46.454866: step: 384/529, loss: 0.0016879403265193105
2023-01-22 20:05:47.541851: step: 388/529, loss: 0.0007610544562339783
2023-01-22 20:05:48.648869: step: 392/529, loss: 0.0009465606999583542
2023-01-22 20:05:49.757129: step: 396/529, loss: 0.00015459379937965423
2023-01-22 20:05:50.877427: step: 400/529, loss: 0.00617228215560317
2023-01-22 20:05:51.993591: step: 404/529, loss: 0.0
2023-01-22 20:05:53.102537: step: 408/529, loss: 0.0006017853738740087
2023-01-22 20:05:54.208444: step: 412/529, loss: 0.003774944692850113
2023-01-22 20:05:55.318785: step: 416/529, loss: 0.00046165072126314044
2023-01-22 20:05:56.419463: step: 420/529, loss: 0.00027317824424244463
2023-01-22 20:05:57.516173: step: 424/529, loss: 0.004298737272620201
2023-01-22 20:05:58.641255: step: 428/529, loss: 0.010374879464507103
2023-01-22 20:05:59.719381: step: 432/529, loss: 0.00047678101691417396
2023-01-22 20:06:00.829530: step: 436/529, loss: 0.00044412966235540807
2023-01-22 20:06:01.957757: step: 440/529, loss: 0.028463061898946762
2023-01-22 20:06:03.048978: step: 444/529, loss: 0.0014933921629562974
2023-01-22 20:06:04.151467: step: 448/529, loss: 0.0002521930728107691
2023-01-22 20:06:05.255333: step: 452/529, loss: 0.002302172826603055
2023-01-22 20:06:06.347755: step: 456/529, loss: 0.007455112412571907
2023-01-22 20:06:07.450623: step: 460/529, loss: 0.010368739254772663
2023-01-22 20:06:08.571929: step: 464/529, loss: 0.01615116186439991
2023-01-22 20:06:09.685394: step: 468/529, loss: 0.00352029618807137
2023-01-22 20:06:10.792029: step: 472/529, loss: 0.00747502688318491
2023-01-22 20:06:11.916243: step: 476/529, loss: 0.0015371283516287804
2023-01-22 20:06:13.039722: step: 480/529, loss: 0.004901760723441839
2023-01-22 20:06:14.148923: step: 484/529, loss: 0.013774470426142216
2023-01-22 20:06:15.268093: step: 488/529, loss: 0.0021839861292392015
2023-01-22 20:06:16.358936: step: 492/529, loss: 0.0003969954268541187
2023-01-22 20:06:17.460157: step: 496/529, loss: 0.004497201181948185
2023-01-22 20:06:18.597486: step: 500/529, loss: 0.0002066479210043326
2023-01-22 20:06:19.723173: step: 504/529, loss: 0.003468351671472192
2023-01-22 20:06:20.833675: step: 508/529, loss: 0.00557201961055398
2023-01-22 20:06:21.951266: step: 512/529, loss: 0.0183720663189888
2023-01-22 20:06:23.038269: step: 516/529, loss: 0.0032495451159775257
2023-01-22 20:06:24.155144: step: 520/529, loss: 0.0011680229799821973
2023-01-22 20:06:25.238876: step: 524/529, loss: 0.0007451308774761856
2023-01-22 20:06:26.347133: step: 528/529, loss: 0.010524425655603409
2023-01-22 20:06:27.453846: step: 532/529, loss: 0.007406124845147133
2023-01-22 20:06:28.574757: step: 536/529, loss: 0.013637742958962917
2023-01-22 20:06:29.671202: step: 540/529, loss: 0.00026450137374922633
2023-01-22 20:06:30.771578: step: 544/529, loss: 0.015263236127793789
2023-01-22 20:06:31.914483: step: 548/529, loss: 0.000903081614524126
2023-01-22 20:06:33.007646: step: 552/529, loss: 6.866855983389542e-05
2023-01-22 20:06:34.103060: step: 556/529, loss: 0.0006684183026663959
2023-01-22 20:06:35.230488: step: 560/529, loss: 0.0023486309219151735
2023-01-22 20:06:36.353551: step: 564/529, loss: 0.008993650786578655
2023-01-22 20:06:37.457088: step: 568/529, loss: 0.004085613414645195
2023-01-22 20:06:38.557535: step: 572/529, loss: 0.0003004330792464316
2023-01-22 20:06:39.658579: step: 576/529, loss: 0.001640260685235262
2023-01-22 20:06:40.820615: step: 580/529, loss: 0.0027144039049744606
2023-01-22 20:06:41.940379: step: 584/529, loss: 0.01900293119251728
2023-01-22 20:06:43.039565: step: 588/529, loss: 0.0005381632363423705
2023-01-22 20:06:44.175316: step: 592/529, loss: 0.00285432324744761
2023-01-22 20:06:45.299963: step: 596/529, loss: 0.0058250403963029385
2023-01-22 20:06:46.395294: step: 600/529, loss: 0.0029124896973371506
2023-01-22 20:06:47.526762: step: 604/529, loss: 0.03352838754653931
2023-01-22 20:06:48.649791: step: 608/529, loss: 0.013501377776265144
2023-01-22 20:06:49.748079: step: 612/529, loss: 0.015476818196475506
2023-01-22 20:06:50.879140: step: 616/529, loss: 0.029871920123696327
2023-01-22 20:06:51.994378: step: 620/529, loss: 0.00037643263931386173
2023-01-22 20:06:53.099010: step: 624/529, loss: 0.0020939160604029894
2023-01-22 20:06:54.229976: step: 628/529, loss: 0.0099239656701684
2023-01-22 20:06:55.356634: step: 632/529, loss: 0.0005623669712804258
2023-01-22 20:06:56.466390: step: 636/529, loss: 0.009362041018903255
2023-01-22 20:06:57.567015: step: 640/529, loss: 0.0028562480583786964
2023-01-22 20:06:58.677792: step: 644/529, loss: 0.003878779709339142
2023-01-22 20:06:59.795027: step: 648/529, loss: 0.011247131042182446
2023-01-22 20:07:00.911815: step: 652/529, loss: 0.021356847137212753
2023-01-22 20:07:02.031093: step: 656/529, loss: 0.011271699331700802
2023-01-22 20:07:03.144461: step: 660/529, loss: 0.005229650530964136
2023-01-22 20:07:04.273699: step: 664/529, loss: 0.0007825507782399654
2023-01-22 20:07:05.374387: step: 668/529, loss: 0.044641777873039246
2023-01-22 20:07:06.488488: step: 672/529, loss: 0.0012233637971803546
2023-01-22 20:07:07.591359: step: 676/529, loss: 0.0007903050282038748
2023-01-22 20:07:08.708203: step: 680/529, loss: 0.0025234618224203587
2023-01-22 20:07:09.808647: step: 684/529, loss: 0.0015214593149721622
2023-01-22 20:07:10.907799: step: 688/529, loss: 0.000100671750260517
2023-01-22 20:07:12.014018: step: 692/529, loss: 0.00117252126801759
2023-01-22 20:07:13.111673: step: 696/529, loss: 0.007785823196172714
2023-01-22 20:07:14.202812: step: 700/529, loss: 0.005848946049809456
2023-01-22 20:07:15.301622: step: 704/529, loss: 0.004434181842952967
2023-01-22 20:07:16.416805: step: 708/529, loss: 0.0005314656882546842
2023-01-22 20:07:17.518130: step: 712/529, loss: 0.001599497045390308
2023-01-22 20:07:18.629229: step: 716/529, loss: 0.006668953690677881
2023-01-22 20:07:19.749675: step: 720/529, loss: 0.007054932881146669
2023-01-22 20:07:20.857543: step: 724/529, loss: 0.0022631841711699963
2023-01-22 20:07:21.966227: step: 728/529, loss: 0.0038365251384675503
2023-01-22 20:07:23.074287: step: 732/529, loss: 0.004223325755447149
2023-01-22 20:07:24.182925: step: 736/529, loss: 0.0007428702665492892
2023-01-22 20:07:25.297420: step: 740/529, loss: 0.0010229283943772316
2023-01-22 20:07:26.405466: step: 744/529, loss: 0.009575918316841125
2023-01-22 20:07:27.526874: step: 748/529, loss: 0.006561367306858301
2023-01-22 20:07:28.635393: step: 752/529, loss: 0.0018939487636089325
2023-01-22 20:07:29.740029: step: 756/529, loss: 0.002845506649464369
2023-01-22 20:07:30.852318: step: 760/529, loss: 0.00011776803148677573
2023-01-22 20:07:31.942691: step: 764/529, loss: 0.0038699107244610786
2023-01-22 20:07:33.061304: step: 768/529, loss: 0.005368166137486696
2023-01-22 20:07:34.178806: step: 772/529, loss: 0.009277998469769955
2023-01-22 20:07:35.266639: step: 776/529, loss: 0.004776305519044399
2023-01-22 20:07:36.387175: step: 780/529, loss: 0.004130480345338583
2023-01-22 20:07:37.492088: step: 784/529, loss: 0.00017559003026690334
2023-01-22 20:07:38.604011: step: 788/529, loss: 0.0018009924096986651
2023-01-22 20:07:39.726531: step: 792/529, loss: 0.0011539142578840256
2023-01-22 20:07:40.812370: step: 796/529, loss: 0.005678319837898016
2023-01-22 20:07:41.900496: step: 800/529, loss: 0.00210260390304029
2023-01-22 20:07:43.023137: step: 804/529, loss: 0.0051914420910179615
2023-01-22 20:07:44.169118: step: 808/529, loss: 0.0024992600083351135
2023-01-22 20:07:45.267739: step: 812/529, loss: 0.0005710808909498155
2023-01-22 20:07:46.405158: step: 816/529, loss: 0.0038517708890140057
2023-01-22 20:07:47.530633: step: 820/529, loss: 0.003562731435522437
2023-01-22 20:07:48.639900: step: 824/529, loss: 0.00018203945364803076
2023-01-22 20:07:49.763236: step: 828/529, loss: 0.0038685575127601624
2023-01-22 20:07:50.859134: step: 832/529, loss: 0.0003838546108454466
2023-01-22 20:07:51.968901: step: 836/529, loss: 0.002460089512169361
2023-01-22 20:07:53.095043: step: 840/529, loss: 0.003453589743003249
2023-01-22 20:07:54.224604: step: 844/529, loss: 0.00018978604930453002
2023-01-22 20:07:55.347223: step: 848/529, loss: 0.0005749117117375135
2023-01-22 20:07:56.472159: step: 852/529, loss: 0.00022143925889395177
2023-01-22 20:07:57.596618: step: 856/529, loss: 0.00037597783375531435
2023-01-22 20:07:58.734054: step: 860/529, loss: 0.0033526206389069557
2023-01-22 20:07:59.848535: step: 864/529, loss: 0.0016919198678806424
2023-01-22 20:08:00.955582: step: 868/529, loss: 0.0013802197063341737
2023-01-22 20:08:02.081675: step: 872/529, loss: 0.006321109365671873
2023-01-22 20:08:03.192009: step: 876/529, loss: 0.004838189575821161
2023-01-22 20:08:04.330934: step: 880/529, loss: 0.012661442160606384
2023-01-22 20:08:05.451676: step: 884/529, loss: 0.0006348208989948034
2023-01-22 20:08:06.560151: step: 888/529, loss: 0.007669542450457811
2023-01-22 20:08:07.650756: step: 892/529, loss: 0.001546063693240285
2023-01-22 20:08:08.756125: step: 896/529, loss: 0.001893994864076376
2023-01-22 20:08:09.860774: step: 900/529, loss: 0.002007062779739499
2023-01-22 20:08:10.976417: step: 904/529, loss: 0.015635212883353233
2023-01-22 20:08:12.089379: step: 908/529, loss: 1.7594678638488404e-06
2023-01-22 20:08:13.219997: step: 912/529, loss: 0.03224106505513191
2023-01-22 20:08:14.312186: step: 916/529, loss: 0.0016301290597766638
2023-01-22 20:08:15.416333: step: 920/529, loss: 0.004916801117360592
2023-01-22 20:08:16.521840: step: 924/529, loss: 0.019051184877753258
2023-01-22 20:08:17.632142: step: 928/529, loss: 0.001486110151745379
2023-01-22 20:08:18.738496: step: 932/529, loss: 0.0009265593835152686
2023-01-22 20:08:19.870760: step: 936/529, loss: 0.0016251954948529601
2023-01-22 20:08:20.981312: step: 940/529, loss: 0.005804730579257011
2023-01-22 20:08:22.087194: step: 944/529, loss: 0.008127120323479176
2023-01-22 20:08:23.184298: step: 948/529, loss: 0.006725279148668051
2023-01-22 20:08:24.277873: step: 952/529, loss: 0.0013801433378830552
2023-01-22 20:08:25.378071: step: 956/529, loss: 0.005127770826220512
2023-01-22 20:08:26.486189: step: 960/529, loss: 0.016132310032844543
2023-01-22 20:08:27.613293: step: 964/529, loss: 0.0035112574696540833
2023-01-22 20:08:28.713203: step: 968/529, loss: 0.02039238251745701
2023-01-22 20:08:29.804493: step: 972/529, loss: 0.0004880115739069879
2023-01-22 20:08:30.940807: step: 976/529, loss: 0.00316818174906075
2023-01-22 20:08:32.074855: step: 980/529, loss: 0.008138158358633518
2023-01-22 20:08:33.221562: step: 984/529, loss: 0.007486666087061167
2023-01-22 20:08:34.334260: step: 988/529, loss: 0.003407453652471304
2023-01-22 20:08:35.434684: step: 992/529, loss: 0.000957888551056385
2023-01-22 20:08:36.559246: step: 996/529, loss: 0.0041221315041184425
2023-01-22 20:08:37.677331: step: 1000/529, loss: 0.0081532197073102
2023-01-22 20:08:38.783697: step: 1004/529, loss: 0.002281612018123269
2023-01-22 20:08:39.905780: step: 1008/529, loss: 0.0033546830527484417
2023-01-22 20:08:41.003221: step: 1012/529, loss: 0.004054310731589794
2023-01-22 20:08:42.100873: step: 1016/529, loss: 0.0037001371383666992
2023-01-22 20:08:43.234040: step: 1020/529, loss: 0.01609238050878048
2023-01-22 20:08:44.337443: step: 1024/529, loss: 0.003183288499712944
2023-01-22 20:08:45.451252: step: 1028/529, loss: 0.005319239571690559
2023-01-22 20:08:46.587001: step: 1032/529, loss: 0.006130259949713945
2023-01-22 20:08:47.719106: step: 1036/529, loss: 0.007439969573169947
2023-01-22 20:08:48.828738: step: 1040/529, loss: 0.005116703920066357
2023-01-22 20:08:49.960057: step: 1044/529, loss: 0.0030436678789556026
2023-01-22 20:08:51.049060: step: 1048/529, loss: 8.897004590835422e-05
2023-01-22 20:08:52.151390: step: 1052/529, loss: 0.0040328060276806355
2023-01-22 20:08:53.253438: step: 1056/529, loss: 0.0003829003544524312
2023-01-22 20:08:54.369236: step: 1060/529, loss: 0.001235216623172164
2023-01-22 20:08:55.502516: step: 1064/529, loss: 0.0004490836290642619
2023-01-22 20:08:56.609660: step: 1068/529, loss: 0.0005292270798236132
2023-01-22 20:08:57.720384: step: 1072/529, loss: 0.0014304673532024026
2023-01-22 20:08:58.820487: step: 1076/529, loss: 0.0005602949531748891
2023-01-22 20:08:59.925772: step: 1080/529, loss: 0.0006935730925761163
2023-01-22 20:09:01.041253: step: 1084/529, loss: 0.001220155507326126
2023-01-22 20:09:02.156274: step: 1088/529, loss: 0.002035715151578188
2023-01-22 20:09:03.259674: step: 1092/529, loss: 0.0
2023-01-22 20:09:04.373870: step: 1096/529, loss: 0.0023127312306314707
2023-01-22 20:09:05.482764: step: 1100/529, loss: 0.002316381549462676
2023-01-22 20:09:06.620864: step: 1104/529, loss: 0.0013327255146577954
2023-01-22 20:09:07.719335: step: 1108/529, loss: 0.00018317702051717788
2023-01-22 20:09:08.821764: step: 1112/529, loss: 0.0016799845034256577
2023-01-22 20:09:09.913366: step: 1116/529, loss: 0.0006235731998458505
2023-01-22 20:09:11.009989: step: 1120/529, loss: 0.0033945569302886724
2023-01-22 20:09:12.121831: step: 1124/529, loss: 0.0022695627994835377
2023-01-22 20:09:13.218314: step: 1128/529, loss: 0.0011129779741168022
2023-01-22 20:09:14.309293: step: 1132/529, loss: 8.847699064062908e-05
2023-01-22 20:09:15.436338: step: 1136/529, loss: 0.0036015366204082966
2023-01-22 20:09:16.539830: step: 1140/529, loss: 0.006102883722633123
2023-01-22 20:09:17.634230: step: 1144/529, loss: 0.0004643523716367781
2023-01-22 20:09:18.748579: step: 1148/529, loss: 0.0033088033087551594
2023-01-22 20:09:19.880485: step: 1152/529, loss: 0.005510775372385979
2023-01-22 20:09:20.983247: step: 1156/529, loss: 0.0017819063505157828
2023-01-22 20:09:22.122443: step: 1160/529, loss: 0.004066335968673229
2023-01-22 20:09:23.242133: step: 1164/529, loss: 0.0023045812267810106
2023-01-22 20:09:24.348590: step: 1168/529, loss: 0.0028221295215189457
2023-01-22 20:09:25.438753: step: 1172/529, loss: 0.0011922846315428615
2023-01-22 20:09:26.541147: step: 1176/529, loss: 0.00424084672704339
2023-01-22 20:09:27.656701: step: 1180/529, loss: 0.014814452268183231
2023-01-22 20:09:28.776343: step: 1184/529, loss: 0.0006933690747246146
2023-01-22 20:09:29.879275: step: 1188/529, loss: 9.850793867371976e-05
2023-01-22 20:09:30.991771: step: 1192/529, loss: 0.0046796114183962345
2023-01-22 20:09:32.114161: step: 1196/529, loss: 0.0018349813763052225
2023-01-22 20:09:33.236874: step: 1200/529, loss: 0.00014269088569562882
2023-01-22 20:09:34.344786: step: 1204/529, loss: 0.0031323202420026064
2023-01-22 20:09:35.447394: step: 1208/529, loss: 0.006606937386095524
2023-01-22 20:09:36.539838: step: 1212/529, loss: 0.0018760734237730503
2023-01-22 20:09:37.653274: step: 1216/529, loss: 3.755764555535279e-05
2023-01-22 20:09:38.771629: step: 1220/529, loss: 0.0013470997801050544
2023-01-22 20:09:39.895691: step: 1224/529, loss: 0.013409907929599285
2023-01-22 20:09:40.983126: step: 1228/529, loss: 0.010340589098632336
2023-01-22 20:09:42.112560: step: 1232/529, loss: 0.005958991125226021
2023-01-22 20:09:43.219147: step: 1236/529, loss: 7.232023926917464e-05
2023-01-22 20:09:44.314759: step: 1240/529, loss: 0.0022805503103882074
2023-01-22 20:09:45.452806: step: 1244/529, loss: 2.1513071260415018e-05
2023-01-22 20:09:46.576468: step: 1248/529, loss: 0.012328597716987133
2023-01-22 20:09:47.677169: step: 1252/529, loss: 0.004221243783831596
2023-01-22 20:09:48.778241: step: 1256/529, loss: 0.00807119719684124
2023-01-22 20:09:49.901112: step: 1260/529, loss: 2.4997354557854123e-05
2023-01-22 20:09:51.008593: step: 1264/529, loss: 0.0009072798420675099
2023-01-22 20:09:52.113121: step: 1268/529, loss: 0.00041539614903740585
2023-01-22 20:09:53.204103: step: 1272/529, loss: 0.003273399081081152
2023-01-22 20:09:54.298213: step: 1276/529, loss: 0.0009283280814997852
2023-01-22 20:09:55.387082: step: 1280/529, loss: 0.0028321912977844477
2023-01-22 20:09:56.502129: step: 1284/529, loss: 0.002910377224907279
2023-01-22 20:09:57.615129: step: 1288/529, loss: 0.0007328179781325161
2023-01-22 20:09:58.732250: step: 1292/529, loss: 0.00022568802523892373
2023-01-22 20:09:59.839635: step: 1296/529, loss: 0.0042230430990457535
2023-01-22 20:10:00.965012: step: 1300/529, loss: 0.00034572515869513154
2023-01-22 20:10:02.110696: step: 1304/529, loss: 0.0042604077607393265
2023-01-22 20:10:03.256641: step: 1308/529, loss: 0.0009138848981820047
2023-01-22 20:10:04.382466: step: 1312/529, loss: 0.0006869505159556866
2023-01-22 20:10:05.459338: step: 1316/529, loss: 0.0027945255860686302
2023-01-22 20:10:06.561933: step: 1320/529, loss: 0.001894089742563665
2023-01-22 20:10:07.673629: step: 1324/529, loss: 0.004271753132343292
2023-01-22 20:10:08.764243: step: 1328/529, loss: 0.0042986320331692696
2023-01-22 20:10:09.881060: step: 1332/529, loss: 0.004983176477253437
2023-01-22 20:10:10.995484: step: 1336/529, loss: 0.0007505838293582201
2023-01-22 20:10:12.108960: step: 1340/529, loss: 0.0036445839796215296
2023-01-22 20:10:13.200211: step: 1344/529, loss: 0.015335672535002232
2023-01-22 20:10:14.294864: step: 1348/529, loss: 0.003140975022688508
2023-01-22 20:10:15.382233: step: 1352/529, loss: 0.00034961881465278566
2023-01-22 20:10:16.494279: step: 1356/529, loss: 0.0019731668289750814
2023-01-22 20:10:17.603566: step: 1360/529, loss: 0.0015774405328556895
2023-01-22 20:10:18.694962: step: 1364/529, loss: 0.0002536348474677652
2023-01-22 20:10:19.798624: step: 1368/529, loss: 0.004726538434624672
2023-01-22 20:10:20.907612: step: 1372/529, loss: 0.0029401544015854597
2023-01-22 20:10:22.006593: step: 1376/529, loss: 0.00013591106107924134
2023-01-22 20:10:23.102968: step: 1380/529, loss: 0.00024330047017429024
2023-01-22 20:10:24.210684: step: 1384/529, loss: 0.005185817833989859
2023-01-22 20:10:25.329476: step: 1388/529, loss: 0.0015014735981822014
2023-01-22 20:10:26.459552: step: 1392/529, loss: 0.0016143311513587832
2023-01-22 20:10:27.586708: step: 1396/529, loss: 0.0026642659213393927
2023-01-22 20:10:28.702212: step: 1400/529, loss: 0.0004948779242113233
2023-01-22 20:10:29.788906: step: 1404/529, loss: 0.00017834542086347938
2023-01-22 20:10:30.884792: step: 1408/529, loss: 0.0012523995246738195
2023-01-22 20:10:31.989996: step: 1412/529, loss: 0.0064910054206848145
2023-01-22 20:10:33.097997: step: 1416/529, loss: 0.00016557337949052453
2023-01-22 20:10:34.199994: step: 1420/529, loss: 0.00013977393973618746
2023-01-22 20:10:35.303721: step: 1424/529, loss: 0.003239166457206011
2023-01-22 20:10:36.409791: step: 1428/529, loss: 0.00019846379291266203
2023-01-22 20:10:37.545980: step: 1432/529, loss: 0.0009895035764202476
2023-01-22 20:10:38.657219: step: 1436/529, loss: 6.420422141673043e-05
2023-01-22 20:10:39.793661: step: 1440/529, loss: 0.0037464520428329706
2023-01-22 20:10:40.884493: step: 1444/529, loss: 0.0007337971474044025
2023-01-22 20:10:42.000659: step: 1448/529, loss: 0.0030959288123995066
2023-01-22 20:10:43.085745: step: 1452/529, loss: 0.0057845087721943855
2023-01-22 20:10:44.189883: step: 1456/529, loss: 2.4277517240989255e-06
2023-01-22 20:10:45.299254: step: 1460/529, loss: 0.002861048560589552
2023-01-22 20:10:46.415685: step: 1464/529, loss: 0.025103222578763962
2023-01-22 20:10:47.529420: step: 1468/529, loss: 0.0005867995787411928
2023-01-22 20:10:48.631666: step: 1472/529, loss: 0.0018123721238225698
2023-01-22 20:10:49.764954: step: 1476/529, loss: 0.00454313401132822
2023-01-22 20:10:50.877271: step: 1480/529, loss: 0.007734512910246849
2023-01-22 20:10:52.000393: step: 1484/529, loss: 0.0008463799022138119
2023-01-22 20:10:53.091705: step: 1488/529, loss: 0.0025026723742485046
2023-01-22 20:10:54.194995: step: 1492/529, loss: 0.002344332169741392
2023-01-22 20:10:55.318350: step: 1496/529, loss: 0.022468727082014084
2023-01-22 20:10:56.430127: step: 1500/529, loss: 0.001937435707077384
2023-01-22 20:10:57.557173: step: 1504/529, loss: 0.004542469047009945
2023-01-22 20:10:58.648194: step: 1508/529, loss: 0.00027558536385186017
2023-01-22 20:10:59.775367: step: 1512/529, loss: 0.00039425372960977256
2023-01-22 20:11:00.884657: step: 1516/529, loss: 0.002080772537738085
2023-01-22 20:11:01.981927: step: 1520/529, loss: 0.0005550920031964779
2023-01-22 20:11:03.110308: step: 1524/529, loss: 0.001061206916347146
2023-01-22 20:11:04.190032: step: 1528/529, loss: 0.0032434735912829638
2023-01-22 20:11:05.293321: step: 1532/529, loss: 0.0002451745676808059
2023-01-22 20:11:06.392855: step: 1536/529, loss: 0.001608675578609109
2023-01-22 20:11:07.514479: step: 1540/529, loss: 0.00017154146917164326
2023-01-22 20:11:08.620946: step: 1544/529, loss: 0.0007907557883299887
2023-01-22 20:11:09.759552: step: 1548/529, loss: 0.003614268731325865
2023-01-22 20:11:10.877392: step: 1552/529, loss: 0.0022618568036705256
2023-01-22 20:11:11.993151: step: 1556/529, loss: 0.0068869260139763355
2023-01-22 20:11:13.113271: step: 1560/529, loss: 0.007398021407425404
2023-01-22 20:11:14.224819: step: 1564/529, loss: 0.0059370240196585655
2023-01-22 20:11:15.377448: step: 1568/529, loss: 0.007094777189195156
2023-01-22 20:11:16.492123: step: 1572/529, loss: 0.0007351635140366852
2023-01-22 20:11:17.574095: step: 1576/529, loss: 0.004753817338496447
2023-01-22 20:11:18.687297: step: 1580/529, loss: 0.0010637149680405855
2023-01-22 20:11:19.825281: step: 1584/529, loss: 3.296718932688236e-05
2023-01-22 20:11:20.926159: step: 1588/529, loss: 0.001035338151268661
2023-01-22 20:11:22.019993: step: 1592/529, loss: 0.002007863251492381
2023-01-22 20:11:23.138524: step: 1596/529, loss: 0.010607047006487846
2023-01-22 20:11:24.244279: step: 1600/529, loss: 0.002998506184667349
2023-01-22 20:11:25.351256: step: 1604/529, loss: 0.0006424991879612207
2023-01-22 20:11:26.455996: step: 1608/529, loss: 0.003501034574583173
2023-01-22 20:11:27.552882: step: 1612/529, loss: 0.0025091341231018305
2023-01-22 20:11:28.661935: step: 1616/529, loss: 0.0004386629443615675
2023-01-22 20:11:29.764859: step: 1620/529, loss: 0.008217046037316322
2023-01-22 20:11:30.856064: step: 1624/529, loss: 0.005666786339133978
2023-01-22 20:11:31.942307: step: 1628/529, loss: 0.003978584427386522
2023-01-22 20:11:33.045200: step: 1632/529, loss: 0.003186688758432865
2023-01-22 20:11:34.190883: step: 1636/529, loss: 0.00022075467859394848
2023-01-22 20:11:35.285125: step: 1640/529, loss: 0.0002991705550812185
2023-01-22 20:11:36.394564: step: 1644/529, loss: 0.004022225271910429
2023-01-22 20:11:37.491638: step: 1648/529, loss: 0.0012513544643297791
2023-01-22 20:11:38.577718: step: 1652/529, loss: 0.003747907467186451
2023-01-22 20:11:39.673949: step: 1656/529, loss: 6.074237899156287e-05
2023-01-22 20:11:40.781935: step: 1660/529, loss: 0.0006146800587885082
2023-01-22 20:11:41.902919: step: 1664/529, loss: 0.005680084228515625
2023-01-22 20:11:43.002105: step: 1668/529, loss: 0.002186031546443701
2023-01-22 20:11:44.105851: step: 1672/529, loss: 0.00376828177832067
2023-01-22 20:11:45.205488: step: 1676/529, loss: 0.0013247650349512696
2023-01-22 20:11:46.307212: step: 1680/529, loss: 0.000754302367568016
2023-01-22 20:11:47.410294: step: 1684/529, loss: 0.007850531488656998
2023-01-22 20:11:48.522752: step: 1688/529, loss: 7.819827442290261e-05
2023-01-22 20:11:49.627643: step: 1692/529, loss: 2.714921356528066e-05
2023-01-22 20:11:50.742718: step: 1696/529, loss: 0.003312834072858095
2023-01-22 20:11:51.854677: step: 1700/529, loss: 0.004837794695049524
2023-01-22 20:11:52.988156: step: 1704/529, loss: 0.005805597640573978
2023-01-22 20:11:54.103589: step: 1708/529, loss: 0.002504920121282339
2023-01-22 20:11:55.196326: step: 1712/529, loss: 0.0016883322969079018
2023-01-22 20:11:56.306709: step: 1716/529, loss: 0.002296832390129566
2023-01-22 20:11:57.431265: step: 1720/529, loss: 0.004409465938806534
2023-01-22 20:11:58.545124: step: 1724/529, loss: 0.00982142798602581
2023-01-22 20:11:59.657697: step: 1728/529, loss: 0.006684282328933477
2023-01-22 20:12:00.756108: step: 1732/529, loss: 0.00036657426971942186
2023-01-22 20:12:01.898352: step: 1736/529, loss: 0.022729065269231796
2023-01-22 20:12:03.013872: step: 1740/529, loss: 0.00011018678924301639
2023-01-22 20:12:04.136639: step: 1744/529, loss: 0.0002326670364709571
2023-01-22 20:12:05.229129: step: 1748/529, loss: 0.002289942465722561
2023-01-22 20:12:06.359298: step: 1752/529, loss: 0.011409563943743706
2023-01-22 20:12:07.462537: step: 1756/529, loss: 0.0027784693520516157
2023-01-22 20:12:08.552583: step: 1760/529, loss: 0.0020392381120473146
2023-01-22 20:12:09.659535: step: 1764/529, loss: 0.0032472293823957443
2023-01-22 20:12:10.766267: step: 1768/529, loss: 0.006544557400047779
2023-01-22 20:12:11.880570: step: 1772/529, loss: 0.004073138814419508
2023-01-22 20:12:12.973436: step: 1776/529, loss: 0.0037605254910886288
2023-01-22 20:12:14.074114: step: 1780/529, loss: 0.003962155431509018
2023-01-22 20:12:15.201940: step: 1784/529, loss: 0.0020130721386522055
2023-01-22 20:12:16.306665: step: 1788/529, loss: 0.0030737388879060745
2023-01-22 20:12:17.415104: step: 1792/529, loss: 0.0002566327166277915
2023-01-22 20:12:18.518133: step: 1796/529, loss: 0.004707719199359417
2023-01-22 20:12:19.646598: step: 1800/529, loss: 0.00910465233027935
2023-01-22 20:12:20.773551: step: 1804/529, loss: 0.0006960343453101814
2023-01-22 20:12:21.867249: step: 1808/529, loss: 0.005849251989275217
2023-01-22 20:12:22.978065: step: 1812/529, loss: 0.005141881760209799
2023-01-22 20:12:24.079417: step: 1816/529, loss: 0.00015971447282936424
2023-01-22 20:12:25.178011: step: 1820/529, loss: 4.826217991649173e-05
2023-01-22 20:12:26.278428: step: 1824/529, loss: 9.297313954448327e-05
2023-01-22 20:12:27.369225: step: 1828/529, loss: 0.0008544176816940308
2023-01-22 20:12:28.470069: step: 1832/529, loss: 0.001272372668609023
2023-01-22 20:12:29.608549: step: 1836/529, loss: 0.002373679308220744
2023-01-22 20:12:30.694381: step: 1840/529, loss: 0.009036741219460964
2023-01-22 20:12:31.807972: step: 1844/529, loss: 0.00551905483007431
2023-01-22 20:12:32.950632: step: 1848/529, loss: 0.000178137473994866
2023-01-22 20:12:34.058351: step: 1852/529, loss: 9.45411557040643e-06
2023-01-22 20:12:35.179334: step: 1856/529, loss: 0.0002576617116574198
2023-01-22 20:12:36.307531: step: 1860/529, loss: 0.001806303858757019
2023-01-22 20:12:37.434932: step: 1864/529, loss: 0.002440019743517041
2023-01-22 20:12:38.546166: step: 1868/529, loss: 0.003919581882655621
2023-01-22 20:12:39.652706: step: 1872/529, loss: 0.002197820693254471
2023-01-22 20:12:40.768262: step: 1876/529, loss: 0.007047176361083984
2023-01-22 20:12:41.884391: step: 1880/529, loss: 0.00910390354692936
2023-01-22 20:12:42.997686: step: 1884/529, loss: 0.014309889636933804
2023-01-22 20:12:44.118748: step: 1888/529, loss: 0.00014088246098253876
2023-01-22 20:12:45.223367: step: 1892/529, loss: 0.0004975051851943135
2023-01-22 20:12:46.354627: step: 1896/529, loss: 0.0011556170647963881
2023-01-22 20:12:47.468698: step: 1900/529, loss: 0.007840687409043312
2023-01-22 20:12:48.583266: step: 1904/529, loss: 0.018665466457605362
2023-01-22 20:12:49.698584: step: 1908/529, loss: 0.004070708993822336
2023-01-22 20:12:50.805622: step: 1912/529, loss: 0.002608062233775854
2023-01-22 20:12:51.910193: step: 1916/529, loss: 0.006647141650319099
2023-01-22 20:12:52.991969: step: 1920/529, loss: 0.0009569816756993532
2023-01-22 20:12:54.095129: step: 1924/529, loss: 0.00476759672164917
2023-01-22 20:12:55.217077: step: 1928/529, loss: 0.0040803831070661545
2023-01-22 20:12:56.333629: step: 1932/529, loss: 0.0036367676220834255
2023-01-22 20:12:57.443941: step: 1936/529, loss: 0.010478099808096886
2023-01-22 20:12:58.544310: step: 1940/529, loss: 0.0038589893374592066
2023-01-22 20:12:59.634845: step: 1944/529, loss: 0.0007154970080591738
2023-01-22 20:13:00.740628: step: 1948/529, loss: 0.0011981292627751827
2023-01-22 20:13:01.871086: step: 1952/529, loss: 0.005452464800328016
2023-01-22 20:13:02.979961: step: 1956/529, loss: 0.0004163089324720204
2023-01-22 20:13:04.062182: step: 1960/529, loss: 0.004430715925991535
2023-01-22 20:13:05.168502: step: 1964/529, loss: 0.0038386895321309566
2023-01-22 20:13:06.265040: step: 1968/529, loss: 0.006286457646638155
2023-01-22 20:13:07.360184: step: 1972/529, loss: 0.007337962742894888
2023-01-22 20:13:08.499320: step: 1976/529, loss: 0.003538707038387656
2023-01-22 20:13:09.638199: step: 1980/529, loss: 0.04257753863930702
2023-01-22 20:13:10.754714: step: 1984/529, loss: 0.003906108206138015
