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 14:43:25.523594: step: 4/529, loss: 0.036906637251377106
2023-01-22 14:43:26.594968: step: 8/529, loss: 0.0621248222887516
2023-01-22 14:43:27.652875: step: 12/529, loss: 0.02300257608294487
2023-01-22 14:43:28.723150: step: 16/529, loss: 0.021292800083756447
2023-01-22 14:43:29.784678: step: 20/529, loss: 0.019287262111902237
2023-01-22 14:43:30.845408: step: 24/529, loss: 0.014699488878250122
2023-01-22 14:43:31.902640: step: 28/529, loss: 0.05607492849230766
2023-01-22 14:43:32.969605: step: 32/529, loss: 0.02246081829071045
2023-01-22 14:43:34.040183: step: 36/529, loss: 0.013310117647051811
2023-01-22 14:43:35.097505: step: 40/529, loss: 0.02030652016401291
2023-01-22 14:43:36.153005: step: 44/529, loss: 0.04427490010857582
2023-01-22 14:43:37.202172: step: 48/529, loss: 0.06931335479021072
2023-01-22 14:43:38.280854: step: 52/529, loss: 0.019074495881795883
2023-01-22 14:43:39.335212: step: 56/529, loss: 0.015496532432734966
2023-01-22 14:43:40.406425: step: 60/529, loss: 0.01601226255297661
2023-01-22 14:43:41.465278: step: 64/529, loss: 0.011658409610390663
2023-01-22 14:43:42.537104: step: 68/529, loss: 0.06258019059896469
2023-01-22 14:43:43.597526: step: 72/529, loss: 0.025525854900479317
2023-01-22 14:43:44.644618: step: 76/529, loss: 0.014389489777386189
2023-01-22 14:43:45.694383: step: 80/529, loss: 0.011208429001271725
2023-01-22 14:43:46.751602: step: 84/529, loss: 0.04706929996609688
2023-01-22 14:43:47.817897: step: 88/529, loss: 0.02508408948779106
2023-01-22 14:43:48.879042: step: 92/529, loss: 0.02566348947584629
2023-01-22 14:43:49.963039: step: 96/529, loss: 0.021056417375802994
2023-01-22 14:43:51.032136: step: 100/529, loss: 0.020041653886437416
2023-01-22 14:43:52.097569: step: 104/529, loss: 0.008005469106137753
2023-01-22 14:43:53.155513: step: 108/529, loss: 0.020515985786914825
2023-01-22 14:43:54.205791: step: 112/529, loss: 0.0
2023-01-22 14:43:55.283338: step: 116/529, loss: 0.020652977749705315
2023-01-22 14:43:56.363906: step: 120/529, loss: 0.01828337460756302
2023-01-22 14:43:57.422604: step: 124/529, loss: 0.018345335498452187
2023-01-22 14:43:58.499332: step: 128/529, loss: 0.01574639417231083
2023-01-22 14:43:59.558594: step: 132/529, loss: 0.05731136351823807
2023-01-22 14:44:00.642399: step: 136/529, loss: 0.011213736608624458
2023-01-22 14:44:01.703302: step: 140/529, loss: 0.013642799109220505
2023-01-22 14:44:02.768916: step: 144/529, loss: 0.02615521103143692
2023-01-22 14:44:03.832614: step: 148/529, loss: 0.028597723692655563
2023-01-22 14:44:04.900279: step: 152/529, loss: 0.07758909463882446
2023-01-22 14:44:05.957551: step: 156/529, loss: 0.032660774886608124
2023-01-22 14:44:07.011936: step: 160/529, loss: 0.010725762695074081
2023-01-22 14:44:08.094469: step: 164/529, loss: 0.08858466893434525
2023-01-22 14:44:09.160319: step: 168/529, loss: 0.015186084434390068
2023-01-22 14:44:10.218364: step: 172/529, loss: 0.04659134894609451
2023-01-22 14:44:11.284617: step: 176/529, loss: 0.024690069258213043
2023-01-22 14:44:12.369753: step: 180/529, loss: 0.04203398898243904
2023-01-22 14:44:13.425772: step: 184/529, loss: 0.014550302177667618
2023-01-22 14:44:14.509482: step: 188/529, loss: 0.021250847727060318
2023-01-22 14:44:15.588449: step: 192/529, loss: 0.008041131310164928
2023-01-22 14:44:16.663018: step: 196/529, loss: 0.017589721828699112
2023-01-22 14:44:17.745944: step: 200/529, loss: 0.05970647558569908
2023-01-22 14:44:18.817799: step: 204/529, loss: 0.010688910260796547
2023-01-22 14:44:19.894906: step: 208/529, loss: 0.05130859836935997
2023-01-22 14:44:20.968020: step: 212/529, loss: 0.008765791542828083
2023-01-22 14:44:22.036216: step: 216/529, loss: 0.014925209805369377
2023-01-22 14:44:23.104503: step: 220/529, loss: 0.04095502570271492
2023-01-22 14:44:24.158044: step: 224/529, loss: 0.006114865653216839
2023-01-22 14:44:25.229080: step: 228/529, loss: 0.01627984270453453
2023-01-22 14:44:26.305619: step: 232/529, loss: 0.017671987414360046
2023-01-22 14:44:27.392222: step: 236/529, loss: 0.015359263867139816
2023-01-22 14:44:28.450414: step: 240/529, loss: 0.05051518976688385
2023-01-22 14:44:29.522643: step: 244/529, loss: 0.023071138188242912
2023-01-22 14:44:30.588634: step: 248/529, loss: 0.014023618772625923
2023-01-22 14:44:31.677888: step: 252/529, loss: 0.009916102513670921
2023-01-22 14:44:32.772684: step: 256/529, loss: 0.04910624772310257
2023-01-22 14:44:33.835491: step: 260/529, loss: 0.01754813827574253
2023-01-22 14:44:34.914702: step: 264/529, loss: 0.009435590356588364
2023-01-22 14:44:35.993959: step: 268/529, loss: 0.013928825967013836
2023-01-22 14:44:37.058754: step: 272/529, loss: 0.011481163091957569
2023-01-22 14:44:38.135681: step: 276/529, loss: 0.10326572507619858
2023-01-22 14:44:39.214691: step: 280/529, loss: 0.04917379841208458
2023-01-22 14:44:40.279270: step: 284/529, loss: 0.021951744332909584
2023-01-22 14:44:41.353978: step: 288/529, loss: 0.021210145205259323
2023-01-22 14:44:42.423362: step: 292/529, loss: 0.016783222556114197
2023-01-22 14:44:43.516976: step: 296/529, loss: 0.01707283779978752
2023-01-22 14:44:44.600217: step: 300/529, loss: 0.01796027459204197
2023-01-22 14:44:45.674119: step: 304/529, loss: 0.036726683378219604
2023-01-22 14:44:46.730851: step: 308/529, loss: 0.00756659172475338
2023-01-22 14:44:47.810196: step: 312/529, loss: 0.010935730300843716
2023-01-22 14:44:48.872442: step: 316/529, loss: 0.004954290110617876
2023-01-22 14:44:49.960697: step: 320/529, loss: 0.012793033383786678
2023-01-22 14:44:51.034591: step: 324/529, loss: 0.021430062130093575
2023-01-22 14:44:52.114211: step: 328/529, loss: 0.0345136933028698
2023-01-22 14:44:53.197252: step: 332/529, loss: 0.007490217220038176
2023-01-22 14:44:54.259245: step: 336/529, loss: 0.024818042293190956
2023-01-22 14:44:55.350055: step: 340/529, loss: 0.04161607474088669
2023-01-22 14:44:56.425026: step: 344/529, loss: 0.06896219402551651
2023-01-22 14:44:57.499951: step: 348/529, loss: 0.04392163082957268
2023-01-22 14:44:58.581819: step: 352/529, loss: 0.006646931637078524
2023-01-22 14:44:59.645116: step: 356/529, loss: 0.0
2023-01-22 14:45:00.735763: step: 360/529, loss: 0.012845569290220737
2023-01-22 14:45:01.820633: step: 364/529, loss: 0.00917950738221407
2023-01-22 14:45:02.885439: step: 368/529, loss: 0.04632199555635452
2023-01-22 14:45:03.961339: step: 372/529, loss: 0.07200482487678528
2023-01-22 14:45:05.028890: step: 376/529, loss: 0.041902121156454086
2023-01-22 14:45:06.109000: step: 380/529, loss: 0.008073313161730766
2023-01-22 14:45:07.177124: step: 384/529, loss: 0.009958234615623951
2023-01-22 14:45:08.241388: step: 388/529, loss: 0.012584754265844822
2023-01-22 14:45:09.338320: step: 392/529, loss: 0.06030331179499626
2023-01-22 14:45:10.418249: step: 396/529, loss: 0.00962952058762312
2023-01-22 14:45:11.487176: step: 400/529, loss: 0.013606185093522072
2023-01-22 14:45:12.555842: step: 404/529, loss: 0.012179278768599033
2023-01-22 14:45:13.631875: step: 408/529, loss: 0.017199020832777023
2023-01-22 14:45:14.725818: step: 412/529, loss: 0.060847386717796326
2023-01-22 14:45:15.811628: step: 416/529, loss: 0.010868166573345661
2023-01-22 14:45:16.887100: step: 420/529, loss: 0.0400981530547142
2023-01-22 14:45:17.955314: step: 424/529, loss: 0.010132329538464546
2023-01-22 14:45:19.016500: step: 428/529, loss: 0.017198748886585236
2023-01-22 14:45:20.084832: step: 432/529, loss: 0.013414408080279827
2023-01-22 14:45:21.174117: step: 436/529, loss: 0.01622629351913929
2023-01-22 14:45:22.241890: step: 440/529, loss: 0.011021781712770462
2023-01-22 14:45:23.314758: step: 444/529, loss: 0.016030149534344673
2023-01-22 14:45:24.400541: step: 448/529, loss: 0.05198883265256882
2023-01-22 14:45:25.497243: step: 452/529, loss: 0.031469158828258514
2023-01-22 14:45:26.568426: step: 456/529, loss: 0.014572232030332088
2023-01-22 14:45:27.665223: step: 460/529, loss: 0.011517726816236973
2023-01-22 14:45:28.744882: step: 464/529, loss: 0.040690720081329346
2023-01-22 14:45:29.823650: step: 468/529, loss: 0.018083972856402397
2023-01-22 14:45:30.920416: step: 472/529, loss: 0.047869883477687836
2023-01-22 14:45:32.001890: step: 476/529, loss: 0.036852624267339706
2023-01-22 14:45:33.096587: step: 480/529, loss: 0.024334874004125595
2023-01-22 14:45:34.170588: step: 484/529, loss: 0.011195872910320759
2023-01-22 14:45:35.256550: step: 488/529, loss: 0.010092330165207386
2023-01-22 14:45:36.334451: step: 492/529, loss: 0.014725054614245892
2023-01-22 14:45:37.408244: step: 496/529, loss: 0.010978207923471928
2023-01-22 14:45:38.485155: step: 500/529, loss: 0.04949723556637764
2023-01-22 14:45:39.560490: step: 504/529, loss: 0.039471693336963654
2023-01-22 14:45:40.645882: step: 508/529, loss: 0.008636035025119781
2023-01-22 14:45:41.736864: step: 512/529, loss: 0.05558284372091293
2023-01-22 14:45:42.829413: step: 516/529, loss: 0.024330083280801773
2023-01-22 14:45:43.939602: step: 520/529, loss: 0.020511817187070847
2023-01-22 14:45:45.024302: step: 524/529, loss: 0.01563498005270958
2023-01-22 14:45:46.101849: step: 528/529, loss: 0.04201168939471245
2023-01-22 14:45:47.198879: step: 532/529, loss: 0.012389475479722023
2023-01-22 14:45:48.284214: step: 536/529, loss: 0.006306052673608065
2023-01-22 14:45:49.368048: step: 540/529, loss: 0.027361616492271423
2023-01-22 14:45:50.458194: step: 544/529, loss: 0.00941076036542654
2023-01-22 14:45:51.550948: step: 548/529, loss: 0.049970827996730804
2023-01-22 14:45:52.615782: step: 552/529, loss: 0.008651609532535076
2023-01-22 14:45:53.689253: step: 556/529, loss: 0.010524558834731579
2023-01-22 14:45:54.767608: step: 560/529, loss: 0.048365574330091476
2023-01-22 14:45:55.858782: step: 564/529, loss: 0.002411904511973262
2023-01-22 14:45:56.944652: step: 568/529, loss: 0.007765104994177818
2023-01-22 14:45:58.022067: step: 572/529, loss: 0.050128962844610214
2023-01-22 14:45:59.100564: step: 576/529, loss: 0.035054419189691544
2023-01-22 14:46:00.177019: step: 580/529, loss: 0.0769512727856636
2023-01-22 14:46:01.253954: step: 584/529, loss: 0.058283016085624695
2023-01-22 14:46:02.342629: step: 588/529, loss: 0.012656567618250847
2023-01-22 14:46:03.429140: step: 592/529, loss: 0.009634032845497131
2023-01-22 14:46:04.506661: step: 596/529, loss: 0.030522329732775688
2023-01-22 14:46:05.595870: step: 600/529, loss: 0.010691116563975811
2023-01-22 14:46:06.686981: step: 604/529, loss: 0.011345036327838898
2023-01-22 14:46:07.768784: step: 608/529, loss: 0.015001209452748299
2023-01-22 14:46:08.843682: step: 612/529, loss: 0.04308963567018509
2023-01-22 14:46:09.937482: step: 616/529, loss: 0.04435019567608833
2023-01-22 14:46:11.012523: step: 620/529, loss: 0.05402511730790138
2023-01-22 14:46:12.094220: step: 624/529, loss: 0.03840957209467888
2023-01-22 14:46:13.189775: step: 628/529, loss: 0.008532053790986538
2023-01-22 14:46:14.270187: step: 632/529, loss: 0.04640606790781021
2023-01-22 14:46:15.353351: step: 636/529, loss: 0.015516658313572407
2023-01-22 14:46:16.439690: step: 640/529, loss: 0.048128049820661545
2023-01-22 14:46:17.526349: step: 644/529, loss: 0.023092491552233696
2023-01-22 14:46:18.606922: step: 648/529, loss: 0.0109193604439497
2023-01-22 14:46:19.679567: step: 652/529, loss: 0.039670784026384354
2023-01-22 14:46:20.774381: step: 656/529, loss: 0.024215450510382652
2023-01-22 14:46:21.852406: step: 660/529, loss: 0.07807125896215439
2023-01-22 14:46:22.931889: step: 664/529, loss: 0.04490305855870247
2023-01-22 14:46:24.031408: step: 668/529, loss: 0.010400510393083096
2023-01-22 14:46:25.120466: step: 672/529, loss: 0.018645433709025383
2023-01-22 14:46:26.186669: step: 676/529, loss: 0.041870374232530594
2023-01-22 14:46:27.257604: step: 680/529, loss: 0.09524698555469513
2023-01-22 14:46:28.325552: step: 684/529, loss: 0.0345437191426754
2023-01-22 14:46:29.408633: step: 688/529, loss: 0.014123331755399704
2023-01-22 14:46:30.483844: step: 692/529, loss: 0.013536249287426472
2023-01-22 14:46:31.559850: step: 696/529, loss: 0.009395051747560501
2023-01-22 14:46:32.643003: step: 700/529, loss: 0.012241140939295292
2023-01-22 14:46:33.712752: step: 704/529, loss: 0.01093914732336998
2023-01-22 14:46:34.786115: step: 708/529, loss: 0.029698064550757408
2023-01-22 14:46:35.875736: step: 712/529, loss: 0.012869570404291153
2023-01-22 14:46:36.972200: step: 716/529, loss: 0.009240290150046349
2023-01-22 14:46:38.053480: step: 720/529, loss: 0.0075867632403969765
2023-01-22 14:46:39.142746: step: 724/529, loss: 0.01640930399298668
2023-01-22 14:46:40.229962: step: 728/529, loss: 0.00956727284938097
2023-01-22 14:46:41.327203: step: 732/529, loss: 0.007887667044997215
2023-01-22 14:46:42.412719: step: 736/529, loss: 0.01039630826562643
2023-01-22 14:46:43.495656: step: 740/529, loss: 0.013838459737598896
2023-01-22 14:46:44.579622: step: 744/529, loss: 0.05541898310184479
2023-01-22 14:46:45.649621: step: 748/529, loss: 0.013446134515106678
2023-01-22 14:46:46.732436: step: 752/529, loss: 0.048116616904735565
2023-01-22 14:46:47.817050: step: 756/529, loss: 0.006654263474047184
2023-01-22 14:46:48.903458: step: 760/529, loss: 0.014451884664595127
2023-01-22 14:46:49.974043: step: 764/529, loss: 0.0052962410263717175
2023-01-22 14:46:51.053506: step: 768/529, loss: 0.0028691133484244347
2023-01-22 14:46:52.145680: step: 772/529, loss: 0.010828969068825245
2023-01-22 14:46:53.236594: step: 776/529, loss: 0.01071922481060028
2023-01-22 14:46:54.316622: step: 780/529, loss: 0.012221409007906914
2023-01-22 14:46:55.400502: step: 784/529, loss: 0.03381427004933357
2023-01-22 14:46:56.487746: step: 788/529, loss: 0.013468189164996147
2023-01-22 14:46:57.560355: step: 792/529, loss: 0.02683264948427677
2023-01-22 14:46:58.641123: step: 796/529, loss: 0.014051465317606926
2023-01-22 14:46:59.732313: step: 800/529, loss: 0.008052659220993519
2023-01-22 14:47:00.823122: step: 804/529, loss: 0.02756400965154171
2023-01-22 14:47:01.906032: step: 808/529, loss: 0.011081838980317116
2023-01-22 14:47:02.995905: step: 812/529, loss: 0.030933188274502754
2023-01-22 14:47:04.084050: step: 816/529, loss: 0.04143639653921127
2023-01-22 14:47:05.158828: step: 820/529, loss: 0.04699551314115524
2023-01-22 14:47:06.263023: step: 824/529, loss: 0.009988164529204369
2023-01-22 14:47:07.360599: step: 828/529, loss: 0.04094613343477249
2023-01-22 14:47:08.454349: step: 832/529, loss: 0.008815049193799496
2023-01-22 14:47:09.534282: step: 836/529, loss: 0.0246005579829216
2023-01-22 14:47:10.621966: step: 840/529, loss: 0.008881958201527596
2023-01-22 14:47:11.698661: step: 844/529, loss: 0.005901203956454992
2023-01-22 14:47:12.770039: step: 848/529, loss: 0.009790322743356228
2023-01-22 14:47:13.857034: step: 852/529, loss: 0.0077022346667945385
2023-01-22 14:47:14.951370: step: 856/529, loss: 0.01971416361629963
2023-01-22 14:47:16.016664: step: 860/529, loss: 0.012111751362681389
2023-01-22 14:47:17.087564: step: 864/529, loss: 0.008319082669913769
2023-01-22 14:47:18.150514: step: 868/529, loss: 0.008041729219257832
2023-01-22 14:47:19.228678: step: 872/529, loss: 0.009349256753921509
2023-01-22 14:47:20.319617: step: 876/529, loss: 0.010881714522838593
2023-01-22 14:47:21.382634: step: 880/529, loss: 0.0036121136508882046
2023-01-22 14:47:22.489137: step: 884/529, loss: 0.04462500289082527
2023-01-22 14:47:23.562546: step: 888/529, loss: 0.014002700336277485
2023-01-22 14:47:24.639183: step: 892/529, loss: 0.009989199228584766
2023-01-22 14:47:25.720072: step: 896/529, loss: 0.008908821269869804
2023-01-22 14:47:26.805617: step: 900/529, loss: 0.011485452763736248
2023-01-22 14:47:27.872311: step: 904/529, loss: 0.01944391056895256
2023-01-22 14:47:28.941675: step: 908/529, loss: 0.03485608100891113
2023-01-22 14:47:30.018765: step: 912/529, loss: 0.03305096551775932
2023-01-22 14:47:31.094212: step: 916/529, loss: 0.007312651723623276
2023-01-22 14:47:32.164465: step: 920/529, loss: 0.013770959340035915
2023-01-22 14:47:33.248217: step: 924/529, loss: 0.05728096887469292
2023-01-22 14:47:34.352394: step: 928/529, loss: 0.020198343321681023
2023-01-22 14:47:35.419497: step: 932/529, loss: 0.01897631399333477
2023-01-22 14:47:36.487832: step: 936/529, loss: 0.010871518403291702
2023-01-22 14:47:37.566220: step: 940/529, loss: 0.03519846871495247
2023-01-22 14:47:38.661180: step: 944/529, loss: 0.01631801947951317
2023-01-22 14:47:39.727427: step: 948/529, loss: 0.006152381654828787
2023-01-22 14:47:40.792850: step: 952/529, loss: 0.006907373666763306
2023-01-22 14:47:41.881952: step: 956/529, loss: 0.007043652702122927
2023-01-22 14:47:42.959803: step: 960/529, loss: 0.025328710675239563
2023-01-22 14:47:44.027824: step: 964/529, loss: 0.020681828260421753
2023-01-22 14:47:45.096715: step: 968/529, loss: 0.03203994035720825
2023-01-22 14:47:46.163954: step: 972/529, loss: 0.004437461961060762
2023-01-22 14:47:47.240309: step: 976/529, loss: 0.007767890114337206
2023-01-22 14:47:48.312433: step: 980/529, loss: 0.03811563923954964
2023-01-22 14:47:49.367249: step: 984/529, loss: 0.014742046594619751
2023-01-22 14:47:50.434488: step: 988/529, loss: 0.00966726616024971
2023-01-22 14:47:51.515018: step: 992/529, loss: 0.011935340240597725
2023-01-22 14:47:52.593593: step: 996/529, loss: 0.033202216029167175
2023-01-22 14:47:53.675602: step: 1000/529, loss: 0.008478621952235699
2023-01-22 14:47:54.750651: step: 1004/529, loss: 0.023013152182102203
2023-01-22 14:47:55.845909: step: 1008/529, loss: 0.006438667420297861
2023-01-22 14:47:56.923031: step: 1012/529, loss: 0.03475933521986008
2023-01-22 14:47:58.002077: step: 1016/529, loss: 0.0068849120289087296
2023-01-22 14:47:59.092021: step: 1020/529, loss: 0.04339052364230156
2023-01-22 14:48:00.166803: step: 1024/529, loss: 0.010688281618058681
2023-01-22 14:48:01.234699: step: 1028/529, loss: 0.01973528042435646
2023-01-22 14:48:02.306035: step: 1032/529, loss: 0.01425983291119337
2023-01-22 14:48:03.382011: step: 1036/529, loss: 0.016061833128333092
2023-01-22 14:48:04.447774: step: 1040/529, loss: 0.010656836442649364
2023-01-22 14:48:05.508926: step: 1044/529, loss: 0.029521167278289795
2023-01-22 14:48:06.573053: step: 1048/529, loss: 0.018340887501835823
2023-01-22 14:48:07.632286: step: 1052/529, loss: 0.048236045986413956
2023-01-22 14:48:08.708173: step: 1056/529, loss: 0.004470358602702618
2023-01-22 14:48:09.783601: step: 1060/529, loss: 0.01605336181819439
2023-01-22 14:48:10.861858: step: 1064/529, loss: 0.014046620577573776
2023-01-22 14:48:11.922724: step: 1068/529, loss: 0.014131884090602398
2023-01-22 14:48:12.988371: step: 1072/529, loss: 0.02307000197470188
2023-01-22 14:48:14.059625: step: 1076/529, loss: 0.06608673185110092
2023-01-22 14:48:15.132405: step: 1080/529, loss: 0.007001555059105158
2023-01-22 14:48:16.231140: step: 1084/529, loss: 0.01940244808793068
2023-01-22 14:48:17.327961: step: 1088/529, loss: 0.010441668331623077
2023-01-22 14:48:18.411707: step: 1092/529, loss: 0.008033023215830326
2023-01-22 14:48:19.488861: step: 1096/529, loss: 0.03955061733722687
2023-01-22 14:48:20.576047: step: 1100/529, loss: 0.043457262217998505
2023-01-22 14:48:21.634644: step: 1104/529, loss: 0.04453654587268829
2023-01-22 14:48:22.709466: step: 1108/529, loss: 0.020859340205788612
2023-01-22 14:48:23.770344: step: 1112/529, loss: 0.009554127231240273
2023-01-22 14:48:24.828552: step: 1116/529, loss: 0.06352561712265015
2023-01-22 14:48:25.886607: step: 1120/529, loss: 0.012546413578093052
2023-01-22 14:48:26.951605: step: 1124/529, loss: 0.00781959481537342
2023-01-22 14:48:28.021322: step: 1128/529, loss: 0.018820233643054962
2023-01-22 14:48:29.089668: step: 1132/529, loss: 0.039390288293361664
2023-01-22 14:48:30.170340: step: 1136/529, loss: 0.03650328144431114
2023-01-22 14:48:31.246373: step: 1140/529, loss: 0.04654746130108833
2023-01-22 14:48:32.309267: step: 1144/529, loss: 0.019812630489468575
2023-01-22 14:48:33.358060: step: 1148/529, loss: 0.011509333737194538
2023-01-22 14:48:34.429740: step: 1152/529, loss: 0.007650483399629593
2023-01-22 14:48:35.486622: step: 1156/529, loss: 0.014886134304106236
2023-01-22 14:48:36.570082: step: 1160/529, loss: 0.05990464612841606
2023-01-22 14:48:37.643643: step: 1164/529, loss: 0.039350491017103195
2023-01-22 14:48:38.709823: step: 1168/529, loss: 0.00626153452321887
2023-01-22 14:48:39.781911: step: 1172/529, loss: 0.009320780634880066
2023-01-22 14:48:40.837652: step: 1176/529, loss: 0.0134690897539258
2023-01-22 14:48:41.910241: step: 1180/529, loss: 0.008416729979217052
2023-01-22 14:48:42.974160: step: 1184/529, loss: 0.04894373193383217
2023-01-22 14:48:44.048370: step: 1188/529, loss: 0.022580036893486977
2023-01-22 14:48:45.137496: step: 1192/529, loss: 0.0033554767724126577
2023-01-22 14:48:46.208069: step: 1196/529, loss: 0.0164506733417511
2023-01-22 14:48:47.298474: step: 1200/529, loss: 0.012273762375116348
2023-01-22 14:48:48.373002: step: 1204/529, loss: 0.06385210156440735
2023-01-22 14:48:49.431847: step: 1208/529, loss: 0.003882566699758172
2023-01-22 14:48:50.503056: step: 1212/529, loss: 0.03736743703484535
2023-01-22 14:48:51.566003: step: 1216/529, loss: 0.007969222031533718
2023-01-22 14:48:52.644374: step: 1220/529, loss: 0.030050775036215782
2023-01-22 14:48:53.713656: step: 1224/529, loss: 0.03377442806959152
2023-01-22 14:48:54.788972: step: 1228/529, loss: 0.008897541090846062
2023-01-22 14:48:55.857084: step: 1232/529, loss: 0.03691292926669121
2023-01-22 14:48:56.963254: step: 1236/529, loss: 0.01646624505519867
2023-01-22 14:48:58.054793: step: 1240/529, loss: 0.02995854802429676
2023-01-22 14:48:59.133454: step: 1244/529, loss: 0.03402078151702881
2023-01-22 14:49:00.193749: step: 1248/529, loss: 0.01780552603304386
2023-01-22 14:49:01.291737: step: 1252/529, loss: 0.009463814087212086
2023-01-22 14:49:02.358690: step: 1256/529, loss: 0.010619205422699451
2023-01-22 14:49:03.420046: step: 1260/529, loss: 0.012928532436490059
2023-01-22 14:49:04.497323: step: 1264/529, loss: 0.009818925522267818
2023-01-22 14:49:05.566766: step: 1268/529, loss: 0.0014176652766764164
2023-01-22 14:49:06.637020: step: 1272/529, loss: 0.01897534541785717
2023-01-22 14:49:07.712318: step: 1276/529, loss: 0.02581171877682209
2023-01-22 14:49:08.802599: step: 1280/529, loss: 0.009975031018257141
2023-01-22 14:49:09.870185: step: 1284/529, loss: 0.03988887742161751
2023-01-22 14:49:10.939256: step: 1288/529, loss: 0.003912187647074461
2023-01-22 14:49:12.026463: step: 1292/529, loss: 0.010445482097566128
2023-01-22 14:49:13.096320: step: 1296/529, loss: 0.016609974205493927
2023-01-22 14:49:14.161748: step: 1300/529, loss: 0.019434276968240738
2023-01-22 14:49:15.225162: step: 1304/529, loss: 0.030209345743060112
2023-01-22 14:49:16.300369: step: 1308/529, loss: 0.03816532343626022
2023-01-22 14:49:17.364564: step: 1312/529, loss: 0.02780003659427166
2023-01-22 14:49:18.430707: step: 1316/529, loss: 0.01622786931693554
2023-01-22 14:49:19.489011: step: 1320/529, loss: 0.011303656734526157
2023-01-22 14:49:20.553947: step: 1324/529, loss: 0.013496220111846924
2023-01-22 14:49:21.620699: step: 1328/529, loss: 0.05611635744571686
2023-01-22 14:49:22.695482: step: 1332/529, loss: 0.047016698867082596
2023-01-22 14:49:23.764970: step: 1336/529, loss: 0.014781685546040535
2023-01-22 14:49:24.837150: step: 1340/529, loss: 0.02529684081673622
2023-01-22 14:49:25.909124: step: 1344/529, loss: 0.04970370978116989
2023-01-22 14:49:26.980553: step: 1348/529, loss: 0.00895818043500185
2023-01-22 14:49:28.050375: step: 1352/529, loss: 0.013945626094937325
2023-01-22 14:49:29.131367: step: 1356/529, loss: 0.01091905776411295
2023-01-22 14:49:30.205469: step: 1360/529, loss: 0.009536290541291237
2023-01-22 14:49:31.274741: step: 1364/529, loss: 0.005469128023833036
2023-01-22 14:49:32.357459: step: 1368/529, loss: 0.013938400894403458
2023-01-22 14:49:33.436895: step: 1372/529, loss: 0.014763103798031807
2023-01-22 14:49:34.496122: step: 1376/529, loss: 0.014497095718979836
2023-01-22 14:49:35.570721: step: 1380/529, loss: 0.01092081144452095
2023-01-22 14:49:36.638203: step: 1384/529, loss: 0.024942563846707344
2023-01-22 14:49:37.701756: step: 1388/529, loss: 0.01457739807665348
2023-01-22 14:49:38.755843: step: 1392/529, loss: 0.004112505353987217
2023-01-22 14:49:39.821000: step: 1396/529, loss: 0.005271682515740395
2023-01-22 14:49:40.875593: step: 1400/529, loss: 0.009081680327653885
2023-01-22 14:49:41.944953: step: 1404/529, loss: 0.018123524263501167
2023-01-22 14:49:43.012617: step: 1408/529, loss: 0.06646265834569931
2023-01-22 14:49:44.088993: step: 1412/529, loss: 0.01829330250620842
2023-01-22 14:49:45.149095: step: 1416/529, loss: 0.014399976469576359
2023-01-22 14:49:46.209687: step: 1420/529, loss: 0.0422513484954834
2023-01-22 14:49:47.266062: step: 1424/529, loss: 0.014533104375004768
2023-01-22 14:49:48.328603: step: 1428/529, loss: 0.003955908119678497
2023-01-22 14:49:49.391197: step: 1432/529, loss: 0.019932806491851807
2023-01-22 14:49:50.483378: step: 1436/529, loss: 0.09128439426422119
2023-01-22 14:49:51.542705: step: 1440/529, loss: 0.009105724282562733
2023-01-22 14:49:52.596221: step: 1444/529, loss: 0.0064781541004776955
2023-01-22 14:49:53.688548: step: 1448/529, loss: 0.004979480989277363
2023-01-22 14:49:54.739795: step: 1452/529, loss: 0.022313237190246582
2023-01-22 14:49:55.793278: step: 1456/529, loss: 0.014171168208122253
2023-01-22 14:49:56.857400: step: 1460/529, loss: 0.012895352207124233
2023-01-22 14:49:57.931940: step: 1464/529, loss: 0.048164334148168564
2023-01-22 14:49:58.992573: step: 1468/529, loss: 0.0479486808180809
2023-01-22 14:50:00.053547: step: 1472/529, loss: 0.009772618301212788
2023-01-22 14:50:01.113482: step: 1476/529, loss: 0.014677603729069233
2023-01-22 14:50:02.185281: step: 1480/529, loss: 0.011042511090636253
2023-01-22 14:50:03.247004: step: 1484/529, loss: 0.02183568850159645
2023-01-22 14:50:04.325286: step: 1488/529, loss: 0.0098685622215271
2023-01-22 14:50:05.410697: step: 1492/529, loss: 0.04448552429676056
2023-01-22 14:50:06.470268: step: 1496/529, loss: 0.012356571853160858
2023-01-22 14:50:07.550858: step: 1500/529, loss: 0.008956319652497768
2023-01-22 14:50:08.616302: step: 1504/529, loss: 0.027506200596690178
2023-01-22 14:50:09.702049: step: 1508/529, loss: 0.03240431100130081
2023-01-22 14:50:10.766353: step: 1512/529, loss: 0.007043669931590557
2023-01-22 14:50:11.829278: step: 1516/529, loss: 0.014196484349668026
2023-01-22 14:50:12.928948: step: 1520/529, loss: 0.03495393320918083
2023-01-22 14:50:14.007951: step: 1524/529, loss: 0.012616559863090515
2023-01-22 14:50:15.077057: step: 1528/529, loss: 0.010927898809313774
2023-01-22 14:50:16.141260: step: 1532/529, loss: 0.015938246622681618
2023-01-22 14:50:17.200801: step: 1536/529, loss: 0.012138689868152142
2023-01-22 14:50:18.262696: step: 1540/529, loss: 0.020071323961019516
2023-01-22 14:50:19.336909: step: 1544/529, loss: 0.010562852025032043
2023-01-22 14:50:20.414291: step: 1548/529, loss: 0.015179213136434555
2023-01-22 14:50:21.480562: step: 1552/529, loss: 0.011046028696000576
2023-01-22 14:50:22.544201: step: 1556/529, loss: 0.023666206747293472
2023-01-22 14:50:23.625351: step: 1560/529, loss: 0.009827623143792152
2023-01-22 14:50:24.695980: step: 1564/529, loss: 0.013244322501122952
2023-01-22 14:50:25.762458: step: 1568/529, loss: 0.006782297044992447
2023-01-22 14:50:26.842189: step: 1572/529, loss: 0.016043927520513535
2023-01-22 14:50:27.914734: step: 1576/529, loss: 0.04864581301808357
2023-01-22 14:50:28.988238: step: 1580/529, loss: 0.011934645473957062
2023-01-22 14:50:30.064968: step: 1584/529, loss: 0.0119180828332901
2023-01-22 14:50:31.141022: step: 1588/529, loss: 0.014821691438555717
2023-01-22 14:50:32.213101: step: 1592/529, loss: 0.019581124186515808
2023-01-22 14:50:33.278526: step: 1596/529, loss: 0.038017239421606064
2023-01-22 14:50:34.360821: step: 1600/529, loss: 0.009091285057365894
2023-01-22 14:50:35.431734: step: 1604/529, loss: 0.010705037042498589
2023-01-22 14:50:36.504659: step: 1608/529, loss: 0.01161727961152792
2023-01-22 14:50:37.573864: step: 1612/529, loss: 0.012504544109106064
2023-01-22 14:50:38.635507: step: 1616/529, loss: 0.01929384469985962
2023-01-22 14:50:39.719878: step: 1620/529, loss: 0.005453450605273247
2023-01-22 14:50:40.818503: step: 1624/529, loss: 0.01647050678730011
2023-01-22 14:50:41.887302: step: 1628/529, loss: 0.02542250044643879
2023-01-22 14:50:42.964276: step: 1632/529, loss: 0.010703759267926216
2023-01-22 14:50:44.036208: step: 1636/529, loss: 0.024750564247369766
2023-01-22 14:50:45.092346: step: 1640/529, loss: 0.019360367208719254
2023-01-22 14:50:46.187374: step: 1644/529, loss: 0.030594654381275177
2023-01-22 14:50:47.271424: step: 1648/529, loss: 0.00952104851603508
2023-01-22 14:50:48.343231: step: 1652/529, loss: 0.008548855781555176
2023-01-22 14:50:49.421452: step: 1656/529, loss: 0.007255463860929012
2023-01-22 14:50:50.482960: step: 1660/529, loss: 0.005405239295214415
2023-01-22 14:50:51.564363: step: 1664/529, loss: 0.011535361409187317
2023-01-22 14:50:52.626564: step: 1668/529, loss: 0.01885666884481907
2023-01-22 14:50:53.705169: step: 1672/529, loss: 0.00498919328674674
2023-01-22 14:50:54.776104: step: 1676/529, loss: 0.014910454861819744
2023-01-22 14:50:55.836760: step: 1680/529, loss: 0.06842447072267532
2023-01-22 14:50:56.910175: step: 1684/529, loss: 0.004844325128942728
2023-01-22 14:50:57.994065: step: 1688/529, loss: 0.018356764689087868
2023-01-22 14:50:59.080364: step: 1692/529, loss: 0.017747139558196068
2023-01-22 14:51:00.159685: step: 1696/529, loss: 0.009090698324143887
2023-01-22 14:51:01.265483: step: 1700/529, loss: 0.008004606701433659
2023-01-22 14:51:02.328015: step: 1704/529, loss: 0.0038984352722764015
2023-01-22 14:51:03.394896: step: 1708/529, loss: 0.01213434524834156
2023-01-22 14:51:04.477273: step: 1712/529, loss: 0.018441416323184967
2023-01-22 14:51:05.549217: step: 1716/529, loss: 0.0013421541079878807
2023-01-22 14:51:06.626030: step: 1720/529, loss: 0.011830998584628105
2023-01-22 14:51:07.702833: step: 1724/529, loss: 0.019219642505049706
2023-01-22 14:51:08.772572: step: 1728/529, loss: 0.08307844400405884
2023-01-22 14:51:09.843822: step: 1732/529, loss: 0.027975892648100853
2023-01-22 14:51:10.921616: step: 1736/529, loss: 0.0045472909696400166
2023-01-22 14:51:11.986571: step: 1740/529, loss: 0.010373634286224842
2023-01-22 14:51:13.077704: step: 1744/529, loss: 0.011059076525270939
2023-01-22 14:51:14.154983: step: 1748/529, loss: 0.011523915454745293
2023-01-22 14:51:15.225669: step: 1752/529, loss: 0.006287896540015936
2023-01-22 14:51:16.288503: step: 1756/529, loss: 0.011118857190012932
2023-01-22 14:51:17.369459: step: 1760/529, loss: 0.013232304714620113
2023-01-22 14:51:18.424975: step: 1764/529, loss: 0.03782587870955467
2023-01-22 14:51:19.494853: step: 1768/529, loss: 0.04864799231290817
2023-01-22 14:51:20.560825: step: 1772/529, loss: 0.01754884421825409
2023-01-22 14:51:21.644041: step: 1776/529, loss: 0.004559441935271025
2023-01-22 14:51:22.728197: step: 1780/529, loss: 0.005559857003390789
2023-01-22 14:51:23.788141: step: 1784/529, loss: 0.00941484235227108
2023-01-22 14:51:24.870376: step: 1788/529, loss: 0.01203937642276287
2023-01-22 14:51:25.935918: step: 1792/529, loss: 0.02942446805536747
2023-01-22 14:51:27.003380: step: 1796/529, loss: 0.027867969125509262
2023-01-22 14:51:28.081230: step: 1800/529, loss: 0.01711081899702549
2023-01-22 14:51:29.152329: step: 1804/529, loss: 0.007564476225525141
2023-01-22 14:51:30.240720: step: 1808/529, loss: 0.0303249042481184
2023-01-22 14:51:31.308638: step: 1812/529, loss: 0.01560313068330288
2023-01-22 14:51:32.390839: step: 1816/529, loss: 0.01105155237019062
2023-01-22 14:51:33.475631: step: 1820/529, loss: 0.026142792776226997
2023-01-22 14:51:34.552404: step: 1824/529, loss: 0.022417457774281502
2023-01-22 14:51:35.610026: step: 1828/529, loss: 0.009239268489181995
2023-01-22 14:51:36.674801: step: 1832/529, loss: 0.016888830810785294
2023-01-22 14:51:37.747342: step: 1836/529, loss: 0.019255323335528374
2023-01-22 14:51:38.800514: step: 1840/529, loss: 0.00810487475246191
2023-01-22 14:51:39.856228: step: 1844/529, loss: 0.008998078294098377
2023-01-22 14:51:40.936874: step: 1848/529, loss: 0.014304356649518013
2023-01-22 14:51:42.012762: step: 1852/529, loss: 0.011611538007855415
2023-01-22 14:51:43.097441: step: 1856/529, loss: 0.015956824645400047
2023-01-22 14:51:44.152883: step: 1860/529, loss: 0.028270462527871132
2023-01-22 14:51:45.212650: step: 1864/529, loss: 0.026612134650349617
2023-01-22 14:51:46.270984: step: 1868/529, loss: 0.00843536015599966
2023-01-22 14:51:47.355258: step: 1872/529, loss: 0.008983597159385681
2023-01-22 14:51:48.419518: step: 1876/529, loss: 0.016142651438713074
2023-01-22 14:51:49.480148: step: 1880/529, loss: 0.03215731680393219
2023-01-22 14:51:50.543159: step: 1884/529, loss: 0.00981141161173582
2023-01-22 14:51:51.606582: step: 1888/529, loss: 0.02600226178765297
2023-01-22 14:51:52.688407: step: 1892/529, loss: 0.006307667586952448
2023-01-22 14:51:53.761750: step: 1896/529, loss: 0.015335206873714924
2023-01-22 14:51:54.872788: step: 1900/529, loss: 0.018125057220458984
2023-01-22 14:51:55.989421: step: 1904/529, loss: 0.0016812998801469803
2023-01-22 14:51:57.074325: step: 1908/529, loss: 0.04461795836687088
2023-01-22 14:51:58.147429: step: 1912/529, loss: 0.010300851427018642
2023-01-22 14:51:59.226582: step: 1916/529, loss: 0.005020210053771734
2023-01-22 14:52:00.305917: step: 1920/529, loss: 0.01172242034226656
2023-01-22 14:52:01.377849: step: 1924/529, loss: 0.012929745018482208
2023-01-22 14:52:02.443177: step: 1928/529, loss: 0.025406766682863235
2023-01-22 14:52:03.534499: step: 1932/529, loss: 0.025732429698109627
2023-01-22 14:52:04.620902: step: 1936/529, loss: 0.0036415972281247377
2023-01-22 14:52:05.683782: step: 1940/529, loss: 0.012167402543127537
2023-01-22 14:52:06.744575: step: 1944/529, loss: 0.0045298305340111256
2023-01-22 14:52:07.809411: step: 1948/529, loss: 0.028993822634220123
2023-01-22 14:52:08.872502: step: 1952/529, loss: 0.007412605918943882
2023-01-22 14:52:09.933166: step: 1956/529, loss: 0.014061648398637772
2023-01-22 14:52:10.999703: step: 1960/529, loss: 0.004360183607786894
2023-01-22 14:52:12.062779: step: 1964/529, loss: 0.021339930593967438
2023-01-22 14:52:13.127649: step: 1968/529, loss: 0.029146555811166763
2023-01-22 14:52:14.195754: step: 1972/529, loss: 0.022972330451011658
2023-01-22 14:52:15.262493: step: 1976/529, loss: 0.011870529502630234
2023-01-22 14:52:16.322234: step: 1980/529, loss: 0.012140263803303242
2023-01-22 14:52:17.381966: step: 1984/529, loss: 0.008505532518029213
2023-01-22 14:52:18.459080: step: 1988/529, loss: 0.01145215891301632
2023-01-22 14:52:19.516291: step: 1992/529, loss: 0.014780446887016296
2023-01-22 14:52:20.578842: step: 1996/529, loss: 0.018030371516942978
2023-01-22 14:52:21.653146: step: 2000/529, loss: 0.005312791559845209
2023-01-22 14:52:22.739968: step: 2004/529, loss: 0.013527121394872665
2023-01-22 14:52:23.805811: step: 2008/529, loss: 0.00816743541508913
2023-01-22 14:52:24.877189: step: 2012/529, loss: 0.009447246789932251
2023-01-22 14:52:25.960925: step: 2016/529, loss: 0.012655762955546379
2023-01-22 14:52:27.038669: step: 2020/529, loss: 0.012693057768046856
2023-01-22 14:52:28.104577: step: 2024/529, loss: 0.02072948031127453
2023-01-22 14:52:29.169476: step: 2028/529, loss: 0.009843254461884499
2023-01-22 14:52:30.240554: step: 2032/529, loss: 0.00949727650731802
2023-01-22 14:52:31.302995: step: 2036/529, loss: 0.007400128059089184
2023-01-22 14:52:32.389151: step: 2040/529, loss: 0.010082544758915901
2023-01-22 14:52:33.473724: step: 2044/529, loss: 0.012053323909640312
2023-01-22 14:52:34.547847: step: 2048/529, loss: 0.008179706521332264
2023-01-22 14:52:35.616089: step: 2052/529, loss: 0.013202308677136898
2023-01-22 14:52:36.696451: step: 2056/529, loss: 0.023810986429452896
2023-01-22 14:52:37.762615: step: 2060/529, loss: 0.010993927717208862
2023-01-22 14:52:38.836989: step: 2064/529, loss: 0.005121553782373667
2023-01-22 14:52:39.896967: step: 2068/529, loss: 0.04755368083715439
2023-01-22 14:52:40.968037: step: 2072/529, loss: 0.06176955997943878
2023-01-22 14:52:42.028190: step: 2076/529, loss: 0.00973560567945242
2023-01-22 14:52:43.120516: step: 2080/529, loss: 0.007067820988595486
2023-01-22 14:52:44.188962: step: 2084/529, loss: 0.011963969096541405
2023-01-22 14:52:45.249673: step: 2088/529, loss: 0.011447635479271412
2023-01-22 14:52:46.320822: step: 2092/529, loss: 0.056180067360401154
2023-01-22 14:52:47.381492: step: 2096/529, loss: 0.005715841893106699
2023-01-22 14:52:48.462654: step: 2100/529, loss: 0.006448804400861263
2023-01-22 14:52:49.540549: step: 2104/529, loss: 0.009625070728361607
2023-01-22 14:52:50.617517: step: 2108/529, loss: 0.012132695876061916
2023-01-22 14:52:51.680154: step: 2112/529, loss: 0.002576471772044897
2023-01-22 14:52:52.747279: step: 2116/529, loss: 0.04353349655866623
==================================================
Loss: 0.021
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3143634840871022, 'r': 0.3561195445920304, 'f1': 0.33394128113879007}, 'combined': 0.24606199662858214, 'stategy': 1, 'epoch': 0}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.29813904649941503, 'r': 0.3000572205118194, 'f1': 0.29909505810065}, 'combined': 0.19526413119524302, 'stategy': 1, 'epoch': 0}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3160625336564351, 'r': 0.3712385357368754, 'f1': 0.3414357911576498}, 'combined': 0.2515842671687946, 'stategy': 1, 'epoch': 0}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3220933527105857, 'r': 0.30521897669541714, 'f1': 0.31342920872544966}, 'combined': 0.20462217771713292, 'stategy': 1, 'epoch': 0}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3059747023809524, 'r': 0.3483582949308756, 'f1': 0.32579382684750924}, 'combined': 0.24005860925605943, 'stategy': 1, 'epoch': 0}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30859371390166324, 'r': 0.31737829161603565, 'f1': 0.31292436357615466}, 'combined': 0.2042925896922046, 'stategy': 1, 'epoch': 0}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29166666666666663, 'r': 0.41666666666666663, 'f1': 0.34313725490196073}, 'combined': 0.2287581699346405, 'stategy': 1, 'epoch': 0}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3409090909090909, 'r': 0.4891304347826087, 'f1': 0.40178571428571425}, 'combined': 0.20089285714285712, 'stategy': 1, 'epoch': 0}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, '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': 0.3143634840871022, 'r': 0.3561195445920304, 'f1': 0.33394128113879007}, 'combined': 0.24606199662858214, 'stategy': 1, 'epoch': 0}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.29813904649941503, 'r': 0.3000572205118194, 'f1': 0.29909505810065}, 'combined': 0.19526413119524302, 'stategy': 1, 'epoch': 0}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29166666666666663, 'r': 0.41666666666666663, 'f1': 0.34313725490196073}, 'combined': 0.2287581699346405, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3160625336564351, 'r': 0.3712385357368754, 'f1': 0.3414357911576498}, 'combined': 0.2515842671687946, 'stategy': 1, 'epoch': 0}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3220933527105857, 'r': 0.30521897669541714, 'f1': 0.31342920872544966}, 'combined': 0.20462217771713292, 'stategy': 1, 'epoch': 0}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3409090909090909, 'r': 0.4891304347826087, 'f1': 0.40178571428571425}, 'combined': 0.20089285714285712, 'stategy': 1, 'epoch': 0}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3059747023809524, 'r': 0.3483582949308756, 'f1': 0.32579382684750924}, 'combined': 0.24005860925605943, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30859371390166324, 'r': 0.31737829161603565, 'f1': 0.31292436357615466}, 'combined': 0.2042925896922046, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, '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 14:55:53.440014: step: 4/529, loss: 0.006389554124325514
2023-01-22 14:55:54.487881: step: 8/529, loss: 0.03755481541156769
2023-01-22 14:55:55.562240: step: 12/529, loss: 0.007507758215069771
2023-01-22 14:55:56.607662: step: 16/529, loss: 0.027793176472187042
2023-01-22 14:55:57.670642: step: 20/529, loss: 0.014019597321748734
2023-01-22 14:55:58.743362: step: 24/529, loss: 0.025989636778831482
2023-01-22 14:55:59.799451: step: 28/529, loss: 0.0033279864583164454
2023-01-22 14:56:00.860341: step: 32/529, loss: 0.007357017602771521
2023-01-22 14:56:01.942269: step: 36/529, loss: 0.0425308533012867
2023-01-22 14:56:03.011007: step: 40/529, loss: 0.005761740263551474
2023-01-22 14:56:04.073716: step: 44/529, loss: 0.007748181466013193
2023-01-22 14:56:05.131472: step: 48/529, loss: 0.011610709130764008
2023-01-22 14:56:06.193563: step: 52/529, loss: 0.006128428038209677
2023-01-22 14:56:07.265340: step: 56/529, loss: 0.011070339009165764
2023-01-22 14:56:08.342056: step: 60/529, loss: 0.013912631198763847
2023-01-22 14:56:09.421266: step: 64/529, loss: 0.008094375021755695
2023-01-22 14:56:10.479718: step: 68/529, loss: 0.009871361777186394
2023-01-22 14:56:11.543930: step: 72/529, loss: 0.006932706106454134
2023-01-22 14:56:12.614916: step: 76/529, loss: 0.006453662179410458
2023-01-22 14:56:13.679471: step: 80/529, loss: 0.00603462615981698
2023-01-22 14:56:14.754139: step: 84/529, loss: 0.0460745170712471
2023-01-22 14:56:15.819840: step: 88/529, loss: 0.008818504400551319
2023-01-22 14:56:16.913535: step: 92/529, loss: 0.006742529571056366
2023-01-22 14:56:17.992366: step: 96/529, loss: 0.009727596305310726
2023-01-22 14:56:19.052730: step: 100/529, loss: 0.009798946790397167
2023-01-22 14:56:20.126735: step: 104/529, loss: 0.016682641580700874
2023-01-22 14:56:21.198124: step: 108/529, loss: 0.010820260271430016
2023-01-22 14:56:22.259807: step: 112/529, loss: 0.0023955171927809715
2023-01-22 14:56:23.329039: step: 116/529, loss: 0.005558701232075691
2023-01-22 14:56:24.397661: step: 120/529, loss: 0.002182362601161003
2023-01-22 14:56:25.462813: step: 124/529, loss: 0.02721530944108963
2023-01-22 14:56:26.537184: step: 128/529, loss: 0.03818333148956299
2023-01-22 14:56:27.600015: step: 132/529, loss: 0.014669663272798061
2023-01-22 14:56:28.655882: step: 136/529, loss: 0.009535056538879871
2023-01-22 14:56:29.739568: step: 140/529, loss: 0.018070055171847343
2023-01-22 14:56:30.793888: step: 144/529, loss: 0.0028326385654509068
2023-01-22 14:56:31.869666: step: 148/529, loss: 0.0418134406208992
2023-01-22 14:56:32.937545: step: 152/529, loss: 0.04009309038519859
2023-01-22 14:56:34.009796: step: 156/529, loss: 0.028574738651514053
2023-01-22 14:56:35.087109: step: 160/529, loss: 0.03564642742276192
2023-01-22 14:56:36.153705: step: 164/529, loss: 0.012470312416553497
2023-01-22 14:56:37.219865: step: 168/529, loss: 0.0017326278612017632
2023-01-22 14:56:38.286578: step: 172/529, loss: 0.005212576128542423
2023-01-22 14:56:39.359255: step: 176/529, loss: 0.012050974182784557
2023-01-22 14:56:40.426717: step: 180/529, loss: 0.00785812083631754
2023-01-22 14:56:41.493450: step: 184/529, loss: 0.06717624515295029
2023-01-22 14:56:42.564489: step: 188/529, loss: 0.008724033832550049
2023-01-22 14:56:43.633796: step: 192/529, loss: 0.019697142764925957
2023-01-22 14:56:44.723091: step: 196/529, loss: 0.006172453984618187
2023-01-22 14:56:45.787721: step: 200/529, loss: 0.014866306446492672
2023-01-22 14:56:46.875906: step: 204/529, loss: 0.052562814205884933
2023-01-22 14:56:47.949411: step: 208/529, loss: 0.00932515412569046
2023-01-22 14:56:49.022998: step: 212/529, loss: 0.011283752508461475
2023-01-22 14:56:50.104875: step: 216/529, loss: 0.007453024387359619
2023-01-22 14:56:51.182268: step: 220/529, loss: 0.007802099920809269
2023-01-22 14:56:52.234599: step: 224/529, loss: 0.008974428288638592
2023-01-22 14:56:53.304933: step: 228/529, loss: 0.014008049853146076
2023-01-22 14:56:54.382404: step: 232/529, loss: 0.032013390213251114
2023-01-22 14:56:55.477380: step: 236/529, loss: 0.007799850776791573
2023-01-22 14:56:56.537052: step: 240/529, loss: 0.006839349400252104
2023-01-22 14:56:57.602181: step: 244/529, loss: 0.01127974409610033
2023-01-22 14:56:58.683779: step: 248/529, loss: 0.005647597834467888
2023-01-22 14:56:59.756316: step: 252/529, loss: 0.007228284142911434
2023-01-22 14:57:00.834067: step: 256/529, loss: 0.008763637393712997
2023-01-22 14:57:01.909816: step: 260/529, loss: 0.009788310155272484
2023-01-22 14:57:02.997192: step: 264/529, loss: 0.009001868776977062
2023-01-22 14:57:04.076535: step: 268/529, loss: 0.01717890240252018
2023-01-22 14:57:05.146754: step: 272/529, loss: 0.011038258671760559
2023-01-22 14:57:06.207953: step: 276/529, loss: 0.04749833419919014
2023-01-22 14:57:07.271054: step: 280/529, loss: 0.0075602903962135315
2023-01-22 14:57:08.343104: step: 284/529, loss: 0.014721144922077656
2023-01-22 14:57:09.433453: step: 288/529, loss: 0.0094086192548275
2023-01-22 14:57:10.517571: step: 292/529, loss: 0.04242559149861336
2023-01-22 14:57:11.575254: step: 296/529, loss: 0.01724233664572239
2023-01-22 14:57:12.646778: step: 300/529, loss: 0.019524725154042244
2023-01-22 14:57:13.723860: step: 304/529, loss: 0.005104272160679102
2023-01-22 14:57:14.795913: step: 308/529, loss: 0.01220310851931572
2023-01-22 14:57:15.885078: step: 312/529, loss: 0.022783854976296425
2023-01-22 14:57:16.966799: step: 316/529, loss: 0.04930324852466583
2023-01-22 14:57:18.044441: step: 320/529, loss: 0.028871264308691025
2023-01-22 14:57:19.115428: step: 324/529, loss: 0.0047592404298484325
2023-01-22 14:57:20.217798: step: 328/529, loss: 0.031854189932346344
2023-01-22 14:57:21.295762: step: 332/529, loss: 0.003642053809016943
2023-01-22 14:57:22.368842: step: 336/529, loss: 0.005386331118643284
2023-01-22 14:57:23.432650: step: 340/529, loss: 0.013746044598519802
2023-01-22 14:57:24.523667: step: 344/529, loss: 0.04910745471715927
2023-01-22 14:57:25.586420: step: 348/529, loss: 0.02622928097844124
2023-01-22 14:57:26.670467: step: 352/529, loss: 0.00903019867837429
2023-01-22 14:57:27.763002: step: 356/529, loss: 0.005778355058282614
2023-01-22 14:57:28.833880: step: 360/529, loss: 0.024011900648474693
2023-01-22 14:57:29.921733: step: 364/529, loss: 0.014881373383104801
2023-01-22 14:57:31.013272: step: 368/529, loss: 0.007700710091739893
2023-01-22 14:57:32.088542: step: 372/529, loss: 0.011685631237924099
2023-01-22 14:57:33.144813: step: 376/529, loss: 0.03502241149544716
2023-01-22 14:57:34.221655: step: 380/529, loss: 0.014022661373019218
2023-01-22 14:57:35.297360: step: 384/529, loss: 0.008072962984442711
2023-01-22 14:57:36.346823: step: 388/529, loss: 0.015174179337918758
2023-01-22 14:57:37.422080: step: 392/529, loss: 0.014057688415050507
2023-01-22 14:57:38.487187: step: 396/529, loss: 0.006233478896319866
2023-01-22 14:57:39.564927: step: 400/529, loss: 0.033747125416994095
2023-01-22 14:57:40.637241: step: 404/529, loss: 0.01181731279939413
2023-01-22 14:57:41.714974: step: 408/529, loss: 0.009264535270631313
2023-01-22 14:57:42.776862: step: 412/529, loss: 0.0316186398267746
2023-01-22 14:57:43.882686: step: 416/529, loss: 0.017516102641820908
2023-01-22 14:57:44.948592: step: 420/529, loss: 0.0
2023-01-22 14:57:46.010432: step: 424/529, loss: 0.0067905536852777
2023-01-22 14:57:47.073427: step: 428/529, loss: 0.01274697482585907
2023-01-22 14:57:48.153274: step: 432/529, loss: 0.014057214371860027
2023-01-22 14:57:49.232647: step: 436/529, loss: 0.010879402048885822
2023-01-22 14:57:50.312789: step: 440/529, loss: 0.0435330756008625
2023-01-22 14:57:51.391519: step: 444/529, loss: 0.0361146405339241
2023-01-22 14:57:52.499443: step: 448/529, loss: 0.025848638266324997
2023-01-22 14:57:53.572873: step: 452/529, loss: 0.03951834514737129
2023-01-22 14:57:54.639995: step: 456/529, loss: 0.03723164275288582
2023-01-22 14:57:55.724041: step: 460/529, loss: 0.03215601295232773
2023-01-22 14:57:56.790360: step: 464/529, loss: 0.02577909082174301
2023-01-22 14:57:57.855549: step: 468/529, loss: 0.02198733203113079
2023-01-22 14:57:58.934335: step: 472/529, loss: 0.009233383461833
2023-01-22 14:57:59.993421: step: 476/529, loss: 0.008173203095793724
2023-01-22 14:58:01.086412: step: 480/529, loss: 0.006877875421196222
2023-01-22 14:58:02.164896: step: 484/529, loss: 0.021933211013674736
2023-01-22 14:58:03.237881: step: 488/529, loss: 0.0135538624599576
2023-01-22 14:58:04.327981: step: 492/529, loss: 0.007879468612372875
2023-01-22 14:58:05.402160: step: 496/529, loss: 0.015126294456422329
2023-01-22 14:58:06.491553: step: 500/529, loss: 0.029508234933018684
2023-01-22 14:58:07.554108: step: 504/529, loss: 0.0085877301171422
2023-01-22 14:58:08.618097: step: 508/529, loss: 0.002188845770433545
2023-01-22 14:58:09.694030: step: 512/529, loss: 0.015549305826425552
2023-01-22 14:58:10.738818: step: 516/529, loss: 0.0
2023-01-22 14:58:11.809195: step: 520/529, loss: 0.008136602118611336
2023-01-22 14:58:12.897487: step: 524/529, loss: 0.021008729934692383
2023-01-22 14:58:13.955205: step: 528/529, loss: 0.02992773801088333
2023-01-22 14:58:15.043482: step: 532/529, loss: 0.018168631941080093
2023-01-22 14:58:16.128320: step: 536/529, loss: 0.028462180867791176
2023-01-22 14:58:17.202545: step: 540/529, loss: 0.01713193953037262
2023-01-22 14:58:18.257298: step: 544/529, loss: 0.005905382800847292
2023-01-22 14:58:19.350288: step: 548/529, loss: 0.007970664650201797
2023-01-22 14:58:20.453381: step: 552/529, loss: 0.011371022090315819
2023-01-22 14:58:21.522285: step: 556/529, loss: 0.0017865701811388135
2023-01-22 14:58:22.590691: step: 560/529, loss: 0.025730127468705177
2023-01-22 14:58:23.660380: step: 564/529, loss: 0.011516742408275604
2023-01-22 14:58:24.735193: step: 568/529, loss: 0.0
2023-01-22 14:58:25.807828: step: 572/529, loss: 0.03642452508211136
2023-01-22 14:58:26.871749: step: 576/529, loss: 0.004339108243584633
2023-01-22 14:58:27.945458: step: 580/529, loss: 0.011853300034999847
2023-01-22 14:58:29.005348: step: 584/529, loss: 0.010838539339601994
2023-01-22 14:58:30.080984: step: 588/529, loss: 0.00917479395866394
2023-01-22 14:58:31.155079: step: 592/529, loss: 0.00919092632830143
2023-01-22 14:58:32.223414: step: 596/529, loss: 0.03562064841389656
2023-01-22 14:58:33.272493: step: 600/529, loss: 0.004526804201304913
2023-01-22 14:58:34.352452: step: 604/529, loss: 0.013805286958813667
2023-01-22 14:58:35.428419: step: 608/529, loss: 0.005685083568096161
2023-01-22 14:58:36.506591: step: 612/529, loss: 0.02160307951271534
2023-01-22 14:58:37.563318: step: 616/529, loss: 0.014341292902827263
2023-01-22 14:58:38.628678: step: 620/529, loss: 0.013234489597380161
2023-01-22 14:58:39.698185: step: 624/529, loss: 0.014834756962954998
2023-01-22 14:58:40.760007: step: 628/529, loss: 0.031487688422203064
2023-01-22 14:58:41.828230: step: 632/529, loss: 0.01619633287191391
2023-01-22 14:58:42.932413: step: 636/529, loss: 0.010047301650047302
2023-01-22 14:58:44.007702: step: 640/529, loss: 0.025032538920640945
2023-01-22 14:58:45.077534: step: 644/529, loss: 0.021785518154501915
2023-01-22 14:58:46.165440: step: 648/529, loss: 0.045387152582407
2023-01-22 14:58:47.275311: step: 652/529, loss: 0.01219183299690485
2023-01-22 14:58:48.351126: step: 656/529, loss: 0.005538894794881344
2023-01-22 14:58:49.431343: step: 660/529, loss: 0.05428878590464592
2023-01-22 14:58:50.492869: step: 664/529, loss: 0.043511323630809784
2023-01-22 14:58:51.606801: step: 668/529, loss: 0.006223185453563929
2023-01-22 14:58:52.664508: step: 672/529, loss: 0.0052870032377541065
2023-01-22 14:58:53.716718: step: 676/529, loss: 0.009733655489981174
2023-01-22 14:58:54.781943: step: 680/529, loss: 0.01350930705666542
2023-01-22 14:58:55.855994: step: 684/529, loss: 0.07173962891101837
2023-01-22 14:58:56.940240: step: 688/529, loss: 0.007063969038426876
2023-01-22 14:58:58.019841: step: 692/529, loss: 0.004214726388454437
2023-01-22 14:58:59.085981: step: 696/529, loss: 0.008578401058912277
2023-01-22 14:59:00.162629: step: 700/529, loss: 0.010689918883144855
2023-01-22 14:59:01.230209: step: 704/529, loss: 0.018659910187125206
2023-01-22 14:59:02.294651: step: 708/529, loss: 0.009841065853834152
2023-01-22 14:59:03.367568: step: 712/529, loss: 0.008847055025398731
2023-01-22 14:59:04.448397: step: 716/529, loss: 0.004942535422742367
2023-01-22 14:59:05.499000: step: 720/529, loss: 0.004865266848355532
2023-01-22 14:59:06.563930: step: 724/529, loss: 0.00932259950786829
2023-01-22 14:59:07.626776: step: 728/529, loss: 0.007701905444264412
2023-01-22 14:59:08.682383: step: 732/529, loss: 0.006199746858328581
2023-01-22 14:59:09.766576: step: 736/529, loss: 0.04192938283085823
2023-01-22 14:59:10.841332: step: 740/529, loss: 0.008602647110819817
2023-01-22 14:59:11.923806: step: 744/529, loss: 0.0036116524133831263
2023-01-22 14:59:13.020660: step: 748/529, loss: 0.005802961066365242
2023-01-22 14:59:14.111170: step: 752/529, loss: 0.03189490735530853
2023-01-22 14:59:15.177409: step: 756/529, loss: 0.010053660720586777
2023-01-22 14:59:16.257201: step: 760/529, loss: 0.02291499264538288
2023-01-22 14:59:17.333000: step: 764/529, loss: 0.019252410158514977
2023-01-22 14:59:18.419000: step: 768/529, loss: 0.027998756617307663
2023-01-22 14:59:19.498097: step: 772/529, loss: 0.01739143207669258
2023-01-22 14:59:20.575231: step: 776/529, loss: 0.058801185339689255
2023-01-22 14:59:21.654824: step: 780/529, loss: 0.0017137709073722363
2023-01-22 14:59:22.728310: step: 784/529, loss: 0.004182151053100824
2023-01-22 14:59:23.792019: step: 788/529, loss: 0.02712380699813366
2023-01-22 14:59:24.869596: step: 792/529, loss: 0.00687322486191988
2023-01-22 14:59:25.947486: step: 796/529, loss: 0.016469301655888557
2023-01-22 14:59:27.016593: step: 800/529, loss: 0.0029740245081484318
2023-01-22 14:59:28.105359: step: 804/529, loss: 0.003832004964351654
2023-01-22 14:59:29.167305: step: 808/529, loss: 0.02452721633017063
2023-01-22 14:59:30.251568: step: 812/529, loss: 0.0071546658873558044
2023-01-22 14:59:31.339402: step: 816/529, loss: 0.009976695291697979
2023-01-22 14:59:32.430866: step: 820/529, loss: 0.04803130775690079
2023-01-22 14:59:33.530437: step: 824/529, loss: 0.0054082116112113
2023-01-22 14:59:34.590251: step: 828/529, loss: 0.01031528227031231
2023-01-22 14:59:35.666513: step: 832/529, loss: 0.009105538949370384
2023-01-22 14:59:36.724878: step: 836/529, loss: 0.017155827954411507
2023-01-22 14:59:37.805382: step: 840/529, loss: 0.0072313230484724045
2023-01-22 14:59:38.904925: step: 844/529, loss: 0.005047089885920286
2023-01-22 14:59:39.967486: step: 848/529, loss: 0.003133185440674424
2023-01-22 14:59:41.043172: step: 852/529, loss: 0.024824628606438637
2023-01-22 14:59:42.111637: step: 856/529, loss: 0.002959504257887602
2023-01-22 14:59:43.186356: step: 860/529, loss: 0.023963922634720802
2023-01-22 14:59:44.275759: step: 864/529, loss: 0.011016862466931343
2023-01-22 14:59:45.343020: step: 868/529, loss: 0.009529675357043743
2023-01-22 14:59:46.415618: step: 872/529, loss: 0.019599657505750656
2023-01-22 14:59:47.484085: step: 876/529, loss: 0.006038099527359009
2023-01-22 14:59:48.546987: step: 880/529, loss: 0.010600242763757706
2023-01-22 14:59:49.624148: step: 884/529, loss: 0.011199026368558407
2023-01-22 14:59:50.708281: step: 888/529, loss: 0.021132322028279305
2023-01-22 14:59:51.771494: step: 892/529, loss: 0.0387236662209034
2023-01-22 14:59:52.857650: step: 896/529, loss: 0.006413321942090988
2023-01-22 14:59:53.938072: step: 900/529, loss: 0.04611104726791382
2023-01-22 14:59:55.012041: step: 904/529, loss: 0.007502878084778786
2023-01-22 14:59:56.081546: step: 908/529, loss: 0.0413038432598114
2023-01-22 14:59:57.162523: step: 912/529, loss: 0.006357306148856878
2023-01-22 14:59:58.247214: step: 916/529, loss: 0.004701308906078339
2023-01-22 14:59:59.326441: step: 920/529, loss: 0.011431719176471233
2023-01-22 15:00:00.396850: step: 924/529, loss: 0.008504052646458149
2023-01-22 15:00:01.457191: step: 928/529, loss: 0.005382700357586145
2023-01-22 15:00:02.525269: step: 932/529, loss: 0.012047774158418179
2023-01-22 15:00:03.591371: step: 936/529, loss: 0.006272532045841217
2023-01-22 15:00:04.665568: step: 940/529, loss: 0.0053003947250545025
2023-01-22 15:00:05.732626: step: 944/529, loss: 0.012830831110477448
2023-01-22 15:00:06.820140: step: 948/529, loss: 0.00279985461384058
2023-01-22 15:00:07.875518: step: 952/529, loss: 0.04484260454773903
2023-01-22 15:00:08.955141: step: 956/529, loss: 0.027535611763596535
2023-01-22 15:00:10.026568: step: 960/529, loss: 0.01332399994134903
2023-01-22 15:00:11.102379: step: 964/529, loss: 0.007254543714225292
2023-01-22 15:00:12.173658: step: 968/529, loss: 0.0031458751764148474
2023-01-22 15:00:13.252752: step: 972/529, loss: 0.006339004263281822
2023-01-22 15:00:14.323220: step: 976/529, loss: 0.019019586965441704
2023-01-22 15:00:15.407463: step: 980/529, loss: 0.004889925941824913
2023-01-22 15:00:16.488151: step: 984/529, loss: 0.02319488115608692
2023-01-22 15:00:17.562316: step: 988/529, loss: 0.011226978152990341
2023-01-22 15:00:18.632483: step: 992/529, loss: 0.0025775248650461435
2023-01-22 15:00:19.692983: step: 996/529, loss: 0.07843223214149475
2023-01-22 15:00:20.780496: step: 1000/529, loss: 0.004787592217326164
2023-01-22 15:00:21.859831: step: 1004/529, loss: 0.009302588179707527
2023-01-22 15:00:22.930461: step: 1008/529, loss: 0.005800108425319195
2023-01-22 15:00:24.017564: step: 1012/529, loss: 0.008581769652664661
2023-01-22 15:00:25.085779: step: 1016/529, loss: 0.011314456351101398
2023-01-22 15:00:26.155447: step: 1020/529, loss: 0.0028924960643053055
2023-01-22 15:00:27.233550: step: 1024/529, loss: 0.008326766081154346
2023-01-22 15:00:28.315562: step: 1028/529, loss: 0.015010037459433079
2023-01-22 15:00:29.389482: step: 1032/529, loss: 0.004664513282477856
2023-01-22 15:00:30.487111: step: 1036/529, loss: 0.009582985192537308
2023-01-22 15:00:31.561629: step: 1040/529, loss: 0.011315559037029743
2023-01-22 15:00:32.654461: step: 1044/529, loss: 0.02792517840862274
2023-01-22 15:00:33.734253: step: 1048/529, loss: 0.002590895164757967
2023-01-22 15:00:34.817144: step: 1052/529, loss: 0.0076039452105760574
2023-01-22 15:00:35.887844: step: 1056/529, loss: 0.01580253429710865
2023-01-22 15:00:36.961176: step: 1060/529, loss: 0.04356185719370842
2023-01-22 15:00:38.043167: step: 1064/529, loss: 0.0076228417456150055
2023-01-22 15:00:39.116554: step: 1068/529, loss: 0.007826216518878937
2023-01-22 15:00:40.189603: step: 1072/529, loss: 0.007501887157559395
2023-01-22 15:00:41.316307: step: 1076/529, loss: 0.018637852743268013
2023-01-22 15:00:42.406552: step: 1080/529, loss: 0.009781665168702602
2023-01-22 15:00:43.496073: step: 1084/529, loss: 0.002811392769217491
2023-01-22 15:00:44.594760: step: 1088/529, loss: 0.009726126678287983
2023-01-22 15:00:45.679292: step: 1092/529, loss: 0.011768890544772148
2023-01-22 15:00:46.754693: step: 1096/529, loss: 0.032852720469236374
2023-01-22 15:00:47.847620: step: 1100/529, loss: 0.004471438936889172
2023-01-22 15:00:48.924990: step: 1104/529, loss: 0.007103884592652321
2023-01-22 15:00:50.015021: step: 1108/529, loss: 0.016453972086310387
2023-01-22 15:00:51.091257: step: 1112/529, loss: 0.008063547313213348
2023-01-22 15:00:52.163588: step: 1116/529, loss: 0.02745014987885952
2023-01-22 15:00:53.255180: step: 1120/529, loss: 0.01557265967130661
2023-01-22 15:00:54.336984: step: 1124/529, loss: 0.013674561865627766
2023-01-22 15:00:55.401108: step: 1128/529, loss: 0.0029267645440995693
2023-01-22 15:00:56.493721: step: 1132/529, loss: 0.005986180156469345
2023-01-22 15:00:57.596543: step: 1136/529, loss: 0.009181891568005085
2023-01-22 15:00:58.685829: step: 1140/529, loss: 0.005270898342132568
2023-01-22 15:00:59.759430: step: 1144/529, loss: 0.039514750242233276
2023-01-22 15:01:00.839326: step: 1148/529, loss: 0.027101781219244003
2023-01-22 15:01:01.915720: step: 1152/529, loss: 0.011535374447703362
2023-01-22 15:01:03.007689: step: 1156/529, loss: 0.042968783527612686
2023-01-22 15:01:04.090051: step: 1160/529, loss: 0.006305822171270847
2023-01-22 15:01:05.176106: step: 1164/529, loss: 0.02580130472779274
2023-01-22 15:01:06.263043: step: 1168/529, loss: 0.009113805368542671
2023-01-22 15:01:07.357753: step: 1172/529, loss: 0.010318076238036156
2023-01-22 15:01:08.446585: step: 1176/529, loss: 0.004338184371590614
2023-01-22 15:01:09.529973: step: 1180/529, loss: 0.005512248259037733
2023-01-22 15:01:10.610507: step: 1184/529, loss: 0.02038363367319107
2023-01-22 15:01:11.702613: step: 1188/529, loss: 0.01213717833161354
2023-01-22 15:01:12.783144: step: 1192/529, loss: 0.010896789841353893
2023-01-22 15:01:13.877139: step: 1196/529, loss: 0.007011616602540016
2023-01-22 15:01:14.954073: step: 1200/529, loss: 0.011035246774554253
2023-01-22 15:01:16.022470: step: 1204/529, loss: 0.010063204914331436
2023-01-22 15:01:17.104123: step: 1208/529, loss: 0.027120720595121384
2023-01-22 15:01:18.201789: step: 1212/529, loss: 0.03099985048174858
2023-01-22 15:01:19.286344: step: 1216/529, loss: 0.03999115526676178
2023-01-22 15:01:20.364426: step: 1220/529, loss: 0.00536049110814929
2023-01-22 15:01:21.457157: step: 1224/529, loss: 0.02533509023487568
2023-01-22 15:01:22.553234: step: 1228/529, loss: 0.007261867169290781
2023-01-22 15:01:23.648209: step: 1232/529, loss: 0.021081771701574326
2023-01-22 15:01:24.755626: step: 1236/529, loss: 0.013951675035059452
2023-01-22 15:01:25.840750: step: 1240/529, loss: 0.0072111631743609905
2023-01-22 15:01:26.925227: step: 1244/529, loss: 0.011290324851870537
2023-01-22 15:01:28.001375: step: 1248/529, loss: 0.0023878600914031267
2023-01-22 15:01:29.085098: step: 1252/529, loss: 0.009116090834140778
2023-01-22 15:01:30.177904: step: 1256/529, loss: 0.013053000904619694
2023-01-22 15:01:31.264484: step: 1260/529, loss: 0.01214775163680315
2023-01-22 15:01:32.346151: step: 1264/529, loss: 0.005877509247511625
2023-01-22 15:01:33.434165: step: 1268/529, loss: 0.011246110312640667
2023-01-22 15:01:34.511694: step: 1272/529, loss: 0.016227534040808678
2023-01-22 15:01:35.586918: step: 1276/529, loss: 0.01072680950164795
2023-01-22 15:01:36.665638: step: 1280/529, loss: 0.008840692229568958
2023-01-22 15:01:37.740857: step: 1284/529, loss: 0.011864015832543373
2023-01-22 15:01:38.845841: step: 1288/529, loss: 0.014883642084896564
2023-01-22 15:01:39.924447: step: 1292/529, loss: 0.004966744687408209
2023-01-22 15:01:41.014938: step: 1296/529, loss: 0.04509740695357323
2023-01-22 15:01:42.087968: step: 1300/529, loss: 0.00328592280857265
2023-01-22 15:01:43.193953: step: 1304/529, loss: 0.00690871849656105
2023-01-22 15:01:44.266402: step: 1308/529, loss: 0.03959457948803902
2023-01-22 15:01:45.341918: step: 1312/529, loss: 0.04519904404878616
2023-01-22 15:01:46.420293: step: 1316/529, loss: 0.021984321996569633
2023-01-22 15:01:47.493070: step: 1320/529, loss: 0.006843100767582655
2023-01-22 15:01:48.579470: step: 1324/529, loss: 0.044762954115867615
2023-01-22 15:01:49.663482: step: 1328/529, loss: 0.014802508056163788
2023-01-22 15:01:50.748964: step: 1332/529, loss: 0.00244291708804667
2023-01-22 15:01:51.819911: step: 1336/529, loss: 0.009213568642735481
2023-01-22 15:01:52.910585: step: 1340/529, loss: 0.011801140382885933
2023-01-22 15:01:53.995797: step: 1344/529, loss: 0.012021483853459358
2023-01-22 15:01:55.083551: step: 1348/529, loss: 0.006623891647905111
2023-01-22 15:01:56.181324: step: 1352/529, loss: 0.005431486293673515
2023-01-22 15:01:57.278165: step: 1356/529, loss: 0.06648432463407516
2023-01-22 15:01:58.367298: step: 1360/529, loss: 0.010971464216709137
2023-01-22 15:01:59.462955: step: 1364/529, loss: 0.029019389301538467
2023-01-22 15:02:00.549017: step: 1368/529, loss: 0.018898412585258484
2023-01-22 15:02:01.652029: step: 1372/529, loss: 0.009463388472795486
2023-01-22 15:02:02.730432: step: 1376/529, loss: 0.006287693046033382
2023-01-22 15:02:03.812238: step: 1380/529, loss: 0.003187919734045863
2023-01-22 15:02:04.924820: step: 1384/529, loss: 0.003515623277053237
2023-01-22 15:02:06.023317: step: 1388/529, loss: 0.0026332989800721407
2023-01-22 15:02:07.112285: step: 1392/529, loss: 0.009394300170242786
2023-01-22 15:02:08.197426: step: 1396/529, loss: 0.004997484851628542
2023-01-22 15:02:09.279942: step: 1400/529, loss: 0.009509800933301449
2023-01-22 15:02:10.373028: step: 1404/529, loss: 0.00559243792667985
2023-01-22 15:02:11.463966: step: 1408/529, loss: 0.0076534803956747055
2023-01-22 15:02:12.544547: step: 1412/529, loss: 0.08146931231021881
2023-01-22 15:02:13.615852: step: 1416/529, loss: 0.010398810729384422
2023-01-22 15:02:14.701854: step: 1420/529, loss: 0.010525343008339405
2023-01-22 15:02:15.784628: step: 1424/529, loss: 0.05010334774851799
2023-01-22 15:02:16.851526: step: 1428/529, loss: 0.005588009022176266
2023-01-22 15:02:17.937179: step: 1432/529, loss: 0.00919264554977417
2023-01-22 15:02:19.013677: step: 1436/529, loss: 0.006516479421406984
2023-01-22 15:02:20.113284: step: 1440/529, loss: 0.013326709158718586
2023-01-22 15:02:21.190248: step: 1444/529, loss: 0.0029639750719070435
2023-01-22 15:02:22.270968: step: 1448/529, loss: 0.010421779938042164
2023-01-22 15:02:23.349410: step: 1452/529, loss: 0.007942502386868
2023-01-22 15:02:24.442279: step: 1456/529, loss: 0.035399384796619415
2023-01-22 15:02:25.526225: step: 1460/529, loss: 0.006975781638175249
2023-01-22 15:02:26.628764: step: 1464/529, loss: 0.05700681731104851
2023-01-22 15:02:27.706385: step: 1468/529, loss: 0.00598968006670475
2023-01-22 15:02:28.768150: step: 1472/529, loss: 0.010580715723335743
2023-01-22 15:02:29.848027: step: 1476/529, loss: 0.0077400836162269115
2023-01-22 15:02:30.932064: step: 1480/529, loss: 0.005843636114150286
2023-01-22 15:02:32.012358: step: 1484/529, loss: 0.03368179500102997
2023-01-22 15:02:33.101261: step: 1488/529, loss: 0.004991909023374319
2023-01-22 15:02:34.187820: step: 1492/529, loss: 0.039475228637456894
2023-01-22 15:02:35.284400: step: 1496/529, loss: 0.020836995914578438
2023-01-22 15:02:36.364496: step: 1500/529, loss: 0.017095476388931274
2023-01-22 15:02:37.442093: step: 1504/529, loss: 0.007995637133717537
2023-01-22 15:02:38.529792: step: 1508/529, loss: 0.03511830419301987
2023-01-22 15:02:39.618951: step: 1512/529, loss: 0.043007515370845795
2023-01-22 15:02:40.692841: step: 1516/529, loss: 0.003032101085409522
2023-01-22 15:02:41.756908: step: 1520/529, loss: 0.008619263768196106
2023-01-22 15:02:42.868406: step: 1524/529, loss: 0.005864525213837624
2023-01-22 15:02:43.949180: step: 1528/529, loss: 0.0013895228039473295
2023-01-22 15:02:45.038775: step: 1532/529, loss: 0.019807903096079826
2023-01-22 15:02:46.119071: step: 1536/529, loss: 0.007260092534124851
2023-01-22 15:02:47.196521: step: 1540/529, loss: 0.004646764136850834
2023-01-22 15:02:48.260855: step: 1544/529, loss: 0.0028868799563497305
2023-01-22 15:02:49.332601: step: 1548/529, loss: 0.006035225931555033
2023-01-22 15:02:50.414440: step: 1552/529, loss: 0.0023739205207675695
2023-01-22 15:02:51.523866: step: 1556/529, loss: 0.014841475524008274
2023-01-22 15:02:52.621777: step: 1560/529, loss: 0.003927040379494429
2023-01-22 15:02:53.696660: step: 1564/529, loss: 0.013967577368021011
2023-01-22 15:02:54.787569: step: 1568/529, loss: 0.01272412296384573
2023-01-22 15:02:55.856350: step: 1572/529, loss: 0.005824252963066101
2023-01-22 15:02:56.952055: step: 1576/529, loss: 0.007159653585404158
2023-01-22 15:02:58.038941: step: 1580/529, loss: 0.010241798125207424
2023-01-22 15:02:59.123554: step: 1584/529, loss: 0.0177440345287323
2023-01-22 15:03:00.211498: step: 1588/529, loss: 0.002803144045174122
2023-01-22 15:03:01.290996: step: 1592/529, loss: 0.0041565364226698875
2023-01-22 15:03:02.395911: step: 1596/529, loss: 0.04219739884138107
2023-01-22 15:03:03.477153: step: 1600/529, loss: 0.013250652700662613
2023-01-22 15:03:04.552770: step: 1604/529, loss: 0.0059806592762470245
2023-01-22 15:03:05.633237: step: 1608/529, loss: 0.010280859656631947
2023-01-22 15:03:06.704179: step: 1612/529, loss: 0.007436178158968687
2023-01-22 15:03:07.782907: step: 1616/529, loss: 0.009739872999489307
2023-01-22 15:03:08.850741: step: 1620/529, loss: 0.0055679879151284695
2023-01-22 15:03:09.931050: step: 1624/529, loss: 0.05519388988614082
2023-01-22 15:03:10.995930: step: 1628/529, loss: 0.0054127671755850315
2023-01-22 15:03:12.060517: step: 1632/529, loss: 0.03428838029503822
2023-01-22 15:03:13.172682: step: 1636/529, loss: 0.016511430963873863
2023-01-22 15:03:14.246090: step: 1640/529, loss: 0.013362477533519268
2023-01-22 15:03:15.337370: step: 1644/529, loss: 0.04664391279220581
2023-01-22 15:03:16.429217: step: 1648/529, loss: 0.005670679267495871
2023-01-22 15:03:17.509326: step: 1652/529, loss: 0.009138268418610096
2023-01-22 15:03:18.590567: step: 1656/529, loss: 0.018803101032972336
2023-01-22 15:03:19.670717: step: 1660/529, loss: 0.014966643415391445
2023-01-22 15:03:20.747213: step: 1664/529, loss: 0.0032274597324430943
2023-01-22 15:03:21.817997: step: 1668/529, loss: 0.016024164855480194
2023-01-22 15:03:22.896457: step: 1672/529, loss: 0.013423580676317215
2023-01-22 15:03:23.977741: step: 1676/529, loss: 0.0057151103392243385
2023-01-22 15:03:25.062447: step: 1680/529, loss: 0.012827717699110508
2023-01-22 15:03:26.153459: step: 1684/529, loss: 0.005884043872356415
2023-01-22 15:03:27.247243: step: 1688/529, loss: 0.0035296257119625807
2023-01-22 15:03:28.334816: step: 1692/529, loss: 0.02579759992659092
2023-01-22 15:03:29.408430: step: 1696/529, loss: 0.04146649315953255
2023-01-22 15:03:30.492520: step: 1700/529, loss: 0.025786763057112694
2023-01-22 15:03:31.565048: step: 1704/529, loss: 0.00027789032901637256
2023-01-22 15:03:32.640024: step: 1708/529, loss: 0.034782007336616516
2023-01-22 15:03:33.709146: step: 1712/529, loss: 0.008539574220776558
2023-01-22 15:03:34.777848: step: 1716/529, loss: 0.029483728110790253
2023-01-22 15:03:35.852821: step: 1720/529, loss: 0.007934585213661194
2023-01-22 15:03:36.927419: step: 1724/529, loss: 0.05138925090432167
2023-01-22 15:03:38.010962: step: 1728/529, loss: 0.011047548614442348
2023-01-22 15:03:39.093338: step: 1732/529, loss: 0.004193627741187811
2023-01-22 15:03:40.169903: step: 1736/529, loss: 0.005660828202962875
2023-01-22 15:03:41.270623: step: 1740/529, loss: 0.009986856020987034
2023-01-22 15:03:42.346297: step: 1744/529, loss: 0.008113296702504158
2023-01-22 15:03:43.440937: step: 1748/529, loss: 0.004208900034427643
2023-01-22 15:03:44.521701: step: 1752/529, loss: 0.005658932030200958
2023-01-22 15:03:45.600394: step: 1756/529, loss: 0.007513790391385555
2023-01-22 15:03:46.698611: step: 1760/529, loss: 0.006018828600645065
2023-01-22 15:03:47.773423: step: 1764/529, loss: 0.015406571328639984
2023-01-22 15:03:48.849633: step: 1768/529, loss: 0.006777746137231588
2023-01-22 15:03:49.939403: step: 1772/529, loss: 0.016631942242383957
2023-01-22 15:03:51.019095: step: 1776/529, loss: 0.05578795447945595
2023-01-22 15:03:52.098707: step: 1780/529, loss: 0.028491957113146782
2023-01-22 15:03:53.196001: step: 1784/529, loss: 0.009910641238093376
2023-01-22 15:03:54.282371: step: 1788/529, loss: 0.010287641547620296
2023-01-22 15:03:55.367014: step: 1792/529, loss: 0.009349336847662926
2023-01-22 15:03:56.455512: step: 1796/529, loss: 0.010252943262457848
2023-01-22 15:03:57.524802: step: 1800/529, loss: 0.008965574204921722
2023-01-22 15:03:58.595584: step: 1804/529, loss: 0.013064608909189701
2023-01-22 15:03:59.679346: step: 1808/529, loss: 0.0067008123733103275
2023-01-22 15:04:00.768062: step: 1812/529, loss: 0.034985847771167755
2023-01-22 15:04:01.836977: step: 1816/529, loss: 0.0029357224702835083
2023-01-22 15:04:02.919013: step: 1820/529, loss: 0.012511278502643108
2023-01-22 15:04:04.017962: step: 1824/529, loss: 0.014967227354645729
2023-01-22 15:04:05.092488: step: 1828/529, loss: 0.009885610081255436
2023-01-22 15:04:06.179757: step: 1832/529, loss: 0.00869726575911045
2023-01-22 15:04:07.252636: step: 1836/529, loss: 0.005111526697874069
2023-01-22 15:04:08.338159: step: 1840/529, loss: 0.026112454012036324
2023-01-22 15:04:09.424397: step: 1844/529, loss: 0.003226904897019267
2023-01-22 15:04:10.501545: step: 1848/529, loss: 0.006491770502179861
2023-01-22 15:04:11.580968: step: 1852/529, loss: 0.007665010169148445
2023-01-22 15:04:12.662906: step: 1856/529, loss: 0.00772461760789156
2023-01-22 15:04:13.733325: step: 1860/529, loss: 0.005196233280003071
2023-01-22 15:04:14.791958: step: 1864/529, loss: 0.009938716888427734
2023-01-22 15:04:15.873134: step: 1868/529, loss: 0.00214287918061018
2023-01-22 15:04:16.944435: step: 1872/529, loss: 0.023980073630809784
2023-01-22 15:04:18.024276: step: 1876/529, loss: 0.011643702164292336
2023-01-22 15:04:19.115910: step: 1880/529, loss: 0.006355784833431244
2023-01-22 15:04:20.194889: step: 1884/529, loss: 0.023815974593162537
2023-01-22 15:04:21.261757: step: 1888/529, loss: 0.04275970906019211
2023-01-22 15:04:22.328692: step: 1892/529, loss: 0.04026271030306816
2023-01-22 15:04:23.417883: step: 1896/529, loss: 0.005890017841011286
2023-01-22 15:04:24.484677: step: 1900/529, loss: 0.01739628054201603
2023-01-22 15:04:25.552218: step: 1904/529, loss: 0.008714761584997177
2023-01-22 15:04:26.618263: step: 1908/529, loss: 0.00838181097060442
2023-01-22 15:04:27.685331: step: 1912/529, loss: 0.010334637947380543
2023-01-22 15:04:28.761313: step: 1916/529, loss: 0.00658290134742856
2023-01-22 15:04:29.838403: step: 1920/529, loss: 0.05561702698469162
2023-01-22 15:04:30.935652: step: 1924/529, loss: 0.009740826673805714
2023-01-22 15:04:32.020451: step: 1928/529, loss: 0.019930532202124596
2023-01-22 15:04:33.098003: step: 1932/529, loss: 0.008057414554059505
2023-01-22 15:04:34.178072: step: 1936/529, loss: 0.058137282729148865
2023-01-22 15:04:35.245494: step: 1940/529, loss: 0.004486719612032175
2023-01-22 15:04:36.323916: step: 1944/529, loss: 0.01392204500734806
2023-01-22 15:04:37.394699: step: 1948/529, loss: 0.03284474089741707
2023-01-22 15:04:38.488685: step: 1952/529, loss: 0.015019644983112812
2023-01-22 15:04:39.575757: step: 1956/529, loss: 0.013032629154622555
2023-01-22 15:04:40.665829: step: 1960/529, loss: 0.005332757253199816
2023-01-22 15:04:41.740145: step: 1964/529, loss: 0.007482311688363552
2023-01-22 15:04:42.805215: step: 1968/529, loss: 0.01071746926754713
2023-01-22 15:04:43.885424: step: 1972/529, loss: 0.006644145119935274
2023-01-22 15:04:44.977150: step: 1976/529, loss: 0.012638228945434093
2023-01-22 15:04:46.057552: step: 1980/529, loss: 0.03407052159309387
2023-01-22 15:04:47.137062: step: 1984/529, loss: 0.0048530432395637035
2023-01-22 15:04:48.222533: step: 1988/529, loss: 0.05103858932852745
2023-01-22 15:04:49.314346: step: 1992/529, loss: 0.013925762847065926
2023-01-22 15:04:50.395164: step: 1996/529, loss: 0.0031792980153113604
2023-01-22 15:04:51.486077: step: 2000/529, loss: 0.1556052714586258
2023-01-22 15:04:52.565547: step: 2004/529, loss: 0.013302719220519066
2023-01-22 15:04:53.638612: step: 2008/529, loss: 0.018728191033005714
2023-01-22 15:04:54.710914: step: 2012/529, loss: 0.004508196841925383
2023-01-22 15:04:55.784619: step: 2016/529, loss: 0.02374061942100525
2023-01-22 15:04:56.861358: step: 2020/529, loss: 0.011305669322609901
2023-01-22 15:04:57.951936: step: 2024/529, loss: 0.01459311880171299
2023-01-22 15:04:59.036338: step: 2028/529, loss: 0.04293946921825409
2023-01-22 15:05:00.116364: step: 2032/529, loss: 0.009750621393322945
2023-01-22 15:05:01.207125: step: 2036/529, loss: 0.028861336410045624
2023-01-22 15:05:02.271359: step: 2040/529, loss: 0.009075273759663105
2023-01-22 15:05:03.346138: step: 2044/529, loss: 0.0069069270975887775
2023-01-22 15:05:04.436124: step: 2048/529, loss: 0.046794530004262924
2023-01-22 15:05:05.525848: step: 2052/529, loss: 0.004367154091596603
2023-01-22 15:05:06.609764: step: 2056/529, loss: 0.005833095870912075
2023-01-22 15:05:07.689049: step: 2060/529, loss: 0.04321917146444321
2023-01-22 15:05:08.764942: step: 2064/529, loss: 0.006839882116764784
2023-01-22 15:05:09.840300: step: 2068/529, loss: 0.0207469891756773
2023-01-22 15:05:10.928690: step: 2072/529, loss: 0.016233840957283974
2023-01-22 15:05:12.005059: step: 2076/529, loss: 0.0068873390555381775
2023-01-22 15:05:13.104459: step: 2080/529, loss: 0.007550279144197702
2023-01-22 15:05:14.193212: step: 2084/529, loss: 0.005358210299164057
2023-01-22 15:05:15.271258: step: 2088/529, loss: 0.0036425397265702486
2023-01-22 15:05:16.349693: step: 2092/529, loss: 0.0075703030452132225
2023-01-22 15:05:17.415546: step: 2096/529, loss: 0.005759506020694971
2023-01-22 15:05:18.492769: step: 2100/529, loss: 0.0191704872995615
2023-01-22 15:05:19.570509: step: 2104/529, loss: 0.010615777224302292
2023-01-22 15:05:20.637227: step: 2108/529, loss: 0.008621551096439362
2023-01-22 15:05:21.709646: step: 2112/529, loss: 0.006205690558999777
2023-01-22 15:05:22.771567: step: 2116/529, loss: 0.007107949815690517
==================================================
Loss: 0.016
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3214224872231687, 'r': 0.3580170777988615, 'f1': 0.33873429084380613}, 'combined': 0.24959368799017292, 'stategy': 1, 'epoch': 1}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30554643725238745, 'r': 0.30695060286476056, 'f1': 0.30624691051523106}, 'combined': 0.19993321619129073, 'stategy': 1, 'epoch': 1}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32013603344298247, 'r': 0.36934100253004426, 'f1': 0.3429827459618209}, 'combined': 0.25272412860344695, 'stategy': 1, 'epoch': 1}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3267940432184065, 'r': 0.31027412375424074, 'f1': 0.3183198931113757}, 'combined': 0.20781505975146808, 'stategy': 1, 'epoch': 1}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3049353088480801, 'r': 0.3465962998102467, 'f1': 0.32443383658969804}, 'combined': 0.23905651117135643, 'stategy': 1, 'epoch': 1}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.31703716839370494, 'r': 0.32082181778683455, 'f1': 0.3189182652394914}, 'combined': 0.20820570684028972, 'stategy': 1, 'epoch': 1}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2976190476190476, 'r': 0.41666666666666663, 'f1': 0.34722222222222227}, 'combined': 0.2314814814814815, 'stategy': 1, 'epoch': 1}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 1}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 1}
New best chinese model...