2023-01-22 20:13:11.850331: step: 1988/529, loss: 0.0028025375213474035
2023-01-22 20:13:12.959316: step: 1992/529, loss: 0.0004601016116794199
2023-01-22 20:13:14.061768: step: 1996/529, loss: 0.0002046436711680144
2023-01-22 20:13:15.165937: step: 2000/529, loss: 1.3262655556900427e-05
2023-01-22 20:13:16.265554: step: 2004/529, loss: 0.00196659192442894
2023-01-22 20:13:17.387569: step: 2008/529, loss: 0.0038509811274707317
2023-01-22 20:13:18.503156: step: 2012/529, loss: 0.005182947032153606
2023-01-22 20:13:19.606890: step: 2016/529, loss: 0.004308459348976612
2023-01-22 20:13:20.726876: step: 2020/529, loss: 0.004337576683610678
2023-01-22 20:13:21.839391: step: 2024/529, loss: 0.0009445503819733858
2023-01-22 20:13:22.945082: step: 2028/529, loss: 0.006655809003859758
2023-01-22 20:13:24.048008: step: 2032/529, loss: 0.002387002110481262
2023-01-22 20:13:25.157009: step: 2036/529, loss: 0.0008364159148186445
2023-01-22 20:13:26.275167: step: 2040/529, loss: 0.0003520515456330031
2023-01-22 20:13:27.399046: step: 2044/529, loss: 0.0003551412373781204
2023-01-22 20:13:28.512668: step: 2048/529, loss: 0.002720827702432871
2023-01-22 20:13:29.623515: step: 2052/529, loss: 0.011590850539505482
2023-01-22 20:13:30.752575: step: 2056/529, loss: 0.0007229375187307596
2023-01-22 20:13:31.893837: step: 2060/529, loss: 0.0027340345550328493
2023-01-22 20:13:33.021300: step: 2064/529, loss: 0.0039020460098981857
2023-01-22 20:13:34.131099: step: 2068/529, loss: 0.0023356035817414522
2023-01-22 20:13:35.232385: step: 2072/529, loss: 0.0012758683878928423
2023-01-22 20:13:36.330020: step: 2076/529, loss: 0.003053620457649231
2023-01-22 20:13:37.439388: step: 2080/529, loss: 0.02930067852139473
2023-01-22 20:13:38.546759: step: 2084/529, loss: 0.0010876203887164593
2023-01-22 20:13:39.651495: step: 2088/529, loss: 0.001289432868361473
2023-01-22 20:13:40.758675: step: 2092/529, loss: 0.0017837306950241327
2023-01-22 20:13:41.875498: step: 2096/529, loss: 0.015498174354434013
2023-01-22 20:13:42.985529: step: 2100/529, loss: 0.006176387891173363
2023-01-22 20:13:44.082993: step: 2104/529, loss: 0.004790736827999353
2023-01-22 20:13:45.166967: step: 2108/529, loss: 0.003857166040688753
2023-01-22 20:13:46.268145: step: 2112/529, loss: 0.017585232853889465
2023-01-22 20:13:47.366559: step: 2116/529, loss: 0.01703360117971897
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3324241913746631, 'r': 0.33431654920032533, 'f1': 0.33336768482227336}, 'combined': 0.2456393467111488, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3725680678240066, 'r': 0.2992812815189377, 'f1': 0.3319275337557464}, 'combined': 0.20401399635719047, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33195153163272817, 'r': 0.35084820326267474, 'f1': 0.34113838213916897}, 'combined': 0.2513651236814929, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35365020505057954, 'r': 0.31074636734946937, 'f1': 0.3308130146875347}, 'combined': 0.2033289748811189, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33724339046658824, 'r': 0.34620241791731354, 'f1': 0.3416641839745772}, 'combined': 0.25175255661284635, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36533596080989306, 'r': 0.2973296997067528, 'f1': 0.32784324884133603}, 'combined': 0.20249141840200172, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36607142857142855, 'r': 0.44565217391304346, 'f1': 0.4019607843137254}, 'combined': 0.2009803921568627, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 15
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 20:16:14.945676: step: 4/529, loss: 0.0025931207928806543
2023-01-22 20:16:16.037995: step: 8/529, loss: 0.002882205881178379
2023-01-22 20:16:17.132182: step: 12/529, loss: 0.0019329885253682733
2023-01-22 20:16:18.223450: step: 16/529, loss: 0.004193895496428013
2023-01-22 20:16:19.318636: step: 20/529, loss: 0.00379492761567235
2023-01-22 20:16:20.402196: step: 24/529, loss: 0.0005721582565456629
2023-01-22 20:16:21.514460: step: 28/529, loss: 0.00034021068131551147
2023-01-22 20:16:22.620061: step: 32/529, loss: 0.0014818633208051324
2023-01-22 20:16:23.734055: step: 36/529, loss: 0.0024233476724475622
2023-01-22 20:16:24.858551: step: 40/529, loss: 0.01127456035465002
2023-01-22 20:16:25.978478: step: 44/529, loss: 0.0026036002673208714
2023-01-22 20:16:27.097461: step: 48/529, loss: 0.009529824368655682
2023-01-22 20:16:28.202328: step: 52/529, loss: 0.003497038036584854
2023-01-22 20:16:29.290696: step: 56/529, loss: 1.0660816087693092e-06
2023-01-22 20:16:30.380244: step: 60/529, loss: 0.0006411707727238536
2023-01-22 20:16:31.470621: step: 64/529, loss: 0.0019496476743370295
2023-01-22 20:16:32.585761: step: 68/529, loss: 8.146338223014027e-05
2023-01-22 20:16:33.684997: step: 72/529, loss: 0.001929825753904879
2023-01-22 20:16:34.790196: step: 76/529, loss: 0.005785155110061169
2023-01-22 20:16:35.881954: step: 80/529, loss: 0.003134605474770069
2023-01-22 20:16:36.993377: step: 84/529, loss: 4.341760813986184e-06
2023-01-22 20:16:38.124272: step: 88/529, loss: 0.008819718845188618
2023-01-22 20:16:39.211915: step: 92/529, loss: 0.0016645672731101513
2023-01-22 20:16:40.317885: step: 96/529, loss: 0.0
2023-01-22 20:16:41.412445: step: 100/529, loss: 0.0015565308276563883
2023-01-22 20:16:42.544260: step: 104/529, loss: 0.004332202486693859
2023-01-22 20:16:43.653204: step: 108/529, loss: 0.011444944888353348
2023-01-22 20:16:44.740256: step: 112/529, loss: 0.00030909196357242763
2023-01-22 20:16:45.846364: step: 116/529, loss: 0.0016193374758586287
2023-01-22 20:16:46.953342: step: 120/529, loss: 0.0003048228973057121
2023-01-22 20:16:48.063452: step: 124/529, loss: 0.00768269831314683
2023-01-22 20:16:49.183285: step: 128/529, loss: 0.002439528238028288
2023-01-22 20:16:50.302374: step: 132/529, loss: 0.0016832355177029967
2023-01-22 20:16:51.397445: step: 136/529, loss: 0.007965903729200363
2023-01-22 20:16:52.504853: step: 140/529, loss: 0.00942944921553135
2023-01-22 20:16:53.586938: step: 144/529, loss: 0.01987425424158573
2023-01-22 20:16:54.688287: step: 148/529, loss: 0.0010225827572867274
2023-01-22 20:16:55.777178: step: 152/529, loss: 0.0005653511034324765
2023-01-22 20:16:56.871224: step: 156/529, loss: 0.00024072726955637336
2023-01-22 20:16:57.942868: step: 160/529, loss: 0.0017016800120472908
2023-01-22 20:16:59.049644: step: 164/529, loss: 0.0008846782729960978
2023-01-22 20:17:00.168374: step: 168/529, loss: 0.01710948720574379
2023-01-22 20:17:01.311565: step: 172/529, loss: 0.0028305889572948217
2023-01-22 20:17:02.428873: step: 176/529, loss: 0.0014025341952219605
2023-01-22 20:17:03.533873: step: 180/529, loss: 0.0015463435556739569
2023-01-22 20:17:04.660175: step: 184/529, loss: 0.006373053882271051
2023-01-22 20:17:05.784572: step: 188/529, loss: 0.0009270533919334412
2023-01-22 20:17:06.905907: step: 192/529, loss: 0.0024236892350018024
2023-01-22 20:17:07.995316: step: 196/529, loss: 0.0032860967330634594
2023-01-22 20:17:09.122731: step: 200/529, loss: 0.007065056823194027
2023-01-22 20:17:10.223396: step: 204/529, loss: 0.0011449287412688136
2023-01-22 20:17:11.341035: step: 208/529, loss: 0.0018164193024858832
2023-01-22 20:17:12.477208: step: 212/529, loss: 0.0077828397043049335
2023-01-22 20:17:13.586792: step: 216/529, loss: 0.0019382606260478497
2023-01-22 20:17:14.707236: step: 220/529, loss: 0.00045744821545667946
2023-01-22 20:17:15.804041: step: 224/529, loss: 0.003052780171856284
2023-01-22 20:17:16.928467: step: 228/529, loss: 0.0009677736088633537
2023-01-22 20:17:18.038579: step: 232/529, loss: 0.0010485561797395349
2023-01-22 20:17:19.152839: step: 236/529, loss: 0.004682354629039764
2023-01-22 20:17:20.298511: step: 240/529, loss: 0.0010485638631507754
2023-01-22 20:17:21.406156: step: 244/529, loss: 0.0005701185436919332
2023-01-22 20:17:22.518521: step: 248/529, loss: 0.0077110594138503075
2023-01-22 20:17:23.641655: step: 252/529, loss: 0.004379655700176954
2023-01-22 20:17:24.734978: step: 256/529, loss: 0.0002996704715769738
2023-01-22 20:17:25.848678: step: 260/529, loss: 0.0031712246127426624
2023-01-22 20:17:26.967051: step: 264/529, loss: 0.002312564058229327
2023-01-22 20:17:28.070435: step: 268/529, loss: 0.0011986871249973774
2023-01-22 20:17:29.176708: step: 272/529, loss: 0.001462261425331235
2023-01-22 20:17:30.312528: step: 276/529, loss: 0.0013160841772332788
2023-01-22 20:17:31.408230: step: 280/529, loss: 0.020053409039974213
2023-01-22 20:17:32.513394: step: 284/529, loss: 0.0011960159754380584
2023-01-22 20:17:33.603131: step: 288/529, loss: 0.0027911916840821505
2023-01-22 20:17:34.697174: step: 292/529, loss: 0.0005166210466995835
2023-01-22 20:17:35.816473: step: 296/529, loss: 0.001611589454114437
2023-01-22 20:17:36.946249: step: 300/529, loss: 0.008736606687307358
2023-01-22 20:17:38.054395: step: 304/529, loss: 0.0021758999209851027
2023-01-22 20:17:39.165793: step: 308/529, loss: 0.00048054257058538496
2023-01-22 20:17:40.265966: step: 312/529, loss: 0.0006689963047392666
2023-01-22 20:17:41.358408: step: 316/529, loss: 0.00018199862097389996
2023-01-22 20:17:42.444328: step: 320/529, loss: 0.001530970330350101
2023-01-22 20:17:43.547853: step: 324/529, loss: 0.0016844660276547074
2023-01-22 20:17:44.665718: step: 328/529, loss: 0.0002713404828682542
2023-01-22 20:17:45.769291: step: 332/529, loss: 0.0018338896334171295
2023-01-22 20:17:46.894388: step: 336/529, loss: 0.011477985419332981
2023-01-22 20:17:48.007165: step: 340/529, loss: 0.003239257726818323
2023-01-22 20:17:49.087586: step: 344/529, loss: 0.0018541333265602589
2023-01-22 20:17:50.196386: step: 348/529, loss: 0.007821747101843357
2023-01-22 20:17:51.295807: step: 352/529, loss: 0.0037999227643013
2023-01-22 20:17:52.419062: step: 356/529, loss: 0.0011009207228198647
2023-01-22 20:17:53.519301: step: 360/529, loss: 8.387991692870855e-05
2023-01-22 20:17:54.644479: step: 364/529, loss: 0.0031167457345873117
2023-01-22 20:17:55.779894: step: 368/529, loss: 0.0050917682237923145
2023-01-22 20:17:56.873972: step: 372/529, loss: 0.0006687749992124736
2023-01-22 20:17:57.989703: step: 376/529, loss: 0.0038873106241226196
2023-01-22 20:17:59.106812: step: 380/529, loss: 0.0040429700165987015
2023-01-22 20:18:00.270240: step: 384/529, loss: 0.012457926757633686
2023-01-22 20:18:01.379853: step: 388/529, loss: 0.005165906623005867
2023-01-22 20:18:02.482892: step: 392/529, loss: 9.569324902258813e-05
2023-01-22 20:18:03.572731: step: 396/529, loss: 0.00024494295939803123
2023-01-22 20:18:04.701414: step: 400/529, loss: 0.0033263189252465963
2023-01-22 20:18:05.852182: step: 404/529, loss: 0.0007285865140147507
2023-01-22 20:18:06.938150: step: 408/529, loss: 4.938764959661057e-06
2023-01-22 20:18:08.070541: step: 412/529, loss: 0.002756058005616069
2023-01-22 20:18:09.182254: step: 416/529, loss: 0.0026710699312388897
2023-01-22 20:18:10.292012: step: 420/529, loss: 0.0003971263358835131
2023-01-22 20:18:11.388231: step: 424/529, loss: 0.004400121513754129
2023-01-22 20:18:12.494151: step: 428/529, loss: 0.004421007353812456
2023-01-22 20:18:13.606476: step: 432/529, loss: 2.6119578251382336e-05
2023-01-22 20:18:14.710553: step: 436/529, loss: 0.0026272854302078485
2023-01-22 20:18:15.812316: step: 440/529, loss: 0.006672269199043512
2023-01-22 20:18:16.895366: step: 444/529, loss: 0.00010470183042343706
2023-01-22 20:18:17.986807: step: 448/529, loss: 7.937334885355085e-05
2023-01-22 20:18:19.093924: step: 452/529, loss: 0.001821152283810079
2023-01-22 20:18:20.199705: step: 456/529, loss: 0.00498504051938653
2023-01-22 20:18:21.331130: step: 460/529, loss: 0.004358218517154455
2023-01-22 20:18:22.440849: step: 464/529, loss: 8.644044282846153e-05
2023-01-22 20:18:23.529399: step: 468/529, loss: 0.0026828604750335217
2023-01-22 20:18:24.655119: step: 472/529, loss: 0.002760467818006873
2023-01-22 20:18:25.765241: step: 476/529, loss: 0.003166378941386938
2023-01-22 20:18:26.873328: step: 480/529, loss: 0.005208566784858704
2023-01-22 20:18:27.977334: step: 484/529, loss: 0.003407896962016821
2023-01-22 20:18:29.095193: step: 488/529, loss: 1.0104229659191333e-05
2023-01-22 20:18:30.204472: step: 492/529, loss: 0.002344684675335884
2023-01-22 20:18:31.321361: step: 496/529, loss: 0.006681410130113363
2023-01-22 20:18:32.458697: step: 500/529, loss: 0.010459478944540024
2023-01-22 20:18:33.575820: step: 504/529, loss: 0.004894265905022621
2023-01-22 20:18:34.674392: step: 508/529, loss: 0.0005904762074351311
2023-01-22 20:18:35.790987: step: 512/529, loss: 0.0008682598127052188
2023-01-22 20:18:36.917525: step: 516/529, loss: 0.005269668530672789
2023-01-22 20:18:38.035837: step: 520/529, loss: 0.00030751971644349396
2023-01-22 20:18:39.148703: step: 524/529, loss: 0.004326560068875551
2023-01-22 20:18:40.269797: step: 528/529, loss: 7.450662815244868e-05
2023-01-22 20:18:41.382051: step: 532/529, loss: 0.0028433911502361298
2023-01-22 20:18:42.483729: step: 536/529, loss: 0.001040037488564849
2023-01-22 20:18:43.592687: step: 540/529, loss: 0.00033004762372002006
2023-01-22 20:18:44.684842: step: 544/529, loss: 0.0007799130980856717
2023-01-22 20:18:45.812448: step: 548/529, loss: 0.00200090603902936
2023-01-22 20:18:46.932579: step: 552/529, loss: 0.0035005605313926935
2023-01-22 20:18:48.017859: step: 556/529, loss: 1.3783548524770595e-08
2023-01-22 20:18:49.131906: step: 560/529, loss: 0.004007306415587664
2023-01-22 20:18:50.248908: step: 564/529, loss: 0.0006187392864376307
2023-01-22 20:18:51.372495: step: 568/529, loss: 0.01276328507810831
2023-01-22 20:18:52.476753: step: 572/529, loss: 0.002960295882076025
2023-01-22 20:18:53.585698: step: 576/529, loss: 8.483040437567979e-05
2023-01-22 20:18:54.698560: step: 580/529, loss: 1.692560726951342e-05
2023-01-22 20:18:55.803494: step: 584/529, loss: 0.002499618800356984
2023-01-22 20:18:56.908088: step: 588/529, loss: 0.0022299056872725487
2023-01-22 20:18:58.008504: step: 592/529, loss: 0.0022444468922913074
2023-01-22 20:18:59.130440: step: 596/529, loss: 0.004373785108327866
2023-01-22 20:19:00.247667: step: 600/529, loss: 0.001633203704841435
2023-01-22 20:19:01.370917: step: 604/529, loss: 0.001125205191783607
2023-01-22 20:19:02.480922: step: 608/529, loss: 0.00473776925355196
2023-01-22 20:19:03.582674: step: 612/529, loss: 0.007133645936846733
2023-01-22 20:19:04.723008: step: 616/529, loss: 0.001407354837283492
2023-01-22 20:19:05.827290: step: 620/529, loss: 0.003916764631867409
2023-01-22 20:19:06.925946: step: 624/529, loss: 0.0006860258872620761
2023-01-22 20:19:08.031392: step: 628/529, loss: 0.0005836035707034171
2023-01-22 20:19:09.140202: step: 632/529, loss: 5.0458707846701145e-05
2023-01-22 20:19:10.267743: step: 636/529, loss: 0.02299467660486698
2023-01-22 20:19:11.390366: step: 640/529, loss: 0.005951618775725365
2023-01-22 20:19:12.499620: step: 644/529, loss: 0.00011345349776092917
2023-01-22 20:19:13.632681: step: 648/529, loss: 0.005091405473649502
2023-01-22 20:19:14.750359: step: 652/529, loss: 0.0007573122857138515
2023-01-22 20:19:15.868377: step: 656/529, loss: 0.000507863238453865
2023-01-22 20:19:16.990062: step: 660/529, loss: 0.0010490842396393418
2023-01-22 20:19:18.125609: step: 664/529, loss: 0.007440539542585611
2023-01-22 20:19:19.255792: step: 668/529, loss: 0.0006416182150132954
2023-01-22 20:19:20.361237: step: 672/529, loss: 0.006349744275212288
2023-01-22 20:19:21.471688: step: 676/529, loss: 0.0023344228975474834
2023-01-22 20:19:22.591428: step: 680/529, loss: 1.2900488400191534e-05
2023-01-22 20:19:23.718739: step: 684/529, loss: 5.103509920445504e-06
2023-01-22 20:19:24.833029: step: 688/529, loss: 0.0015895896358415484
2023-01-22 20:19:25.925873: step: 692/529, loss: 0.0
2023-01-22 20:19:27.025486: step: 696/529, loss: 0.006037390325218439
2023-01-22 20:19:28.141767: step: 700/529, loss: 3.3256092137889937e-05
2023-01-22 20:19:29.250860: step: 704/529, loss: 5.813862571812933e-06
2023-01-22 20:19:30.387501: step: 708/529, loss: 0.007634587585926056
2023-01-22 20:19:31.491365: step: 712/529, loss: 0.0051072873175144196
2023-01-22 20:19:32.612191: step: 716/529, loss: 0.004017191007733345
2023-01-22 20:19:33.729337: step: 720/529, loss: 0.006503316108137369
2023-01-22 20:19:34.822510: step: 724/529, loss: 0.005251658149063587
2023-01-22 20:19:35.941483: step: 728/529, loss: 0.0019055964658036828
2023-01-22 20:19:37.038882: step: 732/529, loss: 0.002239476889371872
2023-01-22 20:19:38.156281: step: 736/529, loss: 0.005064769182354212
2023-01-22 20:19:39.268999: step: 740/529, loss: 0.0077932653948664665
2023-01-22 20:19:40.370895: step: 744/529, loss: 0.003636268898844719
2023-01-22 20:19:41.519953: step: 748/529, loss: 0.004603404551744461
2023-01-22 20:19:42.612092: step: 752/529, loss: 0.006758167874068022
2023-01-22 20:19:43.715509: step: 756/529, loss: 0.002927799941971898
2023-01-22 20:19:44.809127: step: 760/529, loss: 0.0018717690836638212
2023-01-22 20:19:45.909832: step: 764/529, loss: 0.00028159821522422135
2023-01-22 20:19:47.026363: step: 768/529, loss: 0.010703489184379578
2023-01-22 20:19:48.128730: step: 772/529, loss: 0.009481514804065228
2023-01-22 20:19:49.250073: step: 776/529, loss: 0.0008355171303264797
2023-01-22 20:19:50.372553: step: 780/529, loss: 0.0051216003485023975
2023-01-22 20:19:51.458819: step: 784/529, loss: 0.0047023966908454895
2023-01-22 20:19:52.584259: step: 788/529, loss: 0.003678713459521532
2023-01-22 20:19:53.693770: step: 792/529, loss: 0.004792946390807629
2023-01-22 20:19:54.811137: step: 796/529, loss: 0.003073078813031316
2023-01-22 20:19:55.957041: step: 800/529, loss: 0.00048310161218978465
2023-01-22 20:19:57.057317: step: 804/529, loss: 0.004600821062922478
2023-01-22 20:19:58.151366: step: 808/529, loss: 1.5896202967269346e-05
2023-01-22 20:19:59.237956: step: 812/529, loss: 0.02302611619234085
2023-01-22 20:20:00.334617: step: 816/529, loss: 0.0013681501150131226
2023-01-22 20:20:01.447480: step: 820/529, loss: 0.005964048206806183
2023-01-22 20:20:02.562983: step: 824/529, loss: 0.0037615399342030287
2023-01-22 20:20:03.703663: step: 828/529, loss: 0.0024312094319611788
2023-01-22 20:20:04.830686: step: 832/529, loss: 0.00256152031943202
2023-01-22 20:20:05.943715: step: 836/529, loss: 0.01198567170649767
2023-01-22 20:20:07.054316: step: 840/529, loss: 0.0008322140201926231
2023-01-22 20:20:08.157538: step: 844/529, loss: 0.001330302213318646
2023-01-22 20:20:09.288565: step: 848/529, loss: 0.00021860735432710499
2023-01-22 20:20:10.397645: step: 852/529, loss: 0.0007062862860038877
2023-01-22 20:20:11.524473: step: 856/529, loss: 0.00025333184748888016
2023-01-22 20:20:12.629585: step: 860/529, loss: 0.00178387516643852
2023-01-22 20:20:13.715366: step: 864/529, loss: 0.004562384448945522
2023-01-22 20:20:14.826529: step: 868/529, loss: 0.0013166420394554734
2023-01-22 20:20:15.937607: step: 872/529, loss: 0.0011279626050963998
2023-01-22 20:20:17.058710: step: 876/529, loss: 0.0037275163922458887
2023-01-22 20:20:18.145269: step: 880/529, loss: 0.0012887457851320505
2023-01-22 20:20:19.262242: step: 884/529, loss: 0.015079370699822903
2023-01-22 20:20:20.360039: step: 888/529, loss: 0.0024891633074730635
2023-01-22 20:20:21.465076: step: 892/529, loss: 0.008975147269666195
2023-01-22 20:20:22.593079: step: 896/529, loss: 0.008496423251926899
2023-01-22 20:20:23.696969: step: 900/529, loss: 0.0013733908999711275
2023-01-22 20:20:24.795760: step: 904/529, loss: 1.4562931028194726e-05
2023-01-22 20:20:25.923690: step: 908/529, loss: 0.0004261470749042928
2023-01-22 20:20:27.023712: step: 912/529, loss: 0.004404229111969471
2023-01-22 20:20:28.115822: step: 916/529, loss: 0.00046006691991351545
2023-01-22 20:20:29.204233: step: 920/529, loss: 7.002323400229216e-05
2023-01-22 20:20:30.334124: step: 924/529, loss: 0.010251963511109352
2023-01-22 20:20:31.441074: step: 928/529, loss: 0.0015799937536939979
2023-01-22 20:20:32.551551: step: 932/529, loss: 0.006481474731117487
2023-01-22 20:20:33.673707: step: 936/529, loss: 0.006786048877984285
2023-01-22 20:20:34.792805: step: 940/529, loss: 0.02876487374305725
2023-01-22 20:20:35.889296: step: 944/529, loss: 0.0009365540463477373
2023-01-22 20:20:36.980618: step: 948/529, loss: 0.003659546375274658
2023-01-22 20:20:38.075735: step: 952/529, loss: 0.002510154852643609
2023-01-22 20:20:39.176797: step: 956/529, loss: 0.0020188719499856234
2023-01-22 20:20:40.284658: step: 960/529, loss: 0.003070984035730362
2023-01-22 20:20:41.393276: step: 964/529, loss: 0.0010389360832050443
2023-01-22 20:20:42.487395: step: 968/529, loss: 0.0008549040067009628
2023-01-22 20:20:43.606370: step: 972/529, loss: 0.002145325532183051
2023-01-22 20:20:44.711116: step: 976/529, loss: 0.0019552281592041254
2023-01-22 20:20:45.816431: step: 980/529, loss: 0.0033176466822624207
2023-01-22 20:20:46.929599: step: 984/529, loss: 0.002010810188949108
2023-01-22 20:20:48.035415: step: 988/529, loss: 0.007342258468270302
2023-01-22 20:20:49.146511: step: 992/529, loss: 0.0005395688349381089
2023-01-22 20:20:50.263393: step: 996/529, loss: 0.0006495625129900873
2023-01-22 20:20:51.389966: step: 1000/529, loss: 0.0011287410743534565
2023-01-22 20:20:52.525782: step: 1004/529, loss: 0.016856012865900993
2023-01-22 20:20:53.633330: step: 1008/529, loss: 0.0013029822148382664
2023-01-22 20:20:54.742438: step: 1012/529, loss: 0.00048373700701631606
2023-01-22 20:20:55.844640: step: 1016/529, loss: 0.001640502130612731
2023-01-22 20:20:56.978288: step: 1020/529, loss: 0.003887023078277707
2023-01-22 20:20:58.069740: step: 1024/529, loss: 0.00039018431561999023
2023-01-22 20:20:59.190249: step: 1028/529, loss: 0.001211483497172594
2023-01-22 20:21:00.287869: step: 1032/529, loss: 0.00016706189489923418
2023-01-22 20:21:01.410955: step: 1036/529, loss: 0.0021371752955019474
2023-01-22 20:21:02.511576: step: 1040/529, loss: 0.0003996858431492001
2023-01-22 20:21:03.621940: step: 1044/529, loss: 0.0077988081611692905
2023-01-22 20:21:04.757376: step: 1048/529, loss: 0.0009308267035521567
2023-01-22 20:21:05.847614: step: 1052/529, loss: 0.0010225848527625203
2023-01-22 20:21:06.947495: step: 1056/529, loss: 0.0012509291991591454
2023-01-22 20:21:08.043687: step: 1060/529, loss: 0.0005226831999607384
2023-01-22 20:21:09.160323: step: 1064/529, loss: 0.0020150465425103903
2023-01-22 20:21:10.274033: step: 1068/529, loss: 0.0009939377196133137
2023-01-22 20:21:11.411182: step: 1072/529, loss: 0.003210749477148056
2023-01-22 20:21:12.548509: step: 1076/529, loss: 0.0006924484041519463
2023-01-22 20:21:13.651305: step: 1080/529, loss: 0.002885144203901291
2023-01-22 20:21:14.758327: step: 1084/529, loss: 0.0006250622100196779
2023-01-22 20:21:15.869872: step: 1088/529, loss: 0.0024558138102293015
2023-01-22 20:21:16.974525: step: 1092/529, loss: 0.004348600283265114
2023-01-22 20:21:18.092758: step: 1096/529, loss: 3.741820719938005e-08
2023-01-22 20:21:19.202180: step: 1100/529, loss: 0.0008665123605169356
2023-01-22 20:21:20.325682: step: 1104/529, loss: 0.0005608962965197861
2023-01-22 20:21:21.441747: step: 1108/529, loss: 0.019587049260735512
2023-01-22 20:21:22.536646: step: 1112/529, loss: 0.0008584687602706254
2023-01-22 20:21:23.637665: step: 1116/529, loss: 0.00013510460848920047
2023-01-22 20:21:24.734258: step: 1120/529, loss: 0.002296841936185956
2023-01-22 20:21:25.844097: step: 1124/529, loss: 1.9500680537021253e-06
2023-01-22 20:21:26.975191: step: 1128/529, loss: 0.003928482066839933
2023-01-22 20:21:28.090127: step: 1132/529, loss: 0.0007335945847444236
2023-01-22 20:21:29.200916: step: 1136/529, loss: 0.0018274959875270724
2023-01-22 20:21:30.341568: step: 1140/529, loss: 0.002051910385489464
2023-01-22 20:21:31.460080: step: 1144/529, loss: 0.0007606869330629706
2023-01-22 20:21:32.597801: step: 1148/529, loss: 3.3471686037955806e-05
2023-01-22 20:21:33.716290: step: 1152/529, loss: 0.005596863105893135
2023-01-22 20:21:34.822741: step: 1156/529, loss: 0.0036388859152793884
2023-01-22 20:21:35.918313: step: 1160/529, loss: 0.008118441328406334
2023-01-22 20:21:37.022232: step: 1164/529, loss: 0.003701305016875267
2023-01-22 20:21:38.120242: step: 1168/529, loss: 0.0008934138459153473
2023-01-22 20:21:39.210107: step: 1172/529, loss: 3.5706798371393234e-05
2023-01-22 20:21:40.315471: step: 1176/529, loss: 0.0002724910154938698
2023-01-22 20:21:41.426909: step: 1180/529, loss: 8.002180402399972e-05
2023-01-22 20:21:42.531467: step: 1184/529, loss: 0.007702495437115431
2023-01-22 20:21:43.637837: step: 1188/529, loss: 0.0159918200224638
2023-01-22 20:21:44.758900: step: 1192/529, loss: 3.4223314287373796e-05
2023-01-22 20:21:45.845149: step: 1196/529, loss: 0.002196255372837186
2023-01-22 20:21:46.944651: step: 1200/529, loss: 0.0018897982081398368
2023-01-22 20:21:48.062436: step: 1204/529, loss: 0.00416538817808032
2023-01-22 20:21:49.161716: step: 1208/529, loss: 0.0022185135167092085
2023-01-22 20:21:50.259796: step: 1212/529, loss: 0.00011258741142228246
2023-01-22 20:21:51.387006: step: 1216/529, loss: 0.0036868834868073463
2023-01-22 20:21:52.476839: step: 1220/529, loss: 0.0037335033994168043
2023-01-22 20:21:53.593828: step: 1224/529, loss: 0.0033380205277353525
2023-01-22 20:21:54.690787: step: 1228/529, loss: 0.00019725643505807966
2023-01-22 20:21:55.795449: step: 1232/529, loss: 0.0014699926832690835
2023-01-22 20:21:56.895132: step: 1236/529, loss: 0.002882779110223055
2023-01-22 20:21:57.998551: step: 1240/529, loss: 0.0003042803145945072
2023-01-22 20:21:59.118076: step: 1244/529, loss: 0.011927705258131027
2023-01-22 20:22:00.224627: step: 1248/529, loss: 0.0030136331915855408
2023-01-22 20:22:01.324291: step: 1252/529, loss: 0.00015892813098616898
2023-01-22 20:22:02.433867: step: 1256/529, loss: 0.0017119103576987982
2023-01-22 20:22:03.539622: step: 1260/529, loss: 0.003564529586583376
2023-01-22 20:22:04.644442: step: 1264/529, loss: 0.0008605823968537152
2023-01-22 20:22:05.768166: step: 1268/529, loss: 0.0070954738184809685
2023-01-22 20:22:06.900285: step: 1272/529, loss: 8.67826456669718e-05
2023-01-22 20:22:08.016268: step: 1276/529, loss: 0.0005311279091984034
2023-01-22 20:22:09.122943: step: 1280/529, loss: 0.00010013549763243645
2023-01-22 20:22:10.215384: step: 1284/529, loss: 0.0022027790546417236
2023-01-22 20:22:11.340596: step: 1288/529, loss: 0.001970133511349559
2023-01-22 20:22:12.453270: step: 1292/529, loss: 0.0006838677218183875
2023-01-22 20:22:13.559869: step: 1296/529, loss: 0.0027949821669608355
2023-01-22 20:22:14.673271: step: 1300/529, loss: 0.006945587694644928
2023-01-22 20:22:15.767263: step: 1304/529, loss: 0.001283031771890819
2023-01-22 20:22:16.920216: step: 1308/529, loss: 0.00043243009713478386
2023-01-22 20:22:18.040462: step: 1312/529, loss: 0.013830320909619331
2023-01-22 20:22:19.160575: step: 1316/529, loss: 0.006659200880676508
2023-01-22 20:22:20.282168: step: 1320/529, loss: 0.0018646640237420797
2023-01-22 20:22:21.395035: step: 1324/529, loss: 0.001095268176868558
2023-01-22 20:22:22.511155: step: 1328/529, loss: 0.00030951350345276296
2023-01-22 20:22:23.625066: step: 1332/529, loss: 0.00019956431060563773
2023-01-22 20:22:24.746261: step: 1336/529, loss: 0.00010064123489428312
2023-01-22 20:22:25.852622: step: 1340/529, loss: 0.0020738719031214714
2023-01-22 20:22:26.951287: step: 1344/529, loss: 0.006960752420127392
2023-01-22 20:22:28.071131: step: 1348/529, loss: 0.0045841834507882595
2023-01-22 20:22:29.175020: step: 1352/529, loss: 0.0003511657996568829
2023-01-22 20:22:30.274579: step: 1356/529, loss: 0.02579730562865734
2023-01-22 20:22:31.399596: step: 1360/529, loss: 0.0030574908014386892
2023-01-22 20:22:32.500046: step: 1364/529, loss: 0.001733759418129921
2023-01-22 20:22:33.610626: step: 1368/529, loss: 0.012433758936822414
2023-01-22 20:22:34.726399: step: 1372/529, loss: 0.007851693779230118
2023-01-22 20:22:35.819594: step: 1376/529, loss: 0.002105548046529293
2023-01-22 20:22:36.918657: step: 1380/529, loss: 0.017192499712109566
2023-01-22 20:22:38.012374: step: 1384/529, loss: 0.009983750060200691
2023-01-22 20:22:39.109694: step: 1388/529, loss: 0.0007768319337628782
2023-01-22 20:22:40.214592: step: 1392/529, loss: 0.04422217607498169
2023-01-22 20:22:41.312442: step: 1396/529, loss: 2.0303315977798775e-05
2023-01-22 20:22:42.418108: step: 1400/529, loss: 0.006508501712232828
2023-01-22 20:22:43.524103: step: 1404/529, loss: 0.0009816022356972098
2023-01-22 20:22:44.621668: step: 1408/529, loss: 0.011447586119174957
2023-01-22 20:22:45.737288: step: 1412/529, loss: 0.008318210020661354
2023-01-22 20:22:46.855848: step: 1416/529, loss: 3.976057269028388e-05
2023-01-22 20:22:47.967079: step: 1420/529, loss: 0.000183207041118294
2023-01-22 20:22:49.071699: step: 1424/529, loss: 0.012049549259245396
2023-01-22 20:22:50.169184: step: 1428/529, loss: 0.0006835930398665369
2023-01-22 20:22:51.294905: step: 1432/529, loss: 0.0036181756295263767
2023-01-22 20:22:52.397822: step: 1436/529, loss: 0.0009957838337868452
2023-01-22 20:22:53.542316: step: 1440/529, loss: 0.005574852228164673
2023-01-22 20:22:54.656503: step: 1444/529, loss: 0.00015191009151749313
2023-01-22 20:22:55.769308: step: 1448/529, loss: 7.421468762913719e-05
2023-01-22 20:22:56.877705: step: 1452/529, loss: 0.008800877258181572
2023-01-22 20:22:57.986251: step: 1456/529, loss: 0.00680225295946002
2023-01-22 20:22:59.106445: step: 1460/529, loss: 0.0058050998486578465
2023-01-22 20:23:00.228229: step: 1464/529, loss: 0.00039776417543180287
2023-01-22 20:23:01.360426: step: 1468/529, loss: 0.0008068532915785909
2023-01-22 20:23:02.483622: step: 1472/529, loss: 0.006469424348324537
2023-01-22 20:23:03.591230: step: 1476/529, loss: 0.001826525549404323
2023-01-22 20:23:04.704537: step: 1480/529, loss: 0.00032020191429182887
2023-01-22 20:23:05.787789: step: 1484/529, loss: 2.783198760880623e-05
2023-01-22 20:23:06.906345: step: 1488/529, loss: 3.538999067131954e-07
2023-01-22 20:23:08.039332: step: 1492/529, loss: 0.00319074303843081
2023-01-22 20:23:09.156509: step: 1496/529, loss: 0.0022088005207479
2023-01-22 20:23:10.252611: step: 1500/529, loss: 6.174926966195926e-05
2023-01-22 20:23:11.390239: step: 1504/529, loss: 0.05603187903761864
2023-01-22 20:23:12.502735: step: 1508/529, loss: 0.004804931115359068
2023-01-22 20:23:13.609585: step: 1512/529, loss: 0.0020182293374091387
2023-01-22 20:23:14.738311: step: 1516/529, loss: 0.0029437632765620947
2023-01-22 20:23:15.857405: step: 1520/529, loss: 0.006930566858500242
2023-01-22 20:23:16.978752: step: 1524/529, loss: 0.007187227252870798
2023-01-22 20:23:18.112609: step: 1528/529, loss: 0.001824341481551528
2023-01-22 20:23:19.241780: step: 1532/529, loss: 0.003785027889534831
2023-01-22 20:23:20.350632: step: 1536/529, loss: 0.0008193620597012341
2023-01-22 20:23:21.452112: step: 1540/529, loss: 0.00029365732916630805
2023-01-22 20:23:22.575527: step: 1544/529, loss: 0.01056717149913311
2023-01-22 20:23:23.651080: step: 1548/529, loss: 0.0022380375303328037
2023-01-22 20:23:24.793458: step: 1552/529, loss: 0.00021056804689578712
2023-01-22 20:23:25.907722: step: 1556/529, loss: 0.0010288369376212358
2023-01-22 20:23:27.033122: step: 1560/529, loss: 0.021586881950497627
2023-01-22 20:23:28.161422: step: 1564/529, loss: 0.005324484780430794
2023-01-22 20:23:29.270303: step: 1568/529, loss: 0.0009446726180613041
2023-01-22 20:23:30.378547: step: 1572/529, loss: 0.005531106609851122
2023-01-22 20:23:31.466880: step: 1576/529, loss: 0.0044586253352463245
2023-01-22 20:23:32.587825: step: 1580/529, loss: 0.00010495177411939949
2023-01-22 20:23:33.703329: step: 1584/529, loss: 0.0014270716346800327
2023-01-22 20:23:34.808551: step: 1588/529, loss: 5.585437065747101e-06
2023-01-22 20:23:35.922107: step: 1592/529, loss: 0.020020265132188797
2023-01-22 20:23:37.030715: step: 1596/529, loss: 0.019138479605317116
2023-01-22 20:23:38.164817: step: 1600/529, loss: 0.0021841011475771666
2023-01-22 20:23:39.271673: step: 1604/529, loss: 0.0018570291576907039
2023-01-22 20:23:40.402383: step: 1608/529, loss: 0.02626653015613556
2023-01-22 20:23:41.516543: step: 1612/529, loss: 0.0031333270017057657
2023-01-22 20:23:42.619176: step: 1616/529, loss: 0.0030078766867518425
2023-01-22 20:23:43.732140: step: 1620/529, loss: 0.003790183225646615
2023-01-22 20:23:44.826901: step: 1624/529, loss: 0.006445739883929491
2023-01-22 20:23:45.934866: step: 1628/529, loss: 3.877152721543098e-06
2023-01-22 20:23:47.050458: step: 1632/529, loss: 0.0006510972161777318
2023-01-22 20:23:48.152606: step: 1636/529, loss: 0.004444780293852091
2023-01-22 20:23:49.272962: step: 1640/529, loss: 0.0033888453617691994
2023-01-22 20:23:50.383369: step: 1644/529, loss: 0.006991660688072443
2023-01-22 20:23:51.472229: step: 1648/529, loss: 0.002052286406978965
2023-01-22 20:23:52.597295: step: 1652/529, loss: 0.0015124494675546885
2023-01-22 20:23:53.727969: step: 1656/529, loss: 0.0024441606365144253
2023-01-22 20:23:54.834460: step: 1660/529, loss: 2.2919744878890924e-05
2023-01-22 20:23:55.936490: step: 1664/529, loss: 0.0
2023-01-22 20:23:57.041011: step: 1668/529, loss: 0.049203429371118546
2023-01-22 20:23:58.131554: step: 1672/529, loss: 0.0005132881924510002
2023-01-22 20:23:59.234742: step: 1676/529, loss: 0.006499791517853737
2023-01-22 20:24:00.345529: step: 1680/529, loss: 0.00040859272121451795
2023-01-22 20:24:01.455287: step: 1684/529, loss: 0.0
2023-01-22 20:24:02.581977: step: 1688/529, loss: 0.006004152353852987
2023-01-22 20:24:03.693356: step: 1692/529, loss: 0.00030455252272076905
2023-01-22 20:24:04.791897: step: 1696/529, loss: 0.0008103943546302617
2023-01-22 20:24:05.905126: step: 1700/529, loss: 9.840609709499404e-05
2023-01-22 20:24:07.019353: step: 1704/529, loss: 0.006235078908503056
2023-01-22 20:24:08.120181: step: 1708/529, loss: 0.0004101524828001857
2023-01-22 20:24:09.217079: step: 1712/529, loss: 0.003382493741810322
2023-01-22 20:24:10.309798: step: 1716/529, loss: 0.000858451530802995
2023-01-22 20:24:11.419505: step: 1720/529, loss: 0.001419850392267108
2023-01-22 20:24:12.544700: step: 1724/529, loss: 6.0203879002074245e-06
2023-01-22 20:24:13.658638: step: 1728/529, loss: 3.298646697658114e-05
2023-01-22 20:24:14.773370: step: 1732/529, loss: 0.002509482204914093
2023-01-22 20:24:15.878490: step: 1736/529, loss: 0.004608344752341509
2023-01-22 20:24:17.012323: step: 1740/529, loss: 0.00459503848105669
2023-01-22 20:24:18.107515: step: 1744/529, loss: 0.0004937076009809971
2023-01-22 20:24:19.234464: step: 1748/529, loss: 0.0008771317079663277
2023-01-22 20:24:20.359132: step: 1752/529, loss: 0.0012682134984061122
2023-01-22 20:24:21.449540: step: 1756/529, loss: 0.0038723472971469164
2023-01-22 20:24:22.554958: step: 1760/529, loss: 0.00032535448553971946
2023-01-22 20:24:23.691677: step: 1764/529, loss: 0.007817676290869713
2023-01-22 20:24:24.792904: step: 1768/529, loss: 0.0019246513256803155
2023-01-22 20:24:25.904005: step: 1772/529, loss: 1.6376350686186925e-05
2023-01-22 20:24:27.007431: step: 1776/529, loss: 0.00045206412323750556
2023-01-22 20:24:28.133839: step: 1780/529, loss: 0.008600435219705105
2023-01-22 20:24:29.256352: step: 1784/529, loss: 0.0011514080688357353
2023-01-22 20:24:30.370820: step: 1788/529, loss: 0.00010648132592905313
2023-01-22 20:24:31.501130: step: 1792/529, loss: 0.0056484839878976345
2023-01-22 20:24:32.637098: step: 1796/529, loss: 0.013872471638023853
2023-01-22 20:24:33.794563: step: 1800/529, loss: 0.028201404958963394
2023-01-22 20:24:34.920515: step: 1804/529, loss: 0.0005001375102438033
2023-01-22 20:24:36.042428: step: 1808/529, loss: 0.0016479961341246963
2023-01-22 20:24:37.122630: step: 1812/529, loss: 0.0006181947537697852
2023-01-22 20:24:38.228783: step: 1816/529, loss: 0.004524826537817717
2023-01-22 20:24:39.338844: step: 1820/529, loss: 0.006089237052947283
2023-01-22 20:24:40.436151: step: 1824/529, loss: 0.01219960767775774
2023-01-22 20:24:41.545467: step: 1828/529, loss: 0.0004694901581387967
2023-01-22 20:24:42.647132: step: 1832/529, loss: 0.001699551590718329
2023-01-22 20:24:43.743200: step: 1836/529, loss: 0.0028385822661221027
2023-01-22 20:24:44.861802: step: 1840/529, loss: 0.005240814294666052
2023-01-22 20:24:45.964738: step: 1844/529, loss: 0.0035254876129329205
2023-01-22 20:24:47.049124: step: 1848/529, loss: 0.0013566554989665747
2023-01-22 20:24:48.149154: step: 1852/529, loss: 0.0005813108873553574
2023-01-22 20:24:49.262209: step: 1856/529, loss: 0.004426232539117336
2023-01-22 20:24:50.358932: step: 1860/529, loss: 0.001520061050541699
2023-01-22 20:24:51.464317: step: 1864/529, loss: 0.00017613093950785697
2023-01-22 20:24:52.589494: step: 1868/529, loss: 0.0035004280507564545
2023-01-22 20:24:53.703078: step: 1872/529, loss: 0.0010813449043780565
2023-01-22 20:24:54.808878: step: 1876/529, loss: 0.000825048889964819
2023-01-22 20:24:55.931180: step: 1880/529, loss: 0.0018010709900408983
2023-01-22 20:24:57.038488: step: 1884/529, loss: 0.0009285819251090288
2023-01-22 20:24:58.132553: step: 1888/529, loss: 0.00694962777197361
2023-01-22 20:24:59.231599: step: 1892/529, loss: 0.0015481164446100593
2023-01-22 20:25:00.332416: step: 1896/529, loss: 0.002436800394207239
2023-01-22 20:25:01.465565: step: 1900/529, loss: 0.0025722808204591274
2023-01-22 20:25:02.587441: step: 1904/529, loss: 0.0008329510455951095
2023-01-22 20:25:03.706295: step: 1908/529, loss: 5.622550816042349e-06
2023-01-22 20:25:04.793106: step: 1912/529, loss: 0.0020916699431836605
2023-01-22 20:25:05.912595: step: 1916/529, loss: 0.003578364383429289
2023-01-22 20:25:07.034730: step: 1920/529, loss: 0.002008066512644291
2023-01-22 20:25:08.149076: step: 1924/529, loss: 0.0015959724551066756
2023-01-22 20:25:09.261255: step: 1928/529, loss: 0.0024582366459071636
2023-01-22 20:25:10.372464: step: 1932/529, loss: 0.0039808014407753944
2023-01-22 20:25:11.466384: step: 1936/529, loss: 0.0038154874928295612
2023-01-22 20:25:12.573628: step: 1940/529, loss: 0.0017936573131009936
2023-01-22 20:25:13.696229: step: 1944/529, loss: 0.006269370671361685
2023-01-22 20:25:14.802834: step: 1948/529, loss: 6.442765425163088e-06
2023-01-22 20:25:15.921568: step: 1952/529, loss: 0.003060055896639824
2023-01-22 20:25:17.043372: step: 1956/529, loss: 0.00048185596824623644
2023-01-22 20:25:18.159182: step: 1960/529, loss: 0.005622961092740297
2023-01-22 20:25:19.252932: step: 1964/529, loss: 0.001580380485393107
2023-01-22 20:25:20.344055: step: 1968/529, loss: 0.005638332571834326
2023-01-22 20:25:21.436509: step: 1972/529, loss: 0.000876721809618175
2023-01-22 20:25:22.554064: step: 1976/529, loss: 0.019188644364476204
2023-01-22 20:25:23.654425: step: 1980/529, loss: 0.0018977447180077434
2023-01-22 20:25:24.783825: step: 1984/529, loss: 0.001158860744908452
2023-01-22 20:25:25.897763: step: 1988/529, loss: 0.0007904989179223776
2023-01-22 20:25:26.994750: step: 1992/529, loss: 0.0016090063145384192
2023-01-22 20:25:28.107028: step: 1996/529, loss: 0.01789737492799759
2023-01-22 20:25:29.208339: step: 2000/529, loss: 0.0014934086939319968
2023-01-22 20:25:30.329514: step: 2004/529, loss: 0.002243906259536743
2023-01-22 20:25:31.416223: step: 2008/529, loss: 2.849778582003637e-07
2023-01-22 20:25:32.522725: step: 2012/529, loss: 0.0020887048449367285
2023-01-22 20:25:33.661035: step: 2016/529, loss: 0.001315893605351448
2023-01-22 20:25:34.774561: step: 2020/529, loss: 0.003274239832535386
2023-01-22 20:25:35.889363: step: 2024/529, loss: 0.0005489022587426007
2023-01-22 20:25:37.028845: step: 2028/529, loss: 0.00046275195199996233
2023-01-22 20:25:38.150247: step: 2032/529, loss: 0.0018420395208522677
2023-01-22 20:25:39.240503: step: 2036/529, loss: 0.00461282953619957
2023-01-22 20:25:40.355917: step: 2040/529, loss: 0.0030570137314498425
2023-01-22 20:25:41.458746: step: 2044/529, loss: 0.0013270860072225332
2023-01-22 20:25:42.571231: step: 2048/529, loss: 0.0018468780908733606
2023-01-22 20:25:43.692044: step: 2052/529, loss: 0.0014235669514164329
2023-01-22 20:25:44.784596: step: 2056/529, loss: 2.238736669823993e-05
2023-01-22 20:25:45.874276: step: 2060/529, loss: 0.005863823927938938
2023-01-22 20:25:46.978496: step: 2064/529, loss: 0.00011247234942857176
2023-01-22 20:25:48.060715: step: 2068/529, loss: 0.000238575812545605
2023-01-22 20:25:49.168945: step: 2072/529, loss: 0.004164265934377909
2023-01-22 20:25:50.287057: step: 2076/529, loss: 0.011432450264692307
2023-01-22 20:25:51.400929: step: 2080/529, loss: 0.0035359500907361507
2023-01-22 20:25:52.532346: step: 2084/529, loss: 0.004473648499697447
2023-01-22 20:25:53.660902: step: 2088/529, loss: 0.00015654756862204522
2023-01-22 20:25:54.787674: step: 2092/529, loss: 0.01265480276197195
2023-01-22 20:25:55.899068: step: 2096/529, loss: 0.0002174990513594821
2023-01-22 20:25:57.012585: step: 2100/529, loss: 0.004461659584194422
2023-01-22 20:25:58.136827: step: 2104/529, loss: 0.002759193303063512
2023-01-22 20:25:59.266864: step: 2108/529, loss: 0.002610048046335578
2023-01-22 20:26:00.387179: step: 2112/529, loss: 0.00429393770173192
2023-01-22 20:26:01.518959: step: 2116/529, loss: 0.0006658345810137689
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3333522570878062, 'r': 0.3282918812686365, 'f1': 0.3308027178366567}, 'combined': 0.24374937103753652, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.37390707167884013, 'r': 0.2977648170475339, 'f1': 0.33152011468678644}, 'combined': 0.20376358268553701, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33456097387150047, 'r': 0.3453532633512263, 'f1': 0.3398714655202545}, 'combined': 0.25043160617281907, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35877498297237054, 'r': 0.31182955625761494, 'f1': 0.3336590708588666}, 'combined': 0.2050782581864253, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3407278543865622, 'r': 0.34525365131389796, 'f1': 0.3429758232656442}, 'combined': 0.252719027669422, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3670222493703738, 'r': 0.2971132494903026, 'f1': 0.32838832838401866}, 'combined': 0.2028280851783645, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36607142857142855, 'r': 0.44565217391304346, 'f1': 0.4019607843137254}, 'combined': 0.2009803921568627, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 16
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 20:28:26.520133: step: 4/529, loss: 0.0025717103853821754
2023-01-22 20:28:27.612777: step: 8/529, loss: 0.0016217614756897092
2023-01-22 20:28:28.716507: step: 12/529, loss: 0.003504799911752343
2023-01-22 20:28:29.817193: step: 16/529, loss: 0.00043105706572532654
2023-01-22 20:28:30.913270: step: 20/529, loss: 0.002535943640395999
2023-01-22 20:28:32.032532: step: 24/529, loss: 0.0012586342636495829
2023-01-22 20:28:33.123682: step: 28/529, loss: 0.0006895728874951601
2023-01-22 20:28:34.226813: step: 32/529, loss: 0.004079557955265045
2023-01-22 20:28:35.309561: step: 36/529, loss: 0.0005014987546019256
2023-01-22 20:28:36.415418: step: 40/529, loss: 0.0006685298285447061
2023-01-22 20:28:37.519962: step: 44/529, loss: 0.040392834693193436
2023-01-22 20:28:38.603958: step: 48/529, loss: 7.436522992065875e-06
2023-01-22 20:28:39.688196: step: 52/529, loss: 0.00010179962555412203
2023-01-22 20:28:40.790532: step: 56/529, loss: 7.468424882972613e-05
2023-01-22 20:28:41.887274: step: 60/529, loss: 0.01771727204322815
2023-01-22 20:28:42.997148: step: 64/529, loss: 9.653410234022886e-05
2023-01-22 20:28:44.098478: step: 68/529, loss: 0.0009888324420899153
2023-01-22 20:28:45.188822: step: 72/529, loss: 0.0014579963171854615
2023-01-22 20:28:46.286762: step: 76/529, loss: 0.004563336726278067
2023-01-22 20:28:47.376351: step: 80/529, loss: 0.00041388042154721916
2023-01-22 20:28:48.507240: step: 84/529, loss: 0.0013286015018820763
2023-01-22 20:28:49.607285: step: 88/529, loss: 0.0016371209640055895
2023-01-22 20:28:50.696413: step: 92/529, loss: 0.009889336302876472
2023-01-22 20:28:51.801326: step: 96/529, loss: 0.0017702560871839523
2023-01-22 20:28:52.904042: step: 100/529, loss: 0.0018194892909377813
2023-01-22 20:28:53.995437: step: 104/529, loss: 0.0012557179434224963
2023-01-22 20:28:55.093057: step: 108/529, loss: 8.531152707291767e-05
2023-01-22 20:28:56.197973: step: 112/529, loss: 0.016231495887041092
2023-01-22 20:28:57.289171: step: 116/529, loss: 0.00014289762475527823
2023-01-22 20:28:58.399154: step: 120/529, loss: 0.003986806608736515
2023-01-22 20:28:59.504885: step: 124/529, loss: 0.0019169404404237866
2023-01-22 20:29:00.621038: step: 128/529, loss: 0.004707092419266701
2023-01-22 20:29:01.726992: step: 132/529, loss: 0.0001334083644906059
2023-01-22 20:29:02.849529: step: 136/529, loss: 2.7819431124953553e-05
2023-01-22 20:29:03.977583: step: 140/529, loss: 0.0011797597398981452
2023-01-22 20:29:05.082511: step: 144/529, loss: 0.0025056852027773857
2023-01-22 20:29:06.161130: step: 148/529, loss: 0.0002327734255231917
2023-01-22 20:29:07.267608: step: 152/529, loss: 6.277415195654612e-06
2023-01-22 20:29:08.373517: step: 156/529, loss: 0.0027574326377362013
2023-01-22 20:29:09.467636: step: 160/529, loss: 0.0002734310401137918
2023-01-22 20:29:10.582526: step: 164/529, loss: 0.002487284131348133
2023-01-22 20:29:11.701705: step: 168/529, loss: 0.00038747413782402873
2023-01-22 20:29:12.805622: step: 172/529, loss: 0.0020659728907048702
2023-01-22 20:29:13.900331: step: 176/529, loss: 0.005030474159866571
2023-01-22 20:29:15.010675: step: 180/529, loss: 0.0026897662319242954
2023-01-22 20:29:16.113449: step: 184/529, loss: 0.004474503919482231
2023-01-22 20:29:17.210892: step: 188/529, loss: 0.0014012272004038095
2023-01-22 20:29:18.321470: step: 192/529, loss: 4.27848644903861e-05
2023-01-22 20:29:19.421956: step: 196/529, loss: 0.00022527102555613965
2023-01-22 20:29:20.515622: step: 200/529, loss: 0.004181277472525835
2023-01-22 20:29:21.638956: step: 204/529, loss: 0.0021777034271508455
2023-01-22 20:29:22.738484: step: 208/529, loss: 0.0035605314187705517
2023-01-22 20:29:23.851371: step: 212/529, loss: 0.001920978887937963
2023-01-22 20:29:24.931854: step: 216/529, loss: 0.0005725663504563272
2023-01-22 20:29:26.034077: step: 220/529, loss: 0.0014089654432609677
2023-01-22 20:29:27.158006: step: 224/529, loss: 0.0018161915941163898
2023-01-22 20:29:28.252286: step: 228/529, loss: 0.0004696142568718642
2023-01-22 20:29:29.376549: step: 232/529, loss: 0.003012617351487279
2023-01-22 20:29:30.505496: step: 236/529, loss: 0.011388827115297318
2023-01-22 20:29:31.618528: step: 240/529, loss: 0.00019995970069430768
2023-01-22 20:29:32.751504: step: 244/529, loss: 0.0034648762084543705
2023-01-22 20:29:33.842822: step: 248/529, loss: 0.0004728827625513077
2023-01-22 20:29:34.959543: step: 252/529, loss: 0.0006246794364415109
2023-01-22 20:29:36.070359: step: 256/529, loss: 0.0010714423842728138
2023-01-22 20:29:37.182885: step: 260/529, loss: 0.004186289384961128
2023-01-22 20:29:38.283648: step: 264/529, loss: 0.002878075698390603
2023-01-22 20:29:39.411156: step: 268/529, loss: 0.0013346533523872495
2023-01-22 20:29:40.535055: step: 272/529, loss: 0.0009790181647986174
2023-01-22 20:29:41.650531: step: 276/529, loss: 0.0002003751287702471
2023-01-22 20:29:42.761355: step: 280/529, loss: 0.018165085464715958
2023-01-22 20:29:43.863723: step: 284/529, loss: 0.002499673515558243
2023-01-22 20:29:44.989786: step: 288/529, loss: 0.006944416556507349
2023-01-22 20:29:46.125248: step: 292/529, loss: 0.006225381512194872
2023-01-22 20:29:47.225782: step: 296/529, loss: 2.106585270666983e-06
2023-01-22 20:29:48.305527: step: 300/529, loss: 0.0017619356513023376
2023-01-22 20:29:49.408503: step: 304/529, loss: 3.752469638129696e-05
2023-01-22 20:29:50.517875: step: 308/529, loss: 0.002547516953200102
2023-01-22 20:29:51.618496: step: 312/529, loss: 0.008872703649103642
2023-01-22 20:29:52.754637: step: 316/529, loss: 0.0004699170822277665
2023-01-22 20:29:53.872214: step: 320/529, loss: 0.0008881079847924411
2023-01-22 20:29:54.994230: step: 324/529, loss: 0.005238465033471584
2023-01-22 20:29:56.108425: step: 328/529, loss: 0.0028358467388898134
2023-01-22 20:29:57.230944: step: 332/529, loss: 0.0029785530641674995
2023-01-22 20:29:58.332765: step: 336/529, loss: 0.0022968652192503214
2023-01-22 20:29:59.454228: step: 340/529, loss: 0.0015114392153918743
2023-01-22 20:30:00.572425: step: 344/529, loss: 0.004083684179931879
2023-01-22 20:30:01.692278: step: 348/529, loss: 0.00100581138394773
2023-01-22 20:30:02.799695: step: 352/529, loss: 0.004071209579706192
2023-01-22 20:30:03.903899: step: 356/529, loss: 0.000570578733459115
2023-01-22 20:30:05.016163: step: 360/529, loss: 0.00019343972962815315
2023-01-22 20:30:06.126124: step: 364/529, loss: 0.008024826645851135
2023-01-22 20:30:07.216798: step: 368/529, loss: 0.0009940324816852808
2023-01-22 20:30:08.345941: step: 372/529, loss: 0.0017598633421584964
2023-01-22 20:30:09.461885: step: 376/529, loss: 0.008202673867344856
2023-01-22 20:30:10.567452: step: 380/529, loss: 0.0035658571869134903
2023-01-22 20:30:11.695283: step: 384/529, loss: 0.0003102307382505387
2023-01-22 20:30:12.830848: step: 388/529, loss: 0.003027574857696891
2023-01-22 20:30:13.952089: step: 392/529, loss: 3.983555143349804e-05
2023-01-22 20:30:15.061186: step: 396/529, loss: 0.0027810626197606325
2023-01-22 20:30:16.170524: step: 400/529, loss: 0.0006278423243202269
2023-01-22 20:30:17.293722: step: 404/529, loss: 0.0012888809433206916
2023-01-22 20:30:18.398850: step: 408/529, loss: 0.00023472230532206595
2023-01-22 20:30:19.501757: step: 412/529, loss: 0.0004988639848306775
2023-01-22 20:30:20.616666: step: 416/529, loss: 0.003025470767170191
2023-01-22 20:30:21.722134: step: 420/529, loss: 0.0005897580995224416
2023-01-22 20:30:22.836710: step: 424/529, loss: 0.008364231325685978
2023-01-22 20:30:23.947386: step: 428/529, loss: 0.0004518415662460029
2023-01-22 20:30:25.054742: step: 432/529, loss: 0.00026974562206305563
2023-01-22 20:30:26.173166: step: 436/529, loss: 0.0011700447648763657
2023-01-22 20:30:27.286835: step: 440/529, loss: 0.0005974172963760793
2023-01-22 20:30:28.395237: step: 444/529, loss: 0.00010823405318660662
2023-01-22 20:30:29.535163: step: 448/529, loss: 0.0013988834107294679
2023-01-22 20:30:30.671391: step: 452/529, loss: 0.000743257172871381
2023-01-22 20:30:31.782228: step: 456/529, loss: 0.0011069908505305648
2023-01-22 20:30:32.896925: step: 460/529, loss: 0.004662766121327877
2023-01-22 20:30:34.022621: step: 464/529, loss: 0.002533667255192995
2023-01-22 20:30:35.129092: step: 468/529, loss: 0.0009867676999419928
2023-01-22 20:30:36.268917: step: 472/529, loss: 0.0014385950053110719
2023-01-22 20:30:37.389731: step: 476/529, loss: 7.025834929663688e-05
2023-01-22 20:30:38.497127: step: 480/529, loss: 9.569383109919727e-05
2023-01-22 20:30:39.611545: step: 484/529, loss: 3.856765397358686e-05
2023-01-22 20:30:40.724435: step: 488/529, loss: 0.009324731305241585
2023-01-22 20:30:41.821202: step: 492/529, loss: 0.0010695349192246795
2023-01-22 20:30:42.915567: step: 496/529, loss: 0.0005988930934108794
2023-01-22 20:30:44.002723: step: 500/529, loss: 0.00403359392657876
2023-01-22 20:30:45.100201: step: 504/529, loss: 0.002551810350269079
2023-01-22 20:30:46.246638: step: 508/529, loss: 0.002722994890064001
2023-01-22 20:30:47.361682: step: 512/529, loss: 0.011934717185795307
2023-01-22 20:30:48.450373: step: 516/529, loss: 4.795699715032242e-05
2023-01-22 20:30:49.563520: step: 520/529, loss: 0.0013721531722694635
2023-01-22 20:30:50.675107: step: 524/529, loss: 0.0005579236894845963
2023-01-22 20:30:51.776151: step: 528/529, loss: 0.000680211465805769
2023-01-22 20:30:52.876463: step: 532/529, loss: 0.0019231747137382627
2023-01-22 20:30:53.982833: step: 536/529, loss: 0.0002036273363046348
2023-01-22 20:30:55.109244: step: 540/529, loss: 0.005133314523845911
2023-01-22 20:30:56.219014: step: 544/529, loss: 6.001493602525443e-05
2023-01-22 20:30:57.329290: step: 548/529, loss: 0.005198904313147068
2023-01-22 20:30:58.434055: step: 552/529, loss: 0.0007563154795207083
2023-01-22 20:30:59.528559: step: 556/529, loss: 0.022020190954208374
2023-01-22 20:31:00.649935: step: 560/529, loss: 0.00046537353773601353
2023-01-22 20:31:01.755835: step: 564/529, loss: 5.7559747801860794e-05
2023-01-22 20:31:02.886362: step: 568/529, loss: 0.006687423679977655
2023-01-22 20:31:03.989053: step: 572/529, loss: 0.0019201354589313269
2023-01-22 20:31:05.112834: step: 576/529, loss: 0.0036018716637045145
2023-01-22 20:31:06.231453: step: 580/529, loss: 0.0004896539030596614
2023-01-22 20:31:07.343782: step: 584/529, loss: 0.00024399592075496912
2023-01-22 20:31:08.444798: step: 588/529, loss: 0.0013536252081394196
2023-01-22 20:31:09.541260: step: 592/529, loss: 0.0045783184468746185
2023-01-22 20:31:10.659568: step: 596/529, loss: 0.0018999966559931636
2023-01-22 20:31:11.773854: step: 600/529, loss: 0.0021603796631097794
2023-01-22 20:31:12.911107: step: 604/529, loss: 0.0009288553847000003
2023-01-22 20:31:14.030331: step: 608/529, loss: 0.004257046617567539
2023-01-22 20:31:15.163160: step: 612/529, loss: 0.0009372093481943011
2023-01-22 20:31:16.244450: step: 616/529, loss: 0.00114144803956151
2023-01-22 20:31:17.366637: step: 620/529, loss: 0.0003124178620055318
2023-01-22 20:31:18.473368: step: 624/529, loss: 0.0026176832616329193
2023-01-22 20:31:19.612357: step: 628/529, loss: 0.0003139113250654191
2023-01-22 20:31:20.742422: step: 632/529, loss: 0.0021293589379638433
2023-01-22 20:31:21.866661: step: 636/529, loss: 0.0026612153742462397
2023-01-22 20:31:23.002537: step: 640/529, loss: 0.0033271510619670153
2023-01-22 20:31:24.114407: step: 644/529, loss: 0.00028579297941178083
2023-01-22 20:31:25.212190: step: 648/529, loss: 0.002534478669986129
2023-01-22 20:31:26.315420: step: 652/529, loss: 0.0004078938509337604
2023-01-22 20:31:27.425179: step: 656/529, loss: 0.0014979442348703742
2023-01-22 20:31:28.512660: step: 660/529, loss: 0.0006495776469819248
2023-01-22 20:31:29.654826: step: 664/529, loss: 0.004062824882566929
2023-01-22 20:31:30.746095: step: 668/529, loss: 0.00154287985060364
2023-01-22 20:31:31.885379: step: 672/529, loss: 0.00017719483003020287
2023-01-22 20:31:32.998950: step: 676/529, loss: 0.0006408290937542915
2023-01-22 20:31:34.104442: step: 680/529, loss: 0.002912107389420271
2023-01-22 20:31:35.208457: step: 684/529, loss: 0.006114633288234472
2023-01-22 20:31:36.345400: step: 688/529, loss: 0.0022857736330479383
2023-01-22 20:31:37.451930: step: 692/529, loss: 0.00444071926176548
2023-01-22 20:31:38.552940: step: 696/529, loss: 0.006485359743237495
2023-01-22 20:31:39.669641: step: 700/529, loss: 0.00012675090692937374
2023-01-22 20:31:40.767970: step: 704/529, loss: 0.0010553061729297042
2023-01-22 20:31:41.871360: step: 708/529, loss: 0.001653305604122579
2023-01-22 20:31:42.998916: step: 712/529, loss: 0.0031169711146503687
2023-01-22 20:31:44.126571: step: 716/529, loss: 0.00026145848096348345
2023-01-22 20:31:45.240085: step: 720/529, loss: 0.000716778333298862
2023-01-22 20:31:46.340881: step: 724/529, loss: 0.0003580014163162559
2023-01-22 20:31:47.446521: step: 728/529, loss: 0.0002108634653268382
2023-01-22 20:31:48.560371: step: 732/529, loss: 0.0013621096732094884
2023-01-22 20:31:49.678732: step: 736/529, loss: 0.0008688176749274135
2023-01-22 20:31:50.797867: step: 740/529, loss: 0.0005605376791208982
2023-01-22 20:31:51.901840: step: 744/529, loss: 0.00018265502876602113
2023-01-22 20:31:53.023986: step: 748/529, loss: 0.0025329648051410913
2023-01-22 20:31:54.136149: step: 752/529, loss: 0.004075721371918917
2023-01-22 20:31:55.263002: step: 756/529, loss: 0.004107451532036066
2023-01-22 20:31:56.359342: step: 760/529, loss: 0.0068987091071903706
2023-01-22 20:31:57.476202: step: 764/529, loss: 0.0007107718265615404
2023-01-22 20:31:58.583690: step: 768/529, loss: 0.00033213067217729986
2023-01-22 20:31:59.675974: step: 772/529, loss: 0.001406683586537838
2023-01-22 20:32:00.782108: step: 776/529, loss: 0.0009597904863767326
2023-01-22 20:32:01.931793: step: 780/529, loss: 0.0014973916113376617
2023-01-22 20:32:03.047623: step: 784/529, loss: 0.0041592796333134174
2023-01-22 20:32:04.166168: step: 788/529, loss: 0.000729519291780889
2023-01-22 20:32:05.269086: step: 792/529, loss: 0.004153810907155275
2023-01-22 20:32:06.378158: step: 796/529, loss: 0.009740411303937435
2023-01-22 20:32:07.495622: step: 800/529, loss: 0.00046480135642923415
2023-01-22 20:32:08.598593: step: 804/529, loss: 0.00025526570971123874
2023-01-22 20:32:09.699808: step: 808/529, loss: 0.00787463691085577
2023-01-22 20:32:10.807749: step: 812/529, loss: 0.002262952271848917
2023-01-22 20:32:11.923061: step: 816/529, loss: 0.00037824231549166143
2023-01-22 20:32:13.022520: step: 820/529, loss: 9.79991682470427e-07
2023-01-22 20:32:14.134407: step: 824/529, loss: 0.0011657316936179996
2023-01-22 20:32:15.237676: step: 828/529, loss: 3.5719421020985465e-07
2023-01-22 20:32:16.363318: step: 832/529, loss: 0.0005574448150582612
2023-01-22 20:32:17.475589: step: 836/529, loss: 0.0014753448776900768