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3214224872231687, 'r': 0.3580170777988615, 'f1': 0.33873429084380613}, 'combined': 0.24959368799017292, 'stategy': 1, 'epoch': 1}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30554643725238745, 'r': 0.30695060286476056, 'f1': 0.30624691051523106}, 'combined': 0.19993321619129073, 'stategy': 1, 'epoch': 1}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2976190476190476, 'r': 0.41666666666666663, 'f1': 0.34722222222222227}, 'combined': 0.2314814814814815, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32013603344298247, 'r': 0.36934100253004426, 'f1': 0.3429827459618209}, 'combined': 0.25272412860344695, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3267940432184065, 'r': 0.31027412375424074, 'f1': 0.3183198931113757}, 'combined': 0.20781505975146808, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3059747023809524, 'r': 0.3483582949308756, 'f1': 0.32579382684750924}, 'combined': 0.24005860925605943, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30859371390166324, 'r': 0.31737829161603565, 'f1': 0.31292436357615466}, 'combined': 0.2042925896922046, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 0}
******************************
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 15:08:23.757154: step: 4/529, loss: 0.010113946162164211
2023-01-22 15:08:24.816903: step: 8/529, loss: 0.023191876709461212
2023-01-22 15:08:25.885853: step: 12/529, loss: 0.006596298422664404
2023-01-22 15:08:26.971816: step: 16/529, loss: 0.0040982491336762905
2023-01-22 15:08:28.057071: step: 20/529, loss: 0.00264414818957448
2023-01-22 15:08:29.111913: step: 24/529, loss: 0.024419303983449936
2023-01-22 15:08:30.184038: step: 28/529, loss: 0.005509079433977604
2023-01-22 15:08:31.241699: step: 32/529, loss: 0.006224116776138544
2023-01-22 15:08:32.303587: step: 36/529, loss: 0.01086567621678114
2023-01-22 15:08:33.382312: step: 40/529, loss: 0.009877790696918964
2023-01-22 15:08:34.446080: step: 44/529, loss: 0.028803030028939247
2023-01-22 15:08:35.527011: step: 48/529, loss: 0.0053496649488806725
2023-01-22 15:08:36.608026: step: 52/529, loss: 0.02631174772977829
2023-01-22 15:08:37.680799: step: 56/529, loss: 0.0009045038023032248
2023-01-22 15:08:38.761509: step: 60/529, loss: 0.007811385206878185
2023-01-22 15:08:39.820229: step: 64/529, loss: 0.011069833301007748
2023-01-22 15:08:40.896839: step: 68/529, loss: 0.01691410318017006
2023-01-22 15:08:41.966491: step: 72/529, loss: 0.017194414511322975
2023-01-22 15:08:43.042283: step: 76/529, loss: 0.009982526302337646
2023-01-22 15:08:44.098091: step: 80/529, loss: 0.022082049399614334
2023-01-22 15:08:45.178662: step: 84/529, loss: 0.005680608097463846
2023-01-22 15:08:46.243851: step: 88/529, loss: 0.00825822725892067
2023-01-22 15:08:47.300662: step: 92/529, loss: 0.005429005715996027
2023-01-22 15:08:48.361770: step: 96/529, loss: 0.0027572272811084986
2023-01-22 15:08:49.427789: step: 100/529, loss: 0.009466941468417645
2023-01-22 15:08:50.504170: step: 104/529, loss: 0.021326912567019463
2023-01-22 15:08:51.572220: step: 108/529, loss: 0.007840532809495926
2023-01-22 15:08:52.649969: step: 112/529, loss: 0.015168609097599983
2023-01-22 15:08:53.715240: step: 116/529, loss: 0.00839829258620739
2023-01-22 15:08:54.791708: step: 120/529, loss: 0.004541113972663879
2023-01-22 15:08:55.868055: step: 124/529, loss: 0.006309458054602146
2023-01-22 15:08:56.925007: step: 128/529, loss: 0.019247012212872505
2023-01-22 15:08:58.003489: step: 132/529, loss: 0.013402356766164303
2023-01-22 15:08:59.076222: step: 136/529, loss: 0.01287771388888359
2023-01-22 15:09:00.161371: step: 140/529, loss: 0.07247739285230637
2023-01-22 15:09:01.237443: step: 144/529, loss: 0.019719649106264114
2023-01-22 15:09:02.303319: step: 148/529, loss: 0.01630535162985325
2023-01-22 15:09:03.380136: step: 152/529, loss: 0.011462540365755558
2023-01-22 15:09:04.472084: step: 156/529, loss: 0.007881594821810722
2023-01-22 15:09:05.561970: step: 160/529, loss: 0.0306947510689497
2023-01-22 15:09:06.663956: step: 164/529, loss: 0.02132401429116726
2023-01-22 15:09:07.733777: step: 168/529, loss: 0.010975182987749577
2023-01-22 15:09:08.808774: step: 172/529, loss: 0.004137462470680475
2023-01-22 15:09:09.885163: step: 176/529, loss: 0.006465671584010124
2023-01-22 15:09:10.957642: step: 180/529, loss: 0.004132358357310295
2023-01-22 15:09:12.022709: step: 184/529, loss: 0.006023016758263111
2023-01-22 15:09:13.100344: step: 188/529, loss: 0.006676420569419861
2023-01-22 15:09:14.171679: step: 192/529, loss: 0.00285189226269722
2023-01-22 15:09:15.257218: step: 196/529, loss: 0.05700604245066643
2023-01-22 15:09:16.337683: step: 200/529, loss: 0.008522611111402512
2023-01-22 15:09:17.422635: step: 204/529, loss: 0.04799949750304222
2023-01-22 15:09:18.519597: step: 208/529, loss: 0.026255574077367783
2023-01-22 15:09:19.587461: step: 212/529, loss: 0.003190845949575305
2023-01-22 15:09:20.674533: step: 216/529, loss: 0.01589416153728962
2023-01-22 15:09:21.747873: step: 220/529, loss: 0.005084800999611616
2023-01-22 15:09:22.841128: step: 224/529, loss: 0.007687171455472708
2023-01-22 15:09:23.922563: step: 228/529, loss: 0.01149655319750309
2023-01-22 15:09:25.004487: step: 232/529, loss: 0.011149103753268719
2023-01-22 15:09:26.085083: step: 236/529, loss: 0.015421555377542973
2023-01-22 15:09:27.147707: step: 240/529, loss: 0.009221922606229782
2023-01-22 15:09:28.213152: step: 244/529, loss: 0.01107594184577465
2023-01-22 15:09:29.290500: step: 248/529, loss: 0.009078064002096653
2023-01-22 15:09:30.371792: step: 252/529, loss: 0.02102748118340969
2023-01-22 15:09:31.452389: step: 256/529, loss: 0.012334208935499191
2023-01-22 15:09:32.514892: step: 260/529, loss: 0.006269046105444431
2023-01-22 15:09:33.587063: step: 264/529, loss: 0.00042572588426992297
2023-01-22 15:09:34.673693: step: 268/529, loss: 0.015571920201182365
2023-01-22 15:09:35.748653: step: 272/529, loss: 0.0068322112783789635
2023-01-22 15:09:36.827115: step: 276/529, loss: 0.029863247647881508
2023-01-22 15:09:37.891451: step: 280/529, loss: 0.008220745250582695
2023-01-22 15:09:38.971290: step: 284/529, loss: 0.011505833826959133
2023-01-22 15:09:40.043943: step: 288/529, loss: 0.0034879117738455534
2023-01-22 15:09:41.110645: step: 292/529, loss: 0.011915769428014755
2023-01-22 15:09:42.181648: step: 296/529, loss: 0.02561418153345585
2023-01-22 15:09:43.259619: step: 300/529, loss: 0.006159918382763863
2023-01-22 15:09:44.320515: step: 304/529, loss: 0.005980865564197302
2023-01-22 15:09:45.397455: step: 308/529, loss: 0.03755580261349678
2023-01-22 15:09:46.465723: step: 312/529, loss: 0.004994974937289953
2023-01-22 15:09:47.546552: step: 316/529, loss: 0.01340450532734394
2023-01-22 15:09:48.617789: step: 320/529, loss: 0.005502969957888126
2023-01-22 15:09:49.690610: step: 324/529, loss: 0.006256521679461002
2023-01-22 15:09:50.756451: step: 328/529, loss: 0.03778060898184776
2023-01-22 15:09:51.829925: step: 332/529, loss: 0.007686616852879524
2023-01-22 15:09:52.916755: step: 336/529, loss: 0.002084204228594899
2023-01-22 15:09:53.986805: step: 340/529, loss: 0.009598198346793652
2023-01-22 15:09:55.055466: step: 344/529, loss: 0.010809702798724174
2023-01-22 15:09:56.109824: step: 348/529, loss: 0.01607486605644226
2023-01-22 15:09:57.193330: step: 352/529, loss: 0.008933251723647118
2023-01-22 15:09:58.272231: step: 356/529, loss: 0.01987755298614502
2023-01-22 15:09:59.335109: step: 360/529, loss: 0.0035100020468235016
2023-01-22 15:10:00.399880: step: 364/529, loss: 0.008190550841391087
2023-01-22 15:10:01.462682: step: 368/529, loss: 0.0072615742683410645
2023-01-22 15:10:02.529468: step: 372/529, loss: 0.039022739976644516
2023-01-22 15:10:03.593022: step: 376/529, loss: 0.007754258345812559
2023-01-22 15:10:04.662014: step: 380/529, loss: 0.00399549026042223
2023-01-22 15:10:05.735646: step: 384/529, loss: 0.008288799785077572
2023-01-22 15:10:06.802563: step: 388/529, loss: 0.006451813969761133
2023-01-22 15:10:07.864155: step: 392/529, loss: 0.007065907120704651
2023-01-22 15:10:08.953972: step: 396/529, loss: 0.05141688883304596
2023-01-22 15:10:10.004153: step: 400/529, loss: 0.00629222160205245
2023-01-22 15:10:11.061006: step: 404/529, loss: 0.012433497235178947
2023-01-22 15:10:12.132763: step: 408/529, loss: 0.01031239703297615
2023-01-22 15:10:13.197351: step: 412/529, loss: 0.008377622812986374
2023-01-22 15:10:14.260151: step: 416/529, loss: 0.0024060921277850866
2023-01-22 15:10:15.316088: step: 420/529, loss: 0.008515998721122742
2023-01-22 15:10:16.387648: step: 424/529, loss: 0.011796880513429642
2023-01-22 15:10:17.452414: step: 428/529, loss: 0.0015517441788688302
2023-01-22 15:10:18.542063: step: 432/529, loss: 0.005994210485368967
2023-01-22 15:10:19.625030: step: 436/529, loss: 0.006786423735320568
2023-01-22 15:10:20.691920: step: 440/529, loss: 0.014521707780659199
2023-01-22 15:10:21.775051: step: 444/529, loss: 0.006072856020182371
2023-01-22 15:10:22.848026: step: 448/529, loss: 0.014734000898897648
2023-01-22 15:10:23.929726: step: 452/529, loss: 0.012063873000442982
2023-01-22 15:10:25.000091: step: 456/529, loss: 0.010869873687624931
2023-01-22 15:10:26.072406: step: 460/529, loss: 0.0059290737845003605
2023-01-22 15:10:27.121827: step: 464/529, loss: 0.030661994591355324
2023-01-22 15:10:28.184259: step: 468/529, loss: 0.03214063495397568
2023-01-22 15:10:29.252614: step: 472/529, loss: 0.008816438727080822
2023-01-22 15:10:30.330864: step: 476/529, loss: 0.006373694632202387
2023-01-22 15:10:31.406649: step: 480/529, loss: 0.01191974338144064
2023-01-22 15:10:32.456992: step: 484/529, loss: 0.005648419726639986
2023-01-22 15:10:33.550921: step: 488/529, loss: 0.003929120488464832
2023-01-22 15:10:34.631444: step: 492/529, loss: 0.0074152275919914246
2023-01-22 15:10:35.690449: step: 496/529, loss: 0.002956545911729336
2023-01-22 15:10:36.756360: step: 500/529, loss: 0.03752194717526436
2023-01-22 15:10:37.802298: step: 504/529, loss: 0.0006859778659418225
2023-01-22 15:10:38.868388: step: 508/529, loss: 0.011561921797692776
2023-01-22 15:10:39.944038: step: 512/529, loss: 0.005353607703000307
2023-01-22 15:10:41.023775: step: 516/529, loss: 0.02221294306218624
2023-01-22 15:10:42.118539: step: 520/529, loss: 0.06545469909906387
2023-01-22 15:10:43.203464: step: 524/529, loss: 0.01264087576419115
2023-01-22 15:10:44.271543: step: 528/529, loss: 0.002884245477616787
2023-01-22 15:10:45.345854: step: 532/529, loss: 0.007786398287862539
2023-01-22 15:10:46.415630: step: 536/529, loss: 0.008083497174084187
2023-01-22 15:10:47.506837: step: 540/529, loss: 0.030045470222830772
2023-01-22 15:10:48.575213: step: 544/529, loss: 0.014178305864334106
2023-01-22 15:10:49.642492: step: 548/529, loss: 0.008849376812577248
2023-01-22 15:10:50.710511: step: 552/529, loss: 0.008732696995139122
2023-01-22 15:10:51.776887: step: 556/529, loss: 0.004410865716636181
2023-01-22 15:10:52.836935: step: 560/529, loss: 0.006997823249548674
2023-01-22 15:10:53.904357: step: 564/529, loss: 0.022372372448444366
2023-01-22 15:10:54.971219: step: 568/529, loss: 0.010571775026619434
2023-01-22 15:10:56.046709: step: 572/529, loss: 0.009789271280169487
2023-01-22 15:10:57.113500: step: 576/529, loss: 0.011386413127183914
2023-01-22 15:10:58.176044: step: 580/529, loss: 0.0026053423061966896
2023-01-22 15:10:59.281797: step: 584/529, loss: 0.006315314210951328
2023-01-22 15:11:00.344349: step: 588/529, loss: 0.006061123218387365
2023-01-22 15:11:01.419139: step: 592/529, loss: 0.012107725255191326
2023-01-22 15:11:02.496003: step: 596/529, loss: 0.010177775286138058
2023-01-22 15:11:03.543486: step: 600/529, loss: 0.0055756717920303345
2023-01-22 15:11:04.603371: step: 604/529, loss: 0.021189868450164795
2023-01-22 15:11:05.658258: step: 608/529, loss: 0.01046000700443983
2023-01-22 15:11:06.732129: step: 612/529, loss: 0.005971742793917656
2023-01-22 15:11:07.805274: step: 616/529, loss: 0.05866464972496033
2023-01-22 15:11:08.878332: step: 620/529, loss: 0.0023554451763629913
2023-01-22 15:11:09.953324: step: 624/529, loss: 0.0011644354090094566
2023-01-22 15:11:11.030363: step: 628/529, loss: 0.004025870468467474
2023-01-22 15:11:12.098730: step: 632/529, loss: 0.03125376999378204
2023-01-22 15:11:13.178844: step: 636/529, loss: 0.01074403990060091
2023-01-22 15:11:14.251034: step: 640/529, loss: 0.005771816708147526
2023-01-22 15:11:15.322955: step: 644/529, loss: 0.03079116903245449
2023-01-22 15:11:16.387527: step: 648/529, loss: 0.033063679933547974
2023-01-22 15:11:17.466299: step: 652/529, loss: 0.016354400664567947
2023-01-22 15:11:18.555967: step: 656/529, loss: 0.05970814451575279
2023-01-22 15:11:19.627436: step: 660/529, loss: 0.001444636844098568
2023-01-22 15:11:20.718751: step: 664/529, loss: 0.016184290871024132
2023-01-22 15:11:21.810860: step: 668/529, loss: 0.00477588502690196
2023-01-22 15:11:22.888673: step: 672/529, loss: 0.006206808146089315
2023-01-22 15:11:23.949021: step: 676/529, loss: 0.008227761834859848
2023-01-22 15:11:25.024311: step: 680/529, loss: 0.015279300510883331
2023-01-22 15:11:26.097842: step: 684/529, loss: 0.01271582767367363
2023-01-22 15:11:27.162525: step: 688/529, loss: 0.014392211101949215
2023-01-22 15:11:28.233270: step: 692/529, loss: 0.003943356219679117
2023-01-22 15:11:29.301094: step: 696/529, loss: 0.015789717435836792
2023-01-22 15:11:30.369659: step: 700/529, loss: 0.009603102691471577
2023-01-22 15:11:31.436934: step: 704/529, loss: 0.0014994575176388025
2023-01-22 15:11:32.520900: step: 708/529, loss: 0.04623842239379883
2023-01-22 15:11:33.578182: step: 712/529, loss: 0.009516654536128044
2023-01-22 15:11:34.646465: step: 716/529, loss: 0.01575472392141819
2023-01-22 15:11:35.722947: step: 720/529, loss: 0.013767393305897713
2023-01-22 15:11:36.780095: step: 724/529, loss: 0.003637568326666951
2023-01-22 15:11:37.872334: step: 728/529, loss: 0.0043344697915017605
2023-01-22 15:11:38.927991: step: 732/529, loss: 0.006537323351949453
2023-01-22 15:11:39.995241: step: 736/529, loss: 0.0033879082184284925
2023-01-22 15:11:41.061193: step: 740/529, loss: 0.02533634565770626
2023-01-22 15:11:42.137191: step: 744/529, loss: 0.017336128279566765
2023-01-22 15:11:43.207643: step: 748/529, loss: 0.004925339482724667
2023-01-22 15:11:44.262973: step: 752/529, loss: 0.007628203369677067
2023-01-22 15:11:45.329636: step: 756/529, loss: 0.008437758311629295
2023-01-22 15:11:46.411598: step: 760/529, loss: 0.024408672004938126
2023-01-22 15:11:47.488282: step: 764/529, loss: 0.0125978272408247
2023-01-22 15:11:48.568432: step: 768/529, loss: 0.005498663522303104
2023-01-22 15:11:49.645190: step: 772/529, loss: 0.011882169172167778
2023-01-22 15:11:50.715544: step: 776/529, loss: 0.011211286298930645
2023-01-22 15:11:51.788709: step: 780/529, loss: 0.02300315536558628
2023-01-22 15:11:52.866732: step: 784/529, loss: 0.003724579932168126
2023-01-22 15:11:53.919522: step: 788/529, loss: 0.028514083474874496
2023-01-22 15:11:55.001049: step: 792/529, loss: 0.006447245366871357
2023-01-22 15:11:56.060314: step: 796/529, loss: 0.006065033376216888
2023-01-22 15:11:57.120408: step: 800/529, loss: 0.005077395588159561
2023-01-22 15:11:58.214951: step: 804/529, loss: 0.010027355514466763
2023-01-22 15:11:59.285767: step: 808/529, loss: 0.02832377701997757
2023-01-22 15:12:00.370566: step: 812/529, loss: 0.043153002858161926
2023-01-22 15:12:01.422620: step: 816/529, loss: 0.025798605754971504
2023-01-22 15:12:02.505954: step: 820/529, loss: 0.015424206852912903
2023-01-22 15:12:03.578587: step: 824/529, loss: 0.0060752397403120995
2023-01-22 15:12:04.652485: step: 828/529, loss: 0.004287119023501873
2023-01-22 15:12:05.727112: step: 832/529, loss: 0.007462375797331333
2023-01-22 15:12:06.798857: step: 836/529, loss: 0.023030288517475128
2023-01-22 15:12:07.849168: step: 840/529, loss: 0.005865107756108046
2023-01-22 15:12:08.907087: step: 844/529, loss: 0.006104913540184498
2023-01-22 15:12:09.973042: step: 848/529, loss: 0.002652696566656232
2023-01-22 15:12:11.051373: step: 852/529, loss: 0.003942091483622789
2023-01-22 15:12:12.119242: step: 856/529, loss: 0.009529509581625462
2023-01-22 15:12:13.192887: step: 860/529, loss: 0.027600182220339775
2023-01-22 15:12:14.259138: step: 864/529, loss: 0.023900698870420456
2023-01-22 15:12:15.329609: step: 868/529, loss: 0.0259038507938385
2023-01-22 15:12:16.411596: step: 872/529, loss: 0.004927666392177343
2023-01-22 15:12:17.491006: step: 876/529, loss: 0.03155926987528801
2023-01-22 15:12:18.555825: step: 880/529, loss: 0.004801892675459385
2023-01-22 15:12:19.630864: step: 884/529, loss: 0.0028987738769501448
2023-01-22 15:12:20.695539: step: 888/529, loss: 0.011629470624029636
2023-01-22 15:12:21.771956: step: 892/529, loss: 0.011148552410304546
2023-01-22 15:12:22.842388: step: 896/529, loss: 0.13162261247634888
2023-01-22 15:12:23.933131: step: 900/529, loss: 0.008143724873661995
2023-01-22 15:12:25.010596: step: 904/529, loss: 0.03998962789773941
2023-01-22 15:12:26.090757: step: 908/529, loss: 0.0052235922776162624
2023-01-22 15:12:27.140182: step: 912/529, loss: 0.00394093943759799
2023-01-22 15:12:28.238496: step: 916/529, loss: 0.0072084455750882626
2023-01-22 15:12:29.314154: step: 920/529, loss: 0.009431025013327599
2023-01-22 15:12:30.401672: step: 924/529, loss: 0.0255372766405344
2023-01-22 15:12:31.481374: step: 928/529, loss: 0.01579502411186695
2023-01-22 15:12:32.541405: step: 932/529, loss: 0.004735572263598442
2023-01-22 15:12:33.626670: step: 936/529, loss: 0.019908593967556953
2023-01-22 15:12:34.689484: step: 940/529, loss: 0.02770416811108589
2023-01-22 15:12:35.764974: step: 944/529, loss: 0.006304669659584761
2023-01-22 15:12:36.829353: step: 948/529, loss: 0.0403580516576767
2023-01-22 15:12:37.895387: step: 952/529, loss: 0.007796632591634989
2023-01-22 15:12:38.952800: step: 956/529, loss: 0.0030209182295948267
2023-01-22 15:12:40.011019: step: 960/529, loss: 0.013146238401532173
2023-01-22 15:12:41.087767: step: 964/529, loss: 0.01584496907889843
2023-01-22 15:12:42.152601: step: 968/529, loss: 0.003359497059136629
2023-01-22 15:12:43.232480: step: 972/529, loss: 0.03896097093820572
2023-01-22 15:12:44.300272: step: 976/529, loss: 0.0074942875653505325
2023-01-22 15:12:45.364558: step: 980/529, loss: 0.009633627720177174
2023-01-22 15:12:46.451489: step: 984/529, loss: 0.010517396964132786
2023-01-22 15:12:47.525957: step: 988/529, loss: 0.004183989018201828
2023-01-22 15:12:48.603557: step: 992/529, loss: 0.025566834956407547
2023-01-22 15:12:49.666364: step: 996/529, loss: 0.0017568806651979685
2023-01-22 15:12:50.733048: step: 1000/529, loss: 0.003724064212292433
2023-01-22 15:12:51.820022: step: 1004/529, loss: 0.018226245418190956
2023-01-22 15:12:52.893212: step: 1008/529, loss: 0.002621798310428858
2023-01-22 15:12:53.976769: step: 1012/529, loss: 0.01233003567904234
2023-01-22 15:12:55.054102: step: 1016/529, loss: 0.0020173578523099422
2023-01-22 15:12:56.129498: step: 1020/529, loss: 0.055649321526288986
2023-01-22 15:12:57.203773: step: 1024/529, loss: 0.004484891425818205
2023-01-22 15:12:58.271560: step: 1028/529, loss: 0.015714703127741814
2023-01-22 15:12:59.349925: step: 1032/529, loss: 0.0038978324737399817
2023-01-22 15:13:00.450417: step: 1036/529, loss: 0.0031042390037328005
2023-01-22 15:13:01.539197: step: 1040/529, loss: 0.007391402497887611
2023-01-22 15:13:02.609623: step: 1044/529, loss: 0.029405970126390457
2023-01-22 15:13:03.685663: step: 1048/529, loss: 0.018559670075774193
2023-01-22 15:13:04.729272: step: 1052/529, loss: 0.0049636485055089
2023-01-22 15:13:05.807799: step: 1056/529, loss: 0.004320602398365736
2023-01-22 15:13:06.868702: step: 1060/529, loss: 0.010983044281601906
2023-01-22 15:13:07.943656: step: 1064/529, loss: 0.011514020152390003
2023-01-22 15:13:09.017891: step: 1068/529, loss: 0.009376381523907185
2023-01-22 15:13:10.077804: step: 1072/529, loss: 0.008348432369530201
2023-01-22 15:13:11.149557: step: 1076/529, loss: 0.017761917784810066
2023-01-22 15:13:12.233428: step: 1080/529, loss: 0.008414589799940586
2023-01-22 15:13:13.340491: step: 1084/529, loss: 0.005496625322848558
2023-01-22 15:13:14.408101: step: 1088/529, loss: 0.04644312337040901
2023-01-22 15:13:15.482363: step: 1092/529, loss: 0.004304953385144472
2023-01-22 15:13:16.574162: step: 1096/529, loss: 0.005510158836841583
2023-01-22 15:13:17.665185: step: 1100/529, loss: 0.005772853270173073
2023-01-22 15:13:18.731833: step: 1104/529, loss: 0.012061094865202904
2023-01-22 15:13:19.805063: step: 1108/529, loss: 0.0017688010120764375
2023-01-22 15:13:20.903751: step: 1112/529, loss: 0.017434442415833473
2023-01-22 15:13:21.993795: step: 1116/529, loss: 0.014594674110412598
2023-01-22 15:13:23.083668: step: 1120/529, loss: 0.0023712334223091602
2023-01-22 15:13:24.153807: step: 1124/529, loss: 0.006871682126075029
2023-01-22 15:13:25.237062: step: 1128/529, loss: 0.03983144089579582
2023-01-22 15:13:26.322464: step: 1132/529, loss: 0.028394797816872597
2023-01-22 15:13:27.397696: step: 1136/529, loss: 0.007608314510434866
2023-01-22 15:13:28.477434: step: 1140/529, loss: 0.013981778174638748
2023-01-22 15:13:29.560339: step: 1144/529, loss: 0.018365658819675446
2023-01-22 15:13:30.630212: step: 1148/529, loss: 0.008952243253588676
2023-01-22 15:13:31.713777: step: 1152/529, loss: 0.0017094701761379838
2023-01-22 15:13:32.806771: step: 1156/529, loss: 0.004046187736093998
2023-01-22 15:13:33.882174: step: 1160/529, loss: 0.013640028424561024
2023-01-22 15:13:34.945880: step: 1164/529, loss: 0.008996560238301754
2023-01-22 15:13:36.031980: step: 1168/529, loss: 0.02026931196451187
2023-01-22 15:13:37.102809: step: 1172/529, loss: 0.005805299151688814
2023-01-22 15:13:38.176440: step: 1176/529, loss: 0.002212170511484146
2023-01-22 15:13:39.249595: step: 1180/529, loss: 0.02477906085550785
2023-01-22 15:13:40.335345: step: 1184/529, loss: 0.02762446366250515
2023-01-22 15:13:41.406347: step: 1188/529, loss: 0.006099613383412361
2023-01-22 15:13:42.487739: step: 1192/529, loss: 0.012876187451183796
2023-01-22 15:13:43.588333: step: 1196/529, loss: 0.0063935755752027035
2023-01-22 15:13:44.664129: step: 1200/529, loss: 0.003878252115100622
2023-01-22 15:13:45.755519: step: 1204/529, loss: 0.039350178092718124
2023-01-22 15:13:46.843051: step: 1208/529, loss: 0.02139635756611824
2023-01-22 15:13:47.931459: step: 1212/529, loss: 0.00921793095767498
2023-01-22 15:13:49.022961: step: 1216/529, loss: 0.06087804585695267
2023-01-22 15:13:50.109458: step: 1220/529, loss: 0.028340278193354607
2023-01-22 15:13:51.190394: step: 1224/529, loss: 0.055563412606716156
2023-01-22 15:13:52.261378: step: 1228/529, loss: 0.02344418317079544
2023-01-22 15:13:53.327933: step: 1232/529, loss: 0.05165579915046692
2023-01-22 15:13:54.422736: step: 1236/529, loss: 0.001859421725384891
2023-01-22 15:13:55.505204: step: 1240/529, loss: 0.006139685865491629
2023-01-22 15:13:56.580596: step: 1244/529, loss: 0.0014655182603746653
2023-01-22 15:13:57.654312: step: 1248/529, loss: 0.0164926890283823
2023-01-22 15:13:58.766467: step: 1252/529, loss: 0.004378945101052523
2023-01-22 15:13:59.844811: step: 1256/529, loss: 0.024394448846578598
2023-01-22 15:14:00.929021: step: 1260/529, loss: 0.0026625245809555054
2023-01-22 15:14:01.997717: step: 1264/529, loss: 0.0066239298321306705
2023-01-22 15:14:03.083371: step: 1268/529, loss: 0.00588213000446558
2023-01-22 15:14:04.184912: step: 1272/529, loss: 0.00279621547088027
2023-01-22 15:14:05.296822: step: 1276/529, loss: 0.0028513562865555286
2023-01-22 15:14:06.387563: step: 1280/529, loss: 0.025714419782161713
2023-01-22 15:14:07.467363: step: 1284/529, loss: 0.008050620555877686
2023-01-22 15:14:08.545780: step: 1288/529, loss: 0.004834986291825771
2023-01-22 15:14:09.645623: step: 1292/529, loss: 0.0075737726874649525
2023-01-22 15:14:10.716420: step: 1296/529, loss: 0.0038207576144486666
2023-01-22 15:14:11.800205: step: 1300/529, loss: 0.02046213299036026
2023-01-22 15:14:12.911751: step: 1304/529, loss: 0.002661511767655611
2023-01-22 15:14:14.000443: step: 1308/529, loss: 0.0029636435210704803
2023-01-22 15:14:15.091592: step: 1312/529, loss: 0.007103527896106243
2023-01-22 15:14:16.167067: step: 1316/529, loss: 0.015374016016721725
2023-01-22 15:14:17.254946: step: 1320/529, loss: 0.005588351748883724
2023-01-22 15:14:18.343235: step: 1324/529, loss: 0.010644293390214443
2023-01-22 15:14:19.448955: step: 1328/529, loss: 0.013514773920178413
2023-01-22 15:14:20.543147: step: 1332/529, loss: 0.023189803585410118
2023-01-22 15:14:21.628535: step: 1336/529, loss: 0.016200147569179535
2023-01-22 15:14:22.708135: step: 1340/529, loss: 0.005605983082205057
2023-01-22 15:14:23.797313: step: 1344/529, loss: 0.005158822052180767
2023-01-22 15:14:24.909509: step: 1348/529, loss: 0.015752919018268585
2023-01-22 15:14:25.988253: step: 1352/529, loss: 0.007457233965396881
2023-01-22 15:14:27.068636: step: 1356/529, loss: 0.002733898349106312
2023-01-22 15:14:28.158617: step: 1360/529, loss: 0.00803408958017826
2023-01-22 15:14:29.256581: step: 1364/529, loss: 0.012401004321873188
2023-01-22 15:14:30.342158: step: 1368/529, loss: 0.012529886327683926
2023-01-22 15:14:31.433317: step: 1372/529, loss: 0.008226102218031883
2023-01-22 15:14:32.514464: step: 1376/529, loss: 0.003408262971788645
2023-01-22 15:14:33.592179: step: 1380/529, loss: 0.022067299112677574
2023-01-22 15:14:34.695910: step: 1384/529, loss: 0.029023773968219757
2023-01-22 15:14:35.798344: step: 1388/529, loss: 0.00243426114320755
2023-01-22 15:14:36.894438: step: 1392/529, loss: 0.02284083142876625
2023-01-22 15:14:37.980275: step: 1396/529, loss: 0.03285153955221176
2023-01-22 15:14:39.057972: step: 1400/529, loss: 0.0036283060908317566
2023-01-22 15:14:40.133468: step: 1404/529, loss: 0.004334451165050268
2023-01-22 15:14:41.227073: step: 1408/529, loss: 0.00718021159991622
2023-01-22 15:14:42.327323: step: 1412/529, loss: 0.0029661478474736214
2023-01-22 15:14:43.444705: step: 1416/529, loss: 0.008175135590136051
2023-01-22 15:14:44.528378: step: 1420/529, loss: 0.01993684098124504
2023-01-22 15:14:45.614364: step: 1424/529, loss: 0.016457246616482735
2023-01-22 15:14:46.690974: step: 1428/529, loss: 0.002410030923783779
2023-01-22 15:14:47.785708: step: 1432/529, loss: 0.003478674218058586
2023-01-22 15:14:48.869461: step: 1436/529, loss: 0.02772131934762001
2023-01-22 15:14:49.965928: step: 1440/529, loss: 0.04534738510847092
2023-01-22 15:14:51.049574: step: 1444/529, loss: 0.030017990618944168
2023-01-22 15:14:52.146945: step: 1448/529, loss: 0.03938787803053856
2023-01-22 15:14:53.257749: step: 1452/529, loss: 0.01088863518089056
2023-01-22 15:14:54.360044: step: 1456/529, loss: 0.034394435584545135
2023-01-22 15:14:55.442141: step: 1460/529, loss: 0.029155105352401733
2023-01-22 15:14:56.549425: step: 1464/529, loss: 0.008115858770906925
2023-01-22 15:14:57.641295: step: 1468/529, loss: 0.005686505232006311
2023-01-22 15:14:58.732863: step: 1472/529, loss: 0.018737081438302994
2023-01-22 15:14:59.815848: step: 1476/529, loss: 0.04900810867547989
2023-01-22 15:15:00.892377: step: 1480/529, loss: 0.016080887988209724
2023-01-22 15:15:01.971357: step: 1484/529, loss: 0.0045938449911773205
2023-01-22 15:15:03.058498: step: 1488/529, loss: 0.0033197340089827776
2023-01-22 15:15:04.155059: step: 1492/529, loss: 0.0010473380098119378
2023-01-22 15:15:05.266468: step: 1496/529, loss: 0.0172530859708786
2023-01-22 15:15:06.342447: step: 1500/529, loss: 0.007884933613240719
2023-01-22 15:15:07.431696: step: 1504/529, loss: 0.016385843977332115
2023-01-22 15:15:08.525448: step: 1508/529, loss: 0.015001671388745308
2023-01-22 15:15:09.598662: step: 1512/529, loss: 0.0015640354249626398
2023-01-22 15:15:10.676818: step: 1516/529, loss: 0.01059502549469471
2023-01-22 15:15:11.764024: step: 1520/529, loss: 0.006004739552736282
2023-01-22 15:15:12.884781: step: 1524/529, loss: 0.02500385232269764
2023-01-22 15:15:13.958878: step: 1528/529, loss: 0.002497711917385459
2023-01-22 15:15:15.033262: step: 1532/529, loss: 0.0026351953856647015
2023-01-22 15:15:16.121276: step: 1536/529, loss: 0.02436256594955921
2023-01-22 15:15:17.200015: step: 1540/529, loss: 0.004375166725367308
2023-01-22 15:15:18.280260: step: 1544/529, loss: 0.013552402146160603
2023-01-22 15:15:19.363114: step: 1548/529, loss: 0.023637469857931137
2023-01-22 15:15:20.425336: step: 1552/529, loss: 0.005161425564438105
2023-01-22 15:15:21.503532: step: 1556/529, loss: 0.003004640806466341
2023-01-22 15:15:22.596544: step: 1560/529, loss: 0.001522923936136067
2023-01-22 15:15:23.680145: step: 1564/529, loss: 0.0152517044916749
2023-01-22 15:15:24.745354: step: 1568/529, loss: 0.038275524973869324
2023-01-22 15:15:25.832707: step: 1572/529, loss: 0.005669040139764547
2023-01-22 15:15:26.927667: step: 1576/529, loss: 0.03416592627763748
2023-01-22 15:15:28.007516: step: 1580/529, loss: 0.012744205072522163
2023-01-22 15:15:29.086842: step: 1584/529, loss: 0.00821915827691555
2023-01-22 15:15:30.167786: step: 1588/529, loss: 0.01181462500244379
2023-01-22 15:15:31.249969: step: 1592/529, loss: 0.0055070677772164345
2023-01-22 15:15:32.334817: step: 1596/529, loss: 0.0008309081895276904
2023-01-22 15:15:33.418719: step: 1600/529, loss: 0.004739423282444477
2023-01-22 15:15:34.522989: step: 1604/529, loss: 0.006184678990393877
2023-01-22 15:15:35.620326: step: 1608/529, loss: 0.029379019513726234
2023-01-22 15:15:36.710746: step: 1612/529, loss: 0.0038327632937580347
2023-01-22 15:15:37.787691: step: 1616/529, loss: 0.007538485806435347
2023-01-22 15:15:38.876864: step: 1620/529, loss: 0.05112817883491516
2023-01-22 15:15:39.971799: step: 1624/529, loss: 0.007354019675403833
2023-01-22 15:15:41.046769: step: 1628/529, loss: 0.009731377474963665
2023-01-22 15:15:42.145314: step: 1632/529, loss: 0.004311395809054375
2023-01-22 15:15:43.220417: step: 1636/529, loss: 0.010484105907380581
2023-01-22 15:15:44.302253: step: 1640/529, loss: 0.04261666163802147
2023-01-22 15:15:45.383230: step: 1644/529, loss: 0.008501452393829823
2023-01-22 15:15:46.445650: step: 1648/529, loss: 0.03699615225195885
2023-01-22 15:15:47.531509: step: 1652/529, loss: 0.053415074944496155
2023-01-22 15:15:48.610529: step: 1656/529, loss: 0.007597135845571756
2023-01-22 15:15:49.699616: step: 1660/529, loss: 0.01577094942331314
2023-01-22 15:15:50.776164: step: 1664/529, loss: 0.03706006705760956
2023-01-22 15:15:51.853607: step: 1668/529, loss: 0.00483612809330225
2023-01-22 15:15:52.932801: step: 1672/529, loss: 0.01426513772457838
2023-01-22 15:15:54.022219: step: 1676/529, loss: 0.007214435841888189
2023-01-22 15:15:55.095893: step: 1680/529, loss: 0.025714347139000893
2023-01-22 15:15:56.170574: step: 1684/529, loss: 0.009176847524940968
2023-01-22 15:15:57.244360: step: 1688/529, loss: 0.044139422476291656
2023-01-22 15:15:58.326191: step: 1692/529, loss: 0.00020565024169627577
2023-01-22 15:15:59.391595: step: 1696/529, loss: 0.033236853778362274
2023-01-22 15:16:00.471019: step: 1700/529, loss: 0.02413833886384964
2023-01-22 15:16:01.541644: step: 1704/529, loss: 0.014737321063876152
2023-01-22 15:16:02.623849: step: 1708/529, loss: 0.006017411593347788
2023-01-22 15:16:03.702240: step: 1712/529, loss: 0.00570539478212595
2023-01-22 15:16:04.781750: step: 1716/529, loss: 0.01466822437942028
2023-01-22 15:16:05.892860: step: 1720/529, loss: 0.018773669376969337
2023-01-22 15:16:06.979163: step: 1724/529, loss: 0.008616812527179718
2023-01-22 15:16:08.059767: step: 1728/529, loss: 0.0018309402512386441
2023-01-22 15:16:09.133086: step: 1732/529, loss: 0.0016914657317101955
2023-01-22 15:16:10.210510: step: 1736/529, loss: 0.0016465247608721256
2023-01-22 15:16:11.282903: step: 1740/529, loss: 0.00797338504344225
2023-01-22 15:16:12.366511: step: 1744/529, loss: 0.030192503705620766
2023-01-22 15:16:13.464433: step: 1748/529, loss: 0.01001956406980753
2023-01-22 15:16:14.546102: step: 1752/529, loss: 0.006117544136941433
2023-01-22 15:16:15.634045: step: 1756/529, loss: 0.007491874508559704
2023-01-22 15:16:16.718269: step: 1760/529, loss: 0.02282862365245819
2023-01-22 15:16:17.795791: step: 1764/529, loss: 0.004685061983764172
2023-01-22 15:16:18.883616: step: 1768/529, loss: 0.005918607115745544
2023-01-22 15:16:19.943934: step: 1772/529, loss: 0.008445680141448975
2023-01-22 15:16:21.039379: step: 1776/529, loss: 0.00673102680593729
2023-01-22 15:16:22.130571: step: 1780/529, loss: 0.013594028539955616
2023-01-22 15:16:23.228779: step: 1784/529, loss: 0.010501289740204811
2023-01-22 15:16:24.301947: step: 1788/529, loss: 0.005844305269420147
2023-01-22 15:16:25.368051: step: 1792/529, loss: 0.003535617608577013
2023-01-22 15:16:26.441299: step: 1796/529, loss: 0.008703017607331276
2023-01-22 15:16:27.514345: step: 1800/529, loss: 0.03647451475262642
2023-01-22 15:16:28.597936: step: 1804/529, loss: 0.0032347142696380615
2023-01-22 15:16:29.679783: step: 1808/529, loss: 0.0056460085324943066
2023-01-22 15:16:30.754079: step: 1812/529, loss: 0.02136342041194439
2023-01-22 15:16:31.827067: step: 1816/529, loss: 0.026320243254303932
2023-01-22 15:16:32.906153: step: 1820/529, loss: 0.0029856255277991295
2023-01-22 15:16:33.993670: step: 1824/529, loss: 0.07196203619241714
2023-01-22 15:16:35.076160: step: 1828/529, loss: 0.028125401586294174
2023-01-22 15:16:36.136534: step: 1832/529, loss: 0.037703514099121094
2023-01-22 15:16:37.208860: step: 1836/529, loss: 0.008615609258413315
2023-01-22 15:16:38.282008: step: 1840/529, loss: 0.0136657003313303
2023-01-22 15:16:39.352816: step: 1844/529, loss: 0.004803077783435583
2023-01-22 15:16:40.436667: step: 1848/529, loss: 0.005082200281322002
2023-01-22 15:16:41.514284: step: 1852/529, loss: 0.0
2023-01-22 15:16:42.604104: step: 1856/529, loss: 0.01590595580637455
2023-01-22 15:16:43.691041: step: 1860/529, loss: 0.029346419498324394
2023-01-22 15:16:44.771565: step: 1864/529, loss: 0.0018871879437938333
2023-01-22 15:16:45.849645: step: 1868/529, loss: 0.0
2023-01-22 15:16:46.914958: step: 1872/529, loss: 0.003660541260614991
2023-01-22 15:16:48.001090: step: 1876/529, loss: 0.006462095770984888
2023-01-22 15:16:49.078182: step: 1880/529, loss: 0.011465365998446941
2023-01-22 15:16:50.166375: step: 1884/529, loss: 0.010310271754860878
2023-01-22 15:16:51.242407: step: 1888/529, loss: 0.006486890837550163
2023-01-22 15:16:52.337130: step: 1892/529, loss: 0.009188487194478512
2023-01-22 15:16:53.437040: step: 1896/529, loss: 0.009915893897414207
2023-01-22 15:16:54.520586: step: 1900/529, loss: 0.002734539331868291
2023-01-22 15:16:55.594073: step: 1904/529, loss: 0.005615149158984423
2023-01-22 15:16:56.685079: step: 1908/529, loss: 0.05137315392494202
2023-01-22 15:16:57.763157: step: 1912/529, loss: 0.002599590690806508
2023-01-22 15:16:58.827571: step: 1916/529, loss: 0.00834757648408413
2023-01-22 15:16:59.917276: step: 1920/529, loss: 0.049918632954359055
2023-01-22 15:17:01.000616: step: 1924/529, loss: 0.0056789773516356945
2023-01-22 15:17:02.072473: step: 1928/529, loss: 0.004025747999548912
2023-01-22 15:17:03.143163: step: 1932/529, loss: 0.0026592707727104425
2023-01-22 15:17:04.238496: step: 1936/529, loss: 0.003504074178636074
2023-01-22 15:17:05.314593: step: 1940/529, loss: 0.012685788795351982
2023-01-22 15:17:06.393014: step: 1944/529, loss: 0.01997111178934574
2023-01-22 15:17:07.468973: step: 1948/529, loss: 0.0035657461266964674
2023-01-22 15:17:08.564514: step: 1952/529, loss: 0.003932040184736252
2023-01-22 15:17:09.659528: step: 1956/529, loss: 0.0186584684997797
2023-01-22 15:17:10.743237: step: 1960/529, loss: 0.0054773613810539246
2023-01-22 15:17:11.827805: step: 1964/529, loss: 0.010664473287761211
2023-01-22 15:17:12.922173: step: 1968/529, loss: 0.031069811433553696
2023-01-22 15:17:14.009400: step: 1972/529, loss: 0.023229114711284637
2023-01-22 15:17:15.084554: step: 1976/529, loss: 0.007274959702044725
2023-01-22 15:17:16.168083: step: 1980/529, loss: 0.029007315635681152
2023-01-22 15:17:17.241057: step: 1984/529, loss: 0.0015267595881596208
2023-01-22 15:17:18.320427: step: 1988/529, loss: 0.004608352668583393
2023-01-22 15:17:19.411874: step: 1992/529, loss: 0.004273242317140102
2023-01-22 15:17:20.509432: step: 1996/529, loss: 0.004014894366264343
2023-01-22 15:17:21.592309: step: 2000/529, loss: 0.038474246859550476
2023-01-22 15:17:22.680693: step: 2004/529, loss: 0.014269506558775902
2023-01-22 15:17:23.765012: step: 2008/529, loss: 0.006851397920399904
2023-01-22 15:17:24.844903: step: 2012/529, loss: 0.005348716396838427
2023-01-22 15:17:25.915259: step: 2016/529, loss: 0.01597530022263527
2023-01-22 15:17:26.990492: step: 2020/529, loss: 0.011576604098081589
2023-01-22 15:17:28.068936: step: 2024/529, loss: 0.011374489404261112
2023-01-22 15:17:29.156849: step: 2028/529, loss: 0.020817169919610023
2023-01-22 15:17:30.230937: step: 2032/529, loss: 0.049827978014945984
2023-01-22 15:17:31.306830: step: 2036/529, loss: 0.038883961737155914
2023-01-22 15:17:32.386633: step: 2040/529, loss: 0.056108780205249786
2023-01-22 15:17:33.465174: step: 2044/529, loss: 0.015199577435851097
2023-01-22 15:17:34.546457: step: 2048/529, loss: 0.009123128838837147
2023-01-22 15:17:35.621265: step: 2052/529, loss: 0.017961569130420685
2023-01-22 15:17:36.717697: step: 2056/529, loss: 0.009053281508386135
2023-01-22 15:17:37.796007: step: 2060/529, loss: 0.0076627591624855995
2023-01-22 15:17:38.880446: step: 2064/529, loss: 0.010079356841742992
2023-01-22 15:17:39.943574: step: 2068/529, loss: 0.0019372139358893037
2023-01-22 15:17:41.015867: step: 2072/529, loss: 0.0047211721539497375
2023-01-22 15:17:42.104242: step: 2076/529, loss: 0.004959276877343655
2023-01-22 15:17:43.186546: step: 2080/529, loss: 0.006662295665591955
2023-01-22 15:17:44.268562: step: 2084/529, loss: 0.0018974773120135069
2023-01-22 15:17:45.372497: step: 2088/529, loss: 0.005917488597333431
2023-01-22 15:17:46.445110: step: 2092/529, loss: 0.0018383333226665854
2023-01-22 15:17:47.514628: step: 2096/529, loss: 0.036907970905303955
2023-01-22 15:17:48.579175: step: 2100/529, loss: 0.04326321557164192
2023-01-22 15:17:49.664121: step: 2104/529, loss: 0.004703995771706104
2023-01-22 15:17:50.749538: step: 2108/529, loss: 0.0034996713511645794
2023-01-22 15:17:51.842545: step: 2112/529, loss: 0.00457699503749609
2023-01-22 15:17:52.925404: step: 2116/529, loss: 0.006359584629535675
==================================================
Loss: 0.014
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31331385642737897, 'r': 0.3561195445920304, 'f1': 0.333348134991119}, 'combined': 0.24562494157240344, 'stategy': 1, 'epoch': 2}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3085395328859008, 'r': 0.30457300078268446, 'f1': 0.3065434360927388}, 'combined': 0.2001268028377466, 'stategy': 1, 'epoch': 2}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3170870475418693, 'r': 0.3712385357368754, 'f1': 0.34203270687645687}, 'combined': 0.25202409980370505, 'stategy': 1, 'epoch': 2}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3331644509779881, 'r': 0.3114230208130642, 'f1': 0.3219270751967828}, 'combined': 0.210170007641423, 'stategy': 1, 'epoch': 2}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30235990366541354, 'r': 0.3488326782325834, 'f1': 0.32393801132787925}, 'combined': 0.23869116624159523, 'stategy': 1, 'epoch': 2}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3243772689758882, 'r': 0.3228879334893139, 'f1': 0.32363088777714016}, 'combined': 0.21128234124310705, 'stategy': 1, 'epoch': 2}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 2}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 2}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5416666666666666, 'r': 0.33620689655172414, 'f1': 0.41489361702127664}, 'combined': 0.2765957446808511, 'stategy': 1, 'epoch': 2}
New best chinese model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31331385642737897, 'r': 0.3561195445920304, 'f1': 0.333348134991119}, 'combined': 0.24562494157240344, 'stategy': 1, 'epoch': 2}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3085395328859008, 'r': 0.30457300078268446, 'f1': 0.3065434360927388}, 'combined': 0.2001268028377466, 'stategy': 1, 'epoch': 2}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 2}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32013603344298247, 'r': 0.36934100253004426, 'f1': 0.3429827459618209}, 'combined': 0.25272412860344695, 'stategy': 1, 'epoch': 1}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3267940432184065, 'r': 0.31027412375424074, 'f1': 0.3183198931113757}, 'combined': 0.20781505975146808, 'stategy': 1, 'epoch': 1}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 1}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3059747023809524, 'r': 0.3483582949308756, 'f1': 0.32579382684750924}, 'combined': 0.24005860925605943, 'stategy': 1, 'epoch': 0}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30859371390166324, 'r': 0.31737829161603565, 'f1': 0.31292436357615466}, 'combined': 0.2042925896922046, 'stategy': 1, 'epoch': 0}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 0}
******************************
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 15:20:41.602217: step: 4/529, loss: 0.0024898829869925976
2023-01-22 15:20:42.657759: step: 8/529, loss: 0.009998486377298832
2023-01-22 15:20:43.725491: step: 12/529, loss: 0.009323058649897575
2023-01-22 15:20:44.809484: step: 16/529, loss: 0.011328169144690037
2023-01-22 15:20:45.876468: step: 20/529, loss: 0.0009869153145700693
2023-01-22 15:20:46.942225: step: 24/529, loss: 0.030980706214904785
2023-01-22 15:20:48.001687: step: 28/529, loss: 0.05104508623480797
2023-01-22 15:20:49.085873: step: 32/529, loss: 0.0055313920602202415
2023-01-22 15:20:50.156068: step: 36/529, loss: 0.004372811410576105
2023-01-22 15:20:51.223170: step: 40/529, loss: 0.011180211789906025
2023-01-22 15:20:52.301785: step: 44/529, loss: 0.009532887488603592
2023-01-22 15:20:53.372321: step: 48/529, loss: 0.015362439677119255
2023-01-22 15:20:54.453157: step: 52/529, loss: 0.006224817596375942
2023-01-22 15:20:55.512337: step: 56/529, loss: 0.0025285992305725813
2023-01-22 15:20:56.564305: step: 60/529, loss: 0.013974323868751526
2023-01-22 15:20:57.650492: step: 64/529, loss: 0.013623700477182865
2023-01-22 15:20:58.705675: step: 68/529, loss: 0.019874049350619316
2023-01-22 15:20:59.759014: step: 72/529, loss: 0.002674778923392296
2023-01-22 15:21:00.819533: step: 76/529, loss: 0.006196442525833845
2023-01-22 15:21:01.885566: step: 80/529, loss: 0.0
2023-01-22 15:21:02.973442: step: 84/529, loss: 0.0028121531940996647
2023-01-22 15:21:04.068689: step: 88/529, loss: 0.03950012847781181
2023-01-22 15:21:05.124775: step: 92/529, loss: 0.0011263397755101323
2023-01-22 15:21:06.195218: step: 96/529, loss: 0.00035015030880458653
2023-01-22 15:21:07.258244: step: 100/529, loss: 0.013024108484387398
2023-01-22 15:21:08.335745: step: 104/529, loss: 0.002154993126168847
2023-01-22 15:21:09.398544: step: 108/529, loss: 0.004968708846718073
2023-01-22 15:21:10.453509: step: 112/529, loss: 0.010217132978141308
2023-01-22 15:21:11.553042: step: 116/529, loss: 0.02586781233549118
2023-01-22 15:21:12.620927: step: 120/529, loss: 0.0017980748089030385
2023-01-22 15:21:13.692028: step: 124/529, loss: 0.007088362239301205
2023-01-22 15:21:14.780981: step: 128/529, loss: 0.014599244110286236
2023-01-22 15:21:15.851137: step: 132/529, loss: 0.00649668462574482
2023-01-22 15:21:16.910794: step: 136/529, loss: 0.009308228269219398
2023-01-22 15:21:17.980063: step: 140/529, loss: 0.004525244235992432
2023-01-22 15:21:19.054753: step: 144/529, loss: 0.02284422516822815
2023-01-22 15:21:20.147984: step: 148/529, loss: 0.00675962632521987
2023-01-22 15:21:21.220123: step: 152/529, loss: 0.04700329899787903
2023-01-22 15:21:22.302967: step: 156/529, loss: 0.0022611855529248714
2023-01-22 15:21:23.386216: step: 160/529, loss: 0.00609878683462739
2023-01-22 15:21:24.462231: step: 164/529, loss: 0.0028452607803046703
2023-01-22 15:21:25.529262: step: 168/529, loss: 0.007472863886505365
2023-01-22 15:21:26.596837: step: 172/529, loss: 0.014165637083351612
2023-01-22 15:21:27.678815: step: 176/529, loss: 0.018322885036468506
2023-01-22 15:21:28.757927: step: 180/529, loss: 0.005257230717688799
2023-01-22 15:21:29.813018: step: 184/529, loss: 0.0034080655314028263
2023-01-22 15:21:30.871478: step: 188/529, loss: 0.009067095816135406
2023-01-22 15:21:31.935787: step: 192/529, loss: 0.014662901870906353
2023-01-22 15:21:33.012001: step: 196/529, loss: 0.006641920655965805
2023-01-22 15:21:34.098195: step: 200/529, loss: 0.003498903475701809
2023-01-22 15:21:35.169743: step: 204/529, loss: 0.0022364268079400063
2023-01-22 15:21:36.263960: step: 208/529, loss: 0.006371054332703352
2023-01-22 15:21:37.339725: step: 212/529, loss: 0.011325756087899208
2023-01-22 15:21:38.421222: step: 216/529, loss: 0.011798487044870853
2023-01-22 15:21:39.493099: step: 220/529, loss: 0.016787752509117126
2023-01-22 15:21:40.586578: step: 224/529, loss: 0.005627484060823917
2023-01-22 15:21:41.654903: step: 228/529, loss: 0.004370959475636482
2023-01-22 15:21:42.718360: step: 232/529, loss: 0.020324936136603355
2023-01-22 15:21:43.789902: step: 236/529, loss: 0.008290110155940056
2023-01-22 15:21:44.858296: step: 240/529, loss: 0.0093317162245512
2023-01-22 15:21:45.923859: step: 244/529, loss: 0.005572185385972261
2023-01-22 15:21:46.996229: step: 248/529, loss: 0.0072760507464408875
2023-01-22 15:21:48.075996: step: 252/529, loss: 0.002409134991466999
2023-01-22 15:21:49.143286: step: 256/529, loss: 0.0033105802722275257
2023-01-22 15:21:50.221176: step: 260/529, loss: 0.002645289059728384
2023-01-22 15:21:51.291935: step: 264/529, loss: 0.0036009822506457567
2023-01-22 15:21:52.364087: step: 268/529, loss: 0.014621791429817677
2023-01-22 15:21:53.444571: step: 272/529, loss: 0.004520943388342857
2023-01-22 15:21:54.514995: step: 276/529, loss: 0.03241395205259323
2023-01-22 15:21:55.601396: step: 280/529, loss: 0.0014357933541759849
2023-01-22 15:21:56.671417: step: 284/529, loss: 0.016433486714959145
2023-01-22 15:21:57.729337: step: 288/529, loss: 0.00847969762980938
2023-01-22 15:21:58.804600: step: 292/529, loss: 0.005534472409635782
2023-01-22 15:21:59.892771: step: 296/529, loss: 0.009325714781880379
2023-01-22 15:22:00.971936: step: 300/529, loss: 0.0035875560715794563
2023-01-22 15:22:02.053836: step: 304/529, loss: 0.0061773560009896755
2023-01-22 15:22:03.115709: step: 308/529, loss: 0.003879481228068471
2023-01-22 15:22:04.195648: step: 312/529, loss: 0.02109449729323387
2023-01-22 15:22:05.259118: step: 316/529, loss: 0.006028865929692984
2023-01-22 15:22:06.333217: step: 320/529, loss: 0.0077999047935009
2023-01-22 15:22:07.410994: step: 324/529, loss: 0.005089559126645327
2023-01-22 15:22:08.480479: step: 328/529, loss: 0.012071740813553333
2023-01-22 15:22:09.550294: step: 332/529, loss: 0.0156533382833004
2023-01-22 15:22:10.632409: step: 336/529, loss: 0.0017831578152254224
2023-01-22 15:22:11.711514: step: 340/529, loss: 0.02241969108581543
2023-01-22 15:22:12.766098: step: 344/529, loss: 0.014348461292684078
2023-01-22 15:22:13.838257: step: 348/529, loss: 0.013777585700154305
2023-01-22 15:22:14.926691: step: 352/529, loss: 0.004657554905861616
2023-01-22 15:22:15.988519: step: 356/529, loss: 0.010508907958865166
2023-01-22 15:22:17.048604: step: 360/529, loss: 0.0047691757790744305
2023-01-22 15:22:18.104908: step: 364/529, loss: 0.023700784891843796
2023-01-22 15:22:19.178018: step: 368/529, loss: 0.08743604272603989
2023-01-22 15:22:20.243421: step: 372/529, loss: 0.0010982062667608261
2023-01-22 15:22:21.314803: step: 376/529, loss: 0.060454998165369034
2023-01-22 15:22:22.380900: step: 380/529, loss: 0.003574472852051258
2023-01-22 15:22:23.449824: step: 384/529, loss: 0.011014697141945362
2023-01-22 15:22:24.508207: step: 388/529, loss: 0.007280935533344746
2023-01-22 15:22:25.585572: step: 392/529, loss: 0.045963287353515625
2023-01-22 15:22:26.645877: step: 396/529, loss: 0.002156640635803342
2023-01-22 15:22:27.710295: step: 400/529, loss: 0.005824054591357708
2023-01-22 15:22:28.775134: step: 404/529, loss: 0.009582431986927986
2023-01-22 15:22:29.850376: step: 408/529, loss: 0.004311279859393835
2023-01-22 15:22:30.923337: step: 412/529, loss: 0.010646672919392586
2023-01-22 15:22:31.994095: step: 416/529, loss: 0.0013396181166172028
2023-01-22 15:22:33.064959: step: 420/529, loss: 0.02017797902226448
2023-01-22 15:22:34.138435: step: 424/529, loss: 0.011507540941238403
2023-01-22 15:22:35.221501: step: 428/529, loss: 0.0056877946481108665
2023-01-22 15:22:36.304316: step: 432/529, loss: 0.035469356924295425
2023-01-22 15:22:37.391277: step: 436/529, loss: 0.0041465251706540585
2023-01-22 15:22:38.445942: step: 440/529, loss: 0.010650979354977608
2023-01-22 15:22:39.519384: step: 444/529, loss: 0.00836743600666523
2023-01-22 15:22:40.585431: step: 448/529, loss: 0.006790465675294399
2023-01-22 15:22:41.657433: step: 452/529, loss: 0.0030433835927397013
2023-01-22 15:22:42.717342: step: 456/529, loss: 0.005927408114075661
2023-01-22 15:22:43.813113: step: 460/529, loss: 0.001353300060145557
2023-01-22 15:22:44.882650: step: 464/529, loss: 0.0038225119933485985
2023-01-22 15:22:45.939841: step: 468/529, loss: 0.00865098275244236
2023-01-22 15:22:47.015098: step: 472/529, loss: 0.04484766721725464
2023-01-22 15:22:48.080094: step: 476/529, loss: 0.0029634395614266396
2023-01-22 15:22:49.149230: step: 480/529, loss: 0.021705979481339455
2023-01-22 15:22:50.205746: step: 484/529, loss: 0.006049150601029396
2023-01-22 15:22:51.261609: step: 488/529, loss: 0.09693079441785812
2023-01-22 15:22:52.344594: step: 492/529, loss: 0.006209753453731537
2023-01-22 15:22:53.414332: step: 496/529, loss: 0.006873418111354113
2023-01-22 15:22:54.476038: step: 500/529, loss: 0.002736093942075968
2023-01-22 15:22:55.566549: step: 504/529, loss: 0.010693483985960484
2023-01-22 15:22:56.636927: step: 508/529, loss: 0.009600749239325523
2023-01-22 15:22:57.713554: step: 512/529, loss: 0.017675578594207764
2023-01-22 15:22:58.778309: step: 516/529, loss: 0.007996274158358574
2023-01-22 15:22:59.845176: step: 520/529, loss: 0.005945304408669472
2023-01-22 15:23:00.914554: step: 524/529, loss: 0.0015728590078651905
2023-01-22 15:23:01.988941: step: 528/529, loss: 0.0032930667512118816
2023-01-22 15:23:03.045951: step: 532/529, loss: 0.009243723936378956
2023-01-22 15:23:04.117340: step: 536/529, loss: 0.02138587459921837
2023-01-22 15:23:05.179237: step: 540/529, loss: 0.009292421862483025
2023-01-22 15:23:06.248884: step: 544/529, loss: 0.0050464109517633915
2023-01-22 15:23:07.321054: step: 548/529, loss: 0.008963420987129211
2023-01-22 15:23:08.384262: step: 552/529, loss: 0.00029907815041951835
2023-01-22 15:23:09.464773: step: 556/529, loss: 0.004303612280637026
2023-01-22 15:23:10.526983: step: 560/529, loss: 0.014759157784283161
2023-01-22 15:23:11.593288: step: 564/529, loss: 0.004573407582938671
2023-01-22 15:23:12.673154: step: 568/529, loss: 0.016875358298420906
2023-01-22 15:23:13.734499: step: 572/529, loss: 0.051509033888578415
2023-01-22 15:23:14.806369: step: 576/529, loss: 0.0021495213732123375
2023-01-22 15:23:15.852179: step: 580/529, loss: 0.016047941520810127
2023-01-22 15:23:16.914795: step: 584/529, loss: 0.013519387692213058
2023-01-22 15:23:17.990211: step: 588/529, loss: 0.016106870025396347
2023-01-22 15:23:19.068102: step: 592/529, loss: 0.00716715632006526
2023-01-22 15:23:20.150018: step: 596/529, loss: 0.008574715815484524
2023-01-22 15:23:21.231029: step: 600/529, loss: 0.006716846022754908
2023-01-22 15:23:22.302771: step: 604/529, loss: 0.0076522547751665115
2023-01-22 15:23:23.377685: step: 608/529, loss: 0.00690355384722352
2023-01-22 15:23:24.452185: step: 612/529, loss: 0.0062452019192278385
2023-01-22 15:23:25.520313: step: 616/529, loss: 0.0038067682180553675
2023-01-22 15:23:26.585630: step: 620/529, loss: 0.009516894817352295
2023-01-22 15:23:27.659673: step: 624/529, loss: 0.010676353238523006
2023-01-22 15:23:28.724145: step: 628/529, loss: 0.021904734894633293
2023-01-22 15:23:29.804970: step: 632/529, loss: 0.0028012630064040422
2023-01-22 15:23:30.893129: step: 636/529, loss: 0.007320138160139322
2023-01-22 15:23:31.958777: step: 640/529, loss: 0.0008662366308271885
2023-01-22 15:23:33.040650: step: 644/529, loss: 0.0037315881345421076
2023-01-22 15:23:34.118671: step: 648/529, loss: 0.003295026021078229
2023-01-22 15:23:35.185422: step: 652/529, loss: 0.05796245485544205
2023-01-22 15:23:36.252279: step: 656/529, loss: 0.0062024155631661415
2023-01-22 15:23:37.316828: step: 660/529, loss: 0.005118315573781729
2023-01-22 15:23:38.378875: step: 664/529, loss: 0.012726697139441967
2023-01-22 15:23:39.461896: step: 668/529, loss: 0.012336802668869495
2023-01-22 15:23:40.532589: step: 672/529, loss: 0.006135644856840372
2023-01-22 15:23:41.613420: step: 676/529, loss: 0.00828030239790678
2023-01-22 15:23:42.696170: step: 680/529, loss: 0.004346923902630806
2023-01-22 15:23:43.757981: step: 684/529, loss: 0.0007528209243901074
2023-01-22 15:23:44.850305: step: 688/529, loss: 0.0027078480925410986
2023-01-22 15:23:45.918439: step: 692/529, loss: 8.653145778225735e-05
2023-01-22 15:23:47.006189: step: 696/529, loss: 0.0047794790007174015
2023-01-22 15:23:48.071203: step: 700/529, loss: 0.020407507196068764
2023-01-22 15:23:49.147540: step: 704/529, loss: 0.005711992736905813
2023-01-22 15:23:50.241669: step: 708/529, loss: 0.026463540270924568
2023-01-22 15:23:51.301883: step: 712/529, loss: 0.005868465639650822
2023-01-22 15:23:52.358364: step: 716/529, loss: 0.0018788294401019812
2023-01-22 15:23:53.420203: step: 720/529, loss: 0.0010879709152504802
2023-01-22 15:23:54.495653: step: 724/529, loss: 0.009109952487051487
2023-01-22 15:23:55.574172: step: 728/529, loss: 0.003531214315444231
2023-01-22 15:23:56.663075: step: 732/529, loss: 0.015216343104839325
2023-01-22 15:23:57.719561: step: 736/529, loss: 0.015219041146337986
2023-01-22 15:23:58.794498: step: 740/529, loss: 0.0019862083718180656
2023-01-22 15:23:59.870132: step: 744/529, loss: 0.00816744938492775
2023-01-22 15:24:00.926918: step: 748/529, loss: 0.010270909406244755
2023-01-22 15:24:01.991018: step: 752/529, loss: 0.0005229077069088817
2023-01-22 15:24:03.063346: step: 756/529, loss: 0.008877737447619438
2023-01-22 15:24:04.138614: step: 760/529, loss: 0.012867475859820843
2023-01-22 15:24:05.211150: step: 764/529, loss: 0.004842827096581459
2023-01-22 15:24:06.282454: step: 768/529, loss: 0.03432096540927887
2023-01-22 15:24:07.362484: step: 772/529, loss: 0.005269247107207775
2023-01-22 15:24:08.456810: step: 776/529, loss: 0.013661100529134274
2023-01-22 15:24:09.541626: step: 780/529, loss: 0.0031797976698726416
2023-01-22 15:24:10.605657: step: 784/529, loss: 0.022498922422528267
2023-01-22 15:24:11.671523: step: 788/529, loss: 0.0077417767606675625
2023-01-22 15:24:12.750537: step: 792/529, loss: 0.00687831174582243
2023-01-22 15:24:13.874301: step: 796/529, loss: 0.015061895363032818
2023-01-22 15:24:14.947470: step: 800/529, loss: 0.006087824702262878
2023-01-22 15:24:16.010010: step: 804/529, loss: 0.019029002636671066
2023-01-22 15:24:17.099997: step: 808/529, loss: 0.02404755726456642
2023-01-22 15:24:18.179655: step: 812/529, loss: 0.012975217774510384
2023-01-22 15:24:19.250309: step: 816/529, loss: 0.07651344686746597
2023-01-22 15:24:20.308285: step: 820/529, loss: 0.006077010650187731
2023-01-22 15:24:21.375152: step: 824/529, loss: 0.03473775088787079
2023-01-22 15:24:22.437809: step: 828/529, loss: 0.027194304391741753
2023-01-22 15:24:23.507400: step: 832/529, loss: 0.007897722534835339
2023-01-22 15:24:24.577697: step: 836/529, loss: 0.00758944870904088
2023-01-22 15:24:25.660512: step: 840/529, loss: 0.0044963182881474495
2023-01-22 15:24:26.745428: step: 844/529, loss: 0.001894872635602951
2023-01-22 15:24:27.811553: step: 848/529, loss: 0.0027859548572450876
2023-01-22 15:24:28.885577: step: 852/529, loss: 0.010159488767385483
2023-01-22 15:24:29.947154: step: 856/529, loss: 0.00764209870249033
2023-01-22 15:24:31.017846: step: 860/529, loss: 0.009537285193800926
2023-01-22 15:24:32.101907: step: 864/529, loss: 0.007376695517450571
2023-01-22 15:24:33.178243: step: 868/529, loss: 0.013290522620081902
2023-01-22 15:24:34.249785: step: 872/529, loss: 0.0003908459038939327
2023-01-22 15:24:35.300755: step: 876/529, loss: 0.019253509119153023
2023-01-22 15:24:36.394905: step: 880/529, loss: 0.0057402984239161015
2023-01-22 15:24:37.456309: step: 884/529, loss: 0.012292454950511456
2023-01-22 15:24:38.531197: step: 888/529, loss: 0.022274423390626907
2023-01-22 15:24:39.586706: step: 892/529, loss: 0.001244120649062097
2023-01-22 15:24:40.652243: step: 896/529, loss: 0.007655525114387274
2023-01-22 15:24:41.707067: step: 900/529, loss: 0.004843244794756174
2023-01-22 15:24:42.785640: step: 904/529, loss: 0.05078835412859917
2023-01-22 15:24:43.852591: step: 908/529, loss: 0.014287375845015049
2023-01-22 15:24:44.939470: step: 912/529, loss: 0.00481020612642169
2023-01-22 15:24:46.002330: step: 916/529, loss: 0.0033847445156425238
2023-01-22 15:24:47.069997: step: 920/529, loss: 0.0026354873552918434
2023-01-22 15:24:48.141282: step: 924/529, loss: 0.001621701754629612
2023-01-22 15:24:49.206208: step: 928/529, loss: 0.0041492353193461895
2023-01-22 15:24:50.270480: step: 932/529, loss: 0.0052189333364367485
2023-01-22 15:24:51.360333: step: 936/529, loss: 0.007679773028939962
2023-01-22 15:24:52.433750: step: 940/529, loss: 0.00989400502294302
2023-01-22 15:24:53.490478: step: 944/529, loss: 0.016143208369612694
2023-01-22 15:24:54.556854: step: 948/529, loss: 0.007086863741278648
2023-01-22 15:24:55.627608: step: 952/529, loss: 0.003801848040893674
2023-01-22 15:24:56.724407: step: 956/529, loss: 0.008233774453401566
2023-01-22 15:24:57.785692: step: 960/529, loss: 0.02469220571219921
2023-01-22 15:24:58.858839: step: 964/529, loss: 0.027191689237952232
2023-01-22 15:24:59.939797: step: 968/529, loss: 0.028196467086672783
2023-01-22 15:25:01.010949: step: 972/529, loss: 0.0027674532029777765
2023-01-22 15:25:02.084686: step: 976/529, loss: 0.002779850736260414
2023-01-22 15:25:03.148352: step: 980/529, loss: 0.0036088430788367987
2023-01-22 15:25:04.219817: step: 984/529, loss: 0.004137295763939619
2023-01-22 15:25:05.288904: step: 988/529, loss: 0.00014658411964774132
2023-01-22 15:25:06.354792: step: 992/529, loss: 0.003567516803741455
2023-01-22 15:25:07.427864: step: 996/529, loss: 0.007545940112322569
2023-01-22 15:25:08.500113: step: 1000/529, loss: 0.03780417516827583
2023-01-22 15:25:09.562958: step: 1004/529, loss: 0.004817961249500513
2023-01-22 15:25:10.623628: step: 1008/529, loss: 0.004160279408097267
2023-01-22 15:25:11.692209: step: 1012/529, loss: 0.0052159070037305355
2023-01-22 15:25:12.761713: step: 1016/529, loss: 0.003921581897884607
2023-01-22 15:25:13.824661: step: 1020/529, loss: 0.014333940111100674
2023-01-22 15:25:14.906413: step: 1024/529, loss: 0.005078762304037809
2023-01-22 15:25:15.981771: step: 1028/529, loss: 0.004200531169772148
2023-01-22 15:25:17.050995: step: 1032/529, loss: 0.025001676753163338
2023-01-22 15:25:18.119504: step: 1036/529, loss: 0.01375879067927599
2023-01-22 15:25:19.204007: step: 1040/529, loss: 0.011037852615118027
2023-01-22 15:25:20.261607: step: 1044/529, loss: 0.0011660035233944654
2023-01-22 15:25:21.322046: step: 1048/529, loss: 0.04122757911682129
2023-01-22 15:25:22.387111: step: 1052/529, loss: 0.008421225473284721
2023-01-22 15:25:23.452502: step: 1056/529, loss: 0.013406566344201565
2023-01-22 15:25:24.522389: step: 1060/529, loss: 0.0048745060339570045
2023-01-22 15:25:25.594836: step: 1064/529, loss: 0.003069806145504117
2023-01-22 15:25:26.659530: step: 1068/529, loss: 0.001798956305719912
2023-01-22 15:25:27.761854: step: 1072/529, loss: 0.014165295287966728
2023-01-22 15:25:28.840272: step: 1076/529, loss: 0.013126375153660774
2023-01-22 15:25:29.947489: step: 1080/529, loss: 0.010651309043169022
2023-01-22 15:25:31.026829: step: 1084/529, loss: 0.009359825402498245
2023-01-22 15:25:32.098201: step: 1088/529, loss: 0.00133776746224612
2023-01-22 15:25:33.165315: step: 1092/529, loss: 0.006887001916766167
2023-01-22 15:25:34.243657: step: 1096/529, loss: 0.005140291526913643
2023-01-22 15:25:35.334119: step: 1100/529, loss: 0.012525931932032108
2023-01-22 15:25:36.430952: step: 1104/529, loss: 0.002243511378765106
2023-01-22 15:25:37.513391: step: 1108/529, loss: 0.009197882376611233
2023-01-22 15:25:38.596122: step: 1112/529, loss: 0.007377720903605223
2023-01-22 15:25:39.667680: step: 1116/529, loss: 0.012514114379882812
2023-01-22 15:25:40.736847: step: 1120/529, loss: 0.011046313680708408
2023-01-22 15:25:41.793769: step: 1124/529, loss: 0.008019635453820229
2023-01-22 15:25:42.887211: step: 1128/529, loss: 0.004647758789360523
2023-01-22 15:25:43.948862: step: 1132/529, loss: 0.010757249779999256
2023-01-22 15:25:45.018939: step: 1136/529, loss: 0.0026242982130497694
2023-01-22 15:25:46.078657: step: 1140/529, loss: 0.002294326201081276
2023-01-22 15:25:47.149567: step: 1144/529, loss: 0.0063705043867230415
2023-01-22 15:25:48.220516: step: 1148/529, loss: 0.023698003962635994
2023-01-22 15:25:49.315323: step: 1152/529, loss: 0.0035925637930631638
2023-01-22 15:25:50.373809: step: 1156/529, loss: 0.003907541744410992
2023-01-22 15:25:51.443292: step: 1160/529, loss: 0.01026979461312294
2023-01-22 15:25:52.505857: step: 1164/529, loss: 0.046339161694049835
2023-01-22 15:25:53.569140: step: 1168/529, loss: 0.0009419429115951061
2023-01-22 15:25:54.628026: step: 1172/529, loss: 0.008353786543011665
2023-01-22 15:25:55.705051: step: 1176/529, loss: 0.0013033384457230568
2023-01-22 15:25:56.789076: step: 1180/529, loss: 0.017704816535115242
2023-01-22 15:25:57.881698: step: 1184/529, loss: 0.009403382427990437
2023-01-22 15:25:58.953799: step: 1188/529, loss: 0.0026736774016171694
2023-01-22 15:26:00.021486: step: 1192/529, loss: 0.018443763256072998
2023-01-22 15:26:01.085450: step: 1196/529, loss: 0.012267779558897018
2023-01-22 15:26:02.164805: step: 1200/529, loss: 0.007556559517979622
2023-01-22 15:26:03.259605: step: 1204/529, loss: 0.01756388694047928
2023-01-22 15:26:04.339947: step: 1208/529, loss: 0.006873392499983311
2023-01-22 15:26:05.427253: step: 1212/529, loss: 0.001942845294252038
2023-01-22 15:26:06.504923: step: 1216/529, loss: 0.020934734493494034
2023-01-22 15:26:07.589632: step: 1220/529, loss: 0.04420597851276398
2023-01-22 15:26:08.665421: step: 1224/529, loss: 0.012765571475028992
2023-01-22 15:26:09.726519: step: 1228/529, loss: 0.013465002179145813
2023-01-22 15:26:10.815095: step: 1232/529, loss: 0.006584836170077324
2023-01-22 15:26:11.886256: step: 1236/529, loss: 0.01110995002090931
2023-01-22 15:26:12.944959: step: 1240/529, loss: 0.0009530002134852111
2023-01-22 15:26:14.028008: step: 1244/529, loss: 0.0005308607942424715
2023-01-22 15:26:15.101077: step: 1248/529, loss: 0.011963690631091595
2023-01-22 15:26:16.164134: step: 1252/529, loss: 0.028013112023472786
2023-01-22 15:26:17.237175: step: 1256/529, loss: 0.0014048839220777154
2023-01-22 15:26:18.303128: step: 1260/529, loss: 0.022144142538309097
2023-01-22 15:26:19.365615: step: 1264/529, loss: 0.010153418406844139
2023-01-22 15:26:20.424415: step: 1268/529, loss: 0.0351460836827755
2023-01-22 15:26:21.477418: step: 1272/529, loss: 0.01911328360438347
2023-01-22 15:26:22.550330: step: 1276/529, loss: 0.0035000531934201717
2023-01-22 15:26:23.611621: step: 1280/529, loss: 0.014711982570588589
2023-01-22 15:26:24.687738: step: 1284/529, loss: 0.020019857212901115
2023-01-22 15:26:25.740465: step: 1288/529, loss: 0.0009073346736840904
2023-01-22 15:26:26.814123: step: 1292/529, loss: 0.006496801041066647
2023-01-22 15:26:27.880109: step: 1296/529, loss: 0.005249849054962397
2023-01-22 15:26:28.961145: step: 1300/529, loss: 0.09730228781700134
2023-01-22 15:26:30.026553: step: 1304/529, loss: 0.00010446640953887254
2023-01-22 15:26:31.102737: step: 1308/529, loss: 0.0018612323328852654
2023-01-22 15:26:32.169855: step: 1312/529, loss: 0.0047396095469594
2023-01-22 15:26:33.230531: step: 1316/529, loss: 0.003213820978999138
2023-01-22 15:26:34.312867: step: 1320/529, loss: 0.0008751116110943258
2023-01-22 15:26:35.373218: step: 1324/529, loss: 0.011827266775071621
2023-01-22 15:26:36.437538: step: 1328/529, loss: 0.014146394096314907
2023-01-22 15:26:37.533619: step: 1332/529, loss: 0.0036795600317418575
2023-01-22 15:26:38.610549: step: 1336/529, loss: 0.011944161728024483
2023-01-22 15:26:39.680891: step: 1340/529, loss: 0.04109463095664978
2023-01-22 15:26:40.772640: step: 1344/529, loss: 0.009228614158928394
2023-01-22 15:26:41.835400: step: 1348/529, loss: 0.0016489842673763633
2023-01-22 15:26:42.932083: step: 1352/529, loss: 0.01078275591135025
2023-01-22 15:26:44.020400: step: 1356/529, loss: 0.0020169378258287907
2023-01-22 15:26:45.091794: step: 1360/529, loss: 0.013365722261369228
2023-01-22 15:26:46.186106: step: 1364/529, loss: 0.034779567271471024
2023-01-22 15:26:47.262846: step: 1368/529, loss: 0.011920524761080742
2023-01-22 15:26:48.347776: step: 1372/529, loss: 0.005875522270798683
2023-01-22 15:26:49.420545: step: 1376/529, loss: 0.00880617368966341
2023-01-22 15:26:50.482041: step: 1380/529, loss: 0.008332458324730396
2023-01-22 15:26:51.558859: step: 1384/529, loss: 0.013337942771613598
2023-01-22 15:26:52.651948: step: 1388/529, loss: 0.009446166455745697
2023-01-22 15:26:53.717184: step: 1392/529, loss: 0.016431570053100586
2023-01-22 15:26:54.796499: step: 1396/529, loss: 0.021695852279663086
2023-01-22 15:26:55.876891: step: 1400/529, loss: 0.0033575354609638453
2023-01-22 15:26:56.957477: step: 1404/529, loss: 0.037024397403001785
2023-01-22 15:26:58.030951: step: 1408/529, loss: 0.021687215194106102
2023-01-22 15:26:59.114602: step: 1412/529, loss: 0.0077699655666947365
2023-01-22 15:27:00.190667: step: 1416/529, loss: 0.0004141340032219887
2023-01-22 15:27:01.277566: step: 1420/529, loss: 0.003890436142683029
2023-01-22 15:27:02.339617: step: 1424/529, loss: 0.0012461403384804726
2023-01-22 15:27:03.411023: step: 1428/529, loss: 0.0058377389796078205
2023-01-22 15:27:04.484753: step: 1432/529, loss: 0.009935363195836544
2023-01-22 15:27:05.557621: step: 1436/529, loss: 0.01389356330037117
2023-01-22 15:27:06.635535: step: 1440/529, loss: 0.008554589003324509
2023-01-22 15:27:07.712910: step: 1444/529, loss: 0.065959133207798
2023-01-22 15:27:08.811783: step: 1448/529, loss: 0.037170734256505966
2023-01-22 15:27:09.870129: step: 1452/529, loss: 0.004982625599950552
2023-01-22 15:27:10.953849: step: 1456/529, loss: 0.0029572409112006426
2023-01-22 15:27:12.009358: step: 1460/529, loss: 1.1880091733473819e-05
2023-01-22 15:27:13.114763: step: 1464/529, loss: 0.011264627799391747
2023-01-22 15:27:14.184034: step: 1468/529, loss: 0.0030728185083717108
2023-01-22 15:27:15.249189: step: 1472/529, loss: 0.007966026663780212
2023-01-22 15:27:16.324737: step: 1476/529, loss: 0.024318084120750427
2023-01-22 15:27:17.400403: step: 1480/529, loss: 0.0017617353005334735
2023-01-22 15:27:18.490658: step: 1484/529, loss: 0.034694306552410126
2023-01-22 15:27:19.607088: step: 1488/529, loss: 0.08897338062524796
2023-01-22 15:27:20.681358: step: 1492/529, loss: 0.013717732392251492
2023-01-22 15:27:21.777270: step: 1496/529, loss: 0.0101424315944314
2023-01-22 15:27:22.856843: step: 1500/529, loss: 0.0019414408598095179
2023-01-22 15:27:23.944563: step: 1504/529, loss: 0.002259514993056655
2023-01-22 15:27:24.999166: step: 1508/529, loss: 0.0036597619764506817
2023-01-22 15:27:26.076659: step: 1512/529, loss: 0.04667592793703079
2023-01-22 15:27:27.159115: step: 1516/529, loss: 0.017591072246432304
2023-01-22 15:27:28.228968: step: 1520/529, loss: 0.0001521392841823399
2023-01-22 15:27:29.303914: step: 1524/529, loss: 0.013777170330286026
2023-01-22 15:27:30.369155: step: 1528/529, loss: 0.004690087866038084
2023-01-22 15:27:31.438749: step: 1532/529, loss: 0.003948920406401157
2023-01-22 15:27:32.522956: step: 1536/529, loss: 0.07563547044992447
2023-01-22 15:27:33.585507: step: 1540/529, loss: 0.016616258770227432
2023-01-22 15:27:34.643910: step: 1544/529, loss: 0.005448971409350634
2023-01-22 15:27:35.717740: step: 1548/529, loss: 0.009977582842111588
2023-01-22 15:27:36.778348: step: 1552/529, loss: 0.0061608958058059216
2023-01-22 15:27:37.857598: step: 1556/529, loss: 0.002114545786753297
2023-01-22 15:27:38.928290: step: 1560/529, loss: 0.008750095963478088
2023-01-22 15:27:40.000445: step: 1564/529, loss: 0.004472228232771158
2023-01-22 15:27:41.087888: step: 1568/529, loss: 0.008842178620398045
2023-01-22 15:27:42.153286: step: 1572/529, loss: 0.003872595727443695
2023-01-22 15:27:43.222422: step: 1576/529, loss: 0.0160906333476305
2023-01-22 15:27:44.291697: step: 1580/529, loss: 0.012151301838457584
2023-01-22 15:27:45.360762: step: 1584/529, loss: 0.008990393951535225
2023-01-22 15:27:46.445293: step: 1588/529, loss: 0.0468946248292923
2023-01-22 15:27:47.520864: step: 1592/529, loss: 0.0056581636890769005
2023-01-22 15:27:48.571672: step: 1596/529, loss: 0.009731780737638474
2023-01-22 15:27:49.647435: step: 1600/529, loss: 0.012729713693261147
2023-01-22 15:27:50.713902: step: 1604/529, loss: 0.055125731974840164
2023-01-22 15:27:51.787272: step: 1608/529, loss: 0.07322222739458084
2023-01-22 15:27:52.870315: step: 1612/529, loss: 0.05458943918347359
2023-01-22 15:27:53.974668: step: 1616/529, loss: 0.005859483499079943
2023-01-22 15:27:55.058333: step: 1620/529, loss: 0.017146673053503036
2023-01-22 15:27:56.137054: step: 1624/529, loss: 0.016247712075710297
2023-01-22 15:27:57.209125: step: 1628/529, loss: 0.008485060185194016
2023-01-22 15:27:58.296439: step: 1632/529, loss: 0.0033759544603526592
2023-01-22 15:27:59.370630: step: 1636/529, loss: 0.007815441116690636
2023-01-22 15:28:00.431911: step: 1640/529, loss: 0.003971477504819632
2023-01-22 15:28:01.509925: step: 1644/529, loss: 0.006523026153445244
2023-01-22 15:28:02.589249: step: 1648/529, loss: 0.0017680278979241848
2023-01-22 15:28:03.691960: step: 1652/529, loss: 0.0053138285875320435
2023-01-22 15:28:04.771498: step: 1656/529, loss: 0.03768530488014221
2023-01-22 15:28:05.849948: step: 1660/529, loss: 0.0081466194242239
2023-01-22 15:28:06.919633: step: 1664/529, loss: 0.007737896870821714
2023-01-22 15:28:07.991055: step: 1668/529, loss: 0.011441116221249104
2023-01-22 15:28:09.053381: step: 1672/529, loss: 0.01290665753185749
2023-01-22 15:28:10.117288: step: 1676/529, loss: 0.0031395989935845137
2023-01-22 15:28:11.183581: step: 1680/529, loss: 0.01727680116891861
2023-01-22 15:28:12.272226: step: 1684/529, loss: 0.003604139434173703
2023-01-22 15:28:13.354295: step: 1688/529, loss: 0.0049101728945970535
2023-01-22 15:28:14.434631: step: 1692/529, loss: 0.003701012348756194
2023-01-22 15:28:15.518787: step: 1696/529, loss: 0.02277238667011261
2023-01-22 15:28:16.589673: step: 1700/529, loss: 0.0006703791441395879
2023-01-22 15:28:17.656228: step: 1704/529, loss: 0.012263515032827854
2023-01-22 15:28:18.727739: step: 1708/529, loss: 0.003391839098185301
2023-01-22 15:28:19.805622: step: 1712/529, loss: 0.0024109166115522385
2023-01-22 15:28:20.890256: step: 1716/529, loss: 0.0038264933973550797
2023-01-22 15:28:21.975116: step: 1720/529, loss: 0.03251434490084648
2023-01-22 15:28:23.049478: step: 1724/529, loss: 0.002734135603532195
2023-01-22 15:28:24.111174: step: 1728/529, loss: 0.0023881003726273775
2023-01-22 15:28:25.188380: step: 1732/529, loss: 0.011680040508508682
2023-01-22 15:28:26.254219: step: 1736/529, loss: 0.0020366625394672155
2023-01-22 15:28:27.332397: step: 1740/529, loss: 0.00933763850480318
2023-01-22 15:28:28.398867: step: 1744/529, loss: 0.0062961638905107975
2023-01-22 15:28:29.484193: step: 1748/529, loss: 0.0038678504060953856
2023-01-22 15:28:30.564885: step: 1752/529, loss: 0.010100818239152431
2023-01-22 15:28:31.653886: step: 1756/529, loss: 0.010858502238988876
2023-01-22 15:28:32.737256: step: 1760/529, loss: 0.00944447424262762
2023-01-22 15:28:33.818068: step: 1764/529, loss: 0.017714692279696465
2023-01-22 15:28:34.882275: step: 1768/529, loss: 0.006214953027665615
2023-01-22 15:28:35.984086: step: 1772/529, loss: 0.0027611658442765474
2023-01-22 15:28:37.065637: step: 1776/529, loss: 0.037212248891592026
2023-01-22 15:28:38.126645: step: 1780/529, loss: 0.008566268719732761
2023-01-22 15:28:39.207081: step: 1784/529, loss: 0.01868366077542305
2023-01-22 15:28:40.268784: step: 1788/529, loss: 0.002395871328189969
2023-01-22 15:28:41.344873: step: 1792/529, loss: 0.005026060622185469
2023-01-22 15:28:42.424288: step: 1796/529, loss: 0.009730721823871136
2023-01-22 15:28:43.494104: step: 1800/529, loss: 0.019793130457401276
2023-01-22 15:28:44.573503: step: 1804/529, loss: 0.015989243984222412
2023-01-22 15:28:45.666067: step: 1808/529, loss: 0.06439851224422455
2023-01-22 15:28:46.718462: step: 1812/529, loss: 0.002367462031543255
2023-01-22 15:28:47.784390: step: 1816/529, loss: 0.006908094510436058
2023-01-22 15:28:48.864130: step: 1820/529, loss: 0.0035598762333393097
2023-01-22 15:28:49.931309: step: 1824/529, loss: 0.0004046270623803139
2023-01-22 15:28:51.016443: step: 1828/529, loss: 0.010219672694802284
2023-01-22 15:28:52.093295: step: 1832/529, loss: 0.056064531207084656
2023-01-22 15:28:53.157738: step: 1836/529, loss: 0.003887404687702656
2023-01-22 15:28:54.234782: step: 1840/529, loss: 0.010096265003085136
2023-01-22 15:28:55.293410: step: 1844/529, loss: 0.01793801039457321
2023-01-22 15:28:56.358576: step: 1848/529, loss: 0.0017579769482836127
2023-01-22 15:28:57.431043: step: 1852/529, loss: 0.032831039279699326
2023-01-22 15:28:58.505976: step: 1856/529, loss: 0.01784345507621765
2023-01-22 15:28:59.578116: step: 1860/529, loss: 0.008065914735198021
2023-01-22 15:29:00.643611: step: 1864/529, loss: 0.008744626305997372
2023-01-22 15:29:01.704996: step: 1868/529, loss: 0.006435508374124765
2023-01-22 15:29:02.775919: step: 1872/529, loss: 0.010720211081206799
2023-01-22 15:29:03.838361: step: 1876/529, loss: 0.01839168556034565
2023-01-22 15:29:04.921078: step: 1880/529, loss: 0.013671822845935822
2023-01-22 15:29:05.975318: step: 1884/529, loss: 0.0024428698234260082
2023-01-22 15:29:07.030677: step: 1888/529, loss: 0.019225915893912315
2023-01-22 15:29:08.092918: step: 1892/529, loss: 0.006163674872368574
2023-01-22 15:29:09.149403: step: 1896/529, loss: 0.0037699565291404724
2023-01-22 15:29:10.223916: step: 1900/529, loss: 0.013765586540102959
2023-01-22 15:29:11.288146: step: 1904/529, loss: 0.013111330568790436
2023-01-22 15:29:12.344674: step: 1908/529, loss: 0.0034677963703870773
2023-01-22 15:29:13.412554: step: 1912/529, loss: 0.010969200171530247
2023-01-22 15:29:14.480839: step: 1916/529, loss: 0.005650100763887167
2023-01-22 15:29:15.540376: step: 1920/529, loss: 0.007209569215774536
2023-01-22 15:29:16.607416: step: 1924/529, loss: 0.022459348663687706
2023-01-22 15:29:17.674265: step: 1928/529, loss: 0.018021751195192337
2023-01-22 15:29:18.748780: step: 1932/529, loss: 0.01943148858845234
2023-01-22 15:29:19.810626: step: 1936/529, loss: 0.003262628335505724
2023-01-22 15:29:20.865651: step: 1940/529, loss: 0.010799327865242958
2023-01-22 15:29:21.960541: step: 1944/529, loss: 0.004368732217699289
2023-01-22 15:29:23.032794: step: 1948/529, loss: 0.027089713141322136
2023-01-22 15:29:24.106207: step: 1952/529, loss: 0.028108585625886917
2023-01-22 15:29:25.162361: step: 1956/529, loss: 0.006967587396502495
2023-01-22 15:29:26.242888: step: 1960/529, loss: 0.000502319831866771
2023-01-22 15:29:27.307973: step: 1964/529, loss: 0.006585522089153528
2023-01-22 15:29:28.375451: step: 1968/529, loss: 0.006087393034249544
2023-01-22 15:29:29.437620: step: 1972/529, loss: 0.0020255688577890396
2023-01-22 15:29:30.493509: step: 1976/529, loss: 0.0011896903160959482
2023-01-22 15:29:31.576910: step: 1980/529, loss: 0.015363163314759731
2023-01-22 15:29:32.645410: step: 1984/529, loss: 0.004335400182753801
2023-01-22 15:29:33.724863: step: 1988/529, loss: 0.01175539568066597
2023-01-22 15:29:34.844707: step: 1992/529, loss: 0.011699249967932701
2023-01-22 15:29:35.928914: step: 1996/529, loss: 0.02545962482690811
2023-01-22 15:29:37.003764: step: 2000/529, loss: 0.0006460958393290639
2023-01-22 15:29:38.080151: step: 2004/529, loss: 0.009515242651104927
2023-01-22 15:29:39.134095: step: 2008/529, loss: 0.04111385717988014
2023-01-22 15:29:40.194710: step: 2012/529, loss: 0.005877222865819931
2023-01-22 15:29:41.278138: step: 2016/529, loss: 0.007505779154598713
2023-01-22 15:29:42.329285: step: 2020/529, loss: 0.008421323262155056
2023-01-22 15:29:43.415154: step: 2024/529, loss: 0.016268698498606682
2023-01-22 15:29:44.491174: step: 2028/529, loss: 0.012657465413212776
2023-01-22 15:29:45.549710: step: 2032/529, loss: 0.005319786258041859
2023-01-22 15:29:46.615711: step: 2036/529, loss: 0.023542700335383415
2023-01-22 15:29:47.693505: step: 2040/529, loss: 0.006941151339560747
2023-01-22 15:29:48.792592: step: 2044/529, loss: 0.0069933389313519
2023-01-22 15:29:49.860333: step: 2048/529, loss: 0.008115910924971104
2023-01-22 15:29:50.945286: step: 2052/529, loss: 0.0010779907461255789
2023-01-22 15:29:52.026878: step: 2056/529, loss: 0.020473960787057877
2023-01-22 15:29:53.095907: step: 2060/529, loss: 0.007803792133927345
2023-01-22 15:29:54.166959: step: 2064/529, loss: 0.0056096287444233894
2023-01-22 15:29:55.246824: step: 2068/529, loss: 0.02149871550500393
2023-01-22 15:29:56.313353: step: 2072/529, loss: 0.011949121952056885
2023-01-22 15:29:57.377067: step: 2076/529, loss: 0.011404074728488922
2023-01-22 15:29:58.434610: step: 2080/529, loss: 0.010310224257409573
2023-01-22 15:29:59.495612: step: 2084/529, loss: 0.013979884795844555
2023-01-22 15:30:00.577202: step: 2088/529, loss: 0.013739165849983692
2023-01-22 15:30:01.643108: step: 2092/529, loss: 0.0023008326534181833
2023-01-22 15:30:02.712658: step: 2096/529, loss: 0.012866536155343056
2023-01-22 15:30:03.790149: step: 2100/529, loss: 0.004443677142262459
2023-01-22 15:30:04.886945: step: 2104/529, loss: 0.045822624117136
2023-01-22 15:30:05.959193: step: 2108/529, loss: 0.009228694252669811
2023-01-22 15:30:07.032281: step: 2112/529, loss: 0.007563404273241758
2023-01-22 15:30:08.111023: step: 2116/529, loss: 0.009492633864283562
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3263720784641068, 'r': 0.3709618121442125, 'f1': 0.3472413410301954}, 'combined': 0.2558620407590913, 'stategy': 1, 'epoch': 3}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32948847710256257, 'r': 0.3088954472836524, 'f1': 0.318859816550867}, 'combined': 0.20816754862906342, 'stategy': 1, 'epoch': 3}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 3}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
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': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3263720784641068, 'r': 0.3709618121442125, 'f1': 0.3472413410301954}, 'combined': 0.2558620407590913, 'stategy': 1, 'epoch': 3}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32948847710256257, 'r': 0.3088954472836524, 'f1': 0.318859816550867}, 'combined': 0.20816754862906342, 'stategy': 1, 'epoch': 3}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 15:33:12.736456: step: 4/529, loss: 0.005306081846356392
2023-01-22 15:33:13.823041: step: 8/529, loss: 0.01165945827960968
2023-01-22 15:33:14.876011: step: 12/529, loss: 0.025551021099090576
2023-01-22 15:33:15.943268: step: 16/529, loss: 0.00669049471616745
2023-01-22 15:33:17.003723: step: 20/529, loss: 0.002775543835014105
2023-01-22 15:33:18.073403: step: 24/529, loss: 0.0016739120474085212
2023-01-22 15:33:19.123889: step: 28/529, loss: 0.004657388664782047
2023-01-22 15:33:20.190945: step: 32/529, loss: 0.0074105532839894295
2023-01-22 15:33:21.248130: step: 36/529, loss: 0.0015190700069069862
2023-01-22 15:33:22.307723: step: 40/529, loss: 0.04774459823966026
2023-01-22 15:33:23.368677: step: 44/529, loss: 0.007806417997926474
2023-01-22 15:33:24.433076: step: 48/529, loss: 0.006820150185376406
2023-01-22 15:33:25.482426: step: 52/529, loss: 0.0010121590457856655
2023-01-22 15:33:26.555464: step: 56/529, loss: 0.009199569001793861
2023-01-22 15:33:27.618585: step: 60/529, loss: 0.013597894459962845
2023-01-22 15:33:28.674769: step: 64/529, loss: 0.00033319779322482646
2023-01-22 15:33:29.739105: step: 68/529, loss: 0.0039946516044437885
2023-01-22 15:33:30.801251: step: 72/529, loss: 0.004073295276612043
2023-01-22 15:33:31.873365: step: 76/529, loss: 0.005464494228363037
2023-01-22 15:33:32.939998: step: 80/529, loss: 0.014722703024744987
2023-01-22 15:33:33.994325: step: 84/529, loss: 0.00970328040421009
2023-01-22 15:33:35.066206: step: 88/529, loss: 0.0037130180280655622
2023-01-22 15:33:36.136305: step: 92/529, loss: 0.004681583493947983
2023-01-22 15:33:37.184525: step: 96/529, loss: 0.00022668573365081102
2023-01-22 15:33:38.240954: step: 100/529, loss: 0.004565810784697533
2023-01-22 15:33:39.292661: step: 104/529, loss: 0.0077153155580163
2023-01-22 15:33:40.367767: step: 108/529, loss: 0.016666296869516373
2023-01-22 15:33:41.444198: step: 112/529, loss: 0.0030223659705370665
2023-01-22 15:33:42.486597: step: 116/529, loss: 0.006218838505446911
2023-01-22 15:33:43.593226: step: 120/529, loss: 0.012414630502462387
2023-01-22 15:33:44.650001: step: 124/529, loss: 0.0080726845189929
2023-01-22 15:33:45.701502: step: 128/529, loss: 0.0008169668144546449
2023-01-22 15:33:46.759623: step: 132/529, loss: 0.000573504192288965
2023-01-22 15:33:47.838119: step: 136/529, loss: 0.00733181880787015
2023-01-22 15:33:48.910395: step: 140/529, loss: 0.03185557201504707
2023-01-22 15:33:49.984935: step: 144/529, loss: 0.00632117735221982
2023-01-22 15:33:51.052287: step: 148/529, loss: 0.0017276605358347297
2023-01-22 15:33:52.102221: step: 152/529, loss: 0.035782888531684875
2023-01-22 15:33:53.170853: step: 156/529, loss: 0.009627927094697952
2023-01-22 15:33:54.233619: step: 160/529, loss: 0.04056047275662422
2023-01-22 15:33:55.298665: step: 164/529, loss: 0.006219907198101282
2023-01-22 15:33:56.356899: step: 168/529, loss: 0.0039070723578333855
2023-01-22 15:33:57.443715: step: 172/529, loss: 0.019929764792323112
2023-01-22 15:33:58.507724: step: 176/529, loss: 0.003329492174088955
2023-01-22 15:33:59.577172: step: 180/529, loss: 0.010492537170648575
2023-01-22 15:34:00.650836: step: 184/529, loss: 0.01743011362850666
2023-01-22 15:34:01.721400: step: 188/529, loss: 0.00692491140216589
2023-01-22 15:34:02.790223: step: 192/529, loss: 0.006524811498820782
2023-01-22 15:34:03.845156: step: 196/529, loss: 0.0078565813601017
2023-01-22 15:34:04.912737: step: 200/529, loss: 0.015842001885175705
2023-01-22 15:34:05.979914: step: 204/529, loss: 0.005076906643807888
2023-01-22 15:34:07.049907: step: 208/529, loss: 0.010431725531816483
2023-01-22 15:34:08.114857: step: 212/529, loss: 0.0067523508332669735
2023-01-22 15:34:09.190419: step: 216/529, loss: 0.005084163509309292
2023-01-22 15:34:10.262805: step: 220/529, loss: 0.0032661170698702335
2023-01-22 15:34:11.331505: step: 224/529, loss: 0.004277156665921211
2023-01-22 15:34:12.397963: step: 228/529, loss: 0.00416102260351181
2023-01-22 15:34:13.458000: step: 232/529, loss: 0.009883806109428406
2023-01-22 15:34:14.543511: step: 236/529, loss: 0.013675697147846222
2023-01-22 15:34:15.615904: step: 240/529, loss: 0.007257337681949139
2023-01-22 15:34:16.690828: step: 244/529, loss: 0.005144351627677679
2023-01-22 15:34:17.763868: step: 248/529, loss: 0.006191601511090994
2023-01-22 15:34:18.843099: step: 252/529, loss: 0.016674751415848732
2023-01-22 15:34:19.921098: step: 256/529, loss: 0.0012712310999631882
2023-01-22 15:34:20.995632: step: 260/529, loss: 0.006329537369310856
2023-01-22 15:34:22.079118: step: 264/529, loss: 0.004793352447450161
2023-01-22 15:34:23.145660: step: 268/529, loss: 0.01138306688517332
2023-01-22 15:34:24.197263: step: 272/529, loss: 0.004126550629734993
2023-01-22 15:34:25.260618: step: 276/529, loss: 0.0035139364190399647
2023-01-22 15:34:26.315126: step: 280/529, loss: 0.004335692152380943
2023-01-22 15:34:27.386680: step: 284/529, loss: 0.002115140203386545
2023-01-22 15:34:28.470732: step: 288/529, loss: 0.006532656494528055
2023-01-22 15:34:29.530189: step: 292/529, loss: 0.011361896991729736
2023-01-22 15:34:30.595894: step: 296/529, loss: 0.0011511738412082195
2023-01-22 15:34:31.663067: step: 300/529, loss: 0.0339822918176651
2023-01-22 15:34:32.737698: step: 304/529, loss: 0.02406451664865017
2023-01-22 15:34:33.805228: step: 308/529, loss: 0.027834169566631317
2023-01-22 15:34:34.862825: step: 312/529, loss: 0.0013004255015403032
2023-01-22 15:34:35.928764: step: 316/529, loss: 0.003725425573065877
2023-01-22 15:34:37.002335: step: 320/529, loss: 0.00986859854310751
2023-01-22 15:34:38.080180: step: 324/529, loss: 0.009932243265211582
2023-01-22 15:34:39.164739: step: 328/529, loss: 0.002096701180562377
2023-01-22 15:34:40.253665: step: 332/529, loss: 0.030377984046936035
2023-01-22 15:34:41.323882: step: 336/529, loss: 0.00202542869374156
2023-01-22 15:34:42.402001: step: 340/529, loss: 0.0004344083135947585
2023-01-22 15:34:43.462140: step: 344/529, loss: 0.0042776083573699
2023-01-22 15:34:44.531927: step: 348/529, loss: 0.031020637601614
2023-01-22 15:34:45.600146: step: 352/529, loss: 0.0013227768940851092
2023-01-22 15:34:46.680671: step: 356/529, loss: 0.010704068467020988
2023-01-22 15:34:47.759679: step: 360/529, loss: 0.008606866002082825
2023-01-22 15:34:48.827040: step: 364/529, loss: 0.00715230917558074
2023-01-22 15:34:49.883426: step: 368/529, loss: 0.0032142442651093006
2023-01-22 15:34:50.954535: step: 372/529, loss: 0.0022923434153199196
2023-01-22 15:34:52.004328: step: 376/529, loss: 0.02998194471001625
2023-01-22 15:34:53.051001: step: 380/529, loss: 0.004120546858757734
2023-01-22 15:34:54.116935: step: 384/529, loss: 0.007094264030456543
2023-01-22 15:34:55.179302: step: 388/529, loss: 0.014737040735781193
2023-01-22 15:34:56.246961: step: 392/529, loss: 0.010227232240140438
2023-01-22 15:34:57.322770: step: 396/529, loss: 0.018505224958062172
2023-01-22 15:34:58.391412: step: 400/529, loss: 0.0019069066038355231
2023-01-22 15:34:59.466803: step: 404/529, loss: 0.014191785827279091
2023-01-22 15:35:00.533471: step: 408/529, loss: 0.004034942481666803
2023-01-22 15:35:01.610105: step: 412/529, loss: 0.025709589943289757
2023-01-22 15:35:02.690337: step: 416/529, loss: 0.011058644391596317
2023-01-22 15:35:03.748582: step: 420/529, loss: 0.008795877918601036
2023-01-22 15:35:04.819636: step: 424/529, loss: 0.001207193243317306
2023-01-22 15:35:05.876298: step: 428/529, loss: 0.008448513224720955
2023-01-22 15:35:06.930779: step: 432/529, loss: 0.0015582371270284057
2023-01-22 15:35:08.006984: step: 436/529, loss: 0.006277194246649742
2023-01-22 15:35:09.073587: step: 440/529, loss: 0.002147891791537404
2023-01-22 15:35:10.161775: step: 444/529, loss: 0.0020357149187475443
2023-01-22 15:35:11.218071: step: 448/529, loss: 0.016439586877822876
2023-01-22 15:35:12.279171: step: 452/529, loss: 0.023635433986783028
2023-01-22 15:35:13.366396: step: 456/529, loss: 0.017845846712589264
2023-01-22 15:35:14.444823: step: 460/529, loss: 0.005339685827493668
2023-01-22 15:35:15.528175: step: 464/529, loss: 0.0032788454554975033
2023-01-22 15:35:16.588291: step: 468/529, loss: 0.0049303025007247925
2023-01-22 15:35:17.652867: step: 472/529, loss: 0.07946745306253433
2023-01-22 15:35:18.734288: step: 476/529, loss: 0.012931461445987225
2023-01-22 15:35:19.801171: step: 480/529, loss: 0.005204359069466591
2023-01-22 15:35:20.866427: step: 484/529, loss: 0.0033782885875552893
2023-01-22 15:35:21.938382: step: 488/529, loss: 0.0067017050459980965
2023-01-22 15:35:23.014100: step: 492/529, loss: 0.013821267522871494
2023-01-22 15:35:24.089103: step: 496/529, loss: 0.00670505641028285
2023-01-22 15:35:25.160062: step: 500/529, loss: 0.00608456926420331
2023-01-22 15:35:26.243318: step: 504/529, loss: 0.013473868370056152
2023-01-22 15:35:27.318557: step: 508/529, loss: 0.032499514520168304
2023-01-22 15:35:28.390978: step: 512/529, loss: 0.0009791419142857194
2023-01-22 15:35:29.463759: step: 516/529, loss: 0.0044460603967309
2023-01-22 15:35:30.543555: step: 520/529, loss: 0.00795968621969223
2023-01-22 15:35:31.601017: step: 524/529, loss: 0.006531299091875553
2023-01-22 15:35:32.677500: step: 528/529, loss: 0.006767368409782648
2023-01-22 15:35:33.764831: step: 532/529, loss: 0.0035915214102715254
2023-01-22 15:35:34.834164: step: 536/529, loss: 0.030227866023778915
2023-01-22 15:35:35.897301: step: 540/529, loss: 0.0029931794852018356
2023-01-22 15:35:36.970013: step: 544/529, loss: 0.011107520200312138
2023-01-22 15:35:38.033517: step: 548/529, loss: 0.006771856918931007
2023-01-22 15:35:39.119448: step: 552/529, loss: 0.008452314883470535
2023-01-22 15:35:40.194502: step: 556/529, loss: 0.006177971139550209
2023-01-22 15:35:41.269865: step: 560/529, loss: 0.03494871407747269
2023-01-22 15:35:42.346636: step: 564/529, loss: 0.00797675084322691
2023-01-22 15:35:43.423774: step: 568/529, loss: 0.015033339150249958
2023-01-22 15:35:44.513294: step: 572/529, loss: 0.0018735273042693734
2023-01-22 15:35:45.578547: step: 576/529, loss: 0.011242460459470749
2023-01-22 15:35:46.631478: step: 580/529, loss: 0.006593300029635429
2023-01-22 15:35:47.678102: step: 584/529, loss: 0.009311879053711891
2023-01-22 15:35:48.763031: step: 588/529, loss: 0.006556670647114515
2023-01-22 15:35:49.842772: step: 592/529, loss: 0.0021247942931950092
2023-01-22 15:35:50.915525: step: 596/529, loss: 0.0019866900984197855
2023-01-22 15:35:51.990174: step: 600/529, loss: 0.006030280143022537
2023-01-22 15:35:53.054325: step: 604/529, loss: 2.6696779968915507e-05
2023-01-22 15:35:54.142417: step: 608/529, loss: 0.04135812819004059
2023-01-22 15:35:55.218987: step: 612/529, loss: 0.007614175323396921
2023-01-22 15:35:56.291080: step: 616/529, loss: 0.0031433100812137127
2023-01-22 15:35:57.356425: step: 620/529, loss: 0.010717714205384254
2023-01-22 15:35:58.420106: step: 624/529, loss: 0.010698345489799976
2023-01-22 15:35:59.501292: step: 628/529, loss: 0.023886142298579216
2023-01-22 15:36:00.564008: step: 632/529, loss: 0.003928531892597675
2023-01-22 15:36:01.632252: step: 636/529, loss: 0.016103779897093773
2023-01-22 15:36:02.714403: step: 640/529, loss: 0.013525239191949368
2023-01-22 15:36:03.789145: step: 644/529, loss: 0.03457599878311157
2023-01-22 15:36:04.853486: step: 648/529, loss: 0.008419967256486416
2023-01-22 15:36:05.922143: step: 652/529, loss: 0.0049747442826628685
2023-01-22 15:36:07.030139: step: 656/529, loss: 0.008991905488073826
2023-01-22 15:36:08.125430: step: 660/529, loss: 0.0271906778216362
2023-01-22 15:36:09.202467: step: 664/529, loss: 0.018528439104557037
2023-01-22 15:36:10.279317: step: 668/529, loss: 0.007969571277499199
2023-01-22 15:36:11.358515: step: 672/529, loss: 0.024170290678739548
2023-01-22 15:36:12.425620: step: 676/529, loss: 0.019351670518517494
2023-01-22 15:36:13.504460: step: 680/529, loss: 0.004487547092139721
2023-01-22 15:36:14.578117: step: 684/529, loss: 0.006088240537792444
2023-01-22 15:36:15.653312: step: 688/529, loss: 0.002518126042559743
2023-01-22 15:36:16.727587: step: 692/529, loss: 0.00971476174890995
2023-01-22 15:36:17.808163: step: 696/529, loss: 0.004671934992074966
2023-01-22 15:36:18.885092: step: 700/529, loss: 0.004092163406312466
2023-01-22 15:36:19.975363: step: 704/529, loss: 0.023588519543409348
2023-01-22 15:36:21.065518: step: 708/529, loss: 0.012343088164925575
2023-01-22 15:36:22.125718: step: 712/529, loss: 0.0014462524559348822
2023-01-22 15:36:23.197022: step: 716/529, loss: 0.009823783300817013
2023-01-22 15:36:24.293800: step: 720/529, loss: 0.0078210374340415
2023-01-22 15:36:25.370868: step: 724/529, loss: 0.0024997733999043703
2023-01-22 15:36:26.456106: step: 728/529, loss: 0.015557827427983284
2023-01-22 15:36:27.525270: step: 732/529, loss: 0.009667051956057549
2023-01-22 15:36:28.612237: step: 736/529, loss: 0.0020753752905875444
2023-01-22 15:36:29.704322: step: 740/529, loss: 0.0031915053259581327
2023-01-22 15:36:30.774489: step: 744/529, loss: 0.017997652292251587
2023-01-22 15:36:31.852963: step: 748/529, loss: 0.0038397267926484346
2023-01-22 15:36:32.933352: step: 752/529, loss: 0.010845580138266087
2023-01-22 15:36:34.005302: step: 756/529, loss: 0.0056469980627298355
2023-01-22 15:36:35.081297: step: 760/529, loss: 0.024205049499869347
2023-01-22 15:36:36.172973: step: 764/529, loss: 0.009294592775404453
2023-01-22 15:36:37.242651: step: 768/529, loss: 0.005519056227058172
2023-01-22 15:36:38.327204: step: 772/529, loss: 0.0066510592587292194
2023-01-22 15:36:39.406414: step: 776/529, loss: 0.00451636454090476
2023-01-22 15:36:40.500192: step: 780/529, loss: 0.006918779108673334
2023-01-22 15:36:41.570782: step: 784/529, loss: 0.003937877714633942
2023-01-22 15:36:42.638362: step: 788/529, loss: 0.0034500632900744677
2023-01-22 15:36:43.708203: step: 792/529, loss: 0.015180250629782677
2023-01-22 15:36:44.786752: step: 796/529, loss: 0.005527715664356947
2023-01-22 15:36:45.871516: step: 800/529, loss: 0.0026738387532532215
2023-01-22 15:36:46.953706: step: 804/529, loss: 0.010368620976805687
2023-01-22 15:36:48.022842: step: 808/529, loss: 0.005900280084460974
2023-01-22 15:36:49.090030: step: 812/529, loss: 0.01362408697605133
2023-01-22 15:36:50.183124: step: 816/529, loss: 0.009619764983654022
2023-01-22 15:36:51.253625: step: 820/529, loss: 0.011690499261021614
2023-01-22 15:36:52.344557: step: 824/529, loss: 0.01570005528628826
2023-01-22 15:36:53.420835: step: 828/529, loss: 0.00252782111056149
2023-01-22 15:36:54.515408: step: 832/529, loss: 0.033378612250089645
2023-01-22 15:36:55.601198: step: 836/529, loss: 0.02463219128549099
2023-01-22 15:36:56.682137: step: 840/529, loss: 0.01371025387197733
2023-01-22 15:36:57.769461: step: 844/529, loss: 0.0005712570855394006
2023-01-22 15:36:58.850288: step: 848/529, loss: 0.0033849880564957857
2023-01-22 15:36:59.940312: step: 852/529, loss: 0.015501162968575954
2023-01-22 15:37:01.024071: step: 856/529, loss: 0.0033761262893676758
2023-01-22 15:37:02.113800: step: 860/529, loss: 0.003269011853262782
2023-01-22 15:37:03.197542: step: 864/529, loss: 0.005324568599462509
2023-01-22 15:37:04.275018: step: 868/529, loss: 0.015953127294778824
2023-01-22 15:37:05.347838: step: 872/529, loss: 0.011110708117485046
2023-01-22 15:37:06.460253: step: 876/529, loss: 0.009748917073011398
2023-01-22 15:37:07.538698: step: 880/529, loss: 0.030173728242516518
2023-01-22 15:37:08.621510: step: 884/529, loss: 0.009095161221921444
2023-01-22 15:37:09.704010: step: 888/529, loss: 0.007395054213702679
2023-01-22 15:37:10.782121: step: 892/529, loss: 0.001859817304648459
2023-01-22 15:37:11.875078: step: 896/529, loss: 0.015024775639176369
2023-01-22 15:37:12.969143: step: 900/529, loss: 0.036551643162965775
2023-01-22 15:37:14.054183: step: 904/529, loss: 0.004126851912587881
2023-01-22 15:37:15.123482: step: 908/529, loss: 0.0037501517217606306
2023-01-22 15:37:16.197297: step: 912/529, loss: 0.0016765149775892496
2023-01-22 15:37:17.272001: step: 916/529, loss: 0.00263429107144475
2023-01-22 15:37:18.347377: step: 920/529, loss: 0.010215152986347675
2023-01-22 15:37:19.425508: step: 924/529, loss: 0.01056759338825941
2023-01-22 15:37:20.531008: step: 928/529, loss: 0.006834817118942738
2023-01-22 15:37:21.628556: step: 932/529, loss: 0.003006510902196169
2023-01-22 15:37:22.720175: step: 936/529, loss: 0.02883508801460266
2023-01-22 15:37:23.826536: step: 940/529, loss: 0.022211819887161255
2023-01-22 15:37:24.907996: step: 944/529, loss: 0.010564801283180714
2023-01-22 15:37:25.992935: step: 948/529, loss: 0.004062940366566181
2023-01-22 15:37:27.082717: step: 952/529, loss: 0.002742258133366704
2023-01-22 15:37:28.170422: step: 956/529, loss: 0.006772853899747133
2023-01-22 15:37:29.265718: step: 960/529, loss: 0.00285226758569479
2023-01-22 15:37:30.336119: step: 964/529, loss: 0.007859828881919384
2023-01-22 15:37:31.413497: step: 968/529, loss: 0.004809211939573288
2023-01-22 15:37:32.517056: step: 972/529, loss: 0.005635186564177275
2023-01-22 15:37:33.595759: step: 976/529, loss: 0.03100399859249592
2023-01-22 15:37:34.692906: step: 980/529, loss: 0.04693903028964996
2023-01-22 15:37:35.752602: step: 984/529, loss: 0.007040327414870262
2023-01-22 15:37:36.822547: step: 988/529, loss: 0.0003511648974381387
2023-01-22 15:37:37.902948: step: 992/529, loss: 0.021587209776043892
2023-01-22 15:37:38.983844: step: 996/529, loss: 0.008670927956700325
2023-01-22 15:37:40.071419: step: 1000/529, loss: 0.00503647280856967
2023-01-22 15:37:41.152155: step: 1004/529, loss: 0.010647826828062534
2023-01-22 15:37:42.231637: step: 1008/529, loss: 0.004342544358223677
2023-01-22 15:37:43.347128: step: 1012/529, loss: 0.021491017192602158
2023-01-22 15:37:44.435840: step: 1016/529, loss: 0.007109408266842365
2023-01-22 15:37:45.517662: step: 1020/529, loss: 0.026232164353132248
2023-01-22 15:37:46.611918: step: 1024/529, loss: 0.026226766407489777
2023-01-22 15:37:47.701288: step: 1028/529, loss: 0.009091410785913467
2023-01-22 15:37:48.777794: step: 1032/529, loss: 0.013991279527544975
2023-01-22 15:37:49.842597: step: 1036/529, loss: 0.007567662745714188
2023-01-22 15:37:50.924295: step: 1040/529, loss: 0.003366368357092142
2023-01-22 15:37:52.010158: step: 1044/529, loss: 0.0064007192850112915
2023-01-22 15:37:53.095211: step: 1048/529, loss: 0.04431624710559845
2023-01-22 15:37:54.183838: step: 1052/529, loss: 0.02152891270816326
2023-01-22 15:37:55.269176: step: 1056/529, loss: 0.011203648522496223
2023-01-22 15:37:56.355506: step: 1060/529, loss: 0.009548647329211235
2023-01-22 15:37:57.437156: step: 1064/529, loss: 0.003137181745842099
2023-01-22 15:37:58.542799: step: 1068/529, loss: 0.0017036364879459143
2023-01-22 15:37:59.626801: step: 1072/529, loss: 0.022670309990644455
2023-01-22 15:38:00.701244: step: 1076/529, loss: 0.00296448334120214
2023-01-22 15:38:01.774860: step: 1080/529, loss: 0.0032868662383407354
2023-01-22 15:38:02.873668: step: 1084/529, loss: 0.00535968504846096
2023-01-22 15:38:03.949881: step: 1088/529, loss: 0.008010120131075382
2023-01-22 15:38:05.037435: step: 1092/529, loss: 0.0042228600941598415
2023-01-22 15:38:06.117341: step: 1096/529, loss: 0.04953213036060333
2023-01-22 15:38:07.193273: step: 1100/529, loss: 0.015964580699801445
2023-01-22 15:38:08.276229: step: 1104/529, loss: 0.0062031252309679985
2023-01-22 15:38:09.338704: step: 1108/529, loss: 0.01025872491300106
2023-01-22 15:38:10.408291: step: 1112/529, loss: 0.004633505363017321
2023-01-22 15:38:11.486403: step: 1116/529, loss: 0.003801979124546051
2023-01-22 15:38:12.569854: step: 1120/529, loss: 0.0025255049113184214
2023-01-22 15:38:13.655102: step: 1124/529, loss: 0.0019073954317718744
2023-01-22 15:38:14.752186: step: 1128/529, loss: 0.006439147517085075
2023-01-22 15:38:15.840842: step: 1132/529, loss: 0.005457963794469833
2023-01-22 15:38:16.927300: step: 1136/529, loss: 0.0097409188747406
2023-01-22 15:38:17.995539: step: 1140/529, loss: 0.0014348758850246668
2023-01-22 15:38:19.077464: step: 1144/529, loss: 0.004820538684725761
2023-01-22 15:38:20.146935: step: 1148/529, loss: 0.006507347337901592
2023-01-22 15:38:21.227141: step: 1152/529, loss: 0.0009271916933357716
2023-01-22 15:38:22.306574: step: 1156/529, loss: 0.004905874840915203
2023-01-22 15:38:23.393467: step: 1160/529, loss: 0.014403492212295532
2023-01-22 15:38:24.486465: step: 1164/529, loss: 0.01025901548564434
2023-01-22 15:38:25.584480: step: 1168/529, loss: 0.017725173383951187
2023-01-22 15:38:26.660934: step: 1172/529, loss: 0.003254067851230502
2023-01-22 15:38:27.747082: step: 1176/529, loss: 0.06489744037389755
2023-01-22 15:38:28.844234: step: 1180/529, loss: 0.006055659614503384
2023-01-22 15:38:29.919744: step: 1184/529, loss: 0.02200540527701378
2023-01-22 15:38:30.993161: step: 1188/529, loss: 0.01975547894835472
2023-01-22 15:38:32.075519: step: 1192/529, loss: 0.00919928029179573
2023-01-22 15:38:33.147375: step: 1196/529, loss: 0.00953410379588604
2023-01-22 15:38:34.232800: step: 1200/529, loss: 0.02829376608133316
2023-01-22 15:38:35.301616: step: 1204/529, loss: 0.003076962660998106
2023-01-22 15:38:36.383210: step: 1208/529, loss: 0.006185153499245644
2023-01-22 15:38:37.479901: step: 1212/529, loss: 0.001367044635117054
2023-01-22 15:38:38.553259: step: 1216/529, loss: 0.004037867300212383
2023-01-22 15:38:39.623132: step: 1220/529, loss: 0.005665189120918512
2023-01-22 15:38:40.709426: step: 1224/529, loss: 0.008640700951218605
2023-01-22 15:38:41.790320: step: 1228/529, loss: 0.005546838045120239
2023-01-22 15:38:42.886207: step: 1232/529, loss: 0.01690641976892948
2023-01-22 15:38:43.940638: step: 1236/529, loss: 0.004949650727212429
2023-01-22 15:38:45.032284: step: 1240/529, loss: 0.012577560730278492
2023-01-22 15:38:46.097319: step: 1244/529, loss: 0.002623192733153701
2023-01-22 15:38:47.167444: step: 1248/529, loss: 0.015778103843331337
2023-01-22 15:38:48.254319: step: 1252/529, loss: 0.0019661467522382736