2023-01-22 20:32:18.570600: step: 840/529, loss: 0.0022536753676831722
2023-01-22 20:32:19.674642: step: 844/529, loss: 0.0001820512698031962
2023-01-22 20:32:20.783514: step: 848/529, loss: 0.00017026931163854897
2023-01-22 20:32:21.910148: step: 852/529, loss: 0.004859400913119316
2023-01-22 20:32:22.998448: step: 856/529, loss: 0.005671901162713766
2023-01-22 20:32:24.107058: step: 860/529, loss: 0.00024869319167919457
2023-01-22 20:32:25.195260: step: 864/529, loss: 0.002023492008447647
2023-01-22 20:32:26.297420: step: 868/529, loss: 0.006473453715443611
2023-01-22 20:32:27.398084: step: 872/529, loss: 0.0005887337028980255
2023-01-22 20:32:28.506274: step: 876/529, loss: 2.011167089221999e-05
2023-01-22 20:32:29.628994: step: 880/529, loss: 0.0011151591315865517
2023-01-22 20:32:30.745990: step: 884/529, loss: 0.0005417157080955803
2023-01-22 20:32:31.872988: step: 888/529, loss: 0.005306778009980917
2023-01-22 20:32:32.999872: step: 892/529, loss: 0.00022178111248649657
2023-01-22 20:32:34.101664: step: 896/529, loss: 2.738489638431929e-05
2023-01-22 20:32:35.201252: step: 900/529, loss: 0.00855159293860197
2023-01-22 20:32:36.309042: step: 904/529, loss: 0.0006855662213638425
2023-01-22 20:32:37.416691: step: 908/529, loss: 0.0021421255078166723
2023-01-22 20:32:38.527263: step: 912/529, loss: 0.00046271344763226807
2023-01-22 20:32:39.636088: step: 916/529, loss: 0.001973553327843547
2023-01-22 20:32:40.750838: step: 920/529, loss: 0.0021304951515048742
2023-01-22 20:32:41.840045: step: 924/529, loss: 1.0877601198444609e-05
2023-01-22 20:32:42.935447: step: 928/529, loss: 0.002393420087173581
2023-01-22 20:32:44.029849: step: 932/529, loss: 0.02360234595835209
2023-01-22 20:32:45.140897: step: 936/529, loss: 0.004511687438935041
2023-01-22 20:32:46.234460: step: 940/529, loss: 0.009144485928118229
2023-01-22 20:32:47.360988: step: 944/529, loss: 0.0012210506247356534
2023-01-22 20:32:48.486131: step: 948/529, loss: 0.011008385568857193
2023-01-22 20:32:49.621833: step: 952/529, loss: 0.009567197412252426
2023-01-22 20:32:50.731842: step: 956/529, loss: 0.015011078678071499
2023-01-22 20:32:51.853411: step: 960/529, loss: 0.00015445654571522027
2023-01-22 20:32:52.985492: step: 964/529, loss: 0.0002223147894255817
2023-01-22 20:32:54.098143: step: 968/529, loss: 0.0004964654217474163
2023-01-22 20:32:55.210585: step: 972/529, loss: 0.0007797619327902794
2023-01-22 20:32:56.308989: step: 976/529, loss: 0.007512143347412348
2023-01-22 20:32:57.411027: step: 980/529, loss: 0.0027293802704662085
2023-01-22 20:32:58.530178: step: 984/529, loss: 0.01302841305732727
2023-01-22 20:32:59.670817: step: 988/529, loss: 0.0036742209922522306
2023-01-22 20:33:00.805610: step: 992/529, loss: 0.0022326421458274126
2023-01-22 20:33:01.930175: step: 996/529, loss: 5.598732514044968e-06
2023-01-22 20:33:03.047040: step: 1000/529, loss: 0.0024760281667113304
2023-01-22 20:33:04.180478: step: 1004/529, loss: 0.002352792536839843
2023-01-22 20:33:05.276748: step: 1008/529, loss: 0.006052291486412287
2023-01-22 20:33:06.396551: step: 1012/529, loss: 0.0010685940505936742
2023-01-22 20:33:07.500000: step: 1016/529, loss: 0.02471635676920414
2023-01-22 20:33:08.594267: step: 1020/529, loss: 0.00010453932191012427
2023-01-22 20:33:09.722004: step: 1024/529, loss: 0.007075488567352295
2023-01-22 20:33:10.838394: step: 1028/529, loss: 3.012677734659519e-05
2023-01-22 20:33:11.941340: step: 1032/529, loss: 7.301749428734183e-05
2023-01-22 20:33:13.051624: step: 1036/529, loss: 0.00026503007393330336
2023-01-22 20:33:14.145501: step: 1040/529, loss: 6.0722768466803245e-06
2023-01-22 20:33:15.270695: step: 1044/529, loss: 0.0003353578213136643
2023-01-22 20:33:16.387246: step: 1048/529, loss: 0.012445072643458843
2023-01-22 20:33:17.484588: step: 1052/529, loss: 0.0013299036072567105
2023-01-22 20:33:18.585124: step: 1056/529, loss: 0.0008099142578430474
2023-01-22 20:33:19.715272: step: 1060/529, loss: 0.0017548257019370794
2023-01-22 20:33:20.837723: step: 1064/529, loss: 0.002090941881760955
2023-01-22 20:33:21.969488: step: 1068/529, loss: 0.002166630467399955
2023-01-22 20:33:23.071665: step: 1072/529, loss: 0.002670489251613617
2023-01-22 20:33:24.164924: step: 1076/529, loss: 0.0024005977902561426
2023-01-22 20:33:25.259926: step: 1080/529, loss: 0.0003803379076998681
2023-01-22 20:33:26.370708: step: 1084/529, loss: 0.00048365857219323516
2023-01-22 20:33:27.488260: step: 1088/529, loss: 0.00013517634943127632
2023-01-22 20:33:28.603098: step: 1092/529, loss: 0.0015151374973356724
2023-01-22 20:33:29.716582: step: 1096/529, loss: 0.017995454370975494
2023-01-22 20:33:30.834606: step: 1100/529, loss: 1.8497863493394107e-05
2023-01-22 20:33:31.938717: step: 1104/529, loss: 0.006020611617714167
2023-01-22 20:33:33.055722: step: 1108/529, loss: 0.005534281954169273
2023-01-22 20:33:34.155435: step: 1112/529, loss: 0.014497381635010242
2023-01-22 20:33:35.251091: step: 1116/529, loss: 0.0007071839063428342
2023-01-22 20:33:36.359897: step: 1120/529, loss: 0.00246590469032526
2023-01-22 20:33:37.458775: step: 1124/529, loss: 0.0008053151541389525
2023-01-22 20:33:38.584532: step: 1128/529, loss: 0.002608046168461442
2023-01-22 20:33:39.679944: step: 1132/529, loss: 0.0
2023-01-22 20:33:40.786393: step: 1136/529, loss: 0.001271700719371438
2023-01-22 20:33:41.899108: step: 1140/529, loss: 9.087454600376077e-06
2023-01-22 20:33:42.990379: step: 1144/529, loss: 0.003951581660658121
2023-01-22 20:33:44.096893: step: 1148/529, loss: 0.013444422744214535
2023-01-22 20:33:45.217800: step: 1152/529, loss: 0.005554639734327793
2023-01-22 20:33:46.311378: step: 1156/529, loss: 0.00020550722547341138
2023-01-22 20:33:47.417545: step: 1160/529, loss: 5.013829650124535e-05
2023-01-22 20:33:48.544902: step: 1164/529, loss: 0.00479420181363821
2023-01-22 20:33:49.659655: step: 1168/529, loss: 0.006586549803614616
2023-01-22 20:33:50.780652: step: 1172/529, loss: 0.003172085853293538
2023-01-22 20:33:51.901293: step: 1176/529, loss: 0.0005119149573147297
2023-01-22 20:33:53.014464: step: 1180/529, loss: 0.0021032614167779684
2023-01-22 20:33:54.133981: step: 1184/529, loss: 0.004429087974131107
2023-01-22 20:33:55.238356: step: 1188/529, loss: 0.0002172814420191571
2023-01-22 20:33:56.345663: step: 1192/529, loss: 3.550000826635369e-07
2023-01-22 20:33:57.475457: step: 1196/529, loss: 0.002764068776741624
2023-01-22 20:33:58.588837: step: 1200/529, loss: 0.014618205837905407
2023-01-22 20:33:59.697961: step: 1204/529, loss: 0.0005840667872689664
2023-01-22 20:34:00.786755: step: 1208/529, loss: 7.298124842236575e-07
2023-01-22 20:34:01.923200: step: 1212/529, loss: 3.1651381959818536e-06
2023-01-22 20:34:03.034327: step: 1216/529, loss: 0.0030513079836964607
2023-01-22 20:34:04.125063: step: 1220/529, loss: 0.00013405506615526974
2023-01-22 20:34:05.249221: step: 1224/529, loss: 0.002724012592807412
2023-01-22 20:34:06.374149: step: 1228/529, loss: 0.04596179351210594
2023-01-22 20:34:07.467895: step: 1232/529, loss: 0.003376100677996874
2023-01-22 20:34:08.559910: step: 1236/529, loss: 7.784303306834772e-05
2023-01-22 20:34:09.663599: step: 1240/529, loss: 0.004986348561942577
2023-01-22 20:34:10.762904: step: 1244/529, loss: 0.008363432250916958
2023-01-22 20:34:11.879672: step: 1248/529, loss: 0.006280216854065657
2023-01-22 20:34:12.981135: step: 1252/529, loss: 0.0028854506090283394
2023-01-22 20:34:14.101417: step: 1256/529, loss: 7.14949201210402e-05
2023-01-22 20:34:15.190815: step: 1260/529, loss: 0.00020437205967027694
2023-01-22 20:34:16.275146: step: 1264/529, loss: 0.006827040109783411
2023-01-22 20:34:17.377889: step: 1268/529, loss: 0.007519053295254707
2023-01-22 20:34:18.484004: step: 1272/529, loss: 0.003101873444393277
2023-01-22 20:34:19.591878: step: 1276/529, loss: 0.0054717520251870155
2023-01-22 20:34:20.697334: step: 1280/529, loss: 0.006468202918767929
2023-01-22 20:34:21.816392: step: 1284/529, loss: 8.075428195297718e-05
2023-01-22 20:34:22.942807: step: 1288/529, loss: 0.017948390915989876
2023-01-22 20:34:24.065618: step: 1292/529, loss: 0.011312011629343033
2023-01-22 20:34:25.167729: step: 1296/529, loss: 0.0011688899248838425
2023-01-22 20:34:26.278565: step: 1300/529, loss: 0.01398471649736166
2023-01-22 20:34:27.368925: step: 1304/529, loss: 0.017319250851869583
2023-01-22 20:34:28.488933: step: 1308/529, loss: 0.0036821505054831505
2023-01-22 20:34:29.635159: step: 1312/529, loss: 3.2012172596296296e-05
2023-01-22 20:34:30.752630: step: 1316/529, loss: 0.00039172705146484077
2023-01-22 20:34:31.884786: step: 1320/529, loss: 0.0003688477154355496
2023-01-22 20:34:32.963326: step: 1324/529, loss: 0.0052772280760109425
2023-01-22 20:34:34.074558: step: 1328/529, loss: 0.005271188449114561
2023-01-22 20:34:35.184439: step: 1332/529, loss: 0.0037537061143666506
2023-01-22 20:34:36.299886: step: 1336/529, loss: 0.0016629727324470878
2023-01-22 20:34:37.415541: step: 1340/529, loss: 0.015550857409834862
2023-01-22 20:34:38.533804: step: 1344/529, loss: 0.0012086856877431273
2023-01-22 20:34:39.650472: step: 1348/529, loss: 0.0014340326888486743
2023-01-22 20:34:40.770374: step: 1352/529, loss: 0.00011742690548999235
2023-01-22 20:34:41.883034: step: 1356/529, loss: 0.0019932363647967577
2023-01-22 20:34:43.006039: step: 1360/529, loss: 0.0026363031938672066
2023-01-22 20:34:44.147253: step: 1364/529, loss: 0.010177216492593288
2023-01-22 20:34:45.238206: step: 1368/529, loss: 0.000787214026786387
2023-01-22 20:34:46.350348: step: 1372/529, loss: 8.542211617168505e-06
2023-01-22 20:34:47.462006: step: 1376/529, loss: 0.0031283865682780743
2023-01-22 20:34:48.583608: step: 1380/529, loss: 0.0038915451150387526
2023-01-22 20:34:49.690136: step: 1384/529, loss: 0.0017911266768351197
2023-01-22 20:34:50.803123: step: 1388/529, loss: 0.010370921343564987
2023-01-22 20:34:51.918318: step: 1392/529, loss: 0.0003778987447731197
2023-01-22 20:34:53.019743: step: 1396/529, loss: 0.0020700907334685326
2023-01-22 20:34:54.133188: step: 1400/529, loss: 0.0030397188384085894
2023-01-22 20:34:55.245561: step: 1404/529, loss: 0.00019207820878364146
2023-01-22 20:34:56.355886: step: 1408/529, loss: 0.0002488569589331746
2023-01-22 20:34:57.459760: step: 1412/529, loss: 9.417583896720316e-06
2023-01-22 20:34:58.579630: step: 1416/529, loss: 0.005500449799001217
2023-01-22 20:34:59.709357: step: 1420/529, loss: 0.0014790159184485674
2023-01-22 20:35:00.799099: step: 1424/529, loss: 0.00037380136200226843
2023-01-22 20:35:01.928070: step: 1428/529, loss: 0.00012191581481602043
2023-01-22 20:35:03.069416: step: 1432/529, loss: 0.013326038606464863
2023-01-22 20:35:04.199024: step: 1436/529, loss: 0.00698620080947876
2023-01-22 20:35:05.317901: step: 1440/529, loss: 0.002983787329867482
2023-01-22 20:35:06.427935: step: 1444/529, loss: 0.012154568918049335
2023-01-22 20:35:07.586540: step: 1448/529, loss: 0.0009631587308831513
2023-01-22 20:35:08.703191: step: 1452/529, loss: 0.005241477862000465
2023-01-22 20:35:09.818380: step: 1456/529, loss: 0.01132657378911972
2023-01-22 20:35:10.914329: step: 1460/529, loss: 0.005407418590039015
2023-01-22 20:35:12.005911: step: 1464/529, loss: 0.0002528067270759493
2023-01-22 20:35:13.098868: step: 1468/529, loss: 0.000685123261064291
2023-01-22 20:35:14.223685: step: 1472/529, loss: 0.0019333910895511508
2023-01-22 20:35:15.324228: step: 1476/529, loss: 0.00017044621927198023
2023-01-22 20:35:16.429027: step: 1480/529, loss: 6.857896369183436e-05
2023-01-22 20:35:17.530958: step: 1484/529, loss: 0.0020964026916772127
2023-01-22 20:35:18.667269: step: 1488/529, loss: 0.003285354934632778
2023-01-22 20:35:19.805392: step: 1492/529, loss: 0.012821413576602936
2023-01-22 20:35:20.931257: step: 1496/529, loss: 0.003961324226111174
2023-01-22 20:35:22.018906: step: 1500/529, loss: 0.01072637364268303
2023-01-22 20:35:23.142007: step: 1504/529, loss: 0.0047032516449689865
2023-01-22 20:35:24.231308: step: 1508/529, loss: 0.0005648515070788562
2023-01-22 20:35:25.343719: step: 1512/529, loss: 0.0013442575000226498
2023-01-22 20:35:26.454883: step: 1516/529, loss: 0.003088304540142417
2023-01-22 20:35:27.594498: step: 1520/529, loss: 0.012935384176671505
2023-01-22 20:35:28.712988: step: 1524/529, loss: 0.008348672650754452
2023-01-22 20:35:29.813473: step: 1528/529, loss: 0.0009352019988000393
2023-01-22 20:35:30.909712: step: 1532/529, loss: 0.008988582529127598
2023-01-22 20:35:32.027417: step: 1536/529, loss: 0.009629667736589909
2023-01-22 20:35:33.137845: step: 1540/529, loss: 7.732255471637473e-05
2023-01-22 20:35:34.241687: step: 1544/529, loss: 3.29173963109497e-05
2023-01-22 20:35:35.353100: step: 1548/529, loss: 5.4681873734807596e-05
2023-01-22 20:35:36.476929: step: 1552/529, loss: 0.004037510138005018
2023-01-22 20:35:37.604596: step: 1556/529, loss: 0.0022664403077214956
2023-01-22 20:35:38.710558: step: 1560/529, loss: 0.0018641222268342972
2023-01-22 20:35:39.828202: step: 1564/529, loss: 0.014384686946868896
2023-01-22 20:35:40.941623: step: 1568/529, loss: 0.0005332435248419642
2023-01-22 20:35:42.068946: step: 1572/529, loss: 0.004419991280883551
2023-01-22 20:35:43.194981: step: 1576/529, loss: 0.002452877815812826
2023-01-22 20:35:44.301454: step: 1580/529, loss: 2.536845329359494e-07
2023-01-22 20:35:45.425333: step: 1584/529, loss: 0.00212467135861516
2023-01-22 20:35:46.576855: step: 1588/529, loss: 0.001354173757135868
2023-01-22 20:35:47.681822: step: 1592/529, loss: 0.004622694570571184
2023-01-22 20:35:48.789139: step: 1596/529, loss: 0.0048582786694169044
2023-01-22 20:35:49.877702: step: 1600/529, loss: 0.0009130860562436283
2023-01-22 20:35:51.010896: step: 1604/529, loss: 0.0002408235741313547
2023-01-22 20:35:52.092961: step: 1608/529, loss: 0.0017662514001131058
2023-01-22 20:35:53.222496: step: 1612/529, loss: 0.016860710456967354
2023-01-22 20:35:54.346404: step: 1616/529, loss: 0.002983630634844303
2023-01-22 20:35:55.483889: step: 1620/529, loss: 2.401376150373835e-05
2023-01-22 20:35:56.561067: step: 1624/529, loss: 8.327971954713576e-06
2023-01-22 20:35:57.659755: step: 1628/529, loss: 0.0019038262544199824
2023-01-22 20:35:58.768638: step: 1632/529, loss: 0.004824307281523943
2023-01-22 20:35:59.885622: step: 1636/529, loss: 0.013162682764232159
2023-01-22 20:36:01.005162: step: 1640/529, loss: 0.00248154578730464
2023-01-22 20:36:02.123937: step: 1644/529, loss: 0.0015662814257666469
2023-01-22 20:36:03.223886: step: 1648/529, loss: 0.00095345638692379
2023-01-22 20:36:04.376640: step: 1652/529, loss: 0.002873386489227414
2023-01-22 20:36:05.485766: step: 1656/529, loss: 0.0009884893661364913
2023-01-22 20:36:06.618831: step: 1660/529, loss: 9.475088882027194e-05
2023-01-22 20:36:07.747763: step: 1664/529, loss: 0.003958193119615316
2023-01-22 20:36:08.845034: step: 1668/529, loss: 8.166748557414394e-06
2023-01-22 20:36:09.955706: step: 1672/529, loss: 0.0006217619520612061
2023-01-22 20:36:11.068708: step: 1676/529, loss: 0.005632845219224691
2023-01-22 20:36:12.188237: step: 1680/529, loss: 0.003930183127522469
2023-01-22 20:36:13.303110: step: 1684/529, loss: 0.00913216732442379
2023-01-22 20:36:14.403181: step: 1688/529, loss: 0.006910240277647972
2023-01-22 20:36:15.513811: step: 1692/529, loss: 0.00016234745271503925
2023-01-22 20:36:16.618960: step: 1696/529, loss: 0.0012153625721111894
2023-01-22 20:36:17.730633: step: 1700/529, loss: 0.0005787490517832339
2023-01-22 20:36:18.822970: step: 1704/529, loss: 0.008278287947177887
2023-01-22 20:36:19.937430: step: 1708/529, loss: 0.004330865107476711
2023-01-22 20:36:21.055315: step: 1712/529, loss: 0.0007008537650108337
2023-01-22 20:36:22.135350: step: 1716/529, loss: 0.003996940329670906
2023-01-22 20:36:23.248636: step: 1720/529, loss: 0.0009753562626428902
2023-01-22 20:36:24.395765: step: 1724/529, loss: 0.002494469750672579
2023-01-22 20:36:25.539462: step: 1728/529, loss: 0.0013603457482531667
2023-01-22 20:36:26.666360: step: 1732/529, loss: 0.000192040839465335
2023-01-22 20:36:27.777199: step: 1736/529, loss: 0.006484419107437134
2023-01-22 20:36:28.883030: step: 1740/529, loss: 0.005956148263067007
2023-01-22 20:36:29.993072: step: 1744/529, loss: 0.003528010565787554
2023-01-22 20:36:31.082284: step: 1748/529, loss: 0.0008659429149702191
2023-01-22 20:36:32.201515: step: 1752/529, loss: 0.01451429445296526
2023-01-22 20:36:33.305305: step: 1756/529, loss: 0.005417460575699806
2023-01-22 20:36:34.415456: step: 1760/529, loss: 0.0035941393580287695
2023-01-22 20:36:35.515647: step: 1764/529, loss: 0.0005939627299085259
2023-01-22 20:36:36.655309: step: 1768/529, loss: 0.012622364796698093
2023-01-22 20:36:37.737645: step: 1772/529, loss: 0.004787984769791365
2023-01-22 20:36:38.829349: step: 1776/529, loss: 0.00033332998282276094
2023-01-22 20:36:39.938193: step: 1780/529, loss: 0.00048649084055796266
2023-01-22 20:36:41.028940: step: 1784/529, loss: 1.278424520023691e-06
2023-01-22 20:36:42.150715: step: 1788/529, loss: 0.03201339766383171
2023-01-22 20:36:43.277852: step: 1792/529, loss: 0.0031452695839107037
2023-01-22 20:36:44.380259: step: 1796/529, loss: 0.020724741742014885
2023-01-22 20:36:45.485661: step: 1800/529, loss: 3.638499401859008e-05
2023-01-22 20:36:46.579051: step: 1804/529, loss: 0.0011949206236749887
2023-01-22 20:36:47.673464: step: 1808/529, loss: 0.001425070920959115
2023-01-22 20:36:48.783191: step: 1812/529, loss: 0.002037449972704053
2023-01-22 20:36:49.919374: step: 1816/529, loss: 6.524845957756042e-05
2023-01-22 20:36:51.024247: step: 1820/529, loss: 0.004529165104031563
2023-01-22 20:36:52.127073: step: 1824/529, loss: 0.0010282231960445642
2023-01-22 20:36:53.238140: step: 1828/529, loss: 0.0004265310999471694
2023-01-22 20:36:54.331492: step: 1832/529, loss: 0.0016007713275030255
2023-01-22 20:36:55.453091: step: 1836/529, loss: 0.00508074602112174
2023-01-22 20:36:56.587113: step: 1840/529, loss: 0.0005789457354694605
2023-01-22 20:36:57.674580: step: 1844/529, loss: 0.0002382405218668282
2023-01-22 20:36:58.814662: step: 1848/529, loss: 0.012829668819904327
2023-01-22 20:36:59.918402: step: 1852/529, loss: 0.0017798638436943293
2023-01-22 20:37:01.016813: step: 1856/529, loss: 0.00040473564877174795
2023-01-22 20:37:02.123309: step: 1860/529, loss: 0.009256916120648384
2023-01-22 20:37:03.212335: step: 1864/529, loss: 0.0017262959154322743
2023-01-22 20:37:04.305772: step: 1868/529, loss: 0.00021897396072745323
2023-01-22 20:37:05.423265: step: 1872/529, loss: 9.250151151718455e-07
2023-01-22 20:37:06.513193: step: 1876/529, loss: 0.0030344012193381786
2023-01-22 20:37:07.603383: step: 1880/529, loss: 0.0024779189843684435
2023-01-22 20:37:08.730937: step: 1884/529, loss: 0.006793782114982605
2023-01-22 20:37:09.862424: step: 1888/529, loss: 0.05012780427932739
2023-01-22 20:37:10.979889: step: 1892/529, loss: 0.00020729619427584112
2023-01-22 20:37:12.062913: step: 1896/529, loss: 0.0001832045236369595
2023-01-22 20:37:13.170873: step: 1900/529, loss: 0.00016050761041697115
2023-01-22 20:37:14.284131: step: 1904/529, loss: 0.000865721027366817
2023-01-22 20:37:15.386745: step: 1908/529, loss: 4.1270704969065264e-05
2023-01-22 20:37:16.489595: step: 1912/529, loss: 0.007097072433680296
2023-01-22 20:37:17.587487: step: 1916/529, loss: 0.0032081049866974354
2023-01-22 20:37:18.670465: step: 1920/529, loss: 2.236555519630201e-05
2023-01-22 20:37:19.789105: step: 1924/529, loss: 0.0019974568858742714
2023-01-22 20:37:20.893757: step: 1928/529, loss: 0.00019547744886949658
2023-01-22 20:37:21.998669: step: 1932/529, loss: 0.003426668467000127
2023-01-22 20:37:23.104755: step: 1936/529, loss: 0.0005806394619867206
2023-01-22 20:37:24.205262: step: 1940/529, loss: 3.138881947961636e-05
2023-01-22 20:37:25.307043: step: 1944/529, loss: 0.003389429533854127
2023-01-22 20:37:26.411029: step: 1948/529, loss: 0.006837824825197458
2023-01-22 20:37:27.537827: step: 1952/529, loss: 0.007986797951161861
2023-01-22 20:37:28.663479: step: 1956/529, loss: 0.003349900711327791
2023-01-22 20:37:29.759225: step: 1960/529, loss: 0.0003063087642658502
2023-01-22 20:37:30.873720: step: 1964/529, loss: 0.005714362487196922
2023-01-22 20:37:31.979331: step: 1968/529, loss: 0.004642103798687458
2023-01-22 20:37:33.095666: step: 1972/529, loss: 0.0008072683122009039
2023-01-22 20:37:34.192689: step: 1976/529, loss: 0.0020159438718110323
2023-01-22 20:37:35.297348: step: 1980/529, loss: 0.01622905395925045
2023-01-22 20:37:36.399407: step: 1984/529, loss: 0.015225408598780632
2023-01-22 20:37:37.511715: step: 1988/529, loss: 3.215541255485732e-06
2023-01-22 20:37:38.618798: step: 1992/529, loss: 1.694218190095853e-05
2023-01-22 20:37:39.726118: step: 1996/529, loss: 0.020186154171824455
2023-01-22 20:37:40.836142: step: 2000/529, loss: 0.0015899355057626963
2023-01-22 20:37:41.929283: step: 2004/529, loss: 0.005919893737882376
2023-01-22 20:37:43.024903: step: 2008/529, loss: 0.003038746304810047
2023-01-22 20:37:44.141089: step: 2012/529, loss: 0.005171437747776508
2023-01-22 20:37:45.255562: step: 2016/529, loss: 0.033187203109264374
2023-01-22 20:37:46.376386: step: 2020/529, loss: 0.004756687209010124
2023-01-22 20:37:47.491852: step: 2024/529, loss: 0.001483099302276969
2023-01-22 20:37:48.600537: step: 2028/529, loss: 0.022782351821660995
2023-01-22 20:37:49.728230: step: 2032/529, loss: 0.0024399918038398027
2023-01-22 20:37:50.847101: step: 2036/529, loss: 0.010848412290215492
2023-01-22 20:37:51.939597: step: 2040/529, loss: 0.0027393903583288193
2023-01-22 20:37:53.065462: step: 2044/529, loss: 0.015717091038823128
2023-01-22 20:37:54.161752: step: 2048/529, loss: 0.0004864544316660613
2023-01-22 20:37:55.266982: step: 2052/529, loss: 0.0007158090593293309
2023-01-22 20:37:56.391586: step: 2056/529, loss: 0.0589098259806633
2023-01-22 20:37:57.499429: step: 2060/529, loss: 0.011942675337195396
2023-01-22 20:37:58.616088: step: 2064/529, loss: 0.005726232659071684
2023-01-22 20:37:59.712170: step: 2068/529, loss: 0.006156877148896456
2023-01-22 20:38:00.818495: step: 2072/529, loss: 0.0008565317839384079
2023-01-22 20:38:01.932153: step: 2076/529, loss: 0.004122385289520025
2023-01-22 20:38:03.034944: step: 2080/529, loss: 0.0035586629528552294
2023-01-22 20:38:04.130577: step: 2084/529, loss: 0.005014989525079727
2023-01-22 20:38:05.230141: step: 2088/529, loss: 0.0069040898233652115
2023-01-22 20:38:06.354365: step: 2092/529, loss: 0.003997378516942263
2023-01-22 20:38:07.457061: step: 2096/529, loss: 0.00020126454182900488
2023-01-22 20:38:08.550024: step: 2100/529, loss: 0.005807209759950638
2023-01-22 20:38:09.675045: step: 2104/529, loss: 0.029458560049533844
2023-01-22 20:38:10.785563: step: 2108/529, loss: 0.012660758569836617
2023-01-22 20:38:11.905317: step: 2112/529, loss: 0.00018169004761148244
2023-01-22 20:38:13.015342: step: 2116/529, loss: 0.0032339480239897966
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33239429392446634, 'r': 0.32924064787205204, 'f1': 0.3308099550592401}, 'combined': 0.24375470372786112, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3720158167636556, 'r': 0.2972905617946789, 'f1': 0.33048180834730906}, 'combined': 0.2031254041549314, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33454758142926594, 'r': 0.3491483297648885, 'f1': 0.3416920515990645}, 'combined': 0.25177309065194226, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35399931680285057, 'r': 0.31074636734946937, 'f1': 0.3309656741313222}, 'combined': 0.2034228045880322, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33835879747192593, 'r': 0.3447792680121902, 'f1': 0.34153886135794026}, 'combined': 0.2516602136321665, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36502756748002085, 'r': 0.2958145481916013, 'f1': 0.3267965596951693}, 'combined': 0.2018449339293693, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3416666666666667, 'r': 0.44565217391304346, 'f1': 0.3867924528301887}, 'combined': 0.19339622641509435, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 16}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 17
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 20:40:39.135732: step: 4/529, loss: 0.004842862486839294
2023-01-22 20:40:40.271073: step: 8/529, loss: 0.0013065881794318557
2023-01-22 20:40:41.355977: step: 12/529, loss: 0.0008216652786359191
2023-01-22 20:40:42.451225: step: 16/529, loss: 0.00631116796284914
2023-01-22 20:40:43.555030: step: 20/529, loss: 0.0005788739654235542
2023-01-22 20:40:44.670759: step: 24/529, loss: 0.00842339638620615
2023-01-22 20:40:45.772842: step: 28/529, loss: 0.002067488618195057
2023-01-22 20:40:46.884704: step: 32/529, loss: 0.0230601504445076
2023-01-22 20:40:47.990674: step: 36/529, loss: 0.00253194198012352
2023-01-22 20:40:49.083449: step: 40/529, loss: 3.39060316036921e-05
2023-01-22 20:40:50.177662: step: 44/529, loss: 0.001684749498963356
2023-01-22 20:40:51.282664: step: 48/529, loss: 0.0008815735927782953
2023-01-22 20:40:52.419848: step: 52/529, loss: 0.0007355580455623567
2023-01-22 20:40:53.503875: step: 56/529, loss: 0.005363018251955509
2023-01-22 20:40:54.603297: step: 60/529, loss: 0.004475701134651899
2023-01-22 20:40:55.705052: step: 64/529, loss: 0.00017663068138062954
2023-01-22 20:40:56.784011: step: 68/529, loss: 0.0006882011657580733
2023-01-22 20:40:57.864181: step: 72/529, loss: 0.017513057217001915
2023-01-22 20:40:58.947486: step: 76/529, loss: 0.0004277905682101846
2023-01-22 20:41:00.054165: step: 80/529, loss: 0.0017915782518684864
2023-01-22 20:41:01.138116: step: 84/529, loss: 1.4102542081673164e-05
2023-01-22 20:41:02.257383: step: 88/529, loss: 0.004560803063213825
2023-01-22 20:41:03.355085: step: 92/529, loss: 0.00026091779000125825
2023-01-22 20:41:04.437518: step: 96/529, loss: 0.0002933715586550534
2023-01-22 20:41:05.548464: step: 100/529, loss: 0.008458208292722702
2023-01-22 20:41:06.622881: step: 104/529, loss: 2.250103534606751e-05
2023-01-22 20:41:07.735412: step: 108/529, loss: 0.010581783019006252
2023-01-22 20:41:08.841220: step: 112/529, loss: 0.0004243151342961937
2023-01-22 20:41:09.936150: step: 116/529, loss: 9.317338481196202e-06
2023-01-22 20:41:11.006608: step: 120/529, loss: 0.0007180918473750353
2023-01-22 20:41:12.119770: step: 124/529, loss: 4.099328361917287e-05
2023-01-22 20:41:13.204862: step: 128/529, loss: 0.006259743589907885
2023-01-22 20:41:14.292717: step: 132/529, loss: 0.008147217333316803
2023-01-22 20:41:15.384598: step: 136/529, loss: 0.005116383545100689
2023-01-22 20:41:16.471403: step: 140/529, loss: 0.001340121147222817
2023-01-22 20:41:17.575001: step: 144/529, loss: 6.617392500629649e-05
2023-01-22 20:41:18.684221: step: 148/529, loss: 0.0013248852919787169
2023-01-22 20:41:19.820029: step: 152/529, loss: 0.005398974753916264
2023-01-22 20:41:20.947733: step: 156/529, loss: 0.004535573534667492
2023-01-22 20:41:22.051607: step: 160/529, loss: 0.0013997707283124328
2023-01-22 20:41:23.178499: step: 164/529, loss: 0.0009759881650097668
2023-01-22 20:41:24.300097: step: 168/529, loss: 0.0012534017441794276
2023-01-22 20:41:25.418224: step: 172/529, loss: 0.00011824766988866031
2023-01-22 20:41:26.534259: step: 176/529, loss: 3.819718403974548e-05
2023-01-22 20:41:27.660812: step: 180/529, loss: 0.004169910680502653
2023-01-22 20:41:28.780183: step: 184/529, loss: 0.003646740224212408
2023-01-22 20:41:29.870803: step: 188/529, loss: 0.0016268719919025898
2023-01-22 20:41:30.969294: step: 192/529, loss: 0.00851054210215807
2023-01-22 20:41:32.088331: step: 196/529, loss: 3.417914194869809e-05
2023-01-22 20:41:33.209697: step: 200/529, loss: 0.000303057546261698
2023-01-22 20:41:34.319320: step: 204/529, loss: 0.00034946054802276194
2023-01-22 20:41:35.423695: step: 208/529, loss: 0.02442433312535286
2023-01-22 20:41:36.518134: step: 212/529, loss: 6.038112019268738e-07
2023-01-22 20:41:37.620686: step: 216/529, loss: 9.669896826380864e-06
2023-01-22 20:41:38.722965: step: 220/529, loss: 0.0004079095961060375
2023-01-22 20:41:39.829011: step: 224/529, loss: 0.004064992535859346
2023-01-22 20:41:40.938621: step: 228/529, loss: 0.0016780701698735356
2023-01-22 20:41:42.078696: step: 232/529, loss: 0.0067963982000947
2023-01-22 20:41:43.182320: step: 236/529, loss: 0.004488798789680004
2023-01-22 20:41:44.285011: step: 240/529, loss: 0.0002451825712341815
2023-01-22 20:41:45.428049: step: 244/529, loss: 0.002494280692189932
2023-01-22 20:41:46.530496: step: 248/529, loss: 0.010256784036755562
2023-01-22 20:41:47.623136: step: 252/529, loss: 0.0052529508247971535