2023-01-22 15:38:49.335808: step: 1256/529, loss: 0.005598688032478094
2023-01-22 15:38:50.404101: step: 1260/529, loss: 0.023746563121676445
2023-01-22 15:38:51.489500: step: 1264/529, loss: 0.02076910063624382
2023-01-22 15:38:52.563059: step: 1268/529, loss: 0.012793630361557007
2023-01-22 15:38:53.648436: step: 1272/529, loss: 0.007723736576735973
2023-01-22 15:38:54.745039: step: 1276/529, loss: 0.0028649610467255116
2023-01-22 15:38:55.840678: step: 1280/529, loss: 0.022496290504932404
2023-01-22 15:38:56.929040: step: 1284/529, loss: 0.00020430835138540715
2023-01-22 15:38:57.996554: step: 1288/529, loss: 0.06546629965305328
2023-01-22 15:38:59.077863: step: 1292/529, loss: 0.006132582668215036
2023-01-22 15:39:00.161026: step: 1296/529, loss: 0.031766265630722046
2023-01-22 15:39:01.234650: step: 1300/529, loss: 0.016393672674894333
2023-01-22 15:39:02.316500: step: 1304/529, loss: 0.009899788536131382
2023-01-22 15:39:03.377099: step: 1308/529, loss: 0.03336502984166145
2023-01-22 15:39:04.454883: step: 1312/529, loss: 0.02855636365711689
2023-01-22 15:39:05.547938: step: 1316/529, loss: 0.011804209090769291
2023-01-22 15:39:06.642123: step: 1320/529, loss: 0.04140903428196907
2023-01-22 15:39:07.711309: step: 1324/529, loss: 0.025253072381019592
2023-01-22 15:39:08.793838: step: 1328/529, loss: 0.004349129740148783
2023-01-22 15:39:09.876151: step: 1332/529, loss: 0.00424607377499342
2023-01-22 15:39:10.949220: step: 1336/529, loss: 0.05381146818399429
2023-01-22 15:39:12.035061: step: 1340/529, loss: 0.006734470371156931
2023-01-22 15:39:13.097358: step: 1344/529, loss: 0.0036293980665504932
2023-01-22 15:39:14.180380: step: 1348/529, loss: 0.008891493082046509
2023-01-22 15:39:15.265220: step: 1352/529, loss: 0.01908380538225174
2023-01-22 15:39:16.331841: step: 1356/529, loss: 0.016486801207065582
2023-01-22 15:39:17.399451: step: 1360/529, loss: 0.008257966488599777
2023-01-22 15:39:18.466163: step: 1364/529, loss: 0.03334486484527588
2023-01-22 15:39:19.551838: step: 1368/529, loss: 0.013955829665064812
2023-01-22 15:39:20.618643: step: 1372/529, loss: 9.377596143167466e-06
2023-01-22 15:39:21.690317: step: 1376/529, loss: 0.0063485875725746155
2023-01-22 15:39:22.754615: step: 1380/529, loss: 0.002045923611149192
2023-01-22 15:39:23.842492: step: 1384/529, loss: 0.01518089696764946
2023-01-22 15:39:24.904157: step: 1388/529, loss: 0.004115557298064232
2023-01-22 15:39:25.981836: step: 1392/529, loss: 0.0016862958436831832
2023-01-22 15:39:27.067223: step: 1396/529, loss: 0.025592461228370667
2023-01-22 15:39:28.150398: step: 1400/529, loss: 0.024935556575655937
2023-01-22 15:39:29.219431: step: 1404/529, loss: 0.012728538364171982
2023-01-22 15:39:30.276709: step: 1408/529, loss: 0.042654845863580704
2023-01-22 15:39:31.349852: step: 1412/529, loss: 0.010267243720591068
2023-01-22 15:39:32.399431: step: 1416/529, loss: 0.01058992836624384
2023-01-22 15:39:33.469570: step: 1420/529, loss: 0.0026905033737421036
2023-01-22 15:39:34.530323: step: 1424/529, loss: 0.0068442788906395435
2023-01-22 15:39:35.600643: step: 1428/529, loss: 0.003912247251719236
2023-01-22 15:39:36.672795: step: 1432/529, loss: 0.04170241206884384
2023-01-22 15:39:37.741968: step: 1436/529, loss: 0.006908444222062826
2023-01-22 15:39:38.809198: step: 1440/529, loss: 0.005204537883400917
2023-01-22 15:39:39.866468: step: 1444/529, loss: 0.004310019314289093
2023-01-22 15:39:40.941325: step: 1448/529, loss: 0.006490429397672415
2023-01-22 15:39:42.022624: step: 1452/529, loss: 0.005031294655054808
2023-01-22 15:39:43.122283: step: 1456/529, loss: 0.015018314123153687
2023-01-22 15:39:44.198279: step: 1460/529, loss: 0.012576140463352203
2023-01-22 15:39:45.278416: step: 1464/529, loss: 0.01709701679646969
2023-01-22 15:39:46.345112: step: 1468/529, loss: 0.02605600841343403
2023-01-22 15:39:47.411595: step: 1472/529, loss: 0.01831715553998947
2023-01-22 15:39:48.475579: step: 1476/529, loss: 0.0053050946444272995
2023-01-22 15:39:49.547980: step: 1480/529, loss: 0.00328476051799953
2023-01-22 15:39:50.634804: step: 1484/529, loss: 0.006424771621823311
2023-01-22 15:39:51.704394: step: 1488/529, loss: 0.001035862835124135
2023-01-22 15:39:52.765582: step: 1492/529, loss: 0.06115015223622322
2023-01-22 15:39:53.839331: step: 1496/529, loss: 0.027961784973740578
2023-01-22 15:39:54.897803: step: 1500/529, loss: 0.0010620169341564178
2023-01-22 15:39:55.962122: step: 1504/529, loss: 0.017797712236642838
2023-01-22 15:39:57.027397: step: 1508/529, loss: 0.0028727345634251833
2023-01-22 15:39:58.097806: step: 1512/529, loss: 0.003638346679508686
2023-01-22 15:39:59.168803: step: 1516/529, loss: 0.0059278919361531734
2023-01-22 15:40:00.229146: step: 1520/529, loss: 0.04296484962105751
2023-01-22 15:40:01.293951: step: 1524/529, loss: 0.0006260772934183478
2023-01-22 15:40:02.360820: step: 1528/529, loss: 0.0014787226682528853
2023-01-22 15:40:03.410657: step: 1532/529, loss: 0.001329754013568163
2023-01-22 15:40:04.484880: step: 1536/529, loss: 0.008486728183925152
2023-01-22 15:40:05.573863: step: 1540/529, loss: 0.0076823364943265915
2023-01-22 15:40:06.658311: step: 1544/529, loss: 0.014573008753359318
2023-01-22 15:40:07.734018: step: 1548/529, loss: 0.016743669286370277
2023-01-22 15:40:08.798866: step: 1552/529, loss: 0.0349496491253376
2023-01-22 15:40:09.854381: step: 1556/529, loss: 0.007348290644586086
2023-01-22 15:40:10.925220: step: 1560/529, loss: 0.0018828087486326694
2023-01-22 15:40:11.991765: step: 1564/529, loss: 0.022683776915073395
2023-01-22 15:40:13.075121: step: 1568/529, loss: 0.023825807496905327
2023-01-22 15:40:14.131925: step: 1572/529, loss: 0.011531732976436615
2023-01-22 15:40:15.206028: step: 1576/529, loss: 0.008588587865233421
2023-01-22 15:40:16.267418: step: 1580/529, loss: 0.005683989264070988
2023-01-22 15:40:17.330589: step: 1584/529, loss: 0.016850145533680916
2023-01-22 15:40:18.405550: step: 1588/529, loss: 0.005151068791747093
2023-01-22 15:40:19.470267: step: 1592/529, loss: 0.02597479708492756
2023-01-22 15:40:20.533773: step: 1596/529, loss: 0.0303542148321867
2023-01-22 15:40:21.603334: step: 1600/529, loss: 0.02412993647158146
2023-01-22 15:40:22.673974: step: 1604/529, loss: 0.00743184145539999
2023-01-22 15:40:23.743116: step: 1608/529, loss: 0.009544594213366508
2023-01-22 15:40:24.807686: step: 1612/529, loss: 0.015473476611077785
2023-01-22 15:40:25.872414: step: 1616/529, loss: 0.008911818265914917
2023-01-22 15:40:26.939279: step: 1620/529, loss: 0.01670347899198532
2023-01-22 15:40:27.999294: step: 1624/529, loss: 0.002616297686472535
2023-01-22 15:40:29.071736: step: 1628/529, loss: 0.0036034672521054745
2023-01-22 15:40:30.140448: step: 1632/529, loss: 0.006160416640341282
2023-01-22 15:40:31.193575: step: 1636/529, loss: 0.004200714640319347
2023-01-22 15:40:32.258236: step: 1640/529, loss: 0.00981410313397646
2023-01-22 15:40:33.332676: step: 1644/529, loss: 0.004251305479556322
2023-01-22 15:40:34.404448: step: 1648/529, loss: 0.015658719465136528
2023-01-22 15:40:35.477813: step: 1652/529, loss: 0.037121228873729706
2023-01-22 15:40:36.543829: step: 1656/529, loss: 0.09933902323246002
2023-01-22 15:40:37.607914: step: 1660/529, loss: 0.016771141439676285
2023-01-22 15:40:38.676334: step: 1664/529, loss: 0.01599819026887417
2023-01-22 15:40:39.722929: step: 1668/529, loss: 0.0014509749598801136
2023-01-22 15:40:40.776587: step: 1672/529, loss: 0.016085010021924973
2023-01-22 15:40:41.846800: step: 1676/529, loss: 0.025324085727334023
2023-01-22 15:40:42.931722: step: 1680/529, loss: 0.006123365834355354
2023-01-22 15:40:43.999210: step: 1684/529, loss: 0.019563492387533188
2023-01-22 15:40:45.068283: step: 1688/529, loss: 0.0075540728867053986
2023-01-22 15:40:46.146849: step: 1692/529, loss: 0.006424248218536377
2023-01-22 15:40:47.224188: step: 1696/529, loss: 0.007962196134030819
2023-01-22 15:40:48.283810: step: 1700/529, loss: 0.00419227872043848
2023-01-22 15:40:49.353620: step: 1704/529, loss: 0.005730568431317806
2023-01-22 15:40:50.406606: step: 1708/529, loss: 0.006074938923120499
2023-01-22 15:40:51.471288: step: 1712/529, loss: 0.008359881117939949
2023-01-22 15:40:52.515476: step: 1716/529, loss: 0.008949099108576775
2023-01-22 15:40:53.583796: step: 1720/529, loss: 0.0005189424846321344
2023-01-22 15:40:54.667591: step: 1724/529, loss: 0.001241878024302423
2023-01-22 15:40:55.735020: step: 1728/529, loss: 0.023316921666264534
2023-01-22 15:40:56.814769: step: 1732/529, loss: 0.005595780443400145
2023-01-22 15:40:57.881995: step: 1736/529, loss: 0.003928350750356913
2023-01-22 15:40:58.945244: step: 1740/529, loss: 0.025084983557462692
2023-01-22 15:41:00.017209: step: 1744/529, loss: 0.005941771436482668
2023-01-22 15:41:01.091785: step: 1748/529, loss: 0.005050054285675287
2023-01-22 15:41:02.177918: step: 1752/529, loss: 0.03062165156006813
2023-01-22 15:41:03.270615: step: 1756/529, loss: 0.013844349421560764
2023-01-22 15:41:04.337682: step: 1760/529, loss: 0.016237672418355942
2023-01-22 15:41:05.395504: step: 1764/529, loss: 0.004700832534581423
2023-01-22 15:41:06.485434: step: 1768/529, loss: 0.009221207350492477
2023-01-22 15:41:07.551011: step: 1772/529, loss: 0.01399283017963171
2023-01-22 15:41:08.628435: step: 1776/529, loss: 0.000554208701942116
2023-01-22 15:41:09.680057: step: 1780/529, loss: 0.004608966875821352
2023-01-22 15:41:10.765128: step: 1784/529, loss: 0.05405984818935394
2023-01-22 15:41:11.818092: step: 1788/529, loss: 0.00849241204559803
2023-01-22 15:41:12.890087: step: 1792/529, loss: 0.02150285430252552
2023-01-22 15:41:13.952299: step: 1796/529, loss: 0.005432683043181896
2023-01-22 15:41:15.023653: step: 1800/529, loss: 0.0023045307025313377
2023-01-22 15:41:16.101034: step: 1804/529, loss: 2.0657407731050625e-05
2023-01-22 15:41:17.155692: step: 1808/529, loss: 0.0038340457249432802
2023-01-22 15:41:18.228977: step: 1812/529, loss: 0.018187930807471275
2023-01-22 15:41:19.291844: step: 1816/529, loss: 0.012754458002746105
2023-01-22 15:41:20.350143: step: 1820/529, loss: 0.0018092350801452994
2023-01-22 15:41:21.413314: step: 1824/529, loss: 0.006038977764546871
2023-01-22 15:41:22.478693: step: 1828/529, loss: 0.04289066419005394
2023-01-22 15:41:23.550411: step: 1832/529, loss: 0.006066637113690376
2023-01-22 15:41:24.616923: step: 1836/529, loss: 0.019083892926573753
2023-01-22 15:41:25.684490: step: 1840/529, loss: 0.015402274206280708
2023-01-22 15:41:26.757025: step: 1844/529, loss: 0.008550545200705528
2023-01-22 15:41:27.823214: step: 1848/529, loss: 0.006068128161132336
2023-01-22 15:41:28.896172: step: 1852/529, loss: 0.002489842474460602
2023-01-22 15:41:29.977370: step: 1856/529, loss: 0.005711839534342289
2023-01-22 15:41:31.037594: step: 1860/529, loss: 0.011155230924487114
2023-01-22 15:41:32.107607: step: 1864/529, loss: 0.007385375443845987
2023-01-22 15:41:33.196831: step: 1868/529, loss: 0.005201231222599745
2023-01-22 15:41:34.276306: step: 1872/529, loss: 0.013216188177466393
2023-01-22 15:41:35.344940: step: 1876/529, loss: 0.01222376897931099
2023-01-22 15:41:36.409592: step: 1880/529, loss: 0.025436189025640488
2023-01-22 15:41:37.470317: step: 1884/529, loss: 0.004563449416309595
2023-01-22 15:41:38.544232: step: 1888/529, loss: 0.015077211894094944
2023-01-22 15:41:39.612071: step: 1892/529, loss: 0.0257384292781353
2023-01-22 15:41:40.679015: step: 1896/529, loss: 0.0045809973962605
2023-01-22 15:41:41.734880: step: 1900/529, loss: 0.0020767245441675186
2023-01-22 15:41:42.792914: step: 1904/529, loss: 0.009484152309596539
2023-01-22 15:41:43.865577: step: 1908/529, loss: 0.006550249177962542
2023-01-22 15:41:44.935101: step: 1912/529, loss: 0.00044212437933310866
2023-01-22 15:41:46.006654: step: 1916/529, loss: 0.02092244103550911
2023-01-22 15:41:47.059173: step: 1920/529, loss: 0.004801048897206783
2023-01-22 15:41:48.117389: step: 1924/529, loss: 0.003222655039280653
2023-01-22 15:41:49.177773: step: 1928/529, loss: 0.004944137297570705
2023-01-22 15:41:50.246561: step: 1932/529, loss: 0.030959121882915497
2023-01-22 15:41:51.300180: step: 1936/529, loss: 0.0003269213775638491
2023-01-22 15:41:52.384212: step: 1940/529, loss: 0.01522830780595541
2023-01-22 15:41:53.450564: step: 1944/529, loss: 0.003529431065544486
2023-01-22 15:41:54.496162: step: 1948/529, loss: 0.0031008790247142315
2023-01-22 15:41:55.568493: step: 1952/529, loss: 0.013878103345632553
2023-01-22 15:41:56.626166: step: 1956/529, loss: 0.00032939633820205927
2023-01-22 15:41:57.683592: step: 1960/529, loss: 0.00490737147629261
2023-01-22 15:41:58.757173: step: 1964/529, loss: 0.006270409096032381
2023-01-22 15:41:59.837999: step: 1968/529, loss: 0.0027163519989699125
2023-01-22 15:42:00.912748: step: 1972/529, loss: 0.001964374678209424
2023-01-22 15:42:01.979364: step: 1976/529, loss: 0.011277947574853897
2023-01-22 15:42:03.058640: step: 1980/529, loss: 0.03554533049464226
2023-01-22 15:42:04.145361: step: 1984/529, loss: 0.0776987224817276
2023-01-22 15:42:05.215906: step: 1988/529, loss: 0.001686428557150066
2023-01-22 15:42:06.285952: step: 1992/529, loss: 0.004262098576873541
2023-01-22 15:42:07.343296: step: 1996/529, loss: 0.001260052202269435
2023-01-22 15:42:08.396126: step: 2000/529, loss: 0.002083900850266218
2023-01-22 15:42:09.469297: step: 2004/529, loss: 0.022707713767886162
2023-01-22 15:42:10.520761: step: 2008/529, loss: 0.012377276085317135
2023-01-22 15:42:11.599418: step: 2012/529, loss: 0.014637023210525513
2023-01-22 15:42:12.657499: step: 2016/529, loss: 0.007896382361650467
2023-01-22 15:42:13.726102: step: 2020/529, loss: 0.03769185021519661
2023-01-22 15:42:14.794560: step: 2024/529, loss: 0.014995766803622246
2023-01-22 15:42:15.850761: step: 2028/529, loss: 0.01594899408519268
2023-01-22 15:42:16.914314: step: 2032/529, loss: 0.00520738773047924
2023-01-22 15:42:17.979349: step: 2036/529, loss: 0.0034832293167710304
2023-01-22 15:42:19.041632: step: 2040/529, loss: 0.013992756605148315
2023-01-22 15:42:20.110493: step: 2044/529, loss: 0.007770204450935125
2023-01-22 15:42:21.175556: step: 2048/529, loss: 0.000749800237827003
2023-01-22 15:42:22.246363: step: 2052/529, loss: 0.019051600247621536
2023-01-22 15:42:23.320092: step: 2056/529, loss: 0.015893064439296722
2023-01-22 15:42:24.440972: step: 2060/529, loss: 0.07714373618364334
2023-01-22 15:42:25.496115: step: 2064/529, loss: 0.051430750638246536
2023-01-22 15:42:26.559500: step: 2068/529, loss: 0.01454426534473896
2023-01-22 15:42:27.618897: step: 2072/529, loss: 0.029555466026067734
2023-01-22 15:42:28.679329: step: 2076/529, loss: 0.00812841858714819
2023-01-22 15:42:29.742617: step: 2080/529, loss: 0.007017475087195635
2023-01-22 15:42:30.805567: step: 2084/529, loss: 0.005045258905738592
2023-01-22 15:42:31.889478: step: 2088/529, loss: 0.004556868225336075
2023-01-22 15:42:32.953716: step: 2092/529, loss: 0.019676432013511658
2023-01-22 15:42:34.000516: step: 2096/529, loss: 0.0016599795781075954
2023-01-22 15:42:35.058632: step: 2100/529, loss: 0.005418145563453436
2023-01-22 15:42:36.128681: step: 2104/529, loss: 0.006692006718367338
2023-01-22 15:42:37.190435: step: 2108/529, loss: 0.05009535327553749
2023-01-22 15:42:38.258484: step: 2112/529, loss: 0.0026667662896215916
2023-01-22 15:42:39.318121: step: 2116/529, loss: 0.012330101802945137
==================================================
Loss: 0.012
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32148370497427103, 'r': 0.3556451612903226, 'f1': 0.33770270270270275}, 'combined': 0.2488335704125178, 'stategy': 1, 'epoch': 4}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3130186895816293, 'r': 0.30755739013071015, 'f1': 0.3102640091267655}, 'combined': 0.20255577797913188, 'stategy': 1, 'epoch': 4}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32374479166666664, 'r': 0.3685898956356736, 'f1': 0.34471495119787043}, 'combined': 0.25400049035632555, 'stategy': 1, 'epoch': 4}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33423857660835543, 'r': 0.3093550061071819, 'f1': 0.3213157485867436}, 'combined': 0.20977090322243364, 'stategy': 1, 'epoch': 4}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31499116284739154, 'r': 0.3502558281377067, 'f1': 0.33168880759851116}, 'combined': 0.24440227928311348, 'stategy': 1, 'epoch': 4}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.321046474018477, 'r': 0.3169191547932625, 'f1': 0.31896946355809874}, 'combined': 0.2082391316493287, 'stategy': 1, 'epoch': 4}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 4}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 4}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 4}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32374479166666664, 'r': 0.3685898956356736, 'f1': 0.34471495119787043}, 'combined': 0.25400049035632555, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33423857660835543, 'r': 0.3093550061071819, 'f1': 0.3213157485867436}, 'combined': 0.20977090322243364, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 15:45:18.418591: step: 4/529, loss: 0.0023591865319758654
2023-01-22 15:45:19.477555: step: 8/529, loss: 0.022934990003705025
2023-01-22 15:45:20.542146: step: 12/529, loss: 0.00520970206707716
2023-01-22 15:45:21.594186: step: 16/529, loss: 0.02341693826019764
2023-01-22 15:45:22.655570: step: 20/529, loss: 9.770537144504488e-05
2023-01-22 15:45:23.716362: step: 24/529, loss: 0.00018030313367489725
2023-01-22 15:45:24.774164: step: 28/529, loss: 0.02539955824613571
2023-01-22 15:45:25.841471: step: 32/529, loss: 0.03564148768782616
2023-01-22 15:45:26.889574: step: 36/529, loss: 0.0038195543456822634
2023-01-22 15:45:27.944799: step: 40/529, loss: 0.00010295725223841146
2023-01-22 15:45:29.002455: step: 44/529, loss: 0.010775351896882057
2023-01-22 15:45:30.070374: step: 48/529, loss: 0.00821895431727171
2023-01-22 15:45:31.127385: step: 52/529, loss: 0.01877855509519577
2023-01-22 15:45:32.191500: step: 56/529, loss: 0.005858547519892454
2023-01-22 15:45:33.257799: step: 60/529, loss: 0.0328177772462368
2023-01-22 15:45:34.300564: step: 64/529, loss: 0.014643720351159573
2023-01-22 15:45:35.361637: step: 68/529, loss: 0.032504670321941376
2023-01-22 15:45:36.437992: step: 72/529, loss: 0.006147871259599924
2023-01-22 15:45:37.495471: step: 76/529, loss: 0.0531005933880806
2023-01-22 15:45:38.562081: step: 80/529, loss: 0.031548935920000076
2023-01-22 15:45:39.633758: step: 84/529, loss: 0.007868846878409386
2023-01-22 15:45:40.692677: step: 88/529, loss: 0.005373908672481775
2023-01-22 15:45:41.766212: step: 92/529, loss: 0.009822044521570206
2023-01-22 15:45:42.818085: step: 96/529, loss: 0.004009397700428963
2023-01-22 15:45:43.878272: step: 100/529, loss: 0.003939324989914894
2023-01-22 15:45:44.933496: step: 104/529, loss: 0.030637217685580254
2023-01-22 15:45:45.991474: step: 108/529, loss: 0.001025114906951785
2023-01-22 15:45:47.048840: step: 112/529, loss: 0.007835193537175655
2023-01-22 15:45:48.122472: step: 116/529, loss: 0.011833150871098042
2023-01-22 15:45:49.187000: step: 120/529, loss: 0.03219558671116829
2023-01-22 15:45:50.241979: step: 124/529, loss: 0.0002794024767354131
2023-01-22 15:45:51.312139: step: 128/529, loss: 0.0097324438393116
2023-01-22 15:45:52.379808: step: 132/529, loss: 0.024913547560572624
2023-01-22 15:45:53.438665: step: 136/529, loss: 0.017749769613146782
2023-01-22 15:45:54.502145: step: 140/529, loss: 0.0036395140923559666
2023-01-22 15:45:55.567579: step: 144/529, loss: 0.0023946850560605526
2023-01-22 15:45:56.630812: step: 148/529, loss: 0.03142841160297394
2023-01-22 15:45:57.705511: step: 152/529, loss: 0.007366228383034468
2023-01-22 15:45:58.759381: step: 156/529, loss: 0.007933779619634151
2023-01-22 15:45:59.828019: step: 160/529, loss: 0.028447827324271202
2023-01-22 15:46:00.894721: step: 164/529, loss: 0.0027678715996444225
2023-01-22 15:46:01.963594: step: 168/529, loss: 0.01275789923965931
2023-01-22 15:46:03.032182: step: 172/529, loss: 0.0009689267026260495
2023-01-22 15:46:04.087049: step: 176/529, loss: 0.002439645351842046
2023-01-22 15:46:05.145808: step: 180/529, loss: 0.023513024672865868
2023-01-22 15:46:06.232942: step: 184/529, loss: 0.0024362525437027216
2023-01-22 15:46:07.299259: step: 188/529, loss: 0.001983602764084935
2023-01-22 15:46:08.332062: step: 192/529, loss: 0.00682625500485301
2023-01-22 15:46:09.396210: step: 196/529, loss: 0.004751925822347403
2023-01-22 15:46:10.470988: step: 200/529, loss: 0.0021734184119850397
2023-01-22 15:46:11.522127: step: 204/529, loss: 0.0025329540949314833
2023-01-22 15:46:12.588570: step: 208/529, loss: 0.005129461642354727
2023-01-22 15:46:13.665669: step: 212/529, loss: 0.005169543903321028
2023-01-22 15:46:14.750227: step: 216/529, loss: 0.004711352754384279
2023-01-22 15:46:15.810983: step: 220/529, loss: 0.008054588921368122
2023-01-22 15:46:16.873118: step: 224/529, loss: 0.003451740136370063
2023-01-22 15:46:17.944703: step: 228/529, loss: 0.004340517334640026
2023-01-22 15:46:19.013244: step: 232/529, loss: 0.03223850205540657
2023-01-22 15:46:20.102000: step: 236/529, loss: 0.0011079449905082583
2023-01-22 15:46:21.152040: step: 240/529, loss: 0.0015037362463772297
2023-01-22 15:46:22.225735: step: 244/529, loss: 0.020707331597805023
2023-01-22 15:46:23.283398: step: 248/529, loss: 0.020134232938289642
2023-01-22 15:46:24.366773: step: 252/529, loss: 0.009122924879193306
2023-01-22 15:46:25.438889: step: 256/529, loss: 0.00728244986385107
2023-01-22 15:46:26.540259: step: 260/529, loss: 0.0028491420671343803
2023-01-22 15:46:27.590771: step: 264/529, loss: 0.000450416118837893
2023-01-22 15:46:28.660418: step: 268/529, loss: 0.007179692853242159
2023-01-22 15:46:29.748466: step: 272/529, loss: 0.01157737709581852
2023-01-22 15:46:30.800496: step: 276/529, loss: 0.0009326613508164883
2023-01-22 15:46:31.870857: step: 280/529, loss: 0.01036171056330204
2023-01-22 15:46:32.956340: step: 284/529, loss: 0.09236515313386917
2023-01-22 15:46:34.027841: step: 288/529, loss: 0.013139292597770691
2023-01-22 15:46:35.100012: step: 292/529, loss: 0.014926465228199959
2023-01-22 15:46:36.180715: step: 296/529, loss: 0.0029992233030498028
2023-01-22 15:46:37.252704: step: 300/529, loss: 0.0025662067346274853
2023-01-22 15:46:38.330557: step: 304/529, loss: 0.005319194868206978
2023-01-22 15:46:39.394593: step: 308/529, loss: 0.01083306223154068
2023-01-22 15:46:40.466578: step: 312/529, loss: 0.003545610001310706
2023-01-22 15:46:41.531181: step: 316/529, loss: 0.01508993562310934
2023-01-22 15:46:42.591611: step: 320/529, loss: 0.006574643775820732
2023-01-22 15:46:43.679107: step: 324/529, loss: 0.02904742956161499
2023-01-22 15:46:44.738720: step: 328/529, loss: 0.0019047949463129044
2023-01-22 15:46:45.821314: step: 332/529, loss: 0.005265311803668737
2023-01-22 15:46:46.881153: step: 336/529, loss: 0.003619307419285178
2023-01-22 15:46:47.953586: step: 340/529, loss: 0.016096679493784904
2023-01-22 15:46:49.006573: step: 344/529, loss: 0.021636826917529106
2023-01-22 15:46:50.072132: step: 348/529, loss: 0.007235253229737282
2023-01-22 15:46:51.129893: step: 352/529, loss: 0.015154299326241016
2023-01-22 15:46:52.205221: step: 356/529, loss: 0.006073358468711376
2023-01-22 15:46:53.277160: step: 360/529, loss: 0.008909916505217552
2023-01-22 15:46:54.341348: step: 364/529, loss: 0.007834630087018013
2023-01-22 15:46:55.408610: step: 368/529, loss: 2.194949956901837e-06
2023-01-22 15:46:56.473064: step: 372/529, loss: 0.007482160814106464
2023-01-22 15:46:57.543922: step: 376/529, loss: 0.030774014070630074
2023-01-22 15:46:58.619148: step: 380/529, loss: 0.007288197986781597
2023-01-22 15:46:59.690619: step: 384/529, loss: 0.012908224016427994
2023-01-22 15:47:00.758823: step: 388/529, loss: 0.01493560429662466
2023-01-22 15:47:01.804852: step: 392/529, loss: 0.000726421712897718
2023-01-22 15:47:02.871457: step: 396/529, loss: 0.0035562561824917793
2023-01-22 15:47:03.942812: step: 400/529, loss: 0.006127411033958197
2023-01-22 15:47:05.024243: step: 404/529, loss: 0.0435500368475914
2023-01-22 15:47:06.088768: step: 408/529, loss: 0.012825858779251575
2023-01-22 15:47:07.157751: step: 412/529, loss: 0.006627162452787161
2023-01-22 15:47:08.223987: step: 416/529, loss: 0.00868252944201231
2023-01-22 15:47:09.284027: step: 420/529, loss: 0.004846430849283934
2023-01-22 15:47:10.366705: step: 424/529, loss: 0.03135371580719948
2023-01-22 15:47:11.446463: step: 428/529, loss: 0.024940218776464462
2023-01-22 15:47:12.515493: step: 432/529, loss: 0.0085542481392622
2023-01-22 15:47:13.594411: step: 436/529, loss: 0.009447372518479824
2023-01-22 15:47:14.655718: step: 440/529, loss: 0.0028872983530163765
2023-01-22 15:47:15.740319: step: 444/529, loss: 0.01761099323630333
2023-01-22 15:47:16.800510: step: 448/529, loss: 0.009838612750172615
2023-01-22 15:47:17.859025: step: 452/529, loss: 0.0074104429222643375
2023-01-22 15:47:18.929863: step: 456/529, loss: 0.026121564209461212
2023-01-22 15:47:19.994466: step: 460/529, loss: 0.003765722969546914
2023-01-22 15:47:21.059585: step: 464/529, loss: 0.005026004742830992
2023-01-22 15:47:22.120244: step: 468/529, loss: 0.019378002732992172
2023-01-22 15:47:23.206274: step: 472/529, loss: 0.007816677913069725
2023-01-22 15:47:24.269655: step: 476/529, loss: 0.008424460887908936
2023-01-22 15:47:25.335946: step: 480/529, loss: 0.0035309477243572474
2023-01-22 15:47:26.386656: step: 484/529, loss: 0.013482525013387203
2023-01-22 15:47:27.450324: step: 488/529, loss: 0.003127522999420762
2023-01-22 15:47:28.509646: step: 492/529, loss: 0.007443585433065891
2023-01-22 15:47:29.576692: step: 496/529, loss: 0.0033241277560591698
2023-01-22 15:47:30.649386: step: 500/529, loss: 0.005822707433253527
2023-01-22 15:47:31.716758: step: 504/529, loss: 0.00861866120249033
2023-01-22 15:47:32.783847: step: 508/529, loss: 0.030997419729828835
2023-01-22 15:47:33.851028: step: 512/529, loss: 0.012883225455880165
2023-01-22 15:47:34.916604: step: 516/529, loss: 0.026715340092778206
2023-01-22 15:47:36.000797: step: 520/529, loss: 0.01364895235747099
2023-01-22 15:47:37.069409: step: 524/529, loss: 0.0031265225261449814
2023-01-22 15:47:38.136008: step: 528/529, loss: 0.0015215002931654453
2023-01-22 15:47:39.214514: step: 532/529, loss: 0.007553800940513611
2023-01-22 15:47:40.287768: step: 536/529, loss: 0.012286574579775333
2023-01-22 15:47:41.349379: step: 540/529, loss: 0.007760470267385244
2023-01-22 15:47:42.404724: step: 544/529, loss: 0.004370789974927902
2023-01-22 15:47:43.464568: step: 548/529, loss: 0.014047746546566486
2023-01-22 15:47:44.554120: step: 552/529, loss: 0.019543102011084557
2023-01-22 15:47:45.626902: step: 556/529, loss: 0.0006572658894583583
2023-01-22 15:47:46.695852: step: 560/529, loss: 0.009009703062474728
2023-01-22 15:47:47.764256: step: 564/529, loss: 0.0008789764251559973
2023-01-22 15:47:48.839370: step: 568/529, loss: 0.036441605538129807
2023-01-22 15:47:49.897332: step: 572/529, loss: 0.00891857873648405
2023-01-22 15:47:50.972554: step: 576/529, loss: 0.012162557803094387
2023-01-22 15:47:52.023038: step: 580/529, loss: 0.003688802244141698
2023-01-22 15:47:53.088098: step: 584/529, loss: 0.006818746216595173
2023-01-22 15:47:54.155349: step: 588/529, loss: 0.003726058639585972
2023-01-22 15:47:55.245299: step: 592/529, loss: 0.007386893033981323
2023-01-22 15:47:56.307605: step: 596/529, loss: 0.0018032968509942293
2023-01-22 15:47:57.371081: step: 600/529, loss: 0.0017450537998229265
2023-01-22 15:47:58.431965: step: 604/529, loss: 0.013055171817541122
2023-01-22 15:47:59.496663: step: 608/529, loss: 0.0046906559728085995
2023-01-22 15:48:00.557240: step: 612/529, loss: 0.0012650399003177881
2023-01-22 15:48:01.622717: step: 616/529, loss: 0.03179369494318962
2023-01-22 15:48:02.682203: step: 620/529, loss: 0.005403509363532066
2023-01-22 15:48:03.762479: step: 624/529, loss: 0.008115163072943687
2023-01-22 15:48:04.853160: step: 628/529, loss: 0.005907402839511633
2023-01-22 15:48:05.943917: step: 632/529, loss: 0.007011353969573975
2023-01-22 15:48:07.021486: step: 636/529, loss: 0.0007654178771190345
2023-01-22 15:48:08.095267: step: 640/529, loss: 0.014596791937947273
2023-01-22 15:48:09.174886: step: 644/529, loss: 0.01081467792391777
2023-01-22 15:48:10.259260: step: 648/529, loss: 0.012734362855553627
2023-01-22 15:48:11.326560: step: 652/529, loss: 0.008981704711914062
2023-01-22 15:48:12.402814: step: 656/529, loss: 0.0048651322722435
2023-01-22 15:48:13.466472: step: 660/529, loss: 0.0018407233292236924
2023-01-22 15:48:14.529105: step: 664/529, loss: 0.0213095024228096
2023-01-22 15:48:15.586697: step: 668/529, loss: 0.02741035260260105
2023-01-22 15:48:16.674364: step: 672/529, loss: 0.016823599115014076
2023-01-22 15:48:17.743749: step: 676/529, loss: 0.020916426554322243
2023-01-22 15:48:18.825136: step: 680/529, loss: 0.007137995678931475
2023-01-22 15:48:19.889826: step: 684/529, loss: 0.005267574451863766
2023-01-22 15:48:20.966129: step: 688/529, loss: 0.0027815639041364193
2023-01-22 15:48:22.024631: step: 692/529, loss: 0.0036561554297804832
2023-01-22 15:48:23.089105: step: 696/529, loss: 0.007523233070969582
2023-01-22 15:48:24.166273: step: 700/529, loss: 0.0038603900466114283
2023-01-22 15:48:25.238264: step: 704/529, loss: 0.024964014068245888
2023-01-22 15:48:26.320019: step: 708/529, loss: 0.002301727421581745
2023-01-22 15:48:27.392139: step: 712/529, loss: 0.013016752898693085
2023-01-22 15:48:28.458510: step: 716/529, loss: 0.03989667445421219
2023-01-22 15:48:29.546694: step: 720/529, loss: 0.014000875875353813
2023-01-22 15:48:30.638489: step: 724/529, loss: 0.014962454326450825
2023-01-22 15:48:31.718172: step: 728/529, loss: 0.025587832555174828
2023-01-22 15:48:32.784932: step: 732/529, loss: 0.012081263586878777
2023-01-22 15:48:33.868143: step: 736/529, loss: 0.014643527567386627
2023-01-22 15:48:34.941312: step: 740/529, loss: 0.0076567307114601135
2023-01-22 15:48:36.019508: step: 744/529, loss: 0.010932404547929764
2023-01-22 15:48:37.089670: step: 748/529, loss: 0.006697780452668667
2023-01-22 15:48:38.163966: step: 752/529, loss: 0.034995365887880325
2023-01-22 15:48:39.232372: step: 756/529, loss: 0.007777332328259945
2023-01-22 15:48:40.302451: step: 760/529, loss: 0.004732560832053423
2023-01-22 15:48:41.386050: step: 764/529, loss: 0.005508625414222479
2023-01-22 15:48:42.487041: step: 768/529, loss: 0.00552033819258213
2023-01-22 15:48:43.590174: step: 772/529, loss: 0.01584731601178646
2023-01-22 15:48:44.676193: step: 776/529, loss: 0.005111855920404196
2023-01-22 15:48:45.769361: step: 780/529, loss: 0.007852288894355297
2023-01-22 15:48:46.837352: step: 784/529, loss: 0.0010208550374954939
2023-01-22 15:48:47.911466: step: 788/529, loss: 0.0024359177332371473
2023-01-22 15:48:48.997924: step: 792/529, loss: 0.009936979971826077
2023-01-22 15:48:50.082331: step: 796/529, loss: 0.004408544860780239
2023-01-22 15:48:51.168198: step: 800/529, loss: 0.05775133892893791
2023-01-22 15:48:52.252452: step: 804/529, loss: 0.0019695491064339876
2023-01-22 15:48:53.347953: step: 808/529, loss: 0.00781511515378952
2023-01-22 15:48:54.425751: step: 812/529, loss: 0.0046793632209300995
2023-01-22 15:48:55.485659: step: 816/529, loss: 0.0
2023-01-22 15:48:56.579677: step: 820/529, loss: 0.008469846099615097
2023-01-22 15:48:57.665277: step: 824/529, loss: 0.00775155471637845
2023-01-22 15:48:58.746479: step: 828/529, loss: 0.009959186427295208
2023-01-22 15:48:59.824563: step: 832/529, loss: 0.01913496106863022
2023-01-22 15:49:00.915108: step: 836/529, loss: 0.00519212894141674
2023-01-22 15:49:01.995260: step: 840/529, loss: 0.0020829234272241592
2023-01-22 15:49:03.086487: step: 844/529, loss: 0.006178383715450764
2023-01-22 15:49:04.159003: step: 848/529, loss: 0.16761167347431183
2023-01-22 15:49:05.231809: step: 852/529, loss: 0.014773697592318058
2023-01-22 15:49:06.312850: step: 856/529, loss: 0.0010599122615531087
2023-01-22 15:49:07.390015: step: 860/529, loss: 0.011026586405932903
2023-01-22 15:49:08.478662: step: 864/529, loss: 0.014187859371304512
2023-01-22 15:49:09.566819: step: 868/529, loss: 0.004979118704795837
2023-01-22 15:49:10.664647: step: 872/529, loss: 0.005366618279367685
2023-01-22 15:49:11.747701: step: 876/529, loss: 0.00425998168066144
2023-01-22 15:49:12.819779: step: 880/529, loss: 0.0014896979555487633
2023-01-22 15:49:13.905840: step: 884/529, loss: 0.002451414940878749
2023-01-22 15:49:15.013992: step: 888/529, loss: 0.0630563497543335
2023-01-22 15:49:16.098463: step: 892/529, loss: 0.002949623391032219
2023-01-22 15:49:17.192349: step: 896/529, loss: 0.00682945316657424
2023-01-22 15:49:18.274583: step: 900/529, loss: 0.00905640795826912
2023-01-22 15:49:19.374656: step: 904/529, loss: 0.006573675200343132
2023-01-22 15:49:20.472878: step: 908/529, loss: 0.01280137151479721
2023-01-22 15:49:21.562950: step: 912/529, loss: 0.006114022806286812
2023-01-22 15:49:22.630614: step: 916/529, loss: 0.006355506833642721
2023-01-22 15:49:23.728594: step: 920/529, loss: 0.0063613951206207275
2023-01-22 15:49:24.806317: step: 924/529, loss: 0.005754409357905388
2023-01-22 15:49:25.895794: step: 928/529, loss: 0.028570882976055145
2023-01-22 15:49:26.980119: step: 932/529, loss: 0.00022434037236962467
2023-01-22 15:49:28.050367: step: 936/529, loss: 0.020676080137491226
2023-01-22 15:49:29.130191: step: 940/529, loss: 0.004602524451911449
2023-01-22 15:49:30.224458: step: 944/529, loss: 0.009075782261788845
2023-01-22 15:49:31.299426: step: 948/529, loss: 0.007831712253391743
2023-01-22 15:49:32.401384: step: 952/529, loss: 0.006078928709030151
2023-01-22 15:49:33.505077: step: 956/529, loss: 0.003775586374104023
2023-01-22 15:49:34.607336: step: 960/529, loss: 0.01066896878182888
2023-01-22 15:49:35.702512: step: 964/529, loss: 0.007163495756685734
2023-01-22 15:49:36.778957: step: 968/529, loss: 0.015286673791706562
2023-01-22 15:49:37.865333: step: 972/529, loss: 0.0055341958068311214
2023-01-22 15:49:38.949407: step: 976/529, loss: 0.004220864269882441
2023-01-22 15:49:40.047944: step: 980/529, loss: 0.04802757129073143
2023-01-22 15:49:41.132373: step: 984/529, loss: 0.008909719064831734
2023-01-22 15:49:42.206555: step: 988/529, loss: 0.016143960878252983
2023-01-22 15:49:43.286858: step: 992/529, loss: 0.002123722108080983
2023-01-22 15:49:44.369340: step: 996/529, loss: 0.06090731918811798
2023-01-22 15:49:45.449748: step: 1000/529, loss: 0.03460565209388733
2023-01-22 15:49:46.519203: step: 1004/529, loss: 0.003564713755622506
2023-01-22 15:49:47.596569: step: 1008/529, loss: 0.003454942721873522
2023-01-22 15:49:48.668373: step: 1012/529, loss: 0.006876189727336168
2023-01-22 15:49:49.751741: step: 1016/529, loss: 0.020064184442162514
2023-01-22 15:49:50.855895: step: 1020/529, loss: 0.041294246912002563
2023-01-22 15:49:51.931953: step: 1024/529, loss: 0.0030531559605151415
2023-01-22 15:49:53.000869: step: 1028/529, loss: 0.005201972089707851
2023-01-22 15:49:54.096641: step: 1032/529, loss: 0.013871893286705017
2023-01-22 15:49:55.158092: step: 1036/529, loss: 0.016921035945415497
2023-01-22 15:49:56.235528: step: 1040/529, loss: 0.00787028856575489
2023-01-22 15:49:57.326791: step: 1044/529, loss: 0.013744481839239597
2023-01-22 15:49:58.398689: step: 1048/529, loss: 0.0007722425507381558
2023-01-22 15:49:59.498365: step: 1052/529, loss: 0.00881260633468628
2023-01-22 15:50:00.593262: step: 1056/529, loss: 0.007405300159007311
2023-01-22 15:50:01.672804: step: 1060/529, loss: 0.01694301888346672
2023-01-22 15:50:02.749041: step: 1064/529, loss: 0.014890308491885662
2023-01-22 15:50:03.839939: step: 1068/529, loss: 0.008977736346423626
2023-01-22 15:50:04.916692: step: 1072/529, loss: 0.007859176956117153
2023-01-22 15:50:05.980804: step: 1076/529, loss: 0.0032545970752835274
2023-01-22 15:50:07.060295: step: 1080/529, loss: 0.0027104350738227367
2023-01-22 15:50:08.139900: step: 1084/529, loss: 0.00029562684358097613
2023-01-22 15:50:09.265917: step: 1088/529, loss: 0.027976777404546738
2023-01-22 15:50:10.346264: step: 1092/529, loss: 0.0002920544648077339
2023-01-22 15:50:11.420432: step: 1096/529, loss: 0.005539219360798597
2023-01-22 15:50:12.499067: step: 1100/529, loss: 0.017816459760069847
2023-01-22 15:50:13.596700: step: 1104/529, loss: 0.02801329828798771
2023-01-22 15:50:14.668438: step: 1108/529, loss: 0.037525489926338196
2023-01-22 15:50:15.746849: step: 1112/529, loss: 0.007232323754578829
2023-01-22 15:50:16.821066: step: 1116/529, loss: 0.03849571943283081
2023-01-22 15:50:17.908648: step: 1120/529, loss: 0.004483949393033981
2023-01-22 15:50:18.980465: step: 1124/529, loss: 0.0031455166172236204
2023-01-22 15:50:20.059892: step: 1128/529, loss: 0.01355654001235962
2023-01-22 15:50:21.146429: step: 1132/529, loss: 0.0014939901884645224
2023-01-22 15:50:22.240472: step: 1136/529, loss: 0.006358602549880743
2023-01-22 15:50:23.332229: step: 1140/529, loss: 0.010074728168547153
2023-01-22 15:50:24.405458: step: 1144/529, loss: 0.0
2023-01-22 15:50:25.475486: step: 1148/529, loss: 0.004920216277241707
2023-01-22 15:50:26.560676: step: 1152/529, loss: 0.007155633065849543
2023-01-22 15:50:27.627247: step: 1156/529, loss: 0.07974962890148163
2023-01-22 15:50:28.719952: step: 1160/529, loss: 0.0029482811223715544
2023-01-22 15:50:29.793720: step: 1164/529, loss: 0.01466186624020338
2023-01-22 15:50:30.882166: step: 1168/529, loss: 0.011331798508763313
2023-01-22 15:50:31.984314: step: 1172/529, loss: 0.02274644747376442
2023-01-22 15:50:33.075836: step: 1176/529, loss: 0.013689613901078701
2023-01-22 15:50:34.155610: step: 1180/529, loss: 0.03239350765943527
2023-01-22 15:50:35.230127: step: 1184/529, loss: 0.004444632213562727
2023-01-22 15:50:36.293152: step: 1188/529, loss: 0.004769716411828995
2023-01-22 15:50:37.354508: step: 1192/529, loss: 0.0013277638936415315
2023-01-22 15:50:38.428184: step: 1196/529, loss: 0.05235392972826958
2023-01-22 15:50:39.505780: step: 1200/529, loss: 0.024671632796525955
2023-01-22 15:50:40.578385: step: 1204/529, loss: 0.0057119401171803474
2023-01-22 15:50:41.658550: step: 1208/529, loss: 0.0023117177188396454
2023-01-22 15:50:42.729541: step: 1212/529, loss: 0.006331521086394787
2023-01-22 15:50:43.820736: step: 1216/529, loss: 0.01428559236228466
2023-01-22 15:50:44.895571: step: 1220/529, loss: 0.0023710555396974087
2023-01-22 15:50:45.959001: step: 1224/529, loss: 0.004345199093222618
2023-01-22 15:50:47.046768: step: 1228/529, loss: 0.019951367750763893
2023-01-22 15:50:48.121486: step: 1232/529, loss: 0.007890959270298481
2023-01-22 15:50:49.193410: step: 1236/529, loss: 0.07620669901371002
2023-01-22 15:50:50.275530: step: 1240/529, loss: 0.0011335468152537942
2023-01-22 15:50:51.342769: step: 1244/529, loss: 0.009308500215411186
2023-01-22 15:50:52.433667: step: 1248/529, loss: 0.004264793824404478
2023-01-22 15:50:53.506745: step: 1252/529, loss: 0.006576917599886656
2023-01-22 15:50:54.586177: step: 1256/529, loss: 0.013798649422824383
2023-01-22 15:50:55.662332: step: 1260/529, loss: 0.009273541159927845
2023-01-22 15:50:56.725953: step: 1264/529, loss: 0.0014964672736823559
2023-01-22 15:50:57.792736: step: 1268/529, loss: 0.04203373193740845
2023-01-22 15:50:58.869867: step: 1272/529, loss: 0.0029081483371555805
2023-01-22 15:50:59.952958: step: 1276/529, loss: 0.01879449561238289
2023-01-22 15:51:01.021364: step: 1280/529, loss: 0.013544732704758644
2023-01-22 15:51:02.103488: step: 1284/529, loss: 0.005477940663695335
2023-01-22 15:51:03.189449: step: 1288/529, loss: 0.018900319933891296
2023-01-22 15:51:04.256977: step: 1292/529, loss: 0.023639418184757233
2023-01-22 15:51:05.330154: step: 1296/529, loss: 0.007221922278404236
2023-01-22 15:51:06.414100: step: 1300/529, loss: 0.009306453168392181
2023-01-22 15:51:07.495271: step: 1304/529, loss: 0.0028487478848546743
2023-01-22 15:51:08.575585: step: 1308/529, loss: 0.012331938371062279
2023-01-22 15:51:09.659970: step: 1312/529, loss: 0.013492444530129433
2023-01-22 15:51:10.724692: step: 1316/529, loss: 0.0
2023-01-22 15:51:11.811533: step: 1320/529, loss: 0.002121965866535902
2023-01-22 15:51:12.924172: step: 1324/529, loss: 0.004902695305645466
2023-01-22 15:51:13.999093: step: 1328/529, loss: 0.025261392816901207
2023-01-22 15:51:15.091413: step: 1332/529, loss: 0.004776181653141975
2023-01-22 15:51:16.186822: step: 1336/529, loss: 0.017266785725951195
2023-01-22 15:51:17.278646: step: 1340/529, loss: 0.012460139580070972
2023-01-22 15:51:18.357864: step: 1344/529, loss: 0.008990156464278698
2023-01-22 15:51:19.459276: step: 1348/529, loss: 0.04393523931503296
2023-01-22 15:51:20.531979: step: 1352/529, loss: 0.010298765264451504
2023-01-22 15:51:21.631955: step: 1356/529, loss: 0.0396031029522419
2023-01-22 15:51:22.724488: step: 1360/529, loss: 0.03492884337902069
2023-01-22 15:51:23.812145: step: 1364/529, loss: 0.009422865696251392
2023-01-22 15:51:24.885072: step: 1368/529, loss: 0.005993964616209269
2023-01-22 15:51:25.949666: step: 1372/529, loss: 0.010289964266121387
2023-01-22 15:51:27.030398: step: 1376/529, loss: 0.02454109489917755
2023-01-22 15:51:28.107098: step: 1380/529, loss: 0.003755053738132119
2023-01-22 15:51:29.176120: step: 1384/529, loss: 0.005654075648635626
2023-01-22 15:51:30.277830: step: 1388/529, loss: 0.02863590605556965
2023-01-22 15:51:31.344845: step: 1392/529, loss: 0.0035188167821615934
2023-01-22 15:51:32.412677: step: 1396/529, loss: 0.005578240845352411
2023-01-22 15:51:33.485056: step: 1400/529, loss: 0.009057060815393925
2023-01-22 15:51:34.558296: step: 1404/529, loss: 0.005759712308645248
2023-01-22 15:51:35.622940: step: 1408/529, loss: 0.003830369096249342
2023-01-22 15:51:36.698850: step: 1412/529, loss: 0.040804117918014526
2023-01-22 15:51:37.784949: step: 1416/529, loss: 0.004583555273711681
2023-01-22 15:51:38.870054: step: 1420/529, loss: 0.03579489514231682
2023-01-22 15:51:39.933601: step: 1424/529, loss: 0.008261672221124172
2023-01-22 15:51:41.000821: step: 1428/529, loss: 0.00042252615094184875
2023-01-22 15:51:42.072897: step: 1432/529, loss: 0.005859615281224251
2023-01-22 15:51:43.142755: step: 1436/529, loss: 0.00278661772608757
2023-01-22 15:51:44.206605: step: 1440/529, loss: 0.017631590366363525
2023-01-22 15:51:45.291758: step: 1444/529, loss: 0.004680880811065435
2023-01-22 15:51:46.362919: step: 1448/529, loss: 0.010311641730368137
2023-01-22 15:51:47.424900: step: 1452/529, loss: 0.021048827096819878
2023-01-22 15:51:48.497668: step: 1456/529, loss: 0.010116723366081715
2023-01-22 15:51:49.570391: step: 1460/529, loss: 0.03891179710626602
2023-01-22 15:51:50.648738: step: 1464/529, loss: 0.0024544892366975546
2023-01-22 15:51:51.715497: step: 1468/529, loss: 0.009924131445586681
2023-01-22 15:51:52.784216: step: 1472/529, loss: 0.00858625303953886
2023-01-22 15:51:53.862947: step: 1476/529, loss: 0.0024726493284106255
2023-01-22 15:51:54.938563: step: 1480/529, loss: 0.0013446114026010036
2023-01-22 15:51:56.003379: step: 1484/529, loss: 0.004836790729314089
2023-01-22 15:51:57.065998: step: 1488/529, loss: 0.006040053442120552
2023-01-22 15:51:58.145713: step: 1492/529, loss: 0.04293355718255043
2023-01-22 15:51:59.213895: step: 1496/529, loss: 0.008027631789445877
2023-01-22 15:52:00.280851: step: 1500/529, loss: 0.003630795981734991
2023-01-22 15:52:01.350652: step: 1504/529, loss: 0.032587241381406784
2023-01-22 15:52:02.420955: step: 1508/529, loss: 0.0020075689535588026
2023-01-22 15:52:03.501173: step: 1512/529, loss: 0.022222377359867096
2023-01-22 15:52:04.582824: step: 1516/529, loss: 0.0221629049628973
2023-01-22 15:52:05.660449: step: 1520/529, loss: 0.02755477838218212
2023-01-22 15:52:06.729065: step: 1524/529, loss: 0.00889334175735712
2023-01-22 15:52:07.812175: step: 1528/529, loss: 0.026414886116981506
2023-01-22 15:52:08.868091: step: 1532/529, loss: 0.0030905883759260178
2023-01-22 15:52:09.924971: step: 1536/529, loss: 0.0008331799763254821
2023-01-22 15:52:10.989985: step: 1540/529, loss: 0.012762368656694889
2023-01-22 15:52:12.080396: step: 1544/529, loss: 0.013532751239836216
2023-01-22 15:52:13.163506: step: 1548/529, loss: 0.004549093544483185
2023-01-22 15:52:14.254627: step: 1552/529, loss: 0.005234023090451956
2023-01-22 15:52:15.338821: step: 1556/529, loss: 0.006097541190683842
2023-01-22 15:52:16.418609: step: 1560/529, loss: 0.01614624634385109
2023-01-22 15:52:17.485683: step: 1564/529, loss: 0.021045619621872902
2023-01-22 15:52:18.549838: step: 1568/529, loss: 0.007534326054155827
2023-01-22 15:52:19.614382: step: 1572/529, loss: 0.02432713471353054
2023-01-22 15:52:20.678224: step: 1576/529, loss: 0.0026261243037879467
2023-01-22 15:52:21.768008: step: 1580/529, loss: 0.04308377951383591
2023-01-22 15:52:22.839403: step: 1584/529, loss: 0.010176918469369411
2023-01-22 15:52:23.898554: step: 1588/529, loss: 0.005328764673322439
2023-01-22 15:52:24.969739: step: 1592/529, loss: 0.07903500646352768
2023-01-22 15:52:26.043934: step: 1596/529, loss: 0.004221309907734394
2023-01-22 15:52:27.115975: step: 1600/529, loss: 0.015687737613916397
2023-01-22 15:52:28.181305: step: 1604/529, loss: 0.00549752963706851
2023-01-22 15:52:29.248930: step: 1608/529, loss: 0.011800880543887615
2023-01-22 15:52:30.342328: step: 1612/529, loss: 0.027584398165345192
2023-01-22 15:52:31.403436: step: 1616/529, loss: 0.013747325167059898
2023-01-22 15:52:32.476504: step: 1620/529, loss: 0.037530671805143356
2023-01-22 15:52:33.549843: step: 1624/529, loss: 0.005068168509751558
2023-01-22 15:52:34.629232: step: 1628/529, loss: 0.006172776222229004
2023-01-22 15:52:35.699961: step: 1632/529, loss: 0.007974918000400066
2023-01-22 15:52:36.750047: step: 1636/529, loss: 0.006738297641277313
2023-01-22 15:52:37.813859: step: 1640/529, loss: 0.0034984492231160402
2023-01-22 15:52:38.877919: step: 1644/529, loss: 0.014918613247573376
2023-01-22 15:52:39.952743: step: 1648/529, loss: 0.006512226536870003
2023-01-22 15:52:40.996468: step: 1652/529, loss: 0.00737723708152771
2023-01-22 15:52:42.071382: step: 1656/529, loss: 0.0573233962059021
2023-01-22 15:52:43.125112: step: 1660/529, loss: 0.0069577330723404884
2023-01-22 15:52:44.178249: step: 1664/529, loss: 0.019377263262867928
2023-01-22 15:52:45.252435: step: 1668/529, loss: 0.03078649938106537
2023-01-22 15:52:46.316203: step: 1672/529, loss: 0.003216062905266881
2023-01-22 15:52:47.384064: step: 1676/529, loss: 0.0037748897448182106
2023-01-22 15:52:48.434904: step: 1680/529, loss: 0.002429459011182189
2023-01-22 15:52:49.507944: step: 1684/529, loss: 0.004633056931197643
2023-01-22 15:52:50.573166: step: 1688/529, loss: 0.030605506151914597
2023-01-22 15:52:51.671247: step: 1692/529, loss: 0.016295254230499268
2023-01-22 15:52:52.738256: step: 1696/529, loss: 0.01034608669579029
2023-01-22 15:52:53.820943: step: 1700/529, loss: 0.004735305439680815
2023-01-22 15:52:54.906355: step: 1704/529, loss: 0.015845278277993202
2023-01-22 15:52:55.976891: step: 1708/529, loss: 0.007071654312312603
2023-01-22 15:52:57.040273: step: 1712/529, loss: 0.004461943171918392
2023-01-22 15:52:58.116068: step: 1716/529, loss: 0.03569343313574791
2023-01-22 15:52:59.204788: step: 1720/529, loss: 0.01444600522518158
2023-01-22 15:53:00.287774: step: 1724/529, loss: 0.010641595348715782
2023-01-22 15:53:01.354447: step: 1728/529, loss: 0.008447544649243355
2023-01-22 15:53:02.439538: step: 1732/529, loss: 0.0072909072041511536
2023-01-22 15:53:03.514073: step: 1736/529, loss: 0.002131541259586811
2023-01-22 15:53:04.591930: step: 1740/529, loss: 0.02337382733821869
2023-01-22 15:53:05.686674: step: 1744/529, loss: 0.012673169374465942
2023-01-22 15:53:06.763193: step: 1748/529, loss: 0.00959248747676611
2023-01-22 15:53:07.840423: step: 1752/529, loss: 0.026055578142404556
2023-01-22 15:53:08.899027: step: 1756/529, loss: 0.01532035693526268
2023-01-22 15:53:09.953709: step: 1760/529, loss: 0.0015387131134048104
2023-01-22 15:53:11.014499: step: 1764/529, loss: 0.0063927313312888145
2023-01-22 15:53:12.088550: step: 1768/529, loss: 0.025243641808629036
2023-01-22 15:53:13.187874: step: 1772/529, loss: 0.003757145255804062
2023-01-22 15:53:14.257252: step: 1776/529, loss: 0.0054232217371463776
2023-01-22 15:53:15.311762: step: 1780/529, loss: 0.007150574587285519
2023-01-22 15:53:16.380986: step: 1784/529, loss: 0.006214563734829426
2023-01-22 15:53:17.437600: step: 1788/529, loss: 0.003573064459487796
2023-01-22 15:53:18.494768: step: 1792/529, loss: 0.01645597256720066
2023-01-22 15:53:19.553337: step: 1796/529, loss: 0.009686240926384926
2023-01-22 15:53:20.621268: step: 1800/529, loss: 0.013272601179778576
2023-01-22 15:53:21.675647: step: 1804/529, loss: 0.026154495775699615
2023-01-22 15:53:22.748666: step: 1808/529, loss: 0.003204566426575184
2023-01-22 15:53:23.822309: step: 1812/529, loss: 0.014051277190446854
2023-01-22 15:53:24.882414: step: 1816/529, loss: 0.0031279672402888536
2023-01-22 15:53:25.948709: step: 1820/529, loss: 0.006006308831274509
2023-01-22 15:53:27.025173: step: 1824/529, loss: 0.008006137795746326
2023-01-22 15:53:28.088572: step: 1828/529, loss: 0.03570302203297615
2023-01-22 15:53:29.165331: step: 1832/529, loss: 0.008539380505681038
2023-01-22 15:53:30.219032: step: 1836/529, loss: 0.01007886417210102
2023-01-22 15:53:31.275155: step: 1840/529, loss: 0.0075442977249622345
2023-01-22 15:53:32.328173: step: 1844/529, loss: 0.0066248951479792595
2023-01-22 15:53:33.387262: step: 1848/529, loss: 0.0005288355168886483
2023-01-22 15:53:34.454289: step: 1852/529, loss: 0.0009223928791470826
2023-01-22 15:53:35.519319: step: 1856/529, loss: 0.012264363467693329
2023-01-22 15:53:36.597386: step: 1860/529, loss: 0.02287827990949154
2023-01-22 15:53:37.660883: step: 1864/529, loss: 0.017279639840126038
2023-01-22 15:53:38.720068: step: 1868/529, loss: 0.018276898190379143
2023-01-22 15:53:39.776908: step: 1872/529, loss: 0.005971214268356562
2023-01-22 15:53:40.842416: step: 1876/529, loss: 0.01321127824485302
2023-01-22 15:53:41.908152: step: 1880/529, loss: 0.021702038124203682
2023-01-22 15:53:42.978338: step: 1884/529, loss: 0.014448175206780434
2023-01-22 15:53:44.050394: step: 1888/529, loss: 0.010672574862837791
2023-01-22 15:53:45.116313: step: 1892/529, loss: 0.006881430745124817
2023-01-22 15:53:46.171189: step: 1896/529, loss: 0.01842563971877098
2023-01-22 15:53:47.239676: step: 1900/529, loss: 0.00330442120321095
2023-01-22 15:53:48.294833: step: 1904/529, loss: 0.0029181467834860086
2023-01-22 15:53:49.374539: step: 1908/529, loss: 0.01516847312450409
2023-01-22 15:53:50.453029: step: 1912/529, loss: 0.014981931075453758
2023-01-22 15:53:51.507583: step: 1916/529, loss: 0.009225535206496716
2023-01-22 15:53:52.587555: step: 1920/529, loss: 0.0028526494279503822
2023-01-22 15:53:53.676066: step: 1924/529, loss: 0.011153114959597588
2023-01-22 15:53:54.753587: step: 1928/529, loss: 0.013986228033900261
2023-01-22 15:53:55.823715: step: 1932/529, loss: 0.005642796866595745
2023-01-22 15:53:56.878661: step: 1936/529, loss: 0.0047327009961009026
2023-01-22 15:53:57.943503: step: 1940/529, loss: 0.004789605736732483
2023-01-22 15:53:59.002397: step: 1944/529, loss: 0.0016605491982772946
2023-01-22 15:54:00.099546: step: 1948/529, loss: 0.006903086788952351
2023-01-22 15:54:01.178604: step: 1952/529, loss: 0.017687933519482613
2023-01-22 15:54:02.256930: step: 1956/529, loss: 0.01979789510369301
2023-01-22 15:54:03.321851: step: 1960/529, loss: 0.03956262022256851
2023-01-22 15:54:04.405517: step: 1964/529, loss: 0.005671752616763115
2023-01-22 15:54:05.493491: step: 1968/529, loss: 0.0045891073532402515
2023-01-22 15:54:06.560097: step: 1972/529, loss: 0.027699964120984077
2023-01-22 15:54:07.620172: step: 1976/529, loss: 0.0183024350553751
2023-01-22 15:54:08.695545: step: 1980/529, loss: 0.007530553266406059
2023-01-22 15:54:09.758319: step: 1984/529, loss: 0.01620594412088394
2023-01-22 15:54:10.818754: step: 1988/529, loss: 0.014276370406150818
2023-01-22 15:54:11.892432: step: 1992/529, loss: 0.021116022020578384
2023-01-22 15:54:12.974017: step: 1996/529, loss: 0.007424824871122837
2023-01-22 15:54:14.043200: step: 2000/529, loss: 0.006106334272772074
2023-01-22 15:54:15.100920: step: 2004/529, loss: 0.005225195083767176
2023-01-22 15:54:16.170937: step: 2008/529, loss: 0.023255614563822746
2023-01-22 15:54:17.238725: step: 2012/529, loss: 0.016700133681297302
2023-01-22 15:54:18.302608: step: 2016/529, loss: 0.00023159108241088688
2023-01-22 15:54:19.401599: step: 2020/529, loss: 0.004689238965511322
2023-01-22 15:54:20.461345: step: 2024/529, loss: 0.01314149796962738
2023-01-22 15:54:21.531995: step: 2028/529, loss: 0.010646788403391838
2023-01-22 15:54:22.603230: step: 2032/529, loss: 0.005147057585418224
2023-01-22 15:54:23.682860: step: 2036/529, loss: 0.003516519907861948
2023-01-22 15:54:24.744690: step: 2040/529, loss: 0.004199287388473749
2023-01-22 15:54:25.830888: step: 2044/529, loss: 0.010551740415394306
2023-01-22 15:54:26.902848: step: 2048/529, loss: 0.0009885496692731977
2023-01-22 15:54:27.978151: step: 2052/529, loss: 0.006307472940534353
2023-01-22 15:54:29.043354: step: 2056/529, loss: 0.009027451276779175
2023-01-22 15:54:30.111455: step: 2060/529, loss: 0.0068636201322078705
2023-01-22 15:54:31.199326: step: 2064/529, loss: 0.0673711970448494
2023-01-22 15:54:32.259263: step: 2068/529, loss: 0.009444445371627808
2023-01-22 15:54:33.332746: step: 2072/529, loss: 0.004476535599678755
2023-01-22 15:54:34.405944: step: 2076/529, loss: 0.0030442506540566683
2023-01-22 15:54:35.479597: step: 2080/529, loss: 0.001577819581143558
2023-01-22 15:54:36.549618: step: 2084/529, loss: 0.0071356333792209625
2023-01-22 15:54:37.619948: step: 2088/529, loss: 0.00712616927921772
2023-01-22 15:54:38.697543: step: 2092/529, loss: 0.01787043735384941
2023-01-22 15:54:39.758273: step: 2096/529, loss: 0.002402389654889703
2023-01-22 15:54:40.822915: step: 2100/529, loss: 0.010706400498747826
2023-01-22 15:54:41.890908: step: 2104/529, loss: 0.003975633531808853
2023-01-22 15:54:42.967453: step: 2108/529, loss: 0.007619303185492754
2023-01-22 15:54:44.054369: step: 2112/529, loss: 0.04413328319787979
2023-01-22 15:54:45.110912: step: 2116/529, loss: 0.006672995164990425
==================================================
Loss: 0.013
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31693548387096776, 'r': 0.35422201138519926, 'f1': 0.3345430107526882}, 'combined': 0.24650537634408604, 'stategy': 1, 'epoch': 5}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30767521321963015, 'r': 0.30626126462946646, 'f1': 0.3069666107018512}, 'combined': 0.2004030722716749, 'stategy': 1, 'epoch': 5}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3179683223864258, 'r': 0.36744346932321315, 'f1': 0.3409202611502347}, 'combined': 0.2512044029528045, 'stategy': 1, 'epoch': 5}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3312041633770724, 'r': 0.3105039031660054, 'f1': 0.32052015810684426}, 'combined': 0.2092515021837429, 'stategy': 1, 'epoch': 5}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30869156928213687, 'r': 0.3508657495256167, 'f1': 0.32843028419182946}, 'combined': 0.24200126203608485, 'stategy': 1, 'epoch': 5}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32308928137188103, 'r': 0.3221992282551541, 'f1': 0.3226436409837819}, 'combined': 0.2106378174298265, 'stategy': 1, 'epoch': 5}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 5}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.33088235294117646, 'r': 0.4891304347826087, 'f1': 0.39473684210526316}, 'combined': 0.19736842105263158, 'stategy': 1, 'epoch': 5}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 5}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32374479166666664, 'r': 0.3685898956356736, 'f1': 0.34471495119787043}, 'combined': 0.25400049035632555, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33423857660835543, 'r': 0.3093550061071819, 'f1': 0.3213157485867436}, 'combined': 0.20977090322243364, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 15:57:21.886988: step: 4/529, loss: 0.004251775797456503
2023-01-22 15:57:22.941722: step: 8/529, loss: 0.009208057075738907
2023-01-22 15:57:23.997116: step: 12/529, loss: 0.0011367305414751172
2023-01-22 15:57:25.067126: step: 16/529, loss: 0.006010278128087521
2023-01-22 15:57:26.141153: step: 20/529, loss: 0.014736865647137165
2023-01-22 15:57:27.206064: step: 24/529, loss: 0.012458905577659607
2023-01-22 15:57:28.280917: step: 28/529, loss: 0.008214066736400127
2023-01-22 15:57:29.317818: step: 32/529, loss: 0.04549988731741905
2023-01-22 15:57:30.394063: step: 36/529, loss: 0.02159840054810047
2023-01-22 15:57:31.453756: step: 40/529, loss: 0.00996602512896061
2023-01-22 15:57:32.521685: step: 44/529, loss: 0.0031831255182623863
2023-01-22 15:57:33.594379: step: 48/529, loss: 0.00453998101875186
2023-01-22 15:57:34.656364: step: 52/529, loss: 0.00900235679000616
2023-01-22 15:57:35.718415: step: 56/529, loss: 0.0026426673866808414
2023-01-22 15:57:36.780513: step: 60/529, loss: 0.014532829634845257
2023-01-22 15:57:37.850903: step: 64/529, loss: 0.0028687419835478067
2023-01-22 15:57:38.930466: step: 68/529, loss: 0.003404824063181877
2023-01-22 15:57:39.991532: step: 72/529, loss: 0.01833401247859001
2023-01-22 15:57:41.049782: step: 76/529, loss: 0.012656144797801971
2023-01-22 15:57:42.110808: step: 80/529, loss: 0.0019174279877915978
2023-01-22 15:57:43.184644: step: 84/529, loss: 0.009247859008610249
2023-01-22 15:57:44.242760: step: 88/529, loss: 0.011272904463112354
2023-01-22 15:57:45.296544: step: 92/529, loss: 0.023677509278059006
2023-01-22 15:57:46.368074: step: 96/529, loss: 0.009600764140486717
2023-01-22 15:57:47.442818: step: 100/529, loss: 0.0031745238229632378
2023-01-22 15:57:48.511580: step: 104/529, loss: 0.012265895493328571
2023-01-22 15:57:49.571074: step: 108/529, loss: 0.00886599812656641
2023-01-22 15:57:50.638565: step: 112/529, loss: 0.0038776546716690063
2023-01-22 15:57:51.680887: step: 116/529, loss: 0.0036289007402956486
2023-01-22 15:57:52.733213: step: 120/529, loss: 0.0011353361187502742
2023-01-22 15:57:53.793448: step: 124/529, loss: 0.01882966049015522
2023-01-22 15:57:54.851899: step: 128/529, loss: 0.019013207405805588
2023-01-22 15:57:55.924968: step: 132/529, loss: 0.0036519926507025957
2023-01-22 15:57:56.993272: step: 136/529, loss: 0.005039970390498638
2023-01-22 15:57:58.050024: step: 140/529, loss: 0.025404075160622597
2023-01-22 15:57:59.110349: step: 144/529, loss: 0.019541069865226746
2023-01-22 15:58:00.168904: step: 148/529, loss: 0.0047492715530097485
2023-01-22 15:58:01.233635: step: 152/529, loss: 0.007716539781540632
2023-01-22 15:58:02.318328: step: 156/529, loss: 0.004348834976553917
2023-01-22 15:58:03.386250: step: 160/529, loss: 0.013202686794102192
2023-01-22 15:58:04.443464: step: 164/529, loss: 0.0019087671535089612
2023-01-22 15:58:05.504942: step: 168/529, loss: 0.018394405022263527
2023-01-22 15:58:06.571882: step: 172/529, loss: 0.019277531653642654
2023-01-22 15:58:07.638291: step: 176/529, loss: 0.006570256315171719
2023-01-22 15:58:08.694137: step: 180/529, loss: 0.0041452497243881226
2023-01-22 15:58:09.776625: step: 184/529, loss: 0.0023679640144109726
2023-01-22 15:58:10.847584: step: 188/529, loss: 0.008945180103182793
2023-01-22 15:58:11.900300: step: 192/529, loss: 0.0006713150069117546
2023-01-22 15:58:12.959187: step: 196/529, loss: 0.04765382409095764
2023-01-22 15:58:14.035806: step: 200/529, loss: 0.0017833278980106115
2023-01-22 15:58:15.106697: step: 204/529, loss: 0.011787833645939827
2023-01-22 15:58:16.169116: step: 208/529, loss: 0.004820005968213081
2023-01-22 15:58:17.233952: step: 212/529, loss: 0.009184892289340496
2023-01-22 15:58:18.318353: step: 216/529, loss: 0.004535608924925327
2023-01-22 15:58:19.394614: step: 220/529, loss: 0.003341608913615346
2023-01-22 15:58:20.481208: step: 224/529, loss: 0.005843697115778923
2023-01-22 15:58:21.549786: step: 228/529, loss: 8.227876969613135e-05
2023-01-22 15:58:22.616124: step: 232/529, loss: 0.011046051979064941
2023-01-22 15:58:23.679695: step: 236/529, loss: 0.009204757399857044
2023-01-22 15:58:24.751259: step: 240/529, loss: 0.004128958098590374
2023-01-22 15:58:25.829276: step: 244/529, loss: 0.005831011105328798
2023-01-22 15:58:26.906639: step: 248/529, loss: 0.0016641899710521102
2023-01-22 15:58:27.970024: step: 252/529, loss: 0.04585116729140282
2023-01-22 15:58:29.054787: step: 256/529, loss: 0.0307149700820446
2023-01-22 15:58:30.132069: step: 260/529, loss: 0.0036291461437940598
2023-01-22 15:58:31.200906: step: 264/529, loss: 0.00504803191870451
2023-01-22 15:58:32.281361: step: 268/529, loss: 0.0035000613424926996
2023-01-22 15:58:33.350473: step: 272/529, loss: 0.003666242817416787
2023-01-22 15:58:34.400520: step: 276/529, loss: 0.021791420876979828
2023-01-22 15:58:35.468245: step: 280/529, loss: 0.01919335126876831
2023-01-22 15:58:36.546253: step: 284/529, loss: 0.0043715969659388065
2023-01-22 15:58:37.614027: step: 288/529, loss: 0.0025412060786038637
2023-01-22 15:58:38.695253: step: 292/529, loss: 0.00961506087332964
2023-01-22 15:58:39.740633: step: 296/529, loss: 0.00323112728074193
2023-01-22 15:58:40.821300: step: 300/529, loss: 0.012194921262562275
2023-01-22 15:58:41.876800: step: 304/529, loss: 0.005448506213724613
2023-01-22 15:58:42.937022: step: 308/529, loss: 0.006082399748265743
2023-01-22 15:58:44.011002: step: 312/529, loss: 0.006452085915952921
2023-01-22 15:58:45.082284: step: 316/529, loss: 0.0034442876931279898
2023-01-22 15:58:46.145414: step: 320/529, loss: 0.0011805604444816709
2023-01-22 15:58:47.204231: step: 324/529, loss: 0.021573780104517937
2023-01-22 15:58:48.288683: step: 328/529, loss: 0.0031904454808682203
2023-01-22 15:58:49.381303: step: 332/529, loss: 0.008264061994850636
2023-01-22 15:58:50.447001: step: 336/529, loss: 0.015552588738501072
2023-01-22 15:58:51.508443: step: 340/529, loss: 0.0662967711687088
2023-01-22 15:58:52.576290: step: 344/529, loss: 0.010384410619735718
2023-01-22 15:58:53.640641: step: 348/529, loss: 0.0021233269944787025
2023-01-22 15:58:54.697098: step: 352/529, loss: 0.006720137782394886
2023-01-22 15:58:55.749128: step: 356/529, loss: 0.002918441779911518
2023-01-22 15:58:56.818279: step: 360/529, loss: 0.009702460840344429
2023-01-22 15:58:57.887959: step: 364/529, loss: 0.0004309820360504091
2023-01-22 15:58:58.975067: step: 368/529, loss: 0.004881261847913265
2023-01-22 15:59:00.041490: step: 372/529, loss: 0.003993060439825058
2023-01-22 15:59:01.119428: step: 376/529, loss: 0.03987521305680275
2023-01-22 15:59:02.181253: step: 380/529, loss: 0.03511584550142288
2023-01-22 15:59:03.267919: step: 384/529, loss: 0.004193971864879131
2023-01-22 15:59:04.348925: step: 388/529, loss: 0.005980449728667736
2023-01-22 15:59:05.416820: step: 392/529, loss: 0.02889382094144821
2023-01-22 15:59:06.483782: step: 396/529, loss: 0.0008592014200985432
2023-01-22 15:59:07.540102: step: 400/529, loss: 0.01188697200268507
2023-01-22 15:59:08.592264: step: 404/529, loss: 0.000858179060742259
2023-01-22 15:59:09.658678: step: 408/529, loss: 0.0073442463763058186
2023-01-22 15:59:10.716109: step: 412/529, loss: 0.04937830567359924
2023-01-22 15:59:11.791055: step: 416/529, loss: 0.000712226377800107
2023-01-22 15:59:12.887158: step: 420/529, loss: 0.0019556868355721235
2023-01-22 15:59:13.946195: step: 424/529, loss: 0.004297799430787563
2023-01-22 15:59:15.013776: step: 428/529, loss: 0.015537970699369907
2023-01-22 15:59:16.088621: step: 432/529, loss: 0.005229091737419367
2023-01-22 15:59:17.164996: step: 436/529, loss: 0.0068436795845627785
2023-01-22 15:59:18.245928: step: 440/529, loss: 0.010124222375452518
2023-01-22 15:59:19.307093: step: 444/529, loss: 0.003377160057425499
2023-01-22 15:59:20.355160: step: 448/529, loss: 0.005254809744656086
2023-01-22 15:59:21.449689: step: 452/529, loss: 0.002338831778615713
2023-01-22 15:59:22.505867: step: 456/529, loss: 0.001920098438858986
2023-01-22 15:59:23.578142: step: 460/529, loss: 0.0073715196922421455
2023-01-22 15:59:24.651385: step: 464/529, loss: 0.0053662885911762714
2023-01-22 15:59:25.723807: step: 468/529, loss: 0.0035072308965027332
2023-01-22 15:59:26.800936: step: 472/529, loss: 0.002970685251057148
2023-01-22 15:59:27.866597: step: 476/529, loss: 0.00894078053534031
2023-01-22 15:59:28.921774: step: 480/529, loss: 0.0008381872903555632
2023-01-22 15:59:29.987895: step: 484/529, loss: 0.015279687009751797
2023-01-22 15:59:31.058717: step: 488/529, loss: 0.012683913111686707
2023-01-22 15:59:32.129321: step: 492/529, loss: 0.004614950157701969
2023-01-22 15:59:33.194032: step: 496/529, loss: 0.009267103858292103
2023-01-22 15:59:34.254324: step: 500/529, loss: 0.0001331931125605479
2023-01-22 15:59:35.317769: step: 504/529, loss: 0.0029978761449456215
2023-01-22 15:59:36.382680: step: 508/529, loss: 0.0020075913053005934
2023-01-22 15:59:37.460976: step: 512/529, loss: 0.0045829410664737225
2023-01-22 15:59:38.536170: step: 516/529, loss: 0.017840543761849403
2023-01-22 15:59:39.595264: step: 520/529, loss: 0.0050712707452476025
2023-01-22 15:59:40.662853: step: 524/529, loss: 0.003671597223728895
2023-01-22 15:59:41.733371: step: 528/529, loss: 0.029142843559384346
2023-01-22 15:59:42.792434: step: 532/529, loss: 0.007382141891866922
2023-01-22 15:59:43.855808: step: 536/529, loss: 0.009816615842282772
2023-01-22 15:59:44.911262: step: 540/529, loss: 0.0009239738574251533
2023-01-22 15:59:45.984800: step: 544/529, loss: 0.01686771586537361
2023-01-22 15:59:47.058115: step: 548/529, loss: 0.014569797553122044
2023-01-22 15:59:48.138792: step: 552/529, loss: 0.025281637907028198
2023-01-22 15:59:49.221003: step: 556/529, loss: 0.0022701232228428125
2023-01-22 15:59:50.284198: step: 560/529, loss: 0.00023636706464458257
2023-01-22 15:59:51.352167: step: 564/529, loss: 0.002500031143426895
2023-01-22 15:59:52.444885: step: 568/529, loss: 0.005576382856816053
2023-01-22 15:59:53.519796: step: 572/529, loss: 0.023954322561621666
2023-01-22 15:59:54.590631: step: 576/529, loss: 0.007249325513839722
2023-01-22 15:59:55.666368: step: 580/529, loss: 0.03558175638318062
2023-01-22 15:59:56.737476: step: 584/529, loss: 0.0035528670996427536
2023-01-22 15:59:57.810671: step: 588/529, loss: 0.003556488547474146
2023-01-22 15:59:58.899287: step: 592/529, loss: 0.004361058585345745
2023-01-22 15:59:59.960104: step: 596/529, loss: 0.002490002429112792
2023-01-22 16:00:01.027732: step: 600/529, loss: 0.003968839533627033
2023-01-22 16:00:02.096110: step: 604/529, loss: 0.007614034693688154
2023-01-22 16:00:03.163241: step: 608/529, loss: 0.057831019163131714
2023-01-22 16:00:04.229232: step: 612/529, loss: 0.008671285584568977
2023-01-22 16:00:05.301454: step: 616/529, loss: 0.0005794924218207598
2023-01-22 16:00:06.363014: step: 620/529, loss: 0.010089150629937649
2023-01-22 16:00:07.435400: step: 624/529, loss: 0.01467905379831791
2023-01-22 16:00:08.486563: step: 628/529, loss: 0.004232405219227076
2023-01-22 16:00:09.559154: step: 632/529, loss: 0.001756802899762988
2023-01-22 16:00:10.616667: step: 636/529, loss: 4.07196166634094e-05
2023-01-22 16:00:11.682983: step: 640/529, loss: 0.00585485203191638
2023-01-22 16:00:12.764346: step: 644/529, loss: 0.002673714654520154
2023-01-22 16:00:13.863895: step: 648/529, loss: 0.004026413895189762
2023-01-22 16:00:14.945975: step: 652/529, loss: 0.07536202669143677
2023-01-22 16:00:16.023454: step: 656/529, loss: 0.030667327344417572
2023-01-22 16:00:17.104959: step: 660/529, loss: 0.0031212777830660343
2023-01-22 16:00:18.172205: step: 664/529, loss: 0.002480089897289872
2023-01-22 16:00:19.229322: step: 668/529, loss: 0.0024589565582573414
2023-01-22 16:00:20.284767: step: 672/529, loss: 0.0010578534565865993
2023-01-22 16:00:21.367045: step: 676/529, loss: 0.008302543312311172
2023-01-22 16:00:22.420904: step: 680/529, loss: 0.006249351426959038
2023-01-22 16:00:23.488979: step: 684/529, loss: 0.007828416302800179
2023-01-22 16:00:24.560041: step: 688/529, loss: 0.004356584046036005
2023-01-22 16:00:25.621446: step: 692/529, loss: 0.008816482499241829
2023-01-22 16:00:26.683734: step: 696/529, loss: 0.008845777250826359
2023-01-22 16:00:27.742980: step: 700/529, loss: 0.005275289993733168
2023-01-22 16:00:28.806984: step: 704/529, loss: 0.01827814057469368
2023-01-22 16:00:29.884357: step: 708/529, loss: 0.013627135194838047
2023-01-22 16:00:30.949303: step: 712/529, loss: 0.012442792765796185
2023-01-22 16:00:32.005814: step: 716/529, loss: 0.0058509670197963715
2023-01-22 16:00:33.088340: step: 720/529, loss: 0.018941203132271767
2023-01-22 16:00:34.181440: step: 724/529, loss: 0.05661045387387276
2023-01-22 16:00:35.260345: step: 728/529, loss: 0.018146302551031113
2023-01-22 16:00:36.350107: step: 732/529, loss: 0.0035150747280567884
2023-01-22 16:00:37.419878: step: 736/529, loss: 0.002940249862149358
2023-01-22 16:00:38.471259: step: 740/529, loss: 0.00035843192017637193
2023-01-22 16:00:39.549926: step: 744/529, loss: 0.04068102315068245
2023-01-22 16:00:40.629081: step: 748/529, loss: 0.009319968521595001
2023-01-22 16:00:41.700265: step: 752/529, loss: 0.013870734721422195
2023-01-22 16:00:42.800208: step: 756/529, loss: 0.0040064407512545586
2023-01-22 16:00:43.878188: step: 760/529, loss: 0.01702064834535122
2023-01-22 16:00:44.968608: step: 764/529, loss: 0.006673571188002825
2023-01-22 16:00:46.056620: step: 768/529, loss: 0.0037315767258405685
2023-01-22 16:00:47.121639: step: 772/529, loss: 0.01851697266101837
2023-01-22 16:00:48.183912: step: 776/529, loss: 0.0077040973119437695
2023-01-22 16:00:49.266336: step: 780/529, loss: 0.004212753847241402
2023-01-22 16:00:50.338865: step: 784/529, loss: 0.009366575628519058
2023-01-22 16:00:51.410235: step: 788/529, loss: 0.029224945232272148
2023-01-22 16:00:52.476298: step: 792/529, loss: 0.037477053701877594
2023-01-22 16:00:53.560301: step: 796/529, loss: 0.014138245023787022
2023-01-22 16:00:54.625558: step: 800/529, loss: 0.0012153461575508118
2023-01-22 16:00:55.695169: step: 804/529, loss: 0.005523739382624626
2023-01-22 16:00:56.774423: step: 808/529, loss: 0.0036886618472635746
2023-01-22 16:00:57.855767: step: 812/529, loss: 0.0006245935219340026
2023-01-22 16:00:58.948052: step: 816/529, loss: 0.0061524417251348495
2023-01-22 16:01:00.023229: step: 820/529, loss: 0.0014282549964264035
2023-01-22 16:01:01.112595: step: 824/529, loss: 0.00044671798241324723
2023-01-22 16:01:02.174890: step: 828/529, loss: 0.014413303695619106
2023-01-22 16:01:03.251011: step: 832/529, loss: 0.007666704710572958
2023-01-22 16:01:04.331625: step: 836/529, loss: 0.0023659660946577787
2023-01-22 16:01:05.415307: step: 840/529, loss: 0.006354359909892082
2023-01-22 16:01:06.489019: step: 844/529, loss: 0.003157402155920863
2023-01-22 16:01:07.569039: step: 848/529, loss: 0.0024600059259682894
2023-01-22 16:01:08.632077: step: 852/529, loss: 0.00858303438872099
2023-01-22 16:01:09.720913: step: 856/529, loss: 0.005679039750248194
2023-01-22 16:01:10.808176: step: 860/529, loss: 0.010664182715117931
2023-01-22 16:01:11.886648: step: 864/529, loss: 0.010316543281078339
2023-01-22 16:01:12.967084: step: 868/529, loss: 0.01099282968789339
2023-01-22 16:01:14.032013: step: 872/529, loss: 0.002407555002719164
2023-01-22 16:01:15.112028: step: 876/529, loss: 0.006599427200853825
2023-01-22 16:01:16.190540: step: 880/529, loss: 0.0012035934487357736
2023-01-22 16:01:17.259857: step: 884/529, loss: 0.006955781485885382
2023-01-22 16:01:18.344790: step: 888/529, loss: 0.006533194798976183
2023-01-22 16:01:19.428108: step: 892/529, loss: 0.01938214898109436
2023-01-22 16:01:20.514472: step: 896/529, loss: 0.011880344711244106
2023-01-22 16:01:21.580326: step: 900/529, loss: 0.010847535915672779
2023-01-22 16:01:22.648211: step: 904/529, loss: 0.0011242233449593186
2023-01-22 16:01:23.731752: step: 908/529, loss: 0.006665481254458427
2023-01-22 16:01:24.813654: step: 912/529, loss: 0.004542097914963961
2023-01-22 16:01:25.902384: step: 916/529, loss: 0.01959998533129692
2023-01-22 16:01:26.995054: step: 920/529, loss: 0.009096367284655571
2023-01-22 16:01:28.078753: step: 924/529, loss: 0.01188227254897356
2023-01-22 16:01:29.142401: step: 928/529, loss: 0.007576973643153906
2023-01-22 16:01:30.237223: step: 932/529, loss: 0.002881244057789445
2023-01-22 16:01:31.328592: step: 936/529, loss: 0.008614256978034973
2023-01-22 16:01:32.404207: step: 940/529, loss: 0.0070563205517828465
2023-01-22 16:01:33.475534: step: 944/529, loss: 0.0027562417089939117
2023-01-22 16:01:34.542895: step: 948/529, loss: 0.003601611126214266
2023-01-22 16:01:35.618355: step: 952/529, loss: 0.008946127258241177
2023-01-22 16:01:36.698517: step: 956/529, loss: 0.006065301597118378
2023-01-22 16:01:37.769568: step: 960/529, loss: 0.007183948066085577
2023-01-22 16:01:38.842578: step: 964/529, loss: 0.0026896835770457983
2023-01-22 16:01:39.948627: step: 968/529, loss: 0.014979854226112366
2023-01-22 16:01:41.018268: step: 972/529, loss: 0.00674881786108017
2023-01-22 16:01:42.092301: step: 976/529, loss: 0.008472763933241367
2023-01-22 16:01:43.193110: step: 980/529, loss: 0.015505709685385227
2023-01-22 16:01:44.284384: step: 984/529, loss: 0.01022348552942276
2023-01-22 16:01:45.361341: step: 988/529, loss: 0.05629247799515724
2023-01-22 16:01:46.444316: step: 992/529, loss: 0.011514423415064812
2023-01-22 16:01:47.529503: step: 996/529, loss: 0.0020439212676137686
2023-01-22 16:01:48.591671: step: 1000/529, loss: 0.008712699636816978
2023-01-22 16:01:49.670562: step: 1004/529, loss: 0.008198211900889874
2023-01-22 16:01:50.762451: step: 1008/529, loss: 0.003807215951383114
2023-01-22 16:01:51.855860: step: 1012/529, loss: 0.015538888052105904
2023-01-22 16:01:52.943324: step: 1016/529, loss: 0.0028870285023003817
2023-01-22 16:01:54.034182: step: 1020/529, loss: 0.007703030481934547
2023-01-22 16:01:55.127688: step: 1024/529, loss: 0.002175495494157076
2023-01-22 16:01:56.221462: step: 1028/529, loss: 0.00846147257834673
2023-01-22 16:01:57.321909: step: 1032/529, loss: 0.003329416736960411
2023-01-22 16:01:58.398037: step: 1036/529, loss: 0.0047632367350161076
2023-01-22 16:01:59.506904: step: 1040/529, loss: 0.009274058975279331
2023-01-22 16:02:00.596918: step: 1044/529, loss: 0.002075947355479002
2023-01-22 16:02:01.663863: step: 1048/529, loss: 0.0035732085816562176
2023-01-22 16:02:02.761815: step: 1052/529, loss: 0.015886353328824043
2023-01-22 16:02:03.841691: step: 1056/529, loss: 0.0028083750512450933
2023-01-22 16:02:04.921756: step: 1060/529, loss: 0.00417746277526021
2023-01-22 16:02:06.002780: step: 1064/529, loss: 0.0009289412992075086
2023-01-22 16:02:07.099950: step: 1068/529, loss: 0.004043098539113998
2023-01-22 16:02:08.173816: step: 1072/529, loss: 0.0025499416515231133
2023-01-22 16:02:09.266443: step: 1076/529, loss: 0.009742177091538906
2023-01-22 16:02:10.342112: step: 1080/529, loss: 0.01728571392595768
2023-01-22 16:02:11.445879: step: 1084/529, loss: 0.007542267441749573
2023-01-22 16:02:12.523776: step: 1088/529, loss: 0.0013810511445626616
2023-01-22 16:02:13.602997: step: 1092/529, loss: 0.0022976386826485395
2023-01-22 16:02:14.682490: step: 1096/529, loss: 0.0036816869396716356
2023-01-22 16:02:15.771487: step: 1100/529, loss: 0.004171743523329496
2023-01-22 16:02:16.846159: step: 1104/529, loss: 0.005522042512893677
2023-01-22 16:02:17.931499: step: 1108/529, loss: 0.006198076531291008
2023-01-22 16:02:19.021766: step: 1112/529, loss: 0.0028345489408820868
2023-01-22 16:02:20.102461: step: 1116/529, loss: 0.0005563206505030394
2023-01-22 16:02:21.165830: step: 1120/529, loss: 0.0041571143083274364
2023-01-22 16:02:22.248898: step: 1124/529, loss: 0.0032633799128234386
2023-01-22 16:02:23.324173: step: 1128/529, loss: 0.00960410013794899
2023-01-22 16:02:24.408545: step: 1132/529, loss: 0.004124002065509558
2023-01-22 16:02:25.480855: step: 1136/529, loss: 5.40231440027128e-06
2023-01-22 16:02:26.577725: step: 1140/529, loss: 0.003400008426979184
2023-01-22 16:02:27.684844: step: 1144/529, loss: 0.015203959308564663
2023-01-22 16:02:28.763088: step: 1148/529, loss: 0.012904616072773933
2023-01-22 16:02:29.865372: step: 1152/529, loss: 0.003881575772538781
2023-01-22 16:02:30.946189: step: 1156/529, loss: 0.07048137485980988
2023-01-22 16:02:32.034892: step: 1160/529, loss: 0.005223456304520369
2023-01-22 16:02:33.117203: step: 1164/529, loss: 0.008334493264555931
2023-01-22 16:02:34.224263: step: 1168/529, loss: 0.01136496290564537
2023-01-22 16:02:35.315854: step: 1172/529, loss: 0.005291508976370096
2023-01-22 16:02:36.394994: step: 1176/529, loss: 0.013276208192110062
2023-01-22 16:02:37.474927: step: 1180/529, loss: 0.008856615982949734
2023-01-22 16:02:38.567892: step: 1184/529, loss: 0.00530351884663105
2023-01-22 16:02:39.669993: step: 1188/529, loss: 0.001901112962514162
2023-01-22 16:02:40.761663: step: 1192/529, loss: 0.004477955866605043
2023-01-22 16:02:41.828016: step: 1196/529, loss: 0.010055916383862495
2023-01-22 16:02:42.923264: step: 1200/529, loss: 0.0047800056636333466
2023-01-22 16:02:43.986698: step: 1204/529, loss: 0.0027272680308669806
2023-01-22 16:02:45.061986: step: 1208/529, loss: 0.008661479689180851
2023-01-22 16:02:46.146678: step: 1212/529, loss: 0.0013380871387198567
2023-01-22 16:02:47.223541: step: 1216/529, loss: 0.007114128675311804
2023-01-22 16:02:48.318658: step: 1220/529, loss: 0.011884539388120174
2023-01-22 16:02:49.421437: step: 1224/529, loss: 0.02450762689113617
2023-01-22 16:02:50.498128: step: 1228/529, loss: 0.002024158602580428
2023-01-22 16:02:51.586391: step: 1232/529, loss: 0.008725673891603947
2023-01-22 16:02:52.674585: step: 1236/529, loss: 0.002557213883846998
2023-01-22 16:02:53.762137: step: 1240/529, loss: 0.002870753640308976
2023-01-22 16:02:54.840592: step: 1244/529, loss: 0.00911586731672287
2023-01-22 16:02:55.915295: step: 1248/529, loss: 0.0038410075940191746
2023-01-22 16:02:56.985161: step: 1252/529, loss: 0.029661059379577637
2023-01-22 16:02:58.058716: step: 1256/529, loss: 0.003212140640243888
2023-01-22 16:02:59.133536: step: 1260/529, loss: 0.005618896801024675
2023-01-22 16:03:00.203144: step: 1264/529, loss: 0.008286651223897934
2023-01-22 16:03:01.293636: step: 1268/529, loss: 0.01274032611399889
2023-01-22 16:03:02.361822: step: 1272/529, loss: 0.0037362687289714813
2023-01-22 16:03:03.423245: step: 1276/529, loss: 0.00804054457694292
2023-01-22 16:03:04.504012: step: 1280/529, loss: 0.0012157114688307047
2023-01-22 16:03:05.566435: step: 1284/529, loss: 0.0015416594687849283
2023-01-22 16:03:06.648915: step: 1288/529, loss: 0.004680857062339783
2023-01-22 16:03:07.713787: step: 1292/529, loss: 0.0028292019851505756
2023-01-22 16:03:08.809603: step: 1296/529, loss: 0.08718092739582062
2023-01-22 16:03:09.882121: step: 1300/529, loss: 0.009938710369169712
2023-01-22 16:03:10.980921: step: 1304/529, loss: 0.04332110658288002
2023-01-22 16:03:12.060950: step: 1308/529, loss: 0.006968655623495579
2023-01-22 16:03:13.142339: step: 1312/529, loss: 0.004150428343564272
2023-01-22 16:03:14.227655: step: 1316/529, loss: 0.02297881245613098
2023-01-22 16:03:15.329449: step: 1320/529, loss: 0.014645163901150227
2023-01-22 16:03:16.425742: step: 1324/529, loss: 0.005532841198146343
2023-01-22 16:03:17.508359: step: 1328/529, loss: 0.034226030111312866
2023-01-22 16:03:18.593970: step: 1332/529, loss: 0.01838810183107853
2023-01-22 16:03:19.690346: step: 1336/529, loss: 0.0212626364082098
2023-01-22 16:03:20.778313: step: 1340/529, loss: 0.011266743764281273
2023-01-22 16:03:21.840078: step: 1344/529, loss: 0.0025158508215099573
2023-01-22 16:03:22.922641: step: 1348/529, loss: 0.022542087361216545
2023-01-22 16:03:23.996051: step: 1352/529, loss: 0.0013686477905139327
2023-01-22 16:03:25.074382: step: 1356/529, loss: 0.007258938159793615
2023-01-22 16:03:26.154348: step: 1360/529, loss: 0.009761031717061996
2023-01-22 16:03:27.225370: step: 1364/529, loss: 0.0041913497261703014
2023-01-22 16:03:28.318849: step: 1368/529, loss: 0.008142043836414814
2023-01-22 16:03:29.406345: step: 1372/529, loss: 0.0440276637673378
2023-01-22 16:03:30.475348: step: 1376/529, loss: 0.006626906339079142
2023-01-22 16:03:31.553413: step: 1380/529, loss: 0.01024853065609932
2023-01-22 16:03:32.619110: step: 1384/529, loss: 0.003399195149540901
2023-01-22 16:03:33.713450: step: 1388/529, loss: 0.0031623761169612408
2023-01-22 16:03:34.771132: step: 1392/529, loss: 0.00807243399322033
2023-01-22 16:03:35.842343: step: 1396/529, loss: 0.010173263028264046
2023-01-22 16:03:36.916168: step: 1400/529, loss: 0.0015340005047619343
2023-01-22 16:03:37.994422: step: 1404/529, loss: 0.004942870698869228
2023-01-22 16:03:39.078778: step: 1408/529, loss: 0.0024159541353583336
2023-01-22 16:03:40.154717: step: 1412/529, loss: 0.001312845153734088
2023-01-22 16:03:41.222408: step: 1416/529, loss: 0.012278782203793526
2023-01-22 16:03:42.286593: step: 1420/529, loss: 0.005591663997620344
2023-01-22 16:03:43.376143: step: 1424/529, loss: 0.02819264680147171
2023-01-22 16:03:44.455174: step: 1428/529, loss: 0.007811288814991713
2023-01-22 16:03:45.532602: step: 1432/529, loss: 0.00844008382409811
2023-01-22 16:03:46.628543: step: 1436/529, loss: 0.005512373987585306
2023-01-22 16:03:47.728662: step: 1440/529, loss: 0.0018055766122415662
2023-01-22 16:03:48.803024: step: 1444/529, loss: 0.04203746095299721
2023-01-22 16:03:49.894454: step: 1448/529, loss: 0.007252662442624569
2023-01-22 16:03:50.960706: step: 1452/529, loss: 0.03764216601848602
2023-01-22 16:03:52.012681: step: 1456/529, loss: 0.0005199461593292654
2023-01-22 16:03:53.072276: step: 1460/529, loss: 0.005638635251671076
2023-01-22 16:03:54.128893: step: 1464/529, loss: 0.0021217751782387495
2023-01-22 16:03:55.206735: step: 1468/529, loss: 0.01366223581135273
2023-01-22 16:03:56.269904: step: 1472/529, loss: 0.008197786286473274
2023-01-22 16:03:57.336264: step: 1476/529, loss: 0.043221522122621536
2023-01-22 16:03:58.413364: step: 1480/529, loss: 0.007423872593790293
2023-01-22 16:03:59.483445: step: 1484/529, loss: 0.02055491879582405
2023-01-22 16:04:00.544611: step: 1488/529, loss: 0.003961401991546154
2023-01-22 16:04:01.607330: step: 1492/529, loss: 0.003747825277969241
2023-01-22 16:04:02.667957: step: 1496/529, loss: 0.0010228921892121434
2023-01-22 16:04:03.740091: step: 1500/529, loss: 0.009438322857022285
2023-01-22 16:04:04.809789: step: 1504/529, loss: 0.012222778983414173
2023-01-22 16:04:05.891035: step: 1508/529, loss: 0.009745476767420769
2023-01-22 16:04:06.965987: step: 1512/529, loss: 0.0026218045968562365
2023-01-22 16:04:08.038225: step: 1516/529, loss: 0.0007571568130515516
2023-01-22 16:04:09.108967: step: 1520/529, loss: 0.003980558831244707
2023-01-22 16:04:10.200797: step: 1524/529, loss: 0.01007144432514906
2023-01-22 16:04:11.278000: step: 1528/529, loss: 0.0024592960253357887
2023-01-22 16:04:12.370894: step: 1532/529, loss: 0.0179671049118042
2023-01-22 16:04:13.438772: step: 1536/529, loss: 0.0014771640999242663
2023-01-22 16:04:14.534625: step: 1540/529, loss: 0.013780679553747177
2023-01-22 16:04:15.596058: step: 1544/529, loss: 0.0036924942396581173
2023-01-22 16:04:16.665241: step: 1548/529, loss: 0.007804648019373417
2023-01-22 16:04:17.742743: step: 1552/529, loss: 0.02368420548737049
2023-01-22 16:04:18.794906: step: 1556/529, loss: 0.03424181789159775
2023-01-22 16:04:19.885868: step: 1560/529, loss: 0.005288993939757347
2023-01-22 16:04:20.952845: step: 1564/529, loss: 0.02749105915427208
2023-01-22 16:04:22.036108: step: 1568/529, loss: 0.01094154641032219
2023-01-22 16:04:23.104532: step: 1572/529, loss: 0.0087797362357378
2023-01-22 16:04:24.175422: step: 1576/529, loss: 0.002545113442465663
2023-01-22 16:04:25.260784: step: 1580/529, loss: 0.0016076716128736734
2023-01-22 16:04:26.333434: step: 1584/529, loss: 0.0088021419942379
2023-01-22 16:04:27.404538: step: 1588/529, loss: 0.001380827627144754
2023-01-22 16:04:28.477013: step: 1592/529, loss: 0.0028225325513631105
2023-01-22 16:04:29.548552: step: 1596/529, loss: 0.011315269395709038
2023-01-22 16:04:30.606437: step: 1600/529, loss: 0.006238800007849932
2023-01-22 16:04:31.678141: step: 1604/529, loss: 0.0032620918937027454
2023-01-22 16:04:32.746847: step: 1608/529, loss: 0.0069154370576143265
2023-01-22 16:04:33.819373: step: 1612/529, loss: 0.034226495772600174
2023-01-22 16:04:34.901757: step: 1616/529, loss: 0.004367852117866278
2023-01-22 16:04:35.990845: step: 1620/529, loss: 0.00941659975796938
2023-01-22 16:04:37.089904: step: 1624/529, loss: 0.008812328800559044
2023-01-22 16:04:38.167280: step: 1628/529, loss: 0.0028780994471162558
2023-01-22 16:04:39.241647: step: 1632/529, loss: 0.026409205049276352
2023-01-22 16:04:40.301624: step: 1636/529, loss: 0.004808820318430662
2023-01-22 16:04:41.348791: step: 1640/529, loss: 0.0022123989183455706
2023-01-22 16:04:42.430600: step: 1644/529, loss: 0.09495656937360764
2023-01-22 16:04:43.484133: step: 1648/529, loss: 0.006485449615865946
2023-01-22 16:04:44.559498: step: 1652/529, loss: 0.010328743606805801
2023-01-22 16:04:45.616433: step: 1656/529, loss: 0.010405809618532658
2023-01-22 16:04:46.687839: step: 1660/529, loss: 0.07516153156757355
2023-01-22 16:04:47.768270: step: 1664/529, loss: 0.01170724630355835
2023-01-22 16:04:48.840890: step: 1668/529, loss: 0.0043946923688054085
2023-01-22 16:04:49.924777: step: 1672/529, loss: 0.014025701209902763
2023-01-22 16:04:51.000250: step: 1676/529, loss: 0.005781049374490976
2023-01-22 16:04:52.063228: step: 1680/529, loss: 0.0035958215594291687
2023-01-22 16:04:53.138581: step: 1684/529, loss: 0.019465569406747818
2023-01-22 16:04:54.199634: step: 1688/529, loss: 0.0025285258889198303
2023-01-22 16:04:55.252450: step: 1692/529, loss: 0.003045066259801388
2023-01-22 16:04:56.313117: step: 1696/529, loss: 0.009937570430338383
2023-01-22 16:04:57.371616: step: 1700/529, loss: 0.003986789379268885
2023-01-22 16:04:58.436141: step: 1704/529, loss: 0.00230491254478693
2023-01-22 16:04:59.523949: step: 1708/529, loss: 0.001607365207746625
2023-01-22 16:05:00.599463: step: 1712/529, loss: 0.009701140224933624
2023-01-22 16:05:01.686287: step: 1716/529, loss: 0.022345921024680138
2023-01-22 16:05:02.744344: step: 1720/529, loss: 0.006601015571504831
2023-01-22 16:05:03.817102: step: 1724/529, loss: 0.01697540283203125
2023-01-22 16:05:04.925657: step: 1728/529, loss: 0.006874631159007549
2023-01-22 16:05:06.000118: step: 1732/529, loss: 0.03952629119157791
2023-01-22 16:05:07.066594: step: 1736/529, loss: 0.002731254091486335
2023-01-22 16:05:08.132247: step: 1740/529, loss: 0.00044692287337966263
2023-01-22 16:05:09.187931: step: 1744/529, loss: 0.013179549016058445
2023-01-22 16:05:10.256954: step: 1748/529, loss: 0.0005687236553058028
2023-01-22 16:05:11.332236: step: 1752/529, loss: 0.004726551938802004
2023-01-22 16:05:12.391045: step: 1756/529, loss: 0.02497788332402706
2023-01-22 16:05:13.473581: step: 1760/529, loss: 0.02773934230208397
2023-01-22 16:05:14.542228: step: 1764/529, loss: 0.004229980520904064
2023-01-22 16:05:15.621259: step: 1768/529, loss: 0.008047755807638168
2023-01-22 16:05:16.680792: step: 1772/529, loss: 0.0022551477886736393
2023-01-22 16:05:17.747001: step: 1776/529, loss: 0.0018247365951538086
2023-01-22 16:05:18.829582: step: 1780/529, loss: 0.010773323476314545
2023-01-22 16:05:19.916919: step: 1784/529, loss: 0.04095825180411339
2023-01-22 16:05:20.980832: step: 1788/529, loss: 0.012872646562755108
2023-01-22 16:05:22.046077: step: 1792/529, loss: 0.004160088486969471
2023-01-22 16:05:23.119173: step: 1796/529, loss: 0.0038366459775716066
2023-01-22 16:05:24.178079: step: 1800/529, loss: 0.005891278386116028
2023-01-22 16:05:25.264299: step: 1804/529, loss: 1.0860945621971041e-05
2023-01-22 16:05:26.333818: step: 1808/529, loss: 0.00873658712953329
2023-01-22 16:05:27.398261: step: 1812/529, loss: 0.0007788158836774528
2023-01-22 16:05:28.476053: step: 1816/529, loss: 0.03033316507935524
2023-01-22 16:05:29.549543: step: 1820/529, loss: 0.0031953095458447933
2023-01-22 16:05:30.626683: step: 1824/529, loss: 0.0026121840346604586
2023-01-22 16:05:31.689175: step: 1828/529, loss: 0.011429809965193272
2023-01-22 16:05:32.776078: step: 1832/529, loss: 0.005580891389399767
2023-01-22 16:05:33.845741: step: 1836/529, loss: 0.009507030248641968
2023-01-22 16:05:34.916442: step: 1840/529, loss: 0.008096694946289062
2023-01-22 16:05:35.999179: step: 1844/529, loss: 0.00789687130600214
2023-01-22 16:05:37.077940: step: 1848/529, loss: 0.04057244583964348
2023-01-22 16:05:38.143647: step: 1852/529, loss: 0.005006532184779644
2023-01-22 16:05:39.221061: step: 1856/529, loss: 0.003552117384970188
2023-01-22 16:05:40.302247: step: 1860/529, loss: 0.00452266214415431
2023-01-22 16:05:41.368177: step: 1864/529, loss: 0.00851934403181076
2023-01-22 16:05:42.450577: step: 1868/529, loss: 0.010997751727700233
2023-01-22 16:05:43.514493: step: 1872/529, loss: 0.009946765378117561
2023-01-22 16:05:44.590849: step: 1876/529, loss: 0.01137964241206646
2023-01-22 16:05:45.648436: step: 1880/529, loss: 0.0005444071139208972
2023-01-22 16:05:46.712760: step: 1884/529, loss: 0.003657351015135646
2023-01-22 16:05:47.780571: step: 1888/529, loss: 0.0023001153022050858
2023-01-22 16:05:48.856779: step: 1892/529, loss: 0.0052753109484910965
2023-01-22 16:05:49.934583: step: 1896/529, loss: 0.005844618659466505
2023-01-22 16:05:50.997643: step: 1900/529, loss: 0.005758931860327721
2023-01-22 16:05:52.052968: step: 1904/529, loss: 0.008736329153180122
2023-01-22 16:05:53.109360: step: 1908/529, loss: 0.01070530153810978
2023-01-22 16:05:54.170228: step: 1912/529, loss: 0.004352023359388113
2023-01-22 16:05:55.257329: step: 1916/529, loss: 0.013666080310940742
2023-01-22 16:05:56.311849: step: 1920/529, loss: 0.009677940048277378
2023-01-22 16:05:57.373831: step: 1924/529, loss: 0.005825961474329233
2023-01-22 16:05:58.430774: step: 1928/529, loss: 0.005881572142243385
2023-01-22 16:05:59.490246: step: 1932/529, loss: 0.004065447486937046
2023-01-22 16:06:00.547399: step: 1936/529, loss: 0.004868187475949526
2023-01-22 16:06:01.618155: step: 1940/529, loss: 0.020822836086153984
2023-01-22 16:06:02.698024: step: 1944/529, loss: 0.003358823712915182
2023-01-22 16:06:03.772941: step: 1948/529, loss: 0.03390880674123764
2023-01-22 16:06:04.854760: step: 1952/529, loss: 0.003090057522058487
2023-01-22 16:06:05.923670: step: 1956/529, loss: 0.01908806897699833
2023-01-22 16:06:07.005145: step: 1960/529, loss: 0.004665096290409565
2023-01-22 16:06:08.076455: step: 1964/529, loss: 0.01134908851236105
2023-01-22 16:06:09.150448: step: 1968/529, loss: 0.008327435702085495
2023-01-22 16:06:10.224936: step: 1972/529, loss: 0.005929056089371443
2023-01-22 16:06:11.295979: step: 1976/529, loss: 0.006328521762043238
2023-01-22 16:06:12.367464: step: 1980/529, loss: 0.006182138342410326
2023-01-22 16:06:13.455309: step: 1984/529, loss: 0.004397683311253786
2023-01-22 16:06:14.538805: step: 1988/529, loss: 0.03543352708220482
2023-01-22 16:06:15.600342: step: 1992/529, loss: 0.008861798793077469
2023-01-22 16:06:16.698657: step: 1996/529, loss: 0.009600820019841194
2023-01-22 16:06:17.784293: step: 2000/529, loss: 0.032085221260786057
2023-01-22 16:06:18.839093: step: 2004/529, loss: 0.011869809590280056
2023-01-22 16:06:19.915802: step: 2008/529, loss: 0.0226276908069849
2023-01-22 16:06:20.986722: step: 2012/529, loss: 0.00026266343775205314
2023-01-22 16:06:22.059919: step: 2016/529, loss: 0.002348813693970442
2023-01-22 16:06:23.137494: step: 2020/529, loss: 0.020276904106140137
2023-01-22 16:06:24.191694: step: 2024/529, loss: 0.004203373566269875
2023-01-22 16:06:25.248038: step: 2028/529, loss: 0.01897486485540867
2023-01-22 16:06:26.338078: step: 2032/529, loss: 0.02406066283583641
2023-01-22 16:06:27.398564: step: 2036/529, loss: 0.0016599440714344382
2023-01-22 16:06:28.478438: step: 2040/529, loss: 0.007167106494307518
2023-01-22 16:06:29.543723: step: 2044/529, loss: 0.010923652909696102
2023-01-22 16:06:30.636190: step: 2048/529, loss: 0.0004048360569868237
2023-01-22 16:06:31.715378: step: 2052/529, loss: 0.004154149442911148
2023-01-22 16:06:32.798831: step: 2056/529, loss: 0.009003751911222935
2023-01-22 16:06:33.865392: step: 2060/529, loss: 0.004973648581653833
2023-01-22 16:06:34.950795: step: 2064/529, loss: 0.024084147065877914
2023-01-22 16:06:36.023633: step: 2068/529, loss: 0.00817825272679329
2023-01-22 16:06:37.103345: step: 2072/529, loss: 0.00335396034643054
2023-01-22 16:06:38.172518: step: 2076/529, loss: 0.0033416247460991144
2023-01-22 16:06:39.241117: step: 2080/529, loss: 0.006267180200666189
2023-01-22 16:06:40.313089: step: 2084/529, loss: 0.007855514995753765
2023-01-22 16:06:41.377973: step: 2088/529, loss: 0.003910467494279146
2023-01-22 16:06:42.455499: step: 2092/529, loss: 0.03349063917994499
2023-01-22 16:06:43.544943: step: 2096/529, loss: 0.007858878001570702
2023-01-22 16:06:44.604955: step: 2100/529, loss: 0.006541946437209845
2023-01-22 16:06:45.687972: step: 2104/529, loss: 0.02803930640220642
2023-01-22 16:06:46.758861: step: 2108/529, loss: 0.006639318540692329
2023-01-22 16:06:47.837339: step: 2112/529, loss: 0.01448830496519804
2023-01-22 16:06:48.921201: step: 2116/529, loss: 0.010935690253973007
==================================================
Loss: 0.010
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31648397976391235, 'r': 0.3561195445920304, 'f1': 0.3351339285714286}, 'combined': 0.24694078947368422, 'stategy': 1, 'epoch': 6}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3124354223730105, 'r': 0.31100091630150906, 'f1': 0.31171651896212}, 'combined': 0.20350404864884516, 'stategy': 1, 'epoch': 6}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3223650956284153, 'r': 0.3731360689437065, 'f1': 0.3458974640867781}, 'combined': 0.2548718156428891, 'stategy': 1, 'epoch': 6}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3339019141048318, 'r': 0.3121123590483584, 'f1': 0.322639664270417}, 'combined': 0.21063522123353648, 'stategy': 1, 'epoch': 6}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3090129708599858, 'r': 0.35357651124966116, 'f1': 0.3297961441213654}, 'combined': 0.24300768514205867, 'stategy': 1, 'epoch': 6}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3247006994197632, 'r': 0.32380620713486025, 'f1': 0.32425283638608077}, 'combined': 0.21168838023132733, 'stategy': 1, 'epoch': 6}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 6}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 6}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 6}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32374479166666664, 'r': 0.3685898956356736, 'f1': 0.34471495119787043}, 'combined': 0.25400049035632555, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33423857660835543, 'r': 0.3093550061071819, 'f1': 0.3213157485867436}, 'combined': 0.20977090322243364, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 16:09:24.779645: step: 4/529, loss: 0.00568016991019249
2023-01-22 16:09:25.837690: step: 8/529, loss: 0.0037791873328387737
2023-01-22 16:09:26.913852: step: 12/529, loss: 0.015430057421326637
2023-01-22 16:09:27.972397: step: 16/529, loss: 0.00036626451765187085
2023-01-22 16:09:29.049740: step: 20/529, loss: 0.009316004812717438
2023-01-22 16:09:30.124879: step: 24/529, loss: 0.00023781387426424772
2023-01-22 16:09:31.186350: step: 28/529, loss: 0.0019802323076874018
2023-01-22 16:09:32.260640: step: 32/529, loss: 0.02349786087870598
2023-01-22 16:09:33.329792: step: 36/529, loss: 0.009819498285651207
2023-01-22 16:09:34.384712: step: 40/529, loss: 0.002291661687195301
2023-01-22 16:09:35.454588: step: 44/529, loss: 0.002832529367879033
2023-01-22 16:09:36.523394: step: 48/529, loss: 0.007768876384943724
2023-01-22 16:09:37.586483: step: 52/529, loss: 0.0015841801650822163
2023-01-22 16:09:38.670302: step: 56/529, loss: 0.00557374581694603
2023-01-22 16:09:39.740318: step: 60/529, loss: 0.004808449186384678
2023-01-22 16:09:40.800240: step: 64/529, loss: 0.005983045790344477
2023-01-22 16:09:41.865414: step: 68/529, loss: 0.041461579501628876
2023-01-22 16:09:42.940814: step: 72/529, loss: 0.0038062836974859238
2023-01-22 16:09:44.009089: step: 76/529, loss: 0.005338095128536224
2023-01-22 16:09:45.087749: step: 80/529, loss: 0.0025962344370782375
2023-01-22 16:09:46.147906: step: 84/529, loss: 0.0005924426950514317
2023-01-22 16:09:47.225486: step: 88/529, loss: 0.005933774169534445
2023-01-22 16:09:48.301939: step: 92/529, loss: 0.0009836549870669842
2023-01-22 16:09:49.369088: step: 96/529, loss: 0.025895144790410995
2023-01-22 16:09:50.437682: step: 100/529, loss: 0.0028382393065840006
2023-01-22 16:09:51.515582: step: 104/529, loss: 0.00791685190051794
2023-01-22 16:09:52.594606: step: 108/529, loss: 0.002369657391682267
2023-01-22 16:09:53.655254: step: 112/529, loss: 0.003230104921385646
2023-01-22 16:09:54.759681: step: 116/529, loss: 0.002270039636641741
2023-01-22 16:09:55.831110: step: 120/529, loss: 0.0024864375591278076
2023-01-22 16:09:56.888038: step: 124/529, loss: 0.004147215746343136
2023-01-22 16:09:57.947545: step: 128/529, loss: 0.007507805246859789
2023-01-22 16:09:59.018857: step: 132/529, loss: 0.0028371461667120457
2023-01-22 16:10:00.080120: step: 136/529, loss: 0.04736693948507309
2023-01-22 16:10:01.150097: step: 140/529, loss: 0.00560291251167655
2023-01-22 16:10:02.224158: step: 144/529, loss: 0.0023508346639573574
2023-01-22 16:10:03.323345: step: 148/529, loss: 0.005191101226955652
2023-01-22 16:10:04.387286: step: 152/529, loss: 0.013244339264929295
2023-01-22 16:10:05.443424: step: 156/529, loss: 0.003391327103599906
2023-01-22 16:10:06.498233: step: 160/529, loss: 0.09651968628168106
2023-01-22 16:10:07.547904: step: 164/529, loss: 0.002731872024014592
2023-01-22 16:10:08.630620: step: 168/529, loss: 0.06937011331319809
2023-01-22 16:10:09.694311: step: 172/529, loss: 0.0050599537789821625
2023-01-22 16:10:10.757923: step: 176/529, loss: 0.004609157331287861
2023-01-22 16:10:11.822517: step: 180/529, loss: 0.008236760273575783
2023-01-22 16:10:12.891056: step: 184/529, loss: 0.008219015784561634
2023-01-22 16:10:13.954052: step: 188/529, loss: 0.012265676632523537
2023-01-22 16:10:15.030281: step: 192/529, loss: 0.007208076771348715
2023-01-22 16:10:16.111346: step: 196/529, loss: 0.011508278548717499
2023-01-22 16:10:17.196487: step: 200/529, loss: 0.010133801028132439
2023-01-22 16:10:18.265079: step: 204/529, loss: 0.024479715153574944
2023-01-22 16:10:19.338916: step: 208/529, loss: 0.011863814666867256
2023-01-22 16:10:20.398840: step: 212/529, loss: 0.03410855680704117
2023-01-22 16:10:21.457421: step: 216/529, loss: 0.003080726834014058
2023-01-22 16:10:22.541459: step: 220/529, loss: 0.011270204558968544
2023-01-22 16:10:23.625372: step: 224/529, loss: 0.0021524641197174788
2023-01-22 16:10:24.707688: step: 228/529, loss: 0.003030849387869239
2023-01-22 16:10:25.780357: step: 232/529, loss: 0.012466098181903362
2023-01-22 16:10:26.851408: step: 236/529, loss: 0.005734369158744812
2023-01-22 16:10:27.915561: step: 240/529, loss: 0.0007453287253156304
2023-01-22 16:10:28.983500: step: 244/529, loss: 0.004105732310563326
2023-01-22 16:10:30.048985: step: 248/529, loss: 0.008348530158400536
2023-01-22 16:10:31.111721: step: 252/529, loss: 0.003066055942326784
2023-01-22 16:10:32.176879: step: 256/529, loss: 0.013963768258690834
2023-01-22 16:10:33.240700: step: 260/529, loss: 0.0021843169815838337
2023-01-22 16:10:34.317073: step: 264/529, loss: 0.009637662209570408
2023-01-22 16:10:35.392473: step: 268/529, loss: 0.0020488786976784468
2023-01-22 16:10:36.449908: step: 272/529, loss: 0.002763220341876149
2023-01-22 16:10:37.519271: step: 276/529, loss: 0.004496428184211254
2023-01-22 16:10:38.578027: step: 280/529, loss: 0.009399174712598324
2023-01-22 16:10:39.644799: step: 284/529, loss: 0.011515219695866108
2023-01-22 16:10:40.711922: step: 288/529, loss: 0.019486650824546814
2023-01-22 16:10:41.768485: step: 292/529, loss: 0.010760155506432056
2023-01-22 16:10:42.859166: step: 296/529, loss: 0.007388952653855085
2023-01-22 16:10:43.941329: step: 300/529, loss: 0.001067520584911108
2023-01-22 16:10:45.013778: step: 304/529, loss: 0.013397138565778732
2023-01-22 16:10:46.098264: step: 308/529, loss: 0.0052513135597109795
2023-01-22 16:10:47.166313: step: 312/529, loss: 0.016393117606639862
2023-01-22 16:10:48.228700: step: 316/529, loss: 0.0031123885419219732
2023-01-22 16:10:49.296554: step: 320/529, loss: 0.0034190292935818434
2023-01-22 16:10:50.386822: step: 324/529, loss: 0.005750210955739021
2023-01-22 16:10:51.460494: step: 328/529, loss: 0.041475702077150345
2023-01-22 16:10:52.537569: step: 332/529, loss: 0.0017468280857428908
2023-01-22 16:10:53.620229: step: 336/529, loss: 0.0007696906686760485
2023-01-22 16:10:54.683434: step: 340/529, loss: 0.01678144372999668
2023-01-22 16:10:55.753429: step: 344/529, loss: 0.005581000354140997
2023-01-22 16:10:56.819690: step: 348/529, loss: 0.005104969721287489
2023-01-22 16:10:57.886469: step: 352/529, loss: 0.009868049994111061
2023-01-22 16:10:58.987954: step: 356/529, loss: 0.004311675671488047
2023-01-22 16:11:00.048077: step: 360/529, loss: 0.0024313824251294136
2023-01-22 16:11:01.126510: step: 364/529, loss: 0.00486027542501688
2023-01-22 16:11:02.191718: step: 368/529, loss: 0.003816516138613224
2023-01-22 16:11:03.249033: step: 372/529, loss: 0.0021876327227801085
2023-01-22 16:11:04.311948: step: 376/529, loss: 0.005908139981329441
2023-01-22 16:11:05.381171: step: 380/529, loss: 0.00656081223860383
2023-01-22 16:11:06.459228: step: 384/529, loss: 0.023145845159888268
2023-01-22 16:11:07.538951: step: 388/529, loss: 0.013495726510882378
2023-01-22 16:11:08.611292: step: 392/529, loss: 0.0008799554198049009
2023-01-22 16:11:09.667604: step: 396/529, loss: 0.012078013271093369
2023-01-22 16:11:10.753670: step: 400/529, loss: 0.00843176431953907
2023-01-22 16:11:11.823954: step: 404/529, loss: 0.0032087743747979403
2023-01-22 16:11:12.932299: step: 408/529, loss: 0.013576321303844452
2023-01-22 16:11:14.023199: step: 412/529, loss: 0.0016561581287533045
2023-01-22 16:11:15.091173: step: 416/529, loss: 0.015348426066339016
2023-01-22 16:11:16.147601: step: 420/529, loss: 0.005162274930626154
2023-01-22 16:11:17.220676: step: 424/529, loss: 0.010190640576183796
2023-01-22 16:11:18.284814: step: 428/529, loss: 0.0005091220373287797
2023-01-22 16:11:19.353284: step: 432/529, loss: 0.0019746189936995506
2023-01-22 16:11:20.415652: step: 436/529, loss: 0.021828433498740196
2023-01-22 16:11:21.484222: step: 440/529, loss: 0.005172313190996647
2023-01-22 16:11:22.559980: step: 444/529, loss: 0.0010447107488289475
2023-01-22 16:11:23.645362: step: 448/529, loss: 0.007668701000511646
2023-01-22 16:11:24.712899: step: 452/529, loss: 0.01001465693116188
2023-01-22 16:11:25.757184: step: 456/529, loss: 0.014296041801571846
2023-01-22 16:11:26.841441: step: 460/529, loss: 0.012382669374346733
2023-01-22 16:11:27.915430: step: 464/529, loss: 0.0018333930056542158
2023-01-22 16:11:28.975929: step: 468/529, loss: 0.00012185341620352119
2023-01-22 16:11:30.036795: step: 472/529, loss: 0.010263880714774132
2023-01-22 16:11:31.119896: step: 476/529, loss: 0.029986437410116196
2023-01-22 16:11:32.195053: step: 480/529, loss: 0.003973283804953098
2023-01-22 16:11:33.252748: step: 484/529, loss: 0.02596515417098999
2023-01-22 16:11:34.334246: step: 488/529, loss: 0.005611129105091095
2023-01-22 16:11:35.395528: step: 492/529, loss: 0.004910180810838938
2023-01-22 16:11:36.476534: step: 496/529, loss: 0.022428816184401512
2023-01-22 16:11:37.560235: step: 500/529, loss: 0.029541783034801483
2023-01-22 16:11:38.612645: step: 504/529, loss: 0.0011173203820362687
2023-01-22 16:11:39.671345: step: 508/529, loss: 0.005091271363198757
2023-01-22 16:11:40.736609: step: 512/529, loss: 0.0012395735830068588
2023-01-22 16:11:41.807066: step: 516/529, loss: 0.003120470093563199
2023-01-22 16:11:42.890647: step: 520/529, loss: 0.009806467220187187
2023-01-22 16:11:43.952330: step: 524/529, loss: 0.01977851800620556
2023-01-22 16:11:45.026422: step: 528/529, loss: 0.0020553497597575188
2023-01-22 16:11:46.125952: step: 532/529, loss: 0.005043101031333208
2023-01-22 16:11:47.202342: step: 536/529, loss: 0.001568490406498313
2023-01-22 16:11:48.258060: step: 540/529, loss: 0.009771560318768024
2023-01-22 16:11:49.325375: step: 544/529, loss: 0.0005327824037522078
2023-01-22 16:11:50.387998: step: 548/529, loss: 0.00030661284108646214
2023-01-22 16:11:51.458373: step: 552/529, loss: 0.005557921249419451
2023-01-22 16:11:52.523944: step: 556/529, loss: 0.027158109471201897
2023-01-22 16:11:53.592612: step: 560/529, loss: 0.007757531013339758
2023-01-22 16:11:54.670227: step: 564/529, loss: 4.151556368015008e-06
2023-01-22 16:11:55.739692: step: 568/529, loss: 0.002892021555453539
2023-01-22 16:11:56.806599: step: 572/529, loss: 0.019166069105267525
2023-01-22 16:11:57.868922: step: 576/529, loss: 0.00070958212018013
2023-01-22 16:11:58.932836: step: 580/529, loss: 0.0032791781704872847
2023-01-22 16:12:00.000207: step: 584/529, loss: 0.03315307945013046
2023-01-22 16:12:01.076028: step: 588/529, loss: 0.027390863746404648
2023-01-22 16:12:02.151241: step: 592/529, loss: 0.0028754703234881163
2023-01-22 16:12:03.225147: step: 596/529, loss: 0.018367497250437737
2023-01-22 16:12:04.288398: step: 600/529, loss: 0.007619834970682859
2023-01-22 16:12:05.362686: step: 604/529, loss: 0.027885867282748222
2023-01-22 16:12:06.419935: step: 608/529, loss: 0.0044440398924052715
2023-01-22 16:12:07.474307: step: 612/529, loss: 0.007782158441841602
2023-01-22 16:12:08.542699: step: 616/529, loss: 0.012843900360167027
2023-01-22 16:12:09.640815: step: 620/529, loss: 0.008705461397767067
2023-01-22 16:12:10.707853: step: 624/529, loss: 0.011032906360924244
2023-01-22 16:12:11.767078: step: 628/529, loss: 0.002136365044862032
2023-01-22 16:12:12.868835: step: 632/529, loss: 0.004624108783900738
2023-01-22 16:12:13.924981: step: 636/529, loss: 0.0007290123030543327
2023-01-22 16:12:14.985715: step: 640/529, loss: 0.05365367233753204
2023-01-22 16:12:16.050740: step: 644/529, loss: 0.01255691796541214
2023-01-22 16:12:17.127853: step: 648/529, loss: 0.0006463015452027321
2023-01-22 16:12:18.200900: step: 652/529, loss: 0.006273298058658838
2023-01-22 16:12:19.264491: step: 656/529, loss: 0.0043082935735583305
2023-01-22 16:12:20.349179: step: 660/529, loss: 0.009441153146326542
2023-01-22 16:12:21.404096: step: 664/529, loss: 0.01002568006515503
2023-01-22 16:12:22.468531: step: 668/529, loss: 0.006818255875259638
2023-01-22 16:12:23.559511: step: 672/529, loss: 0.012039298191666603
2023-01-22 16:12:24.631859: step: 676/529, loss: 0.0032885251566767693
2023-01-22 16:12:25.709092: step: 680/529, loss: 0.00021989028027746826
2023-01-22 16:12:26.772869: step: 684/529, loss: 0.003094775602221489
2023-01-22 16:12:27.831162: step: 688/529, loss: 0.004029995761811733
2023-01-22 16:12:28.892953: step: 692/529, loss: 0.021245555952191353
2023-01-22 16:12:29.966708: step: 696/529, loss: 0.004962686914950609
2023-01-22 16:12:31.056371: step: 700/529, loss: 0.008309044875204563
2023-01-22 16:12:32.119982: step: 704/529, loss: 0.009739680215716362
2023-01-22 16:12:33.191005: step: 708/529, loss: 0.0043122423812747
2023-01-22 16:12:34.252157: step: 712/529, loss: 0.0180693157017231
2023-01-22 16:12:35.326532: step: 716/529, loss: 0.0024974641855806112
2023-01-22 16:12:36.395439: step: 720/529, loss: 0.010176624171435833
2023-01-22 16:12:37.474149: step: 724/529, loss: 0.001968876225873828
2023-01-22 16:12:38.539468: step: 728/529, loss: 0.006001739297062159
2023-01-22 16:12:39.605170: step: 732/529, loss: 0.0044102114625275135
2023-01-22 16:12:40.678087: step: 736/529, loss: 0.0091475248336792
2023-01-22 16:12:41.742487: step: 740/529, loss: 0.015723884105682373
2023-01-22 16:12:42.811667: step: 744/529, loss: 0.012495236471295357
2023-01-22 16:12:43.884987: step: 748/529, loss: 0.006256813183426857
2023-01-22 16:12:44.944805: step: 752/529, loss: 0.004281683824956417
2023-01-22 16:12:46.017251: step: 756/529, loss: 0.016755009070038795
2023-01-22 16:12:47.072691: step: 760/529, loss: 0.010574867017567158
2023-01-22 16:12:48.147709: step: 764/529, loss: 0.005176052916795015
2023-01-22 16:12:49.213438: step: 768/529, loss: 0.006731318309903145
2023-01-22 16:12:50.289811: step: 772/529, loss: 0.008975555188953876
2023-01-22 16:12:51.357906: step: 776/529, loss: 0.0026803144719451666
2023-01-22 16:12:52.419857: step: 780/529, loss: 0.01217376347631216
2023-01-22 16:12:53.483988: step: 784/529, loss: 0.006609021220356226
2023-01-22 16:12:54.542215: step: 788/529, loss: 0.0013147088466212153
2023-01-22 16:12:55.628721: step: 792/529, loss: 0.0032262145541608334
2023-01-22 16:12:56.699676: step: 796/529, loss: 0.0058262962847948074
2023-01-22 16:12:57.764442: step: 800/529, loss: 0.001048209727741778
2023-01-22 16:12:58.822748: step: 804/529, loss: 0.00857475120574236
2023-01-22 16:12:59.894934: step: 808/529, loss: 0.02058105729520321
2023-01-22 16:13:00.953923: step: 812/529, loss: 0.009505290538072586
2023-01-22 16:13:02.045439: step: 816/529, loss: 0.000214135114219971
2023-01-22 16:13:03.113343: step: 820/529, loss: 0.017492523416876793
2023-01-22 16:13:04.172363: step: 824/529, loss: 0.0019358092686161399
2023-01-22 16:13:05.237055: step: 828/529, loss: 0.0013326627667993307
2023-01-22 16:13:06.314886: step: 832/529, loss: 0.005512428004294634
2023-01-22 16:13:07.380570: step: 836/529, loss: 0.0008948629256337881
2023-01-22 16:13:08.467364: step: 840/529, loss: 0.02665616013109684
2023-01-22 16:13:09.513496: step: 844/529, loss: 0.00874472688883543
2023-01-22 16:13:10.588579: step: 848/529, loss: 0.005078576970845461
2023-01-22 16:13:11.657788: step: 852/529, loss: 0.015749715268611908
2023-01-22 16:13:12.722699: step: 856/529, loss: 0.003927599173039198
2023-01-22 16:13:13.792982: step: 860/529, loss: 0.0026331909466534853
2023-01-22 16:13:14.864582: step: 864/529, loss: 0.0033662368077784777
2023-01-22 16:13:15.932621: step: 868/529, loss: 0.0042876508086919785
2023-01-22 16:13:17.011097: step: 872/529, loss: 0.013326133601367474
2023-01-22 16:13:18.088833: step: 876/529, loss: 0.02533111348748207
2023-01-22 16:13:19.158698: step: 880/529, loss: 0.004523855168372393
2023-01-22 16:13:20.229734: step: 884/529, loss: 0.0015018930425867438
2023-01-22 16:13:21.311801: step: 888/529, loss: 0.004736669827252626
2023-01-22 16:13:22.385071: step: 892/529, loss: 0.004544378258287907
2023-01-22 16:13:23.459273: step: 896/529, loss: 0.0035141941625624895
2023-01-22 16:13:24.525358: step: 900/529, loss: 0.014882017858326435
2023-01-22 16:13:25.599115: step: 904/529, loss: 0.027485407888889313
2023-01-22 16:13:26.667963: step: 908/529, loss: 0.0007455486920662224
2023-01-22 16:13:27.730062: step: 912/529, loss: 0.014828327111899853
2023-01-22 16:13:28.806424: step: 916/529, loss: 0.024159684777259827
2023-01-22 16:13:29.888542: step: 920/529, loss: 0.0006692619062960148
2023-01-22 16:13:30.970356: step: 924/529, loss: 0.006813994143158197
2023-01-22 16:13:32.064973: step: 928/529, loss: 0.002748151309788227
2023-01-22 16:13:33.121766: step: 932/529, loss: 0.003093400038778782
2023-01-22 16:13:34.205708: step: 936/529, loss: 0.011748131364583969
2023-01-22 16:13:35.275466: step: 940/529, loss: 0.016738710924983025
2023-01-22 16:13:36.351387: step: 944/529, loss: 0.0034232211764901876
2023-01-22 16:13:37.434208: step: 948/529, loss: 0.017535418272018433
2023-01-22 16:13:38.498976: step: 952/529, loss: 0.020190685987472534
2023-01-22 16:13:39.569868: step: 956/529, loss: 0.00412218039855361
2023-01-22 16:13:40.649161: step: 960/529, loss: 0.0016655544750392437
2023-01-22 16:13:41.732851: step: 964/529, loss: 0.023878321051597595
2023-01-22 16:13:42.792696: step: 968/529, loss: 0.0038219469133764505
2023-01-22 16:13:43.872122: step: 972/529, loss: 0.0014707164373248816
2023-01-22 16:13:44.966982: step: 976/529, loss: 0.016964400187134743
2023-01-22 16:13:46.038444: step: 980/529, loss: 0.005282182712107897
2023-01-22 16:13:47.112937: step: 984/529, loss: 0.0019000746542587876
2023-01-22 16:13:48.182709: step: 988/529, loss: 0.016119830310344696
2023-01-22 16:13:49.255547: step: 992/529, loss: 0.0033304672688245773
2023-01-22 16:13:50.319515: step: 996/529, loss: 0.0003596344031393528
2023-01-22 16:13:51.390390: step: 1000/529, loss: 0.014452248811721802
2023-01-22 16:13:52.464256: step: 1004/529, loss: 0.00019113316375296563
2023-01-22 16:13:53.536004: step: 1008/529, loss: 0.0005143745802342892
2023-01-22 16:13:54.596065: step: 1012/529, loss: 0.006043735425919294
2023-01-22 16:13:55.657307: step: 1016/529, loss: 0.010864400304853916
2023-01-22 16:13:56.758511: step: 1020/529, loss: 0.003958025481551886
2023-01-22 16:13:57.856345: step: 1024/529, loss: 0.0020520146936178207
2023-01-22 16:13:58.940332: step: 1028/529, loss: 0.0029882951639592648
2023-01-22 16:14:00.016750: step: 1032/529, loss: 0.002661942271515727
2023-01-22 16:14:01.105952: step: 1036/529, loss: 0.00633154297247529
2023-01-22 16:14:02.185937: step: 1040/529, loss: 0.002098259748890996
2023-01-22 16:14:03.246541: step: 1044/529, loss: 0.008438413962721825
2023-01-22 16:14:04.304937: step: 1048/529, loss: 0.007111316546797752
2023-01-22 16:14:05.396029: step: 1052/529, loss: 0.0058357128873467445
2023-01-22 16:14:06.483461: step: 1056/529, loss: 0.00228347210213542
2023-01-22 16:14:07.555434: step: 1060/529, loss: 0.0008982159197330475
2023-01-22 16:14:08.636272: step: 1064/529, loss: 0.008492826484143734
2023-01-22 16:14:09.695601: step: 1068/529, loss: 0.006082760635763407
2023-01-22 16:14:10.777835: step: 1072/529, loss: 0.004790329374372959
2023-01-22 16:14:11.856340: step: 1076/529, loss: 0.009013747796416283
2023-01-22 16:14:12.932930: step: 1080/529, loss: 0.003286935854703188
2023-01-22 16:14:14.022443: step: 1084/529, loss: 0.0022279697004705667
2023-01-22 16:14:15.093843: step: 1088/529, loss: 0.005761610809713602
2023-01-22 16:14:16.162803: step: 1092/529, loss: 0.005899119656533003
2023-01-22 16:14:17.242321: step: 1096/529, loss: 0.0059688580222427845
2023-01-22 16:14:18.322342: step: 1100/529, loss: 0.003196155186742544
2023-01-22 16:14:19.405071: step: 1104/529, loss: 0.0008680655155330896
2023-01-22 16:14:20.476061: step: 1108/529, loss: 0.0014954046346247196
2023-01-22 16:14:21.571024: step: 1112/529, loss: 0.01368359848856926
2023-01-22 16:14:22.638967: step: 1116/529, loss: 0.007206558249890804
2023-01-22 16:14:23.717707: step: 1120/529, loss: 0.004152627661824226
2023-01-22 16:14:24.790430: step: 1124/529, loss: 0.011732162907719612
2023-01-22 16:14:25.873079: step: 1128/529, loss: 0.009585341438651085
2023-01-22 16:14:26.937550: step: 1132/529, loss: 0.01096218079328537
2023-01-22 16:14:28.021820: step: 1136/529, loss: 0.0029368819668889046
2023-01-22 16:14:29.100287: step: 1140/529, loss: 0.008652622811496258
2023-01-22 16:14:30.162165: step: 1144/529, loss: 0.0013932700967416167
2023-01-22 16:14:31.239568: step: 1148/529, loss: 0.009043017402291298
2023-01-22 16:14:32.308179: step: 1152/529, loss: 0.012237952090799809
2023-01-22 16:14:33.400466: step: 1156/529, loss: 0.0013904266525059938
2023-01-22 16:14:34.492105: step: 1160/529, loss: 0.0032105050049722195
2023-01-22 16:14:35.558316: step: 1164/529, loss: 0.007998811081051826
2023-01-22 16:14:36.645157: step: 1168/529, loss: 0.002177305519580841
2023-01-22 16:14:37.711560: step: 1172/529, loss: 0.0014117809478193521
2023-01-22 16:14:38.784553: step: 1176/529, loss: 0.02790038473904133
2023-01-22 16:14:39.852142: step: 1180/529, loss: 0.0012378093088045716
2023-01-22 16:14:40.932074: step: 1184/529, loss: 0.0012186041567474604
2023-01-22 16:14:42.011654: step: 1188/529, loss: 0.006064120680093765
2023-01-22 16:14:43.098527: step: 1192/529, loss: 0.0009852745570242405
2023-01-22 16:14:44.163939: step: 1196/529, loss: 0.006969446316361427
2023-01-22 16:14:45.240321: step: 1200/529, loss: 0.006442433223128319
2023-01-22 16:14:46.302487: step: 1204/529, loss: 0.013939647004008293
2023-01-22 16:14:47.366846: step: 1208/529, loss: 0.0012466382468119264
2023-01-22 16:14:48.443778: step: 1212/529, loss: 0.006464638747274876
2023-01-22 16:14:49.515880: step: 1216/529, loss: 0.010552704334259033
2023-01-22 16:14:50.608521: step: 1220/529, loss: 0.01777702011168003
2023-01-22 16:14:51.695121: step: 1224/529, loss: 0.0006012205849401653
2023-01-22 16:14:52.768042: step: 1228/529, loss: 0.0002604760811664164
2023-01-22 16:14:53.853951: step: 1232/529, loss: 0.000569429190363735
2023-01-22 16:14:54.934600: step: 1236/529, loss: 0.01760999858379364
2023-01-22 16:14:56.013215: step: 1240/529, loss: 0.0448414571583271
2023-01-22 16:14:57.083413: step: 1244/529, loss: 0.002511577680706978
2023-01-22 16:14:58.169152: step: 1248/529, loss: 0.002938677091151476
2023-01-22 16:14:59.261858: step: 1252/529, loss: 0.016430296003818512
2023-01-22 16:15:00.349637: step: 1256/529, loss: 0.00340069318190217
2023-01-22 16:15:01.425099: step: 1260/529, loss: 0.009581729769706726
2023-01-22 16:15:02.516209: step: 1264/529, loss: 0.00018196339078713208
2023-01-22 16:15:03.594645: step: 1268/529, loss: 0.00011938531679334119
2023-01-22 16:15:04.681100: step: 1272/529, loss: 0.0028011722024530172
2023-01-22 16:15:05.744610: step: 1276/529, loss: 0.011804710142314434
2023-01-22 16:15:06.818692: step: 1280/529, loss: 0.004475636873394251
2023-01-22 16:15:07.896351: step: 1284/529, loss: 0.007032283581793308
2023-01-22 16:15:08.988345: step: 1288/529, loss: 0.000515773834194988
2023-01-22 16:15:10.062718: step: 1292/529, loss: 0.019129138439893723
2023-01-22 16:15:11.154154: step: 1296/529, loss: 0.006546602584421635
2023-01-22 16:15:12.245959: step: 1300/529, loss: 0.015814706683158875
2023-01-22 16:15:13.355885: step: 1304/529, loss: 0.0037350074853748083
2023-01-22 16:15:14.430622: step: 1308/529, loss: 0.012844981625676155
2023-01-22 16:15:15.506752: step: 1312/529, loss: 0.015001154504716396
2023-01-22 16:15:16.576660: step: 1316/529, loss: 0.0049246507696807384
2023-01-22 16:15:17.648143: step: 1320/529, loss: 0.002503888914361596
2023-01-22 16:15:18.719194: step: 1324/529, loss: 0.0045127859339118
2023-01-22 16:15:19.794648: step: 1328/529, loss: 0.009251574985682964
2023-01-22 16:15:20.865852: step: 1332/529, loss: 0.00950449239462614
2023-01-22 16:15:21.919820: step: 1336/529, loss: 0.007390092592686415
2023-01-22 16:15:22.998263: step: 1340/529, loss: 0.009491657838225365
2023-01-22 16:15:24.069111: step: 1344/529, loss: 0.023269934579730034
2023-01-22 16:15:25.136986: step: 1348/529, loss: 0.002573844976723194
2023-01-22 16:15:26.224189: step: 1352/529, loss: 0.02060754783451557
2023-01-22 16:15:27.317811: step: 1356/529, loss: 0.004539800342172384
2023-01-22 16:15:28.413284: step: 1360/529, loss: 0.007307715248316526
2023-01-22 16:15:29.488791: step: 1364/529, loss: 0.0040616742335259914
2023-01-22 16:15:30.562246: step: 1368/529, loss: 0.0008702565683051944
2023-01-22 16:15:31.641520: step: 1372/529, loss: 0.0022693159990012646
2023-01-22 16:15:32.712711: step: 1376/529, loss: 0.015980953350663185
2023-01-22 16:15:33.783468: step: 1380/529, loss: 0.04366021603345871
2023-01-22 16:15:34.853618: step: 1384/529, loss: 0.00546699995175004
2023-01-22 16:15:35.910872: step: 1388/529, loss: 0.006896627135574818
2023-01-22 16:15:37.016848: step: 1392/529, loss: 0.01586287096142769
2023-01-22 16:15:38.075368: step: 1396/529, loss: 0.0013543320819735527
2023-01-22 16:15:39.135158: step: 1400/529, loss: 0.003794848918914795
2023-01-22 16:15:40.203870: step: 1404/529, loss: 0.005269336514174938
2023-01-22 16:15:41.267424: step: 1408/529, loss: 0.0042932601645588875
2023-01-22 16:15:42.322517: step: 1412/529, loss: 0.004138121381402016
2023-01-22 16:15:43.411770: step: 1416/529, loss: 0.0054690176621079445
2023-01-22 16:15:44.489118: step: 1420/529, loss: 0.022345731034874916
2023-01-22 16:15:45.563498: step: 1424/529, loss: 0.0009192422730848193
2023-01-22 16:15:46.619187: step: 1428/529, loss: 0.002709059277549386
2023-01-22 16:15:47.709526: step: 1432/529, loss: 0.007847032509744167
2023-01-22 16:15:48.801371: step: 1436/529, loss: 0.032989751547575
2023-01-22 16:15:49.895343: step: 1440/529, loss: 0.007617088500410318
2023-01-22 16:15:50.976262: step: 1444/529, loss: 0.006016429979354143
2023-01-22 16:15:52.046132: step: 1448/529, loss: 0.004423749167472124
2023-01-22 16:15:53.106837: step: 1452/529, loss: 0.0006823095609433949
2023-01-22 16:15:54.184929: step: 1456/529, loss: 0.0030739593785256147
2023-01-22 16:15:55.252068: step: 1460/529, loss: 0.0021899263374507427
2023-01-22 16:15:56.338921: step: 1464/529, loss: 0.005480119958519936
2023-01-22 16:15:57.411091: step: 1468/529, loss: 0.02652132697403431
2023-01-22 16:15:58.487520: step: 1472/529, loss: 0.005870181601494551
2023-01-22 16:15:59.555060: step: 1476/529, loss: 0.0050626457668840885
2023-01-22 16:16:00.641312: step: 1480/529, loss: 0.008457575924694538
2023-01-22 16:16:01.717422: step: 1484/529, loss: 0.02206493727862835
2023-01-22 16:16:02.781153: step: 1488/529, loss: 0.011269577778875828
2023-01-22 16:16:03.858878: step: 1492/529, loss: 0.0010914630256593227
2023-01-22 16:16:04.938698: step: 1496/529, loss: 0.007932956330478191
2023-01-22 16:16:06.002634: step: 1500/529, loss: 0.0023037916980683804
2023-01-22 16:16:07.097723: step: 1504/529, loss: 0.006315466947853565
2023-01-22 16:16:08.180291: step: 1508/529, loss: 0.005262590479105711
2023-01-22 16:16:09.241126: step: 1512/529, loss: 0.0
2023-01-22 16:16:10.303763: step: 1516/529, loss: 0.00033349369186908007
2023-01-22 16:16:11.381383: step: 1520/529, loss: 0.005749932955950499
2023-01-22 16:16:12.471871: step: 1524/529, loss: 0.002397337928414345
2023-01-22 16:16:13.568392: step: 1528/529, loss: 0.00247242022305727
2023-01-22 16:16:14.631784: step: 1532/529, loss: 0.012600021436810493
2023-01-22 16:16:15.700074: step: 1536/529, loss: 0.018075793981552124
2023-01-22 16:16:16.790149: step: 1540/529, loss: 0.006383591331541538
2023-01-22 16:16:17.861938: step: 1544/529, loss: 0.002323059132322669
2023-01-22 16:16:18.940104: step: 1548/529, loss: 0.014821457676589489
2023-01-22 16:16:20.006999: step: 1552/529, loss: 0.00607643648982048
2023-01-22 16:16:21.097826: step: 1556/529, loss: 0.003533856011927128
2023-01-22 16:16:22.155823: step: 1560/529, loss: 0.04687945917248726
2023-01-22 16:16:23.234373: step: 1564/529, loss: 0.03262916952371597
2023-01-22 16:16:24.309343: step: 1568/529, loss: 0.004752876702696085
2023-01-22 16:16:25.378077: step: 1572/529, loss: 0.0013683937722817063
2023-01-22 16:16:26.436644: step: 1576/529, loss: 0.006566714495420456
2023-01-22 16:16:27.510197: step: 1580/529, loss: 0.01917283982038498
2023-01-22 16:16:28.604044: step: 1584/529, loss: 0.003517351346090436
2023-01-22 16:16:29.680330: step: 1588/529, loss: 0.00024256319738924503
2023-01-22 16:16:30.739820: step: 1592/529, loss: 0.0010324452305212617
2023-01-22 16:16:31.813769: step: 1596/529, loss: 0.0018782115075737238
2023-01-22 16:16:32.906193: step: 1600/529, loss: 0.07054159790277481
2023-01-22 16:16:33.973868: step: 1604/529, loss: 0.011130588129162788
2023-01-22 16:16:35.045347: step: 1608/529, loss: 0.0020678380969911814
2023-01-22 16:16:36.115599: step: 1612/529, loss: 0.005637689493596554
2023-01-22 16:16:37.196665: step: 1616/529, loss: 0.004181877709925175
2023-01-22 16:16:38.280013: step: 1620/529, loss: 0.006981275975704193
2023-01-22 16:16:39.351916: step: 1624/529, loss: 0.004725219216197729
2023-01-22 16:16:40.400873: step: 1628/529, loss: 0.006260905880481005
2023-01-22 16:16:41.474117: step: 1632/529, loss: 0.0015165150398388505
2023-01-22 16:16:42.562037: step: 1636/529, loss: 0.0038289874792099
2023-01-22 16:16:43.645975: step: 1640/529, loss: 0.004182036500424147
2023-01-22 16:16:44.718481: step: 1644/529, loss: 0.004378526005893946
2023-01-22 16:16:45.789832: step: 1648/529, loss: 0.004563461989164352
2023-01-22 16:16:46.867307: step: 1652/529, loss: 0.005700966808944941
2023-01-22 16:16:47.957659: step: 1656/529, loss: 0.009548171423375607
2023-01-22 16:16:49.036086: step: 1660/529, loss: 0.0041475142352283
2023-01-22 16:16:50.114289: step: 1664/529, loss: 0.05564342439174652
2023-01-22 16:16:51.171469: step: 1668/529, loss: 0.00832329224795103
2023-01-22 16:16:52.239367: step: 1672/529, loss: 0.004141243640333414
2023-01-22 16:16:53.320725: step: 1676/529, loss: 0.0066801016218960285
2023-01-22 16:16:54.404876: step: 1680/529, loss: 0.0024728206917643547
2023-01-22 16:16:55.491588: step: 1684/529, loss: 0.006450298707932234
2023-01-22 16:16:56.574261: step: 1688/529, loss: 0.006854694336652756
2023-01-22 16:16:57.665783: step: 1692/529, loss: 0.006273137405514717
2023-01-22 16:16:58.760650: step: 1696/529, loss: 0.002281331457197666
2023-01-22 16:16:59.829720: step: 1700/529, loss: 0.0009556938894093037
2023-01-22 16:17:00.901992: step: 1704/529, loss: 0.012507337145507336
2023-01-22 16:17:01.979086: step: 1708/529, loss: 0.0009623004589229822
2023-01-22 16:17:03.075539: step: 1712/529, loss: 0.0036687704268842936
2023-01-22 16:17:04.168517: step: 1716/529, loss: 0.00023484372650273144
2023-01-22 16:17:05.236645: step: 1720/529, loss: 0.0043158261105418205
2023-01-22 16:17:06.310570: step: 1724/529, loss: 0.010423144325613976
2023-01-22 16:17:07.381350: step: 1728/529, loss: 0.009649207815527916
2023-01-22 16:17:08.453865: step: 1732/529, loss: 0.015450162813067436
2023-01-22 16:17:09.514257: step: 1736/529, loss: 0.0005176262930035591
2023-01-22 16:17:10.592413: step: 1740/529, loss: 0.004055425059050322
2023-01-22 16:17:11.662739: step: 1744/529, loss: 0.009960419498383999
2023-01-22 16:17:12.744115: step: 1748/529, loss: 0.026089394465088844
2023-01-22 16:17:13.842448: step: 1752/529, loss: 0.016885975375771523
2023-01-22 16:17:14.923812: step: 1756/529, loss: 0.004090787842869759
2023-01-22 16:17:15.991882: step: 1760/529, loss: 0.0048917243257164955
2023-01-22 16:17:17.070381: step: 1764/529, loss: 0.010180746205151081
2023-01-22 16:17:18.150163: step: 1768/529, loss: 0.003251784946769476
2023-01-22 16:17:19.217794: step: 1772/529, loss: 0.0033885561861097813
2023-01-22 16:17:20.298123: step: 1776/529, loss: 0.006806801538914442
2023-01-22 16:17:21.380533: step: 1780/529, loss: 0.010073409415781498
2023-01-22 16:17:22.455360: step: 1784/529, loss: 0.009834295138716698
2023-01-22 16:17:23.543239: step: 1788/529, loss: 0.006426077801734209
2023-01-22 16:17:24.621680: step: 1792/529, loss: 0.027749070897698402
2023-01-22 16:17:25.697612: step: 1796/529, loss: 0.02370607480406761
2023-01-22 16:17:26.801578: step: 1800/529, loss: 0.005324054043740034
2023-01-22 16:17:27.881350: step: 1804/529, loss: 0.0025302397552877665
2023-01-22 16:17:28.972435: step: 1808/529, loss: 0.0009093704866245389
2023-01-22 16:17:30.058534: step: 1812/529, loss: 0.0007821667823009193
2023-01-22 16:17:31.123040: step: 1816/529, loss: 0.006052022334188223
2023-01-22 16:17:32.187609: step: 1820/529, loss: 0.00571755226701498
2023-01-22 16:17:33.252975: step: 1824/529, loss: 0.00827968493103981
2023-01-22 16:17:34.311798: step: 1828/529, loss: 0.006284003611654043
2023-01-22 16:17:35.386063: step: 1832/529, loss: 0.002431155415251851
2023-01-22 16:17:36.460551: step: 1836/529, loss: 0.008903119713068008
2023-01-22 16:17:37.530070: step: 1840/529, loss: 0.001334880362264812
2023-01-22 16:17:38.617493: step: 1844/529, loss: 0.006673356983810663
2023-01-22 16:17:39.684823: step: 1848/529, loss: 0.0008704556967131793
2023-01-22 16:17:40.759541: step: 1852/529, loss: 0.009662069380283356
2023-01-22 16:17:41.833231: step: 1856/529, loss: 0.010032053105533123
2023-01-22 16:17:42.927360: step: 1860/529, loss: 0.006116312928497791
2023-01-22 16:17:44.022054: step: 1864/529, loss: 0.002026266884058714
2023-01-22 16:17:45.110542: step: 1868/529, loss: 0.04767926037311554
2023-01-22 16:17:46.183654: step: 1872/529, loss: 0.0015611908165737987
2023-01-22 16:17:47.274620: step: 1876/529, loss: 0.0031267593149095774
2023-01-22 16:17:48.359111: step: 1880/529, loss: 0.005828710738569498
2023-01-22 16:17:49.428836: step: 1884/529, loss: 0.003626617370173335
2023-01-22 16:17:50.502519: step: 1888/529, loss: 0.004030480049550533
2023-01-22 16:17:51.593365: step: 1892/529, loss: 0.010975723154842854
2023-01-22 16:17:52.657263: step: 1896/529, loss: 0.0027940827421844006
2023-01-22 16:17:53.730615: step: 1900/529, loss: 0.0009849475463852286
2023-01-22 16:17:54.808190: step: 1904/529, loss: 0.007541480008512735
2023-01-22 16:17:55.882331: step: 1908/529, loss: 0.005235531833022833
2023-01-22 16:17:56.964529: step: 1912/529, loss: 0.003981713205575943
2023-01-22 16:17:58.023293: step: 1916/529, loss: 0.05958854779601097
2023-01-22 16:17:59.086084: step: 1920/529, loss: 0.007360525894910097
2023-01-22 16:18:00.158289: step: 1924/529, loss: 0.013344666920602322
2023-01-22 16:18:01.239778: step: 1928/529, loss: 0.0014688002411276102
2023-01-22 16:18:02.305244: step: 1932/529, loss: 0.0036034630611538887
2023-01-22 16:18:03.365340: step: 1936/529, loss: 0.009805344976484776
2023-01-22 16:18:04.448100: step: 1940/529, loss: 0.002524876967072487
2023-01-22 16:18:05.515136: step: 1944/529, loss: 0.004475317429751158
2023-01-22 16:18:06.590411: step: 1948/529, loss: 0.0008972417563199997
2023-01-22 16:18:07.676962: step: 1952/529, loss: 0.004966420587152243
2023-01-22 16:18:08.751554: step: 1956/529, loss: 0.006108081433922052
2023-01-22 16:18:09.821239: step: 1960/529, loss: 0.01398506760597229
2023-01-22 16:18:10.897353: step: 1964/529, loss: 0.009954427368938923
2023-01-22 16:18:11.968395: step: 1968/529, loss: 0.004458195064216852
2023-01-22 16:18:13.036487: step: 1972/529, loss: 0.0044325548224151134
2023-01-22 16:18:14.113428: step: 1976/529, loss: 0.011509330943226814
2023-01-22 16:18:15.189759: step: 1980/529, loss: 0.017971521243453026
2023-01-22 16:18:16.257162: step: 1984/529, loss: 0.005178586579859257
2023-01-22 16:18:17.328668: step: 1988/529, loss: 0.0030492593068629503
2023-01-22 16:18:18.399223: step: 1992/529, loss: 0.003938610199838877
2023-01-22 16:18:19.467639: step: 1996/529, loss: 0.010159165598452091
2023-01-22 16:18:20.569588: step: 2000/529, loss: 0.0029523978009819984
2023-01-22 16:18:21.641674: step: 2004/529, loss: 0.005174259189516306
2023-01-22 16:18:22.701865: step: 2008/529, loss: 0.027476996183395386
2023-01-22 16:18:23.771915: step: 2012/529, loss: 0.024513723328709602
2023-01-22 16:18:24.842391: step: 2016/529, loss: 0.0024818151723593473
2023-01-22 16:18:25.916235: step: 2020/529, loss: 0.0431428998708725
2023-01-22 16:18:26.994023: step: 2024/529, loss: 0.02708708494901657
2023-01-22 16:18:28.076298: step: 2028/529, loss: 0.004642784595489502
2023-01-22 16:18:29.155179: step: 2032/529, loss: 0.01315707340836525
2023-01-22 16:18:30.226976: step: 2036/529, loss: 0.003880305215716362
2023-01-22 16:18:31.287586: step: 2040/529, loss: 0.00948945339769125
2023-01-22 16:18:32.331328: step: 2044/529, loss: 0.025201668962836266
2023-01-22 16:18:33.403411: step: 2048/529, loss: 0.006676464341580868
2023-01-22 16:18:34.462555: step: 2052/529, loss: 0.0044360230676829815
2023-01-22 16:18:35.531692: step: 2056/529, loss: 0.008129360154271126
2023-01-22 16:18:36.599395: step: 2060/529, loss: 0.016363075003027916
2023-01-22 16:18:37.680683: step: 2064/529, loss: 0.009301436133682728
2023-01-22 16:18:38.744418: step: 2068/529, loss: 0.0007248249021358788
2023-01-22 16:18:39.813852: step: 2072/529, loss: 0.0004125684790778905
2023-01-22 16:18:40.878056: step: 2076/529, loss: 0.0022369003854691982
2023-01-22 16:18:41.955439: step: 2080/529, loss: 0.00980714987963438
2023-01-22 16:18:43.034675: step: 2084/529, loss: 0.01985403709113598
2023-01-22 16:18:44.107255: step: 2088/529, loss: 0.014631159603595734
2023-01-22 16:18:45.174086: step: 2092/529, loss: 0.005297543480992317
2023-01-22 16:18:46.245914: step: 2096/529, loss: 0.006698545068502426
2023-01-22 16:18:47.327956: step: 2100/529, loss: 0.0017708899686113
2023-01-22 16:18:48.391970: step: 2104/529, loss: 0.0005140889552421868
2023-01-22 16:18:49.469410: step: 2108/529, loss: 0.03649412468075752
2023-01-22 16:18:50.542848: step: 2112/529, loss: 0.004563836380839348
2023-01-22 16:18:51.609253: step: 2116/529, loss: 0.010992822237312794
==================================================
Loss: 0.009
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31693548387096776, 'r': 0.35422201138519926, 'f1': 0.3345430107526882}, 'combined': 0.24650537634408604, 'stategy': 1, 'epoch': 7}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3036675099788478, 'r': 0.3053421469824076, 'f1': 0.3045025260466173}, 'combined': 0.19879439524286932, 'stategy': 1, 'epoch': 7}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31548084843492585, 'r': 0.363371679316888, 'f1': 0.3377369929453263}, 'combined': 0.2488588369070825, 'stategy': 1, 'epoch': 7}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32935627105507187, 'r': 0.31119324140129956, 'f1': 0.32001724635596784}, 'combined': 0.20892317637747124, 'stategy': 1, 'epoch': 7}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3115037751677852, 'r': 0.35228889943074004, 'f1': 0.33064336598397154}, 'combined': 0.24363195388292638, 'stategy': 1, 'epoch': 7}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3219006012487355, 'r': 0.32426534395763346, 'f1': 0.3230786455350987}, 'combined': 0.2109218100384582, 'stategy': 1, 'epoch': 7}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.29166666666666663, 'r': 0.41666666666666663, 'f1': 0.34313725490196073}, 'combined': 0.2287581699346405, 'stategy': 1, 'epoch': 7}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.35294117647058826, 'r': 0.5217391304347826, 'f1': 0.4210526315789474}, 'combined': 0.2105263157894737, 'stategy': 1, 'epoch': 7}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5416666666666666, 'r': 0.33620689655172414, 'f1': 0.41489361702127664}, 'combined': 0.2765957446808511, 'stategy': 1, 'epoch': 7}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32374479166666664, 'r': 0.3685898956356736, 'f1': 0.34471495119787043}, 'combined': 0.25400049035632555, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33423857660835543, 'r': 0.3093550061071819, 'f1': 0.3213157485867436}, 'combined': 0.20977090322243364, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 16:21:31.903785: step: 4/529, loss: 0.009747476316988468
2023-01-22 16:21:32.971675: step: 8/529, loss: 0.003275158815085888
2023-01-22 16:21:34.037267: step: 12/529, loss: 0.008259285241365433
2023-01-22 16:21:35.097762: step: 16/529, loss: 0.006497662048786879
2023-01-22 16:21:36.151334: step: 20/529, loss: 0.00302662281319499
2023-01-22 16:21:37.216857: step: 24/529, loss: 0.0007791048265062273
2023-01-22 16:21:38.283889: step: 28/529, loss: 0.0020304741337895393
2023-01-22 16:21:39.346049: step: 32/529, loss: 0.014636431820690632
2023-01-22 16:21:40.406355: step: 36/529, loss: 0.004981345497071743
2023-01-22 16:21:41.468408: step: 40/529, loss: 0.004502154886722565
2023-01-22 16:21:42.533862: step: 44/529, loss: 0.0039527141489088535
2023-01-22 16:21:43.596320: step: 48/529, loss: 0.0004062947991769761
2023-01-22 16:21:44.657098: step: 52/529, loss: 0.01000632531940937
2023-01-22 16:21:45.723279: step: 56/529, loss: 0.0010569922160357237
2023-01-22 16:21:46.788467: step: 60/529, loss: 0.009578239172697067
2023-01-22 16:21:47.845330: step: 64/529, loss: 0.0055840169079601765
2023-01-22 16:21:48.900923: step: 68/529, loss: 0.027266722172498703
2023-01-22 16:21:49.964847: step: 72/529, loss: 0.005511911120265722
2023-01-22 16:21:51.036153: step: 76/529, loss: 0.028164569288492203
2023-01-22 16:21:52.101435: step: 80/529, loss: 0.01114873681217432
2023-01-22 16:21:53.169978: step: 84/529, loss: 0.010442463681101799
2023-01-22 16:21:54.246113: step: 88/529, loss: 0.0019789354410022497
2023-01-22 16:21:55.310148: step: 92/529, loss: 0.002176770241931081
2023-01-22 16:21:56.368720: step: 96/529, loss: 0.011197119019925594
2023-01-22 16:21:57.442824: step: 100/529, loss: 0.021637076511979103
2023-01-22 16:21:58.505047: step: 104/529, loss: 0.009540221653878689
2023-01-22 16:21:59.582368: step: 108/529, loss: 0.0026357679162174463
2023-01-22 16:22:00.660133: step: 112/529, loss: 0.0039633531123399734
2023-01-22 16:22:01.739648: step: 116/529, loss: 0.006209233775734901
2023-01-22 16:22:02.803621: step: 120/529, loss: 0.002560943365097046
2023-01-22 16:22:03.856272: step: 124/529, loss: 0.029506143182516098
2023-01-22 16:22:04.941214: step: 128/529, loss: 0.004663768224418163
2023-01-22 16:22:06.004820: step: 132/529, loss: 0.00984466727823019
2023-01-22 16:22:07.071473: step: 136/529, loss: 0.00023562906426377594
2023-01-22 16:22:08.124192: step: 140/529, loss: 0.006864276714622974
2023-01-22 16:22:09.217483: step: 144/529, loss: 0.0011946257436648011
2023-01-22 16:22:10.312813: step: 148/529, loss: 0.004430925939232111
2023-01-22 16:22:11.377626: step: 152/529, loss: 0.0136809591203928
2023-01-22 16:22:12.452457: step: 156/529, loss: 0.007057512644678354
2023-01-22 16:22:13.520955: step: 160/529, loss: 0.05233162268996239
2023-01-22 16:22:14.585558: step: 164/529, loss: 0.00047828099923208356
2023-01-22 16:22:15.652745: step: 168/529, loss: 0.012809165753424168
2023-01-22 16:22:16.718021: step: 172/529, loss: 0.004256012849509716
2023-01-22 16:22:17.786879: step: 176/529, loss: 0.008155967108905315
2023-01-22 16:22:18.853556: step: 180/529, loss: 0.0017409624997526407
2023-01-22 16:22:19.910565: step: 184/529, loss: 0.006880775094032288
2023-01-22 16:22:20.993401: step: 188/529, loss: 0.002150752581655979
2023-01-22 16:22:22.079687: step: 192/529, loss: 0.015141529031097889
2023-01-22 16:22:23.147965: step: 196/529, loss: 0.0011681936448439956
2023-01-22 16:22:24.217369: step: 200/529, loss: 0.002449402352795005
2023-01-22 16:22:25.285510: step: 204/529, loss: 0.000558110827114433
2023-01-22 16:22:26.365589: step: 208/529, loss: 0.0391618013381958
2023-01-22 16:22:27.448949: step: 212/529, loss: 0.005045281257480383
2023-01-22 16:22:28.499660: step: 216/529, loss: 0.0044939653016626835
2023-01-22 16:22:29.548469: step: 220/529, loss: 3.725290076417309e-09
2023-01-22 16:22:30.635347: step: 224/529, loss: 0.005099854897707701
2023-01-22 16:22:31.702921: step: 228/529, loss: 0.015604529529809952
2023-01-22 16:22:32.791363: step: 232/529, loss: 0.011787890456616879
2023-01-22 16:22:33.849785: step: 236/529, loss: 0.0003547786909621209
2023-01-22 16:22:34.929159: step: 240/529, loss: 0.00912325270473957
2023-01-22 16:22:36.006928: step: 244/529, loss: 0.020363986492156982
2023-01-22 16:22:37.077266: step: 248/529, loss: 0.00735419662669301
2023-01-22 16:22:38.150334: step: 252/529, loss: 0.004128073807805777
2023-01-22 16:22:39.234072: step: 256/529, loss: 0.006799825932830572
2023-01-22 16:22:40.308917: step: 260/529, loss: 0.005110451020300388
2023-01-22 16:22:41.368117: step: 264/529, loss: 0.016539715230464935
2023-01-22 16:22:42.430450: step: 268/529, loss: 0.002039081184193492
2023-01-22 16:22:43.519113: step: 272/529, loss: 0.0021473790984600782
2023-01-22 16:22:44.601284: step: 276/529, loss: 0.0007715190295130014
2023-01-22 16:22:45.678741: step: 280/529, loss: 0.00780539819970727
2023-01-22 16:22:46.737444: step: 284/529, loss: 0.000981232151389122
2023-01-22 16:22:47.812475: step: 288/529, loss: 0.004279303830116987
2023-01-22 16:22:48.861965: step: 292/529, loss: 0.0026296470314264297
2023-01-22 16:22:49.934326: step: 296/529, loss: 0.016560344025492668
2023-01-22 16:22:51.004101: step: 300/529, loss: 0.02972700074315071
2023-01-22 16:22:52.087638: step: 304/529, loss: 0.034799423068761826
2023-01-22 16:22:53.149241: step: 308/529, loss: 0.013093378394842148
2023-01-22 16:22:54.236367: step: 312/529, loss: 0.048066381365060806
2023-01-22 16:22:55.319437: step: 316/529, loss: 0.0057670907117426395
2023-01-22 16:22:56.387351: step: 320/529, loss: 0.017366575077176094
2023-01-22 16:22:57.448682: step: 324/529, loss: 0.0006468056235462427
2023-01-22 16:22:58.518802: step: 328/529, loss: 0.001152149634435773
2023-01-22 16:22:59.601521: step: 332/529, loss: 0.00032867054687812924
2023-01-22 16:23:00.674577: step: 336/529, loss: 0.012116515077650547
2023-01-22 16:23:01.741828: step: 340/529, loss: 0.006163491867482662
2023-01-22 16:23:02.812760: step: 344/529, loss: 0.0011839959770441055
2023-01-22 16:23:03.904941: step: 348/529, loss: 0.009106863290071487
2023-01-22 16:23:04.997597: step: 352/529, loss: 0.003912312909960747
2023-01-22 16:23:06.079600: step: 356/529, loss: 0.012659174390137196
2023-01-22 16:23:07.137625: step: 360/529, loss: 0.010551778599619865
2023-01-22 16:23:08.205685: step: 364/529, loss: 0.004434017464518547
2023-01-22 16:23:09.273692: step: 368/529, loss: 0.02366974763572216
2023-01-22 16:23:10.357358: step: 372/529, loss: 0.006800464820116758
2023-01-22 16:23:11.431016: step: 376/529, loss: 0.0008074561483226717
2023-01-22 16:23:12.511166: step: 380/529, loss: 0.006059197708964348
2023-01-22 16:23:13.601497: step: 384/529, loss: 0.001420728163793683
2023-01-22 16:23:14.676094: step: 388/529, loss: 0.03265802189707756
2023-01-22 16:23:15.740807: step: 392/529, loss: 0.011451431550085545
2023-01-22 16:23:16.825615: step: 396/529, loss: 0.0022584048565477133
2023-01-22 16:23:17.889086: step: 400/529, loss: 0.013998680748045444
2023-01-22 16:23:18.965661: step: 404/529, loss: 0.010839652270078659
2023-01-22 16:23:20.041535: step: 408/529, loss: 0.024989547207951546
2023-01-22 16:23:21.132779: step: 412/529, loss: 0.0008449184824712574
2023-01-22 16:23:22.210325: step: 416/529, loss: 0.015925172716379166
2023-01-22 16:23:23.266952: step: 420/529, loss: 0.008344486355781555
2023-01-22 16:23:24.327963: step: 424/529, loss: 0.006443290039896965
2023-01-22 16:23:25.390557: step: 428/529, loss: 0.0034994876477867365
2023-01-22 16:23:26.462235: step: 432/529, loss: 0.006240661721676588
2023-01-22 16:23:27.527432: step: 436/529, loss: 0.026115959510207176
2023-01-22 16:23:28.613906: step: 440/529, loss: 0.002189795020967722
2023-01-22 16:23:29.694973: step: 444/529, loss: 0.001292856759391725
2023-01-22 16:23:30.789683: step: 448/529, loss: 0.021675340831279755
2023-01-22 16:23:31.889898: step: 452/529, loss: 0.020170198753476143
2023-01-22 16:23:32.965874: step: 456/529, loss: 0.0038539739325642586
2023-01-22 16:23:34.015930: step: 460/529, loss: 0.003045107237994671
2023-01-22 16:23:35.104141: step: 464/529, loss: 0.0020149783231317997
2023-01-22 16:23:36.182198: step: 468/529, loss: 0.0035974527709186077
2023-01-22 16:23:37.271416: step: 472/529, loss: 0.004982856567949057
2023-01-22 16:23:38.354165: step: 476/529, loss: 0.015442381612956524
2023-01-22 16:23:39.419125: step: 480/529, loss: 0.0036645352374762297
2023-01-22 16:23:40.491015: step: 484/529, loss: 0.021050328388810158
2023-01-22 16:23:41.566094: step: 488/529, loss: 0.007365392986685038
2023-01-22 16:23:42.623898: step: 492/529, loss: 7.890837878221646e-05
2023-01-22 16:23:43.710650: step: 496/529, loss: 0.0021499230060726404
2023-01-22 16:23:44.784153: step: 500/529, loss: 0.013126959092915058
2023-01-22 16:23:45.853853: step: 504/529, loss: 0.00651155598461628
2023-01-22 16:23:46.921546: step: 508/529, loss: 0.0042288885451853275
2023-01-22 16:23:47.981908: step: 512/529, loss: 0.010497361421585083
2023-01-22 16:23:49.048063: step: 516/529, loss: 0.0032536915969103575
2023-01-22 16:23:50.133781: step: 520/529, loss: 0.006407783832401037
2023-01-22 16:23:51.208736: step: 524/529, loss: 0.030243633314967155
2023-01-22 16:23:52.277053: step: 528/529, loss: 0.008385750465095043
2023-01-22 16:23:53.359285: step: 532/529, loss: 0.00030342568061314523
2023-01-22 16:23:54.437539: step: 536/529, loss: 0.006019508931785822
2023-01-22 16:23:55.508012: step: 540/529, loss: 0.0023384622763842344
2023-01-22 16:23:56.584630: step: 544/529, loss: 0.007905756123363972
2023-01-22 16:23:57.667532: step: 548/529, loss: 0.008231570944190025
2023-01-22 16:23:58.748957: step: 552/529, loss: 0.0026338002644479275
2023-01-22 16:23:59.821286: step: 556/529, loss: 0.02624349854886532
2023-01-22 16:24:00.885979: step: 560/529, loss: 0.020095830783247948
2023-01-22 16:24:01.961242: step: 564/529, loss: 0.007856771349906921
2023-01-22 16:24:03.025254: step: 568/529, loss: 0.00978147890418768
2023-01-22 16:24:04.097643: step: 572/529, loss: 0.006413714028894901
2023-01-22 16:24:05.183214: step: 576/529, loss: 0.008696607314050198
2023-01-22 16:24:06.266724: step: 580/529, loss: 0.005394941661506891
2023-01-22 16:24:07.340083: step: 584/529, loss: 0.00240964419208467
2023-01-22 16:24:08.418832: step: 588/529, loss: 0.01084339153021574
2023-01-22 16:24:09.489460: step: 592/529, loss: 0.0008681678446009755
2023-01-22 16:24:10.562252: step: 596/529, loss: 0.002573717152699828
2023-01-22 16:24:11.628356: step: 600/529, loss: 0.001686137286014855
2023-01-22 16:24:12.692552: step: 604/529, loss: 0.0002229427482234314
2023-01-22 16:24:13.779663: step: 608/529, loss: 0.0033347313292324543
2023-01-22 16:24:14.852849: step: 612/529, loss: 0.006069518160074949
2023-01-22 16:24:15.941918: step: 616/529, loss: 0.005314069800078869
2023-01-22 16:24:17.036630: step: 620/529, loss: 0.011619308963418007
2023-01-22 16:24:18.107870: step: 624/529, loss: 0.007463936693966389
2023-01-22 16:24:19.174790: step: 628/529, loss: 0.005212721414864063
2023-01-22 16:24:20.264495: step: 632/529, loss: 0.011492015793919563
2023-01-22 16:24:21.336311: step: 636/529, loss: 0.00473751500248909
2023-01-22 16:24:22.402040: step: 640/529, loss: 0.008172940462827682
2023-01-22 16:24:23.483345: step: 644/529, loss: 0.011758987791836262
2023-01-22 16:24:24.540096: step: 648/529, loss: 0.005540257785469294
2023-01-22 16:24:25.609552: step: 652/529, loss: 0.002190530067309737
2023-01-22 16:24:26.691854: step: 656/529, loss: 0.02387157827615738
2023-01-22 16:24:27.776698: step: 660/529, loss: 0.0012084796326234937
2023-01-22 16:24:28.841125: step: 664/529, loss: 0.00021252931037452072
2023-01-22 16:24:29.898353: step: 668/529, loss: 0.005288487765938044
2023-01-22 16:24:30.974797: step: 672/529, loss: 0.011240778490900993
2023-01-22 16:24:32.057401: step: 676/529, loss: 0.00876892264932394
2023-01-22 16:24:33.130663: step: 680/529, loss: 0.015661615878343582
2023-01-22 16:24:34.190583: step: 684/529, loss: 0.0001873767760116607
2023-01-22 16:24:35.259299: step: 688/529, loss: 0.005850032437592745
2023-01-22 16:24:36.333584: step: 692/529, loss: 0.002547177951782942
2023-01-22 16:24:37.415501: step: 696/529, loss: 0.00028295861557126045
2023-01-22 16:24:38.482125: step: 700/529, loss: 0.009461583569645882
2023-01-22 16:24:39.574383: step: 704/529, loss: 0.0023425337858498096
2023-01-22 16:24:40.650718: step: 708/529, loss: 0.0020930746104568243
2023-01-22 16:24:41.731398: step: 712/529, loss: 0.009239100851118565
2023-01-22 16:24:42.833288: step: 716/529, loss: 0.012814832851290703
2023-01-22 16:24:43.910364: step: 720/529, loss: 0.004613940604031086
2023-01-22 16:24:44.971958: step: 724/529, loss: 0.0029280786402523518
2023-01-22 16:24:46.050501: step: 728/529, loss: 0.003943185321986675
2023-01-22 16:24:47.122915: step: 732/529, loss: 0.0027340154629200697
2023-01-22 16:24:48.187225: step: 736/529, loss: 0.0015234225429594517
2023-01-22 16:24:49.251869: step: 740/529, loss: 0.0005853785551153123
2023-01-22 16:24:50.330351: step: 744/529, loss: 0.005643903277814388
2023-01-22 16:24:51.414736: step: 748/529, loss: 0.002172401174902916
2023-01-22 16:24:52.492486: step: 752/529, loss: 0.005956471897661686
2023-01-22 16:24:53.568681: step: 756/529, loss: 0.0038132721092551947
2023-01-22 16:24:54.636410: step: 760/529, loss: 0.0018798239761963487
2023-01-22 16:24:55.705075: step: 764/529, loss: 0.008477110415697098
2023-01-22 16:24:56.775074: step: 768/529, loss: 0.005096436943858862
2023-01-22 16:24:57.859669: step: 772/529, loss: 0.005197742488235235
2023-01-22 16:24:58.936926: step: 776/529, loss: 0.00404119910672307
2023-01-22 16:25:00.018120: step: 780/529, loss: 0.0014957330422475934
2023-01-22 16:25:01.102628: step: 784/529, loss: 0.0028175227344036102
2023-01-22 16:25:02.172882: step: 788/529, loss: 0.010531235486268997
2023-01-22 16:25:03.268633: step: 792/529, loss: 0.006592996418476105
2023-01-22 16:25:04.350850: step: 796/529, loss: 0.001529913512058556
2023-01-22 16:25:05.426613: step: 800/529, loss: 0.0017347006360068917
2023-01-22 16:25:06.509687: step: 804/529, loss: 0.0017265999922528863
2023-01-22 16:25:07.593854: step: 808/529, loss: 0.0023738956078886986
2023-01-22 16:25:08.678526: step: 812/529, loss: 0.006240862421691418
2023-01-22 16:25:09.764539: step: 816/529, loss: 0.0026183349546045065
2023-01-22 16:25:10.831870: step: 820/529, loss: 0.0003096178697887808
2023-01-22 16:25:11.904016: step: 824/529, loss: 0.0034289476461708546
2023-01-22 16:25:12.980174: step: 828/529, loss: 0.0017801757203415036
2023-01-22 16:25:14.065288: step: 832/529, loss: 0.004398096352815628
2023-01-22 16:25:15.120860: step: 836/529, loss: 0.0010579280788078904
2023-01-22 16:25:16.196364: step: 840/529, loss: 0.0036922418512403965
2023-01-22 16:25:17.271093: step: 844/529, loss: 0.013683700934052467
2023-01-22 16:25:18.363124: step: 848/529, loss: 8.35388564155437e-05
2023-01-22 16:25:19.437490: step: 852/529, loss: 0.006110694725066423
2023-01-22 16:25:20.506040: step: 856/529, loss: 0.00912535097450018
2023-01-22 16:25:21.574357: step: 860/529, loss: 0.002674727002158761
2023-01-22 16:25:22.652981: step: 864/529, loss: 0.004322531633079052
2023-01-22 16:25:23.734452: step: 868/529, loss: 0.006016689818352461
2023-01-22 16:25:24.813593: step: 872/529, loss: 0.001576276496052742
2023-01-22 16:25:25.886051: step: 876/529, loss: 0.0008923484710976481
2023-01-22 16:25:26.968765: step: 880/529, loss: 0.013937306590378284
2023-01-22 16:25:28.044048: step: 884/529, loss: 0.004354747943580151
2023-01-22 16:25:29.118712: step: 888/529, loss: 0.001541958306916058
2023-01-22 16:25:30.210139: step: 892/529, loss: 0.00795665942132473
2023-01-22 16:25:31.270647: step: 896/529, loss: 0.0005363939562812448
2023-01-22 16:25:32.347134: step: 900/529, loss: 0.0035471252631396055
2023-01-22 16:25:33.428188: step: 904/529, loss: 0.05340811610221863
2023-01-22 16:25:34.501563: step: 908/529, loss: 0.0034446301870048046
2023-01-22 16:25:35.598718: step: 912/529, loss: 0.00645345076918602
2023-01-22 16:25:36.679476: step: 916/529, loss: 0.0036342365201562643
2023-01-22 16:25:37.774197: step: 920/529, loss: 0.04230709746479988
2023-01-22 16:25:38.853282: step: 924/529, loss: 0.003863136749714613
2023-01-22 16:25:39.949889: step: 928/529, loss: 0.003635154804214835
2023-01-22 16:25:41.030128: step: 932/529, loss: 0.004086005967110395
2023-01-22 16:25:42.116927: step: 936/529, loss: 0.019329141825437546
2023-01-22 16:25:43.192021: step: 940/529, loss: 0.00680341012775898
2023-01-22 16:25:44.278868: step: 944/529, loss: 0.004597218707203865
2023-01-22 16:25:45.373081: step: 948/529, loss: 0.0036511612124741077
2023-01-22 16:25:46.472007: step: 952/529, loss: 0.004385803826153278
2023-01-22 16:25:47.551992: step: 956/529, loss: 0.0045221904292702675
2023-01-22 16:25:48.619340: step: 960/529, loss: 0.0031598364003002644
2023-01-22 16:25:49.706034: step: 964/529, loss: 0.010563013143837452
2023-01-22 16:25:50.777264: step: 968/529, loss: 0.009025481529533863
2023-01-22 16:25:51.889626: step: 972/529, loss: 0.0034501042682677507
2023-01-22 16:25:52.984891: step: 976/529, loss: 0.01031646691262722
2023-01-22 16:25:54.069009: step: 980/529, loss: 0.005332152359187603
2023-01-22 16:25:55.139087: step: 984/529, loss: 8.416222408413887e-05
2023-01-22 16:25:56.214322: step: 988/529, loss: 0.0008549308986403048
2023-01-22 16:25:57.299018: step: 992/529, loss: 0.033310480415821075
2023-01-22 16:25:58.381874: step: 996/529, loss: 0.008810398168861866
2023-01-22 16:25:59.475815: step: 1000/529, loss: 0.006010415498167276
2023-01-22 16:26:00.568295: step: 1004/529, loss: 0.004055732861161232
2023-01-22 16:26:01.661813: step: 1008/529, loss: 0.0
2023-01-22 16:26:02.744064: step: 1012/529, loss: 0.003681538626551628
2023-01-22 16:26:03.835569: step: 1016/529, loss: 0.005241389386355877
2023-01-22 16:26:04.898047: step: 1020/529, loss: 0.013020191341638565
2023-01-22 16:26:05.974807: step: 1024/529, loss: 0.001995422411710024
2023-01-22 16:26:07.062816: step: 1028/529, loss: 0.024140600115060806
2023-01-22 16:26:08.153398: step: 1032/529, loss: 0.007250323425978422
2023-01-22 16:26:09.237291: step: 1036/529, loss: 0.004806543234735727
2023-01-22 16:26:10.318602: step: 1040/529, loss: 0.01244381070137024
2023-01-22 16:26:11.395800: step: 1044/529, loss: 0.0025910362601280212
2023-01-22 16:26:12.502999: step: 1048/529, loss: 0.00502138352021575
2023-01-22 16:26:13.603163: step: 1052/529, loss: 0.028342485427856445
2023-01-22 16:26:14.694252: step: 1056/529, loss: 0.0007401079055853188
2023-01-22 16:26:15.784633: step: 1060/529, loss: 0.019049426540732384
2023-01-22 16:26:16.864825: step: 1064/529, loss: 0.007588242646306753
2023-01-22 16:26:17.956402: step: 1068/529, loss: 0.013227601535618305
2023-01-22 16:26:19.042095: step: 1072/529, loss: 0.004317444283515215
2023-01-22 16:26:20.131284: step: 1076/529, loss: 0.00983927957713604
2023-01-22 16:26:21.223929: step: 1080/529, loss: 0.01683719828724861
2023-01-22 16:26:22.309696: step: 1084/529, loss: 8.491049084113911e-05
2023-01-22 16:26:23.398928: step: 1088/529, loss: 0.005881684832274914
2023-01-22 16:26:24.477814: step: 1092/529, loss: 0.006691095884889364
2023-01-22 16:26:25.566427: step: 1096/529, loss: 0.003454263089224696
2023-01-22 16:26:26.655073: step: 1100/529, loss: 0.015649283304810524
2023-01-22 16:26:27.746266: step: 1104/529, loss: 0.011050356552004814
2023-01-22 16:26:28.818917: step: 1108/529, loss: 0.0032142456620931625
2023-01-22 16:26:29.891253: step: 1112/529, loss: 0.007386663928627968
2023-01-22 16:26:30.987241: step: 1116/529, loss: 0.02004830911755562
2023-01-22 16:26:32.062785: step: 1120/529, loss: 0.009723396971821785
2023-01-22 16:26:33.136373: step: 1124/529, loss: 0.004837788641452789
2023-01-22 16:26:34.226236: step: 1128/529, loss: 0.003017564071342349
2023-01-22 16:26:35.299130: step: 1132/529, loss: 0.00225435639731586
2023-01-22 16:26:36.368607: step: 1136/529, loss: 0.007492497097700834
2023-01-22 16:26:37.457899: step: 1140/529, loss: 0.003741239197552204
2023-01-22 16:26:38.551824: step: 1144/529, loss: 0.03487576171755791
2023-01-22 16:26:39.639672: step: 1148/529, loss: 0.0014335340820252895
2023-01-22 16:26:40.728008: step: 1152/529, loss: 0.0029061236418783665
2023-01-22 16:26:41.816892: step: 1156/529, loss: 0.001039195922203362
2023-01-22 16:26:42.932564: step: 1160/529, loss: 0.0022364326287060976
2023-01-22 16:26:44.016953: step: 1164/529, loss: 0.002948314417153597
2023-01-22 16:26:45.103441: step: 1168/529, loss: 0.0034942475613206625
2023-01-22 16:26:46.191304: step: 1172/529, loss: 0.006814890541136265
2023-01-22 16:26:47.267115: step: 1176/529, loss: 0.004032635595649481
2023-01-22 16:26:48.349945: step: 1180/529, loss: 0.017857084050774574
2023-01-22 16:26:49.427946: step: 1184/529, loss: 0.006571384612470865
2023-01-22 16:26:50.524328: step: 1188/529, loss: 0.02706005796790123
2023-01-22 16:26:51.598005: step: 1192/529, loss: 0.0017993083456531167
2023-01-22 16:26:52.694348: step: 1196/529, loss: 0.010335346683859825
2023-01-22 16:26:53.777263: step: 1200/529, loss: 0.005582628771662712
2023-01-22 16:26:54.855556: step: 1204/529, loss: 0.01272439956665039
2023-01-22 16:26:55.943560: step: 1208/529, loss: 0.004503973294049501
2023-01-22 16:26:57.022932: step: 1212/529, loss: 0.001502827974036336
2023-01-22 16:26:58.122101: step: 1216/529, loss: 0.004217275884002447
2023-01-22 16:26:59.204844: step: 1220/529, loss: 0.018099181354045868
2023-01-22 16:27:00.278068: step: 1224/529, loss: 0.0038011951837688684
2023-01-22 16:27:01.354419: step: 1228/529, loss: 0.006562451366335154
2023-01-22 16:27:02.435601: step: 1232/529, loss: 0.004566310439258814
2023-01-22 16:27:03.524250: step: 1236/529, loss: 0.005925430450588465
2023-01-22 16:27:04.595388: step: 1240/529, loss: 0.0001502680970588699
2023-01-22 16:27:05.680676: step: 1244/529, loss: 0.0070723495446145535
2023-01-22 16:27:06.751358: step: 1248/529, loss: 0.011896009556949139
2023-01-22 16:27:07.839031: step: 1252/529, loss: 0.0024085433688014746
2023-01-22 16:27:08.909845: step: 1256/529, loss: 0.004441781900823116
2023-01-22 16:27:10.011203: step: 1260/529, loss: 0.005776817444711924
2023-01-22 16:27:11.095437: step: 1264/529, loss: 0.03551269322633743
2023-01-22 16:27:12.202219: step: 1268/529, loss: 0.008740313351154327
2023-01-22 16:27:13.301847: step: 1272/529, loss: 0.011169994249939919
2023-01-22 16:27:14.395760: step: 1276/529, loss: 0.01391005888581276
2023-01-22 16:27:15.476074: step: 1280/529, loss: 0.006699708756059408
2023-01-22 16:27:16.544808: step: 1284/529, loss: 0.0006082784966565669
2023-01-22 16:27:17.622189: step: 1288/529, loss: 0.008528091013431549
2023-01-22 16:27:18.691094: step: 1292/529, loss: 0.001084450981579721
2023-01-22 16:27:19.771336: step: 1296/529, loss: 0.004320644773542881
2023-01-22 16:27:20.836209: step: 1300/529, loss: 0.0035094122868031263
2023-01-22 16:27:21.904897: step: 1304/529, loss: 0.0010691630886867642
2023-01-22 16:27:22.981876: step: 1308/529, loss: 0.0007240056293085217
2023-01-22 16:27:24.071304: step: 1312/529, loss: 0.002161764306947589
2023-01-22 16:27:25.160275: step: 1316/529, loss: 0.012812407687306404
2023-01-22 16:27:26.235602: step: 1320/529, loss: 0.010177544318139553
2023-01-22 16:27:27.295296: step: 1324/529, loss: 0.001555904047563672
2023-01-22 16:27:28.379345: step: 1328/529, loss: 0.003890685271471739
2023-01-22 16:27:29.458111: step: 1332/529, loss: 0.023090403527021408
2023-01-22 16:27:30.550072: step: 1336/529, loss: 0.00614022184163332
2023-01-22 16:27:31.630714: step: 1340/529, loss: 0.006378744263201952
2023-01-22 16:27:32.724158: step: 1344/529, loss: 0.008394118398427963
2023-01-22 16:27:33.804073: step: 1348/529, loss: 0.0032654814422130585
2023-01-22 16:27:34.876482: step: 1352/529, loss: 0.007110281381756067
2023-01-22 16:27:35.948599: step: 1356/529, loss: 0.006826352793723345
2023-01-22 16:27:37.026843: step: 1360/529, loss: 0.0021168761886656284
2023-01-22 16:27:38.109716: step: 1364/529, loss: 0.022711405530571938
2023-01-22 16:27:39.189847: step: 1368/529, loss: 0.004626799374818802
2023-01-22 16:27:40.264324: step: 1372/529, loss: 0.003447539871558547
2023-01-22 16:27:41.327418: step: 1376/529, loss: 0.019592512398958206
2023-01-22 16:27:42.413434: step: 1380/529, loss: 0.009044213220477104
2023-01-22 16:27:43.471823: step: 1384/529, loss: 0.005241322796791792
2023-01-22 16:27:44.560749: step: 1388/529, loss: 0.00176662253215909
2023-01-22 16:27:45.652509: step: 1392/529, loss: 0.00025052446289919317
2023-01-22 16:27:46.705929: step: 1396/529, loss: 0.006436891388148069
2023-01-22 16:27:47.779515: step: 1400/529, loss: 0.0014382406370714307
2023-01-22 16:27:48.856186: step: 1404/529, loss: 0.002375274430960417
2023-01-22 16:27:49.925375: step: 1408/529, loss: 0.006078909616917372
2023-01-22 16:27:51.012632: step: 1412/529, loss: 0.01394870225340128
2023-01-22 16:27:52.074985: step: 1416/529, loss: 0.003460199572145939
2023-01-22 16:27:53.143543: step: 1420/529, loss: 0.01040552370250225
2023-01-22 16:27:54.223314: step: 1424/529, loss: 0.0015089769149199128
2023-01-22 16:27:55.287981: step: 1428/529, loss: 0.002916331635788083
2023-01-22 16:27:56.364794: step: 1432/529, loss: 0.007505747955292463
2023-01-22 16:27:57.454115: step: 1436/529, loss: 0.00466849934309721
2023-01-22 16:27:58.519652: step: 1440/529, loss: 0.00920061394572258
2023-01-22 16:27:59.590304: step: 1444/529, loss: 0.0057571628130972385
2023-01-22 16:28:00.659037: step: 1448/529, loss: 0.008626052178442478
2023-01-22 16:28:01.747572: step: 1452/529, loss: 0.014985253103077412
2023-01-22 16:28:02.823668: step: 1456/529, loss: 0.002016692655161023
2023-01-22 16:28:03.885258: step: 1460/529, loss: 0.000815091363620013
2023-01-22 16:28:04.950075: step: 1464/529, loss: 0.007801668718457222
2023-01-22 16:28:06.016909: step: 1468/529, loss: 0.00866541638970375
2023-01-22 16:28:07.090384: step: 1472/529, loss: 0.0009801725391298532
2023-01-22 16:28:08.163976: step: 1476/529, loss: 0.008660559542477131
2023-01-22 16:28:09.233767: step: 1480/529, loss: 0.014192376285791397
2023-01-22 16:28:10.320821: step: 1484/529, loss: 0.0026923012919723988
2023-01-22 16:28:11.388456: step: 1488/529, loss: 0.0075814565643668175
2023-01-22 16:28:12.471376: step: 1492/529, loss: 0.029399165883660316
2023-01-22 16:28:13.547684: step: 1496/529, loss: 0.00834119226783514
2023-01-22 16:28:14.604484: step: 1500/529, loss: 0.006017880514264107
2023-01-22 16:28:15.671585: step: 1504/529, loss: 0.008777924813330173
2023-01-22 16:28:16.727459: step: 1508/529, loss: 0.0019894454162567854
2023-01-22 16:28:17.798670: step: 1512/529, loss: 0.014763196930289268
2023-01-22 16:28:18.863420: step: 1516/529, loss: 0.003023806493729353
2023-01-22 16:28:19.939745: step: 1520/529, loss: 0.014696680940687656
2023-01-22 16:28:21.032864: step: 1524/529, loss: 0.003669432597234845
2023-01-22 16:28:22.119081: step: 1528/529, loss: 0.009443075396120548
2023-01-22 16:28:23.185015: step: 1532/529, loss: 0.01387085858732462
2023-01-22 16:28:24.271954: step: 1536/529, loss: 0.0026909341104328632
2023-01-22 16:28:25.353842: step: 1540/529, loss: 0.07674626260995865
2023-01-22 16:28:26.420009: step: 1544/529, loss: 0.0061227441765367985
2023-01-22 16:28:27.503956: step: 1548/529, loss: 0.008370391093194485
2023-01-22 16:28:28.571808: step: 1552/529, loss: 0.0032957694493234158
2023-01-22 16:28:29.645325: step: 1556/529, loss: 0.001369014149531722
2023-01-22 16:28:30.721164: step: 1560/529, loss: 0.01644028164446354
2023-01-22 16:28:31.779055: step: 1564/529, loss: 0.009593049995601177
2023-01-22 16:28:32.851087: step: 1568/529, loss: 0.004544573370367289
2023-01-22 16:28:33.915547: step: 1572/529, loss: 0.008603706024587154
2023-01-22 16:28:34.992622: step: 1576/529, loss: 0.0034662429243326187
2023-01-22 16:28:36.066653: step: 1580/529, loss: 0.008092181757092476
2023-01-22 16:28:37.156824: step: 1584/529, loss: 0.007533358875662088
2023-01-22 16:28:38.218956: step: 1588/529, loss: 0.0005055989022366703
2023-01-22 16:28:39.300412: step: 1592/529, loss: 0.004422774072736502
2023-01-22 16:28:40.355289: step: 1596/529, loss: 0.0016019812319427729
2023-01-22 16:28:41.426482: step: 1600/529, loss: 0.019868889823555946
2023-01-22 16:28:42.485169: step: 1604/529, loss: 0.003041674615815282
2023-01-22 16:28:43.539950: step: 1608/529, loss: 0.0029272520914673805
2023-01-22 16:28:44.606154: step: 1612/529, loss: 0.006823974195867777
2023-01-22 16:28:45.681381: step: 1616/529, loss: 0.01577920652925968
2023-01-22 16:28:46.752350: step: 1620/529, loss: 0.004937442485243082
2023-01-22 16:28:47.818089: step: 1624/529, loss: 0.01993417553603649
2023-01-22 16:28:48.887823: step: 1628/529, loss: 0.01570660062134266
2023-01-22 16:28:49.961257: step: 1632/529, loss: 0.009924609214067459
2023-01-22 16:28:51.015612: step: 1636/529, loss: 0.016979781910777092
2023-01-22 16:28:52.088807: step: 1640/529, loss: 0.007434999104589224
2023-01-22 16:28:53.156480: step: 1644/529, loss: 0.0029545214492827654
2023-01-22 16:28:54.227137: step: 1648/529, loss: 0.010606428608298302
2023-01-22 16:28:55.304278: step: 1652/529, loss: 0.00034419671283103526
2023-01-22 16:28:56.374931: step: 1656/529, loss: 0.0035986558068543673
2023-01-22 16:28:57.461844: step: 1660/529, loss: 0.0022976382169872522
2023-01-22 16:28:58.533148: step: 1664/529, loss: 0.001503913663327694
2023-01-22 16:28:59.613352: step: 1668/529, loss: 0.004559915047138929
2023-01-22 16:29:00.684296: step: 1672/529, loss: 0.0005347795085981488
2023-01-22 16:29:01.766012: step: 1676/529, loss: 0.03257714956998825
2023-01-22 16:29:02.836795: step: 1680/529, loss: 0.008291545324027538
2023-01-22 16:29:03.892865: step: 1684/529, loss: 0.005107128992676735
2023-01-22 16:29:04.954939: step: 1688/529, loss: 0.005116648972034454
2023-01-22 16:29:06.058724: step: 1692/529, loss: 0.007378586567938328
2023-01-22 16:29:07.136139: step: 1696/529, loss: 0.012093840166926384
2023-01-22 16:29:08.195624: step: 1700/529, loss: 0.007946373894810677
2023-01-22 16:29:09.272449: step: 1704/529, loss: 0.012926735915243626
2023-01-22 16:29:10.335187: step: 1708/529, loss: 0.0031895963475108147
2023-01-22 16:29:11.407575: step: 1712/529, loss: 0.028509464114904404
2023-01-22 16:29:12.463452: step: 1716/529, loss: 0.0009545735665597022
2023-01-22 16:29:13.525921: step: 1720/529, loss: 0.015718529000878334
2023-01-22 16:29:14.592496: step: 1724/529, loss: 0.007813684642314911
2023-01-22 16:29:15.648626: step: 1728/529, loss: 0.012756199575960636
2023-01-22 16:29:16.723901: step: 1732/529, loss: 0.010427942499518394
2023-01-22 16:29:17.790489: step: 1736/529, loss: 0.0031596841290593147
2023-01-22 16:29:18.858921: step: 1740/529, loss: 0.02043180912733078
2023-01-22 16:29:19.946331: step: 1744/529, loss: 0.0011438081273809075
2023-01-22 16:29:21.035154: step: 1748/529, loss: 0.004946943372488022
2023-01-22 16:29:22.089723: step: 1752/529, loss: 0.005224988795816898
2023-01-22 16:29:23.152730: step: 1756/529, loss: 0.007633446715772152
2023-01-22 16:29:24.223705: step: 1760/529, loss: 0.008096297271549702
2023-01-22 16:29:25.310953: step: 1764/529, loss: 0.007603825069963932
2023-01-22 16:29:26.382543: step: 1768/529, loss: 0.006806579418480396
2023-01-22 16:29:27.446974: step: 1772/529, loss: 0.005438607186079025
2023-01-22 16:29:28.536471: step: 1776/529, loss: 0.01815561205148697
2023-01-22 16:29:29.603682: step: 1780/529, loss: 0.020348792895674706
2023-01-22 16:29:30.668626: step: 1784/529, loss: 0.00146417785435915
2023-01-22 16:29:31.741161: step: 1788/529, loss: 0.006973433308303356
2023-01-22 16:29:32.818443: step: 1792/529, loss: 0.007061352953314781
2023-01-22 16:29:33.896952: step: 1796/529, loss: 0.018406858667731285
2023-01-22 16:29:34.974480: step: 1800/529, loss: 0.017630452290177345
2023-01-22 16:29:36.048716: step: 1804/529, loss: 0.009714137762784958
2023-01-22 16:29:37.123489: step: 1808/529, loss: 0.014081901870667934
2023-01-22 16:29:38.183053: step: 1812/529, loss: 0.005558694247156382
2023-01-22 16:29:39.245380: step: 1816/529, loss: 0.006522204261273146
2023-01-22 16:29:40.314748: step: 1820/529, loss: 0.025125302374362946
2023-01-22 16:29:41.388593: step: 1824/529, loss: 0.0002913131029345095
2023-01-22 16:29:42.433780: step: 1828/529, loss: 0.0019964517559856176
2023-01-22 16:29:43.509550: step: 1832/529, loss: 0.0007465678500011563
2023-01-22 16:29:44.579451: step: 1836/529, loss: 0.004286186303943396
2023-01-22 16:29:45.656931: step: 1840/529, loss: 0.00113116845022887
2023-01-22 16:29:46.717047: step: 1844/529, loss: 0.00785467866808176
2023-01-22 16:29:47.780714: step: 1848/529, loss: 0.002037757309153676
2023-01-22 16:29:48.848124: step: 1852/529, loss: 0.0041639553382992744
2023-01-22 16:29:49.918248: step: 1856/529, loss: 0.005991968791931868
2023-01-22 16:29:50.979625: step: 1860/529, loss: 0.0028306187596172094
2023-01-22 16:29:52.033719: step: 1864/529, loss: 0.0008542510913684964
2023-01-22 16:29:53.114645: step: 1868/529, loss: 0.007124752271920443
2023-01-22 16:29:54.179560: step: 1872/529, loss: 0.017392653971910477
2023-01-22 16:29:55.246081: step: 1876/529, loss: 0.0059369513764977455
2023-01-22 16:29:56.313282: step: 1880/529, loss: 0.012182307429611683
2023-01-22 16:29:57.390899: step: 1884/529, loss: 0.012995271943509579
2023-01-22 16:29:58.442613: step: 1888/529, loss: 0.00014857731002848595
2023-01-22 16:29:59.508034: step: 1892/529, loss: 0.0010416853474453092
2023-01-22 16:30:00.584228: step: 1896/529, loss: 0.007235480938106775
2023-01-22 16:30:01.681531: step: 1900/529, loss: 0.005913544446229935
2023-01-22 16:30:02.757515: step: 1904/529, loss: 0.033664945513010025
2023-01-22 16:30:03.815444: step: 1908/529, loss: 0.0007438280154019594
2023-01-22 16:30:04.905551: step: 1912/529, loss: 0.0006379848346114159
2023-01-22 16:30:05.957838: step: 1916/529, loss: 0.07692140340805054
2023-01-22 16:30:07.028814: step: 1920/529, loss: 0.008052946999669075
2023-01-22 16:30:08.088290: step: 1924/529, loss: 0.0034659206867218018
2023-01-22 16:30:09.169675: step: 1928/529, loss: 0.015730535611510277
2023-01-22 16:30:10.242338: step: 1932/529, loss: 0.0060439263470470905
2023-01-22 16:30:11.298903: step: 1936/529, loss: 0.007294867653399706
2023-01-22 16:30:12.371962: step: 1940/529, loss: 0.002797638764604926
2023-01-22 16:30:13.436184: step: 1944/529, loss: 0.01025779265910387
2023-01-22 16:30:14.522054: step: 1948/529, loss: 0.0030402876436710358
2023-01-22 16:30:15.587985: step: 1952/529, loss: 0.0061142644844949245
2023-01-22 16:30:16.669258: step: 1956/529, loss: 0.007880199700593948
2023-01-22 16:30:17.745772: step: 1960/529, loss: 0.01784527488052845
2023-01-22 16:30:18.803774: step: 1964/529, loss: 0.01850874349474907
2023-01-22 16:30:19.861948: step: 1968/529, loss: 0.010088245384395123
2023-01-22 16:30:20.927118: step: 1972/529, loss: 0.003554239869117737
2023-01-22 16:30:21.987367: step: 1976/529, loss: 0.0010395313147455454
2023-01-22 16:30:23.059087: step: 1980/529, loss: 0.008423163555562496
2023-01-22 16:30:24.129012: step: 1984/529, loss: 0.01008532289415598
2023-01-22 16:30:25.194291: step: 1988/529, loss: 0.003578011877834797
2023-01-22 16:30:26.252559: step: 1992/529, loss: 0.02857138030230999
2023-01-22 16:30:27.309305: step: 1996/529, loss: 0.003955631051212549
2023-01-22 16:30:28.377039: step: 2000/529, loss: 0.01996195688843727
2023-01-22 16:30:29.447711: step: 2004/529, loss: 0.02355371229350567
2023-01-22 16:30:30.504816: step: 2008/529, loss: 0.00039478030521422625
2023-01-22 16:30:31.574909: step: 2012/529, loss: 0.0021190063562244177
2023-01-22 16:30:32.644180: step: 2016/529, loss: 0.0034552859142422676
2023-01-22 16:30:33.721286: step: 2020/529, loss: 0.005363295320421457
2023-01-22 16:30:34.809533: step: 2024/529, loss: 0.011911021545529366
2023-01-22 16:30:35.879900: step: 2028/529, loss: 0.011462458409368992
2023-01-22 16:30:36.959470: step: 2032/529, loss: 0.0093986289575696
2023-01-22 16:30:38.036745: step: 2036/529, loss: 0.0017564240843057632
2023-01-22 16:30:39.111054: step: 2040/529, loss: 0.005043210927397013
2023-01-22 16:30:40.175384: step: 2044/529, loss: 0.0028536366298794746
2023-01-22 16:30:41.245859: step: 2048/529, loss: 0.007279288489371538
2023-01-22 16:30:42.332543: step: 2052/529, loss: 0.007180248852819204
2023-01-22 16:30:43.432101: step: 2056/529, loss: 0.025156911462545395
2023-01-22 16:30:44.494831: step: 2060/529, loss: 0.0007034644950181246
2023-01-22 16:30:45.566005: step: 2064/529, loss: 0.0034645809791982174
2023-01-22 16:30:46.625617: step: 2068/529, loss: 0.0022970237769186497
2023-01-22 16:30:47.692395: step: 2072/529, loss: 0.002476394409313798
2023-01-22 16:30:48.768545: step: 2076/529, loss: 0.002615951234474778
2023-01-22 16:30:49.843257: step: 2080/529, loss: 0.0074923718348145485
2023-01-22 16:30:50.910174: step: 2084/529, loss: 0.005540072917938232
2023-01-22 16:30:51.958476: step: 2088/529, loss: 0.009539883583784103
2023-01-22 16:30:53.023731: step: 2092/529, loss: 0.013932091183960438
2023-01-22 16:30:54.089787: step: 2096/529, loss: 0.004204911645501852
2023-01-22 16:30:55.181457: step: 2100/529, loss: 0.017170259729027748
2023-01-22 16:30:56.265739: step: 2104/529, loss: 0.01165766455233097
2023-01-22 16:30:57.343959: step: 2108/529, loss: 0.013586471788585186
2023-01-22 16:30:58.429117: step: 2112/529, loss: 0.038044918328523636
2023-01-22 16:30:59.507902: step: 2116/529, loss: 0.0002362493542023003
==================================================
Loss: 0.008
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3201972555746141, 'r': 0.35422201138519926, 'f1': 0.33635135135135136}, 'combined': 0.24783783783783783, 'stategy': 1, 'epoch': 8}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30613320800401794, 'r': 0.3038842955485247, 'f1': 0.3050046063155239}, 'combined': 0.1991221782163524, 'stategy': 1, 'epoch': 8}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32082812499999996, 'r': 0.36526921252371913, 'f1': 0.34160936113575857}, 'combined': 0.2517121608368747, 'stategy': 1, 'epoch': 8}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3303024991605632, 'r': 0.3093550061071819, 'f1': 0.3194857585615699}, 'combined': 0.20857619470858968, 'stategy': 1, 'epoch': 8}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31372444633730834, 'r': 0.34944259962049334, 'f1': 0.3306216337522442}, 'combined': 0.24361594065954834, 'stategy': 1, 'epoch': 8}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3230609044966416, 'r': 0.32128095460960776, 'f1': 0.3221684710588056}, 'combined': 0.21032760286740676, 'stategy': 1, 'epoch': 8}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 8}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 8}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 8}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32374479166666664, 'r': 0.3685898956356736, 'f1': 0.34471495119787043}, 'combined': 0.25400049035632555, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33423857660835543, 'r': 0.3093550061071819, 'f1': 0.3213157485867436}, 'combined': 0.20977090322243364, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 16:33:37.340789: step: 4/529, loss: 0.0076475683599710464
2023-01-22 16:33:38.384907: step: 8/529, loss: 0.0013952614972367883
2023-01-22 16:33:39.442299: step: 12/529, loss: 0.009745420888066292
2023-01-22 16:33:40.506399: step: 16/529, loss: 0.007470333017408848
2023-01-22 16:33:41.556443: step: 20/529, loss: 0.0030291101429611444
2023-01-22 16:33:42.626118: step: 24/529, loss: 0.0055459002032876015
2023-01-22 16:33:43.675593: step: 28/529, loss: 0.007540428079664707
2023-01-22 16:33:44.751383: step: 32/529, loss: 0.0014579800190404058
2023-01-22 16:33:45.807312: step: 36/529, loss: 0.006648776587098837
2023-01-22 16:33:46.873120: step: 40/529, loss: 0.011146008968353271
2023-01-22 16:33:47.922492: step: 44/529, loss: 0.0004218129615765065
2023-01-22 16:33:48.973135: step: 48/529, loss: 0.0022697325330227613
2023-01-22 16:33:50.046941: step: 52/529, loss: 0.006932941731065512
2023-01-22 16:33:51.107914: step: 56/529, loss: 0.001632420695386827
2023-01-22 16:33:52.168661: step: 60/529, loss: 0.0058930376544594765
2023-01-22 16:33:53.227839: step: 64/529, loss: 0.003020771313458681
2023-01-22 16:33:54.285144: step: 68/529, loss: 0.0036091350484639406
2023-01-22 16:33:55.363173: step: 72/529, loss: 0.008187517523765564
2023-01-22 16:33:56.418245: step: 76/529, loss: 0.0021265442483127117
2023-01-22 16:33:57.480313: step: 80/529, loss: 0.003632922889664769
2023-01-22 16:33:58.545556: step: 84/529, loss: 0.0029451590962707996
2023-01-22 16:33:59.615429: step: 88/529, loss: 0.001857382827438414
2023-01-22 16:34:00.685125: step: 92/529, loss: 0.0010842308402061462
2023-01-22 16:34:01.768034: step: 96/529, loss: 0.0808914303779602
2023-01-22 16:34:02.833634: step: 100/529, loss: 0.011222359724342823
2023-01-22 16:34:03.897237: step: 104/529, loss: 0.002562921494245529
2023-01-22 16:34:04.964407: step: 108/529, loss: 0.006626314949244261
2023-01-22 16:34:06.045211: step: 112/529, loss: 1.3431079423753545e-05
2023-01-22 16:34:07.102709: step: 116/529, loss: 0.002375928685069084
2023-01-22 16:34:08.173751: step: 120/529, loss: 0.004076572600752115
2023-01-22 16:34:09.238774: step: 124/529, loss: 0.004171817097812891
2023-01-22 16:34:10.313778: step: 128/529, loss: 0.006225327495485544
2023-01-22 16:34:11.375976: step: 132/529, loss: 0.005350849125534296
2023-01-22 16:34:12.442476: step: 136/529, loss: 0.005230417009443045
2023-01-22 16:34:13.527304: step: 140/529, loss: 0.00936820451170206
2023-01-22 16:34:14.588917: step: 144/529, loss: 0.002336789621040225
2023-01-22 16:34:15.660302: step: 148/529, loss: 0.02020631544291973
2023-01-22 16:34:16.761509: step: 152/529, loss: 0.011263777501881123
2023-01-22 16:34:17.826570: step: 156/529, loss: 0.006566526833921671
2023-01-22 16:34:18.893387: step: 160/529, loss: 0.00023341966152656823
2023-01-22 16:34:19.967061: step: 164/529, loss: 3.326933801872656e-05
2023-01-22 16:34:21.033535: step: 168/529, loss: 0.000817728927358985
2023-01-22 16:34:22.117490: step: 172/529, loss: 0.004214529413729906
2023-01-22 16:34:23.174773: step: 176/529, loss: 0.0034627956338226795
2023-01-22 16:34:24.264944: step: 180/529, loss: 0.015495163388550282
2023-01-22 16:34:25.355213: step: 184/529, loss: 0.004431141074746847
2023-01-22 16:34:26.428377: step: 188/529, loss: 0.004249555058777332
2023-01-22 16:34:27.494910: step: 192/529, loss: 0.0011924149002879858
2023-01-22 16:34:28.561207: step: 196/529, loss: 0.00422682287171483
2023-01-22 16:34:29.630913: step: 200/529, loss: 0.0014853612519800663
2023-01-22 16:34:30.694149: step: 204/529, loss: 0.007872479036450386
2023-01-22 16:34:31.768151: step: 208/529, loss: 0.005835859104990959
2023-01-22 16:34:32.843480: step: 212/529, loss: 0.0021257756743580103
2023-01-22 16:34:33.889229: step: 216/529, loss: 0.0007697069668211043
2023-01-22 16:34:34.968885: step: 220/529, loss: 0.003168319119140506
2023-01-22 16:34:36.039596: step: 224/529, loss: 0.004536579828709364
2023-01-22 16:34:37.095402: step: 228/529, loss: 0.0032074071932584047
2023-01-22 16:34:38.151636: step: 232/529, loss: 0.0037514548748731613
2023-01-22 16:34:39.231743: step: 236/529, loss: 0.004225895740091801
2023-01-22 16:34:40.298172: step: 240/529, loss: 0.002993042813614011
2023-01-22 16:34:41.401214: step: 244/529, loss: 0.0032093417830765247
2023-01-22 16:34:42.466923: step: 248/529, loss: 0.0036520243156701326
2023-01-22 16:34:43.539120: step: 252/529, loss: 0.007269485387951136
2023-01-22 16:34:44.605361: step: 256/529, loss: 0.009392387233674526
2023-01-22 16:34:45.676037: step: 260/529, loss: 0.0012123326305299997
2023-01-22 16:34:46.745965: step: 264/529, loss: 0.004999190103262663
2023-01-22 16:34:47.833987: step: 268/529, loss: 0.006076238118112087
2023-01-22 16:34:48.926899: step: 272/529, loss: 0.016086755320429802
2023-01-22 16:34:49.979243: step: 276/529, loss: 0.0019808385986834764
2023-01-22 16:34:51.045932: step: 280/529, loss: 0.016098368912935257
2023-01-22 16:34:52.104480: step: 284/529, loss: 2.1055468096164986e-05
2023-01-22 16:34:53.172004: step: 288/529, loss: 0.018915528431534767
2023-01-22 16:34:54.225344: step: 292/529, loss: 0.0068099042400717735
2023-01-22 16:34:55.290716: step: 296/529, loss: 0.0003205329994671047
2023-01-22 16:34:56.367947: step: 300/529, loss: 0.002356010489165783
2023-01-22 16:34:57.436530: step: 304/529, loss: 0.013506465591490269
2023-01-22 16:34:58.492024: step: 308/529, loss: 0.010100096464157104
2023-01-22 16:34:59.553669: step: 312/529, loss: 0.0048659429885447025
2023-01-22 16:35:00.624739: step: 316/529, loss: 0.014681518077850342
2023-01-22 16:35:01.687681: step: 320/529, loss: 0.0005140863941051066
2023-01-22 16:35:02.761482: step: 324/529, loss: 0.010165358893573284
2023-01-22 16:35:03.846582: step: 328/529, loss: 0.008363066241145134
2023-01-22 16:35:04.907420: step: 332/529, loss: 0.0028446551878005266
2023-01-22 16:35:05.969195: step: 336/529, loss: 0.00018585480574984103
2023-01-22 16:35:07.038014: step: 340/529, loss: 0.0018784565618261695
2023-01-22 16:35:08.117401: step: 344/529, loss: 0.006612745113670826
2023-01-22 16:35:09.185597: step: 348/529, loss: 0.020105058327317238
2023-01-22 16:35:10.253594: step: 352/529, loss: 0.013487892225384712
2023-01-22 16:35:11.314576: step: 356/529, loss: 0.01829264685511589
2023-01-22 16:35:12.394615: step: 360/529, loss: 0.0006016806000843644
2023-01-22 16:35:13.454953: step: 364/529, loss: 0.004490015562623739
2023-01-22 16:35:14.537305: step: 368/529, loss: 0.0030565359629690647
2023-01-22 16:35:15.612562: step: 372/529, loss: 0.0021017531398683786
2023-01-22 16:35:16.698447: step: 376/529, loss: 0.0114333126693964
2023-01-22 16:35:17.763731: step: 380/529, loss: 0.005322054028511047
2023-01-22 16:35:18.838964: step: 384/529, loss: 0.021088669076561928
2023-01-22 16:35:19.899543: step: 388/529, loss: 4.0491329855285585e-05
2023-01-22 16:35:20.979186: step: 392/529, loss: 0.003996938467025757
2023-01-22 16:35:22.042595: step: 396/529, loss: 0.006614970974624157
2023-01-22 16:35:23.103193: step: 400/529, loss: 0.004860007669776678
2023-01-22 16:35:24.167553: step: 404/529, loss: 0.0049461605958640575
2023-01-22 16:35:25.245507: step: 408/529, loss: 0.0018996495055034757
2023-01-22 16:35:26.327996: step: 412/529, loss: 0.007716783322393894
2023-01-22 16:35:27.409667: step: 416/529, loss: 0.004638045560568571
2023-01-22 16:35:28.474931: step: 420/529, loss: 0.007567286491394043
2023-01-22 16:35:29.540187: step: 424/529, loss: 0.0034006128553301096
2023-01-22 16:35:30.605660: step: 428/529, loss: 0.0025180901866406202
2023-01-22 16:35:31.667358: step: 432/529, loss: 0.001276357565075159
2023-01-22 16:35:32.735826: step: 436/529, loss: 0.001452281721867621
2023-01-22 16:35:33.804031: step: 440/529, loss: 0.007344067096710205
2023-01-22 16:35:34.864661: step: 444/529, loss: 0.003009831765666604
2023-01-22 16:35:35.953176: step: 448/529, loss: 0.009160235524177551
2023-01-22 16:35:37.034682: step: 452/529, loss: 0.014338766224682331
2023-01-22 16:35:38.098595: step: 456/529, loss: 0.006339029408991337
2023-01-22 16:35:39.171187: step: 460/529, loss: 0.007201789412647486
2023-01-22 16:35:40.236873: step: 464/529, loss: 0.005167341325432062
2023-01-22 16:35:41.304751: step: 468/529, loss: 0.029966171830892563
2023-01-22 16:35:42.367966: step: 472/529, loss: 0.0005870857276022434
2023-01-22 16:35:43.446867: step: 476/529, loss: 0.0003639193018898368
2023-01-22 16:35:44.507351: step: 480/529, loss: 0.0014165329048410058
2023-01-22 16:35:45.575859: step: 484/529, loss: 0.0006119013414718211
2023-01-22 16:35:46.666011: step: 488/529, loss: 0.0005429352750070393
2023-01-22 16:35:47.743660: step: 492/529, loss: 0.005061294883489609
2023-01-22 16:35:48.820866: step: 496/529, loss: 0.013761462643742561
2023-01-22 16:35:49.892347: step: 500/529, loss: 0.016085518524050713
2023-01-22 16:35:50.961396: step: 504/529, loss: 0.0008053927449509501
2023-01-22 16:35:52.034054: step: 508/529, loss: 0.016597095876932144
2023-01-22 16:35:53.091748: step: 512/529, loss: 0.004336851183325052
2023-01-22 16:35:54.157108: step: 516/529, loss: 0.0038900349754840136
2023-01-22 16:35:55.240086: step: 520/529, loss: 0.004234934691339731
2023-01-22 16:35:56.340830: step: 524/529, loss: 0.005054661072790623
2023-01-22 16:35:57.418103: step: 528/529, loss: 0.012339567765593529
2023-01-22 16:35:58.475827: step: 532/529, loss: 0.025672173127532005
2023-01-22 16:35:59.564245: step: 536/529, loss: 0.009109568782150745
2023-01-22 16:36:00.627154: step: 540/529, loss: 0.002947914879769087
2023-01-22 16:36:01.711567: step: 544/529, loss: 0.001444044173695147
2023-01-22 16:36:02.777763: step: 548/529, loss: 0.015618451870977879
2023-01-22 16:36:03.844767: step: 552/529, loss: 0.008262096904218197
2023-01-22 16:36:04.931606: step: 556/529, loss: 0.011409304104745388
2023-01-22 16:36:06.002036: step: 560/529, loss: 0.005359118338674307
2023-01-22 16:36:07.078188: step: 564/529, loss: 0.000634010648354888
2023-01-22 16:36:08.163650: step: 568/529, loss: 0.002230749698355794
2023-01-22 16:36:09.231291: step: 572/529, loss: 0.0030680911149829626
2023-01-22 16:36:10.296272: step: 576/529, loss: 0.007307857740670443
2023-01-22 16:36:11.357613: step: 580/529, loss: 0.0031003218609839678
2023-01-22 16:36:12.437192: step: 584/529, loss: 0.002819253597408533
2023-01-22 16:36:13.503761: step: 588/529, loss: 0.0015863453736528754
2023-01-22 16:36:14.570740: step: 592/529, loss: 0.001516444026492536
2023-01-22 16:36:15.642908: step: 596/529, loss: 0.0012560886098071933
2023-01-22 16:36:16.719556: step: 600/529, loss: 0.002046899637207389
2023-01-22 16:36:17.788323: step: 604/529, loss: 0.0015403830911964178
2023-01-22 16:36:18.860612: step: 608/529, loss: 0.004180640447884798
2023-01-22 16:36:19.931335: step: 612/529, loss: 0.005670543294399977
2023-01-22 16:36:21.010679: step: 616/529, loss: 0.010511565953493118
2023-01-22 16:36:22.065529: step: 620/529, loss: 0.004360548686236143
2023-01-22 16:36:23.137897: step: 624/529, loss: 0.00293146725744009
2023-01-22 16:36:24.196474: step: 628/529, loss: 0.013130432926118374
2023-01-22 16:36:25.255582: step: 632/529, loss: 0.006084002088755369
2023-01-22 16:36:26.330938: step: 636/529, loss: 0.003935667686164379
2023-01-22 16:36:27.397369: step: 640/529, loss: 0.006984036415815353
2023-01-22 16:36:28.462133: step: 644/529, loss: 0.004299352411180735
2023-01-22 16:36:29.528823: step: 648/529, loss: 0.002253611572086811
2023-01-22 16:36:30.593542: step: 652/529, loss: 0.004824842792004347
2023-01-22 16:36:31.660681: step: 656/529, loss: 0.003846768755465746
2023-01-22 16:36:32.733523: step: 660/529, loss: 0.006501362659037113
2023-01-22 16:36:33.783959: step: 664/529, loss: 0.015127809718251228
2023-01-22 16:36:34.853692: step: 668/529, loss: 0.008387857116758823
2023-01-22 16:36:35.921270: step: 672/529, loss: 0.02491394616663456
2023-01-22 16:36:36.983053: step: 676/529, loss: 0.0008256888249889016
2023-01-22 16:36:38.048168: step: 680/529, loss: 0.022070206701755524
2023-01-22 16:36:39.119249: step: 684/529, loss: 0.0008302762289531529
2023-01-22 16:36:40.181924: step: 688/529, loss: 0.004053502809256315
2023-01-22 16:36:41.257005: step: 692/529, loss: 0.0028657459188252687
2023-01-22 16:36:42.340659: step: 696/529, loss: 0.007253702264279127
2023-01-22 16:36:43.439900: step: 700/529, loss: 0.0233880877494812
2023-01-22 16:36:44.516574: step: 704/529, loss: 0.011055349372327328
2023-01-22 16:36:45.582912: step: 708/529, loss: 0.00232279347255826
2023-01-22 16:36:46.651525: step: 712/529, loss: 0.0035306140780448914
2023-01-22 16:36:47.720017: step: 716/529, loss: 0.008902845904231071
2023-01-22 16:36:48.778974: step: 720/529, loss: 0.0016613632906228304
2023-01-22 16:36:49.844392: step: 724/529, loss: 0.0030670773703604937
2023-01-22 16:36:50.908705: step: 728/529, loss: 0.008626404218375683
2023-01-22 16:36:51.984692: step: 732/529, loss: 0.012124470435082912
2023-01-22 16:36:53.070128: step: 736/529, loss: 0.014640077948570251
2023-01-22 16:36:54.156042: step: 740/529, loss: 0.0023502048570662737
2023-01-22 16:36:55.210710: step: 744/529, loss: 0.02139144204556942
2023-01-22 16:36:56.279395: step: 748/529, loss: 0.0
2023-01-22 16:36:57.365513: step: 752/529, loss: 0.0029019841458648443
2023-01-22 16:36:58.429945: step: 756/529, loss: 0.016864478588104248
2023-01-22 16:36:59.501341: step: 760/529, loss: 0.0011493735946714878
2023-01-22 16:37:00.586671: step: 764/529, loss: 0.013748283497989178
2023-01-22 16:37:01.669956: step: 768/529, loss: 0.0035685438197106123
2023-01-22 16:37:02.735619: step: 772/529, loss: 0.0010443481151014566
2023-01-22 16:37:03.821805: step: 776/529, loss: 0.01635405793786049
2023-01-22 16:37:04.896859: step: 780/529, loss: 0.006745730992406607
2023-01-22 16:37:05.968812: step: 784/529, loss: 0.0051277135498821735
2023-01-22 16:37:07.044560: step: 788/529, loss: 0.002445952733978629
2023-01-22 16:37:08.099482: step: 792/529, loss: 0.004199530929327011
2023-01-22 16:37:09.156474: step: 796/529, loss: 0.0009448050404898822
2023-01-22 16:37:10.231724: step: 800/529, loss: 0.011746187694370747
2023-01-22 16:37:11.299667: step: 804/529, loss: 0.0009272314491681755
2023-01-22 16:37:12.358539: step: 808/529, loss: 0.02234543487429619
2023-01-22 16:37:13.439194: step: 812/529, loss: 0.0027863499708473682
2023-01-22 16:37:14.508288: step: 816/529, loss: 0.01994817517697811
2023-01-22 16:37:15.580200: step: 820/529, loss: 0.0022010498214513063
2023-01-22 16:37:16.639247: step: 824/529, loss: 0.023616492748260498
2023-01-22 16:37:17.722061: step: 828/529, loss: 0.004976135212928057
2023-01-22 16:37:18.786548: step: 832/529, loss: 0.004065125714987516
2023-01-22 16:37:19.843625: step: 836/529, loss: 0.0029577077366411686
2023-01-22 16:37:20.906663: step: 840/529, loss: 0.004215072840452194
2023-01-22 16:37:21.988020: step: 844/529, loss: 0.003447695402428508
2023-01-22 16:37:23.076822: step: 848/529, loss: 0.005496373865753412
2023-01-22 16:37:24.151570: step: 852/529, loss: 0.007129501551389694
2023-01-22 16:37:25.238483: step: 856/529, loss: 0.004603737033903599
2023-01-22 16:37:26.336740: step: 860/529, loss: 0.0175398588180542
2023-01-22 16:37:27.404789: step: 864/529, loss: 0.010939725674688816
2023-01-22 16:37:28.493121: step: 868/529, loss: 0.008177352137863636
2023-01-22 16:37:29.573651: step: 872/529, loss: 0.006134300492703915
2023-01-22 16:37:30.639860: step: 876/529, loss: 0.0037835538387298584
2023-01-22 16:37:31.746245: step: 880/529, loss: 0.011444897390902042
2023-01-22 16:37:32.813317: step: 884/529, loss: 0.019874265417456627
2023-01-22 16:37:33.901809: step: 888/529, loss: 0.0016192832263186574
2023-01-22 16:37:34.968838: step: 892/529, loss: 0.014175825752317905
2023-01-22 16:37:36.041409: step: 896/529, loss: 0.0023495086934417486
2023-01-22 16:37:37.108553: step: 900/529, loss: 0.006926489993929863
2023-01-22 16:37:38.171449: step: 904/529, loss: 0.01937299594283104
2023-01-22 16:37:39.247371: step: 908/529, loss: 0.010852350853383541
2023-01-22 16:37:40.316153: step: 912/529, loss: 0.02044033631682396
2023-01-22 16:37:41.389249: step: 916/529, loss: 0.01225733757019043
2023-01-22 16:37:42.472978: step: 920/529, loss: 0.010902819223701954
2023-01-22 16:37:43.543382: step: 924/529, loss: 0.0006711737369187176
2023-01-22 16:37:44.625257: step: 928/529, loss: 0.012211877852678299
2023-01-22 16:37:45.724241: step: 932/529, loss: 0.002037275116890669
2023-01-22 16:37:46.809619: step: 936/529, loss: 0.0019138348288834095
2023-01-22 16:37:47.903706: step: 940/529, loss: 0.0034044641070067883
2023-01-22 16:37:49.001142: step: 944/529, loss: 0.002331846859306097
2023-01-22 16:37:50.075051: step: 948/529, loss: 0.001319916220381856
2023-01-22 16:37:51.146472: step: 952/529, loss: 0.009768449701368809
2023-01-22 16:37:52.235548: step: 956/529, loss: 0.008089636452496052
2023-01-22 16:37:53.347079: step: 960/529, loss: 0.00013672596833202988
2023-01-22 16:37:54.432473: step: 964/529, loss: 0.007477053441107273
2023-01-22 16:37:55.506259: step: 968/529, loss: 0.0013338353019207716
2023-01-22 16:37:56.594653: step: 972/529, loss: 0.0058829886838793755
2023-01-22 16:37:57.682782: step: 976/529, loss: 0.005059738643467426
2023-01-22 16:37:58.762177: step: 980/529, loss: 0.0023297767620533705
2023-01-22 16:37:59.840507: step: 984/529, loss: 0.006030438467860222
2023-01-22 16:38:00.917526: step: 988/529, loss: 0.010914365760982037
2023-01-22 16:38:02.001039: step: 992/529, loss: 0.006999350618571043
2023-01-22 16:38:03.071328: step: 996/529, loss: 0.0009580472833476961
2023-01-22 16:38:04.148108: step: 1000/529, loss: 0.012078394182026386
2023-01-22 16:38:05.221799: step: 1004/529, loss: 0.0022896553855389357
2023-01-22 16:38:06.281869: step: 1008/529, loss: 0.00154294993262738
2023-01-22 16:38:07.369757: step: 1012/529, loss: 0.005238499026745558
2023-01-22 16:38:08.454549: step: 1016/529, loss: 0.005048517603427172
2023-01-22 16:38:09.542769: step: 1020/529, loss: 0.005287530366331339
2023-01-22 16:38:10.631345: step: 1024/529, loss: 0.012809209525585175
2023-01-22 16:38:11.736598: step: 1028/529, loss: 0.005282236263155937
2023-01-22 16:38:12.814772: step: 1032/529, loss: 0.007225828245282173
2023-01-22 16:38:13.893069: step: 1036/529, loss: 0.0038605937734246254
2023-01-22 16:38:14.982334: step: 1040/529, loss: 0.008390206843614578
2023-01-22 16:38:16.093261: step: 1044/529, loss: 0.0072082532569766045
2023-01-22 16:38:17.168063: step: 1048/529, loss: 0.0012835939414799213
2023-01-22 16:38:18.274078: step: 1052/529, loss: 0.010899576358497143
2023-01-22 16:38:19.358677: step: 1056/529, loss: 0.004053235985338688
2023-01-22 16:38:20.437539: step: 1060/529, loss: 0.002784229116514325
2023-01-22 16:38:21.516212: step: 1064/529, loss: 0.00917440839111805
2023-01-22 16:38:22.605172: step: 1068/529, loss: 0.008142219856381416
2023-01-22 16:38:23.693916: step: 1072/529, loss: 0.00158506294246763
2023-01-22 16:38:24.787381: step: 1076/529, loss: 0.014603233896195889
2023-01-22 16:38:25.864173: step: 1080/529, loss: 0.001800975645892322
2023-01-22 16:38:26.940522: step: 1084/529, loss: 0.0008096672245301306
2023-01-22 16:38:28.009451: step: 1088/529, loss: 0.0008882347028702497
2023-01-22 16:38:29.085753: step: 1092/529, loss: 5.980853529763408e-05
2023-01-22 16:38:30.166316: step: 1096/529, loss: 0.0019555939361453056
2023-01-22 16:38:31.260426: step: 1100/529, loss: 0.010712580755352974
2023-01-22 16:38:32.337636: step: 1104/529, loss: 0.00031959067564457655
2023-01-22 16:38:33.425496: step: 1108/529, loss: 0.0001488373236497864
2023-01-22 16:38:34.514697: step: 1112/529, loss: 0.0009048609645105898
2023-01-22 16:38:35.620595: step: 1116/529, loss: 0.0010535198962315917
2023-01-22 16:38:36.703429: step: 1120/529, loss: 0.0004017679311800748
2023-01-22 16:38:37.790838: step: 1124/529, loss: 0.002266225405037403
2023-01-22 16:38:38.872355: step: 1128/529, loss: 0.0054472372867167
2023-01-22 16:38:39.972191: step: 1132/529, loss: 0.0006995557341724634
2023-01-22 16:38:41.064050: step: 1136/529, loss: 0.03537345305085182
2023-01-22 16:38:42.140938: step: 1140/529, loss: 0.015552092343568802
2023-01-22 16:38:43.218223: step: 1144/529, loss: 0.00044780928874388337
2023-01-22 16:38:44.294391: step: 1148/529, loss: 0.008493904955685139
2023-01-22 16:38:45.382469: step: 1152/529, loss: 0.01671547442674637
2023-01-22 16:38:46.455863: step: 1156/529, loss: 0.0052228085696697235
2023-01-22 16:38:47.544214: step: 1160/529, loss: 0.019558357074856758
2023-01-22 16:38:48.622400: step: 1164/529, loss: 2.258449785585981e-05
2023-01-22 16:38:49.726463: step: 1168/529, loss: 0.007621017284691334
2023-01-22 16:38:50.803982: step: 1172/529, loss: 0.001624539028853178
2023-01-22 16:38:51.909983: step: 1176/529, loss: 0.005067102145403624
2023-01-22 16:38:53.010086: step: 1180/529, loss: 0.03003064915537834
2023-01-22 16:38:54.096867: step: 1184/529, loss: 0.0074188909493386745
2023-01-22 16:38:55.165772: step: 1188/529, loss: 0.0017773497384041548
2023-01-22 16:38:56.242610: step: 1192/529, loss: 0.004770188592374325
2023-01-22 16:38:57.324284: step: 1196/529, loss: 0.0003078423033002764
2023-01-22 16:38:58.419771: step: 1200/529, loss: 0.01505332812666893
2023-01-22 16:38:59.498933: step: 1204/529, loss: 0.012690840288996696
2023-01-22 16:39:00.583269: step: 1208/529, loss: 0.0045699733309447765
2023-01-22 16:39:01.653786: step: 1212/529, loss: 0.012958314269781113
2023-01-22 16:39:02.729851: step: 1216/529, loss: 0.018212882801890373
2023-01-22 16:39:03.814451: step: 1220/529, loss: 0.0046076057478785515
2023-01-22 16:39:04.908629: step: 1224/529, loss: 0.002567409072071314
2023-01-22 16:39:05.985160: step: 1228/529, loss: 0.0002043575223069638
2023-01-22 16:39:07.070826: step: 1232/529, loss: 0.002568405820056796
2023-01-22 16:39:08.159686: step: 1236/529, loss: 4.1959297959692776e-05
2023-01-22 16:39:09.243298: step: 1240/529, loss: 0.0026478685904294252
2023-01-22 16:39:10.325527: step: 1244/529, loss: 0.0012978308368474245
2023-01-22 16:39:11.417581: step: 1248/529, loss: 0.005010705441236496
2023-01-22 16:39:12.496965: step: 1252/529, loss: 0.015009735710918903
2023-01-22 16:39:13.600033: step: 1256/529, loss: 0.0007904329104349017
2023-01-22 16:39:14.666688: step: 1260/529, loss: 0.0034027108922600746
2023-01-22 16:39:15.758011: step: 1264/529, loss: 0.0326940156519413
2023-01-22 16:39:16.820257: step: 1268/529, loss: 0.00028689843020401895
2023-01-22 16:39:17.902172: step: 1272/529, loss: 0.011139270849525928
2023-01-22 16:39:18.997747: step: 1276/529, loss: 0.0010533812455832958
2023-01-22 16:39:20.077484: step: 1280/529, loss: 0.007056094706058502
2023-01-22 16:39:21.170792: step: 1284/529, loss: 0.0038725589402019978
2023-01-22 16:39:22.248497: step: 1288/529, loss: 0.00634577963501215
2023-01-22 16:39:23.331555: step: 1292/529, loss: 0.009059863165020943
2023-01-22 16:39:24.412469: step: 1296/529, loss: 0.00016235487419180572
2023-01-22 16:39:25.492624: step: 1300/529, loss: 0.005849065724760294
2023-01-22 16:39:26.559624: step: 1304/529, loss: 0.006454144138842821
2023-01-22 16:39:27.641798: step: 1308/529, loss: 0.000713278423063457
2023-01-22 16:39:28.749187: step: 1312/529, loss: 0.0006331218173727393
2023-01-22 16:39:29.816380: step: 1316/529, loss: 0.0023495752830058336
2023-01-22 16:39:30.906971: step: 1320/529, loss: 0.005079804453998804
2023-01-22 16:39:31.993226: step: 1324/529, loss: 0.0034808525815606117
2023-01-22 16:39:33.080937: step: 1328/529, loss: 0.003095766296610236
2023-01-22 16:39:34.146869: step: 1332/529, loss: 0.00925816223025322
2023-01-22 16:39:35.219213: step: 1336/529, loss: 0.008485754020512104
2023-01-22 16:39:36.306928: step: 1340/529, loss: 0.010287277400493622
2023-01-22 16:39:37.394398: step: 1344/529, loss: 0.003547879634425044
2023-01-22 16:39:38.484043: step: 1348/529, loss: 0.007376531604677439
2023-01-22 16:39:39.564120: step: 1352/529, loss: 0.00036150572123005986
2023-01-22 16:39:40.645261: step: 1356/529, loss: 0.01189280953258276
2023-01-22 16:39:41.710992: step: 1360/529, loss: 0.016222845762968063
2023-01-22 16:39:42.765118: step: 1364/529, loss: 0.007536229211837053
2023-01-22 16:39:43.867109: step: 1368/529, loss: 0.004005281254649162
2023-01-22 16:39:44.937748: step: 1372/529, loss: 0.012071509845554829
2023-01-22 16:39:46.015156: step: 1376/529, loss: 0.00499314209446311
2023-01-22 16:39:47.106596: step: 1380/529, loss: 0.00555872917175293
2023-01-22 16:39:48.183796: step: 1384/529, loss: 0.008989017456769943
2023-01-22 16:39:49.259742: step: 1388/529, loss: 0.0023135317023843527
2023-01-22 16:39:50.326443: step: 1392/529, loss: 0.0020052785985171795
2023-01-22 16:39:51.395938: step: 1396/529, loss: 0.0018481879960745573
2023-01-22 16:39:52.473532: step: 1400/529, loss: 0.005316754337400198
2023-01-22 16:39:53.544955: step: 1404/529, loss: 0.005384465213865042
2023-01-22 16:39:54.609171: step: 1408/529, loss: 0.0035632906947284937
2023-01-22 16:39:55.682924: step: 1412/529, loss: 0.007418631576001644
2023-01-22 16:39:56.764495: step: 1416/529, loss: 0.00488336430862546
2023-01-22 16:39:57.847009: step: 1420/529, loss: 0.0015416296664625406
2023-01-22 16:39:58.939458: step: 1424/529, loss: 0.006803611759096384
2023-01-22 16:40:00.018815: step: 1428/529, loss: 0.003949249163269997
2023-01-22 16:40:01.105267: step: 1432/529, loss: 0.006798784248530865
2023-01-22 16:40:02.183364: step: 1436/529, loss: 0.012535007670521736
2023-01-22 16:40:03.242392: step: 1440/529, loss: 0.00040682428516447544
2023-01-22 16:40:04.323138: step: 1444/529, loss: 0.003597379894927144
2023-01-22 16:40:05.390695: step: 1448/529, loss: 0.005746961571276188
2023-01-22 16:40:06.462167: step: 1452/529, loss: 0.0025634882040321827
2023-01-22 16:40:07.541395: step: 1456/529, loss: 0.012677955441176891
2023-01-22 16:40:08.610278: step: 1460/529, loss: 0.009069709107279778
2023-01-22 16:40:09.697820: step: 1464/529, loss: 0.012745595537126064
2023-01-22 16:40:10.756002: step: 1468/529, loss: 0.009782114066183567
2023-01-22 16:40:11.831058: step: 1472/529, loss: 0.0004659111727960408
2023-01-22 16:40:12.924299: step: 1476/529, loss: 0.003835623385384679
2023-01-22 16:40:13.994333: step: 1480/529, loss: 0.0060687074437737465
2023-01-22 16:40:15.066976: step: 1484/529, loss: 0.0006159237818792462
2023-01-22 16:40:16.127081: step: 1488/529, loss: 0.013183645904064178
2023-01-22 16:40:17.229102: step: 1492/529, loss: 0.005801281426101923
2023-01-22 16:40:18.300793: step: 1496/529, loss: 0.016578853130340576
2023-01-22 16:40:19.369530: step: 1500/529, loss: 0.0008852445753291249
2023-01-22 16:40:20.444476: step: 1504/529, loss: 0.02838902361690998
2023-01-22 16:40:21.520221: step: 1508/529, loss: 0.0008083205320872366
2023-01-22 16:40:22.609118: step: 1512/529, loss: 0.005692531354725361
2023-01-22 16:40:23.680465: step: 1516/529, loss: 0.003928464837372303
2023-01-22 16:40:24.738878: step: 1520/529, loss: 0.009461517445743084
2023-01-22 16:40:25.803354: step: 1524/529, loss: 0.0095612658187747
2023-01-22 16:40:26.860306: step: 1528/529, loss: 0.0062532140873372555
2023-01-22 16:40:27.933801: step: 1532/529, loss: 0.005272820126265287
2023-01-22 16:40:29.003395: step: 1536/529, loss: 0.003997983876615763
2023-01-22 16:40:30.074987: step: 1540/529, loss: 0.0035730230156332254
2023-01-22 16:40:31.154458: step: 1544/529, loss: 0.0037694217171519995
2023-01-22 16:40:32.233298: step: 1548/529, loss: 0.007433673366904259
2023-01-22 16:40:33.310236: step: 1552/529, loss: 0.002951303729787469
2023-01-22 16:40:34.392094: step: 1556/529, loss: 0.000823546084575355
2023-01-22 16:40:35.477526: step: 1560/529, loss: 0.0019693535286933184
2023-01-22 16:40:36.534868: step: 1564/529, loss: 0.0001680671120993793
2023-01-22 16:40:37.604788: step: 1568/529, loss: 0.004970727022737265
2023-01-22 16:40:38.686758: step: 1572/529, loss: 0.004377331584692001
2023-01-22 16:40:39.738039: step: 1576/529, loss: 0.009058392606675625
2023-01-22 16:40:40.803883: step: 1580/529, loss: 0.0016375655541196465
2023-01-22 16:40:41.875942: step: 1584/529, loss: 0.00201908010058105
2023-01-22 16:40:42.963511: step: 1588/529, loss: 0.0015947859501466155
2023-01-22 16:40:44.028911: step: 1592/529, loss: 0.00842420943081379
2023-01-22 16:40:45.107564: step: 1596/529, loss: 0.006397983990609646
2023-01-22 16:40:46.186361: step: 1600/529, loss: 0.006083968561142683
2023-01-22 16:40:47.274653: step: 1604/529, loss: 0.006729488261044025
2023-01-22 16:40:48.351415: step: 1608/529, loss: 0.02505103312432766
2023-01-22 16:40:49.414147: step: 1612/529, loss: 0.00016586524725425988
2023-01-22 16:40:50.477799: step: 1616/529, loss: 0.008201044984161854
2023-01-22 16:40:51.558860: step: 1620/529, loss: 0.00033281039213761687
2023-01-22 16:40:52.635273: step: 1624/529, loss: 0.0005419896915555
2023-01-22 16:40:53.705775: step: 1628/529, loss: 0.008269484154880047
2023-01-22 16:40:54.782199: step: 1632/529, loss: 0.0017122018616646528
2023-01-22 16:40:55.850783: step: 1636/529, loss: 0.06922311335802078
2023-01-22 16:40:56.929324: step: 1640/529, loss: 0.004820461850613356
2023-01-22 16:40:57.987632: step: 1644/529, loss: 0.012144972570240498
2023-01-22 16:40:59.062770: step: 1648/529, loss: 0.003677899017930031
2023-01-22 16:41:00.140291: step: 1652/529, loss: 0.01788925565779209
2023-01-22 16:41:01.212418: step: 1656/529, loss: 0.0032273477409034967
2023-01-22 16:41:02.281190: step: 1660/529, loss: 0.0028945133090019226
2023-01-22 16:41:03.355912: step: 1664/529, loss: 0.009249512106180191
2023-01-22 16:41:04.443194: step: 1668/529, loss: 0.004640126135200262
2023-01-22 16:41:05.506974: step: 1672/529, loss: 0.0012480197474360466