2023-01-22 20:41:48.755342: step: 256/529, loss: 0.0012607721146196127
2023-01-22 20:41:49.850874: step: 260/529, loss: 0.0013416233705356717
2023-01-22 20:41:50.985255: step: 264/529, loss: 6.637816841248423e-05
2023-01-22 20:41:52.084319: step: 268/529, loss: 0.003095069667324424
2023-01-22 20:41:53.175162: step: 272/529, loss: 0.0009119241731241345
2023-01-22 20:41:54.277979: step: 276/529, loss: 0.00046433028182946146
2023-01-22 20:41:55.414066: step: 280/529, loss: 0.0086233364418149
2023-01-22 20:41:56.523888: step: 284/529, loss: 0.002165513811632991
2023-01-22 20:41:57.627661: step: 288/529, loss: 0.0063567450270056725
2023-01-22 20:41:58.741351: step: 292/529, loss: 0.005430347286164761
2023-01-22 20:41:59.846986: step: 296/529, loss: 7.967089914018288e-05
2023-01-22 20:42:00.959364: step: 300/529, loss: 0.0026248586364090443
2023-01-22 20:42:02.094099: step: 304/529, loss: 0.0022789975628256798
2023-01-22 20:42:03.226105: step: 308/529, loss: 0.002096510259434581
2023-01-22 20:42:04.341287: step: 312/529, loss: 0.00257171131670475
2023-01-22 20:42:05.442962: step: 316/529, loss: 0.003633307060226798
2023-01-22 20:42:06.569903: step: 320/529, loss: 0.005026757717132568
2023-01-22 20:42:07.674470: step: 324/529, loss: 0.0029491554014384747
2023-01-22 20:42:08.782018: step: 328/529, loss: 0.0005399062647484243
2023-01-22 20:42:09.890576: step: 332/529, loss: 0.00029754708521068096
2023-01-22 20:42:11.002058: step: 336/529, loss: 0.00021151950932107866
2023-01-22 20:42:12.114833: step: 340/529, loss: 0.002199131064116955
2023-01-22 20:42:13.240612: step: 344/529, loss: 0.005828639958053827
2023-01-22 20:42:14.340709: step: 348/529, loss: 0.0037635453045368195
2023-01-22 20:42:15.455563: step: 352/529, loss: 0.00010130817099707201
2023-01-22 20:42:16.570234: step: 356/529, loss: 0.0024575141724199057
2023-01-22 20:42:17.668569: step: 360/529, loss: 9.871380461845547e-05
2023-01-22 20:42:18.818259: step: 364/529, loss: 0.0003700211236719042
2023-01-22 20:42:19.953013: step: 368/529, loss: 0.002996712224557996
2023-01-22 20:42:21.050983: step: 372/529, loss: 0.0016520009376108646
2023-01-22 20:42:22.156069: step: 376/529, loss: 0.0014316708547994494
2023-01-22 20:42:23.268192: step: 380/529, loss: 0.0003067987854592502
2023-01-22 20:42:24.370420: step: 384/529, loss: 0.0015367676969617605
2023-01-22 20:42:25.484129: step: 388/529, loss: 0.0012711893068626523
2023-01-22 20:42:26.581036: step: 392/529, loss: 3.714159902301617e-06
2023-01-22 20:42:27.677837: step: 396/529, loss: 0.0005633296095766127
2023-01-22 20:42:28.786752: step: 400/529, loss: 0.004472360946238041
2023-01-22 20:42:29.883388: step: 404/529, loss: 0.0008045222493819892
2023-01-22 20:42:30.969291: step: 408/529, loss: 4.425403312779963e-05
2023-01-22 20:42:32.092389: step: 412/529, loss: 0.0006614141166210175
2023-01-22 20:42:33.204161: step: 416/529, loss: 0.0010520628420636058
2023-01-22 20:42:34.320187: step: 420/529, loss: 0.0005907361046411097
2023-01-22 20:42:35.430803: step: 424/529, loss: 0.011500018648803234
2023-01-22 20:42:36.546751: step: 428/529, loss: 0.00042872282210737467
2023-01-22 20:42:37.667604: step: 432/529, loss: 0.0005655869608744979
2023-01-22 20:42:38.761942: step: 436/529, loss: 0.0015152685809880495
2023-01-22 20:42:39.895825: step: 440/529, loss: 0.0053876349702477455
2023-01-22 20:42:41.004365: step: 444/529, loss: 0.0013738598208874464
2023-01-22 20:42:42.135845: step: 448/529, loss: 9.07934590941295e-05
2023-01-22 20:42:43.249786: step: 452/529, loss: 0.0020978262182325125
2023-01-22 20:42:44.374961: step: 456/529, loss: 0.0002569102216511965
2023-01-22 20:42:45.476545: step: 460/529, loss: 0.002703198464587331
2023-01-22 20:42:46.588931: step: 464/529, loss: 0.002207329263910651
2023-01-22 20:42:47.688695: step: 468/529, loss: 0.0037500066682696342
2023-01-22 20:42:48.817889: step: 472/529, loss: 0.0015458130510523915
2023-01-22 20:42:49.926407: step: 476/529, loss: 0.004095096606761217
2023-01-22 20:42:51.061518: step: 480/529, loss: 0.0002553914673626423
2023-01-22 20:42:52.186972: step: 484/529, loss: 0.003892685053870082
2023-01-22 20:42:53.303089: step: 488/529, loss: 0.001569662126712501
2023-01-22 20:42:54.414911: step: 492/529, loss: 0.00350784114561975
2023-01-22 20:42:55.535105: step: 496/529, loss: 0.004785964265465736
2023-01-22 20:42:56.648174: step: 500/529, loss: 3.7438718436533236e-07
2023-01-22 20:42:57.747132: step: 504/529, loss: 0.0015258623752743006
2023-01-22 20:42:58.857960: step: 508/529, loss: 0.007629902567714453
2023-01-22 20:42:59.977339: step: 512/529, loss: 0.0021656774915754795
2023-01-22 20:43:01.090997: step: 516/529, loss: 0.0007478527841158211
2023-01-22 20:43:02.210034: step: 520/529, loss: 0.001216594479046762
2023-01-22 20:43:03.303555: step: 524/529, loss: 0.0009485668269917369
2023-01-22 20:43:04.394483: step: 528/529, loss: 0.0016025895019993186
2023-01-22 20:43:05.512900: step: 532/529, loss: 0.004400855861604214
2023-01-22 20:43:06.616461: step: 536/529, loss: 0.0213177353143692
2023-01-22 20:43:07.712043: step: 540/529, loss: 0.0005097773973830044
2023-01-22 20:43:08.831160: step: 544/529, loss: 0.004329289309680462
2023-01-22 20:43:09.941552: step: 548/529, loss: 0.006629013456404209
2023-01-22 20:43:11.054017: step: 552/529, loss: 0.0022842606995254755
2023-01-22 20:43:12.183558: step: 556/529, loss: 0.00010522679804125801
2023-01-22 20:43:13.305142: step: 560/529, loss: 0.001462854677811265
2023-01-22 20:43:14.412003: step: 564/529, loss: 0.004420223645865917
2023-01-22 20:43:15.510288: step: 568/529, loss: 0.0016169159207493067
2023-01-22 20:43:16.637901: step: 572/529, loss: 0.0032117897644639015
2023-01-22 20:43:17.756522: step: 576/529, loss: 0.012943688780069351
2023-01-22 20:43:18.864836: step: 580/529, loss: 0.0014955911319702864
2023-01-22 20:43:19.970891: step: 584/529, loss: 0.001204931759275496
2023-01-22 20:43:21.092264: step: 588/529, loss: 0.01061182003468275
2023-01-22 20:43:22.219029: step: 592/529, loss: 2.112128640874289e-05
2023-01-22 20:43:23.332427: step: 596/529, loss: 0.004705323372036219
2023-01-22 20:43:24.429199: step: 600/529, loss: 0.003961293958127499
2023-01-22 20:43:25.538589: step: 604/529, loss: 1.799284655135125e-05
2023-01-22 20:43:26.685181: step: 608/529, loss: 5.442715701065026e-05
2023-01-22 20:43:27.814566: step: 612/529, loss: 0.013039590790867805
2023-01-22 20:43:28.926541: step: 616/529, loss: 0.0018619053298607469
2023-01-22 20:43:30.050371: step: 620/529, loss: 0.00030513707315549254
2023-01-22 20:43:31.157653: step: 624/529, loss: 0.018637683242559433
2023-01-22 20:43:32.281566: step: 628/529, loss: 0.00048135354882106185
2023-01-22 20:43:33.396043: step: 632/529, loss: 0.0030350699089467525
2023-01-22 20:43:34.515974: step: 636/529, loss: 0.0024508938658982515
2023-01-22 20:43:35.636856: step: 640/529, loss: 0.0015894307289272547
2023-01-22 20:43:36.743378: step: 644/529, loss: 5.209509617998265e-05
2023-01-22 20:43:37.858071: step: 648/529, loss: 0.004141865763813257
2023-01-22 20:43:38.984952: step: 652/529, loss: 0.008144120685756207
2023-01-22 20:43:40.087885: step: 656/529, loss: 0.0008340466883964837
2023-01-22 20:43:41.214917: step: 660/529, loss: 1.1782837646023836e-05
2023-01-22 20:43:42.342662: step: 664/529, loss: 0.008086221292614937
2023-01-22 20:43:43.462580: step: 668/529, loss: 0.005556774791330099
2023-01-22 20:43:44.590058: step: 672/529, loss: 0.002798590576276183
2023-01-22 20:43:45.701568: step: 676/529, loss: 7.790603558532894e-05
2023-01-22 20:43:46.807890: step: 680/529, loss: 0.00020661650341935456
2023-01-22 20:43:47.902885: step: 684/529, loss: 0.0002519770059734583
2023-01-22 20:43:49.009254: step: 688/529, loss: 0.019149700179696083
2023-01-22 20:43:50.168400: step: 692/529, loss: 0.016743633896112442
2023-01-22 20:43:51.259120: step: 696/529, loss: 8.994508243631572e-05
2023-01-22 20:43:52.364575: step: 700/529, loss: 0.0001768928050296381
2023-01-22 20:43:53.506088: step: 704/529, loss: 0.0016931819263845682
2023-01-22 20:43:54.634802: step: 708/529, loss: 0.0005771567230112851
2023-01-22 20:43:55.735920: step: 712/529, loss: 0.0004616595106199384
2023-01-22 20:43:56.840715: step: 716/529, loss: 0.006313301622867584
2023-01-22 20:43:57.958069: step: 720/529, loss: 0.0011104469886049628
2023-01-22 20:43:59.099508: step: 724/529, loss: 0.0007758499123156071
2023-01-22 20:44:00.221407: step: 728/529, loss: 0.0031370592769235373
2023-01-22 20:44:01.344200: step: 732/529, loss: 0.005197873339056969
2023-01-22 20:44:02.462316: step: 736/529, loss: 0.0002873981720767915
2023-01-22 20:44:03.557676: step: 740/529, loss: 0.01272734347730875
2023-01-22 20:44:04.655099: step: 744/529, loss: 0.0023828912526369095
2023-01-22 20:44:05.770977: step: 748/529, loss: 0.0005365267861634493
2023-01-22 20:44:06.880924: step: 752/529, loss: 9.01796156540513e-05
2023-01-22 20:44:07.996424: step: 756/529, loss: 0.004060475621372461
2023-01-22 20:44:09.092153: step: 760/529, loss: 5.4697760788258165e-05
2023-01-22 20:44:10.198927: step: 764/529, loss: 0.00575790973380208
2023-01-22 20:44:11.321187: step: 768/529, loss: 0.0002694547001738101
2023-01-22 20:44:12.465310: step: 772/529, loss: 0.00958300568163395
2023-01-22 20:44:13.573618: step: 776/529, loss: 0.003376395907253027
2023-01-22 20:44:14.680593: step: 780/529, loss: 0.00019196349603589624
2023-01-22 20:44:15.797176: step: 784/529, loss: 0.0001764356711646542
2023-01-22 20:44:16.884862: step: 788/529, loss: 2.554372940721805e-06
2023-01-22 20:44:17.991672: step: 792/529, loss: 0.00010924295929726213
2023-01-22 20:44:19.106626: step: 796/529, loss: 0.004579189699143171
2023-01-22 20:44:20.191085: step: 800/529, loss: 0.0007217475795187056
2023-01-22 20:44:21.302446: step: 804/529, loss: 0.004084922838956118
2023-01-22 20:44:22.407359: step: 808/529, loss: 0.0045270659029483795
2023-01-22 20:44:23.551597: step: 812/529, loss: 0.002601429121568799
2023-01-22 20:44:24.657571: step: 816/529, loss: 0.0006457374547608197
2023-01-22 20:44:25.795900: step: 820/529, loss: 0.0026850211434066296
2023-01-22 20:44:26.900924: step: 824/529, loss: 0.0027529338840395212
2023-01-22 20:44:28.011346: step: 828/529, loss: 7.03255645930767e-05
2023-01-22 20:44:29.109005: step: 832/529, loss: 0.00843383651226759
2023-01-22 20:44:30.192516: step: 836/529, loss: 0.004879856947809458
2023-01-22 20:44:31.332920: step: 840/529, loss: 0.0002433170157019049
2023-01-22 20:44:32.452614: step: 844/529, loss: 3.3025737593561644e-06
2023-01-22 20:44:33.578392: step: 848/529, loss: 0.003937841858714819
2023-01-22 20:44:34.689042: step: 852/529, loss: 0.001690792734734714
2023-01-22 20:44:35.790431: step: 856/529, loss: 0.002304457128047943
2023-01-22 20:44:36.895438: step: 860/529, loss: 0.0001353982515865937
2023-01-22 20:44:38.014355: step: 864/529, loss: 0.0001049014535965398
2023-01-22 20:44:39.137510: step: 868/529, loss: 0.0010351944947615266
2023-01-22 20:44:40.226313: step: 872/529, loss: 0.000902494415640831
2023-01-22 20:44:41.364940: step: 876/529, loss: 0.001930189784616232
2023-01-22 20:44:42.468819: step: 880/529, loss: 0.004650223534554243
2023-01-22 20:44:43.580917: step: 884/529, loss: 0.0032582019921392202
2023-01-22 20:44:44.687122: step: 888/529, loss: 1.6641257388982922e-05
2023-01-22 20:44:45.771292: step: 892/529, loss: 0.0037625913973897696
2023-01-22 20:44:46.875237: step: 896/529, loss: 0.01676514931023121
2023-01-22 20:44:47.969515: step: 900/529, loss: 0.0005613972898572683
2023-01-22 20:44:49.091812: step: 904/529, loss: 0.0031099531333893538
2023-01-22 20:44:50.206173: step: 908/529, loss: 0.0079199792817235
2023-01-22 20:44:51.320540: step: 912/529, loss: 0.0034890854731202126
2023-01-22 20:44:52.430277: step: 916/529, loss: 0.002971596084535122
2023-01-22 20:44:53.541254: step: 920/529, loss: 0.003686824580654502
2023-01-22 20:44:54.639297: step: 924/529, loss: 0.000566520553547889
2023-01-22 20:44:55.770258: step: 928/529, loss: 0.0025627606082707644
2023-01-22 20:44:56.888711: step: 932/529, loss: 2.4445507733616978e-05
2023-01-22 20:44:57.985551: step: 936/529, loss: 0.0010556881316006184
2023-01-22 20:44:59.090996: step: 940/529, loss: 0.0012016561813652515
2023-01-22 20:45:00.195043: step: 944/529, loss: 0.021858874708414078
2023-01-22 20:45:01.317716: step: 948/529, loss: 7.777874202474777e-07
2023-01-22 20:45:02.474518: step: 952/529, loss: 0.003460739040747285
2023-01-22 20:45:03.607789: step: 956/529, loss: 0.008115353062748909
2023-01-22 20:45:04.725167: step: 960/529, loss: 0.00017997785471379757
2023-01-22 20:45:05.841877: step: 964/529, loss: 0.000490328820887953
2023-01-22 20:45:06.974790: step: 968/529, loss: 0.0020036338828504086
2023-01-22 20:45:08.100995: step: 972/529, loss: 2.4875193048501387e-05
2023-01-22 20:45:09.196786: step: 976/529, loss: 4.555863881705591e-07
2023-01-22 20:45:10.304197: step: 980/529, loss: 0.0001349975063931197
2023-01-22 20:45:11.410102: step: 984/529, loss: 0.0005957207176834345
2023-01-22 20:45:12.507094: step: 988/529, loss: 3.2971909149637213e-06
2023-01-22 20:45:13.618430: step: 992/529, loss: 0.0005863956757821143
2023-01-22 20:45:14.724937: step: 996/529, loss: 0.0010767682688310742
2023-01-22 20:45:15.824242: step: 1000/529, loss: 0.00014322737115435302
2023-01-22 20:45:16.916725: step: 1004/529, loss: 0.0008324292721226811
2023-01-22 20:45:18.034238: step: 1008/529, loss: 0.0010548168793320656
2023-01-22 20:45:19.153554: step: 1012/529, loss: 0.0015078600263223052
2023-01-22 20:45:20.282845: step: 1016/529, loss: 0.004221107345074415
2023-01-22 20:45:21.423212: step: 1020/529, loss: 0.0022938824258744717
2023-01-22 20:45:22.525585: step: 1024/529, loss: 0.001261079334653914
2023-01-22 20:45:23.611229: step: 1028/529, loss: 0.003426574170589447
2023-01-22 20:45:24.706380: step: 1032/529, loss: 9.506597052677535e-06
2023-01-22 20:45:25.826600: step: 1036/529, loss: 2.8146615704827127e-08
2023-01-22 20:45:26.935702: step: 1040/529, loss: 0.0006548360106535256
2023-01-22 20:45:28.067755: step: 1044/529, loss: 0.0025682817213237286
2023-01-22 20:45:29.170982: step: 1048/529, loss: 0.006028341129422188
2023-01-22 20:45:30.302305: step: 1052/529, loss: 0.004621574655175209
2023-01-22 20:45:31.436059: step: 1056/529, loss: 0.004412304610013962
2023-01-22 20:45:32.519663: step: 1060/529, loss: 0.002328735077753663
2023-01-22 20:45:33.634707: step: 1064/529, loss: 0.001587068778462708
2023-01-22 20:45:34.753563: step: 1068/529, loss: 0.002503716852515936
2023-01-22 20:45:35.885109: step: 1072/529, loss: 0.0031970012933015823
2023-01-22 20:45:36.977221: step: 1076/529, loss: 0.005187684204429388
2023-01-22 20:45:38.079504: step: 1080/529, loss: 0.0017413236200809479
2023-01-22 20:45:39.197011: step: 1084/529, loss: 0.0012308568693697453
2023-01-22 20:45:40.295589: step: 1088/529, loss: 0.0026968386955559254
2023-01-22 20:45:41.407723: step: 1092/529, loss: 0.028410574421286583
2023-01-22 20:45:42.511649: step: 1096/529, loss: 0.00022049243852961808
2023-01-22 20:45:43.610504: step: 1100/529, loss: 0.012427431531250477
2023-01-22 20:45:44.723390: step: 1104/529, loss: 0.00017834726895671338
2023-01-22 20:45:45.815482: step: 1108/529, loss: 0.00025669208844192326
2023-01-22 20:45:46.929367: step: 1112/529, loss: 0.004500517621636391
2023-01-22 20:45:48.041921: step: 1116/529, loss: 0.0016848616069182754
2023-01-22 20:45:49.150109: step: 1120/529, loss: 0.004901230800896883
2023-01-22 20:45:50.266257: step: 1124/529, loss: 0.0004051732539664954
2023-01-22 20:45:51.373284: step: 1128/529, loss: 0.0015182949136942625
2023-01-22 20:45:52.492419: step: 1132/529, loss: 0.0011976333335042
2023-01-22 20:45:53.601620: step: 1136/529, loss: 4.3804629967780784e-05
2023-01-22 20:45:54.701460: step: 1140/529, loss: 0.0009048219071701169
2023-01-22 20:45:55.815897: step: 1144/529, loss: 0.001745416666381061
2023-01-22 20:45:56.912771: step: 1148/529, loss: 0.0002892347692977637
2023-01-22 20:45:58.014277: step: 1152/529, loss: 0.001442312728613615
2023-01-22 20:45:59.138983: step: 1156/529, loss: 0.00014769818517379463
2023-01-22 20:46:00.241969: step: 1160/529, loss: 0.00017743515491019934
2023-01-22 20:46:01.377489: step: 1164/529, loss: 0.0009452521335333586
2023-01-22 20:46:02.489107: step: 1168/529, loss: 0.000552690529730171
2023-01-22 20:46:03.577310: step: 1172/529, loss: 0.0003607508260756731
2023-01-22 20:46:04.702151: step: 1176/529, loss: 0.0001325576740782708
2023-01-22 20:46:05.812699: step: 1180/529, loss: 0.0005411426536738873
2023-01-22 20:46:06.903755: step: 1184/529, loss: 1.0884667744903709e-06
2023-01-22 20:46:08.016671: step: 1188/529, loss: 0.0008633073302917182
2023-01-22 20:46:09.135998: step: 1192/529, loss: 0.005612978246062994
2023-01-22 20:46:10.257647: step: 1196/529, loss: 0.00011484552669571713
2023-01-22 20:46:11.379363: step: 1200/529, loss: 0.0016376245766878128
2023-01-22 20:46:12.485107: step: 1204/529, loss: 0.0061323875561356544
2023-01-22 20:46:13.584774: step: 1208/529, loss: 0.0005072249914519489
2023-01-22 20:46:14.678451: step: 1212/529, loss: 0.005355267319828272
2023-01-22 20:46:15.787552: step: 1216/529, loss: 0.0009103429038077593
2023-01-22 20:46:16.896285: step: 1220/529, loss: 0.007965240627527237
2023-01-22 20:46:18.002953: step: 1224/529, loss: 0.0028630553279072046
2023-01-22 20:46:19.116521: step: 1228/529, loss: 0.0010408902307972312
2023-01-22 20:46:20.248860: step: 1232/529, loss: 0.0006647447589784861
2023-01-22 20:46:21.336909: step: 1236/529, loss: 0.003027283353731036
2023-01-22 20:46:22.443633: step: 1240/529, loss: 0.009570627473294735
2023-01-22 20:46:23.553093: step: 1244/529, loss: 0.0022376119159162045
2023-01-22 20:46:24.678538: step: 1248/529, loss: 1.4767417269467842e-05
2023-01-22 20:46:25.789627: step: 1252/529, loss: 0.00483459560200572
2023-01-22 20:46:26.901133: step: 1256/529, loss: 6.593961734324694e-05
2023-01-22 20:46:28.020382: step: 1260/529, loss: 4.537775384960696e-05
2023-01-22 20:46:29.113517: step: 1264/529, loss: 0.0008101099519990385
2023-01-22 20:46:30.229510: step: 1268/529, loss: 7.064333476591855e-05
2023-01-22 20:46:31.347279: step: 1272/529, loss: 0.004025885835289955
2023-01-22 20:46:32.445247: step: 1276/529, loss: 0.0002958209370262921
2023-01-22 20:46:33.555634: step: 1280/529, loss: 0.03730766847729683
2023-01-22 20:46:34.680023: step: 1284/529, loss: 0.00138117338065058
2023-01-22 20:46:35.791280: step: 1288/529, loss: 0.0011050221510231495
2023-01-22 20:46:36.884918: step: 1292/529, loss: 0.0023243525065481663
2023-01-22 20:46:38.001741: step: 1296/529, loss: 0.0044762128964066505
2023-01-22 20:46:39.121646: step: 1300/529, loss: 0.0013400429161265492
2023-01-22 20:46:40.253627: step: 1304/529, loss: 0.00716488528996706
2023-01-22 20:46:41.396299: step: 1308/529, loss: 8.381266525248066e-05
2023-01-22 20:46:42.530953: step: 1312/529, loss: 0.0010223159333691
2023-01-22 20:46:43.638728: step: 1316/529, loss: 3.6384084523888305e-05
2023-01-22 20:46:44.741959: step: 1320/529, loss: 4.647351670428179e-05
2023-01-22 20:46:45.845942: step: 1324/529, loss: 0.0027985365595668554
2023-01-22 20:46:46.945000: step: 1328/529, loss: 0.0005342587828636169
2023-01-22 20:46:48.057817: step: 1332/529, loss: 0.0009523624903522432
2023-01-22 20:46:49.152189: step: 1336/529, loss: 0.004285859875380993
2023-01-22 20:46:50.276504: step: 1340/529, loss: 0.00176473509054631
2023-01-22 20:46:51.405445: step: 1344/529, loss: 0.013424423523247242
2023-01-22 20:46:52.525921: step: 1348/529, loss: 0.00224280240945518
2023-01-22 20:46:53.633271: step: 1352/529, loss: 0.04319550469517708
2023-01-22 20:46:54.761413: step: 1356/529, loss: 0.0005823468090966344
2023-01-22 20:46:55.859132: step: 1360/529, loss: 2.7107134883408435e-05
2023-01-22 20:46:56.941282: step: 1364/529, loss: 0.0008044968126341701
2023-01-22 20:46:58.042547: step: 1368/529, loss: 0.0037706904113292694
2023-01-22 20:46:59.169807: step: 1372/529, loss: 0.0016748812049627304
2023-01-22 20:47:00.292488: step: 1376/529, loss: 0.0030256675090640783
2023-01-22 20:47:01.401226: step: 1380/529, loss: 0.0036881982814520597
2023-01-22 20:47:02.511473: step: 1384/529, loss: 0.005889815744012594
2023-01-22 20:47:03.608690: step: 1388/529, loss: 2.2178968720254488e-05
2023-01-22 20:47:04.705505: step: 1392/529, loss: 0.0002895708894357085
2023-01-22 20:47:05.817407: step: 1396/529, loss: 0.0044743092730641365
2023-01-22 20:47:06.922154: step: 1400/529, loss: 0.0013484794180840254
2023-01-22 20:47:08.044837: step: 1404/529, loss: 0.0009658017661422491
2023-01-22 20:47:09.159157: step: 1408/529, loss: 1.1041333891625982e-05
2023-01-22 20:47:10.273524: step: 1412/529, loss: 0.0024962471798062325
2023-01-22 20:47:11.393555: step: 1416/529, loss: 0.0006889337091706693
2023-01-22 20:47:12.532143: step: 1420/529, loss: 0.006573179271072149
2023-01-22 20:47:13.639754: step: 1424/529, loss: 0.004180037882179022
2023-01-22 20:47:14.734384: step: 1428/529, loss: 0.00026228599017485976
2023-01-22 20:47:15.852667: step: 1432/529, loss: 0.01669810526072979
2023-01-22 20:47:16.987730: step: 1436/529, loss: 0.0023220593575388193
2023-01-22 20:47:18.099672: step: 1440/529, loss: 0.008205053396522999
2023-01-22 20:47:19.189701: step: 1444/529, loss: 0.001476453966461122
2023-01-22 20:47:20.302646: step: 1448/529, loss: 0.0014017869252711535
2023-01-22 20:47:21.425579: step: 1452/529, loss: 0.011860202066600323
2023-01-22 20:47:22.562292: step: 1456/529, loss: 0.008682110346853733
2023-01-22 20:47:23.662957: step: 1460/529, loss: 0.0003301669785287231
2023-01-22 20:47:24.784888: step: 1464/529, loss: 0.006509534083306789
2023-01-22 20:47:25.886555: step: 1468/529, loss: 0.001540094381198287
2023-01-22 20:47:26.999136: step: 1472/529, loss: 0.006667236797511578
2023-01-22 20:47:28.111779: step: 1476/529, loss: 0.0024610089603811502
2023-01-22 20:47:29.205121: step: 1480/529, loss: 0.006118292920291424
2023-01-22 20:47:30.320105: step: 1484/529, loss: 0.001566186547279358
2023-01-22 20:47:31.416749: step: 1488/529, loss: 0.003366619348526001
2023-01-22 20:47:32.537461: step: 1492/529, loss: 0.0007743968744762242
2023-01-22 20:47:33.663943: step: 1496/529, loss: 0.011823554523289204
2023-01-22 20:47:34.761250: step: 1500/529, loss: 0.0015897094272077084
2023-01-22 20:47:35.859359: step: 1504/529, loss: 0.0020350294653326273
2023-01-22 20:47:36.969184: step: 1508/529, loss: 0.0005968995974399149
2023-01-22 20:47:38.063731: step: 1512/529, loss: 0.008535264059901237
2023-01-22 20:47:39.167191: step: 1516/529, loss: 4.37927374150604e-05
2023-01-22 20:47:40.251048: step: 1520/529, loss: 3.8118469092296436e-05
2023-01-22 20:47:41.349306: step: 1524/529, loss: 3.7810514186276123e-07
2023-01-22 20:47:42.472515: step: 1528/529, loss: 0.00646359845995903
2023-01-22 20:47:43.586341: step: 1532/529, loss: 0.007307383231818676
2023-01-22 20:47:44.709253: step: 1536/529, loss: 0.0006296445499174297
2023-01-22 20:47:45.820921: step: 1540/529, loss: 0.0043194969184696674
2023-01-22 20:47:46.940005: step: 1544/529, loss: 0.005620845127850771
2023-01-22 20:47:48.042503: step: 1548/529, loss: 9.999622852774337e-05
2023-01-22 20:47:49.154086: step: 1552/529, loss: 0.0013472764985635877
2023-01-22 20:47:50.249540: step: 1556/529, loss: 0.0020863700192421675
2023-01-22 20:47:51.335369: step: 1560/529, loss: 6.865925388410687e-05
2023-01-22 20:47:52.438234: step: 1564/529, loss: 0.0009123941999860108
2023-01-22 20:47:53.572816: step: 1568/529, loss: 8.940681084368407e-08
2023-01-22 20:47:54.685598: step: 1572/529, loss: 0.00021895303507335484
2023-01-22 20:47:55.800939: step: 1576/529, loss: 0.002487305784597993
2023-01-22 20:47:56.917084: step: 1580/529, loss: 0.0066758678294718266
2023-01-22 20:47:58.034471: step: 1584/529, loss: 0.002572353696450591
2023-01-22 20:47:59.149706: step: 1588/529, loss: 0.0033786918502300978
2023-01-22 20:48:00.242081: step: 1592/529, loss: 0.0010435506701469421
2023-01-22 20:48:01.347248: step: 1596/529, loss: 0.0017752464627847075
2023-01-22 20:48:02.458321: step: 1600/529, loss: 4.545158390101278e-06
2023-01-22 20:48:03.559022: step: 1604/529, loss: 0.000978256925009191
2023-01-22 20:48:04.675947: step: 1608/529, loss: 0.0003334286739118397
2023-01-22 20:48:05.785524: step: 1612/529, loss: 0.006702768616378307
2023-01-22 20:48:06.889533: step: 1616/529, loss: 0.005314180627465248
2023-01-22 20:48:08.013206: step: 1620/529, loss: 0.0015515672275796533
2023-01-22 20:48:09.114985: step: 1624/529, loss: 0.002230458427220583
2023-01-22 20:48:10.227180: step: 1628/529, loss: 0.0021412870846688747
2023-01-22 20:48:11.338067: step: 1632/529, loss: 0.004244758281856775
2023-01-22 20:48:12.412916: step: 1636/529, loss: 0.003596663475036621
2023-01-22 20:48:13.512748: step: 1640/529, loss: 0.00011061842815252021
2023-01-22 20:48:14.609524: step: 1644/529, loss: 3.9888294850243255e-05
2023-01-22 20:48:15.708155: step: 1648/529, loss: 0.0011892083566635847
2023-01-22 20:48:16.834917: step: 1652/529, loss: 0.0068849679082632065
2023-01-22 20:48:17.950841: step: 1656/529, loss: 0.0009346719016321003
2023-01-22 20:48:19.045243: step: 1660/529, loss: 0.003459784435108304
2023-01-22 20:48:20.138372: step: 1664/529, loss: 0.014529464766383171
2023-01-22 20:48:21.235185: step: 1668/529, loss: 0.0025603496469557285
2023-01-22 20:48:22.331681: step: 1672/529, loss: 0.004857127089053392
2023-01-22 20:48:23.445492: step: 1676/529, loss: 0.002069678856059909
2023-01-22 20:48:24.558119: step: 1680/529, loss: 0.004493404179811478
2023-01-22 20:48:25.661522: step: 1684/529, loss: 0.001952928607352078
2023-01-22 20:48:26.761862: step: 1688/529, loss: 0.0003742296830751002
2023-01-22 20:48:27.899182: step: 1692/529, loss: 0.003166137496009469
2023-01-22 20:48:29.024001: step: 1696/529, loss: 0.0013262351276353002
2023-01-22 20:48:30.112458: step: 1700/529, loss: 0.000526068324688822
2023-01-22 20:48:31.222622: step: 1704/529, loss: 0.0011728373356163502
2023-01-22 20:48:32.365427: step: 1708/529, loss: 0.0034445219207555056
2023-01-22 20:48:33.442455: step: 1712/529, loss: 1.594904279045295e-05
2023-01-22 20:48:34.542751: step: 1716/529, loss: 0.005798977334052324
2023-01-22 20:48:35.642192: step: 1720/529, loss: 0.0011578064877539873
2023-01-22 20:48:36.727911: step: 1724/529, loss: 9.41987891565077e-05
2023-01-22 20:48:37.841374: step: 1728/529, loss: 9.05502474779496e-06
2023-01-22 20:48:38.946413: step: 1732/529, loss: 0.0005693563725799322
2023-01-22 20:48:40.030076: step: 1736/529, loss: 0.0018227536929771304
2023-01-22 20:48:41.127905: step: 1740/529, loss: 0.009879037737846375
2023-01-22 20:48:42.238074: step: 1744/529, loss: 0.0022984629031270742
2023-01-22 20:48:43.347807: step: 1748/529, loss: 1.9943654478993267e-05
2023-01-22 20:48:44.438493: step: 1752/529, loss: 0.00018051273946184665
2023-01-22 20:48:45.548829: step: 1756/529, loss: 0.004394138231873512
2023-01-22 20:48:46.674306: step: 1760/529, loss: 0.007042685989290476
2023-01-22 20:48:47.798083: step: 1764/529, loss: 0.003101650159806013
2023-01-22 20:48:48.898471: step: 1768/529, loss: 0.007048295810818672
2023-01-22 20:48:50.030680: step: 1772/529, loss: 0.007986396551132202
2023-01-22 20:48:51.156886: step: 1776/529, loss: 0.0014402285451069474
2023-01-22 20:48:52.270524: step: 1780/529, loss: 0.0004337396239861846
2023-01-22 20:48:53.365435: step: 1784/529, loss: 0.0002032618212979287
2023-01-22 20:48:54.490479: step: 1788/529, loss: 0.0010365210473537445
2023-01-22 20:48:55.593147: step: 1792/529, loss: 0.0006470062653534114
2023-01-22 20:48:56.687467: step: 1796/529, loss: 0.0062573617324233055
2023-01-22 20:48:57.781756: step: 1800/529, loss: 0.004604674875736237
2023-01-22 20:48:58.913153: step: 1804/529, loss: 0.00022221812105271965
2023-01-22 20:49:00.009360: step: 1808/529, loss: 0.0007624908466823399
2023-01-22 20:49:01.129550: step: 1812/529, loss: 0.006311080418527126
2023-01-22 20:49:02.235115: step: 1816/529, loss: 0.00019560764485504478
2023-01-22 20:49:03.343227: step: 1820/529, loss: 2.190223676734604e-05
2023-01-22 20:49:04.455799: step: 1824/529, loss: 0.00048868014710024
2023-01-22 20:49:05.576616: step: 1828/529, loss: 0.01333986222743988
2023-01-22 20:49:06.682427: step: 1832/529, loss: 0.0012826237361878157
2023-01-22 20:49:07.787824: step: 1836/529, loss: 0.00435735983774066
2023-01-22 20:49:08.890929: step: 1840/529, loss: 0.0010146528948098421
2023-01-22 20:49:09.995649: step: 1844/529, loss: 0.007904020138084888
2023-01-22 20:49:11.091524: step: 1848/529, loss: 0.010664430446922779
2023-01-22 20:49:12.224048: step: 1852/529, loss: 0.015014898031949997