2023-01-22 16:41:06.575212: step: 1676/529, loss: 0.0064326198771595955
2023-01-22 16:41:07.636793: step: 1680/529, loss: 0.004940737504512072
2023-01-22 16:41:08.711744: step: 1684/529, loss: 0.011697688139975071
2023-01-22 16:41:09.779228: step: 1688/529, loss: 0.0
2023-01-22 16:41:10.853967: step: 1692/529, loss: 0.009908830747008324
2023-01-22 16:41:11.926284: step: 1696/529, loss: 0.006016677711158991
2023-01-22 16:41:12.989786: step: 1700/529, loss: 0.004238234832882881
2023-01-22 16:41:14.055316: step: 1704/529, loss: 0.007609625346958637
2023-01-22 16:41:15.108485: step: 1708/529, loss: 0.00047207679017446935
2023-01-22 16:41:16.155311: step: 1712/529, loss: 0.006124584935605526
2023-01-22 16:41:17.228484: step: 1716/529, loss: 0.019933952018618584
2023-01-22 16:41:18.288564: step: 1720/529, loss: 0.007246662862598896
2023-01-22 16:41:19.353777: step: 1724/529, loss: 0.00900278426706791
2023-01-22 16:41:20.418858: step: 1728/529, loss: 0.01211378164589405
2023-01-22 16:41:21.506125: step: 1732/529, loss: 0.00901151541620493
2023-01-22 16:41:22.569939: step: 1736/529, loss: 0.01022647600620985
2023-01-22 16:41:23.638368: step: 1740/529, loss: 0.0
2023-01-22 16:41:24.714655: step: 1744/529, loss: 0.007156314328312874
2023-01-22 16:41:25.769630: step: 1748/529, loss: 0.002353959484025836
2023-01-22 16:41:26.838497: step: 1752/529, loss: 0.016793211922049522
2023-01-22 16:41:27.905022: step: 1756/529, loss: 0.00508834095671773
2023-01-22 16:41:28.965769: step: 1760/529, loss: 0.0017321131890639663
2023-01-22 16:41:30.042394: step: 1764/529, loss: 0.00010371057578595355
2023-01-22 16:41:31.112442: step: 1768/529, loss: 0.030849751085042953
2023-01-22 16:41:32.188456: step: 1772/529, loss: 0.006752902641892433
2023-01-22 16:41:33.254893: step: 1776/529, loss: 0.004435475450009108
2023-01-22 16:41:34.325667: step: 1780/529, loss: 0.0037832336965948343
2023-01-22 16:41:35.394020: step: 1784/529, loss: 0.005638766568154097
2023-01-22 16:41:36.450747: step: 1788/529, loss: 0.007061276119202375
2023-01-22 16:41:37.515018: step: 1792/529, loss: 0.00024603374185971916
2023-01-22 16:41:38.603225: step: 1796/529, loss: 0.003160672727972269
2023-01-22 16:41:39.694836: step: 1800/529, loss: 0.013142304494976997
2023-01-22 16:41:40.780462: step: 1804/529, loss: 0.005885056219995022
2023-01-22 16:41:41.862340: step: 1808/529, loss: 0.009415185078978539
2023-01-22 16:41:42.932246: step: 1812/529, loss: 0.0065564364194869995
2023-01-22 16:41:43.999888: step: 1816/529, loss: 0.0025281747803092003
2023-01-22 16:41:45.073462: step: 1820/529, loss: 5.0830625696107745e-05
2023-01-22 16:41:46.151315: step: 1824/529, loss: 0.0009516460704617202
2023-01-22 16:41:47.217157: step: 1828/529, loss: 0.05348248407244682
2023-01-22 16:41:48.294212: step: 1832/529, loss: 0.007529357448220253
2023-01-22 16:41:49.367311: step: 1836/529, loss: 0.0030437230598181486
2023-01-22 16:41:50.440253: step: 1840/529, loss: 0.001966297160834074
2023-01-22 16:41:51.519664: step: 1844/529, loss: 0.038521189242601395
2023-01-22 16:41:52.587996: step: 1848/529, loss: 0.0017159967683255672
2023-01-22 16:41:53.673019: step: 1852/529, loss: 0.0024291304871439934
2023-01-22 16:41:54.760260: step: 1856/529, loss: 0.002658829092979431
2023-01-22 16:41:55.838381: step: 1860/529, loss: 0.0121042151004076
2023-01-22 16:41:56.913293: step: 1864/529, loss: 0.002069308655336499
2023-01-22 16:41:57.981984: step: 1868/529, loss: 0.029283249750733376
2023-01-22 16:41:59.074803: step: 1872/529, loss: 0.0024235681630671024
2023-01-22 16:42:00.150511: step: 1876/529, loss: 0.004316000267863274
2023-01-22 16:42:01.232164: step: 1880/529, loss: 0.005460443906486034
2023-01-22 16:42:02.324143: step: 1884/529, loss: 0.006304616574198008
2023-01-22 16:42:03.388164: step: 1888/529, loss: 0.02929220162332058
2023-01-22 16:42:04.476533: step: 1892/529, loss: 0.005456773564219475
2023-01-22 16:42:05.543716: step: 1896/529, loss: 0.001716810860671103
2023-01-22 16:42:06.608709: step: 1900/529, loss: 0.0020062385592609644
2023-01-22 16:42:07.702442: step: 1904/529, loss: 0.00724907498806715
2023-01-22 16:42:08.778364: step: 1908/529, loss: 0.005905916914343834
2023-01-22 16:42:09.871171: step: 1912/529, loss: 0.021696487441658974
2023-01-22 16:42:10.953858: step: 1916/529, loss: 0.005390317644923925
2023-01-22 16:42:12.031813: step: 1920/529, loss: 0.005775989964604378
2023-01-22 16:42:13.098622: step: 1924/529, loss: 0.010800627991557121
2023-01-22 16:42:14.164466: step: 1928/529, loss: 0.0019488058751448989
2023-01-22 16:42:15.244999: step: 1932/529, loss: 0.0028403939213603735
2023-01-22 16:42:16.303363: step: 1936/529, loss: 0.016468241810798645
2023-01-22 16:42:17.361769: step: 1940/529, loss: 0.008032802492380142
2023-01-22 16:42:18.437114: step: 1944/529, loss: 0.0039010082837194204
2023-01-22 16:42:19.520305: step: 1948/529, loss: 0.0011157785775139928
2023-01-22 16:42:20.592686: step: 1952/529, loss: 0.019286809489130974
2023-01-22 16:42:21.669586: step: 1956/529, loss: 0.009672509506344795
2023-01-22 16:42:22.736980: step: 1960/529, loss: 0.00016585277626290917
2023-01-22 16:42:23.798323: step: 1964/529, loss: 0.0013886081287637353
2023-01-22 16:42:24.885674: step: 1968/529, loss: 0.0017637466080486774
2023-01-22 16:42:25.966913: step: 1972/529, loss: 0.012323351576924324
2023-01-22 16:42:27.042808: step: 1976/529, loss: 0.007403888739645481
2023-01-22 16:42:28.109401: step: 1980/529, loss: 0.011588135734200478
2023-01-22 16:42:29.178331: step: 1984/529, loss: 0.02019616961479187
2023-01-22 16:42:30.245374: step: 1988/529, loss: 0.008840294554829597
2023-01-22 16:42:31.313968: step: 1992/529, loss: 0.0026347257662564516
2023-01-22 16:42:32.375361: step: 1996/529, loss: 0.00047466118121519685
2023-01-22 16:42:33.432298: step: 2000/529, loss: 0.0005630180821754038
2023-01-22 16:42:34.511063: step: 2004/529, loss: 0.005905618891119957
2023-01-22 16:42:35.584967: step: 2008/529, loss: 0.0031517362222075462
2023-01-22 16:42:36.640958: step: 2012/529, loss: 0.0063653071410954
2023-01-22 16:42:37.728780: step: 2016/529, loss: 0.006680846214294434
2023-01-22 16:42:38.807819: step: 2020/529, loss: 0.003968801815062761
2023-01-22 16:42:39.865561: step: 2024/529, loss: 0.00036190554965287447
2023-01-22 16:42:40.924271: step: 2028/529, loss: 0.006771177984774113
2023-01-22 16:42:41.983759: step: 2032/529, loss: 0.00410230690613389
2023-01-22 16:42:43.048626: step: 2036/529, loss: 0.011110005900263786
2023-01-22 16:42:44.118016: step: 2040/529, loss: 0.004130862187594175
2023-01-22 16:42:45.193722: step: 2044/529, loss: 0.0013060435885563493
2023-01-22 16:42:46.271649: step: 2048/529, loss: 0.010264605283737183
2023-01-22 16:42:47.364511: step: 2052/529, loss: 0.0068694911897182465
2023-01-22 16:42:48.459025: step: 2056/529, loss: 0.008920758962631226
2023-01-22 16:42:49.525345: step: 2060/529, loss: 0.0025634404737502337
2023-01-22 16:42:50.617191: step: 2064/529, loss: 0.013335098512470722
2023-01-22 16:42:51.695621: step: 2068/529, loss: 0.003870293963700533
2023-01-22 16:42:52.764432: step: 2072/529, loss: 0.015538040548563004
2023-01-22 16:42:53.846385: step: 2076/529, loss: 0.007456211838871241
2023-01-22 16:42:54.910002: step: 2080/529, loss: 0.001130507211200893
2023-01-22 16:42:55.981027: step: 2084/529, loss: 0.01031955424696207
2023-01-22 16:42:57.056096: step: 2088/529, loss: 0.02968425303697586
2023-01-22 16:42:58.147104: step: 2092/529, loss: 0.005661926697939634
2023-01-22 16:42:59.222358: step: 2096/529, loss: 0.0027986892964690924
2023-01-22 16:43:00.302679: step: 2100/529, loss: 0.012736142612993717
2023-01-22 16:43:01.374982: step: 2104/529, loss: 0.01918371580541134
2023-01-22 16:43:02.475178: step: 2108/529, loss: 0.06171911209821701
2023-01-22 16:43:03.547281: step: 2112/529, loss: 0.014033549465239048
2023-01-22 16:43:04.620669: step: 2116/529, loss: 0.005055828019976616
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3173109965635739, 'r': 0.35042694497153704, 'f1': 0.3330477908025248}, 'combined': 0.24540363532817613, 'stategy': 1, 'epoch': 9}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.31021445606358217, 'r': 0.3087888381588782, 'f1': 0.3095000054508148}, 'combined': 0.20205699837721589, 'stategy': 1, 'epoch': 9}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31887305879090405, 'r': 0.3636484029095509, 'f1': 0.33979203605200947}, 'combined': 0.2503730791962175, 'stategy': 1, 'epoch': 9}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3313694874090244, 'r': 0.31096346198953484, 'f1': 0.3208423391603735}, 'combined': 0.20946183800107288, 'stategy': 1, 'epoch': 9}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.30948604060913704, 'r': 0.34707068311195444, 'f1': 0.32720259391771017}, 'combined': 0.24109664814989168, 'stategy': 1, 'epoch': 9}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.321806029016418, 'r': 0.3215105230209943, 'f1': 0.3216582081487026}, 'combined': 0.20999447785873848, 'stategy': 1, 'epoch': 9}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 9}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 9}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 9}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32374479166666664, 'r': 0.3685898956356736, 'f1': 0.34471495119787043}, 'combined': 0.25400049035632555, 'stategy': 1, 'epoch': 4}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33423857660835543, 'r': 0.3093550061071819, 'f1': 0.3213157485867436}, 'combined': 0.20977090322243364, 'stategy': 1, 'epoch': 4}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 4}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 16:45:42.043043: step: 4/529, loss: 0.009177212603390217
2023-01-22 16:45:43.097294: step: 8/529, loss: 0.006231806706637144
2023-01-22 16:45:44.155288: step: 12/529, loss: 0.013157458044588566
2023-01-22 16:45:45.220379: step: 16/529, loss: 0.023935312405228615
2023-01-22 16:45:46.273244: step: 20/529, loss: 0.0008759293123148382
2023-01-22 16:45:47.344681: step: 24/529, loss: 0.0045522525906562805
2023-01-22 16:45:48.420175: step: 28/529, loss: 2.7001295165973715e-05
2023-01-22 16:45:49.474389: step: 32/529, loss: 0.019330311566591263
2023-01-22 16:45:50.566497: step: 36/529, loss: 0.010645509697496891
2023-01-22 16:45:51.625904: step: 40/529, loss: 0.0075593567453324795
2023-01-22 16:45:52.695577: step: 44/529, loss: 0.004905917681753635
2023-01-22 16:45:53.749279: step: 48/529, loss: 0.0021308085415512323
2023-01-22 16:45:54.817778: step: 52/529, loss: 0.005914323031902313
2023-01-22 16:45:55.889980: step: 56/529, loss: 0.005613838322460651
2023-01-22 16:45:56.944856: step: 60/529, loss: 0.009431330487132072
2023-01-22 16:45:58.011859: step: 64/529, loss: 0.005296084098517895
2023-01-22 16:45:59.076735: step: 68/529, loss: 0.003205634653568268
2023-01-22 16:46:00.160658: step: 72/529, loss: 0.006710636895149946
2023-01-22 16:46:01.230109: step: 76/529, loss: 0.019852634519338608
2023-01-22 16:46:02.277498: step: 80/529, loss: 0.0004563805996440351
2023-01-22 16:46:03.352830: step: 84/529, loss: 0.008617057465016842
2023-01-22 16:46:04.415422: step: 88/529, loss: 0.0058946493081748486
2023-01-22 16:46:05.475317: step: 92/529, loss: 0.003905066754668951
2023-01-22 16:46:06.532848: step: 96/529, loss: 0.0009366964222863317
2023-01-22 16:46:07.585782: step: 100/529, loss: 0.03207209333777428
2023-01-22 16:46:08.657333: step: 104/529, loss: 0.001331940060481429
2023-01-22 16:46:09.727878: step: 108/529, loss: 0.009211969561874866
2023-01-22 16:46:10.815100: step: 112/529, loss: 0.011316678486764431
2023-01-22 16:46:11.877071: step: 116/529, loss: 0.010628294199705124
2023-01-22 16:46:12.945941: step: 120/529, loss: 0.020939765498042107
2023-01-22 16:46:14.014566: step: 124/529, loss: 0.0007465697126463056
2023-01-22 16:46:15.078983: step: 128/529, loss: 0.002736742841079831
2023-01-22 16:46:16.133015: step: 132/529, loss: 0.0066178226843476295
2023-01-22 16:46:17.205577: step: 136/529, loss: 0.004855653736740351
2023-01-22 16:46:18.266176: step: 140/529, loss: 0.000464532058686018
2023-01-22 16:46:19.341662: step: 144/529, loss: 0.0036000816617161036
2023-01-22 16:46:20.421425: step: 148/529, loss: 0.009008240886032581
2023-01-22 16:46:21.477312: step: 152/529, loss: 0.002022910863161087
2023-01-22 16:46:22.550178: step: 156/529, loss: 0.01034573744982481
2023-01-22 16:46:23.620028: step: 160/529, loss: 0.01814563199877739
2023-01-22 16:46:24.690697: step: 164/529, loss: 0.00302757415920496
2023-01-22 16:46:25.764611: step: 168/529, loss: 0.010049357078969479
2023-01-22 16:46:26.833773: step: 172/529, loss: 0.011032577604055405
2023-01-22 16:46:27.921208: step: 176/529, loss: 0.006926556583493948
2023-01-22 16:46:28.994743: step: 180/529, loss: 0.004254165105521679
2023-01-22 16:46:30.069209: step: 184/529, loss: 0.0022481554187834263
2023-01-22 16:46:31.124251: step: 188/529, loss: 0.002917242469266057
2023-01-22 16:46:32.191469: step: 192/529, loss: 0.0072310976684093475
2023-01-22 16:46:33.269653: step: 196/529, loss: 0.007072195410728455
2023-01-22 16:46:34.349833: step: 200/529, loss: 0.005174529273062944
2023-01-22 16:46:35.430463: step: 204/529, loss: 0.02271167002618313
2023-01-22 16:46:36.503965: step: 208/529, loss: 0.0003428247000556439
2023-01-22 16:46:37.578030: step: 212/529, loss: 0.004607544280588627
2023-01-22 16:46:38.639334: step: 216/529, loss: 0.008299225009977818
2023-01-22 16:46:39.701688: step: 220/529, loss: 0.017638826742768288
2023-01-22 16:46:40.760022: step: 224/529, loss: 0.001121660228818655
2023-01-22 16:46:41.829172: step: 228/529, loss: 0.0048792557790875435
2023-01-22 16:46:42.895222: step: 232/529, loss: 0.005989342927932739
2023-01-22 16:46:43.955489: step: 236/529, loss: 0.008433006703853607
2023-01-22 16:46:45.018398: step: 240/529, loss: 0.0029687266796827316
2023-01-22 16:46:46.083950: step: 244/529, loss: 0.008188113570213318
2023-01-22 16:46:47.147279: step: 248/529, loss: 0.009621746838092804
2023-01-22 16:46:48.195217: step: 252/529, loss: 0.0005770410061813891
2023-01-22 16:46:49.261753: step: 256/529, loss: 0.0002183005417464301
2023-01-22 16:46:50.349170: step: 260/529, loss: 0.005462479777634144
2023-01-22 16:46:51.421688: step: 264/529, loss: 0.0034609134308993816
2023-01-22 16:46:52.484231: step: 268/529, loss: 0.010720867663621902
2023-01-22 16:46:53.546219: step: 272/529, loss: 0.00046243920223787427
2023-01-22 16:46:54.618803: step: 276/529, loss: 0.0012837282847613096
2023-01-22 16:46:55.685462: step: 280/529, loss: 0.002034065779298544
2023-01-22 16:46:56.744930: step: 284/529, loss: 0.0012776763178408146
2023-01-22 16:46:57.825397: step: 288/529, loss: 0.022065186873078346
2023-01-22 16:46:58.889871: step: 292/529, loss: 0.015671178698539734
2023-01-22 16:46:59.956502: step: 296/529, loss: 0.020309926941990852
2023-01-22 16:47:01.027675: step: 300/529, loss: 0.00212185550481081
2023-01-22 16:47:02.104969: step: 304/529, loss: 0.007124459370970726
2023-01-22 16:47:03.175530: step: 308/529, loss: 0.0035402572248131037
2023-01-22 16:47:04.238534: step: 312/529, loss: 0.0006490561063401401
2023-01-22 16:47:05.300484: step: 316/529, loss: 0.007779272738844156
2023-01-22 16:47:06.348661: step: 320/529, loss: 0.004670790396630764
2023-01-22 16:47:07.422161: step: 324/529, loss: 0.007918543182313442
2023-01-22 16:47:08.501828: step: 328/529, loss: 0.007585111539810896
2023-01-22 16:47:09.566077: step: 332/529, loss: 0.0010087236296385527
2023-01-22 16:47:10.629974: step: 336/529, loss: 0.017342330887913704
2023-01-22 16:47:11.711212: step: 340/529, loss: 0.0034432823304086924
2023-01-22 16:47:12.781347: step: 344/529, loss: 8.939124381868169e-05
2023-01-22 16:47:13.868398: step: 348/529, loss: 0.008808866143226624
2023-01-22 16:47:14.940663: step: 352/529, loss: 0.006594873033463955
2023-01-22 16:47:16.011995: step: 356/529, loss: 0.008746516890823841
2023-01-22 16:47:17.085772: step: 360/529, loss: 0.004234047140926123
2023-01-22 16:47:18.151635: step: 364/529, loss: 0.0005237410077825189
2023-01-22 16:47:19.209836: step: 368/529, loss: 0.001920199254527688
2023-01-22 16:47:20.278720: step: 372/529, loss: 0.013653873465955257
2023-01-22 16:47:21.333436: step: 376/529, loss: 0.0020227963104844093
2023-01-22 16:47:22.414874: step: 380/529, loss: 0.004719252232462168
2023-01-22 16:47:23.501228: step: 384/529, loss: 0.000996257527731359
2023-01-22 16:47:24.576276: step: 388/529, loss: 0.0007212611963041127
2023-01-22 16:47:25.631847: step: 392/529, loss: 0.0006773895001970232
2023-01-22 16:47:26.695957: step: 396/529, loss: 0.0007422130438499153
2023-01-22 16:47:27.765798: step: 400/529, loss: 0.0011392846936360002
2023-01-22 16:47:28.864749: step: 404/529, loss: 0.0002601121086627245
2023-01-22 16:47:29.943179: step: 408/529, loss: 0.0012339414097368717
2023-01-22 16:47:31.008896: step: 412/529, loss: 0.003740661544725299
2023-01-22 16:47:32.088978: step: 416/529, loss: 0.0035948576405644417
2023-01-22 16:47:33.158542: step: 420/529, loss: 0.000956323929131031
2023-01-22 16:47:34.239475: step: 424/529, loss: 0.0931340679526329
2023-01-22 16:47:35.305474: step: 428/529, loss: 0.0009822794236242771
2023-01-22 16:47:36.375849: step: 432/529, loss: 0.00559822004288435
2023-01-22 16:47:37.424886: step: 436/529, loss: 0.00013511610450223088
2023-01-22 16:47:38.486142: step: 440/529, loss: 0.027110062539577484
2023-01-22 16:47:39.547572: step: 444/529, loss: 0.0018125197384506464
2023-01-22 16:47:40.613503: step: 448/529, loss: 0.003616165369749069
2023-01-22 16:47:41.678131: step: 452/529, loss: 0.0017639797879382968
2023-01-22 16:47:42.759588: step: 456/529, loss: 0.0021489739883691072
2023-01-22 16:47:43.862423: step: 460/529, loss: 0.004466381389647722
2023-01-22 16:47:44.939127: step: 464/529, loss: 0.0029205146711319685
2023-01-22 16:47:46.017810: step: 468/529, loss: 0.0064828842878341675
2023-01-22 16:47:47.090248: step: 472/529, loss: 0.008500788360834122
2023-01-22 16:47:48.168473: step: 476/529, loss: 0.008972913958132267
2023-01-22 16:47:49.261826: step: 480/529, loss: 0.002545770490542054
2023-01-22 16:47:50.318901: step: 484/529, loss: 0.0036424424033612013
2023-01-22 16:47:51.405972: step: 488/529, loss: 0.019571540877223015
2023-01-22 16:47:52.478784: step: 492/529, loss: 0.0022102324292063713
2023-01-22 16:47:53.544488: step: 496/529, loss: 0.00277679692953825
2023-01-22 16:47:54.614281: step: 500/529, loss: 0.00978800654411316
2023-01-22 16:47:55.707846: step: 504/529, loss: 0.00016021693591028452
2023-01-22 16:47:56.786733: step: 508/529, loss: 0.0010758526623249054
2023-01-22 16:47:57.857298: step: 512/529, loss: 0.001040567411109805
2023-01-22 16:47:58.932641: step: 516/529, loss: 0.004138750955462456
2023-01-22 16:48:00.007660: step: 520/529, loss: 0.0023467293940484524
2023-01-22 16:48:01.069839: step: 524/529, loss: 0.005997047759592533
2023-01-22 16:48:02.154172: step: 528/529, loss: 0.012271576561033726
2023-01-22 16:48:03.239895: step: 532/529, loss: 0.0021466920152306557
2023-01-22 16:48:04.311954: step: 536/529, loss: 0.0004516357439570129
2023-01-22 16:48:05.389601: step: 540/529, loss: 0.004927820526063442
2023-01-22 16:48:06.451480: step: 544/529, loss: 0.0055756038054823875
2023-01-22 16:48:07.522994: step: 548/529, loss: 0.031241467222571373
2023-01-22 16:48:08.620963: step: 552/529, loss: 0.045850787311792374
2023-01-22 16:48:09.697595: step: 556/529, loss: 0.004398068878799677
2023-01-22 16:48:10.769772: step: 560/529, loss: 0.008083287626504898
2023-01-22 16:48:11.848488: step: 564/529, loss: 0.05309683457016945
2023-01-22 16:48:12.939198: step: 568/529, loss: 0.013529249466955662
2023-01-22 16:48:13.994783: step: 572/529, loss: 0.006030323449522257
2023-01-22 16:48:15.059591: step: 576/529, loss: 0.00357049866579473
2023-01-22 16:48:16.136777: step: 580/529, loss: 0.0033912579528987408
2023-01-22 16:48:17.203277: step: 584/529, loss: 0.0008257452282123268
2023-01-22 16:48:18.282403: step: 588/529, loss: 0.0028539581689983606
2023-01-22 16:48:19.353698: step: 592/529, loss: 0.007156797684729099
2023-01-22 16:48:20.410039: step: 596/529, loss: 0.00024271325673907995
2023-01-22 16:48:21.493887: step: 600/529, loss: 0.0028622762765735388
2023-01-22 16:48:22.557607: step: 604/529, loss: 0.007389379665255547
2023-01-22 16:48:23.613974: step: 608/529, loss: 0.004982942249625921
2023-01-22 16:48:24.666237: step: 612/529, loss: 0.008847521618008614
2023-01-22 16:48:25.739154: step: 616/529, loss: 0.0016525331884622574
2023-01-22 16:48:26.799646: step: 620/529, loss: 0.00505827646702528
2023-01-22 16:48:27.855019: step: 624/529, loss: 0.0021099450532346964
2023-01-22 16:48:28.940263: step: 628/529, loss: 0.004570155870169401
2023-01-22 16:48:30.012599: step: 632/529, loss: 0.00020336614397820085
2023-01-22 16:48:31.083262: step: 636/529, loss: 0.0035085943527519703
2023-01-22 16:48:32.157212: step: 640/529, loss: 0.005054764449596405
2023-01-22 16:48:33.234900: step: 644/529, loss: 0.0014001630479469895
2023-01-22 16:48:34.307619: step: 648/529, loss: 0.00033254941808991134
2023-01-22 16:48:35.378409: step: 652/529, loss: 0.0017622694140300155
2023-01-22 16:48:36.436433: step: 656/529, loss: 0.00035268146893940866
2023-01-22 16:48:37.509483: step: 660/529, loss: 0.010863285511732101
2023-01-22 16:48:38.586904: step: 664/529, loss: 0.0032234960235655308
2023-01-22 16:48:39.664787: step: 668/529, loss: 0.003366815857589245
2023-01-22 16:48:40.727553: step: 672/529, loss: 0.0008061127737164497
2023-01-22 16:48:41.801100: step: 676/529, loss: 0.0006125570507720113
2023-01-22 16:48:42.887515: step: 680/529, loss: 0.023458849638700485
2023-01-22 16:48:43.946503: step: 684/529, loss: 0.0019004769856110215
2023-01-22 16:48:45.028118: step: 688/529, loss: 0.0068727293983101845
2023-01-22 16:48:46.133580: step: 692/529, loss: 0.005446384195238352
2023-01-22 16:48:47.205430: step: 696/529, loss: 0.015116190537810326
2023-01-22 16:48:48.261878: step: 700/529, loss: 0.006550222635269165
2023-01-22 16:48:49.330304: step: 704/529, loss: 0.006168141029775143
2023-01-22 16:48:50.392682: step: 708/529, loss: 0.0056921085342764854
2023-01-22 16:48:51.455673: step: 712/529, loss: 0.010966421104967594
2023-01-22 16:48:52.539896: step: 716/529, loss: 0.003927030600607395
2023-01-22 16:48:53.592110: step: 720/529, loss: 3.948249650420621e-05
2023-01-22 16:48:54.669470: step: 724/529, loss: 0.00038617607788182795
2023-01-22 16:48:55.737777: step: 728/529, loss: 0.011211150325834751
2023-01-22 16:48:56.800831: step: 732/529, loss: 0.006522752344608307
2023-01-22 16:48:57.864073: step: 736/529, loss: 0.006303978152573109
2023-01-22 16:48:58.938190: step: 740/529, loss: 0.0022232637275010347
2023-01-22 16:49:00.021884: step: 744/529, loss: 0.0018562698969617486
2023-01-22 16:49:01.098994: step: 748/529, loss: 0.008830190636217594
2023-01-22 16:49:02.162714: step: 752/529, loss: 0.011314819566905499
2023-01-22 16:49:03.233843: step: 756/529, loss: 0.0017902416875585914
2023-01-22 16:49:04.296462: step: 760/529, loss: 0.0021212357096374035
2023-01-22 16:49:05.367308: step: 764/529, loss: 0.0058141001500189304
2023-01-22 16:49:06.428154: step: 768/529, loss: 0.0006642450462095439
2023-01-22 16:49:07.514534: step: 772/529, loss: 0.042035046964883804
2023-01-22 16:49:08.586717: step: 776/529, loss: 0.003217842895537615
2023-01-22 16:49:09.681369: step: 780/529, loss: 0.0028717005625367165
2023-01-22 16:49:10.756493: step: 784/529, loss: 0.0011830341536551714
2023-01-22 16:49:11.835935: step: 788/529, loss: 0.0028628401923924685
2023-01-22 16:49:12.927730: step: 792/529, loss: 0.0034351679496467113
2023-01-22 16:49:14.001871: step: 796/529, loss: 0.032102711498737335
2023-01-22 16:49:15.073104: step: 800/529, loss: 0.005031494423747063
2023-01-22 16:49:16.145627: step: 804/529, loss: 0.007227532099932432
2023-01-22 16:49:17.234353: step: 808/529, loss: 0.019073989242315292
2023-01-22 16:49:18.308173: step: 812/529, loss: 0.008997561410069466
2023-01-22 16:49:19.371342: step: 816/529, loss: 0.000582393491640687
2023-01-22 16:49:20.436169: step: 820/529, loss: 0.012501739896833897
2023-01-22 16:49:21.526270: step: 824/529, loss: 0.004014948848634958
2023-01-22 16:49:22.598310: step: 828/529, loss: 0.022581838071346283
2023-01-22 16:49:23.695196: step: 832/529, loss: 0.0025139066856354475
2023-01-22 16:49:24.780576: step: 836/529, loss: 0.0029055378399789333
2023-01-22 16:49:25.833480: step: 840/529, loss: 0.009847921319305897
2023-01-22 16:49:26.908092: step: 844/529, loss: 0.004913387354463339
2023-01-22 16:49:27.991510: step: 848/529, loss: 0.010944134555757046
2023-01-22 16:49:29.064122: step: 852/529, loss: 0.01431617233902216
2023-01-22 16:49:30.138423: step: 856/529, loss: 0.006244725547730923
2023-01-22 16:49:31.197399: step: 860/529, loss: 0.003779197810217738
2023-01-22 16:49:32.256157: step: 864/529, loss: 0.01293051429092884
2023-01-22 16:49:33.327223: step: 868/529, loss: 0.008084164932370186
2023-01-22 16:49:34.393818: step: 872/529, loss: 0.0003463590401224792
2023-01-22 16:49:35.466259: step: 876/529, loss: 0.0012960982276126742
2023-01-22 16:49:36.524797: step: 880/529, loss: 0.0007494304445572197
2023-01-22 16:49:37.611719: step: 884/529, loss: 0.012735312804579735
2023-01-22 16:49:38.696998: step: 888/529, loss: 0.00246731610968709
2023-01-22 16:49:39.773715: step: 892/529, loss: 0.0024457420222461224
2023-01-22 16:49:40.840635: step: 896/529, loss: 0.005838751792907715
2023-01-22 16:49:41.944783: step: 900/529, loss: 0.0006208329577930272
2023-01-22 16:49:43.036874: step: 904/529, loss: 0.008349798619747162
2023-01-22 16:49:44.148836: step: 908/529, loss: 0.0015658786287531257
2023-01-22 16:49:45.224632: step: 912/529, loss: 0.0029360074549913406
2023-01-22 16:49:46.308744: step: 916/529, loss: 0.0030074878595769405
2023-01-22 16:49:47.385843: step: 920/529, loss: 0.008125103078782558
2023-01-22 16:49:48.457591: step: 924/529, loss: 0.0003534247516654432
2023-01-22 16:49:49.545646: step: 928/529, loss: 0.005403808783739805
2023-01-22 16:49:50.608307: step: 932/529, loss: 0.0034687230363488197
2023-01-22 16:49:51.684887: step: 936/529, loss: 0.003291774308308959
2023-01-22 16:49:52.776200: step: 940/529, loss: 0.0038656878750771284
2023-01-22 16:49:53.842673: step: 944/529, loss: 0.00010822190961334854
2023-01-22 16:49:54.926190: step: 948/529, loss: 0.0027201964985579252
2023-01-22 16:49:56.015196: step: 952/529, loss: 0.014513666741549969
2023-01-22 16:49:57.100896: step: 956/529, loss: 0.0007798672304488719
2023-01-22 16:49:58.181199: step: 960/529, loss: 0.023821255192160606
2023-01-22 16:49:59.303239: step: 964/529, loss: 0.004256630316376686
2023-01-22 16:50:00.391852: step: 968/529, loss: 0.004839982837438583
2023-01-22 16:50:01.463410: step: 972/529, loss: 0.00023812487779650837
2023-01-22 16:50:02.553130: step: 976/529, loss: 0.005690691061317921
2023-01-22 16:50:03.633356: step: 980/529, loss: 0.0017980728298425674
2023-01-22 16:50:04.723504: step: 984/529, loss: 0.003909555729478598
2023-01-22 16:50:05.798135: step: 988/529, loss: 0.006293295416980982
2023-01-22 16:50:06.883688: step: 992/529, loss: 0.005559058859944344
2023-01-22 16:50:07.973842: step: 996/529, loss: 0.003048380371183157
2023-01-22 16:50:09.057693: step: 1000/529, loss: 0.003193227807059884
2023-01-22 16:50:10.141358: step: 1004/529, loss: 0.00016463841893710196
2023-01-22 16:50:11.220383: step: 1008/529, loss: 0.010374438017606735
2023-01-22 16:50:12.319751: step: 1012/529, loss: 0.0008038009400479496
2023-01-22 16:50:13.395820: step: 1016/529, loss: 0.0033988088835030794
2023-01-22 16:50:14.476080: step: 1020/529, loss: 0.0026192169170826674
2023-01-22 16:50:15.547779: step: 1024/529, loss: 0.016734879463911057
2023-01-22 16:50:16.608629: step: 1028/529, loss: 0.0007094732718542218
2023-01-22 16:50:17.690256: step: 1032/529, loss: 0.0018715693149715662
2023-01-22 16:50:18.781967: step: 1036/529, loss: 0.003840759629383683
2023-01-22 16:50:19.883097: step: 1040/529, loss: 0.009966296143829823
2023-01-22 16:50:20.972555: step: 1044/529, loss: 0.015022620558738708
2023-01-22 16:50:22.044511: step: 1048/529, loss: 0.002781221177428961
2023-01-22 16:50:23.125864: step: 1052/529, loss: 0.007517424877732992
2023-01-22 16:50:24.208392: step: 1056/529, loss: 0.000453771383035928
2023-01-22 16:50:25.294709: step: 1060/529, loss: 0.004217195324599743
2023-01-22 16:50:26.376107: step: 1064/529, loss: 0.002011943841353059
2023-01-22 16:50:27.469595: step: 1068/529, loss: 0.002803136594593525
2023-01-22 16:50:28.539461: step: 1072/529, loss: 0.0002057022211374715
2023-01-22 16:50:29.627996: step: 1076/529, loss: 0.008079002611339092
2023-01-22 16:50:30.701485: step: 1080/529, loss: 0.004181064199656248
2023-01-22 16:50:31.780983: step: 1084/529, loss: 0.00019540874927770346
2023-01-22 16:50:32.869683: step: 1088/529, loss: 0.00459140632301569
2023-01-22 16:50:33.944479: step: 1092/529, loss: 0.0012845245655626059
2023-01-22 16:50:35.027281: step: 1096/529, loss: 0.0027654164005070925
2023-01-22 16:50:36.101805: step: 1100/529, loss: 0.004545701202005148
2023-01-22 16:50:37.164080: step: 1104/529, loss: 0.0
2023-01-22 16:50:38.258635: step: 1108/529, loss: 0.006438740994781256
2023-01-22 16:50:39.341229: step: 1112/529, loss: 0.012592857703566551
2023-01-22 16:50:40.418186: step: 1116/529, loss: 0.001085448544472456
2023-01-22 16:50:41.494629: step: 1120/529, loss: 9.162333299173042e-05
2023-01-22 16:50:42.599434: step: 1124/529, loss: 0.001993956044316292
2023-01-22 16:50:43.677304: step: 1128/529, loss: 0.014985653571784496
2023-01-22 16:50:44.776860: step: 1132/529, loss: 0.007238594349473715
2023-01-22 16:50:45.876156: step: 1136/529, loss: 0.0006948950467631221
2023-01-22 16:50:46.955153: step: 1140/529, loss: 0.0012186398962512612
2023-01-22 16:50:48.041452: step: 1144/529, loss: 0.0074728853069245815
2023-01-22 16:50:49.127602: step: 1148/529, loss: 0.005998431704938412
2023-01-22 16:50:50.205465: step: 1152/529, loss: 0.017919017001986504
2023-01-22 16:50:51.294239: step: 1156/529, loss: 0.0010136482305824757
2023-01-22 16:50:52.371808: step: 1160/529, loss: 0.00255751283839345
2023-01-22 16:50:53.459663: step: 1164/529, loss: 0.00038443991797976196
2023-01-22 16:50:54.562586: step: 1168/529, loss: 0.0010660532861948013
2023-01-22 16:50:55.634372: step: 1172/529, loss: 0.004924565088003874
2023-01-22 16:50:56.723122: step: 1176/529, loss: 0.001071522245183587
2023-01-22 16:50:57.805852: step: 1180/529, loss: 0.0015187327517196536
2023-01-22 16:50:58.886711: step: 1184/529, loss: 0.00300554558634758
2023-01-22 16:50:59.973773: step: 1188/529, loss: 0.000765617354772985
2023-01-22 16:51:01.045593: step: 1192/529, loss: 0.0062858047895133495
2023-01-22 16:51:02.127050: step: 1196/529, loss: 1.7848709831014276e-05
2023-01-22 16:51:03.201539: step: 1200/529, loss: 0.013907291926443577
2023-01-22 16:51:04.274185: step: 1204/529, loss: 0.009092290885746479
2023-01-22 16:51:05.354429: step: 1208/529, loss: 0.008984521962702274
2023-01-22 16:51:06.437734: step: 1212/529, loss: 0.0009734661434777081
2023-01-22 16:51:07.518962: step: 1216/529, loss: 0.0009463827009312809
2023-01-22 16:51:08.596160: step: 1220/529, loss: 0.0012541133910417557
2023-01-22 16:51:09.685581: step: 1224/529, loss: 0.0026158480904996395
2023-01-22 16:51:10.757820: step: 1228/529, loss: 0.003346783807501197
2023-01-22 16:51:11.832173: step: 1232/529, loss: 0.002754059387370944
2023-01-22 16:51:12.932149: step: 1236/529, loss: 0.0016162253450602293
2023-01-22 16:51:14.016856: step: 1240/529, loss: 0.012374963611364365
2023-01-22 16:51:15.100025: step: 1244/529, loss: 0.00817466527223587
2023-01-22 16:51:16.190846: step: 1248/529, loss: 0.009739483706653118
2023-01-22 16:51:17.266661: step: 1252/529, loss: 0.002772791311144829
2023-01-22 16:51:18.342588: step: 1256/529, loss: 0.004882731940597296
2023-01-22 16:51:19.412692: step: 1260/529, loss: 0.0003424373862799257
2023-01-22 16:51:20.492281: step: 1264/529, loss: 0.002785620978102088
2023-01-22 16:51:21.581010: step: 1268/529, loss: 0.01190499309450388
2023-01-22 16:51:22.674523: step: 1272/529, loss: 0.0028960874769836664
2023-01-22 16:51:23.764288: step: 1276/529, loss: 0.001876495429314673
2023-01-22 16:51:24.856204: step: 1280/529, loss: 0.0038968604058027267
2023-01-22 16:51:25.930122: step: 1284/529, loss: 0.0014473608462139964
2023-01-22 16:51:27.015138: step: 1288/529, loss: 0.003630367573350668
2023-01-22 16:51:28.085377: step: 1292/529, loss: 0.0012406966416165233
2023-01-22 16:51:29.157524: step: 1296/529, loss: 0.0013465335359796882
2023-01-22 16:51:30.230167: step: 1300/529, loss: 0.006871648132801056
2023-01-22 16:51:31.316903: step: 1304/529, loss: 0.0028659726958721876
2023-01-22 16:51:32.404852: step: 1308/529, loss: 0.004046380519866943
2023-01-22 16:51:33.495023: step: 1312/529, loss: 0.025357460603117943
2023-01-22 16:51:34.570930: step: 1316/529, loss: 0.004396599717438221
2023-01-22 16:51:35.643903: step: 1320/529, loss: 0.006586793344467878
2023-01-22 16:51:36.718967: step: 1324/529, loss: 0.00811008084565401
2023-01-22 16:51:37.797511: step: 1328/529, loss: 0.002518047345802188
2023-01-22 16:51:38.859601: step: 1332/529, loss: 0.0019351443042978644
2023-01-22 16:51:39.933384: step: 1336/529, loss: 0.0009093194385059178
2023-01-22 16:51:41.012396: step: 1340/529, loss: 0.004282132722437382
2023-01-22 16:51:42.085102: step: 1344/529, loss: 0.0003690617741085589
2023-01-22 16:51:43.182411: step: 1348/529, loss: 0.003928898833692074
2023-01-22 16:51:44.255992: step: 1352/529, loss: 0.003199152648448944
2023-01-22 16:51:45.343518: step: 1356/529, loss: 0.003624142147600651
2023-01-22 16:51:46.407377: step: 1360/529, loss: 0.0029232895467430353
2023-01-22 16:51:47.497386: step: 1364/529, loss: 0.003160163527354598
2023-01-22 16:51:48.578256: step: 1368/529, loss: 0.018363306298851967
2023-01-22 16:51:49.652284: step: 1372/529, loss: 0.014122958295047283
2023-01-22 16:51:50.717098: step: 1376/529, loss: 0.0013863503700122237
2023-01-22 16:51:51.799882: step: 1380/529, loss: 0.005783788859844208
2023-01-22 16:51:52.887128: step: 1384/529, loss: 0.007065037731081247
2023-01-22 16:51:53.940270: step: 1388/529, loss: 0.0008020845707505941
2023-01-22 16:51:55.000390: step: 1392/529, loss: 0.000981620978564024
2023-01-22 16:51:56.075609: step: 1396/529, loss: 0.0009956590365618467
2023-01-22 16:51:57.168601: step: 1400/529, loss: 0.003136741230264306
2023-01-22 16:51:58.257329: step: 1404/529, loss: 0.0014253241242840886
2023-01-22 16:51:59.318718: step: 1408/529, loss: 0.0011652220273390412
2023-01-22 16:52:00.383059: step: 1412/529, loss: 0.001703666872344911
2023-01-22 16:52:01.448605: step: 1416/529, loss: 0.006479042582213879
2023-01-22 16:52:02.523815: step: 1420/529, loss: 0.004729365464299917
2023-01-22 16:52:03.611488: step: 1424/529, loss: 0.002865213667973876
2023-01-22 16:52:04.714442: step: 1428/529, loss: 0.0038078895304352045
2023-01-22 16:52:05.784137: step: 1432/529, loss: 0.001645090989768505
2023-01-22 16:52:06.842119: step: 1436/529, loss: 0.0028535800520330667
2023-01-22 16:52:07.933361: step: 1440/529, loss: 0.001665384159423411
2023-01-22 16:52:09.001250: step: 1444/529, loss: 0.018140381202101707
2023-01-22 16:52:10.067566: step: 1448/529, loss: 0.0005168024217709899
2023-01-22 16:52:11.138970: step: 1452/529, loss: 0.001085174735635519
2023-01-22 16:52:12.196753: step: 1456/529, loss: 0.0014501296682283282
2023-01-22 16:52:13.249877: step: 1460/529, loss: 0.027862543240189552
2023-01-22 16:52:14.332663: step: 1464/529, loss: 0.011404496617615223
2023-01-22 16:52:15.393805: step: 1468/529, loss: 0.0020065598655492067
2023-01-22 16:52:16.481554: step: 1472/529, loss: 0.001588613260537386
2023-01-22 16:52:17.558711: step: 1476/529, loss: 0.0068007418885827065
2023-01-22 16:52:18.637771: step: 1480/529, loss: 8.738425822230056e-05
2023-01-22 16:52:19.713767: step: 1484/529, loss: 0.013928217813372612
2023-01-22 16:52:20.771374: step: 1488/529, loss: 0.0001934495521709323
2023-01-22 16:52:21.847239: step: 1492/529, loss: 0.008348044008016586
2023-01-22 16:52:22.926483: step: 1496/529, loss: 0.013856679201126099
2023-01-22 16:52:23.999660: step: 1500/529, loss: 0.0014986825408414006
2023-01-22 16:52:25.062337: step: 1504/529, loss: 0.00015405072190333158
2023-01-22 16:52:26.132081: step: 1508/529, loss: 0.007739780005067587
2023-01-22 16:52:27.198823: step: 1512/529, loss: 0.0028329347260296345
2023-01-22 16:52:28.265653: step: 1516/529, loss: 0.0051941354759037495
2023-01-22 16:52:29.343149: step: 1520/529, loss: 0.010268112644553185
2023-01-22 16:52:30.421125: step: 1524/529, loss: 0.006983105558902025
2023-01-22 16:52:31.488554: step: 1528/529, loss: 0.0009511972893960774
2023-01-22 16:52:32.560666: step: 1532/529, loss: 0.0038837611209601164
2023-01-22 16:52:33.636721: step: 1536/529, loss: 0.002611966570839286
2023-01-22 16:52:34.714041: step: 1540/529, loss: 0.02525462582707405
2023-01-22 16:52:35.800620: step: 1544/529, loss: 0.005396829452365637
2023-01-22 16:52:36.859482: step: 1548/529, loss: 0.010904856957495213
2023-01-22 16:52:37.924767: step: 1552/529, loss: 0.007915393449366093
2023-01-22 16:52:38.994046: step: 1556/529, loss: 0.002802344737574458
2023-01-22 16:52:40.075741: step: 1560/529, loss: 0.006745410617440939
2023-01-22 16:52:41.156556: step: 1564/529, loss: 0.0031769820488989353
2023-01-22 16:52:42.206991: step: 1568/529, loss: 0.0
2023-01-22 16:52:43.270282: step: 1572/529, loss: 0.0027002287097275257
2023-01-22 16:52:44.352599: step: 1576/529, loss: 5.949012847850099e-05
2023-01-22 16:52:45.416748: step: 1580/529, loss: 0.012963945977389812
2023-01-22 16:52:46.477186: step: 1584/529, loss: 0.006360412575304508
2023-01-22 16:52:47.550182: step: 1588/529, loss: 0.002343586878851056
2023-01-22 16:52:48.624422: step: 1592/529, loss: 0.002032279735431075
2023-01-22 16:52:49.690319: step: 1596/529, loss: 0.0016265364829450846
2023-01-22 16:52:50.764158: step: 1600/529, loss: 0.011014615185558796
2023-01-22 16:52:51.828485: step: 1604/529, loss: 0.0033035501837730408
2023-01-22 16:52:52.895794: step: 1608/529, loss: 0.0005296764429658651
2023-01-22 16:52:53.965422: step: 1612/529, loss: 0.008404571563005447
2023-01-22 16:52:55.029133: step: 1616/529, loss: 0.011015924625098705
2023-01-22 16:52:56.086254: step: 1620/529, loss: 0.0012217392213642597
2023-01-22 16:52:57.157831: step: 1624/529, loss: 0.00406935578212142
2023-01-22 16:52:58.217093: step: 1628/529, loss: 0.006565426010638475
2023-01-22 16:52:59.273652: step: 1632/529, loss: 0.0009572013514116406
2023-01-22 16:53:00.357933: step: 1636/529, loss: 0.009375134482979774
2023-01-22 16:53:01.422571: step: 1640/529, loss: 0.015614711679518223
2023-01-22 16:53:02.505623: step: 1644/529, loss: 0.002346860943362117
2023-01-22 16:53:03.577635: step: 1648/529, loss: 0.0029121439438313246
2023-01-22 16:53:04.654511: step: 1652/529, loss: 0.001958949724212289
2023-01-22 16:53:05.726502: step: 1656/529, loss: 0.0004589745949488133
2023-01-22 16:53:06.790182: step: 1660/529, loss: 0.0029409106355160475
2023-01-22 16:53:07.861482: step: 1664/529, loss: 0.014715256169438362
2023-01-22 16:53:08.933439: step: 1668/529, loss: 0.00866536982357502
2023-01-22 16:53:10.013356: step: 1672/529, loss: 0.0025762272998690605
2023-01-22 16:53:11.091325: step: 1676/529, loss: 0.004894184414297342
2023-01-22 16:53:12.162056: step: 1680/529, loss: 0.01025621872395277
2023-01-22 16:53:13.225571: step: 1684/529, loss: 0.0006695187767036259
2023-01-22 16:53:14.292591: step: 1688/529, loss: 0.004675024189054966
2023-01-22 16:53:15.372395: step: 1692/529, loss: 0.00014494657807517797
2023-01-22 16:53:16.431330: step: 1696/529, loss: 0.000748831604141742
2023-01-22 16:53:17.501138: step: 1700/529, loss: 0.017094817012548447
2023-01-22 16:53:18.566181: step: 1704/529, loss: 0.01809392310678959
2023-01-22 16:53:19.631816: step: 1708/529, loss: 0.006069628056138754
2023-01-22 16:53:20.694330: step: 1712/529, loss: 0.003959669265896082
2023-01-22 16:53:21.775016: step: 1716/529, loss: 0.0005402990500442684
2023-01-22 16:53:22.864927: step: 1720/529, loss: 0.0004691762151196599
2023-01-22 16:53:23.930506: step: 1724/529, loss: 0.00016597381909377873
2023-01-22 16:53:25.027680: step: 1728/529, loss: 0.0009870573412626982
2023-01-22 16:53:26.109999: step: 1732/529, loss: 0.005165559239685535
2023-01-22 16:53:27.191171: step: 1736/529, loss: 0.002001678105443716
2023-01-22 16:53:28.279221: step: 1740/529, loss: 0.002589354757219553
2023-01-22 16:53:29.352470: step: 1744/529, loss: 0.001608711900189519
2023-01-22 16:53:30.441222: step: 1748/529, loss: 0.007137427106499672
2023-01-22 16:53:31.508652: step: 1752/529, loss: 0.012139768339693546
2023-01-22 16:53:32.583322: step: 1756/529, loss: 0.0017902354011312127
2023-01-22 16:53:33.646788: step: 1760/529, loss: 0.007811323739588261
2023-01-22 16:53:34.708857: step: 1764/529, loss: 0.013736235909163952
2023-01-22 16:53:35.781088: step: 1768/529, loss: 0.0160172488540411
2023-01-22 16:53:36.870621: step: 1772/529, loss: 0.009667756035923958
2023-01-22 16:53:37.938001: step: 1776/529, loss: 0.001788889872841537
2023-01-22 16:53:39.009842: step: 1780/529, loss: 0.0008035851642489433
2023-01-22 16:53:40.091942: step: 1784/529, loss: 0.00268270680680871
2023-01-22 16:53:41.159325: step: 1788/529, loss: 0.0014193312963470817
2023-01-22 16:53:42.237440: step: 1792/529, loss: 0.007340143900364637
2023-01-22 16:53:43.339909: step: 1796/529, loss: 0.0005057966918684542
2023-01-22 16:53:44.401009: step: 1800/529, loss: 0.004738260991871357
2023-01-22 16:53:45.484801: step: 1804/529, loss: 0.0031953398138284683
2023-01-22 16:53:46.549033: step: 1808/529, loss: 0.00093284179456532
2023-01-22 16:53:47.628475: step: 1812/529, loss: 0.0005930204642936587
2023-01-22 16:53:48.696151: step: 1816/529, loss: 0.008809304796159267
2023-01-22 16:53:49.768154: step: 1820/529, loss: 0.013269947841763496
2023-01-22 16:53:50.839763: step: 1824/529, loss: 0.0014831337612122297
2023-01-22 16:53:51.908916: step: 1828/529, loss: 0.0037388396449387074
2023-01-22 16:53:52.977500: step: 1832/529, loss: 0.003756570862606168
2023-01-22 16:53:54.034125: step: 1836/529, loss: 0.008058917708694935
2023-01-22 16:53:55.091072: step: 1840/529, loss: 0.006774854380637407
2023-01-22 16:53:56.174978: step: 1844/529, loss: 0.0005413430044427514
2023-01-22 16:53:57.255616: step: 1848/529, loss: 0.009238917380571365
2023-01-22 16:53:58.346378: step: 1852/529, loss: 0.005848722532391548
2023-01-22 16:53:59.400273: step: 1856/529, loss: 0.004729467444121838
2023-01-22 16:54:00.466270: step: 1860/529, loss: 0.016204742714762688
2023-01-22 16:54:01.528281: step: 1864/529, loss: 0.008855198509991169
2023-01-22 16:54:02.611461: step: 1868/529, loss: 0.11497065424919128
2023-01-22 16:54:03.678358: step: 1872/529, loss: 0.006695417687296867
2023-01-22 16:54:04.736962: step: 1876/529, loss: 0.0015388191677629948
2023-01-22 16:54:05.788318: step: 1880/529, loss: 0.003265910316258669
2023-01-22 16:54:06.861972: step: 1884/529, loss: 0.007440519984811544
2023-01-22 16:54:07.930245: step: 1888/529, loss: 0.006220884621143341
2023-01-22 16:54:09.016919: step: 1892/529, loss: 0.005961087066680193
2023-01-22 16:54:10.098153: step: 1896/529, loss: 0.0016540618380531669
2023-01-22 16:54:11.171178: step: 1900/529, loss: 0.0011557937832549214
2023-01-22 16:54:12.241256: step: 1904/529, loss: 0.00114920805208385
2023-01-22 16:54:13.341958: step: 1908/529, loss: 0.0007330832304432988
2023-01-22 16:54:14.401250: step: 1912/529, loss: 0.0055529153905808926
2023-01-22 16:54:15.484658: step: 1916/529, loss: 0.002856532344594598
2023-01-22 16:54:16.562583: step: 1920/529, loss: 0.0001175344514194876
2023-01-22 16:54:17.646466: step: 1924/529, loss: 0.003297254675999284
2023-01-22 16:54:18.713488: step: 1928/529, loss: 0.006175698712468147
2023-01-22 16:54:19.777360: step: 1932/529, loss: 0.00023109393077902496
2023-01-22 16:54:20.864502: step: 1936/529, loss: 0.002368801971897483
2023-01-22 16:54:21.944169: step: 1940/529, loss: 0.009190341457724571
2023-01-22 16:54:23.025209: step: 1944/529, loss: 0.0017559340922161937
2023-01-22 16:54:24.103958: step: 1948/529, loss: 0.033422596752643585
2023-01-22 16:54:25.196675: step: 1952/529, loss: 0.00014490677858702838
2023-01-22 16:54:26.259424: step: 1956/529, loss: 0.002352301497012377
2023-01-22 16:54:27.320761: step: 1960/529, loss: 0.010715760290622711
2023-01-22 16:54:28.384797: step: 1964/529, loss: 0.0015514919068664312
2023-01-22 16:54:29.458847: step: 1968/529, loss: 0.007033297326415777
2023-01-22 16:54:30.526924: step: 1972/529, loss: 0.00013565286644734442
2023-01-22 16:54:31.598923: step: 1976/529, loss: 0.0035234945826232433
2023-01-22 16:54:32.662661: step: 1980/529, loss: 0.010246050544083118
2023-01-22 16:54:33.736894: step: 1984/529, loss: 0.004345087334513664
2023-01-22 16:54:34.796958: step: 1988/529, loss: 0.0008381556835956872
2023-01-22 16:54:35.864594: step: 1992/529, loss: 0.0020852491725236177
2023-01-22 16:54:36.932052: step: 1996/529, loss: 0.007938524708151817
2023-01-22 16:54:37.991116: step: 2000/529, loss: 0.008011175319552422
2023-01-22 16:54:39.048825: step: 2004/529, loss: 0.02062593586742878
2023-01-22 16:54:40.129638: step: 2008/529, loss: 1.4936611478333361e-05
2023-01-22 16:54:41.199893: step: 2012/529, loss: 0.016349783167243004
2023-01-22 16:54:42.267801: step: 2016/529, loss: 0.00047937972703948617
2023-01-22 16:54:43.353249: step: 2020/529, loss: 0.008948408998548985
2023-01-22 16:54:44.429303: step: 2024/529, loss: 0.007444143295288086
2023-01-22 16:54:45.485734: step: 2028/529, loss: 0.0017338474281132221
2023-01-22 16:54:46.548289: step: 2032/529, loss: 0.0037951997946947813
2023-01-22 16:54:47.618300: step: 2036/529, loss: 0.007294212002307177
2023-01-22 16:54:48.702655: step: 2040/529, loss: 0.010114915668964386
2023-01-22 16:54:49.781122: step: 2044/529, loss: 0.007748943753540516
2023-01-22 16:54:50.850843: step: 2048/529, loss: 0.0004019513726234436
2023-01-22 16:54:51.928744: step: 2052/529, loss: 0.0006413411465473473
2023-01-22 16:54:52.991929: step: 2056/529, loss: 0.010674230754375458
2023-01-22 16:54:54.070484: step: 2060/529, loss: 0.016643160954117775
2023-01-22 16:54:55.129625: step: 2064/529, loss: 0.007731199264526367
2023-01-22 16:54:56.198199: step: 2068/529, loss: 0.00734926201403141
2023-01-22 16:54:57.269657: step: 2072/529, loss: 0.0012264309916645288
2023-01-22 16:54:58.338832: step: 2076/529, loss: 0.00308642047457397
2023-01-22 16:54:59.412540: step: 2080/529, loss: 4.6565954647803665e-08
2023-01-22 16:55:00.488307: step: 2084/529, loss: 0.001504861400462687
2023-01-22 16:55:01.567459: step: 2088/529, loss: 0.0007517228950746357
2023-01-22 16:55:02.635581: step: 2092/529, loss: 0.006435941904783249
2023-01-22 16:55:03.686230: step: 2096/529, loss: 0.00358761684037745
2023-01-22 16:55:04.741363: step: 2100/529, loss: 0.005381579510867596
2023-01-22 16:55:05.814974: step: 2104/529, loss: 0.013732613995671272
2023-01-22 16:55:06.866759: step: 2108/529, loss: 0.0004469332052394748
2023-01-22 16:55:07.914086: step: 2112/529, loss: 0.003604160388931632
2023-01-22 16:55:08.972550: step: 2116/529, loss: 0.0002558234555181116
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31902920962199316, 'r': 0.35232447817836815, 'f1': 0.3348512173128945}, 'combined': 0.24673247591476438, 'stategy': 1, 'epoch': 10}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3090057711410143, 'r': 0.3078697205118194, 'f1': 0.30843669973928134}, 'combined': 0.20136281951890905, 'stategy': 1, 'epoch': 10}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3191614583333333, 'r': 0.363371679316888, 'f1': 0.3398347382431233}, 'combined': 0.25040454396861717, 'stategy': 1, 'epoch': 10}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33341004573001365, 'r': 0.31257191787188776, 'f1': 0.3226548829645293}, 'combined': 0.21064515675404505, 'stategy': 1, 'epoch': 10}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31509533898305087, 'r': 0.35276328273244784, 'f1': 0.33286705461056404}, 'combined': 0.24527046129199453, 'stategy': 1, 'epoch': 10}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3240526428556958, 'r': 0.3219696598437675, 'f1': 0.32300779324722506}, 'combined': 0.21087555414067544, 'stategy': 1, 'epoch': 10}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 10}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 10}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 10}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3191614583333333, 'r': 0.363371679316888, 'f1': 0.3398347382431233}, 'combined': 0.25040454396861717, 'stategy': 1, 'epoch': 10}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33341004573001365, 'r': 0.31257191787188776, 'f1': 0.3226548829645293}, 'combined': 0.21064515675404505, 'stategy': 1, 'epoch': 10}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 10}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 16:57:54.727141: step: 4/529, loss: 0.002799802692607045
2023-01-22 16:57:55.765856: step: 8/529, loss: 0.00098445825278759
2023-01-22 16:57:56.861678: step: 12/529, loss: 0.0031236563809216022
2023-01-22 16:57:57.926689: step: 16/529, loss: 0.003714518388733268
2023-01-22 16:57:58.993958: step: 20/529, loss: 0.004137910436838865
2023-01-22 16:58:00.077973: step: 24/529, loss: 0.001822648337110877
2023-01-22 16:58:01.127025: step: 28/529, loss: 0.0005741449422203004
2023-01-22 16:58:02.189868: step: 32/529, loss: 0.022738302126526833
2023-01-22 16:58:03.264908: step: 36/529, loss: 0.0022163265384733677
2023-01-22 16:58:04.335994: step: 40/529, loss: 0.005905527621507645
2023-01-22 16:58:05.400177: step: 44/529, loss: 0.007161538116633892
2023-01-22 16:58:06.475090: step: 48/529, loss: 0.001817191019654274
2023-01-22 16:58:07.556901: step: 52/529, loss: 0.005079301539808512
2023-01-22 16:58:08.628603: step: 56/529, loss: 0.014951029792428017
2023-01-22 16:58:09.693887: step: 60/529, loss: 0.01486099325120449
2023-01-22 16:58:10.751715: step: 64/529, loss: 0.004643063992261887
2023-01-22 16:58:11.835326: step: 68/529, loss: 0.001184926019050181
2023-01-22 16:58:12.890748: step: 72/529, loss: 0.0004509768623393029
2023-01-22 16:58:13.937130: step: 76/529, loss: 0.0016595391789451241
2023-01-22 16:58:15.003798: step: 80/529, loss: 0.0037661821115761995
2023-01-22 16:58:16.067296: step: 84/529, loss: 0.010828875005245209
2023-01-22 16:58:17.136082: step: 88/529, loss: 0.004606639500707388
2023-01-22 16:58:18.221011: step: 92/529, loss: 0.00365068344399333
2023-01-22 16:58:19.291511: step: 96/529, loss: 0.007801222149282694
2023-01-22 16:58:20.343200: step: 100/529, loss: 0.0074273813515901566
2023-01-22 16:58:21.422256: step: 104/529, loss: 0.0007517495541833341
2023-01-22 16:58:22.478840: step: 108/529, loss: 0.006015571765601635
2023-01-22 16:58:23.538979: step: 112/529, loss: 0.0025424775667488575
2023-01-22 16:58:24.603458: step: 116/529, loss: 0.0035228494089096785
2023-01-22 16:58:25.680246: step: 120/529, loss: 0.0049491506069898605
2023-01-22 16:58:26.734337: step: 124/529, loss: 0.0036107334308326244
2023-01-22 16:58:27.805596: step: 128/529, loss: 0.0030216840095818043
2023-01-22 16:58:28.872900: step: 132/529, loss: 0.002300210762768984
2023-01-22 16:58:29.926756: step: 136/529, loss: 0.004470197018235922
2023-01-22 16:58:31.002708: step: 140/529, loss: 0.0037267478182911873
2023-01-22 16:58:32.071736: step: 144/529, loss: 0.0051951101049780846
2023-01-22 16:58:33.126869: step: 148/529, loss: 0.004832123871892691
2023-01-22 16:58:34.176783: step: 152/529, loss: 0.0027162693440914154
2023-01-22 16:58:35.244333: step: 156/529, loss: 0.00048536615213379264
2023-01-22 16:58:36.303839: step: 160/529, loss: 0.003793970914557576
2023-01-22 16:58:37.380561: step: 164/529, loss: 0.006952115800231695
2023-01-22 16:58:38.467360: step: 168/529, loss: 0.0019066323293372989
2023-01-22 16:58:39.537137: step: 172/529, loss: 9.22923645703122e-05
2023-01-22 16:58:40.607046: step: 176/529, loss: 0.003931107930839062
2023-01-22 16:58:41.676674: step: 180/529, loss: 0.006486900616437197
2023-01-22 16:58:42.741221: step: 184/529, loss: 0.0009289022418670356
2023-01-22 16:58:43.823989: step: 188/529, loss: 0.0030753996688872576
2023-01-22 16:58:44.895917: step: 192/529, loss: 0.0028130351565778255
2023-01-22 16:58:45.986365: step: 196/529, loss: 0.006381553132086992
2023-01-22 16:58:47.059453: step: 200/529, loss: 4.228491889080033e-05
2023-01-22 16:58:48.125333: step: 204/529, loss: 0.01762462593615055
2023-01-22 16:58:49.198240: step: 208/529, loss: 3.691194433486089e-05
2023-01-22 16:58:50.253230: step: 212/529, loss: 0.0
2023-01-22 16:58:51.307148: step: 216/529, loss: 0.0024418069515377283
2023-01-22 16:58:52.376027: step: 220/529, loss: 0.003514789044857025
2023-01-22 16:58:53.445077: step: 224/529, loss: 0.0004902156651951373
2023-01-22 16:58:54.504365: step: 228/529, loss: 0.006283532362431288
2023-01-22 16:58:55.556469: step: 232/529, loss: 0.0024360523093491793
2023-01-22 16:58:56.628272: step: 236/529, loss: 0.003864196129143238
2023-01-22 16:58:57.704945: step: 240/529, loss: 0.00010936384205706418
2023-01-22 16:58:58.780278: step: 244/529, loss: 0.004691033158451319
2023-01-22 16:58:59.855106: step: 248/529, loss: 0.0032178163528442383
2023-01-22 16:59:00.924510: step: 252/529, loss: 0.003401032416149974
2023-01-22 16:59:01.995134: step: 256/529, loss: 0.013381686992943287
2023-01-22 16:59:03.058320: step: 260/529, loss: 0.002689080312848091
2023-01-22 16:59:04.133309: step: 264/529, loss: 0.0006650852737948298
2023-01-22 16:59:05.197545: step: 268/529, loss: 0.0049430374056100845
2023-01-22 16:59:06.262928: step: 272/529, loss: 0.005930429790169001
2023-01-22 16:59:07.357378: step: 276/529, loss: 0.0051653701812028885
2023-01-22 16:59:08.428505: step: 280/529, loss: 0.00038762151962146163
2023-01-22 16:59:09.496767: step: 284/529, loss: 0.00020901841344311833
2023-01-22 16:59:10.579523: step: 288/529, loss: 0.01706971600651741
2023-01-22 16:59:11.652899: step: 292/529, loss: 0.0012292361352592707
2023-01-22 16:59:12.741666: step: 296/529, loss: 0.006169318687170744
2023-01-22 16:59:13.822135: step: 300/529, loss: 0.000375593634089455
2023-01-22 16:59:14.894783: step: 304/529, loss: 0.0010701855644583702
2023-01-22 16:59:15.970087: step: 308/529, loss: 0.0005013360059820116
2023-01-22 16:59:17.021882: step: 312/529, loss: 0.0016539142234250903
2023-01-22 16:59:18.112218: step: 316/529, loss: 0.0019989381544291973
2023-01-22 16:59:19.185181: step: 320/529, loss: 0.0036413585767149925
2023-01-22 16:59:20.256884: step: 324/529, loss: 0.0043944972567260265
2023-01-22 16:59:21.325482: step: 328/529, loss: 0.0036881607957184315
2023-01-22 16:59:22.407542: step: 332/529, loss: 0.0032382241915911436
2023-01-22 16:59:23.487801: step: 336/529, loss: 0.0032929531298577785
2023-01-22 16:59:24.562574: step: 340/529, loss: 0.0062603517435491085
2023-01-22 16:59:25.631129: step: 344/529, loss: 0.006787760648876429
2023-01-22 16:59:26.696270: step: 348/529, loss: 0.0015887313056737185
2023-01-22 16:59:27.780438: step: 352/529, loss: 0.003251665737479925
2023-01-22 16:59:28.873669: step: 356/529, loss: 0.005710741505026817
2023-01-22 16:59:29.934505: step: 360/529, loss: 0.011052190326154232
2023-01-22 16:59:31.001487: step: 364/529, loss: 0.0020662425085902214
2023-01-22 16:59:32.082141: step: 368/529, loss: 0.008903606794774532
2023-01-22 16:59:33.171028: step: 372/529, loss: 0.004032880067825317
2023-01-22 16:59:34.238127: step: 376/529, loss: 0.002282926347106695
2023-01-22 16:59:35.312794: step: 380/529, loss: 0.003698973450809717
2023-01-22 16:59:36.387415: step: 384/529, loss: 0.0038311092648655176
2023-01-22 16:59:37.459566: step: 388/529, loss: 0.004132179077714682
2023-01-22 16:59:38.526179: step: 392/529, loss: 0.0023199536371976137
2023-01-22 16:59:39.606516: step: 396/529, loss: 0.002862815512344241
2023-01-22 16:59:40.667657: step: 400/529, loss: 0.010286512784659863
2023-01-22 16:59:41.735523: step: 404/529, loss: 0.0030006521847099066
2023-01-22 16:59:42.804003: step: 408/529, loss: 0.039712563157081604
2023-01-22 16:59:43.879305: step: 412/529, loss: 0.009774887003004551
2023-01-22 16:59:44.952919: step: 416/529, loss: 0.0008259558235295117
2023-01-22 16:59:46.016454: step: 420/529, loss: 0.0074269408360123634
2023-01-22 16:59:47.083629: step: 424/529, loss: 0.006902003660798073
2023-01-22 16:59:48.158830: step: 428/529, loss: 0.00027348060393705964
2023-01-22 16:59:49.216990: step: 432/529, loss: 0.0012583623174577951
2023-01-22 16:59:50.290365: step: 436/529, loss: 0.0007712326478213072
2023-01-22 16:59:51.361759: step: 440/529, loss: 0.01883554644882679
2023-01-22 16:59:52.433843: step: 444/529, loss: 0.00024521685554645956
2023-01-22 16:59:53.520198: step: 448/529, loss: 0.01075885258615017
2023-01-22 16:59:54.601682: step: 452/529, loss: 0.004799680318683386
2023-01-22 16:59:55.671092: step: 456/529, loss: 0.0005024845013394952
2023-01-22 16:59:56.747599: step: 460/529, loss: 0.0016516101313754916
2023-01-22 16:59:57.828137: step: 464/529, loss: 0.005199144594371319
2023-01-22 16:59:58.926486: step: 468/529, loss: 0.014054781757295132
2023-01-22 16:59:59.999966: step: 472/529, loss: 0.006899752654135227
2023-01-22 17:00:01.091366: step: 476/529, loss: 0.006904142908751965
2023-01-22 17:00:02.165187: step: 480/529, loss: 0.0005460199317894876
2023-01-22 17:00:03.237049: step: 484/529, loss: 0.003620860865339637
2023-01-22 17:00:04.319187: step: 488/529, loss: 0.009071952663362026
2023-01-22 17:00:05.386138: step: 492/529, loss: 3.001012373715639e-05
2023-01-22 17:00:06.454653: step: 496/529, loss: 0.013208171352744102
2023-01-22 17:00:07.546006: step: 500/529, loss: 0.002930690301582217
2023-01-22 17:00:08.626510: step: 504/529, loss: 0.00794550497084856
2023-01-22 17:00:09.705453: step: 508/529, loss: 0.005965706426650286
2023-01-22 17:00:10.775994: step: 512/529, loss: 0.0070600989274680614
2023-01-22 17:00:11.851291: step: 516/529, loss: 0.005748335737735033
2023-01-22 17:00:12.932166: step: 520/529, loss: 0.010124134831130505
2023-01-22 17:00:14.005526: step: 524/529, loss: 0.0030858267564326525
2023-01-22 17:00:15.069084: step: 528/529, loss: 1.776937779141008e-07
2023-01-22 17:00:16.135658: step: 532/529, loss: 0.008894138038158417
2023-01-22 17:00:17.204526: step: 536/529, loss: 0.0003888040955644101
2023-01-22 17:00:18.274892: step: 540/529, loss: 0.00016863054770510644
2023-01-22 17:00:19.334474: step: 544/529, loss: 0.01236016396433115
2023-01-22 17:00:20.390500: step: 548/529, loss: 0.0007682872237637639
2023-01-22 17:00:21.462440: step: 552/529, loss: 0.006971367169171572
2023-01-22 17:00:22.536496: step: 556/529, loss: 0.0015935538103803992
2023-01-22 17:00:23.644649: step: 560/529, loss: 0.002298989798873663
2023-01-22 17:00:24.719635: step: 564/529, loss: 0.0033600274473428726
2023-01-22 17:00:25.788769: step: 568/529, loss: 0.004706053528934717
2023-01-22 17:00:26.841965: step: 572/529, loss: 0.009068414568901062
2023-01-22 17:00:27.931093: step: 576/529, loss: 0.009056344628334045
2023-01-22 17:00:29.018883: step: 580/529, loss: 0.005143926944583654
2023-01-22 17:00:30.086164: step: 584/529, loss: 0.004690610803663731
2023-01-22 17:00:31.159209: step: 588/529, loss: 0.00041718213469721377
2023-01-22 17:00:32.223161: step: 592/529, loss: 0.0032455853652209044
2023-01-22 17:00:33.317996: step: 596/529, loss: 0.002281383378431201
2023-01-22 17:00:34.387399: step: 600/529, loss: 0.0002451192995067686
2023-01-22 17:00:35.464646: step: 604/529, loss: 0.007181620225310326
2023-01-22 17:00:36.515513: step: 608/529, loss: 0.005475702229887247
2023-01-22 17:00:37.602678: step: 612/529, loss: 0.0027037349063903093
2023-01-22 17:00:38.679015: step: 616/529, loss: 0.004738654475659132
2023-01-22 17:00:39.757016: step: 620/529, loss: 0.022524306550621986
2023-01-22 17:00:40.814670: step: 624/529, loss: 0.0028218678198754787
2023-01-22 17:00:41.882037: step: 628/529, loss: 0.0009046487975865602
2023-01-22 17:00:42.942115: step: 632/529, loss: 0.0018516629934310913
2023-01-22 17:00:44.009388: step: 636/529, loss: 0.0008893645135685802
2023-01-22 17:00:45.078296: step: 640/529, loss: 0.006917968392372131
2023-01-22 17:00:46.147710: step: 644/529, loss: 0.002134098904207349
2023-01-22 17:00:47.228786: step: 648/529, loss: 0.0018686726689338684
2023-01-22 17:00:48.323276: step: 652/529, loss: 0.0024751045275479555
2023-01-22 17:00:49.388865: step: 656/529, loss: 0.005321783944964409
2023-01-22 17:00:50.474082: step: 660/529, loss: 0.002583594061434269
2023-01-22 17:00:51.547685: step: 664/529, loss: 0.0026916086208075285
2023-01-22 17:00:52.621985: step: 668/529, loss: 0.004706230945885181
2023-01-22 17:00:53.713047: step: 672/529, loss: 0.0021738982759416103
2023-01-22 17:00:54.773244: step: 676/529, loss: 0.0013355562696233392
2023-01-22 17:00:55.843969: step: 680/529, loss: 0.006208792794495821
2023-01-22 17:00:56.904754: step: 684/529, loss: 0.001460074563510716
2023-01-22 17:00:57.995435: step: 688/529, loss: 0.0035437317565083504
2023-01-22 17:00:59.061380: step: 692/529, loss: 0.0006643783999606967
2023-01-22 17:01:00.146230: step: 696/529, loss: 0.004758054856210947
2023-01-22 17:01:01.209255: step: 700/529, loss: 0.012687666341662407
2023-01-22 17:01:02.264217: step: 704/529, loss: 0.0017439179355278611
2023-01-22 17:01:03.346378: step: 708/529, loss: 0.001834993134252727
2023-01-22 17:01:04.421271: step: 712/529, loss: 0.01399508211761713
2023-01-22 17:01:05.489904: step: 716/529, loss: 0.008070344105362892
2023-01-22 17:01:06.565789: step: 720/529, loss: 0.006971363443881273
2023-01-22 17:01:07.620878: step: 724/529, loss: 0.0007292046793736517
2023-01-22 17:01:08.696291: step: 728/529, loss: 0.0017946661682799459
2023-01-22 17:01:09.755684: step: 732/529, loss: 0.0030234334990382195
2023-01-22 17:01:10.823547: step: 736/529, loss: 0.0008042494300752878
2023-01-22 17:01:11.886430: step: 740/529, loss: 0.0010378105798736215
2023-01-22 17:01:12.977879: step: 744/529, loss: 0.012843229807913303
2023-01-22 17:01:14.048094: step: 748/529, loss: 0.021408304572105408
2023-01-22 17:01:15.128198: step: 752/529, loss: 0.00567891588434577
2023-01-22 17:01:16.189853: step: 756/529, loss: 0.0003825603344012052
2023-01-22 17:01:17.255254: step: 760/529, loss: 6.123925413703546e-05
2023-01-22 17:01:18.319717: step: 764/529, loss: 0.008799569681286812
2023-01-22 17:01:19.392267: step: 768/529, loss: 0.00476152403280139
2023-01-22 17:01:20.462746: step: 772/529, loss: 0.006334402598440647
2023-01-22 17:01:21.535337: step: 776/529, loss: 3.610803832998499e-05
2023-01-22 17:01:22.625986: step: 780/529, loss: 0.00034002639586105943
2023-01-22 17:01:23.707166: step: 784/529, loss: 0.012935356236994267
2023-01-22 17:01:24.776927: step: 788/529, loss: 0.0005749124102294445
2023-01-22 17:01:25.858874: step: 792/529, loss: 0.011290821246802807
2023-01-22 17:01:26.946409: step: 796/529, loss: 0.004592223558574915
2023-01-22 17:01:28.029838: step: 800/529, loss: 0.005901220254600048
2023-01-22 17:01:29.109026: step: 804/529, loss: 0.0009286381537094712
2023-01-22 17:01:30.186472: step: 808/529, loss: 0.004681146237999201
2023-01-22 17:01:31.255536: step: 812/529, loss: 0.0048268684186041355
2023-01-22 17:01:32.327886: step: 816/529, loss: 0.007325382903218269
2023-01-22 17:01:33.431901: step: 820/529, loss: 0.005948640406131744
2023-01-22 17:01:34.506209: step: 824/529, loss: 0.0006674726610071957
2023-01-22 17:01:35.584669: step: 828/529, loss: 0.007661811076104641
2023-01-22 17:01:36.657453: step: 832/529, loss: 0.018102621659636497
2023-01-22 17:01:37.744595: step: 836/529, loss: 0.0024864375591278076
2023-01-22 17:01:38.807600: step: 840/529, loss: 0.00022554029419552535
2023-01-22 17:01:39.885520: step: 844/529, loss: 0.0061652869917452335
2023-01-22 17:01:40.942281: step: 848/529, loss: 0.004371496848762035
2023-01-22 17:01:42.026112: step: 852/529, loss: 0.0037744506262242794
2023-01-22 17:01:43.103188: step: 856/529, loss: 0.0003453693352639675
2023-01-22 17:01:44.187704: step: 860/529, loss: 0.00436187582090497
2023-01-22 17:01:45.265499: step: 864/529, loss: 0.003474610624834895
2023-01-22 17:01:46.336611: step: 868/529, loss: 0.13750362396240234
2023-01-22 17:01:47.418644: step: 872/529, loss: 0.017220474779605865
2023-01-22 17:01:48.508075: step: 876/529, loss: 0.004889114759862423
2023-01-22 17:01:49.597025: step: 880/529, loss: 0.002652924507856369
2023-01-22 17:01:50.688584: step: 884/529, loss: 0.0029058349318802357
2023-01-22 17:01:51.772973: step: 888/529, loss: 0.002441678661853075
2023-01-22 17:01:52.862503: step: 892/529, loss: 0.0016899965703487396
2023-01-22 17:01:53.929691: step: 896/529, loss: 0.0053136046044528484
2023-01-22 17:01:55.008223: step: 900/529, loss: 0.03263198211789131
2023-01-22 17:01:56.078558: step: 904/529, loss: 0.0006510126986540854
2023-01-22 17:01:57.174656: step: 908/529, loss: 0.006777654867619276
2023-01-22 17:01:58.256963: step: 912/529, loss: 0.00010978826321661472
2023-01-22 17:01:59.338031: step: 916/529, loss: 0.0034061321057379246
2023-01-22 17:02:00.422164: step: 920/529, loss: 0.00019502728537190706
2023-01-22 17:02:01.506970: step: 924/529, loss: 0.0017094011418521404
2023-01-22 17:02:02.573415: step: 928/529, loss: 0.006432528607547283
2023-01-22 17:02:03.653765: step: 932/529, loss: 0.0008155680843628943
2023-01-22 17:02:04.730142: step: 936/529, loss: 0.0102853337302804
2023-01-22 17:02:05.812473: step: 940/529, loss: 0.006996444892138243
2023-01-22 17:02:06.903078: step: 944/529, loss: 0.0017697897274047136
2023-01-22 17:02:07.995588: step: 948/529, loss: 0.008571169339120388
2023-01-22 17:02:09.071447: step: 952/529, loss: 0.0005437851068563759
2023-01-22 17:02:10.131984: step: 956/529, loss: 0.016357216984033585
2023-01-22 17:02:11.206463: step: 960/529, loss: 0.004743458703160286
2023-01-22 17:02:12.296861: step: 964/529, loss: 0.05050304904580116
2023-01-22 17:02:13.383406: step: 968/529, loss: 0.00031291492632590234
2023-01-22 17:02:14.470165: step: 972/529, loss: 0.0016435356810688972
2023-01-22 17:02:15.552353: step: 976/529, loss: 2.594915531517472e-05
2023-01-22 17:02:16.645707: step: 980/529, loss: 0.001903029391542077
2023-01-22 17:02:17.743818: step: 984/529, loss: 0.0030033248476684093
2023-01-22 17:02:18.820804: step: 988/529, loss: 0.0005427224677987397
2023-01-22 17:02:19.902184: step: 992/529, loss: 0.000672551803290844
2023-01-22 17:02:20.992682: step: 996/529, loss: 0.002496907953172922
2023-01-22 17:02:22.091734: step: 1000/529, loss: 0.0018266845727339387
2023-01-22 17:02:23.183684: step: 1004/529, loss: 0.012097865343093872
2023-01-22 17:02:24.257245: step: 1008/529, loss: 0.008147796615958214
2023-01-22 17:02:25.354171: step: 1012/529, loss: 0.0016766826156526804
2023-01-22 17:02:26.426547: step: 1016/529, loss: 0.005306873004883528
2023-01-22 17:02:27.493722: step: 1020/529, loss: 0.005997353233397007
2023-01-22 17:02:28.571135: step: 1024/529, loss: 0.00370508199557662
2023-01-22 17:02:29.647594: step: 1028/529, loss: 0.011876273900270462
2023-01-22 17:02:30.731918: step: 1032/529, loss: 0.004483404103666544
2023-01-22 17:02:31.822591: step: 1036/529, loss: 0.0014186983462423086
2023-01-22 17:02:32.897029: step: 1040/529, loss: 7.65753211453557e-05
2023-01-22 17:02:33.973372: step: 1044/529, loss: 0.0012655870523303747
2023-01-22 17:02:35.059921: step: 1048/529, loss: 0.0026184390299022198
2023-01-22 17:02:36.133623: step: 1052/529, loss: 0.004399022553116083
2023-01-22 17:02:37.221703: step: 1056/529, loss: 0.0017807999392971396
2023-01-22 17:02:38.309831: step: 1060/529, loss: 0.008361397311091423
2023-01-22 17:02:39.388404: step: 1064/529, loss: 0.015588500536978245
2023-01-22 17:02:40.464776: step: 1068/529, loss: 0.005209534429013729
2023-01-22 17:02:41.553554: step: 1072/529, loss: 0.01267347950488329
2023-01-22 17:02:42.653894: step: 1076/529, loss: 0.00047251611249521375
2023-01-22 17:02:43.738160: step: 1080/529, loss: 0.0013504591770470142
2023-01-22 17:02:44.813785: step: 1084/529, loss: 0.01155027374625206
2023-01-22 17:02:45.895367: step: 1088/529, loss: 0.0006555234431289136
2023-01-22 17:02:46.984084: step: 1092/529, loss: 0.001129095209762454
2023-01-22 17:02:48.071622: step: 1096/529, loss: 0.009894326329231262
2023-01-22 17:02:49.151830: step: 1100/529, loss: 6.452338129747659e-05
2023-01-22 17:02:50.237188: step: 1104/529, loss: 0.005296661984175444
2023-01-22 17:02:51.321067: step: 1108/529, loss: 0.0045640189200639725
2023-01-22 17:02:52.391787: step: 1112/529, loss: 0.0005523888976313174
2023-01-22 17:02:53.461933: step: 1116/529, loss: 0.007128852419555187
2023-01-22 17:02:54.551036: step: 1120/529, loss: 0.006258789449930191
2023-01-22 17:02:55.629488: step: 1124/529, loss: 0.0005953112849965692
2023-01-22 17:02:56.725883: step: 1128/529, loss: 6.748545274604112e-05
2023-01-22 17:02:57.800139: step: 1132/529, loss: 0.0044932314194738865
2023-01-22 17:02:58.867175: step: 1136/529, loss: 0.009857969358563423
2023-01-22 17:02:59.943678: step: 1140/529, loss: 0.0021883067674934864
2023-01-22 17:03:01.038168: step: 1144/529, loss: 0.0003860625147353858
2023-01-22 17:03:02.113083: step: 1148/529, loss: 0.005602306220680475
2023-01-22 17:03:03.195221: step: 1152/529, loss: 0.016554484143853188
2023-01-22 17:03:04.285186: step: 1156/529, loss: 0.0034943840000778437
2023-01-22 17:03:05.353297: step: 1160/529, loss: 0.0005029496969655156
2023-01-22 17:03:06.434716: step: 1164/529, loss: 0.0033986091148108244
2023-01-22 17:03:07.538653: step: 1168/529, loss: 0.0015404887963086367
2023-01-22 17:03:08.621156: step: 1172/529, loss: 0.0011166732292622328
2023-01-22 17:03:09.712347: step: 1176/529, loss: 0.0002667238295543939
2023-01-22 17:03:10.784913: step: 1180/529, loss: 0.002281706314533949
2023-01-22 17:03:11.898055: step: 1184/529, loss: 0.002955926116555929
2023-01-22 17:03:12.970365: step: 1188/529, loss: 0.009445217438042164
2023-01-22 17:03:14.050366: step: 1192/529, loss: 0.0018050877843052149
2023-01-22 17:03:15.111856: step: 1196/529, loss: 0.0003661549126263708
2023-01-22 17:03:16.195767: step: 1200/529, loss: 0.003146685427054763
2023-01-22 17:03:17.275809: step: 1204/529, loss: 0.0028313391376286745
2023-01-22 17:03:18.342430: step: 1208/529, loss: 0.022725306451320648
2023-01-22 17:03:19.420878: step: 1212/529, loss: 0.011618991382420063
2023-01-22 17:03:20.500825: step: 1216/529, loss: 0.007653260137885809
2023-01-22 17:03:21.588813: step: 1220/529, loss: 0.013248827308416367
2023-01-22 17:03:22.654243: step: 1224/529, loss: 0.0005917140515521169
2023-01-22 17:03:23.738867: step: 1228/529, loss: 0.007229936774820089
2023-01-22 17:03:24.810230: step: 1232/529, loss: 0.003560977755114436
2023-01-22 17:03:25.886768: step: 1236/529, loss: 0.002076733158901334
2023-01-22 17:03:26.978802: step: 1240/529, loss: 0.0009652223670855165
2023-01-22 17:03:28.054046: step: 1244/529, loss: 0.0056844064965844154
2023-01-22 17:03:29.135533: step: 1248/529, loss: 0.00021671729336958379
2023-01-22 17:03:30.222089: step: 1252/529, loss: 0.0025617831852287054
2023-01-22 17:03:31.289052: step: 1256/529, loss: 0.000589905132073909
2023-01-22 17:03:32.360768: step: 1260/529, loss: 0.009309370070695877
2023-01-22 17:03:33.434947: step: 1264/529, loss: 0.0037129605188965797
2023-01-22 17:03:34.518145: step: 1268/529, loss: 0.0019228963647037745
2023-01-22 17:03:35.618620: step: 1272/529, loss: 0.0028096914757043123
2023-01-22 17:03:36.680155: step: 1276/529, loss: 0.004148928448557854
2023-01-22 17:03:37.730791: step: 1280/529, loss: 0.0018817471573129296
2023-01-22 17:03:38.815504: step: 1284/529, loss: 0.00251255976036191
2023-01-22 17:03:39.898780: step: 1288/529, loss: 0.0020330878905951977
2023-01-22 17:03:40.972178: step: 1292/529, loss: 0.001012020860798657
2023-01-22 17:03:42.052975: step: 1296/529, loss: 0.0066626910120248795
2023-01-22 17:03:43.127541: step: 1300/529, loss: 0.0016276236856356263
2023-01-22 17:03:44.193886: step: 1304/529, loss: 0.001064040930941701
2023-01-22 17:03:45.251036: step: 1308/529, loss: 0.0023552991915494204
2023-01-22 17:03:46.317766: step: 1312/529, loss: 0.0011800406500697136
2023-01-22 17:03:47.395717: step: 1316/529, loss: 0.0010205378057435155
2023-01-22 17:03:48.478473: step: 1320/529, loss: 0.0043399096466600895
2023-01-22 17:03:49.558347: step: 1324/529, loss: 0.0019996531773358583
2023-01-22 17:03:50.632660: step: 1328/529, loss: 0.0013175040949136019
2023-01-22 17:03:51.709698: step: 1332/529, loss: 0.008157377131283283
2023-01-22 17:03:52.780588: step: 1336/529, loss: 1.0361813110648654e-05
2023-01-22 17:03:53.858898: step: 1340/529, loss: 0.010931240394711494
2023-01-22 17:03:54.939929: step: 1344/529, loss: 0.004290084820240736
2023-01-22 17:03:56.004092: step: 1348/529, loss: 0.001613378175534308
2023-01-22 17:03:57.070068: step: 1352/529, loss: 0.005706457886844873
2023-01-22 17:03:58.147600: step: 1356/529, loss: 0.0011905826395377517
2023-01-22 17:03:59.221478: step: 1360/529, loss: 0.0011665733763948083
2023-01-22 17:04:00.291745: step: 1364/529, loss: 0.002651187125593424
2023-01-22 17:04:01.349437: step: 1368/529, loss: 0.002460924908518791
2023-01-22 17:04:02.406068: step: 1372/529, loss: 0.0012857065303251147
2023-01-22 17:04:03.498877: step: 1376/529, loss: 0.000723969773389399
2023-01-22 17:04:04.576018: step: 1380/529, loss: 0.005783837754279375
2023-01-22 17:04:05.638340: step: 1384/529, loss: 0.0018851591739803553
2023-01-22 17:04:06.698733: step: 1388/529, loss: 0.0002665466454345733
2023-01-22 17:04:07.766725: step: 1392/529, loss: 0.003083331510424614
2023-01-22 17:04:08.828946: step: 1396/529, loss: 0.00038746505742892623
2023-01-22 17:04:09.905159: step: 1400/529, loss: 0.004574262537062168
2023-01-22 17:04:10.972029: step: 1404/529, loss: 0.00023623576271347702
2023-01-22 17:04:12.050077: step: 1408/529, loss: 0.013189992867410183
2023-01-22 17:04:13.124774: step: 1412/529, loss: 0.0001180979234050028
2023-01-22 17:04:14.202514: step: 1416/529, loss: 0.0003545752842910588
2023-01-22 17:04:15.270772: step: 1420/529, loss: 0.002352015348151326
2023-01-22 17:04:16.350398: step: 1424/529, loss: 0.0014859104994684458
2023-01-22 17:04:17.411113: step: 1428/529, loss: 3.6385048588272184e-05
2023-01-22 17:04:18.498249: step: 1432/529, loss: 0.004082232713699341
2023-01-22 17:04:19.557869: step: 1436/529, loss: 0.005047069396823645
2023-01-22 17:04:20.617168: step: 1440/529, loss: 0.0016998436767607927
2023-01-22 17:04:21.685200: step: 1444/529, loss: 0.017887288704514503
2023-01-22 17:04:22.762225: step: 1448/529, loss: 0.0119456322863698
2023-01-22 17:04:23.830219: step: 1452/529, loss: 0.0003369227342773229
2023-01-22 17:04:24.912117: step: 1456/529, loss: 0.0014498044038191438
2023-01-22 17:04:25.997866: step: 1460/529, loss: 0.001330201979726553
2023-01-22 17:04:27.076022: step: 1464/529, loss: 0.03399517014622688
2023-01-22 17:04:28.152407: step: 1468/529, loss: 0.0009036113042384386
2023-01-22 17:04:29.215249: step: 1472/529, loss: 0.009424423798918724
2023-01-22 17:04:30.280957: step: 1476/529, loss: 0.0045033469796180725
2023-01-22 17:04:31.355640: step: 1480/529, loss: 0.006226568948477507
2023-01-22 17:04:32.421550: step: 1484/529, loss: 0.005201412830501795
2023-01-22 17:04:33.486748: step: 1488/529, loss: 0.0070693036541342735
2023-01-22 17:04:34.566567: step: 1492/529, loss: 0.004682602360844612
2023-01-22 17:04:35.645052: step: 1496/529, loss: 0.007212301250547171
2023-01-22 17:04:36.718674: step: 1500/529, loss: 0.00461286585777998
2023-01-22 17:04:37.790776: step: 1504/529, loss: 0.0016360811423510313
2023-01-22 17:04:38.860915: step: 1508/529, loss: 0.0006825494929216802
2023-01-22 17:04:39.924635: step: 1512/529, loss: 0.0022835417184978724
2023-01-22 17:04:40.989479: step: 1516/529, loss: 0.005479033105075359
2023-01-22 17:04:42.070450: step: 1520/529, loss: 0.030284978449344635
2023-01-22 17:04:43.138787: step: 1524/529, loss: 0.00014283962082117796
2023-01-22 17:04:44.220117: step: 1528/529, loss: 0.0026233394164592028
2023-01-22 17:04:45.281279: step: 1532/529, loss: 0.0020527131855487823
2023-01-22 17:04:46.359730: step: 1536/529, loss: 0.0002474638749845326
2023-01-22 17:04:47.418599: step: 1540/529, loss: 0.0013742984738200903
2023-01-22 17:04:48.502372: step: 1544/529, loss: 0.008978042751550674
2023-01-22 17:04:49.569603: step: 1548/529, loss: 0.00020447769202291965
2023-01-22 17:04:50.636103: step: 1552/529, loss: 0.002034167991951108
2023-01-22 17:04:51.710519: step: 1556/529, loss: 0.00557552557438612
2023-01-22 17:04:52.787539: step: 1560/529, loss: 0.0009481045417487621
2023-01-22 17:04:53.834827: step: 1564/529, loss: 0.0010191145120188594
2023-01-22 17:04:54.912859: step: 1568/529, loss: 0.001281422097235918
2023-01-22 17:04:56.015979: step: 1572/529, loss: 0.0063865589909255505
2023-01-22 17:04:57.085281: step: 1576/529, loss: 0.00016970594879239798
2023-01-22 17:04:58.151671: step: 1580/529, loss: 0.007933572866022587
2023-01-22 17:04:59.229472: step: 1584/529, loss: 0.0042253597639501095
2023-01-22 17:05:00.302253: step: 1588/529, loss: 0.0011132482904940844
2023-01-22 17:05:01.363147: step: 1592/529, loss: 0.0014076882507652044
2023-01-22 17:05:02.436207: step: 1596/529, loss: 0.024389734491705894
2023-01-22 17:05:03.516913: step: 1600/529, loss: 0.0030206141527742147
2023-01-22 17:05:04.586316: step: 1604/529, loss: 0.001388438744470477
2023-01-22 17:05:05.639251: step: 1608/529, loss: 0.012383831664919853
2023-01-22 17:05:06.701905: step: 1612/529, loss: 0.002930454211309552
2023-01-22 17:05:07.786773: step: 1616/529, loss: 0.007121201604604721
2023-01-22 17:05:08.853665: step: 1620/529, loss: 0.0420500710606575
2023-01-22 17:05:09.928695: step: 1624/529, loss: 0.006728779058903456
2023-01-22 17:05:10.997248: step: 1628/529, loss: 0.0018686304101720452
2023-01-22 17:05:12.079936: step: 1632/529, loss: 0.0014674749691039324
2023-01-22 17:05:13.168472: step: 1636/529, loss: 0.0005261803744360805
2023-01-22 17:05:14.230130: step: 1640/529, loss: 0.007460297085344791
2023-01-22 17:05:15.311954: step: 1644/529, loss: 0.006846974138170481
2023-01-22 17:05:16.393506: step: 1648/529, loss: 0.00816772785037756
2023-01-22 17:05:17.479815: step: 1652/529, loss: 0.0028012238908559084
2023-01-22 17:05:18.570371: step: 1656/529, loss: 0.005947655066847801
2023-01-22 17:05:19.666215: step: 1660/529, loss: 0.0053372434340417385
2023-01-22 17:05:20.754480: step: 1664/529, loss: 0.006887024734169245
2023-01-22 17:05:21.841462: step: 1668/529, loss: 0.0029607245232909918
2023-01-22 17:05:22.902280: step: 1672/529, loss: 0.0027111347299069166
2023-01-22 17:05:23.971708: step: 1676/529, loss: 0.0035719876177608967
2023-01-22 17:05:25.037490: step: 1680/529, loss: 0.0029191048815846443
2023-01-22 17:05:26.105830: step: 1684/529, loss: 0.00319719803519547
2023-01-22 17:05:27.196738: step: 1688/529, loss: 0.00456938985735178
2023-01-22 17:05:28.265663: step: 1692/529, loss: 0.006604470312595367
2023-01-22 17:05:29.344950: step: 1696/529, loss: 0.0044240802526474
2023-01-22 17:05:30.425045: step: 1700/529, loss: 0.00014695030404254794
2023-01-22 17:05:31.509394: step: 1704/529, loss: 0.004230601713061333
2023-01-22 17:05:32.583088: step: 1708/529, loss: 0.0005656823632307351
2023-01-22 17:05:33.651214: step: 1712/529, loss: 0.00022217545483727008
2023-01-22 17:05:34.724558: step: 1716/529, loss: 0.0009813887299969792
2023-01-22 17:05:35.798258: step: 1720/529, loss: 0.0016360919689759612
2023-01-22 17:05:36.863326: step: 1724/529, loss: 0.003637816058471799
2023-01-22 17:05:37.929574: step: 1728/529, loss: 0.004927363246679306
2023-01-22 17:05:38.993341: step: 1732/529, loss: 0.00621325708925724
2023-01-22 17:05:40.060370: step: 1736/529, loss: 0.003051426261663437
2023-01-22 17:05:41.128908: step: 1740/529, loss: 0.005948478356003761
2023-01-22 17:05:42.203637: step: 1744/529, loss: 0.003967400640249252
2023-01-22 17:05:43.270547: step: 1748/529, loss: 0.001984755042940378
2023-01-22 17:05:44.343876: step: 1752/529, loss: 0.0008297549211420119
2023-01-22 17:05:45.402720: step: 1756/529, loss: 0.008170767687261105
2023-01-22 17:05:46.477038: step: 1760/529, loss: 0.00993902888149023
2023-01-22 17:05:47.540365: step: 1764/529, loss: 0.0014071790501475334
2023-01-22 17:05:48.596538: step: 1768/529, loss: 0.0007235452649183571
2023-01-22 17:05:49.682856: step: 1772/529, loss: 0.003635557135567069
2023-01-22 17:05:50.745059: step: 1776/529, loss: 0.0019865641370415688
2023-01-22 17:05:51.803552: step: 1780/529, loss: 0.004577450919896364
2023-01-22 17:05:52.871489: step: 1784/529, loss: 0.00024526112247258425
2023-01-22 17:05:53.936016: step: 1788/529, loss: 0.0027508193161338568
2023-01-22 17:05:55.014393: step: 1792/529, loss: 0.007453067693859339
2023-01-22 17:05:56.097356: step: 1796/529, loss: 0.0007248448091559112
2023-01-22 17:05:57.162830: step: 1800/529, loss: 5.425360086519504e-06
2023-01-22 17:05:58.229082: step: 1804/529, loss: 0.0028575537726283073
2023-01-22 17:05:59.302429: step: 1808/529, loss: 0.015212181955575943
2023-01-22 17:06:00.370173: step: 1812/529, loss: 0.011936192400753498
2023-01-22 17:06:01.433837: step: 1816/529, loss: 0.0012568295933306217
2023-01-22 17:06:02.507757: step: 1820/529, loss: 0.004838570021092892
2023-01-22 17:06:03.579715: step: 1824/529, loss: 0.01585705764591694
2023-01-22 17:06:04.639946: step: 1828/529, loss: 0.004867205861955881
2023-01-22 17:06:05.712474: step: 1832/529, loss: 0.006079098209738731
2023-01-22 17:06:06.788875: step: 1836/529, loss: 0.0017804085509851575
2023-01-22 17:06:07.860054: step: 1840/529, loss: 0.0005418629734776914
2023-01-22 17:06:08.935461: step: 1844/529, loss: 0.013174304738640785
2023-01-22 17:06:10.012620: step: 1848/529, loss: 0.015392934903502464
2023-01-22 17:06:11.082869: step: 1852/529, loss: 0.009023748338222504
2023-01-22 17:06:12.156754: step: 1856/529, loss: 0.004224275704473257
2023-01-22 17:06:13.225474: step: 1860/529, loss: 0.0006300094537436962
2023-01-22 17:06:14.290171: step: 1864/529, loss: 0.00799323059618473
2023-01-22 17:06:15.373150: step: 1868/529, loss: 0.0032703541219234467
2023-01-22 17:06:16.425629: step: 1872/529, loss: 0.005142878741025925
2023-01-22 17:06:17.479799: step: 1876/529, loss: 0.0030077104456722736
2023-01-22 17:06:18.546822: step: 1880/529, loss: 2.8942829430889105e-06
2023-01-22 17:06:19.615931: step: 1884/529, loss: 0.0034233068581670523
2023-01-22 17:06:20.685416: step: 1888/529, loss: 0.0021873395889997482
2023-01-22 17:06:21.762375: step: 1892/529, loss: 0.0045728785917162895
2023-01-22 17:06:22.826287: step: 1896/529, loss: 0.00026265758788213134
2023-01-22 17:06:23.907007: step: 1900/529, loss: 0.005356815177947283
2023-01-22 17:06:24.980114: step: 1904/529, loss: 0.0034824293106794357
2023-01-22 17:06:26.058735: step: 1908/529, loss: 0.0072312550619244576
2023-01-22 17:06:27.124169: step: 1912/529, loss: 0.0005669582751579583
2023-01-22 17:06:28.192465: step: 1916/529, loss: 0.008275214582681656
2023-01-22 17:06:29.255634: step: 1920/529, loss: 0.009792604483664036
2023-01-22 17:06:30.340032: step: 1924/529, loss: 0.0022169151343405247
2023-01-22 17:06:31.403355: step: 1928/529, loss: 0.00634088134393096
2023-01-22 17:06:32.481117: step: 1932/529, loss: 0.0030979879666119814
2023-01-22 17:06:33.550264: step: 1936/529, loss: 0.009384188801050186
2023-01-22 17:06:34.632887: step: 1940/529, loss: 0.010857371613383293
2023-01-22 17:06:35.701930: step: 1944/529, loss: 0.00020369526464492083
2023-01-22 17:06:36.764710: step: 1948/529, loss: 0.004388144239783287
2023-01-22 17:06:37.813044: step: 1952/529, loss: 0.005341329611837864
2023-01-22 17:06:38.891022: step: 1956/529, loss: 0.003869568230584264
2023-01-22 17:06:39.958027: step: 1960/529, loss: 0.005754523910582066
2023-01-22 17:06:41.015284: step: 1964/529, loss: 0.02395222708582878
2023-01-22 17:06:42.088958: step: 1968/529, loss: 0.004579734988510609
2023-01-22 17:06:43.170536: step: 1972/529, loss: 0.006186152342706919
2023-01-22 17:06:44.249127: step: 1976/529, loss: 0.024824978783726692
2023-01-22 17:06:45.324717: step: 1980/529, loss: 0.03843974322080612
2023-01-22 17:06:46.381763: step: 1984/529, loss: 0.002381526865065098
2023-01-22 17:06:47.450887: step: 1988/529, loss: 0.00890548899769783
2023-01-22 17:06:48.524624: step: 1992/529, loss: 0.0004151340981479734
2023-01-22 17:06:49.627434: step: 1996/529, loss: 0.00864302646368742
2023-01-22 17:06:50.691409: step: 2000/529, loss: 0.00403991062194109
2023-01-22 17:06:51.755976: step: 2004/529, loss: 0.0007158780936151743
2023-01-22 17:06:52.828002: step: 2008/529, loss: 0.007027340121567249
2023-01-22 17:06:53.903408: step: 2012/529, loss: 0.012439608573913574
2023-01-22 17:06:54.960268: step: 2016/529, loss: 0.004067345056682825
2023-01-22 17:06:56.036968: step: 2020/529, loss: 0.0021914695389568806
2023-01-22 17:06:57.096248: step: 2024/529, loss: 0.011593271978199482
2023-01-22 17:06:58.177269: step: 2028/529, loss: 0.002958855824545026
2023-01-22 17:06:59.242381: step: 2032/529, loss: 0.009319811128079891
2023-01-22 17:07:00.314203: step: 2036/529, loss: 0.0007707621552981436
2023-01-22 17:07:01.383267: step: 2040/529, loss: 0.0005363363306969404
2023-01-22 17:07:02.455289: step: 2044/529, loss: 0.01899806223809719
2023-01-22 17:07:03.524196: step: 2048/529, loss: 0.004605645313858986
2023-01-22 17:07:04.588781: step: 2052/529, loss: 0.009063088335096836
2023-01-22 17:07:05.653043: step: 2056/529, loss: 0.002710837172344327
2023-01-22 17:07:06.707662: step: 2060/529, loss: 0.002295162295922637
2023-01-22 17:07:07.776211: step: 2064/529, loss: 0.0017400173237547278
2023-01-22 17:07:08.858976: step: 2068/529, loss: 0.009092207998037338
2023-01-22 17:07:09.951183: step: 2072/529, loss: 0.006157895550131798
2023-01-22 17:07:11.020313: step: 2076/529, loss: 0.003863296704366803
2023-01-22 17:07:12.088944: step: 2080/529, loss: 0.0002572887751739472
2023-01-22 17:07:13.166109: step: 2084/529, loss: 0.006474801804870367
2023-01-22 17:07:14.237466: step: 2088/529, loss: 6.854459115857026e-07
2023-01-22 17:07:15.285368: step: 2092/529, loss: 0.023611361160874367
2023-01-22 17:07:16.346535: step: 2096/529, loss: 0.006375241558998823
2023-01-22 17:07:17.410072: step: 2100/529, loss: 0.0008411225280724466
2023-01-22 17:07:18.471692: step: 2104/529, loss: 0.002858164021745324
2023-01-22 17:07:19.535227: step: 2108/529, loss: 0.004075914155691862
2023-01-22 17:07:20.604469: step: 2112/529, loss: 0.0010750771034508944
2023-01-22 17:07:21.683144: step: 2116/529, loss: 0.0012862237635999918
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3179366438356165, 'r': 0.35232447817836815, 'f1': 0.33424842484248424}, 'combined': 0.24628831304183046, 'stategy': 1, 'epoch': 11}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3116532986241739, 'r': 0.3087888381588782, 'f1': 0.31021445606358217}, 'combined': 0.2025234272746702, 'stategy': 1, 'epoch': 11}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3214824380165289, 'r': 0.36906427893738136, 'f1': 0.343634054770318}, 'combined': 0.2532040403570764, 'stategy': 1, 'epoch': 11}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33472268370532865, 'r': 0.31257191787188776, 'f1': 0.323268295289557}, 'combined': 0.21104562283152423, 'stategy': 1, 'epoch': 11}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3141391708967851, 'r': 0.35228889943074004, 'f1': 0.33212209302325585}, 'combined': 0.24472154222766218, 'stategy': 1, 'epoch': 11}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32465274034246555, 'r': 0.3219696598437675, 'f1': 0.32330563353606534}, 'combined': 0.2110699990960841, 'stategy': 1, 'epoch': 11}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 11}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 11}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 11}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3214824380165289, 'r': 0.36906427893738136, 'f1': 0.343634054770318}, 'combined': 0.2532040403570764, 'stategy': 1, 'epoch': 11}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33472268370532865, 'r': 0.31257191787188776, 'f1': 0.323268295289557}, 'combined': 0.21104562283152423, 'stategy': 1, 'epoch': 11}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 11}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 17:10:05.511669: step: 4/529, loss: 0.000361921323928982
2023-01-22 17:10:06.569904: step: 8/529, loss: 0.0027543329633772373
2023-01-22 17:10:07.635270: step: 12/529, loss: 0.007630254607647657
2023-01-22 17:10:08.695142: step: 16/529, loss: 0.0007343032048083842
2023-01-22 17:10:09.770797: step: 20/529, loss: 0.0012807133607566357
2023-01-22 17:10:10.837535: step: 24/529, loss: 0.00038759689778089523
2023-01-22 17:10:11.896485: step: 28/529, loss: 0.004231306724250317
2023-01-22 17:10:12.961145: step: 32/529, loss: 0.0023894808255136013
2023-01-22 17:10:14.033517: step: 36/529, loss: 0.1705983281135559
2023-01-22 17:10:15.095131: step: 40/529, loss: 0.007521615829318762
2023-01-22 17:10:16.170598: step: 44/529, loss: 0.0022974121384322643
2023-01-22 17:10:17.233749: step: 48/529, loss: 0.007646316662430763
2023-01-22 17:10:18.305852: step: 52/529, loss: 0.010570627637207508
2023-01-22 17:10:19.359323: step: 56/529, loss: 0.006622339133173227
2023-01-22 17:10:20.436283: step: 60/529, loss: 0.0018222443759441376
2023-01-22 17:10:21.499671: step: 64/529, loss: 0.002226763404905796
2023-01-22 17:10:22.575374: step: 68/529, loss: 4.19920907006599e-05
2023-01-22 17:10:23.631750: step: 72/529, loss: 0.0016830101376399398
2023-01-22 17:10:24.686348: step: 76/529, loss: 0.0011862420942634344
2023-01-22 17:10:25.749250: step: 80/529, loss: 0.002153007546439767
2023-01-22 17:10:26.808042: step: 84/529, loss: 0.00904899276793003
2023-01-22 17:10:27.873707: step: 88/529, loss: 0.0022940707858651876
2023-01-22 17:10:28.954179: step: 92/529, loss: 0.0007194042555056512
2023-01-22 17:10:30.031859: step: 96/529, loss: 0.002703003818169236
2023-01-22 17:10:31.114661: step: 100/529, loss: 0.006100880913436413
2023-01-22 17:10:32.211192: step: 104/529, loss: 0.004942405503243208
2023-01-22 17:10:33.282780: step: 108/529, loss: 0.0005690957768820226
2023-01-22 17:10:34.339788: step: 112/529, loss: 0.002523837611079216
2023-01-22 17:10:35.437865: step: 116/529, loss: 0.0018693087622523308
2023-01-22 17:10:36.497809: step: 120/529, loss: 0.0010828442173078656
2023-01-22 17:10:37.563671: step: 124/529, loss: 0.02824726700782776
2023-01-22 17:10:38.629944: step: 128/529, loss: 0.005307256244122982
2023-01-22 17:10:39.716338: step: 132/529, loss: 0.0017831261502578855
2023-01-22 17:10:40.782418: step: 136/529, loss: 0.001563708414323628
2023-01-22 17:10:41.842163: step: 140/529, loss: 0.00043457504943944514
2023-01-22 17:10:42.932163: step: 144/529, loss: 0.005051839165389538
2023-01-22 17:10:44.034433: step: 148/529, loss: 0.0040791817009449005
2023-01-22 17:10:45.104148: step: 152/529, loss: 0.00046497126459144056
2023-01-22 17:10:46.198705: step: 156/529, loss: 0.006744929123669863
2023-01-22 17:10:47.266540: step: 160/529, loss: 0.05362081900238991
2023-01-22 17:10:48.330394: step: 164/529, loss: 0.0012575376313179731
2023-01-22 17:10:49.403269: step: 168/529, loss: 0.001310107414610684
2023-01-22 17:10:50.481327: step: 172/529, loss: 0.00033167380024679005
2023-01-22 17:10:51.551532: step: 176/529, loss: 0.004193542059510946
2023-01-22 17:10:52.629088: step: 180/529, loss: 0.014545802026987076
2023-01-22 17:10:53.699143: step: 184/529, loss: 0.0028726791497319937
2023-01-22 17:10:54.790948: step: 188/529, loss: 0.020510900765657425
2023-01-22 17:10:55.849413: step: 192/529, loss: 0.0010077552869915962
2023-01-22 17:10:56.943266: step: 196/529, loss: 0.004950291942805052
2023-01-22 17:10:58.007387: step: 200/529, loss: 5.701499503629748e-06
2023-01-22 17:10:59.073440: step: 204/529, loss: 0.0034605127293616533
2023-01-22 17:11:00.163858: step: 208/529, loss: 0.003968795295804739
2023-01-22 17:11:01.237924: step: 212/529, loss: 0.006312464829534292
2023-01-22 17:11:02.294413: step: 216/529, loss: 5.8979509049095213e-05
2023-01-22 17:11:03.365073: step: 220/529, loss: 0.016386644914746284
2023-01-22 17:11:04.436803: step: 224/529, loss: 0.003938872367143631
2023-01-22 17:11:05.497390: step: 228/529, loss: 0.0004759289731737226
2023-01-22 17:11:06.547184: step: 232/529, loss: 0.02547384425997734
2023-01-22 17:11:07.622278: step: 236/529, loss: 0.025544393807649612
2023-01-22 17:11:08.685896: step: 240/529, loss: 0.007377654779702425
2023-01-22 17:11:09.756724: step: 244/529, loss: 0.00414050230756402
2023-01-22 17:11:10.840152: step: 248/529, loss: 0.00026615633396431804
2023-01-22 17:11:11.915314: step: 252/529, loss: 0.0008698086603544652
2023-01-22 17:11:12.969969: step: 256/529, loss: 0.008049258030951023
2023-01-22 17:11:14.035862: step: 260/529, loss: 0.003497631289064884
2023-01-22 17:11:15.108635: step: 264/529, loss: 0.006201254203915596
2023-01-22 17:11:16.204803: step: 268/529, loss: 0.017417285591363907
2023-01-22 17:11:17.284080: step: 272/529, loss: 0.007253679446876049
2023-01-22 17:11:18.354650: step: 276/529, loss: 0.001215081661939621
2023-01-22 17:11:19.436678: step: 280/529, loss: 0.001447502989321947
2023-01-22 17:11:20.505608: step: 284/529, loss: 0.00040332681965082884
2023-01-22 17:11:21.588769: step: 288/529, loss: 0.0032110409811139107
2023-01-22 17:11:22.662467: step: 292/529, loss: 0.0030246665701270103
2023-01-22 17:11:23.749775: step: 296/529, loss: 0.00448493892326951
2023-01-22 17:11:24.820311: step: 300/529, loss: 0.0059451148845255375
2023-01-22 17:11:25.891221: step: 304/529, loss: 0.0013365116901695728
2023-01-22 17:11:26.962613: step: 308/529, loss: 0.00784012209624052
2023-01-22 17:11:28.038457: step: 312/529, loss: 0.006504009012132883
2023-01-22 17:11:29.113823: step: 316/529, loss: 0.000388285203371197
2023-01-22 17:11:30.183194: step: 320/529, loss: 0.0023971241898834705
2023-01-22 17:11:31.256696: step: 324/529, loss: 5.8770178839040454e-06
2023-01-22 17:11:32.309871: step: 328/529, loss: 0.003277328098192811
2023-01-22 17:11:33.378642: step: 332/529, loss: 0.007359951734542847
2023-01-22 17:11:34.469931: step: 336/529, loss: 0.0012199666816741228
2023-01-22 17:11:35.563624: step: 340/529, loss: 0.010876295156776905
2023-01-22 17:11:36.655414: step: 344/529, loss: 0.0017492666374891996
2023-01-22 17:11:37.722240: step: 348/529, loss: 0.0031481008045375347
2023-01-22 17:11:38.786756: step: 352/529, loss: 0.012958996929228306
2023-01-22 17:11:39.856491: step: 356/529, loss: 0.0045308503322303295
2023-01-22 17:11:40.926311: step: 360/529, loss: 0.005091175436973572
2023-01-22 17:11:41.986601: step: 364/529, loss: 0.0011031769681721926
2023-01-22 17:11:43.054766: step: 368/529, loss: 0.014993158169090748
2023-01-22 17:11:44.115612: step: 372/529, loss: 0.0015691436128690839
2023-01-22 17:11:45.204042: step: 376/529, loss: 0.0060926880687475204
2023-01-22 17:11:46.292027: step: 380/529, loss: 0.001660754787735641
2023-01-22 17:11:47.373470: step: 384/529, loss: 0.004047817550599575
2023-01-22 17:11:48.453521: step: 388/529, loss: 0.0015079942531883717
2023-01-22 17:11:49.531779: step: 392/529, loss: 0.0041028582490980625
2023-01-22 17:11:50.610670: step: 396/529, loss: 0.003120981389656663
2023-01-22 17:11:51.677673: step: 400/529, loss: 0.010635006241500378
2023-01-22 17:11:52.762460: step: 404/529, loss: 0.00629972480237484
2023-01-22 17:11:53.829806: step: 408/529, loss: 3.9860097444943676e-07
2023-01-22 17:11:54.918198: step: 412/529, loss: 0.009384317323565483
2023-01-22 17:11:55.978976: step: 416/529, loss: 0.004853838123381138
2023-01-22 17:11:57.053379: step: 420/529, loss: 0.002183604519814253
2023-01-22 17:11:58.133006: step: 424/529, loss: 0.015336764045059681
2023-01-22 17:11:59.219637: step: 428/529, loss: 0.025337018072605133
2023-01-22 17:12:00.304623: step: 432/529, loss: 0.0003656052576843649
2023-01-22 17:12:01.398107: step: 436/529, loss: 0.0012341223191469908
2023-01-22 17:12:02.469681: step: 440/529, loss: 0.004322833381593227
2023-01-22 17:12:03.547958: step: 444/529, loss: 0.007125149946659803
2023-01-22 17:12:04.623861: step: 448/529, loss: 0.017365621402859688
2023-01-22 17:12:05.697952: step: 452/529, loss: 2.6152900318265893e-05
2023-01-22 17:12:06.792068: step: 456/529, loss: 0.0036615203134715557
2023-01-22 17:12:07.885887: step: 460/529, loss: 0.0035374825820326805
2023-01-22 17:12:08.968225: step: 464/529, loss: 0.01242318656295538
2023-01-22 17:12:10.042769: step: 468/529, loss: 0.004052699543535709
2023-01-22 17:12:11.120150: step: 472/529, loss: 0.007320075761526823
2023-01-22 17:12:12.211488: step: 476/529, loss: 0.003266759216785431
2023-01-22 17:12:13.282541: step: 480/529, loss: 0.004201654810458422
2023-01-22 17:12:14.352689: step: 484/529, loss: 0.0026862011291086674
2023-01-22 17:12:15.424923: step: 488/529, loss: 0.002474110806360841
2023-01-22 17:12:16.495096: step: 492/529, loss: 0.006022781133651733
2023-01-22 17:12:17.555532: step: 496/529, loss: 0.005296438001096249
2023-01-22 17:12:18.615000: step: 500/529, loss: 0.002801610389724374
2023-01-22 17:12:19.682312: step: 504/529, loss: 0.0014753537252545357
2023-01-22 17:12:20.745437: step: 508/529, loss: 0.008723734878003597
2023-01-22 17:12:21.824616: step: 512/529, loss: 0.016350971534848213
2023-01-22 17:12:22.908279: step: 516/529, loss: 0.01831996440887451
2023-01-22 17:12:23.971548: step: 520/529, loss: 0.005710884928703308
2023-01-22 17:12:25.049431: step: 524/529, loss: 0.006975293159484863
2023-01-22 17:12:26.106675: step: 528/529, loss: 0.00898286048322916
2023-01-22 17:12:27.182682: step: 532/529, loss: 0.0007190429023467004
2023-01-22 17:12:28.250735: step: 536/529, loss: 0.0038729894440621138
2023-01-22 17:12:29.315732: step: 540/529, loss: 0.016032736748456955
2023-01-22 17:12:30.369969: step: 544/529, loss: 0.0020117787644267082
2023-01-22 17:12:31.460278: step: 548/529, loss: 0.00921130832284689
2023-01-22 17:12:32.530355: step: 552/529, loss: 0.0028724046424031258
2023-01-22 17:12:33.612729: step: 556/529, loss: 0.000245564995566383
2023-01-22 17:12:34.680701: step: 560/529, loss: 0.0024213865399360657
2023-01-22 17:12:35.746104: step: 564/529, loss: 0.003219675738364458
2023-01-22 17:12:36.808507: step: 568/529, loss: 0.002193629974499345
2023-01-22 17:12:37.873149: step: 572/529, loss: 0.005870449356734753
2023-01-22 17:12:38.937891: step: 576/529, loss: 0.014043132774531841
2023-01-22 17:12:40.018248: step: 580/529, loss: 0.0056515890173614025
2023-01-22 17:12:41.100808: step: 584/529, loss: 0.0042397934012115
2023-01-22 17:12:42.175768: step: 588/529, loss: 0.0008258468005806208
2023-01-22 17:12:43.246039: step: 592/529, loss: 0.0009125696960836649
2023-01-22 17:12:44.312614: step: 596/529, loss: 0.0019172930624336004
2023-01-22 17:12:45.387228: step: 600/529, loss: 0.004650169983506203
2023-01-22 17:12:46.463311: step: 604/529, loss: 0.049236856400966644
2023-01-22 17:12:47.536931: step: 608/529, loss: 0.0018092230893671513
2023-01-22 17:12:48.604176: step: 612/529, loss: 0.006917131599038839
2023-01-22 17:12:49.661497: step: 616/529, loss: 0.002702345373108983
2023-01-22 17:12:50.744278: step: 620/529, loss: 0.009933579713106155
2023-01-22 17:12:51.815044: step: 624/529, loss: 0.02553955465555191
2023-01-22 17:12:52.907264: step: 628/529, loss: 0.01620328798890114
2023-01-22 17:12:53.971707: step: 632/529, loss: 0.0029310528188943863
2023-01-22 17:12:55.042222: step: 636/529, loss: 0.008869489654898643
2023-01-22 17:12:56.110144: step: 640/529, loss: 0.0023660664446651936
2023-01-22 17:12:57.178695: step: 644/529, loss: 0.0003124453069176525
2023-01-22 17:12:58.264652: step: 648/529, loss: 0.001961875008419156
2023-01-22 17:12:59.355153: step: 652/529, loss: 0.040871672332286835
2023-01-22 17:13:00.424367: step: 656/529, loss: 0.002327162539586425
2023-01-22 17:13:01.498628: step: 660/529, loss: 0.0022622430697083473
2023-01-22 17:13:02.565850: step: 664/529, loss: 0.0035075093619525433
2023-01-22 17:13:03.643481: step: 668/529, loss: 0.0006215961766429245
2023-01-22 17:13:04.719818: step: 672/529, loss: 0.002107851207256317
2023-01-22 17:13:05.775221: step: 676/529, loss: 0.003571446519345045
2023-01-22 17:13:06.860827: step: 680/529, loss: 0.0031601879745721817
2023-01-22 17:13:07.939655: step: 684/529, loss: 0.006430068053305149
2023-01-22 17:13:09.002893: step: 688/529, loss: 0.006697945296764374
2023-01-22 17:13:10.081274: step: 692/529, loss: 0.012313859537243843
2023-01-22 17:13:11.182214: step: 696/529, loss: 0.006500555202364922
2023-01-22 17:13:12.254354: step: 700/529, loss: 0.004255449865013361
2023-01-22 17:13:13.341149: step: 704/529, loss: 0.010104414075613022
2023-01-22 17:13:14.418317: step: 708/529, loss: 0.006870902143418789
2023-01-22 17:13:15.489188: step: 712/529, loss: 0.0004085441760253161
2023-01-22 17:13:16.546337: step: 716/529, loss: 2.9241049560368992e-05
2023-01-22 17:13:17.619499: step: 720/529, loss: 0.01358101237565279
2023-01-22 17:13:18.699157: step: 724/529, loss: 0.0013228950556367636
2023-01-22 17:13:19.774921: step: 728/529, loss: 0.008493266999721527
2023-01-22 17:13:20.837798: step: 732/529, loss: 0.00284643960185349
2023-01-22 17:13:21.923547: step: 736/529, loss: 0.00036593960248865187
2023-01-22 17:13:23.004953: step: 740/529, loss: 0.004394339397549629
2023-01-22 17:13:24.095103: step: 744/529, loss: 0.0003114200080744922
2023-01-22 17:13:25.157826: step: 748/529, loss: 0.018969858065247536
2023-01-22 17:13:26.244950: step: 752/529, loss: 0.0021657058969140053
2023-01-22 17:13:27.325321: step: 756/529, loss: 0.01967126876115799
2023-01-22 17:13:28.399307: step: 760/529, loss: 0.01050269603729248
2023-01-22 17:13:29.474984: step: 764/529, loss: 0.001448205322958529