2023-01-22 20:49:13.345816: step: 1856/529, loss: 0.00012321044050622731
2023-01-22 20:49:14.449161: step: 1860/529, loss: 0.0026684151962399483
2023-01-22 20:49:15.557812: step: 1864/529, loss: 0.0013764566974714398
2023-01-22 20:49:16.672862: step: 1868/529, loss: 1.3779986147710588e-05
2023-01-22 20:49:17.797733: step: 1872/529, loss: 0.003624596633017063
2023-01-22 20:49:18.900441: step: 1876/529, loss: 0.010003188624978065
2023-01-22 20:49:20.007265: step: 1880/529, loss: 0.0003086858778260648
2023-01-22 20:49:21.118345: step: 1884/529, loss: 0.0012069636723026633
2023-01-22 20:49:22.256603: step: 1888/529, loss: 0.03438347950577736
2023-01-22 20:49:23.364552: step: 1892/529, loss: 0.012207458727061749
2023-01-22 20:49:24.469895: step: 1896/529, loss: 0.005559282843023539
2023-01-22 20:49:25.562291: step: 1900/529, loss: 0.002000851323828101
2023-01-22 20:49:26.687564: step: 1904/529, loss: 0.015440421178936958
2023-01-22 20:49:27.773931: step: 1908/529, loss: 0.002642447827383876
2023-01-22 20:49:28.887516: step: 1912/529, loss: 0.006181693635880947
2023-01-22 20:49:30.010928: step: 1916/529, loss: 0.004210350103676319
2023-01-22 20:49:31.117338: step: 1920/529, loss: 0.0025464389473199844
2023-01-22 20:49:32.223696: step: 1924/529, loss: 0.001145868911407888
2023-01-22 20:49:33.315996: step: 1928/529, loss: 0.00023305659124162048
2023-01-22 20:49:34.408490: step: 1932/529, loss: 5.066372921191942e-08
2023-01-22 20:49:35.504745: step: 1936/529, loss: 0.0004435488663148135
2023-01-22 20:49:36.606305: step: 1940/529, loss: 0.003970756661146879
2023-01-22 20:49:37.726355: step: 1944/529, loss: 0.0027187990490347147
2023-01-22 20:49:38.826396: step: 1948/529, loss: 0.02167487144470215
2023-01-22 20:49:39.939777: step: 1952/529, loss: 0.0005582596641033888
2023-01-22 20:49:41.056241: step: 1956/529, loss: 9.770326141733676e-05
2023-01-22 20:49:42.152201: step: 1960/529, loss: 1.2801962839148473e-05
2023-01-22 20:49:43.258722: step: 1964/529, loss: 0.002035159384831786
2023-01-22 20:49:44.358104: step: 1968/529, loss: 0.0045582628808915615
2023-01-22 20:49:45.464582: step: 1972/529, loss: 0.0003882398596033454
2023-01-22 20:49:46.563490: step: 1976/529, loss: 0.0017868814757093787
2023-01-22 20:49:47.680510: step: 1980/529, loss: 0.010101956315338612
2023-01-22 20:49:48.773837: step: 1984/529, loss: 0.004891541320830584
2023-01-22 20:49:49.875935: step: 1988/529, loss: 7.464100781362504e-05
2023-01-22 20:49:50.989420: step: 1992/529, loss: 0.000726512516848743
2023-01-22 20:49:52.101292: step: 1996/529, loss: 0.0005451508332043886
2023-01-22 20:49:53.232078: step: 2000/529, loss: 0.0024449219927191734
2023-01-22 20:49:54.355968: step: 2004/529, loss: 0.004650231916457415
2023-01-22 20:49:55.470186: step: 2008/529, loss: 0.0001269980421056971
2023-01-22 20:49:56.577789: step: 2012/529, loss: 0.0017350054113194346
2023-01-22 20:49:57.660906: step: 2016/529, loss: 3.4396216506138444e-05
2023-01-22 20:49:58.762092: step: 2020/529, loss: 6.057574410078814e-06
2023-01-22 20:49:59.853623: step: 2024/529, loss: 0.0005801632069051266
2023-01-22 20:50:00.961824: step: 2028/529, loss: 0.0032070535235106945
2023-01-22 20:50:02.083834: step: 2032/529, loss: 0.004249269608408213
2023-01-22 20:50:03.205886: step: 2036/529, loss: 0.00044874960440211
2023-01-22 20:50:04.318268: step: 2040/529, loss: 0.0022949082776904106
2023-01-22 20:50:05.404297: step: 2044/529, loss: 0.007284983526915312
2023-01-22 20:50:06.508367: step: 2048/529, loss: 0.0013661193661391735
2023-01-22 20:50:07.595794: step: 2052/529, loss: 0.00013617941294796765
2023-01-22 20:50:08.674103: step: 2056/529, loss: 0.0016213099006563425
2023-01-22 20:50:09.778302: step: 2060/529, loss: 0.0213764738291502
2023-01-22 20:50:10.888668: step: 2064/529, loss: 0.004255141131579876
2023-01-22 20:50:11.979356: step: 2068/529, loss: 0.003251240588724613
2023-01-22 20:50:13.096875: step: 2072/529, loss: 0.009862186387181282
2023-01-22 20:50:14.205784: step: 2076/529, loss: 0.0055041927844285965
2023-01-22 20:50:15.323236: step: 2080/529, loss: 9.721294190967456e-05
2023-01-22 20:50:16.417265: step: 2084/529, loss: 0.004663102328777313
2023-01-22 20:50:17.529445: step: 2088/529, loss: 0.0009821791900321841
2023-01-22 20:50:18.685746: step: 2092/529, loss: 0.00024189826217480004
2023-01-22 20:50:19.820780: step: 2096/529, loss: 0.011187217198312283
2023-01-22 20:50:20.938121: step: 2100/529, loss: 0.00202218652702868
2023-01-22 20:50:22.053248: step: 2104/529, loss: 0.0006239673239178956
2023-01-22 20:50:23.146760: step: 2108/529, loss: 0.0010713990777730942
2023-01-22 20:50:24.276101: step: 2112/529, loss: 0.0006448101485148072
2023-01-22 20:50:25.375756: step: 2116/529, loss: 0.015399581752717495
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3308171510048886, 'r': 0.3301894144754676, 'f1': 0.3305029846696513}, 'combined': 0.24352851501974304, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3738316493442758, 'r': 0.3015920845229816, 'f1': 0.333848695961171}, 'combined': 0.2051948082493051, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3273077211321813, 'r': 0.3434557301443952, 'f1': 0.3351873514557338}, 'combined': 0.2469801537042249, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35590679913512563, 'r': 0.31334602072901874, 'f1': 0.3332730948583296}, 'combined': 0.20484102415682698, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3414463512677799, 'r': 0.3492212207463631, 'f1': 0.34529002501563477}, 'combined': 0.2544242289588888, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3666130697168593, 'r': 0.3012258036028567, 'f1': 0.3307184440696763}, 'combined': 0.20426727427832952, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3203125, 'r': 0.44565217391304346, 'f1': 0.3727272727272727}, 'combined': 0.18636363636363634, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 18
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 20:52:53.812684: step: 4/529, loss: 0.005106932483613491
2023-01-22 20:52:54.900720: step: 8/529, loss: 0.003267749911174178
2023-01-22 20:52:56.025480: step: 12/529, loss: 0.0031423766631633043
2023-01-22 20:52:57.122021: step: 16/529, loss: 0.0069333529099822044
2023-01-22 20:52:58.222938: step: 20/529, loss: 0.005248202942311764
2023-01-22 20:52:59.291430: step: 24/529, loss: 3.232617018511519e-05
2023-01-22 20:53:00.379889: step: 28/529, loss: 0.039188578724861145
2023-01-22 20:53:01.481138: step: 32/529, loss: 0.008622698485851288
2023-01-22 20:53:02.622215: step: 36/529, loss: 0.0001221944548888132
2023-01-22 20:53:03.717253: step: 40/529, loss: 0.0001730604999465868
2023-01-22 20:53:04.820555: step: 44/529, loss: 0.00037821251316927373
2023-01-22 20:53:05.907493: step: 48/529, loss: 0.0001407468516845256
2023-01-22 20:53:06.989941: step: 52/529, loss: 0.003944792784750462
2023-01-22 20:53:08.097247: step: 56/529, loss: 0.0006200163043104112
2023-01-22 20:53:09.173838: step: 60/529, loss: 0.0011825788533315063
2023-01-22 20:53:10.244848: step: 64/529, loss: 0.00036721606738865376
2023-01-22 20:53:11.338661: step: 68/529, loss: 9.044127364177257e-05
2023-01-22 20:53:12.439935: step: 72/529, loss: 0.0022320484276860952
2023-01-22 20:53:13.519819: step: 76/529, loss: 0.00011526072194101289
2023-01-22 20:53:14.637115: step: 80/529, loss: 0.006719253957271576
2023-01-22 20:53:15.740295: step: 84/529, loss: 0.004242526367306709
2023-01-22 20:53:16.841511: step: 88/529, loss: 4.265863390173763e-05
2023-01-22 20:53:17.945866: step: 92/529, loss: 8.658689330331981e-05
2023-01-22 20:53:19.059459: step: 96/529, loss: 1.9944891391787678e-05
2023-01-22 20:53:20.174730: step: 100/529, loss: 0.0044161598198115826
2023-01-22 20:53:21.275759: step: 104/529, loss: 0.0012425644090399146
2023-01-22 20:53:22.396141: step: 108/529, loss: 2.4390041289734654e-05
2023-01-22 20:53:23.512325: step: 112/529, loss: 0.0029318369925022125
2023-01-22 20:53:24.602784: step: 116/529, loss: 1.213944506162079e-05
2023-01-22 20:53:25.736493: step: 120/529, loss: 0.0011261332547292113
2023-01-22 20:53:26.848226: step: 124/529, loss: 0.0033326521515846252
2023-01-22 20:53:27.938087: step: 128/529, loss: 0.00011628385254880413
2023-01-22 20:53:29.067553: step: 132/529, loss: 0.009727424941956997
2023-01-22 20:53:30.171839: step: 136/529, loss: 0.00048684608191251755
2023-01-22 20:53:31.263808: step: 140/529, loss: 9.700184818939306e-06
2023-01-22 20:53:32.376743: step: 144/529, loss: 0.00033302439260296524
2023-01-22 20:53:33.470730: step: 148/529, loss: 0.0008136171963997185
2023-01-22 20:53:34.594006: step: 152/529, loss: 0.002355230040848255
2023-01-22 20:53:35.702122: step: 156/529, loss: 0.0035317454021424055
2023-01-22 20:53:36.810898: step: 160/529, loss: 0.004527253098785877
2023-01-22 20:53:37.918237: step: 164/529, loss: 0.00010868141544051468
2023-01-22 20:53:39.036306: step: 168/529, loss: 0.001424109097570181
2023-01-22 20:53:40.165535: step: 172/529, loss: 8.110309863695875e-05
2023-01-22 20:53:41.280383: step: 176/529, loss: 0.004578886087983847
2023-01-22 20:53:42.385715: step: 180/529, loss: 0.002410543616861105
2023-01-22 20:53:43.493376: step: 184/529, loss: 0.0005429271259345114
2023-01-22 20:53:44.607242: step: 188/529, loss: 0.0018217784818261862
2023-01-22 20:53:45.720751: step: 192/529, loss: 0.009847326204180717
2023-01-22 20:53:46.813535: step: 196/529, loss: 0.00021384851424954832
2023-01-22 20:53:47.919310: step: 200/529, loss: 0.0008671731338836253
2023-01-22 20:53:49.014123: step: 204/529, loss: 0.0010139402002096176
2023-01-22 20:53:50.112626: step: 208/529, loss: 0.002458571456372738
2023-01-22 20:53:51.244837: step: 212/529, loss: 0.0037513214629143476
2023-01-22 20:53:52.361471: step: 216/529, loss: 0.0011582538718357682
2023-01-22 20:53:53.469293: step: 220/529, loss: 0.0023672557435929775
2023-01-22 20:53:54.564928: step: 224/529, loss: 6.956825382076204e-05
2023-01-22 20:53:55.684718: step: 228/529, loss: 0.003049969905987382
2023-01-22 20:53:56.788778: step: 232/529, loss: 1.3972776287118904e-06
2023-01-22 20:53:57.909334: step: 236/529, loss: 0.00615348294377327
2023-01-22 20:53:59.012732: step: 240/529, loss: 0.001702405046671629
2023-01-22 20:54:00.128669: step: 244/529, loss: 0.0005352931912057102
2023-01-22 20:54:01.238920: step: 248/529, loss: 5.640329618472606e-05
2023-01-22 20:54:02.388388: step: 252/529, loss: 0.0008387555135414004
2023-01-22 20:54:03.498130: step: 256/529, loss: 0.007005666848272085
2023-01-22 20:54:04.597109: step: 260/529, loss: 0.00030807958682999015
2023-01-22 20:54:05.703146: step: 264/529, loss: 0.0024762593675404787
2023-01-22 20:54:06.820616: step: 268/529, loss: 0.00018462726438883692
2023-01-22 20:54:07.922254: step: 272/529, loss: 0.006993254646658897
2023-01-22 20:54:09.038711: step: 276/529, loss: 0.014611868187785149
2023-01-22 20:54:10.134587: step: 280/529, loss: 0.004979503341019154
2023-01-22 20:54:11.232725: step: 284/529, loss: 0.0018948083743453026
2023-01-22 20:54:12.332368: step: 288/529, loss: 0.0008982406579889357
2023-01-22 20:54:13.431846: step: 292/529, loss: 0.006685532629489899
2023-01-22 20:54:14.550427: step: 296/529, loss: 0.00034208057331852615
2023-01-22 20:54:15.653834: step: 300/529, loss: 0.0028365645557641983
2023-01-22 20:54:16.774092: step: 304/529, loss: 0.0027116844430565834
2023-01-22 20:54:17.906956: step: 308/529, loss: 0.00469971913844347
2023-01-22 20:54:19.014316: step: 312/529, loss: 0.0026702755130827427
2023-01-22 20:54:20.139730: step: 316/529, loss: 3.436918996158056e-05
2023-01-22 20:54:21.245326: step: 320/529, loss: 0.0004892255528829992
2023-01-22 20:54:22.383604: step: 324/529, loss: 0.0006125149666331708
2023-01-22 20:54:23.486768: step: 328/529, loss: 0.004796868190169334
2023-01-22 20:54:24.606099: step: 332/529, loss: 0.0001806049549486488
2023-01-22 20:54:25.742259: step: 336/529, loss: 0.01030789501965046
2023-01-22 20:54:26.844076: step: 340/529, loss: 0.001344239222817123
2023-01-22 20:54:27.974382: step: 344/529, loss: 0.008899343200027943
2023-01-22 20:54:29.096564: step: 348/529, loss: 0.007085543591529131
2023-01-22 20:54:30.216365: step: 352/529, loss: 0.0006947821821086109
2023-01-22 20:54:31.320035: step: 356/529, loss: 0.0036569712683558464
2023-01-22 20:54:32.438756: step: 360/529, loss: 4.1255018004449084e-05
2023-01-22 20:54:33.554000: step: 364/529, loss: 0.004831678234040737
2023-01-22 20:54:34.679919: step: 368/529, loss: 7.885137165430933e-06
2023-01-22 20:54:35.804157: step: 372/529, loss: 0.011029841378331184
2023-01-22 20:54:36.900904: step: 376/529, loss: 0.001048399950377643
2023-01-22 20:54:38.009552: step: 380/529, loss: 0.0010899422923102975
2023-01-22 20:54:39.123736: step: 384/529, loss: 0.0016569980653002858
2023-01-22 20:54:40.246667: step: 388/529, loss: 0.003423633985221386
2023-01-22 20:54:41.357067: step: 392/529, loss: 0.0063781579956412315
2023-01-22 20:54:42.452641: step: 396/529, loss: 2.6601039735396625e-06
2023-01-22 20:54:43.563201: step: 400/529, loss: 0.00027619063621386886
2023-01-22 20:54:44.683684: step: 404/529, loss: 0.0022866709623485804
2023-01-22 20:54:45.789771: step: 408/529, loss: 0.0001205329317599535
2023-01-22 20:54:46.872366: step: 412/529, loss: 0.0007061202195473015
2023-01-22 20:54:47.992987: step: 416/529, loss: 0.0023702888283878565
2023-01-22 20:54:49.083024: step: 420/529, loss: 0.0038488905411213636
2023-01-22 20:54:50.195387: step: 424/529, loss: 0.002321971347555518
2023-01-22 20:54:51.300890: step: 428/529, loss: 0.0011883003171533346
2023-01-22 20:54:52.406555: step: 432/529, loss: 0.00013296572433318943
2023-01-22 20:54:53.518744: step: 436/529, loss: 0.008017114363610744
2023-01-22 20:54:54.602928: step: 440/529, loss: 0.0010055091697722673
2023-01-22 20:54:55.707531: step: 444/529, loss: 0.0005035348585806787
2023-01-22 20:54:56.852925: step: 448/529, loss: 0.029983503744006157
2023-01-22 20:54:57.960109: step: 452/529, loss: 0.000848477182444185
2023-01-22 20:54:59.076396: step: 456/529, loss: 0.0005775055033154786
2023-01-22 20:55:00.200701: step: 460/529, loss: 7.234374606923666e-06
2023-01-22 20:55:01.337785: step: 464/529, loss: 0.004597551189363003
2023-01-22 20:55:02.449787: step: 468/529, loss: 0.00011185939365532249
2023-01-22 20:55:03.572015: step: 472/529, loss: 0.014785099774599075
2023-01-22 20:55:04.682373: step: 476/529, loss: 0.0021692917216569185
2023-01-22 20:55:05.823093: step: 480/529, loss: 1.0873933433686034e-06
2023-01-22 20:55:06.941124: step: 484/529, loss: 0.0007050866261124611
2023-01-22 20:55:08.059674: step: 488/529, loss: 4.188654202152975e-05
2023-01-22 20:55:09.163397: step: 492/529, loss: 0.0036822918336838484
2023-01-22 20:55:10.249580: step: 496/529, loss: 0.004835766740143299
2023-01-22 20:55:11.344067: step: 500/529, loss: 0.001007765531539917
2023-01-22 20:55:12.451395: step: 504/529, loss: 0.0021588648669421673
2023-01-22 20:55:13.562907: step: 508/529, loss: 0.0013948113191872835
2023-01-22 20:55:14.657530: step: 512/529, loss: 0.00453182402998209
2023-01-22 20:55:15.761042: step: 516/529, loss: 6.869457138236612e-05
2023-01-22 20:55:16.865385: step: 520/529, loss: 0.008398565463721752
2023-01-22 20:55:17.978202: step: 524/529, loss: 0.004977534059435129
2023-01-22 20:55:19.069713: step: 528/529, loss: 3.146576773360721e-06
2023-01-22 20:55:20.174629: step: 532/529, loss: 0.00215600011870265
2023-01-22 20:55:21.271722: step: 536/529, loss: 0.00429950887337327
2023-01-22 20:55:22.392883: step: 540/529, loss: 0.0013584947446361184
2023-01-22 20:55:23.527571: step: 544/529, loss: 0.007589603308588266
2023-01-22 20:55:24.654499: step: 548/529, loss: 0.0031090250704437494
2023-01-22 20:55:25.750716: step: 552/529, loss: 0.0013651290209963918
2023-01-22 20:55:26.875899: step: 556/529, loss: 0.002238328568637371
2023-01-22 20:55:27.987230: step: 560/529, loss: 0.001540915691293776
2023-01-22 20:55:29.091270: step: 564/529, loss: 0.0011681547621265054
2023-01-22 20:55:30.203797: step: 568/529, loss: 0.0008219557348638773
2023-01-22 20:55:31.327821: step: 572/529, loss: 0.00010092512093251571
2023-01-22 20:55:32.434253: step: 576/529, loss: 0.0007694021915085614
2023-01-22 20:55:33.560519: step: 580/529, loss: 0.004103308077901602
2023-01-22 20:55:34.684548: step: 584/529, loss: 0.001777102705091238
2023-01-22 20:55:35.800319: step: 588/529, loss: 0.0024286648258566856
2023-01-22 20:55:36.900471: step: 592/529, loss: 0.0028878971934318542
2023-01-22 20:55:38.004814: step: 596/529, loss: 0.001692973542958498
2023-01-22 20:55:39.119433: step: 600/529, loss: 0.001142262713983655
2023-01-22 20:55:40.227746: step: 604/529, loss: 0.001316947746090591
2023-01-22 20:55:41.333310: step: 608/529, loss: 0.013509968295693398
2023-01-22 20:55:42.447255: step: 612/529, loss: 5.352353400667198e-05
2023-01-22 20:55:43.568606: step: 616/529, loss: 0.0003583582874853164
2023-01-22 20:55:44.665304: step: 620/529, loss: 0.0010619476670399308
2023-01-22 20:55:45.747351: step: 624/529, loss: 4.98524332215311e-06
2023-01-22 20:55:46.879781: step: 628/529, loss: 0.003712043631821871
2023-01-22 20:55:47.983669: step: 632/529, loss: 1.645502015890088e-05
2023-01-22 20:55:49.065290: step: 636/529, loss: 0.0005195161211304367
2023-01-22 20:55:50.167406: step: 640/529, loss: 9.147680248133838e-05
2023-01-22 20:55:51.260011: step: 644/529, loss: 0.0006765939178876579
2023-01-22 20:55:52.383072: step: 648/529, loss: 0.010582037270069122
2023-01-22 20:55:53.533360: step: 652/529, loss: 0.009574136696755886
2023-01-22 20:55:54.654212: step: 656/529, loss: 0.0003639789065346122
2023-01-22 20:55:55.754691: step: 660/529, loss: 0.018032602965831757
2023-01-22 20:55:56.867619: step: 664/529, loss: 0.004070539493113756
2023-01-22 20:55:57.958447: step: 668/529, loss: 4.918778358842246e-05
2023-01-22 20:55:59.064816: step: 672/529, loss: 0.005503579042851925
2023-01-22 20:56:00.202299: step: 676/529, loss: 0.005368916783481836
2023-01-22 20:56:01.329481: step: 680/529, loss: 0.0029425546526908875
2023-01-22 20:56:02.454029: step: 684/529, loss: 0.0016450523398816586
2023-01-22 20:56:03.557622: step: 688/529, loss: 0.001709225121885538
2023-01-22 20:56:04.663561: step: 692/529, loss: 0.0037631175946444273
2023-01-22 20:56:05.796712: step: 696/529, loss: 0.002494571730494499
2023-01-22 20:56:06.917815: step: 700/529, loss: 0.0022283089347183704
2023-01-22 20:56:08.038455: step: 704/529, loss: 0.0002642963663674891
2023-01-22 20:56:09.146118: step: 708/529, loss: 0.007430787663906813
2023-01-22 20:56:10.262816: step: 712/529, loss: 0.0003395665262360126
2023-01-22 20:56:11.381666: step: 716/529, loss: 0.008697547018527985
2023-01-22 20:56:12.485515: step: 720/529, loss: 1.3025874977756757e-05
2023-01-22 20:56:13.612773: step: 724/529, loss: 0.018177006393671036
2023-01-22 20:56:14.709639: step: 728/529, loss: 0.0010303236776962876
2023-01-22 20:56:15.813265: step: 732/529, loss: 0.006078480742871761
2023-01-22 20:56:16.914750: step: 736/529, loss: 0.0
2023-01-22 20:56:18.043897: step: 740/529, loss: 0.0017693494446575642
2023-01-22 20:56:19.137118: step: 744/529, loss: 2.5048311727005057e-05
2023-01-22 20:56:20.270512: step: 748/529, loss: 0.00029898740467615426
2023-01-22 20:56:21.389140: step: 752/529, loss: 0.00018677431216929108
2023-01-22 20:56:22.505504: step: 756/529, loss: 0.0004084084939677268
2023-01-22 20:56:23.628860: step: 760/529, loss: 0.0027451668865978718
2023-01-22 20:56:24.740227: step: 764/529, loss: 0.0017125324811786413
2023-01-22 20:56:25.853618: step: 768/529, loss: 0.0001601610129000619
2023-01-22 20:56:26.964777: step: 772/529, loss: 0.0008451167959719896
2023-01-22 20:56:28.059853: step: 776/529, loss: 0.004501692485064268
2023-01-22 20:56:29.168665: step: 780/529, loss: 0.003973223268985748
2023-01-22 20:56:30.252034: step: 784/529, loss: 0.000528763746842742
2023-01-22 20:56:31.341890: step: 788/529, loss: 0.008562888950109482
2023-01-22 20:56:32.469723: step: 792/529, loss: 0.0010988907888531685
2023-01-22 20:56:33.586913: step: 796/529, loss: 0.00361588760279119
2023-01-22 20:56:34.687262: step: 800/529, loss: 0.0018999911844730377
2023-01-22 20:56:35.789013: step: 804/529, loss: 0.0041298349387943745
2023-01-22 20:56:36.888963: step: 808/529, loss: 1.4402733540919144e-05
2023-01-22 20:56:38.005425: step: 812/529, loss: 0.0009572546696290374
2023-01-22 20:56:39.114205: step: 816/529, loss: 0.010263328440487385
2023-01-22 20:56:40.218390: step: 820/529, loss: 0.0022119341883808374
2023-01-22 20:56:41.346210: step: 824/529, loss: 0.00024054963432718068
2023-01-22 20:56:42.463102: step: 828/529, loss: 0.0017124079167842865
2023-01-22 20:56:43.575023: step: 832/529, loss: 0.003546376945450902
2023-01-22 20:56:44.664792: step: 836/529, loss: 0.0018881323048844934
2023-01-22 20:56:45.769752: step: 840/529, loss: 0.0010882930364459753
2023-01-22 20:56:46.859213: step: 844/529, loss: 0.0008502752752974629
2023-01-22 20:56:47.963251: step: 848/529, loss: 0.00039398297667503357
2023-01-22 20:56:49.099962: step: 852/529, loss: 0.003617528360337019
2023-01-22 20:56:50.187998: step: 856/529, loss: 7.243848085636273e-05
2023-01-22 20:56:51.334910: step: 860/529, loss: 0.0009569402900524437
2023-01-22 20:56:52.464402: step: 864/529, loss: 0.0003646343247964978
2023-01-22 20:56:53.548154: step: 868/529, loss: 0.0003610481508076191
2023-01-22 20:56:54.664945: step: 872/529, loss: 0.0004116895725019276
2023-01-22 20:56:55.768605: step: 876/529, loss: 0.005916376132518053
2023-01-22 20:56:56.872790: step: 880/529, loss: 0.0031686441507190466
2023-01-22 20:56:57.991723: step: 884/529, loss: 0.0004516146727837622
2023-01-22 20:56:59.091877: step: 888/529, loss: 0.007660240400582552
2023-01-22 20:57:00.190997: step: 892/529, loss: 0.01721937209367752
2023-01-22 20:57:01.309021: step: 896/529, loss: 0.005537746008485556
2023-01-22 20:57:02.448364: step: 900/529, loss: 0.006335179787129164
2023-01-22 20:57:03.540644: step: 904/529, loss: 7.450579597723106e-10
2023-01-22 20:57:04.654671: step: 908/529, loss: 0.01355667132884264
2023-01-22 20:57:05.770394: step: 912/529, loss: 0.000181439274456352
2023-01-22 20:57:06.873541: step: 916/529, loss: 0.004046508576720953
2023-01-22 20:57:08.011838: step: 920/529, loss: 0.003777015721425414
2023-01-22 20:57:09.107868: step: 924/529, loss: 0.002511204918846488
2023-01-22 20:57:10.206424: step: 928/529, loss: 0.0005360101931728423
2023-01-22 20:57:11.316409: step: 932/529, loss: 0.0024796377401798964
2023-01-22 20:57:12.428674: step: 936/529, loss: 0.012718910351395607
2023-01-22 20:57:13.548872: step: 940/529, loss: 0.0012683564564213157
2023-01-22 20:57:14.650871: step: 944/529, loss: 0.0006419944693334401
2023-01-22 20:57:15.741052: step: 948/529, loss: 0.0005474080098792911
2023-01-22 20:57:16.856091: step: 952/529, loss: 0.00010657100938260555
2023-01-22 20:57:18.017931: step: 956/529, loss: 0.0025238357484340668
2023-01-22 20:57:19.132854: step: 960/529, loss: 0.0017542983405292034
2023-01-22 20:57:20.240390: step: 964/529, loss: 0.000137905910378322
2023-01-22 20:57:21.351041: step: 968/529, loss: 3.4363692975603044e-05
2023-01-22 20:57:22.441086: step: 972/529, loss: 0.00024384722928516567
2023-01-22 20:57:23.561064: step: 976/529, loss: 0.0032568054739385843
2023-01-22 20:57:24.655943: step: 980/529, loss: 0.0012569173704832792
2023-01-22 20:57:25.763630: step: 984/529, loss: 0.00011453461047494784
2023-01-22 20:57:26.868353: step: 988/529, loss: 0.0051637813448905945
2023-01-22 20:57:27.962498: step: 992/529, loss: 0.001042092451825738
2023-01-22 20:57:29.093902: step: 996/529, loss: 0.005345347803086042
2023-01-22 20:57:30.197137: step: 1000/529, loss: 0.0013013023417443037
2023-01-22 20:57:31.303806: step: 1004/529, loss: 0.00014702248154208064
2023-01-22 20:57:32.450351: step: 1008/529, loss: 7.827518129488453e-05
2023-01-22 20:57:33.576457: step: 1012/529, loss: 0.007932577282190323
2023-01-22 20:57:34.677114: step: 1016/529, loss: 0.01244633924216032
2023-01-22 20:57:35.787368: step: 1020/529, loss: 0.0005064822034910321
2023-01-22 20:57:36.894073: step: 1024/529, loss: 0.00787703599780798
2023-01-22 20:57:38.043122: step: 1028/529, loss: 0.0034599213395267725
2023-01-22 20:57:39.147675: step: 1032/529, loss: 0.00022355469991452992
2023-01-22 20:57:40.244853: step: 1036/529, loss: 0.01336802076548338
2023-01-22 20:57:41.371303: step: 1040/529, loss: 0.007297166623175144
2023-01-22 20:57:42.464355: step: 1044/529, loss: 0.0017687611980363727
2023-01-22 20:57:43.584292: step: 1048/529, loss: 0.0019895865116268396
2023-01-22 20:57:44.707525: step: 1052/529, loss: 0.0004506449040491134
2023-01-22 20:57:45.829336: step: 1056/529, loss: 0.006986568216234446
2023-01-22 20:57:46.949309: step: 1060/529, loss: 0.00833398662507534
2023-01-22 20:57:48.036547: step: 1064/529, loss: 0.003777771722525358
2023-01-22 20:57:49.132579: step: 1068/529, loss: 0.003777691861614585
2023-01-22 20:57:50.239824: step: 1072/529, loss: 5.398679604695644e-06
2023-01-22 20:57:51.350517: step: 1076/529, loss: 0.00018647620163392276
2023-01-22 20:57:52.450716: step: 1080/529, loss: 2.152389377840791e-09
2023-01-22 20:57:53.557696: step: 1084/529, loss: 0.001387969241477549
2023-01-22 20:57:54.664037: step: 1088/529, loss: 0.0002159702853532508
2023-01-22 20:57:55.775965: step: 1092/529, loss: 0.0013747360790148377
2023-01-22 20:57:56.877890: step: 1096/529, loss: 0.003941033501178026
2023-01-22 20:57:57.990636: step: 1100/529, loss: 0.0008925424772314727
2023-01-22 20:57:59.090980: step: 1104/529, loss: 0.02873014099895954
2023-01-22 20:58:00.188901: step: 1108/529, loss: 0.006290366407483816
2023-01-22 20:58:01.296883: step: 1112/529, loss: 0.002604166278615594
2023-01-22 20:58:02.401437: step: 1116/529, loss: 0.0058943526819348335
2023-01-22 20:58:03.531287: step: 1120/529, loss: 0.0010798239381983876
2023-01-22 20:58:04.639271: step: 1124/529, loss: 8.350842108484358e-05
2023-01-22 20:58:05.795383: step: 1128/529, loss: 0.0006921535823494196
2023-01-22 20:58:06.912622: step: 1132/529, loss: 2.462251541146543e-05
2023-01-22 20:58:08.067850: step: 1136/529, loss: 0.02378924749791622
2023-01-22 20:58:09.184455: step: 1140/529, loss: 0.00030874309595674276
2023-01-22 20:58:10.296770: step: 1144/529, loss: 0.0075066969729959965
2023-01-22 20:58:11.409029: step: 1148/529, loss: 0.007054154761135578
2023-01-22 20:58:12.522283: step: 1152/529, loss: 0.0021517996210604906
2023-01-22 20:58:13.647044: step: 1156/529, loss: 0.0
2023-01-22 20:58:14.769633: step: 1160/529, loss: 0.010792912915349007
2023-01-22 20:58:15.866792: step: 1164/529, loss: 0.002899391343817115
2023-01-22 20:58:16.972850: step: 1168/529, loss: 0.0005356438341550529
2023-01-22 20:58:18.089118: step: 1172/529, loss: 0.0021522645838558674
2023-01-22 20:58:19.211483: step: 1176/529, loss: 0.00047265118337236345
2023-01-22 20:58:20.324782: step: 1180/529, loss: 6.62273735851926e-10
2023-01-22 20:58:21.446112: step: 1184/529, loss: 0.00042347016278654337
2023-01-22 20:58:22.543672: step: 1188/529, loss: 2.6224442990496755e-06
2023-01-22 20:58:23.646136: step: 1192/529, loss: 0.00701815215870738
2023-01-22 20:58:24.735484: step: 1196/529, loss: 0.00039482529973611236
2023-01-22 20:58:25.854455: step: 1200/529, loss: 2.4107577701215632e-05
2023-01-22 20:58:26.970529: step: 1204/529, loss: 0.00021021347492933273
2023-01-22 20:58:28.076409: step: 1208/529, loss: 0.0024844338186085224
2023-01-22 20:58:29.180106: step: 1212/529, loss: 0.0014012468745931983
2023-01-22 20:58:30.279186: step: 1216/529, loss: 3.5549594031181186e-05
2023-01-22 20:58:31.384963: step: 1220/529, loss: 0.0014988539041951299
2023-01-22 20:58:32.492467: step: 1224/529, loss: 0.001629492617212236
2023-01-22 20:58:33.574592: step: 1228/529, loss: 1.7556576494826004e-05
2023-01-22 20:58:34.670748: step: 1232/529, loss: 0.00043667052523232996
2023-01-22 20:58:35.773435: step: 1236/529, loss: 0.0016298576956614852
2023-01-22 20:58:36.903035: step: 1240/529, loss: 0.0023908300790935755
2023-01-22 20:58:38.021376: step: 1244/529, loss: 0.005823827814310789
2023-01-22 20:58:39.115427: step: 1248/529, loss: 0.0006173073779791594
2023-01-22 20:58:40.222092: step: 1252/529, loss: 0.0047931005246937275
2023-01-22 20:58:41.325274: step: 1256/529, loss: 0.00042521071736700833
2023-01-22 20:58:42.437198: step: 1260/529, loss: 0.0023424094542860985
2023-01-22 20:58:43.543435: step: 1264/529, loss: 0.000747110927477479
2023-01-22 20:58:44.661886: step: 1268/529, loss: 0.0023369446862488985
2023-01-22 20:58:45.789143: step: 1272/529, loss: 0.0026558798272162676
2023-01-22 20:58:46.875344: step: 1276/529, loss: 0.00027887432952411473
2023-01-22 20:58:47.974846: step: 1280/529, loss: 0.005888211075216532