2023-01-22 17:13:30.542594: step: 768/529, loss: 0.010337715968489647
2023-01-22 17:13:31.624069: step: 772/529, loss: 0.0022648551966995
2023-01-22 17:13:32.696855: step: 776/529, loss: 0.003120388835668564
2023-01-22 17:13:33.771195: step: 780/529, loss: 0.004174788948148489
2023-01-22 17:13:34.852336: step: 784/529, loss: 0.023587878793478012
2023-01-22 17:13:35.929059: step: 788/529, loss: 0.0042237709276378155
2023-01-22 17:13:37.007349: step: 792/529, loss: 0.0021804224234074354
2023-01-22 17:13:38.078019: step: 796/529, loss: 0.0009366533486172557
2023-01-22 17:13:39.157121: step: 800/529, loss: 0.001944833085872233
2023-01-22 17:13:40.261535: step: 804/529, loss: 0.0083340248093009
2023-01-22 17:13:41.339549: step: 808/529, loss: 0.008067324757575989
2023-01-22 17:13:42.413249: step: 812/529, loss: 0.000578813545871526
2023-01-22 17:13:43.494252: step: 816/529, loss: 0.004300620872527361
2023-01-22 17:13:44.580365: step: 820/529, loss: 0.0051774862222373486
2023-01-22 17:13:45.647664: step: 824/529, loss: 0.0012338312808424234
2023-01-22 17:13:46.745391: step: 828/529, loss: 0.0034790572244673967
2023-01-22 17:13:47.842847: step: 832/529, loss: 0.001092011807486415
2023-01-22 17:13:48.924605: step: 836/529, loss: 0.009042570367455482
2023-01-22 17:13:49.997668: step: 840/529, loss: 0.0023971109185367823
2023-01-22 17:13:51.063280: step: 844/529, loss: 0.004049123730510473
2023-01-22 17:13:52.156259: step: 848/529, loss: 0.009170043282210827
2023-01-22 17:13:53.242805: step: 852/529, loss: 0.0012786417501047254
2023-01-22 17:13:54.325622: step: 856/529, loss: 0.021059595048427582
2023-01-22 17:13:55.416515: step: 860/529, loss: 0.004077080637216568
2023-01-22 17:13:56.497882: step: 864/529, loss: 0.0037740645930171013
2023-01-22 17:13:57.584395: step: 868/529, loss: 0.00802623201161623
2023-01-22 17:13:58.666605: step: 872/529, loss: 0.0048888931050896645
2023-01-22 17:13:59.753872: step: 876/529, loss: 0.000670494104269892
2023-01-22 17:14:00.847539: step: 880/529, loss: 0.006875012535601854
2023-01-22 17:14:01.953267: step: 884/529, loss: 0.0015024887397885323
2023-01-22 17:14:03.046001: step: 888/529, loss: 0.007486126851290464
2023-01-22 17:14:04.131902: step: 892/529, loss: 0.005453349556773901
2023-01-22 17:14:05.218977: step: 896/529, loss: 1.5941181118250825e-05
2023-01-22 17:14:06.341811: step: 900/529, loss: 0.013964889571070671
2023-01-22 17:14:07.436186: step: 904/529, loss: 0.0007833112613297999
2023-01-22 17:14:08.503040: step: 908/529, loss: 0.0020404993556439877
2023-01-22 17:14:09.591185: step: 912/529, loss: 0.024872416630387306
2023-01-22 17:14:10.690383: step: 916/529, loss: 0.0018921869341284037
2023-01-22 17:14:11.765538: step: 920/529, loss: 0.007095129694789648
2023-01-22 17:14:12.885097: step: 924/529, loss: 0.007776946760714054
2023-01-22 17:14:13.944657: step: 928/529, loss: 8.95168795977952e-06
2023-01-22 17:14:15.037524: step: 932/529, loss: 0.0028668097220361233
2023-01-22 17:14:16.121596: step: 936/529, loss: 0.0028234587516635656
2023-01-22 17:14:17.204529: step: 940/529, loss: 0.004628787748515606
2023-01-22 17:14:18.274004: step: 944/529, loss: 0.0007252873620018363
2023-01-22 17:14:19.366625: step: 948/529, loss: 0.0024532407987862825
2023-01-22 17:14:20.438827: step: 952/529, loss: 0.0006805064040236175
2023-01-22 17:14:21.528768: step: 956/529, loss: 0.006331130396574736
2023-01-22 17:14:22.610875: step: 960/529, loss: 0.000772796745877713
2023-01-22 17:14:23.711853: step: 964/529, loss: 0.0010961184743791819
2023-01-22 17:14:24.816865: step: 968/529, loss: 0.005595693364739418
2023-01-22 17:14:25.921243: step: 972/529, loss: 0.00617518974468112
2023-01-22 17:14:26.994898: step: 976/529, loss: 0.002138980431482196
2023-01-22 17:14:28.089758: step: 980/529, loss: 0.00802935566753149
2023-01-22 17:14:29.176267: step: 984/529, loss: 0.00715281255543232
2023-01-22 17:14:30.298663: step: 988/529, loss: 0.002921774983406067
2023-01-22 17:14:31.364773: step: 992/529, loss: 0.0065352581441402435
2023-01-22 17:14:32.442989: step: 996/529, loss: 0.004722020588815212
2023-01-22 17:14:33.525270: step: 1000/529, loss: 0.009458709508180618
2023-01-22 17:14:34.598018: step: 1004/529, loss: 0.005019423086196184
2023-01-22 17:14:35.702298: step: 1008/529, loss: 0.0004274088714737445
2023-01-22 17:14:36.797586: step: 1012/529, loss: 0.0066294982098042965
2023-01-22 17:14:37.893386: step: 1016/529, loss: 0.0027282305527478456
2023-01-22 17:14:38.980169: step: 1020/529, loss: 0.0020150088239461184
2023-01-22 17:14:40.066936: step: 1024/529, loss: 0.007532848045229912
2023-01-22 17:14:41.154567: step: 1028/529, loss: 9.887239139061421e-05
2023-01-22 17:14:42.232875: step: 1032/529, loss: 0.002379458397626877
2023-01-22 17:14:43.348572: step: 1036/529, loss: 0.0005518639227375388
2023-01-22 17:14:44.431792: step: 1040/529, loss: 0.008010240271687508
2023-01-22 17:14:45.504648: step: 1044/529, loss: 0.002007808769121766
2023-01-22 17:14:46.597690: step: 1048/529, loss: 0.0017985260346904397
2023-01-22 17:14:47.674228: step: 1052/529, loss: 0.00574650801718235
2023-01-22 17:14:48.771202: step: 1056/529, loss: 0.00014476251089945436
2023-01-22 17:14:49.851351: step: 1060/529, loss: 0.0032546704169362783
2023-01-22 17:14:50.937149: step: 1064/529, loss: 0.004099247511476278
2023-01-22 17:14:52.008890: step: 1068/529, loss: 0.0032230836804956198
2023-01-22 17:14:53.099113: step: 1072/529, loss: 0.007470614276826382
2023-01-22 17:14:54.201812: step: 1076/529, loss: 0.0032864778768271208
2023-01-22 17:14:55.290450: step: 1080/529, loss: 0.005386980250477791
2023-01-22 17:14:56.384384: step: 1084/529, loss: 0.005451235454529524
2023-01-22 17:14:57.459473: step: 1088/529, loss: 0.006932253483682871
2023-01-22 17:14:58.536656: step: 1092/529, loss: 0.002052298281341791
2023-01-22 17:14:59.606940: step: 1096/529, loss: 0.007956176996231079
2023-01-22 17:15:00.692073: step: 1100/529, loss: 0.010404829867184162
2023-01-22 17:15:01.761166: step: 1104/529, loss: 0.00186672352720052
2023-01-22 17:15:02.881433: step: 1108/529, loss: 0.006265898235142231
2023-01-22 17:15:03.971046: step: 1112/529, loss: 0.006293782033026218
2023-01-22 17:15:05.051471: step: 1116/529, loss: 0.000141568758408539
2023-01-22 17:15:06.141446: step: 1120/529, loss: 0.00019353433162905276
2023-01-22 17:15:07.208982: step: 1124/529, loss: 0.001994740217924118
2023-01-22 17:15:08.275469: step: 1128/529, loss: 0.0038161971606314182
2023-01-22 17:15:09.364155: step: 1132/529, loss: 0.004771463107317686
2023-01-22 17:15:10.453436: step: 1136/529, loss: 0.009334413334727287
2023-01-22 17:15:11.524465: step: 1140/529, loss: 0.002802507719025016
2023-01-22 17:15:12.613479: step: 1144/529, loss: 0.004227387253195047
2023-01-22 17:15:13.714386: step: 1148/529, loss: 0.002585578477010131
2023-01-22 17:15:14.802117: step: 1152/529, loss: 0.005385723430663347
2023-01-22 17:15:15.875609: step: 1156/529, loss: 4.5131346837479214e-07
2023-01-22 17:15:16.943815: step: 1160/529, loss: 0.02335977926850319
2023-01-22 17:15:18.044774: step: 1164/529, loss: 0.001962715294212103
2023-01-22 17:15:19.125418: step: 1168/529, loss: 0.011584354564547539
2023-01-22 17:15:20.193182: step: 1172/529, loss: 0.0030808988958597183
2023-01-22 17:15:21.277709: step: 1176/529, loss: 0.00456633185967803
2023-01-22 17:15:22.353052: step: 1180/529, loss: 0.028549674898386
2023-01-22 17:15:23.427449: step: 1184/529, loss: 0.0036442154087126255
2023-01-22 17:15:24.509970: step: 1188/529, loss: 0.00785110704600811
2023-01-22 17:15:25.596231: step: 1192/529, loss: 0.013239417225122452
2023-01-22 17:15:26.667978: step: 1196/529, loss: 0.0076675256714224815
2023-01-22 17:15:27.777598: step: 1200/529, loss: 0.001430810079909861
2023-01-22 17:15:28.838487: step: 1204/529, loss: 0.008416172116994858
2023-01-22 17:15:29.909570: step: 1208/529, loss: 0.001066521625034511
2023-01-22 17:15:31.009018: step: 1212/529, loss: 0.007978377863764763
2023-01-22 17:15:32.090609: step: 1216/529, loss: 0.007027463987469673
2023-01-22 17:15:33.183570: step: 1220/529, loss: 0.013067848980426788
2023-01-22 17:15:34.256436: step: 1224/529, loss: 0.00699908472597599
2023-01-22 17:15:35.333248: step: 1228/529, loss: 0.035781923681497574
2023-01-22 17:15:36.397542: step: 1232/529, loss: 0.009348358027637005
2023-01-22 17:15:37.496445: step: 1236/529, loss: 0.00537651963531971
2023-01-22 17:15:38.580591: step: 1240/529, loss: 0.03756602853536606
2023-01-22 17:15:39.657217: step: 1244/529, loss: 0.008057399652898312
2023-01-22 17:15:40.739737: step: 1248/529, loss: 0.0017485424177721143
2023-01-22 17:15:41.820010: step: 1252/529, loss: 0.005797643214464188
2023-01-22 17:15:42.895745: step: 1256/529, loss: 0.00043898308649659157
2023-01-22 17:15:43.952814: step: 1260/529, loss: 0.0001829609536798671
2023-01-22 17:15:45.037800: step: 1264/529, loss: 0.001816952251829207
2023-01-22 17:15:46.132393: step: 1268/529, loss: 0.002002737717702985
2023-01-22 17:15:47.209827: step: 1272/529, loss: 0.004937693476676941
2023-01-22 17:15:48.283010: step: 1276/529, loss: 0.008246760815382004
2023-01-22 17:15:49.360310: step: 1280/529, loss: 0.004174930974841118
2023-01-22 17:15:50.448925: step: 1284/529, loss: 0.007025341037660837
2023-01-22 17:15:51.529040: step: 1288/529, loss: 0.00136400549672544
2023-01-22 17:15:52.601924: step: 1292/529, loss: 0.004458239767700434
2023-01-22 17:15:53.667994: step: 1296/529, loss: 0.002784284995868802
2023-01-22 17:15:54.753472: step: 1300/529, loss: 0.008618834428489208
2023-01-22 17:15:55.831412: step: 1304/529, loss: 2.4947779820649885e-05
2023-01-22 17:15:56.904462: step: 1308/529, loss: 0.013042942620813847
2023-01-22 17:15:57.972733: step: 1312/529, loss: 0.000932298949919641
2023-01-22 17:15:59.041943: step: 1316/529, loss: 0.00020931493781972677
2023-01-22 17:16:00.104386: step: 1320/529, loss: 0.005391411483287811
2023-01-22 17:16:01.201027: step: 1324/529, loss: 0.0030733859166502953
2023-01-22 17:16:02.273077: step: 1328/529, loss: 0.0014090086333453655
2023-01-22 17:16:03.344722: step: 1332/529, loss: 0.001266465405933559
2023-01-22 17:16:04.417300: step: 1336/529, loss: 0.011990770697593689
2023-01-22 17:16:05.489574: step: 1340/529, loss: 0.0025625831913203
2023-01-22 17:16:06.557809: step: 1344/529, loss: 0.0024642636999487877
2023-01-22 17:16:07.619637: step: 1348/529, loss: 0.0011555214878171682
2023-01-22 17:16:08.689291: step: 1352/529, loss: 0.005239961203187704
2023-01-22 17:16:09.761921: step: 1356/529, loss: 0.0005212591495364904
2023-01-22 17:16:10.874578: step: 1360/529, loss: 0.0033456392120569944
2023-01-22 17:16:11.958138: step: 1364/529, loss: 0.0008974817465059459
2023-01-22 17:16:13.032575: step: 1368/529, loss: 0.0036943599116057158
2023-01-22 17:16:14.108369: step: 1372/529, loss: 0.004358185920864344
2023-01-22 17:16:15.167035: step: 1376/529, loss: 0.01866780035197735
2023-01-22 17:16:16.231511: step: 1380/529, loss: 0.009757593274116516
2023-01-22 17:16:17.316554: step: 1384/529, loss: 0.003262993646785617
2023-01-22 17:16:18.398461: step: 1388/529, loss: 0.0009631969733163714
2023-01-22 17:16:19.458999: step: 1392/529, loss: 0.00368310185149312
2023-01-22 17:16:20.552690: step: 1396/529, loss: 4.6427554480032995e-05
2023-01-22 17:16:21.628651: step: 1400/529, loss: 0.0003410500066820532
2023-01-22 17:16:22.716117: step: 1404/529, loss: 0.028717441484332085
2023-01-22 17:16:23.801672: step: 1408/529, loss: 0.005228606518357992
2023-01-22 17:16:24.879769: step: 1412/529, loss: 0.001336421468295157
2023-01-22 17:16:25.962920: step: 1416/529, loss: 0.00861088652163744
2023-01-22 17:16:27.025091: step: 1420/529, loss: 0.0001997453800868243
2023-01-22 17:16:28.095106: step: 1424/529, loss: 0.013761427253484726
2023-01-22 17:16:29.186950: step: 1428/529, loss: 0.004547123331576586
2023-01-22 17:16:30.255947: step: 1432/529, loss: 0.001521176309324801
2023-01-22 17:16:31.320662: step: 1436/529, loss: 0.0013128601713106036
2023-01-22 17:16:32.391546: step: 1440/529, loss: 0.00041359514580108225
2023-01-22 17:16:33.454434: step: 1444/529, loss: 0.0028874811250716448
2023-01-22 17:16:34.507249: step: 1448/529, loss: 0.00205975491553545
2023-01-22 17:16:35.592116: step: 1452/529, loss: 0.04599124938249588
2023-01-22 17:16:36.664982: step: 1456/529, loss: 0.0007727158372290432
2023-01-22 17:16:37.729750: step: 1460/529, loss: 5.3414946705743205e-06
2023-01-22 17:16:38.789046: step: 1464/529, loss: 0.002363678067922592
2023-01-22 17:16:39.869716: step: 1468/529, loss: 0.004923494067043066
2023-01-22 17:16:40.938933: step: 1472/529, loss: 0.0018438565311953425
2023-01-22 17:16:42.020081: step: 1476/529, loss: 0.0019986480474472046
2023-01-22 17:16:43.105549: step: 1480/529, loss: 0.010694275610148907
2023-01-22 17:16:44.179001: step: 1484/529, loss: 0.002109937369823456
2023-01-22 17:16:45.264922: step: 1488/529, loss: 0.011114335618913174
2023-01-22 17:16:46.354460: step: 1492/529, loss: 0.0011281033512204885
2023-01-22 17:16:47.419277: step: 1496/529, loss: 0.006920067593455315
2023-01-22 17:16:48.488977: step: 1500/529, loss: 0.0074417442083358765
2023-01-22 17:16:49.584230: step: 1504/529, loss: 0.010387626476585865
2023-01-22 17:16:50.661304: step: 1508/529, loss: 0.0024306965060532093
2023-01-22 17:16:51.745208: step: 1512/529, loss: 0.012259759940207005
2023-01-22 17:16:52.820395: step: 1516/529, loss: 0.05915343761444092
2023-01-22 17:16:53.907491: step: 1520/529, loss: 0.012260396033525467
2023-01-22 17:16:54.999118: step: 1524/529, loss: 0.005930379033088684
2023-01-22 17:16:56.079814: step: 1528/529, loss: 0.0002930450427811593
2023-01-22 17:16:57.166146: step: 1532/529, loss: 0.011883622966706753
2023-01-22 17:16:58.238346: step: 1536/529, loss: 0.01701703481376171
2023-01-22 17:16:59.308088: step: 1540/529, loss: 0.0023777985479682684
2023-01-22 17:17:00.386573: step: 1544/529, loss: 0.0089075593277812
2023-01-22 17:17:01.459388: step: 1548/529, loss: 0.003510445822030306
2023-01-22 17:17:02.532453: step: 1552/529, loss: 0.007700522430241108
2023-01-22 17:17:03.598291: step: 1556/529, loss: 0.004346936475485563
2023-01-22 17:17:04.658136: step: 1560/529, loss: 0.004421493969857693
2023-01-22 17:17:05.732021: step: 1564/529, loss: 0.007850480265915394
2023-01-22 17:17:06.815556: step: 1568/529, loss: 0.03238620236515999
2023-01-22 17:17:07.896733: step: 1572/529, loss: 0.003119183937087655
2023-01-22 17:17:08.970546: step: 1576/529, loss: 0.032034046947956085
2023-01-22 17:17:10.029979: step: 1580/529, loss: 0.0058512696996331215
2023-01-22 17:17:11.098508: step: 1584/529, loss: 0.0043077231384813786
2023-01-22 17:17:12.166810: step: 1588/529, loss: 0.0018022634321823716
2023-01-22 17:17:13.228652: step: 1592/529, loss: 0.005876576527953148
2023-01-22 17:17:14.298855: step: 1596/529, loss: 0.0017832991434261203
2023-01-22 17:17:15.359033: step: 1600/529, loss: 0.010564473457634449
2023-01-22 17:17:16.451968: step: 1604/529, loss: 0.0007911696447990835
2023-01-22 17:17:17.523636: step: 1608/529, loss: 0.0024978939909487963
2023-01-22 17:17:18.597021: step: 1612/529, loss: 0.0014426166890189052
2023-01-22 17:17:19.659865: step: 1616/529, loss: 0.0007707003387622535
2023-01-22 17:17:20.726983: step: 1620/529, loss: 0.0016293848166242242
2023-01-22 17:17:21.794484: step: 1624/529, loss: 0.0015996628208085895
2023-01-22 17:17:22.853869: step: 1628/529, loss: 0.005285800434648991
2023-01-22 17:17:23.924518: step: 1632/529, loss: 0.0022937017492949963
2023-01-22 17:17:25.013922: step: 1636/529, loss: 0.01592060923576355
2023-01-22 17:17:26.078655: step: 1640/529, loss: 0.002437553135678172
2023-01-22 17:17:27.125831: step: 1644/529, loss: 0.016958992928266525
2023-01-22 17:17:28.204352: step: 1648/529, loss: 0.000696833711117506
2023-01-22 17:17:29.280079: step: 1652/529, loss: 0.00597717147320509
2023-01-22 17:17:30.351463: step: 1656/529, loss: 0.0001052335646818392
2023-01-22 17:17:31.437301: step: 1660/529, loss: 0.00012823617726098746
2023-01-22 17:17:32.508593: step: 1664/529, loss: 0.005667322780936956
2023-01-22 17:17:33.581506: step: 1668/529, loss: 0.0011264043860137463
2023-01-22 17:17:34.632356: step: 1672/529, loss: 0.005253660026937723
2023-01-22 17:17:35.697687: step: 1676/529, loss: 0.001289410749450326
2023-01-22 17:17:36.771338: step: 1680/529, loss: 0.0010281333234161139
2023-01-22 17:17:37.856438: step: 1684/529, loss: 0.00605596462264657
2023-01-22 17:17:38.936636: step: 1688/529, loss: 0.012970738112926483
2023-01-22 17:17:40.006603: step: 1692/529, loss: 0.005011787638068199
2023-01-22 17:17:41.101056: step: 1696/529, loss: 0.003135734237730503
2023-01-22 17:17:42.157167: step: 1700/529, loss: 0.00018702501256484538
2023-01-22 17:17:43.252675: step: 1704/529, loss: 0.0030305900145322084
2023-01-22 17:17:44.335140: step: 1708/529, loss: 0.02004946395754814
2023-01-22 17:17:45.408063: step: 1712/529, loss: 0.006373633164912462
2023-01-22 17:17:46.488865: step: 1716/529, loss: 0.0026312260888516903
2023-01-22 17:17:47.567134: step: 1720/529, loss: 0.006205298472195864
2023-01-22 17:17:48.617238: step: 1724/529, loss: 0.004602530039846897
2023-01-22 17:17:49.675032: step: 1728/529, loss: 0.006025823298841715
2023-01-22 17:17:50.726865: step: 1732/529, loss: 0.013049333356320858
2023-01-22 17:17:51.788240: step: 1736/529, loss: 0.006153861526399851
2023-01-22 17:17:52.854673: step: 1740/529, loss: 0.005557524040341377
2023-01-22 17:17:53.929547: step: 1744/529, loss: 0.007490483112633228
2023-01-22 17:17:54.981250: step: 1748/529, loss: 0.008488928899168968
2023-01-22 17:17:56.060001: step: 1752/529, loss: 0.0064591411501169205
2023-01-22 17:17:57.134466: step: 1756/529, loss: 0.0013906044187024236
2023-01-22 17:17:58.199559: step: 1760/529, loss: 0.005087839439511299
2023-01-22 17:17:59.269416: step: 1764/529, loss: 0.0013060927158221602
2023-01-22 17:18:00.351864: step: 1768/529, loss: 0.005546437576413155
2023-01-22 17:18:01.424460: step: 1772/529, loss: 0.0034699239768087864
2023-01-22 17:18:02.505906: step: 1776/529, loss: 0.0005160251748748124
2023-01-22 17:18:03.584035: step: 1780/529, loss: 3.356958768563345e-05
2023-01-22 17:18:04.652364: step: 1784/529, loss: 0.006278616841882467
2023-01-22 17:18:05.728279: step: 1788/529, loss: 0.005382593255490065
2023-01-22 17:18:06.813694: step: 1792/529, loss: 0.0037666133139282465
2023-01-22 17:18:07.899345: step: 1796/529, loss: 0.0072418502531945705
2023-01-22 17:18:08.972973: step: 1800/529, loss: 0.00019383685139473528
2023-01-22 17:18:10.040952: step: 1804/529, loss: 0.001018869923427701
2023-01-22 17:18:11.108588: step: 1808/529, loss: 0.003560728393495083
2023-01-22 17:18:12.172945: step: 1812/529, loss: 0.0006448279600590467
2023-01-22 17:18:13.243605: step: 1816/529, loss: 0.002446823287755251
2023-01-22 17:18:14.303258: step: 1820/529, loss: 0.0024071810767054558
2023-01-22 17:18:15.385018: step: 1824/529, loss: 0.0051125031895935535
2023-01-22 17:18:16.448340: step: 1828/529, loss: 0.00031027488876134157
2023-01-22 17:18:17.518189: step: 1832/529, loss: 0.009204480797052383
2023-01-22 17:18:18.603096: step: 1836/529, loss: 0.0008500593830831349
2023-01-22 17:18:19.677247: step: 1840/529, loss: 0.0037134967278689146
2023-01-22 17:18:20.753009: step: 1844/529, loss: 0.0012093615951016545
2023-01-22 17:18:21.820305: step: 1848/529, loss: 0.005602362100034952
2023-01-22 17:18:22.887141: step: 1852/529, loss: 0.005232165567576885
2023-01-22 17:18:23.951024: step: 1856/529, loss: 0.018830273300409317
2023-01-22 17:18:25.029800: step: 1860/529, loss: 0.011606309562921524
2023-01-22 17:18:26.106259: step: 1864/529, loss: 0.001993372105062008
2023-01-22 17:18:27.177605: step: 1868/529, loss: 0.007100284099578857
2023-01-22 17:18:28.253489: step: 1872/529, loss: 0.0010416858131065965
2023-01-22 17:18:29.317605: step: 1876/529, loss: 0.002694792114198208
2023-01-22 17:18:30.386206: step: 1880/529, loss: 0.002246998017653823
2023-01-22 17:18:31.442456: step: 1884/529, loss: 0.005340383853763342
2023-01-22 17:18:32.519852: step: 1888/529, loss: 0.0008305404917337
2023-01-22 17:18:33.604087: step: 1892/529, loss: 0.004039315041154623
2023-01-22 17:18:34.676351: step: 1896/529, loss: 0.007692957296967506
2023-01-22 17:18:35.741861: step: 1900/529, loss: 0.0009001350263133645
2023-01-22 17:18:36.824032: step: 1904/529, loss: 0.008609401993453503
2023-01-22 17:18:37.904258: step: 1908/529, loss: 0.0026894821785390377
2023-01-22 17:18:38.976533: step: 1912/529, loss: 0.00699479877948761
2023-01-22 17:18:40.063512: step: 1916/529, loss: 0.0025947594549506903
2023-01-22 17:18:41.133201: step: 1920/529, loss: 0.00038627785397693515
2023-01-22 17:18:42.193491: step: 1924/529, loss: 0.0004348678921815008
2023-01-22 17:18:43.268073: step: 1928/529, loss: 0.00037938178866170347
2023-01-22 17:18:44.323358: step: 1932/529, loss: 0.0001086424381355755
2023-01-22 17:18:45.375908: step: 1936/529, loss: 0.008144153282046318
2023-01-22 17:18:46.470547: step: 1940/529, loss: 0.0013748578494414687
2023-01-22 17:18:47.545298: step: 1944/529, loss: 0.000560526445042342
2023-01-22 17:18:48.623253: step: 1948/529, loss: 0.0007381871691904962
2023-01-22 17:18:49.686186: step: 1952/529, loss: 0.0025683450512588024
2023-01-22 17:18:50.762901: step: 1956/529, loss: 0.005808547139167786
2023-01-22 17:18:51.852227: step: 1960/529, loss: 0.0010733160888776183
2023-01-22 17:18:52.905528: step: 1964/529, loss: 0.0008478582021780312
2023-01-22 17:18:53.961923: step: 1968/529, loss: 0.000983109581284225
2023-01-22 17:18:55.029427: step: 1972/529, loss: 0.0032325664069503546
2023-01-22 17:18:56.102676: step: 1976/529, loss: 0.007949438877403736
2023-01-22 17:18:57.172927: step: 1980/529, loss: 0.0005663922638632357
2023-01-22 17:18:58.246150: step: 1984/529, loss: 0.0006114203715696931
2023-01-22 17:18:59.318248: step: 1988/529, loss: 0.0003220208454877138
2023-01-22 17:19:00.380808: step: 1992/529, loss: 0.0018726433627307415
2023-01-22 17:19:01.456791: step: 1996/529, loss: 0.010423687286674976
2023-01-22 17:19:02.525217: step: 2000/529, loss: 0.002392818219959736
2023-01-22 17:19:03.603157: step: 2004/529, loss: 0.0071152630262076855
2023-01-22 17:19:04.671234: step: 2008/529, loss: 0.014891195110976696
2023-01-22 17:19:05.744398: step: 2012/529, loss: 0.004344492219388485
2023-01-22 17:19:06.839668: step: 2016/529, loss: 0.0036844457499682903
2023-01-22 17:19:07.910807: step: 2020/529, loss: 0.003806793363764882
2023-01-22 17:19:08.967061: step: 2024/529, loss: 0.009753200225532055
2023-01-22 17:19:10.041681: step: 2028/529, loss: 0.002347629750147462
2023-01-22 17:19:11.124432: step: 2032/529, loss: 0.0012171134585514665
2023-01-22 17:19:12.223076: step: 2036/529, loss: 0.0045912074856460094
2023-01-22 17:19:13.280736: step: 2040/529, loss: 0.004901139065623283
2023-01-22 17:19:14.339061: step: 2044/529, loss: 0.0003906798083335161
2023-01-22 17:19:15.421624: step: 2048/529, loss: 0.0021583319175988436
2023-01-22 17:19:16.502770: step: 2052/529, loss: 0.004819855559617281
2023-01-22 17:19:17.567800: step: 2056/529, loss: 0.0005273776478134096
2023-01-22 17:19:18.632632: step: 2060/529, loss: 0.005431292578577995
2023-01-22 17:19:19.715863: step: 2064/529, loss: 0.011450282298028469
2023-01-22 17:19:20.779415: step: 2068/529, loss: 0.004794581793248653
2023-01-22 17:19:21.846323: step: 2072/529, loss: 0.0031150751747190952
2023-01-22 17:19:22.905780: step: 2076/529, loss: 0.016725575551390648
2023-01-22 17:19:23.966644: step: 2080/529, loss: 0.0034163992386311293
2023-01-22 17:19:25.048355: step: 2084/529, loss: 0.0029623941518366337
2023-01-22 17:19:26.122689: step: 2088/529, loss: 0.0058944872580468655
2023-01-22 17:19:27.190429: step: 2092/529, loss: 0.0022327504120767117
2023-01-22 17:19:28.251707: step: 2096/529, loss: 0.0022764084860682487
2023-01-22 17:19:29.316333: step: 2100/529, loss: 0.0009543506312184036
2023-01-22 17:19:30.405584: step: 2104/529, loss: 0.026266003027558327
2023-01-22 17:19:31.484408: step: 2108/529, loss: 0.004046869929879904
2023-01-22 17:19:32.558129: step: 2112/529, loss: 0.005345308221876621
2023-01-22 17:19:33.640574: step: 2116/529, loss: 0.011642795987427235
==================================================
Loss: 0.006
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3212370242214533, 'r': 0.35232447817836815, 'f1': 0.33606334841628965}, 'combined': 0.247625625148845, 'stategy': 1, 'epoch': 12}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30938928125985093, 'r': 0.30626126462946646, 'f1': 0.3078173264820873}, 'combined': 0.20095846184840932, 'stategy': 1, 'epoch': 12}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3230331803005008, 'r': 0.36716674573055025, 'f1': 0.34368894316163406}, 'combined': 0.25324448443488823, 'stategy': 1, 'epoch': 12}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33365609306255056, 'r': 0.31188257963659366, 'f1': 0.32240213457920563}, 'combined': 0.21048015003616533, 'stategy': 1, 'epoch': 12}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.315002129471891, 'r': 0.3508657495256167, 'f1': 0.33196813285457816}, 'combined': 0.24460809789284704, 'stategy': 1, 'epoch': 12}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32359053564682333, 'r': 0.3215105230209943, 'f1': 0.32254717602014077}, 'combined': 0.21057484030330434, 'stategy': 1, 'epoch': 12}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 12}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 12}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 12}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3230331803005008, 'r': 0.36716674573055025, 'f1': 0.34368894316163406}, 'combined': 0.25324448443488823, 'stategy': 1, 'epoch': 12}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33365609306255056, 'r': 0.31188257963659366, 'f1': 0.32240213457920563}, 'combined': 0.21048015003616533, 'stategy': 1, 'epoch': 12}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 17:22:12.778481: step: 4/529, loss: 0.00824214518070221
2023-01-22 17:22:13.852978: step: 8/529, loss: 0.0006485304911620915
2023-01-22 17:22:14.916102: step: 12/529, loss: 0.004493335727602243
2023-01-22 17:22:15.985053: step: 16/529, loss: 0.007203877437859774
2023-01-22 17:22:17.046936: step: 20/529, loss: 0.009456831030547619
2023-01-22 17:22:18.101020: step: 24/529, loss: 0.0017443131655454636
2023-01-22 17:22:19.164623: step: 28/529, loss: 0.01108352281153202
2023-01-22 17:22:20.220626: step: 32/529, loss: 0.01880197413265705
2023-01-22 17:22:21.284081: step: 36/529, loss: 0.0032266222406178713
2023-01-22 17:22:22.347124: step: 40/529, loss: 0.00032905503758229315
2023-01-22 17:22:23.417809: step: 44/529, loss: 2.7835616492666304e-05
2023-01-22 17:22:24.479259: step: 48/529, loss: 0.000580169667955488
2023-01-22 17:22:25.532891: step: 52/529, loss: 0.006601984612643719
2023-01-22 17:22:26.587067: step: 56/529, loss: 0.006240781396627426
2023-01-22 17:22:27.660037: step: 60/529, loss: 0.0003889532817993313
2023-01-22 17:22:28.717901: step: 64/529, loss: 0.009685706347227097
2023-01-22 17:22:29.781174: step: 68/529, loss: 0.005073095206171274
2023-01-22 17:22:30.843072: step: 72/529, loss: 0.0002205546188633889
2023-01-22 17:22:31.918897: step: 76/529, loss: 0.0005509615293703973
2023-01-22 17:22:32.970575: step: 80/529, loss: 3.432148787396727e-06
2023-01-22 17:22:34.047813: step: 84/529, loss: 0.0003260619705542922
2023-01-22 17:22:35.106924: step: 88/529, loss: 0.00610450329259038
2023-01-22 17:22:36.183661: step: 92/529, loss: 0.010843431577086449
2023-01-22 17:22:37.264930: step: 96/529, loss: 0.0023373360745608807
2023-01-22 17:22:38.354306: step: 100/529, loss: 0.0012215864844620228
2023-01-22 17:22:39.431573: step: 104/529, loss: 0.0003956040018238127
2023-01-22 17:22:40.488784: step: 108/529, loss: 0.006970307789742947
2023-01-22 17:22:41.551077: step: 112/529, loss: 0.00034082215279340744
2023-01-22 17:22:42.616407: step: 116/529, loss: 0.0028653612826019526
2023-01-22 17:22:43.684163: step: 120/529, loss: 0.0023257178254425526
2023-01-22 17:22:44.748923: step: 124/529, loss: 0.0014433900360018015
2023-01-22 17:22:45.840929: step: 128/529, loss: 0.0045508709736168385
2023-01-22 17:22:46.912863: step: 132/529, loss: 4.12813933508005e-05
2023-01-22 17:22:47.973222: step: 136/529, loss: 0.000526791496668011
2023-01-22 17:22:49.041844: step: 140/529, loss: 0.011098070070147514
2023-01-22 17:22:50.100503: step: 144/529, loss: 0.0017983197467401624
2023-01-22 17:22:51.162900: step: 148/529, loss: 0.001859365263953805
2023-01-22 17:22:52.238883: step: 152/529, loss: 0.013218419626355171
2023-01-22 17:22:53.315074: step: 156/529, loss: 0.007587966043502092
2023-01-22 17:22:54.376486: step: 160/529, loss: 0.0051147788763046265
2023-01-22 17:22:55.446296: step: 164/529, loss: 0.00010762804595287889
2023-01-22 17:22:56.515416: step: 168/529, loss: 0.00015817872190382332
2023-01-22 17:22:57.585431: step: 172/529, loss: 0.019348064437508583
2023-01-22 17:22:58.653117: step: 176/529, loss: 0.0064213513396680355
2023-01-22 17:22:59.728831: step: 180/529, loss: 0.00465433718636632
2023-01-22 17:23:00.812906: step: 184/529, loss: 0.0021932865492999554
2023-01-22 17:23:01.902723: step: 188/529, loss: 0.005030844826251268
2023-01-22 17:23:02.966690: step: 192/529, loss: 0.004534582607448101
2023-01-22 17:23:04.035074: step: 196/529, loss: 0.0021553875412791967
2023-01-22 17:23:05.098092: step: 200/529, loss: 0.004790895618498325
2023-01-22 17:23:06.177825: step: 204/529, loss: 0.0001650998747209087
2023-01-22 17:23:07.246795: step: 208/529, loss: 0.0021575833670794964
2023-01-22 17:23:08.325408: step: 212/529, loss: 0.005316279362887144
2023-01-22 17:23:09.397102: step: 216/529, loss: 0.0034932380076497793
2023-01-22 17:23:10.477517: step: 220/529, loss: 0.004438444040715694
2023-01-22 17:23:11.556372: step: 224/529, loss: 0.00034117026370950043
2023-01-22 17:23:12.630307: step: 228/529, loss: 0.011383119970560074
2023-01-22 17:23:13.713280: step: 232/529, loss: 0.001447061775252223
2023-01-22 17:23:14.788087: step: 236/529, loss: 0.0009878063574433327
2023-01-22 17:23:15.874977: step: 240/529, loss: 0.0016755458200350404
2023-01-22 17:23:16.948118: step: 244/529, loss: 0.0026080089155584574
2023-01-22 17:23:18.038326: step: 248/529, loss: 0.0010913778096437454
2023-01-22 17:23:19.134511: step: 252/529, loss: 0.0028230883181095123
2023-01-22 17:23:20.206657: step: 256/529, loss: 0.001103143789805472
2023-01-22 17:23:21.276390: step: 260/529, loss: 0.00041276152478531003
2023-01-22 17:23:22.349401: step: 264/529, loss: 0.025269627571105957
2023-01-22 17:23:23.418002: step: 268/529, loss: 0.015226365998387337
2023-01-22 17:23:24.479066: step: 272/529, loss: 8.569552301196381e-05
2023-01-22 17:23:25.543413: step: 276/529, loss: 0.0
2023-01-22 17:23:26.617123: step: 280/529, loss: 0.006448135245591402
2023-01-22 17:23:27.671121: step: 284/529, loss: 0.0026999583933502436
2023-01-22 17:23:28.743485: step: 288/529, loss: 0.00784483551979065
2023-01-22 17:23:29.827899: step: 292/529, loss: 0.0004777391441166401
2023-01-22 17:23:30.918660: step: 296/529, loss: 0.0008279381436295807
2023-01-22 17:23:32.000634: step: 300/529, loss: 0.006379679776728153
2023-01-22 17:23:33.072094: step: 304/529, loss: 0.0020584098529070616
2023-01-22 17:23:34.148731: step: 308/529, loss: 0.006110067013651133
2023-01-22 17:23:35.219582: step: 312/529, loss: 0.03464924544095993
2023-01-22 17:23:36.295218: step: 316/529, loss: 0.0020083491690456867
2023-01-22 17:23:37.361430: step: 320/529, loss: 0.00013349168875720352
2023-01-22 17:23:38.434051: step: 324/529, loss: 0.007500241044908762
2023-01-22 17:23:39.500954: step: 328/529, loss: 0.0023305623326450586
2023-01-22 17:23:40.577335: step: 332/529, loss: 0.005106762051582336
2023-01-22 17:23:41.653759: step: 336/529, loss: 0.004585073795169592
2023-01-22 17:23:42.732053: step: 340/529, loss: 0.00680381478741765
2023-01-22 17:23:43.819303: step: 344/529, loss: 0.001004521851427853
2023-01-22 17:23:44.897236: step: 348/529, loss: 0.008059404790401459
2023-01-22 17:23:45.975187: step: 352/529, loss: 0.008250962011516094
2023-01-22 17:23:47.050712: step: 356/529, loss: 0.001658450230024755
2023-01-22 17:23:48.124015: step: 360/529, loss: 0.0024763462133705616
2023-01-22 17:23:49.190169: step: 364/529, loss: 0.0008286912343464792
2023-01-22 17:23:50.267305: step: 368/529, loss: 0.00506360549479723
2023-01-22 17:23:51.355331: step: 372/529, loss: 0.0002563508751336485
2023-01-22 17:23:52.446791: step: 376/529, loss: 0.0045692203566432
2023-01-22 17:23:53.531940: step: 380/529, loss: 0.0001046157703967765
2023-01-22 17:23:54.600775: step: 384/529, loss: 0.004003176931291819
2023-01-22 17:23:55.664883: step: 388/529, loss: 0.012683391571044922
2023-01-22 17:23:56.756268: step: 392/529, loss: 0.009644143283367157
2023-01-22 17:23:57.827923: step: 396/529, loss: 0.0026218497660011053
2023-01-22 17:23:58.923421: step: 400/529, loss: 0.0028819614090025425
2023-01-22 17:23:59.991735: step: 404/529, loss: 0.00339402980171144
2023-01-22 17:24:01.085905: step: 408/529, loss: 0.0032723492477089167
2023-01-22 17:24:02.165462: step: 412/529, loss: 0.000563874957151711
2023-01-22 17:24:03.237130: step: 416/529, loss: 0.0002562661247793585
2023-01-22 17:24:04.298990: step: 420/529, loss: 6.370181893089466e-08
2023-01-22 17:24:05.368496: step: 424/529, loss: 0.0011810840805992484
2023-01-22 17:24:06.440513: step: 428/529, loss: 0.005647722166031599
2023-01-22 17:24:07.523414: step: 432/529, loss: 0.008015875704586506
2023-01-22 17:24:08.608924: step: 436/529, loss: 0.0013981559313833714
2023-01-22 17:24:09.682113: step: 440/529, loss: 0.006221064832061529
2023-01-22 17:24:10.751620: step: 444/529, loss: 0.005132558289915323
2023-01-22 17:24:11.826862: step: 448/529, loss: 0.00134725880343467
2023-01-22 17:24:12.930391: step: 452/529, loss: 0.015525266528129578
2023-01-22 17:24:14.000093: step: 456/529, loss: 0.0005615393165498972
2023-01-22 17:24:15.080374: step: 460/529, loss: 0.0008262925548478961
2023-01-22 17:24:16.153893: step: 464/529, loss: 0.0009931253734976053
2023-01-22 17:24:17.230498: step: 468/529, loss: 0.00593172712251544
2023-01-22 17:24:18.301647: step: 472/529, loss: 0.004466334357857704
2023-01-22 17:24:19.371240: step: 476/529, loss: 0.0019491706043481827
2023-01-22 17:24:20.460469: step: 480/529, loss: 0.0001354796695522964
2023-01-22 17:24:21.545389: step: 484/529, loss: 0.0017280488973483443
2023-01-22 17:24:22.626894: step: 488/529, loss: 0.0015871248906478286
2023-01-22 17:24:23.690269: step: 492/529, loss: 0.00016232201596722007
2023-01-22 17:24:24.762437: step: 496/529, loss: 0.004697137512266636
2023-01-22 17:24:25.842349: step: 500/529, loss: 0.0025716538075357676
2023-01-22 17:24:26.912627: step: 504/529, loss: 0.001128175645135343
2023-01-22 17:24:28.004769: step: 508/529, loss: 0.0031883204355835915
2023-01-22 17:24:29.084617: step: 512/529, loss: 0.00993662141263485
2023-01-22 17:24:30.157356: step: 516/529, loss: 0.0029723665211349726
2023-01-22 17:24:31.228024: step: 520/529, loss: 0.0053993407636880875
2023-01-22 17:24:32.310916: step: 524/529, loss: 0.0024499623104929924
2023-01-22 17:24:33.398027: step: 528/529, loss: 0.001859718351624906
2023-01-22 17:24:34.495283: step: 532/529, loss: 0.006356637459248304
2023-01-22 17:24:35.590481: step: 536/529, loss: 0.020191717892885208
2023-01-22 17:24:36.679899: step: 540/529, loss: 0.0018192763673141599
2023-01-22 17:24:37.772852: step: 544/529, loss: 0.00022298246040008962
2023-01-22 17:24:38.854248: step: 548/529, loss: 0.0011389312567189336
2023-01-22 17:24:39.944088: step: 552/529, loss: 0.0046478998847305775
2023-01-22 17:24:41.036480: step: 556/529, loss: 0.011164539493620396
2023-01-22 17:24:42.125196: step: 560/529, loss: 0.000698400370310992
2023-01-22 17:24:43.202264: step: 564/529, loss: 0.0031681659165769815
2023-01-22 17:24:44.295386: step: 568/529, loss: 0.0033868071623146534
2023-01-22 17:24:45.364171: step: 572/529, loss: 0.00022426863142754883
2023-01-22 17:24:46.444194: step: 576/529, loss: 0.006263082381337881
2023-01-22 17:24:47.517073: step: 580/529, loss: 0.0009689821163192391
2023-01-22 17:24:48.600359: step: 584/529, loss: 0.003132249228656292
2023-01-22 17:24:49.691188: step: 588/529, loss: 0.005541677121073008
2023-01-22 17:24:50.758771: step: 592/529, loss: 0.0068025351502001286
2023-01-22 17:24:51.821938: step: 596/529, loss: 0.0005151866935193539
2023-01-22 17:24:52.891124: step: 600/529, loss: 0.005062904674559832
2023-01-22 17:24:53.962428: step: 604/529, loss: 0.0010287613840773702
2023-01-22 17:24:55.033338: step: 608/529, loss: 0.010212545283138752
2023-01-22 17:24:56.098624: step: 612/529, loss: 0.0031777014955878258
2023-01-22 17:24:57.160633: step: 616/529, loss: 0.0008616489940322936
2023-01-22 17:24:58.242169: step: 620/529, loss: 0.003417890053242445
2023-01-22 17:24:59.321467: step: 624/529, loss: 0.002632226562127471
2023-01-22 17:25:00.392468: step: 628/529, loss: 3.271413879701868e-05
2023-01-22 17:25:01.483165: step: 632/529, loss: 0.0071709370240569115
2023-01-22 17:25:02.554369: step: 636/529, loss: 0.001597222755663097
2023-01-22 17:25:03.621829: step: 640/529, loss: 0.00589072797447443
2023-01-22 17:25:04.701745: step: 644/529, loss: 0.001144689624197781
2023-01-22 17:25:05.764218: step: 648/529, loss: 0.003911987412720919
2023-01-22 17:25:06.848908: step: 652/529, loss: 0.0004588759911712259
2023-01-22 17:25:07.918162: step: 656/529, loss: 0.00029177276883274317
2023-01-22 17:25:08.970555: step: 660/529, loss: 0.0014887326397001743
2023-01-22 17:25:10.049613: step: 664/529, loss: 0.004669911228120327
2023-01-22 17:25:11.114406: step: 668/529, loss: 0.007444572169333696
2023-01-22 17:25:12.196159: step: 672/529, loss: 0.0008700828766450286
2023-01-22 17:25:13.264218: step: 676/529, loss: 0.0003717791405506432
2023-01-22 17:25:14.381384: step: 680/529, loss: 0.0018614951986819506
2023-01-22 17:25:15.452237: step: 684/529, loss: 0.0014391134027391672
2023-01-22 17:25:16.527666: step: 688/529, loss: 1.0803304206774555e-07
2023-01-22 17:25:17.595902: step: 692/529, loss: 0.005155359860509634
2023-01-22 17:25:18.678715: step: 696/529, loss: 0.003998635336756706
2023-01-22 17:25:19.797203: step: 700/529, loss: 0.0009432635270059109
2023-01-22 17:25:20.867979: step: 704/529, loss: 0.0010925807291641831
2023-01-22 17:25:21.940220: step: 708/529, loss: 0.004977728705853224
2023-01-22 17:25:23.013900: step: 712/529, loss: 0.028033442795276642
2023-01-22 17:25:24.069811: step: 716/529, loss: 0.0008672356489114463
2023-01-22 17:25:25.156577: step: 720/529, loss: 0.0010278065456077456
2023-01-22 17:25:26.217656: step: 724/529, loss: 0.0009569845860823989
2023-01-22 17:25:27.293796: step: 728/529, loss: 0.006153136491775513
2023-01-22 17:25:28.369649: step: 732/529, loss: 0.0005688882665708661
2023-01-22 17:25:29.440672: step: 736/529, loss: 0.006432798225432634
2023-01-22 17:25:30.522753: step: 740/529, loss: 0.0031695724464952946
2023-01-22 17:25:31.587897: step: 744/529, loss: 0.002205257536843419
2023-01-22 17:25:32.664584: step: 748/529, loss: 0.001660765497945249
2023-01-22 17:25:33.746246: step: 752/529, loss: 0.000290944502921775
2023-01-22 17:25:34.817723: step: 756/529, loss: 0.004038677550852299
2023-01-22 17:25:35.887263: step: 760/529, loss: 0.018525337800383568
2023-01-22 17:25:36.974210: step: 764/529, loss: 0.004912679083645344
2023-01-22 17:25:38.051505: step: 768/529, loss: 0.037664324045181274
2023-01-22 17:25:39.128313: step: 772/529, loss: 0.03377256169915199
2023-01-22 17:25:40.202693: step: 776/529, loss: 0.001526806503534317
2023-01-22 17:25:41.277209: step: 780/529, loss: 0.0018826342420652509
2023-01-22 17:25:42.361495: step: 784/529, loss: 0.0022028882522135973
2023-01-22 17:25:43.432612: step: 788/529, loss: 0.0059320661239326
2023-01-22 17:25:44.510325: step: 792/529, loss: 1.5464382158825174e-05
2023-01-22 17:25:45.589722: step: 796/529, loss: 0.0032495378982275724
2023-01-22 17:25:46.661975: step: 800/529, loss: 0.0006169435800984502
2023-01-22 17:25:47.745013: step: 804/529, loss: 0.004915500525385141
2023-01-22 17:25:48.812032: step: 808/529, loss: 0.013608753681182861
2023-01-22 17:25:49.909255: step: 812/529, loss: 0.0049199918285012245
2023-01-22 17:25:50.997731: step: 816/529, loss: 0.006587619427591562
2023-01-22 17:25:52.065852: step: 820/529, loss: 0.0015551808755844831
2023-01-22 17:25:53.138145: step: 824/529, loss: 0.008166050538420677
2023-01-22 17:25:54.224700: step: 828/529, loss: 0.00920891109853983
2023-01-22 17:25:55.315589: step: 832/529, loss: 0.0018128411611542106
2023-01-22 17:25:56.394134: step: 836/529, loss: 0.0006175698363222182
2023-01-22 17:25:57.493301: step: 840/529, loss: 0.004237494897097349
2023-01-22 17:25:58.588045: step: 844/529, loss: 0.003978268709033728
2023-01-22 17:25:59.677115: step: 848/529, loss: 0.0027342909015715122
2023-01-22 17:26:00.734956: step: 852/529, loss: 0.010389260947704315
2023-01-22 17:26:01.822904: step: 856/529, loss: 0.005601401440799236
2023-01-22 17:26:02.907514: step: 860/529, loss: 0.0001558121875859797
2023-01-22 17:26:03.999309: step: 864/529, loss: 0.0004491571744438261
2023-01-22 17:26:05.086768: step: 868/529, loss: 0.0035772596020251513
2023-01-22 17:26:06.189655: step: 872/529, loss: 0.003511154092848301
2023-01-22 17:26:07.275170: step: 876/529, loss: 0.021909328177571297
2023-01-22 17:26:08.369658: step: 880/529, loss: 0.012795479036867619
2023-01-22 17:26:09.460540: step: 884/529, loss: 0.00991862639784813
2023-01-22 17:26:10.542853: step: 888/529, loss: 0.012951732613146305
2023-01-22 17:26:11.634632: step: 892/529, loss: 0.0009472208912484348
2023-01-22 17:26:12.722108: step: 896/529, loss: 0.000470205006422475
2023-01-22 17:26:13.803371: step: 900/529, loss: 0.0038967649452388287
2023-01-22 17:26:14.880592: step: 904/529, loss: 0.00014454267511609942
2023-01-22 17:26:15.956499: step: 908/529, loss: 0.00037391152000054717
2023-01-22 17:26:17.048982: step: 912/529, loss: 0.005236899945884943
2023-01-22 17:26:18.120600: step: 916/529, loss: 0.0035261260345578194
2023-01-22 17:26:19.208173: step: 920/529, loss: 0.0012421862920746207
2023-01-22 17:26:20.311344: step: 924/529, loss: 0.0034080306068062782
2023-01-22 17:26:21.390689: step: 928/529, loss: 0.0020261327736079693
2023-01-22 17:26:22.466969: step: 932/529, loss: 0.0039024525322020054
2023-01-22 17:26:23.565580: step: 936/529, loss: 0.0027381600812077522
2023-01-22 17:26:24.644135: step: 940/529, loss: 6.02755208092276e-05
2023-01-22 17:26:25.720521: step: 944/529, loss: 0.008762603625655174
2023-01-22 17:26:26.809602: step: 948/529, loss: 0.00030116699053905904
2023-01-22 17:26:27.892597: step: 952/529, loss: 0.0014694355195388198
2023-01-22 17:26:28.963759: step: 956/529, loss: 0.008344966918230057
2023-01-22 17:26:30.031951: step: 960/529, loss: 0.00015417247777804732
2023-01-22 17:26:31.114493: step: 964/529, loss: 0.004995978437364101
2023-01-22 17:26:32.210344: step: 968/529, loss: 0.0005209104856476188
2023-01-22 17:26:33.291499: step: 972/529, loss: 0.005219424609094858
2023-01-22 17:26:34.381678: step: 976/529, loss: 0.00030140328453853726
2023-01-22 17:26:35.473870: step: 980/529, loss: 0.004988627973943949
2023-01-22 17:26:36.562180: step: 984/529, loss: 0.0004941115621477365
2023-01-22 17:26:37.647551: step: 988/529, loss: 0.004638523794710636
2023-01-22 17:26:38.730933: step: 992/529, loss: 0.001124656293541193
2023-01-22 17:26:39.815640: step: 996/529, loss: 0.00223352387547493
2023-01-22 17:26:40.913911: step: 1000/529, loss: 0.001285680802538991
2023-01-22 17:26:42.015928: step: 1004/529, loss: 0.0013634903589263558
2023-01-22 17:26:43.105183: step: 1008/529, loss: 0.001708086347207427
2023-01-22 17:26:44.188929: step: 1012/529, loss: 0.004962691105902195
2023-01-22 17:26:45.272255: step: 1016/529, loss: 0.0010700155980885029
2023-01-22 17:26:46.366631: step: 1020/529, loss: 0.00023641200095880777
2023-01-22 17:26:47.450448: step: 1024/529, loss: 0.00754582742229104
2023-01-22 17:26:48.529377: step: 1028/529, loss: 0.005813295021653175
2023-01-22 17:26:49.598852: step: 1032/529, loss: 4.928624184685759e-05
2023-01-22 17:26:50.687107: step: 1036/529, loss: 0.0032214426901191473
2023-01-22 17:26:51.765385: step: 1040/529, loss: 0.006151001434773207
2023-01-22 17:26:52.848681: step: 1044/529, loss: 0.010917824693024158
2023-01-22 17:26:53.937339: step: 1048/529, loss: 0.005020971409976482
2023-01-22 17:26:55.025158: step: 1052/529, loss: 0.009902467019855976
2023-01-22 17:26:56.115700: step: 1056/529, loss: 0.0022045476362109184
2023-01-22 17:26:57.187416: step: 1060/529, loss: 0.007249363698065281
2023-01-22 17:26:58.286579: step: 1064/529, loss: 0.006000439636409283
2023-01-22 17:26:59.382454: step: 1068/529, loss: 0.011353102512657642
2023-01-22 17:27:00.482386: step: 1072/529, loss: 0.005109582561999559
2023-01-22 17:27:01.582455: step: 1076/529, loss: 0.0061624315567314625
2023-01-22 17:27:02.662353: step: 1080/529, loss: 0.00034367028274573386
2023-01-22 17:27:03.743678: step: 1084/529, loss: 0.0003387421602383256
2023-01-22 17:27:04.826696: step: 1088/529, loss: 0.006283136084675789
2023-01-22 17:27:05.931499: step: 1092/529, loss: 0.008878123946487904
2023-01-22 17:27:07.004747: step: 1096/529, loss: 6.844523886684328e-05
2023-01-22 17:27:08.084918: step: 1100/529, loss: 0.0013711864594370127
2023-01-22 17:27:09.163467: step: 1104/529, loss: 0.0066091218031942844
2023-01-22 17:27:10.245574: step: 1108/529, loss: 0.0019864237401634455
2023-01-22 17:27:11.332976: step: 1112/529, loss: 0.000602297717705369
2023-01-22 17:27:12.406224: step: 1116/529, loss: 0.002463366137817502
2023-01-22 17:27:13.501818: step: 1120/529, loss: 0.003219776088371873
2023-01-22 17:27:14.589106: step: 1124/529, loss: 0.02767278254032135
2023-01-22 17:27:15.674348: step: 1128/529, loss: 0.0003260983503423631
2023-01-22 17:27:16.752718: step: 1132/529, loss: 0.012269899249076843
2023-01-22 17:27:17.824528: step: 1136/529, loss: 8.498618990415707e-05
2023-01-22 17:27:18.904321: step: 1140/529, loss: 0.0058839088305830956
2023-01-22 17:27:19.979381: step: 1144/529, loss: 0.01344376616179943
2023-01-22 17:27:21.055129: step: 1148/529, loss: 0.0014127636095508933
2023-01-22 17:27:22.141995: step: 1152/529, loss: 0.0172192994505167
2023-01-22 17:27:23.251044: step: 1156/529, loss: 0.012244591489434242
2023-01-22 17:27:24.322774: step: 1160/529, loss: 0.006438829470425844
2023-01-22 17:27:25.404532: step: 1164/529, loss: 0.0033560418523848057
2023-01-22 17:27:26.503584: step: 1168/529, loss: 0.03704174607992172
2023-01-22 17:27:27.601813: step: 1172/529, loss: 0.001134713413193822
2023-01-22 17:27:28.686798: step: 1176/529, loss: 8.293869177578017e-05
2023-01-22 17:27:29.776687: step: 1180/529, loss: 0.007193255238234997
2023-01-22 17:27:30.852141: step: 1184/529, loss: 0.0035913093015551567
2023-01-22 17:27:31.936226: step: 1188/529, loss: 0.005067116115242243
2023-01-22 17:27:33.035277: step: 1192/529, loss: 0.03776457905769348
2023-01-22 17:27:34.117331: step: 1196/529, loss: 0.0029532411135733128
2023-01-22 17:27:35.206701: step: 1200/529, loss: 0.009159223176538944
2023-01-22 17:27:36.318595: step: 1204/529, loss: 0.003995794337242842
2023-01-22 17:27:37.405974: step: 1208/529, loss: 0.002940747421234846
2023-01-22 17:27:38.470151: step: 1212/529, loss: 0.005281684920191765
2023-01-22 17:27:39.591493: step: 1216/529, loss: 0.003792811883613467
2023-01-22 17:27:40.678493: step: 1220/529, loss: 7.246151653816923e-05
2023-01-22 17:27:41.762828: step: 1224/529, loss: 0.00017703989578876644
2023-01-22 17:27:42.877798: step: 1228/529, loss: 0.0006702755927108228
2023-01-22 17:27:43.967741: step: 1232/529, loss: 0.0014314763247966766
2023-01-22 17:27:45.034770: step: 1236/529, loss: 0.0014320998452603817
2023-01-22 17:27:46.112017: step: 1240/529, loss: 0.022254856303334236
2023-01-22 17:27:47.220754: step: 1244/529, loss: 0.011834208853542805
2023-01-22 17:27:48.307792: step: 1248/529, loss: 0.00435211043804884
2023-01-22 17:27:49.383990: step: 1252/529, loss: 0.006410572212189436
2023-01-22 17:27:50.450118: step: 1256/529, loss: 0.0004829451791010797
2023-01-22 17:27:51.524258: step: 1260/529, loss: 0.0005952382343821228
2023-01-22 17:27:52.599659: step: 1264/529, loss: 0.0013238408137112856
2023-01-22 17:27:53.697103: step: 1268/529, loss: 0.007921346463263035
2023-01-22 17:27:54.783158: step: 1272/529, loss: 0.00043858870049007237
2023-01-22 17:27:55.871665: step: 1276/529, loss: 0.00159892113879323
2023-01-22 17:27:56.963080: step: 1280/529, loss: 0.0639544203877449
2023-01-22 17:27:58.043879: step: 1284/529, loss: 0.0013967757113277912
2023-01-22 17:27:59.131837: step: 1288/529, loss: 3.5319928429089487e-05
2023-01-22 17:28:00.198316: step: 1292/529, loss: 0.010427518747746944
2023-01-22 17:28:01.265507: step: 1296/529, loss: 0.00037475820863619447
2023-01-22 17:28:02.344545: step: 1300/529, loss: 0.00021107254724483937
2023-01-22 17:28:03.404957: step: 1304/529, loss: 0.060003846883773804
2023-01-22 17:28:04.488274: step: 1308/529, loss: 0.02229604870080948
2023-01-22 17:28:05.559868: step: 1312/529, loss: 0.0038752174004912376
2023-01-22 17:28:06.634334: step: 1316/529, loss: 0.0001930451689986512
2023-01-22 17:28:07.702758: step: 1320/529, loss: 0.0027876130770891905
2023-01-22 17:28:08.792400: step: 1324/529, loss: 0.003849061904475093
2023-01-22 17:28:09.861549: step: 1328/529, loss: 0.005554105620831251
2023-01-22 17:28:10.938809: step: 1332/529, loss: 0.0014325926313176751
2023-01-22 17:28:12.022053: step: 1336/529, loss: 0.00343710882589221
2023-01-22 17:28:13.114841: step: 1340/529, loss: 0.03830718249082565
2023-01-22 17:28:14.176526: step: 1344/529, loss: 0.00295704766176641
2023-01-22 17:28:15.252477: step: 1348/529, loss: 0.002468763617798686
2023-01-22 17:28:16.326147: step: 1352/529, loss: 0.0012411042116582394
2023-01-22 17:28:17.387634: step: 1356/529, loss: 0.008442936465144157
2023-01-22 17:28:18.475575: step: 1360/529, loss: 0.0016720404382795095
2023-01-22 17:28:19.542965: step: 1364/529, loss: 0.000936595257371664
2023-01-22 17:28:20.621734: step: 1368/529, loss: 0.010597063228487968
2023-01-22 17:28:21.708056: step: 1372/529, loss: 0.003616020316258073
2023-01-22 17:28:22.778379: step: 1376/529, loss: 0.001012818538583815
2023-01-22 17:28:23.863942: step: 1380/529, loss: 0.0013415602734312415
2023-01-22 17:28:24.937310: step: 1384/529, loss: 0.0027728863060474396
2023-01-22 17:28:26.021070: step: 1388/529, loss: 0.00444216001778841
2023-01-22 17:28:27.094218: step: 1392/529, loss: 0.00015794373757671565
2023-01-22 17:28:28.162795: step: 1396/529, loss: 0.002407039748504758
2023-01-22 17:28:29.251147: step: 1400/529, loss: 0.0016656331717967987
2023-01-22 17:28:30.322030: step: 1404/529, loss: 0.0021918434649705887
2023-01-22 17:28:31.398454: step: 1408/529, loss: 0.002362446393817663
2023-01-22 17:28:32.466165: step: 1412/529, loss: 0.004766460508108139
2023-01-22 17:28:33.528960: step: 1416/529, loss: 0.005630891770124435
2023-01-22 17:28:34.606654: step: 1420/529, loss: 0.0015056979609653354
2023-01-22 17:28:35.675868: step: 1424/529, loss: 0.013482719659805298
2023-01-22 17:28:36.751746: step: 1428/529, loss: 0.005831719841808081
2023-01-22 17:28:37.817540: step: 1432/529, loss: 0.0019798949360847473
2023-01-22 17:28:38.893033: step: 1436/529, loss: 0.002944647567346692
2023-01-22 17:28:39.962487: step: 1440/529, loss: 0.0016318289563059807
2023-01-22 17:28:41.020326: step: 1444/529, loss: 0.007818658836185932
2023-01-22 17:28:42.088218: step: 1448/529, loss: 0.00045890428009442985
2023-01-22 17:28:43.165803: step: 1452/529, loss: 0.010443691164255142
2023-01-22 17:28:44.236735: step: 1456/529, loss: 0.006630977150052786
2023-01-22 17:28:45.323966: step: 1460/529, loss: 0.0072214072570204735
2023-01-22 17:28:46.399473: step: 1464/529, loss: 0.002359408885240555
2023-01-22 17:28:47.471052: step: 1468/529, loss: 0.00011643358448054641
2023-01-22 17:28:48.535388: step: 1472/529, loss: 0.010804359801113605
2023-01-22 17:28:49.602703: step: 1476/529, loss: 0.003163361456245184
2023-01-22 17:28:50.684649: step: 1480/529, loss: 0.0021558557637035847
2023-01-22 17:28:51.770077: step: 1484/529, loss: 0.0018655690364539623
2023-01-22 17:28:52.833318: step: 1488/529, loss: 0.001293476321734488
2023-01-22 17:28:53.925099: step: 1492/529, loss: 0.0015365119324997067
2023-01-22 17:28:55.015634: step: 1496/529, loss: 0.0004397197044454515
2023-01-22 17:28:56.095961: step: 1500/529, loss: 0.00013709231279790401
2023-01-22 17:28:57.164906: step: 1504/529, loss: 0.003821911755949259
2023-01-22 17:28:58.257510: step: 1508/529, loss: 7.101294613676146e-05
2023-01-22 17:28:59.331191: step: 1512/529, loss: 0.0037749484181404114
2023-01-22 17:29:00.414854: step: 1516/529, loss: 0.0071118841879069805
2023-01-22 17:29:01.485827: step: 1520/529, loss: 0.0004207525053061545
2023-01-22 17:29:02.542022: step: 1524/529, loss: 0.0030081754084676504
2023-01-22 17:29:03.639180: step: 1528/529, loss: 0.000305487570585683
2023-01-22 17:29:04.713492: step: 1532/529, loss: 0.004214287269860506
2023-01-22 17:29:05.793901: step: 1536/529, loss: 0.011443152092397213
2023-01-22 17:29:06.866202: step: 1540/529, loss: 0.010332275182008743
2023-01-22 17:29:07.939639: step: 1544/529, loss: 0.0007756793638691306
2023-01-22 17:29:09.010782: step: 1548/529, loss: 0.003838974516838789
2023-01-22 17:29:10.074333: step: 1552/529, loss: 0.004816325381398201
2023-01-22 17:29:11.138001: step: 1556/529, loss: 0.0028927952516824007
2023-01-22 17:29:12.200240: step: 1560/529, loss: 0.002183598931878805
2023-01-22 17:29:13.255961: step: 1564/529, loss: 0.004798260051757097
2023-01-22 17:29:14.321111: step: 1568/529, loss: 0.0064127701334655285
2023-01-22 17:29:15.389790: step: 1572/529, loss: 0.002084509702399373
2023-01-22 17:29:16.466746: step: 1576/529, loss: 0.006421895697712898
2023-01-22 17:29:17.537380: step: 1580/529, loss: 0.002261742250993848
2023-01-22 17:29:18.600525: step: 1584/529, loss: 0.00420528557151556
2023-01-22 17:29:19.668454: step: 1588/529, loss: 0.0011106288293376565
2023-01-22 17:29:20.753264: step: 1592/529, loss: 0.006521884817630053
2023-01-22 17:29:21.833806: step: 1596/529, loss: 0.013600890524685383
2023-01-22 17:29:22.902090: step: 1600/529, loss: 0.0025971289724111557
2023-01-22 17:29:23.979082: step: 1604/529, loss: 0.00014028883015271276
2023-01-22 17:29:25.043589: step: 1608/529, loss: 2.604587461974006e-05
2023-01-22 17:29:26.109420: step: 1612/529, loss: 4.4563814299181104e-05
2023-01-22 17:29:27.179219: step: 1616/529, loss: 0.0001973005710169673
2023-01-22 17:29:28.246422: step: 1620/529, loss: 0.001374994171783328
2023-01-22 17:29:29.337129: step: 1624/529, loss: 0.004968054126948118
2023-01-22 17:29:30.410284: step: 1628/529, loss: 0.0001699640997685492
2023-01-22 17:29:31.507103: step: 1632/529, loss: 0.0012247348204255104
2023-01-22 17:29:32.583643: step: 1636/529, loss: 0.0005153222009539604
2023-01-22 17:29:33.668985: step: 1640/529, loss: 0.009150661528110504
2023-01-22 17:29:34.728563: step: 1644/529, loss: 0.004539622459560633
2023-01-22 17:29:35.802135: step: 1648/529, loss: 0.0024223339278250933
2023-01-22 17:29:36.863831: step: 1652/529, loss: 0.005861751735210419
2023-01-22 17:29:37.933607: step: 1656/529, loss: 0.0034328049514442682
2023-01-22 17:29:38.993613: step: 1660/529, loss: 0.0067036347463727
2023-01-22 17:29:40.059251: step: 1664/529, loss: 0.0046232049353420734
2023-01-22 17:29:41.124747: step: 1668/529, loss: 0.008543912321329117
2023-01-22 17:29:42.201241: step: 1672/529, loss: 0.0013973599998280406
2023-01-22 17:29:43.291224: step: 1676/529, loss: 0.0075758653692901134
2023-01-22 17:29:44.356645: step: 1680/529, loss: 0.002628772985190153
2023-01-22 17:29:45.417085: step: 1684/529, loss: 3.391894279047847e-05
2023-01-22 17:29:46.487232: step: 1688/529, loss: 0.00017970365297514945
2023-01-22 17:29:47.561655: step: 1692/529, loss: 0.01029476709663868
2023-01-22 17:29:48.638910: step: 1696/529, loss: 0.005078609567135572
2023-01-22 17:29:49.718267: step: 1700/529, loss: 0.0010321841109544039
2023-01-22 17:29:50.773471: step: 1704/529, loss: 6.0735295846825466e-05
2023-01-22 17:29:51.846087: step: 1708/529, loss: 0.0003616898611653596
2023-01-22 17:29:52.908091: step: 1712/529, loss: 0.0001613723288755864
2023-01-22 17:29:53.993748: step: 1716/529, loss: 0.006900268141180277
2023-01-22 17:29:55.050992: step: 1720/529, loss: 0.00038855645107105374
2023-01-22 17:29:56.113089: step: 1724/529, loss: 4.684772648033686e-06
2023-01-22 17:29:57.185701: step: 1728/529, loss: 0.0012728418223559856
2023-01-22 17:29:58.260551: step: 1732/529, loss: 0.003334173932671547
2023-01-22 17:29:59.328337: step: 1736/529, loss: 0.002552600111812353
2023-01-22 17:30:00.399336: step: 1740/529, loss: 2.339587990718428e-05
2023-01-22 17:30:01.450133: step: 1744/529, loss: 0.0003956110740546137
2023-01-22 17:30:02.523248: step: 1748/529, loss: 0.005057722795754671
2023-01-22 17:30:03.576751: step: 1752/529, loss: 7.605341670569032e-05
2023-01-22 17:30:04.642918: step: 1756/529, loss: 0.0003037995775230229
2023-01-22 17:30:05.723524: step: 1760/529, loss: 0.012842925265431404
2023-01-22 17:30:06.794873: step: 1764/529, loss: 0.004501067101955414
2023-01-22 17:30:07.853543: step: 1768/529, loss: 0.001360322698019445
2023-01-22 17:30:08.920462: step: 1772/529, loss: 0.0017796738538891077
2023-01-22 17:30:10.019921: step: 1776/529, loss: 0.0035017579793930054
2023-01-22 17:30:11.088835: step: 1780/529, loss: 0.00018301911768503487
2023-01-22 17:30:12.170557: step: 1784/529, loss: 0.003364932257682085
2023-01-22 17:30:13.243745: step: 1788/529, loss: 0.0018085100455209613
2023-01-22 17:30:14.303302: step: 1792/529, loss: 0.0044455151073634624
2023-01-22 17:30:15.387488: step: 1796/529, loss: 0.0035848882980644703
2023-01-22 17:30:16.462294: step: 1800/529, loss: 0.002089511835947633
2023-01-22 17:30:17.522077: step: 1804/529, loss: 0.0010881441412493587
2023-01-22 17:30:18.600393: step: 1808/529, loss: 0.003012422239407897
2023-01-22 17:30:19.653178: step: 1812/529, loss: 0.0023543399292975664
2023-01-22 17:30:20.735283: step: 1816/529, loss: 0.00046483860933221877
2023-01-22 17:30:21.805233: step: 1820/529, loss: 0.0051916842348873615
2023-01-22 17:30:22.877213: step: 1824/529, loss: 0.0004477714537642896
2023-01-22 17:30:23.933791: step: 1828/529, loss: 0.0026559936814010143
2023-01-22 17:30:25.003147: step: 1832/529, loss: 0.039945535361766815
2023-01-22 17:30:26.058314: step: 1836/529, loss: 0.0017794484738260508
2023-01-22 17:30:27.138484: step: 1840/529, loss: 0.006043660920113325
2023-01-22 17:30:28.195688: step: 1844/529, loss: 0.0010697685647755861
2023-01-22 17:30:29.270622: step: 1848/529, loss: 0.00010163659317186102
2023-01-22 17:30:30.337033: step: 1852/529, loss: 0.005914970766752958
2023-01-22 17:30:31.405361: step: 1856/529, loss: 0.0015464090975001454
2023-01-22 17:30:32.477063: step: 1860/529, loss: 0.0026120194233953953
2023-01-22 17:30:33.549105: step: 1864/529, loss: 0.004273236729204655
2023-01-22 17:30:34.641285: step: 1868/529, loss: 0.015176031738519669
2023-01-22 17:30:35.705570: step: 1872/529, loss: 0.0030267895199358463
2023-01-22 17:30:36.770712: step: 1876/529, loss: 7.87690169090638e-06
2023-01-22 17:30:37.872141: step: 1880/529, loss: 0.0015675147296860814
2023-01-22 17:30:38.942351: step: 1884/529, loss: 0.0002008663141168654
2023-01-22 17:30:40.004229: step: 1888/529, loss: 0.003913629800081253
2023-01-22 17:30:41.062709: step: 1892/529, loss: 0.003583942074328661
2023-01-22 17:30:42.139218: step: 1896/529, loss: 0.0017871442250907421
2023-01-22 17:30:43.219083: step: 1900/529, loss: 0.001158599043264985
2023-01-22 17:30:44.296602: step: 1904/529, loss: 0.008377348072826862
2023-01-22 17:30:45.376458: step: 1908/529, loss: 0.007920026779174805
2023-01-22 17:30:46.464483: step: 1912/529, loss: 0.025390343740582466
2023-01-22 17:30:47.543511: step: 1916/529, loss: 0.006896121893078089
2023-01-22 17:30:48.606054: step: 1920/529, loss: 0.005686902441084385
2023-01-22 17:30:49.695344: step: 1924/529, loss: 0.016825594007968903
2023-01-22 17:30:50.756327: step: 1928/529, loss: 0.000193691739696078
2023-01-22 17:30:51.814160: step: 1932/529, loss: 0.0020622049923986197
2023-01-22 17:30:52.883078: step: 1936/529, loss: 0.01039885450154543
2023-01-22 17:30:53.963785: step: 1940/529, loss: 0.012124961242079735
2023-01-22 17:30:55.022697: step: 1944/529, loss: 0.00048159074503928423
2023-01-22 17:30:56.102258: step: 1948/529, loss: 0.00028677258524112403
2023-01-22 17:30:57.185506: step: 1952/529, loss: 0.010880428366363049
2023-01-22 17:30:58.255095: step: 1956/529, loss: 0.0038385135121643543
2023-01-22 17:30:59.324786: step: 1960/529, loss: 0.009883001446723938
2023-01-22 17:31:00.396124: step: 1964/529, loss: 0.000713395478669554
2023-01-22 17:31:01.479386: step: 1968/529, loss: 0.006667461711913347
2023-01-22 17:31:02.548098: step: 1972/529, loss: 0.0034269497264176607
2023-01-22 17:31:03.621437: step: 1976/529, loss: 0.0015176531160250306
2023-01-22 17:31:04.689409: step: 1980/529, loss: 0.006744371727108955
2023-01-22 17:31:05.762472: step: 1984/529, loss: 0.0022800147999078035
2023-01-22 17:31:06.830167: step: 1988/529, loss: 0.0009745724964886904
2023-01-22 17:31:07.903092: step: 1992/529, loss: 0.002331268973648548
2023-01-22 17:31:08.963785: step: 1996/529, loss: 0.007197085302323103
2023-01-22 17:31:10.048828: step: 2000/529, loss: 0.0016320046270266175
2023-01-22 17:31:11.110677: step: 2004/529, loss: 0.005486673209816217
2023-01-22 17:31:12.173356: step: 2008/529, loss: 0.0042807552963495255
2023-01-22 17:31:13.243903: step: 2012/529, loss: 0.0007030915003269911
2023-01-22 17:31:14.306327: step: 2016/529, loss: 0.003387653036043048
2023-01-22 17:31:15.372184: step: 2020/529, loss: 5.706393494619988e-05
2023-01-22 17:31:16.448598: step: 2024/529, loss: 0.027386324480175972
2023-01-22 17:31:17.516392: step: 2028/529, loss: 0.0034047963563352823
2023-01-22 17:31:18.590513: step: 2032/529, loss: 0.001972943777218461
2023-01-22 17:31:19.666297: step: 2036/529, loss: 0.0009757645893841982
2023-01-22 17:31:20.736503: step: 2040/529, loss: 0.00035479560028761625
2023-01-22 17:31:21.799497: step: 2044/529, loss: 0.0056922584772109985
2023-01-22 17:31:22.870880: step: 2048/529, loss: 0.0015625410014763474
2023-01-22 17:31:23.947284: step: 2052/529, loss: 0.007033843081444502
2023-01-22 17:31:25.008893: step: 2056/529, loss: 0.000552872137632221
2023-01-22 17:31:26.087314: step: 2060/529, loss: 0.004987975582480431
2023-01-22 17:31:27.177530: step: 2064/529, loss: 0.0005516937817446887
2023-01-22 17:31:28.267111: step: 2068/529, loss: 0.0039209662936627865
2023-01-22 17:31:29.338089: step: 2072/529, loss: 0.0013764798641204834
2023-01-22 17:31:30.425433: step: 2076/529, loss: 0.005496394354850054
2023-01-22 17:31:31.502360: step: 2080/529, loss: 0.0033817782532423735
2023-01-22 17:31:32.574919: step: 2084/529, loss: 0.0036234098952263594
2023-01-22 17:31:33.662398: step: 2088/529, loss: 0.0008921523112803698
2023-01-22 17:31:34.734085: step: 2092/529, loss: 0.005154572427272797
2023-01-22 17:31:35.813712: step: 2096/529, loss: 0.003025319427251816
2023-01-22 17:31:36.879876: step: 2100/529, loss: 0.0009227404370903969
2023-01-22 17:31:37.956835: step: 2104/529, loss: 0.0005347715341486037
2023-01-22 17:31:39.023066: step: 2108/529, loss: 0.008064485155045986
2023-01-22 17:31:40.094118: step: 2112/529, loss: 0.005259071476757526
2023-01-22 17:31:41.174115: step: 2116/529, loss: 0.00626530172303319
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3178571428571429, 'r': 0.35042694497153704, 'f1': 0.33334837545126356}, 'combined': 0.2456251187535626, 'stategy': 1, 'epoch': 13}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3106061857963378, 'r': 0.3071803822765253, 'f1': 0.3088837855054154}, 'combined': 0.20165469934550434, 'stategy': 1, 'epoch': 13}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31976225083056475, 'r': 0.36526921252371913, 'f1': 0.34100420726306463}, 'combined': 0.25126625798331076, 'stategy': 1, 'epoch': 13}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3330820163986344, 'r': 0.3107336825777701, 'f1': 0.32151996827828233}, 'combined': 0.20990422799514805, 'stategy': 1, 'epoch': 13}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31308361629881154, 'r': 0.34991698292220114, 'f1': 0.33047715053763443}, 'combined': 0.2435094793435201, 'stategy': 1, 'epoch': 13}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.323303865771248, 'r': 0.319444407318515, 'f1': 0.3213625492562243}, 'combined': 0.2098014570273796, 'stategy': 1, 'epoch': 13}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 13}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3409090909090909, 'r': 0.4891304347826087, 'f1': 0.40178571428571425}, 'combined': 0.20089285714285712, 'stategy': 1, 'epoch': 13}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 13}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3230331803005008, 'r': 0.36716674573055025, 'f1': 0.34368894316163406}, 'combined': 0.25324448443488823, 'stategy': 1, 'epoch': 12}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33365609306255056, 'r': 0.31188257963659366, 'f1': 0.32240213457920563}, 'combined': 0.21048015003616533, 'stategy': 1, 'epoch': 12}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 17:34:16.374454: step: 4/529, loss: 0.0013083918020129204
2023-01-22 17:34:17.443981: step: 8/529, loss: 0.001629989710636437
2023-01-22 17:34:18.493024: step: 12/529, loss: 0.00506221130490303
2023-01-22 17:34:19.563429: step: 16/529, loss: 0.00011804777022916824
2023-01-22 17:34:20.627914: step: 20/529, loss: 0.02768115885555744
2023-01-22 17:34:21.699569: step: 24/529, loss: 0.00039927702164277434
2023-01-22 17:34:22.767336: step: 28/529, loss: 0.002878830535337329
2023-01-22 17:34:23.820029: step: 32/529, loss: 0.0067565483041107655
2023-01-22 17:34:24.882875: step: 36/529, loss: 0.001153373857960105
2023-01-22 17:34:25.932545: step: 40/529, loss: 1.8734412151388824e-05
2023-01-22 17:34:27.010474: step: 44/529, loss: 0.0002706583763938397
2023-01-22 17:34:28.067194: step: 48/529, loss: 0.002159199910238385
2023-01-22 17:34:29.147003: step: 52/529, loss: 0.00034504308132454753
2023-01-22 17:34:30.205478: step: 56/529, loss: 0.00022985381656326354
2023-01-22 17:34:31.265780: step: 60/529, loss: 0.0035387659445405006
2023-01-22 17:34:32.307838: step: 64/529, loss: 0.0025859409943223
2023-01-22 17:34:33.375784: step: 68/529, loss: 0.00022430610260926187
2023-01-22 17:34:34.452114: step: 72/529, loss: 0.003941799979656935
2023-01-22 17:34:35.523381: step: 76/529, loss: 0.001380683621391654
2023-01-22 17:34:36.590376: step: 80/529, loss: 0.0023522034753113985
2023-01-22 17:34:37.662970: step: 84/529, loss: 0.00308869406580925
2023-01-22 17:34:38.721751: step: 88/529, loss: 0.006730386987328529
2023-01-22 17:34:39.795356: step: 92/529, loss: 0.00849398598074913
2023-01-22 17:34:40.870249: step: 96/529, loss: 0.008255600929260254
2023-01-22 17:34:41.958853: step: 100/529, loss: 0.002060904400423169
2023-01-22 17:34:43.077700: step: 104/529, loss: 0.0008200475131161511
2023-01-22 17:34:44.140703: step: 108/529, loss: 0.004485452547669411
2023-01-22 17:34:45.207011: step: 112/529, loss: 0.006593985483050346
2023-01-22 17:34:46.263454: step: 116/529, loss: 0.0028539884369820356
2023-01-22 17:34:47.340078: step: 120/529, loss: 0.0012559586903080344
2023-01-22 17:34:48.400140: step: 124/529, loss: 0.0001731273514451459
2023-01-22 17:34:49.472967: step: 128/529, loss: 0.003500661114230752
2023-01-22 17:34:50.538358: step: 132/529, loss: 0.0027256000321358442
2023-01-22 17:34:51.615065: step: 136/529, loss: 0.001709451200440526
2023-01-22 17:34:52.696621: step: 140/529, loss: 0.004447990097105503
2023-01-22 17:34:53.767090: step: 144/529, loss: 0.011341128498315811
2023-01-22 17:34:54.854106: step: 148/529, loss: 3.96544965042267e-06
2023-01-22 17:34:55.920179: step: 152/529, loss: 0.0001453894074074924
2023-01-22 17:34:56.982126: step: 156/529, loss: 9.502104512648657e-05
2023-01-22 17:34:58.044203: step: 160/529, loss: 0.002916882745921612
2023-01-22 17:34:59.100415: step: 164/529, loss: 0.0022351504303514957
2023-01-22 17:35:00.183545: step: 168/529, loss: 0.006104897707700729
2023-01-22 17:35:01.274609: step: 172/529, loss: 0.002474898938089609
2023-01-22 17:35:02.344126: step: 176/529, loss: 0.0005531220231205225
2023-01-22 17:35:03.413632: step: 180/529, loss: 0.0026697826106101274
2023-01-22 17:35:04.512249: step: 184/529, loss: 0.0064180525951087475
2023-01-22 17:35:05.586372: step: 188/529, loss: 0.002999653108417988
2023-01-22 17:35:06.686403: step: 192/529, loss: 0.025464113801717758
2023-01-22 17:35:07.766845: step: 196/529, loss: 0.009232824668288231
2023-01-22 17:35:08.835430: step: 200/529, loss: 0.00032653496600687504
2023-01-22 17:35:09.906863: step: 204/529, loss: 0.0027034401427954435
2023-01-22 17:35:10.987918: step: 208/529, loss: 0.003960411064326763
2023-01-22 17:35:12.068396: step: 212/529, loss: 0.003326426725834608
2023-01-22 17:35:13.150668: step: 216/529, loss: 0.010160683654248714
2023-01-22 17:35:14.238643: step: 220/529, loss: 0.0036211484111845493
2023-01-22 17:35:15.319184: step: 224/529, loss: 0.0005328348488546908
2023-01-22 17:35:16.396182: step: 228/529, loss: 0.004893571604043245
2023-01-22 17:35:17.470172: step: 232/529, loss: 0.0014357338659465313
2023-01-22 17:35:18.539130: step: 236/529, loss: 0.006993093993514776
2023-01-22 17:35:19.616537: step: 240/529, loss: 0.0041709295473992825
2023-01-22 17:35:20.698313: step: 244/529, loss: 0.0023953274358063936
2023-01-22 17:35:21.784136: step: 248/529, loss: 0.005794886499643326
2023-01-22 17:35:22.874224: step: 252/529, loss: 3.386481694178656e-05
2023-01-22 17:35:23.955171: step: 256/529, loss: 0.0032592457719147205
2023-01-22 17:35:25.045813: step: 260/529, loss: 0.00032845191890373826
2023-01-22 17:35:26.128546: step: 264/529, loss: 8.309235272463411e-05
2023-01-22 17:35:27.196629: step: 268/529, loss: 0.004330434370785952
2023-01-22 17:35:28.270177: step: 272/529, loss: 0.00031662671244703233
2023-01-22 17:35:29.349292: step: 276/529, loss: 0.009323946200311184
2023-01-22 17:35:30.415995: step: 280/529, loss: 0.000254539045272395
2023-01-22 17:35:31.495624: step: 284/529, loss: 0.0436927005648613
2023-01-22 17:35:32.559477: step: 288/529, loss: 0.006670475006103516
2023-01-22 17:35:33.635373: step: 292/529, loss: 0.00038110025343485177
2023-01-22 17:35:34.716204: step: 296/529, loss: 0.010616067796945572
2023-01-22 17:35:35.784128: step: 300/529, loss: 0.0001866883394541219
2023-01-22 17:35:36.843352: step: 304/529, loss: 0.0013444084906950593
2023-01-22 17:35:37.905175: step: 308/529, loss: 0.0041800630278885365
2023-01-22 17:35:38.988209: step: 312/529, loss: 0.008285368792712688
2023-01-22 17:35:40.065639: step: 316/529, loss: 0.0015832665376365185
2023-01-22 17:35:41.147938: step: 320/529, loss: 0.0008135446696542203
2023-01-22 17:35:42.233781: step: 324/529, loss: 6.871490768389776e-05
2023-01-22 17:35:43.343924: step: 328/529, loss: 0.004307453986257315
2023-01-22 17:35:44.431788: step: 332/529, loss: 0.00017551037308294326
2023-01-22 17:35:45.511366: step: 336/529, loss: 0.0010425669606775045
2023-01-22 17:35:46.591978: step: 340/529, loss: 0.0002904363500420004
2023-01-22 17:35:47.660425: step: 344/529, loss: 0.009340458549559116
2023-01-22 17:35:48.738217: step: 348/529, loss: 0.0013986770063638687
2023-01-22 17:35:49.817536: step: 352/529, loss: 0.002482094569131732
2023-01-22 17:35:50.890814: step: 356/529, loss: 0.0004495203902479261
2023-01-22 17:35:51.977169: step: 360/529, loss: 0.0010811351239681244
2023-01-22 17:35:53.055495: step: 364/529, loss: 0.04078175500035286
2023-01-22 17:35:54.137831: step: 368/529, loss: 0.0013570310547947884
2023-01-22 17:35:55.221342: step: 372/529, loss: 0.002462711650878191
2023-01-22 17:35:56.301587: step: 376/529, loss: 0.001508450717665255
2023-01-22 17:35:57.383759: step: 380/529, loss: 0.007940758019685745
2023-01-22 17:35:58.484420: step: 384/529, loss: 0.005111399106681347
2023-01-22 17:35:59.559140: step: 388/529, loss: 0.00037518609315156937
2023-01-22 17:36:00.639105: step: 392/529, loss: 0.0051468126475811005
2023-01-22 17:36:01.724325: step: 396/529, loss: 0.008642208762466908
2023-01-22 17:36:02.807227: step: 400/529, loss: 0.01035205740481615
2023-01-22 17:36:03.880939: step: 404/529, loss: 0.006263865157961845
2023-01-22 17:36:04.943589: step: 408/529, loss: 3.7809741115779616e-06
2023-01-22 17:36:06.010650: step: 412/529, loss: 0.002615247620269656
2023-01-22 17:36:07.092251: step: 416/529, loss: 0.01604885421693325
2023-01-22 17:36:08.172410: step: 420/529, loss: 0.003055088222026825
2023-01-22 17:36:09.244204: step: 424/529, loss: 0.001945036114193499
2023-01-22 17:36:10.305528: step: 428/529, loss: 0.0010235343361273408
2023-01-22 17:36:11.387715: step: 432/529, loss: 6.6673992478172295e-06
2023-01-22 17:36:12.477365: step: 436/529, loss: 0.0022046423982828856
2023-01-22 17:36:13.556843: step: 440/529, loss: 0.0015066710766404867
2023-01-22 17:36:14.656786: step: 444/529, loss: 0.005969975609332323
2023-01-22 17:36:15.736624: step: 448/529, loss: 0.0009364045108668506
2023-01-22 17:36:16.820142: step: 452/529, loss: 0.00505894236266613
2023-01-22 17:36:17.922121: step: 456/529, loss: 0.0006616225582547486
2023-01-22 17:36:19.006632: step: 460/529, loss: 0.008182837627828121
2023-01-22 17:36:20.072240: step: 464/529, loss: 0.00038651531212963164
2023-01-22 17:36:21.140741: step: 468/529, loss: 0.0025241547264158726
2023-01-22 17:36:22.220412: step: 472/529, loss: 0.0015358327655121684
2023-01-22 17:36:23.275552: step: 476/529, loss: 0.0007262724684551358
2023-01-22 17:36:24.362869: step: 480/529, loss: 0.00014446189743466675
2023-01-22 17:36:25.444220: step: 484/529, loss: 0.020341655239462852
2023-01-22 17:36:26.520907: step: 488/529, loss: 0.014740174636244774
2023-01-22 17:36:27.594895: step: 492/529, loss: 0.002303437562659383
2023-01-22 17:36:28.665093: step: 496/529, loss: 0.000746925245039165
2023-01-22 17:36:29.750695: step: 500/529, loss: 0.012227782048285007
2023-01-22 17:36:30.825819: step: 504/529, loss: 0.00623081810772419
2023-01-22 17:36:31.894653: step: 508/529, loss: 0.005031298846006393
2023-01-22 17:36:32.977132: step: 512/529, loss: 0.00010093992023030296
2023-01-22 17:36:34.057796: step: 516/529, loss: 0.002336269710212946
2023-01-22 17:36:35.120325: step: 520/529, loss: 0.006468994077295065
2023-01-22 17:36:36.199840: step: 524/529, loss: 0.00030392836197279394
2023-01-22 17:36:37.276251: step: 528/529, loss: 0.002299483399838209
2023-01-22 17:36:38.352557: step: 532/529, loss: 0.004743121098726988
2023-01-22 17:36:39.416695: step: 536/529, loss: 0.0024499150458723307
2023-01-22 17:36:40.494468: step: 540/529, loss: 0.0019470476545393467
2023-01-22 17:36:41.573355: step: 544/529, loss: 0.00031268014572560787
2023-01-22 17:36:42.671114: step: 548/529, loss: 0.0016287235775962472
2023-01-22 17:36:43.757979: step: 552/529, loss: 0.003286950755864382
2023-01-22 17:36:44.855223: step: 556/529, loss: 0.006994290743023157
2023-01-22 17:36:45.938999: step: 560/529, loss: 4.9108646635431796e-05
2023-01-22 17:36:47.024885: step: 564/529, loss: 0.0017090942710638046
2023-01-22 17:36:48.114919: step: 568/529, loss: 0.004771821200847626
2023-01-22 17:36:49.185410: step: 572/529, loss: 0.0027980839367955923
2023-01-22 17:36:50.258550: step: 576/529, loss: 0.007625539321452379
2023-01-22 17:36:51.331007: step: 580/529, loss: 0.0020463312976062298
2023-01-22 17:36:52.407362: step: 584/529, loss: 0.0023525923024863005
2023-01-22 17:36:53.481907: step: 588/529, loss: 0.00694476580247283
2023-01-22 17:36:54.554100: step: 592/529, loss: 0.002207657555118203
2023-01-22 17:36:55.615964: step: 596/529, loss: 0.008983233943581581
2023-01-22 17:36:56.679215: step: 600/529, loss: 0.0001583544653840363
2023-01-22 17:36:57.758798: step: 604/529, loss: 0.011797570623457432
2023-01-22 17:36:58.818378: step: 608/529, loss: 0.0018957924330607057
2023-01-22 17:36:59.895717: step: 612/529, loss: 0.0031891940161585808
2023-01-22 17:37:00.987201: step: 616/529, loss: 0.057069331407547
2023-01-22 17:37:02.079169: step: 620/529, loss: 0.0033412936609238386
2023-01-22 17:37:03.159754: step: 624/529, loss: 0.005603430327028036
2023-01-22 17:37:04.251074: step: 628/529, loss: 0.00172527099493891
2023-01-22 17:37:05.342446: step: 632/529, loss: 0.0023448984138667583
2023-01-22 17:37:06.423749: step: 636/529, loss: 0.00036707372055388987
2023-01-22 17:37:07.511124: step: 640/529, loss: 0.003940449096262455
2023-01-22 17:37:08.585604: step: 644/529, loss: 0.011811473406851292
2023-01-22 17:37:09.667197: step: 648/529, loss: 0.0009290999732911587
2023-01-22 17:37:10.735883: step: 652/529, loss: 0.0040426068007946014
2023-01-22 17:37:11.813554: step: 656/529, loss: 0.00016602044343017042
2023-01-22 17:37:12.896129: step: 660/529, loss: 0.000490012695081532
2023-01-22 17:37:13.967899: step: 664/529, loss: 0.013274741359055042
2023-01-22 17:37:15.045055: step: 668/529, loss: 0.004442111123353243
2023-01-22 17:37:16.120395: step: 672/529, loss: 0.004331009928137064
2023-01-22 17:37:17.214656: step: 676/529, loss: 0.006994915660470724
2023-01-22 17:37:18.283965: step: 680/529, loss: 0.007527124602347612
2023-01-22 17:37:19.353168: step: 684/529, loss: 0.00945842731744051
2023-01-22 17:37:20.434908: step: 688/529, loss: 0.0007517659105360508
2023-01-22 17:37:21.495681: step: 692/529, loss: 0.004018715582787991
2023-01-22 17:37:22.564896: step: 696/529, loss: 0.0004807522054761648
2023-01-22 17:37:23.645237: step: 700/529, loss: 0.0001125754788517952
2023-01-22 17:37:24.746449: step: 704/529, loss: 0.0015589147806167603
2023-01-22 17:37:25.831391: step: 708/529, loss: 0.0030514593236148357
2023-01-22 17:37:26.914564: step: 712/529, loss: 0.00042455235961824656
2023-01-22 17:37:28.004052: step: 716/529, loss: 0.0030508958734571934
2023-01-22 17:37:29.068736: step: 720/529, loss: 0.0029742801561951637
2023-01-22 17:37:30.147472: step: 724/529, loss: 0.028850683942437172
2023-01-22 17:37:31.240550: step: 728/529, loss: 0.0040900311432778835
2023-01-22 17:37:32.317895: step: 732/529, loss: 0.00011467358126537874
2023-01-22 17:37:33.388422: step: 736/529, loss: 1.7049587768269703e-05
2023-01-22 17:37:34.450135: step: 740/529, loss: 0.004052354954183102
2023-01-22 17:37:35.534278: step: 744/529, loss: 0.007852279581129551
2023-01-22 17:37:36.605739: step: 748/529, loss: 0.00012509440421126783
2023-01-22 17:37:37.680037: step: 752/529, loss: 0.004132823087275028
2023-01-22 17:37:38.765511: step: 756/529, loss: 0.0019473739666864276
2023-01-22 17:37:39.855986: step: 760/529, loss: 0.003840666264295578
2023-01-22 17:37:40.930848: step: 764/529, loss: 0.0057149589993059635
2023-01-22 17:37:42.000492: step: 768/529, loss: 0.0009152949205599725
2023-01-22 17:37:43.103368: step: 772/529, loss: 0.005389711819589138
2023-01-22 17:37:44.198507: step: 776/529, loss: 0.005897090770304203
2023-01-22 17:37:45.266375: step: 780/529, loss: 0.0005674312124028802
2023-01-22 17:37:46.332106: step: 784/529, loss: 0.0024358986411243677
2023-01-22 17:37:47.387105: step: 788/529, loss: 0.007085789460688829
2023-01-22 17:37:48.455115: step: 792/529, loss: 0.004392254166305065
2023-01-22 17:37:49.531458: step: 796/529, loss: 0.005781763698905706
2023-01-22 17:37:50.602084: step: 800/529, loss: 0.003665948286652565
2023-01-22 17:37:51.694377: step: 804/529, loss: 0.00012799628893844783
2023-01-22 17:37:52.760177: step: 808/529, loss: 0.010023016482591629
2023-01-22 17:37:53.834177: step: 812/529, loss: 0.0021820273250341415
2023-01-22 17:37:54.921464: step: 816/529, loss: 0.009777463972568512
2023-01-22 17:37:55.990550: step: 820/529, loss: 0.010205371305346489
2023-01-22 17:37:57.060705: step: 824/529, loss: 2.6652109227143228e-05
2023-01-22 17:37:58.145908: step: 828/529, loss: 0.003344296244904399
2023-01-22 17:37:59.225736: step: 832/529, loss: 0.004322676919400692
2023-01-22 17:38:00.303284: step: 836/529, loss: 0.00082737288903445
2023-01-22 17:38:01.395025: step: 840/529, loss: 0.002806248376145959
2023-01-22 17:38:02.469384: step: 844/529, loss: 0.0003043327888008207
2023-01-22 17:38:03.549669: step: 848/529, loss: 2.696049341466278e-05
2023-01-22 17:38:04.627022: step: 852/529, loss: 0.0008913210476748645
2023-01-22 17:38:05.701766: step: 856/529, loss: 0.0047568706795573235
2023-01-22 17:38:06.787843: step: 860/529, loss: 0.0006697503849864006
2023-01-22 17:38:07.862247: step: 864/529, loss: 0.0017113873036578298
2023-01-22 17:38:08.928378: step: 868/529, loss: 0.0037341443821787834
2023-01-22 17:38:10.026078: step: 872/529, loss: 0.005166519898921251
2023-01-22 17:38:11.109459: step: 876/529, loss: 0.006426224019378424
2023-01-22 17:38:12.183475: step: 880/529, loss: 0.0006184052326716483
2023-01-22 17:38:13.258557: step: 884/529, loss: 0.003161293687298894
2023-01-22 17:38:14.331556: step: 888/529, loss: 0.010034614242613316
2023-01-22 17:38:15.393443: step: 892/529, loss: 0.026789799332618713
2023-01-22 17:38:16.485848: step: 896/529, loss: 0.001929200254380703
2023-01-22 17:38:17.565904: step: 900/529, loss: 0.0145545220002532
2023-01-22 17:38:18.652357: step: 904/529, loss: 0.0032731760293245316
2023-01-22 17:38:19.738561: step: 908/529, loss: 0.0053643579594790936
2023-01-22 17:38:20.817462: step: 912/529, loss: 0.00484539195895195
2023-01-22 17:38:21.902442: step: 916/529, loss: 0.006907839793711901
2023-01-22 17:38:22.987515: step: 920/529, loss: 3.603533696150407e-05
2023-01-22 17:38:24.076799: step: 924/529, loss: 0.009192566387355328
2023-01-22 17:38:25.161296: step: 928/529, loss: 0.006187533028423786
2023-01-22 17:38:26.243207: step: 932/529, loss: 0.0001257225958397612
2023-01-22 17:38:27.322531: step: 936/529, loss: 0.010146988555788994
2023-01-22 17:38:28.389543: step: 940/529, loss: 0.02705325372517109
2023-01-22 17:38:29.480420: step: 944/529, loss: 0.04710602015256882
2023-01-22 17:38:30.558265: step: 948/529, loss: 0.0009438158595003188
2023-01-22 17:38:31.664253: step: 952/529, loss: 0.004957647528499365
2023-01-22 17:38:32.740142: step: 956/529, loss: 0.003248073160648346
2023-01-22 17:38:33.820850: step: 960/529, loss: 0.0031586489640176296
2023-01-22 17:38:34.921886: step: 964/529, loss: 0.006837042514234781
2023-01-22 17:38:36.012897: step: 968/529, loss: 0.0024759764783084393
2023-01-22 17:38:37.098723: step: 972/529, loss: 0.002118160715326667
2023-01-22 17:38:38.187310: step: 976/529, loss: 0.002055953722447157
2023-01-22 17:38:39.283885: step: 980/529, loss: 0.004124574363231659
2023-01-22 17:38:40.378488: step: 984/529, loss: 0.016004513949155807
2023-01-22 17:38:41.466661: step: 988/529, loss: 0.003560491371899843
2023-01-22 17:38:42.571876: step: 992/529, loss: 0.005313785281032324
2023-01-22 17:38:43.659873: step: 996/529, loss: 0.0032371787820011377
2023-01-22 17:38:44.734721: step: 1000/529, loss: 1.7462771211285144e-05
2023-01-22 17:38:45.817826: step: 1004/529, loss: 0.0001582477561896667
2023-01-22 17:38:46.888169: step: 1008/529, loss: 0.0023180777207016945
2023-01-22 17:38:47.986684: step: 1012/529, loss: 0.001344939460977912
2023-01-22 17:38:49.052960: step: 1016/529, loss: 0.0004612569173332304
2023-01-22 17:38:50.145491: step: 1020/529, loss: 0.0031566154211759567
2023-01-22 17:38:51.243078: step: 1024/529, loss: 0.00035195861710235476
2023-01-22 17:38:52.323699: step: 1028/529, loss: 0.008639510720968246
2023-01-22 17:38:53.412770: step: 1032/529, loss: 0.00013106749975122511
2023-01-22 17:38:54.497137: step: 1036/529, loss: 0.0049845874309539795
2023-01-22 17:38:55.557232: step: 1040/529, loss: 0.00024464441230520606
2023-01-22 17:38:56.632875: step: 1044/529, loss: 0.008739300072193146
2023-01-22 17:38:57.722963: step: 1048/529, loss: 0.00521880853921175
2023-01-22 17:38:58.797020: step: 1052/529, loss: 0.0008859842200763524
2023-01-22 17:38:59.881889: step: 1056/529, loss: 0.009324532002210617
2023-01-22 17:39:00.965679: step: 1060/529, loss: 0.023509660735726357
2023-01-22 17:39:02.051628: step: 1064/529, loss: 0.010008524172008038
2023-01-22 17:39:03.129870: step: 1068/529, loss: 1.1678504961309955e-05
2023-01-22 17:39:04.216683: step: 1072/529, loss: 0.002534510102123022
2023-01-22 17:39:05.300558: step: 1076/529, loss: 0.00048508241889066994
2023-01-22 17:39:06.382271: step: 1080/529, loss: 0.00174156844150275
2023-01-22 17:39:07.459087: step: 1084/529, loss: 0.007203032728284597
2023-01-22 17:39:08.534610: step: 1088/529, loss: 0.0008048833697102964
2023-01-22 17:39:09.600594: step: 1092/529, loss: 0.0001464414526708424
2023-01-22 17:39:10.673623: step: 1096/529, loss: 0.003558980068191886
2023-01-22 17:39:11.736682: step: 1100/529, loss: 0.0011085179867222905
2023-01-22 17:39:12.808392: step: 1104/529, loss: 0.0015488055068999529
2023-01-22 17:39:13.881130: step: 1108/529, loss: 0.0027339491061866283
2023-01-22 17:39:14.971670: step: 1112/529, loss: 0.004658680874854326
2023-01-22 17:39:16.056210: step: 1116/529, loss: 0.004505416844040155
2023-01-22 17:39:17.140175: step: 1120/529, loss: 0.007795459590852261
2023-01-22 17:39:18.222212: step: 1124/529, loss: 0.0011100741103291512
2023-01-22 17:39:19.304737: step: 1128/529, loss: 0.0011100699193775654
2023-01-22 17:39:20.388183: step: 1132/529, loss: 0.0006393307121470571
2023-01-22 17:39:21.486549: step: 1136/529, loss: 0.01404570508748293
2023-01-22 17:39:22.572611: step: 1140/529, loss: 0.005572729744017124
2023-01-22 17:39:23.694411: step: 1144/529, loss: 0.006868306081742048
2023-01-22 17:39:24.778494: step: 1148/529, loss: 0.003913376480340958
2023-01-22 17:39:25.854567: step: 1152/529, loss: 0.004049277398735285
2023-01-22 17:39:26.935776: step: 1156/529, loss: 6.321066757664084e-05
2023-01-22 17:39:28.010213: step: 1160/529, loss: 0.0626671090722084
2023-01-22 17:39:29.090474: step: 1164/529, loss: 0.0026410934515297413
2023-01-22 17:39:30.156009: step: 1168/529, loss: 0.000755573040805757
2023-01-22 17:39:31.243961: step: 1172/529, loss: 0.0007078420021571219
2023-01-22 17:39:32.320868: step: 1176/529, loss: 0.000758122478146106
2023-01-22 17:39:33.418077: step: 1180/529, loss: 0.0005499935941770673
2023-01-22 17:39:34.517834: step: 1184/529, loss: 0.004979957826435566
2023-01-22 17:39:35.602757: step: 1188/529, loss: 0.004975061397999525
2023-01-22 17:39:36.681381: step: 1192/529, loss: 0.0061318762600421906
2023-01-22 17:39:37.754284: step: 1196/529, loss: 6.094748187024379e-06
2023-01-22 17:39:38.831993: step: 1200/529, loss: 0.008106323890388012
2023-01-22 17:39:39.905355: step: 1204/529, loss: 0.0008714957511983812
2023-01-22 17:39:40.991707: step: 1208/529, loss: 0.006702861282974482
2023-01-22 17:39:42.069089: step: 1212/529, loss: 0.0015920302830636501
2023-01-22 17:39:43.174778: step: 1216/529, loss: 0.0017727756639942527
2023-01-22 17:39:44.251966: step: 1220/529, loss: 0.004820380825549364
2023-01-22 17:39:45.345657: step: 1224/529, loss: 0.012969250790774822
2023-01-22 17:39:46.428576: step: 1228/529, loss: 0.004003622569143772
2023-01-22 17:39:47.510590: step: 1232/529, loss: 0.0011055308859795332
2023-01-22 17:39:48.581334: step: 1236/529, loss: 0.005733616184443235
2023-01-22 17:39:49.667173: step: 1240/529, loss: 0.00570191815495491
2023-01-22 17:39:50.754656: step: 1244/529, loss: 2.457704431435559e-05
2023-01-22 17:39:51.821326: step: 1248/529, loss: 0.00041102274553850293
2023-01-22 17:39:52.910562: step: 1252/529, loss: 0.0031053186394274235
2023-01-22 17:39:53.992433: step: 1256/529, loss: 0.012733005918562412
2023-01-22 17:39:55.083630: step: 1260/529, loss: 0.007202472072094679
2023-01-22 17:39:56.161430: step: 1264/529, loss: 0.004870354663580656
2023-01-22 17:39:57.250153: step: 1268/529, loss: 0.0022922626230865717
2023-01-22 17:39:58.328045: step: 1272/529, loss: 0.001979152439162135
2023-01-22 17:39:59.393323: step: 1276/529, loss: 0.010340387932956219
2023-01-22 17:40:00.471181: step: 1280/529, loss: 0.00019813135440927
2023-01-22 17:40:01.528643: step: 1284/529, loss: 0.009121579118072987
2023-01-22 17:40:02.631721: step: 1288/529, loss: 0.0026397088076919317
2023-01-22 17:40:03.722072: step: 1292/529, loss: 0.004600172862410545
2023-01-22 17:40:04.800043: step: 1296/529, loss: 2.715624577831477e-05
2023-01-22 17:40:05.893334: step: 1300/529, loss: 0.002242723712697625
2023-01-22 17:40:06.985680: step: 1304/529, loss: 0.02446291781961918
2023-01-22 17:40:08.054399: step: 1308/529, loss: 0.009032251313328743
2023-01-22 17:40:09.122676: step: 1312/529, loss: 0.007352314889431
2023-01-22 17:40:10.196342: step: 1316/529, loss: 0.0048003834672272205
2023-01-22 17:40:11.265216: step: 1320/529, loss: 0.019572388380765915
2023-01-22 17:40:12.358482: step: 1324/529, loss: 0.003064745804294944
2023-01-22 17:40:13.461406: step: 1328/529, loss: 0.0036644909996539354
2023-01-22 17:40:14.534340: step: 1332/529, loss: 0.012914334423840046
2023-01-22 17:40:15.609661: step: 1336/529, loss: 0.004564644303172827
2023-01-22 17:40:16.692397: step: 1340/529, loss: 0.0030346137937158346
2023-01-22 17:40:17.773317: step: 1344/529, loss: 0.0035736700519919395
2023-01-22 17:40:18.854811: step: 1348/529, loss: 0.006541269365698099
2023-01-22 17:40:19.908658: step: 1352/529, loss: 0.004591689445078373
2023-01-22 17:40:21.015590: step: 1356/529, loss: 0.024633893743157387
2023-01-22 17:40:22.088890: step: 1360/529, loss: 0.005393498111516237
2023-01-22 17:40:23.156221: step: 1364/529, loss: 0.010563160292804241
2023-01-22 17:40:24.228379: step: 1368/529, loss: 0.002505565993487835
2023-01-22 17:40:25.309401: step: 1372/529, loss: 0.000835604325402528
2023-01-22 17:40:26.385205: step: 1376/529, loss: 0.010811658576130867
2023-01-22 17:40:27.501556: step: 1380/529, loss: 0.008302316069602966
2023-01-22 17:40:28.571579: step: 1384/529, loss: 0.00036046322202309966
2023-01-22 17:40:29.639716: step: 1388/529, loss: 0.012536582536995411
2023-01-22 17:40:30.720325: step: 1392/529, loss: 0.005242150742560625
2023-01-22 17:40:31.788081: step: 1396/529, loss: 0.0044818841852247715
2023-01-22 17:40:32.888895: step: 1400/529, loss: 0.0029626083560287952
2023-01-22 17:40:33.954627: step: 1404/529, loss: 0.0069379303604364395
2023-01-22 17:40:35.031704: step: 1408/529, loss: 0.0056917727924883366
2023-01-22 17:40:36.111504: step: 1412/529, loss: 0.001560179516673088
2023-01-22 17:40:37.191204: step: 1416/529, loss: 0.0012899324065074325
2023-01-22 17:40:38.273419: step: 1420/529, loss: 0.0008623880567029119
2023-01-22 17:40:39.349311: step: 1424/529, loss: 0.005058376584202051
2023-01-22 17:40:40.416336: step: 1428/529, loss: 0.01329648494720459
2023-01-22 17:40:41.486719: step: 1432/529, loss: 0.0003696754574775696
2023-01-22 17:40:42.564516: step: 1436/529, loss: 0.0007314187241718173
2023-01-22 17:40:43.644534: step: 1440/529, loss: 0.0035408358089625835
2023-01-22 17:40:44.710781: step: 1444/529, loss: 0.0004966481938026845
2023-01-22 17:40:45.787560: step: 1448/529, loss: 0.005022390745580196
2023-01-22 17:40:46.849851: step: 1452/529, loss: 0.00841954629868269
2023-01-22 17:40:47.925621: step: 1456/529, loss: 0.0026678030844777822
2023-01-22 17:40:48.991060: step: 1460/529, loss: 0.0010666601592674851
2023-01-22 17:40:50.057643: step: 1464/529, loss: 0.0027653449214994907
2023-01-22 17:40:51.117338: step: 1468/529, loss: 0.005911482032388449
2023-01-22 17:40:52.186959: step: 1472/529, loss: 0.009020921774208546
2023-01-22 17:40:53.267273: step: 1476/529, loss: 0.0007216590456664562
2023-01-22 17:40:54.330002: step: 1480/529, loss: 0.0006418696139007807
2023-01-22 17:40:55.415186: step: 1484/529, loss: 0.0011347413528710604
2023-01-22 17:40:56.473805: step: 1488/529, loss: 0.004619520623236895
2023-01-22 17:40:57.564533: step: 1492/529, loss: 0.002761669224128127
2023-01-22 17:40:58.654899: step: 1496/529, loss: 0.0015018106205388904
2023-01-22 17:40:59.732832: step: 1500/529, loss: 0.0011983702424913645
2023-01-22 17:41:00.810619: step: 1504/529, loss: 3.712824036483653e-05
2023-01-22 17:41:01.900973: step: 1508/529, loss: 0.003035917179659009
2023-01-22 17:41:02.986024: step: 1512/529, loss: 0.002935249824076891
2023-01-22 17:41:04.067013: step: 1516/529, loss: 0.0005018645315431058
2023-01-22 17:41:05.131766: step: 1520/529, loss: 7.516053301515058e-05
2023-01-22 17:41:06.202049: step: 1524/529, loss: 0.0006252499297261238
2023-01-22 17:41:07.277010: step: 1528/529, loss: 0.00021914085664320737
2023-01-22 17:41:08.354998: step: 1532/529, loss: 0.00035210527130402625
2023-01-22 17:41:09.416634: step: 1536/529, loss: 0.0049569010734558105
2023-01-22 17:41:10.490556: step: 1540/529, loss: 0.0005235927528701723
2023-01-22 17:41:11.561188: step: 1544/529, loss: 0.0026279399171471596
2023-01-22 17:41:12.636088: step: 1548/529, loss: 0.00324541749432683
2023-01-22 17:41:13.694090: step: 1552/529, loss: 0.009012006223201752
2023-01-22 17:41:14.761263: step: 1556/529, loss: 0.0006068104994483292
2023-01-22 17:41:15.839625: step: 1560/529, loss: 0.0016141320811584592
2023-01-22 17:41:16.889843: step: 1564/529, loss: 0.00028360760188661516
2023-01-22 17:41:17.974178: step: 1568/529, loss: 0.003278398420661688
2023-01-22 17:41:19.030023: step: 1572/529, loss: 0.0009010664070956409
2023-01-22 17:41:20.094591: step: 1576/529, loss: 0.002551017329096794
2023-01-22 17:41:21.175222: step: 1580/529, loss: 0.0016217385418713093
2023-01-22 17:41:22.252524: step: 1584/529, loss: 0.0015589940594509244
2023-01-22 17:41:23.318631: step: 1588/529, loss: 0.0013086016988381743
2023-01-22 17:41:24.385340: step: 1592/529, loss: 0.013980780728161335
2023-01-22 17:41:25.456165: step: 1596/529, loss: 0.02320174314081669
2023-01-22 17:41:26.544025: step: 1600/529, loss: 0.0044688149355351925
2023-01-22 17:41:27.632178: step: 1604/529, loss: 0.03884219005703926
2023-01-22 17:41:28.693412: step: 1608/529, loss: 9.968772246793378e-06
2023-01-22 17:41:29.760061: step: 1612/529, loss: 0.003088307799771428
2023-01-22 17:41:30.825955: step: 1616/529, loss: 0.0023602466098964214
2023-01-22 17:41:31.903252: step: 1620/529, loss: 0.006536624860018492
2023-01-22 17:41:32.988341: step: 1624/529, loss: 0.0
2023-01-22 17:41:34.072141: step: 1628/529, loss: 0.003033406799659133
2023-01-22 17:41:35.134972: step: 1632/529, loss: 0.0013596320059150457
2023-01-22 17:41:36.202274: step: 1636/529, loss: 0.0023997037205845118
2023-01-22 17:41:37.280174: step: 1640/529, loss: 0.003005336970090866
2023-01-22 17:41:38.343212: step: 1644/529, loss: 0.002092453185468912
2023-01-22 17:41:39.399328: step: 1648/529, loss: 0.000312409974867478
2023-01-22 17:41:40.480719: step: 1652/529, loss: 0.0041015553288161755
2023-01-22 17:41:41.552216: step: 1656/529, loss: 0.0017991220811381936
2023-01-22 17:41:42.624325: step: 1660/529, loss: 0.0019315526587888598
2023-01-22 17:41:43.745889: step: 1664/529, loss: 0.004510460887104273
2023-01-22 17:41:44.818090: step: 1668/529, loss: 0.005529333371669054
2023-01-22 17:41:45.885965: step: 1672/529, loss: 0.003165849018841982
2023-01-22 17:41:46.961206: step: 1676/529, loss: 0.0006393567891791463
2023-01-22 17:41:48.025104: step: 1680/529, loss: 0.0023484984412789345
2023-01-22 17:41:49.075277: step: 1684/529, loss: 0.0003511063405312598
2023-01-22 17:41:50.150097: step: 1688/529, loss: 0.00018169709073845297
2023-01-22 17:41:51.200266: step: 1692/529, loss: 0.00715620955452323
2023-01-22 17:41:52.258151: step: 1696/529, loss: 8.939039253164083e-05
2023-01-22 17:41:53.319332: step: 1700/529, loss: 0.0057845208793878555
2023-01-22 17:41:54.386998: step: 1704/529, loss: 0.0036745222751051188
2023-01-22 17:41:55.481510: step: 1708/529, loss: 0.0041084326803684235
2023-01-22 17:41:56.557018: step: 1712/529, loss: 0.005269292276352644
2023-01-22 17:41:57.616556: step: 1716/529, loss: 0.003057217225432396
2023-01-22 17:41:58.702911: step: 1720/529, loss: 0.00042299754568375647
2023-01-22 17:41:59.757952: step: 1724/529, loss: 0.0015383093850687146
2023-01-22 17:42:00.846218: step: 1728/529, loss: 0.0008272006525658071
2023-01-22 17:42:01.912239: step: 1732/529, loss: 0.00575598469004035
2023-01-22 17:42:02.978651: step: 1736/529, loss: 0.000451031606644392
2023-01-22 17:42:04.047690: step: 1740/529, loss: 0.00012466817861422896
2023-01-22 17:42:05.119811: step: 1744/529, loss: 0.0038290719967335463
2023-01-22 17:42:06.196117: step: 1748/529, loss: 0.011712432838976383
2023-01-22 17:42:07.259982: step: 1752/529, loss: 2.7688449335983023e-05
2023-01-22 17:42:08.326456: step: 1756/529, loss: 0.0015026670880615711
2023-01-22 17:42:09.396224: step: 1760/529, loss: 0.003128649899736047
2023-01-22 17:42:10.466423: step: 1764/529, loss: 0.0017477100482210517
2023-01-22 17:42:11.543097: step: 1768/529, loss: 0.006452275440096855
2023-01-22 17:42:12.611583: step: 1772/529, loss: 0.0018919184803962708
2023-01-22 17:42:13.671596: step: 1776/529, loss: 0.001168661518022418
2023-01-22 17:42:14.738478: step: 1780/529, loss: 0.0013780271401628852
2023-01-22 17:42:15.833242: step: 1784/529, loss: 0.0091183390468359
2023-01-22 17:42:16.915443: step: 1788/529, loss: 0.0010438120225444436
2023-01-22 17:42:17.972959: step: 1792/529, loss: 0.002068291185423732
2023-01-22 17:42:19.035710: step: 1796/529, loss: 0.0006684469408355653
2023-01-22 17:42:20.087232: step: 1800/529, loss: 0.006883364636451006
2023-01-22 17:42:21.140562: step: 1804/529, loss: 6.186648533912376e-05
2023-01-22 17:42:22.217596: step: 1808/529, loss: 0.0005298329633660614
2023-01-22 17:42:23.272025: step: 1812/529, loss: 0.0002774820604827255
2023-01-22 17:42:24.354171: step: 1816/529, loss: 0.0002061830018647015
2023-01-22 17:42:25.415523: step: 1820/529, loss: 4.0665730921318755e-05
2023-01-22 17:42:26.480574: step: 1824/529, loss: 0.0008008748409338295
2023-01-22 17:42:27.546144: step: 1828/529, loss: 3.203128289896995e-05
2023-01-22 17:42:28.613247: step: 1832/529, loss: 0.004102792590856552
2023-01-22 17:42:29.696879: step: 1836/529, loss: 0.0005983141018077731
2023-01-22 17:42:30.753008: step: 1840/529, loss: 9.179474000120535e-05
2023-01-22 17:42:31.817895: step: 1844/529, loss: 0.002192548243328929
2023-01-22 17:42:32.890092: step: 1848/529, loss: 0.0021154964342713356
2023-01-22 17:42:33.956447: step: 1852/529, loss: 0.004692483227699995
2023-01-22 17:42:35.039747: step: 1856/529, loss: 0.002063579158857465
2023-01-22 17:42:36.113158: step: 1860/529, loss: 0.0034239974338561296
2023-01-22 17:42:37.195334: step: 1864/529, loss: 0.0017422258388251066
2023-01-22 17:42:38.259988: step: 1868/529, loss: 6.844824383733794e-06
2023-01-22 17:42:39.340923: step: 1872/529, loss: 3.4428646813466912e-06
2023-01-22 17:42:40.403191: step: 1876/529, loss: 0.0005339368362911046
2023-01-22 17:42:41.467969: step: 1880/529, loss: 0.010746901854872704
2023-01-22 17:42:42.538297: step: 1884/529, loss: 0.0029423637315630913
2023-01-22 17:42:43.606844: step: 1888/529, loss: 0.012396391481161118
2023-01-22 17:42:44.666799: step: 1892/529, loss: 2.0159728592261672e-05
2023-01-22 17:42:45.747957: step: 1896/529, loss: 0.0009077794966287911
2023-01-22 17:42:46.825897: step: 1900/529, loss: 0.00228919368237257
2023-01-22 17:42:47.891326: step: 1904/529, loss: 0.0007247887551784515
2023-01-22 17:42:48.956821: step: 1908/529, loss: 0.0069438316859304905
2023-01-22 17:42:50.009074: step: 1912/529, loss: 0.004304738715291023
2023-01-22 17:42:51.082633: step: 1916/529, loss: 0.0035784002393484116
2023-01-22 17:42:52.163889: step: 1920/529, loss: 0.011989950202405453
2023-01-22 17:42:53.237614: step: 1924/529, loss: 0.0019601411186158657
2023-01-22 17:42:54.321360: step: 1928/529, loss: 0.0013878459576517344
2023-01-22 17:42:55.380724: step: 1932/529, loss: 0.002206981647759676
2023-01-22 17:42:56.428787: step: 1936/529, loss: 2.1091598227940267e-06
2023-01-22 17:42:57.486298: step: 1940/529, loss: 0.0016788952052593231
2023-01-22 17:42:58.572564: step: 1944/529, loss: 0.018700117245316505
2023-01-22 17:42:59.649480: step: 1948/529, loss: 0.00289915781468153
2023-01-22 17:43:00.713682: step: 1952/529, loss: 0.006917925551533699
2023-01-22 17:43:01.788180: step: 1956/529, loss: 0.0002779752539936453
2023-01-22 17:43:02.861269: step: 1960/529, loss: 0.0005320819327607751
2023-01-22 17:43:03.937167: step: 1964/529, loss: 0.0
2023-01-22 17:43:05.014219: step: 1968/529, loss: 0.003783997381106019
2023-01-22 17:43:06.096073: step: 1972/529, loss: 0.008835915476083755
2023-01-22 17:43:07.158594: step: 1976/529, loss: 0.00048177296412177384
2023-01-22 17:43:08.221499: step: 1980/529, loss: 0.0069314478896558285
2023-01-22 17:43:09.279113: step: 1984/529, loss: 0.003239867277443409
2023-01-22 17:43:10.345570: step: 1988/529, loss: 0.0015226966934278607
2023-01-22 17:43:11.435056: step: 1992/529, loss: 0.0015954652335494757
2023-01-22 17:43:12.512131: step: 1996/529, loss: 0.0003833039663732052
2023-01-22 17:43:13.598165: step: 2000/529, loss: 0.0002944319858215749
2023-01-22 17:43:14.660892: step: 2004/529, loss: 0.005284524522721767
2023-01-22 17:43:15.736593: step: 2008/529, loss: 0.005018971860408783
2023-01-22 17:43:16.821703: step: 2012/529, loss: 0.0023734390269964933
2023-01-22 17:43:17.896367: step: 2016/529, loss: 0.0006474965484812856
2023-01-22 17:43:18.956784: step: 2020/529, loss: 0.0018509947694838047
2023-01-22 17:43:20.028887: step: 2024/529, loss: 0.008611795492470264
2023-01-22 17:43:21.101911: step: 2028/529, loss: 0.011392266489565372
2023-01-22 17:43:22.170840: step: 2032/529, loss: 0.00043303260463289917
2023-01-22 17:43:23.249095: step: 2036/529, loss: 4.455868838704191e-05
2023-01-22 17:43:24.314991: step: 2040/529, loss: 0.0022229517344385386
2023-01-22 17:43:25.404514: step: 2044/529, loss: 0.003587716957554221
2023-01-22 17:43:26.481206: step: 2048/529, loss: 0.004381757695227861