2023-01-22 20:58:49.067315: step: 1284/529, loss: 0.0002677658631000668
2023-01-22 20:58:50.172871: step: 1288/529, loss: 3.101287438767031e-05
2023-01-22 20:58:51.296444: step: 1292/529, loss: 0.012007524259388447
2023-01-22 20:58:52.445136: step: 1296/529, loss: 6.227909761946648e-05
2023-01-22 20:58:53.583872: step: 1300/529, loss: 0.0014958962565287948
2023-01-22 20:58:54.692443: step: 1304/529, loss: 0.0022140732035040855
2023-01-22 20:58:55.810363: step: 1308/529, loss: 0.0008412807364948094
2023-01-22 20:58:56.920635: step: 1312/529, loss: 0.00641833059489727
2023-01-22 20:58:58.048301: step: 1316/529, loss: 0.005048653576523066
2023-01-22 20:58:59.149665: step: 1320/529, loss: 0.0004380790051072836
2023-01-22 20:59:00.247464: step: 1324/529, loss: 0.006967420689761639
2023-01-22 20:59:01.351774: step: 1328/529, loss: 7.749811629764736e-06
2023-01-22 20:59:02.431832: step: 1332/529, loss: 0.0014396198093891144
2023-01-22 20:59:03.544835: step: 1336/529, loss: 1.9668295863084495e-06
2023-01-22 20:59:04.660592: step: 1340/529, loss: 0.00012819372932426631
2023-01-22 20:59:05.789888: step: 1344/529, loss: 0.011958047747612
2023-01-22 20:59:06.893611: step: 1348/529, loss: 9.598223550710827e-05
2023-01-22 20:59:08.004073: step: 1352/529, loss: 9.899453289108351e-05
2023-01-22 20:59:09.106260: step: 1356/529, loss: 0.0005260020843707025
2023-01-22 20:59:10.223189: step: 1360/529, loss: 0.00037924887146800756
2023-01-22 20:59:11.323354: step: 1364/529, loss: 0.0055696601048111916
2023-01-22 20:59:12.426468: step: 1368/529, loss: 0.004669132176786661
2023-01-22 20:59:13.557986: step: 1372/529, loss: 0.02317608892917633
2023-01-22 20:59:14.672711: step: 1376/529, loss: 0.000990790082141757
2023-01-22 20:59:15.774140: step: 1380/529, loss: 0.0005190148367546499
2023-01-22 20:59:16.909268: step: 1384/529, loss: 0.00034910690737888217
2023-01-22 20:59:18.025357: step: 1388/529, loss: 0.00723663717508316
2023-01-22 20:59:19.127975: step: 1392/529, loss: 0.0031363654416054487
2023-01-22 20:59:20.252606: step: 1396/529, loss: 0.0014973653014749289
2023-01-22 20:59:21.355960: step: 1400/529, loss: 0.004554419312626123
2023-01-22 20:59:22.447168: step: 1404/529, loss: 0.001191581366583705
2023-01-22 20:59:23.551220: step: 1408/529, loss: 0.0031554142478853464
2023-01-22 20:59:24.673096: step: 1412/529, loss: 0.0024024993181228638
2023-01-22 20:59:25.778992: step: 1416/529, loss: 4.039910709252581e-05
2023-01-22 20:59:26.876233: step: 1420/529, loss: 3.621993073466001e-06
2023-01-22 20:59:28.006891: step: 1424/529, loss: 0.0008595092222094536
2023-01-22 20:59:29.156030: step: 1428/529, loss: 0.0011222291504964232
2023-01-22 20:59:30.269698: step: 1432/529, loss: 0.00663272337988019
2023-01-22 20:59:31.371811: step: 1436/529, loss: 0.00023140531266108155
2023-01-22 20:59:32.483153: step: 1440/529, loss: 0.005525258369743824
2023-01-22 20:59:33.586105: step: 1444/529, loss: 0.00027046544710174203
2023-01-22 20:59:34.691512: step: 1448/529, loss: 0.006597304716706276
2023-01-22 20:59:35.783819: step: 1452/529, loss: 0.0035685747861862183
2023-01-22 20:59:36.876127: step: 1456/529, loss: 0.007696566637605429
2023-01-22 20:59:37.979208: step: 1460/529, loss: 0.002407173393294215
2023-01-22 20:59:39.074830: step: 1464/529, loss: 0.0002496056549716741
2023-01-22 20:59:40.214386: step: 1468/529, loss: 0.008003685623407364
2023-01-22 20:59:41.327125: step: 1472/529, loss: 0.013193624094128609
2023-01-22 20:59:42.441429: step: 1476/529, loss: 0.012404588051140308
2023-01-22 20:59:43.541918: step: 1480/529, loss: 6.139960078144213e-06
2023-01-22 20:59:44.676730: step: 1484/529, loss: 0.0014080528635531664
2023-01-22 20:59:45.785215: step: 1488/529, loss: 0.01132181566208601
2023-01-22 20:59:46.885354: step: 1492/529, loss: 0.0034367458429187536
2023-01-22 20:59:47.974848: step: 1496/529, loss: 0.001738079241476953
2023-01-22 20:59:49.080454: step: 1500/529, loss: 1.3410723340712138e-06
2023-01-22 20:59:50.180671: step: 1504/529, loss: 0.0011472956975921988
2023-01-22 20:59:51.301723: step: 1508/529, loss: 0.0015708596911281347
2023-01-22 20:59:52.406501: step: 1512/529, loss: 0.029905790463089943
2023-01-22 20:59:53.505545: step: 1516/529, loss: 7.69003527238965e-05
2023-01-22 20:59:54.620020: step: 1520/529, loss: 0.0021961203310638666
2023-01-22 20:59:55.725564: step: 1524/529, loss: 0.002474252600222826
2023-01-22 20:59:56.826815: step: 1528/529, loss: 0.0004506809636950493
2023-01-22 20:59:57.936498: step: 1532/529, loss: 0.023818355053663254
2023-01-22 20:59:59.078871: step: 1536/529, loss: 0.005450800992548466
2023-01-22 21:00:00.182431: step: 1540/529, loss: 7.33259366825223e-05
2023-01-22 21:00:01.279163: step: 1544/529, loss: 0.004254105035215616
2023-01-22 21:00:02.389366: step: 1548/529, loss: 0.0004345346533227712
2023-01-22 21:00:03.500264: step: 1552/529, loss: 0.0038340215105563402
2023-01-22 21:00:04.595778: step: 1556/529, loss: 0.0022109763231128454
2023-01-22 21:00:05.710519: step: 1560/529, loss: 0.0007847670349292457
2023-01-22 21:00:06.825676: step: 1564/529, loss: 0.001727790106087923
2023-01-22 21:00:07.948124: step: 1568/529, loss: 0.0025347520131617785
2023-01-22 21:00:09.077912: step: 1572/529, loss: 0.0019236218649894
2023-01-22 21:00:10.184099: step: 1576/529, loss: 0.004714879672974348
2023-01-22 21:00:11.306269: step: 1580/529, loss: 0.014267808757722378
2023-01-22 21:00:12.405051: step: 1584/529, loss: 0.0004281363799236715
2023-01-22 21:00:13.491487: step: 1588/529, loss: 0.0004321748565416783
2023-01-22 21:00:14.608325: step: 1592/529, loss: 0.008390305563807487
2023-01-22 21:00:15.707126: step: 1596/529, loss: 0.00016875458823051304
2023-01-22 21:00:16.808626: step: 1600/529, loss: 0.0016817706637084484
2023-01-22 21:00:17.927830: step: 1604/529, loss: 0.0001106054987758398
2023-01-22 21:00:19.045859: step: 1608/529, loss: 0.006818888708949089
2023-01-22 21:00:20.151103: step: 1612/529, loss: 0.0015413295477628708
2023-01-22 21:00:21.246636: step: 1616/529, loss: 0.0073048085905611515
2023-01-22 21:00:22.384298: step: 1620/529, loss: 0.009429523721337318
2023-01-22 21:00:23.498424: step: 1624/529, loss: 0.00010864871001103893
2023-01-22 21:00:24.615968: step: 1628/529, loss: 0.007236195728182793
2023-01-22 21:00:25.737392: step: 1632/529, loss: 0.0015033911913633347
2023-01-22 21:00:26.845536: step: 1636/529, loss: 0.0007201815024018288
2023-01-22 21:00:27.965577: step: 1640/529, loss: 0.0026269180234521627
2023-01-22 21:00:29.072569: step: 1644/529, loss: 8.526886813342571e-05
2023-01-22 21:00:30.166911: step: 1648/529, loss: 0.003903640666976571
2023-01-22 21:00:31.283846: step: 1652/529, loss: 0.006479987408965826
2023-01-22 21:00:32.373609: step: 1656/529, loss: 0.0025715434458106756
2023-01-22 21:00:33.480160: step: 1660/529, loss: 0.006629056762903929
2023-01-22 21:00:34.586943: step: 1664/529, loss: 0.003756292164325714
2023-01-22 21:00:35.685569: step: 1668/529, loss: 0.001194830983877182
2023-01-22 21:00:36.795801: step: 1672/529, loss: 0.001242537167854607
2023-01-22 21:00:37.896781: step: 1676/529, loss: 1.0659944564395119e-05
2023-01-22 21:00:39.027372: step: 1680/529, loss: 0.000265802867943421
2023-01-22 21:00:40.132581: step: 1684/529, loss: 0.0035039852373301983
2023-01-22 21:00:41.257474: step: 1688/529, loss: 0.0009754839702509344
2023-01-22 21:00:42.368099: step: 1692/529, loss: 0.0010972573654726148
2023-01-22 21:00:43.480602: step: 1696/529, loss: 0.011874500662088394
2023-01-22 21:00:44.585487: step: 1700/529, loss: 0.00017801755166146904
2023-01-22 21:00:45.708085: step: 1704/529, loss: 0.0002987853076774627
2023-01-22 21:00:46.819058: step: 1708/529, loss: 0.00041551829781383276
2023-01-22 21:00:47.911508: step: 1712/529, loss: 0.004074069205671549
2023-01-22 21:00:49.017456: step: 1716/529, loss: 5.343437078408897e-05
2023-01-22 21:00:50.123669: step: 1720/529, loss: 0.0005563742597587407
2023-01-22 21:00:51.228673: step: 1724/529, loss: 0.00021904589084442705
2023-01-22 21:00:52.334264: step: 1728/529, loss: 0.040065109729766846
2023-01-22 21:00:53.460227: step: 1732/529, loss: 0.002059804741293192
2023-01-22 21:00:54.558010: step: 1736/529, loss: 0.00015123550838325173
2023-01-22 21:00:55.673336: step: 1740/529, loss: 0.0014656054554507136
2023-01-22 21:00:56.757643: step: 1744/529, loss: 9.985613723983988e-05
2023-01-22 21:00:57.878633: step: 1748/529, loss: 0.0033528830390423536
2023-01-22 21:00:58.983259: step: 1752/529, loss: 0.0006387518951669335
2023-01-22 21:01:00.097429: step: 1756/529, loss: 0.0006074150442145765
2023-01-22 21:01:01.232525: step: 1760/529, loss: 0.00014634014223702252
2023-01-22 21:01:02.377759: step: 1764/529, loss: 0.009260040707886219
2023-01-22 21:01:03.509146: step: 1768/529, loss: 0.008568689227104187
2023-01-22 21:01:04.646592: step: 1772/529, loss: 0.00338767864741385
2023-01-22 21:01:05.760222: step: 1776/529, loss: 0.011118866503238678
2023-01-22 21:01:06.851204: step: 1780/529, loss: 0.00253043370321393
2023-01-22 21:01:07.951284: step: 1784/529, loss: 5.990063800709322e-05
2023-01-22 21:01:09.044557: step: 1788/529, loss: 0.0011806016555055976
2023-01-22 21:01:10.151262: step: 1792/529, loss: 0.0006642257212661207
2023-01-22 21:01:11.296026: step: 1796/529, loss: 0.0026716822758316994
2023-01-22 21:01:12.397928: step: 1800/529, loss: 0.001467812224291265
2023-01-22 21:01:13.502340: step: 1804/529, loss: 0.0006074644043110311
2023-01-22 21:01:14.603209: step: 1808/529, loss: 0.00014966275193728507
2023-01-22 21:01:15.717206: step: 1812/529, loss: 0.0002217055152868852
2023-01-22 21:01:16.844327: step: 1816/529, loss: 0.0028299265541136265
2023-01-22 21:01:17.930632: step: 1820/529, loss: 0.00036575336707755923
2023-01-22 21:01:19.040278: step: 1824/529, loss: 0.005601867102086544
2023-01-22 21:01:20.158083: step: 1828/529, loss: 0.0033093367237597704
2023-01-22 21:01:21.267545: step: 1832/529, loss: 0.0013408302329480648
2023-01-22 21:01:22.382782: step: 1836/529, loss: 0.0020322424825280905
2023-01-22 21:01:23.479121: step: 1840/529, loss: 8.737322059459984e-05
2023-01-22 21:01:24.579075: step: 1844/529, loss: 0.0016424552304670215
2023-01-22 21:01:25.693981: step: 1848/529, loss: 0.001924059703014791
2023-01-22 21:01:26.799731: step: 1852/529, loss: 0.01038040779531002
2023-01-22 21:01:27.913066: step: 1856/529, loss: 0.0006261649541556835
2023-01-22 21:01:29.018460: step: 1860/529, loss: 0.005430380813777447
2023-01-22 21:01:30.115348: step: 1864/529, loss: 0.0007014241418801248
2023-01-22 21:01:31.202546: step: 1868/529, loss: 0.003927120007574558
2023-01-22 21:01:32.294674: step: 1872/529, loss: 0.0032344588544219732
2023-01-22 21:01:33.393074: step: 1876/529, loss: 0.005915793590247631
2023-01-22 21:01:34.516245: step: 1880/529, loss: 0.0015853213844820857
2023-01-22 21:01:35.619201: step: 1884/529, loss: 0.0008371626609005034
2023-01-22 21:01:36.709266: step: 1888/529, loss: 3.7464698834810406e-05
2023-01-22 21:01:37.802467: step: 1892/529, loss: 0.00044671224895864725
2023-01-22 21:01:38.895860: step: 1896/529, loss: 0.0032978130038827658
2023-01-22 21:01:40.005264: step: 1900/529, loss: 0.013345971703529358
2023-01-22 21:01:41.139135: step: 1904/529, loss: 0.0030009010806679726
2023-01-22 21:01:42.247651: step: 1908/529, loss: 0.0051575833931565285
2023-01-22 21:01:43.351868: step: 1912/529, loss: 0.000202733906917274
2023-01-22 21:01:44.458584: step: 1916/529, loss: 0.00024003082944545895
2023-01-22 21:01:45.581594: step: 1920/529, loss: 0.0038450672291219234
2023-01-22 21:01:46.671214: step: 1924/529, loss: 0.0006042091408744454
2023-01-22 21:01:47.807208: step: 1928/529, loss: 0.0026508679147809744
2023-01-22 21:01:48.911202: step: 1932/529, loss: 0.0020235839765518904
2023-01-22 21:01:50.019652: step: 1936/529, loss: 0.0012606607051566243
2023-01-22 21:01:51.132804: step: 1940/529, loss: 7.13535919203423e-05
2023-01-22 21:01:52.244219: step: 1944/529, loss: 0.0018203085055574775
2023-01-22 21:01:53.372443: step: 1948/529, loss: 0.00024992728140205145
2023-01-22 21:01:54.491003: step: 1952/529, loss: 0.009224295616149902
2023-01-22 21:01:55.586439: step: 1956/529, loss: 0.009138788096606731
2023-01-22 21:01:56.694783: step: 1960/529, loss: 7.363649638136849e-05
2023-01-22 21:01:57.819685: step: 1964/529, loss: 0.003996581770479679
2023-01-22 21:01:58.934971: step: 1968/529, loss: 0.010586723685264587
2023-01-22 21:02:00.030379: step: 1972/529, loss: 0.012198311276733875
2023-01-22 21:02:01.123666: step: 1976/529, loss: 0.002869725227355957
2023-01-22 21:02:02.244548: step: 1980/529, loss: 0.0027939460705965757
2023-01-22 21:02:03.346560: step: 1984/529, loss: 0.0009033445967361331
2023-01-22 21:02:04.447794: step: 1988/529, loss: 0.00034655132913030684
2023-01-22 21:02:05.571999: step: 1992/529, loss: 0.00034546529059298337
2023-01-22 21:02:06.703596: step: 1996/529, loss: 9.472626697970554e-05
2023-01-22 21:02:07.807783: step: 2000/529, loss: 0.00038750257226638496
2023-01-22 21:02:08.914845: step: 2004/529, loss: 0.00010098198254127055
2023-01-22 21:02:10.011666: step: 2008/529, loss: 0.0017523944843560457
2023-01-22 21:02:11.129402: step: 2012/529, loss: 0.009964141063392162
2023-01-22 21:02:12.259950: step: 2016/529, loss: 0.0016769433859735727
2023-01-22 21:02:13.387666: step: 2020/529, loss: 0.001277985400520265
2023-01-22 21:02:14.487768: step: 2024/529, loss: 0.0010931261349469423
2023-01-22 21:02:15.598753: step: 2028/529, loss: 4.800800888915546e-05
2023-01-22 21:02:16.720726: step: 2032/529, loss: 0.005852019879966974
2023-01-22 21:02:17.848624: step: 2036/529, loss: 0.0009272924507968128
2023-01-22 21:02:18.955796: step: 2040/529, loss: 0.0001120223241741769
2023-01-22 21:02:20.063232: step: 2044/529, loss: 0.03466195985674858
2023-01-22 21:02:21.165370: step: 2048/529, loss: 0.0005804647807963192
2023-01-22 21:02:22.269113: step: 2052/529, loss: 0.0002751439460553229
2023-01-22 21:02:23.387119: step: 2056/529, loss: 0.004888801369816065
2023-01-22 21:02:24.509600: step: 2060/529, loss: 0.001083503826521337
2023-01-22 21:02:25.630410: step: 2064/529, loss: 2.0044752091052942e-05
2023-01-22 21:02:26.740393: step: 2068/529, loss: 0.0023963588755577803
2023-01-22 21:02:27.843394: step: 2072/529, loss: 0.00373524846509099
2023-01-22 21:02:28.952305: step: 2076/529, loss: 0.007982109673321247
2023-01-22 21:02:30.064167: step: 2080/529, loss: 0.00391481863334775
2023-01-22 21:02:31.168450: step: 2084/529, loss: 0.006526434328407049
2023-01-22 21:02:32.289650: step: 2088/529, loss: 0.0016728973714634776
2023-01-22 21:02:33.400554: step: 2092/529, loss: 0.0007696745451539755
2023-01-22 21:02:34.518078: step: 2096/529, loss: 0.000559842272195965
2023-01-22 21:02:35.606807: step: 2100/529, loss: 0.001780455932021141
2023-01-22 21:02:36.705951: step: 2104/529, loss: 5.166012851987034e-05
2023-01-22 21:02:37.800051: step: 2108/529, loss: 0.00043957686284556985
2023-01-22 21:02:38.905659: step: 2112/529, loss: 1.769682057783939e-05
2023-01-22 21:02:39.994092: step: 2116/529, loss: 0.0025839582085609436
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33497081043956045, 'r': 0.33052148278666305, 'f1': 0.3327312730249693}, 'combined': 0.24517041170260895, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3747237772778003, 'r': 0.29906464373730857, 'f1': 0.33264636035937745}, 'combined': 0.20445581173308078, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3385632028242186, 'r': 0.3456299869438892, 'f1': 0.3420600997547974}, 'combined': 0.2520442840298507, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35921051843972734, 'r': 0.3109630051310985, 'f1': 0.33335003058178136}, 'combined': 0.2048883114795339, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3383870304165248, 'r': 0.34288173480535905, 'f1': 0.3406195555936366}, 'combined': 0.2509828304374164, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.367039277653468, 'r': 0.2977626001396532, 'f1': 0.32879139881577385}, 'combined': 0.20307704044503683, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36607142857142855, 'r': 0.44565217391304346, 'f1': 0.4019607843137254}, 'combined': 0.2009803921568627, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 18}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}
******************************
Epoch: 19
command: python train.py --model_name coref --xlmr_model_name xlm-roberta-large --batch_size 16 --xlmr_learning_rate 2e-5 --accumulate_step 4 --max_epoch 20 --event_hidden_num 500 --p1_data_weight 0.2 --learning_rate 9e-4
2023-01-22 21:05:05.048144: step: 4/529, loss: 0.002515129279345274
2023-01-22 21:05:06.185826: step: 8/529, loss: 0.042117588222026825
2023-01-22 21:05:07.298792: step: 12/529, loss: 0.003714257152751088
2023-01-22 21:05:08.438264: step: 16/529, loss: 0.001972219906747341
2023-01-22 21:05:09.533449: step: 20/529, loss: 6.963654595892876e-05
2023-01-22 21:05:10.634013: step: 24/529, loss: 0.003289313055574894
2023-01-22 21:05:11.733348: step: 28/529, loss: 0.0014585135504603386
2023-01-22 21:05:12.830426: step: 32/529, loss: 0.0010562982643023133
2023-01-22 21:05:13.920152: step: 36/529, loss: 2.54580590990372e-05
2023-01-22 21:05:15.000114: step: 40/529, loss: 0.0003981192712672055
2023-01-22 21:05:16.086332: step: 44/529, loss: 2.651472095749341e-05
2023-01-22 21:05:17.182022: step: 48/529, loss: 0.0005120172281749547
2023-01-22 21:05:18.273279: step: 52/529, loss: 5.1424027333268896e-05
2023-01-22 21:05:19.367221: step: 56/529, loss: 0.004901376087218523
2023-01-22 21:05:20.462090: step: 60/529, loss: 4.443858779268339e-05
2023-01-22 21:05:21.546959: step: 64/529, loss: 4.93349798489362e-05
2023-01-22 21:05:22.630024: step: 68/529, loss: 0.0034470469690859318
2023-01-22 21:05:23.736798: step: 72/529, loss: 0.004224816337227821
2023-01-22 21:05:24.854552: step: 76/529, loss: 0.002208239631727338
2023-01-22 21:05:25.978936: step: 80/529, loss: 0.008191767148673534
2023-01-22 21:05:27.064106: step: 84/529, loss: 0.001234333380125463
2023-01-22 21:05:28.175992: step: 88/529, loss: 0.0028308320324867964
2023-01-22 21:05:29.292549: step: 92/529, loss: 0.0010667319875210524
2023-01-22 21:05:30.416315: step: 96/529, loss: 0.003692012745887041
2023-01-22 21:05:31.508533: step: 100/529, loss: 0.00035669319913722575
2023-01-22 21:05:32.624388: step: 104/529, loss: 0.001542495796456933
2023-01-22 21:05:33.721658: step: 108/529, loss: 0.0021627629175782204
2023-01-22 21:05:34.830103: step: 112/529, loss: 0.00427895225584507
2023-01-22 21:05:35.940155: step: 116/529, loss: 0.002256552455946803
2023-01-22 21:05:37.045287: step: 120/529, loss: 0.006322585977613926
2023-01-22 21:05:38.161100: step: 124/529, loss: 0.003680649446323514
2023-01-22 21:05:39.266475: step: 128/529, loss: 3.325544821564108e-05
2023-01-22 21:05:40.365506: step: 132/529, loss: 0.0007309284410439432
2023-01-22 21:05:41.464260: step: 136/529, loss: 0.0005317345494404435
2023-01-22 21:05:42.555835: step: 140/529, loss: 6.787503025407204e-06
2023-01-22 21:05:43.642767: step: 144/529, loss: 5.30331271875184e-06
2023-01-22 21:05:44.741582: step: 148/529, loss: 0.0012661494547501206
2023-01-22 21:05:45.858665: step: 152/529, loss: 1.0934447345789522e-05
2023-01-22 21:05:46.968530: step: 156/529, loss: 0.0017589119961485267
2023-01-22 21:05:48.074745: step: 160/529, loss: 0.0024684083182364702
2023-01-22 21:05:49.165869: step: 164/529, loss: 0.005677887704223394
2023-01-22 21:05:50.273663: step: 168/529, loss: 9.003043714983505e-07
2023-01-22 21:05:51.376847: step: 172/529, loss: 0.005994025152176619
2023-01-22 21:05:52.493583: step: 176/529, loss: 0.0002197103458456695
2023-01-22 21:05:53.608157: step: 180/529, loss: 0.0005711939302273095
2023-01-22 21:05:54.718312: step: 184/529, loss: 0.0010891571873798966
2023-01-22 21:05:55.814004: step: 188/529, loss: 0.0015627671964466572
2023-01-22 21:05:56.930701: step: 192/529, loss: 0.0008933567441999912
2023-01-22 21:05:58.066138: step: 196/529, loss: 0.011484578251838684
2023-01-22 21:05:59.177391: step: 200/529, loss: 0.03009461797773838
2023-01-22 21:06:00.299070: step: 204/529, loss: 0.0018042160663753748
2023-01-22 21:06:01.427914: step: 208/529, loss: 0.002897471422329545
2023-01-22 21:06:02.534113: step: 212/529, loss: 0.0006291003664955497
2023-01-22 21:06:03.647064: step: 216/529, loss: 0.003515898482874036
2023-01-22 21:06:04.763547: step: 220/529, loss: 0.009037968702614307
2023-01-22 21:06:05.885900: step: 224/529, loss: 7.412202648993116e-06
2023-01-22 21:06:06.997165: step: 228/529, loss: 1.423345224793593e-06
2023-01-22 21:06:08.121692: step: 232/529, loss: 0.0181756392121315
2023-01-22 21:06:09.222813: step: 236/529, loss: 0.00011489960161270574
2023-01-22 21:06:10.333575: step: 240/529, loss: 0.003495260374620557
2023-01-22 21:06:11.446878: step: 244/529, loss: 0.0008709641988389194
2023-01-22 21:06:12.539368: step: 248/529, loss: 0.00031230662716552615
2023-01-22 21:06:13.663742: step: 252/529, loss: 0.001761759864166379
2023-01-22 21:06:14.764655: step: 256/529, loss: 6.900924290675903e-06
2023-01-22 21:06:15.878002: step: 260/529, loss: 0.011513270437717438
2023-01-22 21:06:16.986273: step: 264/529, loss: 0.0017682992620393634
2023-01-22 21:06:18.098928: step: 268/529, loss: 0.009417731314897537
2023-01-22 21:06:19.204353: step: 272/529, loss: 0.000323099346132949
2023-01-22 21:06:20.315653: step: 276/529, loss: 0.040628932416439056
2023-01-22 21:06:21.430195: step: 280/529, loss: 9.981498806155287e-06
2023-01-22 21:06:22.562814: step: 284/529, loss: 0.0041883266530931
2023-01-22 21:06:23.661766: step: 288/529, loss: 0.0012143495259806514
2023-01-22 21:06:24.795116: step: 292/529, loss: 0.0012636932078748941
2023-01-22 21:06:25.904266: step: 296/529, loss: 0.002426756080240011
2023-01-22 21:06:26.998550: step: 300/529, loss: 0.0023101866245269775
2023-01-22 21:06:28.093874: step: 304/529, loss: 0.0038914510514587164
2023-01-22 21:06:29.196524: step: 308/529, loss: 0.000198359542991966
2023-01-22 21:06:30.299657: step: 312/529, loss: 0.0015133768320083618
2023-01-22 21:06:31.398319: step: 316/529, loss: 2.5509900297038257e-05
2023-01-22 21:06:32.513237: step: 320/529, loss: 0.0005425954586826265
2023-01-22 21:06:33.624422: step: 324/529, loss: 0.004145944491028786
2023-01-22 21:06:34.717579: step: 328/529, loss: 0.008070851676166058
2023-01-22 21:06:35.823124: step: 332/529, loss: 0.00023014192993286997
2023-01-22 21:06:36.927063: step: 336/529, loss: 0.0021311254240572453
2023-01-22 21:06:38.020002: step: 340/529, loss: 0.005042993929237127
2023-01-22 21:06:39.119546: step: 344/529, loss: 0.0029296439606696367
2023-01-22 21:06:40.224256: step: 348/529, loss: 0.004642107989639044
2023-01-22 21:06:41.347815: step: 352/529, loss: 0.01388418860733509
2023-01-22 21:06:42.463602: step: 356/529, loss: 0.0027632839046418667
2023-01-22 21:06:43.583273: step: 360/529, loss: 0.0001689031341811642
2023-01-22 21:06:44.676183: step: 364/529, loss: 0.006203958764672279
2023-01-22 21:06:45.796379: step: 368/529, loss: 0.0038964394479990005
2023-01-22 21:06:46.902007: step: 372/529, loss: 0.003068020800128579
2023-01-22 21:06:48.001702: step: 376/529, loss: 0.006584575865417719
2023-01-22 21:06:49.093192: step: 380/529, loss: 0.006145960185676813
2023-01-22 21:06:50.195072: step: 384/529, loss: 0.004592226818203926
2023-01-22 21:06:51.311152: step: 388/529, loss: 0.003500356338918209
2023-01-22 21:06:52.450343: step: 392/529, loss: 0.0023840356152504683
2023-01-22 21:06:53.550974: step: 396/529, loss: 0.0011784323723986745
2023-01-22 21:06:54.648447: step: 400/529, loss: 0.006961505394428968
2023-01-22 21:06:55.735576: step: 404/529, loss: 0.0030000151600688696
2023-01-22 21:06:56.845265: step: 408/529, loss: 0.0008716362644918263
2023-01-22 21:06:57.940174: step: 412/529, loss: 0.0019585415720939636
2023-01-22 21:06:59.057748: step: 416/529, loss: 0.0015604370273649693
2023-01-22 21:07:00.186943: step: 420/529, loss: 0.007060790900141001
2023-01-22 21:07:01.297701: step: 424/529, loss: 0.0002206896460847929
2023-01-22 21:07:02.409710: step: 428/529, loss: 0.005229902919381857
2023-01-22 21:07:03.519914: step: 432/529, loss: 6.697853677906096e-05
2023-01-22 21:07:04.607857: step: 436/529, loss: 0.0004602751287166029
2023-01-22 21:07:05.750151: step: 440/529, loss: 0.0016866980586200953
2023-01-22 21:07:06.856291: step: 444/529, loss: 0.002020878717303276
2023-01-22 21:07:07.980623: step: 448/529, loss: 0.002414423506706953
2023-01-22 21:07:09.062606: step: 452/529, loss: 1.9656768927234225e-05
2023-01-22 21:07:10.184812: step: 456/529, loss: 0.00245417351834476
2023-01-22 21:07:11.316923: step: 460/529, loss: 0.0016583745600655675
2023-01-22 21:07:12.414529: step: 464/529, loss: 0.00048096911632455885
2023-01-22 21:07:13.507523: step: 468/529, loss: 0.00027440875419415534
2023-01-22 21:07:14.620333: step: 472/529, loss: 0.0024998849257826805
2023-01-22 21:07:15.721205: step: 476/529, loss: 0.006224286276847124
2023-01-22 21:07:16.838355: step: 480/529, loss: 0.0019229919416829944
2023-01-22 21:07:17.944003: step: 484/529, loss: 8.527380487066694e-06
2023-01-22 21:07:19.054356: step: 488/529, loss: 0.0027839643880724907
2023-01-22 21:07:20.154567: step: 492/529, loss: 7.896906754467636e-05
2023-01-22 21:07:21.256361: step: 496/529, loss: 0.0017764586955308914
2023-01-22 21:07:22.347923: step: 500/529, loss: 0.0022709884215146303
2023-01-22 21:07:23.448322: step: 504/529, loss: 0.006108562927693129
2023-01-22 21:07:24.543647: step: 508/529, loss: 0.004134563263505697
2023-01-22 21:07:25.644946: step: 512/529, loss: 0.012196128256618977
2023-01-22 21:07:26.750009: step: 516/529, loss: 0.00013790398952551186
2023-01-22 21:07:27.880518: step: 520/529, loss: 2.9570426704594865e-05
2023-01-22 21:07:29.018675: step: 524/529, loss: 0.0010324257891625166
2023-01-22 21:07:30.128597: step: 528/529, loss: 9.28020745050162e-06
2023-01-22 21:07:31.239959: step: 532/529, loss: 0.00012021453585475683
2023-01-22 21:07:32.379197: step: 536/529, loss: 0.016974138095974922
2023-01-22 21:07:33.484370: step: 540/529, loss: 0.029024222865700722
2023-01-22 21:07:34.606650: step: 544/529, loss: 0.004723994992673397
2023-01-22 21:07:35.715323: step: 548/529, loss: 0.0007895179442130029
2023-01-22 21:07:36.830907: step: 552/529, loss: 0.0004907877300865948
2023-01-22 21:07:37.927170: step: 556/529, loss: 0.0010578130604699254
2023-01-22 21:07:39.038128: step: 560/529, loss: 6.065434718038887e-06
2023-01-22 21:07:40.147558: step: 564/529, loss: 0.0006848315824754536
2023-01-22 21:07:41.251126: step: 568/529, loss: 0.008157975971698761
2023-01-22 21:07:42.359193: step: 572/529, loss: 0.0017022100510075688
2023-01-22 21:07:43.463226: step: 576/529, loss: 0.0028045426588505507
2023-01-22 21:07:44.582877: step: 580/529, loss: 0.0014142559375613928
2023-01-22 21:07:45.696825: step: 584/529, loss: 0.004144781269133091
2023-01-22 21:07:46.817738: step: 588/529, loss: 0.0007218053215183318
2023-01-22 21:07:47.929662: step: 592/529, loss: 0.0013224389404058456
2023-01-22 21:07:49.042831: step: 596/529, loss: 0.00015425431774929166
2023-01-22 21:07:50.163725: step: 600/529, loss: 2.098843287967611e-05
2023-01-22 21:07:51.286928: step: 604/529, loss: 0.0001713370147626847
2023-01-22 21:07:52.400936: step: 608/529, loss: 0.00221316353417933
2023-01-22 21:07:53.520326: step: 612/529, loss: 0.004469534382224083
2023-01-22 21:07:54.624213: step: 616/529, loss: 0.0008708247332833707
2023-01-22 21:07:55.738704: step: 620/529, loss: 0.013388365507125854
2023-01-22 21:07:56.837743: step: 624/529, loss: 0.0007657025707885623
2023-01-22 21:07:57.941679: step: 628/529, loss: 0.009786712005734444
2023-01-22 21:07:59.050272: step: 632/529, loss: 0.007056476082652807
2023-01-22 21:08:00.147428: step: 636/529, loss: 0.0005588439526036382
2023-01-22 21:08:01.264078: step: 640/529, loss: 0.00920840073376894
2023-01-22 21:08:02.364992: step: 644/529, loss: 3.497383659123443e-05
2023-01-22 21:08:03.481112: step: 648/529, loss: 0.001605254365131259
2023-01-22 21:08:04.619437: step: 652/529, loss: 0.005136909428983927
2023-01-22 21:08:05.729614: step: 656/529, loss: 0.011881612241268158
2023-01-22 21:08:06.842261: step: 660/529, loss: 0.0009909030050039291
2023-01-22 21:08:07.976178: step: 664/529, loss: 0.001475058263167739
2023-01-22 21:08:09.079350: step: 668/529, loss: 0.008074665442109108
2023-01-22 21:08:10.198583: step: 672/529, loss: 0.00788902398198843
2023-01-22 21:08:11.302308: step: 676/529, loss: 0.0013463061768561602
2023-01-22 21:08:12.411148: step: 680/529, loss: 0.0012964956695213914
2023-01-22 21:08:13.531898: step: 684/529, loss: 0.0011892806505784392
2023-01-22 21:08:14.638199: step: 688/529, loss: 0.004064568784087896
2023-01-22 21:08:15.764576: step: 692/529, loss: 0.0038937286008149385
2023-01-22 21:08:16.848489: step: 696/529, loss: 0.00021936155098956078
2023-01-22 21:08:17.977398: step: 700/529, loss: 0.003658293979242444
2023-01-22 21:08:19.093364: step: 704/529, loss: 2.2889800675329752e-05
2023-01-22 21:08:20.214828: step: 708/529, loss: 0.0003839272540062666
2023-01-22 21:08:21.316142: step: 712/529, loss: 0.0026701060123741627
2023-01-22 21:08:22.420019: step: 716/529, loss: 0.0003877747803926468
2023-01-22 21:08:23.541154: step: 720/529, loss: 0.0018111772369593382
2023-01-22 21:08:24.648480: step: 724/529, loss: 0.002418719232082367
2023-01-22 21:08:25.757899: step: 728/529, loss: 1.604023782419972e-05
2023-01-22 21:08:26.858021: step: 732/529, loss: 0.0035579788964241743
2023-01-22 21:08:27.966492: step: 736/529, loss: 0.0015203305520117283
2023-01-22 21:08:29.093926: step: 740/529, loss: 0.0013580997474491596
2023-01-22 21:08:30.191073: step: 744/529, loss: 2.207766920037102e-05
2023-01-22 21:08:31.295801: step: 748/529, loss: 0.0005680155009031296
2023-01-22 21:08:32.405314: step: 752/529, loss: 0.00043688464211300015
2023-01-22 21:08:33.510542: step: 756/529, loss: 6.899232539581135e-05
2023-01-22 21:08:34.614903: step: 760/529, loss: 0.005713443737477064
2023-01-22 21:08:35.755627: step: 764/529, loss: 0.0022997490596026182
2023-01-22 21:08:36.866240: step: 768/529, loss: 0.014577297493815422
2023-01-22 21:08:37.971619: step: 772/529, loss: 0.0013613359769806266
2023-01-22 21:08:39.070956: step: 776/529, loss: 0.00018187775276601315
2023-01-22 21:08:40.182851: step: 780/529, loss: 0.003970622550696135
2023-01-22 21:08:41.309031: step: 784/529, loss: 0.024156101047992706
2023-01-22 21:08:42.420285: step: 788/529, loss: 0.000991825945675373
2023-01-22 21:08:43.516331: step: 792/529, loss: 0.0002483031712472439
2023-01-22 21:08:44.626233: step: 796/529, loss: 0.0021235086023807526
2023-01-22 21:08:45.748536: step: 800/529, loss: 0.0012124486966058612
2023-01-22 21:08:46.853632: step: 804/529, loss: 0.0022717094980180264
2023-01-22 21:08:47.971603: step: 808/529, loss: 0.002715103793889284
2023-01-22 21:08:49.078756: step: 812/529, loss: 0.00012125296052545309
2023-01-22 21:08:50.187908: step: 816/529, loss: 0.003937737084925175
2023-01-22 21:08:51.271153: step: 820/529, loss: 0.008904669433832169
2023-01-22 21:08:52.380861: step: 824/529, loss: 0.000734749948605895
2023-01-22 21:08:53.472352: step: 828/529, loss: 1.0322844900656492e-05
2023-01-22 21:08:54.584033: step: 832/529, loss: 0.004629488103091717
2023-01-22 21:08:55.678759: step: 836/529, loss: 0.00599862914532423
2023-01-22 21:08:56.769390: step: 840/529, loss: 4.157593866693787e-05
2023-01-22 21:08:57.881794: step: 844/529, loss: 0.0039885928854346275
2023-01-22 21:08:58.998773: step: 848/529, loss: 0.003461960470303893
2023-01-22 21:09:00.116713: step: 852/529, loss: 0.004900790750980377
2023-01-22 21:09:01.215077: step: 856/529, loss: 0.0024634823203086853
2023-01-22 21:09:02.320082: step: 860/529, loss: 0.00343673350289464
2023-01-22 21:09:03.442218: step: 864/529, loss: 0.012906216084957123
2023-01-22 21:09:04.558213: step: 868/529, loss: 0.0062122950330376625
2023-01-22 21:09:05.668955: step: 872/529, loss: 1.521968101769744e-06
2023-01-22 21:09:06.778211: step: 876/529, loss: 0.0002512185601517558
2023-01-22 21:09:07.915640: step: 880/529, loss: 0.0039969272911548615
2023-01-22 21:09:09.009230: step: 884/529, loss: 1.0799634765135124e-05
2023-01-22 21:09:10.122707: step: 888/529, loss: 0.010927834548056126
2023-01-22 21:09:11.245173: step: 892/529, loss: 0.00017552435747347772
2023-01-22 21:09:12.350892: step: 896/529, loss: 7.884536898927763e-05
2023-01-22 21:09:13.486482: step: 900/529, loss: 0.0024376928340643644
2023-01-22 21:09:14.610083: step: 904/529, loss: 0.01575223170220852
2023-01-22 21:09:15.721096: step: 908/529, loss: 0.008317980915307999
2023-01-22 21:09:16.825164: step: 912/529, loss: 0.0005217691068537533
2023-01-22 21:09:17.956761: step: 916/529, loss: 0.00591327203437686
2023-01-22 21:09:19.063951: step: 920/529, loss: 0.03702763095498085
2023-01-22 21:09:20.173627: step: 924/529, loss: 0.00031593296444043517
2023-01-22 21:09:21.344962: step: 928/529, loss: 8.674946002429351e-05
2023-01-22 21:09:22.430493: step: 932/529, loss: 3.282969601059449e-06
2023-01-22 21:09:23.524946: step: 936/529, loss: 0.0012404134031385183
2023-01-22 21:09:24.651762: step: 940/529, loss: 0.006008796393871307
2023-01-22 21:09:25.763945: step: 944/529, loss: 0.002160663018003106
2023-01-22 21:09:26.878834: step: 948/529, loss: 0.0008952803909778595
2023-01-22 21:09:27.972225: step: 952/529, loss: 0.002350547816604376
2023-01-22 21:09:29.092314: step: 956/529, loss: 0.0011286986991763115
2023-01-22 21:09:30.208991: step: 960/529, loss: 0.0002235923457192257
2023-01-22 21:09:31.323525: step: 964/529, loss: 0.0002552682999521494
2023-01-22 21:09:32.438372: step: 968/529, loss: 0.0029484282713383436
2023-01-22 21:09:33.569466: step: 972/529, loss: 0.0025193053297698498
2023-01-22 21:09:34.698189: step: 976/529, loss: 0.00493354257196188
2023-01-22 21:09:35.804217: step: 980/529, loss: 0.002164387609809637
2023-01-22 21:09:36.932664: step: 984/529, loss: 0.0020205946639180183
2023-01-22 21:09:38.031000: step: 988/529, loss: 0.0010405535576865077
2023-01-22 21:09:39.147570: step: 992/529, loss: 0.00023080004029907286
2023-01-22 21:09:40.256011: step: 996/529, loss: 0.004372393246740103
2023-01-22 21:09:41.350627: step: 1000/529, loss: 7.599623495480046e-05
2023-01-22 21:09:42.465792: step: 1004/529, loss: 8.600207365816459e-05
2023-01-22 21:09:43.572368: step: 1008/529, loss: 0.001264549675397575
2023-01-22 21:09:44.720013: step: 1012/529, loss: 0.0015926676569506526
2023-01-22 21:09:45.828844: step: 1016/529, loss: 3.2328262022929266e-05
2023-01-22 21:09:46.931889: step: 1020/529, loss: 0.00256981304846704
2023-01-22 21:09:48.026786: step: 1024/529, loss: 0.00014677700528409332
2023-01-22 21:09:49.140787: step: 1028/529, loss: 0.0010209884494543076
2023-01-22 21:09:50.262305: step: 1032/529, loss: 0.09078031778335571
2023-01-22 21:09:51.395374: step: 1036/529, loss: 5.396077176555991e-05
2023-01-22 21:09:52.511604: step: 1040/529, loss: 0.0020750206895172596
2023-01-22 21:09:53.646298: step: 1044/529, loss: 0.002354108728468418
2023-01-22 21:09:54.756222: step: 1048/529, loss: 0.0007027073879726231
2023-01-22 21:09:55.873867: step: 1052/529, loss: 0.0030362012330442667
2023-01-22 21:09:56.971390: step: 1056/529, loss: 0.005776799283921719
2023-01-22 21:09:58.075669: step: 1060/529, loss: 0.0031625377014279366
2023-01-22 21:09:59.163762: step: 1064/529, loss: 4.4993535993853584e-05
2023-01-22 21:10:00.274963: step: 1068/529, loss: 0.003949759993702173
2023-01-22 21:10:01.386394: step: 1072/529, loss: 0.0009441837319172919
2023-01-22 21:10:02.515568: step: 1076/529, loss: 0.00033297622576355934
2023-01-22 21:10:03.631392: step: 1080/529, loss: 0.002375268144533038
2023-01-22 21:10:04.720742: step: 1084/529, loss: 0.0003824633313342929
2023-01-22 21:10:05.830139: step: 1088/529, loss: 0.011141564697027206
2023-01-22 21:10:06.918696: step: 1092/529, loss: 0.01226444635540247
2023-01-22 21:10:08.032281: step: 1096/529, loss: 0.001025436446070671
2023-01-22 21:10:09.150743: step: 1100/529, loss: 0.0001177908998215571
2023-01-22 21:10:10.264212: step: 1104/529, loss: 0.0011987262405455112
2023-01-22 21:10:11.375976: step: 1108/529, loss: 6.334928002615925e-06
2023-01-22 21:10:12.499453: step: 1112/529, loss: 0.0022149020805954933
2023-01-22 21:10:13.614340: step: 1116/529, loss: 7.053666195133701e-05
2023-01-22 21:10:14.713013: step: 1120/529, loss: 0.0026090338360518217
2023-01-22 21:10:15.813861: step: 1124/529, loss: 0.004320600535720587
2023-01-22 21:10:16.911961: step: 1128/529, loss: 1.1652815373963676e-05
2023-01-22 21:10:18.036059: step: 1132/529, loss: 0.0015827511670067906
2023-01-22 21:10:19.132167: step: 1136/529, loss: 0.0005357727641239762
2023-01-22 21:10:20.239347: step: 1140/529, loss: 0.004198629874736071
2023-01-22 21:10:21.350243: step: 1144/529, loss: 0.005446875002235174
2023-01-22 21:10:22.476745: step: 1148/529, loss: 0.0017383525846526027
2023-01-22 21:10:23.605356: step: 1152/529, loss: 0.0011263630585744977
2023-01-22 21:10:24.704810: step: 1156/529, loss: 0.0014643777394667268
2023-01-22 21:10:25.776350: step: 1160/529, loss: 0.0021422095596790314
2023-01-22 21:10:26.871953: step: 1164/529, loss: 0.0005390482838265598
2023-01-22 21:10:27.995718: step: 1168/529, loss: 0.0011096819071099162
2023-01-22 21:10:29.129927: step: 1172/529, loss: 0.004362502600997686
2023-01-22 21:10:30.238300: step: 1176/529, loss: 1.7825493614509469e-06
2023-01-22 21:10:31.335949: step: 1180/529, loss: 0.0035751163959503174
2023-01-22 21:10:32.439932: step: 1184/529, loss: 0.010183860547840595
2023-01-22 21:10:33.547416: step: 1188/529, loss: 0.005394357722252607
2023-01-22 21:10:34.643702: step: 1192/529, loss: 0.0011433775071054697
2023-01-22 21:10:35.734828: step: 1196/529, loss: 0.0001433080469723791
2023-01-22 21:10:36.843513: step: 1200/529, loss: 0.0010919515043497086
2023-01-22 21:10:37.956293: step: 1204/529, loss: 0.008285412564873695
2023-01-22 21:10:39.052187: step: 1208/529, loss: 0.003191579831764102
2023-01-22 21:10:40.181146: step: 1212/529, loss: 0.0002722078934311867
2023-01-22 21:10:41.311669: step: 1216/529, loss: 0.0010823936900123954
2023-01-22 21:10:42.408811: step: 1220/529, loss: 0.0019861948676407337
2023-01-22 21:10:43.485318: step: 1224/529, loss: 0.0049724578857421875
2023-01-22 21:10:44.602274: step: 1228/529, loss: 8.940689966152604e-09
2023-01-22 21:10:45.717374: step: 1232/529, loss: 0.04660915583372116
2023-01-22 21:10:46.831378: step: 1236/529, loss: 0.002036280930042267
2023-01-22 21:10:47.949009: step: 1240/529, loss: 0.0007337016868405044
2023-01-22 21:10:49.055320: step: 1244/529, loss: 0.00013954381574876606
2023-01-22 21:10:50.144527: step: 1248/529, loss: 0.0001331036473857239
2023-01-22 21:10:51.235106: step: 1252/529, loss: 0.0007688223267905414
2023-01-22 21:10:52.343978: step: 1256/529, loss: 0.0006111471448093653
2023-01-22 21:10:53.469067: step: 1260/529, loss: 0.00044723015162162483
2023-01-22 21:10:54.574308: step: 1264/529, loss: 0.000637308054137975
2023-01-22 21:10:55.688154: step: 1268/529, loss: 0.00019118207274004817
2023-01-22 21:10:56.788190: step: 1272/529, loss: 0.0009755234350450337
2023-01-22 21:10:57.904236: step: 1276/529, loss: 0.003899776376783848
2023-01-22 21:10:59.005994: step: 1280/529, loss: 0.0022934211883693933
2023-01-22 21:11:00.143103: step: 1284/529, loss: 1.9409029846428894e-05
2023-01-22 21:11:01.250112: step: 1288/529, loss: 0.004870065022259951
2023-01-22 21:11:02.381645: step: 1292/529, loss: 0.0005327885155566037
2023-01-22 21:11:03.485576: step: 1296/529, loss: 0.00042267024400644004
2023-01-22 21:11:04.588710: step: 1300/529, loss: 0.006611426826566458
2023-01-22 21:11:05.684417: step: 1304/529, loss: 0.0002100148267345503
2023-01-22 21:11:06.782468: step: 1308/529, loss: 6.575922452611849e-05
2023-01-22 21:11:07.915793: step: 1312/529, loss: 1.5208149306999985e-05
2023-01-22 21:11:09.025488: step: 1316/529, loss: 0.0025981476064771414
2023-01-22 21:11:10.155958: step: 1320/529, loss: 0.0020401678048074245
2023-01-22 21:11:11.258274: step: 1324/529, loss: 6.701559323119e-05
2023-01-22 21:11:12.388137: step: 1328/529, loss: 0.0055059571750462055
2023-01-22 21:11:13.489036: step: 1332/529, loss: 0.0004269076162017882
2023-01-22 21:11:14.586021: step: 1336/529, loss: 0.003423511516302824
2023-01-22 21:11:15.701705: step: 1340/529, loss: 0.0005998878623358905
2023-01-22 21:11:16.822844: step: 1344/529, loss: 0.047127023339271545
2023-01-22 21:11:17.937660: step: 1348/529, loss: 0.0013119399081915617
2023-01-22 21:11:19.047176: step: 1352/529, loss: 0.009838234633207321
2023-01-22 21:11:20.170688: step: 1356/529, loss: 2.9159928089939058e-05
2023-01-22 21:11:21.268028: step: 1360/529, loss: 0.00336446356959641
2023-01-22 21:11:22.374423: step: 1364/529, loss: 0.005810531787574291
2023-01-22 21:11:23.477871: step: 1368/529, loss: 0.01106372568756342
2023-01-22 21:11:24.583731: step: 1372/529, loss: 0.0050170691683888435
2023-01-22 21:11:25.669630: step: 1376/529, loss: 5.2270799642428756e-05
2023-01-22 21:11:26.768509: step: 1380/529, loss: 0.05188421532511711
2023-01-22 21:11:27.871343: step: 1384/529, loss: 0.007389829494059086
2023-01-22 21:11:28.987166: step: 1388/529, loss: 0.0012455395190045238
2023-01-22 21:11:30.100630: step: 1392/529, loss: 0.0072115156799554825
2023-01-22 21:11:31.213842: step: 1396/529, loss: 0.02572551555931568
2023-01-22 21:11:32.337355: step: 1400/529, loss: 0.0066342600621283054
2023-01-22 21:11:33.431260: step: 1404/529, loss: 0.0031778954435139894
2023-01-22 21:11:34.527311: step: 1408/529, loss: 0.005597598850727081
2023-01-22 21:11:35.631702: step: 1412/529, loss: 0.0044565461575984955
2023-01-22 21:11:36.740744: step: 1416/529, loss: 7.092933083185926e-05
2023-01-22 21:11:37.826023: step: 1420/529, loss: 0.0016181654063984752
2023-01-22 21:11:38.933531: step: 1424/529, loss: 0.004665218759328127
2023-01-22 21:11:40.058480: step: 1428/529, loss: 0.0011610727524384856
2023-01-22 21:11:41.179789: step: 1432/529, loss: 0.005263286177068949
2023-01-22 21:11:42.293731: step: 1436/529, loss: 0.0006570618716068566
2023-01-22 21:11:43.403795: step: 1440/529, loss: 0.0006696152267977595
2023-01-22 21:11:44.510207: step: 1444/529, loss: 0.0006329510360956192
2023-01-22 21:11:45.625418: step: 1448/529, loss: 3.4138480259571224e-05
2023-01-22 21:11:46.740369: step: 1452/529, loss: 0.0002547826443333179
2023-01-22 21:11:47.845005: step: 1456/529, loss: 0.01591784879565239
2023-01-22 21:11:48.950929: step: 1460/529, loss: 0.001227688160724938
2023-01-22 21:11:50.047076: step: 1464/529, loss: 0.0003774031938519329
2023-01-22 21:11:51.170341: step: 1468/529, loss: 0.0011182804591953754
2023-01-22 21:11:52.286159: step: 1472/529, loss: 0.015542536973953247
2023-01-22 21:11:53.385843: step: 1476/529, loss: 0.0003420463763177395
2023-01-22 21:11:54.518118: step: 1480/529, loss: 0.0018965578638017178
2023-01-22 21:11:55.616795: step: 1484/529, loss: 0.00140009552706033
2023-01-22 21:11:56.712299: step: 1488/529, loss: 0.0001720975269563496
2023-01-22 21:11:57.800507: step: 1492/529, loss: 4.1165876609738916e-05
2023-01-22 21:11:58.902915: step: 1496/529, loss: 0.00021411824855022132
2023-01-22 21:12:00.014860: step: 1500/529, loss: 0.020264215767383575
2023-01-22 21:12:01.123272: step: 1504/529, loss: 3.779512917390093e-05
2023-01-22 21:12:02.244523: step: 1508/529, loss: 0.0029182955622673035
2023-01-22 21:12:03.353977: step: 1512/529, loss: 0.0006796749075874686
2023-01-22 21:12:04.460696: step: 1516/529, loss: 0.0005390775622799993
2023-01-22 21:12:05.619146: step: 1520/529, loss: 0.0003339150862302631
2023-01-22 21:12:06.737911: step: 1524/529, loss: 0.004776553250849247
2023-01-22 21:12:07.869810: step: 1528/529, loss: 0.004782753065228462
2023-01-22 21:12:08.966065: step: 1532/529, loss: 7.556027412647381e-05
2023-01-22 21:12:10.073527: step: 1536/529, loss: 8.260748290922493e-05
2023-01-22 21:12:11.184338: step: 1540/529, loss: 0.002633172320201993
2023-01-22 21:12:12.310104: step: 1544/529, loss: 0.0031153487507253885
2023-01-22 21:12:13.424606: step: 1548/529, loss: 0.0002114608942065388
2023-01-22 21:12:14.542507: step: 1552/529, loss: 0.02373434789478779
2023-01-22 21:12:15.637521: step: 1556/529, loss: 0.0009980922332033515
2023-01-22 21:12:16.741740: step: 1560/529, loss: 0.004760845098644495
2023-01-22 21:12:17.836747: step: 1564/529, loss: 3.7880527088418603e-06
2023-01-22 21:12:18.965033: step: 1568/529, loss: 0.0019359186990186572
2023-01-22 21:12:20.086745: step: 1572/529, loss: 0.0001558828225824982
2023-01-22 21:12:21.196858: step: 1576/529, loss: 5.598276402452029e-05
2023-01-22 21:12:22.306072: step: 1580/529, loss: 0.00197223131544888
2023-01-22 21:12:23.420390: step: 1584/529, loss: 0.0009332557092420757
2023-01-22 21:12:24.525319: step: 1588/529, loss: 2.346081964788027e-05
2023-01-22 21:12:25.620717: step: 1592/529, loss: 0.002634502248838544
2023-01-22 21:12:26.747684: step: 1596/529, loss: 0.0070084757171571255
2023-01-22 21:12:27.860898: step: 1600/529, loss: 0.0015014380915090442
2023-01-22 21:12:28.984131: step: 1604/529, loss: 0.0024020092096179724
2023-01-22 21:12:30.095391: step: 1608/529, loss: 0.0010112121235579252
2023-01-22 21:12:31.223833: step: 1612/529, loss: 0.008827624842524529
2023-01-22 21:12:32.343955: step: 1616/529, loss: 0.00023526264703832567
2023-01-22 21:12:33.450735: step: 1620/529, loss: 0.0007089654100127518
2023-01-22 21:12:34.558293: step: 1624/529, loss: 0.002622129861265421
2023-01-22 21:12:35.658821: step: 1628/529, loss: 0.005837226752191782
2023-01-22 21:12:36.788532: step: 1632/529, loss: 0.0005664409836754203
2023-01-22 21:12:37.899110: step: 1636/529, loss: 0.00015801946574356407
2023-01-22 21:12:38.998246: step: 1640/529, loss: 0.0006514594424515963
2023-01-22 21:12:40.109911: step: 1644/529, loss: 0.0019710755441337824
2023-01-22 21:12:41.229531: step: 1648/529, loss: 2.5102790459641255e-05
2023-01-22 21:12:42.333087: step: 1652/529, loss: 0.0053861928172409534
2023-01-22 21:12:43.442203: step: 1656/529, loss: 0.0008697125012986362
2023-01-22 21:12:44.551376: step: 1660/529, loss: 0.0011428359430283308
2023-01-22 21:12:45.654233: step: 1664/529, loss: 0.0008945821318775415
2023-01-22 21:12:46.774238: step: 1668/529, loss: 0.006410997360944748
2023-01-22 21:12:47.898494: step: 1672/529, loss: 2.273559039167594e-05
2023-01-22 21:12:49.032120: step: 1676/529, loss: 0.0028206754941493273
2023-01-22 21:12:50.164357: step: 1680/529, loss: 2.4876862880773842e-05
2023-01-22 21:12:51.269811: step: 1684/529, loss: 0.0021191395353525877
2023-01-22 21:12:52.357154: step: 1688/529, loss: 6.235543423827039e-06
2023-01-22 21:12:53.479748: step: 1692/529, loss: 0.004005727358162403
2023-01-22 21:12:54.581211: step: 1696/529, loss: 0.000275185564532876
2023-01-22 21:12:55.694239: step: 1700/529, loss: 0.0028727923054248095
2023-01-22 21:12:56.852303: step: 1704/529, loss: 0.0038915870245546103
2023-01-22 21:12:57.964455: step: 1708/529, loss: 0.0008150855428539217
2023-01-22 21:12:59.094612: step: 1712/529, loss: 0.00023460510419681668
2023-01-22 21:13:00.212697: step: 1716/529, loss: 0.00017404998652637005
2023-01-22 21:13:01.295196: step: 1720/529, loss: 0.012200117111206055
2023-01-22 21:13:02.388271: step: 1724/529, loss: 2.4797329842840554e-06
2023-01-22 21:13:03.483963: step: 1728/529, loss: 0.00195849291048944
2023-01-22 21:13:04.603414: step: 1732/529, loss: 0.0002815011248458177
2023-01-22 21:13:05.718402: step: 1736/529, loss: 0.00023537929519079626
2023-01-22 21:13:06.809433: step: 1740/529, loss: 0.0011688710656017065
2023-01-22 21:13:07.902139: step: 1744/529, loss: 3.492762698442675e-05
2023-01-22 21:13:08.996661: step: 1748/529, loss: 0.0023557599633932114
2023-01-22 21:13:10.110515: step: 1752/529, loss: 0.00015541866014245898
2023-01-22 21:13:11.212233: step: 1756/529, loss: 0.0002262130001327023
2023-01-22 21:13:12.305414: step: 1760/529, loss: 0.00022248901950661093
2023-01-22 21:13:13.404276: step: 1764/529, loss: 0.00015608487592544407
2023-01-22 21:13:14.508044: step: 1768/529, loss: 0.0010604705894365907
2023-01-22 21:13:15.600933: step: 1772/529, loss: 0.0001499402424087748
2023-01-22 21:13:16.729787: step: 1776/529, loss: 0.010341660119593143
2023-01-22 21:13:17.845867: step: 1780/529, loss: 0.0013549277791753411
2023-01-22 21:13:18.957932: step: 1784/529, loss: 0.00013977581693325192
2023-01-22 21:13:20.064666: step: 1788/529, loss: 2.3025436348689254e-06
2023-01-22 21:13:21.162723: step: 1792/529, loss: 0.0017215120606124401
2023-01-22 21:13:22.268916: step: 1796/529, loss: 0.00048215489368885756
2023-01-22 21:13:23.408901: step: 1800/529, loss: 0.001176641322672367
2023-01-22 21:13:24.495908: step: 1804/529, loss: 0.0008501983247697353
2023-01-22 21:13:25.600075: step: 1808/529, loss: 0.00026085422723554075
2023-01-22 21:13:26.708157: step: 1812/529, loss: 0.00016341837181244045
2023-01-22 21:13:27.802277: step: 1816/529, loss: 0.003964359872043133
2023-01-22 21:13:28.905528: step: 1820/529, loss: 0.00013518851483240724
2023-01-22 21:13:29.996401: step: 1824/529, loss: 0.00016970177239272743
2023-01-22 21:13:31.109734: step: 1828/529, loss: 0.0009307496366091073
2023-01-22 21:13:32.236397: step: 1832/529, loss: 0.0003689092700369656
2023-01-22 21:13:33.339307: step: 1836/529, loss: 6.277789361774921e-05
2023-01-22 21:13:34.450187: step: 1840/529, loss: 0.004234683699905872
2023-01-22 21:13:35.563941: step: 1844/529, loss: 0.0023572933860123158
2023-01-22 21:13:36.655277: step: 1848/529, loss: 0.0015700494404882193
2023-01-22 21:13:37.750626: step: 1852/529, loss: 6.459199539676774e-06
2023-01-22 21:13:38.868968: step: 1856/529, loss: 0.008039561100304127
2023-01-22 21:13:39.964789: step: 1860/529, loss: 0.00024027626204770058
2023-01-22 21:13:41.083620: step: 1864/529, loss: 0.0021593887358903885
2023-01-22 21:13:42.179942: step: 1868/529, loss: 0.0004813428095076233
2023-01-22 21:13:43.308315: step: 1872/529, loss: 0.004609021358191967
2023-01-22 21:13:44.418920: step: 1876/529, loss: 0.0011405982077121735
2023-01-22 21:13:45.529418: step: 1880/529, loss: 0.001695619081147015
2023-01-22 21:13:46.633815: step: 1884/529, loss: 8.133264054777101e-05
2023-01-22 21:13:47.757757: step: 1888/529, loss: 1.111825622501783e-05
2023-01-22 21:13:48.902871: step: 1892/529, loss: 0.0006777423550374806
2023-01-22 21:13:49.992056: step: 1896/529, loss: 6.837446107965661e-06
2023-01-22 21:13:51.112279: step: 1900/529, loss: 0.000639311911072582
2023-01-22 21:13:52.226840: step: 1904/529, loss: 0.007955932058393955
2023-01-22 21:13:53.317319: step: 1908/529, loss: 0.0039582024328410625
2023-01-22 21:13:54.406148: step: 1912/529, loss: 0.0005224067135713995
2023-01-22 21:13:55.518797: step: 1916/529, loss: 0.001513217343017459
2023-01-22 21:13:56.629977: step: 1920/529, loss: 0.0008355839527212083
2023-01-22 21:13:57.714500: step: 1924/529, loss: 0.0035183136351406574
2023-01-22 21:13:58.813601: step: 1928/529, loss: 0.0009953314438462257
2023-01-22 21:13:59.913657: step: 1932/529, loss: 0.0002983025333378464
2023-01-22 21:14:01.028097: step: 1936/529, loss: 0.0002993101952597499
2023-01-22 21:14:02.143990: step: 1940/529, loss: 0.01194830983877182
2023-01-22 21:14:03.253997: step: 1944/529, loss: 0.0015975891146808863
2023-01-22 21:14:04.365402: step: 1948/529, loss: 7.630797335878015e-05
2023-01-22 21:14:05.499756: step: 1952/529, loss: 0.0005793973687104881
2023-01-22 21:14:06.605656: step: 1956/529, loss: 0.0002117531403200701
2023-01-22 21:14:07.718285: step: 1960/529, loss: 0.0050086332485079765
2023-01-22 21:14:08.814085: step: 1964/529, loss: 8.809321298031136e-05
2023-01-22 21:14:09.905816: step: 1968/529, loss: 0.0036579458974301815
2023-01-22 21:14:11.001419: step: 1972/529, loss: 0.0018649366684257984
2023-01-22 21:14:12.104499: step: 1976/529, loss: 0.00021319091320037842
2023-01-22 21:14:13.213527: step: 1980/529, loss: 0.0008732384885661304
2023-01-22 21:14:14.327710: step: 1984/529, loss: 0.004350434523075819
2023-01-22 21:14:15.435989: step: 1988/529, loss: 2.229947131127119e-05
2023-01-22 21:14:16.510831: step: 1992/529, loss: 0.00038746881182305515
2023-01-22 21:14:17.630395: step: 1996/529, loss: 0.008658532053232193
2023-01-22 21:14:18.743363: step: 2000/529, loss: 0.002401188015937805
2023-01-22 21:14:19.867815: step: 2004/529, loss: 4.3907028157263994e-05
2023-01-22 21:14:20.981172: step: 2008/529, loss: 8.565664757043123e-05
2023-01-22 21:14:22.064011: step: 2012/529, loss: 0.0002656480355653912
2023-01-22 21:14:23.182946: step: 2016/529, loss: 3.524524800013751e-05
2023-01-22 21:14:24.273628: step: 2020/529, loss: 0.0004568536824081093
2023-01-22 21:14:25.387351: step: 2024/529, loss: 0.0015852776123210788
2023-01-22 21:14:26.486073: step: 2028/529, loss: 2.808785666275071e-07
2023-01-22 21:14:27.620576: step: 2032/529, loss: 0.0023403314407914877
2023-01-22 21:14:28.721845: step: 2036/529, loss: 0.000985249993391335
2023-01-22 21:14:29.823484: step: 2040/529, loss: 0.0001393989659845829
2023-01-22 21:14:30.944758: step: 2044/529, loss: 0.00012857021647505462
2023-01-22 21:14:32.067100: step: 2048/529, loss: 0.0010407324880361557
2023-01-22 21:14:33.169597: step: 2052/529, loss: 0.003112394129857421
2023-01-22 21:14:34.278914: step: 2056/529, loss: 0.001054321532137692
2023-01-22 21:14:35.418856: step: 2060/529, loss: 0.0043740528635680676
2023-01-22 21:14:36.519328: step: 2064/529, loss: 0.004248266573995352
2023-01-22 21:14:37.667634: step: 2068/529, loss: 0.0008075248915702105
2023-01-22 21:14:38.778246: step: 2072/529, loss: 0.007001884281635284
2023-01-22 21:14:39.878506: step: 2076/529, loss: 4.380242171464488e-05
2023-01-22 21:14:40.979466: step: 2080/529, loss: 0.011050237342715263
2023-01-22 21:14:42.093657: step: 2084/529, loss: 0.004162667319178581
2023-01-22 21:14:43.182267: step: 2088/529, loss: 0.0002774244057945907
2023-01-22 21:14:44.287989: step: 2092/529, loss: 0.0007167458534240723
2023-01-22 21:14:45.429259: step: 2096/529, loss: 0.0033906185999512672
2023-01-22 21:14:46.517521: step: 2100/529, loss: 0.0011811114381998777
2023-01-22 21:14:47.613148: step: 2104/529, loss: 9.449777280678973e-05
2023-01-22 21:14:48.711190: step: 2108/529, loss: 0.007078575436025858
2023-01-22 21:14:49.855130: step: 2112/529, loss: 0.00020052571198903024
2023-01-22 21:14:50.962035: step: 2116/529, loss: 0.0016548684798181057
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3319153667214012, 'r': 0.32876626457034425, 'f1': 0.33033331063597987}, 'combined': 0.2434034920475641, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3745876074704936, 'r': 0.29863136817405034, 'f1': 0.3323245890770049}, 'combined': 0.2042580401156225, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3365406040038393, 'r': 0.34867394646318073, 'f1': 0.3424998504866659}, 'combined': 0.25236831088491174, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.35838453884360044, 'r': 0.3111796429127276, 'f1': 0.33311809640193657}, 'combined': 0.20474575681289758, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3389900638851198, 'r': 0.3447792680121902, 'f1': 0.34186015849938706}, 'combined': 0.2518969588942852, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.3687801739459483, 'r': 0.299494201871255, 'f1': 0.330545440192355}, 'combined': 0.20416041894233694, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35344827586206895, 'r': 0.44565217391304346, 'f1': 0.3942307692307692}, 'combined': 0.1971153846153846, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5833333333333334, 'r': 0.2413793103448276, 'f1': 0.34146341463414637}, 'combined': 0.22764227642276424, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.33496141764545206, 'r': 0.3324190159934942, 'f1': 0.3336853741496599}, 'combined': 0.24587343358395988, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.3697192628494092, 'r': 0.29603171479450097, 'f1': 0.32879749650900303}, 'combined': 0.20209016858602136, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3355263157894737, 'r': 0.36428571428571427, 'f1': 0.34931506849315064}, 'combined': 0.23287671232876708, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3328491977009508, 'r': 0.3517969698660903, 'f1': 0.3420608913642612}, 'combined': 0.25204486732103454, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.8513513513513513, 'r': 0.48091603053435117, 'f1': 0.6146341463414634}, 'slot': {'p': 0.34897086155180335, 'r': 0.30814671396991994, 'f1': 0.3272906653670387}, 'combined': 0.2011640187133994, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.36666666666666664, 'r': 0.4782608695652174, 'f1': 0.41509433962264153}, 'combined': 0.20754716981132076, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.34277424810961393, 'r': 0.34667680121902134, 'f1': 0.34471447970268726}, 'combined': 0.25400014293882217, 'stategy': 1, 'epoch': 4}
Test for Russian: {'template': {'p': 0.863013698630137, 'r': 0.48091603053435117, 'f1': 0.6176470588235295}, 'slot': {'p': 0.36490480593521823, 'r': 0.2960309984080515, 'f1': 0.32687935292667253}, 'combined': 0.2018960709252978, 'stategy': 1, 'epoch': 4}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.6363636363636364, 'r': 0.2413793103448276, 'f1': 0.35}, 'combined': 0.2333333333333333, 'stategy': 1, 'epoch': 4}