2023-01-22 17:43:27.568658: step: 2052/529, loss: 0.0020230996888130903
2023-01-22 17:43:28.659005: step: 2056/529, loss: 0.0034694720525294542
2023-01-22 17:43:29.733941: step: 2060/529, loss: 0.003932279068976641
2023-01-22 17:43:30.814352: step: 2064/529, loss: 0.0020144081208854914
2023-01-22 17:43:31.919453: step: 2068/529, loss: 0.0013614704366773367
2023-01-22 17:43:32.991230: step: 2072/529, loss: 0.004141340497881174
2023-01-22 17:43:34.061977: step: 2076/529, loss: 0.0019316418329253793
2023-01-22 17:43:35.134194: step: 2080/529, loss: 0.0006597943720407784
2023-01-22 17:43:36.204252: step: 2084/529, loss: 0.006309060379862785
2023-01-22 17:43:37.293368: step: 2088/529, loss: 0.0016341398004442453
2023-01-22 17:43:38.393286: step: 2092/529, loss: 0.006675537209957838
2023-01-22 17:43:39.475155: step: 2096/529, loss: 0.0009607902029529214
2023-01-22 17:43:40.562370: step: 2100/529, loss: 0.0047721462324261665
2023-01-22 17:43:41.636187: step: 2104/529, loss: 0.031034506857395172
2023-01-22 17:43:42.696143: step: 2108/529, loss: 0.0018453217344358563
2023-01-22 17:43:43.772273: step: 2112/529, loss: 0.011940338648855686
2023-01-22 17:43:44.847966: step: 2116/529, loss: 0.0018543225014582276
==================================================
Loss: 0.005
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31895509499136443, 'r': 0.35042694497153704, 'f1': 0.33395117540687164}, 'combined': 0.2460692871419054, 'stategy': 1, 'epoch': 14}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30974259121117653, 'r': 0.3071803822765253, 'f1': 0.30845616605155474}, 'combined': 0.20137552809583364, 'stategy': 1, 'epoch': 14}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32029430116472546, 'r': 0.36526921252371913, 'f1': 0.34130651595744677}, 'combined': 0.25148901175811866, 'stategy': 1, 'epoch': 14}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3350524597483881, 'r': 0.31257191787188776, 'f1': 0.3234220129763327}, 'combined': 0.21114597738351254, 'stategy': 1, 'epoch': 14}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31457623509369675, 'r': 0.35039136622390893, 'f1': 0.3315192998204668}, 'combined': 0.24427737881508077, 'stategy': 1, 'epoch': 14}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3221064440461693, 'r': 0.319444407318515, 'f1': 0.3207699027845669}, 'combined': 0.20941454793189343, 'stategy': 1, 'epoch': 14}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2976190476190476, 'r': 0.41666666666666663, 'f1': 0.34722222222222227}, 'combined': 0.2314814814814815, 'stategy': 1, 'epoch': 14}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3409090909090909, 'r': 0.4891304347826087, 'f1': 0.40178571428571425}, 'combined': 0.20089285714285712, 'stategy': 1, 'epoch': 14}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 14}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3230331803005008, 'r': 0.36716674573055025, 'f1': 0.34368894316163406}, 'combined': 0.25324448443488823, 'stategy': 1, 'epoch': 12}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33365609306255056, 'r': 0.31188257963659366, 'f1': 0.32240213457920563}, 'combined': 0.21048015003616533, 'stategy': 1, 'epoch': 12}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 17:46:18.379064: step: 4/529, loss: 0.0014406029367819428
2023-01-22 17:46:19.434545: step: 8/529, loss: 0.0005166666815057397
2023-01-22 17:46:20.503976: step: 12/529, loss: 0.0055794198997318745
2023-01-22 17:46:21.577024: step: 16/529, loss: 0.0024013204965740442
2023-01-22 17:46:22.639003: step: 20/529, loss: 0.0009924215264618397
2023-01-22 17:46:23.712807: step: 24/529, loss: 0.052919644862413406
2023-01-22 17:46:24.793239: step: 28/529, loss: 0.0010007554665207863
2023-01-22 17:46:25.848428: step: 32/529, loss: 0.0035555881913751364
2023-01-22 17:46:26.909203: step: 36/529, loss: 0.00017612775263842195
2023-01-22 17:46:27.972452: step: 40/529, loss: 0.0013773787068203092
2023-01-22 17:46:29.038417: step: 44/529, loss: 0.00011239123705308884
2023-01-22 17:46:30.105556: step: 48/529, loss: 0.0119791179895401
2023-01-22 17:46:31.190509: step: 52/529, loss: 0.0032426011748611927
2023-01-22 17:46:32.253568: step: 56/529, loss: 0.0023406182881444693
2023-01-22 17:46:33.320280: step: 60/529, loss: 0.0007079282077029347
2023-01-22 17:46:34.392884: step: 64/529, loss: 0.029164807870984077
2023-01-22 17:46:35.454832: step: 68/529, loss: 0.006156122777611017
2023-01-22 17:46:36.522680: step: 72/529, loss: 0.0028103936929255724
2023-01-22 17:46:37.577620: step: 76/529, loss: 0.0008448417065665126
2023-01-22 17:46:38.652264: step: 80/529, loss: 0.006331016309559345
2023-01-22 17:46:39.711621: step: 84/529, loss: 0.0013154357438907027
2023-01-22 17:46:40.790157: step: 88/529, loss: 0.003233660012483597
2023-01-22 17:46:41.867645: step: 92/529, loss: 0.004117619711905718
2023-01-22 17:46:42.937228: step: 96/529, loss: 0.00036356100463308394
2023-01-22 17:46:44.019032: step: 100/529, loss: 0.0028379629366099834
2023-01-22 17:46:45.097253: step: 104/529, loss: 0.007633896078914404
2023-01-22 17:46:46.169895: step: 108/529, loss: 0.0003820745041593909
2023-01-22 17:46:47.244343: step: 112/529, loss: 0.0018571915570646524
2023-01-22 17:46:48.323603: step: 116/529, loss: 0.004072810057550669
2023-01-22 17:46:49.391632: step: 120/529, loss: 0.004594247322529554
2023-01-22 17:46:50.469360: step: 124/529, loss: 0.0029200438875705004
2023-01-22 17:46:51.530713: step: 128/529, loss: 0.0008496983209624887
2023-01-22 17:46:52.594398: step: 132/529, loss: 0.001706223003566265
2023-01-22 17:46:53.688805: step: 136/529, loss: 0.00247276877053082
2023-01-22 17:46:54.763653: step: 140/529, loss: 0.004223995376378298
2023-01-22 17:46:55.824407: step: 144/529, loss: 0.004998901393264532
2023-01-22 17:46:56.875474: step: 148/529, loss: 0.0010829686652868986
2023-01-22 17:46:57.941221: step: 152/529, loss: 0.004460414871573448
2023-01-22 17:46:59.014380: step: 156/529, loss: 0.00247690686956048
2023-01-22 17:47:00.084389: step: 160/529, loss: 0.0006109255482442677
2023-01-22 17:47:01.146938: step: 164/529, loss: 1.267790503334254e-05
2023-01-22 17:47:02.212162: step: 168/529, loss: 0.0027858333196491003
2023-01-22 17:47:03.296041: step: 172/529, loss: 0.005347960162907839
2023-01-22 17:47:04.366777: step: 176/529, loss: 0.0011582892620936036
2023-01-22 17:47:05.434316: step: 180/529, loss: 8.794327004579827e-05
2023-01-22 17:47:06.497123: step: 184/529, loss: 0.00025748019106686115
2023-01-22 17:47:07.560681: step: 188/529, loss: 1.555074231873732e-05
2023-01-22 17:47:08.626844: step: 192/529, loss: 0.0011577480472624302
2023-01-22 17:47:09.702831: step: 196/529, loss: 0.0011529306648299098
2023-01-22 17:47:10.773844: step: 200/529, loss: 0.0032238292042165995
2023-01-22 17:47:11.851778: step: 204/529, loss: 0.015989812090992928
2023-01-22 17:47:12.936940: step: 208/529, loss: 0.008752340450882912
2023-01-22 17:47:14.024669: step: 212/529, loss: 0.008068365044891834
2023-01-22 17:47:15.116798: step: 216/529, loss: 0.0016642805421724916
2023-01-22 17:47:16.175224: step: 220/529, loss: 0.0010034673614427447
2023-01-22 17:47:17.241982: step: 224/529, loss: 0.004248702432960272
2023-01-22 17:47:18.325759: step: 228/529, loss: 0.006841846741735935
2023-01-22 17:47:19.399482: step: 232/529, loss: 0.0008880904060788453
2023-01-22 17:47:20.470533: step: 236/529, loss: 0.0002831376332323998
2023-01-22 17:47:21.558850: step: 240/529, loss: 0.002143791178241372
2023-01-22 17:47:22.613502: step: 244/529, loss: 0.0009778562234714627
2023-01-22 17:47:23.677670: step: 248/529, loss: 0.00015718958457000554
2023-01-22 17:47:24.744746: step: 252/529, loss: 0.0006788586033508182
2023-01-22 17:47:25.817468: step: 256/529, loss: 0.0001369896490359679
2023-01-22 17:47:26.894561: step: 260/529, loss: 0.006800807546824217
2023-01-22 17:47:27.946179: step: 264/529, loss: 0.002131674438714981
2023-01-22 17:47:29.022774: step: 268/529, loss: 0.012378649786114693
2023-01-22 17:47:30.088339: step: 272/529, loss: 0.005594603717327118
2023-01-22 17:47:31.162138: step: 276/529, loss: 1.4710850564370048e-06
2023-01-22 17:47:32.262731: step: 280/529, loss: 0.00035618359106592834
2023-01-22 17:47:33.349472: step: 284/529, loss: 0.002371045295149088
2023-01-22 17:47:34.412488: step: 288/529, loss: 0.0014916997170075774
2023-01-22 17:47:35.485475: step: 292/529, loss: 0.003098335349932313
2023-01-22 17:47:36.551294: step: 296/529, loss: 0.0009281517122872174
2023-01-22 17:47:37.648161: step: 300/529, loss: 0.0231844000518322
2023-01-22 17:47:38.729283: step: 304/529, loss: 0.0037730697076767683
2023-01-22 17:47:39.808780: step: 308/529, loss: 0.0038550340104848146
2023-01-22 17:47:40.890819: step: 312/529, loss: 0.003156480845063925
2023-01-22 17:47:41.963418: step: 316/529, loss: 0.009825780056416988
2023-01-22 17:47:43.047337: step: 320/529, loss: 0.0002331018476979807
2023-01-22 17:47:44.110168: step: 324/529, loss: 1.4097027815296315e-05
2023-01-22 17:47:45.196954: step: 328/529, loss: 0.0008861885871738195
2023-01-22 17:47:46.266061: step: 332/529, loss: 0.0016851425170898438
2023-01-22 17:47:47.349316: step: 336/529, loss: 0.0005363310337997973
2023-01-22 17:47:48.417186: step: 340/529, loss: 0.0007374809356406331
2023-01-22 17:47:49.516227: step: 344/529, loss: 0.0009122372139245272
2023-01-22 17:47:50.583820: step: 348/529, loss: 0.0001343362091574818
2023-01-22 17:47:51.669629: step: 352/529, loss: 0.0014942878624424338
2023-01-22 17:47:52.752889: step: 356/529, loss: 4.1831168346107006e-05
2023-01-22 17:47:53.827968: step: 360/529, loss: 0.0076486216858029366
2023-01-22 17:47:54.916695: step: 364/529, loss: 0.0057144626043736935
2023-01-22 17:47:55.993593: step: 368/529, loss: 0.0014407701091840863
2023-01-22 17:47:57.057511: step: 372/529, loss: 0.004227327182888985
2023-01-22 17:47:58.145648: step: 376/529, loss: 0.004579753149300814
2023-01-22 17:47:59.226888: step: 380/529, loss: 0.0029917466454207897
2023-01-22 17:48:00.317627: step: 384/529, loss: 0.0003732573240995407
2023-01-22 17:48:01.398096: step: 388/529, loss: 0.0005306508392095566
2023-01-22 17:48:02.481219: step: 392/529, loss: 1.5595917375321733e-06
2023-01-22 17:48:03.541792: step: 396/529, loss: 0.014625673182308674
2023-01-22 17:48:04.609679: step: 400/529, loss: 0.001569255138747394
2023-01-22 17:48:05.687877: step: 404/529, loss: 0.002541843568906188
2023-01-22 17:48:06.756846: step: 408/529, loss: 0.009019548073410988
2023-01-22 17:48:07.861637: step: 412/529, loss: 0.0013536105398088694
2023-01-22 17:48:08.944567: step: 416/529, loss: 0.0003253206086810678
2023-01-22 17:48:10.022350: step: 420/529, loss: 0.0023956219665706158
2023-01-22 17:48:11.081180: step: 424/529, loss: 0.0036653790157288313
2023-01-22 17:48:12.141871: step: 428/529, loss: 0.036183107644319534
2023-01-22 17:48:13.216888: step: 432/529, loss: 0.0028086304664611816
2023-01-22 17:48:14.305009: step: 436/529, loss: 0.005541963502764702
2023-01-22 17:48:15.379559: step: 440/529, loss: 0.011829298920929432
2023-01-22 17:48:16.444935: step: 444/529, loss: 0.001492236857302487
2023-01-22 17:48:17.514792: step: 448/529, loss: 0.004675740376114845
2023-01-22 17:48:18.606063: step: 452/529, loss: 0.0012503373436629772
2023-01-22 17:48:19.676124: step: 456/529, loss: 0.0004541607340797782
2023-01-22 17:48:20.739473: step: 460/529, loss: 0.0011744523653760552
2023-01-22 17:48:21.819921: step: 464/529, loss: 0.0009027521009556949
2023-01-22 17:48:22.883232: step: 468/529, loss: 0.0018053650856018066
2023-01-22 17:48:23.962236: step: 472/529, loss: 0.004834257531911135
2023-01-22 17:48:25.028752: step: 476/529, loss: 1.590656211192254e-05
2023-01-22 17:48:26.117264: step: 480/529, loss: 0.0005579310236498713
2023-01-22 17:48:27.207447: step: 484/529, loss: 0.002521494636312127
2023-01-22 17:48:28.284209: step: 488/529, loss: 0.0009275380289182067
2023-01-22 17:48:29.383796: step: 492/529, loss: 8.145716856233776e-05
2023-01-22 17:48:30.479208: step: 496/529, loss: 0.0035063971299678087
2023-01-22 17:48:31.555799: step: 500/529, loss: 0.004410580266267061
2023-01-22 17:48:32.635444: step: 504/529, loss: 2.120953104167711e-05
2023-01-22 17:48:33.720978: step: 508/529, loss: 0.00011912729678442702
2023-01-22 17:48:34.822069: step: 512/529, loss: 0.0013176235370337963
2023-01-22 17:48:35.893121: step: 516/529, loss: 0.00691906176507473
2023-01-22 17:48:36.970576: step: 520/529, loss: 0.011709775775671005
2023-01-22 17:48:38.045787: step: 524/529, loss: 7.465539965778589e-05
2023-01-22 17:48:39.123891: step: 528/529, loss: 4.04789752792567e-05
2023-01-22 17:48:40.216236: step: 532/529, loss: 0.0036931922659277916
2023-01-22 17:48:41.305707: step: 536/529, loss: 0.0015838434919714928
2023-01-22 17:48:42.372630: step: 540/529, loss: 0.002325591165572405
2023-01-22 17:48:43.462382: step: 544/529, loss: 0.005759669467806816
2023-01-22 17:48:44.545472: step: 548/529, loss: 0.005209536291658878
2023-01-22 17:48:45.642490: step: 552/529, loss: 0.006583836395293474
2023-01-22 17:48:46.719939: step: 556/529, loss: 0.0037974235601723194
2023-01-22 17:48:47.785607: step: 560/529, loss: 0.002532810438424349
2023-01-22 17:48:48.851798: step: 564/529, loss: 0.003581755328923464
2023-01-22 17:48:49.918078: step: 568/529, loss: 0.0007503884844481945
2023-01-22 17:48:50.980691: step: 572/529, loss: 0.006548554636538029
2023-01-22 17:48:52.051617: step: 576/529, loss: 0.002439468400552869
2023-01-22 17:48:53.121162: step: 580/529, loss: 0.00270541338250041
2023-01-22 17:48:54.191478: step: 584/529, loss: 6.443067104555666e-05
2023-01-22 17:48:55.280243: step: 588/529, loss: 0.0006757031078450382
2023-01-22 17:48:56.351267: step: 592/529, loss: 0.0021824685391038656
2023-01-22 17:48:57.431296: step: 596/529, loss: 0.0005361948860809207
2023-01-22 17:48:58.512709: step: 600/529, loss: 0.004789344500750303
2023-01-22 17:48:59.587641: step: 604/529, loss: 0.001820781733840704
2023-01-22 17:49:00.677815: step: 608/529, loss: 0.009909247979521751
2023-01-22 17:49:01.760168: step: 612/529, loss: 0.0002098877594107762
2023-01-22 17:49:02.832262: step: 616/529, loss: 0.0003080358146689832
2023-01-22 17:49:03.908391: step: 620/529, loss: 0.002664165571331978
2023-01-22 17:49:04.987916: step: 624/529, loss: 0.0009047680650837719
2023-01-22 17:49:06.072663: step: 628/529, loss: 0.004044122528284788
2023-01-22 17:49:07.156411: step: 632/529, loss: 0.0039992681704461575
2023-01-22 17:49:08.258188: step: 636/529, loss: 0.0009118133457377553
2023-01-22 17:49:09.339658: step: 640/529, loss: 0.0008229080121964216
2023-01-22 17:49:10.406872: step: 644/529, loss: 0.0015035989927127957
2023-01-22 17:49:11.470950: step: 648/529, loss: 0.003242161124944687
2023-01-22 17:49:12.550275: step: 652/529, loss: 0.00345221278257668
2023-01-22 17:49:13.633670: step: 656/529, loss: 0.00026589020853862166
2023-01-22 17:49:14.724990: step: 660/529, loss: 0.012026051990687847
2023-01-22 17:49:15.796683: step: 664/529, loss: 0.0007402487099170685
2023-01-22 17:49:16.869409: step: 668/529, loss: 0.0045550731010735035
2023-01-22 17:49:17.946625: step: 672/529, loss: 0.003394849132746458
2023-01-22 17:49:19.036398: step: 676/529, loss: 0.004230661783367395
2023-01-22 17:49:20.125323: step: 680/529, loss: 0.0020529828034341335
2023-01-22 17:49:21.194043: step: 684/529, loss: 5.553709343075752e-05
2023-01-22 17:49:22.279105: step: 688/529, loss: 0.0007035293383523822
2023-01-22 17:49:23.356805: step: 692/529, loss: 0.0006701484089717269
2023-01-22 17:49:24.417353: step: 696/529, loss: 0.016399648040533066
2023-01-22 17:49:25.510435: step: 700/529, loss: 0.02274392358958721
2023-01-22 17:49:26.581340: step: 704/529, loss: 0.0034613735042512417
2023-01-22 17:49:27.665717: step: 708/529, loss: 0.01630670204758644
2023-01-22 17:49:28.735569: step: 712/529, loss: 0.004414531867951155
2023-01-22 17:49:29.817161: step: 716/529, loss: 0.00618187990039587
2023-01-22 17:49:30.892139: step: 720/529, loss: 0.012535316869616508
2023-01-22 17:49:31.975423: step: 724/529, loss: 0.025236256420612335
2023-01-22 17:49:33.040499: step: 728/529, loss: 0.0109225083142519
2023-01-22 17:49:34.113646: step: 732/529, loss: 0.0029832429718226194
2023-01-22 17:49:35.195577: step: 736/529, loss: 0.01108157355338335
2023-01-22 17:49:36.259198: step: 740/529, loss: 0.007448251359164715
2023-01-22 17:49:37.355673: step: 744/529, loss: 0.023523937910795212
2023-01-22 17:49:38.433345: step: 748/529, loss: 0.0038337353616952896
2023-01-22 17:49:39.518036: step: 752/529, loss: 0.008344761095941067
2023-01-22 17:49:40.629164: step: 756/529, loss: 0.019771428778767586
2023-01-22 17:49:41.713695: step: 760/529, loss: 0.00035001744981855154
2023-01-22 17:49:42.797789: step: 764/529, loss: 0.005875334143638611
2023-01-22 17:49:43.878431: step: 768/529, loss: 0.002457705792039633
2023-01-22 17:49:44.960254: step: 772/529, loss: 1.4393920537258964e-05
2023-01-22 17:49:46.038510: step: 776/529, loss: 0.006355027202516794
2023-01-22 17:49:47.106833: step: 780/529, loss: 0.00011113999062217772
2023-01-22 17:49:48.187591: step: 784/529, loss: 0.0014787557302042842
2023-01-22 17:49:49.268559: step: 788/529, loss: 0.00033515787799842656
2023-01-22 17:49:50.327124: step: 792/529, loss: 0.011279977858066559
2023-01-22 17:49:51.403115: step: 796/529, loss: 0.00278403889387846
2023-01-22 17:49:52.476174: step: 800/529, loss: 0.005266489926725626
2023-01-22 17:49:53.558735: step: 804/529, loss: 0.002984214574098587
2023-01-22 17:49:54.645677: step: 808/529, loss: 0.004232475534081459
2023-01-22 17:49:55.724839: step: 812/529, loss: 0.002166487742215395
2023-01-22 17:49:56.808577: step: 816/529, loss: 0.022144053131341934
2023-01-22 17:49:57.879785: step: 820/529, loss: 0.004441455472260714
2023-01-22 17:49:58.961148: step: 824/529, loss: 0.00011230283416807652
2023-01-22 17:50:00.041098: step: 828/529, loss: 0.0354902409017086
2023-01-22 17:50:01.110708: step: 832/529, loss: 0.004579294007271528
2023-01-22 17:50:02.192412: step: 836/529, loss: 0.002783134113997221
2023-01-22 17:50:03.268630: step: 840/529, loss: 0.004558006767183542
2023-01-22 17:50:04.347965: step: 844/529, loss: 0.0074923960492014885
2023-01-22 17:50:05.426858: step: 848/529, loss: 0.008867579512298107
2023-01-22 17:50:06.507318: step: 852/529, loss: 0.0037276153452694416
2023-01-22 17:50:07.603027: step: 856/529, loss: 0.002161223441362381
2023-01-22 17:50:08.680276: step: 860/529, loss: 0.00037463707849383354
2023-01-22 17:50:09.757072: step: 864/529, loss: 0.006098653189837933
2023-01-22 17:50:10.832572: step: 868/529, loss: 0.004756368231028318
2023-01-22 17:50:11.919734: step: 872/529, loss: 0.0020644301548600197
2023-01-22 17:50:12.997546: step: 876/529, loss: 0.0030793799087405205
2023-01-22 17:50:14.089160: step: 880/529, loss: 0.00506234634667635
2023-01-22 17:50:15.156763: step: 884/529, loss: 0.0021876669488847256
2023-01-22 17:50:16.260550: step: 888/529, loss: 0.0013469543773680925
2023-01-22 17:50:17.347652: step: 892/529, loss: 0.00020525470608845353
2023-01-22 17:50:18.412014: step: 896/529, loss: 0.00028438394656404853
2023-01-22 17:50:19.493027: step: 900/529, loss: 0.003786481451243162
2023-01-22 17:50:20.562403: step: 904/529, loss: 0.0038216193206608295
2023-01-22 17:50:21.639990: step: 908/529, loss: 8.71155771164922e-06
2023-01-22 17:50:22.722814: step: 912/529, loss: 0.019581666216254234
2023-01-22 17:50:23.786381: step: 916/529, loss: 0.001887670368887484
2023-01-22 17:50:24.862618: step: 920/529, loss: 0.003705795854330063
2023-01-22 17:50:25.966857: step: 924/529, loss: 0.007517037447541952
2023-01-22 17:50:27.040324: step: 928/529, loss: 4.0604254536447115e-07
2023-01-22 17:50:28.132359: step: 932/529, loss: 0.006292502395808697
2023-01-22 17:50:29.196155: step: 936/529, loss: 0.0008214179542846978
2023-01-22 17:50:30.283275: step: 940/529, loss: 0.0001273697562282905
2023-01-22 17:50:31.357574: step: 944/529, loss: 0.006866239011287689
2023-01-22 17:50:32.439588: step: 948/529, loss: 0.004648054949939251
2023-01-22 17:50:33.525563: step: 952/529, loss: 0.0018585880752652884
2023-01-22 17:50:34.580526: step: 956/529, loss: 0.00021947783534415066
2023-01-22 17:50:35.666599: step: 960/529, loss: 0.005518754944205284
2023-01-22 17:50:36.759561: step: 964/529, loss: 0.00654368381947279
2023-01-22 17:50:37.830941: step: 968/529, loss: 0.0060023777186870575
2023-01-22 17:50:38.910449: step: 972/529, loss: 0.000745442055631429
2023-01-22 17:50:39.984486: step: 976/529, loss: 0.0006995638832449913
2023-01-22 17:50:41.070140: step: 980/529, loss: 0.0002712214190978557
2023-01-22 17:50:42.155491: step: 984/529, loss: 4.598938176059164e-05
2023-01-22 17:50:43.247223: step: 988/529, loss: 0.00021073105745017529
2023-01-22 17:50:44.318464: step: 992/529, loss: 0.0026787295937538147
2023-01-22 17:50:45.410329: step: 996/529, loss: 0.004937823861837387
2023-01-22 17:50:46.501354: step: 1000/529, loss: 0.0035365531221032143
2023-01-22 17:50:47.591847: step: 1004/529, loss: 0.002807697979733348
2023-01-22 17:50:48.672379: step: 1008/529, loss: 0.005513792857527733
2023-01-22 17:50:49.755746: step: 1012/529, loss: 0.0002561243891250342
2023-01-22 17:50:50.851988: step: 1016/529, loss: 0.006081057246774435
2023-01-22 17:50:51.923642: step: 1020/529, loss: 0.005015847738832235
2023-01-22 17:50:53.026207: step: 1024/529, loss: 0.0024155641440302134
2023-01-22 17:50:54.118353: step: 1028/529, loss: 0.005686714313924313
2023-01-22 17:50:55.191395: step: 1032/529, loss: 0.0059417602606117725
2023-01-22 17:50:56.287773: step: 1036/529, loss: 0.009248845279216766
2023-01-22 17:50:57.358149: step: 1040/529, loss: 0.004371550865471363
2023-01-22 17:50:58.434124: step: 1044/529, loss: 0.0020127687603235245
2023-01-22 17:50:59.512441: step: 1048/529, loss: 0.001159345149062574
2023-01-22 17:51:00.588205: step: 1052/529, loss: 4.526906559476629e-05
2023-01-22 17:51:01.664515: step: 1056/529, loss: 0.003700123867020011
2023-01-22 17:51:02.739636: step: 1060/529, loss: 0.003462725318968296
2023-01-22 17:51:03.816890: step: 1064/529, loss: 0.005008205771446228
2023-01-22 17:51:04.886294: step: 1068/529, loss: 0.00031501176999881864
2023-01-22 17:51:05.970087: step: 1072/529, loss: 0.0027354652993381023
2023-01-22 17:51:07.053000: step: 1076/529, loss: 0.008873580023646355
2023-01-22 17:51:08.133416: step: 1080/529, loss: 8.971295028459281e-05
2023-01-22 17:51:09.218813: step: 1084/529, loss: 0.014573873020708561
2023-01-22 17:51:10.305105: step: 1088/529, loss: 0.004396980162709951
2023-01-22 17:51:11.369108: step: 1092/529, loss: 0.001197937992401421
2023-01-22 17:51:12.441205: step: 1096/529, loss: 0.00785503163933754
2023-01-22 17:51:13.512364: step: 1100/529, loss: 0.010189991444349289
2023-01-22 17:51:14.585855: step: 1104/529, loss: 0.002251886995509267
2023-01-22 17:51:15.671470: step: 1108/529, loss: 0.002838397864252329
2023-01-22 17:51:16.756301: step: 1112/529, loss: 0.00024347318685613573
2023-01-22 17:51:17.836237: step: 1116/529, loss: 0.0024957633577287197
2023-01-22 17:51:18.910002: step: 1120/529, loss: 0.0016599871451035142
2023-01-22 17:51:19.990723: step: 1124/529, loss: 0.0037962065543979406
2023-01-22 17:51:21.080204: step: 1128/529, loss: 0.0019828176591545343
2023-01-22 17:51:22.158257: step: 1132/529, loss: 0.0019687071908265352
2023-01-22 17:51:23.262842: step: 1136/529, loss: 0.011665153317153454
2023-01-22 17:51:24.339210: step: 1140/529, loss: 0.00034134433371946216
2023-01-22 17:51:25.423835: step: 1144/529, loss: 0.002435169881209731
2023-01-22 17:51:26.495146: step: 1148/529, loss: 0.0007438263855874538
2023-01-22 17:51:27.563111: step: 1152/529, loss: 0.007376573048532009
2023-01-22 17:51:28.635546: step: 1156/529, loss: 0.00010170307359658182
2023-01-22 17:51:29.720064: step: 1160/529, loss: 0.0053239623084664345
2023-01-22 17:51:30.795843: step: 1164/529, loss: 0.010280627757310867
2023-01-22 17:51:31.855547: step: 1168/529, loss: 0.010312197729945183
2023-01-22 17:51:32.938169: step: 1172/529, loss: 0.006687337998300791
2023-01-22 17:51:34.007611: step: 1176/529, loss: 0.0010680067352950573
2023-01-22 17:51:35.094769: step: 1180/529, loss: 0.00954980868846178
2023-01-22 17:51:36.191271: step: 1184/529, loss: 0.004383870866149664
2023-01-22 17:51:37.285333: step: 1188/529, loss: 0.0003942779148928821
2023-01-22 17:51:38.345993: step: 1192/529, loss: 0.001772363786585629
2023-01-22 17:51:39.439873: step: 1196/529, loss: 0.0011210321681573987
2023-01-22 17:51:40.531962: step: 1200/529, loss: 0.013752724044024944
2023-01-22 17:51:41.602322: step: 1204/529, loss: 0.0003787998575717211
2023-01-22 17:51:42.689273: step: 1208/529, loss: 0.011433050036430359
2023-01-22 17:51:43.776442: step: 1212/529, loss: 0.0009741354733705521
2023-01-22 17:51:44.862579: step: 1216/529, loss: 0.013240729458630085
2023-01-22 17:51:45.946330: step: 1220/529, loss: 0.005714384838938713
2023-01-22 17:51:47.043802: step: 1224/529, loss: 0.00011433459440013394
2023-01-22 17:51:48.130627: step: 1228/529, loss: 0.0015510107623413205
2023-01-22 17:51:49.209235: step: 1232/529, loss: 0.0036971797235310078
2023-01-22 17:51:50.303333: step: 1236/529, loss: 0.0013544723624363542
2023-01-22 17:51:51.366502: step: 1240/529, loss: 0.012556590139865875
2023-01-22 17:51:52.431948: step: 1244/529, loss: 0.0016521679935976863
2023-01-22 17:51:53.530148: step: 1248/529, loss: 0.0019292457727715373
2023-01-22 17:51:54.630305: step: 1252/529, loss: 0.0047577121295034885
2023-01-22 17:51:55.708483: step: 1256/529, loss: 0.013279648497700691
2023-01-22 17:51:56.783972: step: 1260/529, loss: 0.0020150321070104837
2023-01-22 17:51:57.864988: step: 1264/529, loss: 0.06822654604911804
2023-01-22 17:51:58.926958: step: 1268/529, loss: 0.00014766899403184652
2023-01-22 17:51:59.998719: step: 1272/529, loss: 0.004514533095061779
2023-01-22 17:52:01.076403: step: 1276/529, loss: 0.003707671305164695
2023-01-22 17:52:02.155497: step: 1280/529, loss: 0.0008800482610240579
2023-01-22 17:52:03.238539: step: 1284/529, loss: 0.0025320565328001976
2023-01-22 17:52:04.321388: step: 1288/529, loss: 0.0003295718925073743
2023-01-22 17:52:05.404742: step: 1292/529, loss: 0.009966210462152958
2023-01-22 17:52:06.482750: step: 1296/529, loss: 0.010593287646770477
2023-01-22 17:52:07.563796: step: 1300/529, loss: 0.01655689999461174
2023-01-22 17:52:08.634610: step: 1304/529, loss: 0.005912919994443655
2023-01-22 17:52:09.713874: step: 1308/529, loss: 0.0003717422659974545
2023-01-22 17:52:10.798891: step: 1312/529, loss: 0.00473179342225194
2023-01-22 17:52:11.880203: step: 1316/529, loss: 0.04951927065849304
2023-01-22 17:52:12.961993: step: 1320/529, loss: 0.0061185224913060665
2023-01-22 17:52:14.045457: step: 1324/529, loss: 0.0075952596962451935
2023-01-22 17:52:15.120855: step: 1328/529, loss: 0.00022339631686918437
2023-01-22 17:52:16.210044: step: 1332/529, loss: 0.003941317554563284
2023-01-22 17:52:17.300309: step: 1336/529, loss: 7.480735803255811e-05
2023-01-22 17:52:18.387893: step: 1340/529, loss: 0.011999009177088737
2023-01-22 17:52:19.471862: step: 1344/529, loss: 0.0013146221172064543
2023-01-22 17:52:20.542103: step: 1348/529, loss: 0.05926206335425377
2023-01-22 17:52:21.600861: step: 1352/529, loss: 0.00828623678535223
2023-01-22 17:52:22.687275: step: 1356/529, loss: 0.004431975074112415
2023-01-22 17:52:23.766310: step: 1360/529, loss: 0.004410061985254288
2023-01-22 17:52:24.836563: step: 1364/529, loss: 0.0013089042622596025
2023-01-22 17:52:25.921529: step: 1368/529, loss: 0.007834733463823795
2023-01-22 17:52:26.977587: step: 1372/529, loss: 0.003975994884967804
2023-01-22 17:52:28.041608: step: 1376/529, loss: 0.010506715625524521
2023-01-22 17:52:29.120200: step: 1380/529, loss: 0.001384251518175006
2023-01-22 17:52:30.212422: step: 1384/529, loss: 0.006658020429313183
2023-01-22 17:52:31.281755: step: 1388/529, loss: 0.0011319330660626292
2023-01-22 17:52:32.364478: step: 1392/529, loss: 0.001445335103198886
2023-01-22 17:52:33.425431: step: 1396/529, loss: 0.0019462514901533723
2023-01-22 17:52:34.525822: step: 1400/529, loss: 0.03967732563614845
2023-01-22 17:52:35.609465: step: 1404/529, loss: 0.022351933643221855
2023-01-22 17:52:36.676507: step: 1408/529, loss: 0.003850222798064351
2023-01-22 17:52:37.760511: step: 1412/529, loss: 0.00017581836436875165
2023-01-22 17:52:38.826537: step: 1416/529, loss: 0.008602466434240341
2023-01-22 17:52:39.926668: step: 1420/529, loss: 0.010391976684331894
2023-01-22 17:52:41.007812: step: 1424/529, loss: 0.0233137384057045
2023-01-22 17:52:42.073694: step: 1428/529, loss: 0.007026453968137503
2023-01-22 17:52:43.148499: step: 1432/529, loss: 0.0029631215147674084
2023-01-22 17:52:44.230076: step: 1436/529, loss: 0.002670511370524764
2023-01-22 17:52:45.301062: step: 1440/529, loss: 0.006047316826879978
2023-01-22 17:52:46.391597: step: 1444/529, loss: 0.02050812914967537
2023-01-22 17:52:47.454557: step: 1448/529, loss: 0.008940990082919598
2023-01-22 17:52:48.540072: step: 1452/529, loss: 0.007197519764304161
2023-01-22 17:52:49.631756: step: 1456/529, loss: 0.005508510861545801
2023-01-22 17:52:50.717162: step: 1460/529, loss: 0.06660294532775879
2023-01-22 17:52:51.803869: step: 1464/529, loss: 0.010147585533559322
2023-01-22 17:52:52.900836: step: 1468/529, loss: 0.0052138096652925014
2023-01-22 17:52:53.978945: step: 1472/529, loss: 0.003988031763583422
2023-01-22 17:52:55.054800: step: 1476/529, loss: 0.004229758400470018
2023-01-22 17:52:56.122663: step: 1480/529, loss: 0.003836695570498705
2023-01-22 17:52:57.196844: step: 1484/529, loss: 0.003095924388617277
2023-01-22 17:52:58.281331: step: 1488/529, loss: 0.0056379917077720165
2023-01-22 17:52:59.365940: step: 1492/529, loss: 0.019603027030825615
2023-01-22 17:53:00.426455: step: 1496/529, loss: 0.002713260240852833
2023-01-22 17:53:01.493315: step: 1500/529, loss: 0.01192429568618536
2023-01-22 17:53:02.565897: step: 1504/529, loss: 0.024023110046982765
2023-01-22 17:53:03.636886: step: 1508/529, loss: 0.02491852082312107
2023-01-22 17:53:04.715826: step: 1512/529, loss: 0.015108231455087662
2023-01-22 17:53:05.793081: step: 1516/529, loss: 0.00885758176445961
2023-01-22 17:53:06.885134: step: 1520/529, loss: 0.004531919956207275
2023-01-22 17:53:07.954913: step: 1524/529, loss: 0.07931800931692123
2023-01-22 17:53:09.039180: step: 1528/529, loss: 0.01182169932872057
2023-01-22 17:53:10.111290: step: 1532/529, loss: 0.004285391420125961
2023-01-22 17:53:11.184655: step: 1536/529, loss: 0.008243849501013756
2023-01-22 17:53:12.232537: step: 1540/529, loss: 0.01846648007631302
2023-01-22 17:53:13.336615: step: 1544/529, loss: 0.0836813822388649
2023-01-22 17:53:14.403450: step: 1548/529, loss: 0.04009845852851868
2023-01-22 17:53:15.480639: step: 1552/529, loss: 0.025475895032286644
2023-01-22 17:53:16.529420: step: 1556/529, loss: 0.002944002626463771
2023-01-22 17:53:17.603819: step: 1560/529, loss: 0.01520458422601223
2023-01-22 17:53:18.692916: step: 1564/529, loss: 0.016403669491410255
2023-01-22 17:53:19.769597: step: 1568/529, loss: 0.010399769991636276
2023-01-22 17:53:20.842944: step: 1572/529, loss: 0.02235635183751583
2023-01-22 17:53:21.927482: step: 1576/529, loss: 0.04166422411799431
2023-01-22 17:53:23.004890: step: 1580/529, loss: 0.006262169219553471
2023-01-22 17:53:24.079582: step: 1584/529, loss: 0.004788485821336508
2023-01-22 17:53:25.159913: step: 1588/529, loss: 0.0006601986242458224
2023-01-22 17:53:26.234099: step: 1592/529, loss: 0.010616461746394634
2023-01-22 17:53:27.302653: step: 1596/529, loss: 0.0005407176213338971
2023-01-22 17:53:28.389576: step: 1600/529, loss: 0.015413879416882992
2023-01-22 17:53:29.463796: step: 1604/529, loss: 0.0013394468696787953
2023-01-22 17:53:30.520192: step: 1608/529, loss: 0.005355029832571745
2023-01-22 17:53:31.589797: step: 1612/529, loss: 0.006717989221215248
2023-01-22 17:53:32.679310: step: 1616/529, loss: 0.009617160074412823
2023-01-22 17:53:33.743317: step: 1620/529, loss: 0.0011271152179688215
2023-01-22 17:53:34.818230: step: 1624/529, loss: 0.03819387033581734
2023-01-22 17:53:35.894021: step: 1628/529, loss: 0.00708995433524251
2023-01-22 17:53:36.973600: step: 1632/529, loss: 0.006487742532044649
2023-01-22 17:53:38.035601: step: 1636/529, loss: 2.0126548406551592e-05
2023-01-22 17:53:39.108528: step: 1640/529, loss: 0.020241333171725273
2023-01-22 17:53:40.199752: step: 1644/529, loss: 0.006108326371759176
2023-01-22 17:53:41.272614: step: 1648/529, loss: 0.0041269357316195965
2023-01-22 17:53:42.357798: step: 1652/529, loss: 0.007861895486712456
2023-01-22 17:53:43.442200: step: 1656/529, loss: 0.016316376626491547
2023-01-22 17:53:44.521088: step: 1660/529, loss: 0.010215459391474724
2023-01-22 17:53:45.583838: step: 1664/529, loss: 0.0442894883453846
2023-01-22 17:53:46.651879: step: 1668/529, loss: 0.003823575796559453
2023-01-22 17:53:47.728404: step: 1672/529, loss: 0.0047595868818461895
2023-01-22 17:53:48.817989: step: 1676/529, loss: 0.00584134366363287
2023-01-22 17:53:49.887832: step: 1680/529, loss: 0.006459423806518316
2023-01-22 17:53:50.967395: step: 1684/529, loss: 0.006974353455007076
2023-01-22 17:53:52.039584: step: 1688/529, loss: 0.008059553802013397
2023-01-22 17:53:53.125826: step: 1692/529, loss: 0.004898645915091038
2023-01-22 17:53:54.199345: step: 1696/529, loss: 0.025280611589550972
2023-01-22 17:53:55.281012: step: 1700/529, loss: 0.0001225828455062583
2023-01-22 17:53:56.344126: step: 1704/529, loss: 0.0002256205480080098
2023-01-22 17:53:57.430353: step: 1708/529, loss: 0.007077811285853386
2023-01-22 17:53:58.491396: step: 1712/529, loss: 0.011649307794868946
2023-01-22 17:53:59.580210: step: 1716/529, loss: 0.02036501280963421
2023-01-22 17:54:00.653525: step: 1720/529, loss: 0.004421024117618799
2023-01-22 17:54:01.711124: step: 1724/529, loss: 0.0001589000748936087
2023-01-22 17:54:02.801263: step: 1728/529, loss: 0.1147143691778183
2023-01-22 17:54:03.876093: step: 1732/529, loss: 0.00032137572998180985
2023-01-22 17:54:04.940668: step: 1736/529, loss: 0.012886990793049335
2023-01-22 17:54:06.018777: step: 1740/529, loss: 0.0007714257808402181
2023-01-22 17:54:07.085245: step: 1744/529, loss: 0.007499590050429106
2023-01-22 17:54:08.167766: step: 1748/529, loss: 0.0013658899115398526
2023-01-22 17:54:09.256615: step: 1752/529, loss: 0.012005806900560856
2023-01-22 17:54:10.317391: step: 1756/529, loss: 0.007383640389889479
2023-01-22 17:54:11.406465: step: 1760/529, loss: 0.012057912535965443
2023-01-22 17:54:12.483757: step: 1764/529, loss: 0.01914384961128235
2023-01-22 17:54:13.543159: step: 1768/529, loss: 0.004751065745949745
2023-01-22 17:54:14.614859: step: 1772/529, loss: 0.037016380578279495
2023-01-22 17:54:15.684192: step: 1776/529, loss: 1.788167173799593e-05
2023-01-22 17:54:16.773233: step: 1780/529, loss: 0.0023537336383014917
2023-01-22 17:54:17.841146: step: 1784/529, loss: 0.06649907678365707
2023-01-22 17:54:18.911126: step: 1788/529, loss: 0.00046867263154126704
2023-01-22 17:54:19.953630: step: 1792/529, loss: 0.0030611385591328144
2023-01-22 17:54:21.023431: step: 1796/529, loss: 0.0029054179321974516
2023-01-22 17:54:22.102574: step: 1800/529, loss: 0.0012938749277964234
2023-01-22 17:54:23.185534: step: 1804/529, loss: 0.019227538257837296
2023-01-22 17:54:24.264794: step: 1808/529, loss: 0.011588284745812416
2023-01-22 17:54:25.348011: step: 1812/529, loss: 0.0004917408805340528
2023-01-22 17:54:26.434471: step: 1816/529, loss: 0.002023714128881693
2023-01-22 17:54:27.513543: step: 1820/529, loss: 0.004464180674403906
2023-01-22 17:54:28.576103: step: 1824/529, loss: 0.003917478956282139
2023-01-22 17:54:29.640523: step: 1828/529, loss: 0.01375524327158928
2023-01-22 17:54:30.717256: step: 1832/529, loss: 0.0004942264058627188
2023-01-22 17:54:31.810905: step: 1836/529, loss: 0.0043309531174600124
2023-01-22 17:54:32.876058: step: 1840/529, loss: 0.004723868332803249
2023-01-22 17:54:33.940443: step: 1844/529, loss: 0.000695010123308748
2023-01-22 17:54:35.002221: step: 1848/529, loss: 0.016243886202573776
2023-01-22 17:54:36.101400: step: 1852/529, loss: 0.009934772737324238
2023-01-22 17:54:37.173240: step: 1856/529, loss: 0.004993104841560125
2023-01-22 17:54:38.241906: step: 1860/529, loss: 0.0043144216760993
2023-01-22 17:54:39.292683: step: 1864/529, loss: 0.002567149233072996
2023-01-22 17:54:40.352233: step: 1868/529, loss: 0.005471567623317242
2023-01-22 17:54:41.426423: step: 1872/529, loss: 0.0025861479807645082
2023-01-22 17:54:42.489693: step: 1876/529, loss: 0.00028775312239304185
2023-01-22 17:54:43.595223: step: 1880/529, loss: 0.014888478443026543
2023-01-22 17:54:44.654334: step: 1884/529, loss: 0.00999882910400629
2023-01-22 17:54:45.718583: step: 1888/529, loss: 0.0033422678243368864
2023-01-22 17:54:46.785013: step: 1892/529, loss: 0.045420411974191666
2023-01-22 17:54:47.850122: step: 1896/529, loss: 0.0019703619182109833
2023-01-22 17:54:48.920903: step: 1900/529, loss: 0.0038814619183540344
2023-01-22 17:54:50.005773: step: 1904/529, loss: 0.006972117815166712
2023-01-22 17:54:51.075670: step: 1908/529, loss: 0.00014306962839327753
2023-01-22 17:54:52.139708: step: 1912/529, loss: 8.572261322115082e-06
2023-01-22 17:54:53.195161: step: 1916/529, loss: 0.0010433811694383621
2023-01-22 17:54:54.261131: step: 1920/529, loss: 0.013767136260867119
2023-01-22 17:54:55.333221: step: 1924/529, loss: 0.018282251432538033
2023-01-22 17:54:56.414023: step: 1928/529, loss: 0.0023097163066267967
2023-01-22 17:54:57.495680: step: 1932/529, loss: 0.008481103926897049
2023-01-22 17:54:58.562191: step: 1936/529, loss: 0.00039895385270938277
2023-01-22 17:54:59.637054: step: 1940/529, loss: 0.006965293549001217
2023-01-22 17:55:00.706398: step: 1944/529, loss: 0.0018776124343276024
2023-01-22 17:55:01.772313: step: 1948/529, loss: 1.5175035514403135e-05
2023-01-22 17:55:02.837810: step: 1952/529, loss: 0.0023299106396734715
2023-01-22 17:55:03.915309: step: 1956/529, loss: 0.001219909405335784
2023-01-22 17:55:04.993355: step: 1960/529, loss: 1.7902691979543306e-05
2023-01-22 17:55:06.077121: step: 1964/529, loss: 0.011577676050364971
2023-01-22 17:55:07.159946: step: 1968/529, loss: 0.010660630650818348
2023-01-22 17:55:08.229340: step: 1972/529, loss: 0.0015880067367106676
2023-01-22 17:55:09.300630: step: 1976/529, loss: 0.0007982393726706505
2023-01-22 17:55:10.358902: step: 1980/529, loss: 0.005514700431376696
2023-01-22 17:55:11.432658: step: 1984/529, loss: 0.00013628712622448802
2023-01-22 17:55:12.518162: step: 1988/529, loss: 0.0029673371464014053
2023-01-22 17:55:13.583410: step: 1992/529, loss: 0.006338965147733688
2023-01-22 17:55:14.665574: step: 1996/529, loss: 0.0006737405201420188
2023-01-22 17:55:15.761940: step: 2000/529, loss: 0.0029726927168667316
2023-01-22 17:55:16.823012: step: 2004/529, loss: 0.0008707870147190988
2023-01-22 17:55:17.883766: step: 2008/529, loss: 0.002293345518410206
2023-01-22 17:55:18.951345: step: 2012/529, loss: 0.010868585668504238
2023-01-22 17:55:20.026886: step: 2016/529, loss: 0.001958066364750266
2023-01-22 17:55:21.081337: step: 2020/529, loss: 0.00029370779520832
2023-01-22 17:55:22.168573: step: 2024/529, loss: 0.002247725147753954
2023-01-22 17:55:23.235506: step: 2028/529, loss: 0.003144902177155018
2023-01-22 17:55:24.308472: step: 2032/529, loss: 0.002322837710380554
2023-01-22 17:55:25.359286: step: 2036/529, loss: 0.008072112686932087
2023-01-22 17:55:26.443414: step: 2040/529, loss: 0.05930409952998161
2023-01-22 17:55:27.524139: step: 2044/529, loss: 0.006734666880220175
2023-01-22 17:55:28.582584: step: 2048/529, loss: 0.0032757148146629333
2023-01-22 17:55:29.631548: step: 2052/529, loss: 0.0004420387267600745
2023-01-22 17:55:30.704688: step: 2056/529, loss: 0.001882361015304923
2023-01-22 17:55:31.783444: step: 2060/529, loss: 0.0025561205111443996
2023-01-22 17:55:32.853165: step: 2064/529, loss: 0.0038214854430407286
2023-01-22 17:55:33.919791: step: 2068/529, loss: 0.00022664254356641322
2023-01-22 17:55:34.992375: step: 2072/529, loss: 0.00832713395357132
2023-01-22 17:55:36.071887: step: 2076/529, loss: 0.0032956209033727646
2023-01-22 17:55:37.144592: step: 2080/529, loss: 0.0043381499126553535
2023-01-22 17:55:38.229705: step: 2084/529, loss: 0.005727696698158979
2023-01-22 17:55:39.312666: step: 2088/529, loss: 0.001343218027614057
2023-01-22 17:55:40.373083: step: 2092/529, loss: 0.0005521242856048048
2023-01-22 17:55:41.447678: step: 2096/529, loss: 0.0005589186330325902
2023-01-22 17:55:42.532238: step: 2100/529, loss: 0.011060362681746483
2023-01-22 17:55:43.593572: step: 2104/529, loss: 0.0019971111323684454
2023-01-22 17:55:44.669410: step: 2108/529, loss: 0.006012806203216314
2023-01-22 17:55:45.752394: step: 2112/529, loss: 0.00186148623470217
2023-01-22 17:55:46.832364: step: 2116/529, loss: 0.025643527507781982
==================================================
Loss: 0.007
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3212370242214533, 'r': 0.35232447817836815, 'f1': 0.33606334841628965}, 'combined': 0.247625625148845, 'stategy': 1, 'epoch': 15}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30805042371455343, 'r': 0.3046528087471135, 'f1': 0.3063421958566169}, 'combined': 0.19999542320172914, 'stategy': 1, 'epoch': 15}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3254499299719888, 'r': 0.36744346932321315, 'f1': 0.34517416815210933}, 'combined': 0.25433886074365947, 'stategy': 1, 'epoch': 15}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33152386480769086, 'r': 0.3095847855189466, 'f1': 0.32017894167738964}, 'combined': 0.20902873912617148, 'stategy': 1, 'epoch': 15}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3177884615384615, 'r': 0.35276328273244784, 'f1': 0.33436375899280574}, 'combined': 0.2463732960999621, 'stategy': 1, 'epoch': 15}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3232917447551827, 'r': 0.3215105230209943, 'f1': 0.3223986736370744}, 'combined': 0.2104778905609916, 'stategy': 1, 'epoch': 15}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 15}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3629032258064516, 'r': 0.4891304347826087, 'f1': 0.41666666666666663}, 'combined': 0.20833333333333331, 'stategy': 1, 'epoch': 15}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 15}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3230331803005008, 'r': 0.36716674573055025, 'f1': 0.34368894316163406}, 'combined': 0.25324448443488823, 'stategy': 1, 'epoch': 12}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.33365609306255056, 'r': 0.31188257963659366, 'f1': 0.32240213457920563}, 'combined': 0.21048015003616533, 'stategy': 1, 'epoch': 12}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 12}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 17:58:22.917905: step: 4/529, loss: 0.0010954438475891948
2023-01-22 17:58:23.993529: step: 8/529, loss: 0.00014005853154230863
2023-01-22 17:58:25.057342: step: 12/529, loss: 0.0013785591581836343
2023-01-22 17:58:26.129534: step: 16/529, loss: 0.005142595618963242
2023-01-22 17:58:27.201291: step: 20/529, loss: 0.008900392800569534
2023-01-22 17:58:28.253454: step: 24/529, loss: 0.0006917696446180344
2023-01-22 17:58:29.331679: step: 28/529, loss: 0.004724801983684301
2023-01-22 17:58:30.390613: step: 32/529, loss: 0.009850116446614265
2023-01-22 17:58:31.452307: step: 36/529, loss: 0.0032707988284528255
2023-01-22 17:58:32.527277: step: 40/529, loss: 0.002567447954788804
2023-01-22 17:58:33.590718: step: 44/529, loss: 0.000650116999167949
2023-01-22 17:58:34.652106: step: 48/529, loss: 0.0013387176441028714
2023-01-22 17:58:35.716576: step: 52/529, loss: 0.006641398649662733
2023-01-22 17:58:36.755376: step: 56/529, loss: 0.0027483964804559946
2023-01-22 17:58:37.830960: step: 60/529, loss: 0.004357555881142616
2023-01-22 17:58:38.922225: step: 64/529, loss: 0.009028466418385506
2023-01-22 17:58:39.992166: step: 68/529, loss: 6.34523676126264e-05
2023-01-22 17:58:41.060243: step: 72/529, loss: 0.006409817840903997
2023-01-22 17:58:42.114093: step: 76/529, loss: 0.009009601548314095
2023-01-22 17:58:43.182638: step: 80/529, loss: 0.0050859469920396805
2023-01-22 17:58:44.240865: step: 84/529, loss: 0.0046436237171292305
2023-01-22 17:58:45.307030: step: 88/529, loss: 0.0021038404665887356
2023-01-22 17:58:46.369460: step: 92/529, loss: 0.0002085765008814633
2023-01-22 17:58:47.444987: step: 96/529, loss: 9.38282537390478e-05
2023-01-22 17:58:48.517304: step: 100/529, loss: 9.447576303500682e-06
2023-01-22 17:58:49.601351: step: 104/529, loss: 0.004167590290307999
2023-01-22 17:58:50.718070: step: 108/529, loss: 0.0044244155287742615
2023-01-22 17:58:51.779482: step: 112/529, loss: 0.0027735703624784946
2023-01-22 17:58:52.858189: step: 116/529, loss: 5.468056406243704e-05
2023-01-22 17:58:53.925464: step: 120/529, loss: 0.008275819011032581
2023-01-22 17:58:54.990794: step: 124/529, loss: 0.000756150926463306
2023-01-22 17:58:56.060991: step: 128/529, loss: 0.009803102351725101
2023-01-22 17:58:57.129384: step: 132/529, loss: 0.0065562487579882145
2023-01-22 17:58:58.206305: step: 136/529, loss: 0.0007596256909891963
2023-01-22 17:58:59.263576: step: 140/529, loss: 0.0006582309724763036
2023-01-22 17:59:00.332075: step: 144/529, loss: 0.0004294962855055928
2023-01-22 17:59:01.392381: step: 148/529, loss: 0.0011537284590303898
2023-01-22 17:59:02.486008: step: 152/529, loss: 0.00482360552996397
2023-01-22 17:59:03.556811: step: 156/529, loss: 0.00574611546471715
2023-01-22 17:59:04.607055: step: 160/529, loss: 0.0026020624209195375
2023-01-22 17:59:05.676743: step: 164/529, loss: 0.0018216570606455207
2023-01-22 17:59:06.763931: step: 168/529, loss: 0.00622558081522584
2023-01-22 17:59:07.820682: step: 172/529, loss: 0.000253814912866801
2023-01-22 17:59:08.897104: step: 176/529, loss: 0.007571086753159761
2023-01-22 17:59:09.964893: step: 180/529, loss: 0.02941497229039669
2023-01-22 17:59:11.027363: step: 184/529, loss: 0.005346913821995258
2023-01-22 17:59:12.114704: step: 188/529, loss: 0.0126403933390975
2023-01-22 17:59:13.192331: step: 192/529, loss: 0.014569035731256008
2023-01-22 17:59:14.261933: step: 196/529, loss: 0.000573804893065244
2023-01-22 17:59:15.325221: step: 200/529, loss: 0.0012837330577895045
2023-01-22 17:59:16.403088: step: 204/529, loss: 0.00323014915920794
2023-01-22 17:59:17.475866: step: 208/529, loss: 0.008282310329377651
2023-01-22 17:59:18.560426: step: 212/529, loss: 1.6132453311001882e-05
2023-01-22 17:59:19.626150: step: 216/529, loss: 0.0003099872265011072
2023-01-22 17:59:20.687623: step: 220/529, loss: 0.0011674208799377084
2023-01-22 17:59:21.768593: step: 224/529, loss: 0.0006898681749589741
2023-01-22 17:59:22.835369: step: 228/529, loss: 0.0030965341720730066
2023-01-22 17:59:23.898567: step: 232/529, loss: 0.0007291412330232561
2023-01-22 17:59:24.966101: step: 236/529, loss: 0.05628994479775429
2023-01-22 17:59:26.032957: step: 240/529, loss: 0.002138701267540455
2023-01-22 17:59:27.105628: step: 244/529, loss: 0.0026771645061671734
2023-01-22 17:59:28.187322: step: 248/529, loss: 0.003572388319298625
2023-01-22 17:59:29.257671: step: 252/529, loss: 0.013278273865580559
2023-01-22 17:59:30.343976: step: 256/529, loss: 0.005799334961920977
2023-01-22 17:59:31.448631: step: 260/529, loss: 0.0029618097469210625
2023-01-22 17:59:32.510926: step: 264/529, loss: 0.004178767558187246
2023-01-22 17:59:33.586547: step: 268/529, loss: 0.0004428937681950629
2023-01-22 17:59:34.663996: step: 272/529, loss: 0.0007823935011401772
2023-01-22 17:59:35.745217: step: 276/529, loss: 0.00128506391774863
2023-01-22 17:59:36.804004: step: 280/529, loss: 0.0005061851697973907
2023-01-22 17:59:37.868800: step: 284/529, loss: 0.0006799264228902757
2023-01-22 17:59:38.923951: step: 288/529, loss: 0.0068840160965919495
2023-01-22 17:59:40.009250: step: 292/529, loss: 0.01142135076224804
2023-01-22 17:59:41.099680: step: 296/529, loss: 0.008359819650650024
2023-01-22 17:59:42.154552: step: 300/529, loss: 0.007426922675222158
2023-01-22 17:59:43.233674: step: 304/529, loss: 0.003563546808436513
2023-01-22 17:59:44.319135: step: 308/529, loss: 0.004988022614270449
2023-01-22 17:59:45.386274: step: 312/529, loss: 0.0009332579211331904
2023-01-22 17:59:46.465796: step: 316/529, loss: 0.001709270873107016
2023-01-22 17:59:47.531043: step: 320/529, loss: 0.0003621365176513791
2023-01-22 17:59:48.598235: step: 324/529, loss: 0.0006478636641986668
2023-01-22 17:59:49.668380: step: 328/529, loss: 0.00011735512089217082
2023-01-22 17:59:50.730370: step: 332/529, loss: 0.000821030989754945
2023-01-22 17:59:51.813710: step: 336/529, loss: 0.0003936767461709678
2023-01-22 17:59:52.896149: step: 340/529, loss: 0.003962892107665539
2023-01-22 17:59:53.975061: step: 344/529, loss: 0.004729588981717825
2023-01-22 17:59:55.051138: step: 348/529, loss: 0.002129775006324053
2023-01-22 17:59:56.123600: step: 352/529, loss: 0.00276339054107666
2023-01-22 17:59:57.213651: step: 356/529, loss: 0.000782274641096592
2023-01-22 17:59:58.294275: step: 360/529, loss: 0.0009951724205166101
2023-01-22 17:59:59.373859: step: 364/529, loss: 0.0035933861508965492
2023-01-22 18:00:00.450976: step: 368/529, loss: 0.000625802029389888
2023-01-22 18:00:01.536592: step: 372/529, loss: 0.0025161586236208677
2023-01-22 18:00:02.599115: step: 376/529, loss: 0.0047616539523005486
2023-01-22 18:00:03.668356: step: 380/529, loss: 0.004277392290532589
2023-01-22 18:00:04.733453: step: 384/529, loss: 0.00019334277021698654
2023-01-22 18:00:05.803371: step: 388/529, loss: 0.001998462015762925
2023-01-22 18:00:06.876343: step: 392/529, loss: 0.0002462692209519446
2023-01-22 18:00:07.962381: step: 396/529, loss: 0.0010160517413169146
2023-01-22 18:00:09.044653: step: 400/529, loss: 0.001342215808108449
2023-01-22 18:00:10.133433: step: 404/529, loss: 0.00032033113529905677
2023-01-22 18:00:11.211533: step: 408/529, loss: 0.0003599270130507648
2023-01-22 18:00:12.292815: step: 412/529, loss: 0.010256094858050346
2023-01-22 18:00:13.372388: step: 416/529, loss: 0.0032527311705052853
2023-01-22 18:00:14.450891: step: 420/529, loss: 0.006540959235280752
2023-01-22 18:00:15.535782: step: 424/529, loss: 0.001434178906492889
2023-01-22 18:00:16.631754: step: 428/529, loss: 0.005891936831176281
2023-01-22 18:00:17.712907: step: 432/529, loss: 8.731216075830162e-05
2023-01-22 18:00:18.793345: step: 436/529, loss: 0.0020319747272878885
2023-01-22 18:00:19.871430: step: 440/529, loss: 0.0036512166261672974
2023-01-22 18:00:20.973150: step: 444/529, loss: 0.013736655935645103
2023-01-22 18:00:22.032491: step: 448/529, loss: 0.0002248917444376275
2023-01-22 18:00:23.114278: step: 452/529, loss: 0.0028420104645192623
2023-01-22 18:00:24.196490: step: 456/529, loss: 0.003367389552295208
2023-01-22 18:00:25.269171: step: 460/529, loss: 7.060422831273172e-06
2023-01-22 18:00:26.341675: step: 464/529, loss: 0.0004347244102973491
2023-01-22 18:00:27.424227: step: 468/529, loss: 0.009450795128941536
2023-01-22 18:00:28.493290: step: 472/529, loss: 0.0001558825751999393
2023-01-22 18:00:29.576592: step: 476/529, loss: 0.004345542285591364
2023-01-22 18:00:30.661650: step: 480/529, loss: 0.0019708226900547743
2023-01-22 18:00:31.737753: step: 484/529, loss: 0.010202948935329914
2023-01-22 18:00:32.826469: step: 488/529, loss: 0.023752881214022636
2023-01-22 18:00:33.924933: step: 492/529, loss: 0.0038924843538552523
2023-01-22 18:00:35.021423: step: 496/529, loss: 0.003336658701300621
2023-01-22 18:00:36.112367: step: 500/529, loss: 0.006687353830784559
2023-01-22 18:00:37.213451: step: 504/529, loss: 0.0003770515904761851
2023-01-22 18:00:38.302658: step: 508/529, loss: 0.00023633446835447103
2023-01-22 18:00:39.369983: step: 512/529, loss: 0.008220965974032879
2023-01-22 18:00:40.439756: step: 516/529, loss: 0.0034480062313377857
2023-01-22 18:00:41.521243: step: 520/529, loss: 0.012186998501420021
2023-01-22 18:00:42.627963: step: 524/529, loss: 0.006798294838517904
2023-01-22 18:00:43.714892: step: 528/529, loss: 0.0014652048703283072
2023-01-22 18:00:44.792154: step: 532/529, loss: 0.002841431647539139
2023-01-22 18:00:45.867515: step: 536/529, loss: 0.004340182989835739
2023-01-22 18:00:46.939838: step: 540/529, loss: 0.00031229222076945007
2023-01-22 18:00:48.013778: step: 544/529, loss: 0.002261245856061578
2023-01-22 18:00:49.092621: step: 548/529, loss: 0.00027513556415215135
2023-01-22 18:00:50.156054: step: 552/529, loss: 8.289164543384686e-05
2023-01-22 18:00:51.226209: step: 556/529, loss: 0.0006063411710783839
2023-01-22 18:00:52.295536: step: 560/529, loss: 0.002139572286978364
2023-01-22 18:00:53.354799: step: 564/529, loss: 0.004961965139955282
2023-01-22 18:00:54.431071: step: 568/529, loss: 0.004999150056391954
2023-01-22 18:00:55.492897: step: 572/529, loss: 0.0012909912038594484
2023-01-22 18:00:56.575153: step: 576/529, loss: 0.010782454162836075
2023-01-22 18:00:57.659547: step: 580/529, loss: 0.003144910791888833
2023-01-22 18:00:58.722304: step: 584/529, loss: 0.005620375741273165
2023-01-22 18:00:59.797767: step: 588/529, loss: 0.0032185467425733805
2023-01-22 18:01:00.862603: step: 592/529, loss: 0.004467971157282591
2023-01-22 18:01:01.938510: step: 596/529, loss: 0.0006425076862797141
2023-01-22 18:01:03.026287: step: 600/529, loss: 0.007304641418159008
2023-01-22 18:01:04.099504: step: 604/529, loss: 0.0007512957672588527
2023-01-22 18:01:05.183778: step: 608/529, loss: 0.00016295410750899464
2023-01-22 18:01:06.282787: step: 612/529, loss: 0.0036396945361047983
2023-01-22 18:01:07.348683: step: 616/529, loss: 3.9047754398779944e-05
2023-01-22 18:01:08.414209: step: 620/529, loss: 3.933031257474795e-05
2023-01-22 18:01:09.478640: step: 624/529, loss: 0.004212466534227133
2023-01-22 18:01:10.540085: step: 628/529, loss: 0.0002174114342778921
2023-01-22 18:01:11.599127: step: 632/529, loss: 0.0013432024279609323
2023-01-22 18:01:12.669930: step: 636/529, loss: 0.00417986698448658
2023-01-22 18:01:13.748002: step: 640/529, loss: 0.00021822468261234462
2023-01-22 18:01:14.822291: step: 644/529, loss: 0.0008427880238741636
2023-01-22 18:01:15.903140: step: 648/529, loss: 0.008065682835876942
2023-01-22 18:01:16.987414: step: 652/529, loss: 0.0015927249332889915
2023-01-22 18:01:18.054860: step: 656/529, loss: 0.00033644938957877457
2023-01-22 18:01:19.123700: step: 660/529, loss: 0.0022307627368718386
2023-01-22 18:01:20.211825: step: 664/529, loss: 0.002486559795215726
2023-01-22 18:01:21.306564: step: 668/529, loss: 0.0035985014401376247
2023-01-22 18:01:22.393649: step: 672/529, loss: 0.001727428869344294
2023-01-22 18:01:23.471190: step: 676/529, loss: 0.004708203487098217
2023-01-22 18:01:24.539839: step: 680/529, loss: 0.0029380577616393566
2023-01-22 18:01:25.623844: step: 684/529, loss: 0.004313901532441378
2023-01-22 18:01:26.701285: step: 688/529, loss: 0.002098947297781706
2023-01-22 18:01:27.760066: step: 692/529, loss: 0.0014363566879183054
2023-01-22 18:01:28.844178: step: 696/529, loss: 0.0016961208311840892
2023-01-22 18:01:29.944064: step: 700/529, loss: 0.011711465194821358
2023-01-22 18:01:31.011763: step: 704/529, loss: 0.023736581206321716
2023-01-22 18:01:32.066844: step: 708/529, loss: 0.003962870687246323
2023-01-22 18:01:33.123229: step: 712/529, loss: 0.0026871052104979753
2023-01-22 18:01:34.198105: step: 716/529, loss: 0.0044683245941996574
2023-01-22 18:01:35.266463: step: 720/529, loss: 0.0010794788831844926
2023-01-22 18:01:36.372549: step: 724/529, loss: 0.002859567292034626
2023-01-22 18:01:37.444555: step: 728/529, loss: 0.0028695364017039537
2023-01-22 18:01:38.532328: step: 732/529, loss: 0.0017105877632275224
2023-01-22 18:01:39.602301: step: 736/529, loss: 0.0015929468208923936
2023-01-22 18:01:40.685466: step: 740/529, loss: 0.0005045856814831495
2023-01-22 18:01:41.756743: step: 744/529, loss: 0.00014082345296628773
2023-01-22 18:01:42.871798: step: 748/529, loss: 0.0057590720243752
2023-01-22 18:01:43.941147: step: 752/529, loss: 0.003147656796500087
2023-01-22 18:01:45.020422: step: 756/529, loss: 0.01637602038681507
2023-01-22 18:01:46.096577: step: 760/529, loss: 0.0022980000358074903
2023-01-22 18:01:47.165864: step: 764/529, loss: 0.003147440729662776
2023-01-22 18:01:48.219384: step: 768/529, loss: 0.0005454433849081397
2023-01-22 18:01:49.287303: step: 772/529, loss: 0.007334181107580662
2023-01-22 18:01:50.364694: step: 776/529, loss: 0.0076117683202028275
2023-01-22 18:01:51.431535: step: 780/529, loss: 0.025856632739305496
2023-01-22 18:01:52.501277: step: 784/529, loss: 0.003416971303522587
2023-01-22 18:01:53.589029: step: 788/529, loss: 0.0033766631968319416
2023-01-22 18:01:54.683339: step: 792/529, loss: 0.002056500408798456
2023-01-22 18:01:55.753340: step: 796/529, loss: 5.327885446604341e-05
2023-01-22 18:01:56.842084: step: 800/529, loss: 0.0005987496115267277
2023-01-22 18:01:57.913720: step: 804/529, loss: 0.0027309113647788763
2023-01-22 18:01:58.985690: step: 808/529, loss: 0.0005045857396908104
2023-01-22 18:02:00.067462: step: 812/529, loss: 7.377019755949732e-06
2023-01-22 18:02:01.137710: step: 816/529, loss: 0.005275465548038483
2023-01-22 18:02:02.242725: step: 820/529, loss: 0.0006710027228109539
2023-01-22 18:02:03.318311: step: 824/529, loss: 0.011098587885499
2023-01-22 18:02:04.387485: step: 828/529, loss: 0.019840924069285393
2023-01-22 18:02:05.475695: step: 832/529, loss: 0.0003957364824600518
2023-01-22 18:02:06.547456: step: 836/529, loss: 0.007990744896233082
2023-01-22 18:02:07.618846: step: 840/529, loss: 0.00018548700609244406
2023-01-22 18:02:08.692891: step: 844/529, loss: 0.0005949554615654051
2023-01-22 18:02:09.788382: step: 848/529, loss: 0.002382143633440137
2023-01-22 18:02:10.863812: step: 852/529, loss: 0.013774306513369083
2023-01-22 18:02:11.953435: step: 856/529, loss: 0.0020129827316850424
2023-01-22 18:02:13.018129: step: 860/529, loss: 0.0001959400251507759
2023-01-22 18:02:14.089848: step: 864/529, loss: 0.002107658889144659
2023-01-22 18:02:15.189540: step: 868/529, loss: 0.014242433942854404
2023-01-22 18:02:16.270077: step: 872/529, loss: 0.0010067049879580736
2023-01-22 18:02:17.350082: step: 876/529, loss: 0.005846137180924416
2023-01-22 18:02:18.435351: step: 880/529, loss: 0.0004147252475377172
2023-01-22 18:02:19.505822: step: 884/529, loss: 0.004995714407414198
2023-01-22 18:02:20.562145: step: 888/529, loss: 0.001140714855864644
2023-01-22 18:02:21.638710: step: 892/529, loss: 0.0021672435104846954
2023-01-22 18:02:22.710122: step: 896/529, loss: 0.0013585336273536086
2023-01-22 18:02:23.803296: step: 900/529, loss: 0.003301621414721012
2023-01-22 18:02:24.894997: step: 904/529, loss: 0.002283631358295679
2023-01-22 18:02:25.961208: step: 908/529, loss: 0.004097479861229658
2023-01-22 18:02:27.030577: step: 912/529, loss: 0.0033491672948002815
2023-01-22 18:02:28.108441: step: 916/529, loss: 0.0006542227929458022
2023-01-22 18:02:29.184939: step: 920/529, loss: 0.0004434731090441346
2023-01-22 18:02:30.275291: step: 924/529, loss: 0.004721059463918209
2023-01-22 18:02:31.355990: step: 928/529, loss: 0.00035630050115287304
2023-01-22 18:02:32.452113: step: 932/529, loss: 0.002155991503968835
2023-01-22 18:02:33.535675: step: 936/529, loss: 0.0004280532302800566
2023-01-22 18:02:34.632056: step: 940/529, loss: 0.0010875569423660636
2023-01-22 18:02:35.717370: step: 944/529, loss: 0.0002769070561043918
2023-01-22 18:02:36.776640: step: 948/529, loss: 5.664702985086478e-05
2023-01-22 18:02:37.869214: step: 952/529, loss: 0.00240424950607121
2023-01-22 18:02:38.931151: step: 956/529, loss: 0.0035321670584380627
2023-01-22 18:02:40.016298: step: 960/529, loss: 0.010955289006233215
2023-01-22 18:02:41.095857: step: 964/529, loss: 0.001727513736113906
2023-01-22 18:02:42.183395: step: 968/529, loss: 0.0005645964411087334
2023-01-22 18:02:43.287645: step: 972/529, loss: 0.015866288915276527
2023-01-22 18:02:44.378403: step: 976/529, loss: 0.023438313975930214
2023-01-22 18:02:45.458619: step: 980/529, loss: 0.00012244908430147916
2023-01-22 18:02:46.524399: step: 984/529, loss: 0.00037967320531606674
2023-01-22 18:02:47.599399: step: 988/529, loss: 0.00013209758617449552
2023-01-22 18:02:48.680252: step: 992/529, loss: 0.0010998069774359465
2023-01-22 18:02:49.774164: step: 996/529, loss: 0.0041693770326673985
2023-01-22 18:02:50.848395: step: 1000/529, loss: 0.0016989033902063966
2023-01-22 18:02:51.952337: step: 1004/529, loss: 0.0012132319388911128
2023-01-22 18:02:53.012832: step: 1008/529, loss: 0.0008248412632383406
2023-01-22 18:02:54.086241: step: 1012/529, loss: 0.0007059279014356434
2023-01-22 18:02:55.165128: step: 1016/529, loss: 0.0009574407013133168
2023-01-22 18:02:56.243591: step: 1020/529, loss: 0.0033111919183284044
2023-01-22 18:02:57.324460: step: 1024/529, loss: 0.007435535080730915
2023-01-22 18:02:58.379327: step: 1028/529, loss: 0.0003497051075100899
2023-01-22 18:02:59.453111: step: 1032/529, loss: 0.0013905841624364257
2023-01-22 18:03:00.540226: step: 1036/529, loss: 0.006318611558526754
2023-01-22 18:03:01.615157: step: 1040/529, loss: 0.0017095108050853014
2023-01-22 18:03:02.689624: step: 1044/529, loss: 0.0034974359441548586
2023-01-22 18:03:03.767876: step: 1048/529, loss: 0.0019471794366836548
2023-01-22 18:03:04.865695: step: 1052/529, loss: 0.0007004099315963686
2023-01-22 18:03:05.950588: step: 1056/529, loss: 0.007734659127891064
2023-01-22 18:03:07.026617: step: 1060/529, loss: 0.004697005730122328
2023-01-22 18:03:08.098741: step: 1064/529, loss: 0.0010571939637884498
2023-01-22 18:03:09.182684: step: 1068/529, loss: 0.0003072860126849264
2023-01-22 18:03:10.266531: step: 1072/529, loss: 0.0023033826146274805
2023-01-22 18:03:11.352470: step: 1076/529, loss: 0.0007356511778198183
2023-01-22 18:03:12.432481: step: 1080/529, loss: 0.006206228863447905
2023-01-22 18:03:13.506180: step: 1084/529, loss: 1.8731745512923226e-05
2023-01-22 18:03:14.582614: step: 1088/529, loss: 0.0010727845365181565
2023-01-22 18:03:15.659563: step: 1092/529, loss: 0.0033734359312802553
2023-01-22 18:03:16.729049: step: 1096/529, loss: 0.014654737897217274
2023-01-22 18:03:17.825546: step: 1100/529, loss: 0.0009916258277371526
2023-01-22 18:03:18.885817: step: 1104/529, loss: 0.0013614826602861285
2023-01-22 18:03:19.967934: step: 1108/529, loss: 0.05653456971049309
2023-01-22 18:03:21.041032: step: 1112/529, loss: 0.012455425225198269
2023-01-22 18:03:22.112008: step: 1116/529, loss: 0.0074430773966014385
2023-01-22 18:03:23.187699: step: 1120/529, loss: 0.00229323236271739
2023-01-22 18:03:24.263524: step: 1124/529, loss: 0.005573911126703024
2023-01-22 18:03:25.362894: step: 1128/529, loss: 0.008381973020732403
2023-01-22 18:03:26.453915: step: 1132/529, loss: 0.0016428804956376553
2023-01-22 18:03:27.508749: step: 1136/529, loss: 0.000961322570219636
2023-01-22 18:03:28.587458: step: 1140/529, loss: 0.0028468400705605745
2023-01-22 18:03:29.677234: step: 1144/529, loss: 1.7321572158834897e-05
2023-01-22 18:03:30.754135: step: 1148/529, loss: 0.004201015457510948
2023-01-22 18:03:31.838039: step: 1152/529, loss: 0.006543593946844339
2023-01-22 18:03:32.935128: step: 1156/529, loss: 0.002083392348140478
2023-01-22 18:03:34.009085: step: 1160/529, loss: 0.0002069090260192752
2023-01-22 18:03:35.070143: step: 1164/529, loss: 0.0020632827654480934
2023-01-22 18:03:36.151570: step: 1168/529, loss: 0.0005716446321457624
2023-01-22 18:03:37.216126: step: 1172/529, loss: 0.008840794675052166
2023-01-22 18:03:38.310205: step: 1176/529, loss: 0.002881059655919671
2023-01-22 18:03:39.380633: step: 1180/529, loss: 0.0035947225987911224
2023-01-22 18:03:40.459180: step: 1184/529, loss: 0.00636895839124918
2023-01-22 18:03:41.525265: step: 1188/529, loss: 0.015454822219908237
2023-01-22 18:03:42.608558: step: 1192/529, loss: 5.2436520491028205e-05
2023-01-22 18:03:43.680300: step: 1196/529, loss: 0.0006554363062605262
2023-01-22 18:03:44.770766: step: 1200/529, loss: 0.0036376938223838806
2023-01-22 18:03:45.856101: step: 1204/529, loss: 0.0006328403833322227
2023-01-22 18:03:46.941858: step: 1208/529, loss: 0.00024968371144495904
2023-01-22 18:03:48.002330: step: 1212/529, loss: 6.73434478812851e-05
2023-01-22 18:03:49.066706: step: 1216/529, loss: 1.1594082025112584e-05
2023-01-22 18:03:50.146905: step: 1220/529, loss: 0.0025993227027356625
2023-01-22 18:03:51.229259: step: 1224/529, loss: 0.0008273287676274776
2023-01-22 18:03:52.303165: step: 1228/529, loss: 0.00030462435097433627
2023-01-22 18:03:53.380074: step: 1232/529, loss: 0.0008110857452265918
2023-01-22 18:03:54.458790: step: 1236/529, loss: 0.009415808133780956
2023-01-22 18:03:55.528567: step: 1240/529, loss: 0.00804172083735466
2023-01-22 18:03:56.603043: step: 1244/529, loss: 0.00652984669432044
2023-01-22 18:03:57.700036: step: 1248/529, loss: 6.674671749351546e-05
2023-01-22 18:03:58.763598: step: 1252/529, loss: 0.0021721862722188234
2023-01-22 18:03:59.859441: step: 1256/529, loss: 0.005228969734162092
2023-01-22 18:04:00.960809: step: 1260/529, loss: 0.0012572129489853978
2023-01-22 18:04:02.038046: step: 1264/529, loss: 0.007516874931752682
2023-01-22 18:04:03.147410: step: 1268/529, loss: 8.773025911068544e-05
2023-01-22 18:04:04.228060: step: 1272/529, loss: 3.598104740376584e-05
2023-01-22 18:04:05.311911: step: 1276/529, loss: 0.0027793648187071085
2023-01-22 18:04:06.383719: step: 1280/529, loss: 0.0015998753951862454
2023-01-22 18:04:07.468357: step: 1284/529, loss: 0.004523026756942272
2023-01-22 18:04:08.546705: step: 1288/529, loss: 0.0004491481522563845
2023-01-22 18:04:09.627076: step: 1292/529, loss: 0.004214296117424965
2023-01-22 18:04:10.706165: step: 1296/529, loss: 0.0004579112573992461
2023-01-22 18:04:11.768044: step: 1300/529, loss: 0.0010065702954307199
2023-01-22 18:04:12.888678: step: 1304/529, loss: 0.017643973231315613
2023-01-22 18:04:13.982746: step: 1308/529, loss: 0.006803768686950207
2023-01-22 18:04:15.063339: step: 1312/529, loss: 0.0012831541243940592
2023-01-22 18:04:16.143366: step: 1316/529, loss: 0.0032608886249363422
2023-01-22 18:04:17.211009: step: 1320/529, loss: 0.0017519196262583137
2023-01-22 18:04:18.270818: step: 1324/529, loss: 0.0032986635342240334
2023-01-22 18:04:19.332797: step: 1328/529, loss: 4.6117744204821065e-05
2023-01-22 18:04:20.420709: step: 1332/529, loss: 0.0014522559940814972
2023-01-22 18:04:21.493455: step: 1336/529, loss: 0.004566948860883713
2023-01-22 18:04:22.558210: step: 1340/529, loss: 0.0013769244542345405
2023-01-22 18:04:23.642633: step: 1344/529, loss: 0.002909476635977626
2023-01-22 18:04:24.723662: step: 1348/529, loss: 0.00917851272970438
2023-01-22 18:04:25.802957: step: 1352/529, loss: 0.003980763256549835
2023-01-22 18:04:26.884958: step: 1356/529, loss: 0.0024915789254009724
2023-01-22 18:04:27.958316: step: 1360/529, loss: 0.0012534555280581117
2023-01-22 18:04:29.062350: step: 1364/529, loss: 0.02174685150384903
2023-01-22 18:04:30.137510: step: 1368/529, loss: 0.010201332159340382
2023-01-22 18:04:31.250937: step: 1372/529, loss: 0.0005428955773822963
2023-01-22 18:04:32.327364: step: 1376/529, loss: 4.276012987247668e-05
2023-01-22 18:04:33.396648: step: 1380/529, loss: 0.00165741634555161
2023-01-22 18:04:34.479167: step: 1384/529, loss: 0.014200867153704166
2023-01-22 18:04:35.537216: step: 1388/529, loss: 8.947202877607197e-05
2023-01-22 18:04:36.610566: step: 1392/529, loss: 0.0011852295137941837
2023-01-22 18:04:37.686159: step: 1396/529, loss: 0.0006104173371568322
2023-01-22 18:04:38.749338: step: 1400/529, loss: 0.001817601383663714
2023-01-22 18:04:39.814873: step: 1404/529, loss: 0.005933358334004879
2023-01-22 18:04:40.899279: step: 1408/529, loss: 2.9284942684171256e-06
2023-01-22 18:04:41.974103: step: 1412/529, loss: 0.010107898153364658
2023-01-22 18:04:43.085739: step: 1416/529, loss: 0.009911715053021908
2023-01-22 18:04:44.184748: step: 1420/529, loss: 6.0493066484923474e-06
2023-01-22 18:04:45.254814: step: 1424/529, loss: 0.00022279111726675183
2023-01-22 18:04:46.320925: step: 1428/529, loss: 0.005169587209820747
2023-01-22 18:04:47.396605: step: 1432/529, loss: 6.311206379905343e-05
2023-01-22 18:04:48.474382: step: 1436/529, loss: 0.005723575595766306
2023-01-22 18:04:49.547245: step: 1440/529, loss: 1.195803491782499e-07
2023-01-22 18:04:50.614699: step: 1444/529, loss: 0.0015658182092010975
2023-01-22 18:04:51.700621: step: 1448/529, loss: 0.0014453926123678684
2023-01-22 18:04:52.799008: step: 1452/529, loss: 0.00023209606297314167
2023-01-22 18:04:53.884381: step: 1456/529, loss: 0.003008805913850665
2023-01-22 18:04:54.967511: step: 1460/529, loss: 0.002512269653379917
2023-01-22 18:04:56.026759: step: 1464/529, loss: 0.005969419609755278
2023-01-22 18:04:57.117542: step: 1468/529, loss: 0.0013168842997401953
2023-01-22 18:04:58.197026: step: 1472/529, loss: 0.013506489805877209
2023-01-22 18:04:59.278894: step: 1476/529, loss: 0.0159147996455431
2023-01-22 18:05:00.358555: step: 1480/529, loss: 0.0004716266121249646
2023-01-22 18:05:01.440307: step: 1484/529, loss: 0.0039177448488771915
2023-01-22 18:05:02.514424: step: 1488/529, loss: 0.001691853511147201
2023-01-22 18:05:03.589410: step: 1492/529, loss: 0.002796584041789174
2023-01-22 18:05:04.656335: step: 1496/529, loss: 0.0006318148225545883
2023-01-22 18:05:05.724248: step: 1500/529, loss: 0.001606442965567112
2023-01-22 18:05:06.816451: step: 1504/529, loss: 0.0017404399113729596
2023-01-22 18:05:07.890373: step: 1508/529, loss: 6.433537055272609e-05
2023-01-22 18:05:08.983430: step: 1512/529, loss: 0.000550813740119338
2023-01-22 18:05:10.069002: step: 1516/529, loss: 0.005006174556910992
2023-01-22 18:05:11.152037: step: 1520/529, loss: 0.0002731724816840142
2023-01-22 18:05:12.219639: step: 1524/529, loss: 0.008615589700639248
2023-01-22 18:05:13.290126: step: 1528/529, loss: 0.005340637639164925
2023-01-22 18:05:14.382200: step: 1532/529, loss: 0.002051289426162839
2023-01-22 18:05:15.467303: step: 1536/529, loss: 0.006582419387996197
2023-01-22 18:05:16.543254: step: 1540/529, loss: 8.828871500554669e-08
2023-01-22 18:05:17.616169: step: 1544/529, loss: 0.0024221024941653013
2023-01-22 18:05:18.677885: step: 1548/529, loss: 0.001180012826807797
2023-01-22 18:05:19.739663: step: 1552/529, loss: 0.0013095546746626496
2023-01-22 18:05:20.831210: step: 1556/529, loss: 0.0002072866482194513
2023-01-22 18:05:21.917267: step: 1560/529, loss: 0.0016030482947826385
2023-01-22 18:05:23.009706: step: 1564/529, loss: 0.015543331392109394
2023-01-22 18:05:24.093253: step: 1568/529, loss: 0.00036658262251876295
2023-01-22 18:05:25.185107: step: 1572/529, loss: 0.0024295509792864323
2023-01-22 18:05:26.277779: step: 1576/529, loss: 0.006785272154957056
2023-01-22 18:05:27.363872: step: 1580/529, loss: 0.004670398309826851
2023-01-22 18:05:28.433120: step: 1584/529, loss: 0.0018465934554114938
2023-01-22 18:05:29.509476: step: 1588/529, loss: 0.00019738740229513496
2023-01-22 18:05:30.591779: step: 1592/529, loss: 8.536456880392507e-05
2023-01-22 18:05:31.665183: step: 1596/529, loss: 0.00225271750241518
2023-01-22 18:05:32.757525: step: 1600/529, loss: 0.003619945840910077
2023-01-22 18:05:33.836382: step: 1604/529, loss: 0.0015065292827785015
2023-01-22 18:05:34.910764: step: 1608/529, loss: 0.0011722138151526451
2023-01-22 18:05:35.985058: step: 1612/529, loss: 0.004720865283161402
2023-01-22 18:05:37.058865: step: 1616/529, loss: 0.0004522582166828215
2023-01-22 18:05:38.141320: step: 1620/529, loss: 0.02775600738823414
2023-01-22 18:05:39.207592: step: 1624/529, loss: 0.0003340844705235213
2023-01-22 18:05:40.287716: step: 1628/529, loss: 0.00024691305588930845
2023-01-22 18:05:41.364340: step: 1632/529, loss: 0.00029908629949204624
2023-01-22 18:05:42.452843: step: 1636/529, loss: 0.0063592176884412766
2023-01-22 18:05:43.535604: step: 1640/529, loss: 0.002701652003452182
2023-01-22 18:05:44.621770: step: 1644/529, loss: 0.009289263747632504
2023-01-22 18:05:45.706539: step: 1648/529, loss: 0.0001726174814393744
2023-01-22 18:05:46.791401: step: 1652/529, loss: 0.0017450257437303662
2023-01-22 18:05:47.880333: step: 1656/529, loss: 0.004294929094612598
2023-01-22 18:05:48.949290: step: 1660/529, loss: 1.2603007235156838e-05
2023-01-22 18:05:50.027291: step: 1664/529, loss: 0.00244903308339417
2023-01-22 18:05:51.111678: step: 1668/529, loss: 0.0025717755779623985
2023-01-22 18:05:52.213112: step: 1672/529, loss: 0.008560407906770706
2023-01-22 18:05:53.292660: step: 1676/529, loss: 0.0027694785967469215
2023-01-22 18:05:54.366901: step: 1680/529, loss: 0.004802444484084845
2023-01-22 18:05:55.447583: step: 1684/529, loss: 0.003135088598355651
2023-01-22 18:05:56.524795: step: 1688/529, loss: 0.009954369626939297
2023-01-22 18:05:57.593937: step: 1692/529, loss: 0.010034805163741112
2023-01-22 18:05:58.681772: step: 1696/529, loss: 0.0026271215174347162
2023-01-22 18:05:59.772701: step: 1700/529, loss: 0.002825000789016485
2023-01-22 18:06:00.849386: step: 1704/529, loss: 0.00971689261496067
2023-01-22 18:06:01.946917: step: 1708/529, loss: 0.004913742188364267
2023-01-22 18:06:03.025781: step: 1712/529, loss: 0.00012328309821896255
2023-01-22 18:06:04.093642: step: 1716/529, loss: 0.005492243450134993
2023-01-22 18:06:05.167335: step: 1720/529, loss: 0.0016261449782177806
2023-01-22 18:06:06.254916: step: 1724/529, loss: 0.009109891019761562
2023-01-22 18:06:07.327136: step: 1728/529, loss: 0.0014789358247071505
2023-01-22 18:06:08.394131: step: 1732/529, loss: 0.0028209127485752106
2023-01-22 18:06:09.461360: step: 1736/529, loss: 0.0003853342786896974
2023-01-22 18:06:10.534218: step: 1740/529, loss: 0.00039297869079746306
2023-01-22 18:06:11.601071: step: 1744/529, loss: 6.063833643565886e-05
2023-01-22 18:06:12.669104: step: 1748/529, loss: 2.0009640138596296e-05
2023-01-22 18:06:13.744934: step: 1752/529, loss: 0.0022021473851054907
2023-01-22 18:06:14.823580: step: 1756/529, loss: 0.0009158815373666584
2023-01-22 18:06:15.884113: step: 1760/529, loss: 0.0018402691930532455
2023-01-22 18:06:16.959069: step: 1764/529, loss: 9.479855361860245e-05
2023-01-22 18:06:18.053905: step: 1768/529, loss: 0.002112946705892682
2023-01-22 18:06:19.131730: step: 1772/529, loss: 0.00384847866371274
2023-01-22 18:06:20.206054: step: 1776/529, loss: 0.0003655296750366688
2023-01-22 18:06:21.289444: step: 1780/529, loss: 0.0007998215733096004
2023-01-22 18:06:22.371285: step: 1784/529, loss: 0.0012237696209922433
2023-01-22 18:06:23.455563: step: 1788/529, loss: 0.0051121520809829235
2023-01-22 18:06:24.519736: step: 1792/529, loss: 0.0017046780558302999
2023-01-22 18:06:25.590335: step: 1796/529, loss: 0.0
2023-01-22 18:06:26.670648: step: 1800/529, loss: 0.0007969383150339127
2023-01-22 18:06:27.733018: step: 1804/529, loss: 0.004054985474795103
2023-01-22 18:06:28.801722: step: 1808/529, loss: 0.0022393804974853992
2023-01-22 18:06:29.877106: step: 1812/529, loss: 0.0010669297771528363
2023-01-22 18:06:30.958658: step: 1816/529, loss: 0.0006529333186335862
2023-01-22 18:06:32.035052: step: 1820/529, loss: 0.006599863525480032
2023-01-22 18:06:33.110624: step: 1824/529, loss: 0.0020184549503028393
2023-01-22 18:06:34.187237: step: 1828/529, loss: 0.002421551151201129
2023-01-22 18:06:35.248288: step: 1832/529, loss: 1.8109219581674552e-06
2023-01-22 18:06:36.328341: step: 1836/529, loss: 0.0013850892428308725
2023-01-22 18:06:37.398647: step: 1840/529, loss: 0.004276327323168516
2023-01-22 18:06:38.466898: step: 1844/529, loss: 0.004120286554098129
2023-01-22 18:06:39.543681: step: 1848/529, loss: 0.004482806660234928
2023-01-22 18:06:40.609132: step: 1852/529, loss: 1.4339137123897672e-05
2023-01-22 18:06:41.682536: step: 1856/529, loss: 0.007714579347521067
2023-01-22 18:06:42.769193: step: 1860/529, loss: 0.0035939589142799377
2023-01-22 18:06:43.864898: step: 1864/529, loss: 0.0004403050697874278
2023-01-22 18:06:44.918088: step: 1868/529, loss: 2.0488961638420733e-07
2023-01-22 18:06:46.015349: step: 1872/529, loss: 0.006935497280210257
2023-01-22 18:06:47.093206: step: 1876/529, loss: 0.001358131063170731
2023-01-22 18:06:48.178156: step: 1880/529, loss: 0.004059590399265289
2023-01-22 18:06:49.243788: step: 1884/529, loss: 0.0001957083004526794
2023-01-22 18:06:50.336454: step: 1888/529, loss: 0.003749070456251502
2023-01-22 18:06:51.411820: step: 1892/529, loss: 1.3325626241567079e-05
2023-01-22 18:06:52.463371: step: 1896/529, loss: 0.003497549332678318
2023-01-22 18:06:53.543586: step: 1900/529, loss: 0.009957300499081612
2023-01-22 18:06:54.632470: step: 1904/529, loss: 0.003748676972463727
2023-01-22 18:06:55.721867: step: 1908/529, loss: 0.002384974854066968
2023-01-22 18:06:56.803797: step: 1912/529, loss: 0.0043234494514763355
2023-01-22 18:06:57.890889: step: 1916/529, loss: 0.03477722406387329
2023-01-22 18:06:58.965760: step: 1920/529, loss: 0.010558787733316422
2023-01-22 18:07:00.040863: step: 1924/529, loss: 0.003296146634966135
2023-01-22 18:07:01.107637: step: 1928/529, loss: 0.003266238607466221
2023-01-22 18:07:02.178230: step: 1932/529, loss: 0.0004403567872941494
2023-01-22 18:07:03.261821: step: 1936/529, loss: 0.0021226985845714808
2023-01-22 18:07:04.344064: step: 1940/529, loss: 0.0006780982366763055
2023-01-22 18:07:05.433200: step: 1944/529, loss: 0.00035880677751265466
2023-01-22 18:07:06.504673: step: 1948/529, loss: 0.0006868747295811772
2023-01-22 18:07:07.575197: step: 1952/529, loss: 0.000473122694529593
2023-01-22 18:07:08.645012: step: 1956/529, loss: 0.0008916643564589322
2023-01-22 18:07:09.725660: step: 1960/529, loss: 0.00961329322308302
2023-01-22 18:07:10.815637: step: 1964/529, loss: 0.0009683585958555341
2023-01-22 18:07:11.898730: step: 1968/529, loss: 0.005597032606601715
2023-01-22 18:07:12.969384: step: 1972/529, loss: 0.0009607592946849763
2023-01-22 18:07:14.040456: step: 1976/529, loss: 0.0030667155515402555
2023-01-22 18:07:15.120249: step: 1980/529, loss: 0.00414391839876771
2023-01-22 18:07:16.207387: step: 1984/529, loss: 0.007180177606642246
2023-01-22 18:07:17.295369: step: 1988/529, loss: 0.0014331936836242676
2023-01-22 18:07:18.366816: step: 1992/529, loss: 0.0032149862963706255
2023-01-22 18:07:19.431681: step: 1996/529, loss: 0.0005135077517479658
2023-01-22 18:07:20.506299: step: 2000/529, loss: 0.0032334676943719387
2023-01-22 18:07:21.586084: step: 2004/529, loss: 0.0012933633988723159
2023-01-22 18:07:22.641568: step: 2008/529, loss: 0.002671900438144803
2023-01-22 18:07:23.725460: step: 2012/529, loss: 0.00028709357138723135
2023-01-22 18:07:24.803754: step: 2016/529, loss: 0.0008177050622180104
2023-01-22 18:07:25.900258: step: 2020/529, loss: 0.007460963446646929
2023-01-22 18:07:26.979949: step: 2024/529, loss: 0.006277134642004967
2023-01-22 18:07:28.057906: step: 2028/529, loss: 0.0037806753534823656
2023-01-22 18:07:29.136464: step: 2032/529, loss: 0.0009752631303854287
2023-01-22 18:07:30.211004: step: 2036/529, loss: 3.725290076417309e-10
2023-01-22 18:07:31.298017: step: 2040/529, loss: 0.002428225474432111
2023-01-22 18:07:32.370250: step: 2044/529, loss: 0.002150231972336769
2023-01-22 18:07:33.444100: step: 2048/529, loss: 0.00016201801190618426
2023-01-22 18:07:34.518268: step: 2052/529, loss: 0.0
2023-01-22 18:07:35.595103: step: 2056/529, loss: 0.014403726905584335
2023-01-22 18:07:36.654443: step: 2060/529, loss: 0.0003406417672522366
2023-01-22 18:07:37.731952: step: 2064/529, loss: 0.0076192887499928474
2023-01-22 18:07:38.814945: step: 2068/529, loss: 0.00010909307457040995
2023-01-22 18:07:39.893578: step: 2072/529, loss: 0.02076174132525921
2023-01-22 18:07:40.981111: step: 2076/529, loss: 0.003686367766931653
2023-01-22 18:07:42.047433: step: 2080/529, loss: 0.0005375833134166896
2023-01-22 18:07:43.110502: step: 2084/529, loss: 0.001783317537046969
2023-01-22 18:07:44.183759: step: 2088/529, loss: 0.00028340835706330836
2023-01-22 18:07:45.277807: step: 2092/529, loss: 0.00456823967397213
2023-01-22 18:07:46.343187: step: 2096/529, loss: 0.005551275797188282
2023-01-22 18:07:47.414876: step: 2100/529, loss: 0.009063190780580044
2023-01-22 18:07:48.500891: step: 2104/529, loss: 0.009672529064118862
2023-01-22 18:07:49.571990: step: 2108/529, loss: 0.004472561180591583
2023-01-22 18:07:50.649299: step: 2112/529, loss: 0.0003142780333291739
2023-01-22 18:07:51.733965: step: 2116/529, loss: 1.1137221918033902e-06
==================================================
Loss: 0.004
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31895509499136443, 'r': 0.35042694497153704, 'f1': 0.33395117540687164}, 'combined': 0.2460692871419054, 'stategy': 1, 'epoch': 16}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30915715498315643, 'r': 0.30603148521770174, 'f1': 0.3075863795998702}, 'combined': 0.20080768823618467, 'stategy': 1, 'epoch': 16}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3238172380156076, 'r': 0.36744346932321315, 'f1': 0.34425370370370373}, 'combined': 0.2536606237816764, 'stategy': 1, 'epoch': 16}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3319312097086922, 'r': 0.3093550061071819, 'f1': 0.32024571517089817}, 'combined': 0.20907233218410967, 'stategy': 1, 'epoch': 16}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3159662969283277, 'r': 0.35134013282732446, 'f1': 0.3327156334231806}, 'combined': 0.2451588877855015, 'stategy': 1, 'epoch': 16}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3239160143633421, 'r': 0.32242879666654073, 'f1': 0.32317069449596214}, 'combined': 0.21098190417871104, 'stategy': 1, 'epoch': 16}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 16}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 16}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 16}
New best korean model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3238172380156076, 'r': 0.36744346932321315, 'f1': 0.34425370370370373}, 'combined': 0.2536606237816764, 'stategy': 1, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3319312097086922, 'r': 0.3093550061071819, 'f1': 0.32024571517089817}, 'combined': 0.20907233218410967, 'stategy': 1, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 18:10:36.468597: step: 4/529, loss: 0.004774351604282856
2023-01-22 18:10:37.549807: step: 8/529, loss: 0.00011110320338048041
2023-01-22 18:10:38.617021: step: 12/529, loss: 0.00041783173219300807
2023-01-22 18:10:39.696689: step: 16/529, loss: 0.00014816332259215415
2023-01-22 18:10:40.776820: step: 20/529, loss: 0.002932025818154216
2023-01-22 18:10:41.848139: step: 24/529, loss: 0.00035048782592639327
2023-01-22 18:10:42.932013: step: 28/529, loss: 0.004982681013643742
2023-01-22 18:10:43.993262: step: 32/529, loss: 2.1233639927231707e-05
2023-01-22 18:10:45.055289: step: 36/529, loss: 0.00013713899534195662
2023-01-22 18:10:46.130346: step: 40/529, loss: 0.00028068991377949715
2023-01-22 18:10:47.190466: step: 44/529, loss: 0.0005943615105934441
2023-01-22 18:10:48.258539: step: 48/529, loss: 0.0031879248563200235
2023-01-22 18:10:49.310918: step: 52/529, loss: 8.189268555724993e-05
2023-01-22 18:10:50.376310: step: 56/529, loss: 0.0006212772568687797
2023-01-22 18:10:51.433330: step: 60/529, loss: 0.00011823880049632862
2023-01-22 18:10:52.499018: step: 64/529, loss: 0.0012236885959282517
2023-01-22 18:10:53.564142: step: 68/529, loss: 0.0004854573926422745
2023-01-22 18:10:54.628849: step: 72/529, loss: 0.007082747295498848
2023-01-22 18:10:55.697119: step: 76/529, loss: 0.0004908978589810431
2023-01-22 18:10:56.773383: step: 80/529, loss: 0.00037303700810298324
2023-01-22 18:10:57.842766: step: 84/529, loss: 0.0001519659417681396
2023-01-22 18:10:58.903785: step: 88/529, loss: 0.0024474391248077154
2023-01-22 18:10:59.966947: step: 92/529, loss: 3.118909080512822e-05
2023-01-22 18:11:01.036454: step: 96/529, loss: 0.010022071190178394
2023-01-22 18:11:02.128441: step: 100/529, loss: 0.0076587870717048645
2023-01-22 18:11:03.197208: step: 104/529, loss: 0.0016353769460693002
2023-01-22 18:11:04.272584: step: 108/529, loss: 7.432909478666261e-05
2023-01-22 18:11:05.321578: step: 112/529, loss: 0.0013143441174179316
2023-01-22 18:11:06.416112: step: 116/529, loss: 0.0016834146808832884
2023-01-22 18:11:07.490429: step: 120/529, loss: 0.0009339546086266637
2023-01-22 18:11:08.571108: step: 124/529, loss: 5.631415479001589e-05
2023-01-22 18:11:09.641319: step: 128/529, loss: 0.0022102429065853357
2023-01-22 18:11:10.712953: step: 132/529, loss: 0.002972292946651578
2023-01-22 18:11:11.776001: step: 136/529, loss: 0.0034958343021571636
2023-01-22 18:11:12.875129: step: 140/529, loss: 0.002566281706094742
2023-01-22 18:11:13.919119: step: 144/529, loss: 0.00019849218369927257
2023-01-22 18:11:15.014063: step: 148/529, loss: 0.005178583785891533
2023-01-22 18:11:16.083983: step: 152/529, loss: 0.002736426191404462
2023-01-22 18:11:17.159757: step: 156/529, loss: 0.007798114325851202
2023-01-22 18:11:18.247983: step: 160/529, loss: 0.0048319618217647076
2023-01-22 18:11:19.334416: step: 164/529, loss: 0.008279364556074142
2023-01-22 18:11:20.421917: step: 168/529, loss: 0.002521841088309884
2023-01-22 18:11:21.507105: step: 172/529, loss: 0.008925371803343296
2023-01-22 18:11:22.578632: step: 176/529, loss: 3.7435679587360937e-06
2023-01-22 18:11:23.669451: step: 180/529, loss: 0.0020514533389359713
2023-01-22 18:11:24.738384: step: 184/529, loss: 0.0038077435456216335
2023-01-22 18:11:25.817412: step: 188/529, loss: 0.000652316608466208
2023-01-22 18:11:26.879026: step: 192/529, loss: 2.0696195861091837e-05
2023-01-22 18:11:27.972149: step: 196/529, loss: 0.002564126392826438
2023-01-22 18:11:29.036466: step: 200/529, loss: 0.003402081085368991
2023-01-22 18:11:30.107261: step: 204/529, loss: 0.004479540046304464
2023-01-22 18:11:31.196054: step: 208/529, loss: 0.0018465116154402494
2023-01-22 18:11:32.267979: step: 212/529, loss: 0.0007151631289161742
2023-01-22 18:11:33.351189: step: 216/529, loss: 0.005244481842964888
2023-01-22 18:11:34.425031: step: 220/529, loss: 0.00010370021482231095
2023-01-22 18:11:35.509706: step: 224/529, loss: 7.456904131686315e-05
2023-01-22 18:11:36.583083: step: 228/529, loss: 0.0018638074398040771
2023-01-22 18:11:37.655818: step: 232/529, loss: 0.004323921166360378
2023-01-22 18:11:38.733276: step: 236/529, loss: 0.0007034416194073856
2023-01-22 18:11:39.826923: step: 240/529, loss: 0.0007420348119921982
2023-01-22 18:11:40.889431: step: 244/529, loss: 0.0023707980290055275
2023-01-22 18:11:41.977928: step: 248/529, loss: 0.0031798563431948423
2023-01-22 18:11:43.077365: step: 252/529, loss: 0.001064923359081149
2023-01-22 18:11:44.149063: step: 256/529, loss: 0.0013210728066042066
2023-01-22 18:11:45.227203: step: 260/529, loss: 4.597189672495006e-06
2023-01-22 18:11:46.297416: step: 264/529, loss: 0.00804111361503601
2023-01-22 18:11:47.356110: step: 268/529, loss: 4.8266265366692096e-05
2023-01-22 18:11:48.439726: step: 272/529, loss: 0.005466201342642307
2023-01-22 18:11:49.516532: step: 276/529, loss: 8.47073461045511e-05
2023-01-22 18:11:50.588937: step: 280/529, loss: 0.0015489307697862387
2023-01-22 18:11:51.662896: step: 284/529, loss: 0.0033976032864302397
2023-01-22 18:11:52.734547: step: 288/529, loss: 0.0016044657677412033
2023-01-22 18:11:53.799225: step: 292/529, loss: 6.452019442804158e-05
2023-01-22 18:11:54.869292: step: 296/529, loss: 0.0023355484008789062
2023-01-22 18:11:55.923839: step: 300/529, loss: 0.009125921875238419
2023-01-22 18:11:56.984862: step: 304/529, loss: 0.009663855656981468
2023-01-22 18:11:58.054943: step: 308/529, loss: 0.0005212817923165858
2023-01-22 18:11:59.116995: step: 312/529, loss: 0.00038913520984351635
2023-01-22 18:12:00.187611: step: 316/529, loss: 2.071810740744695e-06
2023-01-22 18:12:01.269524: step: 320/529, loss: 0.0015925494953989983
2023-01-22 18:12:02.342977: step: 324/529, loss: 6.970712274778634e-05
2023-01-22 18:12:03.411182: step: 328/529, loss: 0.004545920994132757
2023-01-22 18:12:04.491485: step: 332/529, loss: 2.40278552610107e-07
2023-01-22 18:12:05.555528: step: 336/529, loss: 0.00036701513454318047
2023-01-22 18:12:06.625342: step: 340/529, loss: 0.002165420213714242
2023-01-22 18:12:07.691899: step: 344/529, loss: 0.0015689270803704858
2023-01-22 18:12:08.771856: step: 348/529, loss: 0.0008598619024269283
2023-01-22 18:12:09.862724: step: 352/529, loss: 0.030548138543963432
2023-01-22 18:12:10.937105: step: 356/529, loss: 0.004977196920663118
2023-01-22 18:12:12.022946: step: 360/529, loss: 0.00011398706556065008
2023-01-22 18:12:13.110068: step: 364/529, loss: 0.004644823260605335
2023-01-22 18:12:14.185093: step: 368/529, loss: 0.013795222155749798
2023-01-22 18:12:15.274518: step: 372/529, loss: 0.00019335832621436566
2023-01-22 18:12:16.364464: step: 376/529, loss: 1.8577834453026298e-06
2023-01-22 18:12:17.433231: step: 380/529, loss: 0.009377739392220974
2023-01-22 18:12:18.500032: step: 384/529, loss: 0.00037509846151806414
2023-01-22 18:12:19.567986: step: 388/529, loss: 0.004540981724858284
2023-01-22 18:12:20.638098: step: 392/529, loss: 0.00012763110862579197
2023-01-22 18:12:21.728261: step: 396/529, loss: 0.009456207975745201
2023-01-22 18:12:22.795610: step: 400/529, loss: 0.0034424876794219017
2023-01-22 18:12:23.867699: step: 404/529, loss: 0.04370659962296486
2023-01-22 18:12:24.933729: step: 408/529, loss: 0.0003631363215390593
2023-01-22 18:12:26.010985: step: 412/529, loss: 0.0009669842547737062
2023-01-22 18:12:27.085519: step: 416/529, loss: 3.820407982857432e-06
2023-01-22 18:12:28.169253: step: 420/529, loss: 0.0017878817161545157
2023-01-22 18:12:29.241188: step: 424/529, loss: 0.004045877140015364
2023-01-22 18:12:30.315080: step: 428/529, loss: 0.005891798529773951
2023-01-22 18:12:31.384384: step: 432/529, loss: 0.0014330159174278378
2023-01-22 18:12:32.464569: step: 436/529, loss: 0.0009665749967098236
2023-01-22 18:12:33.522120: step: 440/529, loss: 0.002940972102805972
2023-01-22 18:12:34.607379: step: 444/529, loss: 0.0002214901032857597
2023-01-22 18:12:35.690487: step: 448/529, loss: 0.0012117965379729867
2023-01-22 18:12:36.760155: step: 452/529, loss: 0.0108401570469141
2023-01-22 18:12:37.834061: step: 456/529, loss: 0.010137693956494331
2023-01-22 18:12:38.909982: step: 460/529, loss: 0.00017200839647557586
2023-01-22 18:12:39.989067: step: 464/529, loss: 0.005317979026585817
2023-01-22 18:12:41.050109: step: 468/529, loss: 0.0014371046563610435
2023-01-22 18:12:42.133690: step: 472/529, loss: 0.001969830133020878
2023-01-22 18:12:43.214715: step: 476/529, loss: 0.0020322680938988924
2023-01-22 18:12:44.307833: step: 480/529, loss: 0.002301317173987627
2023-01-22 18:12:45.374126: step: 484/529, loss: 0.003000570461153984
2023-01-22 18:12:46.452289: step: 488/529, loss: 0.013125085271894932
2023-01-22 18:12:47.521005: step: 492/529, loss: 0.0026452532038092613
2023-01-22 18:12:48.602887: step: 496/529, loss: 0.003359744790941477
2023-01-22 18:12:49.700427: step: 500/529, loss: 0.012588279321789742
2023-01-22 18:12:50.773359: step: 504/529, loss: 0.0004936831537634134
2023-01-22 18:12:51.830891: step: 508/529, loss: 0.000453014305094257
2023-01-22 18:12:52.893256: step: 512/529, loss: 0.0014283152995631099
2023-01-22 18:12:53.963269: step: 516/529, loss: 6.273492908803746e-05
2023-01-22 18:12:55.020228: step: 520/529, loss: 0.0037453763652592897
2023-01-22 18:12:56.097697: step: 524/529, loss: 0.00708908773958683
2023-01-22 18:12:57.168694: step: 528/529, loss: 0.0003847303451038897
2023-01-22 18:12:58.229283: step: 532/529, loss: 0.0007803772459737957
2023-01-22 18:12:59.306435: step: 536/529, loss: 0.001063131378032267
2023-01-22 18:13:00.370052: step: 540/529, loss: 0.00014132454816717654
2023-01-22 18:13:01.473218: step: 544/529, loss: 0.0003259962541051209
2023-01-22 18:13:02.541602: step: 548/529, loss: 0.0010191089240834117
2023-01-22 18:13:03.616653: step: 552/529, loss: 0.0023419675417244434
2023-01-22 18:13:04.673748: step: 556/529, loss: 0.000528524920810014
2023-01-22 18:13:05.753583: step: 560/529, loss: 0.0004716124967671931
2023-01-22 18:13:06.805756: step: 564/529, loss: 0.0024010816123336554
2023-01-22 18:13:07.887927: step: 568/529, loss: 0.0007846885710023344
2023-01-22 18:13:08.969848: step: 572/529, loss: 0.002488890662789345
2023-01-22 18:13:10.052383: step: 576/529, loss: 0.00165373960044235
2023-01-22 18:13:11.126717: step: 580/529, loss: 0.008673086762428284
2023-01-22 18:13:12.213550: step: 584/529, loss: 0.0015404396690428257
2023-01-22 18:13:13.266107: step: 588/529, loss: 0.002522109542042017
2023-01-22 18:13:14.334674: step: 592/529, loss: 0.002636249642819166
2023-01-22 18:13:15.423174: step: 596/529, loss: 0.001112492405809462
2023-01-22 18:13:16.499609: step: 600/529, loss: 0.004458381794393063
2023-01-22 18:13:17.571564: step: 604/529, loss: 0.0014742023777216673
2023-01-22 18:13:18.617343: step: 608/529, loss: 0.0008885821443982422
2023-01-22 18:13:19.716250: step: 612/529, loss: 1.9904477085219696e-05
2023-01-22 18:13:20.778290: step: 616/529, loss: 0.0017006245907396078
2023-01-22 18:13:21.849930: step: 620/529, loss: 0.0014850731240585446
2023-01-22 18:13:22.905919: step: 624/529, loss: 0.00023758201859891415
2023-01-22 18:13:23.977867: step: 628/529, loss: 0.0010377351427450776
2023-01-22 18:13:25.042205: step: 632/529, loss: 0.0019140334334224463
2023-01-22 18:13:26.100898: step: 636/529, loss: 0.0023769692052155733
2023-01-22 18:13:27.167949: step: 640/529, loss: 0.000245902017923072
2023-01-22 18:13:28.231799: step: 644/529, loss: 0.002616342157125473
2023-01-22 18:13:29.301060: step: 648/529, loss: 0.0038746490608900785
2023-01-22 18:13:30.388989: step: 652/529, loss: 0.002077002776786685
2023-01-22 18:13:31.454645: step: 656/529, loss: 0.005881055723875761
2023-01-22 18:13:32.530421: step: 660/529, loss: 7.45057526785331e-09
2023-01-22 18:13:33.591544: step: 664/529, loss: 0.000414300593547523
2023-01-22 18:13:34.684395: step: 668/529, loss: 0.004773742984980345
2023-01-22 18:13:35.762952: step: 672/529, loss: 0.0036938427947461605
2023-01-22 18:13:36.837250: step: 676/529, loss: 0.0003341565898153931
2023-01-22 18:13:37.931642: step: 680/529, loss: 0.0009104507626034319
2023-01-22 18:13:38.991524: step: 684/529, loss: 5.523121217265725e-06
2023-01-22 18:13:40.050272: step: 688/529, loss: 1.7188789570354857e-05
2023-01-22 18:13:41.101099: step: 692/529, loss: 0.0007495395257137716
2023-01-22 18:13:42.162644: step: 696/529, loss: 0.0033264432568103075
2023-01-22 18:13:43.223892: step: 700/529, loss: 0.0068891653791069984
2023-01-22 18:13:44.312170: step: 704/529, loss: 0.009174483828246593
2023-01-22 18:13:45.393644: step: 708/529, loss: 0.0005347991827875376
2023-01-22 18:13:46.454843: step: 712/529, loss: 0.006793070584535599
2023-01-22 18:13:47.513440: step: 716/529, loss: 0.011829989962279797
2023-01-22 18:13:48.599495: step: 720/529, loss: 0.004367281682789326
2023-01-22 18:13:49.670847: step: 724/529, loss: 0.007348595652729273
2023-01-22 18:13:50.746953: step: 728/529, loss: 0.00039315730100497603
2023-01-22 18:13:51.803638: step: 732/529, loss: 0.009478211402893066
2023-01-22 18:13:52.881780: step: 736/529, loss: 0.0015816637314856052
2023-01-22 18:13:53.928089: step: 740/529, loss: 0.004561400506645441
2023-01-22 18:13:54.991834: step: 744/529, loss: 0.000998090603388846
2023-01-22 18:13:56.064302: step: 748/529, loss: 0.002690277760848403
2023-01-22 18:13:57.133952: step: 752/529, loss: 0.01983640529215336
2023-01-22 18:13:58.213533: step: 756/529, loss: 0.02866826020181179
2023-01-22 18:13:59.273148: step: 760/529, loss: 0.002755439840257168
2023-01-22 18:14:00.348406: step: 764/529, loss: 0.0013352558016777039
2023-01-22 18:14:01.422309: step: 768/529, loss: 0.0014271977124735713
2023-01-22 18:14:02.505715: step: 772/529, loss: 0.0022671674378216267
2023-01-22 18:14:03.594834: step: 776/529, loss: 0.0018875261303037405
2023-01-22 18:14:04.661088: step: 780/529, loss: 3.158912704748218e-06
2023-01-22 18:14:05.736830: step: 784/529, loss: 0.003514400916174054
2023-01-22 18:14:06.813348: step: 788/529, loss: 0.005634487606585026
2023-01-22 18:14:07.900850: step: 792/529, loss: 0.001252013840712607
2023-01-22 18:14:08.979325: step: 796/529, loss: 0.0008378030615858734
2023-01-22 18:14:10.041511: step: 800/529, loss: 0.00011768119293265045
2023-01-22 18:14:11.110922: step: 804/529, loss: 0.0313212051987648
2023-01-22 18:14:12.167833: step: 808/529, loss: 0.003424952272325754
2023-01-22 18:14:13.248462: step: 812/529, loss: 0.0003686647687572986
2023-01-22 18:14:14.311286: step: 816/529, loss: 0.017792463302612305
2023-01-22 18:14:15.358580: step: 820/529, loss: 0.007854940369725227
2023-01-22 18:14:16.420474: step: 824/529, loss: 0.00029206243925727904
2023-01-22 18:14:17.485977: step: 828/529, loss: 0.0015315775526687503
2023-01-22 18:14:18.580848: step: 832/529, loss: 0.00845752377063036
2023-01-22 18:14:19.657434: step: 836/529, loss: 0.00011560235725482926
2023-01-22 18:14:20.719512: step: 840/529, loss: 0.0011882432736456394
2023-01-22 18:14:21.797001: step: 844/529, loss: 0.003570557339116931
2023-01-22 18:14:22.875467: step: 848/529, loss: 7.160241511883214e-05
2023-01-22 18:14:23.943967: step: 852/529, loss: 0.0009545166394673288
2023-01-22 18:14:25.031046: step: 856/529, loss: 0.0002575825492385775
2023-01-22 18:14:26.092601: step: 860/529, loss: 0.0012334130005910993
2023-01-22 18:14:27.175259: step: 864/529, loss: 0.01737028732895851
2023-01-22 18:14:28.251163: step: 868/529, loss: 0.0054113599471747875
2023-01-22 18:14:29.308043: step: 872/529, loss: 7.68220161262434e-06
2023-01-22 18:14:30.376152: step: 876/529, loss: 0.001449385192245245
2023-01-22 18:14:31.439548: step: 880/529, loss: 0.0025277924723923206
2023-01-22 18:14:32.511210: step: 884/529, loss: 0.0007194819045253098
2023-01-22 18:14:33.582420: step: 888/529, loss: 0.006475755479186773
2023-01-22 18:14:34.654936: step: 892/529, loss: 0.0013373121619224548
2023-01-22 18:14:35.719993: step: 896/529, loss: 0.01022915355861187
2023-01-22 18:14:36.794289: step: 900/529, loss: 0.005136055406183004
2023-01-22 18:14:37.876846: step: 904/529, loss: 0.0022083797957748175
2023-01-22 18:14:38.937364: step: 908/529, loss: 0.0032370751723647118
2023-01-22 18:14:40.002328: step: 912/529, loss: 0.001199365477077663
2023-01-22 18:14:41.061881: step: 916/529, loss: 0.0008733494905754924
2023-01-22 18:14:42.145122: step: 920/529, loss: 0.0037629641592502594
2023-01-22 18:14:43.222223: step: 924/529, loss: 0.0030023385770618916
2023-01-22 18:14:44.288244: step: 928/529, loss: 7.729006028966978e-05
2023-01-22 18:14:45.376552: step: 932/529, loss: 0.006165419705212116
2023-01-22 18:14:46.455904: step: 936/529, loss: 0.002081350889056921
2023-01-22 18:14:47.522176: step: 940/529, loss: 0.0010776565177366138
2023-01-22 18:14:48.583645: step: 944/529, loss: 0.0012144746724516153
2023-01-22 18:14:49.638696: step: 948/529, loss: 0.0013656432274729013
2023-01-22 18:14:50.709991: step: 952/529, loss: 0.005908365361392498
2023-01-22 18:14:51.797697: step: 956/529, loss: 0.002732435939833522
2023-01-22 18:14:52.885465: step: 960/529, loss: 0.00545385992154479
2023-01-22 18:14:53.939550: step: 964/529, loss: 0.0019418157171458006
2023-01-22 18:14:54.996390: step: 968/529, loss: 0.001496769953519106
2023-01-22 18:14:56.073670: step: 972/529, loss: 0.0031646527349948883
2023-01-22 18:14:57.158231: step: 976/529, loss: 0.015380684286355972
2023-01-22 18:14:58.215817: step: 980/529, loss: 0.006559289991855621
2023-01-22 18:14:59.281255: step: 984/529, loss: 0.0011803609086200595
2023-01-22 18:15:00.355223: step: 988/529, loss: 0.0028026883956044912
2023-01-22 18:15:01.422611: step: 992/529, loss: 0.0018853460205718875
2023-01-22 18:15:02.489174: step: 996/529, loss: 0.00375824305228889
2023-01-22 18:15:03.573579: step: 1000/529, loss: 0.0008085378794930875
2023-01-22 18:15:04.648784: step: 1004/529, loss: 0.0020609023049473763
2023-01-22 18:15:05.715231: step: 1008/529, loss: 0.007779187988489866
2023-01-22 18:15:06.783984: step: 1012/529, loss: 0.002778386464342475
2023-01-22 18:15:07.867016: step: 1016/529, loss: 0.0001404272043146193
2023-01-22 18:15:08.942187: step: 1020/529, loss: 0.0052325366996228695
2023-01-22 18:15:10.036511: step: 1024/529, loss: 0.002829657169058919
2023-01-22 18:15:11.102707: step: 1028/529, loss: 9.075047273654491e-05
2023-01-22 18:15:12.188606: step: 1032/529, loss: 5.7433717302046716e-05
2023-01-22 18:15:13.266602: step: 1036/529, loss: 0.0005083115538582206
2023-01-22 18:15:14.336410: step: 1040/529, loss: 0.00039361463859677315
2023-01-22 18:15:15.409653: step: 1044/529, loss: 0.0006710219895467162
2023-01-22 18:15:16.467299: step: 1048/529, loss: 6.667277193628252e-05
2023-01-22 18:15:17.542304: step: 1052/529, loss: 7.658819231437519e-05
2023-01-22 18:15:18.609553: step: 1056/529, loss: 0.0006490605883300304
2023-01-22 18:15:19.712186: step: 1060/529, loss: 0.010827995836734772
2023-01-22 18:15:20.788724: step: 1064/529, loss: 0.00015219306806102395
2023-01-22 18:15:21.864128: step: 1068/529, loss: 0.0008494030334986746
2023-01-22 18:15:22.930315: step: 1072/529, loss: 0.0005586376646533608
2023-01-22 18:15:24.000491: step: 1076/529, loss: 0.0015351675683632493
2023-01-22 18:15:25.075875: step: 1080/529, loss: 0.0017223567701876163
2023-01-22 18:15:26.140235: step: 1084/529, loss: 4.26711849286221e-05
2023-01-22 18:15:27.206839: step: 1088/529, loss: 0.003707293886691332
2023-01-22 18:15:28.282705: step: 1092/529, loss: 0.002257500309497118
2023-01-22 18:15:29.369536: step: 1096/529, loss: 0.0008587195188738406
2023-01-22 18:15:30.465811: step: 1100/529, loss: 0.00748869962990284
2023-01-22 18:15:31.552318: step: 1104/529, loss: 0.0008730971603654325
2023-01-22 18:15:32.656215: step: 1108/529, loss: 0.0018483257154002786
2023-01-22 18:15:33.728536: step: 1112/529, loss: 0.0019268756732344627
2023-01-22 18:15:34.808845: step: 1116/529, loss: 0.0015258695930242538
2023-01-22 18:15:35.875253: step: 1120/529, loss: 0.0005209136288613081
2023-01-22 18:15:36.935377: step: 1124/529, loss: 0.0012028071796521544
2023-01-22 18:15:38.017034: step: 1128/529, loss: 0.0038608855102211237
2023-01-22 18:15:39.103725: step: 1132/529, loss: 0.0006154804141260684
2023-01-22 18:15:40.177109: step: 1136/529, loss: 0.003657440422102809
2023-01-22 18:15:41.260886: step: 1140/529, loss: 0.043205469846725464
2023-01-22 18:15:42.322639: step: 1144/529, loss: 6.276134809013456e-05
2023-01-22 18:15:43.423664: step: 1148/529, loss: 0.002498716115951538
2023-01-22 18:15:44.520242: step: 1152/529, loss: 0.004072152078151703
2023-01-22 18:15:45.612340: step: 1156/529, loss: 0.0003936043649446219
2023-01-22 18:15:46.678114: step: 1160/529, loss: 0.007063613273203373
2023-01-22 18:15:47.755754: step: 1164/529, loss: 0.0007550419541075826
2023-01-22 18:15:48.843739: step: 1168/529, loss: 0.004259921610355377
2023-01-22 18:15:49.933449: step: 1172/529, loss: 0.00039926229510456324
2023-01-22 18:15:50.996154: step: 1176/529, loss: 0.0011149825295433402
2023-01-22 18:15:52.075994: step: 1180/529, loss: 0.002595897763967514
2023-01-22 18:15:53.143632: step: 1184/529, loss: 0.008593294769525528
2023-01-22 18:15:54.203543: step: 1188/529, loss: 0.000594412733335048
2023-01-22 18:15:55.260321: step: 1192/529, loss: 1.808378510759212e-05
2023-01-22 18:15:56.328172: step: 1196/529, loss: 0.0048291427083313465
2023-01-22 18:15:57.404443: step: 1200/529, loss: 0.0020109168253839016
2023-01-22 18:15:58.487773: step: 1204/529, loss: 0.0036780221853405237
2023-01-22 18:15:59.566134: step: 1208/529, loss: 0.0044897496700286865
2023-01-22 18:16:00.645996: step: 1212/529, loss: 0.0007382581825368106
2023-01-22 18:16:01.735189: step: 1216/529, loss: 0.010926084592938423
2023-01-22 18:16:02.794610: step: 1220/529, loss: 0.0039057754911482334
2023-01-22 18:16:03.866269: step: 1224/529, loss: 0.006962126586586237
2023-01-22 18:16:04.940960: step: 1228/529, loss: 0.0034068129025399685
2023-01-22 18:16:06.015699: step: 1232/529, loss: 0.00112510088365525
2023-01-22 18:16:07.107879: step: 1236/529, loss: 0.0007346238126046956
2023-01-22 18:16:08.210450: step: 1240/529, loss: 0.0019496228778734803
2023-01-22 18:16:09.291905: step: 1244/529, loss: 0.0038012738805264235
2023-01-22 18:16:10.363490: step: 1248/529, loss: 0.004894669633358717
2023-01-22 18:16:11.449425: step: 1252/529, loss: 0.0005669477395713329
2023-01-22 18:16:12.526234: step: 1256/529, loss: 0.0028599631041288376
2023-01-22 18:16:13.617162: step: 1260/529, loss: 0.00023831026919651777
2023-01-22 18:16:14.705021: step: 1264/529, loss: 0.0017782659269869328
2023-01-22 18:16:15.771709: step: 1268/529, loss: 0.003180332714691758
2023-01-22 18:16:16.846113: step: 1272/529, loss: 0.0005634871777147055
2023-01-22 18:16:17.927970: step: 1276/529, loss: 0.0005659122834913433
2023-01-22 18:16:19.003047: step: 1280/529, loss: 0.0012836528476327658
2023-01-22 18:16:20.063534: step: 1284/529, loss: 0.004379668273031712
2023-01-22 18:16:21.137323: step: 1288/529, loss: 0.009521793574094772
2023-01-22 18:16:22.224073: step: 1292/529, loss: 0.002475961111485958
2023-01-22 18:16:23.293295: step: 1296/529, loss: 0.0009779938263818622
2023-01-22 18:16:24.371196: step: 1300/529, loss: 0.00312836398370564
2023-01-22 18:16:25.447361: step: 1304/529, loss: 0.002582593122497201
2023-01-22 18:16:26.527390: step: 1308/529, loss: 0.00019374507246538997
2023-01-22 18:16:27.605909: step: 1312/529, loss: 0.0006239487556740642
2023-01-22 18:16:28.671200: step: 1316/529, loss: 0.0006423802697099745
2023-01-22 18:16:29.743110: step: 1320/529, loss: 0.001917838817462325
2023-01-22 18:16:30.812633: step: 1324/529, loss: 0.0001850782718975097
2023-01-22 18:16:31.886086: step: 1328/529, loss: 0.007231010589748621
2023-01-22 18:16:32.966751: step: 1332/529, loss: 0.0029431157745420933
2023-01-22 18:16:34.029555: step: 1336/529, loss: 0.007133177947252989
2023-01-22 18:16:35.094412: step: 1340/529, loss: 0.0046417731791734695
2023-01-22 18:16:36.166098: step: 1344/529, loss: 0.0001938982750289142
2023-01-22 18:16:37.244634: step: 1348/529, loss: 0.0010179791133850813
2023-01-22 18:16:38.320842: step: 1352/529, loss: 0.00048548419727012515
2023-01-22 18:16:39.402497: step: 1356/529, loss: 0.0033264486119151115
2023-01-22 18:16:40.488776: step: 1360/529, loss: 0.0009518049191683531
2023-01-22 18:16:41.555058: step: 1364/529, loss: 0.0022814397234469652
2023-01-22 18:16:42.617982: step: 1368/529, loss: 0.0005287769017741084
2023-01-22 18:16:43.691496: step: 1372/529, loss: 0.005225060973316431
2023-01-22 18:16:44.762052: step: 1376/529, loss: 0.00015767682634759694
2023-01-22 18:16:45.832412: step: 1380/529, loss: 0.0011445179115980864
2023-01-22 18:16:46.932214: step: 1384/529, loss: 0.0018238815246149898
2023-01-22 18:16:48.007059: step: 1388/529, loss: 0.007704332936555147
2023-01-22 18:16:49.082750: step: 1392/529, loss: 0.0011966499732807279
2023-01-22 18:16:50.148929: step: 1396/529, loss: 0.002158642979338765
2023-01-22 18:16:51.223347: step: 1400/529, loss: 0.006224733777344227
2023-01-22 18:16:52.296925: step: 1404/529, loss: 0.0010657889069989324
2023-01-22 18:16:53.390566: step: 1408/529, loss: 5.5490858358098194e-05
2023-01-22 18:16:54.458677: step: 1412/529, loss: 0.0014365941751748323
2023-01-22 18:16:55.530983: step: 1416/529, loss: 0.0013984849210828543
2023-01-22 18:16:56.603975: step: 1420/529, loss: 0.0036160035524517298
2023-01-22 18:16:57.685926: step: 1424/529, loss: 0.0035706888884305954
2023-01-22 18:16:58.765340: step: 1428/529, loss: 0.0009824762819334865
2023-01-22 18:16:59.829843: step: 1432/529, loss: 0.0005747652030549943
2023-01-22 18:17:00.908645: step: 1436/529, loss: 0.001848118263296783
2023-01-22 18:17:01.972345: step: 1440/529, loss: 0.0028743401635438204
2023-01-22 18:17:03.028305: step: 1444/529, loss: 0.00449009845033288
2023-01-22 18:17:04.113998: step: 1448/529, loss: 0.00325595261529088
2023-01-22 18:17:05.182667: step: 1452/529, loss: 0.0009442290756851435
2023-01-22 18:17:06.271311: step: 1456/529, loss: 0.0012102173641324043
2023-01-22 18:17:07.346647: step: 1460/529, loss: 0.0039881025440990925
2023-01-22 18:17:08.427952: step: 1464/529, loss: 0.00017110141925513744
2023-01-22 18:17:09.508893: step: 1468/529, loss: 0.0014555882662534714
2023-01-22 18:17:10.587297: step: 1472/529, loss: 0.0022690044716000557
2023-01-22 18:17:11.657369: step: 1476/529, loss: 0.00011602540325839072
2023-01-22 18:17:12.750252: step: 1480/529, loss: 7.570101297460496e-05
2023-01-22 18:17:13.853403: step: 1484/529, loss: 0.0007460275664925575
2023-01-22 18:17:14.935780: step: 1488/529, loss: 0.004927394911646843
2023-01-22 18:17:16.024083: step: 1492/529, loss: 0.00025014503626152873
2023-01-22 18:17:17.103638: step: 1496/529, loss: 0.002118960488587618
2023-01-22 18:17:18.180730: step: 1500/529, loss: 0.018409421667456627
2023-01-22 18:17:19.265886: step: 1504/529, loss: 0.0010395676363259554
2023-01-22 18:17:20.351146: step: 1508/529, loss: 0.0010848288657143712
2023-01-22 18:17:21.427354: step: 1512/529, loss: 7.273046776390402e-06
2023-01-22 18:17:22.502252: step: 1516/529, loss: 0.006037840619683266
2023-01-22 18:17:23.575606: step: 1520/529, loss: 8.223614713642746e-07
2023-01-22 18:17:24.649409: step: 1524/529, loss: 0.0028185120318084955
2023-01-22 18:17:25.719557: step: 1528/529, loss: 4.02489495172631e-05
2023-01-22 18:17:26.806679: step: 1532/529, loss: 0.0015066106570884585
2023-01-22 18:17:27.869626: step: 1536/529, loss: 0.0015155121218413115
2023-01-22 18:17:28.941092: step: 1540/529, loss: 0.0037343150470405817
2023-01-22 18:17:30.034586: step: 1544/529, loss: 3.739988869710942e-07
2023-01-22 18:17:31.114616: step: 1548/529, loss: 0.0009553920244798064
2023-01-22 18:17:32.193323: step: 1552/529, loss: 0.002387288026511669
2023-01-22 18:17:33.273609: step: 1556/529, loss: 0.0016599317314103246
2023-01-22 18:17:34.354135: step: 1560/529, loss: 0.0001930451689986512
2023-01-22 18:17:35.420253: step: 1564/529, loss: 0.0010668542236089706
2023-01-22 18:17:36.508060: step: 1568/529, loss: 0.0007465079543180764
2023-01-22 18:17:37.589701: step: 1572/529, loss: 0.0002625504566822201
2023-01-22 18:17:38.667598: step: 1576/529, loss: 0.0015640161000192165
2023-01-22 18:17:39.747161: step: 1580/529, loss: 0.0017872406169772148
2023-01-22 18:17:40.827482: step: 1584/529, loss: 9.835542005021125e-05
2023-01-22 18:17:41.895281: step: 1588/529, loss: 0.0007155194762162864
2023-01-22 18:17:42.970621: step: 1592/529, loss: 5.46418123121839e-05
2023-01-22 18:17:44.048061: step: 1596/529, loss: 0.00044310936937108636
2023-01-22 18:17:45.120288: step: 1600/529, loss: 0.0043274713680148125
2023-01-22 18:17:46.210621: step: 1604/529, loss: 0.002196304500102997
2023-01-22 18:17:47.297737: step: 1608/529, loss: 0.0061032394878566265
2023-01-22 18:17:48.389463: step: 1612/529, loss: 0.0019603732507675886
2023-01-22 18:17:49.473779: step: 1616/529, loss: 0.00047863248619250953
2023-01-22 18:17:50.556556: step: 1620/529, loss: 0.0017844531685113907
2023-01-22 18:17:51.627582: step: 1624/529, loss: 0.001975511433556676
2023-01-22 18:17:52.706497: step: 1628/529, loss: 0.005960141774266958
2023-01-22 18:17:53.787917: step: 1632/529, loss: 0.0029372964054346085
2023-01-22 18:17:54.878033: step: 1636/529, loss: 0.0025688691530376673
2023-01-22 18:17:55.965350: step: 1640/529, loss: 0.001015074783936143
2023-01-22 18:17:57.057381: step: 1644/529, loss: 2.1234066593933676e-07
2023-01-22 18:17:58.129486: step: 1648/529, loss: 0.0004801612230949104
2023-01-22 18:17:59.214006: step: 1652/529, loss: 0.003322687465697527
2023-01-22 18:18:00.276698: step: 1656/529, loss: 0.0011118465336039662
2023-01-22 18:18:01.352447: step: 1660/529, loss: 0.0073075732216238976
2023-01-22 18:18:02.428182: step: 1664/529, loss: 0.0004294175305403769
2023-01-22 18:18:03.502459: step: 1668/529, loss: 0.00015707006969023496
2023-01-22 18:18:04.587088: step: 1672/529, loss: 0.0001412837445968762
2023-01-22 18:18:05.663295: step: 1676/529, loss: 0.0003383977455087006
2023-01-22 18:18:06.752471: step: 1680/529, loss: 0.019864745438098907
2023-01-22 18:18:07.819022: step: 1684/529, loss: 0.00041160514228977263
2023-01-22 18:18:08.900417: step: 1688/529, loss: 0.002199660986661911
2023-01-22 18:18:09.980523: step: 1692/529, loss: 0.0013559951912611723
2023-01-22 18:18:11.067043: step: 1696/529, loss: 0.0010018300963565707
2023-01-22 18:18:12.138586: step: 1700/529, loss: 0.0021604576613754034
2023-01-22 18:18:13.216744: step: 1704/529, loss: 0.000719524803571403
2023-01-22 18:18:14.288884: step: 1708/529, loss: 0.003140198765322566
2023-01-22 18:18:15.350445: step: 1712/529, loss: 0.0006435253308154643
2023-01-22 18:18:16.416853: step: 1716/529, loss: 0.00011017225187970325
2023-01-22 18:18:17.513705: step: 1720/529, loss: 0.004275134298950434
2023-01-22 18:18:18.596609: step: 1724/529, loss: 0.0005691625992767513
2023-01-22 18:18:19.671972: step: 1728/529, loss: 0.0008874873165041208
2023-01-22 18:18:20.745168: step: 1732/529, loss: 0.005249090027064085
2023-01-22 18:18:21.815740: step: 1736/529, loss: 0.0027024808805435896
2023-01-22 18:18:22.904974: step: 1740/529, loss: 0.0022624663542956114
2023-01-22 18:18:24.004610: step: 1744/529, loss: 0.0131065733730793
2023-01-22 18:18:25.081009: step: 1748/529, loss: 5.179776781005785e-05
2023-01-22 18:18:26.161940: step: 1752/529, loss: 0.0001413149293512106
2023-01-22 18:18:27.237586: step: 1756/529, loss: 0.004212803672999144
2023-01-22 18:18:28.315834: step: 1760/529, loss: 0.0050727264024317265
2023-01-22 18:18:29.400302: step: 1764/529, loss: 0.007901964709162712
2023-01-22 18:18:30.481903: step: 1768/529, loss: 0.0018743944820016623
2023-01-22 18:18:31.552811: step: 1772/529, loss: 0.0020944548305124044
2023-01-22 18:18:32.625889: step: 1776/529, loss: 0.00019091676222160459
2023-01-22 18:18:33.693460: step: 1780/529, loss: 0.0018894568784162402
2023-01-22 18:18:34.761661: step: 1784/529, loss: 6.166517414385453e-05
2023-01-22 18:18:35.841263: step: 1788/529, loss: 0.001851622830145061
2023-01-22 18:18:36.917545: step: 1792/529, loss: 0.01644969917833805
2023-01-22 18:18:37.990563: step: 1796/529, loss: 0.002602136693894863
2023-01-22 18:18:39.077105: step: 1800/529, loss: 0.006712350994348526
2023-01-22 18:18:40.149905: step: 1804/529, loss: 5.161118679097854e-06
2023-01-22 18:18:41.200978: step: 1808/529, loss: 3.353336069267243e-06
2023-01-22 18:18:42.264488: step: 1812/529, loss: 0.0030756357591599226
2023-01-22 18:18:43.360241: step: 1816/529, loss: 0.002079861471429467
2023-01-22 18:18:44.455801: step: 1820/529, loss: 0.003998699132353067
2023-01-22 18:18:45.537629: step: 1824/529, loss: 0.007737547159194946
2023-01-22 18:18:46.616635: step: 1828/529, loss: 0.0038897807244211435
2023-01-22 18:18:47.692851: step: 1832/529, loss: 0.004534234758466482
2023-01-22 18:18:48.764853: step: 1836/529, loss: 0.0004959909711033106
2023-01-22 18:18:49.838374: step: 1840/529, loss: 0.0005378610221669078
2023-01-22 18:18:50.907034: step: 1844/529, loss: 0.002199208363890648
2023-01-22 18:18:51.983932: step: 1848/529, loss: 0.0008325819508172572
2023-01-22 18:18:53.052198: step: 1852/529, loss: 0.007355336099863052
2023-01-22 18:18:54.125419: step: 1856/529, loss: 0.0004597824008669704
2023-01-22 18:18:55.182994: step: 1860/529, loss: 0.0057330504059791565
2023-01-22 18:18:56.253453: step: 1864/529, loss: 0.0001159469029516913
2023-01-22 18:18:57.336769: step: 1868/529, loss: 1.6581265299464576e-05
2023-01-22 18:18:58.404003: step: 1872/529, loss: 0.0005634183180518448
2023-01-22 18:18:59.488081: step: 1876/529, loss: 0.011288592591881752
2023-01-22 18:19:00.556211: step: 1880/529, loss: 0.00043343662400729954
2023-01-22 18:19:01.626388: step: 1884/529, loss: 0.0006984006613492966
2023-01-22 18:19:02.706053: step: 1888/529, loss: 0.0046867490746080875
2023-01-22 18:19:03.773832: step: 1892/529, loss: 0.004059478174895048
2023-01-22 18:19:04.846688: step: 1896/529, loss: 0.0012924011098220944
2023-01-22 18:19:05.943609: step: 1900/529, loss: 0.002071784343570471
2023-01-22 18:19:07.058852: step: 1904/529, loss: 0.011372504755854607
2023-01-22 18:19:08.143253: step: 1908/529, loss: 0.003362776944413781
2023-01-22 18:19:09.212441: step: 1912/529, loss: 0.0023445303086191416
2023-01-22 18:19:10.275730: step: 1916/529, loss: 0.00017955811927095056
2023-01-22 18:19:11.348823: step: 1920/529, loss: 0.001524993684142828
2023-01-22 18:19:12.419133: step: 1924/529, loss: 0.0017600884893909097
2023-01-22 18:19:13.508810: step: 1928/529, loss: 0.0038016540929675102
2023-01-22 18:19:14.590358: step: 1932/529, loss: 2.8747370379278436e-05
2023-01-22 18:19:15.674927: step: 1936/529, loss: 0.0058314017951488495
2023-01-22 18:19:16.751520: step: 1940/529, loss: 0.005763298366218805
2023-01-22 18:19:17.818514: step: 1944/529, loss: 0.0028499593026936054
2023-01-22 18:19:18.891047: step: 1948/529, loss: 0.0020090679172426462
2023-01-22 18:19:19.970691: step: 1952/529, loss: 0.003981693182140589
2023-01-22 18:19:21.058456: step: 1956/529, loss: 0.002778051421046257
2023-01-22 18:19:22.124813: step: 1960/529, loss: 0.0007779460866004229
2023-01-22 18:19:23.220018: step: 1964/529, loss: 0.0042539192363619804
2023-01-22 18:19:24.286139: step: 1968/529, loss: 0.02666550502181053
2023-01-22 18:19:25.363922: step: 1972/529, loss: 4.753031680593267e-05
2023-01-22 18:19:26.427819: step: 1976/529, loss: 0.0035888017155230045
2023-01-22 18:19:27.520037: step: 1980/529, loss: 0.004086082801222801
2023-01-22 18:19:28.608603: step: 1984/529, loss: 0.0005060922121629119
2023-01-22 18:19:29.691044: step: 1988/529, loss: 0.0014637112617492676
2023-01-22 18:19:30.789933: step: 1992/529, loss: 0.004064515233039856
2023-01-22 18:19:31.889504: step: 1996/529, loss: 0.002950838999822736
2023-01-22 18:19:32.975159: step: 2000/529, loss: 0.0011641213204711676
2023-01-22 18:19:34.040579: step: 2004/529, loss: 0.0021604953799396753
2023-01-22 18:19:35.132403: step: 2008/529, loss: 0.0012989185051992536
2023-01-22 18:19:36.212834: step: 2012/529, loss: 0.0018135125283151865
2023-01-22 18:19:37.286539: step: 2016/529, loss: 1.6374669939978048e-05
2023-01-22 18:19:38.368822: step: 2020/529, loss: 0.005068726371973753
2023-01-22 18:19:39.456882: step: 2024/529, loss: 0.0004423893115017563
2023-01-22 18:19:40.538853: step: 2028/529, loss: 0.0006851354846730828
2023-01-22 18:19:41.604962: step: 2032/529, loss: 0.027675429359078407
2023-01-22 18:19:42.682043: step: 2036/529, loss: 0.0033681581262499094
2023-01-22 18:19:43.763429: step: 2040/529, loss: 0.01567409187555313
2023-01-22 18:19:44.828927: step: 2044/529, loss: 0.0022905180230736732
2023-01-22 18:19:45.920801: step: 2048/529, loss: 0.005376490764319897
2023-01-22 18:19:46.998599: step: 2052/529, loss: 0.0035738579463213682
2023-01-22 18:19:48.078896: step: 2056/529, loss: 0.0001299295254284516
2023-01-22 18:19:49.155129: step: 2060/529, loss: 5.431179488368798e-07
2023-01-22 18:19:50.223838: step: 2064/529, loss: 1.3345228353500715e-06
2023-01-22 18:19:51.307375: step: 2068/529, loss: 0.00254993699491024
2023-01-22 18:19:52.377293: step: 2072/529, loss: 0.0019837834406644106
2023-01-22 18:19:53.450337: step: 2076/529, loss: 0.011133707128465176
2023-01-22 18:19:54.523519: step: 2080/529, loss: 0.001869537984021008
2023-01-22 18:19:55.597154: step: 2084/529, loss: 0.0023477799259126186
2023-01-22 18:19:56.669376: step: 2088/529, loss: 0.001385086914524436
2023-01-22 18:19:57.750851: step: 2092/529, loss: 0.0007534649921581149
2023-01-22 18:19:58.824476: step: 2096/529, loss: 0.005786359775811434
2023-01-22 18:19:59.908185: step: 2100/529, loss: 0.008153497241437435
2023-01-22 18:20:00.985627: step: 2104/529, loss: 0.003495414275676012
2023-01-22 18:20:02.063940: step: 2108/529, loss: 3.7915068418215014e-08
2023-01-22 18:20:03.133933: step: 2112/529, loss: 0.0005296847084537148
2023-01-22 18:20:04.197781: step: 2116/529, loss: 0.0
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3212994836488813, 'r': 0.35422201138519926, 'f1': 0.33695848375451265}, 'combined': 0.24828519855595668, 'stategy': 1, 'epoch': 17}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3106693752704907, 'r': 0.3080994999235841, 'f1': 0.3093791009846419}, 'combined': 0.2019780659277973, 'stategy': 1, 'epoch': 17}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3188687996031746, 'r': 0.36303848152164087, 'f1': 0.33952312291376174}, 'combined': 0.2501749326732981, 'stategy': 1, 'epoch': 17}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3332465619672364, 'r': 0.3121123590483584, 'f1': 0.3223334092497522}, 'combined': 0.21043528272263615, 'stategy': 1, 'epoch': 17}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3091856060606061, 'r': 0.3484938330170778, 'f1': 0.3276650312221231}, 'combined': 0.24143739142682752, 'stategy': 1, 'epoch': 17}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32375342527226486, 'r': 0.3219696598437675, 'f1': 0.3228590787936122}, 'combined': 0.21077846594816133, 'stategy': 1, 'epoch': 17}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.2976190476190476, 'r': 0.41666666666666663, 'f1': 0.34722222222222227}, 'combined': 0.2314814814814815, 'stategy': 1, 'epoch': 17}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 17}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 17}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3238172380156076, 'r': 0.36744346932321315, 'f1': 0.34425370370370373}, 'combined': 0.2536606237816764, 'stategy': 1, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3319312097086922, 'r': 0.3093550061071819, 'f1': 0.32024571517089817}, 'combined': 0.20907233218410967, 'stategy': 1, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31698690878378377, 'r': 0.3560839658444023, 'f1': 0.3353999106344951}, 'combined': 0.24713677625699637, 'stategy': 1, 'epoch': 3}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32049214311854907, 'r': 0.3199035441412882, 'f1': 0.32019757313406505}, 'combined': 0.2090409026678352, 'stategy': 1, 'epoch': 3}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 3}
******************************
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 18:22:40.522344: step: 4/529, loss: 0.0005170427029952407
2023-01-22 18:22:41.587566: step: 8/529, loss: 0.003996998071670532
2023-01-22 18:22:42.636348: step: 12/529, loss: 2.510870217520278e-06
2023-01-22 18:22:43.688933: step: 16/529, loss: 1.3675046830030624e-05
2023-01-22 18:22:44.776981: step: 20/529, loss: 0.008300567977130413
2023-01-22 18:22:45.841869: step: 24/529, loss: 0.005986595526337624
2023-01-22 18:22:46.910386: step: 28/529, loss: 0.000947567168623209
2023-01-22 18:22:47.974089: step: 32/529, loss: 3.4728953323792666e-05
2023-01-22 18:22:49.052622: step: 36/529, loss: 0.0001365190400974825
2023-01-22 18:22:50.103416: step: 40/529, loss: 0.006958008278161287
2023-01-22 18:22:51.174009: step: 44/529, loss: 0.006734210532158613
2023-01-22 18:22:52.230691: step: 48/529, loss: 5.352754214982269e-06
2023-01-22 18:22:53.297522: step: 52/529, loss: 2.4183271307265386e-05
2023-01-22 18:22:54.376658: step: 56/529, loss: 0.0011040987446904182
2023-01-22 18:22:55.443005: step: 60/529, loss: 0.001783977379091084
2023-01-22 18:22:56.499102: step: 64/529, loss: 8.852654718793929e-05
2023-01-22 18:22:57.572334: step: 68/529, loss: 0.0026852956507354975
2023-01-22 18:22:58.648059: step: 72/529, loss: 1.2267275451449677e-05
2023-01-22 18:22:59.719119: step: 76/529, loss: 0.0011496621882542968
2023-01-22 18:23:00.803998: step: 80/529, loss: 0.001844880636781454
2023-01-22 18:23:01.881756: step: 84/529, loss: 0.0022491570562124252
2023-01-22 18:23:02.956067: step: 88/529, loss: 0.001819856115616858
2023-01-22 18:23:04.038685: step: 92/529, loss: 0.0009606943349353969
2023-01-22 18:23:05.109755: step: 96/529, loss: 0.0029981129337102175
2023-01-22 18:23:06.178583: step: 100/529, loss: 0.002628811402246356
2023-01-22 18:23:07.239171: step: 104/529, loss: 0.002487039193511009
2023-01-22 18:23:08.318561: step: 108/529, loss: 4.50752122560516e-05
2023-01-22 18:23:09.374635: step: 112/529, loss: 4.667012035497464e-06
2023-01-22 18:23:10.432502: step: 116/529, loss: 0.0
2023-01-22 18:23:11.500780: step: 120/529, loss: 2.5754681701073423e-05
2023-01-22 18:23:12.564572: step: 124/529, loss: 0.006827972363680601
2023-01-22 18:23:13.632946: step: 128/529, loss: 1.8251725123263896e-05
2023-01-22 18:23:14.703120: step: 132/529, loss: 0.0027503070887178183
2023-01-22 18:23:15.787415: step: 136/529, loss: 0.002401398029178381
2023-01-22 18:23:16.864338: step: 140/529, loss: 0.008718474768102169
2023-01-22 18:23:17.927605: step: 144/529, loss: 0.002033430617302656
2023-01-22 18:23:19.002772: step: 148/529, loss: 0.0009262897656299174
2023-01-22 18:23:20.081357: step: 152/529, loss: 0.00035648245830088854
2023-01-22 18:23:21.157569: step: 156/529, loss: 0.0025159530341625214
2023-01-22 18:23:22.230591: step: 160/529, loss: 0.006056359503418207
2023-01-22 18:23:23.289266: step: 164/529, loss: 0.000981770921498537
2023-01-22 18:23:24.366270: step: 168/529, loss: 0.005055608693510294
2023-01-22 18:23:25.462599: step: 172/529, loss: 2.6814668672159314e-05
2023-01-22 18:23:26.548998: step: 176/529, loss: 0.002276569837704301
2023-01-22 18:23:27.622616: step: 180/529, loss: 0.0003162195789627731
2023-01-22 18:23:28.717249: step: 184/529, loss: 9.143976785708219e-05
2023-01-22 18:23:29.785217: step: 188/529, loss: 0.0018073818646371365
2023-01-22 18:23:30.866244: step: 192/529, loss: 0.001006540609523654
2023-01-22 18:23:31.951637: step: 196/529, loss: 0.0051518515683710575
2023-01-22 18:23:33.022044: step: 200/529, loss: 0.0011647173669189215
2023-01-22 18:23:34.105478: step: 204/529, loss: 5.387639703258174e-07
2023-01-22 18:23:35.171339: step: 208/529, loss: 0.001833552261814475
2023-01-22 18:23:36.256391: step: 212/529, loss: 0.0014072679914534092
2023-01-22 18:23:37.332451: step: 216/529, loss: 9.867369226412848e-05
2023-01-22 18:23:38.416219: step: 220/529, loss: 0.00038242017035372555
2023-01-22 18:23:39.476693: step: 224/529, loss: 0.00014357497275341302
2023-01-22 18:23:40.571142: step: 228/529, loss: 0.005328443367034197
2023-01-22 18:23:41.646824: step: 232/529, loss: 0.0025594925973564386
2023-01-22 18:23:42.731909: step: 236/529, loss: 0.0001578389637870714
2023-01-22 18:23:43.822581: step: 240/529, loss: 0.002368208486586809
2023-01-22 18:23:44.901412: step: 244/529, loss: 0.0013675173977389932
2023-01-22 18:23:45.958919: step: 248/529, loss: 9.905160550260916e-05
2023-01-22 18:23:47.049197: step: 252/529, loss: 0.0038675423711538315
2023-01-22 18:23:48.135508: step: 256/529, loss: 0.003128435229882598
2023-01-22 18:23:49.212000: step: 260/529, loss: 0.0050405231304466724
2023-01-22 18:23:50.289954: step: 264/529, loss: 0.0034534321166574955
2023-01-22 18:23:51.343941: step: 268/529, loss: 3.246635606046766e-05
2023-01-22 18:23:52.414050: step: 272/529, loss: 0.0029384715016931295
2023-01-22 18:23:53.496108: step: 276/529, loss: 0.0010744519531726837
2023-01-22 18:23:54.557581: step: 280/529, loss: 0.0022833039984107018
2023-01-22 18:23:55.630335: step: 284/529, loss: 0.0008670688839629292
2023-01-22 18:23:56.746526: step: 288/529, loss: 0.003240938065573573
2023-01-22 18:23:57.824976: step: 292/529, loss: 5.8092631661565974e-05
2023-01-22 18:23:58.899375: step: 296/529, loss: 0.0010195011273026466
2023-01-22 18:23:59.979760: step: 300/529, loss: 0.012319865636527538
2023-01-22 18:24:01.058743: step: 304/529, loss: 0.00497813755646348
2023-01-22 18:24:02.147797: step: 308/529, loss: 0.000755386718083173
2023-01-22 18:24:03.229472: step: 312/529, loss: 0.0019269298063591123
2023-01-22 18:24:04.315002: step: 316/529, loss: 0.0027097086422145367
2023-01-22 18:24:05.378295: step: 320/529, loss: 0.002618101192638278
2023-01-22 18:24:06.450309: step: 324/529, loss: 0.0002074251533485949
2023-01-22 18:24:07.534897: step: 328/529, loss: 0.0022812895476818085
2023-01-22 18:24:08.592503: step: 332/529, loss: 0.0023774162400513887
2023-01-22 18:24:09.663914: step: 336/529, loss: 0.00025950890267267823
2023-01-22 18:24:10.731491: step: 340/529, loss: 0.022284623235464096
2023-01-22 18:24:11.828395: step: 344/529, loss: 0.0007858769386075437
2023-01-22 18:24:12.926437: step: 348/529, loss: 4.798209556611255e-05
2023-01-22 18:24:13.993339: step: 352/529, loss: 0.014714204706251621
2023-01-22 18:24:15.080016: step: 356/529, loss: 0.024418260902166367
2023-01-22 18:24:16.158741: step: 360/529, loss: 0.000383179314667359
2023-01-22 18:24:17.225737: step: 364/529, loss: 0.0006357360980473459
2023-01-22 18:24:18.303757: step: 368/529, loss: 0.000190254402696155
2023-01-22 18:24:19.392369: step: 372/529, loss: 0.00103954307269305
2023-01-22 18:24:20.470044: step: 376/529, loss: 0.0013072279980406165
2023-01-22 18:24:21.550786: step: 380/529, loss: 0.0028431143146008253
2023-01-22 18:24:22.611056: step: 384/529, loss: 0.0
2023-01-22 18:24:23.682452: step: 388/529, loss: 0.001187230576761067
2023-01-22 18:24:24.770166: step: 392/529, loss: 0.0004948079586029053
2023-01-22 18:24:25.845929: step: 396/529, loss: 0.00013973114255350083
2023-01-22 18:24:26.902950: step: 400/529, loss: 0.0002870879543479532
2023-01-22 18:24:27.975458: step: 404/529, loss: 0.00035541175748221576
2023-01-22 18:24:29.045682: step: 408/529, loss: 0.006057152524590492
2023-01-22 18:24:30.116969: step: 412/529, loss: 0.0008274091524071991
2023-01-22 18:24:31.188215: step: 416/529, loss: 0.00019476051966194063
2023-01-22 18:24:32.267003: step: 420/529, loss: 0.0036354619078338146
2023-01-22 18:24:33.351704: step: 424/529, loss: 0.004550225101411343
2023-01-22 18:24:34.421232: step: 428/529, loss: 0.0007033761939965189
2023-01-22 18:24:35.500350: step: 432/529, loss: 0.0021626714151352644
2023-01-22 18:24:36.561904: step: 436/529, loss: 0.00012795602378901094
2023-01-22 18:24:37.635872: step: 440/529, loss: 0.0035500184167176485
2023-01-22 18:24:38.703251: step: 444/529, loss: 0.00013778953871224076
2023-01-22 18:24:39.774262: step: 448/529, loss: 0.00013741859584115446
2023-01-22 18:24:40.847601: step: 452/529, loss: 0.0016091839643195271
2023-01-22 18:24:41.898086: step: 456/529, loss: 0.009337568655610085
2023-01-22 18:24:42.973445: step: 460/529, loss: 0.0006452303496189415
2023-01-22 18:24:44.042472: step: 464/529, loss: 0.0030323772225528955
2023-01-22 18:24:45.130495: step: 468/529, loss: 0.0006839603302069008
2023-01-22 18:24:46.186393: step: 472/529, loss: 0.0006726902793161571
2023-01-22 18:24:47.248746: step: 476/529, loss: 0.0020286915823817253
2023-01-22 18:24:48.324851: step: 480/529, loss: 0.0007536160410381854
2023-01-22 18:24:49.415875: step: 484/529, loss: 0.010548115707933903
2023-01-22 18:24:50.503395: step: 488/529, loss: 0.0012876685941591859
2023-01-22 18:24:51.574654: step: 492/529, loss: 8.220409654313698e-05
2023-01-22 18:24:52.662179: step: 496/529, loss: 0.0008663617190904915
2023-01-22 18:24:53.745460: step: 500/529, loss: 2.1060950530227274e-05
2023-01-22 18:24:54.816458: step: 504/529, loss: 0.0048391143791377544
2023-01-22 18:24:55.887788: step: 508/529, loss: 0.008487492799758911
2023-01-22 18:24:56.957578: step: 512/529, loss: 0.0006959937163628638
2023-01-22 18:24:58.038119: step: 516/529, loss: 0.003163679502904415
2023-01-22 18:24:59.111894: step: 520/529, loss: 0.016245556995272636
2023-01-22 18:25:00.200931: step: 524/529, loss: 0.004731496796011925
2023-01-22 18:25:01.278984: step: 528/529, loss: 0.0008546838071197271
2023-01-22 18:25:02.360644: step: 532/529, loss: 0.006097367964684963
2023-01-22 18:25:03.433803: step: 536/529, loss: 7.900789205450565e-05
2023-01-22 18:25:04.522450: step: 540/529, loss: 0.014645283110439777
2023-01-22 18:25:05.588636: step: 544/529, loss: 0.0045510525815188885
2023-01-22 18:25:06.690379: step: 548/529, loss: 0.0015728421276435256
2023-01-22 18:25:07.781235: step: 552/529, loss: 0.006241316441446543
2023-01-22 18:25:08.853065: step: 556/529, loss: 0.0008262254414148629
2023-01-22 18:25:09.923874: step: 560/529, loss: 0.0002901999687310308
2023-01-22 18:25:10.997711: step: 564/529, loss: 0.0009423245792277157
2023-01-22 18:25:12.071585: step: 568/529, loss: 0.004145944491028786
2023-01-22 18:25:13.157930: step: 572/529, loss: 0.0012021501315757632
2023-01-22 18:25:14.242151: step: 576/529, loss: 0.0011120678391307592
2023-01-22 18:25:15.328388: step: 580/529, loss: 0.005865253508090973
2023-01-22 18:25:16.390442: step: 584/529, loss: 0.0006417521508410573
2023-01-22 18:25:17.452441: step: 588/529, loss: 0.0008551164646632969
2023-01-22 18:25:18.538402: step: 592/529, loss: 0.0051851761527359486
2023-01-22 18:25:19.615938: step: 596/529, loss: 0.0010545669356361032
2023-01-22 18:25:20.691482: step: 600/529, loss: 0.002115735551342368
2023-01-22 18:25:21.760377: step: 604/529, loss: 0.001378060900606215
2023-01-22 18:25:22.822666: step: 608/529, loss: 0.0024605717044323683
2023-01-22 18:25:23.907642: step: 612/529, loss: 4.1022130972123705e-06
2023-01-22 18:25:24.998898: step: 616/529, loss: 0.0020249353256076574
2023-01-22 18:25:26.082790: step: 620/529, loss: 5.1120798161718994e-05
2023-01-22 18:25:27.160732: step: 624/529, loss: 0.0009625621605664492
2023-01-22 18:25:28.243821: step: 628/529, loss: 0.0024871586356312037
2023-01-22 18:25:29.306807: step: 632/529, loss: 0.0018476922996342182
2023-01-22 18:25:30.390347: step: 636/529, loss: 0.002248483942821622
2023-01-22 18:25:31.470305: step: 640/529, loss: 0.00010955056495731696
2023-01-22 18:25:32.546607: step: 644/529, loss: 0.0021941205486655235
2023-01-22 18:25:33.633378: step: 648/529, loss: 0.0007116594351828098
2023-01-22 18:25:34.695871: step: 652/529, loss: 3.0883711588103324e-05
2023-01-22 18:25:35.754934: step: 656/529, loss: 0.00012071282253600657
2023-01-22 18:25:36.822888: step: 660/529, loss: 0.00012231143773533404
2023-01-22 18:25:37.921447: step: 664/529, loss: 0.0038045060355216265
2023-01-22 18:25:38.999351: step: 668/529, loss: 0.0001801444450393319
2023-01-22 18:25:40.078777: step: 672/529, loss: 0.00021985379862599075
2023-01-22 18:25:41.149736: step: 676/529, loss: 0.00038099708035588264
2023-01-22 18:25:42.222840: step: 680/529, loss: 0.0011286812368780375
2023-01-22 18:25:43.309684: step: 684/529, loss: 0.00010883078357437626
2023-01-22 18:25:44.382068: step: 688/529, loss: 0.05610376596450806
2023-01-22 18:25:45.457592: step: 692/529, loss: 4.084552074345993e-06
2023-01-22 18:25:46.544032: step: 696/529, loss: 0.0006638095946982503
2023-01-22 18:25:47.615875: step: 700/529, loss: 0.00024273428425658494
2023-01-22 18:25:48.676598: step: 704/529, loss: 0.0002553915837779641
2023-01-22 18:25:49.767585: step: 708/529, loss: 0.0014193645911291242
2023-01-22 18:25:50.853189: step: 712/529, loss: 0.00038652695366181433
2023-01-22 18:25:51.946057: step: 716/529, loss: 0.0026721444446593523
2023-01-22 18:25:53.033817: step: 720/529, loss: 0.0003787715395446867
2023-01-22 18:25:54.104028: step: 724/529, loss: 0.007860297337174416
2023-01-22 18:25:55.183092: step: 728/529, loss: 0.00029570524930022657
2023-01-22 18:25:56.270339: step: 732/529, loss: 0.005589492153376341
2023-01-22 18:25:57.351793: step: 736/529, loss: 0.0013478923356160522
2023-01-22 18:25:58.445031: step: 740/529, loss: 0.000393137481296435
2023-01-22 18:25:59.519928: step: 744/529, loss: 0.0034523168578743935
2023-01-22 18:26:00.610203: step: 748/529, loss: 0.0018992506666108966
2023-01-22 18:26:01.676118: step: 752/529, loss: 0.0071465312503278255
2023-01-22 18:26:02.762066: step: 756/529, loss: 0.002539483131840825
2023-01-22 18:26:03.834892: step: 760/529, loss: 0.0005039104726165533
2023-01-22 18:26:04.926899: step: 764/529, loss: 1.7175478205899708e-05
2023-01-22 18:26:06.011824: step: 768/529, loss: 0.002322344807907939
2023-01-22 18:26:07.081909: step: 772/529, loss: 0.0006581287016160786
2023-01-22 18:26:08.151301: step: 776/529, loss: 0.0004342835454735905
2023-01-22 18:26:09.228945: step: 780/529, loss: 0.0038829061668366194
2023-01-22 18:26:10.303952: step: 784/529, loss: 0.0034522421192377806
2023-01-22 18:26:11.364923: step: 788/529, loss: 0.00038375702570192516
2023-01-22 18:26:12.423245: step: 792/529, loss: 4.385676948004402e-05
2023-01-22 18:26:13.516596: step: 796/529, loss: 0.006793093867599964
2023-01-22 18:26:14.593672: step: 800/529, loss: 2.044854682026198e-06
2023-01-22 18:26:15.670440: step: 804/529, loss: 0.009319250471889973
2023-01-22 18:26:16.750822: step: 808/529, loss: 0.005190895404666662
2023-01-22 18:26:17.827786: step: 812/529, loss: 0.0005878365482203662
2023-01-22 18:26:18.913946: step: 816/529, loss: 0.0057428255677223206
2023-01-22 18:26:20.016248: step: 820/529, loss: 0.0011091399937868118
2023-01-22 18:26:21.097721: step: 824/529, loss: 0.0009232126176357269
2023-01-22 18:26:22.164805: step: 828/529, loss: 0.0006929375231266022
2023-01-22 18:26:23.241276: step: 832/529, loss: 0.002562541514635086
2023-01-22 18:26:24.331155: step: 836/529, loss: 0.005218657664954662
2023-01-22 18:26:25.400731: step: 840/529, loss: 0.0015394786605611444
2023-01-22 18:26:26.486135: step: 844/529, loss: 0.0017984022852033377
2023-01-22 18:26:27.574694: step: 848/529, loss: 0.0008619173313491046
2023-01-22 18:26:28.654767: step: 852/529, loss: 0.00039507824112661183
2023-01-22 18:26:29.728476: step: 856/529, loss: 0.0033971716184169054
2023-01-22 18:26:30.798752: step: 860/529, loss: 0.0008975898963399231
2023-01-22 18:26:31.882386: step: 864/529, loss: 0.0003234376199543476
2023-01-22 18:26:32.943991: step: 868/529, loss: 0.0014752991264685988
2023-01-22 18:26:34.036947: step: 872/529, loss: 0.0017516027437523007
2023-01-22 18:26:35.145319: step: 876/529, loss: 6.583932554349303e-05
2023-01-22 18:26:36.231007: step: 880/529, loss: 0.0034900950267910957
2023-01-22 18:26:37.316859: step: 884/529, loss: 0.0010465745581313968
2023-01-22 18:26:38.404108: step: 888/529, loss: 0.005252181086689234
2023-01-22 18:26:39.498401: step: 892/529, loss: 0.007148124277591705
2023-01-22 18:26:40.583041: step: 896/529, loss: 3.0493527447106317e-05
2023-01-22 18:26:41.678282: step: 900/529, loss: 0.0016849299427121878
2023-01-22 18:26:42.758994: step: 904/529, loss: 0.0009735008352436125
2023-01-22 18:26:43.852508: step: 908/529, loss: 0.01325288601219654
2023-01-22 18:26:44.934993: step: 912/529, loss: 0.0015434680972248316
2023-01-22 18:26:46.025221: step: 916/529, loss: 0.0019753093365579844
2023-01-22 18:26:47.108432: step: 920/529, loss: 5.046111982665025e-05
2023-01-22 18:26:48.191905: step: 924/529, loss: 0.0026010717265307903
2023-01-22 18:26:49.261146: step: 928/529, loss: 0.001972249476239085
2023-01-22 18:26:50.338909: step: 932/529, loss: 0.00041918802889995277
2023-01-22 18:26:51.417742: step: 936/529, loss: 0.005304364487528801
2023-01-22 18:26:52.504409: step: 940/529, loss: 0.002736226422712207
2023-01-22 18:26:53.594378: step: 944/529, loss: 0.004888090770691633
2023-01-22 18:26:54.699808: step: 948/529, loss: 0.0028150822035968304
2023-01-22 18:26:55.787150: step: 952/529, loss: 0.003160664113238454
2023-01-22 18:26:56.866746: step: 956/529, loss: 0.00039712185389362276
2023-01-22 18:26:57.941669: step: 960/529, loss: 0.0016485154628753662
2023-01-22 18:26:59.014127: step: 964/529, loss: 0.0001912313891807571
2023-01-22 18:27:00.090672: step: 968/529, loss: 0.00421398738399148
2023-01-22 18:27:01.164274: step: 972/529, loss: 0.004482007119804621
2023-01-22 18:27:02.248233: step: 976/529, loss: 0.019088326022028923
2023-01-22 18:27:03.327421: step: 980/529, loss: 0.0032817998435348272
2023-01-22 18:27:04.406374: step: 984/529, loss: 1.5632689610356465e-05
2023-01-22 18:27:05.490576: step: 988/529, loss: 4.045343666803092e-05
2023-01-22 18:27:06.565355: step: 992/529, loss: 0.0042253234423696995
2023-01-22 18:27:07.638809: step: 996/529, loss: 0.002274387050420046
2023-01-22 18:27:08.736388: step: 1000/529, loss: 0.0015770719619467854
2023-01-22 18:27:09.815083: step: 1004/529, loss: 0.002691145520657301
2023-01-22 18:27:10.884427: step: 1008/529, loss: 0.0037738229148089886
2023-01-22 18:27:11.979956: step: 1012/529, loss: 0.0018977581057697535
2023-01-22 18:27:13.096844: step: 1016/529, loss: 0.0006461940356530249
2023-01-22 18:27:14.186507: step: 1020/529, loss: 0.004442417528480291
2023-01-22 18:27:15.267255: step: 1024/529, loss: 0.00022630376042798162
2023-01-22 18:27:16.344680: step: 1028/529, loss: 4.8760248319013044e-05
2023-01-22 18:27:17.441311: step: 1032/529, loss: 0.006847711279988289
2023-01-22 18:27:18.528125: step: 1036/529, loss: 0.0016026971861720085
2023-01-22 18:27:19.611243: step: 1040/529, loss: 2.7047412004321814e-05
2023-01-22 18:27:20.697973: step: 1044/529, loss: 2.033718146776664e-06
2023-01-22 18:27:21.798886: step: 1048/529, loss: 0.00478706369176507
2023-01-22 18:27:22.882133: step: 1052/529, loss: 0.0011160974390804768
2023-01-22 18:27:23.959757: step: 1056/529, loss: 0.0010749862994998693
2023-01-22 18:27:25.030949: step: 1060/529, loss: 0.0022716568782925606
2023-01-22 18:27:26.110673: step: 1064/529, loss: 0.0013149181613698602
2023-01-22 18:27:27.206383: step: 1068/529, loss: 0.0007107298006303608
2023-01-22 18:27:28.282013: step: 1072/529, loss: 4.153432746534236e-05
2023-01-22 18:27:29.359040: step: 1076/529, loss: 0.004577780142426491
2023-01-22 18:27:30.453002: step: 1080/529, loss: 0.0001739071449264884
2023-01-22 18:27:31.526049: step: 1084/529, loss: 0.003044232027605176
2023-01-22 18:27:32.599495: step: 1088/529, loss: 0.004600810818374157
2023-01-22 18:27:33.701975: step: 1092/529, loss: 0.002502787858247757
2023-01-22 18:27:34.802861: step: 1096/529, loss: 0.0013413004344329238
2023-01-22 18:27:35.888020: step: 1100/529, loss: 0.0039334469474852085
2023-01-22 18:27:36.971745: step: 1104/529, loss: 3.0470575438812375e-05
2023-01-22 18:27:38.059713: step: 1108/529, loss: 0.016193196177482605
2023-01-22 18:27:39.137162: step: 1112/529, loss: 0.000409727479564026
2023-01-22 18:27:40.234127: step: 1116/529, loss: 0.0011356855975463986
2023-01-22 18:27:41.321041: step: 1120/529, loss: 0.004081465769559145
2023-01-22 18:27:42.416907: step: 1124/529, loss: 0.00019597906793933362
2023-01-22 18:27:43.486000: step: 1128/529, loss: 0.00021422002464532852
2023-01-22 18:27:44.566476: step: 1132/529, loss: 0.0037924337666481733
2023-01-22 18:27:45.671004: step: 1136/529, loss: 5.8792022173292935e-05
2023-01-22 18:27:46.743742: step: 1140/529, loss: 0.00797716062515974
2023-01-22 18:27:47.831149: step: 1144/529, loss: 0.0022480101324617863
2023-01-22 18:27:48.912950: step: 1148/529, loss: 0.0005457639344967902
2023-01-22 18:27:49.992198: step: 1152/529, loss: 0.00022189089213497937
2023-01-22 18:27:51.087509: step: 1156/529, loss: 0.0033852746710181236
2023-01-22 18:27:52.178922: step: 1160/529, loss: 0.002605618443340063
2023-01-22 18:27:53.257432: step: 1164/529, loss: 1.1136330613226164e-05
2023-01-22 18:27:54.340612: step: 1168/529, loss: 0.0009035008843056858
2023-01-22 18:27:55.431566: step: 1172/529, loss: 0.0035224941093474627
2023-01-22 18:27:56.521441: step: 1176/529, loss: 0.004014801699668169
2023-01-22 18:27:57.598464: step: 1180/529, loss: 0.003338790265843272
2023-01-22 18:27:58.696928: step: 1184/529, loss: 0.0025712866336107254
2023-01-22 18:27:59.806164: step: 1188/529, loss: 0.005512366537004709
2023-01-22 18:28:00.895807: step: 1192/529, loss: 0.00788103323429823
2023-01-22 18:28:01.983837: step: 1196/529, loss: 0.004905066918581724
2023-01-22 18:28:03.063761: step: 1200/529, loss: 3.468736031209119e-05
2023-01-22 18:28:04.174384: step: 1204/529, loss: 0.0030592731200158596
2023-01-22 18:28:05.251117: step: 1208/529, loss: 0.0018325737910345197
2023-01-22 18:28:06.340117: step: 1212/529, loss: 0.0008709755493327975
2023-01-22 18:28:07.424327: step: 1216/529, loss: 0.01195499300956726
2023-01-22 18:28:08.499779: step: 1220/529, loss: 5.310764390742406e-05
2023-01-22 18:28:09.580776: step: 1224/529, loss: 3.789425682043657e-05
2023-01-22 18:28:10.716694: step: 1228/529, loss: 0.00246809353120625
2023-01-22 18:28:11.796375: step: 1232/529, loss: 0.00047421138151548803
2023-01-22 18:28:12.889826: step: 1236/529, loss: 0.001974575687199831
2023-01-22 18:28:13.968473: step: 1240/529, loss: 0.0009810103802010417
2023-01-22 18:28:15.039195: step: 1244/529, loss: 0.00886964425444603
2023-01-22 18:28:16.132167: step: 1248/529, loss: 0.00045228906674310565
2023-01-22 18:28:17.205224: step: 1252/529, loss: 0.004300416447222233
2023-01-22 18:28:18.287442: step: 1256/529, loss: 4.550609446596354e-05
2023-01-22 18:28:19.367273: step: 1260/529, loss: 0.0007722140871919692
2023-01-22 18:28:20.442694: step: 1264/529, loss: 0.0010265677701681852
2023-01-22 18:28:21.515979: step: 1268/529, loss: 0.0029264758341014385
2023-01-22 18:28:22.596709: step: 1272/529, loss: 0.005729811266064644
2023-01-22 18:28:23.685772: step: 1276/529, loss: 0.0037682722322642803
2023-01-22 18:28:24.757357: step: 1280/529, loss: 6.315475184237584e-05
2023-01-22 18:28:25.814118: step: 1284/529, loss: 0.0013305587926879525
2023-01-22 18:28:26.893535: step: 1288/529, loss: 0.0018673146842047572
2023-01-22 18:28:27.953526: step: 1292/529, loss: 7.157486106734723e-05
2023-01-22 18:28:29.019457: step: 1296/529, loss: 0.0017495786305516958
2023-01-22 18:28:30.103634: step: 1300/529, loss: 5.299753320286982e-05
2023-01-22 18:28:31.193284: step: 1304/529, loss: 0.016978254541754723
2023-01-22 18:28:32.259360: step: 1308/529, loss: 0.0028834324330091476
2023-01-22 18:28:33.335942: step: 1312/529, loss: 0.0011937894159927964
2023-01-22 18:28:34.430740: step: 1316/529, loss: 5.6245236919494346e-05
2023-01-22 18:28:35.493961: step: 1320/529, loss: 0.002781190210953355
2023-01-22 18:28:36.557566: step: 1324/529, loss: 0.0015717914793640375
2023-01-22 18:28:37.622391: step: 1328/529, loss: 2.8033493435941637e-05
2023-01-22 18:28:38.697683: step: 1332/529, loss: 0.0006443460588343441
2023-01-22 18:28:39.777399: step: 1336/529, loss: 0.0048844702541828156
2023-01-22 18:28:40.845750: step: 1340/529, loss: 0.0004202676354907453
2023-01-22 18:28:41.911380: step: 1344/529, loss: 0.0019861129112541676
2023-01-22 18:28:42.981220: step: 1348/529, loss: 0.004950982052832842
2023-01-22 18:28:44.044696: step: 1352/529, loss: 0.0005211990792304277
2023-01-22 18:28:45.106257: step: 1356/529, loss: 0.0002867472358047962
2023-01-22 18:28:46.170174: step: 1360/529, loss: 2.4214367400077208e-08
2023-01-22 18:28:47.248848: step: 1364/529, loss: 0.005261734127998352
2023-01-22 18:28:48.339278: step: 1368/529, loss: 0.0006633458542637527
2023-01-22 18:28:49.414862: step: 1372/529, loss: 0.00017273858247790486
2023-01-22 18:28:50.496755: step: 1376/529, loss: 4.366132088762242e-06
2023-01-22 18:28:51.556005: step: 1380/529, loss: 0.0009466444025747478
2023-01-22 18:28:52.619400: step: 1384/529, loss: 0.0013486393727362156
2023-01-22 18:28:53.680847: step: 1388/529, loss: 0.004097298253327608
2023-01-22 18:28:54.760271: step: 1392/529, loss: 0.0016938869375735521
2023-01-22 18:28:55.833562: step: 1396/529, loss: 0.0031844936311244965
2023-01-22 18:28:56.896195: step: 1400/529, loss: 0.0002008500596275553
2023-01-22 18:28:57.971278: step: 1404/529, loss: 0.00039893112261779606
2023-01-22 18:28:59.047588: step: 1408/529, loss: 0.00011707357043633237
2023-01-22 18:29:00.150920: step: 1412/529, loss: 0.002673372160643339
2023-01-22 18:29:01.210939: step: 1416/529, loss: 0.0014983529690653086
2023-01-22 18:29:02.293781: step: 1420/529, loss: 0.0009529491071589291
2023-01-22 18:29:03.366447: step: 1424/529, loss: 0.013765398412942886
2023-01-22 18:29:04.440173: step: 1428/529, loss: 0.0016339631984010339
2023-01-22 18:29:05.493428: step: 1432/529, loss: 0.00101010175421834
2023-01-22 18:29:06.555812: step: 1436/529, loss: 0.0013753349194303155
2023-01-22 18:29:07.636585: step: 1440/529, loss: 0.002998936688527465
2023-01-22 18:29:08.710316: step: 1444/529, loss: 0.001989042153581977
2023-01-22 18:29:09.792776: step: 1448/529, loss: 0.0057318322360515594
2023-01-22 18:29:10.866693: step: 1452/529, loss: 0.0011409578146412969
2023-01-22 18:29:11.926033: step: 1456/529, loss: 0.005625690333545208
2023-01-22 18:29:13.001689: step: 1460/529, loss: 0.00029265269404277205
2023-01-22 18:29:14.085041: step: 1464/529, loss: 0.0018152110278606415
2023-01-22 18:29:15.150277: step: 1468/529, loss: 0.0
2023-01-22 18:29:16.225802: step: 1472/529, loss: 0.0025686740409582853
2023-01-22 18:29:17.292315: step: 1476/529, loss: 0.001083427108824253
2023-01-22 18:29:18.389469: step: 1480/529, loss: 0.002301785396412015
2023-01-22 18:29:19.463274: step: 1484/529, loss: 0.00012055222759954631
2023-01-22 18:29:20.533149: step: 1488/529, loss: 0.006107552908360958
2023-01-22 18:29:21.602123: step: 1492/529, loss: 0.0025829130318015814
2023-01-22 18:29:22.668301: step: 1496/529, loss: 0.00010875325824599713
2023-01-22 18:29:23.736118: step: 1500/529, loss: 0.007653120439499617
2023-01-22 18:29:24.808793: step: 1504/529, loss: 8.807182894088328e-05
2023-01-22 18:29:25.878569: step: 1508/529, loss: 0.045848678797483444
2023-01-22 18:29:26.946965: step: 1512/529, loss: 0.001855504815466702
2023-01-22 18:29:28.025089: step: 1516/529, loss: 0.0022322640288621187
2023-01-22 18:29:29.089878: step: 1520/529, loss: 0.0007884801598265767
2023-01-22 18:29:30.173665: step: 1524/529, loss: 0.0018687976989895105
2023-01-22 18:29:31.242746: step: 1528/529, loss: 0.0019302616128697991
2023-01-22 18:29:32.304615: step: 1532/529, loss: 0.007825545035302639
2023-01-22 18:29:33.375372: step: 1536/529, loss: 0.003675041953101754
2023-01-22 18:29:34.442952: step: 1540/529, loss: 0.004312681034207344
2023-01-22 18:29:35.509073: step: 1544/529, loss: 0.0028086958918720484
2023-01-22 18:29:36.583922: step: 1548/529, loss: 0.003273728536441922
2023-01-22 18:29:37.648996: step: 1552/529, loss: 0.0014557080576196313
2023-01-22 18:29:38.725227: step: 1556/529, loss: 0.003620919305831194
2023-01-22 18:29:39.789203: step: 1560/529, loss: 0.0010540438815951347
2023-01-22 18:29:40.874659: step: 1564/529, loss: 0.0017262566834688187
2023-01-22 18:29:41.931738: step: 1568/529, loss: 0.0012436554534360766
2023-01-22 18:29:43.001105: step: 1572/529, loss: 0.0002291925484314561
2023-01-22 18:29:44.064857: step: 1576/529, loss: 0.0077019124291837215
2023-01-22 18:29:45.149851: step: 1580/529, loss: 0.003642189549282193
2023-01-22 18:29:46.207366: step: 1584/529, loss: 0.001956172287464142
2023-01-22 18:29:47.288693: step: 1588/529, loss: 0.004347768146544695
2023-01-22 18:29:48.357997: step: 1592/529, loss: 1.5669371578042046e-06
2023-01-22 18:29:49.439273: step: 1596/529, loss: 0.004435322713106871
2023-01-22 18:29:50.522514: step: 1600/529, loss: 0.0011272202245891094
2023-01-22 18:29:51.610518: step: 1604/529, loss: 1.7881353286952617e-08
2023-01-22 18:29:52.672142: step: 1608/529, loss: 0.0011762864887714386
2023-01-22 18:29:53.758638: step: 1612/529, loss: 0.003867711639031768
2023-01-22 18:29:54.846033: step: 1616/529, loss: 0.001478060963563621
2023-01-22 18:29:55.898404: step: 1620/529, loss: 0.000472315470688045
2023-01-22 18:29:56.952058: step: 1624/529, loss: 0.001271736458875239
2023-01-22 18:29:58.017937: step: 1628/529, loss: 0.0048606302589178085
2023-01-22 18:29:59.084420: step: 1632/529, loss: 0.0026488814037293196
2023-01-22 18:30:00.154356: step: 1636/529, loss: 0.002292864490300417
2023-01-22 18:30:01.220233: step: 1640/529, loss: 0.005180178210139275
2023-01-22 18:30:02.293039: step: 1644/529, loss: 0.00605470035225153
2023-01-22 18:30:03.373471: step: 1648/529, loss: 0.00026593913207761943
2023-01-22 18:30:04.440022: step: 1652/529, loss: 0.00044693052768707275
2023-01-22 18:30:05.511720: step: 1656/529, loss: 0.008743745274841785
2023-01-22 18:30:06.570607: step: 1660/529, loss: 0.001957723405212164
2023-01-22 18:30:07.662703: step: 1664/529, loss: 0.00011366964463377371
2023-01-22 18:30:08.750024: step: 1668/529, loss: 0.00282717845402658
2023-01-22 18:30:09.812994: step: 1672/529, loss: 0.0017495150677859783
2023-01-22 18:30:10.884031: step: 1676/529, loss: 0.014476480893790722
2023-01-22 18:30:11.955782: step: 1680/529, loss: 4.029765932500595e-06
2023-01-22 18:30:13.045825: step: 1684/529, loss: 0.0037144396919757128
2023-01-22 18:30:14.112255: step: 1688/529, loss: 0.0037353576626628637
2023-01-22 18:30:15.212831: step: 1692/529, loss: 0.0024860119447112083
2023-01-22 18:30:16.293191: step: 1696/529, loss: 0.017800122499465942
2023-01-22 18:30:17.369881: step: 1700/529, loss: 0.003148434916511178
2023-01-22 18:30:18.440569: step: 1704/529, loss: 0.00012700304796453565
2023-01-22 18:30:19.511885: step: 1708/529, loss: 0.0003432237426750362
2023-01-22 18:30:20.579564: step: 1712/529, loss: 0.015456571243703365
2023-01-22 18:30:21.658239: step: 1716/529, loss: 0.013328760862350464
2023-01-22 18:30:22.750279: step: 1720/529, loss: 0.021435288712382317
2023-01-22 18:30:23.815239: step: 1724/529, loss: 0.0032337489537894726
2023-01-22 18:30:24.890365: step: 1728/529, loss: 0.016377339139580727
2023-01-22 18:30:25.950823: step: 1732/529, loss: 1.6883181160665117e-05
2023-01-22 18:30:27.032546: step: 1736/529, loss: 0.002774052554741502
2023-01-22 18:30:28.119734: step: 1740/529, loss: 5.215403664493579e-09
2023-01-22 18:30:29.207170: step: 1744/529, loss: 0.0025115625467151403
2023-01-22 18:30:30.264085: step: 1748/529, loss: 9.311628673458472e-05
2023-01-22 18:30:31.342374: step: 1752/529, loss: 0.00018827612802851945
2023-01-22 18:30:32.408699: step: 1756/529, loss: 0.00016461798804812133
2023-01-22 18:30:33.487691: step: 1760/529, loss: 4.0593829908175394e-05
2023-01-22 18:30:34.578258: step: 1764/529, loss: 0.00020516736549325287
2023-01-22 18:30:35.666242: step: 1768/529, loss: 0.00025373511016368866
2023-01-22 18:30:36.739431: step: 1772/529, loss: 0.0007797826547175646
2023-01-22 18:30:37.802338: step: 1776/529, loss: 0.007685862015932798
2023-01-22 18:30:38.873646: step: 1780/529, loss: 0.003458377905189991
2023-01-22 18:30:39.968617: step: 1784/529, loss: 0.0002428066945867613
2023-01-22 18:30:41.054370: step: 1788/529, loss: 0.001367623801343143
2023-01-22 18:30:42.135881: step: 1792/529, loss: 0.0007303935708478093
2023-01-22 18:30:43.214042: step: 1796/529, loss: 0.0029274916741997004
2023-01-22 18:30:44.286997: step: 1800/529, loss: 0.005029785912483931
2023-01-22 18:30:45.359822: step: 1804/529, loss: 0.0007640636758878827
2023-01-22 18:30:46.429300: step: 1808/529, loss: 0.008094827644526958
2023-01-22 18:30:47.517856: step: 1812/529, loss: 0.0028483157511800528
2023-01-22 18:30:48.590566: step: 1816/529, loss: 0.003843510989099741
2023-01-22 18:30:49.653320: step: 1820/529, loss: 0.0028546745888888836
2023-01-22 18:30:50.730469: step: 1824/529, loss: 0.009414628148078918
2023-01-22 18:30:51.809213: step: 1828/529, loss: 0.000546939205378294
2023-01-22 18:30:52.909252: step: 1832/529, loss: 0.008302607573568821
2023-01-22 18:30:53.970580: step: 1836/529, loss: 0.0018023460870608687
2023-01-22 18:30:55.036458: step: 1840/529, loss: 0.0033640670590102673
2023-01-22 18:30:56.106501: step: 1844/529, loss: 0.00022593063476961106
2023-01-22 18:30:57.185158: step: 1848/529, loss: 0.0032788817770779133
2023-01-22 18:30:58.268834: step: 1852/529, loss: 0.0009824071312323213
2023-01-22 18:30:59.351641: step: 1856/529, loss: 0.0006703875842504203
2023-01-22 18:31:00.426117: step: 1860/529, loss: 4.0801351133268327e-05
2023-01-22 18:31:01.496041: step: 1864/529, loss: 0.005344883073121309
2023-01-22 18:31:02.578742: step: 1868/529, loss: 2.165043042623438e-05
2023-01-22 18:31:03.656320: step: 1872/529, loss: 0.001672480721026659
2023-01-22 18:31:04.714666: step: 1876/529, loss: 0.008345549926161766
2023-01-22 18:31:05.783559: step: 1880/529, loss: 0.004136687610298395
2023-01-22 18:31:06.883724: step: 1884/529, loss: 0.00020024561672471464
2023-01-22 18:31:07.941715: step: 1888/529, loss: 5.363531272450928e-06
2023-01-22 18:31:09.016149: step: 1892/529, loss: 0.0001777696015778929
2023-01-22 18:31:10.088154: step: 1896/529, loss: 0.0006320319953374565
2023-01-22 18:31:11.163858: step: 1900/529, loss: 0.005616499576717615
2023-01-22 18:31:12.231889: step: 1904/529, loss: 7.62258714530617e-05
2023-01-22 18:31:13.326580: step: 1908/529, loss: 0.001104343100450933
2023-01-22 18:31:14.393787: step: 1912/529, loss: 0.00019116631301585585
2023-01-22 18:31:15.462627: step: 1916/529, loss: 0.022298462688922882
2023-01-22 18:31:16.525919: step: 1920/529, loss: 3.74045739590656e-05
2023-01-22 18:31:17.615131: step: 1924/529, loss: 0.0010586337884888053
2023-01-22 18:31:18.706328: step: 1928/529, loss: 0.001114601967856288
2023-01-22 18:31:19.774470: step: 1932/529, loss: 0.0019243746064603329
2023-01-22 18:31:20.861980: step: 1936/529, loss: 0.0047816503793001175
2023-01-22 18:31:21.939586: step: 1940/529, loss: 6.0832117014797404e-05
2023-01-22 18:31:23.015711: step: 1944/529, loss: 0.007426185999065638
2023-01-22 18:31:24.106297: step: 1948/529, loss: 0.004662423860281706
2023-01-22 18:31:25.188434: step: 1952/529, loss: 0.00014836881018709391
2023-01-22 18:31:26.263244: step: 1956/529, loss: 0.037565406411886215
2023-01-22 18:31:27.342439: step: 1960/529, loss: 0.005257372744381428
2023-01-22 18:31:28.403959: step: 1964/529, loss: 0.004434757865965366
2023-01-22 18:31:29.474043: step: 1968/529, loss: 0.00023937605146784335
2023-01-22 18:31:30.558898: step: 1972/529, loss: 0.007027643732726574
2023-01-22 18:31:31.650285: step: 1976/529, loss: 0.0001306109334109351
2023-01-22 18:31:32.732765: step: 1980/529, loss: 0.004706720821559429
2023-01-22 18:31:33.817207: step: 1984/529, loss: 1.9174987755832262e-05
2023-01-22 18:31:34.892760: step: 1988/529, loss: 0.001869891188107431
2023-01-22 18:31:35.968846: step: 1992/529, loss: 0.04575552046298981
2023-01-22 18:31:37.058737: step: 1996/529, loss: 0.0015851868083700538
2023-01-22 18:31:38.128463: step: 2000/529, loss: 0.006763105280697346
2023-01-22 18:31:39.221717: step: 2004/529, loss: 0.00030633527785539627
2023-01-22 18:31:40.288955: step: 2008/529, loss: 0.010973074473440647
2023-01-22 18:31:41.354961: step: 2012/529, loss: 0.0033213645219802856
2023-01-22 18:31:42.416243: step: 2016/529, loss: 0.00019747317128349096
2023-01-22 18:31:43.483749: step: 2020/529, loss: 0.018144918605685234
2023-01-22 18:31:44.562688: step: 2024/529, loss: 0.00255021033808589
2023-01-22 18:31:45.615292: step: 2028/529, loss: 0.0002806618285831064
2023-01-22 18:31:46.679440: step: 2032/529, loss: 0.0019072286086156964
2023-01-22 18:31:47.754553: step: 2036/529, loss: 0.014130468480288982
2023-01-22 18:31:48.828325: step: 2040/529, loss: 0.0043364111334085464
2023-01-22 18:31:49.909347: step: 2044/529, loss: 0.0018080249428749084
2023-01-22 18:31:50.987770: step: 2048/529, loss: 0.0008840971859171987
2023-01-22 18:31:52.081067: step: 2052/529, loss: 0.007227852940559387
2023-01-22 18:31:53.180135: step: 2056/529, loss: 0.003201918676495552
2023-01-22 18:31:54.259662: step: 2060/529, loss: 0.001980405766516924
2023-01-22 18:31:55.325818: step: 2064/529, loss: 0.0018950875382870436
2023-01-22 18:31:56.404275: step: 2068/529, loss: 0.0025689273606985807
2023-01-22 18:31:57.488340: step: 2072/529, loss: 0.022754589095711708
2023-01-22 18:31:58.552724: step: 2076/529, loss: 0.00029317382723093033
2023-01-22 18:31:59.638036: step: 2080/529, loss: 0.0020040625240653753
2023-01-22 18:32:00.710536: step: 2084/529, loss: 0.003298926865682006
2023-01-22 18:32:01.796099: step: 2088/529, loss: 0.007333265617489815
2023-01-22 18:32:02.884436: step: 2092/529, loss: 0.0017135670641437173
2023-01-22 18:32:03.958993: step: 2096/529, loss: 0.004834538325667381
2023-01-22 18:32:05.045152: step: 2100/529, loss: 0.009966586716473103
2023-01-22 18:32:06.109937: step: 2104/529, loss: 0.0009601965430192649
2023-01-22 18:32:07.175351: step: 2108/529, loss: 0.0012738538207486272
2023-01-22 18:32:08.263340: step: 2112/529, loss: 0.002421914367005229
2023-01-22 18:32:09.329247: step: 2116/529, loss: 2.430733547953423e-05
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31648397976391235, 'r': 0.3561195445920304, 'f1': 0.3351339285714286}, 'combined': 0.24694078947368422, 'stategy': 1, 'epoch': 18}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.30956610010840396, 'r': 0.30672082345299584, 'f1': 0.3081368937367123}, 'combined': 0.20116709124780183, 'stategy': 1, 'epoch': 18}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31908640710382513, 'r': 0.36934100253004426, 'f1': 0.34237943418352385}, 'combined': 0.2522795830825965, 'stategy': 1, 'epoch': 18}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3339825776689047, 'r': 0.3128016972836525, 'f1': 0.32304532192179775}, 'combined': 0.21090005472614776, 'stategy': 1, 'epoch': 18}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31567708333333333, 'r': 0.3594046489563567, 'f1': 0.3361246672582076}, 'combined': 0.24767080745341613, 'stategy': 1, 'epoch': 18}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32511570330542855, 'r': 0.32242879666654073, 'f1': 0.3237666754908832}, 'combined': 0.21137099021684605, 'stategy': 1, 'epoch': 18}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 18}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 18}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 18}
New best russian model...
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3238172380156076, 'r': 0.36744346932321315, 'f1': 0.34425370370370373}, 'combined': 0.2536606237816764, 'stategy': 1, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3319312097086922, 'r': 0.3093550061071819, 'f1': 0.32024571517089817}, 'combined': 0.20907233218410967, 'stategy': 1, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31567708333333333, 'r': 0.3594046489563567, 'f1': 0.3361246672582076}, 'combined': 0.24767080745341613, 'stategy': 1, 'epoch': 18}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32511570330542855, 'r': 0.32242879666654073, 'f1': 0.3237666754908832}, 'combined': 0.21137099021684605, 'stategy': 1, 'epoch': 18}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 18}
******************************
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 18:34:54.765859: step: 4/529, loss: 0.005550272762775421
2023-01-22 18:34:55.822296: step: 8/529, loss: 0.0007610549801029265
2023-01-22 18:34:56.873798: step: 12/529, loss: 0.0026525871362537146
2023-01-22 18:34:57.934924: step: 16/529, loss: 0.005220665596425533
2023-01-22 18:34:58.982440: step: 20/529, loss: 8.616345439804718e-05
2023-01-22 18:35:00.052452: step: 24/529, loss: 0.0083405626937747
2023-01-22 18:35:01.094422: step: 28/529, loss: 0.0013250771444290876
2023-01-22 18:35:02.183512: step: 32/529, loss: 0.0005602349410764873
2023-01-22 18:35:03.226550: step: 36/529, loss: 0.0012757163494825363
2023-01-22 18:35:04.274886: step: 40/529, loss: 0.0009365349542349577
2023-01-22 18:35:05.363663: step: 44/529, loss: 0.0006063762702979147
2023-01-22 18:35:06.429298: step: 48/529, loss: 0.006380933336913586
2023-01-22 18:35:07.481164: step: 52/529, loss: 0.005873164162039757
2023-01-22 18:35:08.556350: step: 56/529, loss: 5.03152523378958e-06
2023-01-22 18:35:09.613112: step: 60/529, loss: 0.001569485873915255
2023-01-22 18:35:10.680402: step: 64/529, loss: 0.0010876096785068512
2023-01-22 18:35:11.738218: step: 68/529, loss: 0.001101877074688673
2023-01-22 18:35:12.802032: step: 72/529, loss: 1.7718231902108528e-05
2023-01-22 18:35:13.870751: step: 76/529, loss: 0.0005937537644058466
2023-01-22 18:35:14.940695: step: 80/529, loss: 0.0003423927410040051
2023-01-22 18:35:16.007259: step: 84/529, loss: 0.0021822818089276552
2023-01-22 18:35:17.081380: step: 88/529, loss: 0.006153288297355175
2023-01-22 18:35:18.158015: step: 92/529, loss: 0.00023072838666848838
2023-01-22 18:35:19.226361: step: 96/529, loss: 0.0019809072837233543
2023-01-22 18:35:20.295463: step: 100/529, loss: 6.69790679239668e-05
2023-01-22 18:35:21.378846: step: 104/529, loss: 0.0020098222885280848
2023-01-22 18:35:22.453860: step: 108/529, loss: 0.0010741493897512555
2023-01-22 18:35:23.526762: step: 112/529, loss: 0.0008140694117173553
2023-01-22 18:35:24.607572: step: 116/529, loss: 5.615416739601642e-05
2023-01-22 18:35:25.686168: step: 120/529, loss: 0.00012135961151216179
2023-01-22 18:35:26.756467: step: 124/529, loss: 0.005974811967462301
2023-01-22 18:35:27.819340: step: 128/529, loss: 0.0013884353684261441
2023-01-22 18:35:28.884956: step: 132/529, loss: 0.00014729340909980237
2023-01-22 18:35:29.959537: step: 136/529, loss: 0.0027141727041453123
2023-01-22 18:35:31.005586: step: 140/529, loss: 0.05117199942469597
2023-01-22 18:35:32.063485: step: 144/529, loss: 0.0003811954229604453
2023-01-22 18:35:33.134707: step: 148/529, loss: 0.0009387718746438622
2023-01-22 18:35:34.202677: step: 152/529, loss: 0.0063337781466543674
2023-01-22 18:35:35.262380: step: 156/529, loss: 1.2615866751275462e-07
2023-01-22 18:35:36.330007: step: 160/529, loss: 0.0030080436263233423
2023-01-22 18:35:37.406173: step: 164/529, loss: 0.009680736809968948
2023-01-22 18:35:38.485494: step: 168/529, loss: 0.007572818081825972
2023-01-22 18:35:39.539060: step: 172/529, loss: 0.0037050042301416397
2023-01-22 18:35:40.624129: step: 176/529, loss: 0.0014902646653354168
2023-01-22 18:35:41.676090: step: 180/529, loss: 0.0034742115531116724
2023-01-22 18:35:42.741599: step: 184/529, loss: 0.010083647444844246
2023-01-22 18:35:43.839523: step: 188/529, loss: 0.005261592101305723
2023-01-22 18:35:44.911953: step: 192/529, loss: 0.009679010137915611
2023-01-22 18:35:45.990702: step: 196/529, loss: 0.0016269839834421873
2023-01-22 18:35:47.059989: step: 200/529, loss: 0.005767378956079483
2023-01-22 18:35:48.130737: step: 204/529, loss: 0.003280257573351264
2023-01-22 18:35:49.211437: step: 208/529, loss: 0.003496411256492138
2023-01-22 18:35:50.288875: step: 212/529, loss: 0.0013061660574749112
2023-01-22 18:35:51.356598: step: 216/529, loss: 0.005923225544393063
2023-01-22 18:35:52.416368: step: 220/529, loss: 0.004614126868546009
2023-01-22 18:35:53.498362: step: 224/529, loss: 0.007316398434340954
2023-01-22 18:35:54.556510: step: 228/529, loss: 0.002448020502924919
2023-01-22 18:35:55.628801: step: 232/529, loss: 0.014334214851260185
2023-01-22 18:35:56.682713: step: 236/529, loss: 0.0009581045596860349
2023-01-22 18:35:57.751148: step: 240/529, loss: 5.191339732846245e-05
2023-01-22 18:35:58.856204: step: 244/529, loss: 0.00016784474428277463
2023-01-22 18:35:59.932802: step: 248/529, loss: 0.0031329242046922445
2023-01-22 18:36:00.996529: step: 252/529, loss: 0.001772395451553166
2023-01-22 18:36:02.042685: step: 256/529, loss: 0.0015573803102597594
2023-01-22 18:36:03.105853: step: 260/529, loss: 0.00039358355570584536
2023-01-22 18:36:04.176374: step: 264/529, loss: 0.003650473663583398
2023-01-22 18:36:05.245574: step: 268/529, loss: 0.0006346809095703065
2023-01-22 18:36:06.325586: step: 272/529, loss: 1.9788350982707925e-05
2023-01-22 18:36:07.395940: step: 276/529, loss: 0.00807908084243536
2023-01-22 18:36:08.471321: step: 280/529, loss: 0.0016301866853609681
2023-01-22 18:36:09.554874: step: 284/529, loss: 0.004677473101764917
2023-01-22 18:36:10.626523: step: 288/529, loss: 0.0003901770105585456
2023-01-22 18:36:11.677452: step: 292/529, loss: 0.00012507506471592933
2023-01-22 18:36:12.752099: step: 296/529, loss: 0.008182822726666927
2023-01-22 18:36:13.857201: step: 300/529, loss: 0.0032544543500989676
2023-01-22 18:36:14.946169: step: 304/529, loss: 0.011036175303161144
2023-01-22 18:36:16.018792: step: 308/529, loss: 0.003701606299728155
2023-01-22 18:36:17.097322: step: 312/529, loss: 0.002165562007576227
2023-01-22 18:36:18.145487: step: 316/529, loss: 0.00017161211872007698
2023-01-22 18:36:19.218572: step: 320/529, loss: 0.0003640690993051976
2023-01-22 18:36:20.307921: step: 324/529, loss: 1.0542474626618059e-07
2023-01-22 18:36:21.379972: step: 328/529, loss: 0.0009929283987730742
2023-01-22 18:36:22.477336: step: 332/529, loss: 0.0060135601088404655
2023-01-22 18:36:23.565786: step: 336/529, loss: 1.0803737495734822e-05
2023-01-22 18:36:24.634789: step: 340/529, loss: 0.0031833513639867306
2023-01-22 18:36:25.712881: step: 344/529, loss: 0.0006615098100155592
2023-01-22 18:36:26.803654: step: 348/529, loss: 0.004738308489322662
2023-01-22 18:36:27.873935: step: 352/529, loss: 0.0011392160085961223
2023-01-22 18:36:28.961334: step: 356/529, loss: 6.718080840073526e-05
2023-01-22 18:36:30.046920: step: 360/529, loss: 5.5149335821624845e-05
2023-01-22 18:36:31.106847: step: 364/529, loss: 0.00018120997992809862
2023-01-22 18:36:32.188364: step: 368/529, loss: 0.0002326490357518196
2023-01-22 18:36:33.252084: step: 372/529, loss: 0.0011034633498638868
2023-01-22 18:36:34.327332: step: 376/529, loss: 0.012548612430691719
2023-01-22 18:36:35.389597: step: 380/529, loss: 0.00438894284889102
2023-01-22 18:36:36.437578: step: 384/529, loss: 0.0005325342644937336
2023-01-22 18:36:37.512135: step: 388/529, loss: 0.0005177184357307851
2023-01-22 18:36:38.585407: step: 392/529, loss: 0.00010126904089702293
2023-01-22 18:36:39.668553: step: 396/529, loss: 5.426102507044561e-05
2023-01-22 18:36:40.726877: step: 400/529, loss: 4.5438166125677526e-05
2023-01-22 18:36:41.782977: step: 404/529, loss: 0.001413967227563262
2023-01-22 18:36:42.887056: step: 408/529, loss: 1.5022586012491956e-05
2023-01-22 18:36:43.944529: step: 412/529, loss: 0.00252367090433836
2023-01-22 18:36:45.026603: step: 416/529, loss: 0.0029055026825517416
2023-01-22 18:36:46.120303: step: 420/529, loss: 0.003600257681682706
2023-01-22 18:36:47.195988: step: 424/529, loss: 0.003331037238240242
2023-01-22 18:36:48.266980: step: 428/529, loss: 0.0005742170033045113
2023-01-22 18:36:49.328202: step: 432/529, loss: 1.4974522855482064e-05
2023-01-22 18:36:50.404385: step: 436/529, loss: 0.0027157519944012165
2023-01-22 18:36:51.465290: step: 440/529, loss: 0.004017917905002832
2023-01-22 18:36:52.547036: step: 444/529, loss: 0.00242613791488111
2023-01-22 18:36:53.640640: step: 448/529, loss: 0.0020046711433678865
2023-01-22 18:36:54.732568: step: 452/529, loss: 0.0013640165561810136
2023-01-22 18:36:55.798295: step: 456/529, loss: 0.008201287128031254
2023-01-22 18:36:56.874369: step: 460/529, loss: 0.004405135754495859
2023-01-22 18:36:57.928736: step: 464/529, loss: 0.005086584482342005
2023-01-22 18:36:58.987093: step: 468/529, loss: 3.379970075911842e-05
2023-01-22 18:37:00.058083: step: 472/529, loss: 0.0019488012185320258
2023-01-22 18:37:01.143334: step: 476/529, loss: 0.0008598949643783271
2023-01-22 18:37:02.223658: step: 480/529, loss: 0.0041540260426700115
2023-01-22 18:37:03.286365: step: 484/529, loss: 0.0001484264066675678
2023-01-22 18:37:04.357123: step: 488/529, loss: 0.0028602289967238903
2023-01-22 18:37:05.424990: step: 492/529, loss: 0.0003589103580452502
2023-01-22 18:37:06.499446: step: 496/529, loss: 0.004425681196153164
2023-01-22 18:37:07.579120: step: 500/529, loss: 0.0037166171241551638
2023-01-22 18:37:08.642198: step: 504/529, loss: 0.0032905940897762775
2023-01-22 18:37:09.702899: step: 508/529, loss: 0.0026078030932694674
2023-01-22 18:37:10.765580: step: 512/529, loss: 0.0010439407778903842
2023-01-22 18:37:11.839918: step: 516/529, loss: 0.00939603429287672
2023-01-22 18:37:12.931844: step: 520/529, loss: 0.0077019608579576015
2023-01-22 18:37:14.019103: step: 524/529, loss: 0.0006680558435618877
2023-01-22 18:37:15.098158: step: 528/529, loss: 0.0001808326633181423
2023-01-22 18:37:16.184151: step: 532/529, loss: 0.0021404752042144537
2023-01-22 18:37:17.265649: step: 536/529, loss: 0.0001727363996906206
2023-01-22 18:37:18.333917: step: 540/529, loss: 0.0022375795524567366
2023-01-22 18:37:19.402176: step: 544/529, loss: 0.0009696347988210618
2023-01-22 18:37:20.478981: step: 548/529, loss: 0.00290606077760458
2023-01-22 18:37:21.562999: step: 552/529, loss: 0.003670124337077141
2023-01-22 18:37:22.641723: step: 556/529, loss: 0.00038866783143021166
2023-01-22 18:37:23.715504: step: 560/529, loss: 0.00025236618239432573
2023-01-22 18:37:24.802432: step: 564/529, loss: 0.007980805821716785
2023-01-22 18:37:25.872776: step: 568/529, loss: 2.9802293965985882e-08
2023-01-22 18:37:26.938751: step: 572/529, loss: 0.00014798915071878582
2023-01-22 18:37:28.011342: step: 576/529, loss: 0.0005282009369693696
2023-01-22 18:37:29.065980: step: 580/529, loss: 0.0007339513394981623
2023-01-22 18:37:30.144325: step: 584/529, loss: 0.00027704695821739733
2023-01-22 18:37:31.225430: step: 588/529, loss: 0.004597665276378393
2023-01-22 18:37:32.313901: step: 592/529, loss: 0.001893265056423843
2023-01-22 18:37:33.384218: step: 596/529, loss: 0.00017987325554713607
2023-01-22 18:37:34.466388: step: 600/529, loss: 0.0028877875301986933
2023-01-22 18:37:35.545121: step: 604/529, loss: 0.00735909678041935
2023-01-22 18:37:36.623333: step: 608/529, loss: 0.0003404644376132637
2023-01-22 18:37:37.699124: step: 612/529, loss: 0.008895325474441051
2023-01-22 18:37:38.768909: step: 616/529, loss: 5.1473551138769835e-05
2023-01-22 18:37:39.842574: step: 620/529, loss: 3.52718161593657e-05
2023-01-22 18:37:40.912857: step: 624/529, loss: 0.0007283874438144267
2023-01-22 18:37:42.002424: step: 628/529, loss: 0.0024800642859190702
2023-01-22 18:37:43.093675: step: 632/529, loss: 0.0035599025432020426
2023-01-22 18:37:44.163495: step: 636/529, loss: 0.0012787414016202092
2023-01-22 18:37:45.238474: step: 640/529, loss: 0.0066371182911098
2023-01-22 18:37:46.312535: step: 644/529, loss: 0.0006164282676763833
2023-01-22 18:37:47.385058: step: 648/529, loss: 0.0008739436743780971
2023-01-22 18:37:48.455300: step: 652/529, loss: 3.632759762695059e-05
2023-01-22 18:37:49.538160: step: 656/529, loss: 0.0008676178986206651
2023-01-22 18:37:50.605766: step: 660/529, loss: 0.0028725017327815294
2023-01-22 18:37:51.671586: step: 664/529, loss: 0.006448869127780199
2023-01-22 18:37:52.759704: step: 668/529, loss: 0.00020628042693715543
2023-01-22 18:37:53.831541: step: 672/529, loss: 0.0001328882935922593
2023-01-22 18:37:54.912264: step: 676/529, loss: 0.0027902175206691027
2023-01-22 18:37:56.013332: step: 680/529, loss: 2.019218982241e-06
2023-01-22 18:37:57.087860: step: 684/529, loss: 1.0821781870617997e-06
2023-01-22 18:37:58.175162: step: 688/529, loss: 5.632678949041292e-05
2023-01-22 18:37:59.239290: step: 692/529, loss: 0.0006660653743892908
2023-01-22 18:38:00.311119: step: 696/529, loss: 0.0005596240516752005
2023-01-22 18:38:01.384319: step: 700/529, loss: 9.715823398437351e-05
2023-01-22 18:38:02.450931: step: 704/529, loss: 0.0019281271379441023
2023-01-22 18:38:03.533284: step: 708/529, loss: 0.000764808792155236
2023-01-22 18:38:04.621662: step: 712/529, loss: 0.0011708365054801106
2023-01-22 18:38:05.693725: step: 716/529, loss: 0.0008129074121825397
2023-01-22 18:38:06.771391: step: 720/529, loss: 0.010915243066847324
2023-01-22 18:38:07.841033: step: 724/529, loss: 5.075321496406104e-06
2023-01-22 18:38:08.934159: step: 728/529, loss: 0.001940823276527226
2023-01-22 18:38:10.030913: step: 732/529, loss: 0.005649505648761988
2023-01-22 18:38:11.123703: step: 736/529, loss: 0.013434085063636303
2023-01-22 18:38:12.200969: step: 740/529, loss: 0.0003298694209661335
2023-01-22 18:38:13.280817: step: 744/529, loss: 0.007294130977243185
2023-01-22 18:38:14.363145: step: 748/529, loss: 1.9457265807432123e-06
2023-01-22 18:38:15.432866: step: 752/529, loss: 0.001068144221790135
2023-01-22 18:38:16.529523: step: 756/529, loss: 0.002726457780227065
2023-01-22 18:38:17.604442: step: 760/529, loss: 3.196978650521487e-05
2023-01-22 18:38:18.674567: step: 764/529, loss: 8.373675518669188e-05
2023-01-22 18:38:19.762091: step: 768/529, loss: 0.039239853620529175
2023-01-22 18:38:20.840816: step: 772/529, loss: 0.0013340356526896358
2023-01-22 18:38:21.928854: step: 776/529, loss: 0.011207184754312038
2023-01-22 18:38:23.032402: step: 780/529, loss: 0.003583451034501195
2023-01-22 18:38:24.127963: step: 784/529, loss: 0.007945828139781952
2023-01-22 18:38:25.234070: step: 788/529, loss: 0.018534524366259575
2023-01-22 18:38:26.300003: step: 792/529, loss: 1.5667070329072885e-05
2023-01-22 18:38:27.392675: step: 796/529, loss: 0.00035253335954621434
2023-01-22 18:38:28.487004: step: 800/529, loss: 0.0026388531550765038
2023-01-22 18:38:29.569549: step: 804/529, loss: 0.0035606969613581896
2023-01-22 18:38:30.675378: step: 808/529, loss: 0.00023287774820346385
2023-01-22 18:38:31.770412: step: 812/529, loss: 0.004454170353710651
2023-01-22 18:38:32.836631: step: 816/529, loss: 0.0
2023-01-22 18:38:33.923953: step: 820/529, loss: 2.568472837083391e-06
2023-01-22 18:38:35.023379: step: 824/529, loss: 7.068672130117193e-05
2023-01-22 18:38:36.106679: step: 828/529, loss: 0.00011554638331290334
2023-01-22 18:38:37.181603: step: 832/529, loss: 0.0009226802503690124
2023-01-22 18:38:38.257046: step: 836/529, loss: 7.057376205921173e-05
2023-01-22 18:38:39.334579: step: 840/529, loss: 0.008089513517916203
2023-01-22 18:38:40.416930: step: 844/529, loss: 0.0043051643297076225
2023-01-22 18:38:41.506157: step: 848/529, loss: 0.0011193244718015194
2023-01-22 18:38:42.590725: step: 852/529, loss: 0.002075742231681943
2023-01-22 18:38:43.690883: step: 856/529, loss: 0.004258294124156237
2023-01-22 18:38:44.787025: step: 860/529, loss: 0.01081676222383976
2023-01-22 18:38:45.889468: step: 864/529, loss: 0.0004502387309912592
2023-01-22 18:38:46.966228: step: 868/529, loss: 6.123903585830703e-05
2023-01-22 18:38:48.034139: step: 872/529, loss: 0.003467608941718936
2023-01-22 18:38:49.132698: step: 876/529, loss: 0.0009224391542375088
2023-01-22 18:38:50.216841: step: 880/529, loss: 9.106258858082583e-09
2023-01-22 18:38:51.302533: step: 884/529, loss: 0.001418363768607378
2023-01-22 18:38:52.396341: step: 888/529, loss: 0.0020852508023381233
2023-01-22 18:38:53.475782: step: 892/529, loss: 0.00016155694902408868
2023-01-22 18:38:54.566172: step: 896/529, loss: 0.0060864645056426525
2023-01-22 18:38:55.646866: step: 900/529, loss: 0.0028166677802801132
2023-01-22 18:38:56.728040: step: 904/529, loss: 0.00024000738631002605
2023-01-22 18:38:57.811557: step: 908/529, loss: 0.0015794719802215695
2023-01-22 18:38:58.882522: step: 912/529, loss: 1.4170055919748847e-06
2023-01-22 18:38:59.964444: step: 916/529, loss: 0.002193300984799862
2023-01-22 18:39:01.054333: step: 920/529, loss: 0.0037680587265640497
2023-01-22 18:39:02.133794: step: 924/529, loss: 0.0033980198204517365
2023-01-22 18:39:03.236245: step: 928/529, loss: 0.002662337850779295
2023-01-22 18:39:04.326209: step: 932/529, loss: 0.0006825101445429027
2023-01-22 18:39:05.414034: step: 936/529, loss: 0.004220837727189064
2023-01-22 18:39:06.537642: step: 940/529, loss: 0.000912040879484266
2023-01-22 18:39:07.610590: step: 944/529, loss: 0.00012912981037516147
2023-01-22 18:39:08.705482: step: 948/529, loss: 0.006432090420275927
2023-01-22 18:39:09.788644: step: 952/529, loss: 0.0020078851375728846
2023-01-22 18:39:10.880696: step: 956/529, loss: 0.00226851599290967
2023-01-22 18:39:11.960214: step: 960/529, loss: 0.0008618362480774522
2023-01-22 18:39:13.089428: step: 964/529, loss: 0.0027117962017655373
2023-01-22 18:39:14.174896: step: 968/529, loss: 0.000921405095141381
2023-01-22 18:39:15.248942: step: 972/529, loss: 0.0005355889443308115
2023-01-22 18:39:16.354943: step: 976/529, loss: 0.006245487369596958
2023-01-22 18:39:17.442852: step: 980/529, loss: 0.006575887091457844
2023-01-22 18:39:18.529994: step: 984/529, loss: 0.0007065368117764592
2023-01-22 18:39:19.606424: step: 988/529, loss: 0.004607339855283499
2023-01-22 18:39:20.682882: step: 992/529, loss: 0.005440534092485905
2023-01-22 18:39:21.755972: step: 996/529, loss: 0.002364398678764701
2023-01-22 18:39:22.843906: step: 1000/529, loss: 0.0004719163989648223
2023-01-22 18:39:23.934412: step: 1004/529, loss: 0.011130196042358875
2023-01-22 18:39:25.042014: step: 1008/529, loss: 0.0002421838289592415
2023-01-22 18:39:26.131123: step: 1012/529, loss: 0.0021815448999404907
2023-01-22 18:39:27.223759: step: 1016/529, loss: 0.0010663840221241117
2023-01-22 18:39:28.308496: step: 1020/529, loss: 9.196421888191253e-05
2023-01-22 18:39:29.411651: step: 1024/529, loss: 0.0016589164733886719
2023-01-22 18:39:30.491832: step: 1028/529, loss: 0.010646265931427479
2023-01-22 18:39:31.585757: step: 1032/529, loss: 0.0016196627402678132
2023-01-22 18:39:32.682987: step: 1036/529, loss: 0.001986629329621792
2023-01-22 18:39:33.760144: step: 1040/529, loss: 0.0003384593001101166
2023-01-22 18:39:34.848085: step: 1044/529, loss: 0.0003534338902682066
2023-01-22 18:39:35.961004: step: 1048/529, loss: 2.6854836505663116e-06
2023-01-22 18:39:37.053109: step: 1052/529, loss: 9.029432840179652e-05
2023-01-22 18:39:38.152648: step: 1056/529, loss: 2.8878250304842368e-05
2023-01-22 18:39:39.241268: step: 1060/529, loss: 0.005253805313259363
2023-01-22 18:39:40.326234: step: 1064/529, loss: 0.0022125833202153444
2023-01-22 18:39:41.413572: step: 1068/529, loss: 0.0007990999729372561
2023-01-22 18:39:42.513045: step: 1072/529, loss: 0.0017336050514131784
2023-01-22 18:39:43.608788: step: 1076/529, loss: 0.001977931708097458
2023-01-22 18:39:44.696445: step: 1080/529, loss: 0.0018157617887482047
2023-01-22 18:39:45.771918: step: 1084/529, loss: 6.831006612628698e-05
2023-01-22 18:39:46.854002: step: 1088/529, loss: 0.0008231173851527274
2023-01-22 18:39:47.924372: step: 1092/529, loss: 0.00012559779861476272
2023-01-22 18:39:49.008851: step: 1096/529, loss: 0.002117100404575467
2023-01-22 18:39:50.086314: step: 1100/529, loss: 0.00042675432632677257
2023-01-22 18:39:51.171092: step: 1104/529, loss: 2.101760037476197e-05
2023-01-22 18:39:52.258009: step: 1108/529, loss: 0.0029196669347584248
2023-01-22 18:39:53.331850: step: 1112/529, loss: 0.0001926364639075473
2023-01-22 18:39:54.425456: step: 1116/529, loss: 0.005537739954888821
2023-01-22 18:39:55.522395: step: 1120/529, loss: 0.0007231393246911466
2023-01-22 18:39:56.605642: step: 1124/529, loss: 0.0009354263311251998
2023-01-22 18:39:57.688662: step: 1128/529, loss: 0.0005767861730419099
2023-01-22 18:39:58.757217: step: 1132/529, loss: 0.0016078012995421886
2023-01-22 18:39:59.849180: step: 1136/529, loss: 0.0001219295445480384
2023-01-22 18:40:00.946801: step: 1140/529, loss: 0.002624856773763895
2023-01-22 18:40:02.037137: step: 1144/529, loss: 0.002847106661647558
2023-01-22 18:40:03.125725: step: 1148/529, loss: 0.004916645120829344
2023-01-22 18:40:04.250129: step: 1152/529, loss: 0.004542953800410032
2023-01-22 18:40:05.320404: step: 1156/529, loss: 0.00013412647240329534
2023-01-22 18:40:06.413528: step: 1160/529, loss: 0.0025263663846999407
2023-01-22 18:40:07.505911: step: 1164/529, loss: 0.0010383236221969128
2023-01-22 18:40:08.577288: step: 1168/529, loss: 0.0016580659430474043
2023-01-22 18:40:09.662385: step: 1172/529, loss: 0.005924290511757135
2023-01-22 18:40:10.736099: step: 1176/529, loss: 0.0013048473047092557
2023-01-22 18:40:11.822916: step: 1180/529, loss: 0.007904703728854656
2023-01-22 18:40:12.913297: step: 1184/529, loss: 0.00986100360751152
2023-01-22 18:40:13.995002: step: 1188/529, loss: 3.345069126226008e-05
2023-01-22 18:40:15.075304: step: 1192/529, loss: 0.004237491171807051
2023-01-22 18:40:16.172004: step: 1196/529, loss: 0.001981412759050727
2023-01-22 18:40:17.261521: step: 1200/529, loss: 0.0023590335622429848
2023-01-22 18:40:18.340937: step: 1204/529, loss: 0.013690161518752575
2023-01-22 18:40:19.427000: step: 1208/529, loss: 1.376276827613765e-06
2023-01-22 18:40:20.509555: step: 1212/529, loss: 0.00010868853860301897
2023-01-22 18:40:21.572681: step: 1216/529, loss: 0.002281750086694956
2023-01-22 18:40:22.656713: step: 1220/529, loss: 0.0008225697092711926
2023-01-22 18:40:23.737692: step: 1224/529, loss: 0.0002749623672571033
2023-01-22 18:40:24.828156: step: 1228/529, loss: 0.00037340051494538784
2023-01-22 18:40:25.907419: step: 1232/529, loss: 0.000289250718196854
2023-01-22 18:40:26.990287: step: 1236/529, loss: 0.0015886299079284072
2023-01-22 18:40:28.064081: step: 1240/529, loss: 0.0004179180832579732
2023-01-22 18:40:29.154266: step: 1244/529, loss: 8.27842128181544e-10
2023-01-22 18:40:30.246792: step: 1248/529, loss: 6.55414187349379e-05
2023-01-22 18:40:31.332415: step: 1252/529, loss: 0.0031209278386086226
2023-01-22 18:40:32.401758: step: 1256/529, loss: 0.0170805174857378
2023-01-22 18:40:33.492107: step: 1260/529, loss: 0.005246256478130817
2023-01-22 18:40:34.570125: step: 1264/529, loss: 0.000935079122427851
2023-01-22 18:40:35.650179: step: 1268/529, loss: 0.0010366657515987754
2023-01-22 18:40:36.726625: step: 1272/529, loss: 0.0015398615505546331
2023-01-22 18:40:37.849593: step: 1276/529, loss: 0.0023136036470532417
2023-01-22 18:40:38.932243: step: 1280/529, loss: 0.005282704718410969
2023-01-22 18:40:40.012641: step: 1284/529, loss: 0.0031433331314474344
2023-01-22 18:40:41.092975: step: 1288/529, loss: 0.004818292800337076
2023-01-22 18:40:42.187345: step: 1292/529, loss: 0.003580772550776601
2023-01-22 18:40:43.283481: step: 1296/529, loss: 0.000507801421917975
2023-01-22 18:40:44.357293: step: 1300/529, loss: 0.0007315064431168139
2023-01-22 18:40:45.443846: step: 1304/529, loss: 3.2765165087766945e-05
2023-01-22 18:40:46.529244: step: 1308/529, loss: 0.0001225455926032737
2023-01-22 18:40:47.623507: step: 1312/529, loss: 8.749850530875847e-05
2023-01-22 18:40:48.707549: step: 1316/529, loss: 0.0018611084669828415
2023-01-22 18:40:49.786174: step: 1320/529, loss: 0.006996247451752424
2023-01-22 18:40:50.874923: step: 1324/529, loss: 0.0002824230177793652
2023-01-22 18:40:51.955881: step: 1328/529, loss: 0.0020704646594822407
2023-01-22 18:40:53.029947: step: 1332/529, loss: 0.003465651534497738
2023-01-22 18:40:54.143122: step: 1336/529, loss: 0.0008402460371144116
2023-01-22 18:40:55.208302: step: 1340/529, loss: 0.0015167383244261146
2023-01-22 18:40:56.299234: step: 1344/529, loss: 0.0034511748235672712
2023-01-22 18:40:57.373589: step: 1348/529, loss: 0.00018992846889887005
2023-01-22 18:40:58.455510: step: 1352/529, loss: 0.0006809252081438899
2023-01-22 18:40:59.533158: step: 1356/529, loss: 0.00016157186473719776
2023-01-22 18:41:00.614067: step: 1360/529, loss: 0.006505895871669054
2023-01-22 18:41:01.704178: step: 1364/529, loss: 0.0003203966189175844
2023-01-22 18:41:02.782210: step: 1368/529, loss: 0.0004957928322255611
2023-01-22 18:41:03.856575: step: 1372/529, loss: 1.3241086890047882e-05
2023-01-22 18:41:04.938628: step: 1376/529, loss: 0.0001145578280556947
2023-01-22 18:41:06.003561: step: 1380/529, loss: 0.0009045111946761608
2023-01-22 18:41:07.096401: step: 1384/529, loss: 0.0012526812497526407
2023-01-22 18:41:08.173423: step: 1388/529, loss: 0.010926326736807823
2023-01-22 18:41:09.258941: step: 1392/529, loss: 0.0011335014132782817
2023-01-22 18:41:10.334205: step: 1396/529, loss: 0.0012295488268136978
2023-01-22 18:41:11.401443: step: 1400/529, loss: 0.0005643097683787346
2023-01-22 18:41:12.484723: step: 1404/529, loss: 0.0018103045877069235
2023-01-22 18:41:13.576421: step: 1408/529, loss: 0.00015527053619734943
2023-01-22 18:41:14.652296: step: 1412/529, loss: 0.0007706593023613095
2023-01-22 18:41:15.736957: step: 1416/529, loss: 0.0016050555277615786
2023-01-22 18:41:16.829796: step: 1420/529, loss: 0.0001577777584316209
2023-01-22 18:41:17.909215: step: 1424/529, loss: 0.004776421003043652
2023-01-22 18:41:19.016371: step: 1428/529, loss: 0.001445088186301291
2023-01-22 18:41:20.110430: step: 1432/529, loss: 0.00047005570377223194
2023-01-22 18:41:21.178147: step: 1436/529, loss: 0.00777039211243391
2023-01-22 18:41:22.267785: step: 1440/529, loss: 0.007142259739339352
2023-01-22 18:41:23.368712: step: 1444/529, loss: 0.006781228817999363
2023-01-22 18:41:24.435656: step: 1448/529, loss: 3.7252889661942845e-09
2023-01-22 18:41:25.530160: step: 1452/529, loss: 0.0027382178232073784
2023-01-22 18:41:26.615000: step: 1456/529, loss: 0.003530877409502864
2023-01-22 18:41:27.693116: step: 1460/529, loss: 0.0001910785649670288
2023-01-22 18:41:28.778292: step: 1464/529, loss: 0.0015563304768875241
2023-01-22 18:41:29.868800: step: 1468/529, loss: 0.003940044902265072
2023-01-22 18:41:30.945206: step: 1472/529, loss: 0.00015611646813340485
2023-01-22 18:41:32.021648: step: 1476/529, loss: 0.0033869983162730932
2023-01-22 18:41:33.105001: step: 1480/529, loss: 0.0012347704032436013
2023-01-22 18:41:34.182504: step: 1484/529, loss: 2.8247177397133783e-05
2023-01-22 18:41:35.278013: step: 1488/529, loss: 0.0005833734758198261
2023-01-22 18:41:36.350561: step: 1492/529, loss: 0.002017692429944873
2023-01-22 18:41:37.404294: step: 1496/529, loss: 0.013612544164061546
2023-01-22 18:41:38.501918: step: 1500/529, loss: 0.0019536535255610943
2023-01-22 18:41:39.612002: step: 1504/529, loss: 0.00017686377395875752
2023-01-22 18:41:40.677909: step: 1508/529, loss: 0.0031346355099231005
2023-01-22 18:41:41.755754: step: 1512/529, loss: 0.0034271629992872477
2023-01-22 18:41:42.826133: step: 1516/529, loss: 0.002846606308594346
2023-01-22 18:41:43.920035: step: 1520/529, loss: 6.15144963376224e-05
2023-01-22 18:41:45.005912: step: 1524/529, loss: 0.007690890692174435
2023-01-22 18:41:46.083695: step: 1528/529, loss: 0.0006451900117099285
2023-01-22 18:41:47.164082: step: 1532/529, loss: 0.0039938329719007015
2023-01-22 18:41:48.232232: step: 1536/529, loss: 0.008942309767007828
2023-01-22 18:41:49.299264: step: 1540/529, loss: 0.00010460113117005676
2023-01-22 18:41:50.366400: step: 1544/529, loss: 3.533124618115835e-05
2023-01-22 18:41:51.450164: step: 1548/529, loss: 0.0014272828120738268
2023-01-22 18:41:52.532564: step: 1552/529, loss: 0.0005007721483707428
2023-01-22 18:41:53.622256: step: 1556/529, loss: 0.00017079628014471382
2023-01-22 18:41:54.710957: step: 1560/529, loss: 0.0011937690433114767
2023-01-22 18:41:55.790987: step: 1564/529, loss: 0.0011961006093770266
2023-01-22 18:41:56.870204: step: 1568/529, loss: 0.0019001393811777234
2023-01-22 18:41:57.941779: step: 1572/529, loss: 0.011626417748630047
2023-01-22 18:41:59.010660: step: 1576/529, loss: 4.191290372546064e-06
2023-01-22 18:42:00.090470: step: 1580/529, loss: 0.0005881005199626088
2023-01-22 18:42:01.162671: step: 1584/529, loss: 0.0011072555789723992
2023-01-22 18:42:02.245953: step: 1588/529, loss: 0.00021221810311544687
2023-01-22 18:42:03.329545: step: 1592/529, loss: 0.0037836190313100815
2023-01-22 18:42:04.397657: step: 1596/529, loss: 0.0002930145710706711
2023-01-22 18:42:05.475884: step: 1600/529, loss: 0.00012631977733690292
2023-01-22 18:42:06.537932: step: 1604/529, loss: 0.006007087882608175
2023-01-22 18:42:07.610263: step: 1608/529, loss: 1.868352592282463e-05
2023-01-22 18:42:08.691847: step: 1612/529, loss: 0.0016673553036525846
2023-01-22 18:42:09.761438: step: 1616/529, loss: 0.00011032953625544906
2023-01-22 18:42:10.852264: step: 1620/529, loss: 0.0040433513931930065
2023-01-22 18:42:11.933667: step: 1624/529, loss: 0.0008833800093270838
2023-01-22 18:42:13.006624: step: 1628/529, loss: 0.00011601475853240117
2023-01-22 18:42:14.076948: step: 1632/529, loss: 6.98849034961313e-05
2023-01-22 18:42:15.153817: step: 1636/529, loss: 0.003080921247601509
2023-01-22 18:42:16.223684: step: 1640/529, loss: 0.008081153966486454
2023-01-22 18:42:17.312947: step: 1644/529, loss: 0.004066224675625563
2023-01-22 18:42:18.404814: step: 1648/529, loss: 7.912777800811455e-05
2023-01-22 18:42:19.474877: step: 1652/529, loss: 6.255049811443314e-05
2023-01-22 18:42:20.545233: step: 1656/529, loss: 0.0005993222002871335
2023-01-22 18:42:21.612105: step: 1660/529, loss: 0.00011411066225264221
2023-01-22 18:42:22.699570: step: 1664/529, loss: 0.0017574802041053772
2023-01-22 18:42:23.763685: step: 1668/529, loss: 0.006759719457477331
2023-01-22 18:42:24.868059: step: 1672/529, loss: 0.0006977932062000036
2023-01-22 18:42:25.959141: step: 1676/529, loss: 0.0015799521934241056
2023-01-22 18:42:27.033286: step: 1680/529, loss: 0.0006595553131774068
2023-01-22 18:42:28.104651: step: 1684/529, loss: 0.0002391458983765915
2023-01-22 18:42:29.178444: step: 1688/529, loss: 0.0008294139988720417
2023-01-22 18:42:30.269961: step: 1692/529, loss: 0.002560486551374197
2023-01-22 18:42:31.350292: step: 1696/529, loss: 0.01014238502830267
2023-01-22 18:42:32.438909: step: 1700/529, loss: 0.0023997356183826923
2023-01-22 18:42:33.536578: step: 1704/529, loss: 0.0002925774606410414
2023-01-22 18:42:34.606600: step: 1708/529, loss: 2.1410052795545198e-05
2023-01-22 18:42:35.690202: step: 1712/529, loss: 0.0041291615925729275
2023-01-22 18:42:36.763916: step: 1716/529, loss: 0.0033650079276412725
2023-01-22 18:42:37.832942: step: 1720/529, loss: 0.00014977413229644299
2023-01-22 18:42:38.931467: step: 1724/529, loss: 0.0005717944004572928
2023-01-22 18:42:40.002188: step: 1728/529, loss: 0.0017060530371963978
2023-01-22 18:42:41.087857: step: 1732/529, loss: 0.00021760266099590808
2023-01-22 18:42:42.163015: step: 1736/529, loss: 0.01043646689504385
2023-01-22 18:42:43.256976: step: 1740/529, loss: 0.00029296407592482865
2023-01-22 18:42:44.329962: step: 1744/529, loss: 9.995861910283566e-05
2023-01-22 18:42:45.408156: step: 1748/529, loss: 0.004003719426691532
2023-01-22 18:42:46.475994: step: 1752/529, loss: 0.0003494007105473429
2023-01-22 18:42:47.554519: step: 1756/529, loss: 0.017226722091436386
2023-01-22 18:42:48.643965: step: 1760/529, loss: 0.015792647376656532
2023-01-22 18:42:49.718926: step: 1764/529, loss: 0.0004726860497612506
2023-01-22 18:42:50.799315: step: 1768/529, loss: 0.000832783873192966
2023-01-22 18:42:51.877024: step: 1772/529, loss: 4.9931190005736426e-05
2023-01-22 18:42:52.954423: step: 1776/529, loss: 0.003307485254481435
2023-01-22 18:42:54.016908: step: 1780/529, loss: 0.00029952405020594597
2023-01-22 18:42:55.098938: step: 1784/529, loss: 0.0008505576406605542
2023-01-22 18:42:56.163817: step: 1788/529, loss: 8.7362015619874e-05
2023-01-22 18:42:57.235621: step: 1792/529, loss: 0.00031362142181023955
2023-01-22 18:42:58.311435: step: 1796/529, loss: 0.0051210420206189156
2023-01-22 18:42:59.377823: step: 1800/529, loss: 0.001576750073581934
2023-01-22 18:43:00.454019: step: 1804/529, loss: 0.0009034052491188049
2023-01-22 18:43:01.556795: step: 1808/529, loss: 0.008525361306965351
2023-01-22 18:43:02.636777: step: 1812/529, loss: 6.831515406702238e-07
2023-01-22 18:43:03.714546: step: 1816/529, loss: 9.70430119195953e-05
2023-01-22 18:43:04.765438: step: 1820/529, loss: 0.0005761044449172914
2023-01-22 18:43:05.849507: step: 1824/529, loss: 0.003197520272806287
2023-01-22 18:43:06.941599: step: 1828/529, loss: 0.0046645235270261765
2023-01-22 18:43:08.026125: step: 1832/529, loss: 0.003829003544524312
2023-01-22 18:43:09.102481: step: 1836/529, loss: 0.004863250534981489
2023-01-22 18:43:10.188525: step: 1840/529, loss: 0.0019632449839264154
2023-01-22 18:43:11.266195: step: 1844/529, loss: 4.454702138900757e-05
2023-01-22 18:43:12.349885: step: 1848/529, loss: 0.0008929175091907382
2023-01-22 18:43:13.431204: step: 1852/529, loss: 0.0005542693543247879
2023-01-22 18:43:14.514110: step: 1856/529, loss: 0.0023257785942405462
2023-01-22 18:43:15.612434: step: 1860/529, loss: 7.65239165048115e-05
2023-01-22 18:43:16.676000: step: 1864/529, loss: 1.213531504618004e-05
2023-01-22 18:43:17.725417: step: 1868/529, loss: 0.0008265121723525226
2023-01-22 18:43:18.802358: step: 1872/529, loss: 0.001287953113205731
2023-01-22 18:43:19.883110: step: 1876/529, loss: 4.980025187251158e-05
2023-01-22 18:43:20.969967: step: 1880/529, loss: 0.0007879058830440044
2023-01-22 18:43:22.047652: step: 1884/529, loss: 6.111104448791593e-05
2023-01-22 18:43:23.118114: step: 1888/529, loss: 0.0005668092053383589
2023-01-22 18:43:24.195212: step: 1892/529, loss: 3.9842714613769203e-05
2023-01-22 18:43:25.282372: step: 1896/529, loss: 0.00296900887042284
2023-01-22 18:43:26.356477: step: 1900/529, loss: 0.004442651756107807
2023-01-22 18:43:27.429608: step: 1904/529, loss: 0.0005830864538438618
2023-01-22 18:43:28.508723: step: 1908/529, loss: 0.004742756485939026
2023-01-22 18:43:29.602324: step: 1912/529, loss: 0.0048843384720385075
2023-01-22 18:43:30.672592: step: 1916/529, loss: 2.110856939907535e-06
2023-01-22 18:43:31.751883: step: 1920/529, loss: 0.010243343189358711
2023-01-22 18:43:32.817607: step: 1924/529, loss: 0.003939337562769651
2023-01-22 18:43:33.883556: step: 1928/529, loss: 5.353868800739292e-06
2023-01-22 18:43:34.953795: step: 1932/529, loss: 4.694567178376019e-05
2023-01-22 18:43:36.013201: step: 1936/529, loss: 0.0004204769793432206
2023-01-22 18:43:37.103365: step: 1940/529, loss: 0.0019293130608275533
2023-01-22 18:43:38.181765: step: 1944/529, loss: 0.004171682987362146
2023-01-22 18:43:39.262801: step: 1948/529, loss: 0.00016569948638789356
2023-01-22 18:43:40.338298: step: 1952/529, loss: 0.002988734282553196
2023-01-22 18:43:41.418611: step: 1956/529, loss: 0.0009037981508299708
2023-01-22 18:43:42.489877: step: 1960/529, loss: 0.0018470805371180177
2023-01-22 18:43:43.603318: step: 1964/529, loss: 0.011918551288545132
2023-01-22 18:43:44.674889: step: 1968/529, loss: 0.0007112628081813455
2023-01-22 18:43:45.757458: step: 1972/529, loss: 0.0018391464836895466
2023-01-22 18:43:46.848072: step: 1976/529, loss: 0.011291444301605225
2023-01-22 18:43:47.938119: step: 1980/529, loss: 0.0011909948661923409
2023-01-22 18:43:49.012277: step: 1984/529, loss: 0.006228840909898281
2023-01-22 18:43:50.081602: step: 1988/529, loss: 0.026630794629454613
2023-01-22 18:43:51.151778: step: 1992/529, loss: 0.0002000487584155053
2023-01-22 18:43:52.224934: step: 1996/529, loss: 0.002114376286044717
2023-01-22 18:43:53.309320: step: 2000/529, loss: 0.004504579585045576
2023-01-22 18:43:54.381994: step: 2004/529, loss: 0.010221246629953384
2023-01-22 18:43:55.464514: step: 2008/529, loss: 0.0012430810602381825
2023-01-22 18:43:56.561481: step: 2012/529, loss: 0.0018100414890795946
2023-01-22 18:43:57.647332: step: 2016/529, loss: 0.002091814298182726
2023-01-22 18:43:58.730302: step: 2020/529, loss: 0.0011974122608080506
2023-01-22 18:43:59.791813: step: 2024/529, loss: 0.005928805563598871
2023-01-22 18:44:00.893474: step: 2028/529, loss: 0.005593332927674055
2023-01-22 18:44:01.965333: step: 2032/529, loss: 0.0004174827190581709
2023-01-22 18:44:03.041035: step: 2036/529, loss: 0.014579106122255325
2023-01-22 18:44:04.114307: step: 2040/529, loss: 0.004975006449967623
2023-01-22 18:44:05.197360: step: 2044/529, loss: 0.0005144670139998198
2023-01-22 18:44:06.294283: step: 2048/529, loss: 0.007221609819680452
2023-01-22 18:44:07.388909: step: 2052/529, loss: 0.0027210204862058163
2023-01-22 18:44:08.457405: step: 2056/529, loss: 0.0006094719283282757
2023-01-22 18:44:09.537040: step: 2060/529, loss: 0.0035577979870140553
2023-01-22 18:44:10.614507: step: 2064/529, loss: 0.0004641000123228878
2023-01-22 18:44:11.675145: step: 2068/529, loss: 9.884611063171178e-05
2023-01-22 18:44:12.742227: step: 2072/529, loss: 0.0006773408968001604
2023-01-22 18:44:13.849997: step: 2076/529, loss: 6.177403702167794e-05
2023-01-22 18:44:14.934821: step: 2080/529, loss: 0.003080954309552908
2023-01-22 18:44:16.007241: step: 2084/529, loss: 0.01797344535589218
2023-01-22 18:44:17.087320: step: 2088/529, loss: 0.0004905228852294385
2023-01-22 18:44:18.163202: step: 2092/529, loss: 0.000253918522503227
2023-01-22 18:44:19.252430: step: 2096/529, loss: 0.0067605916410684586
2023-01-22 18:44:20.323805: step: 2100/529, loss: 0.003052406944334507
2023-01-22 18:44:21.388431: step: 2104/529, loss: 0.005314346868544817
2023-01-22 18:44:22.481941: step: 2108/529, loss: 0.0005654231645166874
2023-01-22 18:44:23.564555: step: 2112/529, loss: 0.005869102198630571
2023-01-22 18:44:24.640993: step: 2116/529, loss: 0.007144043687731028
==================================================
Loss: 0.003
--------------------
Dev Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3191025641025641, 'r': 0.35422201138519926, 'f1': 0.33574640287769786}, 'combined': 0.24739208633093526, 'stategy': 1, 'epoch': 19}
Test Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.31101966319783486, 'r': 0.3090186175706429, 'f1': 0.31001591140328216}, 'combined': 0.20239380744462981, 'stategy': 1, 'epoch': 19}
Dev Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.318343369324474, 'r': 0.3636484029095509, 'f1': 0.3394910687924417}, 'combined': 0.2501513138470623, 'stategy': 1, 'epoch': 19}
Test Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3339844947289507, 'r': 0.31188257963659366, 'f1': 0.3225553675329029}, 'combined': 0.21058018813028895, 'stategy': 1, 'epoch': 19}
Dev Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3114870948379352, 'r': 0.35167897804283005, 'f1': 0.33036510058568885}, 'combined': 0.24342691622103388, 'stategy': 1, 'epoch': 19}
Test Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32375342527226486, 'r': 0.3219696598437675, 'f1': 0.3228590787936122}, 'combined': 0.21077846594816133, 'stategy': 1, 'epoch': 19}
Sample Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3038194444444444, 'r': 0.41666666666666663, 'f1': 0.3514056224899598}, 'combined': 0.23427041499330653, 'stategy': 1, 'epoch': 19}
Sample Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.3515625, 'r': 0.4891304347826087, 'f1': 0.4090909090909091}, 'combined': 0.20454545454545456, 'stategy': 1, 'epoch': 19}
Sample Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 19}
==================================================
Current best result:
--------------------
Dev for Chinese: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.32302065404475044, 'r': 0.3561195445920304, 'f1': 0.33876353790613717}, 'combined': 0.2496152384571537, 'stategy': 1, 'epoch': 3}
Test for Chinese: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3094557925156106, 'r': 0.3071803822765253, 'f1': 0.30831388922219516}, 'combined': 0.20128264270464555, 'stategy': 1, 'epoch': 3}
Chinese: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.3102836879432624, 'r': 0.41666666666666663, 'f1': 0.3556910569105691}, 'combined': 0.23712737127371275, 'stategy': 1, 'epoch': 3}
--------------------
Dev for Korean: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.3238172380156076, 'r': 0.36744346932321315, 'f1': 0.34425370370370373}, 'combined': 0.2536606237816764, 'stategy': 1, 'epoch': 16}
Test for Korean: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.3319312097086922, 'r': 0.3093550061071819, 'f1': 0.32024571517089817}, 'combined': 0.20907233218410967, 'stategy': 1, 'epoch': 16}
Korean: {'template': {'p': 0.5, 'r': 0.5, 'f1': 0.5}, 'slot': {'p': 0.375, 'r': 0.5217391304347826, 'f1': 0.43636363636363634}, 'combined': 0.21818181818181817, 'stategy': 1, 'epoch': 16}
--------------------
Dev for Russian: {'template': {'p': 1.0, 'r': 0.5833333333333334, 'f1': 0.7368421052631579}, 'slot': {'p': 0.31567708333333333, 'r': 0.3594046489563567, 'f1': 0.3361246672582076}, 'combined': 0.24767080745341613, 'stategy': 1, 'epoch': 18}
Test for Russian: {'template': {'p': 0.9692307692307692, 'r': 0.4921875, 'f1': 0.6528497409326425}, 'slot': {'p': 0.32511570330542855, 'r': 0.32242879666654073, 'f1': 0.3237666754908832}, 'combined': 0.21137099021684605, 'stategy': 1, 'epoch': 18}
Russian: {'template': {'p': 1.0, 'r': 0.5, 'f1': 0.6666666666666666}, 'slot': {'p': 0.5735294117647058, 'r': 0.33620689655172414, 'f1': 0.4239130434782608}, 'combined': 0.28260869565217384, 'stategy': 1, 'epoch': 18}